diff options
98 files changed, 6197 insertions, 841 deletions
diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst index d3fe4cac0c90..801a6ed3f2e5 100644 --- a/Documentation/bpf/index.rst +++ b/Documentation/bpf/index.rst @@ -42,6 +42,7 @@ Program types .. toctree:: :maxdepth: 1 + prog_cgroup_sockopt prog_cgroup_sysctl prog_flow_dissector diff --git a/Documentation/bpf/prog_cgroup_sockopt.rst b/Documentation/bpf/prog_cgroup_sockopt.rst new file mode 100644 index 000000000000..c47d974629ae --- /dev/null +++ b/Documentation/bpf/prog_cgroup_sockopt.rst @@ -0,0 +1,93 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============================ +BPF_PROG_TYPE_CGROUP_SOCKOPT +============================ + +``BPF_PROG_TYPE_CGROUP_SOCKOPT`` program type can be attached to two +cgroup hooks: + +* ``BPF_CGROUP_GETSOCKOPT`` - called every time process executes ``getsockopt`` + system call. +* ``BPF_CGROUP_SETSOCKOPT`` - called every time process executes ``setsockopt`` + system call. + +The context (``struct bpf_sockopt``) has associated socket (``sk``) and +all input arguments: ``level``, ``optname``, ``optval`` and ``optlen``. + +BPF_CGROUP_SETSOCKOPT +===================== + +``BPF_CGROUP_SETSOCKOPT`` is triggered *before* the kernel handling of +sockopt and it has writable context: it can modify the supplied arguments +before passing them down to the kernel. This hook has access to the cgroup +and socket local storage. + +If BPF program sets ``optlen`` to -1, the control will be returned +back to the userspace after all other BPF programs in the cgroup +chain finish (i.e. kernel ``setsockopt`` handling will *not* be executed). + +Note, that ``optlen`` can not be increased beyond the user-supplied +value. It can only be decreased or set to -1. Any other value will +trigger ``EFAULT``. + +Return Type +----------- + +* ``0`` - reject the syscall, ``EPERM`` will be returned to the userspace. +* ``1`` - success, continue with next BPF program in the cgroup chain. + +BPF_CGROUP_GETSOCKOPT +===================== + +``BPF_CGROUP_GETSOCKOPT`` is triggered *after* the kernel handing of +sockopt. The BPF hook can observe ``optval``, ``optlen`` and ``retval`` +if it's interested in whatever kernel has returned. BPF hook can override +the values above, adjust ``optlen`` and reset ``retval`` to 0. If ``optlen`` +has been increased above initial ``getsockopt`` value (i.e. userspace +buffer is too small), ``EFAULT`` is returned. + +This hook has access to the cgroup and socket local storage. + +Note, that the only acceptable value to set to ``retval`` is 0 and the +original value that the kernel returned. Any other value will trigger +``EFAULT``. + +Return Type +----------- + +* ``0`` - reject the syscall, ``EPERM`` will be returned to the userspace. +* ``1`` - success: copy ``optval`` and ``optlen`` to userspace, return + ``retval`` from the syscall (note that this can be overwritten by + the BPF program from the parent cgroup). + +Cgroup Inheritance +================== + +Suppose, there is the following cgroup hierarchy where each cgroup +has ``BPF_CGROUP_GETSOCKOPT`` attached at each level with +``BPF_F_ALLOW_MULTI`` flag:: + + A (root, parent) + \ + B (child) + +When the application calls ``getsockopt`` syscall from the cgroup B, +the programs are executed from the bottom up: B, A. First program +(B) sees the result of kernel's ``getsockopt``. It can optionally +adjust ``optval``, ``optlen`` and reset ``retval`` to 0. After that +control will be passed to the second (A) program which will see the +same context as B including any potential modifications. + +Same for ``BPF_CGROUP_SETSOCKOPT``: if the program is attached to +A and B, the trigger order is B, then A. If B does any changes +to the input arguments (``level``, ``optname``, ``optval``, ``optlen``), +then the next program in the chain (A) will see those changes, +*not* the original input ``setsockopt`` arguments. The potentially +modified values will be then passed down to the kernel. + +Example +======= + +See ``tools/testing/selftests/bpf/progs/sockopt_sk.c`` for an example +of BPF program that handles socket options. diff --git a/Documentation/networking/af_xdp.rst b/Documentation/networking/af_xdp.rst index 50bccbf68308..eeedc2e826aa 100644 --- a/Documentation/networking/af_xdp.rst +++ b/Documentation/networking/af_xdp.rst @@ -220,7 +220,21 @@ Usage In order to use AF_XDP sockets there are two parts needed. The user-space application and the XDP program. For a complete setup and usage example, please refer to the sample application. The user-space -side is xdpsock_user.c and the XDP side xdpsock_kern.c. +side is xdpsock_user.c and the XDP side is part of libbpf. + +The XDP code sample included in tools/lib/bpf/xsk.c is the following:: + + SEC("xdp_sock") int xdp_sock_prog(struct xdp_md *ctx) + { + int index = ctx->rx_queue_index; + + // A set entry here means that the correspnding queue_id + // has an active AF_XDP socket bound to it. + if (bpf_map_lookup_elem(&xsks_map, &index)) + return bpf_redirect_map(&xsks_map, index, 0); + + return XDP_PASS; + } Naive ring dequeue and enqueue could look like this:: diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 557c565c26fc..32bad014d76c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -641,8 +641,8 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget) struct i40e_tx_desc *tx_desc = NULL; struct i40e_tx_buffer *tx_bi; bool work_done = true; + struct xdp_desc desc; dma_addr_t dma; - u32 len; while (budget-- > 0) { if (!unlikely(I40E_DESC_UNUSED(xdp_ring))) { @@ -651,21 +651,23 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget) break; } - if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &dma, &len)) + if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc)) break; - dma_sync_single_for_device(xdp_ring->dev, dma, len, + dma = xdp_umem_get_dma(xdp_ring->xsk_umem, desc.addr); + + dma_sync_single_for_device(xdp_ring->dev, dma, desc.len, DMA_BIDIRECTIONAL); tx_bi = &xdp_ring->tx_bi[xdp_ring->next_to_use]; - tx_bi->bytecount = len; + tx_bi->bytecount = desc.len; tx_desc = I40E_TX_DESC(xdp_ring, xdp_ring->next_to_use); tx_desc->buffer_addr = cpu_to_le64(dma); tx_desc->cmd_type_offset_bsz = build_ctob(I40E_TX_DESC_CMD_ICRC | I40E_TX_DESC_CMD_EOP, - 0, len, 0); + 0, desc.len, 0); xdp_ring->next_to_use++; if (xdp_ring->next_to_use == xdp_ring->count) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index 6af55bb3bef3..6b609553329f 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -571,8 +571,9 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) union ixgbe_adv_tx_desc *tx_desc = NULL; struct ixgbe_tx_buffer *tx_bi; bool work_done = true; - u32 len, cmd_type; + struct xdp_desc desc; dma_addr_t dma; + u32 cmd_type; while (budget-- > 0) { if (unlikely(!ixgbe_desc_unused(xdp_ring)) || @@ -581,14 +582,16 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) break; } - if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &dma, &len)) + if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &desc)) break; - dma_sync_single_for_device(xdp_ring->dev, dma, len, + dma = xdp_umem_get_dma(xdp_ring->xsk_umem, desc.addr); + + dma_sync_single_for_device(xdp_ring->dev, dma, desc.len, DMA_BIDIRECTIONAL); tx_bi = &xdp_ring->tx_buffer_info[xdp_ring->next_to_use]; - tx_bi->bytecount = len; + tx_bi->bytecount = desc.len; tx_bi->xdpf = NULL; tx_bi->gso_segs = 1; @@ -599,10 +602,10 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) cmd_type = IXGBE_ADVTXD_DTYP_DATA | IXGBE_ADVTXD_DCMD_DEXT | IXGBE_ADVTXD_DCMD_IFCS; - cmd_type |= len | IXGBE_TXD_CMD; + cmd_type |= desc.len | IXGBE_TXD_CMD; tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); tx_desc->read.olinfo_status = - cpu_to_le32(len << IXGBE_ADVTXD_PAYLEN_SHIFT); + cpu_to_le32(desc.len << IXGBE_ADVTXD_PAYLEN_SHIFT); xdp_ring->next_to_use++; if (xdp_ring->next_to_use == xdp_ring->count) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 6aa0fe6de878..8456b19d79cd 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -24,7 +24,7 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \ en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \ en_selftest.o en/port.o en/monitor_stats.o en/reporter_tx.o \ - en/params.o + en/params.o en/xsk/umem.o en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o # # Netdev extra diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 3281ace5e126..f0d77eb66acf 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -137,6 +137,7 @@ struct page_pool; #define MLX5E_MAX_NUM_CHANNELS (MLX5E_INDIR_RQT_SIZE >> 1) #define MLX5E_MAX_NUM_SQS (MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC) #define MLX5E_TX_CQ_POLL_BUDGET 128 +#define MLX5E_TX_XSK_POLL_BUDGET 64 #define MLX5E_SQ_RECOVER_MIN_INTERVAL 500 /* msecs */ #define MLX5E_UMR_WQE_INLINE_SZ \ @@ -155,6 +156,11 @@ do { \ ##__VA_ARGS__); \ } while (0) +enum mlx5e_rq_group { + MLX5E_RQ_GROUP_REGULAR, + MLX5E_RQ_GROUP_XSK, + MLX5E_NUM_RQ_GROUPS /* Keep last. */ +}; static inline u16 mlx5_min_rx_wqes(int wq_type, u32 wq_size) { @@ -179,7 +185,8 @@ static inline int mlx5e_get_max_num_channels(struct mlx5_core_dev *mdev) /* Use this function to get max num channels after netdev was created */ static inline int mlx5e_get_netdev_max_channels(struct net_device *netdev) { - return min_t(unsigned int, netdev->num_rx_queues, + return min_t(unsigned int, + netdev->num_rx_queues / MLX5E_NUM_RQ_GROUPS, netdev->num_tx_queues); } @@ -250,6 +257,7 @@ struct mlx5e_params { u32 lro_timeout; u32 pflags; struct bpf_prog *xdp_prog; + struct mlx5e_xsk *xsk; unsigned int sw_mtu; int hard_mtu; }; @@ -348,6 +356,13 @@ enum { struct mlx5e_sq_wqe_info { u8 opcode; + + /* Auxiliary data for different opcodes. */ + union { + struct { + struct mlx5e_rq *rq; + } umr; + }; }; struct mlx5e_txqsq { @@ -392,14 +407,55 @@ struct mlx5e_txqsq { } ____cacheline_aligned_in_smp; struct mlx5e_dma_info { - struct page *page; - dma_addr_t addr; + dma_addr_t addr; + union { + struct page *page; + struct { + u64 handle; + void *data; + } xsk; + }; +}; + +/* XDP packets can be transmitted in different ways. On completion, we need to + * distinguish between them to clean up things in a proper way. + */ +enum mlx5e_xdp_xmit_mode { + /* An xdp_frame was transmitted due to either XDP_REDIRECT from another + * device or XDP_TX from an XSK RQ. The frame has to be unmapped and + * returned. + */ + MLX5E_XDP_XMIT_MODE_FRAME, + + /* The xdp_frame was created in place as a result of XDP_TX from a + * regular RQ. No DMA remapping happened, and the page belongs to us. + */ + MLX5E_XDP_XMIT_MODE_PAGE, + + /* No xdp_frame was created at all, the transmit happened from a UMEM + * page. The UMEM Completion Ring producer pointer has to be increased. + */ + MLX5E_XDP_XMIT_MODE_XSK, }; struct mlx5e_xdp_info { - struct xdp_frame *xdpf; - dma_addr_t dma_addr; - struct mlx5e_dma_info di; + enum mlx5e_xdp_xmit_mode mode; + union { + struct { + struct xdp_frame *xdpf; + dma_addr_t dma_addr; + } frame; + struct { + struct mlx5e_rq *rq; + struct mlx5e_dma_info di; + } page; + }; +}; + +struct mlx5e_xdp_xmit_data { + dma_addr_t dma_addr; + void *data; + u32 len; }; struct mlx5e_xdp_info_fifo { @@ -425,8 +481,12 @@ struct mlx5e_xdp_mpwqe { }; struct mlx5e_xdpsq; -typedef bool (*mlx5e_fp_xmit_xdp_frame)(struct mlx5e_xdpsq*, - struct mlx5e_xdp_info*); +typedef int (*mlx5e_fp_xmit_xdp_frame_check)(struct mlx5e_xdpsq *); +typedef bool (*mlx5e_fp_xmit_xdp_frame)(struct mlx5e_xdpsq *, + struct mlx5e_xdp_xmit_data *, + struct mlx5e_xdp_info *, + int); + struct mlx5e_xdpsq { /* data path */ @@ -443,8 +503,10 @@ struct mlx5e_xdpsq { struct mlx5e_cq cq; /* read only */ + struct xdp_umem *umem; struct mlx5_wq_cyc wq; struct mlx5e_xdpsq_stats *stats; + mlx5e_fp_xmit_xdp_frame_check xmit_xdp_frame_check; mlx5e_fp_xmit_xdp_frame xmit_xdp_frame; struct { struct mlx5e_xdp_wqe_info *wqe_info; @@ -571,9 +633,11 @@ struct mlx5e_rq { u8 log_stride_sz; u8 umr_in_progress; u8 umr_last_bulk; + u8 umr_completed; } mpwqe; }; struct { + u16 umem_headroom; u16 headroom; u8 map_dir; /* dma map direction */ } buff; @@ -600,10 +664,14 @@ struct mlx5e_rq { /* XDP */ struct bpf_prog *xdp_prog; - struct mlx5e_xdpsq xdpsq; + struct mlx5e_xdpsq *xdpsq; DECLARE_BITMAP(flags, 8); struct page_pool *page_pool; + /* AF_XDP zero-copy */ + struct zero_copy_allocator zca; + struct xdp_umem *umem; + /* control */ struct mlx5_wq_ctrl wq_ctrl; __be32 mkey_be; @@ -616,9 +684,15 @@ struct mlx5e_rq { struct xdp_rxq_info xdp_rxq; } ____cacheline_aligned_in_smp; +enum mlx5e_channel_state { + MLX5E_CHANNEL_STATE_XSK, + MLX5E_CHANNEL_NUM_STATES +}; + struct mlx5e_channel { /* data path */ struct mlx5e_rq rq; + struct mlx5e_xdpsq rq_xdpsq; struct mlx5e_txqsq sq[MLX5E_MAX_NUM_TC]; struct mlx5e_icosq icosq; /* internal control operations */ bool xdp; @@ -631,6 +705,13 @@ struct mlx5e_channel { /* XDP_REDIRECT */ struct mlx5e_xdpsq xdpsq; + /* AF_XDP zero-copy */ + struct mlx5e_rq xskrq; + struct mlx5e_xdpsq xsksq; + struct mlx5e_icosq xskicosq; + /* xskicosq can be accessed from any CPU - the spinlock protects it. */ + spinlock_t xskicosq_lock; + /* data path - accessed per napi poll */ struct irq_desc *irq_desc; struct mlx5e_ch_stats *stats; @@ -639,6 +720,7 @@ struct mlx5e_channel { struct mlx5e_priv *priv; struct mlx5_core_dev *mdev; struct hwtstamp_config *tstamp; + DECLARE_BITMAP(state, MLX5E_CHANNEL_NUM_STATES); int ix; int cpu; cpumask_var_t xps_cpumask; @@ -654,14 +736,17 @@ struct mlx5e_channel_stats { struct mlx5e_ch_stats ch; struct mlx5e_sq_stats sq[MLX5E_MAX_NUM_TC]; struct mlx5e_rq_stats rq; + struct mlx5e_rq_stats xskrq; struct mlx5e_xdpsq_stats rq_xdpsq; struct mlx5e_xdpsq_stats xdpsq; + struct mlx5e_xdpsq_stats xsksq; } ____cacheline_aligned_in_smp; enum { MLX5E_STATE_OPENED, MLX5E_STATE_DESTROYING, MLX5E_STATE_XDP_TX_ENABLED, + MLX5E_STATE_XDP_OPEN, }; struct mlx5e_rqt { @@ -694,6 +779,17 @@ struct mlx5e_modify_sq_param { int rl_index; }; +struct mlx5e_xsk { + /* UMEMs are stored separately from channels, because we don't want to + * lose them when channels are recreated. The kernel also stores UMEMs, + * but it doesn't distinguish between zero-copy and non-zero-copy UMEMs, + * so rely on our mechanism. + */ + struct xdp_umem **umems; + u16 refcnt; + bool ever_used; +}; + struct mlx5e_priv { /* priv data path fields - start */ struct mlx5e_txqsq *txq2sq[MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC]; @@ -714,6 +810,7 @@ struct mlx5e_priv { struct mlx5e_tir indir_tir[MLX5E_NUM_INDIR_TIRS]; struct mlx5e_tir inner_indir_tir[MLX5E_NUM_INDIR_TIRS]; struct mlx5e_tir direct_tir[MLX5E_MAX_NUM_CHANNELS]; + struct mlx5e_tir xsk_tir[MLX5E_MAX_NUM_CHANNELS]; struct mlx5e_rss_params rss_params; u32 tx_rates[MLX5E_MAX_NUM_SQS]; @@ -750,6 +847,7 @@ struct mlx5e_priv { struct mlx5e_tls *tls; #endif struct devlink_health_reporter *tx_reporter; + struct mlx5e_xsk xsk; }; struct mlx5e_profile { @@ -794,11 +892,13 @@ bool mlx5e_striding_rq_possible(struct mlx5_core_dev *mdev, struct mlx5e_params *params); void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info); -void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info, - bool recycle); +void mlx5e_page_release_dynamic(struct mlx5e_rq *rq, + struct mlx5e_dma_info *dma_info, + bool recycle); void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe); bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq); +void mlx5e_poll_ico_cq(struct mlx5e_cq *cq); bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq); void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix); void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix); @@ -854,6 +954,30 @@ void mlx5e_build_indir_tir_ctx_hash(struct mlx5e_rss_params *rss_params, void mlx5e_modify_tirs_hash(struct mlx5e_priv *priv, void *in, int inlen); struct mlx5e_tirc_config mlx5e_tirc_get_default_config(enum mlx5e_traffic_types tt); +struct mlx5e_xsk_param; + +struct mlx5e_rq_param; +int mlx5e_open_rq(struct mlx5e_channel *c, struct mlx5e_params *params, + struct mlx5e_rq_param *param, struct mlx5e_xsk_param *xsk, + struct xdp_umem *umem, struct mlx5e_rq *rq); +int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time); +void mlx5e_deactivate_rq(struct mlx5e_rq *rq); +void mlx5e_close_rq(struct mlx5e_rq *rq); + +struct mlx5e_sq_param; +int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params, + struct mlx5e_sq_param *param, struct mlx5e_icosq *sq); +void mlx5e_close_icosq(struct mlx5e_icosq *sq); +int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params, + struct mlx5e_sq_param *param, struct xdp_umem *umem, + struct mlx5e_xdpsq *sq, bool is_redirect); +void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq); + +struct mlx5e_cq_param; +int mlx5e_open_cq(struct mlx5e_channel *c, struct dim_cq_moder moder, + struct mlx5e_cq_param *param, struct mlx5e_cq *cq); +void mlx5e_close_cq(struct mlx5e_cq *cq); + int mlx5e_open_locked(struct net_device *netdev); int mlx5e_close_locked(struct net_device *netdev); @@ -1024,10 +1148,10 @@ int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv); int mlx5e_create_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc); void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc); -int mlx5e_create_direct_rqts(struct mlx5e_priv *priv); -void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv); -int mlx5e_create_direct_tirs(struct mlx5e_priv *priv); -void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv); +int mlx5e_create_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs); +void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs); +int mlx5e_create_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs); +void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs); void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt); int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc, @@ -1097,6 +1221,7 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv); void mlx5e_destroy_netdev(struct mlx5e_priv *priv); void mlx5e_set_netdev_mtu_boundaries(struct mlx5e_priv *priv); void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, + struct mlx5e_xsk *xsk, struct mlx5e_rss_params *rss_params, struct mlx5e_params *params, u16 max_channels, u16 mtu); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index d3744bffbae3..79301d116667 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -3,65 +3,102 @@ #include "en/params.h" -u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params) +static inline bool mlx5e_rx_is_xdp(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) { - u16 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); - u16 linear_rq_headroom = params->xdp_prog ? - XDP_PACKET_HEADROOM : MLX5_RX_HEADROOM; - u32 frag_sz; + return params->xdp_prog || xsk; +} + +u16 mlx5e_get_linear_rq_headroom(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) +{ + u16 headroom = NET_IP_ALIGN; + + if (mlx5e_rx_is_xdp(params, xsk)) { + headroom += XDP_PACKET_HEADROOM; + if (xsk) + headroom += xsk->headroom; + } else { + headroom += MLX5_RX_HEADROOM; + } + + return headroom; +} + +u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) +{ + u32 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); + u16 linear_rq_headroom = mlx5e_get_linear_rq_headroom(params, xsk); + u32 frag_sz = linear_rq_headroom + hw_mtu; - linear_rq_headroom += NET_IP_ALIGN; + /* AF_XDP doesn't build SKBs in place. */ + if (!xsk) + frag_sz = MLX5_SKB_FRAG_SZ(frag_sz); - frag_sz = MLX5_SKB_FRAG_SZ(linear_rq_headroom + hw_mtu); + /* XDP in mlx5e doesn't support multiple packets per page. */ + if (mlx5e_rx_is_xdp(params, xsk)) + frag_sz = max_t(u32, frag_sz, PAGE_SIZE); - if (params->xdp_prog && frag_sz < PAGE_SIZE) - frag_sz = PAGE_SIZE; + /* Even if we can go with a smaller fragment size, we must not put + * multiple packets into a single frame. + */ + if (xsk) + frag_sz = max_t(u32, frag_sz, xsk->chunk_size); return frag_sz; } -u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params) +u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) { - u32 linear_frag_sz = mlx5e_rx_get_linear_frag_sz(params); + u32 linear_frag_sz = mlx5e_rx_get_linear_frag_sz(params, xsk); return MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(linear_frag_sz); } -bool mlx5e_rx_is_linear_skb(struct mlx5e_params *params) +bool mlx5e_rx_is_linear_skb(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) { - u32 frag_sz = mlx5e_rx_get_linear_frag_sz(params); + /* AF_XDP allocates SKBs on XDP_PASS - ensure they don't occupy more + * than one page. For this, check both with and without xsk. + */ + u32 linear_frag_sz = max(mlx5e_rx_get_linear_frag_sz(params, xsk), + mlx5e_rx_get_linear_frag_sz(params, NULL)); - return !params->lro_en && frag_sz <= PAGE_SIZE; + return !params->lro_en && linear_frag_sz <= PAGE_SIZE; } #define MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ ((BIT(__mlx5_bit_sz(wq, log_wqe_stride_size)) - 1) + \ MLX5_MPWQE_LOG_STRIDE_SZ_BASE) bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev, - struct mlx5e_params *params) + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) { - u32 frag_sz = mlx5e_rx_get_linear_frag_sz(params); + u32 linear_frag_sz = mlx5e_rx_get_linear_frag_sz(params, xsk); s8 signed_log_num_strides_param; u8 log_num_strides; - if (!mlx5e_rx_is_linear_skb(params)) + if (!mlx5e_rx_is_linear_skb(params, xsk)) return false; - if (order_base_2(frag_sz) > MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ) + if (order_base_2(linear_frag_sz) > MLX5_MAX_MPWQE_LOG_WQE_STRIDE_SZ) return false; if (MLX5_CAP_GEN(mdev, ext_stride_num_range)) return true; - log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(frag_sz); + log_num_strides = MLX5_MPWRQ_LOG_WQE_SZ - order_base_2(linear_frag_sz); signed_log_num_strides_param = (s8)log_num_strides - MLX5_MPWQE_LOG_NUM_STRIDES_BASE; return signed_log_num_strides_param >= 0; } -u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params) +u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) { - u8 log_pkts_per_wqe = mlx5e_mpwqe_log_pkts_per_wqe(params); + u8 log_pkts_per_wqe = mlx5e_mpwqe_log_pkts_per_wqe(params, xsk); /* Numbers are unsigned, don't subtract to avoid underflow. */ if (params->log_rq_mtu_frames < @@ -72,33 +109,30 @@ u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params) } u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev, - struct mlx5e_params *params) + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) { - if (mlx5e_rx_mpwqe_is_linear_skb(mdev, params)) - return order_base_2(mlx5e_rx_get_linear_frag_sz(params)); + if (mlx5e_rx_mpwqe_is_linear_skb(mdev, params, xsk)) + return order_base_2(mlx5e_rx_get_linear_frag_sz(params, xsk)); return MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev); } u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev, - struct mlx5e_params *params) + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) { return MLX5_MPWRQ_LOG_WQE_SZ - - mlx5e_mpwqe_get_log_stride_size(mdev, params); + mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk); } u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev, - struct mlx5e_params *params) + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) { - u16 linear_rq_headroom = params->xdp_prog ? - XDP_PACKET_HEADROOM : MLX5_RX_HEADROOM; - bool is_linear_skb; - - linear_rq_headroom += NET_IP_ALIGN; - - is_linear_skb = (params->rq_wq_type == MLX5_WQ_TYPE_CYCLIC) ? - mlx5e_rx_is_linear_skb(params) : - mlx5e_rx_mpwqe_is_linear_skb(mdev, params); + bool is_linear_skb = (params->rq_wq_type == MLX5_WQ_TYPE_CYCLIC) ? + mlx5e_rx_is_linear_skb(params, xsk) : + mlx5e_rx_mpwqe_is_linear_skb(mdev, params, xsk); - return is_linear_skb ? linear_rq_headroom : 0; + return is_linear_skb ? mlx5e_get_linear_rq_headroom(params, xsk) : 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h index b106a0236f36..bd882b5ee9a7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h @@ -6,17 +6,119 @@ #include "en.h" -u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params); -u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params); -bool mlx5e_rx_is_linear_skb(struct mlx5e_params *params); +struct mlx5e_xsk_param { + u16 headroom; + u16 chunk_size; +}; + +struct mlx5e_rq_param { + u32 rqc[MLX5_ST_SZ_DW(rqc)]; + struct mlx5_wq_param wq; + struct mlx5e_rq_frags_info frags_info; +}; + +struct mlx5e_sq_param { + u32 sqc[MLX5_ST_SZ_DW(sqc)]; + struct mlx5_wq_param wq; + bool is_mpw; +}; + +struct mlx5e_cq_param { + u32 cqc[MLX5_ST_SZ_DW(cqc)]; + struct mlx5_wq_param wq; + u16 eq_ix; + u8 cq_period_mode; +}; + +struct mlx5e_channel_param { + struct mlx5e_rq_param rq; + struct mlx5e_sq_param sq; + struct mlx5e_sq_param xdp_sq; + struct mlx5e_sq_param icosq; + struct mlx5e_cq_param rx_cq; + struct mlx5e_cq_param tx_cq; + struct mlx5e_cq_param icosq_cq; +}; + +static inline bool mlx5e_qid_get_ch_if_in_group(struct mlx5e_params *params, + u16 qid, + enum mlx5e_rq_group group, + u16 *ix) +{ + int nch = params->num_channels; + int ch = qid - nch * group; + + if (ch < 0 || ch >= nch) + return false; + + *ix = ch; + return true; +} + +static inline void mlx5e_qid_get_ch_and_group(struct mlx5e_params *params, + u16 qid, + u16 *ix, + enum mlx5e_rq_group *group) +{ + u16 nch = params->num_channels; + + *ix = qid % nch; + *group = qid / nch; +} + +static inline bool mlx5e_qid_validate(struct mlx5e_params *params, u64 qid) +{ + return qid < params->num_channels * MLX5E_NUM_RQ_GROUPS; +} + +/* Parameter calculations */ + +u16 mlx5e_get_linear_rq_headroom(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk); +u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk); +u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk); +bool mlx5e_rx_is_linear_skb(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk); bool mlx5e_rx_mpwqe_is_linear_skb(struct mlx5_core_dev *mdev, - struct mlx5e_params *params); -u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params); + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk); +u8 mlx5e_mpwqe_get_log_rq_size(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk); u8 mlx5e_mpwqe_get_log_stride_size(struct mlx5_core_dev *mdev, - struct mlx5e_params *params); + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk); u8 mlx5e_mpwqe_get_log_num_strides(struct mlx5_core_dev *mdev, - struct mlx5e_params *params); + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk); u16 mlx5e_get_rq_headroom(struct mlx5_core_dev *mdev, - struct mlx5e_params *params); + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk); + +/* Build queue parameters */ + +void mlx5e_build_rq_param(struct mlx5e_priv *priv, + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk, + struct mlx5e_rq_param *param); +void mlx5e_build_sq_param_common(struct mlx5e_priv *priv, + struct mlx5e_sq_param *param); +void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv, + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk, + struct mlx5e_cq_param *param); +void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv, + struct mlx5e_params *params, + struct mlx5e_cq_param *param); +void mlx5e_build_ico_cq_param(struct mlx5e_priv *priv, + u8 log_wq_size, + struct mlx5e_cq_param *param); +void mlx5e_build_icosq_param(struct mlx5e_priv *priv, + u8 log_wq_size, + struct mlx5e_sq_param *param); +void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv, + struct mlx5e_params *params, + struct mlx5e_sq_param *param); #endif /* __MLX5_EN_PARAMS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index eb8ef78e5626..b0b982cf69bb 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -31,11 +31,13 @@ */ #include <linux/bpf_trace.h> +#include <net/xdp_sock.h> #include "en/xdp.h" +#include "en/params.h" -int mlx5e_xdp_max_mtu(struct mlx5e_params *params) +int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk) { - int hr = NET_IP_ALIGN + XDP_PACKET_HEADROOM; + int hr = mlx5e_get_linear_rq_headroom(params, xsk); /* Let S := SKB_DATA_ALIGN(sizeof(struct skb_shared_info)). * The condition checked in mlx5e_rx_is_linear_skb is: @@ -54,25 +56,70 @@ int mlx5e_xdp_max_mtu(struct mlx5e_params *params) } static inline bool -mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_dma_info *di, - struct xdp_buff *xdp) +mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq, + struct mlx5e_dma_info *di, struct xdp_buff *xdp) { + struct mlx5e_xdp_xmit_data xdptxd; struct mlx5e_xdp_info xdpi; + struct xdp_frame *xdpf; + dma_addr_t dma_addr; - xdpi.xdpf = convert_to_xdp_frame(xdp); - if (unlikely(!xdpi.xdpf)) + xdpf = convert_to_xdp_frame(xdp); + if (unlikely(!xdpf)) return false; - xdpi.dma_addr = di->addr + (xdpi.xdpf->data - (void *)xdpi.xdpf); - dma_sync_single_for_device(sq->pdev, xdpi.dma_addr, - xdpi.xdpf->len, PCI_DMA_TODEVICE); - xdpi.di = *di; - return sq->xmit_xdp_frame(sq, &xdpi); + xdptxd.data = xdpf->data; + xdptxd.len = xdpf->len; + + if (xdp->rxq->mem.type == MEM_TYPE_ZERO_COPY) { + /* The xdp_buff was in the UMEM and was copied into a newly + * allocated page. The UMEM page was returned via the ZCA, and + * this new page has to be mapped at this point and has to be + * unmapped and returned via xdp_return_frame on completion. + */ + + /* Prevent double recycling of the UMEM page. Even in case this + * function returns false, the xdp_buff shouldn't be recycled, + * as it was already done in xdp_convert_zc_to_xdp_frame. + */ + __set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); /* non-atomic */ + + xdpi.mode = MLX5E_XDP_XMIT_MODE_FRAME; + + dma_addr = dma_map_single(sq->pdev, xdptxd.data, xdptxd.len, + DMA_TO_DEVICE); + if (dma_mapping_error(sq->pdev, dma_addr)) { + xdp_return_frame(xdpf); + return false; + } + + xdptxd.dma_addr = dma_addr; + xdpi.frame.xdpf = xdpf; + xdpi.frame.dma_addr = dma_addr; + } else { + /* Driver assumes that convert_to_xdp_frame returns an xdp_frame + * that points to the same memory region as the original + * xdp_buff. It allows to map the memory only once and to use + * the DMA_BIDIRECTIONAL mode. + */ + + xdpi.mode = MLX5E_XDP_XMIT_MODE_PAGE; + + dma_addr = di->addr + (xdpf->data - (void *)xdpf); + dma_sync_single_for_device(sq->pdev, dma_addr, xdptxd.len, + DMA_TO_DEVICE); + + xdptxd.dma_addr = dma_addr; + xdpi.page.rq = rq; + xdpi.page.di = *di; + } + + return sq->xmit_xdp_frame(sq, &xdptxd, &xdpi, 0); } /* returns true if packet was consumed by xdp */ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, - void *va, u16 *rx_headroom, u32 *len) + void *va, u16 *rx_headroom, u32 *len, bool xsk) { struct bpf_prog *prog = READ_ONCE(rq->xdp_prog); struct xdp_buff xdp; @@ -86,16 +133,20 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + *len; xdp.data_hard_start = va; + if (xsk) + xdp.handle = di->xsk.handle; xdp.rxq = &rq->xdp_rxq; act = bpf_prog_run_xdp(prog, &xdp); + if (xsk) + xdp.handle += xdp.data - xdp.data_hard_start; switch (act) { case XDP_PASS: *rx_headroom = xdp.data - xdp.data_hard_start; *len = xdp.data_end - xdp.data; return false; case XDP_TX: - if (unlikely(!mlx5e_xmit_xdp_buff(&rq->xdpsq, di, &xdp))) + if (unlikely(!mlx5e_xmit_xdp_buff(rq->xdpsq, rq, di, &xdp))) goto xdp_abort; __set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); /* non-atomic */ return true; @@ -106,7 +157,8 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, goto xdp_abort; __set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); __set_bit(MLX5E_RQ_FLAG_XDP_REDIRECT, rq->flags); - mlx5e_page_dma_unmap(rq, di); + if (!xsk) + mlx5e_page_dma_unmap(rq, di); rq->stats->xdp_redirect++; return true; default: @@ -160,7 +212,7 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq) stats->mpwqe++; } -static void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq) +void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq) { struct mlx5_wq_cyc *wq = &sq->wq; struct mlx5e_xdp_mpwqe *session = &sq->mpwqe; @@ -183,32 +235,55 @@ static void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq) session->wqe = NULL; /* Close session */ } +enum { + MLX5E_XDP_CHECK_OK = 1, + MLX5E_XDP_CHECK_START_MPWQE = 2, +}; + +static int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq) +{ + if (unlikely(!sq->mpwqe.wqe)) { + if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, + MLX5_SEND_WQE_MAX_WQEBBS))) { + /* SQ is full, ring doorbell */ + mlx5e_xmit_xdp_doorbell(sq); + sq->stats->full++; + return -EBUSY; + } + + return MLX5E_XDP_CHECK_START_MPWQE; + } + + return MLX5E_XDP_CHECK_OK; +} + static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, - struct mlx5e_xdp_info *xdpi) + struct mlx5e_xdp_xmit_data *xdptxd, + struct mlx5e_xdp_info *xdpi, + int check_result) { struct mlx5e_xdp_mpwqe *session = &sq->mpwqe; struct mlx5e_xdpsq_stats *stats = sq->stats; - struct xdp_frame *xdpf = xdpi->xdpf; - - if (unlikely(sq->hw_mtu < xdpf->len)) { + if (unlikely(xdptxd->len > sq->hw_mtu)) { stats->err++; return false; } - if (unlikely(!session->wqe)) { - if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, - MLX5_SEND_WQE_MAX_WQEBBS))) { - /* SQ is full, ring doorbell */ - mlx5e_xmit_xdp_doorbell(sq); - stats->full++; - return false; - } + if (!check_result) + check_result = mlx5e_xmit_xdp_frame_check_mpwqe(sq); + if (unlikely(check_result < 0)) + return false; + if (check_result == MLX5E_XDP_CHECK_START_MPWQE) { + /* Start the session when nothing can fail, so it's guaranteed + * that if there is an active session, it has at least one dseg, + * and it's safe to complete it at any time. + */ mlx5e_xdp_mpwqe_session_start(sq); } - mlx5e_xdp_mpwqe_add_dseg(sq, xdpi, stats); + mlx5e_xdp_mpwqe_add_dseg(sq, xdptxd, stats); if (unlikely(session->complete || session->ds_count == session->max_ds_count)) @@ -219,7 +294,22 @@ static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, return true; } -static bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi) +static int mlx5e_xmit_xdp_frame_check(struct mlx5e_xdpsq *sq) +{ + if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, 1))) { + /* SQ is full, ring doorbell */ + mlx5e_xmit_xdp_doorbell(sq); + sq->stats->full++; + return -EBUSY; + } + + return MLX5E_XDP_CHECK_OK; +} + +static bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, + struct mlx5e_xdp_xmit_data *xdptxd, + struct mlx5e_xdp_info *xdpi, + int check_result) { struct mlx5_wq_cyc *wq = &sq->wq; u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); @@ -229,9 +319,8 @@ static bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info * struct mlx5_wqe_eth_seg *eseg = &wqe->eth; struct mlx5_wqe_data_seg *dseg = wqe->data; - struct xdp_frame *xdpf = xdpi->xdpf; - dma_addr_t dma_addr = xdpi->dma_addr; - unsigned int dma_len = xdpf->len; + dma_addr_t dma_addr = xdptxd->dma_addr; + u32 dma_len = xdptxd->len; struct mlx5e_xdpsq_stats *stats = sq->stats; @@ -242,18 +331,16 @@ static bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info * return false; } - if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1))) { - /* SQ is full, ring doorbell */ - mlx5e_xmit_xdp_doorbell(sq); - stats->full++; + if (!check_result) + check_result = mlx5e_xmit_xdp_frame_check(sq); + if (unlikely(check_result < 0)) return false; - } cseg->fm_ce_se = 0; /* copy the inline part if required */ if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) { - memcpy(eseg->inline_hdr.start, xdpf->data, MLX5E_XDP_MIN_INLINE); + memcpy(eseg->inline_hdr.start, xdptxd->data, MLX5E_XDP_MIN_INLINE); eseg->inline_hdr.sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE); dma_len -= MLX5E_XDP_MIN_INLINE; dma_addr += MLX5E_XDP_MIN_INLINE; @@ -277,7 +364,7 @@ static bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info * static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_wqe_info *wi, - struct mlx5e_rq *rq, + u32 *xsk_frames, bool recycle) { struct mlx5e_xdp_info_fifo *xdpi_fifo = &sq->db.xdpi_fifo; @@ -286,22 +373,32 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq, for (i = 0; i < wi->num_pkts; i++) { struct mlx5e_xdp_info xdpi = mlx5e_xdpi_fifo_pop(xdpi_fifo); - if (rq) { - /* XDP_TX */ - mlx5e_page_release(rq, &xdpi.di, recycle); - } else { - /* XDP_REDIRECT */ - dma_unmap_single(sq->pdev, xdpi.dma_addr, - xdpi.xdpf->len, DMA_TO_DEVICE); - xdp_return_frame(xdpi.xdpf); + switch (xdpi.mode) { + case MLX5E_XDP_XMIT_MODE_FRAME: + /* XDP_TX from the XSK RQ and XDP_REDIRECT */ + dma_unmap_single(sq->pdev, xdpi.frame.dma_addr, + xdpi.frame.xdpf->len, DMA_TO_DEVICE); + xdp_return_frame(xdpi.frame.xdpf); + break; + case MLX5E_XDP_XMIT_MODE_PAGE: + /* XDP_TX from the regular RQ */ + mlx5e_page_release_dynamic(xdpi.page.rq, &xdpi.page.di, recycle); + break; + case MLX5E_XDP_XMIT_MODE_XSK: + /* AF_XDP send */ + (*xsk_frames)++; + break; + default: + WARN_ON_ONCE(true); } } } -bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq) +bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq) { struct mlx5e_xdpsq *sq; struct mlx5_cqe64 *cqe; + u32 xsk_frames = 0; u16 sqcc; int i; @@ -343,10 +440,13 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq) sqcc += wi->num_wqebbs; - mlx5e_free_xdpsq_desc(sq, wi, rq, true); + mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, true); } while (!last_wqe); } while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq))); + if (xsk_frames) + xsk_umem_complete_tx(sq->umem, xsk_frames); + sq->stats->cqes += i; mlx5_cqwq_update_db_record(&cq->wq); @@ -358,8 +458,10 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq) return (i == MLX5E_TX_CQ_POLL_BUDGET); } -void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq) +void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq) { + u32 xsk_frames = 0; + while (sq->cc != sq->pc) { struct mlx5e_xdp_wqe_info *wi; u16 ci; @@ -369,8 +471,11 @@ void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq) sq->cc += wi->num_wqebbs; - mlx5e_free_xdpsq_desc(sq, wi, rq, false); + mlx5e_free_xdpsq_desc(sq, wi, &xsk_frames, false); } + + if (xsk_frames) + xsk_umem_complete_tx(sq->umem, xsk_frames); } int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, @@ -398,21 +503,27 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, for (i = 0; i < n; i++) { struct xdp_frame *xdpf = frames[i]; + struct mlx5e_xdp_xmit_data xdptxd; struct mlx5e_xdp_info xdpi; - xdpi.dma_addr = dma_map_single(sq->pdev, xdpf->data, xdpf->len, - DMA_TO_DEVICE); - if (unlikely(dma_mapping_error(sq->pdev, xdpi.dma_addr))) { + xdptxd.data = xdpf->data; + xdptxd.len = xdpf->len; + xdptxd.dma_addr = dma_map_single(sq->pdev, xdptxd.data, + xdptxd.len, DMA_TO_DEVICE); + + if (unlikely(dma_mapping_error(sq->pdev, xdptxd.dma_addr))) { xdp_return_frame_rx_napi(xdpf); drops++; continue; } - xdpi.xdpf = xdpf; + xdpi.mode = MLX5E_XDP_XMIT_MODE_FRAME; + xdpi.frame.xdpf = xdpf; + xdpi.frame.dma_addr = xdptxd.dma_addr; - if (unlikely(!sq->xmit_xdp_frame(sq, &xdpi))) { - dma_unmap_single(sq->pdev, xdpi.dma_addr, - xdpf->len, DMA_TO_DEVICE); + if (unlikely(!sq->xmit_xdp_frame(sq, &xdptxd, &xdpi, 0))) { + dma_unmap_single(sq->pdev, xdptxd.dma_addr, + xdptxd.len, DMA_TO_DEVICE); xdp_return_frame_rx_napi(xdpf); drops++; } @@ -429,7 +540,7 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq) { - struct mlx5e_xdpsq *xdpsq = &rq->xdpsq; + struct mlx5e_xdpsq *xdpsq = rq->xdpsq; if (xdpsq->mpwqe.wqe) mlx5e_xdp_mpwqe_complete(xdpsq); @@ -444,6 +555,8 @@ void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq) void mlx5e_set_xmit_fp(struct mlx5e_xdpsq *sq, bool is_mpw) { + sq->xmit_xdp_frame_check = is_mpw ? + mlx5e_xmit_xdp_frame_check_mpwqe : mlx5e_xmit_xdp_frame_check; sq->xmit_xdp_frame = is_mpw ? mlx5e_xmit_xdp_frame_mpwqe : mlx5e_xmit_xdp_frame; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h index 8b537a4b0840..2d934c8d3807 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -39,11 +39,13 @@ (sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) #define MLX5E_XDP_TX_DS_COUNT (MLX5E_XDP_TX_EMPTY_DS_COUNT + 1 /* SG DS */) -int mlx5e_xdp_max_mtu(struct mlx5e_params *params); +struct mlx5e_xsk_param; +int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, - void *va, u16 *rx_headroom, u32 *len); -bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq); -void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq); + void *va, u16 *rx_headroom, u32 *len, bool xsk); +void mlx5e_xdp_mpwqe_complete(struct mlx5e_xdpsq *sq); +bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq); +void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq); void mlx5e_set_xmit_fp(struct mlx5e_xdpsq *sq, bool is_mpw); void mlx5e_xdp_rx_poll_complete(struct mlx5e_rq *rq); int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames, @@ -66,6 +68,21 @@ static inline bool mlx5e_xdp_tx_is_enabled(struct mlx5e_priv *priv) return test_bit(MLX5E_STATE_XDP_TX_ENABLED, &priv->state); } +static inline void mlx5e_xdp_set_open(struct mlx5e_priv *priv) +{ + set_bit(MLX5E_STATE_XDP_OPEN, &priv->state); +} + +static inline void mlx5e_xdp_set_closed(struct mlx5e_priv *priv) +{ + clear_bit(MLX5E_STATE_XDP_OPEN, &priv->state); +} + +static inline bool mlx5e_xdp_is_open(struct mlx5e_priv *priv) +{ + return test_bit(MLX5E_STATE_XDP_OPEN, &priv->state); +} + static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq) { if (sq->doorbell_cseg) { @@ -97,15 +114,14 @@ static inline void mlx5e_xdp_update_inline_state(struct mlx5e_xdpsq *sq) } static inline void -mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi, +mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, + struct mlx5e_xdp_xmit_data *xdptxd, struct mlx5e_xdpsq_stats *stats) { struct mlx5e_xdp_mpwqe *session = &sq->mpwqe; - dma_addr_t dma_addr = xdpi->dma_addr; - struct xdp_frame *xdpf = xdpi->xdpf; struct mlx5_wqe_data_seg *dseg = (struct mlx5_wqe_data_seg *)session->wqe + session->ds_count; - u16 dma_len = xdpf->len; + u32 dma_len = xdptxd->len; session->pkt_count++; @@ -124,7 +140,7 @@ mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi, } inline_dseg->byte_count = cpu_to_be32(dma_len | MLX5_INLINE_SEG); - memcpy(inline_dseg->data, xdpf->data, dma_len); + memcpy(inline_dseg->data, xdptxd->data, dma_len); session->ds_count += ds_cnt; stats->inlnw++; @@ -132,7 +148,7 @@ mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi, } no_inline: - dseg->addr = cpu_to_be64(dma_addr); + dseg->addr = cpu_to_be64(xdptxd->dma_addr); dseg->byte_count = cpu_to_be32(dma_len); dseg->lkey = sq->mkey_be; session->ds_count++; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/Makefile new file mode 100644 index 000000000000..5ee42991900a --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/Makefile @@ -0,0 +1 @@ +subdir-ccflags-y += -I$(src)/../.. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c new file mode 100644 index 000000000000..6a55573ec8f2 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c @@ -0,0 +1,192 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include "rx.h" +#include "en/xdp.h" +#include <net/xdp_sock.h> + +/* RX data path */ + +bool mlx5e_xsk_pages_enough_umem(struct mlx5e_rq *rq, int count) +{ + /* Check in advance that we have enough frames, instead of allocating + * one-by-one, failing and moving frames to the Reuse Ring. + */ + return xsk_umem_has_addrs_rq(rq->umem, count); +} + +int mlx5e_xsk_page_alloc_umem(struct mlx5e_rq *rq, + struct mlx5e_dma_info *dma_info) +{ + struct xdp_umem *umem = rq->umem; + u64 handle; + + if (!xsk_umem_peek_addr_rq(umem, &handle)) + return -ENOMEM; + + dma_info->xsk.handle = handle + rq->buff.umem_headroom; + dma_info->xsk.data = xdp_umem_get_data(umem, dma_info->xsk.handle); + + /* No need to add headroom to the DMA address. In striding RQ case, we + * just provide pages for UMR, and headroom is counted at the setup + * stage when creating a WQE. In non-striding RQ case, headroom is + * accounted in mlx5e_alloc_rx_wqe. + */ + dma_info->addr = xdp_umem_get_dma(umem, handle); + + xsk_umem_discard_addr_rq(umem); + + dma_sync_single_for_device(rq->pdev, dma_info->addr, PAGE_SIZE, + DMA_BIDIRECTIONAL); + + return 0; +} + +static inline void mlx5e_xsk_recycle_frame(struct mlx5e_rq *rq, u64 handle) +{ + xsk_umem_fq_reuse(rq->umem, handle & rq->umem->chunk_mask); +} + +/* XSKRQ uses pages from UMEM, they must not be released. They are returned to + * the userspace if possible, and if not, this function is called to reuse them + * in the driver. + */ +void mlx5e_xsk_page_release(struct mlx5e_rq *rq, + struct mlx5e_dma_info *dma_info) +{ + mlx5e_xsk_recycle_frame(rq, dma_info->xsk.handle); +} + +/* Return a frame back to the hardware to fill in again. It is used by XDP when + * the XDP program returns XDP_TX or XDP_REDIRECT not to an XSKMAP. + */ +void mlx5e_xsk_zca_free(struct zero_copy_allocator *zca, unsigned long handle) +{ + struct mlx5e_rq *rq = container_of(zca, struct mlx5e_rq, zca); + + mlx5e_xsk_recycle_frame(rq, handle); +} + +static struct sk_buff *mlx5e_xsk_construct_skb(struct mlx5e_rq *rq, void *data, + u32 cqe_bcnt) +{ + struct sk_buff *skb; + + skb = napi_alloc_skb(rq->cq.napi, cqe_bcnt); + if (unlikely(!skb)) { + rq->stats->buff_alloc_err++; + return NULL; + } + + skb_put_data(skb, data, cqe_bcnt); + + return skb; +} + +struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, + struct mlx5e_mpw_info *wi, + u16 cqe_bcnt, + u32 head_offset, + u32 page_idx) +{ + struct mlx5e_dma_info *di = &wi->umr.dma_info[page_idx]; + u16 rx_headroom = rq->buff.headroom - rq->buff.umem_headroom; + u32 cqe_bcnt32 = cqe_bcnt; + void *va, *data; + u32 frag_size; + bool consumed; + + /* Check packet size. Note LRO doesn't use linear SKB */ + if (unlikely(cqe_bcnt > rq->hw_mtu)) { + rq->stats->oversize_pkts_sw_drop++; + return NULL; + } + + /* head_offset is not used in this function, because di->xsk.data and + * di->addr point directly to the necessary place. Furthermore, in the + * current implementation, one page = one packet = one frame, so + * head_offset should always be 0. + */ + WARN_ON_ONCE(head_offset); + + va = di->xsk.data; + data = va + rx_headroom; + frag_size = rq->buff.headroom + cqe_bcnt32; + + dma_sync_single_for_cpu(rq->pdev, di->addr, frag_size, DMA_BIDIRECTIONAL); + prefetch(data); + + rcu_read_lock(); + consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt32, true); + rcu_read_unlock(); + + /* Possible flows: + * - XDP_REDIRECT to XSKMAP: + * The page is owned by the userspace from now. + * - XDP_TX and other XDP_REDIRECTs: + * The page was returned by ZCA and recycled. + * - XDP_DROP: + * Recycle the page. + * - XDP_PASS: + * Allocate an SKB, copy the data and recycle the page. + * + * Pages to be recycled go to the Reuse Ring on MPWQE deallocation. Its + * size is the same as the Driver RX Ring's size, and pages for WQEs are + * allocated first from the Reuse Ring, so it has enough space. + */ + + if (likely(consumed)) { + if (likely(__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))) + __set_bit(page_idx, wi->xdp_xmit_bitmap); /* non-atomic */ + return NULL; /* page/packet was consumed by XDP */ + } + + /* XDP_PASS: copy the data from the UMEM to a new SKB and reuse the + * frame. On SKB allocation failure, NULL is returned. + */ + return mlx5e_xsk_construct_skb(rq, data, cqe_bcnt32); +} + +struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, + struct mlx5_cqe64 *cqe, + struct mlx5e_wqe_frag_info *wi, + u32 cqe_bcnt) +{ + struct mlx5e_dma_info *di = wi->di; + u16 rx_headroom = rq->buff.headroom - rq->buff.umem_headroom; + void *va, *data; + bool consumed; + u32 frag_size; + + /* wi->offset is not used in this function, because di->xsk.data and + * di->addr point directly to the necessary place. Furthermore, in the + * current implementation, one page = one packet = one frame, so + * wi->offset should always be 0. + */ + WARN_ON_ONCE(wi->offset); + + va = di->xsk.data; + data = va + rx_headroom; + frag_size = rq->buff.headroom + cqe_bcnt; + + dma_sync_single_for_cpu(rq->pdev, di->addr, frag_size, DMA_BIDIRECTIONAL); + prefetch(data); + + if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) { + rq->stats->wqe_err++; + return NULL; + } + + rcu_read_lock(); + consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt, true); + rcu_read_unlock(); + + if (likely(consumed)) + return NULL; /* page/packet was consumed by XDP */ + + /* XDP_PASS: copy the data from the UMEM to a new SKB. The frame reuse + * will be handled by mlx5e_put_rx_frag. + * On SKB allocation failure, NULL is returned. + */ + return mlx5e_xsk_construct_skb(rq, data, cqe_bcnt); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h new file mode 100644 index 000000000000..307b923a1361 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h @@ -0,0 +1,27 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#ifndef __MLX5_EN_XSK_RX_H__ +#define __MLX5_EN_XSK_RX_H__ + +#include "en.h" + +/* RX data path */ + +bool mlx5e_xsk_pages_enough_umem(struct mlx5e_rq *rq, int count); +int mlx5e_xsk_page_alloc_umem(struct mlx5e_rq *rq, + struct mlx5e_dma_info *dma_info); +void mlx5e_xsk_page_release(struct mlx5e_rq *rq, + struct mlx5e_dma_info *dma_info); +void mlx5e_xsk_zca_free(struct zero_copy_allocator *zca, unsigned long handle); +struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, + struct mlx5e_mpw_info *wi, + u16 cqe_bcnt, + u32 head_offset, + u32 page_idx); +struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, + struct mlx5_cqe64 *cqe, + struct mlx5e_wqe_frag_info *wi, + u32 cqe_bcnt); + +#endif /* __MLX5_EN_XSK_RX_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c new file mode 100644 index 000000000000..aaffa6f68dc0 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -0,0 +1,223 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include "setup.h" +#include "en/params.h" + +bool mlx5e_validate_xsk_param(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk, + struct mlx5_core_dev *mdev) +{ + /* AF_XDP doesn't support frames larger than PAGE_SIZE, and the current + * mlx5e XDP implementation doesn't support multiple packets per page. + */ + if (xsk->chunk_size != PAGE_SIZE) + return false; + + /* Current MTU and XSK headroom don't allow packets to fit the frames. */ + if (mlx5e_rx_get_linear_frag_sz(params, xsk) > xsk->chunk_size) + return false; + + /* frag_sz is different for regular and XSK RQs, so ensure that linear + * SKB mode is possible. + */ + switch (params->rq_wq_type) { + case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: + return mlx5e_rx_mpwqe_is_linear_skb(mdev, params, xsk); + default: /* MLX5_WQ_TYPE_CYCLIC */ + return mlx5e_rx_is_linear_skb(params, xsk); + } +} + +static void mlx5e_build_xskicosq_param(struct mlx5e_priv *priv, + u8 log_wq_size, + struct mlx5e_sq_param *param) +{ + void *sqc = param->sqc; + void *wq = MLX5_ADDR_OF(sqc, sqc, wq); + + mlx5e_build_sq_param_common(priv, param); + + MLX5_SET(wq, wq, log_wq_sz, log_wq_size); +} + +static void mlx5e_build_xsk_cparam(struct mlx5e_priv *priv, + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk, + struct mlx5e_channel_param *cparam) +{ + const u8 xskicosq_size = MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE; + + mlx5e_build_rq_param(priv, params, xsk, &cparam->rq); + mlx5e_build_xdpsq_param(priv, params, &cparam->xdp_sq); + mlx5e_build_xskicosq_param(priv, xskicosq_size, &cparam->icosq); + mlx5e_build_rx_cq_param(priv, params, xsk, &cparam->rx_cq); + mlx5e_build_tx_cq_param(priv, params, &cparam->tx_cq); + mlx5e_build_ico_cq_param(priv, xskicosq_size, &cparam->icosq_cq); +} + +int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk, struct xdp_umem *umem, + struct mlx5e_channel *c) +{ + struct mlx5e_channel_param cparam = {}; + struct dim_cq_moder icocq_moder = {}; + int err; + + if (!mlx5e_validate_xsk_param(params, xsk, priv->mdev)) + return -EINVAL; + + mlx5e_build_xsk_cparam(priv, params, xsk, &cparam); + + err = mlx5e_open_cq(c, params->rx_cq_moderation, &cparam.rx_cq, &c->xskrq.cq); + if (unlikely(err)) + return err; + + err = mlx5e_open_rq(c, params, &cparam.rq, xsk, umem, &c->xskrq); + if (unlikely(err)) + goto err_close_rx_cq; + + err = mlx5e_open_cq(c, params->tx_cq_moderation, &cparam.tx_cq, &c->xsksq.cq); + if (unlikely(err)) + goto err_close_rq; + + /* Create a separate SQ, so that when the UMEM is disabled, we could + * close this SQ safely and stop receiving CQEs. In other case, e.g., if + * the XDPSQ was used instead, we might run into trouble when the UMEM + * is disabled and then reenabled, but the SQ continues receiving CQEs + * from the old UMEM. + */ + err = mlx5e_open_xdpsq(c, params, &cparam.xdp_sq, umem, &c->xsksq, true); + if (unlikely(err)) + goto err_close_tx_cq; + + err = mlx5e_open_cq(c, icocq_moder, &cparam.icosq_cq, &c->xskicosq.cq); + if (unlikely(err)) + goto err_close_sq; + + /* Create a dedicated SQ for posting NOPs whenever we need an IRQ to be + * triggered and NAPI to be called on the correct CPU. + */ + err = mlx5e_open_icosq(c, params, &cparam.icosq, &c->xskicosq); + if (unlikely(err)) + goto err_close_icocq; + + spin_lock_init(&c->xskicosq_lock); + + set_bit(MLX5E_CHANNEL_STATE_XSK, c->state); + + return 0; + +err_close_icocq: + mlx5e_close_cq(&c->xskicosq.cq); + +err_close_sq: + mlx5e_close_xdpsq(&c->xsksq); + +err_close_tx_cq: + mlx5e_close_cq(&c->xsksq.cq); + +err_close_rq: + mlx5e_close_rq(&c->xskrq); + +err_close_rx_cq: + mlx5e_close_cq(&c->xskrq.cq); + + return err; +} + +void mlx5e_close_xsk(struct mlx5e_channel *c) +{ + clear_bit(MLX5E_CHANNEL_STATE_XSK, c->state); + napi_synchronize(&c->napi); + + mlx5e_close_rq(&c->xskrq); + mlx5e_close_cq(&c->xskrq.cq); + mlx5e_close_icosq(&c->xskicosq); + mlx5e_close_cq(&c->xskicosq.cq); + mlx5e_close_xdpsq(&c->xsksq); + mlx5e_close_cq(&c->xsksq.cq); +} + +void mlx5e_activate_xsk(struct mlx5e_channel *c) +{ + set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state); + /* TX queue is created active. */ + mlx5e_trigger_irq(&c->xskicosq); +} + +void mlx5e_deactivate_xsk(struct mlx5e_channel *c) +{ + mlx5e_deactivate_rq(&c->xskrq); + /* TX queue is disabled on close. */ +} + +static int mlx5e_redirect_xsk_rqt(struct mlx5e_priv *priv, u16 ix, u32 rqn) +{ + struct mlx5e_redirect_rqt_param direct_rrp = { + .is_rss = false, + { + .rqn = rqn, + }, + }; + + u32 rqtn = priv->xsk_tir[ix].rqt.rqtn; + + return mlx5e_redirect_rqt(priv, rqtn, 1, direct_rrp); +} + +int mlx5e_xsk_redirect_rqt_to_channel(struct mlx5e_priv *priv, struct mlx5e_channel *c) +{ + return mlx5e_redirect_xsk_rqt(priv, c->ix, c->xskrq.rqn); +} + +int mlx5e_xsk_redirect_rqt_to_drop(struct mlx5e_priv *priv, u16 ix) +{ + return mlx5e_redirect_xsk_rqt(priv, ix, priv->drop_rq.rqn); +} + +int mlx5e_xsk_redirect_rqts_to_channels(struct mlx5e_priv *priv, struct mlx5e_channels *chs) +{ + int err, i; + + if (!priv->xsk.refcnt) + return 0; + + for (i = 0; i < chs->num; i++) { + struct mlx5e_channel *c = chs->c[i]; + + if (!test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)) + continue; + + err = mlx5e_xsk_redirect_rqt_to_channel(priv, c); + if (unlikely(err)) + goto err_stop; + } + + return 0; + +err_stop: + for (i--; i >= 0; i--) { + if (!test_bit(MLX5E_CHANNEL_STATE_XSK, chs->c[i]->state)) + continue; + + mlx5e_xsk_redirect_rqt_to_drop(priv, i); + } + + return err; +} + +void mlx5e_xsk_redirect_rqts_to_drop(struct mlx5e_priv *priv, struct mlx5e_channels *chs) +{ + int i; + + if (!priv->xsk.refcnt) + return; + + for (i = 0; i < chs->num; i++) { + if (!test_bit(MLX5E_CHANNEL_STATE_XSK, chs->c[i]->state)) + continue; + + mlx5e_xsk_redirect_rqt_to_drop(priv, i); + } +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h new file mode 100644 index 000000000000..0dd11b81c046 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#ifndef __MLX5_EN_XSK_SETUP_H__ +#define __MLX5_EN_XSK_SETUP_H__ + +#include "en.h" + +struct mlx5e_xsk_param; + +bool mlx5e_validate_xsk_param(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk, + struct mlx5_core_dev *mdev); +int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk, struct xdp_umem *umem, + struct mlx5e_channel *c); +void mlx5e_close_xsk(struct mlx5e_channel *c); +void mlx5e_activate_xsk(struct mlx5e_channel *c); +void mlx5e_deactivate_xsk(struct mlx5e_channel *c); +int mlx5e_xsk_redirect_rqt_to_channel(struct mlx5e_priv *priv, struct mlx5e_channel *c); +int mlx5e_xsk_redirect_rqt_to_drop(struct mlx5e_priv *priv, u16 ix); +int mlx5e_xsk_redirect_rqts_to_channels(struct mlx5e_priv *priv, struct mlx5e_channels *chs); +void mlx5e_xsk_redirect_rqts_to_drop(struct mlx5e_priv *priv, struct mlx5e_channels *chs); + +#endif /* __MLX5_EN_XSK_SETUP_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c new file mode 100644 index 000000000000..35e188cf4ea4 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c @@ -0,0 +1,111 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include "tx.h" +#include "umem.h" +#include "en/xdp.h" +#include "en/params.h" +#include <net/xdp_sock.h> + +int mlx5e_xsk_async_xmit(struct net_device *dev, u32 qid) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5e_params *params = &priv->channels.params; + struct mlx5e_channel *c; + u16 ix; + + if (unlikely(!mlx5e_xdp_is_open(priv))) + return -ENETDOWN; + + if (unlikely(!mlx5e_qid_get_ch_if_in_group(params, qid, MLX5E_RQ_GROUP_XSK, &ix))) + return -EINVAL; + + c = priv->channels.c[ix]; + + if (unlikely(!test_bit(MLX5E_CHANNEL_STATE_XSK, c->state))) + return -ENXIO; + + if (!napi_if_scheduled_mark_missed(&c->napi)) { + spin_lock(&c->xskicosq_lock); + mlx5e_trigger_irq(&c->xskicosq); + spin_unlock(&c->xskicosq_lock); + } + + return 0; +} + +/* When TX fails (because of the size of the packet), we need to get completions + * in order, so post a NOP to get a CQE. Since AF_XDP doesn't distinguish + * between successful TX and errors, handling in mlx5e_poll_xdpsq_cq is the + * same. + */ +static void mlx5e_xsk_tx_post_err(struct mlx5e_xdpsq *sq, + struct mlx5e_xdp_info *xdpi) +{ + u16 pi = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->pc); + struct mlx5e_xdp_wqe_info *wi = &sq->db.wqe_info[pi]; + struct mlx5e_tx_wqe *nopwqe; + + wi->num_wqebbs = 1; + wi->num_pkts = 1; + + nopwqe = mlx5e_post_nop(&sq->wq, sq->sqn, &sq->pc); + mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi); + sq->doorbell_cseg = &nopwqe->ctrl; +} + +bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget) +{ + struct xdp_umem *umem = sq->umem; + struct mlx5e_xdp_info xdpi; + struct mlx5e_xdp_xmit_data xdptxd; + bool work_done = true; + bool flush = false; + + xdpi.mode = MLX5E_XDP_XMIT_MODE_XSK; + + for (; budget; budget--) { + int check_result = sq->xmit_xdp_frame_check(sq); + struct xdp_desc desc; + + if (unlikely(check_result < 0)) { + work_done = false; + break; + } + + if (!xsk_umem_consume_tx(umem, &desc)) { + /* TX will get stuck until something wakes it up by + * triggering NAPI. Currently it's expected that the + * application calls sendto() if there are consumed, but + * not completed frames. + */ + break; + } + + xdptxd.dma_addr = xdp_umem_get_dma(umem, desc.addr); + xdptxd.data = xdp_umem_get_data(umem, desc.addr); + xdptxd.len = desc.len; + + dma_sync_single_for_device(sq->pdev, xdptxd.dma_addr, + xdptxd.len, DMA_BIDIRECTIONAL); + + if (unlikely(!sq->xmit_xdp_frame(sq, &xdptxd, &xdpi, check_result))) { + if (sq->mpwqe.wqe) + mlx5e_xdp_mpwqe_complete(sq); + + mlx5e_xsk_tx_post_err(sq, &xdpi); + } + + flush = true; + } + + if (flush) { + if (sq->mpwqe.wqe) + mlx5e_xdp_mpwqe_complete(sq); + mlx5e_xmit_xdp_doorbell(sq); + + xsk_umem_consume_tx_done(umem); + } + + return !(budget && work_done); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h new file mode 100644 index 000000000000..7add18bf78d8 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#ifndef __MLX5_EN_XSK_TX_H__ +#define __MLX5_EN_XSK_TX_H__ + +#include "en.h" + +/* TX data path */ + +int mlx5e_xsk_async_xmit(struct net_device *dev, u32 qid); + +bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget); + +#endif /* __MLX5_EN_XSK_TX_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c new file mode 100644 index 000000000000..4baaa5788320 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.c @@ -0,0 +1,267 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include <net/xdp_sock.h> +#include "umem.h" +#include "setup.h" +#include "en/params.h" + +static int mlx5e_xsk_map_umem(struct mlx5e_priv *priv, + struct xdp_umem *umem) +{ + struct device *dev = priv->mdev->device; + u32 i; + + for (i = 0; i < umem->npgs; i++) { + dma_addr_t dma = dma_map_page(dev, umem->pgs[i], 0, PAGE_SIZE, + DMA_BIDIRECTIONAL); + + if (unlikely(dma_mapping_error(dev, dma))) + goto err_unmap; + umem->pages[i].dma = dma; + } + + return 0; + +err_unmap: + while (i--) { + dma_unmap_page(dev, umem->pages[i].dma, PAGE_SIZE, + DMA_BIDIRECTIONAL); + umem->pages[i].dma = 0; + } + + return -ENOMEM; +} + +static void mlx5e_xsk_unmap_umem(struct mlx5e_priv *priv, + struct xdp_umem *umem) +{ + struct device *dev = priv->mdev->device; + u32 i; + + for (i = 0; i < umem->npgs; i++) { + dma_unmap_page(dev, umem->pages[i].dma, PAGE_SIZE, + DMA_BIDIRECTIONAL); + umem->pages[i].dma = 0; + } +} + +static int mlx5e_xsk_get_umems(struct mlx5e_xsk *xsk) +{ + if (!xsk->umems) { + xsk->umems = kcalloc(MLX5E_MAX_NUM_CHANNELS, + sizeof(*xsk->umems), GFP_KERNEL); + if (unlikely(!xsk->umems)) + return -ENOMEM; + } + + xsk->refcnt++; + xsk->ever_used = true; + + return 0; +} + +static void mlx5e_xsk_put_umems(struct mlx5e_xsk *xsk) +{ + if (!--xsk->refcnt) { + kfree(xsk->umems); + xsk->umems = NULL; + } +} + +static int mlx5e_xsk_add_umem(struct mlx5e_xsk *xsk, struct xdp_umem *umem, u16 ix) +{ + int err; + + err = mlx5e_xsk_get_umems(xsk); + if (unlikely(err)) + return err; + + xsk->umems[ix] = umem; + return 0; +} + +static void mlx5e_xsk_remove_umem(struct mlx5e_xsk *xsk, u16 ix) +{ + xsk->umems[ix] = NULL; + + mlx5e_xsk_put_umems(xsk); +} + +static bool mlx5e_xsk_is_umem_sane(struct xdp_umem *umem) +{ + return umem->headroom <= 0xffff && umem->chunk_size_nohr <= 0xffff; +} + +void mlx5e_build_xsk_param(struct xdp_umem *umem, struct mlx5e_xsk_param *xsk) +{ + xsk->headroom = umem->headroom; + xsk->chunk_size = umem->chunk_size_nohr + umem->headroom; +} + +static int mlx5e_xsk_enable_locked(struct mlx5e_priv *priv, + struct xdp_umem *umem, u16 ix) +{ + struct mlx5e_params *params = &priv->channels.params; + struct mlx5e_xsk_param xsk; + struct mlx5e_channel *c; + int err; + + if (unlikely(mlx5e_xsk_get_umem(&priv->channels.params, &priv->xsk, ix))) + return -EBUSY; + + if (unlikely(!mlx5e_xsk_is_umem_sane(umem))) + return -EINVAL; + + err = mlx5e_xsk_map_umem(priv, umem); + if (unlikely(err)) + return err; + + err = mlx5e_xsk_add_umem(&priv->xsk, umem, ix); + if (unlikely(err)) + goto err_unmap_umem; + + mlx5e_build_xsk_param(umem, &xsk); + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { + /* XSK objects will be created on open. */ + goto validate_closed; + } + + if (!params->xdp_prog) { + /* XSK objects will be created when an XDP program is set, + * and the channels are reopened. + */ + goto validate_closed; + } + + c = priv->channels.c[ix]; + + err = mlx5e_open_xsk(priv, params, &xsk, umem, c); + if (unlikely(err)) + goto err_remove_umem; + + mlx5e_activate_xsk(c); + + /* Don't wait for WQEs, because the newer xdpsock sample doesn't provide + * any Fill Ring entries at the setup stage. + */ + + err = mlx5e_xsk_redirect_rqt_to_channel(priv, priv->channels.c[ix]); + if (unlikely(err)) + goto err_deactivate; + + return 0; + +err_deactivate: + mlx5e_deactivate_xsk(c); + mlx5e_close_xsk(c); + +err_remove_umem: + mlx5e_xsk_remove_umem(&priv->xsk, ix); + +err_unmap_umem: + mlx5e_xsk_unmap_umem(priv, umem); + + return err; + +validate_closed: + /* Check the configuration in advance, rather than fail at a later stage + * (in mlx5e_xdp_set or on open) and end up with no channels. + */ + if (!mlx5e_validate_xsk_param(params, &xsk, priv->mdev)) { + err = -EINVAL; + goto err_remove_umem; + } + + return 0; +} + +static int mlx5e_xsk_disable_locked(struct mlx5e_priv *priv, u16 ix) +{ + struct xdp_umem *umem = mlx5e_xsk_get_umem(&priv->channels.params, + &priv->xsk, ix); + struct mlx5e_channel *c; + + if (unlikely(!umem)) + return -EINVAL; + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + goto remove_umem; + + /* XSK RQ and SQ are only created if XDP program is set. */ + if (!priv->channels.params.xdp_prog) + goto remove_umem; + + c = priv->channels.c[ix]; + mlx5e_xsk_redirect_rqt_to_drop(priv, ix); + mlx5e_deactivate_xsk(c); + mlx5e_close_xsk(c); + +remove_umem: + mlx5e_xsk_remove_umem(&priv->xsk, ix); + mlx5e_xsk_unmap_umem(priv, umem); + + return 0; +} + +static int mlx5e_xsk_enable_umem(struct mlx5e_priv *priv, struct xdp_umem *umem, + u16 ix) +{ + int err; + + mutex_lock(&priv->state_lock); + err = mlx5e_xsk_enable_locked(priv, umem, ix); + mutex_unlock(&priv->state_lock); + + return err; +} + +static int mlx5e_xsk_disable_umem(struct mlx5e_priv *priv, u16 ix) +{ + int err; + + mutex_lock(&priv->state_lock); + err = mlx5e_xsk_disable_locked(priv, ix); + mutex_unlock(&priv->state_lock); + + return err; +} + +int mlx5e_xsk_setup_umem(struct net_device *dev, struct xdp_umem *umem, u16 qid) +{ + struct mlx5e_priv *priv = netdev_priv(dev); + struct mlx5e_params *params = &priv->channels.params; + u16 ix; + + if (unlikely(!mlx5e_qid_get_ch_if_in_group(params, qid, MLX5E_RQ_GROUP_XSK, &ix))) + return -EINVAL; + + return umem ? mlx5e_xsk_enable_umem(priv, umem, ix) : + mlx5e_xsk_disable_umem(priv, ix); +} + +int mlx5e_xsk_resize_reuseq(struct xdp_umem *umem, u32 nentries) +{ + struct xdp_umem_fq_reuse *reuseq; + + reuseq = xsk_reuseq_prepare(nentries); + if (unlikely(!reuseq)) + return -ENOMEM; + xsk_reuseq_free(xsk_reuseq_swap(umem, reuseq)); + + return 0; +} + +u16 mlx5e_xsk_first_unused_channel(struct mlx5e_params *params, struct mlx5e_xsk *xsk) +{ + u16 res = xsk->refcnt ? params->num_channels : 0; + + while (res) { + if (mlx5e_xsk_get_umem(params, xsk, res - 1)) + break; + --res; + } + + return res; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.h new file mode 100644 index 000000000000..25b4cbe58b54 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/umem.h @@ -0,0 +1,31 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#ifndef __MLX5_EN_XSK_UMEM_H__ +#define __MLX5_EN_XSK_UMEM_H__ + +#include "en.h" + +static inline struct xdp_umem *mlx5e_xsk_get_umem(struct mlx5e_params *params, + struct mlx5e_xsk *xsk, u16 ix) +{ + if (!xsk || !xsk->umems) + return NULL; + + if (unlikely(ix >= params->num_channels)) + return NULL; + + return xsk->umems[ix]; +} + +struct mlx5e_xsk_param; +void mlx5e_build_xsk_param(struct xdp_umem *umem, struct mlx5e_xsk_param *xsk); + +/* .ndo_bpf callback. */ +int mlx5e_xsk_setup_umem(struct net_device *dev, struct xdp_umem *umem, u16 qid); + +int mlx5e_xsk_resize_reuseq(struct xdp_umem *umem, u32 nentries); + +u16 mlx5e_xsk_first_unused_channel(struct mlx5e_params *params, struct mlx5e_xsk *xsk); + +#endif /* __MLX5_EN_XSK_UMEM_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 198a52d1e515..126ec4181286 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -32,6 +32,7 @@ #include "en.h" #include "en/port.h" +#include "en/xsk/umem.h" #include "lib/clock.h" void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv, @@ -388,8 +389,17 @@ static int mlx5e_set_ringparam(struct net_device *dev, void mlx5e_ethtool_get_channels(struct mlx5e_priv *priv, struct ethtool_channels *ch) { + mutex_lock(&priv->state_lock); + ch->max_combined = mlx5e_get_netdev_max_channels(priv->netdev); ch->combined_count = priv->channels.params.num_channels; + if (priv->xsk.refcnt) { + /* The upper half are XSK queues. */ + ch->max_combined *= 2; + ch->combined_count *= 2; + } + + mutex_unlock(&priv->state_lock); } static void mlx5e_get_channels(struct net_device *dev, @@ -403,6 +413,7 @@ static void mlx5e_get_channels(struct net_device *dev, int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, struct ethtool_channels *ch) { + struct mlx5e_params *cur_params = &priv->channels.params; unsigned int count = ch->combined_count; struct mlx5e_channels new_channels = {}; bool arfs_enabled; @@ -414,16 +425,26 @@ int mlx5e_ethtool_set_channels(struct mlx5e_priv *priv, return -EINVAL; } - if (priv->channels.params.num_channels == count) + if (cur_params->num_channels == count) return 0; mutex_lock(&priv->state_lock); + /* Don't allow changing the number of channels if there is an active + * XSK, because the numeration of the XSK and regular RQs will change. + */ + if (priv->xsk.refcnt) { + err = -EINVAL; + netdev_err(priv->netdev, "%s: AF_XDP is active, cannot change the number of channels\n", + __func__); + goto out; + } + new_channels.params = priv->channels.params; new_channels.params.num_channels = count; if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { - priv->channels.params = new_channels.params; + *cur_params = new_channels.params; if (!netif_is_rxfh_configured(priv->netdev)) mlx5e_build_default_indir_rqt(priv->rss_params.indirection_rqt, MLX5E_INDIR_RQT_SIZE, count); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index 839662644ed3..ea3a490b569a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -32,6 +32,8 @@ #include <linux/mlx5/fs.h> #include "en.h" +#include "en/params.h" +#include "en/xsk/umem.h" struct mlx5e_ethtool_rule { struct list_head list; @@ -414,6 +416,14 @@ add_ethtool_flow_rule(struct mlx5e_priv *priv, if (fs->ring_cookie == RX_CLS_FLOW_DISC) { flow_act.action = MLX5_FLOW_CONTEXT_ACTION_DROP; } else { + struct mlx5e_params *params = &priv->channels.params; + enum mlx5e_rq_group group; + struct mlx5e_tir *tir; + u16 ix; + + mlx5e_qid_get_ch_and_group(params, fs->ring_cookie, &ix, &group); + tir = group == MLX5E_RQ_GROUP_XSK ? priv->xsk_tir : priv->direct_tir; + dst = kzalloc(sizeof(*dst), GFP_KERNEL); if (!dst) { err = -ENOMEM; @@ -421,7 +431,7 @@ add_ethtool_flow_rule(struct mlx5e_priv *priv, } dst->type = MLX5_FLOW_DESTINATION_TYPE_TIR; - dst->tir_num = priv->direct_tir[fs->ring_cookie].tirn; + dst->tir_num = tir[ix].tirn; flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST; } @@ -600,9 +610,9 @@ static int validate_flow(struct mlx5e_priv *priv, if (fs->location >= MAX_NUM_OF_ETHTOOL_RULES) return -ENOSPC; - if (fs->ring_cookie >= priv->channels.params.num_channels && - fs->ring_cookie != RX_CLS_FLOW_DISC) - return -EINVAL; + if (fs->ring_cookie != RX_CLS_FLOW_DISC) + if (!mlx5e_qid_validate(&priv->channels.params, fs->ring_cookie)) + return -EINVAL; switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) { case ETHER_FLOW: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 1085040675ae..2f9093ba82aa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -38,6 +38,7 @@ #include <linux/bpf.h> #include <linux/if_bridge.h> #include <net/page_pool.h> +#include <net/xdp_sock.h> #include "eswitch.h" #include "en.h" #include "en_tc.h" @@ -56,35 +57,10 @@ #include "en/monitor_stats.h" #include "en/reporter.h" #include "en/params.h" - -struct mlx5e_rq_param { - u32 rqc[MLX5_ST_SZ_DW(rqc)]; - struct mlx5_wq_param wq; - struct mlx5e_rq_frags_info frags_info; -}; - -struct mlx5e_sq_param { - u32 sqc[MLX5_ST_SZ_DW(sqc)]; - struct mlx5_wq_param wq; - bool is_mpw; -}; - -struct mlx5e_cq_param { - u32 cqc[MLX5_ST_SZ_DW(cqc)]; - struct mlx5_wq_param wq; - u16 eq_ix; - u8 cq_period_mode; -}; - -struct mlx5e_channel_param { - struct mlx5e_rq_param rq; - struct mlx5e_sq_param sq; - struct mlx5e_sq_param xdp_sq; - struct mlx5e_sq_param icosq; - struct mlx5e_cq_param rx_cq; - struct mlx5e_cq_param tx_cq; - struct mlx5e_cq_param icosq_cq; -}; +#include "en/xsk/umem.h" +#include "en/xsk/setup.h" +#include "en/xsk/rx.h" +#include "en/xsk/tx.h" bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev) { @@ -114,18 +90,31 @@ void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev, mlx5_core_info(mdev, "MLX5E: StrdRq(%d) RqSz(%ld) StrdSz(%ld) RxCqeCmprss(%d)\n", params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ, params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ ? - BIT(mlx5e_mpwqe_get_log_rq_size(params)) : + BIT(mlx5e_mpwqe_get_log_rq_size(params, NULL)) : BIT(params->log_rq_mtu_frames), - BIT(mlx5e_mpwqe_get_log_stride_size(mdev, params)), + BIT(mlx5e_mpwqe_get_log_stride_size(mdev, params, NULL)), MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)); } bool mlx5e_striding_rq_possible(struct mlx5_core_dev *mdev, struct mlx5e_params *params) { - return mlx5e_check_fragmented_striding_rq_cap(mdev) && - !MLX5_IPSEC_DEV(mdev) && - !