diff options
196 files changed, 4330 insertions, 2569 deletions
diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index de6c4df61082..57420356ce4c 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -124,6 +124,9 @@ #define SO_DETACH_REUSEPORT_BPF 68 +#define SO_PREFER_BUSY_POLL 69 +#define SO_BUSY_POLL_BUDGET 70 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index d0a9ed2ca2d6..2d949969313b 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -135,6 +135,9 @@ #define SO_DETACH_REUSEPORT_BPF 68 +#define SO_PREFER_BUSY_POLL 69 +#define SO_BUSY_POLL_BUDGET 70 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index 10173c32195e..f60904329bbc 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -116,6 +116,9 @@ #define SO_DETACH_REUSEPORT_BPF 0x4042 +#define SO_PREFER_BUSY_POLL 0x4043 +#define SO_BUSY_POLL_BUDGET 0x4044 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 8029b681fc7c..848a22fbac20 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -117,6 +117,9 @@ #define SO_DETACH_REUSEPORT_BPF 0x0047 +#define SO_PREFER_BUSY_POLL 0x0048 +#define SO_BUSY_POLL_BUDGET 0x0049 + #if !defined(__KERNEL__) diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index df1884d57d1a..0e98f45c2b22 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -416,7 +416,7 @@ static int ena_xdp_register_rxq_info(struct ena_ring *rx_ring) { int rc; - rc = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, rx_ring->qid); + rc = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, rx_ring->qid, 0); if (rc) { netif_err(rx_ring->adapter, ifup, rx_ring->netdev, diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 0af0af2b70fe..4edd6f8e017e 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -2884,7 +2884,7 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp) if (rc) return rc; - rc = xdp_rxq_info_reg(&rxr->xdp_rxq, bp->dev, i); + rc = xdp_rxq_info_reg(&rxr->xdp_rxq, bp->dev, i, 0); if (rc < 0) return rc; diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c index 7a141ce32e86..f782e6af45e9 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c @@ -770,7 +770,7 @@ static void nicvf_rcv_queue_config(struct nicvf *nic, struct queue_set *qs, rq->caching = 1; /* Driver have no proper error path for failed XDP RX-queue info reg */ - WARN_ON(xdp_rxq_info_reg(&rq->xdp_rxq, nic->netdev, qidx) < 0); + WARN_ON(xdp_rxq_info_reg(&rq->xdp_rxq, nic->netdev, qidx, 0) < 0); /* Send a mailbox msg to PF to config RQ */ mbx.rq.msg = NIC_MBOX_MSG_RQ_CFG; diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index a0a30c721fe7..91cff93dbdae 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -3334,7 +3334,7 @@ static int dpaa2_eth_setup_rx_flow(struct dpaa2_eth_priv *priv, return 0; err = xdp_rxq_info_reg(&fq->channel->xdp_rxq, priv->net_dev, - fq->flowid); + fq->flowid, 0); if (err) { dev_err(dev, "xdp_rxq_info_reg failed\n"); return err; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index d43ce13a93c9..9f73cd7aee09 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -676,6 +676,8 @@ void i40e_free_tx_resources(struct i40e_ring *tx_ring) i40e_clean_tx_ring(tx_ring); kfree(tx_ring->tx_bi); tx_ring->tx_bi = NULL; + kfree(tx_ring->xsk_descs); + tx_ring->xsk_descs = NULL; if (tx_ring->desc) { dma_free_coherent(tx_ring->dev, tx_ring->size, @@ -1277,6 +1279,13 @@ int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring) if (!tx_ring->tx_bi) goto err; + if (ring_is_xdp(tx_ring)) { + tx_ring->xsk_descs = kcalloc(I40E_MAX_NUM_DESCRIPTORS, sizeof(*tx_ring->xsk_descs), + GFP_KERNEL); + if (!tx_ring->xsk_descs) + goto err; + } + u64_stats_init(&tx_ring->syncp); /* round up to nearest 4K */ @@ -1300,6 +1309,8 @@ int i40e_setup_tx_descriptors(struct i40e_ring *tx_ring) return 0; err: + kfree(tx_ring->xsk_descs); + tx_ring->xsk_descs = NULL; kfree(tx_ring->tx_bi); tx_ring->tx_bi = NULL; return -ENOMEM; @@ -1436,7 +1447,7 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring) /* XDP RX-queue info only needed for RX rings exposed to XDP */ if (rx_ring->vsi->type == I40E_VSI_MAIN) { err = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, - rx_ring->queue_index); + rx_ring->queue_index, rx_ring->q_vector->napi.napi_id); if (err < 0) return err; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 2feed920ef8a..5f531b195959 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -389,6 +389,7 @@ struct i40e_ring { struct i40e_channel *ch; struct xdp_rxq_info xdp_rxq; struct xsk_buff_pool *xsk_pool; + struct xdp_desc *xsk_descs; /* For storing descriptors in the AF_XDP ZC path */ } ____cacheline_internodealigned_in_smp; static inline bool ring_uses_build_skb(struct i40e_ring *ring) diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 67febc7b6798..bfa84bfb0488 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -2,6 +2,7 @@ /* Copyright(c) 2018 Intel Corporation. */ #include <linux/bpf_trace.h> +#include <linux/stringify.h> #include <net/xdp_sock_drv.h> #include <net/xdp.h> @@ -380,58 +381,102 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) return failure ? budget : (int)total_rx_packets; } -/** - * i40e_xmit_zc - Performs zero-copy Tx AF_XDP - * @xdp_ring: XDP Tx ring - * @budget: NAPI budget - * - * Returns true if the work is finished. - **/ -static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget) +static void i40e_xmit_pkt(struct i40e_ring *xdp_ring, struct xdp_desc *desc, + unsigned int *total_bytes) { - unsigned int sent_frames = 0, total_bytes = 0; - struct i40e_tx_desc *tx_desc = NULL; - struct i40e_tx_buffer *tx_bi; - struct xdp_desc desc; + struct i40e_tx_desc *tx_desc; dma_addr_t dma; - while (budget-- > 0) { - if (!xsk_tx_peek_desc(xdp_ring->xsk_pool, &desc)) - break; + dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc->addr); + xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc->len); - dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc.addr); - xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, - 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, desc->len, 0); - tx_bi = &xdp_ring->tx_bi[xdp_ring->next_to_use]; - tx_bi->bytecount = desc.len; + *total_bytes += 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, desc.len, 0); +static void i40e_xmit_pkt_batch(struct i40e_ring *xdp_ring, struct xdp_desc *desc, + unsigned int *total_bytes) +{ + u16 ntu = xdp_ring->next_to_use; + struct i40e_tx_desc *tx_desc; + dma_addr_t dma; + u32 i; - sent_frames++; - total_bytes += tx_bi->bytecount; + loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) { + dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc[i].addr); + xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc[i].len); - xdp_ring->next_to_use++; - if (xdp_ring->next_to_use == xdp_ring->count) - xdp_ring->next_to_use = 0; + tx_desc = I40E_TX_DESC(xdp_ring, ntu++); + 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, desc[i].len, 0); + + *total_bytes += desc[i].len; } - if (tx_desc) { - /* Request an interrupt for the last frame and bump tail ptr. */ - tx_desc->cmd_type_offset_bsz |= (I40E_TX_DESC_CMD_RS << - I40E_TXD_QW1_CMD_SHIFT); - i40e_xdp_ring_update_tail(xdp_ring); + xdp_ring->next_to_use = ntu; +} + +static void i40e_fill_tx_hw_ring(struct i40e_ring *xdp_ring, struct xdp_desc *descs, u32 nb_pkts, + unsigned int *total_bytes) +{ + u32 batched, leftover, i; + + batched = nb_pkts & ~(PKTS_PER_BATCH - 1); + leftover = nb_pkts & (PKTS_PER_BATCH - 1); + for (i = 0; i < batched; i += PKTS_PER_BATCH) + i40e_xmit_pkt_batch(xdp_ring, &descs[i], total_bytes); + for (i = batched; i < batched + leftover; i++) + i40e_xmit_pkt(xdp_ring, &descs[i], total_bytes); +} - xsk_tx_release(xdp_ring->xsk_pool); - i40e_update_tx_stats(xdp_ring, sent_frames, total_bytes); +static void i40e_set_rs_bit(struct i40e_ring *xdp_ring) +{ + u16 ntu = xdp_ring->next_to_use ? xdp_ring->next_to_use - 1 : xdp_ring->count - 1; + struct i40e_tx_desc *tx_desc; + + tx_desc = I40E_TX_DESC(xdp_ring, ntu); + tx_desc->cmd_type_offset_bsz |= (I40E_TX_DESC_CMD_RS << I40E_TXD_QW1_CMD_SHIFT); +} + +/** + * i40e_xmit_zc - Performs zero-copy Tx AF_XDP + * @xdp_ring: XDP Tx ring + * @budget: NAPI budget + * + * Returns true if the work is finished. + **/ +static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget) +{ + struct xdp_desc *descs = xdp_ring->xsk_descs; + u32 nb_pkts, nb_processed = 0; + unsigned int total_bytes = 0; + + nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, descs, budget); + if (!nb_pkts) + return false; + + if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) { + nb_processed = xdp_ring->count - xdp_ring->next_to_use; + i40e_fill_tx_hw_ring(xdp_ring, descs, nb_processed, &total_bytes); + xdp_ring->next_to_use = 0; } - return !!budget; + i40e_fill_tx_hw_ring(xdp_ring, &descs[nb_processed], nb_pkts - nb_processed, + &total_bytes); + + /* Request an interrupt for the last frame and bump tail ptr. */ + i40e_set_rs_bit(xdp_ring); + i40e_xdp_ring_update_tail(xdp_ring); + + i40e_update_tx_stats(xdp_ring, nb_pkts, total_bytes); + + return true; } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h index 7adfd8539247..ea88f4597a07 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h @@ -4,6 +4,22 @@ #ifndef _I40E_XSK_H_ #define _I40E_XSK_H_ +/* This value should match the pragma in the loop_unrolled_for + * macro. Why 4? It is strictly empirical. It seems to be a good + * compromise between the advantage of having simultaneous outstanding + * reads to the DMA array that can hide each others latency and the + * disadvantage of having a larger code path. + */ +#define PKTS_PER_BATCH 4 + +#ifdef __clang__ +#define loop_unrolled_for _Pragma("clang loop unroll_count(4)") for +#elif __GNUC__ >= 8 +#define loop_unrolled_for _Pragma("GCC unroll 4") for +#else +#define loop_unrolled_for for +#endif + struct i40e_vsi; struct xsk_buff_pool; struct zero_copy_allocator; diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index fe4320e2d1f2..3124a3bf519a 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -306,7 +306,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring) if (!xdp_rxq_info_is_reg(&ring->xdp_rxq)) /* coverity[check_return] */ xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, - ring->q_index); + ring->q_index, ring->q_vector->napi.napi_id); ring->xsk_pool = ice_xsk_pool(ring); if (ring->xsk_pool) { @@ -333,7 +333,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring) /* coverity[check_return] */ xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, - ring->q_index); + ring->q_index, ring->q_vector->napi.napi_id); err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_SHARED, diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index eae75260fe20..77d5eae6b4c2 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -483,7 +483,7 @@ int ice_setup_rx_ring(struct ice_ring *rx_ring) if (rx_ring->vsi->type == ICE_VSI_PF && !xdp_rxq_info_is_reg(&rx_ring->xdp_rxq)) if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, - rx_ring->q_index)) + rx_ring->q_index, rx_ring->q_vector->napi.napi_id)) goto err; return 0; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 5fc2c381da55..6a4ef4934fcf 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -4352,7 +4352,7 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring) /* XDP RX-queue info */ if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, - rx_ring->queue_index) < 0) + rx_ring->queue_index, 0) < 0) goto err; return 0; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 45ae33e15303..50e6b8b6ba7b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -6577,7 +6577,7 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter, /* XDP RX-queue info */ if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, adapter->netdev, - rx_ring->queue_index) < 0) + rx_ring->queue_index, rx_ring->q_vector->napi.napi_id) < 0) goto err; rx_ring->xdp_prog = adapter->xdp_prog; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 82fce27f682b..4061cd7db5dd 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -3493,7 +3493,7 @@ int ixgbevf_setup_rx_resources(struct ixgbevf_adapter *adapter, /* XDP RX-queue info */ if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, adapter->netdev, - rx_ring->queue_index) < 0) + rx_ring->queue_index, 0) < 0) goto err; rx_ring->xdp_prog = adapter->xdp_prog; diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index b40804e421a7..563ceac3060f 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -3243,7 +3243,7 @@ static int mvneta_create_page_pool(struct mvneta_port *pp, return err; } - err = xdp_rxq_info_reg(&rxq->xdp_rxq, pp->dev, rxq->id); + err = xdp_rxq_info_reg(&rxq->xdp_rxq, pp->dev, rxq->id, 0); if (err < 0) goto err_free_pp; diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index adf337de00d1..afdd22827223 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -2614,11 +2614,11 @@ static int mvpp2_rxq_init(struct mvpp2_port *port, mvpp2_rxq_status_update(port, rxq->id, 0, rxq->size); if (priv->percpu_pools) { - err = xdp_rxq_info_reg(&rxq->xdp_rxq_short, port->dev, rxq->id); + err = xdp_rxq_info_reg(&rxq->xdp_rxq_short, port->dev, rxq->id, 0); if (err < 0) goto err_free_dma; - err = xdp_rxq_info_reg(&rxq->xdp_rxq_long, port->dev, rxq->id); + err = xdp_rxq_info_reg(&rxq->xdp_rxq_long, port->dev, rxq->id, 0); if (err < 0) goto err_unregister_rxq_short; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 55fc33de4ce7..7954c1daf2b6 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -283,7 +283,7 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv, ring->log_stride = ffs(ring->stride) - 1; ring->buf_size = ring->size * ring->stride + TXBB_SIZE; - if (xdp_rxq_info_reg(&ring->xdp_rxq, priv->dev, queue_index) < 0) + if (xdp_rxq_info_reg(&ring->xdp_rxq, priv->dev, queue_index, 0) < 0) goto err_ring; tmp = size * roundup_pow_of_two(MLX4_EN_MAX_RX_FRAGS * diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 527c5f12c5af..427fc376fe1a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -434,7 +434,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, 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); + err = xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq_xdp_ix, 0); if (err < 0) goto err_rq_xdp_prog; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index b150da43adb2..b4acf2f41e84 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -2533,7 +2533,7 @@ nfp_net_rx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring) if (dp->netdev) { err = xdp_rxq_info_reg(&rx_ring->xdp_rxq, dp->netdev, - rx_ring->idx); + rx_ring->idx, rx_ring->r_vec->napi.napi_id); if (err < 0) return err; } diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index 05e3a3b60269..9cf960a6d007 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -1762,7 +1762,7 @@ static void qede_init_fp(struct qede_dev *edev) /* Driver have no error path from here */ WARN_ON(xdp_rxq_info_reg(&fp->rxq->xdp_rxq, edev->ndev, - fp->rxq->rxq_id) < 0); + fp->rxq->rxq_id, 0) < 0); if (xdp_rxq_info_reg_mem_model(&fp->rxq->xdp_rxq, MEM_TYPE_PAGE_ORDER0, diff --git a/drivers/net/ethernet/sfc/rx_common.c b/drivers/net/ethernet/sfc/rx_common.c index 19cf7cac1e6e..68fc7d317693 100644 --- a/drivers/net/ethernet/sfc/rx_common.c +++ b/drivers/net/ethernet/sfc/rx_common.c @@ -262,7 +262,7 @@ void efx_init_rx_queue(struct efx_rx_queue *rx_queue) /* Initialise XDP queue information */ rc = xdp_rxq_info_reg(&rx_queue->xdp_rxq_info, efx->net_dev, - rx_queue->core_index); + rx_queue->core_index, 0); if (rc) { netif_err(efx, rx_err, efx->net_dev, diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index 536aa8961dc6..19d20a6d0d44 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -1314,7 +1314,7 @@ static int netsec_setup_rx_dring(struct netsec_priv *priv) goto err_out; } - err = xdp_rxq_info_reg(&dring->xdp_rxq, priv->ndev, 0); + err = xdp_rxq_info_reg(&dring->xdp_rxq, priv->ndev, 0, priv->napi.napi_id); if (err) goto err_out; diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c index 31c5e36ff706..6dd73bd0f458 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.c +++ b/drivers/net/ethernet/ti/cpsw_priv.c @@ -1186,7 +1186,7 @@ static int cpsw_ndev_create_xdp_rxq(struct cpsw_priv *priv, int ch) pool = cpsw->page_pool[ch]; rxq = &priv->xdp_rxq[ch]; - ret = xdp_rxq_info_reg(rxq, priv->ndev, ch); + ret = xdp_rxq_info_reg(rxq, priv->ndev, ch, 0); if (ret) return ret; diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 0c3de94b5178..fa8341f8359a 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -1499,7 +1499,7 @@ struct netvsc_device *netvsc_device_add(struct hv_device *device, u64_stats_init(&nvchan->tx_stats.syncp); u64_stats_init(&nvchan->rx_stats.syncp); - ret = xdp_rxq_info_reg(&nvchan->xdp_rxq, ndev, i); + ret = xdp_rxq_info_reg(&nvchan->xdp_rxq, ndev, i, 0); if (ret) { netdev_err(ndev, "xdp_rxq_info_reg fail: %d\n", ret); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 2dc1988a8973..fbed05ae7b0f 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -780,7 +780,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file, } else { /* Setup XDP RX-queue info, for new tfile getting attached */ err = xdp_rxq_info_reg(&tfile->xdp_rxq, - tun->dev, tfile->queue_index); + tun->dev, tfile->queue_index, 0); if (err < 0) goto out; err = xdp_rxq_info_reg_mem_model(&tfile->xdp_rxq, diff --git a/drivers/net/veth.c b/drivers/net/veth.c index 359d3ab33c4d..02bfcdf50a7a 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -884,7 +884,6 @@ static int veth_napi_add(struct net_device *dev) for (i = 0; i < dev->real_num_rx_queues; i++) { struct veth_rq *rq = &priv->rq[i]; - netif_napi_add(dev, &rq->xdp_napi, veth_poll, NAPI_POLL_WEIGHT); napi_enable(&rq->xdp_napi); } @@ -926,7 +925,8 @@ static int veth_enable_xdp(struct net_device *dev) for (i = 0; i < dev->real_num_rx_queues; i++) { struct veth_rq *rq = &priv->rq[i]; - err = xdp_rxq_info_reg(&rq->xdp_rxq, dev, i); + netif_napi_add(dev, &rq->xdp_napi, veth_poll, NAPI_POLL_WEIGHT); + err = xdp_rxq_info_reg(&rq->xdp_rxq, dev, i, rq->xdp_napi.napi_id); if (err < 0) goto err_rxq_reg; @@ -952,8 +952,12 @@ static int veth_enable_xdp(struct net_device *dev) err_reg_mem: xdp_rxq_info_unreg(&priv->rq[i].xdp_rxq); err_rxq_reg: - for (i--; i >= 0; i--) - xdp_rxq_info_unreg(&priv->rq[i].xdp_rxq); + for (i--; i >= 0; i--) { + struct veth_rq *rq = &priv->rq[i]; + + xdp_rxq_info_unreg(&rq->xdp_rxq); + netif_napi_del(&rq->xdp_napi); + } return err; } diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 21b71148c532..052975ea0af4 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -1485,7 +1485,7 @@ static int virtnet_open(struct net_device *dev) if (!try_fill_recv(vi, &vi->rq[i], GFP_KERNEL)) schedule_delayed_work(&vi->refill, 0); - err = xdp_rxq_info_reg(&vi->rq[i].xdp_rxq, dev, i); + err = xdp_rxq_info_reg(&vi->rq[i].xdp_rxq, dev, i, vi->rq[i].napi.napi_id); if (err < 0) return err; diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 920cac4385bf..b01848ef4649 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -2014,7 +2014,7 @@ static int xennet_create_page_pool(struct netfront_queue *queue) } err = xdp_rxq_info_reg(&queue->xdp_rxq, queue->info->netdev, - queue->id); + queue->id, 0); if (err) { netdev_err(queue->info->netdev, "xdp_rxq_info_reg failed\n"); goto err_free_pp; diff --git a/fs/buffer.c b/fs/buffer.c index 23f645657488..b56f99f82b5b 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -657,7 +657,7 @@ int __set_page_dirty_buffers(struct page *page) } while (bh != head); } /* - * Lock out page->mem_cgroup migration to keep PageDirty + * Lock out page's memcg migration to keep PageDirty * synchronized with per-memcg dirty page counters. */ lock_page_memcg(page); diff --git a/fs/eventpoll.c b/fs/eventpoll.c index 4df61129566d..73c346e503d7 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -397,7 +397,8 @@ static void ep_busy_loop(struct eventpoll *ep, int nonblock) unsigned int napi_id = READ_ONCE(ep->napi_id); if ((napi_id >= MIN_NAPI_ID) && net_busy_loop_on()) - napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep); + napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep, false, + BUSY_POLL_BUDGET); } static inline void ep_reset_busy_poll_napi_id(struct eventpoll *ep) diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index 10cc7979ce38..16a1e82e3aeb 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -650,7 +650,7 @@ iomap_set_page_dirty(struct page *page) return !TestSetPageDirty(page); /* - * Lock out page->mem_cgroup migration to keep PageDirty + * Lock out page's memcg migration to keep PageDirty * synchronized with per-memcg dirty page counters. */ lock_page_memcg(page); diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h index ed71bd1a0825..72e69a0e1e8c 100644 --- a/include/linux/bpf-cgroup.h +++ b/include/linux/bpf-cgroup.h @@ -246,11 +246,11 @@ int bpf_percpu_cgroup_storage_update(struct bpf_map *map, void *key, __ret; \ }) -#define BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET4_BIND) +#define BPF_CGROUP_RUN_PROG_INET4_BIND_LOCK(sk, uaddr) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET4_BIND, NULL) -#define BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr) \ - BPF_CGROUP_RUN_SA_PROG(sk, uaddr, BPF_CGROUP_INET6_BIND) +#define BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr) \ + BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, BPF_CGROUP_INET6_BIND, NULL) #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (cgroup_bpf_enabled && \ sk->sk_prot->pre_connect) @@ -434,8 +434,8 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map, #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr) ({ 0; }) -#define BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET4_BIND_LOCK(sk, uaddr) ({ 0; }) +#define BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) ({ 0; }) #define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) ({ 0; }) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 581b2a2e78eb..d05e75ed8c1b 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -20,6 +20,8 @@ #include <linux/module.h> #include <linux/kallsyms.h> #include <linux/capability.h> +#include <linux/sched/mm.h> +#include <linux/slab.h> struct bpf_verifier_env; struct bpf_verifier_log; @@ -37,6 +39,7 @@ struct bpf_iter_aux_info; struct bpf_local_storage; struct bpf_local_storage_map; struct kobject; +struct mem_cgroup; extern struct idr btf_idr; extern spinlock_t btf_idr_lock; @@ -135,11 +138,6 @@ struct bpf_map_ops { const struct bpf_iter_seq_info *iter_seq_info; }; -struct bpf_map_memory { - u32 pages; - struct user_struct *user; -}; - struct bpf_map { /* The first two cachelines with read-mostly members of which some * are also accessed in fast-path (e.g. ops, max_entries). @@ -160,7 +158,9 @@ struct bpf_map { u32 btf_key_type_id; u32 btf_value_type_id; struct btf *btf; - struct bpf_map_memory memory; +#ifdef CONFIG_MEMCG_KMEM + struct mem_cgroup *memcg; +#endif char name[BPF_OBJ_NAME_LEN]; u32 btf_vmlinux_value_type_id; bool bypass_spec_v1; @@ -421,7 +421,10 @@ struct bpf_insn_access_aux { enum bpf_reg_type reg_type; union { int ctx_field_size; - u32 btf_id; + struct { + struct btf *btf; + u32 btf_id; + }; }; struct bpf_verifier_log *log; /* for verbose logs */ }; @@ -458,6 +461,7 @@ struct bpf_verifier_ops { struct bpf_insn *dst, struct bpf_prog *prog, u32 *target_size); int (*btf_struct_access)(struct bpf_verifier_log *log, + const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id); @@ -771,6 +775,7 @@ struct bpf_prog_aux { u32 ctx_arg_info_size; u32 max_rdonly_access; u32 max_rdwr_access; + struct btf *attach_btf; const struct bpf_ctx_arg_aux *ctx_arg_info; struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */ struct bpf_prog *dst_prog; @@ -1005,7 +1010,6 @@ struct bpf_event_entry { bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp); int bpf_prog_calc_tag(struct bpf_prog *fp); -const char *kernel_type_name(u32 btf_type_id); const struct bpf_func_proto *bpf_get_trace_printk_proto(void); @@ -1202,8 +1206,6 @@ void bpf_prog_sub(struct bpf_prog *prog, int i); void bpf_prog_inc(struct bpf_prog *prog); struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog); void bpf_prog_put(struct bpf_prog *prog); -int __bpf_prog_charge(struct user_struct *user, u32 pages); -void __bpf_prog_uncharge(struct user_struct *user, u32 pages); void __bpf_free_used_maps(struct bpf_prog_aux *aux, struct bpf_map **used_maps, u32 len); @@ -1218,12 +1220,6 @@ void bpf_map_inc_with_uref(struct bpf_map *map); struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map); void bpf_map_put_with_uref(struct bpf_map *map); void bpf_map_put(struct bpf_map *map); -int bpf_map_charge_memlock(struct bpf_map *map, u32 pages); -void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages); -int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size); -void bpf_map_charge_finish(struct bpf_map_memory *mem); -void bpf_map_charge_move(struct bpf_map_memory *dst, - struct bpf_map_memory *src); void *bpf_map_area_alloc(u64 size, int numa_node); void *bpf_map_area_mmapable_alloc(u64 size, int numa_node); void bpf_map_area_free(void *base); @@ -1240,6 +1236,34 @@ int generic_map_delete_batch(struct bpf_map *map, struct bpf_map *bpf_map_get_curr_or_next(u32 *id); struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id); +#ifdef CONFIG_MEMCG_KMEM +void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, + int node); +void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags); +void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, + size_t align, gfp_t flags); +#else +static inline void * +bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, + int node) +{ + return kmalloc_node(size, flags, node); +} + +static inline void * +bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags) +{ + return kzalloc(size, flags); +} + +static inline void __percpu * +bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align, + gfp_t flags) +{ + return __alloc_percpu_gfp(size, align, flags); +} +#endif + extern int sysctl_unprivileged_bpf_disabled; static inline bool bpf_allow_ptr_leaks(void) @@ -1430,12 +1454,13 @@ int bpf_prog_test_run_raw_tp(struct bpf_prog *prog, bool btf_ctx_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info); -int btf_struct_access(struct bpf_verifier_log *log, +int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id); bool btf_struct_ids_match(struct bpf_verifier_log *log, - int off, u32 id, u32 need_type_id); + const struct btf *btf, u32 id, int off, + const struct btf *need_btf, u32 need_type_id); int btf_distill_func_proto(struct bpf_verifier_log *log, struct btf *btf, @@ -1490,15 +1515,6 @@ bpf_prog_inc_not_zero(struct bpf_prog *prog) return ERR_PTR(-EOPNOTSUPP); } -static inline int __bpf_prog_charge(struct user_struct *user, u32 pages) -{ - return 0; -} - -static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages) -{ -} - static inline void bpf_link_init(struct bpf_link *link, enum bpf_link_type type, const struct bpf_link_ops *ops, struct bpf_prog *prog) @@ -1842,6 +1858,7 @@ extern const struct bpf_func_proto bpf_copy_from_user_proto; extern const struct bpf_func_proto bpf_snprintf_btf_proto; extern const struct bpf_func_proto bpf_per_cpu_ptr_proto; extern const struct bpf_func_proto bpf_this_cpu_ptr_proto; +extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto; const struct bpf_func_proto *bpf_tracing_func_proto( enum bpf_func_id func_id, const struct bpf_prog *prog); diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 306869d4743b..e941fe1484e5 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -5,6 +5,7 @@ #define _LINUX_BPF_VERIFIER_H 1 #include <linux/bpf.h> /* for enum bpf_reg_type */ +#include <linux/btf.h> /* for struct btf and btf_id() */ #include <linux/filter.h> /* for MAX_BPF_STACK */ #include <linux/tnum.h> @@ -43,6 +44,8 @@ enum bpf_reg_liveness { struct bpf_reg_state { /* Ordering of fields matters. See states_equal() */ enum bpf_reg_type type; + /* Fixed part of pointer offset, pointer types only */ + s32 off; union { /* valid when type == PTR_TO_PACKET */ int range; @@ -52,15 +55,20 @@ struct bpf_reg_state { */ struct bpf_map *map_ptr; - u32 btf_id; /* for PTR_TO_BTF_ID */ + /* for PTR_TO_BTF_ID */ + struct { + struct btf *btf; + u32 btf_id; + }; u32 mem_size; /* for PTR_TO_MEM | PTR_TO_MEM_OR_NULL */ /* Max size from any of the above. */ - unsigned long raw; + struct { + unsigned long raw1; + unsigned long raw2; + } raw; }; - /* Fixed part of pointer offset, pointer types only */ - s32 off; /* For PTR_TO_PACKET, used to find other pointers with the same variable * offset, so they can share range knowledge. * For PTR_TO_MAP_VALUE_OR_NULL this is used to share which map value we @@ -311,7 +319,10 @@ struct bpf_insn_aux_data { struct { enum bpf_reg_type reg_type; /* type of pseudo_btf_id */ union { - u32 btf_id; /* btf_id for struct typed var */ + struct { + struct btf *btf; + u32 btf_id; /* btf_id for struct typed var */ + }; u32 mem_size; /* mem_size for non-struct typed var */ }; } btf_var; @@ -459,9 +470,12 @@ int check_ctx_reg(struct bpf_verifier_env *env, /* this lives here instead of in bpf.h because it needs to dereference tgt_prog */ static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog, - u32 btf_id) + struct btf *btf, u32 btf_id) { - return tgt_prog ? (((u64)tgt_prog->aux->id) << 32 | btf_id) : btf_id; + if (tgt_prog) + return ((u64)tgt_prog->aux->id << 32) | btf_id; + else + return ((u64)btf_obj_id(btf) << 32) | 0x80000000 | btf_id; } int bpf_check_attach_target(struct bpf_verifier_log *log, diff --git a/include/linux/btf.h b/include/linux/btf.h index 2bf641829664..4c200f5d242b 100644 --- a/include/linux/btf.h +++ b/include/linux/btf.h @@ -18,6 +18,7 @@ struct btf_show; extern const struct file_operations btf_fops; +void btf_get(struct btf *btf); void btf_put(struct btf *btf); int btf_new_fd(const union bpf_attr *attr); struct btf *btf_get_by_fd(int fd); @@ -88,7 +89,8 @@ int btf_type_snprintf_show(const struct btf *btf, u32 type_id, void *obj, char *buf, int len, u64 flags); int btf_get_fd_by_id(u32 id); -u32 btf_id(const struct btf *btf); +u32 btf_obj_id(const struct btf *btf); +bool btf_is_kernel(const struct btf *btf); bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s, const struct btf_member *m, u32 expected_offset, u32 expected_size); @@ -206,6 +208,8 @@ static inline const struct btf_var_secinfo *btf_type_var_secinfo( } #ifdef CONFIG_BPF_SYSCALL +struct bpf_prog; + const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id); const char *btf_name_by_offset(const struct btf *btf, u32 offset); struct btf *btf_parse_vmlinux(void); diff --git a/include/linux/ima.h b/include/linux/ima.h index 8fa7bcfb2da2..7233a2751754 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -29,6 +29,7 @@ extern int ima_post_read_file(struct file *file, void *buf, loff_t size, enum kernel_read_file_id id); extern void ima_post_path_mknod(struct dentry *dentry); extern int ima_file_hash(struct file *file, char *buf, size_t buf_size); +extern int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size); extern void ima_kexec_cmdline(int kernel_fd, const void *buf, int size); #ifdef CONFIG_IMA_KEXEC @@ -115,6 +116,11 @@ static inline int ima_file_hash(struct file *file, char *buf, size_t buf_size) return -EOPNOTSUPP; } +static inline int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size) +{ + return -EOPNOTSUPP; +} + static inline void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) {} #endif /* CONFIG_IMA */ diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 922a7f600465..320369c841f5 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -343,6 +343,175 @@ struct mem_cgroup { extern struct mem_cgroup *root_mem_cgroup; +enum page_memcg_data_flags { + /* page->memcg_data is a pointer to an objcgs vector */ + MEMCG_DATA_OBJCGS = (1UL << 0), + /* page has been accounted as a non-slab kernel page */ + MEMCG_DATA_KMEM = (1UL << 1), + /* the next bit after the last actual flag */ + __NR_MEMCG_DATA_FLAGS = (1UL << 2), +}; + +#define MEMCG_DATA_FLAGS_MASK (__NR_MEMCG_DATA_FLAGS - 1) + +/* + * page_memcg - get the memory cgroup associated with a page + * @page: a pointer to the page struct + * + * Returns a pointer to the memory cgroup associated with the page, + * or NULL. This function assumes that the page is known to have a + * proper memory cgroup pointer. It's not safe to call this function + * against some type of pages, e.g. slab pages or ex-slab pages. + * + * Any of the following ensures page and memcg binding stability: + * - the page lock + * - LRU isolation + * - lock_page_memcg() + * - exclusive reference + */ +static inline struct mem_cgroup *page_memcg(struct page *page) +{ + unsigned long memcg_data = page->memcg_data; + + VM_BUG_ON_PAGE(PageSlab(page), page); + VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_OBJCGS, page); + + return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); +} + +/* + * page_memcg_rcu - locklessly get the memory cgroup associated with a page + * @page: a pointer to the page struct + * + * Returns a pointer to the memory cgroup associated with the page, + * or NULL. This function assumes that the page is known to have a + * proper memory cgroup pointer. It's not safe to call this function + * against some type of pages, e.g. slab pages or ex-slab pages. + */ +static inline struct mem_cgroup *page_memcg_rcu(struct page *page) +{ + VM_BUG_ON_PAGE(PageSlab(page), page); + WARN_ON_ONCE(!rcu_read_lock_held()); + + return (struct mem_cgroup *)(READ_ONCE(page->memcg_data) & + ~MEMCG_DATA_FLAGS_MASK); +} + +/* + * page_memcg_check - get the memory cgroup associated with a page + * @page: a pointer to the page struct + * + * Returns a pointer to the memory cgroup associated with the page, + * or NULL. This function unlike page_memcg() can take any page + * as an argument. It has to be used in cases when it's not known if a page + * has an associated memory cgroup pointer or an object cgroups vector. + * + * Any of the following ensures page and memcg binding stability: + * - the page lock + * - LRU isolation + * - lock_page_memcg() + * - exclusive reference + */ +static inline struct mem_cgroup *page_memcg_check(struct page *page) +{ + /* + * Because page->memcg_data might be changed asynchronously + * for slab pages, READ_ONCE() should be used here. + */ + unsigned long memcg_data = READ_ONCE(page->memcg_data); + + if (memcg_data & MEMCG_DATA_OBJCGS) + return NULL; + + return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); +} + +/* + * PageMemcgKmem - check if the page has MemcgKmem flag set + * @page: a pointer to the page struct + * + * Checks if the page has MemcgKmem flag set. The caller must ensure that + * the page has an associated memory cgroup. It's not safe to call this function + * against some types of pages, e.g. slab pages. + */ +static inline bool PageMemcgKmem(struct page *page) +{ + VM_BUG_ON_PAGE(page->memcg_data & MEMCG_DATA_OBJCGS, page); + return page->memcg_data & MEMCG_DATA_KMEM; +} + +#ifdef CONFIG_MEMCG_KMEM +/* + * page_objcgs - get the object cgroups vector associated with a page + * @page: a pointer to the page struct + * + * Returns a pointer to the object cgroups vector associated with the page, + * or NULL. This function assumes that the page is known to have an + * associated object cgroups vector. It's not safe to call this function + * against pages, which might have an associated memory cgroup: e.g. + * kernel stack pages. + */ +static inline struct obj_cgroup **page_objcgs(struct page *page) +{ + unsigned long memcg_data = READ_ONCE(page->memcg_data); + + VM_BUG_ON_PAGE(memcg_data && !(memcg_data & MEMCG_DATA_OBJCGS), page); + VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page); + + return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); +} + +/* + * page_objcgs_check - get the object cgroups vector associated with a page + * @page: a pointer to the page struct + * + * Returns a pointer to the object cgroups vector associated with the page, + * or NULL. This function is safe to use if the page can be directly associated + * with a memory cgroup. + */ +static inline struct obj_cgroup **page_objcgs_check(struct page *page) +{ + unsigned long memcg_data = READ_ONCE(page->memcg_data); + + if (!memcg_data || !(memcg_data & MEMCG_DATA_OBJCGS)) + return NULL; + + VM_BUG_ON_PAGE(memcg_data & MEMCG_DATA_KMEM, page); + + return (struct obj_cgroup **)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); +} + +/* + * set_page_objcgs - associate a page with a object cgroups vector + * @page: a pointer to the page struct + * @objcgs: a pointer to the object cgroups vector + * + * Atomically associates a page with a vector of object cgroups. + */ +static inline bool set_page_objcgs(struct page *page, + struct obj_cgroup **objcgs) +{ + return !cmpxchg(&page->memcg_data, 0, (unsigned long)objcgs | + MEMCG_DATA_OBJCGS); +} +#else +static inline struct obj_cgroup **page_objcgs(struct page *page) +{ + return NULL; +} + +static inline struct obj_cgroup **page_objcgs_check(struct page *page) +{ + return NULL; +} + +static inline bool set_page_objcgs(struct page *page, + struct obj_cgroup **objcgs) +{ + return true; +} +#endif + static __always_inline bool memcg_stat_item_in_bytes(int idx) { if (idx == MEMCG_PERCPU_B) @@ -743,15 +912,19 @@ static inline void mod_memcg_state(struct mem_cgroup *memcg, static inline void __mod_memcg_page_state(struct page *page, int idx, int val) { - if (page->mem_cgroup) - __mod_memcg_state(page->mem_cgroup, idx, val); + struct mem_cgroup *memcg = page_memcg(page); + + if (memcg) + __mod_memcg_state(memcg, idx, val); } static inline void mod_memcg_page_state(struct page *page, int idx, int val) { - if (page->mem_cgroup) - mod_memcg_state(page->mem_cgroup, idx, val); + struct mem_cgroup *memcg = page_memcg(page); + + if (memcg) + mod_memcg_state(memcg, idx, val); } static inline unsigned long lruvec_page_state(struct lruvec *lruvec, @@ -834,16 +1007,17 @@ static inline void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { struct page *head = compound_head(page); /* rmap on tail pages */ + struct mem_cgroup *memcg = page_memcg(head); pg_data_t *pgdat = page_pgdat(page); struct lruvec *lruvec; /* Untracked pages have no memcg, no lruvec. Update only the node */ - if (!head->mem_cgroup) { + if (!memcg) { __mod_node_page_state(pgdat, idx, val); return; } - lruvec = mem_cgroup_lruvec(head->mem_cgroup, pgdat); + lruvec = mem_cgroup_lruvec(memcg, pgdat); __mod_lruvec_state(lruvec, idx, val); } @@ -878,8 +1052,10 @@ static inline void count_memcg_events(struct mem_cgroup *memcg, static inline void count_memcg_page_event(struct page *page, enum vm_event_item idx) { - if (page->mem_cgroup) - count_memcg_events(page->mem_cgroup, idx, 1); + struct mem_cgroup *memcg = page_memcg(page); + + if (memcg) + count_memcg_events(memcg, idx, 1); } static inline void count_memcg_event_mm(struct mm_struct *mm, @@ -948,6 +1124,27 @@ void mem_cgroup_split_huge_fixup(struct page *head); struct mem_cgroup; +static inline struct mem_cgroup *page_memcg(struct page *page) +{ + return NULL; +} + +static inline struct mem_cgroup *page_memcg_rcu(struct page *page) +{ + WARN_ON_ONCE(!rcu_read_lock_held()); + return NULL; +} + +static inline struct mem_cgroup *page_memcg_check(struct page *page) +{ + return NULL; +} + +static inline bool PageMemcgKmem(struct page *page) +{ + return false; +} + static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return true; @@ -1437,7 +1634,7 @@ static inline void mem_cgroup_track_foreign_dirty(struct page *page, if (mem_cgroup_disabled()) return; - if (unlikely(&page->mem_cgroup->css != wb->memcg_css)) + if (unlikely(&page_memcg(page)->css != wb->memcg_css)) mem_cgroup_track_foreign_dirty_slowpath(page, wb); } diff --git a/include/linux/mm.h b/include/linux/mm.h index db6ae4d3fb4e..6b0c9d2c1d10 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1484,28 +1484,6 @@ static inline void set_page_links(struct page *page, enum zone_type zone, #endif } -#ifdef CONFIG_MEMCG -static inline struct mem_cgroup *page_memcg(struct page *page) -{ - return page->mem_cgroup; -} -static inline struct mem_cgroup *page_memcg_rcu(struct page *page) -{ - WARN_ON_ONCE(!rcu_read_lock_held()); - return READ_ONCE(page->mem_cgroup); -} -#else -static inline struct mem_cgroup *page_memcg(struct page *page) -{ - return NULL; -} -static inline struct mem_cgroup *page_memcg_rcu(struct page *page) -{ - WARN_ON_ONCE(!rcu_read_lock_held()); - return NULL; -} -#endif - /* * Some inline functions in vmstat.h depend on page_zone() */ diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 5a9238f6caad..80f5d755c037 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -199,10 +199,7 @@ struct page { atomic_t _refcount; #ifdef CONFIG_MEMCG - union { - struct mem_cgroup *mem_cgroup; - struct obj_cgroup **obj_cgroups; - }; + unsigned long memcg_data; #endif /* diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7f85c23d52ab..7bf167993c05 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -350,23 +350,25 @@ struct napi_struct { }; enum { - NAPI_STATE_SCHED, /* Poll is scheduled */ - NAPI_STATE_MISSED, /* reschedule a napi */ - NAPI_STATE_DISABLE, /* Disable pending */ - NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ - NAPI_STATE_LISTED, /* NAPI added to system lists */ - NAPI_STATE_NO_BUSY_POLL,/* Do not add in napi_hash, no busy polling */ - NAPI_STATE_IN_BUSY_POLL,/* sk_busy_loop() owns this NAPI */ + NAPI_STATE_SCHED, /* Poll is scheduled */ + NAPI_STATE_MISSED, /* reschedule a napi */ + NAPI_STATE_DISABLE, /* Disable pending */ + NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ + NAPI_STATE_LISTED, /* NAPI added to system lists */ + NAPI_STATE_NO_BUSY_POLL, /* Do not add in napi_hash, no busy polling */ + NAPI_STATE_IN_BUSY_POLL, /* sk_busy_loop() owns this NAPI */ + NAPI_STATE_PREFER_BUSY_POLL, /* prefer busy-polling over softirq processing*/ }; enum { - NAPIF_STATE_SCHED = BIT(NAPI_STATE_SCHED), - NAPIF_STATE_MISSED = BIT(NAPI_STATE_MISSED), - NAPIF_STATE_DISABLE = BIT(NAPI_STATE_DISABLE), - NAPIF_STATE_NPSVC = BIT(NAPI_STATE_NPSVC), - NAPIF_STATE_LISTED = BIT(NAPI_STATE_LISTED), - NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL), - NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL), + NAPIF_STATE_SCHED = BIT(NAPI_STATE_SCHED), + NAPIF_STATE_MISSED = BIT(NAPI_STATE_MISSED), + NAPIF_STATE_DISABLE = BIT(NAPI_STATE_DISABLE), + NAPIF_STATE_NPSVC = BIT(NAPI_STATE_NPSVC), + NAPIF_STATE_LISTED = BIT(NAPI_STATE_LISTED), + NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL), + NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL), + NAPIF_STATE_PREFER_BUSY_POLL = BIT(NAPI_STATE_PREFER_BUSY_POLL), }; enum gro_result { @@ -437,6 +439,11 @@ static inline bool napi_disable_pending(struct napi_struct *n) return test_bit(NAPI_STATE_DISABLE, &n->state); } +static inline bool napi_prefer_busy_poll(struct napi_struct *n) +{ + return test_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state); +} + bool napi_schedule_prep(struct napi_struct *n); /** diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 4f6ba9379112..fc0e1bd48e73 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -715,9 +715,8 @@ PAGEFLAG_FALSE(DoubleMap) #define PAGE_MAPCOUNT_RESERVE -128 #define PG_buddy 0x00000080 #define PG_offline 0x00000100 -#define PG_kmemcg 0x00000200 -#define PG_table 0x00000400 -#define PG_guard 0x00000800 +#define PG_table 0x00000200 +#define PG_guard 0x00000400 #define PageType(page, flag) \ ((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE) @@ -769,12 +768,6 @@ PAGE_TYPE_OPS(Buddy, buddy) PAGE_TYPE_OPS(Offline, offline) /* - * If kmemcg is enabled, the buddy allocator will set PageKmemcg() on - * pages allocated with __GFP_ACCOUNT. It gets cleared on page free. - */ -PAGE_TYPE_OPS(Kmemcg, kmemcg) - -/* * Marks pages in use as page tables. */ PAGE_TYPE_OPS(Table, table) diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index b001fa91c14e..73af4a64a599 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -23,6 +23,8 @@ */ #define MIN_NAPI_ID ((unsigned int)(NR_CPUS + 1)) +#define BUSY_POLL_BUDGET 8 + #ifdef CONFIG_NET_RX_BUSY_POLL struct napi_struct; @@ -43,7 +45,7 @@ bool sk_busy_loop_end(void *p, unsigned long start_time); void napi_busy_loop(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), - void *loop_end_arg); + void *loop_end_arg, bool prefer_busy_poll, u16 budget); #else /* CONFIG_NET_RX_BUSY_POLL */ static inline unsigned long net_busy_loop_on(void) @@ -105,7 +107,9 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock) unsigned int napi_id = READ_ONCE(sk->sk_napi_id); if (napi_id >= MIN_NAPI_ID) - napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk); + napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk, + READ_ONCE(sk->sk_prefer_busy_poll), + READ_ONCE(sk->sk_busy_poll_budget) ?: BUSY_POLL_BUDGET); #endif } @@ -131,13 +135,28 @@ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb) sk_rx_queue_set(sk, skb); } +static inline void __sk_mark_napi_id_once(struct sock *sk, unsigned int napi_id) +{ +#ifdef CONFIG_NET_RX_BUSY_POLL + if (!READ_ONCE(sk->sk_napi_id)) + WRITE_ONCE(sk->sk_napi_id, napi_id); +#endif +} + /* variant used for unconnected sockets */ static inline void sk_mark_napi_id_once(struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_NET_RX_BUSY_POLL - if (!READ_ONCE(sk->sk_napi_id)) - WRITE_ONCE(sk->sk_napi_id, skb->napi_id); + __sk_mark_napi_id_once(sk, skb->napi_id); +#endif +} + +static inline void sk_mark_napi_id_once_xdp(struct sock *sk, + const struct xdp_buff *xdp) +{ +#ifdef CONFIG_NET_RX_BUSY_POLL + __sk_mark_napi_id_once(sk, xdp->rxq->napi_id); #endif } diff --git a/include/net/sock.h b/include/net/sock.h index f59764614e30..ffacdfdd9894 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -301,6 +301,8 @@ struct bpf_local_storage; * @sk_ack_backlog: current listen backlog * @sk_max_ack_backlog: listen backlog set in listen() * @sk_uid: user id of owner + * @sk_prefer_busy_poll: prefer busypolling over softirq processing + * @sk_busy_poll_budget: napi processing budget when busypolling * @sk_priority: %SO_PRIORITY setting * @sk_type: socket type (%SOCK_STREAM, etc) * @sk_protocol: which protocol this socket belongs in this network family @@ -479,6 +481,10 @@ struct sock { u32 sk_ack_backlog; u32 sk_max_ack_backlog; kuid_t sk_uid; +#ifdef CONFIG_NET_RX_BUSY_POLL + u8 sk_prefer_busy_poll; + u16 sk_busy_poll_budget; +#endif struct pid *sk_peer_pid; const struct cred *sk_peer_cred; long sk_rcvtimeo; diff --git a/include/net/tcp.h b/include/net/tcp.h index 4525d6256321..a62fb7f8a1e3 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -410,6 +410,7 @@ void tcp_syn_ack_timeout(const struct request_sock *req); int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); int tcp_set_rcvlowat(struct sock *sk, int val); +int tcp_set_window_clamp(struct sock *sk, int val); void tcp_data_ready(struct sock *sk); #ifdef CONFIG_MMU int tcp_mmap(struct file *file, struct socket *sock, diff --git a/include/net/xdp.h b/include/net/xdp.h index 7d48b2ae217a..700ad5db7f5d 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -59,6 +59,7 @@ struct xdp_rxq_info { u32 queue_index; u32 reg_state; struct xdp_mem_info mem; + unsigned int napi_id; } ____cacheline_aligned; /* perf critical, avoid false-sharing */ struct xdp_txq_info { @@ -226,7 +227,7 @@ static inline void xdp_release_frame(struct xdp_frame *xdpf) } int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, - struct net_device *dev, u32 queue_index); + struct net_device *dev, u32 queue_index, unsigned int napi_id); void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq); void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq); diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h index 5b1ee8a9976d..4e295541e396 100644 --- a/include/net/xdp_sock_drv.h +++ b/include/net/xdp_sock_drv.h @@ -13,6 +13,7 @@ void xsk_tx_completed(struct xsk_buff_pool *pool, u32 nb_entries); bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, struct xdp_desc *desc); +u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, struct xdp_desc *desc, u32 max); void xsk_tx_release(struct xsk_buff_pool *pool); struct xsk_buff_pool *xsk_get_pool_from_qid(struct net_device *dev, u16 queue_id); @@ -128,6 +129,12 @@ static inline bool xsk_tx_peek_desc(struct xsk_buff_pool *pool, return false; } +static inline u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, struct xdp_desc *desc, + u32 max) +{ + return 0; +} + static inline void xsk_tx_release(struct xsk_buff_pool *pool) { } diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index 57d795365987..1efa463c4979 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -257,7 +257,7 @@ TRACE_EVENT(track_foreign_dirty, __entry->ino = inode ? inode->i_ino : 0; __entry->memcg_id = wb->memcg_css->id; __entry->cgroup_ino = __trace_wb_assign_cgroup(wb); - __entry->page_cgroup_ino = cgroup_ino(page->mem_cgroup->css.cgroup); + __entry->page_cgroup_ino = cgroup_ino(page_memcg(page)->css.cgroup); ), TP_printk("bdi %s[%llu]: ino=%lu memcg_id=%u cgroup_ino=%lu page_cgroup_ino=%lu", diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 77f7c1638eb1..4dcd13d097a9 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -119,6 +119,9 @@ #define SO_DETACH_REUSEPORT_BPF 68 +#define SO_PREFER_BUSY_POLL 69 +#define SO_BUSY_POLL_BUDGET 70 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index 162999b12790..1233f14f659f 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -557,7 +557,12 @@ union bpf_attr { __aligned_u64 line_info; /* line info */ __u32 line_info_cnt; /* number of bpf_line_info records */ __u32 attach_btf_id; /* in-kernel BTF type id to attach to */ - __u32 attach_prog_fd; /* 0 to attach to vmlinux */ + union { + /* valid prog_fd to attach to bpf prog */ + __u32 attach_prog_fd; + /* or valid module BTF object fd or 0 to attach to vmlinux */ + __u32 attach_btf_obj_fd; + }; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -3787,6 +3792,36 @@ union bpf_attr { * *ARG_PTR_TO_BTF_ID* of type *task_struct*. * Return * Pointer to the current task. + * + * long bpf_bprm_opts_set(struct linux_binprm *bprm, u64 flags) + * Description + * Set or clear certain options on *bprm*: + * + * **BPF_F_BPRM_SECUREEXEC** Set the secureexec bit + * which sets the **AT_SECURE** auxv for glibc. The bit + * is cleared if the flag is not specified. + * Return + * **-EINVAL** if invalid *flags* are passed, zero otherwise. + * + * u64 bpf_ktime_get_coarse_ns(void) + * Description + * Return a coarse-grained version of the time elapsed since + * system boot, in nanoseconds. Does not include time the system + * was suspended. + * + * See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**) + * Return + * Current *ktime*. + * + * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size) + * Description + * Returns the stored IMA hash of the *inode* (if it's avaialable). + * If the hash is larger than *size*, then only *size* + * bytes will be copied to *dst* + * Return + * The **hash_algo** is returned on success, + * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if + * invalid arguments are passed. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3948,6 +3983,9 @@ union bpf_attr { FN(task_storage_get), \ FN(task_storage_delete), \ FN(get_current_task_btf), \ + FN(bprm_opts_set), \ + FN(ktime_get_coarse_ns), \ + FN(ima_inode_hash), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -4119,6 +4157,11 @@ enum bpf_lwt_encap_mode { BPF_LWT_ENCAP_IP, }; +/* Flags for bpf_bprm_opts_set helper */ +enum { + BPF_F_BPRM_SECUREEXEC = (1ULL << 0), +}; + #define __bpf_md_ptr(type, name) \ union { \ type name; \ diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index c6c81eceb68f..1f8453343bf2 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -34,8 +34,8 @@ static int bpf_array_alloc_percpu(struct bpf_array *array) int i; for (i = 0; i < array->map.max_entries; i++) { - ptr = __alloc_percpu_gfp(array->elem_size, 8, - GFP_USER | __GFP_NOWARN); + ptr = bpf_map_alloc_percpu(&array->map, array->elem_size, 8, + GFP_USER | __GFP_NOWARN); if (!ptr) { bpf_array_free_percpu(array); return -ENOMEM; @@ -81,11 +81,10 @@ int array_map_alloc_check(union bpf_attr *attr) static struct bpf_map *array_map_alloc(union bpf_attr *attr) { bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY; - int ret, numa_node = bpf_map_attr_numa_node(attr); + int numa_node = bpf_map_attr_numa_node(attr); u32 elem_size, index_mask, max_entries; bool bypass_spec_v1 = bpf_bypass_spec_v1(); - u64 cost, array_size, mask64; - struct bpf_map_memory mem; + u64 array_size, mask64; struct bpf_array *array; elem_size = round_up(attr->value_size, 8); @@ -126,44 +125,29 @@ static struct bpf_map *array_map_alloc(union bpf_attr *attr) } } - /* make sure there is no u32 overflow later in round_up() */ - cost = array_size; - if (percpu) - cost += (u64)attr->max_entries * elem_size * num_possible_cpus(); - - ret = bpf_map_charge_init(&mem, cost); - if (ret < 0) - return ERR_PTR(ret); - /* allocate all map elements and zero-initialize them */ if (attr->map_flags & BPF_F_MMAPABLE) { void *data; /* kmalloc'ed memory can't be mmap'ed, use explicit vmalloc */ data = bpf_map_area_mmapable_alloc(array_size, numa_node); - if (!data) { - bpf_map_charge_finish(&mem); + if (!data) return ERR_PTR(-ENOMEM); - } array = data + PAGE_ALIGN(sizeof(struct bpf_array)) - offsetof(struct bpf_array, value); } else { array = bpf_map_area_alloc(array_size, numa_node); } - if (!array) { - bpf_map_charge_finish(&mem); + if (!array) return ERR_PTR(-ENOMEM); - } array->index_mask = index_mask; array->map.bypass_spec_v1 = bypass_spec_v1; /* copy mandatory map attributes */ bpf_map_init_from_attr(&array->map, attr); - bpf_map_charge_move(&array->map.memory, &mem); array->elem_size = elem_size; if (percpu && bpf_array_alloc_percpu(array)) { - bpf_map_charge_finish(&array->map.memory); bpf_map_area_free(array); return ERR_PTR(-ENOMEM); } @@ -1018,7 +1002,7 @@ static struct bpf_map *prog_array_map_alloc(union bpf_attr *attr) struct bpf_array_aux *aux; struct bpf_map *map; - aux = kzalloc(sizeof(*aux), GFP_KERNEL); + aux = kzalloc(sizeof(*aux), GFP_KERNEL_ACCOUNT); if (!aux) return ERR_PTR(-ENOMEM); diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c index 5d3a7af9ba9b..dd5aedee99e7 100644 --- a/kernel/bpf/bpf_local_storage.c +++ b/kernel/bpf/bpf_local_storage.c @@ -67,7 +67,8 @@ bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, if (charge_mem && mem_charge(smap, owner, smap->elem_size)) return NULL; - selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN); + selem = bpf_map_kzalloc(&smap->map, smap->elem_size, + GFP_ATOMIC | __GFP_NOWARN); if (selem) { if (value) memcpy(SDATA(selem)->data, value, smap->map.value_size); @@ -264,7 +265,8 @@ int bpf_local_storage_alloc(void *owner, if (err) return err; - storage = kzalloc(sizeof(*storage), GFP_ATOMIC | __GFP_NOWARN); + storage = bpf_map_kzalloc(&smap->map, sizeof(*storage), + GFP_ATOMIC | __GFP_NOWARN); if (!storage) { err = -ENOMEM; goto uncharge; @@ -543,10 +545,8 @@ struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr) struct bpf_local_storage_map *smap; unsigned int i; u32 nbuckets; - u64 cost; - int ret; - smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN); + smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN | __GFP_ACCOUNT); if (!smap) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&smap->map, attr); @@ -555,18 +555,10 @@ struct bpf_local_storage_map *bpf_local_storage_map_alloc(union bpf_attr *attr) /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */ nbuckets = max_t(u32, 2, nbuckets); smap->bucket_log = ilog2(nbuckets); - cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap); - - ret = bpf_map_charge_init(&smap->map.memory, cost); - if (ret < 0) { - kfree(smap); - return ERR_PTR(ret); - } smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets, - GFP_USER | __GFP_NOWARN); + GFP_USER | __GFP_NOWARN | __GFP_ACCOUNT); if (!smap->buckets) { - bpf_map_charge_finish(&smap->map.memory); kfree(smap); return ERR_PTR(-ENOMEM); } diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c index 553107f4706a..70e5e0b6d69d 100644 --- a/kernel/bpf/bpf_lsm.c +++ b/kernel/bpf/bpf_lsm.c @@ -7,6 +7,7 @@ #include <linux/filter.h> #include <linux/bpf.h> #include <linux/btf.h> +#include <linux/binfmts.h> #include <linux/lsm_hooks.h> #include <linux/bpf_lsm.h> #include <linux/kallsyms.h> @@ -14,6 +15,7 @@ #include <net/bpf_sk_storage.h> #include <linux/bpf_local_storage.h> #include <linux/btf_ids.h> +#include <linux/ima.h> /* For every LSM hook that allows attachment of BPF programs, declare a nop * function where a BPF program can be attached. @@ -51,6 +53,52 @@ int bpf_lsm_verify_prog(struct bpf_verifier_log *vlog, return 0; } +/* Mask for all the currently supported BPRM option flags */ +#define BPF_F_BRPM_OPTS_MASK BPF_F_BPRM_SECUREEXEC + +BPF_CALL_2(bpf_bprm_opts_set, struct linux_binprm *, bprm, u64, flags) +{ + if (flags & ~BPF_F_BRPM_OPTS_MASK) + return -EINVAL; + + bprm->secureexec = (flags & BPF_F_BPRM_SECUREEXEC); + return 0; +} + +BTF_ID_LIST_SINGLE(bpf_bprm_opts_set_btf_ids, struct, linux_binprm) + +const static struct bpf_func_proto bpf_bprm_opts_set_proto = { + .func = bpf_bprm_opts_set, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_bprm_opts_set_btf_ids[0], + .arg2_type = ARG_ANYTHING, +}; + +BPF_CALL_3(bpf_ima_inode_hash, struct inode *, inode, void *, dst, u32, size) +{ + return ima_inode_hash(inode, dst, size); +} + +static bool bpf_ima_inode_hash_allowed(const struct bpf_prog *prog) +{ + return bpf_lsm_is_sleepable_hook(prog->aux->attach_btf_id); +} + +BTF_ID_LIST_SINGLE(bpf_ima_inode_hash_btf_ids, struct, inode) + +const static struct bpf_func_proto bpf_ima_inode_hash_proto = { + .func = bpf_ima_inode_hash, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_ima_inode_hash_btf_ids[0], + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE, + .allowed = bpf_ima_inode_hash_allowed, +}; + static const struct bpf_func_proto * bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -71,6 +119,10 @@ bpf_lsm_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_task_storage_get_proto; case BPF_FUNC_task_storage_delete: return &bpf_task_storage_delete_proto; + case BPF_FUNC_bprm_opts_set: + return &bpf_bprm_opts_set_proto; + case BPF_FUNC_ima_inode_hash: + return prog->aux->sleepable ? &bpf_ima_inode_hash_proto : NULL; default: return tracing_prog_func_proto(func_id, prog); } diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c index 4c3b543bb33b..1a666a975416 100644 --- a/kernel/bpf/bpf_struct_ops.c +++ b/kernel/bpf/bpf_struct_ops.c @@ -548,12 +548,10 @@ static int bpf_struct_ops_map_alloc_check(union bpf_attr *attr) static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) { const struct bpf_struct_ops *st_ops; - size_t map_total_size, st_map_size; + size_t st_map_size; struct bpf_struct_ops_map *st_map; const struct btf_type *t, *vt; - struct bpf_map_memory mem; struct bpf_map *map; - int err; if (!bpf_capable()) return ERR_PTR(-EPERM); @@ -573,20 +571,11 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) * struct bpf_struct_ops_tcp_congestions_ops */ (vt->size - sizeof(struct bpf_struct_ops_value)); - map_total_size = st_map_size + - /* uvalue */ - sizeof(vt->size) + - /* struct bpf_progs **progs */ - btf_type_vlen(t) * sizeof(struct bpf_prog *); - err = bpf_map_charge_init(&mem, map_total_size); - if (err < 0) - return ERR_PTR(err); st_map = bpf_map_area_alloc(st_map_size, NUMA_NO_NODE); - if (!st_map) { - bpf_map_charge_finish(&mem); + if (!st_map) return ERR_PTR(-ENOMEM); - } + st_map->st_ops = st_ops; map = &st_map->map; @@ -597,14 +586,12 @@ static struct bpf_map *bpf_struct_ops_map_alloc(union bpf_attr *attr) st_map->image = bpf_jit_alloc_exec(PAGE_SIZE); if (!st_map->uvalue || !st_map->progs || !st_map->image) { bpf_struct_ops_map_free(map); - bpf_map_charge_finish(&mem); return ERR_PTR(-ENOMEM); } mutex_init(&st_map->lock); set_vm_flush_reset_perms(st_map->image); bpf_map_init_from_attr(map, attr); - bpf_map_charge_move(&map->memory, &mem); return map; } diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c index 6b2d508b33d4..8d6bdb4f4d61 100644 --- a/kernel/bpf/btf.c +++ b/kernel/bpf/btf.c @@ -1524,6 +1524,11 @@ static void btf_free_rcu(struct rcu_head *rcu) btf_free(btf); } +void btf_get(struct btf *btf) +{ + refcount_inc(&btf->refcnt); +} + void btf_put(struct btf *btf) { if (btf && refcount_dec_and_test(&btf->refcnt)) { @@ -4555,11 +4560,10 @@ struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog) { struct bpf_prog *tgt_prog = prog->aux->dst_prog; - if (tgt_prog) { + if (tgt_prog) return tgt_prog->aux->btf; - } else { - return btf_vmlinux; - } + else + return prog->aux->attach_btf; } static bool is_string_ptr(struct btf *btf, const struct btf_type *t) @@ -4700,6 +4704,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, if (ctx_arg_info->offset == off) { info->reg_type = ctx_arg_info->reg_type; + info->btf = btf_vmlinux; info->btf_id = ctx_arg_info->btf_id; return true; } @@ -4716,6 +4721,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, ret = btf_translate_to_vmlinux(log, btf, t, tgt_type, arg); if (ret > 0) { + info->btf = btf_vmlinux; info->btf_id = ret; return true; } else { @@ -4723,6 +4729,7 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type, } } + info->btf = btf; info->btf_id = t->type; t = btf_type_by_id(btf, t->type); /* skip modifiers */ @@ -4749,7 +4756,7 @@ enum bpf_struct_walk_result { WALK_STRUCT, }; -static int btf_struct_walk(struct bpf_verifier_log *log, +static int btf_struct_walk(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, u32 *next_btf_id) { @@ -4760,7 +4767,7 @@ static int btf_struct_walk(struct bpf_verifier_log *log, u32 vlen, elem_id, mid; again: - tname = __btf_name_by_offset(btf_vmlinux, t->name_off); + tname = __btf_name_by_offset(btf, t->name_off); if (!btf_type_is_struct(t)) { bpf_log(log, "Type '%s' is not a struct\n", tname); return -EINVAL; @@ -4777,7 +4784,7 @@ again: goto error; member = btf_type_member(t) + vlen - 1; - mtype = btf_type_skip_modifiers(btf_vmlinux, member->type, + mtype = btf_type_skip_modifiers(btf, member->type, NULL); if (!btf_type_is_array(mtype)) goto error; @@ -4793,7 +4800,7 @@ again: /* Only allow structure for now, can be relaxed for * other types later. */ - t = btf_type_skip_modifiers(btf_vmlinux, array_elem->type, + t = btf_type_skip_modifiers(btf, array_elem->type, NULL); if (!btf_type_is_struct(t)) goto error; @@ -4851,10 +4858,10 @@ error: /* type of the field */ mid = member->type; - mtype = btf_type_by_id(btf_vmlinux, member->type); - mname = __btf_name_by_offset(btf_vmlinux, member->name_off); + mtype = btf_type_by_id(btf, member->type); + mname = __btf_name_by_offset(btf, member->name_off); - mtype = __btf_resolve_size(btf_vmlinux, mtype, &msize, + mtype = __btf_resolve_size(btf, mtype, &msize, &elem_type, &elem_id, &total_nelems, &mid); if (IS_ERR(mtype)) { @@ -4949,7 +4956,7 @@ error: mname, moff, tname, off, size); return -EACCES; } - stype = btf_type_skip_modifiers(btf_vmlinux, mtype->type, &id); + stype = btf_type_skip_modifiers(btf, mtype->type, &id); if (btf_type_is_struct(stype)) { *next_btf_id = id; return WALK_PTR; @@ -4975,7 +4982,7 @@ error: return -EINVAL; } -int btf_struct_access(struct bpf_verifier_log *log, +int btf_struct_access(struct bpf_verifier_log *log, const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype __maybe_unused, u32 *next_btf_id) @@ -4984,7 +4991,7 @@ int btf_struct_access(struct bpf_verifier_log *log, u32 id; do { - err = btf_struct_walk(log, t, off, size, &id); + err = btf_struct_walk(log, btf, t, off, size, &id); switch (err) { case WALK_PTR: @@ -5000,7 +5007,7 @@ int btf_struct_access(struct bpf_verifier_log *log, * by diving in it. At this point the offset is * aligned with the new type, so set it to 0. */ - t = btf_type_by_id(btf_vmlinux, id); + t = btf_type_by_id(btf, id); off = 0; break; default: @@ -5016,21 +5023,37 @@ int btf_struct_access(struct bpf_verifier_log *log, return -EINVAL; } +/* Check that two BTF types, each specified as an BTF object + id, are exactly + * the same. Trivial ID check is not enough due to module BTFs, because we can + * end up with two different module BTFs, but IDs point to the common type in + * vmlinux BTF. + */ +static bool btf_types_are_same(const struct btf *btf1, u32 id1, + const struct btf *btf2, u32 id2) +{ + if (id1 != id2) + return false; + if (btf1 == btf2) + return true; + return btf_type_by_id(btf1, id1) == btf_type_by_id(btf2, id2); +} + bool btf_struct_ids_match(struct bpf_verifier_log *log, - int off, u32 id, u32 need_type_id) + const struct btf *btf, u32 id, int off, + const struct btf *need_btf, u32 need_type_id) { const struct btf_type *type; int err; /* Are we already done? */ - if (need_type_id == id && off == 0) + if (off == 0 && btf_types_are_same(btf, id, need_btf, need_type_id)) return true; again: - type = btf_type_by_id(btf_vmlinux, id); + type = btf_type_by_id(btf, id); if (!type) return false; - err = btf_struct_walk(log, type, off, 1, &id); + err = btf_struct_walk(log, btf, type, off, 1, &id); if (err != WALK_STRUCT) return false; @@ -5039,7 +5062,7 @@ again: * continue the search with offset 0 in the new * type. */ - if (need_type_id != id) { + if (!btf_types_are_same(btf, id, need_btf, need_type_id)) { off = 0; goto again; } @@ -5710,11 +5733,16 @@ int btf_get_fd_by_id(u32 id) return fd; } -u32 btf_id(const struct btf *btf) +u32 btf_obj_id(const struct btf *btf) { return btf->id; } +bool btf_is_kernel(const struct btf *btf) +{ + return btf->kernel_btf; +} + static int btf_id_cmp_func(const void *a, const void *b) { const int *pa = a, *pb = b; diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 55454d2278b1..261f8692d0d2 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -77,7 +77,7 @@ void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, uns struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags) { - gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags; + gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags; struct bpf_prog_aux *aux; struct bpf_prog *fp; @@ -86,7 +86,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag if (fp == NULL) return NULL; - aux = kzalloc(sizeof(*aux), GFP_KERNEL | gfp_extra_flags); + aux = kzalloc(sizeof(*aux), GFP_KERNEL_ACCOUNT | gfp_extra_flags); if (aux == NULL) { vfree(fp); return NULL; @@ -106,7 +106,7 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags) { - gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags; + gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *prog; int cpu; @@ -138,7 +138,7 @@ int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog) prog->aux->jited_linfo = kcalloc(prog->aux->nr_linfo, sizeof(*prog->aux->jited_linfo), - GFP_KERNEL | __GFP_NOWARN); + GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!prog->aux->jited_linfo) return -ENOMEM; @@ -219,25 +219,17 @@ void bpf_prog_free_linfo(struct bpf_prog *prog) struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags) { - gfp_t gfp_flags = GFP_KERNEL | __GFP_ZERO | gfp_extra_flags; + gfp_t gfp_flags = GFP_KERNEL_ACCOUNT | __GFP_ZERO | gfp_extra_flags; struct bpf_prog *fp; - u32 pages, delta; - int ret; + u32 pages; size = round_up(size, PAGE_SIZE); pages = size / PAGE_SIZE; if (pages <= fp_old->pages) return fp_old; - delta = pages - fp_old->pages; - ret = __bpf_prog_charge(fp_old->aux->user, delta); - if (ret) - return NULL; - fp = __vmalloc(size, gfp_flags); - if (fp == NULL) { - __bpf_prog_uncharge(fp_old->aux->user, delta); - } else { + if (fp) { memcpy(fp, fp_old, fp_old->pages * PAGE_SIZE); fp->pages = pages; fp->aux->prog = fp; @@ -2211,6 +2203,7 @@ const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; const struct bpf_func_proto bpf_get_numa_node_id_proto __weak; const struct bpf_func_proto bpf_ktime_get_ns_proto __weak; const struct bpf_func_proto bpf_ktime_get_boot_ns_proto __weak; +const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto __weak; const struct bpf_func_proto bpf_get_current_pid_tgid_proto __weak; const struct bpf_func_proto bpf_get_current_uid_gid_proto __weak; diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index c61a23b564aa..747313698178 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -84,8 +84,6 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) u32 value_size = attr->value_size; struct bpf_cpu_map *cmap; int err = -ENOMEM; - u64 cost; - int ret; if (!bpf_capable()) return ERR_PTR(-EPERM); @@ -97,7 +95,7 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) attr->map_flags & ~BPF_F_NUMA_NODE) return ERR_PTR(-EINVAL); - cmap = kzalloc(sizeof(*cmap), GFP_USER); + cmap = kzalloc(sizeof(*cmap), GFP_USER | __GFP_ACCOUNT); if (!cmap) return ERR_PTR(-ENOMEM); @@ -109,26 +107,14 @@ static struct bpf_map *cpu_map_alloc(union bpf_attr *attr) goto free_cmap; } - /* make sure page count doesn't overflow */ - cost = (u64) cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *); - - /* Notice returns -EPERM on if map size is larger than memlock limit */ - ret = bpf_map_charge_init(&cmap->map.memory, cost); - if (ret) { - err = ret; - goto free_cmap; - } - /* Alloc array for possible remote "destination" CPUs */ cmap->cpu_map = bpf_map_area_alloc(cmap->map.max_entries * sizeof(struct bpf_cpu_map_entry *), cmap->map.numa_node); if (!cmap->cpu_map) - goto free_charge; + goto free_cmap; return &cmap->map; -free_charge: - bpf_map_charge_finish(&cmap->map.memory); free_cmap: kfree(cmap); return ERR_PTR(err); @@ -412,7 +398,8 @@ static int __cpu_map_load_bpf_program(struct bpf_cpu_map_entry *rcpu, int fd) } static struct bpf_cpu_map_entry * -__cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id) +__cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value, + u32 cpu) { int numa, err, i, fd = value->bpf_prog.fd; gfp_t gfp = GFP_KERNEL | __GFP_NOWARN; @@ -422,13 +409,13 @@ __cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id) /* Have map->numa_node, but choose node of redirect target CPU */ numa = cpu_to_node(cpu); - rcpu = kzalloc_node(sizeof(*rcpu), gfp, numa); + rcpu = bpf_map_kmalloc_node(map, sizeof(*rcpu), gfp | __GFP_ZERO, numa); if (!rcpu) return NULL; /* Alloc percpu bulkq */ - rcpu->bulkq = __alloc_percpu_gfp(sizeof(*rcpu->bulkq), - sizeof(void *), gfp); + rcpu->bulkq = bpf_map_alloc_percpu(map, sizeof(*rcpu->bulkq), + sizeof(void *), gfp); if (!rcpu->bulkq) goto free_rcu; @@ -438,7 +425,8 @@ __cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id) } /* Alloc queue */ - rcpu->queue = kzalloc_node(sizeof(*rcpu->queue), gfp, numa); + rcpu->queue = bpf_map_kmalloc_node(map, sizeof(*rcpu->queue), gfp, + numa); if (!rcpu->queue) goto free_bulkq; @@ -447,7 +435,7 @@ __cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id) goto free_queue; rcpu->cpu = cpu; - rcpu->map_id = map_id; + rcpu->map_id = map->id; rcpu->value.qsize = value->qsize; if (fd > 0 && __cpu_map_load_bpf_program(rcpu, fd)) @@ -455,7 +443,8 @@ __cpu_map_entry_alloc(struct bpf_cpumap_val *value, u32 cpu, int map_id) /* Setup kthread */ rcpu->kthread = kthread_create_on_node(cpu_map_kthread_run, rcpu, numa, - "cpumap/%d/map:%d", cpu, map_id); + "cpumap/%d/map:%d", cpu, + map->id); if (IS_ERR(rcpu->kthread)) goto free_prog; @@ -571,7 +560,7 @@ static int cpu_map_update_elem(struct bpf_map *map, void *key, void *value, rcpu = NULL; /* Same as deleting */ } else { /* Updating qsize cause re-allocation of bpf_cpu_map_entry */ - rcpu = __cpu_map_entry_alloc(&cpumap_value, key_cpu, map->id); + rcpu = __cpu_map_entry_alloc(map, &cpumap_value, key_cpu); if (!rcpu) return -ENOMEM; rcpu->cmap = cmap; diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 2b5ca93c17de..f6e9c68afdd4 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -109,8 +109,6 @@ static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab, static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) { u32 valsize = attr->value_size; - u64 cost = 0; - int err; /* check sanity of attributes. 2 value sizes supported: * 4 bytes: ifindex @@ -135,21 +133,13 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) if (!dtab->n_buckets) /* Overflow check */ return -EINVAL; - cost += (u64) sizeof(struct hlist_head) * dtab->n_buckets; - } else { - cost += (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *); } - /* if map size is larger than memlock limit, reject it */ - err = bpf_map_charge_init(&dtab->map.memory, cost); - if (err) - return -EINVAL; - if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets, dtab->map.numa_node); if (!dtab->dev_index_head) - goto free_charge; + return -ENOMEM; spin_lock_init(&dtab->index_lock); } else { @@ -157,14 +147,10 @@ static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) sizeof(struct bpf_dtab_netdev *), dtab->map.numa_node); if (!dtab->netdev_map) - goto free_charge; + return -ENOMEM; } return 0; - -free_charge: - bpf_map_charge_finish(&dtab->map.memory); - return -ENOMEM; } static struct bpf_map *dev_map_alloc(union bpf_attr *attr) @@ -175,7 +161,7 @@ static struct bpf_map *dev_map_alloc(union bpf_attr *attr) if (!capable(CAP_NET_ADMIN)) return ERR_PTR(-EPERM); - dtab = kzalloc(sizeof(*dtab), GFP_USER); + dtab = kzalloc(sizeof(*dtab), GFP_USER | __GFP_ACCOUNT); if (!dtab) return ERR_PTR(-ENOMEM); @@ -602,8 +588,9 @@ static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, struct bpf_prog *prog = NULL; struct bpf_dtab_netdev *dev; - dev = kmalloc_node(sizeof(*dev), GFP_ATOMIC | __GFP_NOWARN, - dtab->map.numa_node); + dev = bpf_map_kmalloc_node(&dtab->map, sizeof(*dev), + GFP_ATOMIC | __GFP_NOWARN, + dtab->map.numa_node); if (!dev) return ERR_PTR(-ENOMEM); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index ec46266aaf1c..fe7a0733a63a 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -292,7 +292,8 @@ static int prealloc_init(struct bpf_htab *htab) u32 size = round_up(htab->map.value_size, 8); void __percpu *pptr; - pptr = __alloc_percpu_gfp(size, 8, GFP_USER | __GFP_NOWARN); + pptr = bpf_map_alloc_percpu(&htab->map, size, 8, + GFP_USER | __GFP_NOWARN); if (!pptr) goto free_elems; htab_elem_set_ptr(get_htab_elem(htab, i), htab->map.key_size, @@ -346,8 +347,8 @@ static int alloc_extra_elems(struct bpf_htab *htab) struct pcpu_freelist_node *l; int cpu; - pptr = __alloc_percpu_gfp(sizeof(struct htab_elem *), 8, - GFP_USER | __GFP_NOWARN); + pptr = bpf_map_alloc_percpu(&htab->map, sizeof(struct htab_elem *), 8, + GFP_USER | __GFP_NOWARN); if (!pptr) return -ENOMEM; @@ -442,9 +443,8 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC); struct bpf_htab *htab; int err, i; - u64 cost; - htab = kzalloc(sizeof(*htab), GFP_USER); + htab = kzalloc(sizeof(*htab), GFP_USER | __GFP_ACCOUNT); if (!htab) return ERR_PTR(-ENOMEM); @@ -480,30 +480,18 @@ static struct bpf_map *htab_map_alloc(union bpf_attr *attr) htab->n_buckets > U32_MAX / sizeof(struct bucket)) goto free_htab; - cost = (u64) htab->n_buckets * sizeof(struct bucket) + - (u64) htab->elem_size * htab->map.max_entries; - - if (percpu) - cost += (u64) round_up(htab->map.value_size, 8) * - num_possible_cpus() * htab->map.max_entries; - else - cost += (u64) htab->elem_size * num_possible_cpus(); - - /* if map size is larger than memlock limit, reject it */ - err = bpf_map_charge_init(&htab->map.memory, cost); - if (err) - goto free_htab; - err = -ENOMEM; htab->buckets = bpf_map_area_alloc(htab->n_buckets * sizeof(struct bucket), htab->map.numa_node); if (!htab->buckets) - goto free_charge; + goto free_htab; for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++) { - htab->map_locked[i] = __alloc_percpu_gfp(sizeof(int), - sizeof(int), GFP_USER); + htab->map_locked[i] = bpf_map_alloc_percpu(&htab->map, + sizeof(int), + sizeof(int), + GFP_USER); if (!htab->map_locked[i]) goto free_map_locked; } @@ -538,8 +526,6 @@ free_map_locked: for (i = 0; i < HASHTAB_MAP_LOCK_COUNT; i++) free_percpu(htab->map_locked[i]); bpf_map_area_free(htab->buckets); -free_charge: - bpf_map_charge_finish(&htab->map.memory); free_htab: lockdep_unregister_key(&htab->lockdep_key); kfree(htab); @@ -925,8 +911,9 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, l_new = ERR_PTR(-E2BIG); goto dec_count; } - l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, - htab->map.numa_node); + l_new = bpf_map_kmalloc_node(&htab->map, htab->elem_size, + GFP_ATOMIC | __GFP_NOWARN, + htab->map.numa_node); if (!l_new) { l_new = ERR_PTR(-ENOMEM); goto dec_count; @@ -942,8 +929,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, pptr = htab_elem_get_ptr(l_new, key_size); } else { /* alloc_percpu zero-fills */ - pptr = __alloc_percpu_gfp(size, 8, - GFP_ATOMIC | __GFP_NOWARN); + pptr = bpf_map_alloc_percpu(&htab->map, size, 8, + GFP_ATOMIC | __GFP_NOWARN); if (!pptr) { kfree(l_new); l_new = ERR_PTR(-ENOMEM); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 25520f5eeaf6..2c395deae279 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -167,6 +167,17 @@ const struct bpf_func_proto bpf_ktime_get_boot_ns_proto = { .ret_type = RET_INTEGER, }; +BPF_CALL_0(bpf_ktime_get_coarse_ns) +{ + return ktime_get_coarse_ns(); +} + +const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto = { + .func = bpf_ktime_get_coarse_ns, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; + BPF_CALL_0(bpf_get_current_pid_tgid) { struct task_struct *task = current; @@ -685,6 +696,8 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; case BPF_FUNC_ringbuf_output: return &bpf_ringbuf_output_proto; case BPF_FUNC_ringbuf_reserve: diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index 571bb351ed3b..2d4f9ac12377 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -164,10 +164,10 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *key, return 0; } - new = kmalloc_node(sizeof(struct bpf_storage_buffer) + - map->value_size, - __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN, - map->numa_node); + new = bpf_map_kmalloc_node(map, sizeof(struct bpf_storage_buffer) + + map->value_size, + __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN, + map->numa_node); if (!new) return -ENOMEM; @@ -287,8 +287,6 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) { int numa_node = bpf_map_attr_numa_node(attr); struct bpf_cgroup_storage_map *map; - struct bpf_map_memory mem; - int ret; if (attr->key_size != sizeof(struct bpf_cgroup_storage_key) && attr->key_size != sizeof(__u64)) @@ -308,18 +306,10 @@ static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr) /* max_entries is not used and enforced to be 0 */ return ERR_PTR(-EINVAL); - ret = bpf_map_charge_init(&mem, sizeof(struct bpf_cgroup_storage_map)); - if (ret < 0) - return ERR_PTR(ret); - map = kmalloc_node(sizeof(struct bpf_cgroup_storage_map), - __GFP_ZERO | GFP_USER, numa_node); - if (!map) { - bpf_map_charge_finish(&mem); + __GFP_ZERO | GFP_USER | __GFP_ACCOUNT, numa_node); + if (!map) return ERR_PTR(-ENOMEM); - } - - bpf_map_charge_move(&map->map.memory, &mem); /* copy mandatory map attributes */ bpf_map_init_from_attr(&map->map, attr); @@ -496,9 +486,9 @@ static size_t bpf_cgroup_storage_calculate_size(struct bpf_map *map, u32 *pages) struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, enum bpf_cgroup_storage_type stype) { + const gfp_t gfp = __GFP_ZERO | GFP_USER; struct bpf_cgroup_storage *storage; struct bpf_map *map; - gfp_t flags; size_t size; u32 pages; @@ -508,23 +498,19 @@ struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, size = bpf_cgroup_storage_calculate_size(map, &pages); - if (bpf_map_charge_memlock(map, pages)) - return ERR_PTR(-EPERM); - - storage = kmalloc_node(sizeof(struct bpf_cgroup_storage), - __GFP_ZERO | GFP_USER, map->numa_node); + storage = bpf_map_kmalloc_node(map, sizeof(struct bpf_cgroup_storage), + gfp, map->numa_node); if (!storage) goto enomem; - flags = __GFP_ZERO | GFP_USER; - if (stype == BPF_CGROUP_STORAGE_SHARED) { - storage->buf = kmalloc_node(size, flags, map->numa_node); + storage->buf = bpf_map_kmalloc_node(map, size, gfp, + map->numa_node); if (!storage->buf) goto enomem; check_and_init_map_lock(map, storage->buf->data); } else { - storage->percpu_buf = __alloc_percpu_gfp(size, 8, flags); + storage->percpu_buf = bpf_map_alloc_percpu(map, size, 8, gfp); if (!storage->percpu_buf) goto enomem; } @@ -534,7 +520,6 @@ struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog, return storage; enomem: - bpf_map_uncharge_memlock(map, pages); kfree(storage); return ERR_PTR(-ENOMEM); } @@ -561,16 +546,11 @@ void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage) { enum bpf_cgroup_storage_type stype; struct bpf_map *map; - u32 pages; if (!storage) return; map = &storage->map->map; - - bpf_cgroup_storage_calculate_size(map, &pages); - bpf_map_uncharge_memlock(map, pages); - stype = cgroup_storage_type(map); if (stype == BPF_CGROUP_STORAGE_SHARED) call_rcu(&storage->rcu, free_shared_cgroup_storage_rcu); diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 00e32f2ec3e6..cec792a17e5f 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -282,8 +282,8 @@ static struct lpm_trie_node *lpm_trie_node_alloc(const struct lpm_trie *trie, if (value) size += trie->map.value_size; - node = kmalloc_node(size, GFP_ATOMIC | __GFP_NOWARN, - trie->map.numa_node); + node = bpf_map_kmalloc_node(&trie->map, size, GFP_ATOMIC | __GFP_NOWARN, + trie->map.numa_node); if (!node) return NULL; @@ -540,8 +540,6 @@ out: static struct bpf_map *trie_alloc(union bpf_attr *attr) { struct lpm_trie *trie; - u64 cost = sizeof(*trie), cost_per_node; - int ret; if (!bpf_capable()) return ERR_PTR(-EPERM); @@ -557,7 +555,7 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) attr->value_size > LPM_VAL_SIZE_MAX) return ERR_PTR(-EINVAL); - trie = kzalloc(sizeof(*trie), GFP_USER | __GFP_NOWARN); + trie = kzalloc(sizeof(*trie), GFP_USER | __GFP_NOWARN | __GFP_ACCOUNT); if (!trie) return ERR_PTR(-ENOMEM); @@ -567,20 +565,9 @@ static struct bpf_map *trie_alloc(union bpf_attr *attr) offsetof(struct bpf_lpm_trie_key, data); trie->max_prefixlen = trie->data_size * 8; - cost_per_node = sizeof(struct lpm_trie_node) + - attr->value_size + trie->data_size; - cost += (u64) attr->max_entries * cost_per_node; - - ret = bpf_map_charge_init(&trie->map.memory, cost); - if (ret) - goto out_err; - spin_lock_init(&trie->lock); return &trie->map; -out_err: - kfree(trie); - return ERR_PTR(ret); } static void trie_free(struct bpf_map *map) diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c index 0ee2347ba510..f9c734aaa990 100644 --- a/kernel/bpf/queue_stack_maps.c +++ b/kernel/bpf/queue_stack_maps.c @@ -66,29 +66,21 @@ static int queue_stack_map_alloc_check(union bpf_attr *attr) static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr) { - int ret, numa_node = bpf_map_attr_numa_node(attr); - struct bpf_map_memory mem = {0}; + int numa_node = bpf_map_attr_numa_node(attr); struct bpf_queue_stack *qs; - u64 size, queue_size, cost; + u64 size, queue_size; size = (u64) attr->max_entries + 1; - cost = queue_size = sizeof(*qs) + size * attr->value_size; - - ret = bpf_map_charge_init(&mem, cost); - if (ret < 0) - return ERR_PTR(ret); + queue_size = sizeof(*qs) + size * attr->value_size; qs = bpf_map_area_alloc(queue_size, numa_node); - if (!qs) { - bpf_map_charge_finish(&mem); + if (!qs) return ERR_PTR(-ENOMEM); - } memset(qs, 0, sizeof(*qs)); bpf_map_init_from_attr(&qs->map, attr); - bpf_map_charge_move(&qs->map.memory, &mem); qs->size = size; raw_spin_lock_init(&qs->lock); diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c index a55cd542f2ce..4838922f723d 100644 --- a/kernel/bpf/reuseport_array.c +++ b/kernel/bpf/reuseport_array.c @@ -150,9 +150,8 @@ static void reuseport_array_free(struct bpf_map *map) static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr) { - int err, numa_node = bpf_map_attr_numa_node(attr); + int numa_node = bpf_map_attr_numa_node(attr); struct reuseport_array *array; - struct bpf_map_memory mem; u64 array_size; if (!bpf_capable()) @@ -161,20 +160,13 @@ static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr) array_size = sizeof(*array); array_size += (u64)attr->max_entries * sizeof(struct sock *); - err = bpf_map_charge_init(&mem, array_size); - if (err) - return ERR_PTR(err); - /* allocate all map elements and zero-initialize them */ array = bpf_map_area_alloc(array_size, numa_node); - if (!array) { - bpf_map_charge_finish(&mem); + if (!array) return ERR_PTR(-ENOMEM); - } /* copy mandatory map attributes */ bpf_map_init_from_attr(&array->map, attr); - bpf_map_charge_move(&array->map.memory, &mem); return &array->map; } diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c index 31cb04a4dd2d..f25b719ac786 100644 --- a/kernel/bpf/ringbuf.c +++ b/kernel/bpf/ringbuf.c @@ -48,7 +48,6 @@ struct bpf_ringbuf { struct bpf_ringbuf_map { struct bpf_map map; - struct bpf_map_memory memory; struct bpf_ringbuf *rb; }; @@ -60,8 +59,8 @@ struct bpf_ringbuf_hdr { static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node) { - const gfp_t flags = GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN | - __GFP_ZERO; + const gfp_t flags = GFP_KERNEL_ACCOUNT | __GFP_RETRY_MAYFAIL | + __GFP_NOWARN | __GFP_ZERO; int nr_meta_pages = RINGBUF_PGOFF + RINGBUF_POS_PAGES; int nr_data_pages = data_sz >> PAGE_SHIFT; int nr_pages = nr_meta_pages + nr_data_pages; @@ -88,10 +87,7 @@ static struct bpf_ringbuf *bpf_ringbuf_area_alloc(size_t data_sz, int numa_node) * user-space implementations significantly. */ array_size = (nr_meta_pages + 2 * nr_data_pages) * sizeof(*pages); - if (array_size > PAGE_SIZE) - pages = vmalloc_node(array_size, numa_node); - else - pages = kmalloc_node(array_size, flags, numa_node); + pages = bpf_map_area_alloc(array_size, numa_node); if (!pages) return NULL; @@ -134,7 +130,7 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node) rb = bpf_ringbuf_area_alloc(data_sz, numa_node); if (!rb) - return ERR_PTR(-ENOMEM); + return NULL; spin_lock_init(&rb->spinlock); init_waitqueue_head(&rb->waitq); @@ -150,8 +146,6 @@ static struct bpf_ringbuf *bpf_ringbuf_alloc(size_t data_sz, int numa_node) static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr) { struct bpf_ringbuf_map *rb_map; - u64 cost; - int err; if (attr->map_flags & ~RINGBUF_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); @@ -167,32 +161,19 @@ static struct bpf_map *ringbuf_map_alloc(union bpf_attr *attr) return ERR_PTR(-E2BIG); #endif - rb_map = kzalloc(sizeof(*rb_map), GFP_USER); + rb_map = kzalloc(sizeof(*rb_map), GFP_USER | __GFP_ACCOUNT); if (!rb_map) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&rb_map->map, attr); - cost = sizeof(struct bpf_ringbuf_map) + - sizeof(struct bpf_ringbuf) + - attr->max_entries; - err = bpf_map_charge_init(&rb_map->map.memory, cost); - if (err) - goto err_free_map; - rb_map->rb = bpf_ringbuf_alloc(attr->max_entries, rb_map->map.numa_node); - if (IS_ERR(rb_map->rb)) { - err = PTR_ERR(rb_map->rb); - goto err_uncharge; + if (!rb_map->rb) { + kfree(rb_map); + return ERR_PTR(-ENOMEM); } return &rb_map->map; - -err_uncharge: - bpf_map_charge_finish(&rb_map->map.memory); -err_free_map: - kfree(rb_map); - return ERR_PTR(err); } static void bpf_ringbuf_free(struct bpf_ringbuf *rb) diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 06065fa27124..3325add8e629 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -90,7 +90,6 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) { u32 value_size = attr->value_size; struct bpf_stack_map *smap; - struct bpf_map_memory mem; u64 cost, n_buckets; int err; @@ -119,15 +118,9 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) cost = n_buckets * sizeof(struct stack_map_bucket *) + sizeof(*smap); cost += n_buckets * (value_size + sizeof(struct stack_map_bucket)); - err = bpf_map_charge_init(&mem, cost); - if (err) - return ERR_PTR(err); - smap = bpf_map_area_alloc(cost, bpf_map_attr_numa_node(attr)); - if (!smap) { - bpf_map_charge_finish(&mem); + if (!smap) return ERR_PTR(-ENOMEM); - } bpf_map_init_from_attr(&smap->map, attr); smap->map.value_size = value_size; @@ -135,20 +128,17 @@ static struct bpf_map *stack_map_alloc(union bpf_attr *attr) err = get_callchain_buffers(sysctl_perf_event_max_stack); if (err) - goto free_charge; + goto free_smap; err = prealloc_elems_and_freelist(smap); if (err) goto put_buffers; - bpf_map_charge_move(&smap->map.memory, &mem); - return &smap->map; put_buffers: put_callchain_buffers(); -free_charge: - bpf_map_charge_finish(&mem); +free_smap: bpf_map_area_free(smap); return ERR_PTR(err); } diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index f3fe9f53f93c..0cd3cc2af9c1 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -31,6 +31,7 @@ #include <linux/poll.h> #include <linux/bpf-netns.h> #include <linux/rcupdate_trace.h> +#include <linux/memcontrol.