diff --git a/drivers/net/ethernet/intel/i40e/Makefile b/drivers/net/ethernet/intel/i40e/Makefile index 14397e7e9925..50590e8d1fd1 100644 --- a/drivers/net/ethernet/intel/i40e/Makefile +++ b/drivers/net/ethernet/intel/i40e/Makefile @@ -22,6 +22,7 @@ i40e-objs := i40e_main.o \ i40e_txrx.o \ i40e_ptp.o \ i40e_client.o \ - i40e_virtchnl_pf.o + i40e_virtchnl_pf.o \ + i40e_xsk.o i40e-$(CONFIG_I40E_DCB) += i40e_dcb.o i40e_dcb_nl.o diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 7a80652e2500..876cac317e79 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -786,6 +786,11 @@ struct i40e_vsi { /* VSI specific handlers */ irqreturn_t (*irq_handler)(int irq, void *data); + + /* AF_XDP zero-copy */ + struct xdp_umem **xsk_umems; + u16 num_xsk_umems_used; + u16 num_xsk_umems; } ____cacheline_internodealigned_in_smp; struct i40e_netdev_priv { @@ -1090,6 +1095,20 @@ static inline bool i40e_enabled_xdp_vsi(struct i40e_vsi *vsi) return !!vsi->xdp_prog; } +static inline struct xdp_umem *i40e_xsk_umem(struct i40e_ring *ring) +{ + bool xdp_on = i40e_enabled_xdp_vsi(ring->vsi); + int qid = ring->queue_index; + + if (ring_is_xdp(ring)) + qid -= ring->vsi->alloc_queue_pairs; + + if (!ring->vsi->xsk_umems || !ring->vsi->xsk_umems[qid] || !xdp_on) + return NULL; + + return ring->vsi->xsk_umems[qid]; +} + int i40e_create_queue_channel(struct i40e_vsi *vsi, struct i40e_channel *ch); int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate); int i40e_add_del_cloud_filter(struct i40e_vsi *vsi, diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 112245f32d7d..5d209d8fe9b8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -9,7 +9,9 @@ /* Local includes */ #include "i40e.h" #include "i40e_diag.h" +#include "i40e_xsk.h" #include +#include /* All i40e tracepoints are defined by the include below, which * must be included exactly once across the whole kernel with * CREATE_TRACE_POINTS defined @@ -3074,6 +3076,9 @@ static int i40e_configure_tx_ring(struct i40e_ring *ring) i40e_status err = 0; u32 qtx_ctl = 0; + if (ring_is_xdp(ring)) + ring->xsk_umem = i40e_xsk_umem(ring); + /* some ATR related tx ring init */ if (vsi->back->flags & I40E_FLAG_FD_ATR_ENABLED) { ring->atr_sample_rate = vsi->back->atr_sample_rate; @@ -3183,13 +3188,46 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) struct i40e_hw *hw = &vsi->back->hw; struct i40e_hmc_obj_rxq rx_ctx; i40e_status err = 0; + bool ok; + int ret; bitmap_zero(ring->state, __I40E_RING_STATE_NBITS); /* clear the context structure first */ memset(&rx_ctx, 0, sizeof(rx_ctx)); - ring->rx_buf_len = vsi->rx_buf_len; + if (ring->vsi->type == I40E_VSI_MAIN) + xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); + + ring->xsk_umem = i40e_xsk_umem(ring); + if (ring->xsk_umem) { + ring->rx_buf_len = ring->xsk_umem->chunk_size_nohr - + XDP_PACKET_HEADROOM; + /* For AF_XDP ZC, we disallow packets to span on + * multiple buffers, thus letting us skip that + * handling in the fast-path. + */ + chain_len = 1; + ring->zca.free = i40e_zca_free; + ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_ZERO_COPY, + &ring->zca); + if (ret) + return ret; + dev_info(&vsi->back->pdev->dev, + "Registered XDP mem model MEM_TYPE_ZERO_COPY on Rx ring %d\n", + ring->queue_index); + + } else { + ring->rx_buf_len = vsi->rx_buf_len; + if (ring->vsi->type == I40E_VSI_MAIN) { + ret = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_PAGE_SHARED, + NULL); + if (ret) + return ret; + } + } rx_ctx.dbuff = DIV_ROUND_UP(ring->rx_buf_len, BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT)); @@ -3245,7 +3283,15 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) ring->tail = hw->hw_addr + I40E_QRX_TAIL(pf_q); writel(0, ring->tail); - i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring)); + ok = ring->xsk_umem ? + i40e_alloc_rx_buffers_zc(ring, I40E_DESC_UNUSED(ring)) : + !i40e_alloc_rx_buffers(ring, I40E_DESC_UNUSED(ring)); + if (!ok) { + dev_info(&vsi->back->pdev->dev, + "Failed allocate some buffers on %sRx ring %d (pf_q %d)\n", + ring->xsk_umem ? "UMEM enabled " : "", + ring->queue_index, pf_q); + } return 0; } @@ -11850,6 +11896,256 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, return 0; } +/** + * i40e_enter_busy_conf - Enters busy config state + * @vsi: vsi + * + * Returns 0 on success, <0 for failure. + **/ +static int i40e_enter_busy_conf(struct i40e_vsi *vsi) +{ + struct i40e_pf *pf = vsi->back; + int timeout = 50; + + while (test_and_set_bit(__I40E_CONFIG_BUSY, pf->state)) { + timeout--; + if (!timeout) + return -EBUSY; + usleep_range(1000, 2000); + } + + return 0; +} + +/** + * i40e_exit_busy_conf - Exits busy config state + * @vsi: vsi + **/ +static void i40e_exit_busy_conf(struct i40e_vsi *vsi) +{ + struct i40e_pf *pf = vsi->back; + + clear_bit(__I40E_CONFIG_BUSY, pf->state); +} + +/** + * i40e_queue_pair_reset_stats - Resets all statistics for a queue pair + * @vsi: vsi + * @queue_pair: queue pair + **/ +static void i40e_queue_pair_reset_stats(struct i40e_vsi *vsi, int queue_pair) +{ + memset(&vsi->rx_rings[queue_pair]->rx_stats, 0, + sizeof(vsi->rx_rings[queue_pair]->rx_stats)); + memset(&vsi->tx_rings[queue_pair]->stats, 0, + sizeof(vsi->tx_rings[queue_pair]->stats)); + if (i40e_enabled_xdp_vsi(vsi)) { + memset(&vsi->xdp_rings[queue_pair]->stats, 0, + sizeof(vsi->xdp_rings[queue_pair]->stats)); + } +} + +/** + * i40e_queue_pair_clean_rings - Cleans all the rings of a queue pair + * @vsi: vsi + * @queue_pair: queue pair + **/ +static void i40e_queue_pair_clean_rings(struct i40e_vsi *vsi, int queue_pair) +{ + i40e_clean_tx_ring(vsi->tx_rings[queue_pair]); + if (i40e_enabled_xdp_vsi(vsi)) + i40e_clean_tx_ring(vsi->xdp_rings[queue_pair]); + i40e_clean_rx_ring(vsi->rx_rings[queue_pair]); +} + +/** + * i40e_queue_pair_toggle_napi - Enables/disables NAPI for a queue pair + * @vsi: vsi + * @queue_pair: queue pair + * @enable: true for enable, false for disable + **/ +static void i40e_queue_pair_toggle_napi(struct i40e_vsi *vsi, int queue_pair, + bool enable) +{ + struct i40e_ring *rxr = vsi->rx_rings[queue_pair]; + struct i40e_q_vector *q_vector = rxr->q_vector; + + if (!vsi->netdev) + return; + + /* All rings in a qp belong to the same qvector. */ + if (q_vector->rx.ring || q_vector->tx.ring) { + if (enable) + napi_enable(&q_vector->napi); + else + napi_disable(&q_vector->napi); + } +} + +/** + * i40e_queue_pair_toggle_rings - Enables/disables all rings for a queue pair + * @vsi: vsi + * @queue_pair: queue pair + * @enable: true for enable, false for disable + * + * Returns 0 on success, <0 on failure. + **/ +static int i40e_queue_pair_toggle_rings(struct i40e_vsi *vsi, int queue_pair, + bool enable) +{ + struct i40e_pf *pf = vsi->back; + int pf_q, ret = 0; + + pf_q = vsi->base_queue + queue_pair; + ret = i40e_control_wait_tx_q(vsi->seid, pf, pf_q, + false /*is xdp*/, enable); + if (ret) { + dev_info(&pf->pdev->dev, + "VSI seid %d Tx ring %d %sable timeout\n", + vsi->seid, pf_q, (enable ? "en" : "dis")); + return ret; + } + + i40e_control_rx_q(pf, pf_q, enable); + ret = i40e_pf_rxq_wait(pf, pf_q, enable); + if (ret) { + dev_info(&pf->pdev->dev, + "VSI seid %d Rx ring %d %sable timeout\n", + vsi->seid, pf_q, (enable ? "en" : "dis")); + return ret; + } + + /* Due to HW errata, on Rx disable only, the register can + * indicate done before it really is. Needs 50ms to be sure + */ + if (!enable) + mdelay(50); + + if (!i40e_enabled_xdp_vsi(vsi)) + return ret; + + ret = i40e_control_wait_tx_q(vsi->seid, pf, + pf_q + vsi->alloc_queue_pairs, + true /*is xdp*/, enable); + if (ret) { + dev_info(&pf->pdev->dev, + "VSI seid %d XDP Tx ring %d %sable timeout\n", + vsi->seid, pf_q, (enable ? "en" : "dis")); + } + + return ret; +} + +/** + * i40e_queue_pair_enable_irq - Enables interrupts for a queue pair + * @vsi: vsi + * @queue_pair: queue_pair + **/ +static void i40e_queue_pair_enable_irq(struct i40e_vsi *vsi, int queue_pair) +{ + struct i40e_ring *rxr = vsi->rx_rings[queue_pair]; + struct i40e_pf *pf = vsi->back; + struct i40e_hw *hw = &pf->hw; + + /* All rings in a qp belong to the same qvector. */ + if (pf->flags & I40E_FLAG_MSIX_ENABLED) + i40e_irq_dynamic_enable(vsi, rxr->q_vector->v_idx); + else + i40e_irq_dynamic_enable_icr0(pf); + + i40e_flush(hw); +} + +/** + * i40e_queue_pair_disable_irq - Disables interrupts for a queue pair + * @vsi: vsi + * @queue_pair: queue_pair + **/ +static void i40e_queue_pair_disable_irq(struct i40e_vsi *vsi, int queue_pair) +{ + struct i40e_ring *rxr = vsi->rx_rings[queue_pair]; + struct i40e_pf *pf = vsi->back; + struct i40e_hw *hw = &pf->hw; + + /* For simplicity, instead of removing the qp interrupt causes + * from the interrupt linked list, we simply disable the interrupt, and + * leave the list intact. + * + * All rings in a qp belong to the same qvector. + */ + if (pf->flags & I40E_FLAG_MSIX_ENABLED) { + u32 intpf = vsi->base_vector + rxr->q_vector->v_idx; + + wr32(hw, I40E_PFINT_DYN_CTLN(intpf - 1), 0); + i40e_flush(hw); + synchronize_irq(pf->msix_entries[intpf].vector); + } else { + /* Legacy and MSI mode - this stops all interrupt handling */ + wr32(hw, I40E_PFINT_ICR0_ENA, 0); + wr32(hw, I40E_PFINT_DYN_CTL0, 0); + i40e_flush(hw); + synchronize_irq(pf->pdev->irq); + } +} + +/** + * i40e_queue_pair_disable - Disables a queue pair + * @vsi: vsi + * @queue_pair: queue pair + * + * Returns 0 on success, <0 on failure. + **/ +int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair) +{ + int err; + + err = i40e_enter_busy_conf(vsi); + if (err) + return err; + + i40e_queue_pair_disable_irq(vsi, queue_pair); + err = i40e_queue_pair_toggle_rings(vsi, queue_pair, false /* off */); + i40e_queue_pair_toggle_napi(vsi, queue_pair, false /* off */); + i40e_queue_pair_clean_rings(vsi, queue_pair); + i40e_queue_pair_reset_stats(vsi, queue_pair); + + return err; +} + +/** + * i40e_queue_pair_enable - Enables a queue pair + * @vsi: vsi + * @queue_pair: queue pair + * + * Returns 0 on success, <0 on failure. + **/ +int i40e_queue_pair_enable(struct i40e_vsi *vsi, int queue_pair) +{ + int err; + + err = i40e_configure_tx_ring(vsi->tx_rings[queue_pair]); + if (err) + return err; + + if (i40e_enabled_xdp_vsi(vsi)) { + err = i40e_configure_tx_ring(vsi->xdp_rings[queue_pair]); + if (err) + return err; + } + + err = i40e_configure_rx_ring(vsi->rx_rings[queue_pair]); + if (err) + return err; + + err = i40e_queue_pair_toggle_rings(vsi, queue_pair, true /* on */); + i40e_queue_pair_toggle_napi(vsi, queue_pair, true /* on */); + i40e_queue_pair_enable_irq(vsi, queue_pair); + + i40e_exit_busy_conf(vsi); + + return err; +} + /** * i40e_xdp - implements ndo_bpf for i40e * @dev: netdevice @@ -11870,6 +12166,12 @@ static int i40e_xdp(struct net_device *dev, case XDP_QUERY_PROG: xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0; return 0; + case XDP_QUERY_XSK_UMEM: + return i40e_xsk_umem_query(vsi, &xdp->xsk.umem, + xdp->xsk.queue_id); + case XDP_SETUP_XSK_UMEM: + return i40e_xsk_umem_setup(vsi, xdp->xsk.umem, + xdp->xsk.queue_id); default: return -EINVAL; } @@ -11909,6 +12211,7 @@ static const struct net_device_ops i40e_netdev_ops = { .ndo_bridge_setlink = i40e_ndo_bridge_setlink, .ndo_bpf = i40e_xdp, .ndo_xdp_xmit = i40e_xdp_xmit, + .ndo_xsk_async_xmit = i40e_xsk_async_xmit, }; /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index b5042d1a63c0..37bd4e50ccde 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -8,16 +8,8 @@ #include "i40e.h" #include "i40e_trace.h" #include "i40e_prototype.h" - -static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size, - u32 td_tag) -{ - return cpu_to_le64(I40E_TX_DESC_DTYPE_DATA | - ((u64)td_cmd << I40E_TXD_QW1_CMD_SHIFT) | - ((u64)td_offset << I40E_TXD_QW1_OFFSET_SHIFT) | - ((u64)size << I40E_TXD_QW1_TX_BUF_SZ_SHIFT) | - ((u64)td_tag << I40E_TXD_QW1_L2TAG1_SHIFT)); -} +#include "i40e_txrx_common.h" +#include "i40e_xsk.h" #define I40E_TXD_CMD (I40E_TX_DESC_CMD_EOP | I40E_TX_DESC_CMD_RS) /** @@ -536,8 +528,8 @@ int i40e_add_del_fdir(struct i40e_vsi *vsi, * This is used to verify if the FD programming or invalidation * requested by SW to the HW is successful or not and take actions accordingly. **/ -static void i40e_fd_handle_status(struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc, u8 prog_id) +void i40e_fd_handle_status(struct i40e_ring *rx_ring, + union i40e_rx_desc *rx_desc, u8 prog_id) { struct i40e_pf *pf = rx_ring->vsi->back; struct pci_dev *pdev = pf->pdev; @@ -767,8 +759,6 @@ void i40e_detect_recover_hung(struct i40e_vsi *vsi) } } -#define WB_STRIDE 4 - /** * i40e_clean_tx_irq - Reclaim