(params->xdp_prog && !mlx5e_rx_mpwqe_is_linear_skb(mdev, params)); + if (!mlx5e_check_fragmented_striding_rq_cap(mdev)) + return false; + + if (MLX5_IPSEC_DEV(mdev)) + return false; + + if (params->xdp_prog) { + /* XSK params are not considered here. If striding RQ is in use, + * and an XSK is being opened, mlx5e_rx_mpwqe_is_linear_skb will + * be called with the known XSK params. + */ + if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL)) + return false; + } + + return true; } void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params) @@ -394,6 +383,8 @@ static void mlx5e_free_di_list(struct mlx5e_rq *rq) static int mlx5e_alloc_rq(struct mlx5e_channel *c, struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk, + struct xdp_umem *umem, struct mlx5e_rq_param *rqp, struct mlx5e_rq *rq) { @@ -401,6 +392,8 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, struct mlx5_core_dev *mdev = c->mdev; void *rqc = rqp->rqc; void *rqc_wq = MLX5_ADDR_OF(rqc, rqc, wq); + u32 num_xsk_frames = 0; + u32 rq_xdp_ix; u32 pool_size; int wq_sz; int err; @@ -417,7 +410,13 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, rq->ix = c->ix; rq->mdev = mdev; rq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); - rq->stats = &c->priv->channel_stats[c->ix].rq; + rq->xdpsq = &c->rq_xdpsq; + rq->umem = umem; + + if (rq->umem) + rq->stats = &c->priv->channel_stats[c->ix].xskrq; + else + rq->stats = &c->priv->channel_stats[c->ix].rq; rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL; if (IS_ERR(rq->xdp_prog)) { @@ -426,12 +425,16 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, goto err_rq_wq_destroy; } - err = xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq->ix); + rq_xdp_ix = rq->ix; + if (xsk) + rq_xdp_ix += params->num_channels * MLX5E_RQ_GROUP_XSK; + err = xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq_xdp_ix); if (err < 0) goto err_rq_wq_destroy; rq->buff.map_dir = rq->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; - rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params); + rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params, xsk); + rq->buff.umem_headroom = xsk ? xsk->headroom : 0; pool_size = 1 << params->log_rq_mtu_frames; switch (rq->wq_type) { @@ -445,7 +448,12 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq); - pool_size = MLX5_MPWRQ_PAGES_PER_WQE << mlx5e_mpwqe_get_log_rq_size(params); + if (xsk) + num_xsk_frames = wq_sz << + mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk); + + pool_size = MLX5_MPWRQ_PAGES_PER_WQE << + mlx5e_mpwqe_get_log_rq_size(params, xsk); rq->post_wqes = mlx5e_post_rx_mpwqes; rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe; @@ -464,12 +472,15 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, goto err_rq_wq_destroy; } - rq->mpwqe.skb_from_cqe_mpwrq = - mlx5e_rx_mpwqe_is_linear_skb(mdev, params) ? - mlx5e_skb_from_cqe_mpwrq_linear : - mlx5e_skb_from_cqe_mpwrq_nonlinear; - rq->mpwqe.log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params); - rq->mpwqe.num_strides = BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params)); + rq->mpwqe.skb_from_cqe_mpwrq = xsk ? + mlx5e_xsk_skb_from_cqe_mpwrq_linear : + mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL) ? + mlx5e_skb_from_cqe_mpwrq_linear : + mlx5e_skb_from_cqe_mpwrq_nonlinear; + + rq->mpwqe.log_stride_sz = mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk); + rq->mpwqe.num_strides = + BIT(mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk)); err = mlx5e_create_rq_umr_mkey(mdev, rq); if (err) @@ -490,6 +501,9 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, wq_sz = mlx5_wq_cyc_get_size(&rq->wqe.wq); + if (xsk) + num_xsk_frames = wq_sz << rq->wqe.info.log_num_frags; + rq->wqe.info = rqp->frags_info; rq->wqe.frags = kvzalloc_node(array_size(sizeof(*rq->wqe.frags), @@ -503,6 +517,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, err = mlx5e_init_di_list(rq, wq_sz, c->cpu); if (err) goto err_free; + rq->post_wqes = mlx5e_post_rx_wqes; rq->dealloc_wqe = mlx5e_dealloc_rx_wqe; @@ -518,37 +533,53 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, goto err_free; } - rq->wqe.skb_from_cqe = mlx5e_rx_is_linear_skb(params) ? - mlx5e_skb_from_cqe_linear : - mlx5e_skb_from_cqe_nonlinear; + rq->wqe.skb_from_cqe = xsk ? + mlx5e_xsk_skb_from_cqe_linear : + mlx5e_rx_is_linear_skb(params, NULL) ? + mlx5e_skb_from_cqe_linear : + mlx5e_skb_from_cqe_nonlinear; rq->mkey_be = c->mkey_be; } - /* Create a page_pool and register it with rxq */ - pp_params.order = 0; - pp_params.flags = 0; /* No-internal DMA mapping in page_pool */ - pp_params.pool_size = pool_size; - pp_params.nid = cpu_to_node(c->cpu); - pp_params.dev = c->pdev; - pp_params.dma_dir = rq->buff.map_dir; - - /* page_pool can be used even when there is no rq->xdp_prog, - * given page_pool does not handle DMA mapping there is no - * required state to clear. And page_pool gracefully handle - * elevated refcnt. - */ - rq->page_pool = page_pool_create(&pp_params); - if (IS_ERR(rq->page_pool)) { - err = PTR_ERR(rq->page_pool); - rq->page_pool = NULL; - goto err_free; + if (xsk) { + err = mlx5e_xsk_resize_reuseq(umem, num_xsk_frames); + if (unlikely(err)) { + mlx5_core_err(mdev, "Unable to allocate the Reuse Ring for %u frames\n", + num_xsk_frames); + goto err_free; + } + + rq->zca.free = mlx5e_xsk_zca_free; + err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, + MEM_TYPE_ZERO_COPY, + &rq->zca); + } else { + /* Create a page_pool and register it with rxq */ + pp_params.order = 0; + pp_params.flags = 0; /* No-internal DMA mapping in page_pool */ + pp_params.pool_size = pool_size; + pp_params.nid = cpu_to_node(c->cpu); + pp_params.dev = c->pdev; + pp_params.dma_dir = rq->buff.map_dir; + + /* page_pool can be used even when there is no rq->xdp_prog, + * given page_pool does not handle DMA mapping there is no + * required state to clear. And page_pool gracefully handle + * elevated refcnt. + */ + rq->page_pool = page_pool_create(&pp_params); + if (IS_ERR(rq->page_pool)) { + err = PTR_ERR(rq->page_pool); + rq->page_pool = NULL; + goto err_free; + } + err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, + MEM_TYPE_PAGE_POOL, rq->page_pool); + if (err) + page_pool_free(rq->page_pool); } - err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, - MEM_TYPE_PAGE_POOL, rq->page_pool); - if (err) { - page_pool_free(rq->page_pool); + if (err) goto err_free; - } for (i = 0; i < wq_sz; i++) { if (rq->wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { @@ -639,7 +670,11 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq) i = (i + 1) & (MLX5E_CACHE_SIZE - 1)) { struct mlx5e_dma_info *dma_info = &rq->page_cache.page_cache[i]; - mlx5e_page_release(rq, dma_info, false); + /* With AF_XDP, page_cache is not used, so this loop is not + * entered, and it's safe to call mlx5e_page_release_dynamic + * directly. + */ + mlx5e_page_release_dynamic(rq, dma_info, false); } xdp_rxq_info_unreg(&rq->xdp_rxq); @@ -776,7 +811,7 @@ static void mlx5e_destroy_rq(struct mlx5e_rq *rq) mlx5_core_destroy_rq(rq->mdev, rq->rqn); } -static int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time) +int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time) { unsigned long exp_time = jiffies + msecs_to_jiffies(wait_time); struct mlx5e_channel *c = rq->channel; @@ -834,14 +869,13 @@ static void mlx5e_free_rx_descs(struct mlx5e_rq *rq) } -static int mlx5e_open_rq(struct mlx5e_channel *c, - struct mlx5e_params *params, - struct mlx5e_rq_param *param, - struct mlx5e_rq *rq) +int mlx5e_open_rq(struct mlx5e_channel *c, struct mlx5e_params *params, + struct mlx5e_rq_param *param, struct mlx5e_xsk_param *xsk, + struct xdp_umem *umem, struct mlx5e_rq *rq) { int err; - err = mlx5e_alloc_rq(c, params, param, rq); + err = mlx5e_alloc_rq(c, params, xsk, umem, param, rq); if (err) return err; @@ -879,13 +913,13 @@ static void mlx5e_activate_rq(struct mlx5e_rq *rq) mlx5e_trigger_irq(&rq->channel->icosq); } -static void mlx5e_deactivate_rq(struct mlx5e_rq *rq) +void mlx5e_deactivate_rq(struct mlx5e_rq *rq) { clear_bit(MLX5E_RQ_STATE_ENABLED, &rq->state); napi_synchronize(&rq->channel->napi); /* prevent mlx5e_post_rx_wqes */ } -static void mlx5e_close_rq(struct mlx5e_rq *rq) +void mlx5e_close_rq(struct mlx5e_rq *rq) { cancel_work_sync(&rq->dim.work); mlx5e_destroy_rq(rq); @@ -938,6 +972,7 @@ static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa) static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params, + struct xdp_umem *umem, struct mlx5e_sq_param *param, struct mlx5e_xdpsq *sq, bool is_redirect) @@ -953,9 +988,13 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c, sq->uar_map = mdev->mlx5e_res.bfreg.map; sq->min_inline_mode = params->tx_min_inline_mode; sq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); - sq->stats = is_redirect ? - &c->priv->channel_stats[c->ix].xdpsq : - &c->priv->channel_stats[c->ix].rq_xdpsq; + sq->umem = umem; + + sq->stats = sq->umem ? + &c->priv->channel_stats[c->ix].xsksq : + is_redirect ? + &c->priv->channel_stats[c->ix].xdpsq : + &c->priv->channel_stats[c->ix].rq_xdpsq; param->wq.db_numa_node = cpu_to_node(c->cpu); err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, wq, &sq->wq_ctrl); @@ -1335,10 +1374,8 @@ static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work) mlx5e_tx_reporter_err_cqe(sq); } -static int mlx5e_open_icosq(struct mlx5e_channel *c, - struct mlx5e_params *params, - struct mlx5e_sq_param *param, - struct mlx5e_icosq *sq) +int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params, + struct mlx5e_sq_param *param, struct mlx5e_icosq *sq) { struct mlx5e_create_sq_param csp = {}; int err; @@ -1364,7 +1401,7 @@ err_free_icosq: return err; } -static void mlx5e_close_icosq(struct mlx5e_icosq *sq) +void mlx5e_close_icosq(struct mlx5e_icosq *sq) { struct mlx5e_channel *c = sq->channel; @@ -1375,16 +1412,14 @@ static void mlx5e_close_icosq(struct mlx5e_icosq *sq) mlx5e_free_icosq(sq); } -static int mlx5e_open_xdpsq(struct mlx5e_channel *c, - struct mlx5e_params *params, - struct mlx5e_sq_param *param, - struct mlx5e_xdpsq *sq, - bool is_redirect) +int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params, + struct mlx5e_sq_param *param, struct xdp_umem *umem, + struct mlx5e_xdpsq *sq, bool is_redirect) { struct mlx5e_create_sq_param csp = {}; int err; - err = mlx5e_alloc_xdpsq(c, params, param, sq, is_redirect); + err = mlx5e_alloc_xdpsq(c, params, umem, param, sq, is_redirect); if (err) return err; @@ -1438,7 +1473,7 @@ err_free_xdpsq: return err; } -static void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq) +void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq) { struct mlx5e_channel *c = sq->channel; @@ -1446,7 +1481,7 @@ static void mlx5e_close_xdpsq(struct mlx5e_xdpsq *sq, struct mlx5e_rq *rq) napi_synchronize(&c->napi); mlx5e_destroy_sq(c->mdev, sq->sqn); - mlx5e_free_xdpsq_descs(sq, rq); + mlx5e_free_xdpsq_descs(sq); mlx5e_free_xdpsq(sq); } @@ -1567,10 +1602,8 @@ static void mlx5e_destroy_cq(struct mlx5e_cq *cq) mlx5_core_destroy_cq(cq->mdev, &cq->mcq); } -static int mlx5e_open_cq(struct mlx5e_channel *c, - struct dim_cq_moder moder, - struct mlx5e_cq_param *param, - struct mlx5e_cq *cq) +int mlx5e_open_cq(struct mlx5e_channel *c, struct dim_cq_moder moder, + struct mlx5e_cq_param *param, struct mlx5e_cq *cq) { struct mlx5_core_dev *mdev = c->mdev; int err; @@ -1593,7 +1626,7 @@ err_free_cq: return err; } -static void mlx5e_close_cq(struct mlx5e_cq *cq) +void mlx5e_close_cq(struct mlx5e_cq *cq) { mlx5e_destroy_cq(cq); mlx5e_free_cq(cq); @@ -1767,49 +1800,16 @@ static void mlx5e_free_xps_cpumask(struct mlx5e_channel *c) free_cpumask_var(c->xps_cpumask); } -static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, - struct mlx5e_params *params, - struct mlx5e_channel_param *cparam, - struct mlx5e_channel **cp) +static int mlx5e_open_queues(struct mlx5e_channel *c, + struct mlx5e_params *params, + struct mlx5e_channel_param *cparam) { - int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(priv->mdev, ix)); struct dim_cq_moder icocq_moder = {0, 0}; - struct net_device *netdev = priv->netdev; - struct mlx5e_channel *c; - unsigned int irq; int err; - int eqn; - - err = mlx5_vector2eqn(priv->mdev, ix, &eqn, &irq); - if (err) - return err; - - c = kvzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu)); - if (!c) - return -ENOMEM; - - c->priv = priv; - c->mdev = priv->mdev; - c->tstamp = &priv->tstamp; - c->ix = ix; - c->cpu = cpu; - c->pdev = priv->mdev->device; - c->netdev = priv->netdev; - c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key); - c->num_tc = params->num_tc; - c->xdp = !!params->xdp_prog; - c->stats = &priv->channel_stats[ix].ch; - c->irq_desc = irq_to_desc(irq); - - err = mlx5e_alloc_xps_cpumask(c, params); - if (err) - goto err_free_channel; - - netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64); err = mlx5e_open_cq(c, icocq_moder, &cparam->icosq_cq, &c->icosq.cq); if (err) - goto err_napi_del; + return err; err = mlx5e_open_tx_cqs(c, params, cparam); if (err) @@ -1825,7 +1825,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, /* XDP SQ CQ params are same as normal TXQ sq CQ params */ err = c->xdp ? mlx5e_open_cq(c, params->tx_cq_moderation, - &cparam->tx_cq, &c->rq.xdpsq.cq) : 0; + &cparam->tx_cq, &c->rq_xdpsq.cq) : 0; if (err) goto err_close_rx_cq; @@ -1839,20 +1839,21 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, if (err) goto err_close_icosq; - err = c->xdp ? mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->rq.xdpsq, false) : 0; - if (err) - goto err_close_sqs; + if (c->xdp) { + err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, NULL, + &c->rq_xdpsq, false); + if (err) + goto err_close_sqs; + } - err = mlx5e_open_rq(c, params, &cparam->rq, &c->rq); + err = mlx5e_open_rq(c, params, &cparam->rq, NULL, NULL, &c->rq); if (err) goto err_close_xdp_sq; - err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->xdpsq, true); + err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, NULL, &c->xdpsq, true); if (err) goto err_close_rq; - *cp = c; - return 0; err_close_rq: @@ -1860,7 +1861,7 @@ err_close_rq: err_close_xdp_sq: if (c->xdp) - mlx5e_close_xdpsq(&c->rq.xdpsq, &c->rq); + mlx5e_close_xdpsq(&c->rq_xdpsq); err_close_sqs: mlx5e_close_sqs(c); @@ -1870,8 +1871,9 @@ err_close_icosq: err_disable_napi: napi_disable(&c->napi); + if (c->xdp) - mlx5e_close_cq(&c->rq.xdpsq.cq); + mlx5e_close_cq(&c->rq_xdpsq.cq); err_close_rx_cq: mlx5e_close_cq(&c->rq.cq); @@ -1885,6 +1887,85 @@ err_close_tx_cqs: err_close_icosq_cq: mlx5e_close_cq(&c->icosq.cq); + return err; +} + +static void mlx5e_close_queues(struct mlx5e_channel *c) +{ + mlx5e_close_xdpsq(&c->xdpsq); + mlx5e_close_rq(&c->rq); + if (c->xdp) + mlx5e_close_xdpsq(&c->rq_xdpsq); + mlx5e_close_sqs(c); + mlx5e_close_icosq(&c->icosq); + napi_disable(&c->napi); + if (c->xdp) + mlx5e_close_cq(&c->rq_xdpsq.cq); + mlx5e_close_cq(&c->rq.cq); + mlx5e_close_cq(&c->xdpsq.cq); + mlx5e_close_tx_cqs(c); + mlx5e_close_cq(&c->icosq.cq); +} + +static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, + struct mlx5e_params *params, + struct mlx5e_channel_param *cparam, + struct xdp_umem *umem, + struct mlx5e_channel **cp) +{ + int cpu = cpumask_first(mlx5_comp_irq_get_affinity_mask(priv->mdev, ix)); + struct net_device *netdev = priv->netdev; + struct mlx5e_xsk_param xsk; + struct mlx5e_channel *c; + unsigned int irq; + int err; + int eqn; + + err = mlx5_vector2eqn(priv->mdev, ix, &eqn, &irq); + if (err) + return err; + + c = kvzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu)); + if (!c) + return -ENOMEM; + + c->priv = priv; + c->mdev = priv->mdev; + c->tstamp = &priv->tstamp; + c->ix = ix; + c->cpu = cpu; + c->pdev = priv->mdev->device; + c->netdev = priv->netdev; + c->mkey_be = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key); + c->num_tc = params->num_tc; + c->xdp = !!params->xdp_prog; + c->stats = &priv->channel_stats[ix].ch; + c->irq_desc = irq_to_desc(irq); + + err = mlx5e_alloc_xps_cpumask(c, params); + if (err) + goto err_free_channel; + + netif_napi_add(netdev, &c->napi, mlx5e_napi_poll, 64); + + err = mlx5e_open_queues(c, params, cparam); + if (unlikely(err)) + goto err_napi_del; + + if (umem) { + mlx5e_build_xsk_param(umem, &xsk); + err = mlx5e_open_xsk(priv, params, &xsk, umem, c); + if (unlikely(err)) + goto err_close_queues; + } + + *cp = c; + + return 0; + +err_close_queues: + mlx5e_close_queues(c); + err_napi_del: netif_napi_del(&c->napi); mlx5e_free_xps_cpumask(c); @@ -1903,12 +1984,18 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c) mlx5e_activate_txqsq(&c->sq[tc]); mlx5e_activate_rq(&c->rq); netif_set_xps_queue(c->netdev, c->xps_cpumask, c->ix); + + if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)) + mlx5e_activate_xsk(c); } static void mlx5e_deactivate_channel(struct mlx5e_channel *c) { int tc; + if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)) + mlx5e_deactivate_xsk(c); + mlx5e_deactivate_rq(&c->rq); for (tc = 0; tc < c->num_tc; tc++) mlx5e_deactivate_txqsq(&c->sq[tc]); @@ -1916,19 +2003,9 @@ static void mlx5e_deactivate_channel(struct mlx5e_channel *c) static void mlx5e_close_channel(struct mlx5e_channel *c) { - mlx5e_close_xdpsq(&c->xdpsq, NULL); - mlx5e_close_rq(&c->rq); - if (c->xdp) - mlx5e_close_xdpsq(&c->rq.xdpsq, &c->rq); - mlx5e_close_sqs(c); - mlx5e_close_icosq(&c->icosq); - napi_disable(&c->napi); - if (c->xdp) - mlx5e_close_cq(&c->rq.xdpsq.cq); - mlx5e_close_cq(&c->rq.cq); - mlx5e_close_cq(&c->xdpsq.cq); - mlx5e_close_tx_cqs(c); - mlx5e_close_cq(&c->icosq.cq); + if (test_bit(MLX5E_CHANNEL_STATE_XSK, c->state)) + mlx5e_close_xsk(c); + mlx5e_close_queues(c); netif_napi_del(&c->napi); mlx5e_free_xps_cpumask(c); @@ -1939,6 +2016,7 @@ static void mlx5e_close_channel(struct mlx5e_channel *c) static void mlx5e_build_rq_frags_info(struct mlx5_core_dev *mdev, struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk, struct mlx5e_rq_frags_info *info) { u32 byte_count = MLX5E_SW2HW_MTU(params, params->sw_mtu); @@ -1951,10 +2029,10 @@ static void mlx5e_build_rq_frags_info(struct mlx5_core_dev *mdev, byte_count += MLX5E_METADATA_ETHER_LEN; #endif - if (mlx5e_rx_is_linear_skb(params)) { + if (mlx5e_rx_is_linear_skb(params, xsk)) { int frag_stride; - frag_stride = mlx5e_rx_get_linear_frag_sz(params); + frag_stride = mlx5e_rx_get_linear_frag_sz(params, xsk); frag_stride = roundup_pow_of_two(frag_stride); info->arr[0].frag_size = byte_count; @@ -2012,9 +2090,10 @@ static u8 mlx5e_get_rq_log_wq_sz(void *rqc) return MLX5_GET(wq, wq, log_wq_sz); } -static void mlx5e_build_rq_param(struct mlx5e_priv *priv, - struct mlx5e_params *params, - struct mlx5e_rq_param *param) +void mlx5e_build_rq_param(struct mlx5e_priv *priv, + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk, + struct mlx5e_rq_param *param) { struct mlx5_core_dev *mdev = priv->mdev; void *rqc = param->rqc; @@ -2024,16 +2103,16 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv, switch (params->rq_wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: MLX5_SET(wq, wq, log_wqe_num_of_strides, - mlx5e_mpwqe_get_log_num_strides(mdev, params) - + mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk) - MLX5_MPWQE_LOG_NUM_STRIDES_BASE); MLX5_SET(wq, wq, log_wqe_stride_size, - mlx5e_mpwqe_get_log_stride_size(mdev, params) - + mlx5e_mpwqe_get_log_stride_size(mdev, params, xsk) - MLX5_MPWQE_LOG_STRIDE_SZ_BASE); - MLX5_SET(wq, wq, log_wq_sz, mlx5e_mpwqe_get_log_rq_size(params)); + MLX5_SET(wq, wq, log_wq_sz, mlx5e_mpwqe_get_log_rq_size(params, xsk)); break; default: /* MLX5_WQ_TYPE_CYCLIC */ MLX5_SET(wq, wq, log_wq_sz, params->log_rq_mtu_frames); - mlx5e_build_rq_frags_info(mdev, params, ¶m->frags_info); + mlx5e_build_rq_frags_info(mdev, params, xsk, ¶m->frags_info); ndsegs = param->frags_info.num_frags; } @@ -2064,8 +2143,8 @@ static void mlx5e_build_drop_rq_param(struct mlx5e_priv *priv, param->wq.buf_numa_node = dev_to_node(mdev->device); } -static void mlx5e_build_sq_param_common(struct mlx5e_priv *priv, - struct mlx5e_sq_param *param) +void mlx5e_build_sq_param_common(struct mlx5e_priv *priv, + struct mlx5e_sq_param *param) { void *sqc = param->sqc; void *wq = MLX5_ADDR_OF(sqc, sqc, wq); @@ -2101,9 +2180,10 @@ static void mlx5e_build_common_cq_param(struct mlx5e_priv *priv, MLX5_SET(cqc, cqc, cqe_sz, CQE_STRIDE_128_PAD); } -static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv, - struct mlx5e_params *params, - struct mlx5e_cq_param *param) +void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv, + struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk, + struct mlx5e_cq_param *param) { struct mlx5_core_dev *mdev = priv->mdev; void *cqc = param->cqc; @@ -2111,8 +2191,8 @@ static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv, switch (params->rq_wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: - log_cq_size = mlx5e_mpwqe_get_log_rq_size(params) + - mlx5e_mpwqe_get_log_num_strides(mdev, params); + log_cq_size = mlx5e_mpwqe_get_log_rq_size(params, xsk) + + mlx5e_mpwqe_get_log_num_strides(mdev, params, xsk); break; default: /* MLX5_WQ_TYPE_CYCLIC */ log_cq_size = params->log_rq_mtu_frames; @@ -2128,9 +2208,9 @@ static void mlx5e_build_rx_cq_param(struct mlx5e_priv *priv, param->cq_period_mode = params->rx_cq_moderation.cq_period_mode; } -static void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv, - struct mlx5e_params *params, - struct mlx5e_cq_param *param) +void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv, + struct mlx5e_params *params, + struct mlx5e_cq_param *param) { void *cqc = param->cqc; @@ -2140,9 +2220,9 @@ static void mlx5e_build_tx_cq_param(struct mlx5e_priv *priv, param->cq_period_mode = params->tx_cq_moderation.cq_period_mode; } -static void mlx5e_build_ico_cq_param(struct mlx5e_priv *priv, - u8 log_wq_size, - struct mlx5e_cq_param *param) +void mlx5e_build_ico_cq_param(struct mlx5e_priv *priv, + u8 log_wq_size, + struct mlx5e_cq_param *param) { void *cqc = param->cqc; @@ -2153,9 +2233,9 @@ static void mlx5e_build_ico_cq_param(struct mlx5e_priv *priv, param->cq_period_mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE; } -static void mlx5e_build_icosq_param(struct mlx5e_priv *priv, - u8 log_wq_size, - struct mlx5e_sq_param *param) +void mlx5e_build_icosq_param(struct mlx5e_priv *priv, + u8 log_wq_size, + struct mlx5e_sq_param *param) { void *sqc = param->sqc; void *wq = MLX5_ADDR_OF(sqc, sqc, wq); @@ -2166,9 +2246,9 @@ static void mlx5e_build_icosq_param(struct mlx5e_priv *priv, MLX5_SET(sqc, sqc, reg_umr, MLX5_CAP_ETH(priv->mdev, reg_umr_sq)); } -static void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv, - struct mlx5e_params *params, - struct mlx5e_sq_param *param) +void mlx5e_build_xdpsq_param(struct mlx5e_priv *priv, + struct mlx5e_params *params, + struct mlx5e_sq_param *param) { void *sqc = param->sqc; void *wq = MLX5_ADDR_OF(sqc, sqc, wq); @@ -2196,14 +2276,14 @@ static void mlx5e_build_channel_param(struct mlx5e_priv *priv, { u8 icosq_log_wq_sz; - mlx5e_build_rq_param(priv, params, &cparam->rq); + mlx5e_build_rq_param(priv, params, NULL, &cparam->rq); icosq_log_wq_sz = mlx5e_build_icosq_log_wq_sz(params, &cparam->rq); mlx5e_build_sq_param(priv, params, &cparam->sq); mlx5e_build_xdpsq_param(priv, params, &cparam->xdp_sq); mlx5e_build_icosq_param(priv, icosq_log_wq_sz, &cparam->icosq); - mlx5e_build_rx_cq_param(priv, params, &cparam->rx_cq); + mlx5e_build_rx_cq_param(priv, params, NULL, &cparam->rx_cq); mlx5e_build_tx_cq_param(priv, params, &cparam->tx_cq); mlx5e_build_ico_cq_param(priv, icosq_log_wq_sz, &cparam->icosq_cq); } @@ -2224,7 +2304,12 @@ int mlx5e_open_channels(struct mlx5e_priv *priv, mlx5e_build_channel_param(priv, &chs->params, cparam); for (i = 0; i < chs->num; i++) { - err = mlx5e_open_channel(priv, i, &chs->params, cparam, &chs->c[i]); + struct xdp_umem *umem = NULL; + + if (chs->params.xdp_prog) + umem = mlx5e_xsk_get_umem(&chs->params, chs->params.xsk, i); + + err = mlx5e_open_channel(priv, i, &chs->params, cparam, umem, &chs->c[i]); if (err) goto err_close_channels; } @@ -2266,6 +2351,10 @@ static int mlx5e_wait_channels_min_rx_wqes(struct mlx5e_channels *chs) int timeout = err ? 0 : MLX5E_RQ_WQES_TIMEOUT; err |= mlx5e_wait_for_min_rx_wqes(&chs->c[i]->rq, timeout); + + /* Don't wait on the XSK RQ, because the newer xdpsock sample + * doesn't provide any Fill Ring entries at the setup stage. + */ } return err ? -ETIMEDOUT : 0; @@ -2338,35 +2427,35 @@ int mlx5e_create_indirect_rqt(struct mlx5e_priv *priv) return err; } -int mlx5e_create_direct_rqts(struct mlx5e_priv *priv) +int mlx5e_create_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs) { - struct mlx5e_rqt *rqt; + const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); int err; int ix; - for (ix = 0; ix < mlx5e_get_netdev_max_channels(priv->netdev); ix++) { - rqt = &priv->direct_tir[ix].rqt; - err = mlx5e_create_rqt(priv, 1 /*size */, rqt); - if (err) + for (ix = 0; ix < max_nch; ix++) { + err = mlx5e_create_rqt(priv, 1 /*size */, &tirs[ix].rqt); + if (unlikely(err)) goto err_destroy_rqts; } return 0; err_destroy_rqts: - mlx5_core_warn(priv->mdev, "create direct rqts failed, %d\n", err); + mlx5_core_warn(priv->mdev, "create rqts failed, %d\n", err); for (ix--; ix >= 0; ix--) - mlx5e_destroy_rqt(priv, &priv->direct_tir[ix].rqt); + mlx5e_destroy_rqt(priv, &tirs[ix].rqt); return err; } -void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv) +void mlx5e_destroy_direct_rqts(struct mlx5e_priv *priv, struct mlx5e_tir *tirs) { + const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); int i; - for (i = 0; i < mlx5e_get_netdev_max_channels(priv->netdev); i++) - mlx5e_destroy_rqt(priv, &priv->direct_tir[i].rqt); + for (i = 0; i < max_nch; i++) + mlx5e_destroy_rqt(priv, &tirs[i].rqt); } static int mlx5e_rx_hash_fn(int hfunc) @@ -2786,11 +2875,12 @@ static void mlx5e_build_tx2sq_maps(struct mlx5e_priv *priv) void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) { int num_txqs = priv->channels.num * priv->channels.params.num_tc; + int num_rxqs = priv->channels.num * MLX5E_NUM_RQ_GROUPS; struct net_device *netdev = priv->netdev; mlx5e_netdev_set_tcs(netdev); netif_set_real_num_tx_queues(netdev, num_txqs); - netif_set_real_num_rx_queues(netdev, priv->channels.num); + netif_set_real_num_rx_queues(netdev, num_rxqs); mlx5e_build_tx2sq_maps(priv); mlx5e_activate_channels(&priv->channels); @@ -2802,10 +2892,14 @@ void mlx5e_activate_priv_channels(struct mlx5e_priv *priv) mlx5e_wait_channels_min_rx_wqes(&priv->channels); mlx5e_redirect_rqts_to_channels(priv, &priv->channels); + + mlx5e_xsk_redirect_rqts_to_channels(priv, &priv->channels); } void mlx5e_deactivate_priv_channels(struct mlx5e_priv *priv) { + mlx5e_xsk_redirect_rqts_to_drop(priv, &priv->channels); + mlx5e_redirect_rqts_to_drop(priv); if (mlx5e_is_vport_rep(priv)) @@ -2884,9 +2978,12 @@ void mlx5e_timestamp_init(struct mlx5e_priv *priv) int mlx5e_open_locked(struct net_device *netdev) { struct mlx5e_priv *priv = netdev_priv(netdev); + bool is_xdp = priv->channels.params.xdp_prog; int err; set_bit(MLX5E_STATE_OPENED, &priv->state); + if (is_xdp) + mlx5e_xdp_set_open(priv); err = mlx5e_open_channels(priv, &priv->channels); if (err) @@ -2901,6 +2998,8 @@ int mlx5e_open_locked(struct net_device *netdev) return 0; err_clear_state_opened_flag: + if (is_xdp) + mlx5e_xdp_set_closed(priv); clear_bit(MLX5E_STATE_OPENED, &priv->state); return err; } @@ -2932,6 +3031,8 @@ int mlx5e_close_locked(struct net_device *netdev) if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) return 0; + if (priv->channels.params.xdp_prog) + mlx5e_xdp_set_closed(priv); clear_bit(MLX5E_STATE_OPENED, &priv->state); netif_carrier_off(priv->netdev); @@ -3188,13 +3289,13 @@ err_destroy_inner_tirs: return err; } -int mlx5e_create_direct_tirs(struct mlx5e_priv *priv) +int mlx5e_create_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs) { - int nch = mlx5e_get_netdev_max_channels(priv->netdev); + const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); struct mlx5e_tir *tir; void *tirc; int inlen; - int err; + int err = 0; u32 *in; int ix; @@ -3203,25 +3304,24 @@ int mlx5e_create_direct_tirs(struct mlx5e_priv *priv) if (!in) return -ENOMEM; - for (ix = 0; ix < nch; ix++) { + for (ix = 0; ix < max_nch; ix++) { memset(in, 0, inlen); - tir = &priv->direct_tir[ix]; + tir = &tirs[ix]; tirc = MLX5_ADDR_OF(create_tir_in, in, ctx); - mlx5e_build_direct_tir_ctx(priv, priv->direct_tir[ix].rqt.rqtn, tirc); + mlx5e_build_direct_tir_ctx(priv, tir->rqt.rqtn, tirc); err = mlx5e_create_tir(priv->mdev, tir, in, inlen); - if (err) + if (unlikely(err)) goto err_destroy_ch_tirs; } - kvfree(in); - - return 0; + goto out; err_destroy_ch_tirs: - mlx5_core_warn(priv->mdev, "create direct tirs failed, %d\n", err); + mlx5_core_warn(priv->mdev, "create tirs failed, %d\n", err); for (ix--; ix >= 0; ix--) - mlx5e_destroy_tir(priv->mdev, &priv->direct_tir[ix]); + mlx5e_destroy_tir(priv->mdev, &tirs[ix]); +out: kvfree(in); return err; @@ -3241,13 +3341,13 @@ void mlx5e_destroy_indirect_tirs(struct mlx5e_priv *priv, bool inner_ttc) mlx5e_destroy_tir(priv->mdev, &priv->inner_indir_tir[i]); } -void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv) +void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv, struct mlx5e_tir *tirs) { - int nch = mlx5e_get_netdev_max_channels(priv->netdev); + const int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); int i; - for (i = 0; i < nch; i++) - mlx5e_destroy_tir(priv->mdev, &priv->direct_tir[i]); + for (i = 0; i < max_nch; i++) + mlx5e_destroy_tir(priv->mdev, &tirs[i]); } static int mlx5e_modify_channels_scatter_fcs(struct mlx5e_channels *chs, bool enable) @@ -3389,11 +3489,12 @@ void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s) for (i = 0; i < mlx5e_get_netdev_max_channels(priv->netdev); i++) { struct mlx5e_channel_stats *channel_stats = &priv->channel_stats[i]; + struct mlx5e_rq_stats *xskrq_stats = &channel_stats->xskrq; struct mlx5e_rq_stats *rq_stats = &channel_stats->rq; int j; - s->rx_packets += rq_stats->packets; - s->rx_bytes += rq_stats->bytes; + s->rx_packets += rq_stats->packets + xskrq_stats->packets; + s->rx_bytes += rq_stats->bytes + xskrq_stats->bytes; for (j = 0; j < priv->max_opened_tc; j++) { struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j]; @@ -3492,6 +3593,13 @@ static int set_feature_lro(struct net_device *netdev, bool enable) mutex_lock(&priv->state_lock); + if (enable && priv->xsk.refcnt) { + netdev_warn(netdev, "LRO is incompatible with AF_XDP (%hu XSKs are active)\n", + priv->xsk.refcnt); + err = -EINVAL; + goto out; + } + old_params = &priv->channels.params; if (enable && !MLX5E_GET_PFLAG(old_params, MLX5E_PFLAG_RX_STRIDING_RQ)) { netdev_warn(netdev, "can't set LRO with legacy RQ\n"); @@ -3505,8 +3613,8 @@ static int set_feature_lro(struct net_device *netdev, bool enable) new_channels.params.lro_en = enable; if (old_params->rq_wq_type != MLX5_WQ_TYPE_CYCLIC) { - if (mlx5e_rx_mpwqe_is_linear_skb(mdev, old_params) == - mlx5e_rx_mpwqe_is_linear_skb(mdev, &new_channels.params)) + if (mlx5e_rx_mpwqe_is_linear_skb(mdev, old_params, NULL) == + mlx5e_rx_mpwqe_is_linear_skb(mdev, &new_channels.params, NULL)) reset = false; } @@ -3696,6 +3804,43 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev, return features; } +static bool mlx5e_xsk_validate_mtu(struct net_device *netdev, + struct mlx5e_channels *chs, + struct mlx5e_params *new_params, + struct mlx5_core_dev *mdev) +{ + u16 ix; + + for (ix = 0; ix < chs->params.num_channels; ix++) { + struct xdp_umem *umem = mlx5e_xsk_get_umem(&chs->params, chs->params.xsk, ix); + struct mlx5e_xsk_param xsk; + + if (!umem) + continue; + + mlx5e_build_xsk_param(umem, &xsk); + + if (!mlx5e_validate_xsk_param(new_params, &xsk, mdev)) { + u32 hr = mlx5e_get_linear_rq_headroom(new_params, &xsk); + int max_mtu_frame, max_mtu_page, max_mtu; + + /* Two criteria must be met: + * 1. HW MTU + all headrooms <= XSK frame size. + * 2. Size of SKBs allocated on XDP_PASS <= PAGE_SIZE. + */ + max_mtu_frame = MLX5E_HW2SW_MTU(new_params, xsk.chunk_size - hr); + max_mtu_page = mlx5e_xdp_max_mtu(new_params, &xsk); + max_mtu = min(max_mtu_frame, max_mtu_page); + + netdev_err(netdev, "MTU %d is too big for an XSK running on channel %hu. Try MTU <= %d\n", + new_params->sw_mtu, ix, max_mtu); + return false; + } + } + + return true; +} + int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, change_hw_mtu_cb set_mtu_cb) { @@ -3716,18 +3861,31 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu, new_channels.params.sw_mtu = new_mtu; if (params->xdp_prog && - !mlx5e_rx_is_linear_skb(&new_channels.params)) { + !mlx5e_rx_is_linear_skb(&new_channels.params, NULL)) { netdev_err(netdev, "MTU(%d) > %d is not allowed while XDP enabled\n", - new_mtu, mlx5e_xdp_max_mtu(params)); + new_mtu, mlx5e_xdp_max_mtu(params, NULL)); + err = -EINVAL; + goto out; + } + + if (priv->xsk.refcnt && + !mlx5e_xsk_validate_mtu(netdev, &priv->channels, + &new_channels.params, priv->mdev)) { err = -EINVAL; goto out; } if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { - bool is_linear = mlx5e_rx_mpwqe_is_linear_skb(priv->mdev, &new_channels.params); - u8 ppw_old = mlx5e_mpwqe_log_pkts_per_wqe(params); - u8 ppw_new = mlx5e_mpwqe_log_pkts_per_wqe(&new_channels.params); + bool is_linear = mlx5e_rx_mpwqe_is_linear_skb(priv->mdev, + &new_channels.params, + NULL); + u8 ppw_old = mlx5e_mpwqe_log_pkts_per_wqe(params, NULL); + u8 ppw_new = mlx5e_mpwqe_log_pkts_per_wqe(&new_channels.params, NULL); + + /* If XSK is active, XSK RQs are linear. */ + is_linear |= priv->xsk.refcnt; + /* Always reset in linear mode - hw_mtu is used in data path. */ reset = reset && (is_linear || (ppw_old != ppw_new)); } @@ -4160,16 +4318,29 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog) new_channels.params = priv->channels.params; new_channels.params.xdp_prog = prog; - if (!mlx5e_rx_is_linear_skb(&new_channels.params)) { + /* No XSK params: AF_XDP can't be enabled yet at the point of setting + * the XDP program. + */ + if (!mlx5e_rx_is_linear_skb(&new_channels.params, NULL)) { netdev_warn(netdev, "XDP is not allowed with MTU(%d) > %d\n", new_channels.params.sw_mtu, - mlx5e_xdp_max_mtu(&new_channels.params)); + mlx5e_xdp_max_mtu(&new_channels.params, NULL)); return -EINVAL; } return 0; } +static int mlx5e_xdp_update_state(struct mlx5e_priv *priv) +{ + if (priv->channels.params.xdp_prog) + mlx5e_xdp_set_open(priv); + else + mlx5e_xdp_set_closed(priv); + + return 0; +} + static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) { struct mlx5e_priv *priv = netdev_priv(netdev); @@ -4190,8 +4361,6 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) /* no need for full reset when exchanging programs */ reset = (!priv->channels.params.xdp_prog || !prog); - if (was_opened && reset) - mlx5e_close_locked(netdev); if (was_opened && !reset) { /* num_channels is invariant here, so we can take the * batched reference right upfront. @@ -4203,20 +4372,31 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) } } - /* exchange programs, extra prog reference we got from caller - * as long as we don't fail from this point onwards. - */ - old_prog = xchg(&priv->channels.params.xdp_prog, prog); + if (was_opened && reset) { + struct mlx5e_channels new_channels = {}; + + new_channels.params = priv->channels.params; + new_channels.params.xdp_prog = prog; + mlx5e_set_rq_type(priv->mdev, &new_channels.params); + old_prog = priv->channels.params.xdp_prog; + + err = mlx5e_safe_switch_channels(priv, &new_channels, mlx5e_xdp_update_state); + if (err) + goto unlock; + } else { + /* exchange programs, extra prog reference we got from caller + * as long as we don't fail from this point onwards. + */ + old_prog = xchg(&priv->channels.params.xdp_prog, prog); + } + if (old_prog) bpf_prog_put(old_prog); - if (reset) /* change RQ type according to priv->xdp_prog */ + if (!was_opened && reset) /* change RQ type according to priv->xdp_prog */ mlx5e_set_rq_type(priv->mdev, &priv->channels.params); - if (was_opened && reset) - err = mlx5e_open_locked(netdev); - - if (!test_bit(MLX5E_STATE_OPENED, &priv->state) || reset) + if (!was_opened || reset) goto unlock; /* exchanging programs w/o reset, we update ref counts on behalf @@ -4224,19 +4404,29 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog) */ for (i = 0; i < priv->channels.num; i++) { struct mlx5e_channel *c = priv->channels.c[i]; + bool xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state); clear_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state); + if (xsk_open) + clear_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state); napi_synchronize(&c->napi); /* prevent mlx5e_poll_rx_cq from accessing rq->xdp_prog */ old_prog = xchg(&c->rq.xdp_prog, prog); + if (old_prog) + bpf_prog_put(old_prog); + + if (xsk_open) { + old_prog = xchg(&c->xskrq.xdp_prog, prog); + if (old_prog) + bpf_prog_put(old_prog); + } set_bit(MLX5E_RQ_STATE_ENABLED, &c->rq.state); + if (xsk_open) + set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state); /* napi_schedule in case we have missed anything */ napi_schedule(&c->napi); - - if (old_prog) - bpf_prog_put(old_prog); } unlock: @@ -4267,6 +4457,9 @@ static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp) case XDP_QUERY_PROG: xdp->prog_id = mlx5e_xdp_query(dev); return 0; + case XDP_SETUP_XSK_UMEM: + return mlx5e_xsk_setup_umem(dev, xdp->xsk.umem, + xdp->xsk.queue_id); default: return -EINVAL; } @@ -4349,6 +4542,7 @@ const struct net_device_ops mlx5e_netdev_ops = { .ndo_tx_timeout = mlx5e_tx_timeout, .ndo_bpf = mlx5e_xdp, .ndo_xdp_xmit = mlx5e_xdp_xmit, + .ndo_xsk_async_xmit = mlx5e_xsk_async_xmit, #ifdef CONFIG_MLX5_EN_ARFS .ndo_rx_flow_steer = mlx5e_rx_flow_steer, #endif @@ -4500,11 +4694,13 @@ void mlx5e_build_rq_params(struct mlx5_core_dev *mdev, * - Striding RQ configuration is not possible/supported. * - Slow PCI heuristic. * - Legacy RQ would use linear SKB while Striding RQ would use non-linear. + * + * No XSK params: checking the availability of striding RQ in general. */ if (!slow_pci_heuristic(mdev) && mlx5e_striding_rq_possible(mdev, params) && - (mlx5e_rx_mpwqe_is_linear_skb(mdev, params) || - !mlx5e_rx_is_linear_skb(params))) + (mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL) || + !mlx5e_rx_is_linear_skb(params, NULL))) MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ, true); mlx5e_set_rq_type(mdev, params); mlx5e_init_rq_type_params(mdev, params); @@ -4526,6 +4722,7 @@ void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params, } void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, + struct mlx5e_xsk *xsk, struct mlx5e_rss_params *rss_params, struct mlx5e_params *params, u16 max_channels, u16 mtu) @@ -4561,9 +4758,11 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, /* HW LRO */ /* TODO: && MLX5_CAP_ETH(mdev, lro_cap) */ - if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) - if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params)) + if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) { + /* No XSK params: checking the availability of striding RQ in general. */ + if (!mlx5e_rx_mpwqe_is_linear_skb(mdev, params, NULL)) params->lro_en = !slow_pci_heuristic(mdev); + } params->lro_timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT); /* CQ moderation params */ @@ -4582,6 +4781,9 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, mlx5e_build_rss_params(rss_params, params->num_channels); params->tunneled_offload_en = mlx5e_tunnel_inner_ft_supported(mdev); + + /* AF_XDP */ + params->xsk = xsk; } static void mlx5e_set_netdev_dev_addr(struct net_device *netdev) @@ -4757,7 +4959,7 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, if (err) return err; - mlx5e_build_nic_params(mdev, rss, &priv->channels.params, + mlx5e_build_nic_params(mdev, &priv->xsk, rss, &priv->channels.params, mlx5e_get_netdev_max_channels(netdev), netdev->mtu); @@ -4799,7 +5001,7 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) if (err) goto err_close_drop_rq; - err = mlx5e_create_direct_rqts(priv); + err = mlx5e_create_direct_rqts(priv, priv->direct_tir); if (err) goto err_destroy_indirect_rqts; @@ -4807,14 +5009,22 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) if (err) goto err_destroy_direct_rqts; - err = mlx5e_create_direct_tirs(priv); + err = mlx5e_create_direct_tirs(priv, priv->direct_tir); if (err) goto err_destroy_indirect_tirs; + err = mlx5e_create_direct_rqts(priv, priv->xsk_tir); + if (unlikely(err)) + goto err_destroy_direct_tirs; + + err = mlx5e_create_direct_tirs(priv, priv->xsk_tir); + if (unlikely(err)) + goto err_destroy_xsk_rqts; + err = mlx5e_create_flow_steering(priv); if (err) { mlx5_core_warn(mdev, "create flow steering failed, %d\n", err); - goto err_destroy_direct_tirs; + goto err_destroy_xsk_tirs; } err = mlx5e_tc_nic_init(priv); @@ -4825,12 +5035,16 @@ static int mlx5e_init_nic_rx(struct mlx5e_priv *priv) err_destroy_flow_steering: mlx5e_destroy_flow_steering(priv); +err_destroy_xsk_tirs: + mlx5e_destroy_direct_tirs(priv, priv->xsk_tir); +err_destroy_xsk_rqts: + mlx5e_destroy_direct_rqts(priv, priv->xsk_tir); err_destroy_direct_tirs: - mlx5e_destroy_direct_tirs(priv); + mlx5e_destroy_direct_tirs(priv, priv->direct_tir); err_destroy_indirect_tirs: mlx5e_destroy_indirect_tirs(priv, true); err_destroy_direct_rqts: - mlx5e_destroy_direct_rqts(priv); + mlx5e_destroy_direct_rqts(priv, priv->direct_tir); err_destroy_indirect_rqts: mlx5e_destroy_rqt(priv, &priv->indir_rqt); err_close_drop_rq: @@ -4844,9 +5058,11 @@ static void mlx5e_cleanup_nic_rx(struct mlx5e_priv *priv) { mlx5e_tc_nic_cleanup(priv); mlx5e_destroy_flow_steering(priv); - mlx5e_destroy_direct_tirs(priv); + mlx5e_destroy_direct_tirs(priv, priv->xsk_tir); + mlx5e_destroy_direct_rqts(priv, priv->xsk_tir); + mlx5e_destroy_direct_tirs(priv, priv->direct_tir); mlx5e_destroy_indirect_tirs(priv, true); - mlx5e_destroy_direct_rqts(priv); + mlx5e_destroy_direct_rqts(priv, priv->direct_tir); mlx5e_destroy_rqt(priv, &priv->indir_rqt); mlx5e_close_drop_rq(&priv->drop_rq); mlx5e_destroy_q_counters(priv); @@ -5002,7 +5218,7 @@ struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev, netdev = alloc_etherdev_mqs(sizeof(struct mlx5e_priv), nch * profile->max_tc, - nch); + nch * MLX5E_NUM_RQ_GROUPS); if (!netdev) { mlx5_core_err(mdev, "alloc_etherdev_mqs() failed\n"); return NULL; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index 330034fcdfc5..6a013a8c1150 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -1510,7 +1510,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) if (err) goto err_close_drop_rq; - err = mlx5e_create_direct_rqts(priv); + err = mlx5e_create_direct_rqts(priv, priv->direct_tir); if (err) goto err_destroy_indirect_rqts; @@ -1518,7 +1518,7 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) if (err) goto err_destroy_direct_rqts; - err = mlx5e_create_direct_tirs(priv); + err = mlx5e_create_direct_tirs(priv, priv->direct_tir); if (err) goto err_destroy_indirect_tirs; @@ -1535,11 +1535,11 @@ static int mlx5e_init_rep_rx(struct mlx5e_priv *priv) err_destroy_ttc_table: mlx5e_destroy_ttc_table(priv, &priv->fs.ttc); err_destroy_direct_tirs: - mlx5e_destroy_direct_tirs(priv); + mlx5e_destroy_direct_tirs(priv, priv->direct_tir); err_destroy_indirect_tirs: mlx5e_destroy_indirect_tirs(priv, false); err_destroy_direct_rqts: - mlx5e_destroy_direct_rqts(priv); + mlx5e_destroy_direct_rqts(priv, priv->direct_tir); err_destroy_indirect_rqts: mlx5e_destroy_rqt(priv, &priv->indir_rqt); err_close_drop_rq: @@ -1553,9 +1553,9 @@ static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv) mlx5_del_flow_rules(rpriv->vport_rx_rule); mlx5e_destroy_ttc_table(priv, &priv->fs.ttc); - mlx5e_destroy_direct_tirs(priv); + mlx5e_destroy_direct_tirs(priv, priv->direct_tir); mlx5e_destroy_indirect_tirs(priv, false); - mlx5e_destroy_direct_rqts(priv); + mlx5e_destroy_direct_rqts(priv, priv->direct_tir); mlx5e_destroy_rqt(priv, &priv->indir_rqt); mlx5e_close_drop_rq(&priv->drop_rq); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 234a3fd39901..56a2f4666c47 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -47,6 +47,7 @@ #include "en_accel/tls_rxtx.h" #include "lib/clock.h" #include "en/xdp.h" +#include "en/xsk/rx.h" static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config) { @@ -235,8 +236,8 @@ static inline bool mlx5e_rx_cache_get(struct mlx5e_rq *rq, return true; } -static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq, - struct mlx5e_dma_info *dma_info) +static inline int mlx5e_page_alloc_pool(struct mlx5e_rq *rq, + struct mlx5e_dma_info *dma_info) { if (mlx5e_rx_cache_get(rq, dma_info)) return 0; @@ -256,13 +257,23 @@ static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq, return 0; } +static inline int mlx5e_page_alloc(struct mlx5e_rq *rq, + struct mlx5e_dma_info *dma_info) +{ + if (rq->umem) + return mlx5e_xsk_page_alloc_umem(rq, dma_info); + else + return mlx5e_page_alloc_pool(rq, dma_info); +} + void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info) { dma_unmap_page(rq->pdev, dma_info->addr, PAGE_SIZE, rq->buff.map_dir); } -void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info, - bool recycle) +void mlx5e_page_release_dynamic(struct mlx5e_rq *rq, + struct mlx5e_dma_info *dma_info, + bool recycle) { if (likely(recycle)) { if (mlx5e_rx_cache_put(rq, dma_info)) @@ -277,6 +288,20 @@ void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info, } } +static inline void mlx5e_page_release(struct mlx5e_rq *rq, + struct mlx5e_dma_info *dma_info, + bool recycle) +{ + if (rq->umem) + /* The `recycle` parameter is ignored, and the page is always + * put into the Reuse Ring, because there is no way to return + * the page to the userspace when the interface goes down. + */ + mlx5e_xsk_page_release(rq, dma_info); + else + mlx5e_page_release_dynamic(rq, dma_info, recycle); +} + static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *frag) { @@ -288,7 +313,7 @@ static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq, * offset) should just use the new one without replenishing again * by themselves. */ - err = mlx5e_page_alloc_mapped(rq, frag->di); + err = mlx5e_page_alloc(rq, frag->di); return err; } @@ -354,6 +379,13 @@ static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, u8 wqe_bulk) int err; int i; + if (rq->umem) { + int pages_desired = wqe_bulk << rq->wqe.info.log_num_frags; + + if (unlikely(!mlx5e_xsk_pages_enough_umem(rq, pages_desired))) + return -ENOMEM; + } + for (i = 0; i < wqe_bulk; i++) { struct mlx5e_rx_wqe_cyc *wqe = mlx5_wq_cyc_get_wqe(wq, ix + i); @@ -401,11 +433,17 @@ mlx5e_copy_skb_header(struct device *pdev, struct sk_buff *skb, static void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, bool recycle) { - const bool no_xdp_xmit = - bitmap_empty(wi->xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE); + bool no_xdp_xmit; struct mlx5e_dma_info *dma_info = wi->umr.dma_info; int i; + /* A common case for AF_XDP. */ + if (bitmap_full(wi->xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE)) + return; + + no_xdp_xmit = bitmap_empty(wi->xdp_xmit_bitmap, + MLX5_MPWRQ_PAGES_PER_WQE); + for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++) if (no_xdp_xmit || !test_bit(i, wi->xdp_xmit_bitmap)) mlx5e_page_release(rq, &dma_info[i], recycle); @@ -427,11 +465,6 @@ static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq, u8 n) mlx5_wq_ll_update_db_record(wq); } -static inline u16 mlx5e_icosq_wrap_cnt(struct mlx5e_icosq *sq) -{ - return mlx5_wq_cyc_get_ctr_wrap_cnt(&sq->wq, sq->pc); -} - static inline void mlx5e_fill_icosq_frag_edge(struct mlx5e_icosq *sq, struct mlx5_wq_cyc *wq, u16 pi, u16 nnops) @@ -459,6 +492,12 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) int err; int i; + if (rq->umem && + unlikely(!mlx5e_xsk_pages_enough_umem(rq, MLX5_MPWRQ_PAGES_PER_WQE))) { + err = -ENOMEM; + goto err; + } + pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); contig_wqebbs_room = mlx5_wq_cyc_get_contig_wqebbs(wq, pi); if (unlikely(contig_wqebbs_room < MLX5E_UMR_WQEBBS)) { @@ -467,12 +506,10 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) } umr_wqe = mlx5_wq_cyc_get_wqe(wq, pi); - if (unlikely(mlx5e_icosq_wrap_cnt(sq) < 2)) - memcpy(umr_wqe, &rq->mpwqe.umr_wqe, - offsetof(struct mlx5e_umr_wqe, inline_mtts)); + memcpy(umr_wqe, &rq->mpwqe.umr_wqe, offsetof(struct mlx5e_umr_wqe, inline_mtts)); for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++, dma_info++) { - err = mlx5e_page_alloc_mapped(rq, dma_info); + err = mlx5e_page_alloc(rq, dma_info); if (unlikely(err)) goto err_unmap; umr_wqe->inline_mtts[i].ptag = cpu_to_be64(dma_info->addr | MLX5_EN_WR); @@ -487,6 +524,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix) umr_wqe->uctrl.xlt_offset = cpu_to_be16(xlt_offset); sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR; + sq->db.ico_wqe[pi].umr.rq = rq; sq->pc += MLX5E_UMR_WQEBBS; sq->doorbell_cseg = &umr_wqe->ctrl; @@ -498,6 +536,8 @@ err_unmap: dma_info--; mlx5e_page_release(rq, dma_info, true); } + +err: rq->stats->buff_alloc_err++; return err; @@ -544,11 +584,10 @@ bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq) return !!err; } -static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq) +void mlx5e_poll_ico_cq(struct mlx5e_cq *cq) { struct mlx5e_icosq *sq = container_of(cq, struct mlx5e_icosq, cq); struct mlx5_cqe64 *cqe; - u8 completed_umr = 0; u16 sqcc; int i; @@ -589,7 +628,7 @@ static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq) if (likely(wi->opcode == MLX5_OPCODE_UMR)) { sqcc += MLX5E_UMR_WQEBBS; - completed_umr++; + wi->umr.rq->mpwqe.umr_completed++; } else if (likely(wi->opcode == MLX5_OPCODE_NOP)) { sqcc++; } else { @@ -605,24 +644,25 @@ static void mlx5e_poll_ico_cq(struct mlx5e_cq *cq, struct mlx5e_rq *rq) sq->cc = sqcc; mlx5_cqwq_update_db_record(&cq->wq); - - if (likely(completed_umr)) { - mlx5e_post_rx_mpwqe(rq, completed_umr); - rq->mpwqe.umr_in_progress -= completed_umr; - } } bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq) { struct mlx5e_icosq *sq = &rq->channel->icosq; struct mlx5_wq_ll *wq = &rq->mpwqe.wq; + u8 umr_completed = rq->mpwqe.umr_completed; + int alloc_err = 0; u8 missing, i; u16 head; if (unlikely(!test_bit(MLX5E_RQ_STATE_ENABLED, &rq->state))) return false; - mlx5e_poll_ico_cq(&sq->cq, rq); + if (umr_completed) { + mlx5e_post_rx_mpwqe(rq, umr_completed); + rq->mpwqe.umr_in_progress -= umr_completed; + rq->mpwqe.umr_completed = 0; + } missing = mlx5_wq_ll_missing(wq) - rq->mpwqe.umr_in_progress; @@ -636,7 +676,9 @@ bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq) head = rq->mpwqe.actual_wq_head; i = missing; do { - if (unlikely(mlx5e_alloc_rx_mpwqe(rq, head))) + alloc_err = mlx5e_alloc_rx_mpwqe(rq, head); + + if (unlikely(alloc_err)) break; head = mlx5_wq_ll_get_wqe_next_ix(wq, head); } while (--i); @@ -650,6 +692,12 @@ bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq) rq->mpwqe.umr_in_progress += rq->mpwqe.umr_last_bulk; rq->mpwqe.actual_wq_head = head; + /* If XSK Fill Ring doesn't have enough frames, busy poll by + * rescheduling the NAPI poll. + */ + if (unlikely(alloc_err == -ENOMEM && rq->umem)) + return true; + return false; } @@ -1018,7 +1066,7 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, } rcu_read_lock(); - consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt); + consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt, false); rcu_read_unlock(); if (consumed) return NULL; /* page/packet was consumed by XDP */ @@ -1235,7 +1283,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, prefetch(data); rcu_read_lock(); - consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt32); + consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt32, false); rcu_read_unlock(); if (consumed) { if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 483d321d2151..5f540db47cc9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -104,7 +104,33 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_poll) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_arm) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_aff_change) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_force_irq) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_eq_rearm) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_packets) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_bytes) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_csum_complete) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_csum_unnecessary) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_csum_unnecessary_inner) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_csum_none) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_ecn_mark) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_removed_vlan_packets) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_xdp_drop) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_xdp_redirect) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_wqe_err) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_mpwqe_filler_cqes) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_mpwqe_filler_strides) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_oversize_pkts_sw_drop) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_buff_alloc_err) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_cqe_compress_blks) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_cqe_compress_pkts) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_congst_umr) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xsk_arfs_err) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xsk_xmit) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xsk_mpwqe) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xsk_inlnw) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xsk_full) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xsk_err) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xsk_cqes) }, }; #define NUM_SW_COUNTERS ARRAY_SIZE(sw_stats_desc) @@ -144,6 +170,8 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) &priv->channel_stats[i]; struct mlx5e_xdpsq_stats *xdpsq_red_stats = &channel_stats->xdpsq; struct mlx5e_xdpsq_stats *xdpsq_stats = &channel_stats->rq_xdpsq; + struct mlx5e_xdpsq_stats *xsksq_stats = &channel_stats->xsksq; + struct mlx5e_rq_stats *xskrq_stats = &channel_stats->xskrq; struct mlx5e_rq_stats *rq_stats = &channel_stats->rq; struct mlx5e_ch_stats *ch_stats = &channel_stats->ch; int j; @@ -186,6 +214,7 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->ch_poll += ch_stats->poll; s->ch_arm += ch_stats->arm; s->ch_aff_change += ch_stats->aff_change; + s->ch_force_irq += ch_stats->force_irq; s->ch_eq_rearm += ch_stats->eq_rearm; /* xdp redirect */ s->tx_xdp_xmit += xdpsq_red_stats->xmit; @@ -194,6 +223,32 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->tx_xdp_full += xdpsq_red_stats->full; s->tx_xdp_err += xdpsq_red_stats->err; s->tx_xdp_cqes += xdpsq_red_stats->cqes; + /* AF_XDP zero-copy */ + s->rx_xsk_packets += xskrq_stats->packets; + s->rx_xsk_bytes += xskrq_stats->bytes; + s->rx_xsk_csum_complete += xskrq_stats->csum_complete; + s->rx_xsk_csum_unnecessary += xskrq_stats->csum_unnecessary; + s->rx_xsk_csum_unnecessary_inner += xskrq_stats->csum_unnecessary_inner; + s->rx_xsk_csum_none += xskrq_stats->csum_none; + s->rx_xsk_ecn_mark += xskrq_stats->ecn_mark; + s->rx_xsk_removed_vlan_packets += xskrq_stats->removed_vlan_packets; + s->rx_xsk_xdp_drop += xskrq_stats->xdp_drop; + s->rx_xsk_xdp_redirect += xskrq_stats->xdp_redirect; + s->rx_xsk_wqe_err += xskrq_stats->wqe_err; + s->rx_xsk_mpwqe_filler_cqes += xskrq_stats->mpwqe_filler_cqes; + s->rx_xsk_mpwqe_filler_strides += xskrq_stats->mpwqe_filler_strides; + s->rx_xsk_oversize_pkts_sw_drop += xskrq_stats->oversize_pkts_sw_drop; + s->rx_xsk_buff_alloc_err += xskrq_stats->buff_alloc_err; + s->rx_xsk_cqe_compress_blks += xskrq_stats->cqe_compress_blks; + s->rx_xsk_cqe_compress_pkts += xskrq_stats->cqe_compress_pkts; + s->rx_xsk_congst_umr += xskrq_stats->congst_umr; + s->rx_xsk_arfs_err += xskrq_stats->arfs_err; + s->tx_xsk_xmit += xsksq_stats->xmit; + s->tx_xsk_mpwqe += xsksq_stats->mpwqe; + s->tx_xsk_inlnw += xsksq_stats->inlnw; + s->tx_xsk_full += xsksq_stats->full; + s->tx_xsk_err += xsksq_stats->err; + s->tx_xsk_cqes += xsksq_stats->cqes; for (j = 0; j < priv->max_opened_tc; j++) { struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j]; @@ -1266,11 +1321,43 @@ static const struct counter_desc xdpsq_stats_desc[] = { { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) }, }; +static const struct counter_desc xskrq_stats_desc[] = { + { MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, packets) }, + { MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, bytes) }, + { MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, csum_complete) }, + { MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, csum_unnecessary) }, + { MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) }, + { MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, csum_none) }, + { MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, ecn_mark) }, + { MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, removed_vlan_packets) }, + { MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, xdp_drop) }, + { MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, xdp_redirect) }, + { MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, wqe_err) }, + { MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, mpwqe_filler_cqes) }, + { MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, mpwqe_filler_strides) }, + { MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, oversize_pkts_sw_drop) }, + { MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, buff_alloc_err) }, + { MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, cqe_compress_blks) }, + { MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) }, + { MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, congst_umr) }, + { MLX5E_DECLARE_XSKRQ_STAT(struct mlx5e_rq_stats, arfs_err) }, +}; + +static const struct counter_desc xsksq_stats_desc[] = { + { MLX5E_DECLARE_XSKSQ_STAT(struct mlx5e_xdpsq_stats, xmit) }, + { MLX5E_DECLARE_XSKSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) }, + { MLX5E_DECLARE_XSKSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) }, + { MLX5E_DECLARE_XSKSQ_STAT(struct mlx5e_xdpsq_stats, full) }, + { MLX5E_DECLARE_XSKSQ_STAT(struct mlx5e_xdpsq_stats, err) }, + { MLX5E_DECLARE_XSKSQ_STAT(struct mlx5e_xdpsq_stats, cqes) }, +}; + static const struct counter_desc ch_stats_desc[] = { { MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, events) }, { MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, poll) }, { MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, arm) }, { MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, aff_change) }, + { MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, force_irq) }, { MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, eq_rearm) }, }; @@ -1278,6 +1365,8 @@ static const struct counter_desc ch_stats_desc[] = { #define NUM_SQ_STATS ARRAY_SIZE(sq_stats_desc) #define NUM_XDPSQ_STATS ARRAY_SIZE(xdpsq_stats_desc) #define NUM_RQ_XDPSQ_STATS ARRAY_SIZE(rq_xdpsq_stats_desc) +#define NUM_XSKRQ_STATS ARRAY_SIZE(xskrq_stats_desc) +#define NUM_XSKSQ_STATS ARRAY_SIZE(xsksq_stats_desc) #define NUM_CH_STATS ARRAY_SIZE(ch_stats_desc) static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv) @@ -1288,13 +1377,16 @@ static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv) (NUM_CH_STATS * max_nch) + (NUM_SQ_STATS * max_nch * priv->max_opened_tc) + (NUM_RQ_XDPSQ_STATS * max_nch) + - (NUM_XDPSQ_STATS * max_nch); + (NUM_XDPSQ_STATS * max_nch) + + (NUM_XSKRQ_STATS * max_nch * priv->xsk.ever_used) + + (NUM_XSKSQ_STATS * max_nch * priv->xsk.ever_used); } static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data, int idx) { int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); + bool is_xsk = priv->xsk.ever_used; int i, j, tc; for (i = 0; i < max_nch; i++) @@ -1306,6 +1398,9 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data, for (j = 0; j < NUM_RQ_STATS; j++) sprintf(data + (idx++) * ETH_GSTRING_LEN, rq_stats_desc[j].format, i); + for (j = 0; j < NUM_XSKRQ_STATS * is_xsk; j++) + sprintf(data + (idx++) * ETH_GSTRING_LEN, + xskrq_stats_desc[j].format, i); for (j = 0; j < NUM_RQ_XDPSQ_STATS; j++) sprintf(data + (idx++) * ETH_GSTRING_LEN, rq_xdpsq_stats_desc[j].format, i); @@ -1318,10 +1413,14 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data, sq_stats_desc[j].format, priv->channel_tc2txq[i][tc]); - for (i = 0; i < max_nch; i++) + for (i = 0; i < max_nch; i++) { + for (j = 0; j < NUM_XSKSQ_STATS * is_xsk; j++) + sprintf(data + (idx++) * ETH_GSTRING_LEN, + xsksq_stats_desc[j].format, i); for (j = 0; j < NUM_XDPSQ_STATS; j++) sprintf(data + (idx++) * ETH_GSTRING_LEN, xdpsq_stats_desc[j].format, i); + } return idx; } @@ -1330,6 +1429,7 @@ static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx) { int max_nch = mlx5e_get_netdev_max_channels(priv->netdev); + bool is_xsk = priv->xsk.ever_used; int i, j, tc; for (i = 0; i < max_nch; i++) @@ -1343,6 +1443,10 @@ static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data, data[idx++] = MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].rq, rq_stats_desc, j); + for (j = 0; j < NUM_XSKRQ_STATS * is_xsk; j++) + data[idx++] = + MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].xskrq, + xskrq_stats_desc, j); for (j = 0; j < NUM_RQ_XDPSQ_STATS; j++) data[idx++] = MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].rq_xdpsq, @@ -1356,11 +1460,16 @@ static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data, MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].sq[tc], sq_stats_desc, j); - for (i = 0; i < max_nch; i++) + for (i = 0; i < max_nch; i++) { + for (j = 0; j < NUM_XSKSQ_STATS * is_xsk; j++) + data[idx++] = + MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].xsksq, + xsksq_stats_desc, j); for (j = 0; j < NUM_XDPSQ_STATS; j++) data[idx++] = MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].xdpsq, xdpsq_stats_desc, j); + } return idx; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index cdddcc46971b..fb3ad7231e11 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -46,6 +46,8 @@ #define MLX5E_DECLARE_TX_STAT(type, fld) "tx%d_"#fld, offsetof(type, fld) #define MLX5E_DECLARE_XDPSQ_STAT(type, fld) "tx%d_xdp_"#fld, offsetof(type, fld) #define MLX5E_DECLARE_RQ_XDPSQ_STAT(type, fld) "rx%d_xdp_tx_"#fld, offsetof(type, fld) +#define MLX5E_DECLARE_XSKRQ_STAT(type, fld) "rx%d_xsk_"#fld, offsetof(type, fld) +#define MLX5E_DECLARE_XSKSQ_STAT(type, fld) "tx%d_xsk_"#fld, offsetof(type, fld) #define MLX5E_DECLARE_CH_STAT(type, fld) "ch%d_"#fld, offsetof(type, fld) struct counter_desc { @@ -116,12 +118,39 @@ struct mlx5e_sw_stats { u64 ch_poll; u64 ch_arm; u64 ch_aff_change; + u64 ch_force_irq; u64 ch_eq_rearm; #ifdef CONFIG_MLX5_EN_TLS u64 tx_tls_ooo; u64 tx_tls_resync_bytes; #endif + + u64 rx_xsk_packets; + u64 rx_xsk_bytes; + u64 rx_xsk_csum_complete; + u64 rx_xsk_csum_unnecessary; + u64 rx_xsk_csum_unnecessary_inner; + u64 rx_xsk_csum_none; + u64 rx_xsk_ecn_mark; + u64 rx_xsk_removed_vlan_packets; + u64 rx_xsk_xdp_drop; + u64 rx_xsk_xdp_redirect; + u64 rx_xsk_wqe_err; + u64 rx_xsk_mpwqe_filler_cqes; + u64 rx_xsk_mpwqe_filler_strides; + u64 rx_xsk_oversize_pkts_sw_drop; + u64 rx_xsk_buff_alloc_err; + u64 rx_xsk_cqe_compress_blks; + u64 rx_xsk_cqe_compress_pkts; + u64 rx_xsk_congst_umr; + u64 rx_xsk_arfs_err; + u64 tx_xsk_xmit; + u64 tx_xsk_mpwqe; + u64 tx_xsk_inlnw; + u64 tx_xsk_full; + u64 tx_xsk_err; + u64 tx_xsk_cqes; }; struct mlx5e_qcounter_stats { @@ -256,6 +285,7 @@ struct mlx5e_ch_stats { u64 poll; u64 arm; u64 aff_change; + u64 force_irq; u64 eq_rearm; }; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index e6c434efbd46..3c98b7fe2923 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -33,6 +33,7 @@ #include <linux/irq.h> #include "en.h" #include "en/xdp.h" +#include "en/xsk/tx.h" static inline bool mlx5e_channel_no_affinity_change(struct mlx5e_channel *c) { @@ -85,7 +86,12 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel, napi); struct mlx5e_ch_stats *ch_stats = c->stats; + struct mlx5e_xdpsq *xsksq = &c->xsksq; + struct mlx5e_rq *xskrq = &c->xskrq; struct mlx5e_rq *rq = &c->rq; + bool xsk_open = test_bit(MLX5E_CHANNEL_STATE_XSK, c->state); + bool aff_change = false; + bool busy_xsk = false; bool busy = false; int work_done = 0; int i; @@ -95,22 +101,38 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) for (i = 0; i < c->num_tc; i++) busy |= mlx5e_poll_tx_cq(&c->sq[i].cq, budget); - busy |= mlx5e_poll_xdpsq_cq(&c->xdpsq.cq, NULL); + busy |= mlx5e_poll_xdpsq_cq(&c->xdpsq.cq); if (c->xdp) - busy |= mlx5e_poll_xdpsq_cq(&rq->xdpsq.cq, rq); + busy |= mlx5e_poll_xdpsq_cq(&c->rq_xdpsq.cq); if (likely(budget)) { /* budget=0 means: don't poll rx rings */ - work_done = mlx5e_poll_rx_cq(&rq->cq, budget); + if (xsk_open) + work_done = mlx5e_poll_rx_cq(&xskrq->cq, budget); + + if (likely(budget - work_done)) + work_done += mlx5e_poll_rx_cq(&rq->cq, budget - work_done); + busy |= work_done == budget; } - busy |= c->rq.post_wqes(rq); + mlx5e_poll_ico_cq(&c->icosq.cq); + + busy |= rq->post_wqes(rq); + if (xsk_open) { + mlx5e_poll_ico_cq(&c->xskicosq.cq); + busy |= mlx5e_poll_xdpsq_cq(&xsksq->cq); + busy_xsk |= mlx5e_xsk_tx(xsksq, MLX5E_TX_XSK_POLL_BUDGET); + busy_xsk |= xskrq->post_wqes(xskrq); + } + + busy |= busy_xsk; if (busy) { if (likely(mlx5e_channel_no_affinity_change(c))) return budget; ch_stats->aff_change++; + aff_change = true; if (budget && work_done == budget) work_done--; } @@ -131,6 +153,18 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) mlx5e_cq_arm(&c->icosq.cq); mlx5e_cq_arm(&c->xdpsq.cq); + if (xsk_open) { + mlx5e_handle_rx_dim(xskrq); + mlx5e_cq_arm(&c->xskicosq.cq); + mlx5e_cq_arm(&xsksq->cq); + mlx5e_cq_arm(&xskrq->cq); + } + + if (unlikely(aff_change && busy_xsk)) { + mlx5e_trigger_irq(&c->icosq); + ch_stats->force_irq++; + } + return work_done; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index e68d124eb625..00e66c3772cc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -87,7 +87,7 @@ int mlx5i_init(struct mlx5_core_dev *mdev, mlx5e_set_netdev_mtu_boundaries(priv); netdev->mtu = netdev->max_mtu; - mlx5e_build_nic_params(mdev, &priv->rss_params, &priv->channels.params, + mlx5e_build_nic_params(mdev, NULL, &priv->rss_params, &priv->channels.params, mlx5e_get_netdev_max_channels(netdev), netdev->mtu); mlx5i_build_nic_params(mdev, &priv->channels.params); @@ -365,7 +365,7 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv) if (err) goto err_close_drop_rq; - err = mlx5e_create_direct_rqts(priv); + err = mlx5e_create_direct_rqts(priv, priv->direct_tir); if (err) goto err_destroy_indirect_rqts; @@ -373,7 +373,7 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv) if (err) goto err_destroy_direct_rqts; - err = mlx5e_create_direct_tirs(priv); + err = mlx5e_create_direct_tirs(priv, priv->direct_tir); if (err) goto err_destroy_indirect_tirs; @@ -384,11 +384,11 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv) return 0; err_destroy_direct_tirs: - mlx5e_destroy_direct_tirs(priv); + mlx5e_destroy_direct_tirs(priv, priv->direct_tir); err_destroy_indirect_tirs: mlx5e_destroy_indirect_tirs(priv, true); err_destroy_direct_rqts: - mlx5e_destroy_direct_rqts(priv); + mlx5e_destroy_direct_rqts(priv, priv->direct_tir); err_destroy_indirect_rqts: mlx5e_destroy_rqt(priv, &priv->indir_rqt); err_close_drop_rq: @@ -401,9 +401,9 @@ err_destroy_q_counters: static void mlx5i_cleanup_rx(struct mlx5e_priv *priv) { mlx5i_destroy_flow_steering(priv); - mlx5e_destroy_direct_tirs(priv); + mlx5e_destroy_direct_tirs(priv, priv->direct_tir); mlx5e_destroy_indirect_tirs(priv, true); - mlx5e_destroy_direct_rqts(priv); + mlx5e_destroy_direct_rqts(priv, priv->direct_tir); mlx5e_destroy_rqt(priv, &priv->indir_rqt); mlx5e_close_drop_rq(&priv->drop_rq); mlx5e_destroy_q_counters(priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h index 1f87cce421e0..f1ec58c9e9e3 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h @@ -134,11 +134,6 @@ static inline void mlx5_wq_cyc_update_db_record(struct mlx5_wq_cyc *wq) *wq->db = cpu_to_be32(wq->wqe_ctr); } -static inline u16 mlx5_wq_cyc_get_ctr_wrap_cnt(struct mlx5_wq_cyc *wq, u16 ctr) -{ - return ctr >> wq->fbc.log_sz; -} - static inline u16 mlx5_wq_cyc_ctr2ix(struct mlx5_wq_cyc *wq, u16 ctr) { return ctr & wq->fbc.sz_m1; diff --git a/drivers/net/veth.c b/drivers/net/veth.c index c6916bf1017b..9f3c839f9e5f 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -38,6 +38,8 @@ #define VETH_XDP_TX BIT(0) #define VETH_XDP_REDIR BIT(1) +#define VETH_XDP_TX_BULK_SIZE 16 + struct veth_rq_stats { u64 xdp_packets; u64 xdp_bytes; @@ -64,6 +66,11 @@ struct veth_priv { unsigned int requested_headroom; }; +struct veth_xdp_tx_bq { + struct xdp_frame *q[VETH_XDP_TX_BULK_SIZE]; + unsigned int count; +}; + /* * ethtool interface */ @@ -442,13 +449,30 @@ drop: return ret; } -static void veth_xdp_flush(struct net_device *dev) +static void veth_xdp_flush_bq(struct net_device *dev, struct veth_xdp_tx_bq *bq) +{ + int sent, i, err = 0; + + sent = veth_xdp_xmit(dev, bq->count, bq->q, 0); + if (sent < 0) { + err = sent; + sent = 0; + for (i = 0; i < bq->count; i++) + xdp_return_frame(bq->q[i]); + } + trace_xdp_bulk_tx(dev, sent, bq->count - sent, err); + + bq->count = 0; +} + +static void veth_xdp_flush(struct net_device *dev, struct veth_xdp_tx_bq *bq) { struct veth_priv *rcv_priv, *priv = netdev_priv(dev); struct net_device *rcv; struct veth_rq *rq; rcu_read_lock(); + veth_xdp_flush_bq(dev, bq); rcv = rcu_dereference(priv->peer); if (unlikely(!rcv)) goto out; @@ -464,19 +488,26 @@ out: rcu_read_unlock(); } -static int veth_xdp_tx(struct net_device *dev, struct xdp_buff *xdp) +static int veth_xdp_tx(struct net_device *dev, struct xdp_buff *xdp, + struct veth_xdp_tx_bq *bq) { struct xdp_frame *frame = convert_to_xdp_frame(xdp); if (unlikely(!frame)) return -EOVERFLOW; - return veth_xdp_xmit(dev, 1, &frame, 0); + if (unlikely(bq->count == VETH_XDP_TX_BULK_SIZE)) + veth_xdp_flush_bq(dev, bq); + + bq->q[bq->count++] = frame; + + return 0; } static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq, struct xdp_frame *frame, - unsigned int *xdp_xmit) + unsigned int *xdp_xmit, + struct veth_xdp_tx_bq *bq) { void *hard_start = frame->data - frame->headroom; void *head = hard_start - sizeof(struct xdp_frame); @@ -509,7 +540,7 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq, orig_frame = *frame; xdp.data_hard_start = head; xdp.rxq->mem = frame->mem; - if (unlikely(veth_xdp_tx(rq->dev, &xdp) < 0)) { + if (unlikely(veth_xdp_tx(rq->dev, &xdp, bq) < 0)) { trace_xdp_exception(rq->dev, xdp_prog, act); frame = &orig_frame; goto err_xdp; @@ -560,7 +591,8 @@ xdp_xmit: } static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, struct sk_buff *skb, - unsigned int *xdp_xmit) + unsigned int *xdp_xmit, + struct veth_xdp_tx_bq *bq) { u32 pktlen, headroom, act, metalen; void *orig_data, *orig_data_end; @@ -636,7 +668,7 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, struct sk_buff *skb, get_page(virt_to_page(xdp.data)); consume_skb(skb); xdp.rxq->mem = rq->xdp_mem; - if (unlikely(veth_xdp_tx(rq->dev, &xdp) < 0)) { + if (unlikely(veth_xdp_tx(rq->dev, &xdp, bq) < 0)) { trace_xdp_exception(rq->dev, xdp_prog, act); goto err_xdp; } @@ -691,7 +723,8 @@ xdp_xmit: return NULL; } -static int veth_xdp_rcv(struct veth_rq *rq, int budget, unsigned int *xdp_xmit) +static int veth_xdp_rcv(struct veth_rq *rq, int budget, unsigned int *xdp_xmit, + struct veth_xdp_tx_bq *bq) { int i, done = 0, drops = 0, bytes = 0; @@ -707,11 +740,11 @@ static int veth_xdp_rcv(struct veth_rq *rq, int budget, unsigned int *xdp_xmit) struct xdp_frame *frame = veth_ptr_to_xdp(ptr); bytes += frame->len; - skb = veth_xdp_rcv_one(rq, frame, &xdp_xmit_one); + skb = veth_xdp_rcv_one(rq, frame, &xdp_xmit_one, bq); } else { skb = ptr; bytes += skb->len; - skb = veth_xdp_rcv_skb(rq, skb, &xdp_xmit_one); + skb = veth_xdp_rcv_skb(rq, skb, &xdp_xmit_one, bq); } *xdp_xmit |= xdp_xmit_one; @@ -737,10 +770,13 @@ static int veth_poll(struct napi_struct *napi, int budget) struct veth_rq *rq = container_of(napi, struct veth_rq, xdp_napi); unsigned int xdp_xmit = 0; + struct veth_xdp_tx_bq bq; int done; + bq.count = 0; + xdp_set_return_frame_no_direct(); - done = veth_xdp_rcv(rq, budget, &xdp_xmit); + done = veth_xdp_rcv(rq, budget, &xdp_xmit, &bq); if (done < budget && napi_complete_done(napi, done)) { /* Write rx_notify_masked before reading ptr_ring */ @@ -752,7 +788,7 @@ static int veth_poll(struct napi_struct *napi, int budget) } if (xdp_xmit & VETH_XDP_TX) - veth_xdp_flush(rq->dev); + veth_xdp_flush(rq->dev, &bq); if (xdp_xmit & VETH_XDP_REDIR) xdp_do_flush_map(); xdp_clear_return_frame_no_direct(); diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index bd79ae32909a..169fd25f6bc2 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -124,6 +124,14 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, loff_t *ppos, void **new_buf, enum bpf_attach_type type); +int __cgroup_bpf_run_filter_setsockopt(struct sock *sock, int *level, + int *optname, char __user *optval, + int *optlen, char **kernel_optval); +int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, + int optname, char __user *optval, + int __user *optlen, int max_optlen, + int retval); + static inline enum bpf_cgroup_storage_type cgroup_storage_type( struct bpf_map *map) { @@ -286,6 +294,38 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, __ret; \ }) +#define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \ + kernel_optval) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_run_filter_setsockopt(sock, level, \ + optname, optval, \ + optlen, \ + kernel_optval); \ + __ret; \ +}) + +#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) \ +({ \ + int __ret = 0; \ + if (cgroup_bpf_enabled) \ + get_user(__ret, optlen); \ + __ret; \ +}) + +#define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, optlen, \ + max_optlen, retval) \ +({ \ + int __ret = retval; \ + if (cgroup_bpf_enabled) \ + __ret = __cgroup_bpf_run_filter_getsockopt(sock, level, \ + optname, optval, \ + optlen, max_optlen, \ + retval); \ + __ret; \ +}) + int cgroup_bpf_prog_attach(const union bpf_attr *attr, enum bpf_prog_type ptype, struct bpf_prog *prog); int cgroup_bpf_prog_detach(const union bpf_attr *attr, @@ -357,6 +397,11 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; }) #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(type,major,minor,access) ({ 0; }) #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos,nbuf) ({ 0; }) +#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \ + optlen, max_optlen, retval) ({ retval; }) +#define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \ + kernel_optval) ({ 0; }) #define for_each_cgroup_storage_type(stype) for (; false; ) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a62e7889b0b6..18f4cc2c6acd 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -518,6 +518,7 @@ struct bpf_prog_array { struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); void bpf_prog_array_free(struct bpf_prog_array *progs); int bpf_prog_array_length(struct bpf_prog_array *progs); +bool bpf_prog_array_is_empty(struct bpf_prog_array *array); int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs, __u32 __user *prog_ids, u32 cnt); @@ -1051,6 +1052,7 @@ extern const struct bpf_func_proto bpf_spin_unlock_proto; extern const struct bpf_func_proto bpf_get_local_storage_proto; extern const struct bpf_func_proto bpf_strtol_proto; extern const struct bpf_func_proto bpf_strtoul_proto; +extern const struct bpf_func_proto bpf_tcp_sock_proto; /* Shared helpers among cBPF and eBPF. */ void bpf_user_rnd_init_once(void); diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 5a9975678d6f..eec5aeeeaf92 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -30,6 +30,7 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable) #ifdef CONFIG_CGROUP_BPF BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev) BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl) +BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCKOPT, cg_sockopt) #endif #ifdef CONFIG_BPF_LIRC_MODE2 BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2) diff --git a/include/linux/filter.h b/include/linux/filter.h index 43b45d6db36d..1fe53e78c7e3 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -578,8 +578,9 @@ struct bpf_skb_data_end { }; struct bpf_redirect_info { - u32 ifindex; u32 flags; + u32 tgt_index; + void *tgt_value; struct bpf_map *map; struct bpf_map *map_to_flush; u32 kern_flags; @@ -1199,4 +1200,14 @@ struct bpf_sysctl_kern { u64 tmp_reg; }; +struct bpf_sockopt_kern { + struct sock *sk; + u8 *optval; + u8 *optval_end; + s32 level; + s32 optname; + s32 optlen; + s32 retval; +}; + #endif /* __LINUX_FILTER_H__ */ diff --git a/include/linux/list.h b/include/linux/list.h index e951228db4b2..85c92555e31f 100644 --- a/include/linux/list.h +++ b/include/linux/list.h @@ -106,6 +106,20 @@ static inline void __list_del(struct list_head * prev, struct list_head * next) WRITE_ONCE(prev->next, next); } +/* + * Delete a list entry and clear the 'prev' pointer. + * + * This is a special-purpose list clearing method used in the networking code + * for lists allocated as per-cpu, where we don't want to incur the extra + * WRITE_ONCE() overhead of a regular list_del_init(). The code that uses this + * needs to check the node 'prev' pointer instead of calling list_empty(). + */ +static inline void __list_del_clearprev(struct list_head *entry) +{ + __list_del(entry->prev, entry->next); + entry->prev = NULL; +} + /** * list_del - deletes entry from list. * @entry: the element to delete from the list. diff --git a/include/net/tcp.h b/include/net/tcp.h index 9d36cc88d043..e16d8a3fd3b4 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2221,6 +2221,14 @@ static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk) return (tcp_call_bpf(sk, BPF_SOCK_OPS_NEEDS_ECN, 0, NULL) == 1); } +static inline void tcp_bpf_rtt(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTT_CB_FLAG)) + tcp_call_bpf(sk, BPF_SOCK_OPS_RTT_CB, 0, NULL); +} + #if IS_ENABLED(CONFIG_SMC) extern struct static_key_false tcp_have_smc; #endif diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index ae0f368a62bb..057b159ff8b9 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -77,10 +77,11 @@ int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp); void xsk_flush(struct xdp_sock *xs); bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs); /* Used from netdev driver */ +bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt); u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr); void xsk_umem_discard_addr(struct xdp_umem *umem); void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries); -bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, u32 *len); +bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc); void xsk_umem_consume_tx_done(struct xdp_umem *umem); struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries); struct xdp_umem_fq_reuse *xsk_reuseq_swap(struct xdp_umem *umem, @@ -99,6 +100,16 @@ static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr) } /* Reuse-queue aware version of FILL queue helpers */ +static inline bool xsk_umem_has_addrs_rq(struct xdp_umem *umem, u32 cnt) +{ + struct xdp_umem_fq_reuse *rq = umem->fq_reuse; + + if (rq->length >= cnt) + return true; + + return xsk_umem_has_addrs(umem, cnt - rq->length); +} + static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr) { struct xdp_umem_fq_reuse *rq = umem->fq_reuse; @@ -146,6 +157,11 @@ static inline bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) return false; } +static inline bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt) +{ + return false; +} + static inline u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr) { return NULL; @@ -159,8 +175,8 @@ static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries) { } -static inline bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, - u32 *len) +static inline bool xsk_umem_consume_tx(struct xdp_umem *umem, + struct xdp_desc *desc) { return false; } @@ -200,6 +216,11 @@ static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr) return 0; } +static inline bool xsk_umem_has_addrs_rq(struct xdp_umem *umem, u32 cnt) +{ + return false; +} + static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr) { return NULL; diff --git a/include/trace/events/xdp.h b/include/trace/events/xdp.h index bb5e380e2ef3..68899fdc985b 100644 --- a/include/trace/events/xdp.h +++ b/include/trace/events/xdp.h @@ -50,6 +50,35 @@ TRACE_EVENT(xdp_exception, __entry->ifindex) ); +TRACE_EVENT(xdp_bulk_tx, + + TP_PROTO(const struct net_device *dev, + int sent, int drops, int err), + + TP_ARGS(dev, sent, drops, err), + + TP_STRUCT__entry( + __field(int, ifindex) + __field(u32, act) + __field(int, drops) + __field(int, sent) + __field(int, err) + ), + + TP_fast_assign( + __entry->ifindex = dev->ifindex; + __entry->act = XDP_TX; + __entry->drops = drops; + __entry->sent = sent; + __entry->err = err; + ), + + TP_printk("ifindex=%d action=%s sent=%d drops=%d err=%d", + __entry->ifindex, + __print_symbolic(__entry->act, __XDP_ACT_SYM_TAB), + __entry->sent, __entry->drops, __entry->err) +); + DECLARE_EVENT_CLASS(xdp_redirect_template, TP_PROTO(const struct net_device *dev, @@ -146,9 +175,8 @@ struct _bpf_dtab_netdev { #endif /* __DEVMAP_OBJ_TYPE */ #define devmap_ifindex(fwd, map) \ - (!fwd ? 