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \ (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \ @@ -127,7 +128,7 @@ static struct bpf_map *find_and_alloc_map(union bpf_attr *attr) return map; } -static u32 bpf_map_value_size(struct bpf_map *map) +static u32 bpf_map_value_size(const struct bpf_map *map) { if (map->map_type == BPF_MAP_TYPE_PERCPU_HASH || map->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH || @@ -267,6 +268,10 @@ static int bpf_map_copy_value(struct bpf_map *map, void *key, void *value, return err; } +/* Please, do not use this function outside from the map creation path + * (e.g. in map update path) without taking care of setting the active + * memory cgroup (see at bpf_map_kmalloc_node() for example). + */ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable) { /* We really just want to fail instead of triggering OOM killer @@ -279,7 +284,7 @@ static void *__bpf_map_area_alloc(u64 size, int numa_node, bool mmapable) * __GFP_RETRY_MAYFAIL to avoid such situations. */ - const gfp_t gfp = __GFP_NOWARN | __GFP_ZERO; + const gfp_t gfp = __GFP_NOWARN | __GFP_ZERO | __GFP_ACCOUNT; unsigned int flags = 0; unsigned long align = 1; void *area; @@ -341,77 +346,6 @@ void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr) map->numa_node = bpf_map_attr_numa_node(attr); } -static int bpf_charge_memlock(struct user_struct *user, u32 pages) -{ - unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; - - if (atomic_long_add_return(pages, &user->locked_vm) > memlock_limit) { - atomic_long_sub(pages, &user->locked_vm); - return -EPERM; - } - return 0; -} - -static void bpf_uncharge_memlock(struct user_struct *user, u32 pages) -{ - if (user) - atomic_long_sub(pages, &user->locked_vm); -} - -int bpf_map_charge_init(struct bpf_map_memory *mem, u64 size) -{ - u32 pages = round_up(size, PAGE_SIZE) >> PAGE_SHIFT; - struct user_struct *user; - int ret; - - if (size >= U32_MAX - PAGE_SIZE) - return -E2BIG; - - user = get_current_user(); - ret = bpf_charge_memlock(user, pages); - if (ret) { - free_uid(user); - return ret; - } - - mem->pages = pages; - mem->user = user; - - return 0; -} - -void bpf_map_charge_finish(struct bpf_map_memory *mem) -{ - bpf_uncharge_memlock(mem->user, mem->pages); - free_uid(mem->user); -} - -void bpf_map_charge_move(struct bpf_map_memory *dst, - struct bpf_map_memory *src) -{ - *dst = *src; - - /* Make sure src will not be used for the redundant uncharging. */ - memset(src, 0, sizeof(struct bpf_map_memory)); -} - -int bpf_map_charge_memlock(struct bpf_map *map, u32 pages) -{ - int ret; - - ret = bpf_charge_memlock(map->memory.user, pages); - if (ret) - return ret; - map->memory.pages += pages; - return ret; -} - -void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages) -{ - bpf_uncharge_memlock(map->memory.user, pages); - map->memory.pages -= pages; -} - static int bpf_map_alloc_id(struct bpf_map *map) { int id; @@ -456,17 +390,74 @@ void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock) __release(&map_idr_lock); } +#ifdef CONFIG_MEMCG_KMEM +static void bpf_map_save_memcg(struct bpf_map *map) +{ + map->memcg = get_mem_cgroup_from_mm(current->mm); +} + +static void bpf_map_release_memcg(struct bpf_map *map) +{ + mem_cgroup_put(map->memcg); +} + +void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, + int node) +{ + struct mem_cgroup *old_memcg; + void *ptr; + + old_memcg = set_active_memcg(map->memcg); + ptr = kmalloc_node(size, flags | __GFP_ACCOUNT, node); + set_active_memcg(old_memcg); + + return ptr; +} + +void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags) +{ + struct mem_cgroup *old_memcg; + void *ptr; + + old_memcg = set_active_memcg(map->memcg); + ptr = kzalloc(size, flags | __GFP_ACCOUNT); + set_active_memcg(old_memcg); + + return ptr; +} + +void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, + size_t align, gfp_t flags) +{ + struct mem_cgroup *old_memcg; + void __percpu *ptr; + + old_memcg = set_active_memcg(map->memcg); + ptr = __alloc_percpu_gfp(size, align, flags | __GFP_ACCOUNT); + set_active_memcg(old_memcg); + + return ptr; +} + +#else +static void bpf_map_save_memcg(struct bpf_map *map) +{ +} + +static void bpf_map_release_memcg(struct bpf_map *map) +{ +} +#endif + /* called from workqueue */ static void bpf_map_free_deferred(struct work_struct *work) { struct bpf_map *map = container_of(work, struct bpf_map, work); - struct bpf_map_memory mem; - bpf_map_charge_move(&mem, &map->memory); security_bpf_map_free(map); + bpf_map_release_memcg(map); /* implementation dependent freeing */ map->ops->map_free(map); - bpf_map_charge_finish(&mem); } static void bpf_map_put_uref(struct bpf_map *map) @@ -527,6 +518,19 @@ static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f) } #ifdef CONFIG_PROC_FS +/* Provides an approximation of the map's memory footprint. + * Used only to provide a backward compatibility and display + * a reasonable "memlock" info. + */ +static unsigned long bpf_map_memory_footprint(const struct bpf_map *map) +{ + unsigned long size; + + size = round_up(map->key_size + bpf_map_value_size(map), 8); + + return round_up(map->max_entries * size, PAGE_SIZE); +} + static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) { const struct bpf_map *map = filp->private_data; @@ -545,7 +549,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) "value_size:\t%u\n" "max_entries:\t%u\n" "map_flags:\t%#x\n" - "memlock:\t%llu\n" + "memlock:\t%lu\n" "map_id:\t%u\n" "frozen:\t%u\n", map->map_type, @@ -553,7 +557,7 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp) map->value_size, map->max_entries, map->map_flags, - map->memory.pages * 1ULL << PAGE_SHIFT, + bpf_map_memory_footprint(map), map->id, READ_ONCE(map->frozen)); if (type) { @@ -796,7 +800,6 @@ static int map_check_btf(struct bpf_map *map, const struct btf *btf, static int map_create(union bpf_attr *attr) { int numa_node = bpf_map_attr_numa_node(attr); - struct bpf_map_memory mem; struct bpf_map *map; int f_flags; int err; @@ -875,6 +878,8 @@ static int map_create(union bpf_attr *attr) if (err) goto free_map_sec; + bpf_map_save_memcg(map); + err = bpf_map_new_fd(map, f_flags); if (err < 0) { /* failed to allocate fd. @@ -893,9 +898,7 @@ free_map_sec: security_bpf_map_free(map); free_map: btf_put(map->btf); - bpf_map_charge_move(&mem, &map->memory); map->ops->map_free(map); - bpf_map_charge_finish(&mem); return err; } @@ -1629,51 +1632,6 @@ static void bpf_audit_prog(const struct bpf_prog *prog, unsigned int op) audit_log_end(ab); } -int __bpf_prog_charge(struct user_struct *user, u32 pages) -{ - unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; - unsigned long user_bufs; - - if (user) { - user_bufs = atomic_long_add_return(pages, &user->locked_vm); - if (user_bufs > memlock_limit) { - atomic_long_sub(pages, &user->locked_vm); - return -EPERM; - } - } - - return 0; -} - -void __bpf_prog_uncharge(struct user_struct *user, u32 pages) -{ - if (user) - atomic_long_sub(pages, &user->locked_vm); -} - -static int bpf_prog_charge_memlock(struct bpf_prog *prog) -{ - struct user_struct *user = get_current_user(); - int ret; - - ret = __bpf_prog_charge(user, prog->pages); - if (ret) { - free_uid(user); - return ret; - } - - prog->aux->user = user; - return 0; -} - -static void bpf_prog_uncharge_memlock(struct bpf_prog *prog) -{ - struct user_struct *user = prog->aux->user; - - __bpf_prog_uncharge(user, prog->pages); - free_uid(user); -} - static int bpf_prog_alloc_id(struct bpf_prog *prog) { int id; @@ -1723,7 +1681,7 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu) kvfree(aux->func_info); kfree(aux->func_info_aux); - bpf_prog_uncharge_memlock(aux->prog); + free_uid(aux->user); security_bpf_prog_free(aux); bpf_prog_free(aux->prog); } @@ -1733,6 +1691,8 @@ static void __bpf_prog_put_noref(struct bpf_prog *prog, bool deferred) bpf_prog_kallsyms_del_all(prog); btf_put(prog->aux->btf); bpf_prog_free_linfo(prog); + if (prog->aux->attach_btf) + btf_put(prog->aux->attach_btf); if (deferred) { if (prog->aux->sleepable) @@ -1966,12 +1926,16 @@ static void bpf_prog_load_fixup_attach_type(union bpf_attr *attr) static int bpf_prog_load_check_attach(enum bpf_prog_type prog_type, enum bpf_attach_type expected_attach_type, - u32 btf_id, u32 prog_fd) + struct btf *attach_btf, u32 btf_id, + struct bpf_prog *dst_prog) { if (btf_id) { if (btf_id > BTF_MAX_TYPE) return -EINVAL; + if (!attach_btf && !dst_prog) + return -EINVAL; + switch (prog_type) { case BPF_PROG_TYPE_TRACING: case BPF_PROG_TYPE_LSM: @@ -1983,7 +1947,10 @@ bpf_prog_load_check_attach(enum bpf_prog_type prog_type, } } - if (prog_fd && prog_type != BPF_PROG_TYPE_TRACING && + if (attach_btf && (!btf_id || dst_prog)) + return -EINVAL; + + if (dst_prog && prog_type != BPF_PROG_TYPE_TRACING && prog_type != BPF_PROG_TYPE_EXT) return -EINVAL; @@ -2100,7 +2067,8 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type) static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) { enum bpf_prog_type type = attr->prog_type; - struct bpf_prog *prog; + struct bpf_prog *prog, *dst_prog = NULL; + struct btf *attach_btf = NULL; int err; char license[128]; bool is_gpl; @@ -2142,47 +2110,70 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) if (is_perfmon_prog_type(type) && !perfmon_capable()) return -EPERM; + /* attach_prog_fd/attach_btf_obj_fd can specify fd of either bpf_prog + * or btf, we need to check which one it is + */ + if (attr->attach_prog_fd) { + dst_prog = bpf_prog_get(attr->attach_prog_fd); + if (IS_ERR(dst_prog)) { + dst_prog = NULL; + attach_btf = btf_get_by_fd(attr->attach_btf_obj_fd); + if (IS_ERR(attach_btf)) + return -EINVAL; + if (!btf_is_kernel(attach_btf)) { + btf_put(attach_btf); + return -EINVAL; + } + } + } else if (attr->attach_btf_id) { + /* fall back to vmlinux BTF, if BTF type ID is specified */ + attach_btf = bpf_get_btf_vmlinux(); + if (IS_ERR(attach_btf)) + return PTR_ERR(attach_btf); + if (!attach_btf) + return -EINVAL; + btf_get(attach_btf); + } + bpf_prog_load_fixup_attach_type(attr); if (bpf_prog_load_check_attach(type, attr->expected_attach_type, - attr->attach_btf_id, - attr->attach_prog_fd)) + attach_btf, attr->attach_btf_id, + dst_prog)) { + if (dst_prog) + bpf_prog_put(dst_prog); + if (attach_btf) + btf_put(attach_btf); return -EINVAL; + } /* plain bpf_prog allocation */ prog = bpf_prog_alloc(bpf_prog_size(attr->insn_cnt), GFP_USER); - if (!prog) + if (!prog) { + if (dst_prog) + bpf_prog_put(dst_prog); + if (attach_btf) + btf_put(attach_btf); return -ENOMEM; + } prog->expected_attach_type = attr->expected_attach_type; + prog->aux->attach_btf = attach_btf; prog->aux->attach_btf_id = attr->attach_btf_id; - if (attr->attach_prog_fd) { - struct bpf_prog *dst_prog; - - dst_prog = bpf_prog_get(attr->attach_prog_fd); - if (IS_ERR(dst_prog)) { - err = PTR_ERR(dst_prog); - goto free_prog_nouncharge; - } - prog->aux->dst_prog = dst_prog; - } - + prog->aux->dst_prog = dst_prog; prog->aux->offload_requested = !!attr->prog_ifindex; prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; err = security_bpf_prog_alloc(prog->aux); if (err) - goto free_prog_nouncharge; - - err = bpf_prog_charge_memlock(prog); - if (err) - goto free_prog_sec; + goto free_prog; + prog->aux->user = get_current_user(); prog->len = attr->insn_cnt; err = -EFAULT; if (copy_from_user(prog->insns, u64_to_user_ptr(attr->insns), bpf_prog_insn_size(prog)) != 0) - goto free_prog; + goto free_prog_sec; prog->orig_prog = NULL; prog->jited = 0; @@ -2193,19 +2184,19 @@ static int bpf_prog_load(union bpf_attr *attr, union bpf_attr __user *uattr) if (bpf_prog_is_dev_bound(prog->aux)) { err = bpf_prog_offload_init(prog, attr); if (err) - goto free_prog; + goto free_prog_sec; } /* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); if (err < 0) - goto free_prog; + goto free_prog_sec; prog->aux->load_time = ktime_get_boottime_ns(); err = bpf_obj_name_cpy(prog->aux->name, attr->prog_name, sizeof(attr->prog_name)); if (err < 0) - goto free_prog; + goto free_prog_sec; /* run eBPF verifier */ err = bpf_check(&prog, attr, uattr); @@ -2250,11 +2241,12 @@ free_used_maps: */ __bpf_prog_put_noref(prog, prog->aux->func_cnt); return err; -free_prog: - bpf_prog_uncharge_memlock(prog); free_prog_sec: + free_uid(prog->aux->user); security_bpf_prog_free(prog->aux); -free_prog_nouncharge: +free_prog: + if (prog->aux->attach_btf) + btf_put(prog->aux->attach_btf); bpf_prog_free(prog); return err; } @@ -2612,7 +2604,7 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog, goto out_put_prog; } - key = bpf_trampoline_compute_key(tgt_prog, btf_id); + key = bpf_trampoline_compute_key(tgt_prog, NULL, btf_id); } link = kzalloc(sizeof(*link), GFP_USER); @@ -3589,7 +3581,7 @@ static int bpf_prog_get_info_by_fd(struct file *file, } if (prog->aux->btf) - info.btf_id = btf_id(prog->aux->btf); + info.btf_id = btf_obj_id(prog->aux->btf); ulen = info.nr_func_info; info.nr_func_info = prog->aux->func_info_cnt; @@ -3692,7 +3684,7 @@ static int bpf_map_get_info_by_fd(struct file *file, memcpy(info.name, map->name, sizeof(map->name)); if (map->btf) { - info.btf_id = btf_id(map->btf); + info.btf_id = btf_obj_id(map->btf); info.btf_key_type_id = map->btf_key_type_id; info.btf_value_type_id = map->btf_value_type_id; } diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index 1fdb2fc196cd..0458a40edf10 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -136,8 +136,7 @@ struct bpf_iter_seq_task_file_info { }; static struct file * -task_file_seq_get_next(struct bpf_iter_seq_task_file_info *info, - struct task_struct **task, struct files_struct **fstruct) +task_file_seq_get_next(struct bpf_iter_seq_task_file_info *info) { struct pid_namespace *ns = info->common.ns; u32 curr_tid = info->tid, max_fds; @@ -150,14 +149,17 @@ task_file_seq_get_next(struct bpf_iter_seq_task_file_info *info, * Otherwise, it does not hold any reference. */ again: - if (*task) { - curr_task = *task; - curr_files = *fstruct; + if (info->task) { + curr_task = info->task; + curr_files = info->files; curr_fd = info->fd; } else { curr_task = task_seq_get_next(ns, &curr_tid, true); - if (!curr_task) + if (!curr_task) { + info->task = NULL; + info->files = NULL; return NULL; + } curr_files = get_files_struct(curr_task); if (!curr_files) { @@ -167,9 +169,8 @@ again: goto again; } - /* set *fstruct, *task and info->tid */ - *fstruct = curr_files; - *task = curr_task; + info->files = curr_files; + info->task = curr_task; if (curr_tid == info->tid) { curr_fd = info->fd; } else { @@ -199,8 +200,8 @@ again: rcu_read_unlock(); put_files_struct(curr_files); put_task_struct(curr_task); - *task = NULL; - *fstruct = NULL; + info->task = NULL; + info->files = NULL; info->fd = 0; curr_tid = ++(info->tid); goto again; @@ -209,21 +210,13 @@ again: static void *task_file_seq_start(struct seq_file *seq, loff_t *pos) { struct bpf_iter_seq_task_file_info *info = seq->private; - struct files_struct *files = NULL; - struct task_struct *task = NULL; struct file *file; - file = task_file_seq_get_next(info, &task, &files); - if (!file) { - info->files = NULL; - info->task = NULL; - return NULL; - } - - if (*pos == 0) + info->task = NULL; + info->files = NULL; + file = task_file_seq_get_next(info); + if (file && *pos == 0) ++*pos; - info->task = task; - info->files = files; return file; } @@ -231,24 +224,11 @@ static void *task_file_seq_start(struct seq_file *seq, loff_t *pos) static void *task_file_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct bpf_iter_seq_task_file_info *info = seq->private; - struct files_struct *files = info->files; - struct task_struct *task = info->task; - struct file *file; ++*pos; ++info->fd; fput((struct file *)v); - file = task_file_seq_get_next(info, &task, &files); - if (!file) { - info->files = NULL; - info->task = NULL; - return NULL; - } - - info->task = task; - info->files = files; - - return file; + return task_file_seq_get_next(info); } struct bpf_iter__task_file { diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index ab2d6a02aee0..93def76cf32b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -238,7 +238,9 @@ struct bpf_call_arg_meta { u64 msize_max_value; int ref_obj_id; int func_id; + struct btf *btf; u32 btf_id; + struct btf *ret_btf; u32 ret_btf_id; }; @@ -556,10 +558,9 @@ static struct bpf_func_state *func(struct bpf_verifier_env *env, return cur->frame[reg->frameno]; } -const char *kernel_type_name(u32 id) +static const char *kernel_type_name(const struct btf* btf, u32 id) { - return btf_name_by_offset(btf_vmlinux, - btf_type_by_id(btf_vmlinux, id)->name_off); + return btf_name_by_offset(btf, btf_type_by_id(btf, id)->name_off); } static void print_verifier_state(struct bpf_verifier_env *env, @@ -589,7 +590,7 @@ static void print_verifier_state(struct bpf_verifier_env *env, if (t == PTR_TO_BTF_ID || t == PTR_TO_BTF_ID_OR_NULL || t == PTR_TO_PERCPU_BTF_ID) - verbose(env, "%s", kernel_type_name(reg->btf_id)); + verbose(env, "%s", kernel_type_name(reg->btf, reg->btf_id)); verbose(env, "(id=%d", reg->id); if (reg_type_may_be_refcounted_or_null(t)) verbose(env, ",ref_obj_id=%d", reg->ref_obj_id); @@ -1383,7 +1384,8 @@ static void mark_reg_not_init(struct bpf_verifier_env *env, static void mark_btf_ld_reg(struct bpf_verifier_env *env, struct bpf_reg_state *regs, u32 regno, - enum bpf_reg_type reg_type, u32 btf_id) + enum bpf_reg_type reg_type, + struct btf *btf, u32 btf_id) { if (reg_type == SCALAR_VALUE) { mark_reg_unknown(env, regs, regno); @@ -1391,6 +1393,7 @@ static void mark_btf_ld_reg(struct bpf_verifier_env *env, } mark_reg_known_zero(env, regs, regno); regs[regno].type = PTR_TO_BTF_ID; + regs[regno].btf = btf; regs[regno].btf_id = btf_id; } @@ -2764,7 +2767,7 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off, /* check access to 'struct bpf_context' fields. Supports fixed offsets only */ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size, enum bpf_access_type t, enum bpf_reg_type *reg_type, - u32 *btf_id) + struct btf **btf, u32 *btf_id) { struct bpf_insn_access_aux info = { .reg_type = *reg_type, @@ -2782,10 +2785,12 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, */ *reg_type = info.reg_type; - if (*reg_type == PTR_TO_BTF_ID || *reg_type == PTR_TO_BTF_ID_OR_NULL) + if (*reg_type == PTR_TO_BTF_ID || *reg_type == PTR_TO_BTF_ID_OR_NULL) { + *btf = info.btf; *btf_id = info.btf_id; - else + } else { env->insn_aux_data[insn_idx].ctx_field_size = info.ctx_field_size; + } /* remember the offset of last byte accessed in ctx */ if (env->prog->aux->max_ctx_offset < off + size) env->prog->aux->max_ctx_offset = off + size; @@ -3297,8 +3302,8 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, int value_regno) { struct bpf_reg_state *reg = regs + regno; - const struct btf_type *t = btf_type_by_id(btf_vmlinux, reg->btf_id); - const char *tname = btf_name_by_offset(btf_vmlinux, t->name_off); + const struct btf_type *t = btf_type_by_id(reg->btf, reg->btf_id); + const char *tname = btf_name_by_offset(reg->btf, t->name_off); u32 btf_id; int ret; @@ -3319,23 +3324,23 @@ static int check_ptr_to_btf_access(struct bpf_verifier_env *env, } if (env->ops->btf_struct_access) { - ret = env->ops->btf_struct_access(&env->log, t, off, size, - atype, &btf_id); + ret = env->ops->btf_struct_access(&env->log, reg->btf, t, + off, size, atype, &btf_id); } else { if (atype != BPF_READ) { verbose(env, "only read is supported\n"); return -EACCES; } - ret = btf_struct_access(&env->log, t, off, size, atype, - &btf_id); + ret = btf_struct_access(&env->log, reg->btf, t, off, size, + atype, &btf_id); } if (ret < 0) return ret; if (atype == BPF_READ && value_regno >= 0) - mark_btf_ld_reg(env, regs, value_regno, ret, btf_id); + mark_btf_ld_reg(env, regs, value_regno, ret, reg->btf, btf_id); return 0; } @@ -3385,12 +3390,12 @@ static int check_ptr_to_map_access(struct bpf_verifier_env *env, return -EACCES; } - ret = btf_struct_access(&env->log, t, off, size, atype, &btf_id); + ret = btf_struct_access(&env->log, btf_vmlinux, t, off, size, atype, &btf_id); if (ret < 0) return ret; if (value_regno >= 0) - mark_btf_ld_reg(env, regs, value_regno, ret, btf_id); + mark_btf_ld_reg(env, regs, value_regno, ret, btf_vmlinux, btf_id); return 0; } @@ -3466,6 +3471,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn mark_reg_unknown(env, regs, value_regno); } else if (reg->type == PTR_TO_CTX) { enum bpf_reg_type reg_type = SCALAR_VALUE; + struct btf *btf = NULL; u32 btf_id = 0; if (t == BPF_WRITE && value_regno >= 0 && @@ -3478,7 +3484,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn if (err < 0) return err; - err = check_ctx_access(env, insn_idx, off, size, t, ®_type, &btf_id); + err = check_ctx_access(env, insn_idx, off, size, t, ®_type, &btf, &btf_id); if (err) verbose_linfo(env, insn_idx, "; "); if (!err && t == BPF_READ && value_regno >= 0) { @@ -3500,8 +3506,10 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn */ regs[value_regno].subreg_def = DEF_NOT_SUBREG; if (reg_type == PTR_TO_BTF_ID || - reg_type == PTR_TO_BTF_ID_OR_NULL) + reg_type == PTR_TO_BTF_ID_OR_NULL) { + regs[value_regno].btf = btf; regs[value_regno].btf_id = btf_id; + } } regs[value_regno].type = reg_type; } @@ -4118,11 +4126,11 @@ found: arg_btf_id = compatible->btf_id; } - if (!btf_struct_ids_match(&env->log, reg->off, reg->btf_id, - *arg_btf_id)) { + if (!btf_struct_ids_match(&env->log, reg->btf, reg->btf_id, reg->off, + btf_vmlinux, *arg_btf_id)) { verbose(env, "R%d is of type %s but %s is expected\n", - regno, kernel_type_name(reg->btf_id), - kernel_type_name(*arg_btf_id)); + regno, kernel_type_name(reg->btf, reg->btf_id), + kernel_type_name(btf_vmlinux, *arg_btf_id)); return -EACCES; } @@ -4244,6 +4252,7 @@ skip_type_check: verbose(env, "Helper has invalid btf_id in R%d\n", regno); return -EACCES; } + meta->ret_btf = reg->btf; meta->ret_btf_id = reg->btf_id; } else if (arg_type == ARG_PTR_TO_SPIN_LOCK) { if (meta->func_id == BPF_FUNC_spin_lock) { @@ -5190,16 +5199,16 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn const struct btf_type *t; mark_reg_known_zero(env, regs, BPF_REG_0); - t = btf_type_skip_modifiers(btf_vmlinux, meta.ret_btf_id, NULL); + t = btf_type_skip_modifiers(meta.ret_btf, meta.ret_btf_id, NULL); if (!btf_type_is_struct(t)) { u32 tsize; const struct btf_type *ret; const char *tname; /* resolve the type size of ksym. */ - ret = btf_resolve_size(btf_vmlinux, t, &tsize); + ret = btf_resolve_size(meta.ret_btf, t, &tsize); if (IS_ERR(ret)) { - tname = btf_name_by_offset(btf_vmlinux, t->name_off); + tname = btf_name_by_offset(meta.ret_btf, t->name_off); verbose(env, "unable to resolve the size of type '%s': %ld\n", tname, PTR_ERR(ret)); return -EINVAL; @@ -5212,6 +5221,7 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn regs[BPF_REG_0].type = fn->ret_type == RET_PTR_TO_MEM_OR_BTF_ID ? PTR_TO_BTF_ID : PTR_TO_BTF_ID_OR_NULL; + regs[BPF_REG_0].btf = meta.ret_btf; regs[BPF_REG_0].btf_id = meta.ret_btf_id; } } else if (fn->ret_type == RET_PTR_TO_BTF_ID_OR_NULL || @@ -5228,6 +5238,10 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn fn->ret_type, func_id_name(func_id), func_id); return -EINVAL; } + /* current BPF helper definitions are only coming from + * built-in code with type IDs from vmlinux BTF + */ + regs[BPF_REG_0].btf = btf_vmlinux; regs[BPF_REG_0].btf_id = ret_btf_id; } else { verbose(env, "unknown return type %d of func %s#%d\n", @@ -5627,7 +5641,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, if (reg_is_pkt_pointer(ptr_reg)) { dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ - dst_reg->raw = 0; + memset(&dst_reg->raw, 0, sizeof(dst_reg->raw)); } break; case BPF_SUB: @@ -5692,7 +5706,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env, dst_reg->id = ++env->id_gen; /* something was added to pkt_ptr, set range to zero */ if (smin_val < 0) - dst_reg->raw = 0; + memset(&dst_reg->raw, 0, sizeof(dst_reg->raw)); } break; case BPF_AND: @@ -7744,6 +7758,7 @@ static int check_ld_imm(struct bpf_verifier_env *env, struct bpf_insn *insn) break; case PTR_TO_BTF_ID: case PTR_TO_PERCPU_BTF_ID: + dst_reg->btf = aux->btf_var.btf; dst_reg->btf_id = aux->btf_var.btf_id; break; default: @@ -8058,6 +8073,11 @@ static void init_explored_state(struct bpf_verifier_env *env, int idx) env->insn_aux_data[idx].prune_point = true; } +enum { + DONE_EXPLORING = 0, + KEEP_EXPLORING = 1, +}; + /* t, w, e - match pseudo-code above: * t - index of current instruction * w - next instruction @@ -8070,10 +8090,10 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, int *insn_state = env->cfg.insn_state; if (e == FALLTHROUGH && insn_state[t] >= (DISCOVERED | FALLTHROUGH)) - return 0; + return DONE_EXPLORING; if (e == BRANCH && insn_state[t] >= (DISCOVERED | BRANCH)) - return 0; + return DONE_EXPLORING; if (w < 0 || w >= env->prog->len) { verbose_linfo(env, t, "%d: ", t); @@ -8092,10 +8112,10 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, if (env->cfg.cur_stack >= env->prog->len) return -E2BIG; insn_stack[env->cfg.cur_stack++] = w; - return 1; + return KEEP_EXPLORING; } else if ((insn_state[w] & 0xF0) == DISCOVERED) { if (loop_ok && env->bpf_capable) - return 0; + return DONE_EXPLORING; verbose_linfo(env, t, "%d: ", t); verbose_linfo(env, w, "%d: ", w); verbose(env, "back-edge from insn %d to %d\n", t, w); @@ -8107,7 +8127,74 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, verbose(env, "insn state internal bug\n"); return -EFAULT; } - return 0; + return DONE_EXPLORING; +} + +/* Visits the instruction at index t and returns one of the following: + * < 0 - an error occurred + * DONE_EXPLORING - the instruction was fully explored + * KEEP_EXPLORING - there is still work to be done before it is fully explored + */ +static int visit_insn(int t, int insn_cnt, struct bpf_verifier_env *env) +{ + struct bpf_insn *insns = env->prog->insnsi; + int ret; + + /* All non-branch instructions have a single fall-through edge. */ + if (BPF_CLASS(insns[t].code) != BPF_JMP && + BPF_CLASS(insns[t].code) != BPF_JMP32) + return push_insn(t, t + 1, FALLTHROUGH, env, false); + + switch (BPF_OP(insns[t].code)) { + case BPF_EXIT: + return DONE_EXPLORING; + + case BPF_CALL: + ret = push_insn(t, t + 1, FALLTHROUGH, env, false); + if (ret) + return ret; + + if (t + 1 < insn_cnt) + init_explored_state(env, t + 1); + if (insns[t].src_reg == BPF_PSEUDO_CALL) { + init_explored_state(env, t); + ret = push_insn(t, t + insns[t].imm + 1, BRANCH, + env, false); + } + return ret; + + case BPF_JA: + if (BPF_SRC(insns[t].code) != BPF_K) + return -EINVAL; + + /* unconditional jump with single edge */ + ret = push_insn(t, t + insns[t].off + 1, FALLTHROUGH, env, + true); + if (ret) + return ret; + + /* unconditional jmp is not a good pruning point, + * but it's marked, since backtracking needs + * to record jmp history in is_state_visited(). + */ + init_explored_state(env, t + insns[t].off + 1); + /* tell verifier to check for equivalent states + * after every call and jump + */ + if (t + 1 < insn_cnt) + init_explored_state(env, t + 1); + + return ret; + + default: + /* conditional jump with two edges */ + init_explored_state(env, t); + ret = push_insn(t, t + 1, FALLTHROUGH, env, true); + if (ret) + return ret; + + return push_insn(t, t + insns[t].off + 1, BRANCH, env, true); + } } /* non-recursive depth-first-search to detect loops in BPF program @@ -8115,11 +8202,10 @@ static int push_insn(int t, int w, int e, struct bpf_verifier_env *env, */ static int check_cfg(struct bpf_verifier_env *env) { - struct bpf_insn *insns = env->prog->insnsi; int insn_cnt = env->prog->len; int *insn_stack, *insn_state; int ret = 0; - int i, t; + int i; insn_state = env->cfg.insn_state = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL); if (!insn_state) @@ -8135,92 +8221,32 @@ static int check_cfg(struct bpf_verifier_env *env) insn_stack[0] = 0; /* 0 is the first instruction */ env->cfg.cur_stack = 1; -peek_stack: - if (env->cfg.cur_stack == 0) - goto check_state; - t = insn_stack[env->cfg.cur_stack - 1]; - - if (BPF_CLASS(insns[t].code) == BPF_JMP || - BPF_CLASS(insns[t].code) == BPF_JMP32) { - u8 opcode = BPF_OP(insns[t].code); - - if (opcode == BPF_EXIT) { - goto mark_explored; - } else if (opcode == BPF_CALL) { - ret = push_insn(t, t + 1, FALLTHROUGH, env, false); - if (ret == 1) - goto peek_stack; - else if (ret < 0) - goto err_free; - if (t + 1 < insn_cnt) - init_explored_state(env, t + 1); - if (insns[t].src_reg == BPF_PSEUDO_CALL) { - init_explored_state(env, t); - ret = push_insn(t, t + insns[t].imm + 1, BRANCH, - env, false); - if (ret == 1) - goto peek_stack; - else if (ret < 0) - goto err_free; - } - } else if (opcode == BPF_JA) { - if (BPF_SRC(insns[t].code) != BPF_K) { - ret = -EINVAL; - goto err_free; - } - /* unconditional jump with single edge */ - ret = push_insn(t, t + insns[t].off + 1, - FALLTHROUGH, env, true); - if (ret == 1) - goto peek_stack; - else if (ret < 0) - goto err_free; - /* unconditional jmp is not a good pruning point, - * but it's marked, since backtracking needs - * to record jmp history in is_state_visited(). - */ - init_explored_state(env, t + insns[t].off + 1); - /* tell verifier to check for equivalent states - * after every call and jump - */ - if (t + 1 < insn_cnt) - init_explored_state(env, t + 1); - } else { - /* conditional jump with two edges */ - init_explored_state(env, t); - ret = push_insn(t, t + 1, FALLTHROUGH, env, true); - if (ret == 1) - goto peek_stack; - else if (ret < 0) - goto err_free; + while (env->cfg.cur_stack > 0) { + int t = insn_stack[env->cfg.cur_stack - 1]; - ret = push_insn(t, t + insns[t].off + 1, BRANCH, env, true); - if (ret == 1) - goto peek_stack; - else if (ret < 0) - goto err_free; - } - } else { - /* all other non-branch instructions with single - * fall-through edge - */ - ret = push_insn(t, t + 1, FALLTHROUGH, env, false); - if (ret == 1) - goto peek_stack; - else if (ret < 0) + ret = visit_insn(t, insn_cnt, env); + switch (ret) { + case DONE_EXPLORING: + insn_state[t] = EXPLORED; + env->cfg.cur_stack--; + break; + case KEEP_EXPLORING: + break; + default: + if (ret > 0) { + verbose(env, "visit_insn internal bug\n"); + ret = -EFAULT; + } goto err_free; + } } -mark_explored: - insn_state[t] = EXPLORED; - if (env->cfg.cur_stack-- <= 0) { + if (env->cfg.cur_stack < 0) { verbose(env, "pop stack internal bug\n"); ret = -EFAULT; goto err_free; } - goto peek_stack; -check_state: for (i = 0; i < insn_cnt; i++) { if (insn_state[i] != EXPLORED) { verbose(env, "unreachable insn %d\n", i); @@ -9740,6 +9766,7 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env, t = btf_type_skip_modifiers(btf_vmlinux, type, NULL); if (percpu) { aux->btf_var.reg_type = PTR_TO_PERCPU_BTF_ID; + aux->btf_var.btf = btf_vmlinux; aux->btf_var.btf_id = type; } else if (!btf_type_is_struct(t)) { const struct btf_type *ret; @@ -9758,6 +9785,7 @@ static int check_pseudo_btf_id(struct bpf_verifier_env *env, aux->btf_var.mem_size = tsize; } else { aux->btf_var.reg_type = PTR_TO_BTF_ID; + aux->btf_var.btf = btf_vmlinux; aux->btf_var.btf_id = type; } return 0; @@ -11610,7 +11638,7 @@ int bpf_check_attach_target(struct bpf_verifier_log *log, bpf_log(log, "Tracing programs must provide btf_id\n"); return -EINVAL; } - btf = tgt_prog ? tgt_prog->aux->btf : btf_vmlinux; + btf = tgt_prog ? tgt_prog->aux->btf : prog->aux->attach_btf; if (!btf) { bpf_log(log, "FENTRY/FEXIT program can only be attached to another program annotated with BTF\n"); @@ -11886,7 +11914,7 @@ static int check_attach_btf_id(struct bpf_verifier_env *env) return ret; } - key = bpf_trampoline_compute_key(tgt_prog, btf_id); + key = bpf_trampoline_compute_key(tgt_prog, prog->aux->attach_btf, btf_id); tr = bpf_trampoline_get(key, &tgt_info); if (!tr) return -ENOMEM; diff --git a/kernel/fork.c b/kernel/fork.c index 6d266388d380..cbd4f6f58409 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -404,9 +404,10 @@ static int memcg_charge_kernel_stack(struct task_struct *tsk) for (i = 0; i < THREAD_SIZE / PAGE_SIZE; i++) { /* - * If memcg_kmem_charge_page() fails, page->mem_cgroup - * pointer is NULL, and memcg_kmem_uncharge_page() in - * free_thread_stack() will ignore this page. + * If memcg_kmem_charge_page() fails, page's + * memory cgroup pointer is NULL, and + * memcg_kmem_uncharge_page() in free_thread_stack() + * will ignore this page. */ ret = memcg_kmem_charge_page(vm->pages[i], GFP_KERNEL, 0); diff --git a/kernel/module.c b/kernel/module.c index f2996b02ab2e..c3a9e972d3b2 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -3709,6 +3709,10 @@ static noinline int do_init_module(struct module *mod) mod->init_layout.ro_size = 0; mod->init_layout.ro_after_init_size = 0; mod->init_layout.text_size = 0; +#ifdef CONFIG_DEBUG_INFO_BTF_MODULES + /* .BTF is not SHF_ALLOC and will get removed, so sanitize pointer */ + mod->btf_data = NULL; +#endif /* * We want to free module_init, but be aware that kallsyms may be * walking this with preempt disabled. In all the failure paths, we diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index a18fee10e906..cb9d7478ef0c 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -1290,6 +1290,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; + case BPF_FUNC_ktime_get_coarse_ns: + return &bpf_ktime_get_coarse_ns_proto; case BPF_FUNC_tail_call: return &bpf_tail_call_proto; case BPF_FUNC_get_current_pid_tgid: @@ -2068,10 +2070,12 @@ struct bpf_raw_event_map *bpf_get_raw_tracepoint(const char *name) void bpf_put_raw_tracepoint(struct bpf_raw_event_map *btp) { - struct module *mod = __module_address((unsigned long)btp); + struct module *mod; - if (mod) - module_put(mod); + preempt_disable(); + mod = __module_address((unsigned long)btp); + module_put(mod); + preempt_enable(); } static __always_inline diff --git a/mm/debug.c b/mm/debug.c index ccca576b2899..8a40b3fefbeb 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -182,8 +182,8 @@ hex_only: pr_warn("page dumped because: %s\n", reason); #ifdef CONFIG_MEMCG - if (!page_poisoned && page->mem_cgroup) - pr_warn("page->mem_cgroup:%px\n", page->mem_cgroup); + if (!page_poisoned && page->memcg_data) + pr_warn("pages's memcg:%lx\n", page->memcg_data); #endif } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index ec2bb93f7431..8bbf1c1affde 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -470,7 +470,7 @@ pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) #ifdef CONFIG_MEMCG static inline struct deferred_split *get_deferred_split_queue(struct page *page) { - struct mem_cgroup *memcg = compound_head(page)->mem_cgroup; + struct mem_cgroup *memcg = page_memcg(compound_head(page)); struct pglist_data *pgdat = NODE_DATA(page_to_nid(page)); if (memcg) @@ -2764,7 +2764,7 @@ void deferred_split_huge_page(struct page *page) { struct deferred_split *ds_queue = get_deferred_split_queue(page); #ifdef CONFIG_MEMCG - struct mem_cgroup *memcg = compound_head(page)->mem_cgroup; + struct mem_cgroup *memcg = page_memcg(compound_head(page)); #endif unsigned long flags; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 29459a6ce1c7..7535042ac1ec 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -533,7 +533,7 @@ struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page) { struct mem_cgroup *memcg; - memcg = page->mem_cgroup; + memcg = page_memcg(page); if (!memcg || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) memcg = root_mem_cgroup; @@ -560,16 +560,7 @@ ino_t page_cgroup_ino(struct page *page) unsigned long ino = 0; rcu_read_lock(); - memcg = page->mem_cgroup; - - /* - * The lowest bit set means that memcg isn't a valid - * memcg pointer, but a obj_cgroups pointer. - * In this case the page is shared and doesn't belong - * to any specific memory cgroup. - */ - if ((unsigned long) memcg & 0x1UL) - memcg = NULL; + memcg = page_memcg_check(page); while (memcg && !(memcg->css.flags & CSS_ONLINE)) memcg = parent_mem_cgroup(memcg); @@ -1055,7 +1046,7 @@ EXPORT_SYMBOL(get_mem_cgroup_from_mm); */ struct mem_cgroup *get_mem_cgroup_from_page(struct page *page) { - struct mem_cgroup *memcg = page->mem_cgroup; + struct mem_cgroup *memcg = page_memcg(page); if (mem_cgroup_disabled()) return NULL; @@ -1354,7 +1345,7 @@ struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgd goto out; } - memcg = page->mem_cgroup; + memcg = page_memcg(page); /* * Swapcache readahead pages are added to the LRU - and * possibly migrated - before they are charged. @@ -2114,7 +2105,7 @@ void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) } /** - * lock_page_memcg - lock a page->mem_cgroup binding + * lock_page_memcg - lock a page and memcg binding * @page: the page * * This function protects unlocked LRU pages from being moved to @@ -2146,7 +2137,7 @@ struct mem_cgroup *lock_page_memcg(struct page *page) if (mem_cgroup_disabled()) return NULL; again: - memcg = head->mem_cgroup; + memcg = page_memcg(head); if (unlikely(!memcg)) return NULL; @@ -2154,7 +2145,7 @@ again: return memcg; spin_lock_irqsave(&memcg->move_lock, flags); - if (memcg != head->mem_cgroup) { + if (memcg != page_memcg(head)) { spin_unlock_irqrestore(&memcg->move_lock, flags); goto again; } @@ -2192,14 +2183,14 @@ void __unlock_page_memcg(struct mem_cgroup *memcg) } /** - * unlock_page_memcg - unlock a page->mem_cgroup binding + * unlock_page_memcg - unlock a page and memcg binding * @page: the page */ void unlock_page_memcg(struct page *page) { struct page *head = compound_head(page); - __unlock_page_memcg(head->mem_cgroup); + __unlock_page_memcg(page_memcg(head)); } EXPORT_SYMBOL(unlock_page_memcg); @@ -2889,7 +2880,7 @@ static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages) static void commit_charge(struct page *page, struct mem_cgroup *memcg) { - VM_BUG_ON_PAGE(page->mem_cgroup, page); + VM_BUG_ON_PAGE(page_memcg(page), page); /* * Any of the following ensures page->mem_cgroup stability: * @@ -2898,7 +2889,7 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg) * - lock_page_memcg() * - exclusive reference */ - page->mem_cgroup = memcg; + page->memcg_data = (unsigned long)memcg; } #ifdef CONFIG_MEMCG_KMEM @@ -2913,8 +2904,7 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, if (!vec) return -ENOMEM; - if (cmpxchg(&page->obj_cgroups, NULL, - (struct obj_cgroup **) ((unsigned long)vec | 0x1UL))) + if (!set_page_objcgs(page, vec)) kfree(vec); else kmemleak_not_leak(vec); @@ -2925,6 +2915,12 @@ int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, /* * Returns a pointer to the memory cgroup to which the kernel object is charged. * + * A passed kernel object can be a slab object or a generic kernel page, so + * different mechanisms for getting the memory cgroup pointer should be used. + * In certain cases (e.g. kernel stacks or large kmallocs with SLUB) the caller + * can not know for sure how the kernel object is implemented. + * mem_cgroup_from_obj() can be safely used in such cases. + * * The caller must ensure the memcg lifetime, e.g. by taking rcu_read_lock(), * cgroup_mutex, etc. */ @@ -2938,35 +2934,30 @@ struct mem_cgroup *mem_cgroup_from_obj(void *p) page = virt_to_head_page(p); /* - * If page->mem_cgroup is set, it's either a simple mem_cgroup pointer - * or a pointer to obj_cgroup vector. In the latter case the lowest - * bit of the pointer is set. - * The page->mem_cgroup pointer can be asynchronously changed - * from NULL to (obj_cgroup_vec | 0x1UL), but can't be changed - * from a valid memcg pointer to objcg vector or back. - */ - if (!page->mem_cgroup) - return NULL; - - /* * Slab objects are accounted individually, not per-page. * Memcg membership data for each individual object is saved in * the page->obj_cgroups. */ - if (page_has_obj_cgroups(page)) { + if (page_objcgs_check(page)) { struct obj_cgroup *objcg; unsigned int off; off = obj_to_index(page->slab_cache, page, p); - objcg = page_obj_cgroups(page)[off]; + objcg = page_objcgs(page)[off]; if (objcg) return obj_cgroup_memcg(objcg); return NULL; } - /* All other pages use page->mem_cgroup */ - return page->mem_cgroup; + /* + * page_memcg_check() is used here, because page_has_obj_cgroups() + * check above could fail because the object cgroups vector wasn't set + * at that moment, but it can be set concurrently. + * page_memcg_check(page) will guarantee that a proper memory + * cgroup pointer or NULL will be returned. + */ + return page_memcg_check(page); } __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void) @@ -3104,8 +3095,8 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) if (memcg && !mem_cgroup_is_root(memcg)) { ret = __memcg_kmem_charge(memcg, gfp, 1 << order); if (!ret) { - page->mem_cgroup = memcg; - __SetPageKmemcg(page); + page->memcg_data = (unsigned long)memcg | + MEMCG_DATA_KMEM; return 0; } css_put(&memcg->css); @@ -3120,7 +3111,7 @@ int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) */ void __memcg_kmem_uncharge_page(struct page *page, int order) { - struct mem_cgroup *memcg = page->mem_cgroup; + struct mem_cgroup *memcg = page_memcg(page); unsigned int nr_pages = 1 << order; if (!memcg) @@ -3128,12 +3119,8 @@ void __memcg_kmem_uncharge_page(struct page *page, int order) VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page); __memcg_kmem_uncharge(memcg, nr_pages); - page->mem_cgroup = NULL; + page->memcg_data = 0; css_put(&memcg->css); - - /* slab pages do not have PageKmemcg flag set */ - if (PageKmemcg(page)) - __ClearPageKmemcg(page); } static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes) @@ -3279,7 +3266,7 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size) */ void mem_cgroup_split_huge_fixup(struct page *head) { - struct mem_cgroup *memcg = head->mem_cgroup; + struct mem_cgroup *memcg = page_memcg(head); int i; if (mem_cgroup_disabled()) @@ -3287,7 +3274,7 @@ void mem_cgroup_split_huge_fixup(struct page *head) for (i = 1; i < HPAGE_PMD_NR; i++) { css_get(&memcg->css); - head[i].mem_cgroup = memcg; + head[i].memcg_data = (unsigned long)memcg; } } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -4669,7 +4656,7 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, void mem_cgroup_track_foreign_dirty_slowpath(struct page *page, struct bdi_writeback *wb) { - struct mem_cgroup *memcg = page->mem_cgroup; + struct mem_cgroup *memcg = page_memcg(page); struct memcg_cgwb_frn *frn; u64 now = get_jiffies_64(); u64 oldest_at = now; @@ -5646,14 +5633,14 @@ static int mem_cgroup_move_account(struct page *page, /* * Prevent mem_cgroup_migrate() from looking at - * page->mem_cgroup of its source page while we change it. + * page's memory cgroup of its source page while we change it. */ ret = -EBUSY; if (!trylock_page(page)) goto out; ret = -EINVAL; - if (page->mem_cgroup != from) + if (page_memcg(page) != from) goto out_unlock; pgdat = page_pgdat(page); @@ -5708,13 +5695,13 @@ static int mem_cgroup_move_account(struct page *page, /* * All state has been migrated, let's switch to the new memcg. * - * It is safe to change page->mem_cgroup here because the page + * It is safe to change page's memcg here because the page * is referenced, charged, isolated, and locked: we can't race * with (un)charging, migration, LRU putback, or anything else - * that would rely on a stable page->mem_cgroup. + * that would rely on a stable page's memory cgroup. * * Note that lock_page_memcg is a memcg lock, not a page lock, - * to save space. As soon as we switch page->mem_cgroup to a + * to save space. As soon as we switch page's memory cgroup to a * new memcg that isn't locked, the above state can change * concurrently again. Make sure we're truly done with it. */ @@ -5723,7 +5710,7 @@ static int mem_cgroup_move_account(struct page *page, css_get(&to->css); css_put(&from->css); - page->mem_cgroup = to; + page->memcg_data = (unsigned long)to; __unlock_page_memcg(from); @@ -5789,7 +5776,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, * mem_cgroup_move_account() checks the page is valid or * not under LRU exclusion. */ - if (page->mem_cgroup == mc.from) { + if (page_memcg(page) == mc.from) { ret = MC_TARGET_PAGE; if (is_device_private_page(page)) ret = MC_TARGET_DEVICE; @@ -5833,7 +5820,7 @@ static enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma, VM_BUG_ON_PAGE(!page || !PageHead(page), page); if (!