resources after transmit completes * @vsi: the VSI we care about @@ -873,27 +863,8 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, i += tx_ring->count; tx_ring->next_to_clean = i; - u64_stats_update_begin(&tx_ring->syncp); - tx_ring->stats.bytes += total_bytes; - tx_ring->stats.packets += total_packets; - u64_stats_update_end(&tx_ring->syncp); - tx_ring->q_vector->tx.total_bytes += total_bytes; - tx_ring->q_vector->tx.total_packets += total_packets; - - if (tx_ring->flags & I40E_TXR_FLAGS_WB_ON_ITR) { - /* check to see if there are < 4 descriptors - * waiting to be written back, then kick the hardware to force - * them to be written back in case we stay in NAPI. - * In this mode on X722 we do not enable Interrupt. - */ - unsigned int j = i40e_get_tx_pending(tx_ring, false); - - if (budget && - ((j / WB_STRIDE) == 0) && (j > 0) && - !test_bit(__I40E_VSI_DOWN, vsi->state) && - (I40E_DESC_UNUSED(tx_ring) != tx_ring->count)) - tx_ring->arm_wb = true; - } + i40e_update_tx_stats(tx_ring, total_packets, total_bytes); + i40e_arm_wb(tx_ring, vsi, budget); if (ring_is_xdp(tx_ring)) return !!budget; @@ -1244,6 +1215,11 @@ static void i40e_reuse_rx_page(struct i40e_ring *rx_ring, new_buff->page = old_buff->page; new_buff->page_offset = old_buff->page_offset; new_buff->pagecnt_bias = old_buff->pagecnt_bias; + + rx_ring->rx_stats.page_reuse_count++; + + /* clear contents of buffer_info */ + old_buff->page = NULL; } /** @@ -1266,7 +1242,7 @@ static inline bool i40e_rx_is_programming_status(u64 qw) } /** - * i40e_clean_programming_status - clean the programming status descriptor + * i40e_clean_programming_status - try clean the programming status descriptor * @rx_ring: the rx ring that has this descriptor * @rx_desc: the rx descriptor written back by HW * @qw: qword representing status_error_len in CPU ordering @@ -1275,15 +1251,22 @@ static inline bool i40e_rx_is_programming_status(u64 qw) * status being successful or not and take actions accordingly. FCoE should * handle its context/filter programming/invalidation status and take actions. * + * Returns an i40e_rx_buffer to reuse if the cleanup occurred, otherwise NULL. **/ -static void i40e_clean_programming_status(struct i40e_ring *rx_ring, - union i40e_rx_desc *rx_desc, - u64 qw) +struct i40e_rx_buffer *i40e_clean_programming_status( + struct i40e_ring *rx_ring, + union i40e_rx_desc *rx_desc, + u64 qw) { struct i40e_rx_buffer *rx_buffer; - u32 ntc = rx_ring->next_to_clean; + u32 ntc; u8 id; + if (!i40e_rx_is_programming_status(qw)) + return NULL; + + ntc = rx_ring->next_to_clean; + /* fetch, update, and store next to clean */ rx_buffer = &rx_ring->rx_bi[ntc++]; ntc = (ntc < rx_ring->count) ? ntc : 0; @@ -1291,18 +1274,13 @@ static void i40e_clean_programming_status(struct i40e_ring *rx_ring, prefetch(I40E_RX_DESC(rx_ring, ntc)); - /* place unused page back on the ring */ - i40e_reuse_rx_page(rx_ring, rx_buffer); - rx_ring->rx_stats.page_reuse_count++; - - /* clear contents of buffer_info */ - rx_buffer->page = NULL; - id = (qw & I40E_RX_PROG_STATUS_DESC_QW1_PROGID_MASK) >> I40E_RX_PROG_STATUS_DESC_QW1_PROGID_SHIFT; if (id == I40E_RX_PROG_STATUS_DESC_FD_FILTER_STATUS) i40e_fd_handle_status(rx_ring, rx_desc, id); + + return rx_buffer; } /** @@ -1372,6 +1350,9 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) rx_ring->skb = NULL; } + if (rx_ring->xsk_umem) + goto skip_free; + /* Free all the Rx ring sk_buffs */ for (i = 0; i < rx_ring->count; i++) { struct i40e_rx_buffer *rx_bi = &rx_ring->rx_bi[i]; @@ -1400,6 +1381,7 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) rx_bi->page_offset = 0; } +skip_free: bi_size = sizeof(struct i40e_rx_buffer) * rx_ring->count; memset(rx_ring->rx_bi, 0, bi_size); @@ -1492,7 +1474,7 @@ err: * @rx_ring: ring to bump * @val: new head index **/ -static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) +void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) { rx_ring->next_to_use = val; @@ -1576,8 +1558,8 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, * @skb: packet to send up * @vlan_tag: vlan tag for packet **/ -static void i40e_receive_skb(struct i40e_ring *rx_ring, - struct sk_buff *skb, u16 vlan_tag) +void i40e_receive_skb(struct i40e_ring *rx_ring, + struct sk_buff *skb, u16 vlan_tag) { struct i40e_q_vector *q_vector = rx_ring->q_vector; @@ -1804,7 +1786,6 @@ static inline void i40e_rx_hash(struct i40e_ring *ring, * order to populate the hash, checksum, VLAN, protocol, and * other fields within the skb. **/ -static inline void i40e_process_skb_fields(struct i40e_ring *rx_ring, union i40e_rx_desc *rx_desc, struct sk_buff *skb, u8 rx_ptype) @@ -2152,7 +2133,6 @@ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, if (i40e_can_reuse_rx_page(rx_buffer)) { /* hand second half of page back to the ring */ i40e_reuse_rx_page(rx_ring, rx_buffer); - rx_ring->rx_stats.page_reuse_count++; } else { /* we are not reusing the buffer so unmap it */ dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, @@ -2160,10 +2140,9 @@ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, DMA_FROM_DEVICE, I40E_RX_DMA_ATTR); __page_frag_cache_drain(rx_buffer->page, rx_buffer->pagecnt_bias); + /* clear contents of buffer_info */ + rx_buffer->page = NULL; } - - /* clear contents of buffer_info */ - rx_buffer->page = NULL; } /** @@ -2199,16 +2178,10 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring, return true; } -#define I40E_XDP_PASS 0 -#define I40E_XDP_CONSUMED BIT(0) -#define I40E_XDP_TX BIT(1) -#define I40E_XDP_REDIR BIT(2) - static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf, struct i40e_ring *xdp_ring); -static int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp, - struct i40e_ring *xdp_ring) +int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp, struct i40e_ring *xdp_ring) { struct xdp_frame *xdpf = convert_to_xdp_frame(xdp); @@ -2287,7 +2260,13 @@ static void i40e_rx_buffer_flip(struct i40e_ring *rx_ring, #endif } -static inline void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring) +/** + * i40e_xdp_ring_update_tail - Updates the XDP Tx ring tail register + * @xdp_ring: XDP Tx ring + * + * This function updates the XDP Tx ring tail register. + **/ +void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring) { /* Force memory writes to complete before letting h/w * know there are new descriptors to fetch. @@ -2296,6 +2275,48 @@ static inline void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring) writel_relaxed(xdp_ring->next_to_use, xdp_ring->tail); } +/** + * i40e_update_rx_stats - Update Rx ring statistics + * @rx_ring: rx descriptor ring + * @total_rx_bytes: number of bytes received + * @total_rx_packets: number of packets received + * + * This function updates the Rx ring statistics. + **/ +void i40e_update_rx_stats(struct i40e_ring *rx_ring, + unsigned int total_rx_bytes, + unsigned int total_rx_packets) +{ + u64_stats_update_begin(&rx_ring->syncp); + rx_ring->stats.packets += total_rx_packets; + rx_ring->stats.bytes += total_rx_bytes; + u64_stats_update_end(&rx_ring->syncp); + rx_ring->q_vector->rx.total_packets += total_rx_packets; + rx_ring->q_vector->rx.total_bytes += total_rx_bytes; +} + +/** + * i40e_finalize_xdp_rx - Bump XDP Tx tail and/or flush redirect map + * @rx_ring: Rx ring + * @xdp_res: Result of the receive batch + * + * This function bumps XDP Tx tail and/or flush redirect map, and + * should be called when a batch of packets has been processed in the + * napi loop. + **/ +void i40e_finalize_xdp_rx(struct i40e_ring *rx_ring, unsigned int xdp_res) +{ + if (xdp_res & I40E_XDP_REDIR) + xdp_do_flush_map(); + + if (xdp_res & I40E_XDP_TX) { + struct i40e_ring *xdp_ring = + rx_ring->vsi->xdp_rings[rx_ring->queue_index]; + + i40e_xdp_ring_update_tail(xdp_ring); + } +} + /** * i40e_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf * @rx_ring: rx descriptor ring to transact packets on @@ -2349,11 +2370,14 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) */ dma_rmb(); - if (unlikely(i40e_rx_is_programming_status(qword))) { - i40e_clean_programming_status(rx_ring, rx_desc, qword); + rx_buffer = i40e_clean_programming_status(rx_ring, rx_desc, + qword); + if (unlikely(rx_buffer)) { + i40e_reuse_rx_page(rx_ring, rx_buffer); cleaned_count++; continue; } + size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >> I40E_RXD_QW1_LENGTH_PBUF_SHIFT; if (!size) @@ -2432,24 +2456,10 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) total_rx_packets++; } - if (xdp_xmit & I40E_XDP_REDIR) - xdp_do_flush_map(); - - if (xdp_xmit & I40E_XDP_TX) { - struct i40e_ring *xdp_ring = - rx_ring->vsi->xdp_rings[rx_ring->queue_index]; - - i40e_xdp_ring_update_tail(xdp_ring); - } - + i40e_finalize_xdp_rx(rx_ring, xdp_xmit); rx_ring->skb = skb; - u64_stats_update_begin(&rx_ring->syncp); - rx_ring->stats.packets += total_rx_packets; - rx_ring->stats.bytes += total_rx_bytes; - u64_stats_update_end(&rx_ring->syncp); - rx_ring->q_vector->rx.total_packets += total_rx_packets; - rx_ring->q_vector->rx.total_bytes += total_rx_bytes; + i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets); /* guarantee a trip back through this routine if there was a failure */ return failure ? budget : (int)total_rx_packets; @@ -2587,7 +2597,11 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) * budget and be more aggressive about cleaning up the Tx descriptors. */ i40e_for_each_ring(ring, q_vector->tx) { - if (!i40e_clean_tx_irq(vsi, ring, budget)) { + bool wd = ring->xsk_umem ? + i40e_clean_xdp_tx_irq(vsi, ring, budget) : + i40e_clean_tx_irq(vsi, ring, budget); + + if (!wd) { clean_complete = false; continue; } @@ -2605,7 +2619,9 @@ int i40e_napi_poll(struct napi_struct *napi, int budget) budget_per_ring = max(budget/q_vector->num_ringpairs, 1); i40e_for_each_ring(ring, q_vector->rx) { - int cleaned = i40e_clean_rx_irq(ring, budget_per_ring); + int cleaned = ring->xsk_umem ? + i40e_clean_rx_irq_zc(ring, budget_per_ring) : + i40e_clean_rx_irq(ring, budget_per_ring); work_done += cleaned; /* if we clean as many as budgeted, we must not be done */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index bb04f6a731fe..100e92d2982f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -296,13 +296,17 @@ struct i40e_tx_buffer { struct i40e_rx_buffer { dma_addr_t dma; - struct page *page; -#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) - __u32 page_offset; -#else - __u16 page_offset; -#endif - __u16 pagecnt_bias; + union { + struct { + struct page *page; + __u32 page_offset; + __u16 pagecnt_bias; + }; + struct { + void *addr; + u64 handle; + }; + }; }; struct i40e_queue_stats { @@ -414,6 +418,8 @@ struct i40e_ring { struct i40e_channel *ch; struct xdp_rxq_info xdp_rxq; + struct xdp_umem *xsk_umem; + struct zero_copy_allocator zca; /* ZC allocator anchor */ } ____cacheline_internodealigned_in_smp; static inline bool ring_uses_build_skb(struct i40e_ring *ring) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h new file mode 100644 index 000000000000..b5afd479a9c5 --- /dev/null +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx_common.h @@ -0,0 +1,90 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2018 Intel Corporation. */ + +#ifndef I40E_TXRX_COMMON_ +#define I40E_TXRX_COMMON_ + +void i40e_fd_handle_status(struct i40e_ring *rx_ring, + union i40e_rx_desc *rx_desc, u8 prog_id); +int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp, struct i40e_ring *xdp_ring); +struct i40e_rx_buffer *i40e_clean_programming_status( + struct i40e_ring *rx_ring, + union i40e_rx_desc *rx_desc, + u64 qw); +void i40e_process_skb_fields(struct i40e_ring *rx_ring, + union i40e_rx_desc *rx_desc, struct sk_buff *skb, + u8 rx_ptype); +void i40e_receive_skb(struct i40e_ring *rx_ring, + struct sk_buff *skb, u16 vlan_tag); +void i40e_xdp_ring_update_tail(struct i40e_ring *xdp_ring); +void i40e_update_rx_stats(struct i40e_ring *rx_ring, + unsigned int total_rx_bytes, + unsigned int total_rx_packets); +void i40e_finalize_xdp_rx(struct i40e_ring *rx_ring, unsigned int xdp_res); +void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val); + +#define I40E_XDP_PASS 0 +#define I40E_XDP_CONSUMED BIT(0) +#define I40E_XDP_TX BIT(1) +#define I40E_XDP_REDIR BIT(2) + +/** + * build_ctob - Builds the Tx descriptor (cmd, offset and type) qword + **/ +static inline __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size, + u32 td_tag) +{ + return cpu_to_le64(I40E_TX_DESC_DTYPE_DATA | + ((u64)td_cmd << I40E_TXD_QW1_CMD_SHIFT) | + ((u64)td_offset << I40E_TXD_QW1_OFFSET_SHIFT) | + ((u64)size << I40E_TXD_QW1_TX_BUF_SZ_SHIFT) | + ((u64)td_tag << I40E_TXD_QW1_L2TAG1_SHIFT)); +} + +/** + * i40e_update_tx_stats - Update the egress statistics for the Tx ring + * @tx_ring: Tx ring to update + * @total_packet: total packets sent + * @total_bytes: total bytes sent + **/ +static inline void i40e_update_tx_stats(struct i40e_ring *tx_ring, + unsigned int total_packets, + unsigned int total_bytes) +{ + u64_stats_update_begin(&tx_ring->syncp); + tx_ring->stats.bytes += total_bytes; + tx_ring->stats.packets += total_packets; + u64_stats_update_end(&tx_ring->syncp); + tx_ring->q_vector->tx.total_bytes += total_bytes; + tx_ring->q_vector->tx.total_packets += total_packets; +} + +#define WB_STRIDE 4 + +/** + * i40e_arm_wb - (Possibly) arms Tx write-back + * @tx_ring: Tx ring to update + * @vsi: the VSI + * @budget: the NAPI budget left + **/ +static inline void i40e_arm_wb(struct i40e_ring *tx_ring, + struct i40e_vsi *vsi, + int budget) +{ + if (tx_ring->flags & I40E_TXR_FLAGS_WB_ON_ITR) { + /* check to see if there are < 4 descriptors + * waiting to be written back, then kick the hardware to force + * them to be written back in case we stay in NAPI. + * In this mode on X722 we do not enable Interrupt. + */ + unsigned int j = i40e_get_tx_pending(tx_ring, false); + + if (budget && + ((j / WB_STRIDE) == 0) && j > 0 && + !test_bit(__I40E_VSI_DOWN, vsi->state) && + (I40E_DESC_UNUSED(tx_ring) != tx_ring->count)) + tx_ring->arm_wb = true; + } +} + +#endif /* I40E_TXRX_COMMON_ */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c new file mode 100644 index 000000000000..2ebfc78bbd09 --- /dev/null +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -0,0 +1,832 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2018 Intel Corporation. */ + +#include +#include +#include + +#include "i40e.h" +#include "i40e_txrx_common.h" +#include "i40e_xsk.h" + +/** + * i40e_alloc_xsk_umems - Allocate an array to store per ring UMEMs + * @vsi: Current VSI + * + * Returns 0 on success, <0 on failure + **/ +static int i40e_alloc_xsk_umems(struct i40e_vsi *vsi) +{ + if (vsi->xsk_umems) + return 0; + + vsi->num_xsk_umems_used = 0; + vsi->num_xsk_umems = vsi->alloc_queue_pairs; + vsi->xsk_umems = kcalloc(vsi->num_xsk_umems, sizeof(*vsi->xsk_umems), + GFP_KERNEL); + if (!vsi->xsk_umems) { + vsi->num_xsk_umems = 0; + return -ENOMEM; + } + + return 0; +} + +/** + * i40e_add_xsk_umem - Store an UMEM for a certain ring/qid + * @vsi: Current VSI + * @umem: UMEM to store + * @qid: Ring/qid to associate with the UMEM + * + * Returns 0 on success, <0 on failure + **/ +static int i40e_add_xsk_umem(struct i40e_vsi *vsi, struct xdp_umem *umem, + u16 qid) +{ + int err; + + err = i40e_alloc_xsk_umems(vsi); + if (err) + return err; + + vsi->xsk_umems[qid] = umem; + vsi->num_xsk_umems_used++; + + return 0; +} + +/** + * i40e_remove_xsk_umem - Remove an UMEM for a certain ring/qid + * @vsi: Current VSI + * @qid: Ring/qid associated with the UMEM + **/ +static void i40e_remove_xsk_umem(struct i40e_vsi *vsi, u16 qid) +{ + vsi->xsk_umems[qid] = NULL; + vsi->num_xsk_umems_used--; + + if (vsi->num_xsk_umems == 0) { + kfree(vsi->xsk_umems); + vsi->xsk_umems = NULL; + vsi->num_xsk_umems = 0; + } +} + +/** + * i40e_xsk_umem_dma_map - DMA maps all UMEM memory for the netdev + * @vsi: Current VSI + * @umem: UMEM to DMA map + * + * Returns 0 on success, <0 on failure + **/ +static int i40e_xsk_umem_dma_map(struct i40e_vsi *vsi, struct xdp_umem *umem) +{ + struct i40e_pf *pf = vsi->back; + struct device *dev; + unsigned int i, j; + dma_addr_t dma; + + dev = &pf->pdev->dev; + for (i = 0; i < umem->npgs; i++) { + dma = dma_map_page_attrs(dev, umem->pgs[i], 0, PAGE_SIZE, + DMA_BIDIRECTIONAL, I40E_RX_DMA_ATTR); + if (dma_mapping_error(dev, dma)) + goto out_unmap; + + umem->pages[i].dma = dma; + } + + return 0; + +out_unmap: + for (j = 0; j < i; j++) { + dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE, + DMA_BIDIRECTIONAL, I40E_RX_DMA_ATTR); + umem->pages[i].dma = 0; + } + + return -1; +} + +/** + * i40e_xsk_umem_dma_unmap - DMA unmaps all UMEM memory for the netdev + * @vsi: Current VSI + * @umem: UMEM to DMA map + **/ +static void i40e_xsk_umem_dma_unmap(struct i40e_vsi *vsi, struct xdp_umem *umem) +{ + struct i40e_pf *pf = vsi->back; + struct device *dev; + unsigned int i; + + dev = &pf->pdev->dev; + + for (i = 0; i < umem->npgs; i++) { + dma_unmap_page_attrs(dev, umem->pages[i].dma, PAGE_SIZE, + DMA_BIDIRECTIONAL, I40E_RX_DMA_ATTR); + + umem->pages[i].dma = 0; + } +} + +/** + * i40e_xsk_umem_enable - Enable/associate an UMEM to a certain ring/qid + * @vsi: Current VSI + * @umem: UMEM + * @qid: Rx ring to associate UMEM to + * + * Returns 0 on success, <0 on failure + **/ +static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem, + u16 qid) +{ + bool if_running; + int err; + + if (vsi->type != I40E_VSI_MAIN) + return -EINVAL; + + if (qid >= vsi->num_queue_pairs) + return -EINVAL; + + if (vsi->xsk_umems) { + if (qid >= vsi->num_xsk_umems) + return -EINVAL; + if (vsi->xsk_umems[qid]) + return -EBUSY; + } + + err = i40e_xsk_umem_dma_map(vsi, umem); + if (err) + return err; + + if_running = netif_running(vsi->netdev) && i40e_enabled_xdp_vsi(vsi); + + if (if_running) { + err = i40e_queue_pair_disable(vsi, qid); + if (err) + return err; + } + + err = i40e_add_xsk_umem(vsi, umem, qid); + if (err) + return err; + + if (if_running) { + err = i40e_queue_pair_enable(vsi, qid); + if (err) + return err; + } + + return 0; +} + +/** + * i40e_xsk_umem_disable - Diassociate an UMEM from a certain ring/qid + * @vsi: Current VSI + * @qid: Rx ring to associate UMEM to + * + * Returns 0 on success, <0 on failure + **/ +static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid) +{ + bool if_running; + int err; + + if (!vsi->xsk_umems || qid >= vsi->num_xsk_umems || + !vsi->xsk_umems[qid]) + return -EINVAL; + + if_running = netif_running(vsi->netdev) && i40e_enabled_xdp_vsi(vsi); + + if (if_running) { + err = i40e_queue_pair_disable(vsi, qid); + if (err) + return err; + } + + i40e_xsk_umem_dma_unmap(vsi, vsi->xsk_umems[qid]); + i40e_remove_xsk_umem(vsi, qid); + + if (if_running) { + err = i40e_queue_pair_enable(vsi, qid); + if (err) + return err; + } + + return 0; +} + +/** + * i40e_xsk_umem_query - Queries a certain ring/qid for its UMEM + * @vsi: Current VSI + * @umem: UMEM associated to the ring, if any + * @qid: Rx ring to associate UMEM to + * + * This function will store, if any, the UMEM associated to certain ring. + * + * Returns 0 on success, <0 on failure + **/ +int i40e_xsk_umem_query(struct i40e_vsi *vsi, struct xdp_umem **umem, + u16 qid) +{ + if (vsi->type != I40E_VSI_MAIN) + return -EINVAL; + + if (qid >= vsi->num_queue_pairs) + return -EINVAL; + + if (vsi->xsk_umems) { + if (qid >= vsi->num_xsk_umems) + return -EINVAL; + *umem = vsi->xsk_umems[qid]; + return 0; + } + + *umem = NULL; + return 0; +} + +/** + * i40e_xsk_umem_query - Queries a certain ring/qid for its UMEM + * @vsi: Current VSI + * @umem: UMEM to enable/associate to a ring, or NULL to disable + * @qid: Rx ring to (dis)associate UMEM (from)to + * + * This function enables or disables an UMEM to a certain ring. + * + * Returns 0 on success, <0 on failure + **/ +int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem, + u16 qid) +{ + return umem ? i40e_xsk_umem_enable(vsi, umem, qid) : + i40e_xsk_umem_disable(vsi, qid); +} + +/** + * i40e_run_xdp_zc - Executes an XDP program on an xdp_buff + * @rx_ring: Rx ring + * @xdp: xdp_buff used as input to the XDP program + * + * This function enables or disables an UMEM to a certain ring. + * + * Returns any of I40E_XDP_{PASS, CONSUMED, TX, REDIR} + **/ +static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp) +{ + int err, result = I40E_XDP_PASS; + struct i40e_ring *xdp_ring; + struct bpf_prog *xdp_prog; + u32 act; + + rcu_read_lock(); + /* NB! xdp_prog will always be !NULL, due to the fact that + * this path is enabled by setting an XDP program. + */ + xdp_prog = READ_ONCE(rx_ring->xdp_prog); + act = bpf_prog_run_xdp(xdp_prog, xdp); + xdp->handle += xdp->data - xdp->data_hard_start; + switch (act) { + case XDP_PASS: + break; + case XDP_TX: + xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index]; + result = i40e_xmit_xdp_tx_ring(xdp, xdp_ring); + break; + case XDP_REDIRECT: + err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); + result = !err ? I40E_XDP_REDIR : I40E_XDP_CONSUMED; + break; + default: + bpf_warn_invalid_xdp_action(act); + case XDP_ABORTED: + trace_xdp_exception(rx_ring->netdev, xdp_prog, act); + /* fallthrough -- handle aborts by dropping packet */ + case XDP_DROP: + result = I40E_XDP_CONSUMED; + break; + } + rcu_read_unlock(); + return result; +} + +/** + * i40e_alloc_buffer_zc - Allocates an i40e_rx_buffer + * @rx_ring: Rx ring + * @bi: Rx buffer to populate + * + * This function allocates an Rx buffer. The buffer can come from fill + * queue, or via the recycle queue (next_to_alloc). + * + * Returns true for a successful allocation, false otherwise + **/ +static bool i40e_alloc_buffer_zc(struct i40e_ring *rx_ring, + struct i40e_rx_buffer *bi) +{ + struct xdp_umem *umem = rx_ring->xsk_umem; + void *addr = bi->addr; + u64 handle, hr; + + if (addr) { + rx_ring->rx_stats.page_reuse_count++; + return true; + } + + if (!xsk_umem_peek_addr(umem, &handle)) { + rx_ring->rx_stats.alloc_page_failed++; + return false; + } + + hr = umem->headroom + XDP_PACKET_HEADROOM; + + bi->dma = xdp_umem_get_dma(umem, handle); + bi->dma += hr; + + bi->addr = xdp_umem_get_data(umem, handle); + bi->addr += hr; + + bi->handle = handle + umem->headroom; + + xsk_umem_discard_addr(umem); + return true; +} + +/** + * i40e_alloc_rx_buffers_zc - Allocates a number of Rx buffers + * @rx_ring: Rx ring + * @count: The number of buffers to allocate + * + * This function allocates a number of Rx buffers and places them on + * the Rx ring. + * + * Returns true for a successful allocation, false otherwise + **/ +bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 count) +{ + u16 ntu = rx_ring->next_to_use; + union i40e_rx_desc *rx_desc; + struct i40e_rx_buffer *bi; + bool ok = true; + + rx_desc = I40E_RX_DESC(rx_ring, ntu); + bi = &rx_ring->rx_bi[ntu]; + do { + if (!i40e_alloc_buffer_zc(rx_ring, bi)) { + ok = false; + goto no_buffers; + } + + dma_sync_single_range_for_device(rx_ring->dev, bi->dma, 0, + rx_ring->rx_buf_len, + DMA_BIDIRECTIONAL); + + rx_desc->read.pkt_addr = cpu_to_le64(bi->dma); + + rx_desc++; + bi++; + ntu++; + + if (unlikely(ntu == rx_ring->count)) { + rx_desc = I40E_RX_DESC(rx_ring, 0); + bi = rx_ring->rx_bi; + ntu = 0; + } + + rx_desc->wb.qword1.status_error_len = 0; + count--; + } while (count); + +no_buffers: + if (rx_ring->next_to_use != ntu) + i40e_release_rx_desc(rx_ring, ntu); + + return ok; +} + +/** + * i40e_get_rx_buffer_zc - Return the current Rx buffer + * @rx_ring: Rx ring + * @size: The size of the rx buffer (read from descriptor) + * + * This function returns the current, received Rx buffer, and also + * does DMA synchronization. the Rx ring. + * + * Returns the received Rx buffer + **/ +static struct i40e_rx_buffer *i40e_get_rx_buffer_zc(struct i40e_ring *rx_ring, + const unsigned int size) +{ + struct i40e_rx_buffer *bi; + + bi = &rx_ring->rx_bi[rx_ring->next_to_clean]; + + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + bi->dma, 0, + size, + DMA_BIDIRECTIONAL); + + return bi; +} + +/** + * i40e_reuse_rx_buffer_zc - Recycle an Rx buffer + * @rx_ring: Rx ring + * @old_bi: The Rx buffer to recycle + * + * This function recycles a finished Rx buffer, and places it on the + * recycle queue (next_to_alloc). + **/ +static void i40e_reuse_rx_buffer_zc(struct i40e_ring *rx_ring, + struct i40e_rx_buffer *old_bi) +{ + struct i40e_rx_buffer *new_bi = &rx_ring->rx_bi[rx_ring->next_to_alloc]; + unsigned long mask = (unsigned long)rx_ring->xsk_umem->chunk_mask; + u64 hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM; + u16 nta = rx_ring->next_to_alloc; + + /* update, and store next to alloc */ + nta++; + rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; + + /* transfer page from old buffer to new buffer */ + new_bi->dma = old_bi->dma & mask; + new_bi->dma += hr; + + new_bi->addr = (void *)((unsigned long)old_bi->addr & mask); + new_bi->addr += hr; + + new_bi->handle = old_bi->handle & mask; + new_bi->handle += rx_ring->xsk_umem->headroom; + + old_bi->addr = NULL; +} + +/** + * i40e_zca_free - Free callback for MEM_TYPE_ZERO_COPY allocations + * @alloc: Zero-copy allocator + * @handle: Buffer