0 : \ - ((map->map_type == BPF_MAP_TYPE_DEVMAP) ? \ - ((struct _bpf_dtab_netdev *)fwd)->dev->ifindex : 0)) + ((map->map_type == BPF_MAP_TYPE_DEVMAP) ? \ + ((struct _bpf_dtab_netdev *)fwd)->dev->ifindex : 0) #define _trace_xdp_redirect_map(dev, xdp, fwd, map, idx) \ trace_xdp_redirect_map(dev, xdp, devmap_ifindex(fwd, map), \ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index b077507efa3f..ead27aebf491 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -170,6 +170,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_FLOW_DISSECTOR, BPF_PROG_TYPE_CGROUP_SYSCTL, BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, + BPF_PROG_TYPE_CGROUP_SOCKOPT, }; enum bpf_attach_type { @@ -194,6 +195,8 @@ enum bpf_attach_type { BPF_CGROUP_SYSCTL, BPF_CGROUP_UDP4_RECVMSG, BPF_CGROUP_UDP6_RECVMSG, + BPF_CGROUP_GETSOCKOPT, + BPF_CGROUP_SETSOCKOPT, __MAX_BPF_ATTACH_TYPE }; @@ -1568,8 +1571,11 @@ union bpf_attr { * but this is only implemented for native XDP (with driver * support) as of this writing). * - * All values for *flags* are reserved for future usage, and must - * be left at zero. + * The lower two bits of *flags* are used as the return code if + * the map lookup fails. This is so that the return value can be + * one of the XDP program return codes up to XDP_TX, as chosen by + * the caller. Any higher bits in the *flags* argument must be + * unset. * * When used to redirect packets to net devices, this helper * provides a high performance increase over **bpf_redirect**\ (). @@ -1764,6 +1770,7 @@ union bpf_attr { * * **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) + * * **BPF_SOCK_OPS_RTT_CB_FLAG** (every RTT) * * Therefore, this function can be used to clear a callback flag by * setting the appropriate bit to zero. e.g. to disable the RTO @@ -3066,6 +3073,12 @@ struct bpf_tcp_sock { * sum(delta(snd_una)), or how many bytes * were acked. */ + __u32 dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups + * total number of DSACK blocks received + */ + __u32 delivered; /* Total data packets delivered incl. rexmits */ + __u32 delivered_ce; /* Like the above but only ECE marked packets */ + __u32 icsk_retransmits; /* Number of unrecovered [RTO] timeouts */ }; struct bpf_sock_tuple { @@ -3308,7 +3321,8 @@ struct bpf_sock_ops { #define BPF_SOCK_OPS_RTO_CB_FLAG (1<<0) #define BPF_SOCK_OPS_RETRANS_CB_FLAG (1<<1) #define BPF_SOCK_OPS_STATE_CB_FLAG (1<<2) -#define BPF_SOCK_OPS_ALL_CB_FLAGS 0x7 /* Mask of all currently +#define BPF_SOCK_OPS_RTT_CB_FLAG (1<<3) +#define BPF_SOCK_OPS_ALL_CB_FLAGS 0xF /* Mask of all currently * supported cb flags */ @@ -3363,6 +3377,8 @@ enum { BPF_SOCK_OPS_TCP_LISTEN_CB, /* Called on listen(2), right after * socket transition to LISTEN state. */ + BPF_SOCK_OPS_RTT_CB, /* Called on every RTT. + */ }; /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect @@ -3541,4 +3557,15 @@ struct bpf_sysctl { */ }; +struct bpf_sockopt { + __bpf_md_ptr(struct bpf_sock *, sk); + __bpf_md_ptr(void *, optval); + __bpf_md_ptr(void *, optval_end); + + __s32 level; + __s32 optname; + __s32 optlen; + __s32 retval; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h index caed8b1614ff..faaa5ca2a117 100644 --- a/include/uapi/linux/if_xdp.h +++ b/include/uapi/linux/if_xdp.h @@ -46,6 +46,7 @@ struct xdp_mmap_offsets { #define XDP_UMEM_FILL_RING 5 #define XDP_UMEM_COMPLETION_RING 6 #define XDP_STATISTICS 7 +#define XDP_OPTIONS 8 struct xdp_umem_reg { __u64 addr; /* Start of packet data area */ @@ -60,6 +61,13 @@ struct xdp_statistics { __u64 tx_invalid_descs; /* Dropped due to invalid descriptor */ }; +struct xdp_options { + __u32 flags; +}; + +/* Flags for the flags field of struct xdp_options */ +#define XDP_OPTIONS_ZEROCOPY (1 << 0) + /* Pgoff for mmaping the rings */ #define XDP_PGOFF_RX_RING 0 #define XDP_PGOFF_TX_RING 0x80000000 diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index c225c42e114a..76fa0076f20d 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -15,6 +15,9 @@ #include <linux/bpf.h> #include <linux/bpf-cgroup.h> #include <net/sock.h> +#include <net/bpf_sk_storage.h> + +#include "../cgroup/cgroup-internal.h" DEFINE_STATIC_KEY_FALSE(cgroup_bpf_enabled_key); EXPORT_SYMBOL(cgroup_bpf_enabled_key); @@ -38,6 +41,8 @@ static void cgroup_bpf_release(struct work_struct *work) struct bpf_prog_array *old_array; unsigned int type; + mutex_lock(&cgroup_mutex); + for (type = 0; type < ARRAY_SIZE(cgrp->bpf.progs); type++) { struct list_head *progs = &cgrp->bpf.progs[type]; struct bpf_prog_list *pl, *tmp; @@ -54,10 +59,12 @@ static void cgroup_bpf_release(struct work_struct *work) } old_array = rcu_dereference_protected( cgrp->bpf.effective[type], - percpu_ref_is_dying(&cgrp->bpf.refcnt)); + lockdep_is_held(&cgroup_mutex)); bpf_prog_array_free(old_array); } + mutex_unlock(&cgroup_mutex); + percpu_ref_exit(&cgrp->bpf.refcnt); cgroup_put(cgrp); } @@ -229,6 +236,9 @@ static int update_effective_progs(struct cgroup *cgrp, css_for_each_descendant_pre(css, &cgrp->self) { struct cgroup *desc = container_of(css, struct cgroup, self); + if (percpu_ref_is_zero(&desc->bpf.refcnt)) + continue; + err = compute_effective_progs(desc, type, &desc->bpf.inactive); if (err) goto cleanup; @@ -238,6 +248,14 @@ static int update_effective_progs(struct cgroup *cgrp, css_for_each_descendant_pre(css, &cgrp->self) { struct cgroup *desc = container_of(css, struct cgroup, self); + if (percpu_ref_is_zero(&desc->bpf.refcnt)) { + if (unlikely(desc->bpf.inactive)) { + bpf_prog_array_free(desc->bpf.inactive); + desc->bpf.inactive = NULL; + } + continue; + } + activate_effective_progs(desc, type, desc->bpf.inactive); desc->bpf.inactive = NULL; } @@ -921,6 +939,188 @@ int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head, } EXPORT_SYMBOL(__cgroup_bpf_run_filter_sysctl); +static bool __cgroup_bpf_prog_array_is_empty(struct cgroup *cgrp, + enum bpf_attach_type attach_type) +{ + struct bpf_prog_array *prog_array; + bool empty; + + rcu_read_lock(); + prog_array = rcu_dereference(cgrp->bpf.effective[attach_type]); + empty = bpf_prog_array_is_empty(prog_array); + rcu_read_unlock(); + + return empty; +} + +static int sockopt_alloc_buf(struct bpf_sockopt_kern *ctx, int max_optlen) +{ + if (unlikely(max_optlen > PAGE_SIZE) || max_optlen < 0) + return -EINVAL; + + ctx->optval = kzalloc(max_optlen, GFP_USER); + if (!ctx->optval) + return -ENOMEM; + + ctx->optval_end = ctx->optval + max_optlen; + ctx->optlen = max_optlen; + + return 0; +} + +static void sockopt_free_buf(struct bpf_sockopt_kern *ctx) +{ + kfree(ctx->optval); +} + +int __cgroup_bpf_run_filter_setsockopt(struct sock *sk, int *level, + int *optname, char __user *optval, + int *optlen, char **kernel_optval) +{ + struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); + struct bpf_sockopt_kern ctx = { + .sk = sk, + .level = *level, + .optname = *optname, + }; + int ret; + + /* Opportunistic check to see whether we have any BPF program + * attached to the hook so we don't waste time allocating + * memory and locking the socket. + */ + if (!cgroup_bpf_enabled || + __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_SETSOCKOPT)) + return 0; + + ret = sockopt_alloc_buf(&ctx, *optlen); + if (ret) + return ret; + + if (copy_from_user(ctx.optval, optval, *optlen) != 0) { + ret = -EFAULT; + goto out; + } + + lock_sock(sk); + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_SETSOCKOPT], + &ctx, BPF_PROG_RUN); + release_sock(sk); + + if (!ret) { + ret = -EPERM; + goto out; + } + + if (ctx.optlen == -1) { + /* optlen set to -1, bypass kernel */ + ret = 1; + } else if (ctx.optlen > *optlen || ctx.optlen < -1) { + /* optlen is out of bounds */ + ret = -EFAULT; + } else { + /* optlen within bounds, run kernel handler */ + ret = 0; + + /* export any potential modifications */ + *level = ctx.level; + *optname = ctx.optname; + *optlen = ctx.optlen; + *kernel_optval = ctx.optval; + } + +out: + if (ret) + sockopt_free_buf(&ctx); + return ret; +} +EXPORT_SYMBOL(__cgroup_bpf_run_filter_setsockopt); + +int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level, + int optname, char __user *optval, + int __user *optlen, int max_optlen, + int retval) +{ + struct cgroup *cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); + struct bpf_sockopt_kern ctx = { + .sk = sk, + .level = level, + .optname = optname, + .retval = retval, + }; + int ret; + + /* Opportunistic check to see whether we have any BPF program + * attached to the hook so we don't waste time allocating + * memory and locking the socket. + */ + if (!cgroup_bpf_enabled || + __cgroup_bpf_prog_array_is_empty(cgrp, BPF_CGROUP_GETSOCKOPT)) + return retval; + + ret = sockopt_alloc_buf(&ctx, max_optlen); + if (ret) + return ret; + + if (!retval) { + /* If kernel getsockopt finished successfully, + * copy whatever was returned to the user back + * into our temporary buffer. Set optlen to the + * one that kernel returned as well to let + * BPF programs inspect the value. + */ + + if (get_user(ctx.optlen, optlen)) { + ret = -EFAULT; + goto out; + } + + if (ctx.optlen > max_optlen) + ctx.optlen = max_optlen; + + if (copy_from_user(ctx.optval, optval, ctx.optlen) != 0) { + ret = -EFAULT; + goto out; + } + } + + lock_sock(sk); + ret = BPF_PROG_RUN_ARRAY(cgrp->bpf.effective[BPF_CGROUP_GETSOCKOPT], + &ctx, BPF_PROG_RUN); + release_sock(sk); + + if (!ret) { + ret = -EPERM; + goto out; + } + + if (ctx.optlen > max_optlen) { + ret = -EFAULT; + goto out; + } + + /* BPF programs only allowed to set retval to 0, not some + * arbitrary value. + */ + if (ctx.retval != 0 && ctx.retval != retval) { + ret = -EFAULT; + goto out; + } + + if (copy_to_user(optval, ctx.optval, ctx.optlen) || + put_user(ctx.optlen, optlen)) { + ret = -EFAULT; + goto out; + } + + ret = ctx.retval; + +out: + sockopt_free_buf(&ctx); + return ret; +} +EXPORT_SYMBOL(__cgroup_bpf_run_filter_getsockopt); + static ssize_t sysctl_cpy_dir(const struct ctl_dir *dir, char **bufp, size_t *lenp) { @@ -1181,3 +1381,153 @@ const struct bpf_verifier_ops cg_sysctl_verifier_ops = { const struct bpf_prog_ops cg_sysctl_prog_ops = { }; + +static const struct bpf_func_proto * +cg_sockopt_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) +{ + switch (func_id) { + case BPF_FUNC_sk_storage_get: + return &bpf_sk_storage_get_proto; + case BPF_FUNC_sk_storage_delete: + return &bpf_sk_storage_delete_proto; +#ifdef CONFIG_INET + case BPF_FUNC_tcp_sock: + return &bpf_tcp_sock_proto; +#endif + default: + return cgroup_base_func_proto(func_id, prog); + } +} + +static bool cg_sockopt_is_valid_access(int off, int size, + enum bpf_access_type type, + const struct bpf_prog *prog, + struct bpf_insn_access_aux *info) +{ + const int size_default = sizeof(__u32); + + if (off < 0 || off >= sizeof(struct bpf_sockopt)) + return false; + + if (off % size != 0) + return false; + + if (type == BPF_WRITE) { + switch (off) { + case offsetof(struct bpf_sockopt, retval): + if (size != size_default) + return false; + return prog->expected_attach_type == + BPF_CGROUP_GETSOCKOPT; + case offsetof(struct bpf_sockopt, optname): + /* fallthrough */ + case offsetof(struct bpf_sockopt, level): + if (size != size_default) + return false; + return prog->expected_attach_type == + BPF_CGROUP_SETSOCKOPT; + case offsetof(struct bpf_sockopt, optlen): + return size == size_default; + default: + return false; + } + } + + switch (off) { + case offsetof(struct bpf_sockopt, sk): + if (size != sizeof(__u64)) + return false; + info->reg_type = PTR_TO_SOCKET; + break; + case offsetof(struct bpf_sockopt, optval): + if (size != sizeof(__u64)) + return false; + info->reg_type = PTR_TO_PACKET; + break; + case offsetof(struct bpf_sockopt, optval_end): + if (size != sizeof(__u64)) + return false; + info->reg_type = PTR_TO_PACKET_END; + break; + case offsetof(struct bpf_sockopt, retval): + if (size != size_default) + return false; + return prog->expected_attach_type == BPF_CGROUP_GETSOCKOPT; + default: + if (size != size_default) + return false; + break; + } + return true; +} + +#define CG_SOCKOPT_ACCESS_FIELD(T, F) \ + T(BPF_FIELD_SIZEOF(struct bpf_sockopt_kern, F), \ + si->dst_reg, si->src_reg, \ + offsetof(struct bpf_sockopt_kern, F)) + +static u32 cg_sockopt_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 bpf_sockopt, sk): + *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, sk); + break; + case offsetof(struct bpf_sockopt, level): + if (type == BPF_WRITE) + *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, level); + else + *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, level); + break; + case offsetof(struct bpf_sockopt, optname): + if (type == BPF_WRITE) + *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, optname); + else + *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optname); + break; + case offsetof(struct bpf_sockopt, optlen): + if (type == BPF_WRITE) + *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, optlen); + else + *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optlen); + break; + case offsetof(struct bpf_sockopt, retval): + if (type == BPF_WRITE) + *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_STX_MEM, retval); + else + *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, retval); + break; + case offsetof(struct bpf_sockopt, optval): + *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optval); + break; + case offsetof(struct bpf_sockopt, optval_end): + *insn++ = CG_SOCKOPT_ACCESS_FIELD(BPF_LDX_MEM, optval_end); + break; + } + + return insn - insn_buf; +} + +static int cg_sockopt_get_prologue(struct bpf_insn *insn_buf, + bool direct_write, + const struct bpf_prog *prog) +{ + /* Nothing to do for sockopt argument. The data is kzalloc'ated. + */ + return 0; +} + +const struct bpf_verifier_ops cg_sockopt_verifier_ops = { + .get_func_proto = cg_sockopt_func_proto, + .is_valid_access = cg_sockopt_is_valid_access, + .convert_ctx_access = cg_sockopt_convert_ctx_access, + .gen_prologue = cg_sockopt_get_prologue, +}; + +const struct bpf_prog_ops cg_sockopt_prog_ops = { +}; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index ad3be85f1411..e2c1b43728da 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1809,6 +1809,15 @@ int bpf_prog_array_length(struct bpf_prog_array *array) return cnt; } +bool bpf_prog_array_is_empty(struct bpf_prog_array *array) +{ + struct bpf_prog_array_item *item; + + for (item = array->items; item->prog; item++) + if (item->prog != &dummy_bpf_prog.prog) + return false; + return true; +} static bool bpf_prog_array_copy_core(struct bpf_prog_array *array, u32 *prog_ids, @@ -2101,3 +2110,4 @@ EXPORT_SYMBOL(bpf_stats_enabled_key); #include <linux/bpf_trace.h> EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception); +EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_bulk_tx); diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index 8dff08768087..ef49e17ae47c 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -32,14 +32,19 @@ /* General idea: XDP packets getting XDP redirected to another CPU, * will maximum be stored/queued for one driver ->poll() call. It is - * guaranteed that setting flush bit and flush operation happen on + * guaranteed that queueing the frame and the flush operation happen on * same CPU. Thus, cpu_map_flush operation can deduct via this_cpu_ptr() * which queue in bpf_cpu_map_entry contains packets. */ #define CPU_MAP_BULK_SIZE 8 /* 8 == one cacheline on 64-bit archs */ +struct bpf_cpu_map_entry; +struct bpf_cpu_map; + struct xdp_bulk_queue { void *q[CPU_MAP_BULK_SIZE]; + struct list_head flush_node; + struct bpf_cpu_map_entry *obj; unsigned int count; }; @@ -52,6 +57,8 @@ struct bpf_cpu_map_entry { /* XDP can run multiple RX-ring queues, need __percpu enqueue store */ struct xdp_bulk_queue __percpu *bulkq; + struct bpf_cpu_map *cmap; + /* Queue with potential multi-producers, and single-consumer kthread */ struct ptr_ring *queue; struct task_struct *kthread; @@ -65,23 +72,17 @@ struct bpf_cpu_map { struct bpf_map map; /* Below members specific for map type */ struct bpf_cpu_map_entry **cpu_map; - unsigned long __percpu *flush_needed; + struct list_head __percpu *flush_list; }; -static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, - struct xdp_bulk_queue *bq, bool in_napi_ctx); - -static u64 cpu_map_bitmap_size(const union bpf_attr *attr) -{ - return BITS_TO_LONGS(attr->max_entries) * sizeof(unsigned long); -} +static int bq_flush_to_queue(struct xdp_bulk_queue *bq, bool in_napi_ctx); static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) { struct bpf_cpu_map *cmap; int err = -ENOMEM; + int ret, cpu; u64 cost; - int ret; if (!capable(CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); @@ -105,7 +106,7 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) /* make sure page count doesn't overflow */ cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *); - cost += cpu_map_bitmap_size(attr) * num_possible_cpus(); + cost += sizeof(struct list_head) * num_possible_cpus(); /* Notice returns -EPERM on if map size is larger than memlock limit */ ret = bpf_map_charge_init(&cmap->map.memory, cost); @@ -114,12 +115,13 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) goto free_cmap; } - /* A per cpu bitfield with a bit per possible CPU in map */ - cmap->flush_needed = __alloc_percpu(cpu_map_bitmap_size(attr), - __alignof__(unsigned long)); - if (!cmap->flush_needed) + cmap->flush_list = alloc_percpu(struct list_head); + if (!cmap->flush_list) goto free_charge; + for_each_possible_cpu(cpu) + INIT_LIST_HEAD(per_cpu_ptr(cmap->flush_list, cpu)); + /* Alloc array for possible remote "destination" CPUs */ cmap->cpu_map = bpf_map_area_alloc(cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *), @@ -129,7 +131,7 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) return &cmap->map; free_percpu: - free_percpu(cmap->flush_needed); + free_percpu(cmap->flush_list); free_charge: bpf_map_charge_finish(&cmap->map.memory); free_cmap: @@ -334,7 +336,8 @@ static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, { gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; struct bpf_cpu_map_entry *rcpu; - int numa, err; + struct xdp_bulk_queue *bq; + int numa, err, i; /* Have map->numa_node, but choose node of redirect target CPU */ numa = cpu_to_node(cpu); @@ -349,6 +352,11 @@ static struct bpf_cpu_map_entry *__cpu_map_entry_alloc(u32 qsize, u32 cpu, if (!rcpu->bulkq) goto free_rcu; + for_each_possible_cpu(i) { + bq = per_cpu_ptr(rcpu->bulkq, i); + bq->obj = rcpu; + } + /* Alloc queue */ rcpu->queue = kzalloc_node(sizeof(*rcpu->queue), gfp, numa); if (!rcpu->queue) @@ -405,7 +413,7 @@ static void __cpu_map_entry_free(struct rcu_head *rcu) struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu); /* No concurrent bq_enqueue can run at this point */ - bq_flush_to_queue(rcpu, bq, false); + bq_flush_to_queue(bq, false); } free_percpu(rcpu->bulkq); /* Cannot kthread_stop() here, last put free rcpu resources */ @@ -488,6 +496,7 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value, rcpu = __cpu_map_entry_alloc(qsize, key_cpu, map->id); if (!rcpu) return -ENOMEM; + rcpu->cmap = cmap; } rcu_read_lock(); __cpu_map_entry_replace(cmap, key_cpu, rcpu); @@ -514,14 +523,14 @@ static void cpu_map_free(struct bpf_map *map) synchronize_rcu(); /* To ensure all pending flush operations have completed wait for flush - * bitmap to indicate all flush_needed bits to be zero on _all_ cpus. - * Because the above synchronize_rcu() ensures the map is disconnected - * from the program we can assume no new bits will be set. + * list be empty on _all_ cpus. Because the above synchronize_rcu() + * ensures the map is disconnected from the program we can assume no new + * items will be added to the list. */ for_each_online_cpu(cpu) { - unsigned long *bitmap = per_cpu_ptr(cmap->flush_needed, cpu); + struct list_head *flush_list = per_cpu_ptr(cmap->flush_list, cpu); - while (!bitmap_empty(bitmap, cmap->map.max_entries)) + while (!list_empty(flush_list)) cond_resched(); } @@ -538,7 +547,7 @@ static void cpu_map_free(struct bpf_map *map) /* bq flush and cleanup happens after RCU graze-period */ __cpu_map_entry_replace(cmap, i, NULL); /* call_rcu */ } - free_percpu(cmap->flush_needed); + free_percpu(cmap->flush_list); bpf_map_area_free(cmap->cpu_map); kfree(cmap); } @@ -590,9 +599,9 @@ const struct bpf_map_ops cpu_map_ops = { .map_check_btf = map_check_no_btf, }; -static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, - struct xdp_bulk_queue *bq, bool in_napi_ctx) +static int bq_flush_to_queue(struct xdp_bulk_queue *bq, bool in_napi_ctx) { + struct bpf_cpu_map_entry *rcpu = bq->obj; unsigned int processed = 0, drops = 0; const int to_cpu = rcpu->cpu; struct ptr_ring *q; @@ -621,6 +630,8 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, bq->count = 0; spin_unlock(&q->producer_lock); + __list_del_clearprev(&bq->flush_node); + /* Feedback loop via tracepoints */ trace_xdp_cpumap_enqueue(rcpu->map_id, processed, drops, to_cpu); return 0; @@ -631,10 +642,11 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, */ static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) { + struct list_head *flush_list = this_cpu_ptr(rcpu->cmap->flush_list); struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq); if (unlikely(bq->count == CPU_MAP_BULK_SIZE)) - bq_flush_to_queue(rcpu, bq, true); + bq_flush_to_queue(bq, true); /* Notice, xdp_buff/page MUST be queued here, long enough for * driver to code invoking us to finished, due to driver @@ -646,6 +658,10 @@ static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) * operation, when completing napi->poll call. */ bq->q[bq->count++] = xdpf; + + if (!bq->flush_node.prev) + list_add(&bq->flush_node, flush_list); + return 0; } @@ -665,41 +681,16 @@ int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, return 0; } -void __cpu_map_insert_ctx(struct bpf_map *map, u32 bit) -{ - struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); - unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed); - - __set_bit(bit, bitmap); -} - void __cpu_map_flush(struct bpf_map *map) { struct bpf_cpu_map *cmap = container_of(map, struct bpf_cpu_map, map); - unsigned long *bitmap = this_cpu_ptr(cmap->flush_needed); - u32 bit; - - /* The napi->poll softirq makes sure __cpu_map_insert_ctx() - * and __cpu_map_flush() happen on same CPU. Thus, the percpu - * bitmap indicate which percpu bulkq have packets. - */ - for_each_set_bit(bit, bitmap, map->max_entries) { - struct bpf_cpu_map_entry *rcpu = READ_ONCE(cmap->cpu_map[bit]); - struct xdp_bulk_queue *bq; - - /* This is possible if entry is removed by user space - * between xdp redirect and flush op. - */ - if (unlikely(!rcpu)) - continue; - - __clear_bit(bit, bitmap); + struct list_head *flush_list = this_cpu_ptr(cmap->flush_list); + struct xdp_bulk_queue *bq, *tmp; - /* Flush all frames in bulkq to real queue */ - bq = this_cpu_ptr(rcpu->bulkq); - bq_flush_to_queue(rcpu, bq, true); + list_for_each_entry_safe(bq, tmp, flush_list, flush_node) { + bq_flush_to_queue(bq, true); /* If already running, costs spin_lock_irqsave + smb_mb */ - wake_up_process(rcpu->kthread); + wake_up_process(bq->obj->kthread); } } diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 40e86a7e0ef0..d83cf8ccc872 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -17,9 +17,8 @@ * datapath always has a valid copy. However, the datapath does a "flush" * operation that pushes any pending packets in the driver outside the RCU * critical section. Each bpf_dtab_netdev tracks these pending operations using - * an atomic per-cpu bitmap. The bpf_dtab_netdev object will not be destroyed - * until all bits are cleared indicating outstanding flush operations have - * completed. + * a per-cpu flush list. The bpf_dtab_netdev object will not be destroyed until + * this list is empty, indicating outstanding flush operations have completed. * * BPF syscalls may race with BPF program calls on any of the update, delete * or lookup operations. As noted above the xchg() operation also keep the @@ -48,9 +47,13 @@ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) #define DEV_MAP_BULK_SIZE 16 +struct bpf_dtab_netdev; + struct xdp_bulk_queue { struct xdp_frame *q[DEV_MAP_BULK_SIZE]; + struct list_head flush_node; struct net_device *dev_rx; + struct bpf_dtab_netdev *obj; unsigned int count; }; @@ -65,23 +68,18 @@ struct bpf_dtab_netdev { struct bpf_dtab { struct bpf_map map; struct bpf_dtab_netdev **netdev_map; - unsigned long __percpu *flush_needed; + struct list_head __percpu *flush_list; struct list_head list; }; static DEFINE_SPINLOCK(dev_map_lock); static LIST_HEAD(dev_map_list); -static u64 dev_map_bitmap_size(const union bpf_attr *attr) -{ - return BITS_TO_LONGS((u64) attr->max_entries) * sizeof(unsigned long); -} - static struct bpf_map *dev_map_alloc(union bpf_attr *attr) { struct bpf_dtab *dtab; + int err, cpu; u64 cost; - int err; if (!capable(CAP_NET_ADMIN)) return ERR_PTR(-EPERM); @@ -91,6 +89,11 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); + /* Lookup returns a pointer straight to dev->ifindex, so make sure the + * verifier prevents writes from the BPF side + */ + attr->map_flags |= BPF_F_RDONLY_PROG; + dtab = kzalloc(sizeof(*dtab), GFP_USER); if (!dtab) return ERR_PTR(-ENOMEM); @@ -99,7 +102,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) /* make sure page count doesn't overflow */ cost = (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *); - cost += dev_map_bitmap_size(attr) * num_possible_cpus(); + cost += sizeof(struct list_head) * num_possible_cpus(); /* if map size is larger than memlock limit, reject it */ err = bpf_map_charge_init(&dtab->map.memory, cost); @@ -108,28 +111,30 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) err = -ENOMEM; - /* A per cpu bitfield with a bit per possible net device */ - dtab->flush_needed = __alloc_percpu_gfp(dev_map_bitmap_size(attr), - __alignof__(unsigned long), - GFP_KERNEL | __GFP_NOWARN); - if (!dtab->flush_needed) + dtab->flush_list = alloc_percpu(struct list_head); + if (!dtab->flush_list) goto free_charge; + for_each_possible_cpu(cpu) + INIT_LIST_HEAD(per_cpu_ptr(dtab->flush_list, cpu)); + dtab->netdev_map = bpf_map_area_alloc(dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *), dtab->map.numa_node); if (!dtab->netdev_map) - goto free_charge; + goto free_percpu; spin_lock(&dev_map_lock); list_add_tail_rcu(&dtab->list, &dev_map_list); spin_unlock(&dev_map_lock); return &dtab->map; + +free_percpu: + free_percpu(dtab->flush_list); free_charge: bpf_map_charge_finish(&dtab->map.memory); free_dtab: - free_percpu(dtab->flush_needed); kfree(dtab); return ERR_PTR(err); } @@ -158,14 +163,14 @@ static void dev_map_free(struct bpf_map *map) rcu_barrier(); /* To ensure all pending flush operations have completed wait for flush - * bitmap to indicate all flush_needed bits to be zero on _all_ cpus. + * list to empty on _all_ cpus. * Because the above synchronize_rcu() ensures the map is disconnected - * from the program we can assume no new bits will be set. + * from the program we can assume no new items will be added. */ for_each_online_cpu(cpu) { - unsigned long *bitmap = per_cpu_ptr(dtab->flush_needed, cpu); + struct list_head *flush_list = per_cpu_ptr(dtab->flush_list, cpu); - while (!bitmap_empty(bitmap, dtab->map.max_entries)) + while (!list_empty(flush_list)) cond_resched(); } @@ -181,7 +186,7 @@ static void dev_map_free(struct bpf_map *map) kfree(dev); } - free_percpu(dtab->flush_needed); + free_percpu(dtab->flush_list); bpf_map_area_free(dtab->netdev_map); kfree(dtab); } @@ -203,18 +208,10 @@ static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) return 0; } -void __dev_map_insert_ctx(struct bpf_map *map, u32 bit) -{ - struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); - unsigned long *bitmap = this_cpu_ptr(dtab->flush_needed); - - __set_bit(bit, bitmap); -} - -static int bq_xmit_all(struct bpf_dtab_netdev *obj, - struct xdp_bulk_queue *bq, u32 flags, +static int bq_xmit_all(struct xdp_bulk_queue *bq, u32 flags, bool in_napi_ctx) { + struct bpf_dtab_netdev *obj = bq->obj; struct net_device *dev = obj->dev; int sent = 0, drops = 0, err = 0; int i; @@ -241,6 +238,7 @@ out: trace_xdp_devmap_xmit(&obj->dtab->map, obj->bit, sent, drops, bq->dev_rx, dev, err); bq->dev_rx = NULL; + __list_del_clearprev(&bq->flush_node); return 0; error: /* If ndo_xdp_xmit fails with an errno, no frames have been @@ -263,31 +261,18 @@ error: * from the driver before returning from its napi->poll() routine. The poll() * routine is called either from busy_poll context or net_rx_action signaled * from NET_RX_SOFTIRQ. Either way the poll routine must complete before the - * net device can be torn down. On devmap tear down we ensure the ctx bitmap - * is zeroed before completing to ensure all flush operations have completed. + * net device can be torn down. On devmap tear down we ensure the flush list + * is empty before completing to ensure all flush operations have completed. */ void __dev_map_flush(struct bpf_map *map) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); - unsigned long *bitmap = this_cpu_ptr(dtab->flush_needed); - u32 bit; + struct list_head *flush_list = this_cpu_ptr(dtab->flush_list); + struct xdp_bulk_queue *bq, *tmp; rcu_read_lock(); - for_each_set_bit(bit, bitmap, map->max_entries) { - struct bpf_dtab_netdev *dev = READ_ONCE(dtab->netdev_map[bit]); - struct xdp_bulk_queue *bq; - - /* This is possible if the dev entry is removed by user space - * between xdp redirect and flush op. - */ - if (unlikely(!dev)) - continue; - - bq = this_cpu_ptr(dev->bulkq); - bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, true); - - __clear_bit(bit, bitmap); - } + list_for_each_entry_safe(bq, tmp, flush_list, flush_node) + bq_xmit_all(bq, XDP_XMIT_FLUSH, true); rcu_read_unlock(); } @@ -314,10 +299,11 @@ static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf, struct net_device *dev_rx) { + struct list_head *flush_list = this_cpu_ptr(obj->dtab->flush_list); struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq); if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) - bq_xmit_all(obj, bq, 0, true); + bq_xmit_all(bq, 0, true); /* Ingress dev_rx will be the same for all xdp_frame's in * bulk_queue, because bq stored per-CPU and must be flushed @@ -327,6 +313,10 @@ static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf, bq->dev_rx = dev_rx; bq->q[bq->count++] = xdpf; + + if (!bq->flush_node.prev) + list_add(&bq->flush_node, flush_list); + return 0; } @@ -377,17 +367,12 @@ static void dev_map_flush_old(struct bpf_dtab_netdev *dev) { if (dev->dev->netdev_ops->ndo_xdp_xmit) { struct xdp_bulk_queue *bq; - unsigned long *bitmap; - int cpu; rcu_read_lock(); for_each_online_cpu(cpu) { - bitmap = per_cpu_ptr(dev->dtab->flush_needed, cpu); - __clear_bit(dev->bit, bitmap); - bq = per_cpu_ptr(dev->bulkq, cpu); - bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, false); + bq_xmit_all(bq, XDP_XMIT_FLUSH, false); } rcu_read_unlock(); } @@ -434,8 +419,10 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, struct net *net = current->nsproxy->net_ns; gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN; struct bpf_dtab_netdev *dev, *old_dev; - u32 i = *(u32 *)key; u32 ifindex = *(u32 *)value; + struct xdp_bulk_queue *bq; + u32 i = *(u32 *)key; + int cpu; if (unlikely(map_flags > BPF_EXIST)) return -EINVAL; @@ -458,6 +445,11 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, return -ENOMEM; } + for_each_possible_cpu(cpu) { + bq = per_cpu_ptr(dev->bulkq, cpu); + bq->obj = dev; + } + dev->dev = dev_get_by_index(net, ifindex); if (!dev->dev) { free_percpu(dev->bulkq); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 7713cf39795a..b0f545e07425 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -1590,6 +1590,14 @@ bpf_prog_load_check_attach_type(enum bpf_prog_type prog_type, default: return -EINVAL; } + case BPF_PROG_TYPE_CGROUP_SOCKOPT: + switch (expected_attach_type) { + case BPF_CGROUP_SETSOCKOPT: + case BPF_CGROUP_GETSOCKOPT: + return 0; + default: + return -EINVAL; + } default: return 0; } @@ -1840,6 +1848,7 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog, switch (prog->type) { case BPF_PROG_TYPE_CGROUP_SOCK: case BPF_PROG_TYPE_CGROUP_SOCK_ADDR: + case BPF_PROG_TYPE_CGROUP_SOCKOPT: return attach_type == prog->expected_attach_type ? 0 : -EINVAL; case BPF_PROG_TYPE_CGROUP_SKB: return prog->enforce_expected_attach_type && @@ -1912,6 +1921,10 @@ static int bpf_prog_attach(const union bpf_attr *attr) case BPF_CGROUP_SYSCTL: ptype = BPF_PROG_TYPE_CGROUP_SYSCTL; break; + case BPF_CGROUP_GETSOCKOPT: + case BPF_CGROUP_SETSOCKOPT: + ptype = BPF_PROG_TYPE_CGROUP_SOCKOPT; + break; default: return -EINVAL; } @@ -1995,6 +2008,10 @@ static int bpf_prog_detach(const union bpf_attr *attr) case BPF_CGROUP_SYSCTL: ptype = BPF_PROG_TYPE_CGROUP_SYSCTL; break; + case BPF_CGROUP_GETSOCKOPT: + case BPF_CGROUP_SETSOCKOPT: + ptype = BPF_PROG_TYPE_CGROUP_SOCKOPT; + break; default: return -EINVAL; } @@ -2031,6 +2048,8 @@ static int bpf_prog_query(const union bpf_attr *attr, case BPF_CGROUP_SOCK_OPS: case BPF_CGROUP_DEVICE: case BPF_CGROUP_SYSCTL: + case BPF_CGROUP_GETSOCKOPT: + case BPF_CGROUP_SETSOCKOPT: break; case BPF_LIRC_MODE2: return lirc_prog_query(attr, uattr); diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 0e079b2298f8..a2e763703c30 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1659,16 +1659,18 @@ static void mark_all_scalars_precise(struct bpf_verifier_env *env, } } -static int mark_chain_precision(struct bpf_verifier_env *env, int regno) +static int __mark_chain_precision(struct bpf_verifier_env *env, int regno, + int spi) { struct bpf_verifier_state *st = env->cur_state; int first_idx = st->first_insn_idx; int last_idx = env->insn_idx; struct bpf_func_state *func; struct bpf_reg_state *reg; - u32 reg_mask = 1u << regno; - u64 stack_mask = 0; + u32 reg_mask = regno >= 0 ? 1u << regno : 0; + u64 stack_mask = spi >= 0 ? 1ull << spi : 0; bool skip_first = true; + bool new_marks = false; int i, err; if (!env->allow_ptr_leaks) @@ -1676,18 +1678,43 @@ static int mark_chain_precision(struct bpf_verifier_env *env, int regno) return 0; func = st->frame[st->curframe]; - reg = &func->regs[regno]; - if (reg->type != SCALAR_VALUE) { - WARN_ONCE(1, "backtracing misuse"); - return -EFAULT; + if (regno >= 0) { + reg = &func->regs[regno]; + if (reg->type != SCALAR_VALUE) { + WARN_ONCE(1, "backtracing misuse"); + return -EFAULT; + } + if (!reg->precise) + new_marks = true; + else + reg_mask = 0; + reg->precise = true; + } + + while (spi >= 0) { + if (func->stack[spi].slot_type[0] != STACK_SPILL) { + stack_mask = 0; + break; + } + reg = &func->stack[spi].spilled_ptr; + if (reg->type != SCALAR_VALUE) { + stack_mask = 0; + break; + } + if (!reg->precise) + new_marks = true; + else + stack_mask = 0; + reg->precise = true; + break; } - if (reg->precise) - return 0; - func->regs[regno].precise = true; + if (!new_marks) + return 0; + if (!reg_mask && !stack_mask) + return 0; for (;;) { DECLARE_BITMAP(mask, 64); - bool new_marks = false; u32 history = st->jmp_history_cnt; if (env->log.level & BPF_LOG_LEVEL) @@ -1730,12 +1757,15 @@ static int mark_chain_precision(struct bpf_verifier_env *env, int regno) if (!st) break; + new_marks = false; func = st->frame[st->curframe]; bitmap_from_u64(mask, reg_mask); for_each_set_bit(i, mask, 32) { reg = &func->regs[i]; - if (reg->type != SCALAR_VALUE) + if (reg->type != SCALAR_VALUE) { + reg_mask &= ~(1u << i); continue; + } if (!reg->precise) new_marks = true; reg->precise = true; @@ -1756,11 +1786,15 @@ static int mark_chain_precision(struct bpf_verifier_env *env, int regno) return -EFAULT; } - if (func->stack[i].slot_type[0] != STACK_SPILL) + if (func->stack[i].slot_type[0] != STACK_SPILL) { + stack_mask &= ~(1ull << i); continue; + } reg = &func->stack[i].spilled_ptr; - if (reg->type != SCALAR_VALUE) + if (reg->type != SCALAR_VALUE) { + stack_mask &= ~(1ull << i); continue; + } if (!reg->precise) new_marks = true; reg->precise = true; @@ -1772,6 +1806,8 @@ static int mark_chain_precision(struct bpf_verifier_env *env, int regno) reg_mask, stack_mask); } + if (!reg_mask && !stack_mask) + break; if (!new_marks) break; @@ -1781,6 +1817,15 @@ static int mark_chain_precision(struct bpf_verifier_env *env, int regno) return 0; } +static int mark_chain_precision(struct bpf_verifier_env *env, int regno) +{ + return __mark_chain_precision(env, regno, -1); +} + +static int mark_chain_precision_stack(struct bpf_verifier_env *env, int spi) +{ + return __mark_chain_precision(env, -1, spi); +} static bool is_spillable_regtype(enum bpf_reg_type type) { @@ -2215,6 +2260,13 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env, env->seen_direct_write = true; return true; + + case BPF_PROG_TYPE_CGROUP_SOCKOPT: + if (t == BPF_WRITE) + env->seen_direct_write = true; + + return true; + default: return false; } @@ -3407,12 +3459,9 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (func_id != BPF_FUNC_get_local_storage) goto error; break; - /* devmap returns a pointer to a live net_device ifindex that we cannot - * allow to be modified from bpf side. So do not allow lookup elements - * for now. - */ case BPF_MAP_TYPE_DEVMAP: - if (func_id != BPF_FUNC_redirect_map) + if (func_id != BPF_FUNC_redirect_map && + func_id != BPF_FUNC_map_lookup_elem) goto error; break; /* Restrict bpf side of cpumap and xskmap, open when use-cases @@ -6066,6 +6115,7 @@ static int check_return_code(struct bpf_verifier_env *env) case BPF_PROG_TYPE_SOCK_OPS: case BPF_PROG_TYPE_CGROUP_DEVICE: case BPF_PROG_TYPE_CGROUP_SYSCTL: + case BPF_PROG_TYPE_CGROUP_SOCKOPT: break; default: return 0; @@ -7106,6 +7156,46 @@ static int propagate_liveness(struct bpf_verifier_env *env, return 0; } +/* find precise scalars in the previous equivalent state and + * propagate them into the current state + */ +static int propagate_precision(struct bpf_verifier_env *env, + const struct bpf_verifier_state *old) +{ + struct bpf_reg_state *state_reg; + struct bpf_func_state *state; + int i, err = 0; + + state = old->frame[old->curframe]; + state_reg = state->regs; + for (i = 0; i < BPF_REG_FP; i++, state_reg++) { + if (state_reg->type != SCALAR_VALUE || + !state_reg->precise) + continue; + if (env->log.level & BPF_LOG_LEVEL2) + verbose(env, "propagating r%d\n", i); + err = mark_chain_precision(env, i); + if (err < 0) + return err; + } + + for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { + if (state->stack[i].slot_type[0] != STACK_SPILL) + continue; + state_reg = &state->stack[i].spilled_ptr; + if (state_reg->type != SCALAR_VALUE || + !state_reg->precise) + continue; + if (env->log.level & BPF_LOG_LEVEL2) + verbose(env, "propagating fp%d\n", + (-i - 1) * BPF_REG_SIZE); + err = mark_chain_precision_stack(env, i); + if (err < 0) + return err; + } + return 0; +} + static bool states_maybe_looping(struct bpf_verifier_state *old, struct bpf_verifier_state *cur) { @@ -7198,6 +7288,14 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) * this state and will pop a new one. */ err = propagate_liveness(env, &sl->state, cur); + + /* if previous state reached the exit with precision and + * current state is equivalent to it (except precsion marks) + * the precision needs to be propagated back in + * the current state. + */ + err = err ? : push_jmp_history(env, cur); + err = err ? : propagate_precision(env, &sl->state); if (err) return err; return 1; diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c index ef7338cebd18..9bb96ace9fa1 100644 --- a/kernel/bpf/xskmap.c +++ b/kernel/bpf/xskmap.c @@ -145,8 +145,7 @@ void __xsk_map_flush(struct bpf_map *map) list_for_each_entry_safe(xs, tmp, flush_list, flush_node) { xsk_flush(xs); - __list_del(xs->flush_node.prev, xs->flush_node.next); - xs->flush_node.prev = NULL; + __list_del_clearprev(&xs->flush_node); } } diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index c102c240bb0b..ca1255d14576 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1431,6 +1431,20 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id, return err; } +static int __init send_signal_irq_work_init(void) +{ + int cpu; + struct send_signal_irq_work *work; + + for_each_possible_cpu(cpu) { + work = per_cpu_ptr(&send_signal_work, cpu); + init_irq_work(&work->irq_work, do_bpf_send_signal); + } + return 0; +} + +subsys_initcall(send_signal_irq_work_init); + #ifdef CONFIG_MODULES static int bpf_event_notify(struct notifier_block *nb, unsigned long op, void *module) @@ -1478,18 +1492,5 @@ static int __init bpf_event_init(void) return 0; } -static int __init send_signal_irq_work_init(void) -{ - int cpu; - struct send_signal_irq_work *work; - - for_each_possible_cpu(cpu) { - work = per_cpu_ptr(&send_signal_work, cpu); - init_irq_work(&work->irq_work, do_bpf_send_signal); - } - return 0; -} - fs_initcall(bpf_event_init); -subsys_initcall(send_signal_irq_work_init); #endif /* CONFIG_MODULES */ diff --git a/net/core/filter.c b/net/core/filter.c index 2014d76e0d2a..089aaea0ccc6 