(mc.flags & MOVE_ANON)) return ret; - if (page->mem_cgroup == mc.from) { + if (page_memcg(page) == mc.from) { ret = MC_TARGET_PAGE; if (target) { get_page(page); @@ -6779,12 +6766,12 @@ int mem_cgroup_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) /* * Every swap fault against a single page tries to charge the * page, bail as early as possible. shmem_unuse() encounters - * already charged pages, too. page->mem_cgroup is protected - * by the page lock, which serializes swap cache removal, which - * in turn serializes uncharging. + * already charged pages, too. page and memcg binding is + * protected by the page lock, which serializes swap cache + * removal, which in turn serializes uncharging. */ VM_BUG_ON_PAGE(!PageLocked(page), page); - if (compound_head(page)->mem_cgroup) + if (page_memcg(compound_head(page))) goto out; id = lookup_swap_cgroup_id(ent); @@ -6868,21 +6855,21 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) VM_BUG_ON_PAGE(PageLRU(page), page); - if (!page->mem_cgroup) + if (!page_memcg(page)) return; /* * Nobody should be changing or seriously looking at - * page->mem_cgroup at this point, we have fully + * page_memcg(page) at this point, we have fully * exclusive access to the page. */ - if (ug->memcg != page->mem_cgroup) { + if (ug->memcg != page_memcg(page)) { if (ug->memcg) { uncharge_batch(ug); uncharge_gather_clear(ug); } - ug->memcg = page->mem_cgroup; + ug->memcg = page_memcg(page); /* pairs with css_put in uncharge_batch */ css_get(&ug->memcg->css); @@ -6891,15 +6878,13 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug) nr_pages = compound_nr(page); ug->nr_pages += nr_pages; - if (!PageKmemcg(page)) { - ug->pgpgout++; - } else { + if (PageMemcgKmem(page)) ug->nr_kmem += nr_pages; - __ClearPageKmemcg(page); - } + else + ug->pgpgout++; ug->dummy_page = page; - page->mem_cgroup = NULL; + page->memcg_data = 0; css_put(&ug->memcg->css); } @@ -6942,7 +6927,7 @@ void mem_cgroup_uncharge(struct page *page) return; /* Don't touch page->lru of any random page, pre-check: */ - if (!page->mem_cgroup) + if (!page_memcg(page)) return; uncharge_gather_clear(&ug); @@ -6992,11 +6977,11 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage) return; /* Page cache replacement: new page already charged? */ - if (newpage->mem_cgroup) + if (page_memcg(newpage)) return; /* Swapcache readahead pages can get replaced before being charged */ - memcg = oldpage->mem_cgroup; + memcg = page_memcg(oldpage); if (!memcg) return; @@ -7191,7 +7176,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return; - memcg = page->mem_cgroup; + memcg = page_memcg(page); /* Readahead page, never charged */ if (!memcg) @@ -7212,7 +7197,7 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) VM_BUG_ON_PAGE(oldid, page); mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries); - page->mem_cgroup = NULL; + page->memcg_data = 0; if (!mem_cgroup_is_root(memcg)) page_counter_uncharge(&memcg->memory, nr_entries); @@ -7255,7 +7240,7 @@ int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) return 0; - memcg = page->mem_cgroup; + memcg = page_memcg(page); /* Readahead page, never charged */ if (!memcg) @@ -7336,7 +7321,7 @@ bool mem_cgroup_swap_full(struct page *page) if (cgroup_memory_noswap || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) return false; - memcg = page->mem_cgroup; + memcg = page_memcg(page); if (!memcg) return false; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index eaa227a479e4..ad423950d01c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1092,7 +1092,7 @@ static inline bool page_expected_state(struct page *page, if (unlikely((unsigned long)page->mapping | page_ref_count(page) | #ifdef CONFIG_MEMCG - (unsigned long)page->mem_cgroup | + (unsigned long)page_memcg(page) | #endif (page->flags & check_flags))) return false; @@ -1117,7 +1117,7 @@ static const char *page_bad_reason(struct page *page, unsigned long flags) bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set"; } #ifdef CONFIG_MEMCG - if (unlikely(page->mem_cgroup)) + if (unlikely(page_memcg(page))) bad_reason = "page still charged to cgroup"; #endif return bad_reason; @@ -1214,7 +1214,7 @@ static __always_inline bool free_pages_prepare(struct page *page, * Do not let hwpoison pages hit pcplists/buddy * Untie memcg state and reset page's owner */ - if (memcg_kmem_enabled() && PageKmemcg(page)) + if (memcg_kmem_enabled() && PageMemcgKmem(page)) __memcg_kmem_uncharge_page(page, order); reset_page_owner(page, order); return false; @@ -1244,7 +1244,7 @@ static __always_inline bool free_pages_prepare(struct page *page, } if (PageMappingFlags(page)) page->mapping = NULL; - if (memcg_kmem_enabled() && PageKmemcg(page)) + if (memcg_kmem_enabled() && PageMemcgKmem(page)) __memcg_kmem_uncharge_page(page, order); if (check_free) bad += check_free_page(page); diff --git a/mm/page_io.c b/mm/page_io.c index 433df1263349..9bca17ecc4df 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -291,12 +291,14 @@ static inline void count_swpout_vm_event(struct page *page) static void bio_associate_blkg_from_page(struct bio *bio, struct page *page) { struct cgroup_subsys_state *css; + struct mem_cgroup *memcg; - if (!page->mem_cgroup) + memcg = page_memcg(page); + if (!memcg) return; rcu_read_lock(); - css = cgroup_e_css(page->mem_cgroup->css.cgroup, &io_cgrp_subsys); + css = cgroup_e_css(memcg->css.cgroup, &io_cgrp_subsys); bio_associate_blkg_from_css(bio, css); rcu_read_unlock(); } diff --git a/mm/slab.h b/mm/slab.h index 6d7c6a5056ba..9a54a0cb5cca 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -239,30 +239,13 @@ static inline bool kmem_cache_debug_flags(struct kmem_cache *s, slab_flags_t fla } #ifdef CONFIG_MEMCG_KMEM -static inline struct obj_cgroup **page_obj_cgroups(struct page *page) -{ - /* - * page->mem_cgroup and page->obj_cgroups are sharing the same - * space. To distinguish between them in case we don't know for sure - * that the page is a slab page (e.g. page_cgroup_ino()), let's - * always set the lowest bit of obj_cgroups. - */ - return (struct obj_cgroup **) - ((unsigned long)page->obj_cgroups & ~0x1UL); -} - -static inline bool page_has_obj_cgroups(struct page *page) -{ - return ((unsigned long)page->obj_cgroups & 0x1UL); -} - int memcg_alloc_page_obj_cgroups(struct page *page, struct kmem_cache *s, gfp_t gfp); static inline void memcg_free_page_obj_cgroups(struct page *page) { - kfree(page_obj_cgroups(page)); - page->obj_cgroups = NULL; + kfree(page_objcgs(page)); + page->memcg_data = 0; } static inline size_t obj_full_size(struct kmem_cache *s) @@ -323,7 +306,7 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, if (likely(p[i])) { page = virt_to_head_page(p[i]); - if (!page_has_obj_cgroups(page) && + if (!page_objcgs(page) && memcg_alloc_page_obj_cgroups(page, s, flags)) { obj_cgroup_uncharge(objcg, obj_full_size(s)); continue; @@ -331,7 +314,7 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, off = obj_to_index(s, page, p[i]); obj_cgroup_get(objcg); - page_obj_cgroups(page)[off] = objcg; + page_objcgs(page)[off] = objcg; mod_objcg_state(objcg, page_pgdat(page), cache_vmstat_idx(s), obj_full_size(s)); } else { @@ -345,6 +328,7 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s_orig, void **p, int objects) { struct kmem_cache *s; + struct obj_cgroup **objcgs; struct obj_cgroup *objcg; struct page *page; unsigned int off; @@ -358,7 +342,8 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s_orig, continue; page = virt_to_head_page(p[i]); - if (!page_has_obj_cgroups(page)) + objcgs = page_objcgs(page); + if (!objcgs) continue; if (!s_orig) @@ -367,11 +352,11 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s_orig, s = s_orig; off = obj_to_index(s, page, p[i]); - objcg = page_obj_cgroups(page)[off]; + objcg = objcgs[off]; if (!objcg) continue; - page_obj_cgroups(page)[off] = NULL; + objcgs[off] = NULL; obj_cgroup_uncharge(objcg, obj_full_size(s)); mod_objcg_state(objcg, page_pgdat(page), cache_vmstat_idx(s), -obj_full_size(s)); @@ -380,11 +365,6 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s_orig, } #else /* CONFIG_MEMCG_KMEM */ -static inline bool page_has_obj_cgroups(struct page *page) -{ - return false; -} - static inline struct mem_cgroup *memcg_from_slab_obj(void *ptr) { return NULL; diff --git a/mm/workingset.c b/mm/workingset.c index 975a4d2dd02e..130348cbf40a 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -257,7 +257,7 @@ void *workingset_eviction(struct page *page, struct mem_cgroup *target_memcg) struct lruvec *lruvec; int memcgid; - /* Page is fully exclusive and pins page->mem_cgroup */ + /* Page is fully exclusive and pins page's memory cgroup pointer */ VM_BUG_ON_PAGE(PageLRU(page), page); VM_BUG_ON_PAGE(page_count(page), page); VM_BUG_ON_PAGE(!PageLocked(page), page); diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index 359908a7d3c1..a32037daa933 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -415,7 +415,7 @@ static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog) BPF_CALL_4(bpf_sk_storage_get_tracing, struct bpf_map *, map, struct sock *, sk, void *, value, u64, flags) { - if (!in_serving_softirq() && !in_task()) + if (in_irq() || in_nmi()) return (unsigned long)NULL; return (unsigned long)____bpf_sk_storage_get(map, sk, value, flags); @@ -424,7 +424,7 @@ BPF_CALL_4(bpf_sk_storage_get_tracing, struct bpf_map *, map, struct sock *, sk, BPF_CALL_2(bpf_sk_storage_delete_tracing, struct bpf_map *, map, struct sock *, sk) { - if (!in_serving_softirq() && !in_task()) + if (in_irq() || in_nmi()) return -EPERM; return ____bpf_sk_storage_delete(map, sk); diff --git a/net/core/dev.c b/net/core/dev.c index e3f998d5c15c..ce8fea2e2788 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6448,7 +6448,8 @@ bool napi_complete_done(struct napi_struct *n, int work_done) WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED)); - new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED); + new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED | + NAPIF_STATE_PREFER_BUSY_POLL); /* If STATE_MISSED was set, leave STATE_SCHED set, * because we will call napi->poll() one more time. @@ -6485,10 +6486,30 @@ static struct napi_struct *napi_by_id(unsigned int napi_id) #if defined(CONFIG_NET_RX_BUSY_POLL) -#define BUSY_POLL_BUDGET 8 +static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule) +{ + if (!skip_schedule) { + gro_normal_list(napi); + __napi_schedule(napi); + return; + } + + if (napi->gro_bitmask) { + /* flush too old packets + * If HZ < 1000, flush all packets. + */ + napi_gro_flush(napi, HZ >= 1000); + } -static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock) + gro_normal_list(napi); + clear_bit(NAPI_STATE_SCHED, &napi->state); +} + +static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool prefer_busy_poll, + u16 budget) { + bool skip_schedule = false; + unsigned long timeout; int rc; /* Busy polling means there is a high chance device driver hard irq @@ -6505,29 +6526,33 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock) local_bh_disable(); + if (prefer_busy_poll) { + napi->defer_hard_irqs_count = READ_ONCE(napi->dev->napi_defer_hard_irqs); + timeout = READ_ONCE(napi->dev->gro_flush_timeout); + if (napi->defer_hard_irqs_count && timeout) { + hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED); + skip_schedule = true; + } + } + /* All we really want here is to re-enable device interrupts. * Ideally, a new ndo_busy_poll_stop() could avoid another round. */ - rc = napi->poll(napi, BUSY_POLL_BUDGET); + rc = napi->poll(napi, budget); /* We can't gro_normal_list() here, because napi->poll() might have * rearmed the napi (napi_complete_done()) in which case it could * already be running on another CPU. */ - trace_napi_poll(napi, rc, BUSY_POLL_BUDGET); + trace_napi_poll(napi, rc, budget); netpoll_poll_unlock(have_poll_lock); - if (rc == BUSY_POLL_BUDGET) { - /* As the whole budget was spent, we still own the napi so can - * safely handle the rx_list. - */ - gro_normal_list(napi); - __napi_schedule(napi); - } + if (rc == budget) + __busy_poll_stop(napi, skip_schedule); local_bh_enable(); } void napi_busy_loop(unsigned int napi_id, bool (*loop_end)(void *, unsigned long), - void *loop_end_arg) + void *loop_end_arg, bool prefer_busy_poll, u16 budget) { unsigned long start_time = loop_end ? busy_loop_current_time() : 0; int (*napi_poll)(struct napi_struct *napi, int budget); @@ -6555,17 +6580,23 @@ restart: * we avoid dirtying napi->state as much as we can. */ if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED | - NAPIF_STATE_IN_BUSY_POLL)) + NAPIF_STATE_IN_BUSY_POLL)) { + if (prefer_busy_poll) + set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); goto count; + } if (cmpxchg(&napi->state, val, val | NAPIF_STATE_IN_BUSY_POLL | - NAPIF_STATE_SCHED) != val) + NAPIF_STATE_SCHED) != val) { + if (prefer_busy_poll) + set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); goto count; + } have_poll_lock = netpoll_poll_lock(napi); napi_poll = napi->poll; } - work = napi_poll(napi, BUSY_POLL_BUDGET); - trace_napi_poll(napi, work, BUSY_POLL_BUDGET); + work = napi_poll(napi, budget); + trace_napi_poll(napi, work, budget); gro_normal_list(napi); count: if (work > 0) @@ -6578,7 +6609,7 @@ count: if (unlikely(need_resched())) { if (napi_poll) - busy_poll_stop(napi, have_poll_lock); + busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget); preempt_enable(); rcu_read_unlock(); cond_resched(); @@ -6589,7 +6620,7 @@ count: cpu_relax(); } if (napi_poll) - busy_poll_stop(napi, have_poll_lock); + busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget); preempt_enable(); out: rcu_read_unlock(); @@ -6640,8 +6671,10 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) * NAPI_STATE_MISSED, since we do not react to a device IRQ. */ if (!napi_disable_pending(napi) && - !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) + !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) { + clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state); __napi_schedule_irqoff(napi); + } return HRTIMER_NORESTART; } @@ -6699,6 +6732,7 @@ void napi_disable(struct napi_struct *n) hrtimer_cancel(&n->timer); + clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state); clear_bit(NAPI_STATE_DISABLE, &n->state); } EXPORT_SYMBOL(napi_disable); @@ -6771,6 +6805,19 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) goto out_unlock; } + /* The NAPI context has more processing work, but busy-polling + * is preferred. Exit early. + */ + if (napi_prefer_busy_poll(n)) { + if (napi_complete_done(n, work)) { + /* If timeout is not set, we need to make sure + * that the NAPI is re-scheduled. + */ + napi_schedule(n); + } + goto out_unlock; + } + if (n->gro_bitmask) { /* flush too old packets * If HZ < 1000, flush all packets. @@ -9753,7 +9800,7 @@ static int netif_alloc_rx_queues(struct net_device *dev) rx[i].dev = dev; /* XDP RX-queue setup */ - err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i); + err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i, 0); if (err < 0) goto err_rxq_info; } diff --git a/net/core/filter.c b/net/core/filter.c index 2ca5eecebacf..77001a35768f 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4910,6 +4910,9 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, tp->notsent_lowat = val; sk->sk_write_space(sk); break; + case TCP_WINDOW_CLAMP: + ret = tcp_set_window_clamp(sk, val); + break; default: ret = -EINVAL; } @@ -6995,6 +6998,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sk_storage_delete_proto; case BPF_FUNC_setsockopt: switch (prog->expected_attach_type) { + case BPF_CGROUP_INET4_BIND: + case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: return &bpf_sock_addr_setsockopt_proto; @@ -7003,6 +7008,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) } case BPF_FUNC_getsockopt: switch (prog->expected_attach_type) { + case BPF_CGROUP_INET4_BIND: + case BPF_CGROUP_INET6_BIND: case BPF_CGROUP_INET4_CONNECT: case BPF_CGROUP_INET6_CONNECT: return &bpf_sock_addr_getsockopt_proto; diff --git a/net/core/sock.c b/net/core/sock.c index f0f096852876..4fd7e785f177 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1159,6 +1159,22 @@ set_sndbuf: sk->sk_ll_usec = val; } break; + case SO_PREFER_BUSY_POLL: + if (valbool && !capable(CAP_NET_ADMIN)) + ret = -EPERM; + else + WRITE_ONCE(sk->sk_prefer_busy_poll, valbool); + break; + case SO_BUSY_POLL_BUDGET: + if (val > READ_ONCE(sk->sk_busy_poll_budget) && !capable(CAP_NET_ADMIN)) { + ret = -EPERM; + } else { + if (val < 0 || val > U16_MAX) + ret = -EINVAL; + else + WRITE_ONCE(sk->sk_busy_poll_budget, val); + } + break; #endif case SO_MAX_PACING_RATE: @@ -1523,6 +1539,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname, case SO_BUSY_POLL: v.val = sk->sk_ll_usec; break; + case SO_PREFER_BUSY_POLL: + v.val = READ_ONCE(sk->sk_prefer_busy_poll); + break; #endif case SO_MAX_PACING_RATE: diff --git a/net/core/sock_map.c b/net/core/sock_map.c index ddc899e83313..64b5ec14ff50 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -27,8 +27,6 @@ struct bpf_stab { static struct bpf_map *sock_map_alloc(union bpf_attr *attr) { struct bpf_stab *stab; - u64 cost; - int err; if (!capable(CAP_NET_ADMIN)) return ERR_PTR(-EPERM); @@ -39,29 +37,22 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr) attr->map_flags & ~SOCK_CREATE_FLAG_MASK) return ERR_PTR(-EINVAL); - stab = kzalloc(sizeof(*stab), GFP_USER); + stab = kzalloc(sizeof(*stab), GFP_USER | __GFP_ACCOUNT); if (!stab) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&stab->map, attr); raw_spin_lock_init(&stab->lock); - /* Make sure page count doesn't overflow. */ - cost = (u64) stab->map.max_entries * sizeof(struct sock *); - err = bpf_map_charge_init(&stab->map.memory, cost); - if (err) - goto free_stab; - stab->sks = bpf_map_area_alloc(stab->map.max_entries * sizeof(struct sock *), stab->map.numa_node); - if (stab->sks) - return &stab->map; - err = -ENOMEM; - bpf_map_charge_finish(&stab->map.memory); -free_stab: - kfree(stab); - return ERR_PTR(err); + if (!stab->sks) { + kfree(stab); + return ERR_PTR(-ENOMEM); + } + + return &stab->map; } int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog) @@ -975,8 +966,9 @@ static struct bpf_shtab_elem *sock_hash_alloc_elem(struct bpf_shtab *htab, } } - new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, - htab->map.numa_node); + new = bpf_map_kmalloc_node(&htab->map, htab->elem_size, + GFP_ATOMIC | __GFP_NOWARN, + htab->map.numa_node); if (!new) { atomic_dec(&htab->count); return ERR_PTR(-ENOMEM); @@ -1103,7 +1095,6 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr) { struct bpf_shtab *htab; int i, err; - u64 cost; if (!capable(CAP_NET_ADMIN)) return ERR_PTR(-EPERM); @@ -1116,7 +1107,7 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr) if (attr->key_size > MAX_BPF_STACK) return ERR_PTR(-E2BIG); - htab = kzalloc(sizeof(*htab), GFP_USER); + htab = kzalloc(sizeof(*htab), GFP_USER | __GFP_ACCOUNT); if (!htab) return ERR_PTR(-ENOMEM); @@ -1131,21 +1122,10 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr) goto free_htab; } - cost = (u64) htab->buckets_num * sizeof(struct bpf_shtab_bucket) + - (u64) htab->elem_size * htab->map.max_entries; - if (cost >= U32_MAX - PAGE_SIZE) { - err = -EINVAL; - goto free_htab; - } - err = bpf_map_charge_init(&htab->map.memory, cost); - if (err) - goto free_htab; - htab->buckets = bpf_map_area_alloc(htab->buckets_num * sizeof(struct bpf_shtab_bucket), htab->map.numa_node); if (!htab->buckets) { - bpf_map_charge_finish(&htab->map.memory); err = -ENOMEM; goto free_htab; } diff --git a/net/core/xdp.c b/net/core/xdp.c index 3d330ebda893..17ffd33c6b18 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -158,7 +158,7 @@ static void xdp_rxq_info_init(struct xdp_rxq_info *xdp_rxq) /* Returns 0 on success, negative on failure */ int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, - struct net_device *dev, u32 queue_index) + struct net_device *dev, u32 queue_index, unsigned int napi_id) { if (xdp_rxq->reg_state == REG_STATE_UNUSED) { WARN(1, "Driver promised not to register this"); @@ -179,6 +179,7 @@ int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, xdp_rxq_info_init(xdp_rxq); xdp_rxq->dev = dev; xdp_rxq->queue_index = queue_index; + xdp_rxq->napi_id = napi_id; xdp_rxq->reg_state = REG_STATE_REGISTERED; return 0; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index b7260c8cef2e..b94fa8eb831b 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -450,7 +450,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) /* BPF prog is run before any checks are done so that if the prog * changes context in a wrong way it will be caught. */ - err = BPF_CGROUP_RUN_PROG_INET4_BIND(sk, uaddr); + err = BPF_CGROUP_RUN_PROG_INET4_BIND_LOCK(sk, uaddr); if (err) return err; diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c index 618954f82764..d520e61649c8 100644 --- a/net/ipv4/bpf_tcp_ca.c +++ b/net/ipv4/bpf_tcp_ca.c @@ -95,6 +95,7 @@ static bool bpf_tcp_ca_is_valid_access(int off, int size, } static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log, + const struct btf *btf, const struct btf_type *t, int off, int size, enum bpf_access_type atype, u32 *next_btf_id) @@ -102,7 +103,7 @@ static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log, size_t end; if (atype == BPF_READ) - return btf_struct_access(log, t, off, size, atype, next_btf_id); + return btf_struct_access(log, btf, t, off, size, atype, next_btf_id); if (t != tcp_sock_type) { bpf_log(log, "only read is supported\n"); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b285b338a019..75a28b8f4470 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3042,6 +3042,21 @@ int tcp_sock_set_keepcnt(struct sock *sk, int val) } EXPORT_SYMBOL(tcp_sock_set_keepcnt); +int tcp_set_window_clamp(struct sock *sk, int val) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (!val) { + if (sk->sk_state != TCP_CLOSE) + return -EINVAL; + tp->window_clamp = 0; + } else { + tp->window_clamp = val < SOCK_MIN_RCVBUF / 2 ? + SOCK_MIN_RCVBUF / 2 : val; + } + return 0; +} + /* * Socket option code for TCP. */ @@ -3255,15 +3270,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname, break; case TCP_WINDOW_CLAMP: - if (!val) { - if (sk->sk_state != TCP_CLOSE) { - err = -EINVAL; - break; - } - tp->window_clamp = 0; - } else - tp->window_clamp = val < SOCK_MIN_RCVBUF / 2 ? - SOCK_MIN_RCVBUF / 2 : val; + err = tcp_set_window_clamp(sk, val); break; case TCP_QUICKACK: diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index e648fbebb167..a7e3d170af51 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -451,7 +451,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) /* BPF prog is run before any checks are done so that if the prog * changes context in a wrong way it will be caught. */ - err = BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr); + err = BPF_CGROUP_RUN_PROG_INET6_BIND_LOCK(sk, uaddr); if (err) return err; diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index b7b039bd9d03..56c46e5f57bc 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -23,6 +23,7 @@ #include <linux/netdevice.h> #include <linux/rculist.h> #include <net/xdp_sock_drv.h> +#include <net/busy_poll.h> #include <net/xdp.h> #include "xsk_queue.h" @@ -232,6 +233,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index) return -EINVAL; + sk_mark_napi_id_once_xdp(&xs->sk, xdp); len = xdp->data_end - xdp->data; return xdp->rxq->mem.type == MEM_TYPE_XSK_BUFF_POOL ? @@ -332,6 +334,63 @@ out: } EXPORT_SYMBOL(xsk_tx_peek_desc); +static u32 xsk_tx_peek_release_fallback(struct xsk_buff_pool *pool, struct xdp_desc *descs, + u32 max_entries) +{ + u32 nb_pkts = 0; + + while (nb_pkts < max_entries && xsk_tx_peek_desc(pool, &descs[nb_pkts])) + nb_pkts++; + + xsk_tx_release(pool); + return nb_pkts; +} + +u32 xsk_tx_peek_release_desc_batch(struct xsk_buff_pool *pool, struct xdp_desc *descs, + u32 max_entries) +{ + struct xdp_sock *xs; + u32 nb_pkts; + + rcu_read_lock(); + if (!list_is_singular(&pool->xsk_tx_list)) { + /* Fallback to the non-batched version */ + rcu_read_unlock(); + return xsk_tx_peek_release_fallback(pool, descs, max_entries); + } + + xs = list_first_or_null_rcu(&pool->xsk_tx_list, struct xdp_sock, tx_list); + if (!xs) { + nb_pkts = 0; + goto out; + } + + nb_pkts = xskq_cons_peek_desc_batch(xs->tx, descs, pool, max_entries); + if (!nb_pkts) { + xs->tx->queue_empty_descs++; + goto out; + } + + /* This is the backpressure mechanism for the Tx path. Try to + * reserve space in the completion queue for all packets, but + * if there are fewer slots available, just process that many + * packets. This avoids having to implement any buffering in + * the Tx path. + */ + nb_pkts = xskq_prod_reserve_addr_batch(pool->cq, descs, nb_pkts); + if (!nb_pkts) + goto out; + + xskq_cons_release_n(xs->tx, nb_pkts); + __xskq_cons_release(xs->tx); + xs->sk.sk_write_space(&xs->sk); + +out: + rcu_read_unlock(); + return nb_pkts; +} +EXPORT_SYMBOL(xsk_tx_peek_release_desc_batch); + static int xsk_wakeup(struct xdp_sock *xs, u8 flags) { struct net_device *dev = xs->dev; @@ -454,18 +513,65 @@ static int __xsk_sendmsg(struct sock *sk) return xs->zc ? xsk_zc_xmit(xs) : xsk_generic_xmit(sk); } +static bool xsk_no_wakeup(struct sock *sk) +{ +#ifdef CONFIG_NET_RX_BUSY_POLL + /* Prefer busy-polling, skip the wakeup. */ + return READ_ONCE(sk->sk_prefer_busy_poll) && READ_ONCE(sk->sk_ll_usec) && + READ_ONCE(sk->sk_napi_id) >= MIN_NAPI_ID; +#else + return false; +#endif +} + static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) { bool need_wait = !(m->msg_flags & MSG_DONTWAIT); struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); + struct xsk_buff_pool *pool; if (unlikely(!xsk_is_bound(xs))) return -ENXIO; if (unlikely(need_wait)) return -EOPNOTSUPP; - return __xsk_sendmsg(sk); + if (sk_can_busy_loop(sk)) + sk_busy_loop(sk, 1); /* only support non-blocking sockets */ + + if (xsk_no_wakeup(sk)) + return 0; + + pool = xs->pool; + if (pool->cached_need_wakeup & XDP_WAKEUP_TX) + return __xsk_sendmsg(sk); + return 0; +} + +static int xsk_recvmsg(struct socket *sock, struct msghdr *m, size_t len, int flags) +{ + bool need_wait = !(flags & MSG_DONTWAIT); + struct sock *sk = sock->sk; + struct xdp_sock *xs = xdp_sk(sk); + + if (unlikely(!(xs->dev->flags & IFF_UP))) + return -ENETDOWN; + if (unlikely(!xs->rx)) + return -ENOBUFS; + if (unlikely(!xsk_is_bound(xs))) + return -ENXIO; + if (unlikely(need_wait)) + return -EOPNOTSUPP; + + if (sk_can_busy_loop(sk)) + sk_busy_loop(sk, 1); /* only support non-blocking sockets */ + + if (xsk_no_wakeup(sk)) + return 0; + + if (xs->pool->cached_need_wakeup & XDP_WAKEUP_RX && xs->zc) + return xsk_wakeup(xs, XDP_WAKEUP_RX); + return 0; } static __poll_t xsk_poll(struct file *file, struct socket *sock, @@ -542,7 +648,7 @@ static struct xsk_map *xsk_get_map_list_entry(struct xdp_sock *xs, node = list_first_entry_or_null(&xs->map_list, struct xsk_map_node, node); if (node) { - WARN_ON(xsk_map_inc(node->map)); + bpf_map_inc(&node->map->map); map = node->map; *map_entry = node->map_entry; } @@ -572,7 +678,7 @@ static void xsk_delete_from_maps(struct xdp_sock *xs) while ((map = xsk_get_map_list_entry(xs, &map_entry))) { xsk_map_try_sock_delete(map, xs, map_entry); - xsk_map_put(map); + bpf_map_put(&map->map); } } @@ -1128,7 +1234,7 @@ static const struct proto_ops xsk_proto_ops = { .setsockopt = xsk_setsockopt, .getsockopt = xsk_getsockopt, .sendmsg = xsk_sendmsg, - .recvmsg = sock_no_recvmsg, + .recvmsg = xsk_recvmsg, .mmap = xsk_mmap, .sendpage = sock_no_sendpage, }; diff --git a/net/xdp/xsk.h b/net/xdp/xsk.h index b9e896cee5bb..edcf249ad1f1 100644 --- a/net/xdp/xsk.h +++ b/net/xdp/xsk.h @@ -41,8 +41,6 @@ static inline struct xdp_sock *xdp_sk(struct sock *sk) void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, struct xdp_sock **map_entry); -int xsk_map_inc(struct xsk_map *map); -void xsk_map_put(struct xsk_map *map); void xsk_clear_pool_at_qid(struct net_device *dev, u16 queue_id); int xsk_reg_pool_at_qid(struct net_device *dev, struct xsk_buff_pool *pool, u16 queue_id); diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 9287eddec52c..556d82d03687 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -144,14 +144,13 @@ static int __xp_assign_dev(struct xsk_buff_pool *pool, if (err) return err; - if (flags & XDP_USE_NEED_WAKEUP) { + if (flags & XDP_USE_NEED_WAKEUP) pool->uses_need_wakeup = true; - /* Tx needs to be explicitly woken up the first time. - * Also for supporting drivers that do not implement this - * feature. They will always have to call sendto(). - */ - pool->cached_need_wakeup = XDP_WAKEUP_TX; - } + /* Tx needs to be explicitly woken up the first time. Also + * for supporting drivers that do not implement this + * feature. They will always have to call sendto() or poll(). + */ + pool->cached_need_wakeup = XDP_WAKEUP_TX; dev_hold(netdev); diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index cdb9cf3cd136..b936c46b1e16 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -18,9 +18,11 @@ struct xdp_ring { /* Hinder the adjacent cache prefetcher to prefetch the consumer * pointer if the producer pointer is touched and vice versa. */ - u32 pad ____cacheline_aligned_in_smp; + u32 pad1 ____cacheline_aligned_in_smp; u32 consumer ____cacheline_aligned_in_smp; + u32 pad2 ____cacheline_aligned_in_smp; u32 flags; + u32 pad3 ____cacheline_aligned_in_smp; }; /* Used for the RX and TX queues for packets */ @@ -197,6 +199,30 @@ static inline bool xskq_cons_read_desc(struct xsk_queue *q, return false; } +static inline u32 xskq_cons_read_desc_batch(struct xsk_queue *q, + struct xdp_desc *descs, + struct xsk_buff_pool *pool, u32 max) +{ + u32 cached_cons = q->cached_cons, nb_entries = 0; + + while (cached_cons != q->cached_prod && nb_entries < max) { + struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; + u32 idx = cached_cons & q->ring_mask; + + descs[nb_entries] = ring->desc[idx]; + if (unlikely(!xskq_cons_is_valid_desc(q, &descs[nb_entries], pool))) { + /* Skip the entry */ + cached_cons++; + continue; + } + + nb_entries++; + cached_cons++; + } + + return nb_entries; +} + /* Functions for consumers */ static inline void __xskq_cons_release(struct xsk_queue *q) @@ -218,17 +244,22 @@ static inline void xskq_cons_get_entries(struct xsk_queue *q) __xskq_cons_peek(q); } -static inline bool xskq_cons_has_entries(struct xsk_queue *q, u32 cnt) +static inline u32 xskq_cons_nb_entries(struct xsk_queue *q, u32 max) { u32 entries = q->cached_prod - q->cached_cons; - if (entries >= cnt) - return true; + if (entries >= max) + return max; __xskq_cons_peek(q); entries = q->cached_prod - q->cached_cons; - return entries >= cnt; + return entries >= max ? max : entries; +} + +static inline bool xskq_cons_has_entries(struct xsk_queue *q, u32 cnt) +{ + return xskq_cons_nb_entries(q, cnt) >= cnt ? true : false; } static inline bool xskq_cons_peek_addr_unchecked(struct xsk_queue *q, u64 *addr) @@ -247,16 +278,28 @@ static inline bool xskq_cons_peek_desc(struct xsk_queue *q, return xskq_cons_read_desc(q, desc, pool); } +static inline u32 xskq_cons_peek_desc_batch(struct xsk_queue *q, struct xdp_desc *descs, + struct xsk_buff_pool *pool, u32 max) +{ + u32 entries = xskq_cons_nb_entries(q, max); + + return xskq_cons_read_desc_batch(q, descs, pool, entries); +} + +/* To improve performance in the xskq_cons_release functions, only update local state here. + * Reflect this to global state when we get new entries from the ring in + * xskq_cons_get_entries() and whenever Rx or Tx processing are completed in the NAPI loop. + */ static inline void xskq_cons_release(struct xsk_queue *q) { - /* To improve performance, only update local state here. - * Reflect this to global state when we get new entries - * from the ring in xskq_cons_get_entries() and whenever - * Rx or Tx processing are completed in the NAPI loop. - */ q->cached_cons++; } +static inline void xskq_cons_release_n(struct xsk_queue *q, u32 cnt) +{ + q->cached_cons += cnt; +} + static inline bool xskq_cons_is_full(struct xsk_queue *q) { /* No barriers needed since data is not accessed */ @@ -266,18 +309,23 @@ static inline bool xskq_cons_is_full(struct xsk_queue *q) /* Functions for producers */ -static inline bool xskq_prod_is_full(struct xsk_queue *q) +static inline u32 xskq_prod_nb_free(struct xsk_queue *q, u32 max) { u32 free_entries = q->nentries - (q->cached_prod - q->cached_cons); - if (free_entries) - return false; + if (free_entries >= max) + return max; /* Refresh the local tail pointer */ q->cached_cons = READ_ONCE(q->ring->consumer); free_entries = q->nentries - (q->cached_prod - q->cached_cons); - return !free_entries; + return free_entries >= max ? max : free_entries; +} + +static inline bool xskq_prod_is_full(struct xsk_queue *q) +{ + return xskq_prod_nb_free(q, 1) ? false : true; } static inline int xskq_prod_reserve(struct xsk_queue *q) @@ -302,6 +350,23 @@ static inline int xskq_prod_reserve_addr(struct xsk_queue *q, u64 addr) return 0; } +static inline u32 xskq_prod_reserve_addr_batch(struct xsk_queue *q, struct xdp_desc *descs, + u32 max) +{ + struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; + u32 nb_entries, i, cached_prod; + + nb_entries = xskq_prod_nb_free(q, max); + + /* A, matches D */ + cached_prod = q->cached_prod; + for (i = 0; i < nb_entries; i++) + ring->desc[cached_prod++ & q->ring_mask] = descs[i].addr; + q->cached_prod = cached_prod; + + return nb_entries; +} + static inline int xskq_prod_reserve_desc(struct xsk_queue *q, u64 addr, u32 len) { diff --git a/net/xdp/xskmap.c b/net/xdp/xskmap.c index 49da2b8ace8b..113fd9017203 100644 --- a/net/xdp/xskmap.c +++ b/net/xdp/xskmap.c @@ -11,32 +11,17 @@ #include "xsk.h" -int xsk_map_inc(struct xsk_map *map) -{ - bpf_map_inc(&map->map); - return 0; -} - -void xsk_map_put(struct xsk_map *map) -{ - bpf_map_put(&map->map); -} - static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map, struct xdp_sock **map_entry) { struct xsk_map_node *node; - int err; - node = kzalloc(sizeof(*node), GFP_ATOMIC | __GFP_NOWARN); + node = bpf_map_kzalloc(&map->map, sizeof(*node), + GFP_ATOMIC | __GFP_NOWARN); if (!node) return ERR_PTR(-ENOMEM); - err = xsk_map_inc(map); - if (err) { - kfree(node); - return ERR_PTR(err); - } + bpf_map_inc(&map->map); node->map = map; node->map_entry = map_entry; @@ -45,7 +30,7 @@ static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map, static void xsk_map_node_free(struct xsk_map_node *node) { - xsk_map_put(node->map); + bpf_map_put(&node->map->map); kfree(node); } @@ -73,9 +58,8 @@ static void xsk_map_sock_delete(struct xdp_sock *xs, static struct bpf_map *xsk_map_alloc(union bpf_attr *attr) { - struct bpf_map_memory mem; - int err, numa_node; struct xsk_map *m; + int numa_node; u64 size; if (!capable(CAP_NET_ADMIN)) @@ -89,18 +73,11 @@ static struct bpf_map *xsk_map_alloc(union bpf_attr *attr) numa_node = bpf_map_attr_numa_node(attr); size = struct_size(m, xsk_map, attr->max_entries); - err = bpf_map_charge_init(&mem, size); - if (err < 0) - return ERR_PTR(err); - m = bpf_map_area_alloc(size, numa_node); - if (!m) { - bpf_map_charge_finish(&mem); + if (!m) return ERR_PTR(-ENOMEM); - } bpf_map_init_from_attr(&m->map, attr); - bpf_map_charge_move(&m->map.memory, &mem); spin_lock_init(&m->lock); return &m->map; diff --git a/samples/bpf/.gitignore b/samples/bpf/.gitignore index b2f29bc8dc43..0b9548ea8477 100644 --- a/samples/bpf/.gitignore +++ b/samples/bpf/.gitignore @@ -52,3 +52,6 @@ xdp_tx_iptunnel xdpsock xsk_fwd testfile.img +hbm_out.log +iperf.* +*.out diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index aeebf5d12f32..26fc96ca619e 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -48,6 +48,7 @@ tprogs-y += syscall_tp tprogs-y += cpustat tprogs-y += xdp_adjust_tail tprogs-y += xdpsock +tprogs-y += xdpsock_ctrl_proc tprogs-y += xsk_fwd tprogs-y += xdp_fwd tprogs-y += task_fd_query @@ -73,16 +74,16 @@ tracex5-objs := tracex5_user.o $(TRACE_HELPERS) tracex6-objs := tracex6_user.o tracex7-objs := tracex7_user.o test_probe_write_user-objs := test_probe_write_user_user.o -trace_output-objs := trace_output_user.o $(TRACE_HELPERS) +trace_output-objs := trace_output_user.o lathist-objs := lathist_user.o offwaketime-objs := offwaketime_user.o $(TRACE_HELPERS) spintest-objs := spintest_user.o $(TRACE_HELPERS) map_perf_test-objs := map_perf_test_user.o -test_overhead-objs := bpf_load.o test_overhead_user.o +test_overhead-objs := test_overhead_user.o test_cgrp2_array_pin-objs := test_cgrp2_array_pin.o test_cgrp2_attach-objs := test_cgrp2_attach.o test_cgrp2_sock-objs := test_cgrp2_sock.o -test_cgrp2_sock2-objs := bpf_load.o test_cgrp2_sock2.o +test_cgrp2_sock2-objs := test_cgrp2_sock2.o xdp1-objs := xdp1_user.o # reuse xdp1 source intentionally xdp2-objs := xdp1_user.o @@ -91,8 +92,8 @@ test_current_task_under_cgroup-objs := $(CGROUP_HELPERS) \ test_current_task_under_cgroup_user.o trace_event-objs := trace_event_user.o $(TRACE_HELPERS) sampleip-objs := sampleip_user.o $(TRACE_HELPERS) -tc_l2_redirect-objs := bpf_load.o tc_l2_redirect_user.o -lwt_len_hist-objs := bpf_load.o lwt_len_hist_user.o +tc_l2_redirect-objs := tc_l2_redirect_user.o +lwt_len_hist-objs := lwt_len_hist_user.o xdp_tx_iptunnel-objs := xdp_tx_iptunnel_user.o test_map_in_map-objs := test_map_in_map_user.o per_socket_stats_example-objs := cookie_uid_helper_example.o @@ -105,12 +106,13 @@ syscall_tp-objs := syscall_tp_user.o cpustat-objs := cpustat_user.o xdp_adjust_tail-objs := xdp_adjust_tail_user.o xdpsock-objs := xdpsock_user.o +xdpsock_ctrl_proc-objs := xdpsock_ctrl_proc.o xsk_fwd-objs := xsk_fwd.o xdp_fwd-objs := xdp_fwd_user.o -task_fd_query-objs := bpf_load.o task_fd_query_user.o $(TRACE_HELPERS) -xdp_sample_pkts-objs := xdp_sample_pkts_user.o $(TRACE_HELPERS) -ibumad-objs := bpf_load.o ibumad_user.o $(TRACE_HELPERS) -hbm-objs := bpf_load.o hbm.o $(CGROUP_HELPERS) +task_fd_query-objs := task_fd_query_user.o $(TRACE_HELPERS) +xdp_sample_pkts-objs := xdp_sample_pkts_user.o +ibumad-objs := ibumad_user.o +hbm-objs := hbm.o $(CGROUP_HELPERS) # Tell kbuild to always build the programs always-y := $(tprogs-y) @@ -197,14 +199,12 @@ TPROGS_CFLAGS += --sysroot=$(SYSROOT) TPROGS_LDFLAGS := -L$(SYSROOT)/usr/lib endif -TPROGCFLAGS_bpf_load.o += -Wno-unused-variable - TPROGS_LDLIBS += $(LIBBPF) -lelf -lz TPROGLDLIBS_tracex4 += -lrt TPROGLDLIBS_trace_output += -lrt TPROGLDLIBS_map_perf_test += -lrt TPROGLDLIBS_test_overhead += -lrt -TPROGLDLIBS_xdpsock += -pthread +TPROGLDLIBS_xdpsock += -pthread -lcap TPROGLDLIBS_xsk_fwd += -pthread # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline: diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c deleted file mode 100644 index c5ad528f046e..000000000000 --- a/samples/bpf/bpf_load.c +++ /dev/null @@ -1,667 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <stdio.h> -#include <sys/types.h> -#include <sys/stat.h> -#include <fcntl.h> -#include <libelf.h> -#include <gelf.h> -#include <errno.h> -#include <unistd.h> -#include <string.h> -#include <stdbool.h> -#include <stdlib.h> -#include <linux/bpf.h> -#include <linux/filter.h> -#include <linux/perf_event.h> -#include <linux/netlink.h> -#include <linux/rtnetlink.h> -#include <linux/types.h> -#include <sys/socket.h> -#include <sys/syscall.h> -#include <sys/ioctl.h> -#include <sys/mman.h> -#include <poll.h> -#include <ctype.h> -#include <assert.h> -#include <bpf/bpf.h> -#include "bpf_load.h" -#include "perf-sys.h" - -#define DEBUGFS "/sys/kernel/debug/tracing/" - -static char license[128]; -static int kern_version; -static bool processed_sec[128]; -char bpf_log_buf[BPF_LOG_BUF_SIZE]; -int map_fd[MAX_MAPS]; -int prog_fd[MAX_PROGS]; -int event_fd[MAX_PROGS]; -int prog_cnt; -int prog_array_fd = -1; - -struct bpf_map_data map_data[MAX_MAPS]; -int map_data_count; - -static int populate_prog_array(const char *event, int prog_fd) -{ - int ind = atoi(event), err; - - err = bpf_map_update_elem(prog_array_fd, &ind, &prog_fd, BPF_ANY); - if (err < 0) { - printf("failed to store prog_fd in prog_array\n"); - return -1; - } - return 0; -} - -static int write_kprobe_events(const char *val) -{ - int fd, ret, flags; - - if (val == NULL) - return -1; - else if (val[0] == '\0') - flags = O_WRONLY | O_TRUNC; - else - flags = O_WRONLY | O_APPEND; - - fd = open(DEBUGFS "kprobe_events", flags); - - ret = write(fd, val, strlen(val)); - close(fd); - - return ret; -} - -static int load_and_attach(const char *event, struct bpf_insn *prog, int size) -{ - bool is_socket = strncmp(event, "socket", 6) == 0; - bool is_kprobe = strncmp(event, "kprobe/", 7) == 0; - bool is_kretprobe = strncmp(event, "kretprobe/", 10) == 0; - bool is_tracepoint = strncmp(event, "tracepoint/", 11) == 0; - bool is_raw_tracepoint = strncmp(event, "raw_tracepoint/", 15) == 0; - bool is_xdp = strncmp(event, "xdp", 3) == 0; - bool is_perf_event = strncmp(event, "perf_event", 10) == 0; - bool is_cgroup_skb = strncmp(event, "cgroup/skb", 10) == 0; - bool is_cgroup_sk = strncmp(event, "cgroup/sock", 11) == 0; - bool is_sockops = strncmp(event, "sockops", 7) == 0; - bool is_sk_skb = strncmp(event, "sk_skb", 6) == 0; - bool is_sk_msg = strncmp(event, "sk_msg", 6) == 0; - size_t insns_cnt = size / sizeof(struct bpf_insn); - enum bpf_prog_type prog_type; - char buf[256]; - int fd, efd, err, id; - struct perf_event_attr attr = {}; - - attr.type = PERF_TYPE_TRACEPOINT; - attr.sample_type = PERF_SAMPLE_RAW; - attr.sample_period = 1; - attr.wakeup_events = 1; - - if (is_socket) { - prog_type = BPF_PROG_TYPE_SOCKET_FILTER; - } else if (is_kprobe || is_kretprobe) { - prog_type = BPF_PROG_TYPE_KPROBE; - } else if (is_tracepoint) { - prog_type = BPF_PROG_TYPE_TRACEPOINT; - } else if (is_raw_tracepoint) { - prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT; - } else if (is_xdp) { - prog_type = BPF_PROG_TYPE_XDP; - } else if (is_perf_event) { - prog_type = BPF_PROG_TYPE_PERF_EVENT; - } else if (is_cgroup_skb) { - prog_type = BPF_PROG_TYPE_CGROUP_SKB; - } else if (is_cgroup_sk) { - prog_type = BPF_PROG_TYPE_CGROUP_SOCK; - } else if (is_sockops) { - prog_type = BPF_PROG_TYPE_SOCK_OPS; - } else if (is_sk_skb) { - prog_type = BPF_PROG_TYPE_SK_SKB; - } else if (is_sk_msg) { - prog_type = BPF_PROG_TYPE_SK_MSG; - } else { - printf("Unknown event '%s'\n", event); - return -1; - } - - if (prog_cnt == MAX_PROGS) - return -1; - - fd = bpf_load_program(prog_type, prog, insns_cnt, license, kern_version, - bpf_log_buf, BPF_LOG_BUF_SIZE); - if (fd < 0) { - printf("bpf_load_program() err=%d\n%s", errno, bpf_log_buf); - return -1; - } - - prog_fd[prog_cnt++] = fd; - - if (is_xdp || is_perf_event || is_cgroup_skb || is_cgroup_sk) - return 0; - - if (is_socket || is_sockops || is_sk_skb || is_sk_msg) { - if (is_socket) - event += 6; - else - event += 7; - if (*event != '/') - return 0; - event++; - if (!isdigit(*event)) { - printf("invalid prog number\n"); - return -1; - } - return populate_prog_array(event, fd); - } - - if (is_raw_tracepoint) { - efd = bpf_raw_tracepoint_open(event + 15, fd); - if (efd < 0) { - printf("tracepoint %s %s\n", event + 15, strerror(errno)); - return -1; - } - event_fd[prog_cnt - 1] = efd; - return 0; - } - - if (is_kprobe || is_kretprobe) { - bool need_normal_check = true; - const char *event_prefix = ""; - - if (is_kprobe) - event += 7; - else - event += 10; - - if (*event == 0) { - printf("event name cannot be empty\n"); - return -1; - } - - if (isdigit(*event)) - return populate_prog_array(event, fd); - -#ifdef __x86_64__ - if (strncmp(event, "sys_", 4) == 0) { - snprintf(buf, sizeof(buf), "%c:__x64_%s __x64_%s", - is_kprobe ? 'p' : 'r', event, event); - err = write_kprobe_events(buf); - if (err >= 0) { - need_normal_check = false; - event_prefix = "__x64_"; - } - } -#endif - if (need_normal_check) { - snprintf(buf, sizeof(buf), "%c:%s %s", - is_kprobe ? 'p' : 'r', event, event); - err = write_kprobe_events(buf); - if (err < 0) { - printf("failed to create kprobe '%s' error '%s'\n", - event, strerror(errno)); - return -1; - } - } - - strcpy(buf, DEBUGFS); - strcat(buf, "events/kprobes/"); - strcat(buf, event_prefix); - strcat(buf, event); - strcat(buf, "/id"); - } else if (is_tracepoint) { - event += 11; - - if (*event == 0) { - printf("event name cannot be empty\n"); - return -1; - } - strcpy(buf, DEBUGFS); - strcat(buf, "events/"); - strcat(buf, event); - strcat(buf, "/id"); - } - - efd = open(buf, O_RDONLY, 0); - if (efd < 0) { - printf("failed to open event %s\n", event); - return -1; - } - - err = read(efd, buf, sizeof(buf)); - if (err < 0 || err >= sizeof(buf)) { - printf("read from '%s' failed '%s'\n", event, strerror(errno)); - return -1; - } - - close(efd); - - buf[err] = 0; - id = atoi(buf); - attr.config = id; - - efd = sys_perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0); - if (efd < 0) { - printf("event %d fd %d err %s\n", id, efd, strerror(errno)); - return -1; - } - event_fd[prog_cnt - 1] = efd; - err = ioctl(efd, PERF_EVENT_IOC_ENABLE, 0); - if (err < 0) { - printf("ioctl PERF_EVENT_IOC_ENABLE failed err %s\n", - strerror(errno)); - return -1; - } - err = ioctl(efd, PERF_EVENT_IOC_SET_BPF, fd); - if (err < 0) { - printf("ioctl PERF_EVENT_IOC_SET_BPF failed err %s\n", - strerror(errno)); - return -1; - } - - return 0; -} - -static int load_maps(struct bpf_map_data *maps, int nr_maps, - fixup_map_cb fixup_map) -{ - int i, numa_node; - - for (i = 0; i < nr_maps; i++) { - if (fixup_map) { - fixup_map(&maps[i], i); - /* Allow userspace to assign map FD prior to creation */ - if (maps[i].fd != -1) { - map_fd[i] = maps[i].fd; - continue; - } - } - - numa_node = maps[i].def.map_flags & BPF_F_NUMA_NODE ? - maps[i].def.numa_node : -1; - - if (maps[i].def.type == BPF_MAP_TYPE_ARRAY_OF_MAPS || - maps[i].def.type == BPF_MAP_TYPE_HASH_OF_MAPS) { - int inner_map_fd = map_fd[maps[i].def.inner_map_idx]; - - map_fd[i] = bpf_create_map_in_map_node(maps[i].def.type, - maps[i].name, - maps[i].def.key_size, - inner_map_fd, - maps[i].def.max_entries, - maps[i].def.map_flags, - numa_node); - } else { - map_fd[i] = bpf_create_map_node(maps[i].def.type, - maps[i].name, - maps[i].def.key_size, - maps[i].def.value_size, - maps[i].def.max_entries, - maps[i].def.map_flags, - numa_node); - } - if (map_fd[i] < 0) { - printf("failed to create map %d (%s): %d %s\n", - i, maps[i].name, errno, strerror(errno)); - return 1; - } - maps[i].fd = map_fd[i]; - - if (maps[i].def.type == BPF_MAP_TYPE_PROG_ARRAY) - prog_array_fd = map_fd[i]; - } - return 0; -} - -static int get_sec(Elf *elf, int i, GElf_Ehdr *ehdr, char **shname, - GElf_Shdr *shdr, Elf_Data **data) -{ - Elf_Scn *scn; - - scn = elf_getscn(elf, i); - if (!scn) - return 1; - - if (gelf_getshdr(scn, shdr) != shdr) - return 2; - - *shname = elf_strptr(elf, ehdr->e_shstrndx, shdr->sh_name); - if (!*shname || !shdr->sh_size) - return 3; - - *data = elf_getdata(scn, 0); - if (!