handle + **/ +void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle) +{ + struct i40e_rx_buffer *bi; + struct i40e_ring *rx_ring; + u64 hr, mask; + u16 nta; + + rx_ring = container_of(alloc, struct i40e_ring, zca); + hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM; + mask = rx_ring->xsk_umem->chunk_mask; + + nta = rx_ring->next_to_alloc; + bi = &rx_ring->rx_bi[nta]; + + nta++; + rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; + + handle &= mask; + + bi->dma = xdp_umem_get_dma(rx_ring->xsk_umem, handle); + bi->dma += hr; + + bi->addr = xdp_umem_get_data(rx_ring->xsk_umem, handle); + bi->addr += hr; + + bi->handle = (u64)handle + rx_ring->xsk_umem->headroom; +} + +/** + * i40e_construct_skb_zc - Create skbufff from zero-copy Rx buffer + * @rx_ring: Rx ring + * @bi: Rx buffer + * @xdp: xdp_buff + * + * This functions allocates a new skb from a zero-copy Rx buffer. + * + * Returns the skb, or NULL on failure. + **/ +static struct sk_buff *i40e_construct_skb_zc(struct i40e_ring *rx_ring, + struct i40e_rx_buffer *bi, + struct xdp_buff *xdp) +{ + unsigned int metasize = xdp->data - xdp->data_meta; + unsigned int datasize = xdp->data_end - xdp->data; + struct sk_buff *skb; + + /* allocate a skb to store the frags */ + skb = __napi_alloc_skb(&rx_ring->q_vector->napi, + xdp->data_end - xdp->data_hard_start, + GFP_ATOMIC | __GFP_NOWARN); + if (unlikely(!skb)) + return NULL; + + skb_reserve(skb, xdp->data - xdp->data_hard_start); + memcpy(__skb_put(skb, datasize), xdp->data, datasize); + if (metasize) + skb_metadata_set(skb, metasize); + + i40e_reuse_rx_buffer_zc(rx_ring, bi); + return skb; +} + +/** + * i40e_inc_ntc: Advance the next_to_clean index + * @rx_ring: Rx ring + **/ +static void i40e_inc_ntc(struct i40e_ring *rx_ring) +{ + u32 ntc = rx_ring->next_to_clean + 1; + + ntc = (ntc < rx_ring->count) ? ntc : 0; + rx_ring->next_to_clean = ntc; + prefetch(I40E_RX_DESC(rx_ring, ntc)); +} + +/** + * i40e_clean_rx_irq_zc - Consumes Rx packets from the hardware ring + * @rx_ring: Rx ring + * @budget: NAPI budget + * + * Returns amount of work completed + **/ +int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) +{ + unsigned int total_rx_bytes = 0, total_rx_packets = 0; + u16 cleaned_count = I40E_DESC_UNUSED(rx_ring); + unsigned int xdp_res, xdp_xmit = 0; + bool failure = false; + struct sk_buff *skb; + struct xdp_buff xdp; + + xdp.rxq = &rx_ring->xdp_rxq; + + while (likely(total_rx_packets < (unsigned int)budget)) { + struct i40e_rx_buffer *bi; + union i40e_rx_desc *rx_desc; + unsigned int size; + u16 vlan_tag; + u8 rx_ptype; + u64 qword; + + if (cleaned_count >= I40E_RX_BUFFER_WRITE) { + failure = failure || + !i40e_alloc_rx_buffers_zc(rx_ring, + cleaned_count); + cleaned_count = 0; + } + + rx_desc = I40E_RX_DESC(rx_ring, rx_ring->next_to_clean); + qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); + + /* This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc until we have + * verified the descriptor has been written back. + */ + dma_rmb(); + + bi = i40e_clean_programming_status(rx_ring, rx_desc, + qword); + if (unlikely(bi)) { + i40e_reuse_rx_buffer_zc(rx_ring, bi); + cleaned_count++; + continue; + } + + size = (qword & I40E_RXD_QW1_LENGTH_PBUF_MASK) >> + I40E_RXD_QW1_LENGTH_PBUF_SHIFT; + if (!size) + break; + + bi = i40e_get_rx_buffer_zc(rx_ring, size); + xdp.data = bi->addr; + xdp.data_meta = xdp.data; + xdp.data_hard_start = xdp.data - XDP_PACKET_HEADROOM; + xdp.data_end = xdp.data + size; + xdp.handle = bi->handle; + + xdp_res = i40e_run_xdp_zc(rx_ring, &xdp); + if (xdp_res) { + if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) { + xdp_xmit |= xdp_res; + bi->addr = NULL; + } else { + i40e_reuse_rx_buffer_zc(rx_ring, bi); + } + + total_rx_bytes += size; + total_rx_packets++; + + cleaned_count++; + i40e_inc_ntc(rx_ring); + continue; + } + + /* XDP_PASS path */ + + /* NB! We are not checking for errors using + * i40e_test_staterr with + * BIT(I40E_RXD_QW1_ERROR_SHIFT). This is due to that + * SBP is *not* set in PRT_SBPVSI (default not set). + */ + skb = i40e_construct_skb_zc(rx_ring, bi, &xdp); + if (!skb) { + rx_ring->rx_stats.alloc_buff_failed++; + break; + } + + cleaned_count++; + i40e_inc_ntc(rx_ring); + + if (eth_skb_pad(skb)) + continue; + + total_rx_bytes += skb->len; + total_rx_packets++; + + qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); + rx_ptype = (qword & I40E_RXD_QW1_PTYPE_MASK) >> + I40E_RXD_QW1_PTYPE_SHIFT; + i40e_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); + + vlan_tag = (qword & BIT(I40E_RX_DESC_STATUS_L2TAG1P_SHIFT)) ? + le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1) : 0; + i40e_receive_skb(rx_ring, skb, vlan_tag); + } + + i40e_finalize_xdp_rx(rx_ring, xdp_xmit); + i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets); + 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) +{ + struct i40e_tx_desc *tx_desc = NULL; + struct i40e_tx_buffer *tx_bi; + bool work_done = true; + dma_addr_t dma; + u32 len; + + while (budget-- > 0) { + if (!unlikely(I40E_DESC_UNUSED(xdp_ring))) { + xdp_ring->tx_stats.tx_busy++; + work_done = false; + break; + } + + if (!xsk_umem_consume_tx(xdp_ring->xsk_umem, &dma, &len)) + break; + + dma_sync_single_for_device(xdp_ring->dev, dma, len, + DMA_BIDIRECTIONAL); + + tx_bi = &xdp_ring->tx_bi[xdp_ring->next_to_use]; + tx_bi->bytecount = len; + + tx_desc = I40E_TX_DESC(xdp_ring, xdp_ring->next_to_use); + tx_desc->buffer_addr = cpu_to_le64(dma); + tx_desc->cmd_type_offset_bsz = + build_ctob(I40E_TX_DESC_CMD_ICRC + | I40E_TX_DESC_CMD_EOP, + 0, len, 0); + + xdp_ring->next_to_use++; + if (xdp_ring->next_to_use == xdp_ring->count) + xdp_ring->next_to_use = 0; + } + + 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); + + xsk_umem_consume_tx_done(xdp_ring->xsk_umem); + } + + return !!budget && work_done; +} + +/** + * i40e_clean_xdp_tx_buffer - Frees and unmaps an XDP Tx entry + * @tx_ring: XDP Tx ring + * @tx_bi: Tx buffer info to clean + **/ +static void i40e_clean_xdp_tx_buffer(struct i40e_ring *tx_ring, + struct i40e_tx_buffer *tx_bi) +{ + xdp_return_frame(tx_bi->xdpf); + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_bi, dma), + dma_unmap_len(tx_bi, len), DMA_TO_DEVICE); + dma_unmap_len_set(tx_bi, len, 0); +} + +/** + * i40e_clean_xdp_tx_irq - Completes AF_XDP entries, and cleans XDP entries + * @tx_ring: XDP Tx ring + * @tx_bi: Tx buffer info to clean + * + * Returns true if cleanup/tranmission is done. + **/ +bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi, + struct i40e_ring *tx_ring, int napi_budget) +{ + unsigned int ntc, total_bytes = 0, budget = vsi->work_limit; + u32 i, completed_frames, frames_ready, xsk_frames = 0; + struct xdp_umem *umem = tx_ring->xsk_umem; + u32 head_idx = i40e_get_head(tx_ring); + bool work_done = true, xmit_done; + struct i40e_tx_buffer *tx_bi; + + if (head_idx < tx_ring->next_to_clean) + head_idx += tx_ring->count; + frames_ready = head_idx - tx_ring->next_to_clean; + + if (frames_ready == 0) { + goto out_xmit; + } else if (frames_ready > budget) { + completed_frames = budget; + work_done = false; + } else { + completed_frames = frames_ready; + } + + ntc = tx_ring->next_to_clean; + + for (i = 0; i < completed_frames; i++) { + tx_bi = &tx_ring->tx_bi[ntc]; + + if (tx_bi->xdpf) + i40e_clean_xdp_tx_buffer(tx_ring, tx_bi); + else + xsk_frames++; + + tx_bi->xdpf = NULL; + total_bytes += tx_bi->bytecount; + + if (++ntc >= tx_ring->count) + ntc = 0; + } + + tx_ring->next_to_clean += completed_frames; + if (unlikely(tx_ring->next_to_clean >= tx_ring->count)) + tx_ring->next_to_clean -= tx_ring->count; + + if (xsk_frames) + xsk_umem_complete_tx(umem, xsk_frames); + + i40e_arm_wb(tx_ring, vsi, budget); + i40e_update_tx_stats(tx_ring, completed_frames, total_bytes); + +out_xmit: + xmit_done = i40e_xmit_zc(tx_ring, budget); + + return work_done && xmit_done; +} + +/** + * i40e_xsk_async_xmit - Implements the ndo_xsk_async_xmit + * @dev: the netdevice + * @queue_id: queue id to wake up + * + * Returns <0 for errors, 0 otherwise. + **/ +int i40e_xsk_async_xmit(struct net_device *dev, u32 queue_id) +{ + struct i40e_netdev_priv *np = netdev_priv(dev); + struct i40e_vsi *vsi = np->vsi; + struct i40e_ring *ring; + + if (test_bit(__I40E_VSI_DOWN, vsi->state)) + return -ENETDOWN; + + if (!i40e_enabled_xdp_vsi(vsi)) + return -ENXIO; + + if (queue_id >= vsi->num_queue_pairs) + return -ENXIO; + + if (!vsi->xdp_rings[queue_id]->xsk_umem) + return -ENXIO; + + ring = vsi->xdp_rings[queue_id]; + + /* The idea here is that if NAPI is running, mark a miss, so + * it will run again. If not, trigger an interrupt and + * schedule the NAPI from interrupt context. If NAPI would be + * scheduled here, the interrupt affinity would not be + * honored. + */ + if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) + i40e_force_wb(vsi, ring->q_vector); + + return 0; +} diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h new file mode 100644 index 000000000000..9038c5d5cf08 --- /dev/null +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2018 Intel Corporation. */ + +#ifndef _I40E_XSK_H_ +#define _I40E_XSK_H_ + +struct i40e_vsi; +struct xdp_umem; +struct zero_copy_allocator; + +int i40e_queue_pair_disable(struct i40e_vsi *vsi, int queue_pair); +int i40e_queue_pair_enable(struct i40e_vsi *vsi, int queue_pair); +int i40e_xsk_umem_query(struct i40e_vsi *vsi, struct xdp_umem **umem, + u16 qid); +int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem, + u16 qid); +void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle); +bool i40e_alloc_rx_buffers_zc(struct i40e_ring *rx_ring, u16 cleaned_count); +int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget); + +bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi, + struct i40e_ring *tx_ring, int napi_budget); +int i40e_xsk_async_xmit(struct net_device *dev, u32 queue_id); + +#endif /* _I40E_XSK_H_ */ diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 38b04f559ad3..b42b60a83e19 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -41,6 +41,7 @@ enum bpf_reg_liveness { }; struct bpf_reg_state { + /* Ordering of fields matters. See states_equal() */ enum bpf_reg_type type; union { /* valid when type == PTR_TO_PACKET */ @@ -59,7 +60,6 @@ struct bpf_reg_state { * came from, when one is tested for != NULL. */ u32 id; - /* Ordering of fields matters. See states_equal() */ /* For scalar types (SCALAR_VALUE), this represents our knowledge of * the actual value. * For pointer types, this represents the variable part of the offset @@ -76,15 +76,15 @@ struct bpf_reg_state { s64 smax_value; /* maximum possible (s64)value */ u64 umin_value; /* minimum possible (u64)value */ u64 umax_value; /* maximum possible (u64)value */ + /* parentage chain for liveness checking */ + struct bpf_reg_state *parent; /* Inside the callee two registers can be both PTR_TO_STACK like * R1=fp-8 and R2=fp-8, but one of them points to this function stack * while another to the caller's stack. To differentiate them 'frameno' * is used which is an index in bpf_verifier_state->frame[] array * pointing to bpf_func_state. - * This field must be second to last, for states_equal() reasons. */ u32 frameno; - /* This field must be last, for states_equal() reasons. */ enum bpf_reg_liveness live; }; @@ -107,7 +107,6 @@ struct bpf_stack_state { */ struct bpf_func_state { struct bpf_reg_state regs[MAX_BPF_REG]; - struct bpf_verifier_state *parent; /* index of call instruction that called into this func */ int callsite; /* stack frame number of this function state from pov of @@ -129,7 +128,6 @@ struct bpf_func_state { struct bpf_verifier_state { /* call stack tracking */ struct bpf_func_state *frame[MAX_CALL_FRAMES]; - struct bpf_verifier_state *parent; u32 curframe; }; diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index ca5ab98053c8..4271f6b4e419 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -535,6 +535,32 @@ static inline void napi_synchronize(const struct napi_struct *n) barrier(); } +/** + * napi_if_scheduled_mark_missed - if napi is running, set the + * NAPIF_STATE_MISSED + * @n: NAPI context + * + * If napi is running, set the NAPIF_STATE_MISSED, and return true if + * NAPI is scheduled. + **/ +static inline bool napi_if_scheduled_mark_missed(struct napi_struct *n) +{ + unsigned long val, new; + + do { + val = READ_ONCE(n->state); + if (val & NAPIF_STATE_DISABLE) + return true; + + if (!