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2158,8 +2158,8 @@ BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) if (unlikely(flags & ~(BPF_F_INGRESS))) return TC_ACT_SHOT; - ri->ifindex = ifindex; ri->flags = flags; + ri->tgt_index = ifindex; return TC_ACT_REDIRECT; } @@ -2169,8 +2169,8 @@ int skb_do_redirect(struct sk_buff *skb) struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); struct net_device *dev; - dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->ifindex); - ri->ifindex = 0; + dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->tgt_index); + ri->tgt_index = 0; if (unlikely(!dev)) { kfree_skb(skb); return -EINVAL; @@ -3488,11 +3488,11 @@ xdp_do_redirect_slow(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog, struct bpf_redirect_info *ri) { struct net_device *fwd; - u32 index = ri->ifindex; + u32 index = ri->tgt_index; int err; fwd = dev_get_by_index_rcu(dev_net(dev), index); - ri->ifindex = 0; + ri->tgt_index = 0; if (unlikely(!fwd)) { err = -EINVAL; goto err; @@ -3523,7 +3523,6 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd, err = dev_map_enqueue(dst, xdp, dev_rx); if (unlikely(err)) return err; - __dev_map_insert_ctx(map, index); break; } case BPF_MAP_TYPE_CPUMAP: { @@ -3532,7 +3531,6 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd, err = cpu_map_enqueue(rcpu, xdp, dev_rx); if (unlikely(err)) return err; - __cpu_map_insert_ctx(map, index); break; } case BPF_MAP_TYPE_XSKMAP: { @@ -3606,18 +3604,14 @@ static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *xdp_prog, struct bpf_map *map, struct bpf_redirect_info *ri) { - u32 index = ri->ifindex; - void *fwd = NULL; + u32 index = ri->tgt_index; + void *fwd = ri->tgt_value; int err; - ri->ifindex = 0; + ri->tgt_index = 0; + ri->tgt_value = NULL; WRITE_ONCE(ri->map, NULL); - fwd = __xdp_map_lookup_elem(map, index); - if (unlikely(!fwd)) { - err = -EINVAL; - goto err; - } if (ri->map_to_flush && unlikely(ri->map_to_flush != map)) xdp_do_flush_map(); @@ -3653,19 +3647,14 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, struct bpf_map *map) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); - u32 index = ri->ifindex; - void *fwd = NULL; + u32 index = ri->tgt_index; + void *fwd = ri->tgt_value; int err = 0; - ri->ifindex = 0; + ri->tgt_index = 0; + ri->tgt_value = NULL; WRITE_ONCE(ri->map, NULL); - fwd = __xdp_map_lookup_elem(map, index); - if (unlikely(!fwd)) { - err = -EINVAL; - goto err; - } - if (map->map_type == BPF_MAP_TYPE_DEVMAP) { struct bpf_dtab_netdev *dst = fwd; @@ -3697,14 +3686,14 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); struct bpf_map *map = READ_ONCE(ri->map); - u32 index = ri->ifindex; + u32 index = ri->tgt_index; struct net_device *fwd; int err = 0; if (map) return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, map); - ri->ifindex = 0; + ri->tgt_index = 0; fwd = dev_get_by_index_rcu(dev_net(dev), index); if (unlikely(!fwd)) { err = -EINVAL; @@ -3732,8 +3721,9 @@ BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags) if (unlikely(flags)) return XDP_ABORTED; - ri->ifindex = ifindex; ri->flags = flags; + ri->tgt_index = ifindex; + ri->tgt_value = NULL; WRITE_ONCE(ri->map, NULL); return XDP_REDIRECT; @@ -3752,11 +3742,23 @@ BPF_CALL_3(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex, { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); - if (unlikely(flags)) + /* Lower bits of the flags are used as return code on lookup failure */ + if (unlikely(flags > XDP_TX)) return XDP_ABORTED; - ri->ifindex = ifindex; + ri->tgt_value = __xdp_map_lookup_elem(map, ifindex); + if (unlikely(!ri->tgt_value)) { + /* If the lookup fails we want to clear out the state in the + * redirect_info struct completely, so that if an eBPF program + * performs multiple lookups, the last one always takes + * precedence. + */ + WRITE_ONCE(ri->map, NULL); + return flags; + } + ri->flags = flags; + ri->tgt_index = ifindex; WRITE_ONCE(ri->map, map); return XDP_REDIRECT; @@ -5192,54 +5194,6 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = { }; #endif /* CONFIG_IPV6_SEG6_BPF */ -#define CONVERT_COMMON_TCP_SOCK_FIELDS(md_type, CONVERT) \ -do { \ - switch (si->off) { \ - case offsetof(md_type, snd_cwnd): \ - CONVERT(snd_cwnd); break; \ - case offsetof(md_type, srtt_us): \ - CONVERT(srtt_us); break; \ - case offsetof(md_type, snd_ssthresh): \ - CONVERT(snd_ssthresh); break; \ - case offsetof(md_type, rcv_nxt): \ - CONVERT(rcv_nxt); break; \ - case offsetof(md_type, snd_nxt): \ - CONVERT(snd_nxt); break; \ - case offsetof(md_type, snd_una): \ - CONVERT(snd_una); break; \ - case offsetof(md_type, mss_cache): \ - CONVERT(mss_cache); break; \ - case offsetof(md_type, ecn_flags): \ - CONVERT(ecn_flags); break; \ - case offsetof(md_type, rate_delivered): \ - CONVERT(rate_delivered); break; \ - case offsetof(md_type, rate_interval_us): \ - CONVERT(rate_interval_us); break; \ - case offsetof(md_type, packets_out): \ - CONVERT(packets_out); break; \ - case offsetof(md_type, retrans_out): \ - CONVERT(retrans_out); break; \ - case offsetof(md_type, total_retrans): \ - CONVERT(total_retrans); break; \ - case offsetof(md_type, segs_in): \ - CONVERT(segs_in); break; \ - case offsetof(md_type, data_segs_in): \ - CONVERT(data_segs_in); break; \ - case offsetof(md_type, segs_out): \ - CONVERT(segs_out); break; \ - case offsetof(md_type, data_segs_out): \ - CONVERT(data_segs_out); break; \ - case offsetof(md_type, lost_out): \ - CONVERT(lost_out); break; \ - case offsetof(md_type, sacked_out): \ - CONVERT(sacked_out); break; \ - case offsetof(md_type, bytes_received): \ - CONVERT(bytes_received); break; \ - case offsetof(md_type, bytes_acked): \ - CONVERT(bytes_acked); break; \ - } \ -} while (0) - #ifdef CONFIG_INET static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple, int dif, int sdif, u8 family, u8 proto) @@ -5590,7 +5544,8 @@ static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = { bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { - if (off < 0 || off >= offsetofend(struct bpf_tcp_sock, bytes_acked)) + if (off < 0 || off >= offsetofend(struct bpf_tcp_sock, + icsk_retransmits)) return false; if (off % size != 0) @@ -5621,8 +5576,19 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, offsetof(struct tcp_sock, FIELD)); \ } while (0) - CONVERT_COMMON_TCP_SOCK_FIELDS(struct bpf_tcp_sock, - BPF_TCP_SOCK_GET_COMMON); +#define BPF_INET_SOCK_GET_COMMON(FIELD) \ + do { \ + BUILD_BUG_ON(FIELD_SIZEOF(struct inet_connection_sock, \ + FIELD) > \ + FIELD_SIZEOF(struct bpf_tcp_sock, FIELD)); \ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ + struct inet_connection_sock, \ + FIELD), \ + si->dst_reg, si->src_reg, \ + offsetof( \ + struct inet_connection_sock, \ + FIELD)); \ + } while (0) if (insn > insn_buf) return insn - insn_buf; @@ -5638,6 +5604,81 @@ u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type, offsetof(struct tcp_sock, rtt_min) + offsetof(struct minmax_sample, v)); break; + case offsetof(struct bpf_tcp_sock, snd_cwnd): + BPF_TCP_SOCK_GET_COMMON(snd_cwnd); + break; + case offsetof(struct bpf_tcp_sock, srtt_us): + BPF_TCP_SOCK_GET_COMMON(srtt_us); + break; + case offsetof(struct bpf_tcp_sock, snd_ssthresh): + BPF_TCP_SOCK_GET_COMMON(snd_ssthresh); + break; + case offsetof(struct bpf_tcp_sock, rcv_nxt): + BPF_TCP_SOCK_GET_COMMON(rcv_nxt); + break; + case offsetof(struct bpf_tcp_sock, snd_nxt): + BPF_TCP_SOCK_GET_COMMON(snd_nxt); + break; + case offsetof(struct bpf_tcp_sock, snd_una): + BPF_TCP_SOCK_GET_COMMON(snd_una); + break; + case offsetof(struct bpf_tcp_sock, mss_cache): + BPF_TCP_SOCK_GET_COMMON(mss_cache); + break; + case offsetof(struct bpf_tcp_sock, ecn_flags): + BPF_TCP_SOCK_GET_COMMON(ecn_flags); + break; + case offsetof(struct bpf_tcp_sock, rate_delivered): + BPF_TCP_SOCK_GET_COMMON(rate_delivered); + break; + case offsetof(struct bpf_tcp_sock, rate_interval_us): + BPF_TCP_SOCK_GET_COMMON(rate_interval_us); + break; + case offsetof(struct bpf_tcp_sock, packets_out): + BPF_TCP_SOCK_GET_COMMON(packets_out); + break; + case offsetof(struct bpf_tcp_sock, retrans_out): + BPF_TCP_SOCK_GET_COMMON(retrans_out); + break; + case offsetof(struct bpf_tcp_sock, total_retrans): + BPF_TCP_SOCK_GET_COMMON(total_retrans); + break; + case offsetof(struct bpf_tcp_sock, segs_in): + BPF_TCP_SOCK_GET_COMMON(segs_in); + break; + case offsetof(struct bpf_tcp_sock, data_segs_in): + BPF_TCP_SOCK_GET_COMMON(data_segs_in); + break; + case offsetof(struct bpf_tcp_sock, segs_out): + BPF_TCP_SOCK_GET_COMMON(segs_out); + break; + case offsetof(struct bpf_tcp_sock, data_segs_out): + BPF_TCP_SOCK_GET_COMMON(data_segs_out); + break; + case offsetof(struct bpf_tcp_sock, lost_out): + BPF_TCP_SOCK_GET_COMMON(lost_out); + break; + case offsetof(struct bpf_tcp_sock, sacked_out): + BPF_TCP_SOCK_GET_COMMON(sacked_out); + break; + case offsetof(struct bpf_tcp_sock, bytes_received): + BPF_TCP_SOCK_GET_COMMON(bytes_received); + break; + case offsetof(struct bpf_tcp_sock, bytes_acked): + BPF_TCP_SOCK_GET_COMMON(bytes_acked); + break; + case offsetof(struct bpf_tcp_sock, dsack_dups): + BPF_TCP_SOCK_GET_COMMON(dsack_dups); + break; + case offsetof(struct bpf_tcp_sock, delivered): + BPF_TCP_SOCK_GET_COMMON(delivered); + break; + case offsetof(struct bpf_tcp_sock, delivered_ce): + BPF_TCP_SOCK_GET_COMMON(delivered_ce); + break; + case offsetof(struct bpf_tcp_sock, icsk_retransmits): + BPF_INET_SOCK_GET_COMMON(icsk_retransmits); + break; } return insn - insn_buf; @@ -5651,7 +5692,7 @@ BPF_CALL_1(bpf_tcp_sock, struct sock *, sk) return (unsigned long)NULL; } -static const struct bpf_func_proto bpf_tcp_sock_proto = { +const struct bpf_func_proto bpf_tcp_sock_proto = { .func = bpf_tcp_sock, .gpl_only = false, .ret_type = RET_PTR_TO_TCP_SOCK_OR_NULL, @@ -7911,9 +7952,6 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ); \ } while (0) - CONVERT_COMMON_TCP_SOCK_FIELDS(struct bpf_sock_ops, - SOCK_OPS_GET_TCP_SOCK_FIELD); - if (insn > insn_buf) return insn - insn_buf; @@ -8083,6 +8121,69 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, SOCK_OPS_GET_OR_SET_FIELD(sk_txhash, sk_txhash, struct sock, type); break; + case offsetof(struct bpf_sock_ops, snd_cwnd): + SOCK_OPS_GET_TCP_SOCK_FIELD(snd_cwnd); + break; + case offsetof(struct bpf_sock_ops, srtt_us): + SOCK_OPS_GET_TCP_SOCK_FIELD(srtt_us); + break; + case offsetof(struct bpf_sock_ops, snd_ssthresh): + SOCK_OPS_GET_TCP_SOCK_FIELD(snd_ssthresh); + break; + case offsetof(struct bpf_sock_ops, rcv_nxt): + SOCK_OPS_GET_TCP_SOCK_FIELD(rcv_nxt); + break; + case offsetof(struct bpf_sock_ops, snd_nxt): + SOCK_OPS_GET_TCP_SOCK_FIELD(snd_nxt); + break; + case offsetof(struct bpf_sock_ops, snd_una): + SOCK_OPS_GET_TCP_SOCK_FIELD(snd_una); + break; + case offsetof(struct bpf_sock_ops, mss_cache): + SOCK_OPS_GET_TCP_SOCK_FIELD(mss_cache); + break; + case offsetof(struct bpf_sock_ops, ecn_flags): + SOCK_OPS_GET_TCP_SOCK_FIELD(ecn_flags); + break; + case offsetof(struct bpf_sock_ops, rate_delivered): + SOCK_OPS_GET_TCP_SOCK_FIELD(rate_delivered); + break; + case offsetof(struct bpf_sock_ops, rate_interval_us): + SOCK_OPS_GET_TCP_SOCK_FIELD(rate_interval_us); + break; + case offsetof(struct bpf_sock_ops, packets_out): + SOCK_OPS_GET_TCP_SOCK_FIELD(packets_out); + break; + case offsetof(struct bpf_sock_ops, retrans_out): + SOCK_OPS_GET_TCP_SOCK_FIELD(retrans_out); + break; + case offsetof(struct bpf_sock_ops, total_retrans): + SOCK_OPS_GET_TCP_SOCK_FIELD(total_retrans); + break; + case offsetof(struct bpf_sock_ops, segs_in): + SOCK_OPS_GET_TCP_SOCK_FIELD(segs_in); + break; + case offsetof(struct bpf_sock_ops, data_segs_in): + SOCK_OPS_GET_TCP_SOCK_FIELD(data_segs_in); + break; + case offsetof(struct bpf_sock_ops, segs_out): + SOCK_OPS_GET_TCP_SOCK_FIELD(segs_out); + break; + case offsetof(struct bpf_sock_ops, data_segs_out): + SOCK_OPS_GET_TCP_SOCK_FIELD(data_segs_out); + break; + case offsetof(struct bpf_sock_ops, lost_out): + SOCK_OPS_GET_TCP_SOCK_FIELD(lost_out); + break; + case offsetof(struct bpf_sock_ops, sacked_out): + SOCK_OPS_GET_TCP_SOCK_FIELD(sacked_out); + break; + case offsetof(struct bpf_sock_ops, bytes_received): + SOCK_OPS_GET_TCP_SOCK_FIELD(bytes_received); + break; + case offsetof(struct bpf_sock_ops, bytes_acked): + SOCK_OPS_GET_TCP_SOCK_FIELD(bytes_acked); + break; case offsetof(struct bpf_sock_ops, sk): *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, diff --git a/net/core/xdp.c b/net/core/xdp.c index b29d7b513a18..829377cc83db 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -85,7 +85,7 @@ static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu) kfree(xa); } -bool __mem_id_disconnect(int id, bool force) +static bool __mem_id_disconnect(int id, bool force) { struct xdp_mem_allocator *xa; bool safe_to_remove = true; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b71efeb0ae5b..c21e8a22fb3b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -778,6 +778,8 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us) tp->rttvar_us -= (tp->rttvar_us - tp->mdev_max_us) >> 2; tp->rtt_seq = tp->snd_nxt; tp->mdev_max_us = tcp_rto_min_us(sk); + + tcp_bpf_rtt(sk); } } else { /* no previous measure. */ @@ -786,6 +788,8 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us) tp->rttvar_us = max(tp->mdev_us, tcp_rto_min_us(sk)); tp->mdev_max_us = tp->rttvar_us; tp->rtt_seq = tp->snd_nxt; + + tcp_bpf_rtt(sk); } tp->srtt_us = max(1U, srtt); } diff --git a/net/socket.c b/net/socket.c index a865708940f9..d97b74f762e8 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2050,6 +2050,8 @@ SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size, static int __sys_setsockopt(int fd, int level, int optname, char __user *optval, int optlen) { + mm_segment_t oldfs = get_fs(); + char *kernel_optval = NULL; int err, fput_needed; struct socket *sock; @@ -2062,6 +2064,22 @@ static int __sys_setsockopt(int fd, int level, int optname, if (err) goto out_put; + err = BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock->sk, &level, + &optname, optval, &optlen, + &kernel_optval); + + if (err < 0) { + goto out_put; + } else if (err > 0) { + err = 0; + goto out_put; + } + + if (kernel_optval) { + set_fs(KERNEL_DS); + optval = (char __user __force *)kernel_optval; + } + if (level == SOL_SOCKET) err = sock_setsockopt(sock, level, optname, optval, @@ -2070,6 +2088,11 @@ static int __sys_setsockopt(int fd, int level, int optname, err = sock->ops->setsockopt(sock, level, optname, optval, optlen); + + if (kernel_optval) { + set_fs(oldfs); + kfree(kernel_optval); + } out_put: fput_light(sock->file, fput_needed); } @@ -2092,6 +2115,7 @@ static int __sys_getsockopt(int fd, int level, int optname, { int err, fput_needed; struct socket *sock; + int max_optlen; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock != NULL) { @@ -2099,6 +2123,8 @@ static int __sys_getsockopt(int fd, int level, int optname, if (err) goto out_put; + max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen); + if (level == SOL_SOCKET) err = sock_getsockopt(sock, level, optname, optval, @@ -2107,6 +2133,10 @@ static int __sys_getsockopt(int fd, int level, int optname, err = sock->ops->getsockopt(sock, level, optname, optval, optlen); + + err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level, optname, + optval, optlen, + max_optlen, err); out_put: fput_light(sock->file, fput_needed); } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index a14e8864e4fa..74417a851ed5 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -37,6 +37,12 @@ bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) READ_ONCE(xs->umem->fq); } +bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt) +{ + return xskq_has_addrs(umem->fq, cnt); +} +EXPORT_SYMBOL(xsk_umem_has_addrs); + u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr) { return xskq_peek_addr(umem->fq, addr); @@ -166,22 +172,18 @@ void xsk_umem_consume_tx_done(struct xdp_umem *umem) } EXPORT_SYMBOL(xsk_umem_consume_tx_done); -bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, u32 *len) +bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc) { - struct xdp_desc desc; struct xdp_sock *xs; rcu_read_lock(); list_for_each_entry_rcu(xs, &umem->xsk_list, list) { - if (!xskq_peek_desc(xs->tx, &desc)) + if (!xskq_peek_desc(xs->tx, desc)) continue; - if (xskq_produce_addr_lazy(umem->cq, desc.addr)) + if (xskq_produce_addr_lazy(umem->cq, desc->addr)) goto out; - *dma = xdp_umem_get_dma(umem, desc.addr); - *len = desc.len; - xskq_discard_desc(xs->tx); rcu_read_unlock(); return true; @@ -644,6 +646,26 @@ static int xsk_getsockopt(struct socket *sock, int level, int optname, return 0; } + case XDP_OPTIONS: + { + struct xdp_options opts = {}; + + if (len < sizeof(opts)) + return -EINVAL; + + mutex_lock(&xs->mutex); + if (xs->zc) + opts.flags |= XDP_OPTIONS_ZEROCOPY; + mutex_unlock(&xs->mutex); + + len = sizeof(opts); + if (copy_to_user(optval, &opts, len)) + return -EFAULT; + if (put_user(len, optlen)) + return -EFAULT; + + return 0; + } default: break; } diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 88b9ae24658d..12b49784a6d5 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -117,6 +117,20 @@ static inline u32 xskq_nb_free(struct xsk_queue *q, u32 producer, u32 dcnt) return q->nentries - (producer - q->cons_tail); } +static inline bool xskq_has_addrs(struct xsk_queue *q, u32 cnt) +{ + u32 entries = q->prod_tail - q->cons_tail; + + if (entries >= cnt) + return true; + + /* Refresh the local pointer. */ + q->prod_tail = READ_ONCE(q->ring->producer); + entries = q->prod_tail - q->cons_tail; + + return entries >= cnt; +} + /* UMEM queue */ static inline bool xskq_is_valid_addr(struct xsk_queue *q, u64 addr) diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 0917f8cf4fab..f90daadfbc89 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -154,6 +154,7 @@ always += tcp_iw_kern.o always += tcp_clamp_kern.o always += tcp_basertt_kern.o always += tcp_tos_reflect_kern.o +always += tcp_dumpstats_kern.o always += xdp_redirect_kern.o always += xdp_redirect_map_kern.o always += xdp_redirect_cpu_kern.o @@ -168,6 +169,7 @@ always += task_fd_query_kern.o always += xdp_sample_pkts_kern.o always += ibumad_kern.o always += hbm_out_kern.o +always += hbm_edt_kern.o KBUILD_HOSTCFLAGS += -I$(objtree)/usr/include KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/bpf/ @@ -272,6 +274,7 @@ $(src)/*.c: verify_target_bpf $(LIBBPF) $(obj)/tracex5_kern.o: $(obj)/syscall_nrs.h $(obj)/hbm_out_kern.o: $(src)/hbm.h $(src)/hbm_kern.h $(obj)/hbm.o: $(src)/hbm.h +$(obj)/hbm_edt_kern.o: $(src)/hbm.h $(src)/hbm_kern.h # asm/sysreg.h - inline assembly used by it is incompatible with llvm. # But, there is no easy way to fix it, so just exclude it since it is diff --git a/samples/bpf/do_hbm_test.sh b/samples/bpf/do_hbm_test.sh index e48b047d4646..ffe4c0607341 100755 --- a/samples/bpf/do_hbm_test.sh +++ b/samples/bpf/do_hbm_test.sh @@ -14,7 +14,7 @@ Usage() { echo "loads. The output is the goodput in Mbps (unless -D was used)." echo "" echo "USAGE: $name [out] [-b=<prog>|--bpf=<prog>] [-c=<cc>|--cc=<cc>]" - echo " [-D] [-d=<delay>|--delay=<delay>] [--debug] [-E]" + echo " [-D] [-d=<delay>|--delay=<delay>] [--debug] [-E] [--edt]" echo " [-f=<#flows>|--flows=<#flows>] [-h] [-i=<id>|--id=<id >]" echo " [-l] [-N] [--no_cn] [-p=<port>|--port=<port>] [-P]" echo " [-q=<qdisc>] [-R] [-s=<server>|--server=<server]" @@ -30,6 +30,7 @@ Usage() { echo " other detailed information. This information is" echo " test dependent (i.e. iperf3 or netperf)." echo " -E enable ECN (not required for dctcp)" + echo " --edt use fq's Earliest Departure Time (requires fq)" echo " -f or --flows number of concurrent flows (default=1)" echo " -i or --id cgroup id (an integer, default is 1)" echo " -N use netperf instead of iperf3" @@ -130,13 +131,12 @@ processArgs () { details=1 ;; -E) - ecn=1 + ecn=1 + ;; + --edt) + flags="$flags --edt" + qdisc="fq" ;; - # Support for upcomming fq Early Departure Time egress rate limiting - #--edt) - # prog="hbm_out_edt_kern.o" - # qdisc="fq" - # ;; -f=*|--flows=*) flows="${i#*=}" ;; @@ -228,8 +228,8 @@ if [ "$netem" -ne "0" ] ; then tc qdisc del dev lo root > /dev/null 2>&1 tc qdisc add dev lo root netem delay $netem\ms > /dev/null 2>&1 elif [ "$qdisc" != "" ] ; then - tc qdisc del dev lo root > /dev/null 2>&1 - tc qdisc add dev lo root $qdisc > /dev/null 2>&1 + tc qdisc del dev eth0 root > /dev/null 2>&1 + tc qdisc add dev eth0 root $qdisc > /dev/null 2>&1 fi n=0 @@ -399,7 +399,9 @@ fi if [ "$netem" -ne "0" ] ; then tc qdisc del dev lo root > /dev/null 2>&1 fi - +if [ "$qdisc" != "" ] ; then + tc qdisc del dev eth0 root > /dev/null 2>&1 +fi sleep 2 hbmPid=`ps ax | grep "hbm " | grep --invert-match "grep" | awk '{ print $1 }'` diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c index b905b32ff185..e0fbab9bec83 100644 --- a/samples/bpf/hbm.c +++ b/samples/bpf/hbm.c @@ -62,6 +62,7 @@ bool loopback_flag; bool debugFlag; bool work_conserving_flag; bool no_cn_flag; +bool edt_flag; static void Usage(void); static void read_trace_pipe2(void); @@ -372,9 +373,14 @@ static int run_bpf_prog(char *prog, int cg_id) fprintf(fout, "avg rtt:%d\n", (int)(qstats.sum_rtt / (qstats.pkts_total + 1))); // Average credit - fprintf(fout, "avg credit:%d\n", - (int)(qstats.sum_credit / - (1500 * ((int)qstats.pkts_total) + 1))); + if (edt_flag) + fprintf(fout, "avg credit_ms:%.03f\n", + (qstats.sum_credit / + (qstats.pkts_total + 1.0)) / 1000000.0); + else + fprintf(fout, "avg credit:%d\n", + (int)(qstats.sum_credit / + (1500 * ((int)qstats.pkts_total ) + 1))); // Return values stats for (k = 0; k < RET_VAL_COUNT; k++) { @@ -408,6 +414,7 @@ static void Usage(void) " Where:\n" " -o indicates egress direction (default)\n" " -d print BPF trace debug buffer\n" + " --edt use fq's Earliest Departure Time\n" " -l also limit flows using loopback\n" " -n <#> to create cgroup \"/hbm#\" and attach prog\n" " Default is /hbm1\n" @@ -433,6 +440,7 @@ int main(int argc, char **argv) char *optstring = "iodln:r:st:wh"; struct option loptions[] = { {"no_cn", 0, NULL, 1}, + {"edt", 0, NULL, 2}, {NULL, 0, NULL, 0} }; @@ -441,6 +449,10 @@ int main(int argc, char **argv) case 1: no_cn_flag = true; break; + case 2: + prog = "hbm_edt_kern.o"; + edt_flag = true; + break; case'o': break; case 'd': diff --git a/samples/bpf/hbm_edt_kern.c b/samples/bpf/hbm_edt_kern.c new file mode 100644 index 000000000000..a65b677acdb0 --- /dev/null +++ b/samples/bpf/hbm_edt_kern.c @@ -0,0 +1,168 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * Sample Host Bandwidth Manager (HBM) BPF program. + * + * A cgroup skb BPF egress program to limit cgroup output bandwidth. + * It uses a modified virtual token bucket queue to limit average + * egress bandwidth. The implementation uses credits instead of tokens. + * Negative credits imply that queueing would have happened (this is + * a virtual queue, so no queueing is done by it. However, queueing may + * occur at the actual qdisc (which is not used for rate limiting). + * + * This implementation uses 3 thresholds, one to start marking packets and + * the other two to drop packets: + * CREDIT + * - <--------------------------|------------------------> + + * | | | 0 + * | Large pkt | + * | drop thresh | + * Small pkt drop Mark threshold + * thresh + * + * The effect of marking depends on the type of packet: + * a) If the packet is ECN enabled and it is a TCP packet, then the packet + * is ECN marked. + * b) If the packet is a TCP packet, then we probabilistically call tcp_cwr + * to reduce the congestion window. The current implementation uses a linear + * distribution (0% probability at marking threshold, 100% probability + * at drop threshold). + * c) If the packet is not a TCP packet, then it is dropped. + * + * If the credit is below the drop threshold, the packet is dropped. If it + * is a TCP packet, then it also calls tcp_cwr since packets dropped by + * by a cgroup skb BPF program do not automatically trigger a call to + * tcp_cwr in the current kernel code. + * + * This BPF program actually uses 2 drop thresholds, one threshold + * for larger packets (>= 120 bytes) and another for smaller packets. This + * protects smaller packets such as SYNs, ACKs, etc. + * + * The default bandwidth limit is set at 1Gbps but this can be changed by + * a user program through a shared BPF map. In addition, by default this BPF + * program does not limit connections using loopback. This behavior can be + * overwritten by the user program. There is also an option to calculate + * some statistics, such as percent of packets marked or dropped, which + * a user program, such as hbm, can access. + */ + +#include "hbm_kern.h" + +SEC("cgroup_skb/egress") +int _hbm_out_cg(struct __sk_buff *skb) +{ + long long delta = 0, delta_send; + unsigned long long curtime, sendtime; + struct hbm_queue_stats *qsp = NULL; + unsigned int queue_index = 0; + bool congestion_flag = false; + bool ecn_ce_flag = false; + struct hbm_pkt_info pkti = {}; + struct hbm_vqueue *qdp; + bool drop_flag = false; + bool cwr_flag = false; + int len = skb->len; + int rv = ALLOW_PKT; + + qsp = bpf_map_lookup_elem(&queue_stats, &queue_index); + + // Check if we should ignore loopback traffic + if (qsp != NULL && !qsp->loopback && (skb->ifindex == 1)) + return ALLOW_PKT; + + hbm_get_pkt_info(skb, &pkti); + + // We may want to account for the length of headers in len + // calculation, like ETH header + overhead, specially if it + // is a gso packet. But I am not doing it right now. + + qdp = bpf_get_local_storage(&queue_state, 0); + if (!qdp) + return ALLOW_PKT; + if (qdp->lasttime == 0) + hbm_init_edt_vqueue(qdp, 1024); + + curtime = bpf_ktime_get_ns(); + + // Begin critical section + bpf_spin_lock(&qdp->lock); + delta = qdp->lasttime - curtime; + // bound bursts to 100us + if (delta < -BURST_SIZE_NS) { + // negative delta is a credit that allows bursts + qdp->lasttime = curtime - BURST_SIZE_NS; + delta = -BURST_SIZE_NS; + } + sendtime = qdp->lasttime; + delta_send = BYTES_TO_NS(len, qdp->rate); + __sync_add_and_fetch(&(qdp->lasttime), delta_send); + bpf_spin_unlock(&qdp->lock); + // End critical section + + // Set EDT of packet + skb->tstamp = sendtime; + + // Check if we should update rate + if (qsp != NULL && (qsp->rate * 128) != qdp->rate) + qdp->rate = qsp->rate * 128; + + // Set flags (drop, congestion, cwr) + // last packet will be sent in the future, bound latency + if (delta > DROP_THRESH_NS || (delta > LARGE_PKT_DROP_THRESH_NS && + len > LARGE_PKT_THRESH)) { + drop_flag = true; + if (pkti.is_tcp && pkti.ecn == 0) + cwr_flag = true; + } else if (delta > MARK_THRESH_NS) { + if (pkti.is_tcp) + congestion_flag = true; + else + drop_flag = true; + } + + if (congestion_flag) { + if (bpf_skb_ecn_set_ce(skb)) { + ecn_ce_flag = true; + } else { + if (pkti.is_tcp) { + unsigned int rand = bpf_get_prandom_u32(); + + if (delta >= MARK_THRESH_NS + + (rand % MARK_REGION_SIZE_NS)) { + // Do congestion control + cwr_flag = true; + } + } else if (len > LARGE_PKT_THRESH) { + // Problem if too many small packets? + drop_flag = true; + congestion_flag = false; + } + } + } + + if (pkti.is_tcp && drop_flag && pkti.packets_out <= 1) { + drop_flag = false; + cwr_flag = true; + congestion_flag = false; + } + + if (qsp != NULL && qsp->no_cn) + cwr_flag = false; + + hbm_update_stats(qsp, len, curtime, congestion_flag, drop_flag, + cwr_flag, ecn_ce_flag, &pkti, (int) delta); + + if (drop_flag) { + __sync_add_and_fetch(&(qdp->lasttime), -delta_send); + rv = DROP_PKT; + } + + if (cwr_flag) + rv |= CWR; + return rv; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/hbm_kern.h b/samples/bpf/hbm_kern.h index be19cf1d5cd5..aa207a2eebbd 100644 --- a/samples/bpf/hbm_kern.h +++ b/samples/bpf/hbm_kern.h @@ -29,6 +29,7 @@ #define DROP_PKT 0 #define ALLOW_PKT 1 #define TCP_ECN_OK 1 +#define CWR 2 #ifndef HBM_DEBUG // Define HBM_DEBUG to enable debugging #undef bpf_printk @@ -45,8 +46,18 @@ #define MAX_CREDIT (100 * MAX_BYTES_PER_PACKET) #define INIT_CREDIT (INITIAL_CREDIT_PACKETS * MAX_BYTES_PER_PACKET) +// Time base accounting for fq's EDT +#define BURST_SIZE_NS 100000 // 100us +#define MARK_THRESH_NS 50000 // 50us +#define DROP_THRESH_NS 500000 // 500us +// Reserve 20us of queuing for small packets (less than 120 bytes) +#define LARGE_PKT_DROP_THRESH_NS (DROP_THRESH_NS - 20000) +#define MARK_REGION_SIZE_NS (LARGE_PKT_DROP_THRESH_NS - MARK_THRESH_NS) + // rate in bytes per ns << 20 #define CREDIT_PER_NS(delta, rate) ((((u64)(delta)) * (rate)) >> 20) +#define BYTES_PER_NS(delta, rate) ((((u64)(delta)) * (rate)) >> 20) +#define BYTES_TO_NS(bytes, rate) div64_u64(((u64)(bytes)) << 20, (u64)(rate)) struct bpf_map_def SEC("maps") queue_state = { .type = BPF_MAP_TYPE_CGROUP_STORAGE, @@ -67,6 +78,7 @@ BPF_ANNOTATE_KV_PAIR(queue_stats, int, struct hbm_queue_stats); struct hbm_pkt_info { int cwnd; int rtt; + int packets_out; bool is_ip; bool is_tcp; short ecn; @@ -86,16 +98,20 @@ static int get_tcp_info(struct __sk_buff *skb, struct hbm_pkt_info *pkti) if (tp) { pkti->cwnd = tp->snd_cwnd; pkti->rtt = tp->srtt_us >> 3; + pkti->packets_out = tp->packets_out; return 0; } } } } + pkti->cwnd = 0; + pkti->rtt = 0; + pkti->packets_out = 0; return 1; } -static __always_inline void hbm_get_pkt_info(struct __sk_buff *skb, - struct hbm_pkt_info *pkti) +static void hbm_get_pkt_info(struct __sk_buff *skb, + struct hbm_pkt_info *pkti) { struct iphdr iph; struct ipv6hdr *ip6h; @@ -123,10 +139,22 @@ static __always_inline void hbm_get_pkt_info(struct __sk_buff *skb, static __always_inline void hbm_init_vqueue(struct hbm_vqueue *qdp, int rate) { - bpf_printk("Initializing queue_state, rate:%d\n", rate * 128); - qdp->lasttime = bpf_ktime_get_ns(); - qdp->credit = INIT_CREDIT; - qdp->rate = rate * 128; + bpf_printk("Initializing queue_state, rate:%d\n", rate * 128); + qdp->lasttime = bpf_ktime_get_ns(); + qdp->credit = INIT_CREDIT; + qdp->rate = rate * 128; +} + +static __always_inline void hbm_init_edt_vqueue(struct hbm_vqueue *qdp, + int rate) +{ + unsigned long long curtime; + + curtime = bpf_ktime_get_ns(); + bpf_printk("Initializing queue_state, rate:%d\n", rate * 128); + qdp->lasttime = curtime - BURST_SIZE_NS; // support initial burst + qdp->credit = 0; // not used + qdp->rate = rate * 128; } static __always_inline void hbm_update_stats(struct hbm_queue_stats *qsp, diff --git a/samples/bpf/ibumad_kern.c b/samples/bpf/ibumad_kern.c index 38b2b3f22049..f281df7e0089 100644 --- a/samples/bpf/ibumad_kern.c +++ b/samples/bpf/ibumad_kern.c @@ -31,15 +31,9 @@ struct bpf_map_def SEC("maps") write_count = { }; #undef DEBUG -#ifdef DEBUG -#define bpf_debug(fmt, ...) \ -({ \ - char ____fmt[] = fmt; \ - bpf_trace_printk(____fmt, sizeof(____fmt), \ - ##__VA_ARGS__); \ -}) -#else -#define bpf_debug(fmt, ...) +#ifndef DEBUG +#undef bpf_printk +#define bpf_printk(fmt, ...) #endif /* Taken from the current format defined in @@ -86,7 +80,7 @@ int on_ib_umad_read_recv(struct ib_umad_rw_args *ctx) u64 zero = 0, *val; u8 class = ctx->mgmt_class; - bpf_debug("ib_umad read recv : class 0x%x\n", class); + bpf_printk("ib_umad read recv : class 0x%x\n", class); val = bpf_map_lookup_elem(&read_count, &class); if (!val) { @@ -106,7 +100,7 @@ int on_ib_umad_read_send(struct ib_umad_rw_args *ctx) u64 zero = 0, *val; u8 class = ctx->mgmt_class; - bpf_debug("ib_umad read send : class 0x%x\n", class); + bpf_printk("ib_umad read send : class 0x%x\n", class); val = bpf_map_lookup_elem(&read_count, &class); if (!val) { @@ -126,7 +120,7 @@ int on_ib_umad_write(struct ib_umad_rw_args *ctx) u64 zero = 0, *val; u8 class = ctx->mgmt_class; - bpf_debug("ib_umad write : class 0x%x\n", class); + bpf_printk("ib_umad write : class 0x%x\n", class); val = bpf_map_lookup_elem(&write_count, &class); if (!val) { diff --git a/samples/bpf/tcp_bpf.readme b/samples/bpf/tcp_bpf.readme index fee746621aec..78e247f62108 100644 --- a/samples/bpf/tcp_bpf.readme +++ b/samples/bpf/tcp_bpf.readme @@ -25,4 +25,4 @@ attached to the cgroupv2). To remove (unattach) a socket_ops BPF program from a cgroupv2: - bpftool cgroup attach /tmp/cgroupv2/foo sock_ops pinned /sys/fs/bpf/tcp_prog + bpftool cgroup detach /tmp/cgroupv2/foo sock_ops pinned /sys/fs/bpf/tcp_prog diff --git a/samples/bpf/tcp_dumpstats_kern.c b/samples/bpf/tcp_dumpstats_kern.c new file mode 100644 index 000000000000..8557913106a0 --- /dev/null +++ b/samples/bpf/tcp_dumpstats_kern.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Refer to samples/bpf/tcp_bpf.readme for the instructions on + * how to run this sample program. + */ +#include <linux/bpf.h> + +#include "bpf_helpers.h" +#include "bpf_endian.h" + +#define INTERVAL 1000000000ULL + +int _version SEC("version") = 1; +char _license[] SEC("license") = "GPL"; + +struct { + __u32 type; + __u32 map_flags; + int *key; + __u64 *value; +} bpf_next_dump SEC(".maps") = { + .type = BPF_MAP_TYPE_SK_STORAGE, + .map_flags = BPF_F_NO_PREALLOC, +}; + +SEC("sockops") +int _sockops(struct bpf_sock_ops *ctx) +{ + struct bpf_tcp_sock *tcp_sk; + struct bpf_sock *sk; + __u64 *next_dump; + __u64 now; + + switch (ctx->op) { + case BPF_SOCK_OPS_TCP_CONNECT_CB: + bpf_sock_ops_cb_flags_set(ctx, BPF_SOCK_OPS_RTT_CB_FLAG); + return 1; + case BPF_SOCK_OPS_RTT_CB: + break; + default: + return 1; + } + + sk = ctx->sk; + if (!sk) + return 1; + + next_dump = bpf_sk_storage_get(&bpf_next_dump, sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!next_dump) + return 1; + + now = bpf_ktime_get_ns(); + if (now < *next_dump) + return 1; + + tcp_sk = bpf_tcp_sock(sk); + if (!tcp_sk) + return 1; + + *next_dump = now + INTERVAL; + + bpf_printk("dsack_dups=%u delivered=%u\n", + tcp_sk->dsack_dups, tcp_sk->delivered); + bpf_printk("delivered_ce=%u icsk_retransmits=%u\n", + tcp_sk->delivered_ce, tcp_sk->icsk_retransmits); + + return 1; +} diff --git a/samples/bpf/xdp_adjust_tail_user.c b/samples/bpf/xdp_adjust_tail_user.c index 586ff751aba9..a3596b617c4c 100644 --- a/samples/bpf/xdp_adjust_tail_user.c +++ b/samples/bpf/xdp_adjust_tail_user.c @@ -13,6 +13,7 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <net/if.h> #include <sys/resource.h> #include <arpa/inet.h> #include <netinet/ether.h> @@ -69,7 +70,7 @@ static void usage(const char *cmd) printf("Start a XDP prog which send ICMP \"packet too big\" \n" "messages if ingress packet is bigger then MAX_SIZE bytes\n"); printf("Usage: %s [...]\n", cmd); - printf(" -i <ifindex> Interface Index\n"); + printf(" -i <ifname|ifindex> Interface\n"); printf(" -T <stop-after-X-seconds> Default: 0 (forever)\n"); printf(" -S use skb-mode\n"); printf(" -N enforce native mode\n"); @@ -102,7 +103,9 @@ int main(int argc, char **argv) switch (opt) { case 'i': - ifindex = atoi(optarg); + ifindex = if_nametoindex(optarg); + if (!ifindex) + ifindex = atoi(optarg); break; case 'T': kill_after_s = atoi(optarg); @@ -136,6 +139,11 @@ int main(int argc, char **argv) return 1; } + if (!ifindex) { + fprintf(stderr, "Invalid ifname\n"); + return 1; + } + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); prog_load_attr.file = filename; diff --git a/samples/bpf/xdp_redirect_map_user.c b/samples/bpf/xdp_redirect_map_user.c index 15bb6f67f9c3..f70ee33907fd 100644 --- a/samples/bpf/xdp_redirect_map_user.c +++ b/samples/bpf/xdp_redirect_map_user.c @@ -10,6 +10,7 @@ #include <stdlib.h> #include <stdbool.h> #include <string.h> +#include <net/if.h> #include <unistd.h> #include <libgen.h> #include <sys/resource.h> @@ -85,7 +86,7 @@ static void poll_stats(int interval, int ifindex) static void usage(const char *prog) { fprintf(stderr, - "usage: %s [OPTS] IFINDEX_IN IFINDEX_OUT\n\n" + "usage: %s [OPTS] <IFNAME|IFINDEX>_IN <IFNAME|IFINDEX>_OUT\n\n" "OPTS:\n" " -S use skb-mode\n" " -N enforce native mode\n" @@ -127,7 +128,7 @@ int main(int argc, char **argv) } if (optind == argc) { - printf("usage: %s IFINDEX_IN IFINDEX_OUT\n", argv[0]); + printf("usage: %s <IFNAME|IFINDEX>_IN <IFNAME|IFINDEX>_OUT\n", argv[0]); return 1; } @@ -136,8 +137,14 @@ int main(int argc, char **argv) return 1; } - ifindex_in = strtoul(argv[optind], NULL, 0); - ifindex_out = strtoul(argv[optind + 1], NULL, 0); + ifindex_in = if_nametoindex(argv[optind]); + if (!ifindex_in) + ifindex_in = strtoul(argv[optind], NULL, 0); + + ifindex_out = if_nametoindex(argv[optind + 1]); + if (!ifindex_out) + ifindex_out = strtoul(argv[optind + 1], NULL, 0); + printf("input: %d output: %d\n", ifindex_in, ifindex_out); snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c index ce71be187205..39de06f3ec25 100644 --- a/samples/bpf/xdp_redirect_user.c +++ b/samples/bpf/xdp_redirect_user.c @@ -10,6 +10,7 @@ #include <stdlib.h> #include <stdbool.h> #include <string.h> +#include <net/if.h> #include <unistd.h> #include <libgen.h> #include <sys/resource.h> @@ -85,7 +86,7 @@ static void poll_stats(int interval, int ifindex) static void usage(const char *prog) { fprintf(stderr, - "usage: %s [OPTS] IFINDEX_IN IFINDEX_OUT\n\n" + "usage: %s [OPTS] <IFNAME|IFINDEX>_IN <IFNAME|IFINDEX>_OUT\n\n" "OPTS:\n" " -S use skb-mode\n" " -N enforce native mode\n" @@ -128,7 +129,7 @@ int main(int argc, char **argv) } if (optind == argc) { - printf("usage: %s IFINDEX_IN IFINDEX_OUT\n", argv[0]); + printf("usage: %s <IFNAME|IFINDEX>_IN <IFNAME|IFINDEX>_OUT\n", argv[0]); return 1; } @@ -137,8 +138,14 @@ int main(int argc, char **argv) return 1; } - ifindex_in = strtoul(argv[optind], NULL, 0); - ifindex_out = strtoul(argv[optind + 1], NULL, 0); + ifindex_in = if_nametoindex(argv[optind]); + if (!ifindex_in) + ifindex_in = strtoul(argv[optind], NULL, 0); + + ifindex_out = if_nametoindex(argv[optind + 1]); + if (!ifindex_out) + ifindex_out = strtoul(argv[optind + 1], NULL, 0); + printf("input: %d output: %d\n", ifindex_in, ifindex_out); snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c index 394896430712..dfb68582e243 100644 --- a/samples/bpf/xdp_tx_iptunnel_user.c +++ b/samples/bpf/xdp_tx_iptunnel_user.c @@ -9,6 +9,7 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <net/if.h> #include <sys/resource.h> #include <arpa/inet.h> #include <netinet/ether.h> @@ -83,7 +84,7 @@ static void usage(const char *cmd) "in an IPv4/v6 header and XDP_TX it out. The dst <VIP:PORT>\n" "is used to select packets to encapsulate\n\n"); printf("Usage: %s [...]