*data || elf_getdata(scn, *data) != NULL) - return 4; - - return 0; -} - -static int parse_relo_and_apply(Elf_Data *data, Elf_Data *symbols, - GElf_Shdr *shdr, struct bpf_insn *insn, - struct bpf_map_data *maps, int nr_maps) -{ - int i, nrels; - - nrels = shdr->sh_size / shdr->sh_entsize; - - for (i = 0; i < nrels; i++) { - GElf_Sym sym; - GElf_Rel rel; - unsigned int insn_idx; - bool match = false; - int j, map_idx; - - gelf_getrel(data, i, &rel); - - insn_idx = rel.r_offset / sizeof(struct bpf_insn); - - gelf_getsym(symbols, GELF_R_SYM(rel.r_info), &sym); - - if (insn[insn_idx].code != (BPF_LD | BPF_IMM | BPF_DW)) { - printf("invalid relo for insn[%d].code 0x%x\n", - insn_idx, insn[insn_idx].code); - return 1; - } - insn[insn_idx].src_reg = BPF_PSEUDO_MAP_FD; - - /* Match FD relocation against recorded map_data[] offset */ - for (map_idx = 0; map_idx < nr_maps; map_idx++) { - if (maps[map_idx].elf_offset == sym.st_value) { - match = true; - break; - } - } - if (match) { - insn[insn_idx].imm = maps[map_idx].fd; - } else { - printf("invalid relo for insn[%d] no map_data match\n", - insn_idx); - return 1; - } - } - - return 0; -} - -static int cmp_symbols(const void *l, const void *r) -{ - const GElf_Sym *lsym = (const GElf_Sym *)l; - const GElf_Sym *rsym = (const GElf_Sym *)r; - - if (lsym->st_value < rsym->st_value) - return -1; - else if (lsym->st_value > rsym->st_value) - return 1; - else - return 0; -} - -static int load_elf_maps_section(struct bpf_map_data *maps, int maps_shndx, - Elf *elf, Elf_Data *symbols, int strtabidx) -{ - int map_sz_elf, map_sz_copy; - bool validate_zero = false; - Elf_Data *data_maps; - int i, nr_maps; - GElf_Sym *sym; - Elf_Scn *scn; - int copy_sz; - - if (maps_shndx < 0) - return -EINVAL; - if (!symbols) - return -EINVAL; - - /* Get data for maps section via elf index */ - scn = elf_getscn(elf, maps_shndx); - if (scn) - data_maps = elf_getdata(scn, NULL); - if (!scn || !data_maps) { - printf("Failed to get Elf_Data from maps section %d\n", - maps_shndx); - return -EINVAL; - } - - /* For each map get corrosponding symbol table entry */ - sym = calloc(MAX_MAPS+1, sizeof(GElf_Sym)); - for (i = 0, nr_maps = 0; i < symbols->d_size / sizeof(GElf_Sym); i++) { - assert(nr_maps < MAX_MAPS+1); - if (!gelf_getsym(symbols, i, &sym[nr_maps])) - continue; - if (sym[nr_maps].st_shndx != maps_shndx) - continue; - /* Only increment iif maps section */ - nr_maps++; - } - - /* Align to map_fd[] order, via sort on offset in sym.st_value */ - qsort(sym, nr_maps, sizeof(GElf_Sym), cmp_symbols); - - /* Keeping compatible with ELF maps section changes - * ------------------------------------------------ - * The program size of struct bpf_load_map_def is known by loader - * code, but struct stored in ELF file can be different. - * - * Unfortunately sym[i].st_size is zero. To calculate the - * struct size stored in the ELF file, assume all struct have - * the same size, and simply divide with number of map - * symbols. - */ - map_sz_elf = data_maps->d_size / nr_maps; - map_sz_copy = sizeof(struct bpf_load_map_def); - if (map_sz_elf < map_sz_copy) { - /* - * Backward compat, loading older ELF file with - * smaller struct, keeping remaining bytes zero. - */ - map_sz_copy = map_sz_elf; - } else if (map_sz_elf > map_sz_copy) { - /* - * Forward compat, loading newer ELF file with larger - * struct with unknown features. Assume zero means - * feature not used. Thus, validate rest of struct - * data is zero. - */ - validate_zero = true; - } - - /* Memcpy relevant part of ELF maps data to loader maps */ - for (i = 0; i < nr_maps; i++) { - struct bpf_load_map_def *def; - unsigned char *addr, *end; - const char *map_name; - size_t offset; - - map_name = elf_strptr(elf, strtabidx, sym[i].st_name); - maps[i].name = strdup(map_name); - if (!maps[i].name) { - printf("strdup(%s): %s(%d)\n", map_name, - strerror(errno), errno); - free(sym); - return -errno; - } - - /* Symbol value is offset into ELF maps section data area */ - offset = sym[i].st_value; - def = (struct bpf_load_map_def *)(data_maps->d_buf + offset); - maps[i].elf_offset = offset; - memset(&maps[i].def, 0, sizeof(struct bpf_load_map_def)); - memcpy(&maps[i].def, def, map_sz_copy); - - /* Verify no newer features were requested */ - if (validate_zero) { - addr = (unsigned char *) def + map_sz_copy; - end = (unsigned char *) def + map_sz_elf; - for (; addr < end; addr++) { - if (*addr != 0) { - free(sym); - return -EFBIG; - } - } - } - } - - free(sym); - return nr_maps; -} - -static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map) -{ - int fd, i, ret, maps_shndx = -1, strtabidx = -1; - Elf *elf; - GElf_Ehdr ehdr; - GElf_Shdr shdr, shdr_prog; - Elf_Data *data, *data_prog, *data_maps = NULL, *symbols = NULL; - char *shname, *shname_prog; - int nr_maps = 0; - - /* reset global variables */ - kern_version = 0; - memset(license, 0, sizeof(license)); - memset(processed_sec, 0, sizeof(processed_sec)); - - if (elf_version(EV_CURRENT) == EV_NONE) - return 1; - - fd = open(path, O_RDONLY, 0); - if (fd < 0) - return 1; - - elf = elf_begin(fd, ELF_C_READ, NULL); - - if (!elf) - return 1; - - if (gelf_getehdr(elf, &ehdr) != &ehdr) - return 1; - - /* clear all kprobes */ - i = write_kprobe_events(""); - - /* scan over all elf sections to get license and map info */ - for (i = 1; i < ehdr.e_shnum; i++) { - - if (get_sec(elf, i, &ehdr, &shname, &shdr, &data)) - continue; - - if (0) /* helpful for llvm debugging */ - printf("section %d:%s data %p size %zd link %d flags %d\n", - i, shname, data->d_buf, data->d_size, - shdr.sh_link, (int) shdr.sh_flags); - - if (strcmp(shname, "license") == 0) { - processed_sec[i] = true; - memcpy(license, data->d_buf, data->d_size); - } else if (strcmp(shname, "version") == 0) { - processed_sec[i] = true; - if (data->d_size != sizeof(int)) { - printf("invalid size of version section %zd\n", - data->d_size); - return 1; - } - memcpy(&kern_version, data->d_buf, sizeof(int)); - } else if (strcmp(shname, "maps") == 0) { - int j; - - maps_shndx = i; - data_maps = data; - for (j = 0; j < MAX_MAPS; j++) - map_data[j].fd = -1; - } else if (shdr.sh_type == SHT_SYMTAB) { - strtabidx = shdr.sh_link; - symbols = data; - } - } - - ret = 1; - - if (!symbols) { - printf("missing SHT_SYMTAB section\n"); - goto done; - } - - if (data_maps) { - nr_maps = load_elf_maps_section(map_data, maps_shndx, - elf, symbols, strtabidx); - if (nr_maps < 0) { - printf("Error: Failed loading ELF maps (errno:%d):%s\n", - nr_maps, strerror(-nr_maps)); - goto done; - } - if (load_maps(map_data, nr_maps, fixup_map)) - goto done; - map_data_count = nr_maps; - - processed_sec[maps_shndx] = true; - } - - /* process all relo sections, and rewrite bpf insns for maps */ - for (i = 1; i < ehdr.e_shnum; i++) { - if (processed_sec[i]) - continue; - - if (get_sec(elf, i, &ehdr, &shname, &shdr, &data)) - continue; - - if (shdr.sh_type == SHT_REL) { - struct bpf_insn *insns; - - /* locate prog sec that need map fixup (relocations) */ - if (get_sec(elf, shdr.sh_info, &ehdr, &shname_prog, - &shdr_prog, &data_prog)) - continue; - - if (shdr_prog.sh_type != SHT_PROGBITS || - !(shdr_prog.sh_flags & SHF_EXECINSTR)) - continue; - - insns = (struct bpf_insn *) data_prog->d_buf; - processed_sec[i] = true; /* relo section */ - - if (parse_relo_and_apply(data, symbols, &shdr, insns, - map_data, nr_maps)) - continue; - } - } - - /* load programs */ - for (i = 1; i < ehdr.e_shnum; i++) { - - if (processed_sec[i]) - continue; - - if (get_sec(elf, i, &ehdr, &shname, &shdr, &data)) - continue; - - if (memcmp(shname, "kprobe/", 7) == 0 || - memcmp(shname, "kretprobe/", 10) == 0 || - memcmp(shname, "tracepoint/", 11) == 0 || - memcmp(shname, "raw_tracepoint/", 15) == 0 || - memcmp(shname, "xdp", 3) == 0 || - memcmp(shname, "perf_event", 10) == 0 || - memcmp(shname, "socket", 6) == 0 || - memcmp(shname, "cgroup/", 7) == 0 || - memcmp(shname, "sockops", 7) == 0 || - memcmp(shname, "sk_skb", 6) == 0 || - memcmp(shname, "sk_msg", 6) == 0) { - ret = load_and_attach(shname, data->d_buf, - data->d_size); - if (ret != 0) - goto done; - } - } - -done: - close(fd); - return ret; -} - -int load_bpf_file(char *path) -{ - return do_load_bpf_file(path, NULL); -} - -int load_bpf_file_fixup_map(const char *path, fixup_map_cb fixup_map) -{ - return do_load_bpf_file(path, fixup_map); -} diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h deleted file mode 100644 index 4fcd258c616f..000000000000 --- a/samples/bpf/bpf_load.h +++ /dev/null @@ -1,57 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __BPF_LOAD_H -#define __BPF_LOAD_H - -#include <bpf/bpf.h> - -#define MAX_MAPS 32 -#define MAX_PROGS 32 - -struct bpf_load_map_def { - unsigned int type; - unsigned int key_size; - unsigned int value_size; - unsigned int max_entries; - unsigned int map_flags; - unsigned int inner_map_idx; - unsigned int numa_node; -}; - -struct bpf_map_data { - int fd; - char *name; - size_t elf_offset; - struct bpf_load_map_def def; -}; - -typedef void (*fixup_map_cb)(struct bpf_map_data *map, int idx); - -extern int prog_fd[MAX_PROGS]; -extern int event_fd[MAX_PROGS]; -extern char bpf_log_buf[BPF_LOG_BUF_SIZE]; -extern int prog_cnt; - -/* There is a one-to-one mapping between map_fd[] and map_data[]. - * The map_data[] just contains more rich info on the given map. - */ -extern int map_fd[MAX_MAPS]; -extern struct bpf_map_data map_data[MAX_MAPS]; -extern int map_data_count; - -/* parses elf file compiled by llvm .c->.o - * . parses 'maps' section and creates maps via BPF syscall - * . parses 'license' section and passes it to syscall - * . parses elf relocations for BPF maps and adjusts BPF_LD_IMM64 insns by - * storing map_fd into insn->imm and marking such insns as BPF_PSEUDO_MAP_FD - * . loads eBPF programs via BPF syscall - * - * One ELF file can contain multiple BPF programs which will be loaded - * and their FDs stored stored in prog_fd array - * - * returns zero on success - */ -int load_bpf_file(char *path); -int load_bpf_file_fixup_map(const char *path, fixup_map_cb fixup_map); - -int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); -#endif diff --git a/samples/bpf/do_hbm_test.sh b/samples/bpf/do_hbm_test.sh index ffe4c0607341..21790ea5c460 100755 --- a/samples/bpf/do_hbm_test.sh +++ b/samples/bpf/do_hbm_test.sh @@ -91,6 +91,16 @@ qdisc="" flags="" do_stats=0 +BPFFS=/sys/fs/bpf +function config_bpffs () { + if mount | grep $BPFFS > /dev/null; then + echo "bpffs already mounted" + else + echo "bpffs not mounted. Mounting..." + mount -t bpf none $BPFFS + fi +} + function start_hbm () { rm -f hbm.out echo "./hbm $dir -n $id -r $rate -t $dur $flags $dbg $prog" > hbm.out @@ -192,6 +202,7 @@ processArgs () { } processArgs +config_bpffs if [ $debug_flag -eq 1 ] ; then rm -f hbm_out.log @@ -201,7 +212,7 @@ hbm_pid=$(start_hbm) usleep 100000 host=`hostname` -cg_base_dir=/sys/fs/cgroup +cg_base_dir=/sys/fs/cgroup/unified cg_dir="$cg_base_dir/cgroup-test-work-dir/hbm$id" echo $$ >> $cg_dir/cgroup.procs @@ -411,23 +422,8 @@ fi sleep 1 -# Detach any BPF programs that may have lingered -ttx=`bpftool cgroup tree | grep hbm` -v=2 -for x in $ttx ; do - if [ "${x:0:36}" == "/sys/fs/cgroup/cgroup-test-work-dir/" ] ; then - cg=$x ; v=0 - else - if [ $v -eq 0 ] ; then - id=$x ; v=1 - else - if [ $v -eq 1 ] ; then - type=$x ; bpftool cgroup detach $cg $type id $id - v=0 - fi - fi - fi -done +# Detach any pinned BPF programs that may have lingered +rm -rf $BPFFS/hbm* if [ $use_netperf -ne 0 ] ; then if [ "$server" == "" ] ; then diff --git a/samples/bpf/hbm.c b/samples/bpf/hbm.c index 400e741a56eb..b0c18efe7928 100644 --- a/samples/bpf/hbm.c +++ b/samples/bpf/hbm.c @@ -46,7 +46,6 @@ #include <bpf/bpf.h> #include <getopt.h> -#include "bpf_load.h" #include "bpf_rlimit.h" #include "cgroup_helpers.h" #include "hbm.h" @@ -70,9 +69,9 @@ static void do_error(char *msg, bool errno_flag); #define DEBUGFS "/sys/kernel/debug/tracing/" -struct bpf_object *obj; -int bpfprog_fd; -int cgroup_storage_fd; +static struct bpf_program *bpf_prog; +static struct bpf_object *obj; +static int queue_stats_fd; static void read_trace_pipe2(void) { @@ -121,56 +120,50 @@ static void do_error(char *msg, bool errno_flag) static int prog_load(char *prog) { - struct bpf_prog_load_attr prog_load_attr = { - .prog_type = BPF_PROG_TYPE_CGROUP_SKB, - .file = prog, - .expected_attach_type = BPF_CGROUP_INET_EGRESS, - }; - int map_fd; - struct bpf_map *map; - - int ret = 0; - - if (access(prog, O_RDONLY) < 0) { - printf("Error accessing file %s: %s\n", prog, strerror(errno)); + obj = bpf_object__open_file(prog, NULL); + if (libbpf_get_error(obj)) { + printf("ERROR: opening BPF object file failed\n"); return 1; } - if (bpf_prog_load_xattr(&prog_load_attr, &obj, &bpfprog_fd)) - ret = 1; - if (!ret) { - map = bpf_object__find_map_by_name(obj, "queue_stats"); - map_fd = bpf_map__fd(map); - if (map_fd < 0) { - printf("Map not found: %s\n", strerror(map_fd)); - ret = 1; - } + + /* load BPF program */ + if (bpf_object__load(obj)) { + printf("ERROR: loading BPF object file failed\n"); + goto err; } - if (ret) { - printf("ERROR: bpf_prog_load_xattr failed for: %s\n", prog); - printf(" Output from verifier:\n%s\n------\n", bpf_log_buf); - ret = -1; - } else { - ret = map_fd; + bpf_prog = bpf_object__find_program_by_title(obj, "cgroup_skb/egress"); + if (!bpf_prog) { + printf("ERROR: finding a prog in obj file failed\n"); + goto err; + } + + queue_stats_fd = bpf_object__find_map_fd_by_name(obj, "queue_stats"); + if (queue_stats_fd < 0) { + printf("ERROR: finding a map in obj file failed\n"); + goto err; } - return ret; + return 0; + +err: + bpf_object__close(obj); + return 1; } static int run_bpf_prog(char *prog, int cg_id) { - int map_fd; - int rc = 0; + struct hbm_queue_stats qstats = {0}; + char cg_dir[100], cg_pin_path[100]; + struct bpf_link *link = NULL; int key = 0; int cg1 = 0; - int type = BPF_CGROUP_INET_EGRESS; - char cg_dir[100]; - struct hbm_queue_stats qstats = {0}; + int rc = 0; sprintf(cg_dir, "/hbm%d", cg_id); - map_fd = prog_load(prog); - if (map_fd == -1) - return 1; + rc = prog_load(prog); + if (rc != 0) + return rc; if (setup_cgroup_environment()) { printf("ERROR: setting cgroup environment\n"); @@ -190,16 +183,24 @@ static int run_bpf_prog(char *prog, int cg_id) qstats.stats = stats_flag ? 1 : 0; qstats.loopback = loopback_flag ? 1 : 0; qstats.no_cn = no_cn_flag ? 1 : 0; - if (bpf_map_update_elem(map_fd, &key, &qstats, BPF_ANY)) { + if (bpf_map_update_elem(queue_stats_fd, &key, &qstats, BPF_ANY)) { printf("ERROR: Could not update map element\n"); goto err; } if (!outFlag) - type = BPF_CGROUP_INET_INGRESS; - if (bpf_prog_attach(bpfprog_fd, cg1, type, 0)) { - printf("ERROR: bpf_prog_attach fails!\n"); - log_err("Attaching prog"); + bpf_program__set_expected_attach_type(bpf_prog, BPF_CGROUP_INET_INGRESS); + + link = bpf_program__attach_cgroup(bpf_prog, cg1); + if (libbpf_get_error(link)) { + fprintf(stderr, "ERROR: bpf_program__attach_cgroup failed\n"); + goto err; + } + + sprintf(cg_pin_path, "/sys/fs/bpf/hbm%d", cg_id); + rc = bpf_link__pin(link, cg_pin_path); + if (rc < 0) { + printf("ERROR: bpf_link__pin failed: %d\n", rc); goto err; } @@ -213,7 +214,7 @@ static int run_bpf_prog(char *prog, int cg_id) #define DELTA_RATE_CHECK 10000 /* in us */ #define RATE_THRESHOLD 9500000000 /* 9.5 Gbps */ - bpf_map_lookup_elem(map_fd, &key, &qstats); + bpf_map_lookup_elem(queue_stats_fd, &key, &qstats); if (gettimeofday(&t0, NULL) < 0) do_error("gettimeofday failed", true); t_last = t0; @@ -242,7 +243,7 @@ static int run_bpf_prog(char *prog, int cg_id) fclose(fin); printf(" new_eth_tx_bytes:%llu\n", new_eth_tx_bytes); - bpf_map_lookup_elem(map_fd, &key, &qstats); + bpf_map_lookup_elem(queue_stats_fd, &key, &qstats); new_cg_tx_bytes = qstats.bytes_total; delta_bytes = new_eth_tx_bytes - last_eth_tx_bytes; last_eth_tx_bytes = new_eth_tx_bytes; @@ -289,14 +290,14 @@ static int run_bpf_prog(char *prog, int cg_id) rate = minRate; qstats.rate = rate; } - if (bpf_map_update_elem(map_fd, &key, &qstats, BPF_ANY)) + if (bpf_map_update_elem(queue_stats_fd, &key, &qstats, BPF_ANY)) do_error("update map element fails", false); } } else { sleep(dur); } // Get stats! - if (stats_flag && bpf_map_lookup_elem(map_fd, &key, &qstats)) { + if (stats_flag && bpf_map_lookup_elem(queue_stats_fd, &key, &qstats)) { char fname[100]; FILE *fout; @@ -394,14 +395,20 @@ static int run_bpf_prog(char *prog, int cg_id) if (debugFlag) read_trace_pipe2(); - return rc; + goto cleanup; + err: rc = 1; - if (cg1) +cleanup: + bpf_link__destroy(link); + bpf_object__close(obj); + + if (cg1 != -1) close(cg1); - cleanup_cgroup_environment(); + if (rc != 0) + cleanup_cgroup_environment(); return rc; } diff --git a/samples/bpf/hbm_kern.h b/samples/bpf/hbm_kern.h index e00f26f6afba..722b3fadb467 100644 --- a/samples/bpf/hbm_kern.h +++ b/samples/bpf/hbm_kern.h @@ -69,7 +69,7 @@ struct { __uint(type, BPF_MAP_TYPE_ARRAY); __uint(max_entries, 1); __type(key, u32); - __type(value, struct hvm_queue_stats); + __type(value, struct hbm_queue_stats); } queue_stats SEC(".maps"); struct hbm_pkt_info { diff --git a/samples/bpf/ibumad_kern.c b/samples/bpf/ibumad_kern.c index 3a91b4c1989a..26dcd4dde946 100644 --- a/samples/bpf/ibumad_kern.c +++ b/samples/bpf/ibumad_kern.c @@ -16,19 +16,19 @@ #include <bpf/bpf_helpers.h> -struct bpf_map_def SEC("maps") read_count = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(u32), /* class; u32 required */ - .value_size = sizeof(u64), /* count of mads read */ - .max_entries = 256, /* Room for all Classes */ -}; - -struct bpf_map_def SEC("maps") write_count = { - .type = BPF_MAP_TYPE_ARRAY, - .key_size = sizeof(u32), /* class; u32 required */ - .value_size = sizeof(u64), /* count of mads written */ - .max_entries = 256, /* Room for all Classes */ -}; +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); /* class; u32 required */ + __type(value, u64); /* count of mads read */ + __uint(max_entries, 256); /* Room for all Classes */ +} read_count SEC(".maps"); + +struct { + __uint(type, BPF_MAP_TYPE_ARRAY); + __type(key, u32); /* class; u32 required */ + __type(value, u64); /* count of mads written */ + __uint(max_entries, 256); /* Room for all Classes */ +} write_count SEC(".maps"); #undef DEBUG #ifndef DEBUG diff --git a/samples/bpf/ibumad_user.c b/samples/bpf/ibumad_user.c index fa06eef31a84..d83d8102f489 100644 --- a/samples/bpf/ibumad_user.c +++ b/samples/bpf/ibumad_user.c @@ -23,10 +23,15 @@ #include <getopt.h> #include <net/if.h> -#include "bpf_load.h" +#include <bpf/bpf.h> #include "bpf_util.h" #include <bpf/libbpf.h> +static struct bpf_link *tp_links[3]; +static struct bpf_object *obj; +static int map_fd[2]; +static int tp_cnt; + static void dump_counts(int fd) { __u32 key; @@ -53,6 +58,11 @@ static void dump_all_counts(void) static void dump_exit(int sig) { dump_all_counts(); + /* Detach tracepoints */ + while (tp_cnt) + bpf_link__destroy(tp_links[--tp_cnt]); + + bpf_object__close(obj); exit(0); } @@ -73,19 +83,11 @@ static void usage(char *cmd) int main(int argc, char **argv) { + struct bpf_program *prog; unsigned long delay = 5; + char filename[256]; int longindex = 0; - int opt; - char bpf_file[256]; - - /* Create the eBPF kernel code path name. - * This follows the pattern of all of the other bpf samples - */ - snprintf(bpf_file, sizeof(bpf_file), "%s_kern.o", argv[0]); - - /* Do one final dump when exiting */ - signal(SIGINT, dump_exit); - signal(SIGTERM, dump_exit); + int opt, err = -1; while ((opt = getopt_long(argc, argv, "hd:rSw", long_options, &longindex)) != -1) { @@ -107,16 +109,51 @@ int main(int argc, char **argv) } } - if (load_bpf_file(bpf_file)) { - fprintf(stderr, "ERROR: failed to load eBPF from file : %s\n", - bpf_file); - return 1; + /* Do one final dump when exiting */ + signal(SIGINT, dump_exit); + signal(SIGTERM, dump_exit); + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return err; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; + } + + map_fd[0] = bpf_object__find_map_fd_by_name(obj, "read_count"); + map_fd[1] = bpf_object__find_map_fd_by_name(obj, "write_count"); + if (map_fd[0] < 0 || map_fd[1] < 0) { + fprintf(stderr, "ERROR: finding a map in obj file failed\n"); + goto cleanup; + } + + bpf_object__for_each_program(prog, obj) { + tp_links[tp_cnt] = bpf_program__attach(prog); + if (libbpf_get_error(tp_links[tp_cnt])) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + tp_links[tp_cnt] = NULL; + goto cleanup; + } + tp_cnt++; } while (1) { sleep(delay); dump_all_counts(); } + err = 0; + +cleanup: + /* Detach tracepoints */ + while (tp_cnt) + bpf_link__destroy(tp_links[--tp_cnt]); - return 0; + bpf_object__close(obj); + return err; } diff --git a/samples/bpf/lwt_len_hist.sh b/samples/bpf/lwt_len_hist.sh index 090b96eaf7f7..0eda9754f50b 100644..100755 --- a/samples/bpf/lwt_len_hist.sh +++ b/samples/bpf/lwt_len_hist.sh @@ -8,6 +8,8 @@ VETH1=tst_lwt1b TRACE_ROOT=/sys/kernel/debug/tracing function cleanup { + # To reset saved histogram, remove pinned map + rm /sys/fs/bpf/tc/globals/lwt_len_hist_map ip route del 192.168.253.2/32 dev $VETH0 2> /dev/null ip link del $VETH0 2> /dev/null ip link del $VETH1 2> /dev/null diff --git a/samples/bpf/map_perf_test_user.c b/samples/bpf/map_perf_test_user.c index 8b13230b4c46..9db949290a78 100644 --- a/samples/bpf/map_perf_test_user.c +++ b/samples/bpf/map_perf_test_user.c @@ -421,7 +421,6 @@ static void fixup_map(struct bpf_object *obj) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; int nr_cpus = sysconf(_SC_NPROCESSORS_ONLN); struct bpf_link *links[8]; struct bpf_program *prog; @@ -430,11 +429,6 @@ int main(int argc, char **argv) char filename[256]; int i = 0; - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - if (argc > 1) test_flags = atoi(argv[1]) ? : test_flags; diff --git a/samples/bpf/offwaketime_user.c b/samples/bpf/offwaketime_user.c index 5734cfdaaacb..73a986876c1a 100644 --- a/samples/bpf/offwaketime_user.c +++ b/samples/bpf/offwaketime_user.c @@ -95,18 +95,12 @@ static void int_exit(int sig) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_object *obj = NULL; struct bpf_link *links[2]; struct bpf_program *prog; int delay = 1, i = 0; char filename[256]; - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - if (load_kallsyms()) { printf("failed to process /proc/kallsyms\n"); return 2; diff --git a/samples/bpf/sockex2_user.c b/samples/bpf/sockex2_user.c index af925a5afd1d..bafa567b840c 100644 --- a/samples/bpf/sockex2_user.c +++ b/samples/bpf/sockex2_user.c @@ -16,7 +16,6 @@ struct pair { int main(int ac, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_object *obj; int map_fd, prog_fd; char filename[256]; @@ -24,7 +23,6 @@ int main(int ac, char **argv) FILE *f; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - setrlimit(RLIMIT_MEMLOCK, &r); if (bpf_prog_load(filename, BPF_PROG_TYPE_SOCKET_FILTER, &obj, &prog_fd)) diff --git a/samples/bpf/sockex3_user.c b/samples/bpf/sockex3_user.c index 7793f6a6ae7e..6ae99ecc766c 100644 --- a/samples/bpf/sockex3_user.c +++ b/samples/bpf/sockex3_user.c @@ -26,7 +26,6 @@ struct pair { int main(int argc, char **argv) { int i, sock, key, fd, main_prog_fd, jmp_table_fd, hash_map_fd; - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_program *prog; struct bpf_object *obj; const char *section; @@ -34,7 +33,6 @@ int main(int argc, char **argv) FILE *f; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - setrlimit(RLIMIT_MEMLOCK, &r); obj = bpf_object__open_file(filename, NULL); if (libbpf_get_error(obj)) { diff --git a/samples/bpf/spintest_user.c b/samples/bpf/spintest_user.c index f090d0dc60d6..0d7e1e5a8658 100644 --- a/samples/bpf/spintest_user.c +++ b/samples/bpf/spintest_user.c @@ -10,7 +10,6 @@ int main(int ac, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; char filename[256], symbol[256]; struct bpf_object *obj = NULL; struct bpf_link *links[20]; @@ -20,11 +19,6 @@ int main(int ac, char **argv) const char *section; struct ksym *sym; - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - if (load_kallsyms()) { printf("failed to process /proc/kallsyms\n"); return 2; diff --git a/samples/bpf/syscall_tp_user.c b/samples/bpf/syscall_tp_user.c index 76a1d00128fb..a0ebf1833ed3 100644 --- a/samples/bpf/syscall_tp_user.c +++ b/samples/bpf/syscall_tp_user.c @@ -115,7 +115,6 @@ cleanup: int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; int opt, num_progs = 1; char filename[256]; @@ -131,7 +130,6 @@ int main(int argc, char **argv) } } - setrlimit(RLIMIT_MEMLOCK, &r); snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); return test(filename, num_progs); diff --git a/samples/bpf/task_fd_query_user.c b/samples/bpf/task_fd_query_user.c index b68bd2f8fdc9..a78025b0026b 100644 --- a/samples/bpf/task_fd_query_user.c +++ b/samples/bpf/task_fd_query_user.c @@ -15,12 +15,15 @@ #include <sys/stat.h> #include <linux/perf_event.h> +#include <bpf/bpf.h> #include <bpf/libbpf.h> -#include "bpf_load.h" #include "bpf_util.h" #include "perf-sys.h" #include "trace_helpers.h" +static struct bpf_program *progs[2]; +static struct bpf_link *links[2]; + #define CHECK_PERROR_RET(condition) ({ \ int __ret = !!(condition); \ if (__ret) { \ @@ -86,21 +89,22 @@ static int bpf_get_retprobe_bit(const char *event_type) return ret; } -static int test_debug_fs_kprobe(int prog_fd_idx, const char *fn_name, +static int test_debug_fs_kprobe(int link_idx, const char *fn_name, __u32 expected_fd_type) { __u64 probe_offset, probe_addr; __u32 len, prog_id, fd_type; + int err, event_fd; char buf[256]; - int err; len = sizeof(buf); - err = bpf_task_fd_query(getpid(), event_fd[prog_fd_idx], 0, buf, &len, + event_fd = bpf_link__fd(links[link_idx]); + err = bpf_task_fd_query(getpid(), event_fd, 0, buf, &len, &prog_id, &fd_type, &probe_offset, &probe_addr); if (err < 0) { printf("FAIL: %s, for event_fd idx %d, fn_name %s\n", - __func__, prog_fd_idx, fn_name); + __func__, link_idx, fn_name); perror(" :"); return -1; } @@ -108,7 +112,7 @@ static int test_debug_fs_kprobe(int prog_fd_idx, const char *fn_name, fd_type != expected_fd_type || probe_offset != 0x0 || probe_addr != 0x0) { printf("FAIL: bpf_trace_event_query(event_fd[%d]):\n", - prog_fd_idx); + link_idx); printf("buf: %s, fd_type: %u, probe_offset: 0x%llx," " probe_addr: 0x%llx\n", buf, fd_type, probe_offset, probe_addr); @@ -125,12 +129,13 @@ static int test_nondebug_fs_kuprobe_common(const char *event_type, int is_return_bit = bpf_get_retprobe_bit(event_type); int type = bpf_find_probe_type(event_type); struct perf_event_attr attr = {}; - int fd; + struct bpf_link *link; + int fd, err = -1; if (type < 0 || is_return_bit < 0) { printf("FAIL: %s incorrect type (%d) or is_return_bit (%d)\n", __func__, type, is_return_bit); - return -1; + return err; } attr.sample_period = 1; @@ -149,14 +154,21 @@ static int test_nondebug_fs_kuprobe_common(const char *event_type, attr.type = type; fd = sys_perf_event_open(&attr, -1, 0, -1, 0); - CHECK_PERROR_RET(fd < 0); + link = bpf_program__attach_perf_event(progs[0], fd); + if (libbpf_get_error(link)) { + printf("ERROR: bpf_program__attach_perf_event failed\n"); + link = NULL; + close(fd); + goto cleanup; + } - CHECK_PERROR_RET(ioctl(fd, PERF_EVENT_IOC_ENABLE, 0) < 0); - CHECK_PERROR_RET(ioctl(fd, PERF_EVENT_IOC_SET_BPF, prog_fd[0]) < 0); CHECK_PERROR_RET(bpf_task_fd_query(getpid(), fd, 0, buf, buf_len, prog_id, fd_type, probe_offset, probe_addr) < 0); + err = 0; - return 0; +cleanup: + bpf_link__destroy(link); + return err; } static int test_nondebug_fs_probe(const char *event_type, const char *name, @@ -215,17 +227,18 @@ static int test_nondebug_fs_probe(const char *event_type, const char *name, static int test_debug_fs_uprobe(char *binary_path, long offset, bool is_return) { + char buf[256], event_alias[sizeof("test_1234567890")]; const char *event_type = "uprobe"; struct perf_event_attr attr = {}; - char buf[256], event_alias[sizeof("test_1234567890")]; __u64 probe_offset, probe_addr; __u32 len, prog_id, fd_type; - int err, res, kfd, efd; + int err = -1, res, kfd, efd; + struct bpf_link *link; ssize_t bytes; snprintf(buf, sizeof(buf), "/sys/kernel/debug/tracing/%s_events", event_type); - kfd = open(buf, O_WRONLY | O_APPEND, 0); + kfd = open(buf, O_WRONLY | O_TRUNC, 0); CHECK_PERROR_RET(kfd < 0); res = snprintf(event_alias, sizeof(event_alias), "test_%d", getpid()); @@ -254,10 +267,15 @@ static int test_debug_fs_uprobe(char *binary_path, long offset, bool is_return) attr.type = PERF_TYPE_TRACEPOINT; attr.sample_period = 1; attr.wakeup_events = 1; + kfd = sys_perf_event_open(&attr, -1, 0, -1, PERF_FLAG_FD_CLOEXEC); - CHECK_PERROR_RET(kfd < 0); - CHECK_PERROR_RET(ioctl(kfd, PERF_EVENT_IOC_SET_BPF, prog_fd[0]) < 0); - CHECK_PERROR_RET(ioctl(kfd, PERF_EVENT_IOC_ENABLE, 0) < 0); + link = bpf_program__attach_perf_event(progs[0], kfd); + if (libbpf_get_error(link)) { + printf("ERROR: bpf_program__attach_perf_event failed\n"); + link = NULL; + close(kfd); + goto cleanup; + } len = sizeof(buf); err = bpf_task_fd_query(getpid(), kfd, 0, buf, &len, @@ -283,32 +301,49 @@ static int test_debug_fs_uprobe(char *binary_path, long offset, bool is_return) probe_offset); return -1; } + err = 0; - close(kfd); - return 0; +cleanup: + bpf_link__destroy(link); + return err; } int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; extern char __executable_start; char filename[256], buf[256]; __u64 uprobe_file_offset; + struct bpf_program *prog; + struct bpf_object *obj; + int i = 0, err = -1; + + if (load_kallsyms()) { + printf("failed to process /proc/kallsyms\n"); + return err; + } snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; + obj = bpf_object__open_file(filename, NULL); + if (libbpf_get_error(obj)) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return err; } - if (load_kallsyms()) { - printf("failed to process /proc/kallsyms\n"); - return 1; + /* load BPF program */ + if (bpf_object__load(obj)) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + goto cleanup; } - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; + bpf_object__for_each_program(prog, obj) { + progs[i] = prog; + links[i] = bpf_program__attach(progs[i]); + if (libbpf_get_error(links[i])) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + links[i] = NULL; + goto cleanup; + } + i++; } /* test two functions in the corresponding *_kern.c file */ @@ -378,6 +413,12 @@ int main(int argc, char **argv) false)); CHECK_AND_RET(test_debug_fs_uprobe((char *)argv[0], uprobe_file_offset, true)); + err = 0; - return 0; +cleanup: + for (i--; i >= 0; i--) + bpf_link__destroy(links[i]); + + bpf_object__close(obj); + return err; } diff --git a/samples/bpf/test_cgrp2_sock2.c b/samples/bpf/test_cgrp2_sock2.c index a9277b118c33..e7060aaa2f5a 100644 --- a/samples/bpf/test_cgrp2_sock2.c +++ b/samples/bpf/test_cgrp2_sock2.c @@ -20,9 +20,9 @@ #include <net/if.h> #include <linux/bpf.h> #include <bpf/bpf.h> +#include <bpf/libbpf.h> #include "bpf_insn.h" -#include "bpf_load.h" static int usage(const char *argv0) { @@ -32,37 +32,64 @@ static int usage(const char *argv0) int main(int argc, char **argv) { - int cg_fd, ret, filter_id = 0; + int cg_fd, err, ret = EXIT_FAILURE, filter_id = 0, prog_cnt = 0; + const char *link_pin_path = "/sys/fs/bpf/test_cgrp2_sock2"; + struct bpf_link *link = NULL; + struct bpf_program *progs[2]; + struct bpf_program *prog; + struct bpf_object *obj; if (argc < 3) return usage(argv[0]); + if (argc > 3) + filter_id = atoi(argv[3]); + cg_fd = open(argv[1], O_DIRECTORY | O_RDONLY); if (cg_fd < 0) { printf("Failed to open cgroup path: '%s'\n", strerror(errno)); - return EXIT_FAILURE; + return ret; } - if (load_bpf_file(argv[2])) - return EXIT_FAILURE; - - printf("Output from kernel verifier:\n%s\n-------\n", bpf_log_buf); + obj = bpf_object__open_file(argv[2], NULL); + if (libbpf_get_error(obj)) { + printf("ERROR: opening BPF object file failed\n"); + return ret; + } - if (argc > 3) - filter_id = atoi(argv[3]); + bpf_object__for_each_program(prog, obj) { + progs[prog_cnt] = prog; + prog_cnt++; + } if (filter_id >= prog_cnt) { printf("Invalid program id; program not found in file\n"); - return EXIT_FAILURE; + goto cleanup; + } + + /* load BPF program */ + if (bpf_object__load(obj)) { + printf("ERROR: loading BPF object file failed\n"); + goto cleanup; } - ret = bpf_prog_attach(prog_fd[filter_id], cg_fd, - BPF_CGROUP_INET_SOCK_CREATE, 0); - if (ret < 0) { - printf("Failed to attach prog to cgroup: '%s'\n", - strerror(errno)); - return EXIT_FAILURE; + link = bpf_program__attach_cgroup(progs[filter_id], cg_fd); + if (libbpf_get_error(link)) { + printf("ERROR: bpf_program__attach failed\n"); + link = NULL; + goto cleanup; } - return EXIT_SUCCESS; + err = bpf_link__pin(link, link_pin_path); + if (err < 0) { + printf("ERROR: bpf_link__pin failed: %d\n", err); + goto cleanup; + } + + ret = EXIT_SUCCESS; + +cleanup: + bpf_link__destroy(link); + bpf_object__close(obj); + return ret; } diff --git a/samples/bpf/test_cgrp2_sock2.sh b/samples/bpf/test_cgrp2_sock2.sh index 0f396a86e0cb..6a3dbe642b2b 100755 --- a/samples/bpf/test_cgrp2_sock2.sh +++ b/samples/bpf/test_cgrp2_sock2.sh @@ -1,6 +1,9 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +BPFFS=/sys/fs/bpf +LINK_PIN=$BPFFS/test_cgrp2_sock2 + function config_device { ip netns add at_ns0 ip link add veth0 type veth peer name veth0b @@ -21,16 +24,22 @@ function config_cgroup { echo $$ >> /tmp/cgroupv2/foo/cgroup.procs } +function config_bpffs { + if mount | grep $BPFFS > /dev/null; then + echo "bpffs already mounted" + else + echo "bpffs not mounted. Mounting..." + mount -t bpf none $BPFFS + fi +} function attach_bpf { - test_cgrp2_sock2 /tmp/cgroupv2/foo sock_flags_kern.o $1 + ./test_cgrp2_sock2 /tmp/cgroupv2/foo sock_flags_kern.o $1 [ $? -ne 0 ] && exit 1 } function cleanup { - if [ -d /tmp/cgroupv2/foo ]; then - test_cgrp2_sock -d /tmp/cgroupv2/foo - fi + rm -rf $LINK_PIN ip link del veth0b ip netns delete at_ns0 umount /tmp/cgroupv2 @@ -42,6 +51,7 @@ cleanup 2>/dev/null set -e config_device config_cgroup +config_bpffs set +e # @@ -62,6 +72,9 @@ if [ $? -eq 0 ]; then exit 1 fi +rm -rf $LINK_PIN +sleep 1 # Wait for link detach + # # Test 2 - fail ping # diff --git a/samples/bpf/test_lru_dist.c b/samples/bpf/test_lru_dist.c index b313dba4111b..c92c5c06b965 100644 --- a/samples/bpf/test_lru_dist.c +++ b/samples/bpf/test_lru_dist.c @@ -489,7 +489,6 @@ static void test_parallel_lru_loss(int map_type, int map_flags, int nr_tasks) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; int map_flags[] = {0, BPF_F_NO_COMMON_LRU}; const char *dist_file; int nr_tasks = 1; @@ -508,8 +507,6 @@ int main(int argc, char **argv) setbuf(stdout, NULL); - assert(!setrlimit(RLIMIT_MEMLOCK, &r)); - srand(time(NULL)); nr_cpus = bpf_num_possible_cpus(); diff --git a/samples/bpf/test_lwt_bpf.sh b/samples/bpf/test_lwt_bpf.sh index 65a976058dd3..65a976058dd3 100644..100755 --- a/samples/bpf/test_lwt_bpf.sh +++ b/samples/bpf/test_lwt_bpf.sh diff --git a/samples/bpf/test_map_in_map_user.c b/samples/bpf/test_map_in_map_user.c index 98656de56b83..472d65c70354 100644 --- a/samples/bpf/test_map_in_map_user.c +++ b/samples/bpf/test_map_in_map_user.c @@ -114,17 +114,11 @@ static void test_map_in_map(void) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_link *link = NULL; struct bpf_program *prog; struct bpf_object *obj; char filename[256]; - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); obj = bpf_object__open_file(filename, NULL); if (libbpf_get_error(obj)) { diff --git a/samples/bpf/test_overhead_user.c b/samples/bpf/test_overhead_user.c index 94f74112a20e..4821f9d99c1f 100644 --- a/samples/bpf/test_overhead_user.c +++ b/samples/bpf/test_overhead_user.c @@ -18,10 +18,14 @@ #include <time.h> #include <sys/resource.h> #include <bpf/bpf.h> -#include "bpf_load.h" +#include <bpf/libbpf.h> #define MAX_CNT 1000000 +static struct bpf_link *links[2]; +static struct bpf_object *obj; +static int cnt; + static __u64 time_get_ns(void) { struct timespec ts; @@ -115,22 +119,54 @@ static void run_perf_test(int tasks, int flags) } } +static int load_progs(char *filename) +{ + struct bpf_program *prog; + int err = 0; + + obj = bpf_object__open_file(filename, NULL); + err = libbpf_get_error(obj); + if (err < 0) { + fprintf(stderr, "ERROR: opening BPF object file failed\n"); + return err; + } + + /* load BPF program */ + err = bpf_object__load(obj); + if (err < 0) { + fprintf(stderr, "ERROR: loading BPF object file failed\n"); + return err; + } + + bpf_object__for_each_program(prog, obj) { + links[cnt] = bpf_program__attach(prog); + err = libbpf_get_error(links[cnt]); + if (err < 0) { + fprintf(stderr, "ERROR: bpf_program__attach failed\n"); + links[cnt] = NULL; + return err; + } + cnt++; + } + + return err; +} + static void unload_progs(void) { - close(prog_fd[0]); - close(prog_fd[1]); - close(event_fd[0]); - close(event_fd[1]); + while (cnt) + bpf_link__destroy(links[--cnt]); + + bpf_object__close(obj); } int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; - char filename[256]; - int num_cpu = 8; + int num_cpu = sysconf(_SC_NPROCESSORS_ONLN); int test_flags = ~0; + char filename[256]; + int err = 0; - setrlimit(RLIMIT_MEMLOCK, &r); if (argc > 1) test_flags = atoi(argv[1]) ? : test_flags; @@ -145,38 +181,36 @@ int main(int argc, char **argv) if (test_flags & 0xC) { snprintf(filename, sizeof(filename), "%s_kprobe_kern.o", argv[0]); - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; - } + printf("w/KPROBE\n"); - run_perf_test(num_cpu, test_flags >> 2); + err = load_progs(filename); + if (!err) + run_perf_test(num_cpu, test_flags >> 2); + unload_progs(); } if (test_flags & 0x30) { snprintf(filename, sizeof(filename), "%s_tp_kern.o", argv[0]); - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; - } printf("w/TRACEPOINT\n"); - run_perf_test(num_cpu, test_flags >> 4); + err = load_progs(filename); + if (!err) + run_perf_test(num_cpu, test_flags >> 4); + unload_progs(); } if (test_flags & 0xC0) { snprintf(filename, sizeof(filename), "%s_raw_tp_kern.o", argv[0]); - if (load_bpf_file(filename)) { - printf("%s", bpf_log_buf); - return 1; - } printf("w/RAW_TRACEPOINT\n"); - run_perf_test(num_cpu, test_flags >> 6); + err = load_progs(filename); + if (!err) + run_perf_test(num_cpu, test_flags >> 6); + unload_progs(); } - return 0; + return err; } diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c index ac1ba368195c..9664749bf618 100644 --- a/samples/bpf/trace_event_user.c +++ b/samples/bpf/trace_event_user.c @@ -294,13 +294,11 @@ static void test_bpf_perf_event(void) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_object *obj = NULL; char filename[256]; int error = 1; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - setrlimit(RLIMIT_MEMLOCK, &r); signal(SIGINT, err_exit); signal(SIGTERM, err_exit); diff --git a/samples/bpf/tracex2_user.c b/samples/bpf/tracex2_user.c index 3d6eab711d23..1626d51dfffd 100644 --- a/samples/bpf/tracex2_user.c +++ b/samples/bpf/tracex2_user.c @@ -116,7 +116,6 @@ static void int_exit(int sig) int main(int ac, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; long key, next_key, value; struct bpf_link *links[2]; struct bpf_program *prog; @@ -125,11 +124,6 @@ int main(int ac, char **argv) int i, j = 0; FILE *f; - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); obj = bpf_object__open_file(filename, NULL); if (libbpf_get_error(obj)) { diff --git a/samples/bpf/tracex3_user.c b/samples/bpf/tracex3_user.c index 83e0fecbb01a..33e16ba39f25 100644 --- a/samples/bpf/tracex3_user.c +++ b/samples/bpf/tracex3_user.c @@ -107,7 +107,6 @@ static void print_hist(int fd) int main(int ac, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_link *links[2]; struct bpf_program *prog; struct bpf_object *obj; @@ -127,11 +126,6 @@ int main(int ac, char **argv) } } - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); obj = bpf_object__open_file(filename, NULL); if (libbpf_get_error(obj)) { diff --git a/samples/bpf/tracex4_user.c b/samples/bpf/tracex4_user.c index e8faf8f184ae..cea399424bca 100644 --- a/samples/bpf/tracex4_user.c +++ b/samples/bpf/tracex4_user.c @@ -48,18 +48,12 @@ static void print_old_objects(int fd) int main(int ac, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_link *links[2]; struct bpf_program *prog; struct bpf_object *obj; char filename[256]; int map_fd, i, j = 0; - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK, RLIM_INFINITY)"); - return 1; - } - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); obj = bpf_object__open_file(filename, NULL); if (libbpf_get_error(obj)) { diff --git a/samples/bpf/tracex5_user.c b/samples/bpf/tracex5_user.c index c17d3fb5fd64..08dfdc77ad2a 100644 --- a/samples/bpf/tracex5_user.c +++ b/samples/bpf/tracex5_user.c @@ -34,7 +34,6 @@ static void install_accept_all_seccomp(void) int main(int ac, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_link *link = NULL; struct bpf_program *prog; struct bpf_object *obj; @@ -43,8 +42,6 @@ int main(int ac, char **argv) char filename[256]; FILE *f; - setrlimit(RLIMIT_MEMLOCK, &r); - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); obj = bpf_object__open_file(filename, NULL); if (libbpf_get_error(obj)) { diff --git a/samples/bpf/tracex6_user.c b/samples/bpf/tracex6_user.c index 33df9784775d..28296f40c133 100644 --- a/samples/bpf/tracex6_user.c +++ b/samples/bpf/tracex6_user.c @@ -175,15 +175,12 @@ static void test_bpf_perf_event(void) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_link *links[2]; struct bpf_program *prog; struct bpf_object *obj; char filename[256]; int i = 0; - setrlimit(RLIMIT_MEMLOCK, &r); - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); obj = bpf_object__open_file(filename, NULL); if (libbpf_get_error(obj)) { diff --git a/samples/bpf/xdp1_user.c b/samples/bpf/xdp1_user.c index c447ad9e3a1d..116e39f6b666 100644 --- a/samples/bpf/xdp1_user.c +++ b/samples/bpf/xdp1_user.c @@ -79,7 +79,6 @@ static void usage(const char *prog) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; @@ -117,11 +116,6 @@ int main(int argc, char **argv) return 1; } - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - ifindex = if_nametoindex(argv[optind]); if (!ifindex) { perror("if_nametoindex"); diff --git a/samples/bpf/xdp2skb_meta_kern.c b/samples/bpf/xdp2skb_meta_kern.c index 9b783316e860..d5631014a176 100644 --- a/samples/bpf/xdp2skb_meta_kern.c +++ b/samples/bpf/xdp2skb_meta_kern.c @@ -6,7 +6,7 @@ * This uses the XDP data_meta infrastructure, and is a cooperation * between two bpf-programs (1) XDP and (2) clsact at TC-ingress hook. * - * Notice: This example does not use the BPF C-loader (bpf_load.c), + * Notice: This example does not use the BPF C-loader, * but instead rely on the iproute2 TC tool for loading BPF-objects. */ #include <uapi/linux/bpf.h> diff --git a/samples/bpf/xdp_adjust_tail_user.c b/samples/bpf/xdp_adjust_tail_user.c index ba482dc3da33..a70b094c8ec5 100644 --- a/samples/bpf/xdp_adjust_tail_user.c +++ b/samples/bpf/xdp_adjust_tail_user.c @@ -82,7 +82,6 @@ static void usage(const char *cmd) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; @@ -143,11 +142,6 @@ int main(int argc, char **argv) } } - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK, RLIM_INFINITY)"); - return 1; - } - if (!ifindex) { fprintf(stderr, "Invalid ifname\n"); return 1; diff --git a/samples/bpf/xdp_monitor_user.c b/samples/bpf/xdp_monitor_user.c index 03d0a182913f..49ebc49aefc3 100644 --- a/samples/bpf/xdp_monitor_user.c +++ b/samples/bpf/xdp_monitor_user.c @@ -687,7 +687,6 @@ static void print_bpf_prog_info(void) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_program *prog; int longindex = 0, opt; int ret = EXIT_FAILURE; @@ -719,10 +718,6 @@ int main(int argc, char **argv) } snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return ret; - } /* Remove tracepoint program when program is interrupted or killed */ signal(SIGINT, int_exit); diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c index f78cb18319aa..576411612523 100644 --- a/samples/bpf/xdp_redirect_cpu_user.c +++ b/samples/bpf/xdp_redirect_cpu_user.c @@ -765,7 +765,6 @@ static int load_cpumap_prog(char *file_name, char *prog_name, int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; char *prog_name = "xdp_cpu_map5_lb_hash_ip_pairs"; char *mprog_filename = "xdp_redirect_kern.o"; char *redir_interface = NULL, *redir_map = NULL; @@ -804,11 +803,6 @@ int main(int argc, char **argv) snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); prog_load_attr.file = filename; - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) return err; diff --git a/samples/bpf/xdp_redirect_map_user.c b/samples/bpf/xdp_redirect_map_user.c index 35e16dee613e..31131b6e7782 100644 --- a/samples/bpf/xdp_redirect_map_user.c +++ b/samples/bpf/xdp_redirect_map_user.c @@ -96,7 +96,6 @@ static void usage(const char *prog) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; @@ -135,11 +134,6 @@ int main(int argc, char **argv) return 1; } - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - ifindex_in = if_nametoindex(argv[optind]); if (!ifindex_in) ifindex_in = strtoul(argv[optind], NULL, 0); diff --git a/samples/bpf/xdp_redirect_user.c b/samples/bpf/xdp_redirect_user.c index 9ca2bf457cda..41d705c3a1f7 100644 --- a/samples/bpf/xdp_redirect_user.c +++ b/samples/bpf/xdp_redirect_user.c @@ -97,7 +97,6 @@ static void usage(const char *prog) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; @@ -136,11 +135,6 @@ int main(int argc, char **argv) return 1; } - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - ifindex_in = if_nametoindex(argv[optind]); if (!ifindex_in) ifindex_in = strtoul(argv[optind], NULL, 0); diff --git a/samples/bpf/xdp_router_ipv4_user.c b/samples/bpf/xdp_router_ipv4_user.c index c2da1b51ff95..b5f03cb17a3c 100644 --- a/samples/bpf/xdp_router_ipv4_user.c +++ b/samples/bpf/xdp_router_ipv4_user.c @@ -625,7 +625,6 @@ static void usage(const char *prog) int main(int ac, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; @@ -670,11 +669,6 @@ int main(int ac, char **argv) return 1; } - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) return 1; diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c index 93fa1bc54f13..74a2926eba08 100644 --- a/samples/bpf/xdp_rxq_info_user.c +++ b/samples/bpf/xdp_rxq_info_user.c @@ -450,7 +450,6 @@ static void stats_poll(int interval, int action, __u32 cfg_opt) int main(int argc, char **argv) { __u32 cfg_options= NO_TOUCH ; /* Default: Don't touch packet memory */ - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; @@ -474,11 +473,6 @@ int main(int argc, char **argv) snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); prog_load_attr.file = filename; - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd)) return EXIT_FAIL; diff --git a/samples/bpf/xdp_sample_pkts_user.c b/samples/bpf/xdp_sample_pkts_user.c index 4b2a300c750c..706475e004cb 100644 --- a/samples/bpf/xdp_sample_pkts_user.c +++ b/samples/bpf/xdp_sample_pkts_user.c @@ -109,7 +109,6 @@ static void usage(const char *prog) int main(int argc, char **argv) { - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; @@ -143,11 +142,6 @@ int main(int argc, char **argv) return 1; } - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); prog_load_attr.file = filename; diff --git a/samples/bpf/xdp_tx_iptunnel_user.c b/samples/bpf/xdp_tx_iptunnel_user.c index a419bee151a8..1d4f305d02aa 100644 --- a/samples/bpf/xdp_tx_iptunnel_user.c +++ b/samples/bpf/xdp_tx_iptunnel_user.c @@ -155,7 +155,6 @@ int main(int argc, char **argv) struct bpf_prog_load_attr prog_load_attr = { .prog_type = BPF_PROG_TYPE_XDP, }; - struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; int min_port = 0, max_port = 0, vip2tnl_map_fd; const char *optstr = "i:a:p:s:d:m:T:P:FSNh"; unsigned char opt_flags[256] = {}; @@ -254,11 +253,6 @@ int main(int argc, char **argv) } } - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK, RLIM_INFINITY)"); - return 1; - } - if (!ifindex) { fprintf(stderr, "Invalid ifname\n"); return 1; diff --git a/samples/bpf/xdpsock.h b/samples/bpf/xdpsock.h index b7eca15c78cc..fd70cce60712 100644 --- a/samples/bpf/xdpsock.h +++ b/samples/bpf/xdpsock.h @@ -8,4 +8,12 @@ #define MAX_SOCKS 4 +#define SOCKET_NAME "sock_cal_bpf_fd" +#define MAX_NUM_OF_CLIENTS 10 + +#define CLOSE_CONN 1 + +typedef __u64 u64; +typedef __u32 u32; + #endif /* XDPSOCK_H */ diff --git a/samples/bpf/xdpsock_ctrl_proc.c b/samples/bpf/xdpsock_ctrl_proc.c new file mode 100644 index 000000000000..384e62e3c6d6 --- /dev/null +++ b/samples/bpf/xdpsock_ctrl_proc.