(val & NAPIF_STATE_SCHED)) + return false; + + new = val | NAPIF_STATE_MISSED; + } while (cmpxchg(&n->state, val, new) != val); + + return true; +} + enum netdev_queue_state_t { __QUEUE_STATE_DRV_XOFF, __QUEUE_STATE_STACK_XOFF, diff --git a/include/net/xdp.h b/include/net/xdp.h index 76b95256c266..0f25b3675c5c 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -91,6 +91,8 @@ static inline void xdp_scrub_frame(struct xdp_frame *frame) frame->dev_rx = NULL; } +struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp); + /* Convert xdp_buff to xdp_frame */ static inline struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp) @@ -99,9 +101,8 @@ struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp) int metasize; int headroom; - /* TODO: implement clone, copy, use "native" MEM_TYPE */ if (xdp->rxq->mem.type == MEM_TYPE_ZERO_COPY) - return NULL; + return xdp_convert_zc_to_xdp_frame(xdp); /* Assure headroom is available for storing info */ headroom = xdp->data - xdp->data_hard_start; @@ -135,6 +136,7 @@ void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq); int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, enum xdp_mem_type type, void *allocator); +void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq); /* Drivers not supporting XDP metadata can use this helper, which * rejects any room expansion for metadata as a result. diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h index 7161856bcf9c..932ca0dad6f3 100644 --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@ -16,11 +16,6 @@ struct net_device; struct xsk_queue; -struct xdp_umem_props { - u64 chunk_mask; - u64 size; -}; - struct xdp_umem_page { void *addr; dma_addr_t dma; @@ -30,7 +25,8 @@ struct xdp_umem { struct xsk_queue *fq; struct xsk_queue *cq; struct xdp_umem_page *pages; - struct xdp_umem_props props; + u64 chunk_mask; + u64 size; u32 headroom; u32 chunk_size_nohr; struct user_struct *user; @@ -79,6 +75,16 @@ void xsk_umem_discard_addr(struct xdp_umem *umem); void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries); bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, u32 *len); void xsk_umem_consume_tx_done(struct xdp_umem *umem); + +static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr) +{ + return umem->pages[addr >> PAGE_SHIFT].addr + (addr & (PAGE_SIZE - 1)); +} + +static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr) +{ + return umem->pages[addr >> PAGE_SHIFT].dma + (addr & (PAGE_SIZE - 1)); +} #else static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) { @@ -98,6 +104,39 @@ static inline bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) { return false; } + +static inline u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr) +{ + return NULL; +} + +static inline void xsk_umem_discard_addr(struct xdp_umem *umem) +{ +} + +static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries) +{ +} + +static inline bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, + u32 *len) +{ + return false; +} + +static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem) +{ +} + +static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr) +{ + return NULL; +} + +static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr) +{ + return 0; +} #endif /* CONFIG_XDP_SOCKETS */ #endif /* _LINUX_XDP_SOCK_H */ diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 0c17aab3ce5f..f9d24121be99 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -358,6 +358,29 @@ static void array_map_seq_show_elem(struct bpf_map *map, void *key, rcu_read_unlock(); } +static void percpu_array_map_seq_show_elem(struct bpf_map *map, void *key, + struct seq_file *m) +{ + struct bpf_array *array = container_of(map, struct bpf_array, map); + u32 index = *(u32 *)key; + void __percpu *pptr; + int cpu; + + rcu_read_lock(); + + seq_printf(m, "%u: {\n", *(u32 *)key); + pptr = array->pptrs[index & array->index_mask]; + for_each_possible_cpu(cpu) { + seq_printf(m, "\tcpu%d: ", cpu); + btf_type_seq_show(map->btf, map->btf_value_type_id, + per_cpu_ptr(pptr, cpu), m); + seq_puts(m, "\n"); + } + seq_puts(m, "}\n"); + + rcu_read_unlock(); +} + static int array_map_check_btf(const struct bpf_map *map, const struct btf_type *key_type, const struct btf_type *value_type) @@ -398,6 +421,7 @@ const struct bpf_map_ops percpu_array_map_ops = { .map_lookup_elem = percpu_array_map_lookup_elem, .map_update_elem = array_map_update_elem, .map_delete_elem = array_map_delete_elem, + .map_seq_show_elem = percpu_array_map_seq_show_elem, .map_check_btf = array_map_check_btf, }; diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 03cc59ee9c95..2c1790288138 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -1285,6 +1285,35 @@ int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, return ret; } +static void htab_percpu_map_seq_show_elem(struct bpf_map *map, void *key, + struct seq_file *m) +{ + struct htab_elem *l; + void __percpu *pptr; + int cpu; + + rcu_read_lock(); + + l = __htab_map_lookup_elem(map, key); + if (!l) { + rcu_read_unlock(); + return; + } + + btf_type_seq_show(map->btf, map->btf_key_type_id, key, m); + seq_puts(m, ": {\n"); + pptr = htab_elem_get_ptr(l, map->key_size); + for_each_possible_cpu(cpu) { + seq_printf(m, "\tcpu%d: ", cpu); + btf_type_seq_show(map->btf, map->btf_value_type_id, + per_cpu_ptr(pptr, cpu), m); + seq_puts(m, "\n"); + } + seq_puts(m, "}\n"); + + rcu_read_unlock(); +} + const struct bpf_map_ops htab_percpu_map_ops = { .map_alloc_check = htab_map_alloc_check, .map_alloc = htab_map_alloc, @@ -1293,6 +1322,7 @@ const struct bpf_map_ops htab_percpu_map_ops = { .map_lookup_elem = htab_percpu_map_lookup_elem, .map_update_elem = htab_percpu_map_update_elem, .map_delete_elem = htab_map_delete_elem, + .map_seq_show_elem = htab_percpu_map_seq_show_elem, }; const struct bpf_map_ops htab_lru_percpu_map_ops = { @@ -1303,6 +1333,7 @@ const struct bpf_map_ops htab_lru_percpu_map_ops = { .map_lookup_elem = htab_lru_percpu_map_lookup_elem, .map_update_elem = htab_lru_percpu_map_update_elem, .map_delete_elem = htab_lru_map_delete_elem, + .map_seq_show_elem = htab_percpu_map_seq_show_elem, }; static int fd_htab_map_alloc_check(union bpf_attr *attr) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 8339d81cba1d..3c9636f03bb2 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -30,7 +30,6 @@ #include #include #include -#include #include #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \ diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 92246117d2b0..f4ff0c569e54 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -263,6 +263,13 @@ static const char * const reg_type_str[] = { [PTR_TO_PACKET_END] = "pkt_end", }; +static char slot_type_char[] = { + [STACK_INVALID] = '?', + [STACK_SPILL] = 'r', + [STACK_MISC] = 'm', + [STACK_ZERO] = '0', +}; + static void print_liveness(struct bpf_verifier_env *env, enum bpf_reg_liveness live) { @@ -349,15 +356,26 @@ static void print_verifier_state(struct bpf_verifier_env *env, } } for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (state->stack[i].slot_type[0] == STACK_SPILL) { - verbose(env, " fp%d", - (-i - 1) * BPF_REG_SIZE); - print_liveness(env, state->stack[i].spilled_ptr.live); + char types_buf[BPF_REG_SIZE + 1]; + bool valid = false; + int j; + + for (j = 0; j < BPF_REG_SIZE; j++) { + if (state->stack[i].slot_type[j] != STACK_INVALID) + valid = true; + types_buf[j] = slot_type_char[ + state->stack[i].slot_type[j]]; + } + types_buf[BPF_REG_SIZE] = 0; + if (!valid) + continue; + verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); + print_liveness(env, state->stack[i].spilled_ptr.live); + if (state->stack[i].slot_type[0] == STACK_SPILL) verbose(env, "=%s", reg_type_str[state->stack[i].spilled_ptr.type]); - } - if (state->stack[i].slot_type[0] == STACK_ZERO) - verbose(env, " fp%d=0", (-i - 1) * BPF_REG_SIZE); + else + verbose(env, "=%s", types_buf); } verbose(env, "\n"); } @@ -380,9 +398,9 @@ static int copy_stack_state(struct bpf_func_state *dst, /* do_check() starts with zero-sized stack in struct bpf_verifier_state to * make it consume minimal amount of memory. check_stack_write() access from * the program calls into realloc_func_state() to grow the stack size. - * Note there is a non-zero 'parent' pointer inside bpf_verifier_state - * which this function copies over. It points to previous bpf_verifier_state - * which is never reallocated + * Note there is a non-zero parent pointer inside each reg of bpf_verifier_state + * which this function copies over. It points to corresponding reg in previous + * bpf_verifier_state which is never reallocated */ static int realloc_func_state(struct bpf_func_state *state, int size, bool copy_old) @@ -466,7 +484,6 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state, dst_state->frame[i] = NULL; } dst_state->curframe = src->curframe; - dst_state->parent = src->parent; for (i = 0; i <= src->curframe; i++) { dst = dst_state->frame[i]; if (!dst) { @@ -732,6 +749,7 @@ static void init_reg_state(struct bpf_verifier_env *env, for (i = 0; i < MAX_BPF_REG; i++) { mark_reg_not_init(env, regs, i); regs[i].live = REG_LIVE_NONE; + regs[i].parent = NULL; } /* frame pointer */ @@ -876,74 +894,21 @@ next: return 0; } -static -struct bpf_verifier_state *skip_callee(struct bpf_verifier_env *env, - const struct bpf_verifier_state *state, - struct bpf_verifier_state *parent, - u32 regno) -{ - struct bpf_verifier_state *tmp = NULL; - - /* 'parent' could be a state of caller and - * 'state' could be a state of callee. In such case - * parent->curframe < state->curframe - * and it's ok for r1 - r5 registers - * - * 'parent' could be a callee's state after it bpf_exit-ed. - * In such case parent->curframe > state->curframe - * and it's ok for r0 only - */ - if (parent->curframe == state->curframe || - (parent->curframe < state->curframe && - regno >= BPF_REG_1 && regno <= BPF_REG_5) || - (parent->curframe > state->curframe && - regno == BPF_REG_0)) - return parent; - - if (parent->curframe > state->curframe && - regno >= BPF_REG_6) { - /* for callee saved regs we have to skip the whole chain - * of states that belong to callee and mark as LIVE_READ - * the registers before the call - */ - tmp = parent; - while (tmp && tmp->curframe != state->curframe) { - tmp = tmp->parent; - } - if (!tmp) - goto bug; - parent = tmp; - } else { - goto bug; - } - return parent; -bug: - verbose(env, "verifier bug regno %d tmp %p\n", regno, tmp); - verbose(env, "regno %d parent frame %d current frame %d\n", - regno, parent->curframe, state->curframe); - return NULL; -} - +/* Parentage chain of this register (or stack slot) should take care of all + * issues like callee-saved registers, stack slot allocation time, etc. + */ static int mark_reg_read(struct bpf_verifier_env *env, - const struct bpf_verifier_state *state, - struct bpf_verifier_state *parent, - u32 regno) + const struct bpf_reg_state *state, + struct bpf_reg_state *parent) { bool writes = parent == state->parent; /* Observe write marks */ - if (regno == BPF_REG_FP) - /* We don't need to worry about FP liveness because it's read-only */ - return 0; - while (parent) { /* if read wasn't screened by an earlier write ... */ - if (writes && state->frame[state->curframe]->regs[regno].live & REG_LIVE_WRITTEN) + if (writes && state->live & REG_LIVE_WRITTEN) break; - parent = skip_callee(env, state, parent, regno); - if (!parent) - return -EFAULT; /* ... then we depend on parent's value */ - parent->frame[parent->curframe]->regs[regno].live |= REG_LIVE_READ; + parent->live |= REG_LIVE_READ; state = parent; parent = state->parent; writes = true; @@ -969,7 +934,10 @@ static int check_reg_arg(struct bpf_verifier_env *env, u32 regno, verbose(env, "R%d !read_ok\n", regno); return -EACCES; } - return mark_reg_read(env, vstate, vstate->parent, regno); + /* We don't need to worry about FP liveness because it's read-only */ + if (regno != BPF_REG_FP) + return mark_reg_read(env, ®s[regno], + regs[regno].parent); } else { /* check whether register used as dest operand can be written to */ if (regno == BPF_REG_FP) { @@ -1080,8 +1048,8 @@ static int check_stack_write(struct bpf_verifier_env *env, } else { u8 type = STACK_MISC; - /* regular write of data into stack */ - state->stack[spi].spilled_ptr = (struct bpf_reg_state) {}; + /* regular write of data into stack destroys any spilled ptr */ + state->stack[spi].spilled_ptr.type = NOT_INIT; /* only mark the slot as written if all 8 bytes were written * otherwise read propagation may incorrectly stop too soon @@ -1106,61 +1074,6 @@ static int check_stack_write(struct bpf_verifier_env *env, return 0; } -/* registers of every function are unique and mark_reg_read() propagates - * the liveness in the following cases: - * - from callee into caller for R1 - R5 that were used as arguments - * - from caller into callee for R0 that used as result of the call - * - from caller to the same caller skipping states of the callee for R6 - R9, - * since R6 - R9 are callee saved by implicit function prologue and - * caller's R6 != callee's R6, so when we propagate liveness up to - * parent states we need to skip callee states for R6 - R9. - * - * stack slot marking is different, since stacks of caller and callee are - * accessible in both (since caller can pass a pointer to caller's stack to - * callee which can pass it to another function), hence mark_stack_slot_read() - * has to propagate the stack liveness to all parent states at given frame number. - * Consider code: - * f1() { - * ptr = fp - 8; - * *ptr = ctx; - * call f2 { - * .. = *ptr; - * } - * .. = *ptr; - * } - * First *ptr is reading from f1's stack and mark_stack_slot_read() has - * to mark liveness at the f1's frame and not f2's frame. - * Second *ptr is also reading from f1's stack and mark_stack_slot_read() has - * to propagate liveness to f2 states at f1's frame level and further into - * f1 states at f1's frame level until write into that stack slot - */ -static void mark_stack_slot_read(struct bpf_verifier_env *env, - const struct bpf_verifier_state *state, - struct bpf_verifier_state *parent, - int slot, int frameno) -{ - bool writes = parent == state->parent; /* Observe write marks */ - - while (parent) { - if (parent->frame[frameno]->allocated_stack <= slot * BPF_REG_SIZE) - /* since LIVE_WRITTEN mark is only done for full 8-byte - * write the read marks are conservative and parent - * state may not even have the stack allocated. In such case - * end the propagation, since the loop reached beginning - * of the function - */ - break; - /* if read wasn't screened by an earlier write ... */ - if (writes && state->frame[frameno]->stack[slot].spilled_ptr.live & REG_LIVE_WRITTEN) - break; - /* ... then we depend on parent's value */ - parent->frame[frameno]->stack[slot].spilled_ptr.live |= REG_LIVE_READ; - state = parent; - parent = state->parent; - writes = true; - } -} - static int check_stack_read(struct bpf_verifier_env *env, struct bpf_func_state *reg_state /* func where register points to */, int off, int size, int value_regno) @@ -1198,8 +1111,8 @@ static int check_stack_read(struct bpf_verifier_env *env, */ state->regs[value_regno].live |= REG_LIVE_WRITTEN; } - mark_stack_slot_read(env, vstate, vstate->parent, spi, - reg_state->frameno); + mark_reg_read(env, ®_state->stack[spi].spilled_ptr, + reg_state->stack[spi].spilled_ptr.parent); return 0; } else { int zeros = 0; @@ -1215,8 +1128,8 @@ static int check_stack_read(struct bpf_verifier_env *env, off, i, size); return -EACCES; } - mark_stack_slot_read(env, vstate, vstate->parent, spi, - reg_state->frameno); + mark_reg_read(env, ®_state->stack[spi].spilled_ptr, + reg_state->stack[spi].spilled_ptr.parent); if (value_regno >= 0) { if (zeros == size) { /* any size read into register is zero extended, @@ -1908,8 +1821,8 @@ mark: /* reading any byte out of 8-byte 'spill_slot' will cause * the whole slot to be marked as 'read' */ - mark_stack_slot_read(env, env->cur_state, env->cur_state->parent, - spi, state->frameno); + mark_reg_read(env, &state->stack[spi].spilled_ptr, + state->stack[spi].spilled_ptr.parent); } return update_stack_depth(env, state, off); } @@ -2366,11 +2279,13 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, state->curframe + 1 /* frameno within this callchain */, subprog /* subprog number within this prog */); - /* copy r1 - r5 args that callee can access */ + /* copy r1 - r5 args that callee can access. The copy includes parent + * pointers, which connects us up to the liveness chain + */ for (i = BPF_REG_1; i <= BPF_REG_5; i++) callee->regs[i] = caller->regs[i]; - /* after the call regsiters r0 - r5 were scratched */ + /* after the call registers r0 - r5 were scratched */ for (i = 0; i < CALLER_SAVED_REGS; i++) { mark_reg_not_init(env, caller->regs, caller_saved[i]); check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK); @@ -4370,7 +4285,7 @@ static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur, /* explored state didn't use this */ return true; - equal = memcmp(rold, rcur, offsetof(struct bpf_reg_state, frameno)) == 0; + equal = memcmp(rold, rcur, offsetof(struct bpf_reg_state, parent)) == 0; if (rold->type == PTR_TO_STACK) /* two stack pointers are equal only if they're pointing to @@ -4603,7 +4518,7 @@ static bool states_equal(struct bpf_verifier_env *env, * equivalent state (jump target or such) we didn't arrive by the straight-line * code, so read marks in the state must propagate to the parent regardless * of the state's write marks. That's what 'parent == state->parent' comparison - * in mark_reg_read() and mark_stack_slot_read() is for. + * in mark_reg_read() is for. */ static int propagate_liveness(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate, @@ -4624,7 +4539,8 @@ static int propagate_liveness(struct bpf_verifier_env *env, if (vparent->frame[vparent->curframe]->regs[i].live & REG_LIVE_READ) continue; if (vstate->frame[vstate->curframe]->regs[i].live & REG_LIVE_READ) { - err = mark_reg_read(env, vstate, vparent, i); + err = mark_reg_read(env, &vstate->frame[vstate->curframe]->regs[i], + &vparent->frame[vstate->curframe]->regs[i]); if (err) return err; } @@ -4639,7 +4555,8 @@ static int propagate_liveness(struct bpf_verifier_env *env, if (parent->stack[i].spilled_ptr.live & REG_LIVE_READ) continue; if (state->stack[i].spilled_ptr.live & REG_LIVE_READ) - mark_stack_slot_read(env, vstate, vparent, i, frame); + mark_reg_read(env, &state->stack[i].spilled_ptr, + &parent->stack[i].spilled_ptr); } } return err; @@ -4649,7 +4566,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) { struct bpf_verifier_state_list *new_sl; struct bpf_verifier_state_list *sl; - struct bpf_verifier_state *cur = env->cur_state; + struct bpf_verifier_state *cur = env->cur_state, *new; int i, j, err; sl = env->explored_states[insn_idx]; @@ -4691,16 +4608,18 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) return -ENOMEM; /* add new state to the head of linked list */ - err = copy_verifier_state(&new_sl->state, cur); + new = &new_sl->state; + err = copy_verifier_state(new, cur); if (err) { - free_verifier_state(&new_sl->state, false); + free_verifier_state(new, false); kfree(new_sl); return err; } new_sl->next = env->explored_states[insn_idx]; env->explored_states[insn_idx] = new_sl; /* connect new state to parentage chain */ - cur->parent = &new_sl->state; + for (i = 0; i < BPF_REG_FP; i++) + cur_regs(env)[i].parent = &new->frame[new->curframe]->regs[i]; /* clear write marks in current state: the writes we did are not writes * our child did, so they don't screen off its reads from us. * (There are no read marks in current state, because reads always mark @@ -4713,9 +4632,13 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx) /* all stack frames are accessible from callee, clear them all */ for (j = 0; j <= cur->curframe; j++) { struct bpf_func_state *frame = cur->frame[j]; + struct bpf_func_state *newframe = new->frame[j]; - for (i = 0; i < frame->allocated_stack / BPF_REG_SIZE; i++) + for (i = 0; i < frame->allocated_stack / BPF_REG_SIZE; i++) { frame->stack[i].spilled_ptr.live = REG_LIVE_NONE; + frame->stack[i].spilled_ptr.parent = + &newframe->stack[i].spilled_ptr; + } } return 0; } @@ -4734,7 +4657,6 @@ static int do_check(struct bpf_verifier_env *env) if (!state) return -ENOMEM; state->curframe = 0; - state->parent = NULL; state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL); if (!state->frame[0]) { kfree(state); diff --git a/net/core/filter.c b/net/core/filter.c index c25eb36f1320..feb578506009 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -4007,6 +4007,12 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, tp->snd_ssthresh = val; } break; + case TCP_SAVE_SYN: + if (val < 0 || val > 1) + ret = -EINVAL; + else + tp->save_syn = val; + break; default: ret = -EINVAL; } @@ -4032,21 +4038,32 @@ static const struct bpf_func_proto bpf_setsockopt_proto = { BPF_CALL_5(bpf_getsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { + struct inet_connection_sock *icsk; struct sock *sk = bpf_sock->sk; + struct tcp_sock *tp; if (!sk_fullsock(sk)) goto err_clear; - #ifdef CONFIG_INET if (level == SOL_TCP && sk->sk_prot->getsockopt == tcp_getsockopt) { - if (optname == TCP_CONGESTION) { - struct inet_connection_sock *icsk = inet_csk(sk); + switch (optname) { + case TCP_CONGESTION: + icsk = inet_csk(sk); if (!icsk->icsk_ca_ops || optlen <= 1) goto err_clear; strncpy(optval, icsk->icsk_ca_ops->name, optlen); optval[optlen - 1] = 0; - } else { + break; + case TCP_SAVED_SYN: + tp = tcp_sk(sk); + + if (optlen <= 0 || !tp->saved_syn || + optlen > tp->saved_syn[0]) + goto err_clear; + memcpy(optval, tp->saved_syn + 1, optlen); + break; + default: goto err_clear; } } else if (level == SOL_IP) { diff --git a/net/core/xdp.c b/net/core/xdp.c index 89b6785cef2a..4b2b194f4f1f 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -94,11 +94,21 @@ static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu) kfree(xa); } -static void __xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) +void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) { struct xdp_mem_allocator *xa; int id = xdp_rxq->mem.id; + if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { + WARN(1, "Missing register, driver bug"); + return; + } + + if (xdp_rxq->mem.type != MEM_TYPE_PAGE_POOL && + xdp_rxq->mem.type != MEM_TYPE_ZERO_COPY) { + return; + } + if (id == 0) return; @@ -110,6 +120,7 @@ static void __xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) mutex_unlock(&mem_id_lock); } +EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg_mem_model); void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq) { @@ -119,7 +130,7 @@ void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq) WARN(!(xdp_rxq->reg_state == REG_STATE_REGISTERED), "Driver BUG"); - __xdp_rxq_info_unreg_mem_model(xdp_rxq); + xdp_rxq_info_unreg_mem_model(xdp_rxq); xdp_rxq->reg_state = REG_STATE_UNREGISTERED; xdp_rxq->dev = NULL; @@ -398,3 +409,41 @@ void xdp_attachment_setup(struct xdp_attachment_info *info, info->flags = bpf->flags; } EXPORT_SYMBOL_GPL(xdp_attachment_setup); + +struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp) +{ + unsigned int metasize, totsize; + void *addr, *data_to_copy; + struct xdp_frame *xdpf; + struct page *page; + + /* Clone into a MEM_TYPE_PAGE_ORDER0 xdp_frame. */ + metasize = xdp_data_meta_unsupported(xdp) ? 