\n", cmd); - printf(" -i <ifindex> Interface Index\n"); + printf(" -i <ifname|ifindex> Interface\n"); printf(" -a <vip-service-address> IPv4 or IPv6\n"); printf(" -p <vip-service-port> A port range (e.g. 433-444) is also allowed\n"); printf(" -s <source-ip> Used in the IPTunnel header\n"); @@ -181,7 +182,9 @@ int main(int argc, char **argv) switch (opt) { case 'i': - ifindex = atoi(optarg); + ifindex = if_nametoindex(optarg); + if (!ifindex) + ifindex = atoi(optarg); break; case 'a': vip.family = parse_ipstr(optarg, vip.daddr.v6); @@ -253,6 +256,11 @@ int main(int argc, char **argv) return 1; } + if (!ifindex) { + fprintf(stderr, "Invalid ifname\n"); + return 1; + } + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); prog_load_attr.file = filename; diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index 0f5eb0d7f2df..93eaaf7239b2 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -68,6 +68,7 @@ static int opt_queue; static int opt_poll; static int opt_interval = 1; static u32 opt_xdp_bind_flags; +static int opt_xsk_frame_size = XSK_UMEM__DEFAULT_FRAME_SIZE; static __u32 prog_id; struct xsk_umem_info { @@ -276,6 +277,12 @@ static size_t gen_eth_frame(struct xsk_umem_info *umem, u64 addr) static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size) { struct xsk_umem_info *umem; + struct xsk_umem_config cfg = { + .fill_size = XSK_RING_PROD__DEFAULT_NUM_DESCS, + .comp_size = XSK_RING_CONS__DEFAULT_NUM_DESCS, + .frame_size = opt_xsk_frame_size, + .frame_headroom = XSK_UMEM__DEFAULT_FRAME_HEADROOM, + }; int ret; umem = calloc(1, sizeof(*umem)); @@ -283,7 +290,7 @@ static struct xsk_umem_info *xsk_configure_umem(void *buffer, u64 size) exit_with_error(errno); ret = xsk_umem__create(&umem->umem, buffer, size, &umem->fq, &umem->cq, - NULL); + &cfg); if (ret) exit_with_error(-ret); @@ -323,11 +330,9 @@ static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem) &idx); if (ret != XSK_RING_PROD__DEFAULT_NUM_DESCS) exit_with_error(-ret); - for (i = 0; - i < XSK_RING_PROD__DEFAULT_NUM_DESCS * - XSK_UMEM__DEFAULT_FRAME_SIZE; - i += XSK_UMEM__DEFAULT_FRAME_SIZE) - *xsk_ring_prod__fill_addr(&xsk->umem->fq, idx++) = i; + for (i = 0; i < XSK_RING_PROD__DEFAULT_NUM_DESCS; i++) + *xsk_ring_prod__fill_addr(&xsk->umem->fq, idx++) = + i * opt_xsk_frame_size; xsk_ring_prod__submit(&xsk->umem->fq, XSK_RING_PROD__DEFAULT_NUM_DESCS); @@ -346,6 +351,7 @@ static struct option long_options[] = { {"interval", required_argument, 0, 'n'}, {"zero-copy", no_argument, 0, 'z'}, {"copy", no_argument, 0, 'c'}, + {"frame-size", required_argument, 0, 'f'}, {0, 0, 0, 0} }; @@ -365,8 +371,9 @@ static void usage(const char *prog) " -n, --interval=n Specify statistics update interval (default 1 sec).\n" " -z, --zero-copy Force zero-copy mode.\n" " -c, --copy Force copy mode.\n" + " -f, --frame-size=n Set the frame size (must be a power of two, default is %d).\n" "\n"; - fprintf(stderr, str, prog); + fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE); exit(EXIT_FAILURE); } @@ -377,7 +384,7 @@ static void parse_command_line(int argc, char **argv) opterr = 0; for (;;) { - c = getopt_long(argc, argv, "Frtli:q:psSNn:cz", long_options, + c = getopt_long(argc, argv, "Frtli:q:psSNn:czf:", long_options, &option_index); if (c == -1) break; @@ -420,6 +427,9 @@ static void parse_command_line(int argc, char **argv) case 'F': opt_xdp_flags &= ~XDP_FLAGS_UPDATE_IF_NOEXIST; break; + case 'f': + opt_xsk_frame_size = atoi(optarg); + break; default: usage(basename(argv[0])); } @@ -432,6 +442,11 @@ static void parse_command_line(int argc, char **argv) usage(basename(argv[0])); } + if (opt_xsk_frame_size & (opt_xsk_frame_size - 1)) { + fprintf(stderr, "--frame-size=%d is not a power of two\n", + opt_xsk_frame_size); + usage(basename(argv[0])); + } } static void kick_tx(struct xsk_socket_info *xsk) @@ -583,8 +598,7 @@ static void tx_only(struct xsk_socket_info *xsk) for (i = 0; i < BATCH_SIZE; i++) { xsk_ring_prod__tx_desc(&xsk->tx, idx + i)->addr - = (frame_nb + i) << - XSK_UMEM__DEFAULT_FRAME_SHIFT; + = (frame_nb + i) * opt_xsk_frame_size; xsk_ring_prod__tx_desc(&xsk->tx, idx + i)->len = sizeof(pkt_data) - 1; } @@ -661,21 +675,19 @@ int main(int argc, char **argv) } ret = posix_memalign(&bufs, getpagesize(), /* PAGE_SIZE aligned */ - NUM_FRAMES * XSK_UMEM__DEFAULT_FRAME_SIZE); + NUM_FRAMES * opt_xsk_frame_size); if (ret) exit_with_error(ret); /* Create sockets... */ - umem = xsk_configure_umem(bufs, - NUM_FRAMES * XSK_UMEM__DEFAULT_FRAME_SIZE); + umem = xsk_configure_umem(bufs, NUM_FRAMES * opt_xsk_frame_size); xsks[num_socks++] = xsk_configure_socket(umem); if (opt_bench == BENCH_TXONLY) { int i; - for (i = 0; i < NUM_FRAMES * XSK_UMEM__DEFAULT_FRAME_SIZE; - i += XSK_UMEM__DEFAULT_FRAME_SIZE) - (void)gen_eth_frame(umem, i); + for (i = 0; i < NUM_FRAMES; i++) + (void)gen_eth_frame(umem, i * opt_xsk_frame_size); } signal(SIGINT, int_exit); diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index d80fdde79c22..585f270c2d25 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -29,7 +29,8 @@ CGROUP COMMANDS | *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } | *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** | | **bind4** | **bind6** | **post_bind4** | **post_bind6** | **connect4** | **connect6** | -| **sendmsg4** | **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** } +| **sendmsg4** | **sendmsg6** | **recvmsg4** | **recvmsg6** | **sysctl** | +| **getsockopt** | **setsockopt** } | *ATTACH_FLAGS* := { **multi** | **override** } DESCRIPTION @@ -90,7 +91,9 @@ DESCRIPTION an unconnected udp4 socket (since 5.2); **recvmsg6** call to recvfrom(2), recvmsg(2), recvmmsg(2) for an unconnected udp6 socket (since 5.2); - **sysctl** sysctl access (since 5.2). + **sysctl** sysctl access (since 5.2); + **getsockopt** call to getsockopt (since 5.3); + **setsockopt** call to setsockopt (since 5.3). **bpftool cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG* Detach *PROG* from the cgroup *CGROUP* and attach type diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 55dd06517a3b..1df637f85f94 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -40,7 +40,8 @@ PROG COMMANDS | **lwt_seg6local** | **sockops** | **sk_skb** | **sk_msg** | **lirc_mode2** | | **cgroup/bind4** | **cgroup/bind6** | **cgroup/post_bind4** | **cgroup/post_bind6** | | **cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6** | -| **cgroup/recvmsg4** | **cgroup/recvmsg6** | **cgroup/sysctl** +| **cgroup/recvmsg4** | **cgroup/recvmsg6** | **cgroup/sysctl** | +| **cgroup/getsockopt** | **cgroup/setsockopt** | } | *ATTACH_TYPE* := { | **msg_verdict** | **stream_verdict** | **stream_parser** | **flow_dissector** diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index a17e84c67498..ba37095e1f62 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -379,7 +379,8 @@ _bpftool() cgroup/sendmsg4 cgroup/sendmsg6 \ cgroup/recvmsg4 cgroup/recvmsg6 \ cgroup/post_bind4 cgroup/post_bind6 \ - cgroup/sysctl" -- \ + cgroup/sysctl cgroup/getsockopt \ + cgroup/setsockopt" -- \ "$cur" ) ) return 0 ;; @@ -689,7 +690,8 @@ _bpftool() attach|detach) local ATTACH_TYPES='ingress egress sock_create sock_ops \ device bind4 bind6 post_bind4 post_bind6 connect4 \ - connect6 sendmsg4 sendmsg6 recvmsg4 recvmsg6 sysctl' + connect6 sendmsg4 sendmsg6 recvmsg4 recvmsg6 sysctl \ + getsockopt setsockopt' local ATTACH_FLAGS='multi override' local PROG_TYPE='id pinned tag' case $prev in @@ -699,7 +701,8 @@ _bpftool() ;; ingress|egress|sock_create|sock_ops|device|bind4|bind6|\ post_bind4|post_bind6|connect4|connect6|sendmsg4|\ - sendmsg6|recvmsg4|recvmsg6|sysctl) + sendmsg6|recvmsg4|recvmsg6|sysctl|getsockopt|\ + setsockopt) COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \ "$cur" ) ) return 0 diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index 73ec8ea33fb4..390b89a224f1 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -26,7 +26,8 @@ " sock_ops | device | bind4 | bind6 |\n" \ " post_bind4 | post_bind6 | connect4 |\n" \ " connect6 | sendmsg4 | sendmsg6 |\n" \ - " recvmsg4 | recvmsg6 | sysctl }" + " recvmsg4 | recvmsg6 | sysctl |\n" \ + " getsockopt | setsockopt }" static const char * const attach_type_strings[] = { [BPF_CGROUP_INET_INGRESS] = "ingress", @@ -45,6 +46,8 @@ static const char * const attach_type_strings[] = { [BPF_CGROUP_SYSCTL] = "sysctl", [BPF_CGROUP_UDP4_RECVMSG] = "recvmsg4", [BPF_CGROUP_UDP6_RECVMSG] = "recvmsg6", + [BPF_CGROUP_GETSOCKOPT] = "getsockopt", + [BPF_CGROUP_SETSOCKOPT] = "setsockopt", [__MAX_BPF_ATTACH_TYPE] = NULL, }; diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 28a2a5857e14..9c5d9c80f71e 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -74,6 +74,7 @@ static const char * const prog_type_name[] = { [BPF_PROG_TYPE_SK_REUSEPORT] = "sk_reuseport", [BPF_PROG_TYPE_FLOW_DISSECTOR] = "flow_dissector", [BPF_PROG_TYPE_CGROUP_SYSCTL] = "cgroup_sysctl", + [BPF_PROG_TYPE_CGROUP_SOCKOPT] = "cgroup_sockopt", }; extern const char * const map_type_name[]; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index f1a831f05010..9b0db5d14e31 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -1071,7 +1071,8 @@ static int do_help(int argc, char **argv) " cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n" " cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n" " cgroup/sendmsg4 | cgroup/sendmsg6 | cgroup/recvmsg4 |\n" - " cgroup/recvmsg6 }\n" + " cgroup/recvmsg6 | cgroup/getsockopt |\n" + " cgroup/setsockopt }\n" " ATTACH_TYPE := { msg_verdict | stream_verdict | stream_parser |\n" " flow_dissector }\n" " " HELP_SPEC_OPTIONS "\n" diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index b077507efa3f..cecf42c871d4 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -170,6 +170,7 @@ enum bpf_prog_type { BPF_PROG_TYPE_FLOW_DISSECTOR, BPF_PROG_TYPE_CGROUP_SYSCTL, BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, + BPF_PROG_TYPE_CGROUP_SOCKOPT, }; enum bpf_attach_type { @@ -194,6 +195,8 @@ enum bpf_attach_type { BPF_CGROUP_SYSCTL, BPF_CGROUP_UDP4_RECVMSG, BPF_CGROUP_UDP6_RECVMSG, + BPF_CGROUP_GETSOCKOPT, + BPF_CGROUP_SETSOCKOPT, __MAX_BPF_ATTACH_TYPE }; @@ -1764,6 +1767,7 @@ union bpf_attr { * * **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) + * * **BPF_SOCK_OPS_RTT_CB_FLAG** (every RTT) * * Therefore, this function can be used to clear a callback flag by * setting the appropriate bit to zero. e.g. to disable the RTO @@ -3066,6 +3070,12 @@ struct bpf_tcp_sock { * sum(delta(snd_una)), or how many bytes * were acked. */ + __u32 dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups + * total number of DSACK blocks received + */ + __u32 delivered; /* Total data packets delivered incl. rexmits */ + __u32 delivered_ce; /* Like the above but only ECE marked packets */ + __u32 icsk_retransmits; /* Number of unrecovered [RTO] timeouts */ }; struct bpf_sock_tuple { @@ -3308,7 +3318,8 @@ struct bpf_sock_ops { #define BPF_SOCK_OPS_RTO_CB_FLAG (1<<0) #define BPF_SOCK_OPS_RETRANS_CB_FLAG (1<<1) #define BPF_SOCK_OPS_STATE_CB_FLAG (1<<2) -#define BPF_SOCK_OPS_ALL_CB_FLAGS 0x7 /* Mask of all currently +#define BPF_SOCK_OPS_RTT_CB_FLAG (1<<3) +#define BPF_SOCK_OPS_ALL_CB_FLAGS 0xF /* Mask of all currently * supported cb flags */ @@ -3363,6 +3374,8 @@ enum { BPF_SOCK_OPS_TCP_LISTEN_CB, /* Called on listen(2), right after * socket transition to LISTEN state. */ + BPF_SOCK_OPS_RTT_CB, /* Called on every RTT. + */ }; /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect @@ -3541,4 +3554,15 @@ struct bpf_sysctl { */ }; +struct bpf_sockopt { + __bpf_md_ptr(struct bpf_sock *, sk); + __bpf_md_ptr(void *, optval); + __bpf_md_ptr(void *, optval_end); + + __s32 level; + __s32 optname; + __s32 optlen; + __s32 retval; +}; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h index caed8b1614ff..faaa5ca2a117 100644 --- a/tools/include/uapi/linux/if_xdp.h +++ b/tools/include/uapi/linux/if_xdp.h @@ -46,6 +46,7 @@ struct xdp_mmap_offsets { #define XDP_UMEM_FILL_RING 5 #define XDP_UMEM_COMPLETION_RING 6 #define XDP_STATISTICS 7 +#define XDP_OPTIONS 8 struct xdp_umem_reg { __u64 addr; /* Start of packet data area */ @@ -60,6 +61,13 @@ struct xdp_statistics { __u64 tx_invalid_descs; /* Dropped due to invalid descriptor */ }; +struct xdp_options { + __u32 flags; +}; + +/* Flags for the flags field of struct xdp_options */ +#define XDP_OPTIONS_ZEROCOPY (1 << 0) + /* Pgoff for mmaping the rings */ #define XDP_PGOFF_RX_RING 0 #define XDP_PGOFF_TX_RING 0x80000000 diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 4259c9f0cfe7..4907997289e9 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -778,7 +778,7 @@ static struct bpf_map *bpf_object__add_map(struct bpf_object *obj) if (obj->nr_maps < obj->maps_cap) return &obj->maps[obj->nr_maps++]; - new_cap = max(4ul, obj->maps_cap * 3 / 2); + new_cap = max((size_t)4, obj->maps_cap * 3 / 2); new_maps = realloc(obj->maps, new_cap * sizeof(*obj->maps)); if (!new_maps) { pr_warning("alloc maps for object failed\n"); @@ -1169,7 +1169,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, pr_debug("map '%s': found key_size = %u.\n", map_name, sz); if (map->def.key_size && map->def.key_size != sz) { - pr_warning("map '%s': conflictling key size %u != %u.\n", + pr_warning("map '%s': conflicting key size %u != %u.\n", map_name, map->def.key_size, sz); return -EINVAL; } @@ -1197,7 +1197,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, pr_debug("map '%s': found key [%u], sz = %lld.\n", map_name, t->type, sz); if (map->def.key_size && map->def.key_size != sz) { - pr_warning("map '%s': conflictling key size %u != %lld.\n", + pr_warning("map '%s': conflicting key size %u != %lld.\n", map_name, map->def.key_size, sz); return -EINVAL; } @@ -1212,7 +1212,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, pr_debug("map '%s': found value_size = %u.\n", map_name, sz); if (map->def.value_size && map->def.value_size != sz) { - pr_warning("map '%s': conflictling value size %u != %u.\n", + pr_warning("map '%s': conflicting value size %u != %u.\n", map_name, map->def.value_size, sz); return -EINVAL; } @@ -1240,7 +1240,7 @@ static int bpf_object__init_user_btf_map(struct bpf_object *obj, pr_debug("map '%s': found value [%u], sz = %lld.\n", map_name, t->type, sz); if (map->def.value_size && map->def.value_size != sz) { - pr_warning("map '%s': conflictling value size %u != %lld.\n", + pr_warning("map '%s': conflicting value size %u != %lld.\n", map_name, map->def.value_size, sz); return -EINVAL; } @@ -2646,6 +2646,7 @@ static bool bpf_prog_type__needs_kver(enum bpf_prog_type type) case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE: case BPF_PROG_TYPE_PERF_EVENT: case BPF_PROG_TYPE_CGROUP_SYSCTL: + case BPF_PROG_TYPE_CGROUP_SOCKOPT: return false; case BPF_PROG_TYPE_KPROBE: default: @@ -3604,6 +3605,10 @@ static const struct { BPF_CGROUP_UDP6_RECVMSG), BPF_EAPROG_SEC("cgroup/sysctl", BPF_PROG_TYPE_CGROUP_SYSCTL, BPF_CGROUP_SYSCTL), + BPF_EAPROG_SEC("cgroup/getsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT, + BPF_CGROUP_GETSOCKOPT), + BPF_EAPROG_SEC("cgroup/setsockopt", BPF_PROG_TYPE_CGROUP_SOCKOPT, + BPF_CGROUP_SETSOCKOPT), }; #undef BPF_PROG_SEC_IMPL @@ -3867,10 +3872,7 @@ int bpf_prog_load(const char *file, enum bpf_prog_type type, int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, struct bpf_object **pobj, int *prog_fd) { - struct bpf_object_open_attr open_attr = { - .file = attr->file, - .prog_type = attr->prog_type, - }; + struct bpf_object_open_attr open_attr = {}; struct bpf_program *prog, *first_prog = NULL; enum bpf_attach_type expected_attach_type; enum bpf_prog_type prog_type; @@ -3883,6 +3885,9 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr, if (!attr->file) return -EINVAL; + open_attr.file = attr->file; + open_attr.prog_type = attr->prog_type; + obj = bpf_object__open_xattr(&open_attr); if (IS_ERR_OR_NULL(obj)) return -ENOENT; diff --git a/tools/lib/bpf/libbpf_probes.c b/tools/lib/bpf/libbpf_probes.c index 6635a31a7a16..ace1a0708d99 100644 --- a/tools/lib/bpf/libbpf_probes.c +++ b/tools/lib/bpf/libbpf_probes.c @@ -101,6 +101,7 @@ probe_load(enum bpf_prog_type prog_type, const struct bpf_insn *insns, case BPF_PROG_TYPE_SK_REUSEPORT: case BPF_PROG_TYPE_FLOW_DISSECTOR: case BPF_PROG_TYPE_CGROUP_SYSCTL: + case BPF_PROG_TYPE_CGROUP_SOCKOPT: default: break; } diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 7ef6293b4fd7..b33740221b7e 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -65,6 +65,7 @@ struct xsk_socket { int xsks_map_fd; __u32 queue_id; char ifname[IFNAMSIZ]; + bool zc; }; struct xsk_nl_info { @@ -326,7 +327,8 @@ static int xsk_get_max_queues(struct xsk_socket *xsk) channels.cmd = ETHTOOL_GCHANNELS; ifr.ifr_data = (void *)&channels; - strncpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ); + strncpy(ifr.ifr_name, xsk->ifname, IFNAMSIZ - 1); + ifr.ifr_name[IFNAMSIZ - 1] = '\0'; err = ioctl(fd, SIOCETHTOOL, &ifr); if (err && errno != EOPNOTSUPP) { ret = -errno; @@ -480,6 +482,7 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, void *rx_map = NULL, *tx_map = NULL; struct sockaddr_xdp sxdp = {}; struct xdp_mmap_offsets off; + struct xdp_options opts; struct xsk_socket *xsk; socklen_t optlen; int err; @@ -597,6 +600,16 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname, } xsk->prog_fd = -1; + + optlen = sizeof(opts); + err = getsockopt(xsk->fd, SOL_XDP, XDP_OPTIONS, &opts, &optlen); + if (err) { + err = -errno; + goto out_mmap_tx; + } + + xsk->zc = opts.flags & XDP_OPTIONS_ZEROCOPY; + if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) { err = xsk_setup_xdp_prog(xsk); if (err) diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h index 82ea71a0f3ec..833a6e60d065 100644 --- a/tools/lib/bpf/xsk.h +++ b/tools/lib/bpf/xsk.h @@ -167,7 +167,7 @@ LIBBPF_API int xsk_socket__fd(const struct xsk_socket *xsk); #define XSK_RING_CONS__DEFAULT_NUM_DESCS 2048 #define XSK_RING_PROD__DEFAULT_NUM_DESCS 2048 -#define XSK_UMEM__DEFAULT_FRAME_SHIFT 11 /* 2048 bytes */ +#define XSK_UMEM__DEFAULT_FRAME_SHIFT 12 /* 4096 bytes */ #define XSK_UMEM__DEFAULT_FRAME_SIZE (1 << XSK_UMEM__DEFAULT_FRAME_SHIFT) #define XSK_UMEM__DEFAULT_FRAME_HEADROOM 0 diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 7470327edcfe..a2f7f79c7908 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -39,3 +39,6 @@ libbpf.so.* test_hashmap test_btf_dump xdping +test_sockopt +test_sockopt_sk +test_sockopt_multi diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index fb5ce43e28b3..2620406a53ec 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -15,7 +15,7 @@ LLC ?= llc LLVM_OBJCOPY ?= llvm-objcopy LLVM_READELF ?= llvm-readelf BTF_PAHOLE ?= pahole -CFLAGS += -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(BPFDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include \ +CFLAGS += -g -Wall -O2 -I$(APIDIR) -I$(LIBDIR) -I$(BPFDIR) -I$(GENDIR) $(GENFLAGS) -I../../../include \ -Dbpf_prog_load=bpf_prog_test_load \ -Dbpf_load_program=bpf_test_load_program LDLIBS += -lcap -lelf -lrt -lpthread @@ -26,7 +26,8 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test test_sock test_btf test_sockmap get_cgroup_id_user test_socket_cookie \ test_cgroup_storage test_select_reuseport test_section_names \ test_netcnt test_tcpnotify_user test_sock_fields test_sysctl test_hashmap \ - test_btf_dump test_cgroup_attach xdping + test_btf_dump test_cgroup_attach xdping test_sockopt test_sockopt_sk \ + test_sockopt_multi test_tcp_rtt BPF_OBJ_FILES = $(patsubst %.c,%.o, $(notdir $(wildcard progs/*.c))) TEST_GEN_FILES = $(BPF_OBJ_FILES) @@ -46,6 +47,7 @@ TEST_PROGS := test_kmod.sh \ test_libbpf.sh \ test_xdp_redirect.sh \ test_xdp_meta.sh \ + test_xdp_veth.sh \ test_offload.py \ test_sock_addr.sh \ test_tunnel.sh \ @@ -102,6 +104,10 @@ $(OUTPUT)/test_netcnt: cgroup_helpers.c $(OUTPUT)/test_sock_fields: cgroup_helpers.c $(OUTPUT)/test_sysctl: cgroup_helpers.c $(OUTPUT)/test_cgroup_attach: cgroup_helpers.c +$(OUTPUT)/test_sockopt: cgroup_helpers.c +$(OUTPUT)/test_sockopt_sk: cgroup_helpers.c +$(OUTPUT)/test_sockopt_multi: cgroup_helpers.c +$(OUTPUT)/test_tcp_rtt: cgroup_helpers.c .PHONY: force diff --git a/tools/testing/selftests/bpf/progs/pyperf.h b/tools/testing/selftests/bpf/progs/pyperf.h index 6b0781391be5..abf6224649be 100644 --- a/tools/testing/selftests/bpf/progs/pyperf.h +++ b/tools/testing/selftests/bpf/progs/pyperf.h @@ -75,8 +75,7 @@ typedef struct { void* co_name; // PyCodeObject.co_name } FrameData; -static inline __attribute__((__always_inline__)) void* -get_thread_state(void* tls_base, PidData* pidData) +static __always_inline void *get_thread_state(void *tls_base, PidData *pidData) { void* thread_state; int key; @@ -87,8 +86,8 @@ get_thread_state(void* tls_base, PidData* pidData) return thread_state; } -static inline __attribute__((__always_inline__)) bool -get_frame_data(void* frame_ptr, PidData* pidData, FrameData* frame, Symbol* symbol) +static __always_inline bool get_frame_data(void *frame_ptr, PidData *pidData, + FrameData *frame, Symbol *symbol) { // read data from PyFrameObject bpf_probe_read(&frame->f_back, @@ -161,7 +160,7 @@ struct bpf_elf_map SEC("maps") stackmap = { .max_elem = 1000, }; -static inline __attribute__((__always_inline__)) int __on_event(struct pt_regs *ctx) +static __always_inline int __on_event(struct pt_regs *ctx) { uint64_t pid_tgid = bpf_get_current_pid_tgid(); pid_t pid = (pid_t)(pid_tgid >> 32); diff --git a/tools/testing/selftests/bpf/progs/sockopt_multi.c b/tools/testing/selftests/bpf/progs/sockopt_multi.c new file mode 100644 index 000000000000..4afd2595c08e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sockopt_multi.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <netinet/in.h> +#include <linux/bpf.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; +__u32 _version SEC("version") = 1; + +SEC("cgroup/getsockopt/child") +int _getsockopt_child(struct bpf_sockopt *ctx) +{ + __u8 *optval_end = ctx->optval_end; + __u8 *optval = ctx->optval; + + if (ctx->level != SOL_IP || ctx->optname != IP_TOS) + return 1; + + if (optval + 1 > optval_end) + return 0; /* EPERM, bounds check */ + + if (optval[0] != 0x80) + return 0; /* EPERM, unexpected optval from the kernel */ + + ctx->retval = 0; /* Reset system call return value to zero */ + + optval[0] = 0x90; + ctx->optlen = 1; + + return 1; +} + +SEC("cgroup/getsockopt/parent") +int _getsockopt_parent(struct bpf_sockopt *ctx) +{ + __u8 *optval_end = ctx->optval_end; + __u8 *optval = ctx->optval; + + if (ctx->level != SOL_IP || ctx->optname != IP_TOS) + return 1; + + if (optval + 1 > optval_end) + return 0; /* EPERM, bounds check */ + + if (optval[0] != 0x90) + return 0; /* EPERM, unexpected optval from the kernel */ + + ctx->retval = 0; /* Reset system call return value to zero */ + + optval[0] = 0xA0; + ctx->optlen = 1; + + return 1; +} + +SEC("cgroup/setsockopt") +int _setsockopt(struct bpf_sockopt *ctx) +{ + __u8 *optval_end = ctx->optval_end; + __u8 *optval = ctx->optval; + + if (ctx->level != SOL_IP || ctx->optname != IP_TOS) + return 1; + + if (optval + 1 > optval_end) + return 0; /* EPERM, bounds check */ + + optval[0] += 0x10; + ctx->optlen = 1; + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/sockopt_sk.c b/tools/testing/selftests/bpf/progs/sockopt_sk.c new file mode 100644 index 000000000000..076122c898e9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/sockopt_sk.c @@ -0,0 +1,111 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <netinet/in.h> +#include <linux/bpf.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; +__u32 _version SEC("version") = 1; + +#define SOL_CUSTOM 0xdeadbeef + +struct sockopt_sk { + __u8 val; +}; + +struct bpf_map_def SEC("maps") socket_storage_map = { + .type = BPF_MAP_TYPE_SK_STORAGE, + .key_size = sizeof(int), + .value_size = sizeof(struct sockopt_sk), + .map_flags = BPF_F_NO_PREALLOC, +}; +BPF_ANNOTATE_KV_PAIR(socket_storage_map, int, struct sockopt_sk); + +SEC("cgroup/getsockopt") +int _getsockopt(struct bpf_sockopt *ctx) +{ + __u8 *optval_end = ctx->optval_end; + __u8 *optval = ctx->optval; + struct sockopt_sk *storage; + + if (ctx->level == SOL_IP && ctx->optname == IP_TOS) + /* Not interested in SOL_IP:IP_TOS; + * let next BPF program in the cgroup chain or kernel + * handle it. + */ + return 1; + + if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) { + /* Not interested in SOL_SOCKET:SO_SNDBUF; + * let next BPF program in the cgroup chain or kernel + * handle it. + */ + return 1; + } + + if (ctx->level != SOL_CUSTOM) + return 0; /* EPERM, deny everything except custom level */ + + if (optval + 1 > optval_end) + return 0; /* EPERM, bounds check */ + + storage = bpf_sk_storage_get(&socket_storage_map, ctx->sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!storage) + return 0; /* EPERM, couldn't get sk storage */ + + if (!ctx->retval) + return 0; /* EPERM, kernel should not have handled + * SOL_CUSTOM, something is wrong! + */ + ctx->retval = 0; /* Reset system call return value to zero */ + + optval[0] = storage->val; + ctx->optlen = 1; + + return 1; +} + +SEC("cgroup/setsockopt") +int _setsockopt(struct bpf_sockopt *ctx) +{ + __u8 *optval_end = ctx->optval_end; + __u8 *optval = ctx->optval; + struct sockopt_sk *storage; + + if (ctx->level == SOL_IP && ctx->optname == IP_TOS) + /* Not interested in SOL_IP:IP_TOS; + * let next BPF program in the cgroup chain or kernel + * handle it. + */ + return 1; + + if (ctx->level == SOL_SOCKET && ctx->optname == SO_SNDBUF) { + /* Overwrite SO_SNDBUF value */ + + if (optval + sizeof(__u32) > optval_end) + return 0; /* EPERM, bounds check */ + + *(__u32 *)optval = 0x55AA; + ctx->optlen = 4; + + return 1; + } + + if (ctx->level != SOL_CUSTOM) + return 0; /* EPERM, deny everything except custom level */ + + if (optval + 1 > optval_end) + return 0; /* EPERM, bounds check */ + + storage = bpf_sk_storage_get(&socket_storage_map, ctx->sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!storage) + return 0; /* EPERM, couldn't get sk storage */ + + storage->val = optval[0]; + ctx->optlen = -1; /* BPF has consumed this option, don't call kernel + * setsockopt handler. + */ + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/strobemeta.h b/tools/testing/selftests/bpf/progs/strobemeta.h index 1ff73f60a3e4..553bc3b62e89 100644 --- a/tools/testing/selftests/bpf/progs/strobemeta.h +++ b/tools/testing/selftests/bpf/progs/strobemeta.h @@ -266,8 +266,8 @@ struct tls_index { uint64_t offset; }; -static inline __attribute__((always_inline)) -void *calc_location(struct strobe_value_loc *loc, void *tls_base) +static __always_inline void *calc_location(struct strobe_value_loc *loc, + void *tls_base) { /* * tls_mode value is: @@ -327,10 +327,10 @@ void *calc_location(struct strobe_value_loc *loc, void *tls_base) : NULL; } -static inline __attribute__((always_inline)) -void read_int_var(struct strobemeta_cfg *cfg, size_t idx, void *tls_base, - struct strobe_value_generic *value, - struct strobemeta_payload *data) +static __always_inline void read_int_var(struct strobemeta_cfg *cfg, + size_t idx, void *tls_base, + struct strobe_value_generic *value, + struct strobemeta_payload *data) { void *location = calc_location(&cfg->int_locs[idx], tls_base); if (!location) @@ -342,10 +342,11 @@ void read_int_var(struct strobemeta_cfg *cfg, size_t idx, void *tls_base, data->int_vals_set_mask |= (1 << idx); } -static inline __attribute__((always_inline)) -uint64_t read_str_var(struct strobemeta_cfg* cfg, size_t idx, void *tls_base, - struct strobe_value_generic *value, - struct strobemeta_payload *data, void *payload) +static __always_inline uint64_t read_str_var(struct strobemeta_cfg *cfg, + size_t idx, void *tls_base, + struct strobe_value_generic *value, + struct strobemeta_payload *data, + void *payload) { void *location; uint32_t len; @@ -371,10 +372,11 @@ uint64_t read_str_var(struct strobemeta_cfg* cfg, size_t idx, void *tls_base, return len; } -static inline __attribute__((always_inline)) -void *read_map_var(struct strobemeta_cfg *cfg, size_t idx, void *tls_base, - struct strobe_value_generic *value, - struct strobemeta_payload* data, void *payload) +static __always_inline void *read_map_var(struct strobemeta_cfg *cfg, + size_t idx, void *tls_base, + struct strobe_value_generic *value, + struct strobemeta_payload *data, + void *payload) { struct strobe_map_descr* descr = &data->map_descrs[idx]; struct strobe_map_raw map; @@ -435,9 +437,9 @@ void *read_map_var(struct strobemeta_cfg *cfg, size_t idx, void *tls_base, * read_strobe_meta returns NULL, if no metadata was read; otherwise returns * pointer to *right after* payload ends */ -static inline __attribute__((always_inline)) -void *read_strobe_meta(struct task_struct* task, - struct strobemeta_payload* data) { +static __always_inline void *read_strobe_meta(struct task_struct *task, + struct strobemeta_payload *data) +{ pid_t pid = bpf_get_current_pid_tgid() >> 32; struct strobe_value_generic value = {0}; struct strobemeta_cfg *cfg; diff --git a/tools/testing/selftests/bpf/progs/tcp_rtt.c b/tools/testing/selftests/bpf/progs/tcp_rtt.c new file mode 100644 index 000000000000..233bdcb1659e --- /dev/null +++ b/tools/testing/selftests/bpf/progs/tcp_rtt.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bpf.h> +#include "bpf_helpers.h" + +char _license[] SEC("license") = "GPL"; +__u32 _version SEC("version") = 1; + +struct tcp_rtt_storage { + __u32 invoked; + __u32 dsack_dups; + __u32 delivered; + __u32 delivered_ce; + __u32 icsk_retransmits; +}; + +struct bpf_map_def SEC("maps") socket_storage_map = { + .type = BPF_MAP_TYPE_SK_STORAGE, + .key_size = sizeof(int), + .value_size = sizeof(struct tcp_rtt_storage), + .map_flags = BPF_F_NO_PREALLOC, +}; +BPF_ANNOTATE_KV_PAIR(socket_storage_map, int, struct tcp_rtt_storage); + +SEC("sockops") +int _sockops(struct bpf_sock_ops *ctx) +{ + struct tcp_rtt_storage *storage; + struct bpf_tcp_sock *tcp_sk; + int op = (int) ctx->op; + struct bpf_sock *sk; + + sk = ctx->sk; + if (!sk) + return 1; + + storage = bpf_sk_storage_get(&socket_storage_map, sk, 0, + BPF_SK_STORAGE_GET_F_CREATE); + if (!storage) + return 1; + + if (op == BPF_SOCK_OPS_TCP_CONNECT_CB) { + bpf_sock_ops_cb_flags_set(ctx, BPF_SOCK_OPS_RTT_CB_FLAG); + return 1; + } + + if (op != BPF_SOCK_OPS_RTT_CB) + return 1; + + tcp_sk = bpf_tcp_sock(sk); + if (!tcp_sk) + return 1; + + storage->invoked++; + + storage->dsack_dups = tcp_sk->dsack_dups; + storage->delivered = tcp_sk->delivered; + storage->delivered_ce = tcp_sk->delivered_ce; + storage->icsk_retransmits = tcp_sk->icsk_retransmits; + + return 1; +} diff --git a/tools/testing/selftests/bpf/progs/test_jhash.h b/tools/testing/selftests/bpf/progs/test_jhash.h index 3d12c11a8d47..c300734d26f6 100644 --- a/tools/testing/selftests/bpf/progs/test_jhash.h +++ b/tools/testing/selftests/bpf/progs/test_jhash.h @@ -1,9 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 // Copyright (c) 2019 Facebook +#include <features.h> typedef unsigned int u32; -static __attribute__((always_inline)) u32 rol32(u32 word, unsigned int shift) +static __always_inline u32 rol32(u32 word, unsigned int shift) { return (word << shift) | (word >> ((-shift) & 31)); } diff --git a/tools/testing/selftests/bpf/progs/test_seg6_loop.c b/tools/testing/selftests/bpf/progs/test_seg6_loop.c index 463964d79f73..1dbe1d4d467e 100644 --- a/tools/testing/selftests/bpf/progs/test_seg6_loop.c +++ b/tools/testing/selftests/bpf/progs/test_seg6_loop.c @@ -54,7 +54,7 @@ struct sr6_tlv_t { unsigned char value[0]; } BPF_PACKET_HEADER; -static __attribute__((always_inline)) struct ip6_srh_t *get_srh(struct __sk_buff *skb) +static __always_inline struct ip6_srh_t *get_srh(struct __sk_buff *skb) { void *cursor, *data_end; struct ip6_srh_t *srh; @@ -88,9 +88,9 @@ static __attribute__((always_inline)) struct ip6_srh_t *get_srh(struct __sk_buff return srh; } -static __attribute__((always_inline)) -int update_tlv_pad(struct __sk_buff *skb, uint32_t new_pad, - uint32_t old_pad, uint32_t pad_off) +static __always_inline int update_tlv_pad(struct __sk_buff *skb, + uint32_t new_pad, uint32_t old_pad, + uint32_t pad_off) { int err; @@ -118,10 +118,11 @@ int update_tlv_pad(struct __sk_buff *skb, uint32_t new_pad, return 0; } -static __attribute__((always_inline)) -int is_valid_tlv_boundary(struct __sk_buff *skb, struct ip6_srh_t *srh, - uint32_t *tlv_off, uint32_t *pad_size, - uint32_t *pad_off) +static __always_inline int is_valid_tlv_boundary(struct __sk_buff *skb, + struct ip6_srh_t *srh, + uint32_t *tlv_off, + uint32_t *pad_size, + uint32_t *pad_off) { uint32_t srh_off, cur_off; int offset_valid = 0; @@ -177,9 +178,9 @@ int is_valid_tlv_boundary(struct __sk_buff *skb, struct ip6_srh_t *srh, return 0; } -static __attribute__((always_inline)) -int add_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh, uint32_t tlv_off, - struct sr6_tlv_t *itlv, uint8_t tlv_size) +static __always_inline int add_tlv(struct __sk_buff *skb, + struct ip6_srh_t *srh, uint32_t tlv_off, + struct sr6_tlv_t *itlv, uint8_t tlv_size) { uint32_t srh_off = (char *)srh - (char *)(long)skb->data; uint8_t len_remaining, new_pad; diff --git a/tools/testing/selftests/bpf/progs/test_verif_scale2.c b/tools/testing/selftests/bpf/progs/test_verif_scale2.c index 77830693eccb..9897150ed516 100644 --- a/tools/testing/selftests/bpf/progs/test_verif_scale2.c +++ b/tools/testing/selftests/bpf/progs/test_verif_scale2.c @@ -2,7 +2,7 @@ // Copyright (c) 2019 Facebook #include <linux/bpf.h> #include "bpf_helpers.h" -#define ATTR __attribute__((always_inline)) +#define ATTR __always_inline #include "test_jhash.h" SEC("scale90_inline") diff --git a/tools/testing/selftests/bpf/progs/xdp_redirect_map.c b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c new file mode 100644 index 000000000000..e87a985b9df9 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdp_redirect_map.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include "bpf_helpers.h" + +struct bpf_map_def SEC("maps") tx_port = { + .type = BPF_MAP_TYPE_DEVMAP, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 8, +}; + +SEC("redirect_map_0") +int xdp_redirect_map_0(struct xdp_md *xdp) +{ + return bpf_redirect_map(&tx_port, 0, 0); +} + +SEC("redirect_map_1") +int xdp_redirect_map_1(struct xdp_md *xdp) +{ + return bpf_redirect_map(&tx_port, 1, 0); +} + +SEC("redirect_map_2") +int xdp_redirect_map_2(struct xdp_md *xdp) +{ + return bpf_redirect_map(&tx_port, 2, 0); +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/xdp_tx.c b/tools/testing/selftests/bpf/progs/xdp_tx.c new file mode 100644 index 000000000000..57912e7c94b0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/xdp_tx.c @@ -0,0 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include "bpf_helpers.h" + +SEC("tx") +int xdp_tx(struct xdp_md *xdp) +{ + return XDP_TX; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_section_names.c b/tools/testing/selftests/bpf/test_section_names.c index dee2f2eceb0f..29833aeaf0de 100644 --- a/tools/testing/selftests/bpf/test_section_names.c +++ b/tools/testing/selftests/bpf/test_section_names.c @@ -134,6 +134,16 @@ static struct sec_name_test tests[] = { {0, BPF_PROG_TYPE_CGROUP_SYSCTL, BPF_CGROUP_SYSCTL}, {0, BPF_CGROUP_SYSCTL}, }, + { + "cgroup/getsockopt", + {0, BPF_PROG_TYPE_CGROUP_SOCKOPT, BPF_CGROUP_GETSOCKOPT}, + {0, BPF_CGROUP_GETSOCKOPT}, + }, + { + "cgroup/setsockopt", + {0, BPF_PROG_TYPE_CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT}, + {0, BPF_CGROUP_SETSOCKOPT}, + }, }; static int test_prog_type_by_name(const struct sec_name_test *test) diff --git a/tools/testing/selftests/bpf/test_sockopt.c b/tools/testing/selftests/bpf/test_sockopt.c new file mode 100644 index 000000000000..23bd0819382d --- /dev/null +++ b/tools/testing/selftests/bpf/test_sockopt.c @@ -0,0 +1,1021 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <errno.h> +#include <stdio.h> +#include <unistd.h> +#include <sys/types.h> +#include <sys/socket.h> +#include <netinet/in.h> + +#include <linux/filter.