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2018 Intel Corporation. */ + +#include <errno.h> +#include <getopt.h> +#include <libgen.h> +#include <net/if.h> +#include <stdio.h> +#include <stdlib.h> +#include <sys/socket.h> +#include <sys/un.h> +#include <unistd.h> + +#include <bpf/bpf.h> +#include <bpf/xsk.h> +#include "xdpsock.h" + +static const char *opt_if = ""; + +static struct option long_options[] = { + {"interface", required_argument, 0, 'i'}, + {0, 0, 0, 0} +}; + +static void usage(const char *prog) +{ + const char *str = + " Usage: %s [OPTIONS]\n" + " Options:\n" + " -i, --interface=n Run on interface n\n" + "\n"; + fprintf(stderr, "%s\n", str); + + exit(0); +} + +static void parse_command_line(int argc, char **argv) +{ + int option_index, c; + + opterr = 0; + + for (;;) { + c = getopt_long(argc, argv, "i:", + long_options, &option_index); + if (c == -1) + break; + + switch (c) { + case 'i': + opt_if = optarg; + break; + default: + usage(basename(argv[0])); + } + } +} + +static int send_xsks_map_fd(int sock, int fd) +{ + char cmsgbuf[CMSG_SPACE(sizeof(int))]; + struct msghdr msg; + struct iovec iov; + int value = 0; + + if (fd == -1) { + fprintf(stderr, "Incorrect fd = %d\n", fd); + return -1; + } + iov.iov_base = &value; + iov.iov_len = sizeof(int); + + msg.msg_name = NULL; + msg.msg_namelen = 0; + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_flags = 0; + msg.msg_control = cmsgbuf; + msg.msg_controllen = CMSG_LEN(sizeof(int)); + + struct cmsghdr *cmsg = CMSG_FIRSTHDR(&msg); + + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_RIGHTS; + cmsg->cmsg_len = CMSG_LEN(sizeof(int)); + + *(int *)CMSG_DATA(cmsg) = fd; + int ret = sendmsg(sock, &msg, 0); + + if (ret == -1) { + fprintf(stderr, "Sendmsg failed with %s", strerror(errno)); + return -errno; + } + + return ret; +} + +int +main(int argc, char **argv) +{ + struct sockaddr_un server; + int listening = 1; + int rval, msgsock; + int ifindex = 0; + int flag = 1; + int cmd = 0; + int sock; + int err; + int xsks_map_fd; + + parse_command_line(argc, argv); + + ifindex = if_nametoindex(opt_if); + if (ifindex == 0) { + fprintf(stderr, "Unable to get ifindex for Interface %s. Reason:%s", + opt_if, strerror(errno)); + return -errno; + } + + sock = socket(AF_UNIX, SOCK_STREAM, 0); + if (sock < 0) { + fprintf(stderr, "Opening socket stream failed: %s", strerror(errno)); + return -errno; + } + + server.sun_family = AF_UNIX; + strcpy(server.sun_path, SOCKET_NAME); + + setsockopt(sock, SOL_SOCKET, SO_REUSEADDR, &flag, sizeof(int)); + + if (bind(sock, (struct sockaddr *)&server, sizeof(struct sockaddr_un))) { + fprintf(stderr, "Binding to socket stream failed: %s", strerror(errno)); + return -errno; + } + + listen(sock, MAX_NUM_OF_CLIENTS); + + err = xsk_setup_xdp_prog(ifindex, &xsks_map_fd); + if (err) { + fprintf(stderr, "Setup of xdp program failed\n"); + goto close_sock; + } + + while (listening) { + msgsock = accept(sock, 0, 0); + if (msgsock == -1) { + fprintf(stderr, "Error accepting connection: %s", strerror(errno)); + err = -errno; + goto close_sock; + } + err = send_xsks_map_fd(msgsock, xsks_map_fd); + if (err <= 0) { + fprintf(stderr, "Error %d sending xsks_map_fd\n", err); + goto cleanup; + } + do { + rval = read(msgsock, &cmd, sizeof(int)); + if (rval < 0) { + fprintf(stderr, "Error reading stream message"); + } else { + if (cmd != CLOSE_CONN) + fprintf(stderr, "Recv unknown cmd = %d\n", cmd); + listening = 0; + break; + } + } while (rval > 0); + } + close(msgsock); + close(sock); + unlink(SOCKET_NAME); + + /* Unset fd for given ifindex */ + err = bpf_set_link_xdp_fd(ifindex, -1, 0); + if (err) { + fprintf(stderr, "Error when unsetting bpf prog_fd for ifindex(%d)\n", ifindex); + return err; + } + + return 0; + +cleanup: + close(msgsock); +close_sock: + close(sock); + unlink(SOCKET_NAME); + return err; +} diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index 1149e94ca32f..568f9815bb1b 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -24,10 +24,12 @@ #include <stdio.h> #include <stdlib.h> #include <string.h> +#include <sys/capability.h> #include <sys/mman.h> #include <sys/resource.h> #include <sys/socket.h> #include <sys/types.h> +#include <sys/un.h> #include <time.h> #include <unistd.h> @@ -95,6 +97,8 @@ static int opt_timeout = 1000; static bool opt_need_wakeup = true; static u32 opt_num_xsks = 1; static u32 prog_id; +static bool opt_busy_poll; +static bool opt_reduced_cap; struct xsk_ring_stats { unsigned long rx_npkts; @@ -153,6 +157,7 @@ struct xsk_socket_info { static int num_socks; struct xsk_socket_info *xsks[MAX_SOCKS]; +int sock; static unsigned long get_nsecs(void) { @@ -460,6 +465,7 @@ static void *poller(void *arg) static void remove_xdp_program(void) { u32 curr_prog_id = 0; + int cmd = CLOSE_CONN; if (bpf_get_link_xdp_id(opt_ifindex, &curr_prog_id, opt_xdp_flags)) { printf("bpf_get_link_xdp_id failed\n"); @@ -471,6 +477,13 @@ static void remove_xdp_program(void) printf("couldn't find a prog id on a given interface\n"); else printf("program on interface changed, not removing\n"); + + if (opt_reduced_cap) { + if (write(sock, &cmd, sizeof(int)) < 0) { + fprintf(stderr, "Error writing into stream socket: %s", strerror(errno)); + exit(EXIT_FAILURE); + } + } } static void int_exit(int sig) @@ -853,7 +866,7 @@ static struct xsk_socket_info *xsk_configure_socket(struct xsk_umem_info *umem, xsk->umem = umem; cfg.rx_size = XSK_RING_CONS__DEFAULT_NUM_DESCS; cfg.tx_size = XSK_RING_PROD__DEFAULT_NUM_DESCS; - if (opt_num_xsks > 1) + if (opt_num_xsks > 1 || opt_reduced_cap) cfg.libbpf_flags = XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD; else cfg.libbpf_flags = 0; @@ -911,6 +924,8 @@ static struct option long_options[] = { {"quiet", no_argument, 0, 'Q'}, {"app-stats", no_argument, 0, 'a'}, {"irq-string", no_argument, 0, 'I'}, + {"busy-poll", no_argument, 0, 'B'}, + {"reduce-cap", no_argument, 0, 'R'}, {0, 0, 0, 0} }; @@ -933,7 +948,7 @@ static void usage(const char *prog) " -m, --no-need-wakeup Turn off use of driver need wakeup flag.\n" " -f, --frame-size=n Set the frame size (must be a power of two in aligned mode, default is %d).\n" " -u, --unaligned Enable unaligned chunk placement\n" - " -M, --shared-umem Enable XDP_SHARED_UMEM\n" + " -M, --shared-umem Enable XDP_SHARED_UMEM (cannot be used with -R)\n" " -F, --force Force loading the XDP prog\n" " -d, --duration=n Duration in secs to run command.\n" " Default: forever.\n" @@ -949,6 +964,8 @@ static void usage(const char *prog) " -Q, --quiet Do not display any stats.\n" " -a, --app-stats Display application (syscall) statistics.\n" " -I, --irq-string Display driver interrupt statistics for interface associated with irq-string.\n" + " -B, --busy-poll Busy poll.\n" + " -R, --reduce-cap Use reduced capabilities (cannot be used with -M)\n" "\n"; fprintf(stderr, str, prog, XSK_UMEM__DEFAULT_FRAME_SIZE, opt_batch_size, MIN_PKT_SIZE, MIN_PKT_SIZE, @@ -964,7 +981,7 @@ static void parse_command_line(int argc, char **argv) opterr = 0; for (;;) { - c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:xQaI:", + c = getopt_long(argc, argv, "Frtli:q:pSNn:czf:muMd:b:C:s:P:xQaI:BR", long_options, &option_index); if (c == -1) break; @@ -1062,7 +1079,12 @@ static void parse_command_line(int argc, char **argv) fprintf(stderr, "ERROR: Failed to get irqs for %s\n", opt_irq_str); usage(basename(argv[0])); } - + break; + case 'B': + opt_busy_poll = 1; + break; + case 'R': + opt_reduced_cap = true; break; default: usage(basename(argv[0])); @@ -1085,6 +1107,11 @@ static void parse_command_line(int argc, char **argv) opt_xsk_frame_size); usage(basename(argv[0])); } + + if (opt_reduced_cap && opt_num_xsks > 1) { + fprintf(stderr, "ERROR: -M and -R cannot be used together\n"); + usage(basename(argv[0])); + } } static void kick_tx(struct xsk_socket_info *xsk) @@ -1098,8 +1125,7 @@ static void kick_tx(struct xsk_socket_info *xsk) exit_with_error(errno); } -static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk, - struct pollfd *fds) +static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk) { struct xsk_umem_info *umem = xsk->umem; u32 idx_cq = 0, idx_fq = 0; @@ -1132,9 +1158,10 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk, while (ret != rcvd) { if (ret < 0) exit_with_error(-ret); - if (xsk_ring_prod__needs_wakeup(&umem->fq)) { + if (opt_busy_poll || xsk_ring_prod__needs_wakeup(&umem->fq)) { xsk->app_stats.fill_fail_polls++; - ret = poll(fds, num_socks, opt_timeout); + recvfrom(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, + NULL); } ret = xsk_ring_prod__reserve(&umem->fq, rcvd, &idx_fq); } @@ -1146,7 +1173,6 @@ static inline void complete_tx_l2fwd(struct xsk_socket_info *xsk, xsk_ring_prod__submit(&xsk->umem->fq, rcvd); xsk_ring_cons__release(&xsk->umem->cq, rcvd); xsk->outstanding_tx -= rcvd; - xsk->ring_stats.tx_npkts += rcvd; } } @@ -1168,11 +1194,10 @@ static inline void complete_tx_only(struct xsk_socket_info *xsk, if (rcvd > 0) { xsk_ring_cons__release(&xsk->umem->cq, rcvd); xsk->outstanding_tx -= rcvd; - xsk->ring_stats.tx_npkts += rcvd; } } -static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds) +static void rx_drop(struct xsk_socket_info *xsk) { unsigned int rcvd, i; u32 idx_rx = 0, idx_fq = 0; @@ -1180,9 +1205,9 @@ static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds) rcvd = xsk_ring_cons__peek(&xsk->rx, opt_batch_size, &idx_rx); if (!rcvd) { - if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + if (opt_busy_poll || xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { xsk->app_stats.rx_empty_polls++; - ret = poll(fds, num_socks, opt_timeout); + recvfrom(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, NULL); } return; } @@ -1191,9 +1216,9 @@ static void rx_drop(struct xsk_socket_info *xsk, struct pollfd *fds) while (ret != rcvd) { if (ret < 0) exit_with_error(-ret); - if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + if (opt_busy_poll || xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { xsk->app_stats.fill_fail_polls++; - ret = poll(fds, num_socks, opt_timeout); + recvfrom(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, NULL); } ret = xsk_ring_prod__reserve(&xsk->umem->fq, rcvd, &idx_fq); } @@ -1235,7 +1260,7 @@ static void rx_drop_all(void) } for (i = 0; i < num_socks; i++) - rx_drop(xsks[i], fds); + rx_drop(xsks[i]); if (benchmark_done) break; @@ -1260,6 +1285,7 @@ static void tx_only(struct xsk_socket_info *xsk, u32 *frame_nb, int batch_size) } xsk_ring_prod__submit(&xsk->tx, batch_size); + xsk->ring_stats.tx_npkts += batch_size; xsk->outstanding_tx += batch_size; *frame_nb += batch_size; *frame_nb %= NUM_FRAMES; @@ -1332,29 +1358,30 @@ static void tx_only_all(void) complete_tx_only_all(); } -static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds) +static void l2fwd(struct xsk_socket_info *xsk) { unsigned int rcvd, i; u32 idx_rx = 0, idx_tx = 0; int ret; - complete_tx_l2fwd(xsk, fds); + complete_tx_l2fwd(xsk); rcvd = xsk_ring_cons__peek(&xsk->rx, opt_batch_size, &idx_rx); if (!rcvd) { - if (xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { + if (opt_busy_poll || xsk_ring_prod__needs_wakeup(&xsk->umem->fq)) { xsk->app_stats.rx_empty_polls++; - ret = poll(fds, num_socks, opt_timeout); + recvfrom(xsk_socket__fd(xsk->xsk), NULL, 0, MSG_DONTWAIT, NULL, NULL); } return; } + xsk->ring_stats.rx_npkts += rcvd; ret = xsk_ring_prod__reserve(&xsk->tx, rcvd, &idx_tx); while (ret != rcvd) { if (ret < 0) exit_with_error(-ret); - complete_tx_l2fwd(xsk, fds); - if (xsk_ring_prod__needs_wakeup(&xsk->tx)) { + complete_tx_l2fwd(xsk); + if (opt_busy_poll || xsk_ring_prod__needs_wakeup(&xsk->tx)) { xsk->app_stats.tx_wakeup_sendtos++; kick_tx(xsk); } @@ -1379,7 +1406,7 @@ static void l2fwd(struct xsk_socket_info *xsk, struct pollfd *fds) xsk_ring_prod__submit(&xsk->tx, rcvd); xsk_ring_cons__release(&xsk->rx, rcvd); - xsk->ring_stats.rx_npkts += rcvd; + xsk->ring_stats.tx_npkts += rcvd; xsk->outstanding_tx += rcvd; } @@ -1388,22 +1415,20 @@ static void l2fwd_all(void) struct pollfd fds[MAX_SOCKS] = {}; int i, ret; - for (i = 0; i < num_socks; i++) { - fds[i].fd = xsk_socket__fd(xsks[i]->xsk); - fds[i].events = POLLOUT | POLLIN; - } - for (;;) { if (opt_poll) { - for (i = 0; i < num_socks; i++) + for (i = 0; i < num_socks; i++) { + fds[i].fd = xsk_socket__fd(xsks[i]->xsk); + fds[i].events = POLLOUT | POLLIN; xsks[i]->app_stats.opt_polls++; + } ret = poll(fds, num_socks, opt_timeout); if (ret <= 0) continue; } for (i = 0; i < num_socks; i++) - l2fwd(xsks[i], fds); + l2fwd(xsks[i]); if (benchmark_done) break; @@ -1461,26 +1486,139 @@ static void enter_xsks_into_map(struct bpf_object *obj) } } +static void apply_setsockopt(struct xsk_socket_info *xsk) +{ + int sock_opt; + + if (!opt_busy_poll) + return; + + sock_opt = 1; + if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_PREFER_BUSY_POLL, + (void *)&sock_opt, sizeof(sock_opt)) < 0) + exit_with_error(errno); + + sock_opt = 20; + if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_BUSY_POLL, + (void *)&sock_opt, sizeof(sock_opt)) < 0) + exit_with_error(errno); + + sock_opt = opt_batch_size; + if (setsockopt(xsk_socket__fd(xsk->xsk), SOL_SOCKET, SO_BUSY_POLL_BUDGET, + (void *)&sock_opt, sizeof(sock_opt)) < 0) + exit_with_error(errno); +} + +static int recv_xsks_map_fd_from_ctrl_node(int sock, int *_fd) +{ + char cms[CMSG_SPACE(sizeof(int))]; + struct cmsghdr *cmsg; + struct msghdr msg; + struct iovec iov; + int value; + int len; + + iov.iov_base = &value; + iov.iov_len = sizeof(int); + + msg.msg_name = 0; + msg.msg_namelen = 0; + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_flags = 0; + msg.msg_control = (caddr_t)cms; + msg.msg_controllen = sizeof(cms); + + len = recvmsg(sock, &msg, 0); + + if (len < 0) { + fprintf(stderr, "Recvmsg failed length incorrect.\n"); + return -EINVAL; + } + + if (len == 0) { + fprintf(stderr, "Recvmsg failed no data\n"); + return -EINVAL; + } + + cmsg = CMSG_FIRSTHDR(&msg); + *_fd = *(int *)CMSG_DATA(cmsg); + + return 0; +} + +static int +recv_xsks_map_fd(int *xsks_map_fd) +{ + struct sockaddr_un server; + int err; + + sock = socket(AF_UNIX, SOCK_STREAM, 0); + if (sock < 0) { + fprintf(stderr, "Error opening socket stream: %s", strerror(errno)); + return errno; + } + + server.sun_family = AF_UNIX; + strcpy(server.sun_path, SOCKET_NAME); + + if (connect(sock, (struct sockaddr *)&server, sizeof(struct sockaddr_un)) < 0) { + close(sock); + fprintf(stderr, "Error connecting stream socket: %s", strerror(errno)); + return errno; + } + + err = recv_xsks_map_fd_from_ctrl_node(sock, xsks_map_fd); + if (err) { + fprintf(stderr, "Error %d receiving fd\n", err); + return err; + } + return 0; +} + int main(int argc, char **argv) { + struct __user_cap_header_struct hdr = { _LINUX_CAPABILITY_VERSION_3, 0 }; + struct __user_cap_data_struct data[2] = { { 0 } }; struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; bool rx = false, tx = false; struct xsk_umem_info *umem; struct bpf_object *obj; + int xsks_map_fd = 0; pthread_t pt; int i, ret; void *bufs; parse_command_line(argc, argv); - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - fprintf(stderr, "ERROR: setrlimit(RLIMIT_MEMLOCK) \"%s\"\n", - strerror(errno)); - exit(EXIT_FAILURE); - } + if (opt_reduced_cap) { + if (capget(&hdr, data) < 0) + fprintf(stderr, "Error getting capabilities\n"); + + data->effective &= CAP_TO_MASK(CAP_NET_RAW); + data->permitted &= CAP_TO_MASK(CAP_NET_RAW); + + if (capset(&hdr, data) < 0) + fprintf(stderr, "Setting capabilities failed\n"); - if (opt_num_xsks > 1) - load_xdp_program(argv, &obj); + if (capget(&hdr, data) < 0) { + fprintf(stderr, "Error getting capabilities\n"); + } else { + fprintf(stderr, "Capabilities EFF %x Caps INH %x Caps Per %x\n", + data[0].effective, data[0].inheritable, data[0].permitted); + fprintf(stderr, "Capabilities EFF %x Caps INH %x Caps Per %x\n", + data[1].effective, data[1].inheritable, data[1].permitted); + } + } else { + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + fprintf(stderr, "ERROR: setrlimit(RLIMIT_MEMLOCK) \"%s\"\n", + strerror(errno)); + exit(EXIT_FAILURE); + } + + if (opt_num_xsks > 1) + load_xdp_program(argv, &obj); + } /* Reserve memory for the umem. Use hugepages if unaligned chunk mode */ bufs = mmap(NULL, NUM_FRAMES * opt_xsk_frame_size, @@ -1502,6 +1640,9 @@ int main(int argc, char **argv) for (i = 0; i < opt_num_xsks; i++) xsks[num_socks++] = xsk_configure_socket(umem, rx, tx); + for (i = 0; i < opt_num_xsks; i++) + apply_setsockopt(xsks[i]); + if (opt_bench == BENCH_TXONLY) { gen_eth_hdr_data(); @@ -1512,6 +1653,21 @@ int main(int argc, char **argv) if (opt_num_xsks > 1 && opt_bench != BENCH_TXONLY) enter_xsks_into_map(obj); + if (opt_reduced_cap) { + ret = recv_xsks_map_fd(&xsks_map_fd); + if (ret) { + fprintf(stderr, "Error %d receiving xsks_map_fd\n", ret); + exit_with_error(ret); + } + if (xsks[0]->xsk) { + ret = xsk_socket__update_xskmap(xsks[0]->xsk, xsks_map_fd); + if (ret) { + fprintf(stderr, "Update of BPF map failed(%d)\n", ret); + exit_with_error(ret); + } + } + } + signal(SIGINT, int_exit); signal(SIGTERM, int_exit); signal(SIGABRT, int_exit); diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal index 02b892421f7a..d49ec001825d 100644 --- a/scripts/Makefile.modfinal +++ b/scripts/Makefile.modfinal @@ -38,7 +38,12 @@ quiet_cmd_ld_ko_o = LD [M] $@ $(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true) quiet_cmd_btf_ko = BTF [M] $@ - cmd_btf_ko = LLVM_OBJCOPY=$(OBJCOPY) $(PAHOLE) -J --btf_base vmlinux $@ + cmd_btf_ko = \ + if [ -f vmlinux ]; then \ + LLVM_OBJCOPY=$(OBJCOPY) $(PAHOLE) -J --btf_base vmlinux $@; \ + else \ + printf "Skipping BTF generation for %s due to unavailability of vmlinux\n" $@ 1>&2; \ + fi; # Same as newer-prereqs, but allows to exclude specified extra dependencies newer_prereqs_except = $(filter-out $(PHONY) $(1),$?) @@ -49,7 +54,7 @@ if_changed_except = $(if $(call newer_prereqs_except,$(2))$(cmd-check), \ printf '%s\n' 'cmd_$@ := $(make-cmd)' > $(dot-target).cmd, @:) # Re-generate module BTFs if either module's .ko or vmlinux changed -$(modules): %.ko: %.o %.mod.o scripts/module.lds vmlinux FORCE +$(modules): %.ko: %.o %.mod.o scripts/module.lds $(if $(KBUILD_BUILTIN),vmlinux) FORCE +$(call if_changed_except,ld_ko_o,vmlinux) ifdef CONFIG_DEBUG_INFO_BTF_MODULES +$(if $(newer-prereqs),$(call cmd,btf_ko)) diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py index 31484377b8b1..8b829748d488 100755 --- a/scripts/bpf_helpers_doc.py +++ b/scripts/bpf_helpers_doc.py @@ -418,6 +418,7 @@ class PrinterHelpers(Printer): 'struct bpf_tcp_sock', 'struct bpf_tunnel_key', 'struct bpf_xfrm_state', + 'struct linux_binprm', 'struct pt_regs', 'struct sk_reuseport_md', 'struct sockaddr', @@ -435,6 +436,7 @@ class PrinterHelpers(Printer): 'struct xdp_md', 'struct path', 'struct btf_ptr', + 'struct inode', ] known_types = { '...', @@ -465,6 +467,7 @@ class PrinterHelpers(Printer): 'struct bpf_tcp_sock', 'struct bpf_tunnel_key', 'struct bpf_xfrm_state', + 'struct linux_binprm', 'struct pt_regs', 'struct sk_reuseport_md', 'struct sockaddr', @@ -478,6 +481,7 @@ class PrinterHelpers(Printer): 'struct task_struct', 'struct path', 'struct btf_ptr', + 'struct inode', } mapped_types = { 'u8': '__u8', diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 2d1af8899cab..cb2deaa188e7 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -501,37 +501,14 @@ int ima_file_check(struct file *file, int mask) } EXPORT_SYMBOL_GPL(ima_file_check); -/** - * ima_file_hash - return the stored measurement if a file has been hashed and - * is in the iint cache. - * @file: pointer to the file - * @buf: buffer in which to store the hash - * @buf_size: length of the buffer - * - * On success, return the hash algorithm (as defined in the enum hash_algo). - * If buf is not NULL, this function also outputs the hash into buf. - * If the hash is larger than buf_size, then only buf_size bytes will be copied. - * It generally just makes sense to pass a buffer capable of holding the largest - * possible hash: IMA_MAX_DIGEST_SIZE. - * The file hash returned is based on the entire file, including the appended - * signature. - * - * If IMA is disabled or if no measurement is available, return -EOPNOTSUPP. - * If the parameters are incorrect, return -EINVAL. - */ -int ima_file_hash(struct file *file, char *buf, size_t buf_size) +static int __ima_inode_hash(struct inode *inode, char *buf, size_t buf_size) { - struct inode *inode; struct integrity_iint_cache *iint; int hash_algo; - if (!file) - return -EINVAL; - if (!ima_policy_flag) return -EOPNOTSUPP; - inode = file_inode(file); iint = integrity_iint_find(inode); if (!iint) return -EOPNOTSUPP; @@ -558,9 +535,62 @@ int ima_file_hash(struct file *file, char *buf, size_t buf_size) return hash_algo; } + +/** + * ima_file_hash - return the stored measurement if a file has been hashed and + * is in the iint cache. + * @file: pointer to the file + * @buf: buffer in which to store the hash + * @buf_size: length of the buffer + * + * On success, return the hash algorithm (as defined in the enum hash_algo). + * If buf is not NULL, this function also outputs the hash into buf. + * If the hash is larger than buf_size, then only buf_size bytes will be copied. + * It generally just makes sense to pass a buffer capable of holding the largest + * possible hash: IMA_MAX_DIGEST_SIZE. + * The file hash returned is based on the entire file, including the appended + * signature. + * + * If IMA is disabled or if no measurement is available, return -EOPNOTSUPP. + * If the parameters are incorrect, return -EINVAL. + */ +int ima_file_hash(struct file *file, char *buf, size_t buf_size) +{ + if (!file) + return -EINVAL; + + return __ima_inode_hash(file_inode(file), buf, buf_size); +} EXPORT_SYMBOL_GPL(ima_file_hash); /** + * ima_inode_hash - return the stored measurement if the inode has been hashed + * and is in the iint cache. + * @inode: pointer to the inode + * @buf: buffer in which to store the hash + * @buf_size: length of the buffer + * + * On success, return the hash algorithm (as defined in the enum hash_algo). + * If buf is not NULL, this function also outputs the hash into buf. + * If the hash is larger than buf_size, then only buf_size bytes will be copied. + * It generally just makes sense to pass a buffer capable of holding the largest + * possible hash: IMA_MAX_DIGEST_SIZE. + * The hash returned is based on the entire contents, including the appended + * signature. + * + * If IMA is disabled or if no measurement is available, return -EOPNOTSUPP. + * If the parameters are incorrect, return -EINVAL. + */ +int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size) +{ + if (!inode) + return -EINVAL; + + return __ima_inode_hash(inode, buf, buf_size); +} +EXPORT_SYMBOL_GPL(ima_inode_hash); + +/** * ima_post_create_tmpfile - mark newly created tmpfile as new * @file : newly created tmpfile * diff --git a/tools/bpf/bpftool/btf.c b/tools/bpf/bpftool/btf.c index c873a7999aba..fe9e7b3a4b50 100644 --- a/tools/bpf/bpftool/btf.c +++ b/tools/bpf/bpftool/btf.c @@ -357,11 +357,13 @@ static int dump_btf_raw(const struct btf *btf, dump_btf_type(btf, root_type_ids[i], t); } } else { + const struct btf *base; int cnt = btf__get_nr_types(btf); int start_id = 1; - if (base_btf) - start_id = btf__get_nr_types(base_btf) + 1; + base = btf__base_btf(btf); + if (base) + start_id = btf__get_nr_types(base) + 1; for (i = start_id; i <= cnt; i++) { t = btf__type_by_id(btf, i); @@ -428,7 +430,7 @@ done: static int do_dump(int argc, char **argv) { - struct btf *btf = NULL; + struct btf *btf = NULL, *base = NULL; __u32 root_type_ids[2]; int root_type_cnt = 0; bool dump_c = false; @@ -502,7 +504,21 @@ static int do_dump(int argc, char **argv) } NEXT_ARG(); } else if (is_prefix(src, "file")) { - btf = btf__parse_split(*argv, base_btf); + const char sysfs_prefix[] = "/sys/kernel/btf/"; + const char sysfs_vmlinux[] = "/sys/kernel/btf/vmlinux"; + + if (!base_btf && + strncmp(*argv, sysfs_prefix, sizeof(sysfs_prefix) - 1) == 0 && + strcmp(*argv, sysfs_vmlinux) != 0) { + base = btf__parse(sysfs_vmlinux, NULL); + if (libbpf_get_error(base)) { + p_err("failed to parse vmlinux BTF at '%s': %ld\n", + sysfs_vmlinux, libbpf_get_error(base)); + base = NULL; + } + } + + btf = btf__parse_split(*argv, base ?: base_btf); if (IS_ERR(btf)) { err = -PTR_ERR(btf); btf = NULL; @@ -567,6 +583,7 @@ static int do_dump(int argc, char **argv) done: close(fd); btf__free(btf); + btf__free(base); return err; } @@ -751,6 +768,8 @@ show_btf_plain(struct bpf_btf_info *info, int fd, printf("name [%s] ", name); else if (name && name[0]) printf("name %s ", name); + else + printf("name <anon> "); printf("size %uB", info->btf_size); n = 0; diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index acdb2c245f0a..1fe3ba255bad 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -1717,6 +1717,34 @@ struct profile_metric { .ratio_desc = "LLC misses per million insns", .ratio_mul = 1e6, }, + { + .name = "itlb_misses", + .attr = { + .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_ITLB | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_MISS << 16), + .exclude_user = 1 + }, + .ratio_metric = 2, + .ratio_desc = "itlb misses per million insns", + .ratio_mul = 1e6, + }, + { + .name = "dtlb_misses", + .attr = { + .type = PERF_TYPE_HW_CACHE, + .config = + PERF_COUNT_HW_CACHE_DTLB | + (PERF_COUNT_HW_CACHE_OP_READ << 8) | + (PERF_COUNT_HW_CACHE_RESULT_MISS << 16), + .exclude_user = 1 + }, + .ratio_metric = 2, + .ratio_desc = "dtlb misses per million insns", + .ratio_mul = 1e6, + }, }; static __u64 profile_total_count; @@ -2109,7 +2137,7 @@ static int do_help(int argc, char **argv) " struct_ops | fentry | fexit | freplace | sk_lookup }\n" " ATTACH_TYPE := { msg_verdict | stream_verdict | stream_parser |\n" " flow_dissector }\n" - " METRIC := { cycles | instructions | l1d_loads | llc_misses }\n" + " METRIC := { cycles | instructions | l1d_loads | llc_misses | itlb_misses | dtlb_misses }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, argv[-2]); diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c index dfa540d8a02d..e3ea569ee125 100644 --- a/tools/bpf/resolve_btfids/main.c +++ b/tools/bpf/resolve_btfids/main.c @@ -454,7 +454,7 @@ static int symbols_collect(struct object *obj) return -ENOMEM; if (id->addr_cnt >= ADDR_CNT) { - pr_err("FAILED symbol %s crossed the number of allowed lists", + pr_err("FAILED symbol %s crossed the number of allowed lists\n", id->name); return -1; } @@ -477,8 +477,8 @@ static int symbols_resolve(struct object *obj) btf = btf__parse(obj->btf ?: obj->path, NULL); err = libbpf_get_error(btf); if (err) { - pr_err("FAILED: load BTF from %s: %s", - obj->path, strerror(err)); + pr_err("FAILED: load BTF from %s: %s\n", + obj->path, strerror(-err)); return -1; } diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index 162999b12790..1233f14f659f 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -557,7 +557,12 @@ union bpf_attr { __aligned_u64 line_info; /* line info */ __u32 line_info_cnt; /* number of bpf_line_info records */ __u32 attach_btf_id; /* in-kernel BTF type id to attach to */ - __u32 attach_prog_fd; /* 0 to attach to vmlinux */ + union { + /* valid prog_fd to attach to bpf prog */ + __u32 attach_prog_fd; + /* or valid module BTF object fd or 0 to attach to vmlinux */ + __u32 attach_btf_obj_fd; + }; }; struct { /* anonymous struct used by BPF_OBJ_* commands */ @@ -3787,6 +3792,36 @@ union bpf_attr { * *ARG_PTR_TO_BTF_ID* of type *task_struct*. * Return * Pointer to the current task. + * + * long bpf_bprm_opts_set(struct linux_binprm *bprm, u64 flags) + * Description + * Set or clear certain options on *bprm*: + * + * **BPF_F_BPRM_SECUREEXEC** Set the secureexec bit + * which sets the **AT_SECURE** auxv for glibc. The bit + * is cleared if the flag is not specified. + * Return + * **-EINVAL** if invalid *flags* are passed, zero otherwise. + * + * u64 bpf_ktime_get_coarse_ns(void) + * Description + * Return a coarse-grained version of the time elapsed since + * system boot, in nanoseconds. Does not include time the system + * was suspended. + * + * See: **clock_gettime**\ (**CLOCK_MONOTONIC_COARSE**) + * Return + * Current *ktime*. + * + * long bpf_ima_inode_hash(struct inode *inode, void *dst, u32 size) + * Description + * Returns the stored IMA hash of the *inode* (if it's avaialable). + * If the hash is larger than *size*, then only *size* + * bytes will be copied to *dst* + * Return + * The **hash_algo** is returned on success, + * **-EOPNOTSUP** if IMA is disabled or **-EINVAL** if + * invalid arguments are passed. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -3948,6 +3983,9 @@ union bpf_attr { FN(task_storage_get), \ FN(task_storage_delete), \ FN(get_current_task_btf), \ + FN(bprm_opts_set), \ + FN(ktime_get_coarse_ns), \ + FN(ima_inode_hash), \ /* */ /* integer value in 'imm' field of BPF_CALL instruction selects which helper @@ -4119,6 +4157,11 @@ enum bpf_lwt_encap_mode { BPF_LWT_ENCAP_IP, }; +/* Flags for bpf_bprm_opts_set helper */ +enum { + BPF_F_BPRM_SECUREEXEC = (1ULL << 0), +}; + #define __bpf_md_ptr(type, name) \ union { \ type name; \ diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index d27e34133973..bba48ff4c5c0 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -67,11 +67,12 @@ static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, static inline int sys_bpf_prog_load(union bpf_attr *attr, unsigned int size) { + int retries = 5; int fd; do { fd = sys_bpf(BPF_PROG_LOAD, attr, size); - } while (fd < 0 && errno == EAGAIN); + } while (fd < 0 && errno == EAGAIN && retries-- > 0); return fd; } @@ -214,59 +215,55 @@ alloc_zero_tailing_info(const void *orecord, __u32 cnt, return info; } -int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, - char *log_buf, size_t log_buf_sz) +int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr) { void *finfo = NULL, *linfo = NULL; union bpf_attr attr; - __u32 log_level; int fd; - if (!load_attr || !log_buf != !log_buf_sz) + if (!load_attr->log_buf != !load_attr->log_buf_sz) return -EINVAL; - log_level = load_attr->log_level; - if (log_level > (4 | 2 | 1) || (log_level && !log_buf)) + if (load_attr->log_level > (4 | 2 | 1) || (load_attr->log_level && !load_attr->log_buf)) return -EINVAL; memset(&attr, 0, sizeof(attr)); attr.prog_type = load_attr->prog_type; attr.expected_attach_type = load_attr->expected_attach_type; - if (attr.prog_type == BPF_PROG_TYPE_STRUCT_OPS || - attr.prog_type == BPF_PROG_TYPE_LSM) { - attr.attach_btf_id = load_attr->attach_btf_id; - } else if (attr.prog_type == BPF_PROG_TYPE_TRACING || - attr.prog_type == BPF_PROG_TYPE_EXT) { - attr.attach_btf_id = load_attr->attach_btf_id; + + if (load_attr->attach_prog_fd) attr.attach_prog_fd = load_attr->attach_prog_fd; - } else { - attr.prog_ifindex = load_attr->prog_ifindex; - attr.kern_version = load_attr->kern_version; - } - attr.insn_cnt = (__u32)load_attr->insns_cnt; + else + attr.attach_btf_obj_fd = load_attr->attach_btf_obj_fd; + attr.attach_btf_id = load_attr->attach_btf_id; + + attr.prog_ifindex = load_attr->prog_ifindex; + attr.kern_version = load_attr->kern_version; + + attr.insn_cnt = (__u32)load_attr->insn_cnt; attr.insns = ptr_to_u64(load_attr->insns); attr.license = ptr_to_u64(load_attr->license); - attr.log_level = log_level; - if (log_level) { - attr.log_buf = ptr_to_u64(log_buf); - attr.log_size = log_buf_sz; - } else { - attr.log_buf = ptr_to_u64(NULL); - attr.log_size = 0; + attr.log_level = load_attr->log_level; + if (attr.log_level) { + attr.log_buf = ptr_to_u64(load_attr->log_buf); + attr.log_size = load_attr->log_buf_sz; } attr.prog_btf_fd = load_attr->prog_btf_fd; + attr.prog_flags = load_attr->prog_flags; + attr.func_info_rec_size = load_attr->func_info_rec_size; attr.func_info_cnt = load_attr->func_info_cnt; attr.func_info = ptr_to_u64(load_attr->func_info); + attr.line_info_rec_size = load_attr->line_info_rec_size; attr.line_info_cnt = load_attr->line_info_cnt; attr.line_info = ptr_to_u64(load_attr->line_info); + if (load_attr->name) memcpy(attr.prog_name, load_attr->name, - min(strlen(load_attr->name), BPF_OBJ_NAME_LEN - 1)); - attr.prog_flags = load_attr->prog_flags; + min(strlen(load_attr->name), (size_t)BPF_OBJ_NAME_LEN - 1)); fd = sys_bpf_prog_load(&attr, sizeof(attr)); if (fd >= 0) @@ -306,19 +303,19 @@ int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, } fd = sys_bpf_prog_load(&attr, sizeof(attr)); - if (fd >= 0) goto done; } - if (log_level || !log_buf) + if (load_attr->log_level || !load_attr->log_buf) goto done; /* Try again with log */ - attr.log_buf = ptr_to_u64(log_buf); - attr.log_size = log_buf_sz; + attr.log_buf = ptr_to_u64(load_attr->log_buf); + attr.log_size = load_attr->log_buf_sz; attr.log_level = 1; - log_buf[0] = 0; + load_attr->log_buf[0] = 0; + fd = sys_bpf_prog_load(&attr, sizeof(attr)); done: free(finfo); @@ -326,6 +323,49 @@ done: return fd; } +int bpf_load_program_xattr(const struct bpf_load_program_attr *load_attr, + char *log_buf, size_t log_buf_sz) +{ + struct bpf_prog_load_params p = {}; + + if (!load_attr || !log_buf != !log_buf_sz) + return -EINVAL; + + p.prog_type = load_attr->prog_type; + p.expected_attach_type = load_attr->expected_attach_type; + switch (p.prog_type) { + case BPF_PROG_TYPE_STRUCT_OPS: + case BPF_PROG_TYPE_LSM: + p.attach_btf_id = load_attr->attach_btf_id; + break; + case BPF_PROG_TYPE_TRACING: + case BPF_PROG_TYPE_EXT: + p.attach_btf_id = load_attr->attach_btf_id; + p.attach_prog_fd = load_attr->attach_prog_fd; + break; + default: + p.prog_ifindex = load_attr->prog_ifindex; + p.kern_version = load_attr->kern_version; + } + p.insn_cnt = load_attr->insns_cnt; + p.insns = load_attr->insns; + p.license = load_attr->license; + p.log_level = load_attr->log_level; + p.log_buf = log_buf; + p.log_buf_sz = log_buf_sz; + p.prog_btf_fd = load_attr->prog_btf_fd; + p.func_info_rec_size = load_attr->func_info_rec_size; + p.func_info_cnt = load_attr->func_info_cnt; + p.func_info = load_attr->func_info; + p.line_info_rec_size = load_attr->line_info_rec_size; + p.line_info_cnt = load_attr->line_info_cnt; + p.line_info = load_attr->line_info; + p.name = load_attr->name; + p.prog_flags = load_attr->prog_flags; + + return libbpf__bpf_prog_load(&p); +} + int bpf_load_program(enum bpf_prog_type type, const struct bpf_insn *insns, size_t insns_cnt, const char *license, __u32 kern_version, char *log_buf, diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c index 2d0d064c6d31..3c3f2bc6c652 100644 --- a/tools/lib/bpf/btf.c +++ b/tools/lib/bpf/btf.c @@ -432,6 +432,11 @@ __u32 btf__get_nr_types(const struct btf *btf) return btf->start_id + btf->nr_types - 1; } +const struct btf *btf__base_btf(const struct btf *btf) +{ + return btf->base_btf; +} + /* internal helper returning non-const pointer to a type */ static struct btf_type *btf_type_by_id(struct btf *btf, __u32 type_id) { @@ -674,12 +679,12 @@ int btf__resolve_type(const struct btf *btf, __u32 type_id) __s32 btf__find_by_name(const struct btf *btf, const char *type_name) { - __u32 i; + __u32 i, nr_types = btf__get_nr_types(btf); if (!strcmp(type_name, "void")) return 0; - for (i = 1; i <= btf->nr_types; i++) { + for (i = 1; i <= nr_types; i++) { const struct btf_type *t = btf__type_by_id(btf, i); const char *name = btf__name_by_offset(btf, t->name_off); @@ -693,12 +698,12 @@ __s32 btf__find_by_name(const struct btf *btf, const char *type_name) __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name, __u32 kind) { - __u32 i; + __u32 i, nr_types = btf__get_nr_types(btf); if (kind == BTF_KIND_UNKN || !strcmp(type_name, "void")) return 0; - for (i = 1; i <= btf->nr_types; i++) { + for (i = 1; i <= nr_types; i++) { const struct btf_type *t = btf__type_by_id(btf, i); const char *name; @@ -1318,35 +1323,27 @@ const char *btf__name_by_offset(const struct btf *btf, __u32 offset) return btf__str_by_offset(btf, offset); } -int btf__get_from_id(__u32 id, struct btf **btf) +struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf) { - struct bpf_btf_info btf_info = { 0 }; + struct bpf_btf_info btf_info; __u32 len = sizeof(btf_info); __u32 last_size; - int btf_fd; + struct btf *btf; void *ptr; int err; - err = 0; - *btf = NULL; - btf_fd = bpf_btf_get_fd_by_id(id); - if (btf_fd < 0) - return 0; - /* we won't know btf_size until we call bpf_obj_get_info_by_fd(). so * let's start with a sane default - 4KiB here - and resize it only if * bpf_obj_get_info_by_fd() needs a bigger buffer. */ - btf_info.btf_size = 4096; - last_size = btf_info.btf_size; + last_size = 4096; ptr = malloc(last_size); - if (!ptr) { - err = -ENOMEM; - goto exit_free; - } + if (!ptr) + return ERR_PTR(-ENOMEM); - memset(ptr, 0, last_size); + memset(&btf_info, 0, sizeof(btf_info)); btf_info.btf = ptr_to_u64(ptr); + btf_info.btf_size = last_size; err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); if (!err && btf_info.btf_size > last_size) { @@ -1355,31 +1352,48 @@ int btf__get_from_id(__u32 id, struct btf **btf) last_size = btf_info.btf_size; temp_ptr = realloc(ptr, last_size); if (!temp_ptr) { - err = -ENOMEM; + btf = ERR_PTR(-ENOMEM); goto exit_free; } ptr = temp_ptr; - memset(ptr, 0, last_size); + + len = sizeof(btf_info); + memset(&btf_info, 0, sizeof(btf_info)); btf_info.btf = ptr_to_u64(ptr); + btf_info.btf_size = last_size; + err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len); } if (err || btf_info.btf_size > last_size) { - err = errno; + btf = err ? ERR_PTR(-errno) : ERR_PTR(-E2BIG); goto exit_free; } - *btf = btf__new((__u8 *)(long)btf_info.btf, btf_info.btf_size); - if (IS_ERR(*btf)) { - err = PTR_ERR(*btf); - *btf = NULL; - } + btf = btf_new(ptr, btf_info.btf_size, base_btf); exit_free: - close(btf_fd); free(ptr); + return btf; +} - return err; +int btf__get_from_id(__u32 id, struct btf **btf) +{ + struct btf *res; + int btf_fd; + + *btf = NULL; + btf_fd = bpf_btf_get_fd_by_id(id); + if (btf_fd < 0) + return -errno; + + res = btf_get_from_fd(btf_fd, NULL); + close(btf_fd); + if (IS_ERR(res)) + return PTR_ERR(res); + + *btf = res; + return 0; } int btf__get_map_kv_tids(const struct btf *btf, const char *map_name, diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h index 1093f6fe6800..1237bcd1dd17 100644 --- a/tools/lib/bpf/btf.h +++ b/tools/lib/bpf/btf.h @@ -51,6 +51,7 @@ LIBBPF_API __s32 btf__find_by_name(const struct btf *btf, LIBBPF_API __s32 btf__find_by_name_kind(const struct btf *btf, const char *type_name, __u32 kind); LIBBPF_API __u32 btf__get_nr_types(const struct btf *btf); +LIBBPF_API const struct btf *btf__base_btf(const struct btf *btf); LIBBPF_API const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 id); LIBBPF_API size_t btf__pointer_size(const struct btf *btf); diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 28baee7ba1ca..9be88a90a4aa 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -176,6 +176,8 @@ enum kern_feature_id { FEAT_PROBE_READ_KERN, /* BPF_PROG_BIND_MAP is supported */ FEAT_PROG_BIND_MAP, + /* Kernel support for module BTFs */ + FEAT_MODULE_BTF, __FEAT_CNT, }; @@ -276,6 +278,7 @@ struct bpf_program { enum bpf_prog_type type; enum bpf_attach_type expected_attach_type; int prog_ifindex; + __u32 attach_btf_obj_fd; __u32 attach_btf_id; __u32 attach_prog_fd; void *func_info; @@ -402,6 +405,13 @@ struct extern_desc { static LIST_HEAD(bpf_objects_list); +struct module_btf { + struct btf *btf; + char *name; + __u32 id; + int fd; +}; + struct bpf_object { char name[BPF_OBJ_NAME_LEN]; char license[64]; @@ -462,11 +472,19 @@ struct bpf_object { struct list_head list; struct btf *btf; + struct btf_ext *btf_ext; + /* Parse and load BTF vmlinux if any of the programs in the object need * it at load time. */ struct btf *btf_vmlinux; - struct btf_ext *btf_ext; + /* vmlinux BTF override for CO-RE relocations */ + struct btf *btf_vmlinux_override; + /* Lazily initialized kernel module BTFs */ + struct module_btf *btf_modules; + bool btf_modules_loaded; + size_t btf_module_cnt; + size_t btf_module_cap; void *priv; bpf_object_clear_priv_t clear_priv; @@ -3960,6 +3978,35 @@ static int probe_prog_bind_map(void) return ret >= 0; } +static int probe_module_btf(void) +{ + static const char strs[] = "\0int"; + __u32 types[] = { + /* int */ + BTF_TYPE_INT_ENC(1, BTF_INT_SIGNED, 0, 32, 4), + }; + struct bpf_btf_info info; + __u32 len = sizeof(info); + char name[16]; + int fd, err; + + fd = libbpf__load_raw_btf((char *)types, sizeof(types), strs, sizeof(strs)); + if (fd < 0) + return 0; /* BTF not supported at all */ + + memset(&info, 0, sizeof(info)); + info.name = ptr_to_u64(name); + info.name_len = sizeof(name); + + /* check that BPF_OBJ_GET_INFO_BY_FD supports specifying name pointer; + * kernel's module BTF support coincides with support for + * name/name_len fields in struct bpf_btf_info. + */ + err = bpf_obj_get_info_by_fd(fd, &info, &len); + close(fd); + return !err; +} + enum kern_feature_result { FEAT_UNKNOWN = 0, FEAT_SUPPORTED = 1, @@ -4003,7 +4050,10 @@ static struct kern_feature_desc { }, [FEAT_PROG_BIND_MAP] = { "BPF_PROG_BIND_MAP support", probe_prog_bind_map, - } + }, + [FEAT_MODULE_BTF] = { + "module BTF support", probe_module_btf, + }, }; static bool kernel_supports(enum kern_feature_id feat_id) @@ -4603,46 +4653,43 @@ static size_t bpf_core_essential_name_len(const char *name) return n; } -/* dynamically sized list of type IDs */ -struct ids_vec { - __u32 *data; +struct core_cand +{ + const struct btf *btf; + const struct btf_type *t; + const char *name; + __u32 id; +}; + +/* dynamically sized list of type IDs and its associated struct btf */ +struct core_cand_list { + struct core_cand *cands; int len; }; -static void bpf_core_free_cands(struct ids_vec *cand_ids) +static void bpf_core_free_cands(struct core_cand_list *cands) { - free(cand_ids->data); - free(cand_ids); + free(cands->cands); + free(cands); } -static struct ids_vec *bpf_core_find_cands(const struct btf *local_btf, - __u32 local_type_id, - const struct btf *targ_btf) +static int bpf_core_add_cands(struct core_cand *local_cand, + size_t local_essent_len, + const struct btf *targ_btf, + const char *targ_btf_name, + int targ_start_id, + struct core_cand_list *cands) { - size_t local_essent_len, targ_essent_len; - const char *local_name, *targ_name; - const struct btf_type *t, *local_t; - struct ids_vec *cand_ids; - __u32 *new_ids; - int i, err, n; - - local_t = btf__type_by_id(local_btf, local_type_id); - if (!local_t) - return ERR_PTR(-EINVAL); - - local_name = btf__name_by_offset(local_btf, local_t->name_off); - if (str_is_empty(local_name)) - return ERR_PTR(-EINVAL); - local_essent_len = bpf_core_essential_name_len(local_name); - - cand_ids = calloc(1, sizeof(*cand_ids)); - if (!cand_ids) - return ERR_PTR(-ENOMEM); + struct core_cand *new_cands, *cand; + const struct btf_type *t; + const char *targ_name; + size_t targ_essent_len; + int n, i; n = btf__get_nr_types(targ_btf); - for (i = 1; i <= n; i++) { + for (i = targ_start_id; i <= n; i++) { t = btf__type_by_id(targ_btf, i); - if (btf_kind(t) != btf_kind(local_t)) + if (btf_kind(t) != btf_kind(local_cand->t)) continue; targ_name = btf__name_by_offset(targ_btf, t->name_off); @@ -4653,24 +4700,174 @@ static struct ids_vec *bpf_core_find_cands(const struct btf *local_btf, if (targ_essent_len != local_essent_len) continue; - if (strncmp(local_name, targ_name, local_essent_len) == 0) { - pr_debug("CO-RE relocating [%d] %s %s: found target candidate [%d] %s %s\n", - local_type_id, btf_kind_str(local_t), - local_name, i, btf_kind_str(t), targ_name); - new_ids = libbpf_reallocarray(cand_ids->data, - cand_ids->len + 1, - sizeof(*cand_ids->data)); - if (!new_ids) { - err = -ENOMEM; - goto err_out; - } - cand_ids->data = new_ids; - cand_ids->data[cand_ids->len++] = i; + if (strncmp(local_cand->name, targ_name, local_essent_len) != 0) + continue; + + pr_debug("CO-RE relocating [%d] %s %s: found target candidate [%d] %s %s in [%s]\n", + local_cand->id, btf_kind_str(local_cand->t), + local_cand->name, i, btf_kind_str(t), targ_name, + targ_btf_name); + new_cands = libbpf_reallocarray(cands->cands, cands->len + 1, + sizeof(*cands->cands)); + if (!new_cands) + return -ENOMEM; + + cand = &new_cands[cands->len]; + cand->btf = targ_btf; + cand->t = t; + cand->name = targ_name; + cand->id = i; + + cands->cands = new_cands; + cands->len++; + } + return 0; +} + +static int load_module_btfs(struct bpf_object *obj) +{ + struct bpf_btf_info info; + struct module_btf *mod_btf; + struct btf *btf; + char name[64]; + __u32 id = 0, len; + int err, fd; + + if (obj->btf_modules_loaded) + return 0; + + /* don't do this again, even if we find no module BTFs */ + obj->btf_modules_loaded = true; + + /* kernel too old to support module BTFs */ + if (!kernel_supports(FEAT_MODULE_BTF)) + return 0; + + while (true) { + err = bpf_btf_get_next_id(id, &id); + if (err && errno == ENOENT) + return 0; + if (err) { + err = -errno; + pr_warn("failed to iterate BTF objects: %d\n", err); + return err; + } + + fd = bpf_btf_get_fd_by_id(id); + if (fd < 0) { + if (errno == ENOENT) + continue; /* expected race: BTF was unloaded */ + err = -errno; + pr_warn("failed to get BTF object #%d FD: %d\n", id, err); + return err; + } + + len = sizeof(info); + memset(&info, 0, sizeof(info)); + info.name = ptr_to_u64(name); + info.name_len = sizeof(name); + + err = bpf_obj_get_info_by_fd(fd, &info, &len); + if (err) { + err = -errno; + pr_warn("failed to get BTF object #%d info: %d\n", id, err); + goto err_out; + } + + /* ignore non-module BTFs */ + if (!info.kernel_btf || strcmp(name, "vmlinux") == 0) { + close(fd); + continue; } + + btf = btf_get_from_fd(fd, obj->btf_vmlinux); + if (IS_ERR(btf)) { + pr_warn("failed to load module [%s]'s BTF object #%d: %ld\n", + name, id, PTR_ERR(btf)); + err = PTR_ERR(btf); + goto err_out; + } + + err = btf_ensure_mem((void **)&obj->btf_modules, &obj->btf_module_cap, + sizeof(*obj->btf_modules), obj->btf_module_cnt + 1); + if (err) + goto err_out; + + mod_btf = &obj->btf_modules[obj->btf_module_cnt++]; + + mod_btf->btf = btf; + mod_btf->id = id; + mod_btf->fd = fd; + mod_btf->name = strdup(name); + if (!mod_btf->name) { + err = -ENOMEM; + goto err_out; + } + continue; + +err_out: + close(fd); + return err; } - return cand_ids; + + return 0; +} + +static struct core_cand_list * +bpf_core_find_cands(struct bpf_object *obj, const struct btf *local_btf, __u32 local_type_id) +{ + struct core_cand local_cand = {}; + struct core_cand_list *cands; + const struct btf *main_btf; + size_t local_essent_len; + int err, i; + + local_cand.btf = local_btf; + local_cand.t = btf__type_by_id(local_btf, local_type_id); + if (!local_cand.t) + return ERR_PTR(-EINVAL); + + local_cand.name = btf__name_by_offset(local_btf, local_cand.t->name_off); + if (str_is_empty(local_cand.name)) + return ERR_PTR(-EINVAL); + local_essent_len = bpf_core_essential_name_len(local_cand.name); + + cands = calloc(1, sizeof(*cands)); + if (!cands) + return ERR_PTR(-ENOMEM); + + /* Attempt to find target candidates in vmlinux BTF first */ + main_btf = obj->btf_vmlinux_override ?: obj->btf_vmlinux; + err = bpf_core_add_cands(&local_cand, local_essent_len, main_btf, "vmlinux", 1, cands); + if (err) + goto err_out; + + /* if vmlinux BTF has any candidate, don't got for module BTFs */ + if (cands->len) + return cands; + + /* if vmlinux BTF was overridden, don't attempt to load module BTFs */ + if (obj->btf_vmlinux_override) + return cands; + + /* now look through module BTFs, trying to still find candidates */ + err = load_module_btfs(obj); + if (err) + goto err_out; + + for (i = 0; i < obj->btf_module_cnt; i++) { + err = bpf_core_add_cands(&local_cand, local_essent_len, + obj->btf_modules[i].btf, + obj->btf_modules[i].name, + btf__get_nr_types(obj->btf_vmlinux) + 1, + cands); + if (err) + goto err_out; + } + + return cands; err_out: - bpf_core_free_cands(cand_ids); + bpf_core_free_cands(cands); return ERR_PTR(err); } @@ -5664,7 +5861,6 @@ static int bpf_core_apply_relo(struct bpf_program *prog, const struct bpf_core_relo *relo, int relo_idx, const struct btf *local_btf, - const struct btf *targ_btf, struct hashmap *cand_cache) { struct bpf_core_spec local_spec, cand_spec, targ_spec = {}; @@ -5672,8 +5868,8 @@ static int bpf_core_apply_relo(struct bpf_program *prog, struct bpf_core_relo_res cand_res, targ_res; const struct btf_type *local_type; const char *local_name; - struct ids_vec *cand_ids; - __u32 local_id, cand_id; + struct core_cand_list *cands = NULL; + __u32 local_id; const char *spec_str; int i, j, err; @@ -5720,24 +5916,24 @@ static int bpf_core_apply_relo(struct bpf_program *prog, return -EOPNOTSUPP; } - if (!hashmap__find(cand_cache, type_key, (void **)&cand_ids)) { - cand_ids = bpf_core_find_cands(local_btf, local_id, targ_btf); - if (IS_ERR(cand_ids)) { - pr_warn("prog '%s': relo #%d: target candidate search failed for [%d] %s %s: %ld", + if (!hashmap__find(cand_cache, type_key, (void **)&cands)) { + cands = bpf_core_find_cands(prog->obj, local_btf, local_id); + if (IS_ERR(cands)) { + pr_warn("prog '%s': relo #%d: target candidate search failed for [%d] %s %s: %ld\n", prog->name, relo_idx, local_id, btf_kind_str(local_type), - local_name, PTR_ERR(cand_ids)); - return PTR_ERR(cand_ids); + local_name, PTR_ERR(cands)); + return PTR_ERR(cands); } - err = hashmap__set(cand_cache, type_key, cand_ids, NULL, NULL); + err = hashmap__set(cand_cache, type_key, cands, NULL, NULL); if (err) { - bpf_core_free_cands(cand_ids); + bpf_core_free_cands(cands); return err; } } - for (i = 0, j = 0; i < cand_ids->len; i++) { - cand_id = cand_ids->data[i]; - err = bpf_core_spec_match(&local_spec, targ_btf, cand_id, &cand_spec); + for (i = 0, j = 0; i < cands->len; i++) { + err = bpf_core_spec_match(&local_spec, cands->cands[i].btf, + cands->cands[i].id, &cand_spec); if (err < 0) { pr_warn("prog '%s': relo #%d: error matching candidate #%d ", prog->name, relo_idx, i); @@ -5781,7 +5977,7 @@ static int bpf_core_apply_relo(struct bpf_program *prog, return -EINVAL; } - cand_ids->data[j++] = cand_spec.root_type_id; + cands->cands[j++] = cands->cands[i]; } /* @@ -5793,7 +5989,7 @@ static int bpf_core_apply_relo(struct bpf_program *prog, * depending on relo's kind. */ if (j > 0) - cand_ids->len = j; + cands->len = j; /* * If no candidates were found, it might be both a programmer error, @@ -5837,20 +6033,19 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) struct hashmap_entry *entry; struct hashmap *cand_cache = NULL; struct bpf_program *prog; - struct btf *targ_btf; const char *sec_name; int i, err = 0, insn_idx, sec_idx; if (obj->btf_ext->core_relo_info.len == 0) return 0; - if (targ_btf_path) - targ_btf = btf__parse(targ_btf_path, NULL); - else - targ_btf = obj->btf_vmlinux; - if (IS_ERR_OR_NULL(targ_btf)) { - pr_warn("failed to get target BTF: %ld\n", PTR_ERR(targ_btf)); - return PTR_ERR(targ_btf); + if (targ_btf_path) { + obj->btf_vmlinux_override = btf__parse(targ_btf_path, NULL); + if (IS_ERR_OR_NULL(obj->btf_vmlinux_override)) { + err = PTR_ERR(obj->btf_vmlinux_override); + pr_warn("failed to parse target BTF: %d\n", err); + return err; + } } cand_cache = hashmap__new(bpf_core_hash_fn, bpf_core_equal_fn, NULL); @@ -5902,8 +6097,7 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) if (!prog->load) continue; - err = bpf_core_apply_relo(prog, rec, i, obj->btf, - targ_btf, cand_cache); + err = bpf_core_apply_relo(prog, rec, i, obj->btf, cand_cache); if (err) { pr_warn("prog '%s': relo #%d: failed to relocate: %d\n", prog->name, i, err); @@ -5913,9 +6107,10 @@ bpf_object__relocate_core(struct bpf_object *obj, const char *targ_btf_path) } out: - /* obj->btf_vmlinux is freed at the end of object load phase */ - if (targ_btf != obj->btf_vmlinux) - btf__free(targ_btf); + /* obj->btf_vmlinux and module BTFs are freed after object load */ + btf__free(obj->btf_vmlinux_override); + obj->btf_vmlinux_override = NULL; + if (!IS_ERR_OR_NULL(cand_cache)) { hashmap__for_each_entry(cand_cache, entry, i) { bpf_core_free_cands(entry->value); @@ -6626,16 +6821,25 @@ static int load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, char *license, __u32 kern_version, int *pfd) { - struct bpf_load_program_attr load_attr; + struct bpf_prog_load_params load_attr = {}; char *cp, errmsg[STRERR_BUFSIZE]; size_t log_buf_size = 0; char *log_buf = NULL; int btf_fd, ret; + if (prog->type == BPF_PROG_TYPE_UNSPEC) { + /* + * The program type must be set. Most likely we couldn't find a proper + * section definition at load time, and thus we didn't infer the type. + */ + pr_warn("prog '%s': missing BPF prog type, check ELF section name '%s'\n", + prog->name, prog->sec_name); + return -EINVAL; + } + if (!insns || !insns_cnt) return -EINVAL; - memset(&load_attr, 0, sizeof(struct bpf_load_program_attr)); load_attr.prog_type = prog->type; /* old kernels might not support specifying expected_attach_type */ if (!kernel_supports(FEAT_EXP_ATTACH_TYPE) && prog->sec_def && @@ -6646,19 +6850,17 @@ load_program(struct bpf_program *prog, struct bpf_insn *insns, int insns_cnt, if (kernel_supports(FEAT_PROG_NAME)) load_attr.name = prog->name; load_attr.insns = insns; - load_attr.insns_cnt = insns_cnt; + load_attr.insn_cnt = insns_cnt; load_attr.license = license; - if (prog->type == BPF_PROG_TYPE_STRUCT_OPS || - prog->type == BPF_PROG_TYPE_LSM) { - load_attr.attach_btf_id = prog->attach_btf_id; - } else if (prog->type == BPF_PROG_TYPE_TRACING || - prog->type == BPF_PROG_TYPE_EXT) { + load_attr.attach_btf_id = prog->attach_btf_id; + if (prog->attach_prog_fd) load_attr.attach_prog_fd = prog->attach_prog_fd; - load_attr.attach_btf_id = prog->attach_btf_id; - } else { - load_attr.kern_version = kern_version; - load_attr.prog_ifindex = prog->prog_ifindex; - } + else + load_attr.attach_btf_obj_fd = prog->attach_btf_obj_fd; + load_attr.attach_btf_id = prog->attach_btf_id; + load_attr.kern_version = kern_version; + load_attr.prog_ifindex = prog->prog_ifindex; + /* specify func_info/line_info only if kernel supports them */ btf_fd = bpf_object__btf_fd(prog->obj); if (btf_fd >= 0 && kernel_supports(FEAT_BTF_FUNC)) { @@ -6682,7 +6884,9 @@ retry_load: *log_buf = 0; } - ret = bpf_load_program_xattr(&load_attr, log_buf, log_buf_size); + load_attr.log_buf = log_buf; + load_attr.log_buf_sz = log_buf_size; + ret = libbpf__bpf_prog_load(&load_attr); if (ret >= 0) { if (log_buf && load_attr.log_level) @@ -6723,9 +6927,9 @@ retry_load: pr_warn("-- BEGIN DUMP LOG ---\n"); pr_warn("\n%s\n", log_buf); pr_warn("-- END LOG --\n"); - } else if (load_attr.insns_cnt >= BPF_MAXINSNS) { + } else if (load_attr.insn_cnt >= BPF_MAXINSNS) { pr_warn("Program too large (%zu insns), at most %d insns\n", - load_attr.insns_cnt, BPF_MAXINSNS); + load_attr.insn_cnt, BPF_MAXINSNS); ret = -LIBBPF_ERRNO__PROG2BIG; } else if (load_attr.prog_type != BPF_PROG_TYPE_KPROBE) { /* Wrong program type? */ @@ -6733,7 +6937,9 @@ retry_load: load_attr.prog_type = BPF_PROG_TYPE_KPROBE; load_attr.expected_attach_type = 0; - fd = bpf_load_program_xattr(&load_attr, NULL, 0); + load_attr.log_buf = NULL; + load_attr.log_buf_sz = 0; + fd = libbpf__bpf_prog_load(&load_attr); if (fd >= 0) { close(fd); ret = -LIBBPF_ERRNO__PROGTYPE; @@ -6746,11 +6952,11 @@ out: return ret; } -static int libbpf_find_attach_btf_id(struct bpf_program *prog); +static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id); int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) { - int err = 0, fd, i, btf_id; + int err = 0, fd, i; if (prog->obj->loaded) { pr_warn("prog '%s': can't load after object was loaded\n", prog->name); @@ -6760,10 +6966,14 @@ int bpf_program__load(struct bpf_program *prog, char *license, __u32 kern_ver) if ((prog->type == BPF_PROG_TYPE_TRACING || prog->type == BPF_PROG_TYPE_LSM || prog->type == BPF_PROG_TYPE_EXT) && !prog->attach_btf_id) { - btf_id = libbpf_find_attach_btf_id(prog); - if (btf_id <= 0) - return btf_id; - prog->attach_btf_id = btf_id; + int btf_obj_fd = 0, btf_type_id = 0; + + err = libbpf_find_attach_btf_id(prog, &btf_obj_fd, &btf_type_id); + if (err) + return err; + + prog->attach_btf_obj_fd = btf_obj_fd; + prog->attach_btf_id = btf_type_id; } if (prog->instances.nr < 0 || !prog->instances.fds) { @@ -6923,9 +7133,12 @@ __bpf_object__open(const char *path, const void *obj_buf, size_t obj_buf_sz, bpf_object__for_each_program(prog, obj) { prog->sec_def = find_sec_def(prog->sec_name); - if (!prog->sec_def) + if (!prog->sec_def) { /* couldn't guess, but user might manually specify */ + pr_debug("prog '%s': unrecognized ELF section name '%s'\n", + prog->name, prog->sec_name); continue; + } if (prog->sec_def->is_sleepable) prog->prog_flags |= BPF_F_SLEEPABLE; @@ -7271,6 +7484,15 @@ int bpf_object__load_xattr(struct bpf_object_load_attr *attr) err = err ? : bpf_object__relocate(obj, attr->target_btf_path); err = err ? : bpf_object__load_progs(obj, attr->log_level); + /* clean up module BTFs */ + for (i = 0; i < obj->btf_module_cnt; i++) { + close(obj->btf_modules[i].fd); + btf__free(obj->btf_modules[i].btf); + free(obj->btf_modules[i].name); + } + free(obj->btf_modules); + + /* clean up vmlinux BTF */ btf__free(obj->btf_vmlinux); obj->btf_vmlinux = NULL; @@ -7649,6 +7871,16 @@ bool bpf_map__is_pinned(const struct bpf_map *map) return map->pinned; } +static void sanitize_pin_path(char *s) +{ + /* bpffs disallows periods in path names */ + while (*s) { + if (*s == '.') + *s = '_'; + s++; + } +} + int bpf_object__pin_maps(struct bpf_object *obj, const char *path) { struct bpf_map *map; @@ -7678,6 +7910,7 @@ int bpf_object__pin_maps(struct bpf_object *obj, const char *path) err = -ENAMETOOLONG; goto err_unpin_maps; } + sanitize_pin_path(buf); pin_path = buf; } else if (!map->pin_path) { continue; @@ -7722,6 +7955,7 @@ int bpf_object__unpin_maps(struct bpf_object *obj, const char *path) return -EINVAL; else if (len >= PATH_MAX) return -ENAMETOOLONG; + sanitize_pin_path(buf); pin_path = buf; } else if (!map->pin_path) { continue; @@ -8607,8 +8841,8 @@ static int find_btf_by_prefix_kind(const struct btf *btf, const char *prefix, return btf__find_by_name_kind(btf, btf_type_name, kind); } -static inline int __find_vmlinux_btf_id(struct btf *btf, const char *name, - enum bpf_attach_type attach_type) +static inline int find_attach_btf_id(struct btf *btf, const char *name, + enum bpf_attach_type attach_type) { int err; @@ -8624,9 +8858,6 @@ static inline int __find_vmlinux_btf_id(struct btf *btf, const char *name, else err = btf__find_by_name_kind(btf, name, BTF_KIND_FUNC); - if (err <= 0) - pr_warn("%s is not found in vmlinux BTF\n", name); - return err; } @@ -8642,7 +8873,10 @@ int libbpf_find_vmlinux_btf_id(const char *name, return -EINVAL; } - err = __find_vmlinux_btf_id(btf, name, attach_type); + err = find_attach_btf_id(btf, name, attach_type); + if (err <= 0) + pr_warn("%s is not found in vmlinux BTF\n", name); + btf__free(btf); return err; } @@ -8680,11 +8914,49 @@ out: return err; } -static int libbpf_find_attach_btf_id(struct bpf_program *prog) +static int find_kernel_btf_id(struct bpf_object *obj, const char *attach_name, + enum bpf_attach_type attach_type, + int *btf_obj_fd, int *btf_type_id) +{ + int ret, i; + + ret = find_attach_btf_id(obj->btf_vmlinux, attach_name, attach_type); + if (ret > 0) { + *btf_obj_fd = 0; /* vmlinux BTF */ + *btf_type_id = ret; + return 0; + } + if (ret != -ENOENT) + return ret; + + ret = load_module_btfs(obj); + if (ret) + return ret; + + for (i = 0; i < obj->btf_module_cnt; i++) { + const struct module_btf *mod = &obj->btf_modules[i]; + + ret = find_attach_btf_id(mod->btf, attach_name, attach_type); + if (ret > 0) { + *btf_obj_fd = mod->fd; + *btf_type_id = ret; + return 0; + } + if (ret == -ENOENT) + continue; + + return ret; + } + + return -ESRCH; +} + +static int libbpf_find_attach_btf_id(struct bpf_program *prog, int *btf_obj_fd, int *btf_type_id) { enum bpf_attach_type attach_type = prog->expected_attach_type; __u32 attach_prog_fd = prog->attach_prog_fd; - const char *name = prog->sec_name; + const char *name = prog->sec_name, *attach_name; + const struct bpf_sec_def *sec = NULL; int i, err; if (!name) @@ -8695,17 +8967,37 @@ static int libbpf_find_attach_btf_id(struct bpf_program *prog) continue; if (strncmp(name, section_defs[i].sec, section_defs[i].len)) continue; - if (attach_prog_fd) - err = libbpf_find_prog_btf_id(name + section_defs[i].len, - attach_prog_fd); - else - err = __find_vmlinux_btf_id(prog->obj->btf_vmlinux, - name + section_defs[i].len, - attach_type); + + sec = §ion_defs[i]; + break; + } + + if (!sec) { + pr_warn("failed to identify BTF ID based on ELF section name '%s'\n", name); + return -ESRCH; + } + attach_name = name + sec->len; + + /* BPF program's BTF ID */ + if (attach_prog_fd) { + err = libbpf_find_prog_btf_id(attach_name, attach_prog_fd); + if (err < 0) { + pr_warn("failed to find BPF program (FD %d) BTF ID for '%s': %d\n", + attach_prog_fd, attach_name, err); + return err; + } + *btf_obj_fd = 0; + *btf_type_id = err; + return 0; + } + + /* kernel/module BTF ID */ + err = find_kernel_btf_id(prog->obj, attach_name, attach_type, btf_obj_fd, btf_type_id); + if (err) { + pr_warn("failed to find kernel BTF type ID of '%s': %d\n", attach_name, err); return err; } - pr_warn("failed to identify btf_id based on ELF section name '%s'\n", name); - return -ESRCH; + return 0; } int libbpf_attach_type_by_name(const char *name, @@ -10594,6 +10886,7 @@ int bpf_program__set_attach_target(struct bpf_program *prog, return btf_id; prog->attach_btf_id = btf_id; + prog->attach_btf_obj_fd = 0; prog->attach_prog_fd = attach_prog_fd; return 0; } diff --git a/tools/lib/bpf/libbpf.map b/tools/lib/bpf/libbpf.map index 29ff4807b909..7c4126542e2b 100644 --- a/tools/lib/bpf/libbpf.map +++ b/tools/lib/bpf/libbpf.map @@ -340,9 +340,12 @@ LIBBPF_0.2.0 { LIBBPF_0.3.0 { global: + btf__base_btf; btf__parse_elf_split; btf__parse_raw_split; btf__parse_split; btf__new_empty_split; btf__new_split; + xsk_setup_xdp_prog; + xsk_socket__update_xskmap; } LIBBPF_0.2.0; diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h index d99bc847bf84..969d0ac592ba 100644 --- a/tools/lib/bpf/libbpf_internal.h +++ b/tools/lib/bpf/libbpf_internal.h @@ -151,10 +151,41 @@ int parse_cpu_mask_file(const char *fcpu, bool **mask, int *mask_sz); int libbpf__load_raw_btf(const char *raw_types, size_t types_len, const char *str_sec, size_t str_len); +struct bpf_prog_load_params { + enum bpf_prog_type prog_type; + enum bpf_attach_type expected_attach_type; + const char *name; + const struct bpf_insn *insns; + size_t insn_cnt; + const char *license; + __u32 kern_version; + __u32 attach_prog_fd; + __u32 attach_btf_obj_fd; + __u32 attach_btf_id; + __u32 prog_ifindex; + __u32 prog_btf_fd; + __u32 prog_flags; + + __u32 func_info_rec_size; + const void *func_info; + __u32 func_info_cnt; + + __u32 line_info_rec_size; + const void *line_info; + __u32 line_info_cnt; + + __u32 log_level; + char *log_buf; + size_t log_buf_sz; +}; + +int libbpf__bpf_prog_load(const struct bpf_prog_load_params *load_attr); + int bpf_object__section_size(const struct bpf_object *obj, const char *name, __u32 *size); int bpf_object__variable_offset(const struct bpf_object *obj, const char *name, __u32 *off); +struct btf *btf_get_from_fd(int btf_fd, struct btf *base_btf); struct btf_ext_info { /* diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c index 9bc537d0b92d..e3e41ceeb1bc 100644 --- a/tools/lib/bpf/xsk.c +++ b/tools/lib/bpf/xsk.c @@ -566,8 +566,35 @@ static int xsk_set_bpf_maps(struct xsk_socket *xsk) &xsk->fd, 0); } -static int xsk_setup_xdp_prog(struct xsk_socket *xsk) +static int xsk_create_xsk_struct(int ifindex, struct xsk_socket *xsk) { + char ifname[IFNAMSIZ]; + struct xsk_ctx *ctx; + char *interface; + + ctx = calloc(1, sizeof(*ctx)); + if (!ctx) + return -ENOMEM; + + interface = if_indextoname(ifindex, &ifname[0]); + if (!interface) { + free(ctx); + return -errno; + } + + ctx->ifindex = ifindex; + memcpy(ctx->ifname, ifname, IFNAMSIZ -1); + ctx->ifname[IFNAMSIZ - 1] = 0; + + xsk->ctx = ctx; + + return 0; +} + +static int __xsk_setup_xdp_prog(struct xsk_socket *_xdp, + int *xsks_map_fd) +{ + struct xsk_socket *xsk = _xdp; struct xsk_ctx *ctx = xsk->ctx; __u32 prog_id = 0; int err; @@ -584,8 +611,7 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk) err = xsk_load_xdp_prog(xsk); if (err) { - xsk_delete_bpf_maps(xsk); - return err; + goto err_load_xdp_prog; } } else { ctx->prog_fd = bpf_prog_get_fd_by_id(prog_id); @@ -598,15 +624,29 @@ static int xsk_setup_xdp_prog(struct xsk_socket *xsk) } } - if (xsk->rx) + if (xsk->rx) { err = xsk_set_bpf_maps(xsk); - if (err) { - xsk_delete_bpf_maps(xsk); - close(ctx->prog_fd); - return err; + if (err) { + if (!prog_id) { + goto err_set_bpf_maps; + } else { + close(ctx->prog_fd); + return err; + } + } } + if (xsks_map_fd) + *xsks_map_fd = ctx->xsks_map_fd; return 0; + +err_set_bpf_maps: + close(ctx->prog_fd); + bpf_set_link_xdp_fd(ctx->ifindex, -1, 0); +err_load_xdp_prog: + xsk_delete_bpf_maps(xsk); + + return err; } static struct xsk_ctx *xsk_get_ctx(struct xsk_umem *umem, int ifindex, @@ -689,6 +729,40 @@ static struct xsk_ctx *xsk_create_ctx(struct xsk_socket *xsk, return ctx; } +static void xsk_destroy_xsk_struct(struct xsk_socket *xsk) +{ + free(xsk->ctx); + free(xsk); +} + +int xsk_socket__update_xskmap(struct xsk_socket *xsk, int fd) +{ + xsk->ctx->xsks_map_fd = fd; + return xsk_set_bpf_maps(xsk); +} + +int xsk_setup_xdp_prog(int ifindex, int *xsks_map_fd) +{ + struct xsk_socket *xsk; + int res; + + xsk = calloc(1, sizeof(*xsk)); + if (!xsk) + return -ENOMEM; + + res = xsk_create_xsk_struct(ifindex, xsk); + if (res) { + free(xsk); + return -EINVAL; + } + + res = __xsk_setup_xdp_prog(xsk, xsks_map_fd); + + xsk_destroy_xsk_struct(xsk); + + return res; +} + int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, const char *ifname, __u32 queue_id, struct xsk_umem *umem, @@ -838,7 +912,7 @@ int xsk_socket__create_shared(struct xsk_socket **xsk_ptr, ctx->prog_fd = -1; if (!(xsk->config.libbpf_flags & XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD)) { - err = xsk_setup_xdp_prog(xsk); + err = __xsk_setup_xdp_prog(xsk, NULL); if (err) goto out_mmap_tx; } diff --git a/tools/lib/bpf/xsk.h b/tools/lib/bpf/xsk.h index 1069c46364ff..e9f121f5d129 100644 --- a/tools/lib/bpf/xsk.h +++ b/tools/lib/bpf/xsk.h @@ -113,8 +113,7 @@ static inline __u32 xsk_cons_nb_avail(struct xsk_ring_cons *r, __u32 nb) return (entries > nb) ? nb : entries; } -static inline size_t xsk_ring_prod__reserve(struct xsk_ring_prod *prod, - size_t nb, __u32 *idx) +static inline __u32 xsk_ring_prod__reserve(struct xsk_ring_prod *prod, __u32 nb, __u32 *idx) { if (xsk_prod_nb_free(prod, nb) < nb) return 0; @@ -125,7 +124,7 @@ static inline size_t xsk_ring_prod__reserve(struct xsk_ring_prod *prod, return nb; } -static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, size_t nb) +static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, __u32 nb) { /* Make sure everything has been written to the ring before indicating * this to the kernel by writing the producer pointer. @@ -135,10 +134,9 @@ static inline void xsk_ring_prod__submit(struct xsk_ring_prod *prod, size_t nb) *prod->producer += nb; } -static inline size_t xsk_ring_cons__peek(struct xsk_ring_cons *cons, - size_t nb, __u32 *idx) +static inline __u32 xsk_ring_cons__peek(struct xsk_ring_cons *cons, __u32 nb, __u32 *idx) { - size_t entries = xsk_cons_nb_avail(cons, nb); + __u32 entries = xsk_cons_nb_avail(cons, nb); if (entries > 0) { /* Make sure we do not speculatively read the data before @@ -153,7 +151,12 @@ static inline size_t xsk_ring_cons__peek(struct xsk_ring_cons *cons, return entries; } -static inline void xsk_ring_cons__release(struct xsk_ring_cons *cons, size_t nb) +static inline void xsk_ring_cons__cancel(struct xsk_ring_cons *cons, __u32 nb) +{ + cons->cached_cons -= nb; +} + +static inline void xsk_ring_cons__release(struct xsk_ring_cons *cons, __u32 nb) { /* Make sure data has been read before indicating we are done * with the entries by updating the consumer pointer. @@ -201,6 +204,11 @@ struct xsk_umem_config { __u32 flags; }; +LIBBPF_API int xsk_setup_xdp_prog(int ifindex, + int *xsks_map_fd); +LIBBPF_API int xsk_socket__update_xskmap(struct xsk_socket *xsk, + int xsks_map_fd); + /* Flags for the libbpf_flags field. */ #define XSK_LIBBPF_FLAGS__INHIBIT_PROG_LOAD (1 << 0) diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 395ae040ce1f..752d8edddc66 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -35,3 +35,4 @@ test_cpp /tools /runqslower /bench +*.ko diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index c1708ffa6b1c..ac25ba5d0d6c 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -80,7 +80,7 @@ TEST_PROGS_EXTENDED := with_addr.sh \ # Compile but not part of 'make run_tests' TEST_GEN_PROGS_EXTENDED = test_sock_addr test_skb_cgroup_id_user \ flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user \ - test_lirc_mode2_user xdping test_cpp runqslower bench + test_lirc_mode2_user xdping test_cpp runqslower bench bpf_testmod.ko TEST_CUSTOM_PROGS = urandom_read @@ -104,6 +104,7 @@ OVERRIDE_TARGETS := 1 override define CLEAN $(call msg,CLEAN) $(Q)$(RM) -r $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) $(EXTRA_CLEAN) + $(Q)$(MAKE) -C bpf_testmod clean endef include ../lib.mk @@ -136,6 +137,11 @@ $(OUTPUT)/urandom_read: urandom_read.c $(call msg,BINARY,,$@) $(Q)$(CC) $(LDFLAGS) -o $@ $< $(LDLIBS) -Wl,--build-id=sha1 +$(OUTPUT)/bpf_testmod.ko: $(VMLINUX_BTF) $(wildcard bpf_testmod/Makefile bpf_testmod/*.[ch]) + $(call msg,MOD,,$@) + $(Q)$(MAKE) $(submake_extras) -C bpf_testmod + $(Q)cp bpf_testmod/bpf_testmod.ko $@ + $(OUTPUT)/test_stub.o: test_stub.c $(BPFOBJ) $(call msg,CC,,$@) $(Q)$(CC) -c $(CFLAGS) -o $@ $< @@ -219,7 +225,8 @@ $(RESOLVE_BTFIDS): $(BPFOBJ) | $(BUILD_DIR)/resolve_btfids \ # build would have failed anyways. define get_sys_includes $(shell $(1) -v -E - </dev/null 2>&1 \ - | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') + | sed -n '/<...> search starts here:/,/End of search list./{ s| \(/.*\)|-idirafter \1|p }') \ +$(shell $(1) -dM -E - </dev/null | grep '#define __riscv_xlen ' | sed 's/#define /-D/' | sed 's/ /=/') endef # Determine target endianness. @@ -377,7 +384,7 @@ $(OUTPUT)/$(TRUNNER_BINARY): $(TRUNNER_TEST_OBJS) \ | $(TRUNNER_BINARY)-extras $$(call msg,BINARY,,$$@) $(Q)$$(CC) $$(CFLAGS) $$(filter %.a %.o,$$^) $$(LDLIBS) -o $$@ - $(Q)$(RESOLVE_BTFIDS) --no-fail --btf btf_data.o $$@ + $(Q)$(RESOLVE_BTFIDS) --no-fail --btf $(TRUNNER_OUTPUT)/btf_data.o $$@ endef @@ -387,7 +394,8 @@ TRUNNER_BPF_PROGS_DIR := progs TRUNNER_EXTRA_SOURCES := test_progs.c cgroup_helpers.c trace_helpers.c \ network_helpers.c testing_helpers.c \ btf_helpers.c flow_dissector_load.h -TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read \ +TRUNNER_EXTRA_FILES := $(OUTPUT)/urandom_read $(OUTPUT)/bpf_testmod.ko \ + ima_setup.sh \ $(wildcard progs/btf_dump_test_case_*.c) TRUNNER_BPF_BUILD_RULE := CLANG_BPF_BUILD_RULE TRUNNER_BPF_CFLAGS := $(BPF_CFLAGS) $(CLANG_CFLAGS) @@ -458,4 +466,4 @@ $(OUTPUT)/bench: $(OUTPUT)/bench.o $(OUTPUT)/testing_helpers.o \ EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) $(SCRATCH_DIR) \ prog_tests/tests.h map_tests/tests.h verifier/tests.h \ feature \ - $(addprefix $(OUTPUT)/,*.o *.skel.h no_alu32 bpf_gcc) + $(addprefix $(OUTPUT)/,*.o *.skel.h no_alu32 bpf_gcc bpf_testmod.ko) diff --git a/tools/testing/selftests/bpf/README.rst b/tools/testing/selftests/bpf/README.rst index ac9eda830187..ca064180d4d0 100644 --- a/tools/testing/selftests/bpf/README.rst +++ b/tools/testing/selftests/bpf/README.rst @@ -2,7 +2,10 @@ BPF Selftest Notes ================== General instructions on running selftests can be found in -`Documentation/bpf/bpf_devel_QA.rst`_. +`Documentation/bpf/bpf_devel_QA.rst`__. + +__ /Documentation/bpf/bpf_devel_QA.rst#q-how-to-run-bpf-selftests + Additional information about selftest failures are documented here. @@ -30,11 +33,12 @@ The verifier will reject such code with above error. At insn 18 the r7 is indeed unbounded. The later insn 19 checks the bounds and the insn 20 undoes map_value addition. It is currently impossible for the verifier to understand such speculative pointer arithmetic. -Hence - https://reviews.llvm.org/D85570 -addresses it on the compiler side. It was committed on llvm 12. +Hence `this patch`__ addresses it on the compiler side. It was committed on llvm 12. + +__ https://reviews.llvm.org/D85570 The corresponding C code + .. code-block:: c for (int i = 0; i < MAX_CGROUPS_PATH_DEPTH; i++) { @@ -77,10 +81,11 @@ The symptom for ``bpf_iter/netlink`` looks like 17: (7b) *(u64 *)(r7 +0) = r2 only read is supported -This is due to a llvm BPF backend bug. The fix - https://reviews.llvm.org/D78466 +This is due to a llvm BPF backend bug. `The fix`__ has been pushed to llvm 10.x release branch and will be -available in 10.0.1. The fix is available in llvm 11.0.0 trunk. +available in 10.0.1. The patch is available in llvm 11.0.0 trunk. + +__ https://reviews.llvm.org/D78466 BPF CO-RE-based tests and Clang version ======================================= @@ -94,11 +99,11 @@ them to Clang/LLVM. These sub-tests are going to be skipped if Clang is too old to support them, they shouldn't cause build failures or runtime test failures: - - __builtin_btf_type_id() ([0], [1], [2]); - - __builtin_preserve_type_info(), __builtin_preserve_enum_value() ([3], [4]). +- __builtin_btf_type_id() [0_, 1_, 2_]; +- __builtin_preserve_type_info(), __builtin_preserve_enum_value() [3_, 4_]. - [0] https://reviews.llvm.org/D74572 - [1] https://reviews.llvm.org/D74668 - [2] https://reviews.llvm.org/D85174 - [3] https://reviews.llvm.org/D83878 - [4] https://reviews.llvm.org/D83242 +.. _0: https://reviews.llvm.org/D74572 +.. _1: https://reviews.llvm.org/D74668 +.. _2: https://reviews.llvm.org/D85174 +.. _3: https://reviews.llvm.org/D83878 +.. _4: https://reviews.llvm.org/D83242 diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h index 2915664c335d..6a9053162cf2 100644 --- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h +++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h @@ -56,6 +56,7 @@ struct tcp_sock { __u32 rcv_nxt; __u32 snd_nxt; __u32 snd_una; + __u32 window_clamp; __u8 ecn_flags; __u32 delivered; __u32 delivered_ce; diff --git a/tools/testing/selftests/bpf/bpf_testmod/.gitignore b/tools/testing/selftests/bpf/bpf_testmod/.gitignore new file mode 100644 index 000000000000..ded513777281 --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_testmod/.gitignore @@ -0,0 +1,6 @@ +*.mod +*.mod.c +*.o +.ko +/Module.symvers +/modules.order diff --git a/tools/testing/selftests/bpf/bpf_testmod/Makefile b/tools/testing/selftests/bpf/bpf_testmod/Makefile new file mode 100644 index 000000000000..15cb36c4483a --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_testmod/Makefile @@ -0,0 +1,20 @@ +BPF_TESTMOD_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST))))) +KDIR ?= $(abspath $(BPF_TESTMOD_DIR)/../../../../..) + +ifeq ($(V),1) +Q = +else +Q = @ +endif + +MODULES = bpf_testmod.ko + +obj-m += bpf_testmod.o +CFLAGS_bpf_testmod.o = -I$(src) + +all: + +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) modules + +clean: + +$(Q)make -C $(KDIR) M=$(BPF_TESTMOD_DIR) clean + diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h new file mode 100644 index 000000000000..b83ea448bc79 --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod-events.h @@ -0,0 +1,36 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2020 Facebook */ +#undef TRACE_SYSTEM +#define TRACE_SYSTEM bpf_testmod + +#if !defined(_BPF_TESTMOD_EVENTS_H) || defined(TRACE_HEADER_MULTI_READ) +#define _BPF_TESTMOD_EVENTS_H + +#include <linux/tracepoint.h> +#include "bpf_testmod.h" + +TRACE_EVENT(bpf_testmod_test_read, + TP_PROTO(struct task_struct *task, struct bpf_testmod_test_read_ctx *ctx), + TP_ARGS(task, ctx), + TP_STRUCT__entry( + __field(pid_t, pid) + __array(char, comm, TASK_COMM_LEN) + __field(loff_t, off) + __field(size_t, len) + ), + TP_fast_assign( + __entry->pid = task->pid; + memcpy(__entry->comm, task->comm, TASK_COMM_LEN); + __entry->off = ctx->off; + __entry->len = ctx->len; + ), + TP_printk("pid=%d comm=%s off=%llu len=%zu", + __entry->pid, __entry->comm, __entry->off, __entry->len) +); + +#endif /* _BPF_TESTMOD_EVENTS_H */ + +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH . +#define TRACE_INCLUDE_FILE bpf_testmod-events +#include <trace/define_trace.h> diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c new file mode 100644 index 000000000000..2df19d73ca49 --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.c @@ -0,0 +1,52 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ +#include <linux/error-injection.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/sysfs.h> +#include <linux/tracepoint.h> +#include "bpf_testmod.h" + +#define CREATE_TRACE_POINTS +#include "bpf_testmod-events.h" + +noinline ssize_t +bpf_testmod_test_read(struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, + char *buf, loff_t off, size_t len) +{ + struct bpf_testmod_test_read_ctx ctx = { + .buf = buf, + .off = off, + .len = len, + }; + + trace_bpf_testmod_test_read(current, &ctx); + + return -EIO; /* always fail */ +} +EXPORT_SYMBOL(bpf_testmod_test_read); +ALLOW_ERROR_INJECTION(bpf_testmod_test_read, ERRNO); + +static struct bin_attribute bin_attr_bpf_testmod_file __ro_after_init = { + .attr = { .name = "bpf_testmod", .mode = 0444, }, + .read = bpf_testmod_test_read, +}; + +static int bpf_testmod_init(void) +{ + return sysfs_create_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); +} + +static void bpf_testmod_exit(void) +{ + return sysfs_remove_bin_file(kernel_kobj, &bin_attr_bpf_testmod_file); +} + +module_init(bpf_testmod_init); +module_exit(bpf_testmod_exit); + +MODULE_AUTHOR("Andrii Nakryiko"); +MODULE_DESCRIPTION("BPF selftests module"); +MODULE_LICENSE("Dual BSD/GPL"); + diff --git a/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h new file mode 100644 index 000000000000..b81adfedb4f6 --- /dev/null +++ b/tools/testing/selftests/bpf/bpf_testmod/bpf_testmod.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2020 Facebook */ +#ifndef _BPF_TESTMOD_H +#define _BPF_TESTMOD_H + +#include <linux/types.h> + +struct bpf_testmod_test_read_ctx { + char *buf; + loff_t off; + size_t len; +}; + +#endif /* _BPF_TESTMOD_H */ diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index 2118e23ac07a..37e1f303fc11 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -39,3 +39,8 @@ CONFIG_BPF_JIT=y CONFIG_BPF_LSM=y CONFIG_SECURITY=y CONFIG_LIRC=y +CONFIG_IMA=y +CONFIG_SECURITYFS=y +CONFIG_IMA_WRITE_POLICY=y +CONFIG_IMA_READ_POLICY=y +CONFIG_BLK_DEV_LOOP=y diff --git a/tools/testing/selftests/bpf/ima_setup.sh b/tools/testing/selftests/bpf/ima_setup.sh new file mode 100755 index 000000000000..2bfc646bc230 --- /dev/null +++ b/tools/testing/selftests/bpf/ima_setup.sh @@ -0,0 +1,99 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +set -e +set -u +set -o pipefail + +IMA_POLICY_FILE="/sys/kernel/security/ima/policy" +TEST_BINARY="/bin/true" + +usage() +{ + echo "Usage: $0 <setup|cleanup|run> <existing_tmp_dir>" + exit 1 +} + +ensure_mount_securityfs() +{ + local securityfs_dir=$(grep "securityfs" /proc/mounts | awk '{print $2}') + + if [ -z "${securityfs_dir}" ]; then + securityfs_dir=/sys/kernel/security + mount -t securityfs security "${securityfs_dir}" + fi + + if [ ! -d "${securityfs_dir}" ]; then + echo "${securityfs_dir}: securityfs is not mounted" && exit 1 + fi +} + +setup() +{ + local tmp_dir="$1" + local mount_img="${tmp_dir}/test.img" + local mount_dir="${tmp_dir}/mnt" + local copied_bin_path="${mount_dir}/$(basename ${TEST_BINARY})" + mkdir -p ${mount_dir} + + dd if=/dev/zero of="${mount_img}" bs=1M count=10 + + losetup -f "${mount_img}" + local loop_device=$(losetup -a | grep ${mount_img:?} | cut -d ":" -f1) + + mkfs.ext2 "${loop_device:?}" + mount "${loop_device}" "${mount_dir}" + + cp "${TEST_BINARY}" "${mount_dir}" + local mount_uuid="$(blkid ${loop_device} | sed 's/.*UUID="\([^"]*\)".*/\1/')" + + ensure_mount_securityfs + echo "measure func=BPRM_CHECK fsuuid=${mount_uuid}" > ${IMA_POLICY_FILE} +} + +cleanup() { + local tmp_dir="$1" + local mount_img="${tmp_dir}/test.img" + local mount_dir="${tmp_dir}/mnt" + + local loop_devices=$(losetup -a | grep ${mount_img:?} | cut -d ":" -f1) + + for loop_dev in "${loop_devices}"; do + losetup -d $loop_dev + done + + umount ${mount_dir} + rm -rf ${tmp_dir} +} + +run() +{ + local tmp_dir="$1" + local mount_dir="${tmp_dir}/mnt" + local copied_bin_path="${mount_dir}/$(basename ${TEST_BINARY})" + + exec "${copied_bin_path}" +} + +main() +{ + [[ $# -ne 2 ]] && usage + + local action="$1" + local tmp_dir="$2" + + [[ ! -d "${tmp_dir}" ]] && echo "Directory ${tmp_dir} doesn't exist" && exit 1 + + if [[ "${action}" == "setup" ]]; then + setup "${tmp_dir}" + elif [[ "${action}" == "cleanup" ]]; then + cleanup "${tmp_dir}" + elif [[ "${action}" == "run" ]]; then + run "${tmp_dir}" + else + echo "Unknown action: ${action}" + exit 1 + fi +} + +main "$@" diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c index 30e40ff4b0d8..06eb956ff7bb 100644 --- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c +++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include <test_progs.h> #include "progs/core_reloc_types.h" +#include "bpf_testmod/bpf_testmod.h" #include <sys/mman.h> #include <sys/syscall.h> #include <bpf/btf.h> @@ -9,6 +10,30 @@ static int duration = 0; #define STRUCT_TO_CHAR_PTR(struct_name) (const char *)&(struct struct_name) +#define MODULES_CASE(name, sec_name, tp_name) { \ + .case_name = name, \ + .bpf_obj_file = "test_core_reloc_module.o", \ + .btf_src_file = NULL, /* find in kernel module BTFs */ \ + .input = "", \ + .input_len = 0, \ + .output = STRUCT_TO_CHAR_PTR(core_reloc_module_output) { \ + .read_ctx_sz = sizeof(struct bpf_testmod_test_read_ctx),\ + .read_ctx_exists = true, \ + .buf_exists = true, \ + .len_exists = true, \ + .off_exists = true, \ + .len = 123, \ + .off = 0, \ + .comm = "test_progs", \ + .comm_len = sizeof("test_progs"), \ + }, \ + .output_len = sizeof(struct core_reloc_module_output), \ + .prog_sec_name = sec_name, \ + .raw_tp_name = tp_name, \ + .trigger = trigger_module_test_read, \ + .needs_testmod = true, \ +} + #define FLAVORS_DATA(struct_name) STRUCT_TO_CHAR_PTR(struct_name) { \ .a = 42, \ .b = 0xc001, \ @@ -211,7 +236,7 @@ static int duration = 0; .output = STRUCT_TO_CHAR_PTR(core_reloc_bitfields_output) \ __VA_ARGS__, \ .output_len = sizeof(struct core_reloc_bitfields_output), \ - .direct_raw_tp = true, \ + .prog_sec_name = "tp_btf/sys_enter", \ } @@ -222,7 +247,7 @@ static int duration = 0; }, { \ BITFIELDS_CASE_COMMON("test_core_reloc_bitfields_direct.o", \ "direct:", name), \ - .direct_raw_tp = true, \ + .prog_sec_name = "tp_btf/sys_enter", \ .fails = true, \ } @@ -309,6 +334,7 @@ static int duration = 0; struct core_reloc_test_case; typedef int (*setup_test_fn)(struct core_reloc_test_case *test); +typedef int (*trigger_test_fn)(const struct core_reloc_test_case *test); struct core_reloc_test_case { const char *case_name; @@ -319,9 +345,12 @@ struct core_reloc_test_case { const char *output; int output_len; bool fails; + bool needs_testmod; bool relaxed_core_relocs; - bool direct_raw_tp; + const char *prog_sec_name; + const char *raw_tp_name; setup_test_fn setup; + trigger_test_fn trigger; }; static int find_btf_type(const struct btf *btf, const char *name, __u32 kind) @@ -451,6 +480,23 @@ static int setup_type_id_case_failure(struct core_reloc_test_case *test) return 0; } +static int trigger_module_test_read(const struct core_reloc_test_case *test) +{ + struct core_reloc_module_output *exp = (void *)test->output; + int fd, err; + + fd = open("/sys/kernel/bpf_testmod", O_RDONLY); + err = -errno; + if (CHECK(fd < 0, "testmod_file_open", "failed: %d\n", err)) + return err; + + read(fd, NULL, exp->len); /* request expected number of bytes */ + close(fd); + + return 0; +} + + static struct core_reloc_test_case test_cases[] = { /* validate we can find kernel image and use its BTF for relocs */ { @@ -467,6 +513,10 @@ static struct core_reloc_test_case test_cases[] = { .output_len = sizeof(struct core_reloc_kernel_output), }, + /* validate we can find kernel module BTF types for relocs/attach */ + MODULES_CASE("module_probed", "raw_tp/bpf_testmod_test_read", "bpf_testmod_test_read"), + MODULES_CASE("module_direct", "tp_btf/bpf_testmod_test_read", NULL), + /* validate BPF program can use multiple flavors to match against * single target BTF type */ @@ -779,6 +829,11 @@ void test_core_reloc(void) if (!test__start_subtest(test_case->case_name)) continue; + if (test_case->needs_testmod && !env.has_testmod) { + test__skip(); + continue; + } + if (test_case->setup) { err = test_case->setup(test_case); if (CHECK(err, "test_setup", "test #%d setup failed: %d\n", i, err)) @@ -790,13 +845,11 @@ void test_core_reloc(void) test_case->bpf_obj_file, PTR_ERR(obj))) continue; - /* for typed raw tracepoints, NULL should be specified */ - if (test_case->direct_raw_tp) { - probe_name = "tp_btf/sys_enter"; - tp_name = NULL; - } else { - probe_name = "raw_tracepoint/sys_enter"; - tp_name = "sys_enter"; + probe_name = "raw_tracepoint/sys_enter"; + tp_name = "sys_enter"; + if (test_case->prog_sec_name) { + probe_name = test_case->prog_sec_name; + tp_name = test_case->raw_tp_name; /* NULL for tp_btf */ } prog = bpf_object__find_program_by_title(obj, probe_name); @@ -837,7 +890,12 @@ void test_core_reloc(void) goto cleanup; /* trigger test run */ - usleep(1); + if (test_case->trigger) { + if (!ASSERT_OK(test_case->trigger(test_case), "test_trigger")) + goto cleanup; + } else { + usleep(1); + } if (data->skip) { test__skip(); diff --git a/tools/testing/selftests/bpf/prog_tests/module_attach.c b/tools/testing/selftests/bpf/prog_tests/module_attach.c new file mode 100644 index 000000000000..4b65e9918764 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/module_attach.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include <test_progs.h> +#include "test_module_attach.skel.h" + +static int duration; + +static int trigger_module_test_read(int read_sz) +{ + int fd, err; + + fd = open("/sys/kernel/bpf_testmod", O_RDONLY); + err = -errno; + if (CHECK(fd < 0, "testmod_file_open", "failed: %d\n", err)) + return err; + + read(fd, NULL, read_sz); + close(fd); + + return 0; +} + +void test_module_attach(void) +{ + const int READ_SZ = 456; + struct test_module_attach* skel; + struct test_module_attach__bss *bss; + int err; + + skel = test_module_attach__open_and_load(); + if (CHECK(!skel, "skel_open", "failed to open skeleton\n")) + return; + + bss = skel->bss; + + err = test_module_attach__attach(skel); + if (CHECK(err, "skel_attach", "skeleton attach failed: %d\n", err)) + goto cleanup; + + /* trigger tracepoint */ + ASSERT_OK(trigger_module_test_read(READ_SZ), "trigger_read"); + + ASSERT_EQ(bss->raw_tp_read_sz, READ_SZ, "raw_tp"); + ASSERT_EQ(bss->tp_btf_read_sz, READ_SZ, "tp_btf"); + ASSERT_EQ(bss->fentry_read_sz, READ_SZ, "fentry"); + ASSERT_EQ(bss->fexit_read_sz, READ_SZ, "fexit"); + ASSERT_EQ(bss->fexit_ret, -EIO, "fexit_tet"); + ASSERT_EQ(bss->fmod_ret_read_sz, READ_SZ, "fmod_ret"); + +cleanup: + test_module_attach__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/tcpbpf_user.c b/tools/testing/selftests/bpf/prog_tests/tcpbpf_user.c index ab5281475f44..87923d2865b7 100644 --- a/tools/testing/selftests/bpf/prog_tests/tcpbpf_user.c +++ b/tools/testing/selftests/bpf/prog_tests/tcpbpf_user.c @@ -42,6 +42,10 @@ static void verify_result(struct tcpbpf_globals *result) /* check getsockopt for SAVED_SYN */ ASSERT_EQ(result->tcp_saved_syn, 1, "tcp_saved_syn"); + + /* check getsockopt for window_clamp */ + ASSERT_EQ(result->window_clamp_client, 9216, "window_clamp_client"); + ASSERT_EQ(result->window_clamp_server, 9216, "window_clamp_server"); } static void run_test(struct tcpbpf_globals *result) diff --git a/tools/testing/selftests/bpf/prog_tests/test_bprm_opts.c b/tools/testing/selftests/bpf/prog_tests/test_bprm_opts.c new file mode 100644 index 000000000000..2559bb775762 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_bprm_opts.c @@ -0,0 +1,116 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (C) 2020 Google LLC. + */ + +#include <test_progs.h> +#include <linux/limits.h> + +#include "bprm_opts.skel.h" +#include "network_helpers.h" + +#ifndef __NR_pidfd_open +#define __NR_pidfd_open 434 +#endif + +static const char * const bash_envp[] = { "TMPDIR=shouldnotbeset", NULL }; + +static inline int sys_pidfd_open(pid_t pid, unsigned int flags) +{ + return syscall(__NR_pidfd_open, pid, flags); +} + +static int update_storage(int map_fd, int secureexec) +{ + int task_fd, ret = 0; + + task_fd = sys_pidfd_open(getpid(), 0); + if (task_fd < 0) + return errno; + + ret = bpf_map_update_elem(map_fd, &task_fd, &secureexec, BPF_NOEXIST); + if (ret) + ret = errno; + + close(task_fd); + return ret; +} + +static int run_set_secureexec(int map_fd, int secureexec) +{ + int child_pid, child_status, ret, null_fd; + + child_pid = fork(); + if (child_pid == 0) { + null_fd = open("/dev/null", O_WRONLY); + if (null_fd == -1) + exit(errno); + dup2(null_fd, STDOUT_FILENO); + dup2(null_fd, STDERR_FILENO); + close(null_fd); + + /* Ensure that all executions from hereon are + * secure by setting a local storage which is read by + * the bprm_creds_for_exec hook and sets bprm->secureexec. + */ + ret = update_storage(map_fd, secureexec); + if (ret) + exit(ret); + + /* If the binary is executed with securexec=1, the dynamic + * loader ingores and unsets certain variables like LD_PRELOAD, + * TMPDIR etc. TMPDIR is used here to simplify the example, as + * LD_PRELOAD requires a real .so file. + * + * If the value of TMPDIR is set, the bash command returns 10 + * and if the value is unset, it returns 20. + */ + execle("/bin/bash", "bash", "-c", + "[[ -z \"${TMPDIR}\" ]] || exit 10 && exit 20", NULL, + bash_envp); + exit(errno); + } else if (child_pid > 0) { + waitpid(child_pid, &child_status, 0); + ret = WEXITSTATUS(child_status); + + /* If a secureexec occurred, the exit status should be 20 */ + if (secureexec && ret == 20) + return 0; + + /* If normal execution happened, the exit code should be 10 */ + if (!secureexec && ret == 10) + return 0; + } + + return -EINVAL; +} + +void test_test_bprm_opts(void) +{ + int err, duration = 0; + struct bprm_opts *skel = NULL; + + skel = bprm_opts__open_and_load(); + if (CHECK(!skel, "skel_load", "skeleton failed\n")) + goto close_prog; + + err = bprm_opts__attach(skel); + if (CHECK(err, "attach", "attach failed: %d\n", err)) + goto close_prog; + + /* Run the test with the secureexec bit unset */ + err = run_set_secureexec(bpf_map__fd(skel->maps.secure_exec_task_map), + 0 /* secureexec */); + if (CHECK(err, "run_set_secureexec:0", "err = %d\n", err)) + goto close_prog; + + /* Run the test with the secureexec bit set */ + err = run_set_secureexec(bpf_map__fd(skel->maps.secure_exec_task_map), + 1 /* secureexec */); + if (CHECK(err, "run_set_secureexec:1", "err = %d\n", err)) + goto close_prog; + +close_prog: + bprm_opts__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_ima.c b/tools/testing/selftests/bpf/prog_tests/test_ima.c new file mode 100644 index 000000000000..61fca681d524 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/test_ima.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (C) 2020 Google LLC. + */ + +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <sys/wait.h> +#include <test_progs.h> + +#include "ima.skel.h" + +static int run_measured_process(const char *measured_dir, u32 *monitored_pid) +{ + int child_pid, child_status; + + child_pid = fork(); + if (child_pid == 0) { + *monitored_pid = getpid(); + execlp("./ima_setup.sh", "./ima_setup.sh", "run", measured_dir, + NULL); + exit(errno); + + } else if (child_pid > 0) { + waitpid(child_pid, &child_status, 0); + return WEXITSTATUS(child_status); + } + + return -EINVAL; +} + +void test_test_ima(void) +{ + char measured_dir_template[] = "/tmp/ima_measuredXXXXXX"; + const char *measured_dir; + char cmd[256]; + + int err, duration = 0; + struct ima *skel = NULL; + + skel = ima__open_and_load(); + if (CHECK(!skel, "skel_load", "skeleton failed\n")) + goto close_prog; + + err = ima__attach(skel); + if (CHECK(err, "attach", "attach failed: %d\n", err)) + goto close_prog; + + measured_dir = mkdtemp(measured_dir_template); + if (CHECK(measured_dir == NULL, "mkdtemp", "err %d\n", errno)) + goto close_prog; + + snprintf(cmd, sizeof(cmd), "./ima_setup.sh setup %s", measured_dir); + if (CHECK_FAIL(system(cmd))) + goto close_clean; + + err = run_measured_process(measured_dir, &skel->bss->monitored_pid); + if (CHECK(err, "run_measured_process", "err = %d\n", err)) + goto close_clean; + + CHECK(skel->data->ima_hash_ret < 0, "ima_hash_ret", + "ima_hash_ret = %ld\n", skel->data->ima_hash_ret); + + CHECK(skel->bss->ima_hash == 0, "ima_hash", + "ima_hash = %lu\n", skel->bss->ima_hash); + +close_clean: + snprintf(cmd, sizeof(cmd), "./ima_setup.sh cleanup %s", measured_dir); + CHECK_FAIL(system(cmd)); +close_prog: + ima__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/test_local_storage.c b/tools/testing/selftests/bpf/prog_tests/test_local_storage.c index fcca7ba1f368..c0fe73a17ed1 100644 --- a/tools/testing/selftests/bpf/prog_tests/test_local_storage.c +++ b/tools/testing/selftests/bpf/prog_tests/test_local_storage.c @@ -21,14 +21,6 @@ static inline int sys_pidfd_open(pid_t pid, unsigned int flags) return syscall(__NR_pidfd_open, pid, flags); } -static inline ssize_t copy_file_range(int fd_in, loff_t *off_in, int fd_out, - loff_t *off_out, size_t len, - unsigned int flags) -{ - return syscall(__NR_copy_file_range, fd_in, off_in, fd_out, off_out, - len, flags); -} - static unsigned int duration; #define TEST_STORAGE_VALUE 0xbeefdead @@ -47,6 +39,7 @@ static int copy_rm(char *dest) { int fd_in, fd_out = -1, ret = 0; struct stat stat; + char *buf = NULL; fd_in = open("/bin/rm", O_RDONLY); if (fd_in < 0) @@ -64,18 +57,33 @@ static int copy_rm(char *dest) goto out; } - ret = copy_file_range(fd_in, NULL, fd_out, NULL, stat.st_size, 0); - if (ret == -1) { + buf = malloc(stat.st_blksize); + if (!buf) { ret = -errno; goto out; } + while (ret = read(fd_in, buf, stat.st_blksize), ret > 0) { + ret = write(fd_out, buf, ret); + if (ret < 0) { + ret = -errno; + goto out; + + } + } + if (ret < 0) { + ret = -errno; + goto out; + + } + /* Set executable permission on the copied file */ ret = chmod(dest, 0100); if (ret == -1) ret = -errno; out: + free(buf); close(fd_in); close(fd_out); return ret; diff --git a/tools/testing/selftests/bpf/progs/bind4_prog.c b/tools/testing/selftests/bpf/progs/bind4_prog.c new file mode 100644 index 000000000000..c6520f21f5f5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bind4_prog.c @@ -0,0 +1,102 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <string.h> + +#include <linux/stddef.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <sys/socket.h> +#include <netinet/tcp.h> +#include <linux/if.h> +#include <errno.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define SERV4_IP 0xc0a801feU /* 192.168.1.254 */ +#define SERV4_PORT 4040 +#define SERV4_REWRITE_IP 0x7f000001U /* 127.0.0.1 */ +#define SERV4_REWRITE_PORT 4444 + +#ifndef IFNAMSIZ +#define IFNAMSIZ 16 +#endif + +static __inline int bind_to_device(struct bpf_sock_addr *ctx) +{ + char veth1[IFNAMSIZ] = "test_sock_addr1"; + char veth2[IFNAMSIZ] = "test_sock_addr2"; + char missing[IFNAMSIZ] = "nonexistent_dev"; + char del_bind[IFNAMSIZ] = ""; + + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &veth1, sizeof(veth1))) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &veth2, sizeof(veth2))) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &missing, sizeof(missing)) != -ENODEV) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &del_bind, sizeof(del_bind))) + return 1; + + return 0; +} + +SEC("cgroup/bind4") +int bind_v4_prog(struct bpf_sock_addr *ctx) +{ + struct bpf_sock *sk; + __u32 user_ip4; + __u16 user_port; + + sk = ctx->sk; + if (!sk) + return 0; + + if (sk->family != AF_INET) + return 0; + + if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM) + return 0; + + if (ctx->user_ip4 != bpf_htonl(SERV4_IP) || + ctx->user_port != bpf_htons(SERV4_PORT)) + return 0; + + // u8 narrow loads: + user_ip4 = 0; + user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[0] << 0; + user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[1] << 8; + user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[2] << 16; + user_ip4 |= ((volatile __u8 *)&ctx->user_ip4)[3] << 24; + if (ctx->user_ip4 != user_ip4) + return 0; + + user_port = 0; + user_port |= ((volatile __u8 *)&ctx->user_port)[0] << 0; + user_port |= ((volatile __u8 *)&ctx->user_port)[1] << 8; + if (ctx->user_port != user_port) + return 0; + + // u16 narrow loads: + user_ip4 = 0; + user_ip4 |= ((volatile __u16 *)&ctx->user_ip4)[0] << 0; + user_ip4 |= ((volatile __u16 *)&ctx->user_ip4)[1] << 16; + if (ctx->user_ip4 != user_ip4) + return 0; + + /* Bind to device and unbind it. */ + if (bind_to_device(ctx)) + return 0; + + ctx->user_ip4 = bpf_htonl(SERV4_REWRITE_IP); + ctx->user_port = bpf_htons(SERV4_REWRITE_PORT); + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bind6_prog.c b/tools/testing/selftests/bpf/progs/bind6_prog.c new file mode 100644 index 000000000000..4358e44dcf47 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bind6_prog.c @@ -0,0 +1,119 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <string.h> + +#include <linux/stddef.h> +#include <linux/bpf.h> +#include <linux/in.h> +#include <linux/in6.h> +#include <sys/socket.h> +#include <netinet/tcp.h> +#include <linux/if.h> +#include <errno.h> + +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_endian.h> + +#define SERV6_IP_0 0xfaceb00c /* face:b00c:1234:5678::abcd */ +#define SERV6_IP_1 0x12345678 +#define SERV6_IP_2 0x00000000 +#define SERV6_IP_3 0x0000abcd +#define SERV6_PORT 6060 +#define SERV6_REWRITE_IP_0 0x00000000 +#define SERV6_REWRITE_IP_1 0x00000000 +#define SERV6_REWRITE_IP_2 0x00000000 +#define SERV6_REWRITE_IP_3 0x00000001 +#define SERV6_REWRITE_PORT 6666 + +#ifndef IFNAMSIZ +#define IFNAMSIZ 16 +#endif + +static __inline int bind_to_device(struct bpf_sock_addr *ctx) +{ + char veth1[IFNAMSIZ] = "test_sock_addr1"; + char veth2[IFNAMSIZ] = "test_sock_addr2"; + char missing[IFNAMSIZ] = "nonexistent_dev"; + char del_bind[IFNAMSIZ] = ""; + + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &veth1, sizeof(veth1))) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &veth2, sizeof(veth2))) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &missing, sizeof(missing)) != -ENODEV) + return 1; + if (bpf_setsockopt(ctx, SOL_SOCKET, SO_BINDTODEVICE, + &del_bind, sizeof(del_bind))) + return 1; + + return 0; +} + +SEC("cgroup/bind6") +int bind_v6_prog(struct bpf_sock_addr *ctx) +{ + struct bpf_sock *sk; + __u32 user_ip6; + __u16 user_port; + int i; + + sk = ctx->sk; + if (!sk) + return 0; + + if (sk->family != AF_INET6) + return 0; + + if (ctx->type != SOCK_STREAM && ctx->type != SOCK_DGRAM) + return 0; + + if (ctx->user_ip6[0] != bpf_htonl(SERV6_IP_0) || + ctx->user_ip6[1] != bpf_htonl(SERV6_IP_1) || + ctx->user_ip6[2] != bpf_htonl(SERV6_IP_2) || + ctx->user_ip6[3] != bpf_htonl(SERV6_IP_3) || + ctx->user_port != bpf_htons(SERV6_PORT)) + return 0; + + // u8 narrow loads: + for (i = 0; i < 4; i++) { + user_ip6 = 0; + user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[0] << 0; + user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[1] << 8; + user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[2] << 16; + user_ip6 |= ((volatile __u8 *)&ctx->user_ip6[i])[3] << 24; + if (ctx->user_ip6[i] != user_ip6) + return 0; + } + + user_port = 0; + user_port |= ((volatile __u8 *)&ctx->user_port)[0] << 0; + user_port |= ((volatile __u8 *)&ctx->user_port)[1] << 8; + if (ctx->user_port != user_port) + return 0; + + // u16 narrow loads: + for (i = 0; i < 4; i++) { + user_ip6 = 0; + user_ip6 |= ((volatile __u16 *)&ctx->user_ip6[i])[0] << 0; + user_ip6 |= ((volatile __u16 *)&ctx->user_ip6[i])[1] << 16; + if (ctx->user_ip6[i] != user_ip6) + return 0; + } + + /* Bind to device and unbind it. */ + if (bind_to_device(ctx)) + return 0; + + ctx->user_ip6[0] = bpf_htonl(SERV6_REWRITE_IP_0); + ctx->user_ip6[1] = bpf_htonl(SERV6_REWRITE_IP_1); + ctx->user_ip6[2] = bpf_htonl(SERV6_REWRITE_IP_2); + ctx->user_ip6[3] = bpf_htonl(SERV6_REWRITE_IP_3); + ctx->user_port = bpf_htons(SERV6_REWRITE_PORT); + + return 1; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/bpf_flow.c b/tools/testing/selftests/bpf/progs/bpf_flow.c index 5a65f6b51377..95a5a0778ed7 100644 --- a/tools/testing/selftests/bpf/progs/bpf_flow.c +++ b/tools/testing/selftests/bpf/progs/bpf_flow.c @@ -368,6 +368,8 @@ PROG(IPV6FR)(struct __sk_buff *skb) */ if (!(keys->flags & BPF_FLOW_DISSECTOR_F_PARSE_1ST_FRAG)) return export_flow_keys(keys, BPF_OK); + } else { + return export_flow_keys(keys, BPF_OK); } return parse_ipv6_proto(skb, fragh->nexthdr); diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c index 08651b23edba..b83b5d2e17dc 100644 --- a/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c +++ b/tools/testing/selftests/bpf/progs/bpf_iter_bpf_map.c @@ -23,6 +23,6 @@ int dump_bpf_map(struct bpf_iter__bpf_map *ctx) BPF_SEQ_PRINTF(seq, "%8u %8ld %8ld %10lu\n", map->id, map->refcnt.counter, map->usercnt.counter, - map->memory.user->locked_vm.counter); + 0LLU); return 0; } diff --git a/tools/testing/selftests/bpf/progs/bprm_opts.c b/tools/testing/selftests/bpf/progs/bprm_opts.c new file mode 100644 index 000000000000..5bfef2887e70 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/bprm_opts.c @@ -0,0 +1,34 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright 2020 Google LLC. + */ + +#include "vmlinux.h" +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct { + __uint(type, BPF_MAP_TYPE_TASK_STORAGE); + __uint(map_flags, BPF_F_NO_PREALLOC); + __type(key, int); + __type(value, int); +} secure_exec_task_map SEC(".maps"); + +SEC("lsm/bprm_creds_for_exec") +int BPF_PROG(secure_exec, struct linux_binprm *bprm) +{ + int *secureexec; + + secureexec = bpf_task_storage_get(&secure_exec_task_map, + bpf_get_current_task_btf(), 0, + BPF_LOCAL_STORAGE_GET_F_CREATE); + + if (secureexec && *secureexec) + bpf_bprm_opts_set(bprm, BPF_F_BPRM_SECUREEXEC); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/core_reloc_types.h b/tools/testing/selftests/bpf/progs/core_reloc_types.h index e6e616cb7bc9..9a2850850121 100644 --- a/tools/testing/selftests/bpf/progs/core_reloc_types.h +++ b/tools/testing/selftests/bpf/progs/core_reloc_types.h @@ -16,6 +16,23 @@ struct core_reloc_kernel_output { }; /* + * MODULE + */ + +struct core_reloc_module_output { + long long len; + long long off; + int read_ctx_sz; + bool read_ctx_exists; + bool buf_exists; + bool len_exists; + bool off_exists; + /* we have test_progs[-flavor], so cut flavor part */ + char comm[sizeof("test_progs")]; + int comm_len; +}; + +/* * FLAVORS */ struct core_reloc_flavors { diff --git a/tools/testing/selftests/bpf/progs/ima.c b/tools/testing/selftests/bpf/progs/ima.c new file mode 100644 index 000000000000..86b21aff4bc5 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/ima.c @@ -0,0 +1,28 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright 2020 Google LLC. + */ + +#include "vmlinux.h" +#include <errno.h> +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> + +long ima_hash_ret = -1; +u64 ima_hash = 0; +u32 monitored_pid = 0; + +char _license[] SEC("license") = "GPL"; + +SEC("lsm.s/bprm_committed_creds") +int BPF_PROG(ima, struct linux_binprm *bprm) +{ + u32 pid = bpf_get_current_pid_tgid() >> 32; + + if (pid == monitored_pid) + ima_hash_ret = bpf_ima_inode_hash(bprm->file->f_inode, + &ima_hash, sizeof(ima_hash)); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/map_ptr_kern.c b/tools/testing/selftests/bpf/progs/map_ptr_kern.c index c325405751e2..d8850bc6a9f1 100644 --- a/tools/testing/selftests/bpf/progs/map_ptr_kern.c +++ b/tools/testing/selftests/bpf/progs/map_ptr_kern.c @@ -26,17 +26,12 @@ __u32 g_line = 0; return 0; \ }) -struct bpf_map_memory { - __u32 pages; -} __attribute__((preserve_access_index)); - struct bpf_map { enum bpf_map_type map_type; __u32 key_size; __u32 value_size; __u32 max_entries; __u32 id; - struct bpf_map_memory memory; } __attribute__((preserve_access_index)); static inline int check_bpf_map_fields(struct bpf_map *map, __u32 key_size, @@ -47,7 +42,6 @@ static inline int check_bpf_map_fields(struct bpf_map *map, __u32 key_size, VERIFY(map->value_size == value_size); VERIFY(map->max_entries == max_entries); VERIFY(map->id > 0); - VERIFY(map->memory.pages > 0); return 1; } @@ -60,7 +54,6 @@ static inline int check_bpf_map_ptr(struct bpf_map *indirect, VERIFY(indirect->value_size == direct->value_size); VERIFY(indirect->max_entries == direct->max_entries); VERIFY(indirect->id == direct->id); - VERIFY(indirect->memory.pages == direct->memory.pages); return 1; } diff --git a/tools/testing/selftests/bpf/progs/profiler.inc.h b/tools/testing/selftests/bpf/progs/profiler.inc.h index 30982a7e4d0f..4896fdf816f7 100644 --- a/tools/testing/selftests/bpf/progs/profiler.inc.h +++ b/tools/testing/selftests/bpf/progs/profiler.inc.h @@ -256,6 +256,7 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, BPF_CORE_READ(task, nsproxy, cgroup_ns, root_cset, dfl_cgrp, kn); struct kernfs_node* proc_kernfs = BPF_CORE_READ(task, cgroups, dfl_cgrp, kn); +#if __has_builtin(__builtin_preserve_enum_value) if (ENABLE_CGROUP_V1_RESOLVER && CONFIG_CGROUP_PIDS) { int cgrp_id = bpf_core_enum_value(enum cgroup_subsys_id___local, pids_cgrp_id___local); @@ -275,6 +276,7 @@ static INLINE void* populate_cgroup_info(struct cgroup_data_t* cgroup_data, } } } +#endif cgroup_data->cgroup_root_inode = get_inode_from_kernfs(root_kernfs); cgroup_data->cgroup_proc_inode = get_inode_from_kernfs(proc_kernfs); diff --git a/tools/testing/selftests/bpf/progs/test_core_reloc_module.c b/tools/testing/selftests/bpf/progs/test_core_reloc_module.c new file mode 100644 index 000000000000..56363959f7b0 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_core_reloc_module.c @@ -0,0 +1,96 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_core_read.h> +#include <bpf/bpf_tracing.h> + +char _license[] SEC("license") = "GPL"; + +struct bpf_testmod_test_read_ctx { + /* field order is mixed up */ + size_t len; + char *buf; + loff_t off; +} __attribute__((preserve_access_index)); + +struct { + char in[256]; + char out[256]; + bool skip; + uint64_t my_pid_tgid; +} data = {}; + +struct core_reloc_module_output { + long long len; + long long off; + int read_ctx_sz; + bool read_ctx_exists; + bool buf_exists; + bool len_exists; + bool off_exists; + /* we have test_progs[-flavor], so cut flavor part */ + char comm[sizeof("test_progs")]; + int comm_len; +}; + +SEC("raw_tp/bpf_testmod_test_read") +int BPF_PROG(test_core_module_probed, + struct task_struct *task, + struct bpf_testmod_test_read_ctx *read_ctx) +{ + struct core_reloc_module_output *out = (void *)&data.out; + __u64 pid_tgid = bpf_get_current_pid_tgid(); + __u32 real_tgid = (__u32)(pid_tgid >> 32); + __u32 real_pid = (__u32)pid_tgid; + + if (data.my_pid_tgid != pid_tgid) + return 0; + + if (BPF_CORE_READ(task, pid) != real_pid || BPF_CORE_READ(task, tgid) != real_tgid) + return 0; + + out->len = BPF_CORE_READ(read_ctx, len); + out->off = BPF_CORE_READ(read_ctx, off); + + out->read_ctx_sz = bpf_core_type_size(struct bpf_testmod_test_read_ctx); + out->read_ctx_exists = bpf_core_type_exists(struct bpf_testmod_test_read_ctx); + out->buf_exists = bpf_core_field_exists(read_ctx->buf); + out->off_exists = bpf_core_field_exists(read_ctx->off); + out->len_exists = bpf_core_field_exists(read_ctx->len); + + out->comm_len = BPF_CORE_READ_STR_INTO(&out->comm, task, comm); + + return 0; +} + +SEC("tp_btf/bpf_testmod_test_read") +int BPF_PROG(test_core_module_direct, + struct task_struct *task, + struct bpf_testmod_test_read_ctx *read_ctx) +{ + struct core_reloc_module_output *out = (void *)&data.out; + __u64 pid_tgid = bpf_get_current_pid_tgid(); + __u32 real_tgid = (__u32)(pid_tgid >> 32); + __u32 real_pid = (__u32)pid_tgid; + + if (data.my_pid_tgid != pid_tgid) + return 0; + + if (task->pid != real_pid || task->tgid != real_tgid) + return 0; + + out->len = read_ctx->len; + out->off = read_ctx->off; + + out->read_ctx_sz = bpf_core_type_size(struct bpf_testmod_test_read_ctx); + out->read_ctx_exists = bpf_core_type_exists(struct bpf_testmod_test_read_ctx); + out->buf_exists = bpf_core_field_exists(read_ctx->buf); + out->off_exists = bpf_core_field_exists(read_ctx->off); + out->len_exists = bpf_core_field_exists(read_ctx->len); + + out->comm_len = BPF_CORE_READ_STR_INTO(&out->comm, task, comm); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/test_module_attach.c b/tools/testing/selftests/bpf/progs/test_module_attach.c new file mode 100644 index 000000000000..b563563df172 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/test_module_attach.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2020 Facebook */ + +#include "vmlinux.h" +#include <bpf/bpf_helpers.h> +#include <bpf/bpf_tracing.h> +#include <bpf/bpf_core_read.h> +#include "../bpf_testmod/bpf_testmod.h" + +__u32 raw_tp_read_sz = 0; + +SEC("raw_tp/bpf_testmod_test_read") +int BPF_PROG(handle_raw_tp, + struct task_struct *task, struct bpf_testmod_test_read_ctx *read_ctx) +{ + raw_tp_read_sz = BPF_CORE_READ(read_ctx, len); + return 0; +} + +__u32 tp_btf_read_sz = 0; + +SEC("tp_btf/bpf_testmod_test_read") +int BPF_PROG(handle_tp_btf, + struct task_struct *task, struct bpf_testmod_test_read_ctx *read_ctx) +{ + tp_btf_read_sz = read_ctx->len; + return 0; +} + +__u32 fentry_read_sz = 0; + +SEC("fentry/bpf_testmod_test_read") +int BPF_PROG(handle_fentry, + struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len) +{ + fentry_read_sz = len; + return 0; +} + +__u32 fexit_read_sz = 0; +int fexit_ret = 0; + +SEC("fexit/bpf_testmod_test_read") +int BPF_PROG(handle_fexit, + struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len, + int ret) +{ + fexit_read_sz = len; + fexit_ret = ret; + return 0; +} + +__u32 fmod_ret_read_sz = 0; + +SEC("fmod_ret/bpf_testmod_test_read") +int BPF_PROG(handle_fmod_ret, + struct file *file, struct kobject *kobj, + struct bin_attribute *bin_attr, char *buf, loff_t off, size_t len) +{ + fmod_ret_read_sz = len; + return 0; /* don't override the exit code */ +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c index e85e49deba70..94f50f7e94d6 100644 --- a/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c +++ b/tools/testing/selftests/bpf/progs/test_tcpbpf_kern.c @@ -12,17 +12,41 @@ #include <linux/tcp.h> #include <bpf/bpf_helpers.h> #include <bpf/bpf_endian.h> +#include "bpf_tcp_helpers.h" #include "test_tcpbpf.h" struct tcpbpf_globals global = {}; int _version SEC("version") = 1; +/** + * SOL_TCP is defined in <netinet/tcp.h> while + * TCP_SAVED_SYN is defined in already included <linux/tcp.h> + */ +#ifndef SOL_TCP +#define SOL_TCP 6 +#endif + +static __always_inline int get_tp_window_clamp(struct bpf_sock_ops *skops) +{ + struct bpf_sock *sk; + struct tcp_sock *tp; + + sk = skops->sk; + if (!sk) + return -1; + tp = bpf_skc_to_tcp_sock(sk); + if (!tp) + return -1; + return tp->window_clamp; +} + SEC("sockops") int bpf_testcb(struct bpf_sock_ops *skops) { char header[sizeof(struct ipv6hdr) + sizeof(struct tcphdr)]; struct bpf_sock_ops *reuse = skops; struct tcphdr *thdr; + int window_clamp = 9216; int good_call_rv = 0; int bad_call_rv = 0; int save_syn = 1; @@ -75,6 +99,11 @@ int bpf_testcb(struct bpf_sock_ops *skops) global.event_map |= (1 << op); switch (op) { + case BPF_SOCK_OPS_TCP_CONNECT_CB: + rv = bpf_setsockopt(skops, SOL_TCP, TCP_WINDOW_CLAMP, + &window_clamp, sizeof(window_clamp)); + global.window_clamp_client = get_tp_window_clamp(skops); + break; case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB: /* Test failure to set largest cb flag (assumes not defined) */ global.bad_cb_test_rv = bpf_sock_ops_cb_flags_set(skops, 0x80); @@ -100,6 +129,10 @@ int bpf_testcb(struct bpf_sock_ops *skops) global.tcp_saved_syn = v; } } + rv = bpf_setsockopt(skops, SOL_TCP, TCP_WINDOW_CLAMP, + &window_clamp, sizeof(window_clamp)); + + global.window_clamp_server = get_tp_window_clamp(skops); break; case BPF_SOCK_OPS_RTO_CB: break; diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 22943b58d752..5ef081bdae4e 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -149,15 +149,15 @@ void test__end_subtest() if (sub_error_cnt) env.fail_cnt++; - else + else if (test->skip_cnt == 0) env.sub_succ_cnt++; skip_account(); dump_test_log(test, sub_error_cnt); fprintf(env.stdout, "#%d/%d %s:%s\n", - test->test_num, test->subtest_num, - test->subtest_name, sub_error_cnt ? "FAIL" : "OK"); + test->test_num, test->subtest_num, test->subtest_name, + sub_error_cnt ? "FAIL" : (test->skip_cnt ? "SKIP" : "OK")); free(test->subtest_name); test->subtest_name = NULL; @@ -360,6 +360,58 @@ err: return -1; } +static int finit_module(int fd, const char *param_values, int flags) +{ + return syscall(__NR_finit_module, fd, param_values, flags); +} + +static int delete_module(const char *name, int flags) +{ + return syscall(__NR_delete_module, name, flags); +} + +static void unload_bpf_testmod(void) +{ + if (delete_module("bpf_testmod", 0)) { + if (errno == ENOENT) { + if (env.verbosity > VERBOSE_NONE) + fprintf(stdout, "bpf_testmod.ko is already unloaded.\n"); + return; + } + fprintf(env.stderr, "Failed to unload bpf_testmod.ko from kernel: %d\n", -errno); + exit(1); + } + if (env.verbosity > VERBOSE_NONE) + fprintf(stdout, "Successfully unloaded bpf_testmod.ko.\n"); +} + +static int load_bpf_testmod(void) +{ + int fd; + + /* ensure previous instance of the module is unloaded */ + unload_bpf_testmod(); + + if (env.verbosity > VERBOSE_NONE) + fprintf(stdout, "Loading bpf_testmod.ko...\n"); + + fd = open("bpf_testmod.ko", O_RDONLY); + if (fd < 0) { + fprintf(env.stderr, "Can't find bpf_testmod.ko kernel module: %d\n", -errno); + return -ENOENT; + } + if (finit_module(fd, "", 0)) { + fprintf(env.stderr, "Failed to load bpf_testmod.ko into the kernel: %d\n", -errno); + close(fd); + return -EINVAL; + } + close(fd); + + if (env.verbosity > VERBOSE_NONE) + fprintf(stdout, "Successfully loaded bpf_testmod.ko.\n"); + return 0; +} + /* extern declarations for test funcs */ #define DEFINE_TEST(name) extern void test_##name(void); #include <prog_tests/tests.h> @@ -678,6 +730,11 @@ int main(int argc, char **argv) save_netns(); stdio_hijack(); + env.has_testmod = true; + if (load_bpf_testmod()) { + fprintf(env.stderr, "WARNING! Selftests relying on bpf_testmod.ko will be skipped.\n"); + env.has_testmod = false; + } for (i = 0; i < prog_test_cnt; i++) { struct prog_test_def *test = &prog_test_defs[i]; @@ -722,6 +779,8 @@ int main(int argc, char **argv) if (test->need_cgroup_cleanup) cleanup_cgroup_environment(); } + if (env.has_testmod) + unload_bpf_testmod(); stdio_restore(); if (env.get_test_cnt) { diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h index d6b14853f3bc..115953243f62 100644 --- a/tools/testing/selftests/bpf/test_progs.h +++ b/tools/testing/selftests/bpf/test_progs.h @@ -66,6 +66,7 @@ struct test_env { enum verbosity verbosity; bool jit_enabled; + bool has_testmod; bool get_test_cnt; bool list_test_names; diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c index b8c72c1d9cf7..dcb83ab02919 100644 --- a/tools/testing/selftests/bpf/test_sock_addr.c +++ b/tools/testing/selftests/bpf/test_sock_addr.c @@ -31,6 +31,8 @@ #define CONNECT6_PROG_PATH "./connect6_prog.o" #define SENDMSG4_PROG_PATH "./sendmsg4_prog.o" #define SENDMSG6_PROG_PATH "./sendmsg6_prog.o" +#define BIND4_PROG_PATH "./bind4_prog.o" +#define BIND6_PROG_PATH "./bind6_prog.o" #define SERV4_IP "192.168.1.254" #define SERV4_REWRITE_IP "127.0.0.1" @@ -660,190 +662,6 @@ static int load_insns(const struct sock_addr_test *test, return ret; } -/* [1] These testing programs try to read different context fields, including - * narrow loads of different sizes from user_ip4 and user_ip6, and write to - * those allowed to be overridden. - * - * [2] BPF_LD_IMM64 & BPF_JMP_REG are used below whenever there is a need to - * compare a register with unsigned 32bit integer. BPF_JMP_IMM can't be used - * in such cases since it accepts only _signed_ 32bit integer as IMM - * argument. Also note that BPF_LD_IMM64 contains 2 instructions what matters - * to count jumps properly. - */ - -static int bind4_prog_load(const struct sock_addr_test *test) -{ - union { - uint8_t u4_addr8[4]; - uint16_t u4_addr16[2]; - uint32_t u4_addr32; - } ip4, port; - struct sockaddr_in addr4_rw; - - if (inet_pton(AF_INET, SERV4_IP, (void *)&ip4) != 1) { - log_err("Invalid IPv4: %s", SERV4_IP); - return -1; - } - - port.u4_addr32 = htons(SERV4_PORT); - - if (mk_sockaddr(AF_INET, SERV4_REWRITE_IP, SERV4_REWRITE_PORT, - (struct sockaddr *)&addr4_rw, sizeof(addr4_rw)) == -1) - return -1; - - /* See [1]. */ - struct bpf_insn insns[] = { - BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), - - /* if (sk.family == AF_INET && */ - BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock_addr, family)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET, 32), - - /* (sk.type == SOCK_DGRAM || sk.type == SOCK_STREAM) && */ - BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock_addr, type)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_DGRAM, 1), - BPF_JMP_A(1), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, SOCK_STREAM, 28), - - /* 1st_byte_of_user_ip4 == expected && */ - BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock_addr, user_ip4)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[0], 26), - - /* 2nd_byte_of_user_ip4 == expected && */ - BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock_addr, user_ip4) + 1), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[1], 24), - - /* 3rd_byte_of_user_ip4 == expected && */ - BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock_addr, user_ip4) + 2), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[2], 22), - - /* 4th_byte_of_user_ip4 == expected && */ - BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock_addr, user_ip4) + 3), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr8[3], 20), - - /* 1st_half_of_user_ip4 == expected && */ - BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock_addr, user_ip4)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[0], 18), - - /* 2nd_half_of_user_ip4 == expected && */ - BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock_addr, user_ip4) + 2), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip4.u4_addr16[1], 16), - - /* whole_user_ip4 == expected && */ - BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock_addr, user_ip4)), - BPF_LD_IMM64(BPF_REG_8, ip4.u4_addr32), /* See [2]. */ - BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_8, 12), - - /* 1st_byte_of_user_port == expected && */ - BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock_addr, user_port)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, port.u4_addr8[0], 10), - - /* 1st_half_of_user_port == expected && */ - BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock_addr, user_port)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, port.u4_addr16[0], 8), - - /* user_port == expected) { */ - BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock_addr, user_port)), - BPF_LD_IMM64(BPF_REG_8, port.u4_addr32), /* See [2]. */ - BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_8, 4), - - /* user_ip4 = addr4_rw.sin_addr */ - BPF_MOV32_IMM(BPF_REG_7, addr4_rw.sin_addr.s_addr), - BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, - offsetof(struct bpf_sock_addr, user_ip4)), - - /* user_port = addr4_rw.sin_port */ - BPF_MOV32_IMM(BPF_REG_7, addr4_rw.sin_port), - BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, - offsetof(struct bpf_sock_addr, user_port)), - /* } */ - - /* return 1 */ - BPF_MOV64_IMM(BPF_REG_0, 1), - BPF_EXIT_INSN(), - }; - - return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); -} - -static int bind6_prog_load(const struct sock_addr_test *test) -{ - struct sockaddr_in6 addr6_rw; - struct in6_addr ip6; - - if (inet_pton(AF_INET6, SERV6_IP, (void *)&ip6) != 1) { - log_err("Invalid IPv6: %s", SERV6_IP); - return -1; - } - - if (mk_sockaddr(AF_INET6, SERV6_REWRITE_IP, SERV6_REWRITE_PORT, - (struct sockaddr *)&addr6_rw, sizeof(addr6_rw)) == -1) - return -1; - - /* See [1]. */ - struct bpf_insn insns[] = { - BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), - - /* if (sk.family == AF_INET6 && */ - BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock_addr, family)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, AF_INET6, 18), - - /* 5th_byte_of_user_ip6 == expected && */ - BPF_LDX_MEM(BPF_B, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock_addr, user_ip6[1])), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip6.s6_addr[4], 16), - - /* 3rd_half_of_user_ip6 == expected && */ - BPF_LDX_MEM(BPF_H, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock_addr, user_ip6[1])), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, ip6.s6_addr16[2], 14), - - /* last_word_of_user_ip6 == expected) { */ - BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, - offsetof(struct bpf_sock_addr, user_ip6[3])), - BPF_LD_IMM64(BPF_REG_8, ip6.s6_addr32[3]), /* See [2]. */ - BPF_JMP_REG(BPF_JNE, BPF_REG_7, BPF_REG_8, 10), - - -#define STORE_IPV6_WORD(N) \ - BPF_MOV32_IMM(BPF_REG_7, addr6_rw.sin6_addr.s6_addr32[N]), \ - BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, \ - offsetof(struct bpf_sock_addr, user_ip6[N])) - - /* user_ip6 = addr6_rw.sin6_addr */ - STORE_IPV6_WORD(0), - STORE_IPV6_WORD(1), - STORE_IPV6_WORD(2), - STORE_IPV6_WORD(3), - - /* user_port = addr6_rw.sin6_port */ - BPF_MOV32_IMM(BPF_REG_7, addr6_rw.sin6_port), - BPF_STX_MEM(BPF_W, BPF_REG_6, BPF_REG_7, - offsetof(struct bpf_sock_addr, user_port)), - - /* } */ - - /* return 1 */ - BPF_MOV64_IMM(BPF_REG_0, 1), - BPF_EXIT_INSN(), - }; - - return load_insns(test, insns, sizeof(insns) / sizeof(struct bpf_insn)); -} - static int load_path(const struct sock_addr_test *test, const char *path) { struct bpf_prog_load_attr attr; @@ -865,6 +683,16 @@ static int load_path(const struct sock_addr_test *test, const char *path) return prog_fd; } +static int bind4_prog_load(const struct sock_addr_test *test) +{ + return load_path(test, BIND4_PROG_PATH); +} + +static int bind6_prog_load(const struct sock_addr_test *test) +{ + return load_path(test, BIND6_PROG_PATH); +} + static int connect4_prog_load(const struct sock_addr_test *test) { return load_path(test, CONNECT4_PROG_PATH); diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 0fa1e421c3d7..427ca00a3217 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -1273,6 +1273,16 @@ static char *test_to_str(int test) return "unknown"; } +static void append_str(char *dst, const char *src, size_t dst_cap) +{ + size_t avail = dst_cap - strlen(dst); + + if (avail <= 1) /* just zero byte could be written */ + return; + + strncat(dst, src, avail - 1); /* strncat() adds + 1 for zero byte */ +} + #define OPTSTRING 60 static void test_options(char *options) { @@ -1281,42 +1291,42 @@ static void test_options(char *options) memset(options, 0, OPTSTRING); if (txmsg_pass) - strncat(options, "pass,", OPTSTRING); + append_str(options, "pass,", OPTSTRING); if (txmsg_redir) - strncat(options, "redir,", OPTSTRING); + append_str(options, "redir,", OPTSTRING); if (txmsg_drop) - strncat(options, "drop,", OPTSTRING); + append_str(options, "drop,", OPTSTRING); if (txmsg_apply) { snprintf(tstr, OPTSTRING, "apply %d,", txmsg_apply); - strncat(options, tstr, OPTSTRING); + append_str(options, tstr, OPTSTRING); } if (txmsg_cork) { snprintf(tstr, OPTSTRING, "cork %d,", txmsg_cork); - strncat(options, tstr, OPTSTRING); + append_str(options, tstr, OPTSTRING); } if (txmsg_start) { snprintf(tstr, OPTSTRING, "start %d,", txmsg_start); - strncat(options, tstr, OPTSTRING); + append_str(options, tstr, OPTSTRING); } if (txmsg_end) { snprintf(tstr, OPTSTRING, "end %d,", txmsg_end); - strncat(options, tstr, OPTSTRING); + append_str(options, tstr, OPTSTRING); } if (txmsg_start_pop) { snprintf(tstr, OPTSTRING, "pop (%d,%d),", txmsg_start_pop, txmsg_start_pop + txmsg_pop); - strncat(options, tstr, OPTSTRING); + append_str(options, tstr, OPTSTRING); } if (txmsg_ingress) - strncat(options, "ingress,", OPTSTRING); + append_str(options, "ingress,", OPTSTRING); if (txmsg_redir_skb) - strncat(options, "redir_skb,", OPTSTRING); + append_str(options, "redir_skb,", OPTSTRING); if (txmsg_ktls_skb) - strncat(options, "ktls_skb,", OPTSTRING); + append_str(options, "ktls_skb,", OPTSTRING); if (ktls) - strncat(options, "ktls,", OPTSTRING); + append_str(options, "ktls,", OPTSTRING); if (peek_flag) - strncat(options, "peek,", OPTSTRING); + append_str(options, "peek,", OPTSTRING); } static int __test_exec(int cgrp, int test, struct sockmap_options *opt) diff --git a/tools/testing/selftests/bpf/test_tcpbpf.h b/tools/testing/selftests/bpf/test_tcpbpf.h index 0ed33521cbbb..9dd9b5590f9d 100644 --- a/tools/testing/selftests/bpf/test_tcpbpf.h +++ b/tools/testing/selftests/bpf/test_tcpbpf.h @@ -16,5 +16,7 @@ struct tcpbpf_globals { __u32 num_close_events; __u32 tcp_save_syn; __u32 tcp_saved_syn; + __u32 window_clamp_client; + __u32 window_clamp_server; }; #endif diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 9be395d9dc64..4bfe3aa2cfc4 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -1152,6 +1152,19 @@ static void get_unpriv_disabled() static bool test_as_unpriv(struct bpf_test *test) { +#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + /* Some architectures have strict alignment requirements. In + * that case, the BPF verifier detects if a program has + * unaligned accesses and rejects them. A user can pass + * BPF_F_ANY_ALIGNMENT to a program to override this + * check. That, however, will only work when a privileged user + * loads a program. An unprivileged user loading a program + * with this flag will be rejected prior entering the + * verifier. + */ + if (test->flags & F_NEEDS_EFFICIENT_UNALIGNED_ACCESS) + return false; +#endif return !test->prog_type || test->prog_type == BPF_PROG_TYPE_SOCKET_FILTER || test->prog_type == BPF_PROG_TYPE_CGROUP_SKB; diff --git a/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c b/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c index 2ad5f974451c..fb13ca2d5606 100644 --- a/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c +++ b/tools/testing/selftests/bpf/verifier/ctx_sk_lookup.c @@ -266,6 +266,7 @@ .result = REJECT, .prog_type = BPF_PROG_TYPE_SK_LOOKUP, .expected_attach_type = BPF_SK_LOOKUP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "invalid 8-byte read from bpf_sk_lookup remote_ip4 field", @@ -292,6 +293,7 @@ .result = REJECT, .prog_type = BPF_PROG_TYPE_SK_LOOKUP, .expected_attach_type = BPF_SK_LOOKUP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "invalid 8-byte read from bpf_sk_lookup remote_port field", @@ -305,6 +307,7 @@ .result = REJECT, .prog_type = BPF_PROG_TYPE_SK_LOOKUP, .expected_attach_type = BPF_SK_LOOKUP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "invalid 8-byte read from bpf_sk_lookup local_ip4 field", @@ -331,6 +334,7 @@ .result = REJECT, .prog_type = BPF_PROG_TYPE_SK_LOOKUP, .expected_attach_type = BPF_SK_LOOKUP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "invalid 8-byte read from bpf_sk_lookup local_port field", @@ -344,6 +348,7 @@ .result = REJECT, .prog_type = BPF_PROG_TYPE_SK_LOOKUP, .expected_attach_type = BPF_SK_LOOKUP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, /* invalid 1,2,4-byte reads from 8-byte fields in bpf_sk_lookup */ { @@ -410,6 +415,7 @@ .result = REJECT, .prog_type = BPF_PROG_TYPE_SK_LOOKUP, .expected_attach_type = BPF_SK_LOOKUP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "invalid 4-byte unaligned read from bpf_sk_lookup at even offset", @@ -422,6 +428,7 @@ .result = REJECT, .prog_type = BPF_PROG_TYPE_SK_LOOKUP, .expected_attach_type = BPF_SK_LOOKUP, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, /* in-bound and out-of-bound writes to bpf_sk_lookup */ { diff --git a/tools/testing/selftests/bpf/verifier/direct_value_access.c b/tools/testing/selftests/bpf/verifier/direct_value_access.c index 988f46a1a4c7..c0648dc009b5 100644 --- a/tools/testing/selftests/bpf/verifier/direct_value_access.c +++ b/tools/testing/selftests/bpf/verifier/direct_value_access.c @@ -69,6 +69,7 @@ .fixup_map_array_48b = { 1 }, .result = REJECT, .errstr = "R1 min value is outside of the allowed memory range", + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "direct map access, write test 7", @@ -195,6 +196,7 @@ .fixup_map_array_48b = { 1, 3 }, .result = REJECT, .errstr = "invalid access to map value, value_size=48 off=47 size=2", + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "direct map access, write test 17", @@ -209,6 +211,7 @@ .fixup_map_array_48b = { 1, 3 }, .result = REJECT, .errstr = "invalid access to map value, value_size=48 off=47 size=2", + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "direct map access, write test 18", diff --git a/tools/testing/selftests/bpf/verifier/map_ptr.c b/tools/testing/selftests/bpf/verifier/map_ptr.c index 637f9293bda8..b117bdd3806d 100644 --- a/tools/testing/selftests/bpf/verifier/map_ptr.c +++ b/tools/testing/selftests/bpf/verifier/map_ptr.c @@ -44,6 +44,7 @@ .errstr_unpriv = "bpf_array access is allowed only to CAP_PERFMON and CAP_SYS_ADMIN", .result = REJECT, .errstr = "cannot access ptr member ops with moff 0 in struct bpf_map with off 1 size 4", + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "bpf_map_ptr: read ops field accepted", diff --git a/tools/testing/selftests/bpf/verifier/raw_tp_writable.c b/tools/testing/selftests/bpf/verifier/raw_tp_writable.c index 95b5d70a1dc1..2978fb5a769d 100644 --- a/tools/testing/selftests/bpf/verifier/raw_tp_writable.c +++ b/tools/testing/selftests/bpf/verifier/raw_tp_writable.c @@ -31,4 +31,5 @@ .fixup_map_hash_8b = { 1, }, .prog_type = BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, .errstr = "R6 invalid variable buffer offset: off=0, var_off=(0x0; 0xffffffff)", + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, diff --git a/tools/testing/selftests/bpf/verifier/ref_tracking.c b/tools/testing/selftests/bpf/verifier/ref_tracking.c index 006b5bd99c08..3b6ee009c00b 100644 --- a/tools/testing/selftests/bpf/verifier/ref_tracking.c +++ b/tools/testing/selftests/bpf/verifier/ref_tracking.c @@ -675,6 +675,7 @@ .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, .errstr = "invalid mem access", + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "reference tracking: use ptr from bpf_sk_fullsock() after release", @@ -698,6 +699,7 @@ .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, .errstr = "invalid mem access", + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "reference tracking: use ptr from bpf_sk_fullsock(tp) after release", @@ -725,6 +727,7 @@ .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, .errstr = "invalid mem access", + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "reference tracking: use sk after bpf_sk_release(tp)", @@ -747,6 +750,7 @@ .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, .errstr = "invalid mem access", + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "reference tracking: use ptr from bpf_get_listener_sock() after bpf_sk_release(sk)", diff --git a/tools/testing/selftests/bpf/verifier/regalloc.c b/tools/testing/selftests/bpf/verifier/regalloc.c index 4ad7e05de706..bb0dd89dd212 100644 --- a/tools/testing/selftests/bpf/verifier/regalloc.c +++ b/tools/testing/selftests/bpf/verifier/regalloc.c @@ -21,6 +21,7 @@ .fixup_map_hash_48b = { 4 }, .result = ACCEPT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "regalloc negative", @@ -71,6 +72,7 @@ .fixup_map_hash_48b = { 4 }, .result = ACCEPT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "regalloc src_reg negative", @@ -97,6 +99,7 @@ .result = REJECT, .errstr = "invalid access to map value, value_size=48 off=44 size=8", .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "regalloc and spill", @@ -126,6 +129,7 @@ .fixup_map_hash_48b = { 4 }, .result = ACCEPT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "regalloc and spill negative", @@ -156,6 +160,7 @@ .result = REJECT, .errstr = "invalid access to map value, value_size=48 off=48 size=8", .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "regalloc three regs", @@ -182,6 +187,7 @@ .fixup_map_hash_48b = { 4 }, .result = ACCEPT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "regalloc after call", @@ -210,6 +216,7 @@ .fixup_map_hash_48b = { 4 }, .result = ACCEPT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "regalloc in callee", @@ -240,6 +247,7 @@ .fixup_map_hash_48b = { 4 }, .result = ACCEPT, .prog_type = BPF_PROG_TYPE_TRACEPOINT, + .flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS, }, { "regalloc, spill, JEQ", diff --git a/tools/testing/selftests/bpf/verifier/wide_access.c b/tools/testing/selftests/bpf/verifier/wide_access.c index ccade9312d21..55af248efa93 100644 --- a/tools/testing/selftests/bpf/verifier/wide_access.c +++ b/tools/testing/selftests/bpf/verifier/wide_access.c @@ -1,4 +1,4 @@ -#define BPF_SOCK_ADDR_STORE(field, off, res, err) \ +#define BPF_SOCK_ADDR_STORE(field, off, res, err, flgs) \ { \ "wide store to bpf_sock_addr." #field "[" #off "]", \ .insns = { \ @@ -11,31 +11,36 @@ .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, \ .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, \ .errstr = err, \ + .flags = flgs, \ } /* user_ip6[0] is u64 aligned */ BPF_SOCK_ADDR_STORE(user_ip6, 0, ACCEPT, - NULL), + NULL, 0), BPF_SOCK_ADDR_STORE(user_ip6, 1, REJECT, - "invalid bpf_context access off=12 size=8"), + "invalid bpf_context access off=12 size=8", + F_NEEDS_EFFICIENT_UNALIGNED_ACCESS), BPF_SOCK_ADDR_STORE(user_ip6, 2, ACCEPT, - NULL), + NULL, 0), BPF_SOCK_ADDR_STORE(user_ip6, 3, REJECT, - "invalid bpf_context access off=20 size=8"), + "invalid bpf_context access off=20 size=8", + F_NEEDS_EFFICIENT_UNALIGNED_ACCESS), /* msg_src_ip6[0] is _not_ u64 aligned */ BPF_SOCK_ADDR_STORE(msg_src_ip6, 0, REJECT, - "invalid bpf_context access off=44 size=8"), + "invalid bpf_context access off=44 size=8", + F_NEEDS_EFFICIENT_UNALIGNED_ACCESS), BPF_SOCK_ADDR_STORE(msg_src_ip6, 1, ACCEPT, - NULL), + NULL, 0), BPF_SOCK_ADDR_STORE(msg_src_ip6, 2, REJECT, - "invalid bpf_context access off=52 size=8"), + "invalid bpf_context access off=52 size=8", + F_NEEDS_EFFICIENT_UNALIGNED_ACCESS), BPF_SOCK_ADDR_STORE(msg_src_ip6, 3, REJECT, - "invalid bpf_context access off=56 size=8"), + "invalid bpf_context access off=56 size=8", 0), #undef BPF_SOCK_ADDR_STORE -#define BPF_SOCK_ADDR_LOAD(field, off, res, err) \ +#define BPF_SOCK_ADDR_LOAD(field, off, res, err, flgs) \ { \ "wide load from bpf_sock_addr." #field "[" #off "]", \ .insns = { \ @@ -48,26 +53,31 @@ BPF_SOCK_ADDR_STORE(msg_src_ip6, 3, REJECT, .prog_type = BPF_PROG_TYPE_CGROUP_SOCK_ADDR, \ .expected_attach_type = BPF_CGROUP_UDP6_SENDMSG, \ .errstr = err, \ + .flags = flgs, \ } /* user_ip6[0] is u64 aligned */ BPF_SOCK_ADDR_LOAD(user_ip6, 0, ACCEPT, - NULL), + NULL, 0), BPF_SOCK_ADDR_LOAD(user_ip6, 1, REJECT, - "invalid bpf_context access off=12 size=8"), + "invalid bpf_context access off=12 size=8", + F_NEEDS_EFFICIENT_UNALIGNED_ACCESS), BPF_SOCK_ADDR_LOAD(user_ip6, 2, ACCEPT, - NULL), + NULL, 0), BPF_SOCK_ADDR_LOAD(user_ip6, 3, REJECT, - "invalid bpf_context access off=20 size=8"), + "invalid bpf_context access off=20 size=8", + F_NEEDS_EFFICIENT_UNALIGNED_ACCESS), /* msg_src_ip6[0] is _not_ u64 aligned */ BPF_SOCK_ADDR_LOAD(msg_src_ip6, 0, REJECT, - "invalid bpf_context access off=44 size=8"), + "invalid bpf_context access off=44 size=8", + F_NEEDS_EFFICIENT_UNALIGNED_ACCESS), BPF_SOCK_ADDR_LOAD(msg_src_ip6, 1, ACCEPT, - NULL), + NULL, 0), BPF_SOCK_ADDR_LOAD(msg_src_ip6, 2, REJECT, - "invalid bpf_context access off=52 size=8"), + "invalid bpf_context access off=52 size=8", + F_NEEDS_EFFICIENT_UNALIGNED_ACCESS), BPF_SOCK_ADDR_LOAD(msg_src_ip6, 3, REJECT, - "invalid bpf_context access off=56 size=8"), + "invalid bpf_context access off=56 size=8", 0), #undef BPF_SOCK_ADDR_LOAD |