0 : + xdp->data - xdp->data_meta; + totsize = xdp->data_end - xdp->data + metasize; + + if (sizeof(*xdpf) + totsize > PAGE_SIZE) + return NULL; + + page = dev_alloc_page(); + if (!page) + return NULL; + + addr = page_to_virt(page); + xdpf = addr; + memset(xdpf, 0, sizeof(*xdpf)); + + addr += sizeof(*xdpf); + data_to_copy = metasize ? xdp->data_meta : xdp->data; + memcpy(addr, data_to_copy, totsize); + + xdpf->data = addr + metasize; + xdpf->len = totsize - metasize; + xdpf->headroom = 0; + xdpf->metasize = metasize; + xdpf->mem.type = MEM_TYPE_PAGE_ORDER0; + + xdp_return_buff(xdp); + return xdpf; +} +EXPORT_SYMBOL_GPL(xdp_convert_zc_to_xdp_frame); diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index bfe2dbea480b..b3b632c5aeae 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -76,8 +76,6 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_async_xmit) return force_zc ? -EOPNOTSUPP : 0; /* fail or fallback */ - bpf.command = XDP_QUERY_XSK_UMEM; - rtnl_lock(); err = xdp_umem_query(dev, queue_id); if (err) { @@ -314,8 +312,8 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) umem->pid = get_task_pid(current, PIDTYPE_PID); umem->address = (unsigned long)addr; - umem->props.chunk_mask = ~((u64)chunk_size - 1); - umem->props.size = size; + umem->chunk_mask = ~((u64)chunk_size - 1); + umem->size = size; umem->headroom = headroom; umem->chunk_size_nohr = chunk_size - headroom; umem->npgs = size / PAGE_SIZE; diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h index f11560334f88..c8be1ad3eb88 100644 --- a/net/xdp/xdp_umem.h +++ b/net/xdp/xdp_umem.h @@ -8,16 +8,6 @@ #include -static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr) -{ - return umem->pages[addr >> PAGE_SHIFT].addr + (addr & (PAGE_SIZE - 1)); -} - -static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr) -{ - return umem->pages[addr >> PAGE_SHIFT].dma + (addr & (PAGE_SIZE - 1)); -} - int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev, u32 queue_id, u16 flags); bool xdp_umem_validate_queues(struct xdp_umem *umem); diff --git a/net/xdp/xdp_umem_props.h b/net/xdp/xdp_umem_props.h deleted file mode 100644 index 40eab10dfc49..000000000000 --- a/net/xdp/xdp_umem_props.h +++ /dev/null @@ -1,14 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* XDP user-space packet buffer - * Copyright(c) 2018 Intel Corporation. - */ - -#ifndef XDP_UMEM_PROPS_H_ -#define XDP_UMEM_PROPS_H_ - -struct xdp_umem_props { - u64 chunk_mask; - u64 size; -}; - -#endif /* XDP_UMEM_PROPS_H_ */ diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 4e937cd7c17d..5a432dfee4ee 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -55,20 +55,30 @@ EXPORT_SYMBOL(xsk_umem_discard_addr); static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp, u32 len) { - void *buffer; + void *to_buf, *from_buf; + u32 metalen; u64 addr; int err; if (!xskq_peek_addr(xs->umem->fq, &addr) || - len > xs->umem->chunk_size_nohr) { + len > xs->umem->chunk_size_nohr - XDP_PACKET_HEADROOM) { xs->rx_dropped++; return -ENOSPC; } addr += xs->umem->headroom; - buffer = xdp_umem_get_data(xs->umem, addr); - memcpy(buffer, xdp->data, len); + if (unlikely(xdp_data_meta_unsupported(xdp))) { + from_buf = xdp->data; + metalen = 0; + } else { + from_buf = xdp->data_meta; + metalen = xdp->data - xdp->data_meta; + } + + to_buf = xdp_umem_get_data(xs->umem, addr); + memcpy(to_buf, from_buf, len + metalen); + addr += metalen; err = xskq_produce_batch_desc(xs->rx, addr, len); if (!err) { xskq_discard_addr(xs->umem->fq); @@ -111,6 +121,7 @@ void xsk_flush(struct xdp_sock *xs) int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) { + u32 metalen = xdp->data - xdp->data_meta; u32 len = xdp->data_end - xdp->data; void *buffer; u64 addr; @@ -120,7 +131,7 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) return -EINVAL; if (!xskq_peek_addr(xs->umem->fq, &addr) || - len > xs->umem->chunk_size_nohr) { + len > xs->umem->chunk_size_nohr - XDP_PACKET_HEADROOM) { xs->rx_dropped++; return -ENOSPC; } @@ -128,7 +139,8 @@ int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) addr += xs->umem->headroom; buffer = xdp_umem_get_data(xs->umem, addr); - memcpy(buffer, xdp->data, len); + memcpy(buffer, xdp->data_meta, len + metalen); + addr += metalen; err = xskq_produce_batch_desc(xs->rx, addr, len); if (!err) { xskq_discard_addr(xs->umem->fq); @@ -458,8 +470,10 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) goto out_unlock; } else { /* This xsk has its own umem. */ - xskq_set_umem(xs->umem->fq, &xs->umem->props); - xskq_set_umem(xs->umem->cq, &xs->umem->props); + xskq_set_umem(xs->umem->fq, xs->umem->size, + xs->umem->chunk_mask); + xskq_set_umem(xs->umem->cq, xs->umem->size, + xs->umem->chunk_mask); err = xdp_umem_assign_dev(xs->umem, dev, qid, flags); if (err) @@ -469,8 +483,8 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) xs->dev = dev; xs->zc = xs->umem->zc; xs->queue_id = qid; - xskq_set_umem(xs->rx, &xs->umem->props); - xskq_set_umem(xs->tx, &xs->umem->props); + xskq_set_umem(xs->rx, xs->umem->size, xs->umem->chunk_mask); + xskq_set_umem(xs->tx, xs->umem->size, xs->umem->chunk_mask); xdp_add_sk_umem(xs->umem, xs); out_unlock: diff --git a/net/xdp/xsk_queue.c b/net/xdp/xsk_queue.c index 6c32e92e98fc..2dc1384d9f27 100644 --- a/net/xdp/xsk_queue.c +++ b/net/xdp/xsk_queue.c @@ -7,12 +7,13 @@ #include "xsk_queue.h" -void xskq_set_umem(struct xsk_queue *q, struct xdp_umem_props *umem_props) +void xskq_set_umem(struct xsk_queue *q, u64 size, u64 chunk_mask) { if (!q) return; - q->umem_props = *umem_props; + q->size = size; + q->chunk_mask = chunk_mask; } static u32 xskq_umem_get_ring_size(struct xsk_queue *q) diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h index 8a64b150be54..82252cccb4e0 100644 --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@ -31,7 +31,8 @@ struct xdp_umem_ring { }; struct xsk_queue { - struct xdp_umem_props umem_props; + u64 chunk_mask; + u64 size; u32 ring_mask; u32 nentries; u32 prod_head; @@ -78,7 +79,7 @@ static inline u32 xskq_nb_free(struct xsk_queue *q, u32 producer, u32 dcnt) static inline bool xskq_is_valid_addr(struct xsk_queue *q, u64 addr) { - if (addr >= q->umem_props.size) { + if (addr >= q->size) { q->invalid_descs++; return false; } @@ -92,7 +93,7 @@ static inline u64 *xskq_validate_addr(struct xsk_queue *q, u64 *addr) struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; unsigned int idx = q->cons_tail & q->ring_mask; - *addr = READ_ONCE(ring->desc[idx]) & q->umem_props.chunk_mask; + *addr = READ_ONCE(ring->desc[idx]) & q->chunk_mask; if (xskq_is_valid_addr(q, *addr)) return addr; @@ -173,8 +174,8 @@ static inline bool xskq_is_valid_desc(struct xsk_queue *q, struct xdp_desc *d) if (!xskq_is_valid_addr(q, d->addr)) return false; - if (((d->addr + d->len) & q->umem_props.chunk_mask) != - (d->addr & q->umem_props.chunk_mask)) { + if (((d->addr + d->len) & q->chunk_mask) != + (d->addr & q->chunk_mask)) { q->invalid_descs++; return false; } @@ -253,7 +254,7 @@ static inline bool xskq_empty_desc(struct xsk_queue *q) return xskq_nb_free(q, q->prod_tail, q->nentries) == q->nentries; } -void xskq_set_umem(struct xsk_queue *q, struct xdp_umem_props *umem_props); +void xskq_set_umem(struct xsk_queue *q, u64 size, u64 chunk_mask); struct xsk_queue *xskq_create(u32 nentries, bool umem_queue); void xskq_destroy(struct xsk_queue *q_ops); diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 36f9f41d094b..be0a961450bc 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -153,6 +153,7 @@ always += tcp_cong_kern.o always += tcp_iw_kern.o always += tcp_clamp_kern.o always += tcp_basertt_kern.o +always += tcp_tos_reflect_kern.o always += xdp_redirect_kern.o always += xdp_redirect_map_kern.o always += xdp_redirect_cpu_kern.o diff --git a/samples/bpf/tcp_tos_reflect_kern.c b/samples/bpf/tcp_tos_reflect_kern.c new file mode 100644 index 000000000000..d51dab19eca6 --- /dev/null +++ b/samples/bpf/tcp_tos_reflect_kern.c @@ -0,0 +1,87 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2018 Facebook + * + * BPF program to automatically reflect TOS option from received syn packet + * + * Use load_sock_ops to load this BPF program. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include "bpf_helpers.h" +#include "bpf_endian.h" + +#define DEBUG 1 + +#define bpf_printk(fmt, ...) \ +({ \ + char ____fmt[] = fmt; \ + bpf_trace_printk(____fmt, sizeof(____fmt), \ + ##__VA_ARGS__); \ +}) + +SEC("sockops") +int bpf_basertt(struct bpf_sock_ops *skops) +{ + char header[sizeof(struct ipv6hdr)]; + struct ipv6hdr *hdr6; + struct iphdr *hdr; + int hdr_size = 0; + int save_syn = 1; + int tos = 0; + int rv = 0; + int op; + + op = (int) skops->op; + +#ifdef DEBUG + bpf_printk("BPF command: %d\n", op); +#endif + switch (op) { + case BPF_SOCK_OPS_TCP_LISTEN_CB: + rv = bpf_setsockopt(skops, SOL_TCP, TCP_SAVE_SYN, + &save_syn, sizeof(save_syn)); + break; + case BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB: + if (skops->family == AF_INET) + hdr_size = sizeof(struct iphdr); + else + hdr_size = sizeof(struct ipv6hdr); + rv = bpf_getsockopt(skops, SOL_TCP, TCP_SAVED_SYN, + header, hdr_size); + if (!rv) { + if (skops->family == AF_INET) { + hdr = (struct iphdr *) header; + tos = hdr->tos; + if (tos != 0) + bpf_setsockopt(skops, SOL_IP, IP_TOS, + &tos, sizeof(tos)); + } else { + hdr6 = (struct ipv6hdr *) header; + tos = ((hdr6->priority) << 4 | + (hdr6->flow_lbl[0]) >> 4); + if (tos) + bpf_setsockopt(skops, SOL_IPV6, + IPV6_TCLASS, + &tos, sizeof(tos)); + } + rv = 0; + } + break; + default: + rv = -1; + } +#ifdef DEBUG + bpf_printk("Returning %d\n", rv); +#endif + skops->reply = rv; + return 1; +} +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/xdpsock_kern.c b/samples/bpf/xdpsock_kern.c index d8806c41362e..b8ccd0802b3f 100644 --- a/samples/bpf/xdpsock_kern.c +++ b/samples/bpf/xdpsock_kern.c @@ -16,7 +16,7 @@ struct bpf_map_def SEC("maps") xsks_map = { .type = BPF_MAP_TYPE_XSKMAP, .key_size = sizeof(int), .value_size = sizeof(int), - .max_entries = 4, + .max_entries = MAX_SOCKS, }; struct bpf_map_def SEC("maps") rr_map = { diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c index 4914788b6727..57ecadc58403 100644 --- a/samples/bpf/xdpsock_user.c +++ b/samples/bpf/xdpsock_user.c @@ -118,7 +118,6 @@ struct xdpsock { unsigned long prev_tx_npkts; }; -#define MAX_SOCKS 4 static int num_socks; struct xdpsock *xsks[MAX_SOCKS]; @@ -596,7 +595,7 @@ static void dump_stats(void) prev_time = now; - for (i = 0; i < num_socks; i++) { + for (i = 0; i < num_socks && xsks[i]; i++) { char *fmt = "%-15s %'-11.0f %'-11lu\n"; double rx_pps, tx_pps; @@ -649,6 +648,8 @@ static struct option long_options[] = { {"xdp-skb", no_argument, 0, 'S'}, {"xdp-native", no_argument, 0, 'N'}, {"interval", required_argument, 0, 'n'}, + {"zero-copy", no_argument, 0, 'z'}, + {"copy", no_argument, 0, 'c'}, {0, 0, 0, 0} }; @@ -667,6 +668,8 @@ static void usage(const char *prog) " -S, --xdp-skb=n Use XDP skb-mod\n" " -N, --xdp-native=n Enfore XDP native mode\n" " -n, --interval=n Specify statistics update interval (default 1 sec).\n" + " -z, --zero-copy Force zero-copy mode.\n" + " -c, --copy Force copy mode.\n" "\n"; fprintf(stderr, str, prog); exit(EXIT_FAILURE); @@ -679,7 +682,7 @@ static void parse_command_line(int argc, char **argv) opterr = 0; for (;;) { - c = getopt_long(argc, argv, "rtli:q:psSNn:", long_options, + c = getopt_long(argc, argv, "rtli:q:psSNn:cz", long_options, &option_index); if (c == -1) break; @@ -716,6 +719,12 @@ static void parse_command_line(int argc, char **argv) case 'n': opt_interval = atoi(optarg); break; + case 'z': + opt_xdp_bind_flags |= XDP_ZEROCOPY; + break; + case 'c': + opt_xdp_bind_flags |= XDP_COPY; + break; default: usage(basename(argv[0])); } diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index b2ec20e562bd..df175bc33c5d 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -169,9 +169,28 @@ static int do_dump_btf(const struct btf_dumper *d, if (ret) goto err_end_obj; - jsonw_name(d->jw, "value"); + if (!map_is_per_cpu(map_info->type)) { + jsonw_name(d->jw, "value"); + ret = btf_dumper_type(d, map_info->btf_value_type_id, value); + } else { + unsigned int i, n, step; - ret = btf_dumper_type(d, map_info->btf_value_type_id, value); + jsonw_name(d->jw, "values"); + jsonw_start_array(d->jw); + n = get_possible_cpus(); + step = round_up(map_info->value_size, 8); + for (i = 0; i < n; i++) { + jsonw_start_object(d->jw); + jsonw_int_field(d->jw, "cpu", i); + jsonw_name(d->jw, "value"); + ret = btf_dumper_type(d, map_info->btf_value_type_id, + value + i * step); + jsonw_end_object(d->jw); + if (ret) + break; + } + jsonw_end_array(d->jw); + } err_end_obj: /* end of key-value pair */ @@ -298,6 +317,16 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key, jsonw_end_object(json_wtr); } jsonw_end_array(json_wtr); + if (btf) { + struct btf_dumper d = { + .btf = btf, + .jw = json_wtr, + .is_plain_text = false, + }; + + jsonw_name(json_wtr, "formatted"); + do_dump_btf(&d, info, key, value); + } } jsonw_end_object(json_wtr); diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c index 6b5cfeb7a9cc..f42b3396d622 100644 --- a/tools/testing/selftests/bpf/test_btf.c +++ b/tools/testing/selftests/bpf/test_btf.c @@ -4,6 +4,7 @@ #include #include #include +#include #include #include #include @@ -45,7 +46,6 @@ static int count_result(int err) return err; } -#define min(a, b) ((a) < (b) ? (a) : (b)) #define __printf(a, b) __attribute__((format(printf, a, b))) __printf(1, 2) @@ -130,6 +130,7 @@ struct btf_raw_test { bool map_create_err; bool ordered_map; bool lossless_map; + bool percpu_map; int hdr_len_delta; int type_off_delta; int str_off_delta; @@ -2157,6 +2158,7 @@ static struct btf_pprint_test_meta { const char *map_name; bool ordered_map; bool lossless_map; + bool percpu_map; } pprint_tests_meta[] = { { .descr = "BTF pretty print array", @@ -2164,6 +2166,7 @@ static struct btf_pprint_test_meta { .map_name = "pprint_test_array", .ordered_map = true, .lossless_map = true, + .percpu_map = false, }, { @@ -2172,6 +2175,7 @@ static struct btf_pprint_test_meta { .map_name = "pprint_test_hash", .ordered_map = false, .lossless_map = true, + .percpu_map = false, }, { @@ -2180,30 +2184,83 @@ static struct btf_pprint_test_meta { .map_name = "pprint_test_lru_hash", .ordered_map = false, .lossless_map = false, + .percpu_map = false, +}, + +{ + .descr = "BTF pretty