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include "bpf_rlimit.h" +#include "bpf_util.h" +#include "cgroup_helpers.h" + +#define CG_PATH "/sockopt" + +static char bpf_log_buf[4096]; +static bool verbose; + +enum sockopt_test_error { + OK = 0, + DENY_LOAD, + DENY_ATTACH, + EPERM_GETSOCKOPT, + EFAULT_GETSOCKOPT, + EPERM_SETSOCKOPT, + EFAULT_SETSOCKOPT, +}; + +static struct sockopt_test { + const char *descr; + const struct bpf_insn insns[64]; + enum bpf_attach_type attach_type; + enum bpf_attach_type expected_attach_type; + + int set_optname; + int set_level; + const char set_optval[64]; + socklen_t set_optlen; + + int get_optname; + int get_level; + const char get_optval[64]; + socklen_t get_optlen; + socklen_t get_optlen_ret; + + enum sockopt_test_error error; +} tests[] = { + + /* ==================== getsockopt ==================== */ + + { + .descr = "getsockopt: no expected_attach_type", + .insns = { + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + + }, + .attach_type = BPF_CGROUP_GETSOCKOPT, + .expected_attach_type = 0, + .error = DENY_LOAD, + }, + { + .descr = "getsockopt: wrong expected_attach_type", + .insns = { + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + + }, + .attach_type = BPF_CGROUP_GETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + .error = DENY_ATTACH, + }, + { + .descr = "getsockopt: bypass bpf hook", + .insns = { + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_GETSOCKOPT, + .expected_attach_type = BPF_CGROUP_GETSOCKOPT, + + .get_level = SOL_IP, + .set_level = SOL_IP, + + .get_optname = IP_TOS, + .set_optname = IP_TOS, + + .set_optval = { 1 << 3 }, + .set_optlen = 1, + + .get_optval = { 1 << 3 }, + .get_optlen = 1, + }, + { + .descr = "getsockopt: return EPERM from bpf hook", + .insns = { + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_GETSOCKOPT, + .expected_attach_type = BPF_CGROUP_GETSOCKOPT, + + .get_level = SOL_IP, + .get_optname = IP_TOS, + + .get_optlen = 1, + .error = EPERM_GETSOCKOPT, + }, + { + .descr = "getsockopt: no optval bounds check, deny loading", + .insns = { + /* r6 = ctx->optval */ + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, + offsetof(struct bpf_sockopt, optval)), + + /* ctx->optval[0] = 0x80 */ + BPF_MOV64_IMM(BPF_REG_0, 0x80), + BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_0, 0), + + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_GETSOCKOPT, + .expected_attach_type = BPF_CGROUP_GETSOCKOPT, + .error = DENY_LOAD, + }, + { + .descr = "getsockopt: read ctx->level", + .insns = { + /* r6 = ctx->level */ + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct bpf_sockopt, level)), + + /* if (ctx->level == 123) { */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 123, 4), + /* ctx->retval = 0 */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, retval)), + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + /* } else { */ + /* return 0 */ + BPF_MOV64_IMM(BPF_REG_0, 0), + /* } */ + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_GETSOCKOPT, + .expected_attach_type = BPF_CGROUP_GETSOCKOPT, + + .get_level = 123, + + .get_optlen = 1, + }, + { + .descr = "getsockopt: deny writing to ctx->level", + .insns = { + /* ctx->level = 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, level)), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_GETSOCKOPT, + .expected_attach_type = BPF_CGROUP_GETSOCKOPT, + + .error = DENY_LOAD, + }, + { + .descr = "getsockopt: read ctx->optname", + .insns = { + /* r6 = ctx->optname */ + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct bpf_sockopt, optname)), + + /* if (ctx->optname == 123) { */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 123, 4), + /* ctx->retval = 0 */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, retval)), + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + /* } else { */ + /* return 0 */ + BPF_MOV64_IMM(BPF_REG_0, 0), + /* } */ + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_GETSOCKOPT, + .expected_attach_type = BPF_CGROUP_GETSOCKOPT, + + .get_optname = 123, + + .get_optlen = 1, + }, + { + .descr = "getsockopt: read ctx->retval", + .insns = { + /* r6 = ctx->retval */ + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct bpf_sockopt, retval)), + + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_GETSOCKOPT, + .expected_attach_type = BPF_CGROUP_GETSOCKOPT, + + .get_level = SOL_IP, + .get_optname = IP_TOS, + .get_optlen = 1, + }, + { + .descr = "getsockopt: deny writing to ctx->optname", + .insns = { + /* ctx->optname = 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, optname)), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_GETSOCKOPT, + .expected_attach_type = BPF_CGROUP_GETSOCKOPT, + + .error = DENY_LOAD, + }, + { + .descr = "getsockopt: read ctx->optlen", + .insns = { + /* r6 = ctx->optlen */ + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct bpf_sockopt, optlen)), + + /* if (ctx->optlen == 64) { */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 64, 4), + /* ctx->retval = 0 */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, retval)), + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + /* } else { */ + /* return 0 */ + BPF_MOV64_IMM(BPF_REG_0, 0), + /* } */ + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_GETSOCKOPT, + .expected_attach_type = BPF_CGROUP_GETSOCKOPT, + + .get_optlen = 64, + }, + { + .descr = "getsockopt: deny bigger ctx->optlen", + .insns = { + /* ctx->optlen = 65 */ + BPF_MOV64_IMM(BPF_REG_0, 65), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, optlen)), + + /* ctx->retval = 0 */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, retval)), + + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_GETSOCKOPT, + .expected_attach_type = BPF_CGROUP_GETSOCKOPT, + + .get_optlen = 64, + + .error = EFAULT_GETSOCKOPT, + }, + { + .descr = "getsockopt: deny arbitrary ctx->retval", + .insns = { + /* ctx->retval = 123 */ + BPF_MOV64_IMM(BPF_REG_0, 123), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, retval)), + + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_GETSOCKOPT, + .expected_attach_type = BPF_CGROUP_GETSOCKOPT, + + .get_optlen = 64, + + .error = EFAULT_GETSOCKOPT, + }, + { + .descr = "getsockopt: support smaller ctx->optlen", + .insns = { + /* ctx->optlen = 32 */ + BPF_MOV64_IMM(BPF_REG_0, 32), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, optlen)), + /* ctx->retval = 0 */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, retval)), + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_GETSOCKOPT, + .expected_attach_type = BPF_CGROUP_GETSOCKOPT, + + .get_optlen = 64, + .get_optlen_ret = 32, + }, + { + .descr = "getsockopt: deny writing to ctx->optval", + .insns = { + /* ctx->optval = 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, optval)), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_GETSOCKOPT, + .expected_attach_type = BPF_CGROUP_GETSOCKOPT, + + .error = DENY_LOAD, + }, + { + .descr = "getsockopt: deny writing to ctx->optval_end", + .insns = { + /* ctx->optval_end = 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, optval_end)), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_GETSOCKOPT, + .expected_attach_type = BPF_CGROUP_GETSOCKOPT, + + .error = DENY_LOAD, + }, + { + .descr = "getsockopt: rewrite value", + .insns = { + /* r6 = ctx->optval */ + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, + offsetof(struct bpf_sockopt, optval)), + /* r2 = ctx->optval */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + /* r6 = ctx->optval + 1 */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + + /* r7 = ctx->optval_end */ + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_1, + offsetof(struct bpf_sockopt, optval_end)), + + /* if (ctx->optval + 1 <= ctx->optval_end) { */ + BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_7, 1), + /* ctx->optval[0] = 0xF0 */ + BPF_ST_MEM(BPF_B, BPF_REG_2, 0, 0xF0), + /* } */ + + /* ctx->retval = 0 */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, retval)), + + /* return 1*/ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_GETSOCKOPT, + .expected_attach_type = BPF_CGROUP_GETSOCKOPT, + + .get_level = SOL_IP, + .get_optname = IP_TOS, + + .get_optval = { 0xF0 }, + .get_optlen = 1, + }, + + /* ==================== setsockopt ==================== */ + + { + .descr = "setsockopt: no expected_attach_type", + .insns = { + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = 0, + .error = DENY_LOAD, + }, + { + .descr = "setsockopt: wrong expected_attach_type", + .insns = { + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_GETSOCKOPT, + .error = DENY_ATTACH, + }, + { + .descr = "setsockopt: bypass bpf hook", + .insns = { + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + + .get_level = SOL_IP, + .set_level = SOL_IP, + + .get_optname = IP_TOS, + .set_optname = IP_TOS, + + .set_optval = { 1 << 3 }, + .set_optlen = 1, + + .get_optval = { 1 << 3 }, + .get_optlen = 1, + }, + { + .descr = "setsockopt: return EPERM from bpf hook", + .insns = { + /* return 0 */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + + .set_level = SOL_IP, + .set_optname = IP_TOS, + + .set_optlen = 1, + .error = EPERM_SETSOCKOPT, + }, + { + .descr = "setsockopt: no optval bounds check, deny loading", + .insns = { + /* r6 = ctx->optval */ + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, + offsetof(struct bpf_sockopt, optval)), + + /* r0 = ctx->optval[0] */ + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_6, 0), + + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + .error = DENY_LOAD, + }, + { + .descr = "setsockopt: read ctx->level", + .insns = { + /* r6 = ctx->level */ + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct bpf_sockopt, level)), + + /* if (ctx->level == 123) { */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 123, 4), + /* ctx->optlen = -1 */ + BPF_MOV64_IMM(BPF_REG_0, -1), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, optlen)), + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + /* } else { */ + /* return 0 */ + BPF_MOV64_IMM(BPF_REG_0, 0), + /* } */ + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + + .set_level = 123, + + .set_optlen = 1, + }, + { + .descr = "setsockopt: allow changing ctx->level", + .insns = { + /* ctx->level = SOL_IP */ + BPF_MOV64_IMM(BPF_REG_0, SOL_IP), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, level)), + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + + .get_level = SOL_IP, + .set_level = 234, /* should be rewritten to SOL_IP */ + + .get_optname = IP_TOS, + .set_optname = IP_TOS, + + .set_optval = { 1 << 3 }, + .set_optlen = 1, + .get_optval = { 1 << 3 }, + .get_optlen = 1, + }, + { + .descr = "setsockopt: read ctx->optname", + .insns = { + /* r6 = ctx->optname */ + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct bpf_sockopt, optname)), + + /* if (ctx->optname == 123) { */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 123, 4), + /* ctx->optlen = -1 */ + BPF_MOV64_IMM(BPF_REG_0, -1), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, optlen)), + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + /* } else { */ + /* return 0 */ + BPF_MOV64_IMM(BPF_REG_0, 0), + /* } */ + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + + .set_optname = 123, + + .set_optlen = 1, + }, + { + .descr = "setsockopt: allow changing ctx->optname", + .insns = { + /* ctx->optname = IP_TOS */ + BPF_MOV64_IMM(BPF_REG_0, IP_TOS), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, optname)), + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + + .get_level = SOL_IP, + .set_level = SOL_IP, + + .get_optname = IP_TOS, + .set_optname = 456, /* should be rewritten to IP_TOS */ + + .set_optval = { 1 << 3 }, + .set_optlen = 1, + .get_optval = { 1 << 3 }, + .get_optlen = 1, + }, + { + .descr = "setsockopt: read ctx->optlen", + .insns = { + /* r6 = ctx->optlen */ + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct bpf_sockopt, optlen)), + + /* if (ctx->optlen == 64) { */ + BPF_JMP_IMM(BPF_JNE, BPF_REG_6, 64, 4), + /* ctx->optlen = -1 */ + BPF_MOV64_IMM(BPF_REG_0, -1), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, optlen)), + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + /* } else { */ + /* return 0 */ + BPF_MOV64_IMM(BPF_REG_0, 0), + /* } */ + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + + .set_optlen = 64, + }, + { + .descr = "setsockopt: ctx->optlen == -1 is ok", + .insns = { + /* ctx->optlen = -1 */ + BPF_MOV64_IMM(BPF_REG_0, -1), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, optlen)), + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + + .set_optlen = 64, + }, + { + .descr = "setsockopt: deny ctx->optlen < 0 (except -1)", + .insns = { + /* ctx->optlen = -2 */ + BPF_MOV64_IMM(BPF_REG_0, -2), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, optlen)), + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + + .set_optlen = 4, + + .error = EFAULT_SETSOCKOPT, + }, + { + .descr = "setsockopt: deny ctx->optlen > input optlen", + .insns = { + /* ctx->optlen = 65 */ + BPF_MOV64_IMM(BPF_REG_0, 65), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, optlen)), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + + .set_optlen = 64, + + .error = EFAULT_SETSOCKOPT, + }, + { + .descr = "setsockopt: allow changing ctx->optlen within bounds", + .insns = { + /* r6 = ctx->optval */ + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, + offsetof(struct bpf_sockopt, optval)), + /* r2 = ctx->optval */ + BPF_MOV64_REG(BPF_REG_2, BPF_REG_6), + /* r6 = ctx->optval + 1 */ + BPF_ALU64_IMM(BPF_ADD, BPF_REG_6, 1), + + /* r7 = ctx->optval_end */ + BPF_LDX_MEM(BPF_DW, BPF_REG_7, BPF_REG_1, + offsetof(struct bpf_sockopt, optval_end)), + + /* if (ctx->optval + 1 <= ctx->optval_end) { */ + BPF_JMP_REG(BPF_JGT, BPF_REG_6, BPF_REG_7, 1), + /* ctx->optval[0] = 1 << 3 */ + BPF_ST_MEM(BPF_B, BPF_REG_2, 0, 1 << 3), + /* } */ + + /* ctx->optlen = 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, optlen)), + + /* return 1*/ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + + .get_level = SOL_IP, + .set_level = SOL_IP, + + .get_optname = IP_TOS, + .set_optname = IP_TOS, + + .set_optval = { 1, 1, 1, 1 }, + .set_optlen = 4, + .get_optval = { 1 << 3 }, + .get_optlen = 1, + }, + { + .descr = "setsockopt: deny write ctx->retval", + .insns = { + /* ctx->retval = 0 */ + BPF_MOV64_IMM(BPF_REG_0, 0), + BPF_STX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, retval)), + + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + + .error = DENY_LOAD, + }, + { + .descr = "setsockopt: deny read ctx->retval", + .insns = { + /* r6 = ctx->retval */ + BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1, + offsetof(struct bpf_sockopt, retval)), + + /* return 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + + .error = DENY_LOAD, + }, + { + .descr = "setsockopt: deny writing to ctx->optval", + .insns = { + /* ctx->optval = 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, optval)), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + + .error = DENY_LOAD, + }, + { + .descr = "setsockopt: deny writing to ctx->optval_end", + .insns = { + /* ctx->optval_end = 1 */ + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, + offsetof(struct bpf_sockopt, optval_end)), + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + + .error = DENY_LOAD, + }, + { + .descr = "setsockopt: allow IP_TOS <= 128", + .insns = { + /* r6 = ctx->optval */ + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, + offsetof(struct bpf_sockopt, optval)), + /* r7 = ctx->optval + 1 */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 1), + + /* r8 = ctx->optval_end */ + BPF_LDX_MEM(BPF_DW, BPF_REG_8, BPF_REG_1, + offsetof(struct bpf_sockopt, optval_end)), + + /* if (ctx->optval + 1 <= ctx->optval_end) { */ + BPF_JMP_REG(BPF_JGT, BPF_REG_7, BPF_REG_8, 4), + + /* r9 = ctx->optval[0] */ + BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_6, 0), + + /* if (ctx->optval[0] < 128) */ + BPF_JMP_IMM(BPF_JGT, BPF_REG_9, 128, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + /* } */ + + /* } else { */ + BPF_MOV64_IMM(BPF_REG_0, 0), + /* } */ + + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + + .get_level = SOL_IP, + .set_level = SOL_IP, + + .get_optname = IP_TOS, + .set_optname = IP_TOS, + + .set_optval = { 0x80 }, + .set_optlen = 1, + .get_optval = { 0x80 }, + .get_optlen = 1, + }, + { + .descr = "setsockopt: deny IP_TOS > 128", + .insns = { + /* r6 = ctx->optval */ + BPF_LDX_MEM(BPF_DW, BPF_REG_6, BPF_REG_1, + offsetof(struct bpf_sockopt, optval)), + /* r7 = ctx->optval + 1 */ + BPF_MOV64_REG(BPF_REG_7, BPF_REG_6), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_7, 1), + + /* r8 = ctx->optval_end */ + BPF_LDX_MEM(BPF_DW, BPF_REG_8, BPF_REG_1, + offsetof(struct bpf_sockopt, optval_end)), + + /* if (ctx->optval + 1 <= ctx->optval_end) { */ + BPF_JMP_REG(BPF_JGT, BPF_REG_7, BPF_REG_8, 4), + + /* r9 = ctx->optval[0] */ + BPF_LDX_MEM(BPF_B, BPF_REG_9, BPF_REG_6, 0), + + /* if (ctx->optval[0] < 128) */ + BPF_JMP_IMM(BPF_JGT, BPF_REG_9, 128, 2), + BPF_MOV64_IMM(BPF_REG_0, 1), + BPF_JMP_A(1), + /* } */ + + /* } else { */ + BPF_MOV64_IMM(BPF_REG_0, 0), + /* } */ + + BPF_EXIT_INSN(), + }, + .attach_type = BPF_CGROUP_SETSOCKOPT, + .expected_attach_type = BPF_CGROUP_SETSOCKOPT, + + .get_level = SOL_IP, + .set_level = SOL_IP, + + .get_optname = IP_TOS, + .set_optname = IP_TOS, + + .set_optval = { 0x81 }, + .set_optlen = 1, + .get_optval = { 0x00 }, + .get_optlen = 1, + + .error = EPERM_SETSOCKOPT, + }, +}; + +static int load_prog(const struct bpf_insn *insns, + enum bpf_attach_type expected_attach_type) +{ + struct bpf_load_program_attr attr = { + .prog_type = BPF_PROG_TYPE_CGROUP_SOCKOPT, + .expected_attach_type = expected_attach_type, + .insns = insns, + .license = "GPL", + .log_level = 2, + }; + int fd; + + for (; + insns[attr.insns_cnt].code != (BPF_JMP | BPF_EXIT); + attr.insns_cnt++) { + } + attr.insns_cnt++; + + fd = bpf_load_program_xattr(&attr, bpf_log_buf, sizeof(bpf_log_buf)); + if (verbose && fd < 0) + fprintf(stderr, "%s\n", bpf_log_buf); + + return fd; +} + +static int run_test(int cgroup_fd, struct sockopt_test *test) +{ + int sock_fd, err, prog_fd; + void *optval = NULL; + int ret = 0; + + prog_fd = load_prog(test->insns, test->expected_attach_type); + if (prog_fd < 0) { + if (test->error == DENY_LOAD) + return 0; + + log_err("Failed to load BPF program"); + return -1; + } + + err = bpf_prog_attach(prog_fd, cgroup_fd, test->attach_type, 0); + if (err < 0) { + if (test->error == DENY_ATTACH) + goto close_prog_fd; + + log_err("Failed to attach BPF program"); + ret = -1; + goto close_prog_fd; + } + + sock_fd = socket(AF_INET, SOCK_STREAM, 0); + if (sock_fd < 0) { + log_err("Failed to create AF_INET socket"); + ret = -1; + goto detach_prog; + } + + if (test->set_optlen) { + err = setsockopt(sock_fd, test->set_level, test->set_optname, + test->set_optval, test->set_optlen); + if (err) { + if (errno == EPERM && test->error == EPERM_SETSOCKOPT) + goto close_sock_fd; + if (errno == EFAULT && test->error == EFAULT_SETSOCKOPT) + goto free_optval; + + log_err("Failed to call setsockopt"); + ret = -1; + goto close_sock_fd; + } + } + + if (test->get_optlen) { + optval = malloc(test->get_optlen); + socklen_t optlen = test->get_optlen; + socklen_t expected_get_optlen = test->get_optlen_ret ?: + test->get_optlen; + + err = getsockopt(sock_fd, test->get_level, test->get_optname, + optval, &optlen); + if (err) { + if (errno == EPERM && test->error == EPERM_GETSOCKOPT) + goto free_optval; + if (errno == EFAULT && test->error == EFAULT_GETSOCKOPT) + goto free_optval; + + log_err("Failed to call getsockopt"); + ret = -1; + goto free_optval; + } + + if (optlen != expected_get_optlen) { + errno = 0; + log_err("getsockopt returned unexpected optlen"); + ret = -1; + goto free_optval; + } + + if (memcmp(optval, test->get_optval, optlen) != 0) { + errno = 0; + log_err("getsockopt returned unexpected optval"); + ret = -1; + goto free_optval; + } + } + + ret = test->error != OK; + +free_optval: + free(optval); +close_sock_fd: + close(sock_fd); +detach_prog: + bpf_prog_detach2(prog_fd, cgroup_fd, test->attach_type); +close_prog_fd: + close(prog_fd); + return ret; +} + +int main(int args, char **argv) +{ + int err = EXIT_FAILURE, error_cnt = 0; + int cgroup_fd, i; + + if (setup_cgroup_environment()) + goto cleanup_obj; + + cgroup_fd = create_and_get_cgroup(CG_PATH); + if (cgroup_fd < 0) + goto cleanup_cgroup_env; + + if (join_cgroup(CG_PATH)) + goto cleanup_cgroup; + + for (i = 0; i < ARRAY_SIZE(tests); i++) { + int err = run_test(cgroup_fd, &tests[i]); + + if (err) + error_cnt++; + + printf("#%d %s: %s\n", i, err ? "FAIL" : "PASS", + tests[i].descr); + } + + printf("Summary: %ld PASSED, %d FAILED\n", + ARRAY_SIZE(tests) - error_cnt, error_cnt); + err = error_cnt ? EXIT_FAILURE : EXIT_SUCCESS; + +cleanup_cgroup: + close(cgroup_fd); +cleanup_cgroup_env: + cleanup_cgroup_environment(); +cleanup_obj: + return err; +} diff --git a/tools/testing/selftests/bpf/test_sockopt_multi.c b/tools/testing/selftests/bpf/test_sockopt_multi.c new file mode 100644 index 000000000000..4be3441db867 --- /dev/null +++ b/tools/testing/selftests/bpf/test_sockopt_multi.c @@ -0,0 +1,374 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <error.h> +#include <errno.h> +#include <stdio.h> +#include <unistd.h> +#include <sys/types.h> +#include <sys/socket.h> +#include <netinet/in.h> + +#include <linux/filter.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include "bpf_rlimit.h" +#include "bpf_util.h" +#include "cgroup_helpers.h" + +static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title) +{ + enum bpf_attach_type attach_type; + enum bpf_prog_type prog_type; + struct bpf_program *prog; + int err; + + err = libbpf_prog_type_by_name(title, &prog_type, &attach_type); + if (err) { + log_err("Failed to deduct types for %s BPF program", title); + return -1; + } + + prog = bpf_object__find_program_by_title(obj, title); + if (!prog) { + log_err("Failed to find %s BPF program", title); + return -1; + } + + err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd, + attach_type, BPF_F_ALLOW_MULTI); + if (err) { + log_err("Failed to attach %s BPF program", title); + return -1; + } + + return 0; +} + +static int prog_detach(struct bpf_object *obj, int cgroup_fd, const char *title) +{ + enum bpf_attach_type attach_type; + enum bpf_prog_type prog_type; + struct bpf_program *prog; + int err; + + err = libbpf_prog_type_by_name(title, &prog_type, &attach_type); + if (err) + return -1; + + prog = bpf_object__find_program_by_title(obj, title); + if (!prog) + return -1; + + err = bpf_prog_detach2(bpf_program__fd(prog), cgroup_fd, + attach_type); + if (err) + return -1; + + return 0; +} + +static int run_getsockopt_test(struct bpf_object *obj, int cg_parent, + int cg_child, int sock_fd) +{ + socklen_t optlen; + __u8 buf; + int err; + + /* Set IP_TOS to the expected value (0x80). */ + + buf = 0x80; + err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1); + if (err < 0) { + log_err("Failed to call setsockopt(IP_TOS)"); + goto detach; + } + + buf = 0x00; + optlen = 1; + err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen); + if (err) { + log_err("Failed to call getsockopt(IP_TOS)"); + goto detach; + } + + if (buf != 0x80) { + log_err("Unexpected getsockopt 0x%x != 0x80 without BPF", buf); + err = -1; + goto detach; + } + + /* Attach child program and make sure it returns new value: + * - kernel: -> 0x80 + * - child: 0x80 -> 0x90 + */ + + err = prog_attach(obj, cg_child, "cgroup/getsockopt/child"); + if (err) + goto detach; + + buf = 0x00; + optlen = 1; + err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen); + if (err) { + log_err("Failed to call getsockopt(IP_TOS)"); + goto detach; + } + + if (buf != 0x90) { + log_err("Unexpected getsockopt 0x%x != 0x90", buf); + err = -1; + goto detach; + } + + /* Attach parent program and make sure it returns new value: + * - kernel: -> 0x80 + * - child: 0x80 -> 0x90 + * - parent: 0x90 -> 0xA0 + */ + + err = prog_attach(obj, cg_parent, "cgroup/getsockopt/parent"); + if (err) + goto detach; + + buf = 0x00; + optlen = 1; + err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen); + if (err) { + log_err("Failed to call getsockopt(IP_TOS)"); + goto detach; + } + + if (buf != 0xA0) { + log_err("Unexpected getsockopt 0x%x != 0xA0", buf); + err = -1; + goto detach; + } + + /* Setting unexpected initial sockopt should return EPERM: + * - kernel: -> 0x40 + * - child: unexpected 0x40, EPERM + * - parent: unexpected 0x40, EPERM + */ + + buf = 0x40; + if (setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1) < 0) { + log_err("Failed to call setsockopt(IP_TOS)"); + goto detach; + } + + buf = 0x00; + optlen = 1; + err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen); + if (!err) { + log_err("Unexpected success from getsockopt(IP_TOS)"); + goto detach; + } + + /* Detach child program and make sure we still get EPERM: + * - kernel: -> 0x40 + * - parent: unexpected 0x40, EPERM + */ + + err = prog_detach(obj, cg_child, "cgroup/getsockopt/child"); + if (err) { + log_err("Failed to detach child program"); + goto detach; + } + + buf = 0x00; + optlen = 1; + err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen); + if (!err) { + log_err("Unexpected success from getsockopt(IP_TOS)"); + goto detach; + } + + /* Set initial value to the one the parent program expects: + * - kernel: -> 0x90 + * - parent: 0x90 -> 0xA0 + */ + + buf = 0x90; + err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1); + if (err < 0) { + log_err("Failed to call setsockopt(IP_TOS)"); + goto detach; + } + + buf = 0x00; + optlen = 1; + err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen); + if (err) { + log_err("Failed to call getsockopt(IP_TOS)"); + goto detach; + } + + if (buf != 0xA0) { + log_err("Unexpected getsockopt 0x%x != 0xA0", buf); + err = -1; + goto detach; + } + +detach: + prog_detach(obj, cg_child, "cgroup/getsockopt/child"); + prog_detach(obj, cg_parent, "cgroup/getsockopt/parent"); + + return err; +} + +static int run_setsockopt_test(struct bpf_object *obj, int cg_parent, + int cg_child, int sock_fd) +{ + socklen_t optlen; + __u8 buf; + int err; + + /* Set IP_TOS to the expected value (0x80). */ + + buf = 0x80; + err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1); + if (err < 0) { + log_err("Failed to call setsockopt(IP_TOS)"); + goto detach; + } + + buf = 0x00; + optlen = 1; + err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen); + if (err) { + log_err("Failed to call getsockopt(IP_TOS)"); + goto detach; + } + + if (buf != 0x80) { + log_err("Unexpected getsockopt 0x%x != 0x80 without BPF", buf); + err = -1; + goto detach; + } + + /* Attach child program and make sure it adds 0x10. */ + + err = prog_attach(obj, cg_child, "cgroup/setsockopt"); + if (err) + goto detach; + + buf = 0x80; + err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1); + if (err < 0) { + log_err("Failed to call setsockopt(IP_TOS)"); + goto detach; + } + + buf = 0x00; + optlen = 1; + err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen); + if (err) { + log_err("Failed to call getsockopt(IP_TOS)"); + goto detach; + } + + if (buf != 0x80 + 0x10) { + log_err("Unexpected getsockopt 0x%x != 0x80 + 0x10", buf); + err = -1; + goto detach; + } + + /* Attach parent program and make sure it adds another 0x10. */ + + err = prog_attach(obj, cg_parent, "cgroup/setsockopt"); + if (err) + goto detach; + + buf = 0x80; + err = setsockopt(sock_fd, SOL_IP, IP_TOS, &buf, 1); + if (err < 0) { + log_err("Failed to call setsockopt(IP_TOS)"); + goto detach; + } + + buf = 0x00; + optlen = 1; + err = getsockopt(sock_fd, SOL_IP, IP_TOS, &buf, &optlen); + if (err) { + log_err("Failed to call getsockopt(IP_TOS)"); + goto detach; + } + + if (buf != 0x80 + 2 * 0x10) { + log_err("Unexpected getsockopt 0x%x != 0x80 + 2 * 0x10", buf); + err = -1; + goto detach; + } + +detach: + prog_detach(obj, cg_child, "cgroup/setsockopt"); + prog_detach(obj, cg_parent, "cgroup/setsockopt"); + + return err; +} + +int main(int argc, char **argv) +{ + struct bpf_prog_load_attr attr = { + .file = "./sockopt_multi.o", + }; + int cg_parent = -1, cg_child = -1; + struct bpf_object *obj = NULL; + int sock_fd = -1; + int err = -1; + int ignored; + + if (setup_cgroup_environment()) { + log_err("Failed to setup cgroup environment\n"); + goto out; + } + + cg_parent = create_and_get_cgroup("/parent"); + if (cg_parent < 0) { + log_err("Failed to create cgroup /parent\n"); + goto out; + } + + cg_child = create_and_get_cgroup("/parent/child"); + if (cg_child < 0) { + log_err("Failed to create cgroup /parent/child\n"); + goto out; + } + + if (join_cgroup("/parent/child")) { + log_err("Failed to join cgroup /parent/child\n"); + goto out; + } + + err = bpf_prog_load_xattr(&attr, &obj, &ignored); + if (err) { + log_err("Failed to load BPF object"); + goto out; + } + + sock_fd = socket(AF_INET, SOCK_STREAM, 0); + if (sock_fd < 0) { + log_err("Failed to create socket"); + goto out; + } + + if (run_getsockopt_test(obj, cg_parent, cg_child, sock_fd)) + err = -1; + printf("test_sockopt_multi: getsockopt %s\n", + err ? "FAILED" : "PASSED"); + + if (run_setsockopt_test(obj, cg_parent, cg_child, sock_fd)) + err = -1; + printf("test_sockopt_multi: setsockopt %s\n", + err ? "FAILED" : "PASSED"); + +out: + close(sock_fd); + bpf_object__close(obj); + close(cg_child); + close(cg_parent); + + printf("test_sockopt_multi: %s\n", err ? "FAILED" : "PASSED"); + return err ? EXIT_FAILURE : EXIT_SUCCESS; +} diff --git a/tools/testing/selftests/bpf/test_sockopt_sk.c b/tools/testing/selftests/bpf/test_sockopt_sk.c new file mode 100644 index 000000000000..036b652e5ca9 --- /dev/null +++ b/tools/testing/selftests/bpf/test_sockopt_sk.c @@ -0,0 +1,211 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <errno.h> +#include <stdio.h> +#include <unistd.h> +#include <sys/types.h> +#include <sys/socket.h> +#include <netinet/in.h> + +#include <linux/filter.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include "bpf_rlimit.h" +#include "bpf_util.h" +#include "cgroup_helpers.h" + +#define CG_PATH "/sockopt" + +#define SOL_CUSTOM 0xdeadbeef + +static int getsetsockopt(void) +{ + int fd, err; + union { + char u8[4]; + __u32 u32; + } buf = {}; + socklen_t optlen; + + fd = socket(AF_INET, SOCK_STREAM, 0); + if (fd < 0) { + log_err("Failed to create socket"); + return -1; + } + + /* IP_TOS - BPF bypass */ + + buf.u8[0] = 0x08; + err = setsockopt(fd, SOL_IP, IP_TOS, &buf, 1); + if (err) { + log_err("Failed to call setsockopt(IP_TOS)"); + goto err; + } + + buf.u8[0] = 0x00; + optlen = 1; + err = getsockopt(fd, SOL_IP, IP_TOS, &buf, &optlen); + if (err) { + log_err("Failed to call getsockopt(IP_TOS)"); + goto err; + } + + if (buf.u8[0] != 0x08) { + log_err("Unexpected getsockopt(IP_TOS) buf[0] 0x%02x != 0x08", + buf.u8[0]); + goto err; + } + + /* IP_TTL - EPERM */ + + buf.u8[0] = 1; + err = setsockopt(fd, SOL_IP, IP_TTL, &buf, 1); + if (!err || errno != EPERM) { + log_err("Unexpected success from setsockopt(IP_TTL)"); + goto err; + } + + /* SOL_CUSTOM - handled by BPF */ + + buf.u8[0] = 0x01; + err = setsockopt(fd, SOL_CUSTOM, 0, &buf, 1); + if (err) { + log_err("Failed to call setsockopt"); + goto err; + } + + buf.u32 = 0x00; + optlen = 4; + err = getsockopt(fd, SOL_CUSTOM, 0, &buf, &optlen); + if (err) { + log_err("Failed to call getsockopt"); + goto err; + } + + if (optlen != 1) { + log_err("Unexpected optlen %d != 1", optlen); + goto err; + } + if (buf.u8[0] != 0x01) { + log_err("Unexpected buf[0] 0x%02x != 0x01", buf.u8[0]); + goto err; + } + + /* SO_SNDBUF is overwritten */ + + buf.u32 = 0x01010101; + err = setsockopt(fd, SOL_SOCKET, SO_SNDBUF, &buf, 4); + if (err) { + log_err("Failed to call setsockopt(SO_SNDBUF)"); + goto err; + } + + buf.u32 = 0x00; + optlen = 4; + err = getsockopt(fd, SOL_SOCKET, SO_SNDBUF, &buf, &optlen); + if (err) { + log_err("Failed to call getsockopt(SO_SNDBUF)"); + goto err; + } + + if (buf.u32 != 0x55AA*2) { + log_err("Unexpected getsockopt(SO_SNDBUF) 0x%x != 0x55AA*2", + buf.u32); + goto err; + } + + close(fd); + return 0; +err: + close(fd); + return -1; +} + +static int prog_attach(struct bpf_object *obj, int cgroup_fd, const char *title) +{ + enum bpf_attach_type attach_type; + enum bpf_prog_type prog_type; + struct bpf_program *prog; + int err; + + err = libbpf_prog_type_by_name(title, &prog_type, &attach_type); + if (err) { + log_err("Failed to deduct types for %s BPF program", title); + return -1; + } + + prog = bpf_object__find_program_by_title(obj, title); + if (!prog) { + log_err("Failed to find %s BPF program", title); + return -1; + } + + err = bpf_prog_attach(bpf_program__fd(prog), cgroup_fd, + attach_type, 0); + if (err) { + log_err("Failed to attach %s BPF program", title); + return -1; + } + + return 0; +} + +static int run_test(int cgroup_fd) +{ + struct bpf_prog_load_attr attr = { + .file = "./sockopt_sk.o", + }; + struct bpf_object *obj; + int ignored; + int err; + + err = bpf_prog_load_xattr(&attr, &obj, &ignored); + if (err) { + log_err("Failed to load BPF object"); + return -1; + } + + err = prog_attach(obj, cgroup_fd, "cgroup/getsockopt"); + if (err) + goto close_bpf_object; + + err = prog_attach(obj, cgroup_fd, "cgroup/setsockopt"); + if (err) + goto close_bpf_object; + + err = getsetsockopt(); + +close_bpf_object: + bpf_object__close(obj); + return err; +} + +int main(int args, char **argv) +{ + int cgroup_fd; + int err = EXIT_SUCCESS; + + if (setup_cgroup_environment()) + goto cleanup_obj; + + cgroup_fd = create_and_get_cgroup(CG_PATH); + if (cgroup_fd < 0) + goto cleanup_cgroup_env; + + if (join_cgroup(CG_PATH)) + goto cleanup_cgroup; + + if (run_test(cgroup_fd)) + err = EXIT_FAILURE; + + printf("test_sockopt_sk: %s\n", + err == EXIT_SUCCESS ? "PASSED" : "FAILED"); + +cleanup_cgroup: + close(cgroup_fd); +cleanup_cgroup_env: + cleanup_cgroup_environment(); +cleanup_obj: + return err; +} diff --git a/tools/testing/selftests/bpf/test_tcp_rtt.c b/tools/testing/selftests/bpf/test_tcp_rtt.c new file mode 100644 index 000000000000..90c3862f74a8 --- /dev/null +++ b/tools/testing/selftests/bpf/test_tcp_rtt.c @@ -0,0 +1,254 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <error.h> +#include <errno.h> +#include <stdio.h> +#include <unistd.h> +#include <sys/types.h> +#include <sys/socket.h> +#include <netinet/in.h> +#include <pthread.h> + +#include <linux/filter.h> +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include "bpf_rlimit.h" +#include "bpf_util.h" +#include "cgroup_helpers.h" + +#define CG_PATH "/tcp_rtt" + +struct tcp_rtt_storage { + __u32 invoked; + __u32 dsack_dups; + __u32 delivered; + __u32 delivered_ce; + __u32 icsk_retransmits; +}; + +static void send_byte(int fd) +{ + char b = 0x55; + + if (write(fd, &b, sizeof(b)) != 1) + error(1, errno, "Failed to send single byte"); +} + +static int verify_sk(int map_fd, int client_fd, const char *msg, __u32 invoked, + __u32 dsack_dups, __u32 delivered, __u32 delivered_ce, + __u32 icsk_retransmits) +{ + int err = 0; + struct tcp_rtt_storage val; + + if (bpf_map_lookup_elem(map_fd, &client_fd, &val) < 0) + error(1, errno, "Failed to read socket storage"); + + if (val.invoked != invoked) { + log_err("%s: unexpected bpf_tcp_sock.invoked %d != %d", + msg, val.invoked, invoked); + err++; + } + + if (val.dsack_dups != dsack_dups) { + log_err("%s: unexpected bpf_tcp_sock.dsack_dups %d != %d", + msg, val.dsack_dups, dsack_dups); + err++; + } + + if (val.delivered != delivered) { + log_err("%s: unexpected bpf_tcp_sock.delivered %d != %d", + msg, val.delivered, delivered); + err++; + } + + if (val.delivered_ce != delivered_ce) { + log_err("%s: unexpected bpf_tcp_sock.delivered_ce %d != %d", + msg, val.delivered_ce, delivered_ce); + err++; + } + + if (val.icsk_retransmits != icsk_retransmits) { + log_err("%s: unexpected bpf_tcp_sock.icsk_retransmits %d != %d", + msg, val.icsk_retransmits, icsk_retransmits); + err++; + } + + return err; +} + +static int connect_to_server(int server_fd) +{ + struct sockaddr_storage addr; + socklen_t len = sizeof(addr); + int fd; + + fd = socket(AF_INET, SOCK_STREAM, 0); + if (fd < 0) { + log_err("Failed to create client socket"); + return -1; + } + + if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) { + log_err("Failed to get server addr"); + goto out; + } + + if (connect(fd, (const struct sockaddr *)&addr, len) < 0) { + log_err("Fail to connect to server"); + goto out; + } + + return fd; + +out: + close(fd); + return -1; +} + +static int run_test(int cgroup_fd, int server_fd) +{ + struct bpf_prog_load_attr attr = { + .prog_type = BPF_PROG_TYPE_SOCK_OPS, + .file = "./tcp_rtt.o", + .expected_attach_type = BPF_CGROUP_SOCK_OPS, + }; + struct bpf_object *obj; + struct bpf_map *map; + int client_fd; + int prog_fd; + int map_fd; + int err; + + err = bpf_prog_load_xattr(&attr, &obj, &prog_fd); + if (err) { + log_err("Failed to load BPF object"); + return -1; + } + + map = bpf_map__next(NULL, obj); + map_fd = bpf_map__fd(map); + + err = bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_SOCK_OPS, 0); + if (err) { + log_err("Failed to attach BPF program"); + goto close_bpf_object; + } + + client_fd = connect_to_server(server_fd); + if (client_fd < 0) { + err = -1; + goto close_bpf_object; + } + + err += verify_sk(map_fd, client_fd, "syn-ack", + /*invoked=*/1, + /*dsack_dups=*/0, + /*delivered=*/1, + /*delivered_ce=*/0, + /*icsk_retransmits=*/0); + + send_byte(client_fd); + + err += verify_sk(map_fd, client_fd, "first payload byte", + /*invoked=*/2, + /*dsack_dups=*/0, + /*delivered=*/2, + /*delivered_ce=*/0, + /*icsk_retransmits=*/0); + + close(client_fd); + +close_bpf_object: + bpf_object__close(obj); + return err; +} + +static int start_server(void) +{ + struct sockaddr_in addr = { + .sin_family = AF_INET, + .sin_addr.s_addr = htonl(INADDR_LOOPBACK), + }; + int fd; + + fd = socket(AF_INET, SOCK_STREAM, 0); + if (fd < 0) { + log_err("Failed to create server socket"); + return -1; + } + + if (bind(fd, (const struct sockaddr *)&addr, sizeof(addr)) < 0) { + log_err("Failed to bind socket"); + close(fd); + return -1; + } + + return fd; +} + +static void *server_thread(void *arg) +{ + struct sockaddr_storage addr; + socklen_t len = sizeof(addr); + int fd = *(int *)arg; + int client_fd; + + if (listen(fd, 1) < 0) + error(1, errno, "Failed to listed on socket"); + + client_fd = accept(fd, (struct sockaddr *)&addr, &len); + if (client_fd < 0) + error(1, errno, "Failed to accept client"); + + /* Wait for the next connection (that never arrives) + * to keep this thread alive to prevent calling + * close() on client_fd. + */ + if (accept(fd, (struct sockaddr *)&addr, &len) >= 0) + error(1, errno, "Unexpected success in second accept"); + + close(client_fd); + + return NULL; +} + +int main(int args, char **argv) +{ + int server_fd, cgroup_fd; + int err = EXIT_SUCCESS; + pthread_t tid; + + if (setup_cgroup_environment()) + goto cleanup_obj; + + cgroup_fd = create_and_get_cgroup(CG_PATH); + if (cgroup_fd < 0) + goto cleanup_cgroup_env; + + if (join_cgroup(CG_PATH)) + goto cleanup_cgroup; + + server_fd = start_server(); + if (server_fd < 0) { + err = EXIT_FAILURE; + goto cleanup_cgroup; + } + + pthread_create(&tid, NULL, server_thread, (void *)&server_fd); + + if (run_test(cgroup_fd, server_fd)) + err = EXIT_FAILURE; + + close(server_fd); + + printf("test_sockopt_sk: %s\n", + err == EXIT_SUCCESS ? "PASSED" : "FAILED"); + +cleanup_cgroup: + close(cgroup_fd); +cleanup_cgroup_env: + cleanup_cgroup_environment(); +cleanup_obj: + return err; +} diff --git a/tools/testing/selftests/bpf/test_xdp_veth.sh b/tools/testing/selftests/bpf/test_xdp_veth.sh new file mode 100755 index 000000000000..ba8ffcdaac30 --- /dev/null +++ b/tools/testing/selftests/bpf/test_xdp_veth.sh @@ -0,0 +1,118 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Create 3 namespaces with 3 veth peers, and +# forward packets in-between using native XDP +# +# XDP_TX +# NS1(veth11) NS2(veth22) NS3(veth33) +# | | | +# | | | +# (veth1, (veth2, (veth3, +# id:111) id:122) id:133) +# ^ | ^ | ^ | +# | | XDP_REDIRECT | | XDP_REDIRECT | | +# | ------------------ ------------------ | +# ----------------------------------------- +# XDP_REDIRECT + +# Kselftest framework requirement - SKIP code is 4. +ksft_skip=4 + +TESTNAME=xdp_veth +BPF_FS=$(awk '$3 == "bpf" {print $2; exit}' /proc/mounts) +BPF_DIR=$BPF_FS/test_$TESTNAME + +_cleanup() +{ + set +e + ip link del veth1 2> /dev/null + ip link del veth2 2> /dev/null + ip link del veth3 2> /dev/null + ip netns del ns1 2> /dev/null + ip netns del ns2 2> /dev/null + ip netns del ns3 2> /dev/null + rm -rf $BPF_DIR 2> /dev/null +} + +cleanup_skip() +{ + echo "selftests: $TESTNAME [SKIP]" + _cleanup + + exit $ksft_skip +} + +cleanup() +{ + if [ "$?" = 0 ]; then + echo "selftests: $TESTNAME [PASS]" + else + echo "selftests: $TESTNAME [FAILED]" + fi + _cleanup +} + +if [ $(id -u) -ne 0 ]; then + echo "selftests: $TESTNAME [SKIP] Need root privileges" + exit $ksft_skip +fi + +if ! ip link set dev lo xdp off > /dev/null 2>&1; then + echo "selftests: $TESTNAME [SKIP] Could not run test without the ip xdp support" + exit $ksft_skip +fi + +if [ -z "$BPF_FS" ]; then + echo "selftests: $TESTNAME [SKIP] Could not run test without bpffs mounted" + exit $ksft_skip +fi + +if ! bpftool version > /dev/null 2>&1; then + echo "selftests: $TESTNAME [SKIP] Could not run test without bpftool" + exit $ksft_skip +fi + +set -e + +trap cleanup_skip EXIT + +ip netns add ns1 +ip netns add ns2 +ip netns add ns3 + +ip link add veth1 index 111 type veth peer name veth11 netns ns1 +ip link add veth2 index 122 type veth peer name veth22 netns ns2 +ip link add veth3 index 133 type veth peer name veth33 netns ns3 + +ip link set veth1 up +ip link set veth2 up +ip link set veth3 up + +ip -n ns1 addr add 10.1.1.11/24 dev veth11 +ip -n ns3 addr add 10.1.1.33/24 dev veth33 + +ip -n ns1 link set dev veth11 up +ip -n ns2 link set dev veth22 up +ip -n ns3 link set dev veth33 up + +mkdir $BPF_DIR +bpftool prog loadall \ + xdp_redirect_map.o $BPF_DIR/progs type xdp \ + pinmaps $BPF_DIR/maps +bpftool map update pinned $BPF_DIR/maps/tx_port key 0 0 0 0 value 122 0 0 0 +bpftool map update pinned $BPF_DIR/maps/tx_port key 1 0 0 0 value 133 0 0 0 +bpftool map update pinned $BPF_DIR/maps/tx_port key 2 0 0 0 value 111 0 0 0 +ip link set dev veth1 xdp pinned $BPF_DIR/progs/redirect_map_0 +ip link set dev veth2 xdp pinned $BPF_DIR/progs/redirect_map_1 +ip link set dev veth3 xdp pinned $BPF_DIR/progs/redirect_map_2 + +ip -n ns1 link set dev veth11 xdp obj xdp_dummy.o sec xdp_dummy +ip -n ns2 link set dev veth22 xdp obj xdp_tx.o sec tx +ip -n ns3 link set dev veth33 xdp obj xdp_dummy.o sec xdp_dummy + +trap cleanup EXIT + +ip netns exec ns1 ping -c 1 -W 1 10.1.1.33 + +exit 0 |