print percpu array", + .map_type = BPF_MAP_TYPE_PERCPU_ARRAY, + .map_name = "pprint_test_percpu_array", + .ordered_map = true, + .lossless_map = true, + .percpu_map = true, +}, + +{ + .descr = "BTF pretty print percpu hash", + .map_type = BPF_MAP_TYPE_PERCPU_HASH, + .map_name = "pprint_test_percpu_hash", + .ordered_map = false, + .lossless_map = true, + .percpu_map = true, +}, + +{ + .descr = "BTF pretty print lru percpu hash", + .map_type = BPF_MAP_TYPE_LRU_PERCPU_HASH, + .map_name = "pprint_test_lru_percpu_hash", + .ordered_map = false, + .lossless_map = false, + .percpu_map = true, }, }; -static void set_pprint_mapv(struct pprint_mapv *v, uint32_t i) +static void set_pprint_mapv(struct pprint_mapv *v, uint32_t i, + int num_cpus, int rounded_value_size) { - v->ui32 = i; - v->si32 = -i; - v->unused_bits2a = 3; - v->bits28 = i; - v->unused_bits2b = 3; - v->ui64 = i; - v->aenum = i & 0x03; + int cpu; + + for (cpu = 0; cpu < num_cpus; cpu++) { + v->ui32 = i + cpu; + v->si32 = -i; + v->unused_bits2a = 3; + v->bits28 = i; + v->unused_bits2b = 3; + v->ui64 = i; + v->aenum = i & 0x03; + v = (void *)v + rounded_value_size; + } } +static int check_line(const char *expected_line, int nexpected_line, + int expected_line_len, const char *line) +{ + if (CHECK(nexpected_line == expected_line_len, + "expected_line is too long")) + return -1; + + if (strcmp(expected_line, line)) { + fprintf(stderr, "unexpected pprint output\n"); + fprintf(stderr, "expected: %s", expected_line); + fprintf(stderr, " read: %s", line); + return -1; + } + + return 0; +} + + static int do_test_pprint(void) { const struct btf_raw_test *test = &pprint_test_template; struct bpf_create_map_attr create_attr = {}; + bool ordered_map, lossless_map, percpu_map; + int err, ret, num_cpus, rounded_value_size; + struct pprint_mapv *mapv = NULL; unsigned int key, nr_read_elems; - bool ordered_map, lossless_map; int map_fd = -1, btf_fd = -1; - struct pprint_mapv mapv = {}; unsigned int raw_btf_size; char expected_line[255]; FILE *pin_file = NULL; @@ -2212,7 +2269,6 @@ static int do_test_pprint(void) char *line = NULL; uint8_t *raw_btf; ssize_t nread; - int err, ret; fprintf(stderr, "%s......", test->descr); raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types, @@ -2261,9 +2317,18 @@ static int do_test_pprint(void) if (CHECK(err, "bpf_obj_pin(%s): errno:%d.", pin_path, errno)) goto done; + percpu_map = test->percpu_map; + num_cpus = percpu_map ? bpf_num_possible_cpus() : 1; + rounded_value_size = round_up(sizeof(struct pprint_mapv), 8); + mapv = calloc(num_cpus, rounded_value_size); + if (CHECK(!mapv, "mapv allocation failure")) { + err = -1; + goto done; + } + for (key = 0; key < test->max_entries; key++) { - set_pprint_mapv(&mapv, key); - bpf_map_update_elem(map_fd, &key, &mapv, 0); + set_pprint_mapv(mapv, key, num_cpus, rounded_value_size); + bpf_map_update_elem(map_fd, &key, mapv, 0); } pin_file = fopen(pin_path, "r"); @@ -2286,33 +2351,74 @@ static int do_test_pprint(void) ordered_map = test->ordered_map; lossless_map = test->lossless_map; do { + struct pprint_mapv *cmapv; ssize_t nexpected_line; unsigned int next_key; + int cpu; next_key = ordered_map ? nr_read_elems : atoi(line); - set_pprint_mapv(&mapv, next_key); - nexpected_line = snprintf(expected_line, sizeof(expected_line), - "%u: {%u,0,%d,0x%x,0x%x,0x%x,{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s}\n", - next_key, - mapv.ui32, mapv.si32, - mapv.unused_bits2a, mapv.bits28, mapv.unused_bits2b, - mapv.ui64, - mapv.ui8a[0], mapv.ui8a[1], mapv.ui8a[2], mapv.ui8a[3], - mapv.ui8a[4], mapv.ui8a[5], mapv.ui8a[6], mapv.ui8a[7], - pprint_enum_str[mapv.aenum]); + set_pprint_mapv(mapv, next_key, num_cpus, rounded_value_size); + cmapv = mapv; - if (CHECK(nexpected_line == sizeof(expected_line), - "expected_line is too long")) { - err = -1; - goto done; + for (cpu = 0; cpu < num_cpus; cpu++) { + if (percpu_map) { + /* for percpu map, the format looks like: + * : { + * cpu0: + * cpu1: + * ... + * cpun: + * } + * + * let us verify the line containing the key here. + */ + if (cpu == 0) { + nexpected_line = snprintf(expected_line, + sizeof(expected_line), + "%u: {\n", + next_key); + + err = check_line(expected_line, nexpected_line, + sizeof(expected_line), line); + if (err == -1) + goto done; + } + + /* read value@cpu */ + nread = getline(&line, &line_len, pin_file); + if (nread < 0) + break; + } + + nexpected_line = snprintf(expected_line, sizeof(expected_line), + "%s%u: {%u,0,%d,0x%x,0x%x,0x%x," + "{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s}\n", + percpu_map ? "\tcpu" : "", + percpu_map ? cpu : next_key, + cmapv->ui32, cmapv->si32, + cmapv->unused_bits2a, + cmapv->bits28, + cmapv->unused_bits2b, + cmapv->ui64, + cmapv->ui8a[0], cmapv->ui8a[1], + cmapv->ui8a[2], cmapv->ui8a[3], + cmapv->ui8a[4], cmapv->ui8a[5], + cmapv->ui8a[6], cmapv->ui8a[7], + pprint_enum_str[cmapv->aenum]); + + err = check_line(expected_line, nexpected_line, + sizeof(expected_line), line); + if (err == -1) + goto done; + + cmapv = (void *)cmapv + rounded_value_size; } - if (strcmp(expected_line, line)) { - err = -1; - fprintf(stderr, "unexpected pprint output\n"); - fprintf(stderr, "expected: %s", expected_line); - fprintf(stderr, " read: %s", line); - goto done; + if (percpu_map) { + /* skip the last bracket for the percpu map */ + nread = getline(&line, &line_len, pin_file); + if (nread < 0) + break; } nread = getline(&line, &line_len, pin_file); @@ -2334,6 +2440,8 @@ static int do_test_pprint(void) err = 0; done: + if (mapv) + free(mapv); if (!err) fprintf(stderr, "OK"); if (*btf_log_buf && (err || args.always_log)) @@ -2361,6 +2469,7 @@ static int test_pprint(void) pprint_test_template.map_name = pprint_tests_meta[i].map_name; pprint_test_template.ordered_map = pprint_tests_meta[i].ordered_map; pprint_test_template.lossless_map = pprint_tests_meta[i].lossless_map; + pprint_test_template.percpu_map = pprint_tests_meta[i].percpu_map; err |= count_result(do_test_pprint()); } diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c index 0c7d9e556b47..ac7de38e5c63 100644 --- a/tools/testing/selftests/bpf/test_sockmap.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -469,8 +469,6 @@ static int sendmsg_test(struct sockmap_options *opt) fprintf(stderr, "msg_loop_rx: iov_count %i iov_buf %i cnt %i err %i\n", iov_count, iov_buf, cnt, err); - shutdown(p2, SHUT_RDWR); - shutdown(p1, SHUT_RDWR); if (s.end.tv_sec - s.start.tv_sec) { sent_Bps = sentBps(s); recvd_Bps = recvdBps(s); @@ -500,7 +498,6 @@ static int sendmsg_test(struct sockmap_options *opt) fprintf(stderr, "msg_loop_tx: iov_count %i iov_buf %i cnt %i err %i\n", iov_count, iov_buf, cnt, err); - shutdown(c1, SHUT_RDWR); if (s.end.tv_sec - s.start.tv_sec) { sent_Bps = sentBps(s); recvd_Bps = recvdBps(s); @@ -1348,9 +1345,9 @@ static int populate_progs(char *bpf_file) return 0; } -static int __test_suite(char *bpf_file) +static int __test_suite(int cg_fd, char *bpf_file) { - int cg_fd, err; + int err, cleanup = cg_fd; err = populate_progs(bpf_file); if (err < 0) { @@ -1358,22 +1355,24 @@ static int __test_suite(char *bpf_file) return err; } - if (setup_cgroup_environment()) { - fprintf(stderr, "ERROR: cgroup env failed\n"); - return -EINVAL; - } - - cg_fd = create_and_get_cgroup(CG_PATH); if (cg_fd < 0) { - fprintf(stderr, - "ERROR: (%i) open cg path failed: %s\n", - cg_fd, optarg); - return cg_fd; - } + if (setup_cgroup_environment()) { + fprintf(stderr, "ERROR: cgroup env failed\n"); + return -EINVAL; + } - if (join_cgroup(CG_PATH)) { - fprintf(stderr, "ERROR: failed to join cgroup\n"); - return -EINVAL; + cg_fd = create_and_get_cgroup(CG_PATH); + if (cg_fd < 0) { + fprintf(stderr, + "ERROR: (%i) open cg path failed: %s\n", + cg_fd, optarg); + return cg_fd; + } + + if (join_cgroup(CG_PATH)) { + fprintf(stderr, "ERROR: failed to join cgroup\n"); + return -EINVAL; + } } /* Tests basic commands and APIs with range of iov values */ @@ -1394,20 +1393,24 @@ static int __test_suite(char *bpf_file) out: printf("Summary: %i PASSED %i FAILED\n", passed, failed); - cleanup_cgroup_environment(); - close(cg_fd); + if (cleanup < 0) { + cleanup_cgroup_environment(); + close(cg_fd); + } return err; } -static int test_suite(void) +static int test_suite(int cg_fd) { int err; - err = __test_suite(BPF_SOCKMAP_FILENAME); + err = __test_suite(cg_fd, BPF_SOCKMAP_FILENAME); if (err) goto out; - err = __test_suite(BPF_SOCKHASH_FILENAME); + err = __test_suite(cg_fd, BPF_SOCKHASH_FILENAME); out: + if (cg_fd > -1) + close(cg_fd); return err; } @@ -1420,7 +1423,7 @@ int main(int argc, char **argv) int test = PING_PONG; if (argc < 2) - return test_suite(); + return test_suite(-1); while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:", long_options, &longindex)) != -1) { @@ -1486,6 +1489,9 @@ int main(int argc, char **argv) } } + if (argc <= 3 && cg_fd) + return test_suite(cg_fd); + if (!cg_fd) { fprintf(stderr, "%s requires cgroup option: --cgroup \n", argv[0]); diff --git a/tools/testing/selftests/bpf/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/test_tcpbpf_kern.c index 4b7fd540cea9..74f73b33a7b0 100644 --- a/tools/testing/selftests/bpf/test_tcpbpf_kern.c +++ b/tools/testing/selftests/bpf/test_tcpbpf_kern.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -17,6 +18,13 @@ struct bpf_map_def SEC("maps") global_map = { .type = BPF_MAP_TYPE_ARRAY, .key_size = sizeof(__u32), .value_size = sizeof(struct tcpbpf_globals), + .max_entries = 4, +}; + +struct bpf_map_def SEC("maps") sockopt_results = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(int), .max_entries = 2, }; @@ -45,11 +53,14 @@ int _version SEC("version") = 1; SEC("sockops") int bpf_testcb(struct bpf_sock_ops *skops) { - int rv = -1; - int bad_call_rv = 0; + char header[sizeof(struct ipv6hdr) + sizeof(struct tcphdr)]; + struct tcphdr *thdr; int good_call_rv = 0; - int op; + int bad_call_rv = 0; + int save_syn = 1; + int rv = -1; int v = 0; + int op; op = (int) skops->op; @@ -82,6 +93,21 @@ int bpf_testcb(struct bpf_sock_ops *skops) v = 0xff; rv = bpf_setsockopt(skops, SOL_IPV6, IPV6_TCLASS, &v, sizeof(v)); + if (skops->family == AF_INET6) { + v = bpf_getsockopt(skops, IPPROTO_TCP, TCP_SAVED_SYN, + header, (sizeof(struct ipv6hdr) + + sizeof(struct tcphdr))); + if (!v) { + int offset = sizeof(struct ipv6hdr); + + thdr = (struct tcphdr *)(header + offset); + v = thdr->syn; + __u32 key = 1; + + bpf_map_update_elem(&sockopt_results, &key, &v, + BPF_ANY); + } + } break; case BPF_SOCK_OPS_RTO_CB: break; @@ -111,6 +137,12 @@ int bpf_testcb(struct bpf_sock_ops *skops) break; case BPF_SOCK_OPS_TCP_LISTEN_CB: bpf_sock_ops_cb_flags_set(skops, BPF_SOCK_OPS_STATE_CB_FLAG); + v = bpf_setsockopt(skops, IPPROTO_TCP, TCP_SAVE_SYN, + &save_syn, sizeof(save_syn)); + /* Update global map w/ result of setsock opt */ + __u32 key = 0; + + bpf_map_update_elem(&sockopt_results, &key, &v, BPF_ANY); break; default: rv = -1; diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c index a275c2971376..e6eebda7d112 100644 --- a/tools/testing/selftests/bpf/test_tcpbpf_user.c +++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c @@ -54,6 +54,26 @@ err: return -1; } +int verify_sockopt_result(int sock_map_fd) +{ + __u32 key = 0; + int res; + int rv; + + /* check setsockopt for SAVE_SYN */ + rv = bpf_map_lookup_elem(sock_map_fd, &key, &res); + EXPECT_EQ(0, rv, "d"); + EXPECT_EQ(0, res, "d"); + key = 1; + /* check getsockopt for SAVED_SYN */ + rv = bpf_map_lookup_elem(sock_map_fd, &key, &res); + EXPECT_EQ(0, rv, "d"); + EXPECT_EQ(1, res, "d"); + return 0; +err: + return -1; +} + static int bpf_find_map(const char *test, struct bpf_object *obj, const char *name) { @@ -70,11 +90,11 @@ static int bpf_find_map(const char *test, struct bpf_object *obj, int main(int argc, char **argv) { const char *file = "test_tcpbpf_kern.o"; + int prog_fd, map_fd, sock_map_fd; struct tcpbpf_globals g = {0}; const char *cg_path = "/foo"; int error = EXIT_FAILURE; struct bpf_object *obj; - int prog_fd, map_fd; int cg_fd = -1; __u32 key = 0; int rv; @@ -110,6 +130,10 @@ int main(int argc, char **argv) if (map_fd < 0) goto err; + sock_map_fd = bpf_find_map(__func__, obj, "sockopt_results"); + if (sock_map_fd < 0) + goto err; + rv = bpf_map_lookup_elem(map_fd, &key, &g); if (rv != 0) { printf("FAILED: bpf_map_lookup_elem returns %d\n", rv); @@ -121,6 +145,11 @@ int main(int argc, char **argv) goto err; } + if (verify_sockopt_result(sock_map_fd)) { + printf("FAILED: Wrong sockopt stats\n"); + goto err; + } + printf("PASSED!\n"); error = 0; err: