diff options
Diffstat (limited to 'drivers/net')
24 files changed, 486 insertions, 241 deletions
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 5883eb93efb1..22513f3d56db 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -2541,6 +2541,9 @@ mt7531_setup_common(struct dsa_switch *ds) struct mt7530_priv *priv = ds->priv; int ret, i; + ds->assisted_learning_on_cpu_port = true; + ds->mtu_enforcement_ingress = true; + mt753x_trap_frames(priv); /* Enable and reset MIB counters */ @@ -2688,9 +2691,6 @@ mt7531_setup(struct dsa_switch *ds) if (ret) return ret; - ds->assisted_learning_on_cpu_port = true; - ds->mtu_enforcement_ingress = true; - return 0; } diff --git a/drivers/net/ethernet/amd/pds_core/adminq.c b/drivers/net/ethernet/amd/pds_core/adminq.c index c83a0a80d533..506f682d15c1 100644 --- a/drivers/net/ethernet/amd/pds_core/adminq.c +++ b/drivers/net/ethernet/amd/pds_core/adminq.c @@ -5,11 +5,6 @@ #include "core.h" -struct pdsc_wait_context { - struct pdsc_qcq *qcq; - struct completion wait_completion; -}; - static int pdsc_process_notifyq(struct pdsc_qcq *qcq) { union pds_core_notifyq_comp *comp; @@ -109,10 +104,10 @@ void pdsc_process_adminq(struct pdsc_qcq *qcq) q_info = &q->info[q->tail_idx]; q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1); - /* Copy out the completion data */ - memcpy(q_info->dest, comp, sizeof(*comp)); - - complete_all(&q_info->wc->wait_completion); + if (!completion_done(&q_info->completion)) { + memcpy(q_info->dest, comp, sizeof(*comp)); + complete(&q_info->completion); + } if (cq->tail_idx == cq->num_descs - 1) cq->done_color = !cq->done_color; @@ -162,8 +157,7 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data) static int __pdsc_adminq_post(struct pdsc *pdsc, struct pdsc_qcq *qcq, union pds_core_adminq_cmd *cmd, - union pds_core_adminq_comp *comp, - struct pdsc_wait_context *wc) + union pds_core_adminq_comp *comp) { struct pdsc_queue *q = &qcq->q; struct pdsc_q_info *q_info; @@ -205,9 +199,9 @@ static int __pdsc_adminq_post(struct pdsc *pdsc, /* Post the request */ index = q->head_idx; q_info = &q->info[index]; - q_info->wc = wc; q_info->dest = comp; memcpy(q_info->desc, cmd, sizeof(*cmd)); + reinit_completion(&q_info->completion); dev_dbg(pdsc->dev, "head_idx %d tail_idx %d\n", q->head_idx, q->tail_idx); @@ -231,16 +225,13 @@ int pdsc_adminq_post(struct pdsc *pdsc, union pds_core_adminq_comp *comp, bool fast_poll) { - struct pdsc_wait_context wc = { - .wait_completion = - COMPLETION_INITIALIZER_ONSTACK(wc.wait_completion), - }; unsigned long poll_interval = 1; unsigned long poll_jiffies; unsigned long time_limit; unsigned long time_start; unsigned long time_done; unsigned long remaining; + struct completion *wc; int err = 0; int index; @@ -250,20 +241,19 @@ int pdsc_adminq_post(struct pdsc *pdsc, return -ENXIO; } - wc.qcq = &pdsc->adminqcq; - index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp, &wc); + index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp); if (index < 0) { err = index; goto err_out; } + wc = &pdsc->adminqcq.q.info[index].completion; time_start = jiffies; time_limit = time_start + HZ * pdsc->devcmd_timeout; do { /* Timeslice the actual wait to catch IO errors etc early */ poll_jiffies = msecs_to_jiffies(poll_interval); - remaining = wait_for_completion_timeout(&wc.wait_completion, - poll_jiffies); + remaining = wait_for_completion_timeout(wc, poll_jiffies); if (remaining) break; @@ -292,9 +282,11 @@ int pdsc_adminq_post(struct pdsc *pdsc, dev_dbg(pdsc->dev, "%s: elapsed %d msecs\n", __func__, jiffies_to_msecs(time_done - time_start)); - /* Check the results */ - if (time_after_eq(time_done, time_limit)) + /* Check the results and clear an un-completed timeout */ + if (time_after_eq(time_done, time_limit) && !completion_done(wc)) { err = -ETIMEDOUT; + complete(wc); + } dev_dbg(pdsc->dev, "read admin queue completion idx %d:\n", index); dynamic_hex_dump("comp ", DUMP_PREFIX_OFFSET, 16, 1, diff --git a/drivers/net/ethernet/amd/pds_core/auxbus.c b/drivers/net/ethernet/amd/pds_core/auxbus.c index 2babea110991..b76a9b7e0aed 100644 --- a/drivers/net/ethernet/amd/pds_core/auxbus.c +++ b/drivers/net/ethernet/amd/pds_core/auxbus.c @@ -107,9 +107,6 @@ int pds_client_adminq_cmd(struct pds_auxiliary_dev *padev, dev_dbg(pf->dev, "%s: %s opcode %d\n", __func__, dev_name(&padev->aux_dev.dev), req->opcode); - if (pf->state) - return -ENXIO; - /* Wrap the client's request */ cmd.client_request.opcode = PDS_AQ_CMD_CLIENT_CMD; cmd.client_request.client_id = cpu_to_le16(padev->client_id); diff --git a/drivers/net/ethernet/amd/pds_core/core.c b/drivers/net/ethernet/amd/pds_core/core.c index 536635e57727..3c60d4cf9d0e 100644 --- a/drivers/net/ethernet/amd/pds_core/core.c +++ b/drivers/net/ethernet/amd/pds_core/core.c @@ -167,8 +167,10 @@ static void pdsc_q_map(struct pdsc_queue *q, void *base, dma_addr_t base_pa) q->base = base; q->base_pa = base_pa; - for (i = 0, cur = q->info; i < q->num_descs; i++, cur++) + for (i = 0, cur = q->info; i < q->num_descs; i++, cur++) { cur->desc = base + (i * q->desc_size); + init_completion(&cur->completion); + } } static void pdsc_cq_map(struct pdsc_cq *cq, void *base, dma_addr_t base_pa) @@ -325,10 +327,7 @@ static int pdsc_core_init(struct pdsc *pdsc) size_t sz; int err; - /* Scale the descriptor ring length based on number of CPUs and VFs */ - numdescs = max_t(int, PDSC_ADMINQ_MIN_LENGTH, num_online_cpus()); - numdescs += 2 * pci_sriov_get_totalvfs(pdsc->pdev); - numdescs = roundup_pow_of_two(numdescs); + numdescs = PDSC_ADMINQ_MAX_LENGTH; err = pdsc_qcq_alloc(pdsc, PDS_CORE_QTYPE_ADMINQ, 0, "adminq", PDS_CORE_QCQ_F_CORE | PDS_CORE_QCQ_F_INTR, numdescs, diff --git a/drivers/net/ethernet/amd/pds_core/core.h b/drivers/net/ethernet/amd/pds_core/core.h index 14522d6d5f86..ec637dc4327a 100644 --- a/drivers/net/ethernet/amd/pds_core/core.h +++ b/drivers/net/ethernet/amd/pds_core/core.h @@ -16,7 +16,7 @@ #define PDSC_WATCHDOG_SECS 5 #define PDSC_QUEUE_NAME_MAX_SZ 16 -#define PDSC_ADMINQ_MIN_LENGTH 16 /* must be a power of two */ +#define PDSC_ADMINQ_MAX_LENGTH 16 /* must be a power of two */ #define PDSC_NOTIFYQ_LENGTH 64 /* must be a power of two */ #define PDSC_TEARDOWN_RECOVERY false #define PDSC_TEARDOWN_REMOVING true @@ -96,7 +96,7 @@ struct pdsc_q_info { unsigned int bytes; unsigned int nbufs; struct pdsc_buf_info bufs[PDS_CORE_MAX_FRAGS]; - struct pdsc_wait_context *wc; + struct completion completion; void *dest; }; diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c index 44971e71991f..ca23cde385e6 100644 --- a/drivers/net/ethernet/amd/pds_core/devlink.c +++ b/drivers/net/ethernet/amd/pds_core/devlink.c @@ -102,7 +102,7 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req, .fw_control.opcode = PDS_CORE_CMD_FW_CONTROL, .fw_control.oper = PDS_CORE_FW_GET_LIST, }; - struct pds_core_fw_list_info fw_list; + struct pds_core_fw_list_info fw_list = {}; struct pdsc *pdsc = devlink_priv(dl); union pds_core_dev_comp comp; char buf[32]; @@ -115,8 +115,6 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req, if (!err) memcpy_fromio(&fw_list, pdsc->cmd_regs->data, sizeof(fw_list)); mutex_unlock(&pdsc->devcmd_lock); - if (err && err != -EIO) - return err; listlen = min(fw_list.num_fw_slots, ARRAY_SIZE(fw_list.fw_names)); for (i = 0; i < listlen; i++) { diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 2106861463e4..3ee52f4b1166 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -1850,6 +1850,16 @@ static void enetc_xdp_drop(struct enetc_bdr *rx_ring, int rx_ring_first, } } +static void enetc_bulk_flip_buff(struct enetc_bdr *rx_ring, int rx_ring_first, + int rx_ring_last) +{ + while (rx_ring_first != rx_ring_last) { + enetc_flip_rx_buff(rx_ring, + &rx_ring->rx_swbd[rx_ring_first]); + enetc_bdr_idx_inc(rx_ring, &rx_ring_first); + } +} + static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, struct napi_struct *napi, int work_limit, struct bpf_prog *prog) @@ -1868,11 +1878,10 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, while (likely(rx_frm_cnt < work_limit)) { union enetc_rx_bd *rxbd, *orig_rxbd; - int orig_i, orig_cleaned_cnt; struct xdp_buff xdp_buff; struct sk_buff *skb; + int orig_i, err; u32 bd_status; - int err; rxbd = enetc_rxbd(rx_ring, i); bd_status = le32_to_cpu(rxbd->r.lstatus); @@ -1887,7 +1896,6 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, break; orig_rxbd = rxbd; - orig_cleaned_cnt = cleaned_cnt; orig_i = i; enetc_build_xdp_buff(rx_ring, bd_status, &rxbd, &i, @@ -1915,15 +1923,21 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, rx_ring->stats.xdp_drops++; break; case XDP_PASS: - rxbd = orig_rxbd; - cleaned_cnt = orig_cleaned_cnt; - i = orig_i; - - skb = enetc_build_skb(rx_ring, bd_status, &rxbd, - &i, &cleaned_cnt, - ENETC_RXB_DMA_SIZE_XDP); - if (unlikely(!skb)) + skb = xdp_build_skb_from_buff(&xdp_buff); + /* Probably under memory pressure, stop NAPI */ + if (unlikely(!skb)) { + enetc_xdp_drop(rx_ring, orig_i, i); + rx_ring->stats.xdp_drops++; goto out; + } + + enetc_get_offloads(rx_ring, orig_rxbd, skb); + + /* These buffers are about to be owned by the stack. + * Update our buffer cache (the rx_swbd array elements) + * with their other page halves. + */ + enetc_bulk_flip_buff(rx_ring, orig_i, i); napi_gro_receive(napi, skb); break; @@ -1965,11 +1979,7 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring, enetc_xdp_drop(rx_ring, orig_i, i); rx_ring->stats.xdp_redirect_failures++; } else { - while (orig_i != i) { - enetc_flip_rx_buff(rx_ring, - &rx_ring->rx_swbd[orig_i]); - enetc_bdr_idx_inc(rx_ring, &orig_i); - } + enetc_bulk_flip_buff(rx_ring, orig_i, i); xdp_redirect_frm_cnt++; rx_ring->stats.xdp_redirect++; } @@ -3362,7 +3372,8 @@ static int enetc_int_vector_init(struct enetc_ndev_priv *priv, int i, bdr->buffer_offset = ENETC_RXB_PAD; priv->rx_ring[i] = bdr; - err = xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0); + err = __xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0, + ENETC_RXB_DMA_SIZE_XDP); if (err) goto free_vector; diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 0cd1ecacfd29..477b8732b860 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -3997,11 +3997,27 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset) mtk_w32(eth, 0x21021000, MTK_FE_INT_GRP); if (mtk_is_netsys_v3_or_greater(eth)) { - /* PSE should not drop port1, port8 and port9 packets */ - mtk_w32(eth, 0x00000302, PSE_DROP_CFG); + /* PSE dummy page mechanism */ + mtk_w32(eth, PSE_DUMMY_WORK_GDM(1) | PSE_DUMMY_WORK_GDM(2) | + PSE_DUMMY_WORK_GDM(3) | DUMMY_PAGE_THR, PSE_DUMY_REQ); + + /* PSE free buffer drop threshold */ + mtk_w32(eth, 0x00600009, PSE_IQ_REV(8)); + + /* PSE should not drop port8, port9 and port13 packets from + * WDMA Tx + */ + mtk_w32(eth, 0x00002300, PSE_DROP_CFG); + + /* PSE should drop packets to port8, port9 and port13 on WDMA Rx + * ring full + */ + mtk_w32(eth, 0x00002300, PSE_PPE_DROP(0)); + mtk_w32(eth, 0x00002300, PSE_PPE_DROP(1)); + mtk_w32(eth, 0x00002300, PSE_PPE_DROP(2)); /* GDM and CDM Threshold */ - mtk_w32(eth, 0x00000707, MTK_CDMW0_THRES); + mtk_w32(eth, 0x08000707, MTK_CDMW0_THRES); mtk_w32(eth, 0x00000077, MTK_CDMW1_THRES); /* Disable GDM1 RX CRC stripping */ @@ -4018,7 +4034,7 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset) mtk_w32(eth, 0x00000300, PSE_DROP_CFG); /* PSE should drop packets to port 8/9 on WDMA Rx ring full */ - mtk_w32(eth, 0x00000300, PSE_PPE0_DROP); + mtk_w32(eth, 0x00000300, PSE_PPE_DROP(0)); /* PSE Free Queue Flow Control */ mtk_w32(eth, 0x01fa01f4, PSE_FQFC_CFG2); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 8d7b6818d860..0570623e569d 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -151,7 +151,15 @@ #define PSE_FQFC_CFG1 0x100 #define PSE_FQFC_CFG2 0x104 #define PSE_DROP_CFG 0x108 -#define PSE_PPE0_DROP 0x110 +#define PSE_PPE_DROP(x) (0x110 + ((x) * 0x4)) + +/* PSE Last FreeQ Page Request Control */ +#define PSE_DUMY_REQ 0x10C +/* PSE_DUMY_REQ is not a typo but actually called like that also in + * MediaTek's datasheet + */ +#define PSE_DUMMY_WORK_GDM(x) BIT(16 + (x)) +#define DUMMY_PAGE_THR 0x1 /* PSE Input Queue Reservation Register*/ #define PSE_IQ_REV(x) (0x140 + (((x) - 1) << 2)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c index 9f13cea16446..43b2216bc0a2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c @@ -618,10 +618,6 @@ struct mlx5_ttc_table *mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev, bool use_l4_type; int err; - ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL); - if (!ttc) - return ERR_PTR(-ENOMEM); - switch (params->ns_type) { case MLX5_FLOW_NAMESPACE_PORT_SEL: use_l4_type = MLX5_CAP_GEN_2(dev, pcc_ifa2) && @@ -635,7 +631,16 @@ struct mlx5_ttc_table *mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev, return ERR_PTR(-EINVAL); } + ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL); + if (!ttc) + return ERR_PTR(-ENOMEM); + ns = mlx5_get_flow_namespace(dev, params->ns_type); + if (!ns) { + kvfree(ttc); + return ERR_PTR(-EOPNOTSUPP); + } + groups = use_l4_type ? &inner_ttc_groups[TTC_GROUPS_USE_L4_TYPE] : &inner_ttc_groups[TTC_GROUPS_DEFAULT]; @@ -691,10 +696,6 @@ struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev, bool use_l4_type; int err; - ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL); - if (!ttc) - return ERR_PTR(-ENOMEM); - switch (params->ns_type) { case MLX5_FLOW_NAMESPACE_PORT_SEL: use_l4_type = MLX5_CAP_GEN_2(dev, pcc_ifa2) && @@ -708,7 +709,16 @@ struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev, return ERR_PTR(-EINVAL); } + ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL); + if (!ttc) + return ERR_PTR(-ENOMEM); + ns = mlx5_get_flow_namespace(dev, params->ns_type); + if (!ns) { + kvfree(ttc); + return ERR_PTR(-EOPNOTSUPP); + } + groups = use_l4_type ? &ttc_groups[TTC_GROUPS_USE_L4_TYPE] : &ttc_groups[TTC_GROUPS_DEFAULT]; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index 16020b72dec8..ece8588b3b17 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -523,24 +523,6 @@ static int socfpga_dwmac_resume(struct device *dev) dwmac_priv->ops->set_phy_mode(priv->plat->bsp_priv); - /* Before the enet controller is suspended, the phy is suspended. - * This causes the phy clock to be gated. The enet controller is - * resumed before the phy, so the clock is still gated "off" when - * the enet controller is resumed. This code makes sure the phy - * is "resumed" before reinitializing the enet controller since - * the enet controller depends on an active phy clock to complete - * a DMA reset. A DMA reset will "time out" if executed - * with no phy clock input on the Synopsys enet controller. - * Verified through Synopsys Case #8000711656. - * - * Note that the phy clock is also gated when the phy is isolated. - * Phy "suspend" and "isolate" controls are located in phy basic - * control register 0, and can be modified by the phy driver - * framework. - */ - if (ndev->phydev) - phy_resume(ndev->phydev); - return stmmac_resume(dev); } #endif /* CONFIG_PM_SLEEP */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h index 600fea8f712f..2d5bf1de5d2e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h @@ -331,8 +331,8 @@ enum rtc_control { /* PTP and timestamping registers */ -#define GMAC3_X_ATSNS GENMASK(19, 16) -#define GMAC3_X_ATSNS_SHIFT 16 +#define GMAC3_X_ATSNS GENMASK(29, 25) +#define GMAC3_X_ATSNS_SHIFT 25 #define GMAC_PTP_TCR_ATSFC BIT(24) #define GMAC_PTP_TCR_ATSEN0 BIT(25) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index 96bcda0856ec..11c525b8d269 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -560,7 +560,7 @@ void dwmac1000_get_ptptime(void __iomem *ptpaddr, u64 *ptp_time) u64 ns; ns = readl(ptpaddr + GMAC_PTP_ATNR); - ns += readl(ptpaddr + GMAC_PTP_ATSR) * NSEC_PER_SEC; + ns += (u64)readl(ptpaddr + GMAC_PTP_ATSR) * NSEC_PER_SEC; *ptp_time = ns; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index 0f59aa982604..e2840fa241f2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -222,7 +222,7 @@ static void get_ptptime(void __iomem *ptpaddr, u64 *ptp_time) u64 ns; ns = readl(ptpaddr + PTP_ATNR); - ns += readl(ptpaddr + PTP_ATSR) * NSEC_PER_SEC; + ns += (u64)readl(ptpaddr + PTP_ATSR) * NSEC_PER_SEC; *ptp_time = ns; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index b7c3bfdaa180..b9340f8bd182 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -3448,9 +3448,18 @@ static int stmmac_hw_setup(struct net_device *dev, bool ptp_register) if (priv->hw->phylink_pcs) phylink_pcs_pre_init(priv->phylink, priv->hw->phylink_pcs); + /* Note that clk_rx_i must be running for reset to complete. This + * clock may also be required when setting the MAC address. + * + * Block the receive clock stop for LPI mode at the PHY in case + * the link is established with EEE mode active. + */ + phylink_rx_clk_stop_block(priv->phylink); + /* DMA initialization and SW reset */ ret = stmmac_init_dma_engine(priv); if (ret < 0) { + phylink_rx_clk_stop_unblock(priv->phylink); netdev_err(priv->dev, "%s: DMA engine initialization failed\n", __func__); return ret; @@ -3458,6 +3467,7 @@ static int stmmac_hw_setup(struct net_device *dev, bool ptp_register) /* Copy the MAC addr into the HW */ stmmac_set_umac_addr(priv, priv->hw, dev->dev_addr, 0); + phylink_rx_clk_stop_unblock(priv->phylink); /* PS and related bits will be programmed according to the speed */ if (priv->hw->pcs) { @@ -3568,7 +3578,9 @@ static int stmmac_hw_setup(struct net_device *dev, bool ptp_register) /* Start the ball rolling... */ stmmac_start_all_dma(priv); + phylink_rx_clk_stop_block(priv->phylink); stmmac_set_hw_vlan_mode(priv, priv->hw); + phylink_rx_clk_stop_unblock(priv->phylink); return 0; } @@ -5853,6 +5865,9 @@ static void stmmac_tx_timeout(struct net_device *dev, unsigned int txqueue) * whenever multicast addresses must be enabled/disabled. * Return value: * void. + * + * FIXME: This may need RXC to be running, but it may be called with BH + * disabled, which means we can't call phylink_rx_clk_stop*(). */ static void stmmac_set_rx_mode(struct net_device *dev) { @@ -5985,7 +6000,9 @@ static int stmmac_set_features(struct net_device *netdev, else priv->hw->hw_vlan_en = false; + phylink_rx_clk_stop_block(priv->phylink); stmmac_set_hw_vlan_mode(priv, priv->hw); + phylink_rx_clk_stop_unblock(priv->phylink); return 0; } @@ -6269,7 +6286,9 @@ static int stmmac_set_mac_address(struct net_device *ndev, void *addr) if (ret) goto set_mac_error; + phylink_rx_clk_stop_block(priv->phylink); stmmac_set_umac_addr(priv, priv->hw, ndev->dev_addr, 0); + phylink_rx_clk_stop_unblock(priv->phylink); set_mac_error: pm_runtime_put(priv->device); @@ -6625,6 +6644,9 @@ static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double) return stmmac_update_vlan_hash(priv, priv->hw, hash, pmatch, is_double); } +/* FIXME: This may need RXC to be running, but it may be called with BH + * disabled, which means we can't call phylink_rx_clk_stop*(). + */ static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid) { struct stmmac_priv *priv = netdev_priv(ndev); @@ -6656,6 +6678,9 @@ err_pm_put: return ret; } +/* FIXME: This may need RXC to be running, but it may be called with BH + * disabled, which means we can't call phylink_rx_clk_stop*(). + */ static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid) { struct stmmac_priv *priv = netdev_priv(ndev); @@ -7813,13 +7838,11 @@ int stmmac_suspend(struct device *dev) mutex_unlock(&priv->lock); rtnl_lock(); - if (device_may_wakeup(priv->device) && priv->plat->pmt) { - phylink_suspend(priv->phylink, true); - } else { - if (device_may_wakeup(priv->device)) - phylink_speed_down(priv->phylink, false); - phylink_suspend(priv->phylink, false); - } + if (device_may_wakeup(priv->device) && !priv->plat->pmt) + phylink_speed_down(priv->phylink, false); + + phylink_suspend(priv->phylink, + device_may_wakeup(priv->device) && priv->plat->pmt); rtnl_unlock(); if (stmmac_fpe_supported(priv)) @@ -7909,16 +7932,12 @@ int stmmac_resume(struct device *dev) } rtnl_lock(); - if (device_may_wakeup(priv->device) && priv->plat->pmt) { - phylink_resume(priv->phylink); - } else { - phylink_resume(priv->phylink); - if (device_may_wakeup(priv->device)) - phylink_speed_up(priv->phylink); - } - rtnl_unlock(); - rtnl_lock(); + /* Prepare the PHY to resume, ensuring that its clocks which are + * necessary for the MAC DMA reset to complete are running + */ + phylink_prepare_resume(priv->phylink); + mutex_lock(&priv->lock); stmmac_reset_queues_param(priv); @@ -7928,14 +7947,25 @@ int stmmac_resume(struct device *dev) stmmac_hw_setup(ndev, false); stmmac_init_coalesce(priv); + phylink_rx_clk_stop_block(priv->phylink); stmmac_set_rx_mode(ndev); stmmac_restore_hw_vlan_rx_fltr(priv, ndev, priv->hw); + phylink_rx_clk_stop_unblock(priv->phylink); stmmac_enable_all_queues(priv); stmmac_enable_all_dma_irq(priv); mutex_unlock(&priv->lock); + + /* phylink_resume() must be called after the hardware has been + * initialised because it may bring the link up immediately in a + * workqueue thread, which will race with initialisation. + */ + phylink_resume(priv->phylink); + if (device_may_wakeup(priv->device) && !priv->plat->pmt) + phylink_speed_up(priv->phylink); + rtnl_unlock(); netif_device_attach(ndev); diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 72177fea1cfb..edc3165f0077 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -9064,6 +9064,8 @@ static void niu_try_msix(struct niu *np, u8 *ldg_num_map) msi_vec[i].entry = i; } + pdev->dev_flags |= PCI_DEV_FLAGS_MSIX_TOUCH_ENTRY_DATA_FIRST; + num_irqs = pci_enable_msix_range(pdev, msi_vec, 1, num_irqs); if (num_irqs < 0) { np->flags &= ~NIU_FLAGS_MSIX; diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c index 6599feca1967..e32013eb0186 100644 --- a/drivers/net/phy/dp83822.c +++ b/drivers/net/phy/dp83822.c @@ -31,6 +31,7 @@ #define MII_DP83822_RCSR 0x17 #define MII_DP83822_RESET_CTRL 0x1f #define MII_DP83822_MLEDCR 0x25 +#define MII_DP83822_LDCTRL 0x403 #define MII_DP83822_LEDCFG1 0x460 #define MII_DP83822_IOCTRL1 0x462 #define MII_DP83822_IOCTRL2 0x463 @@ -123,6 +124,9 @@ #define DP83822_IOCTRL1_GPIO1_CTRL GENMASK(2, 0) #define DP83822_IOCTRL1_GPIO1_CTRL_LED_1 BIT(0) +/* LDCTRL bits */ +#define DP83822_100BASE_TX_LINE_DRIVER_SWING GENMASK(7, 4) + /* IOCTRL2 bits */ #define DP83822_IOCTRL2_GPIO2_CLK_SRC GENMASK(6, 4) #define DP83822_IOCTRL2_GPIO2_CTRL GENMASK(2, 0) @@ -197,6 +201,7 @@ struct dp83822_private { bool set_gpio2_clk_out; u32 gpio2_clk_out; bool led_pin_enable[DP83822_MAX_LED_PINS]; + int tx_amplitude_100base_tx_index; }; static int dp83822_config_wol(struct phy_device *phydev, @@ -522,6 +527,12 @@ static int dp83822_config_init(struct phy_device *phydev) FIELD_PREP(DP83822_IOCTRL2_GPIO2_CLK_SRC, dp83822->gpio2_clk_out)); + if (dp83822->tx_amplitude_100base_tx_index >= 0) + phy_modify_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_LDCTRL, + DP83822_100BASE_TX_LINE_DRIVER_SWING, + FIELD_PREP(DP83822_100BASE_TX_LINE_DRIVER_SWING, + dp83822->tx_amplitude_100base_tx_index)); + err = dp83822_config_init_leds(phydev); if (err) return err; @@ -719,7 +730,12 @@ static int dp83822_phy_reset(struct phy_device *phydev) return phydev->drv->config_init(phydev); } -#ifdef CONFIG_OF_MDIO +#if IS_ENABLED(CONFIG_OF_MDIO) +static const u32 tx_amplitude_100base_tx_gain[] = { + 80, 82, 83, 85, 87, 88, 90, 92, + 93, 95, 97, 98, 100, 102, 103, 105, +}; + static int dp83822_of_init_leds(struct phy_device *phydev) { struct device_node *node = phydev->mdio.dev.of_node; @@ -780,6 +796,8 @@ static int dp83822_of_init(struct phy_device *phydev) struct dp83822_private *dp83822 = phydev->priv; struct device *dev = &phydev->mdio.dev; const char *of_val; + int i, ret; + u32 val; /* Signal detection for the PHY is only enabled if the FX_EN and the * SD_EN pins are strapped. Signal detection can only enabled if FX_EN @@ -815,6 +833,25 @@ static int dp83822_of_init(struct phy_device *phydev) dp83822->set_gpio2_clk_out = true; } + ret = phy_get_tx_amplitude_gain(phydev, dev, + ETHTOOL_LINK_MODE_100baseT_Full_BIT, + &val); + if (!ret) { + for (i = 0; i < ARRAY_SIZE(tx_amplitude_100base_tx_gain); i++) { + if (tx_amplitude_100base_tx_gain[i] == val) { + dp83822->tx_amplitude_100base_tx_index = i; + break; + } + } + + if (dp83822->tx_amplitude_100base_tx_index < 0) { + phydev_err(phydev, + "Invalid value for tx-amplitude-100base-tx-percent property (%u)\n", + val); + return -EINVAL; + } + } + return dp83822_of_init_leds(phydev); } @@ -893,6 +930,7 @@ static int dp8382x_probe(struct phy_device *phydev) if (!dp83822) return -ENOMEM; + dp83822->tx_amplitude_100base_tx_index = -1; phydev->priv = dp83822; return 0; diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c index 0e17cc458efd..93de88c1c8fd 100644 --- a/drivers/net/phy/microchip.c +++ b/drivers/net/phy/microchip.c @@ -37,47 +37,6 @@ static int lan88xx_write_page(struct phy_device *phydev, int page) return __phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, page); } -static int lan88xx_phy_config_intr(struct phy_device *phydev) -{ - int rc; - - if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { - /* unmask all source and clear them before enable */ - rc = phy_write(phydev, LAN88XX_INT_MASK, 0x7FFF); - rc = phy_read(phydev, LAN88XX_INT_STS); - rc = phy_write(phydev, LAN88XX_INT_MASK, - LAN88XX_INT_MASK_MDINTPIN_EN_ | - LAN88XX_INT_MASK_LINK_CHANGE_); - } else { - rc = phy_write(phydev, LAN88XX_INT_MASK, 0); - if (rc) - return rc; - - /* Ack interrupts after they have been disabled */ - rc = phy_read(phydev, LAN88XX_INT_STS); - } - - return rc < 0 ? rc : 0; -} - -static irqreturn_t lan88xx_handle_interrupt(struct phy_device *phydev) -{ - int irq_status; - - irq_status = phy_read(phydev, LAN88XX_INT_STS); - if (irq_status < 0) { - phy_error(phydev); - return IRQ_NONE; - } - - if (!(irq_status & LAN88XX_INT_STS_LINK_CHANGE_)) - return IRQ_NONE; - - phy_trigger_machine(phydev); - - return IRQ_HANDLED; -} - static int lan88xx_suspend(struct phy_device *phydev) { struct lan88xx_priv *priv = phydev->priv; @@ -528,8 +487,9 @@ static struct phy_driver microchip_phy_driver[] = { .config_aneg = lan88xx_config_aneg, .link_change_notify = lan88xx_link_change_notify, - .config_intr = lan88xx_phy_config_intr, - .handle_interrupt = lan88xx_handle_interrupt, + /* Interrupt handling is broken, do not define related + * functions to force polling. + */ .suspend = lan88xx_suspend, .resume = genphy_resume, diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 92161af788af..2a01887c5617 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -3123,19 +3123,12 @@ void phy_get_pause(struct phy_device *phydev, bool *tx_pause, bool *rx_pause) EXPORT_SYMBOL(phy_get_pause); #if IS_ENABLED(CONFIG_OF_MDIO) -static int phy_get_int_delay_property(struct device *dev, const char *name) +static int phy_get_u32_property(struct device *dev, const char *name, u32 *val) { - s32 int_delay; - int ret; - - ret = device_property_read_u32(dev, name, &int_delay); - if (ret) - return ret; - - return int_delay; + return device_property_read_u32(dev, name, val); } #else -static int phy_get_int_delay_property(struct device *dev, const char *name) +static int phy_get_u32_property(struct device *dev, const char *name, u32 *val) { return -EINVAL; } @@ -3160,12 +3153,12 @@ static int phy_get_int_delay_property(struct device *dev, const char *name) s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev, const int *delay_values, int size, bool is_rx) { - s32 delay; - int i; + int i, ret; + u32 delay; if (is_rx) { - delay = phy_get_int_delay_property(dev, "rx-internal-delay-ps"); - if (delay < 0 && size == 0) { + ret = phy_get_u32_property(dev, "rx-internal-delay-ps", &delay); + if (ret < 0 && size == 0) { if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID || phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) return 1; @@ -3174,8 +3167,8 @@ s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev, } } else { - delay = phy_get_int_delay_property(dev, "tx-internal-delay-ps"); - if (delay < 0 && size == 0) { + ret = phy_get_u32_property(dev, "tx-internal-delay-ps", &delay); + if (ret < 0 && size == 0) { if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID || phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID) return 1; @@ -3184,8 +3177,8 @@ s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev, } } - if (delay < 0) - return delay; + if (ret < 0) + return ret; if (size == 0) return delay; @@ -3220,6 +3213,30 @@ s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev, } EXPORT_SYMBOL(phy_get_internal_delay); +/** + * phy_get_tx_amplitude_gain - stores tx amplitude gain in @val + * @phydev: phy_device struct + * @dev: pointer to the devices device struct + * @linkmode: linkmode for which the tx amplitude gain should be retrieved + * @val: tx amplitude gain + * + * Returns: 0 on success, < 0 on failure + */ +int phy_get_tx_amplitude_gain(struct phy_device *phydev, struct device *dev, + enum ethtool_link_mode_bit_indices linkmode, + u32 *val) +{ + switch (linkmode) { + case ETHTOOL_LINK_MODE_100baseT_Full_BIT: + return phy_get_u32_property(dev, + "tx-amplitude-100base-tx-percent", + val); + default: + return -EINVAL; + } +} +EXPORT_SYMBOL_GPL(phy_get_tx_amplitude_gain); + static int phy_led_set_brightness(struct led_classdev *led_cdev, enum led_brightness value) { diff --git a/drivers/net/phy/phy_led_triggers.c b/drivers/net/phy/phy_led_triggers.c index f550576eb9da..6f9d8da76c4d 100644 --- a/drivers/net/phy/phy_led_triggers.c +++ b/drivers/net/phy/phy_led_triggers.c @@ -91,9 +91,8 @@ int phy_led_triggers_register(struct phy_device *phy) if (!phy->phy_num_led_triggers) return 0; - phy->led_link_trigger = devm_kzalloc(&phy->mdio.dev, - sizeof(*phy->led_link_trigger), - GFP_KERNEL); + phy->led_link_trigger = kzalloc(sizeof(*phy->led_link_trigger), + GFP_KERNEL); if (!phy->led_link_trigger) { err = -ENOMEM; goto out_clear; @@ -103,10 +102,9 @@ int phy_led_triggers_register(struct phy_device *phy) if (err) goto out_free_link; - phy->phy_led_triggers = devm_kcalloc(&phy->mdio.dev, - phy->phy_num_led_triggers, - sizeof(struct phy_led_trigger), - GFP_KERNEL); + phy->phy_led_triggers = kcalloc(phy->phy_num_led_triggers, + sizeof(struct phy_led_trigger), + GFP_KERNEL); if (!phy->phy_led_triggers) { err = -ENOMEM; goto out_unreg_link; @@ -127,11 +125,11 @@ int phy_led_triggers_register(struct phy_device *phy) out_unreg: while (i--) phy_led_trigger_unregister(&phy->phy_led_triggers[i]); - devm_kfree(&phy->mdio.dev, phy->phy_led_triggers); + kfree(phy->phy_led_triggers); out_unreg_link: phy_led_trigger_unregister(phy->led_link_trigger); out_free_link: - devm_kfree(&phy->mdio.dev, phy->led_link_trigger); + kfree(phy->led_link_trigger); phy->led_link_trigger = NULL; out_clear: phy->phy_num_led_triggers = 0; @@ -145,8 +143,13 @@ void phy_led_triggers_unregister(struct phy_device *phy) for (i = 0; i < phy->phy_num_led_triggers; i++) phy_led_trigger_unregister(&phy->phy_led_triggers[i]); + kfree(phy->phy_led_triggers); + phy->phy_led_triggers = NULL; - if (phy->led_link_trigger) + if (phy->led_link_trigger) { phy_led_trigger_unregister(phy->led_link_trigger); + kfree(phy->led_link_trigger); + phy->led_link_trigger = NULL; + } } EXPORT_SYMBOL_GPL(phy_led_triggers_unregister); diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index b00a315de060..5be48eb810ab 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -82,12 +82,15 @@ struct phylink { unsigned int pcs_state; bool link_failed; + bool suspend_link_up; + bool major_config_failed; bool mac_supports_eee_ops; bool mac_supports_eee; bool phy_enable_tx_lpi; bool mac_enable_tx_lpi; bool mac_tx_clk_stop; u32 mac_tx_lpi_timer; + u8 mac_rx_clk_stop_blocked; struct sfp_bus *sfp_bus; bool sfp_may_have_phy; @@ -1360,12 +1363,16 @@ static void phylink_major_config(struct phylink *pl, bool restart, phylink_an_mode_str(pl->req_link_an_mode), phy_modes(state->interface)); + pl->major_config_failed = false; + if (pl->mac_ops->mac_select_pcs) { pcs = pl->mac_ops->mac_select_pcs(pl->config, state->interface); if (IS_ERR(pcs)) { phylink_err(pl, "mac_select_pcs unexpectedly failed: %pe\n", pcs); + + pl->major_config_failed = true; return; } @@ -1387,6 +1394,7 @@ static void phylink_major_config(struct phylink *pl, bool restart, if (err < 0) { phylink_err(pl, "mac_prepare failed: %pe\n", ERR_PTR(err)); + pl->major_config_failed = true; return; } } @@ -1410,8 +1418,15 @@ static void phylink_major_config(struct phylink *pl, bool restart, phylink_mac_config(pl, state); - if (pl->pcs) - phylink_pcs_post_config(pl->pcs, state->interface); + if (pl->pcs) { + err = phylink_pcs_post_config(pl->pcs, state->interface); + if (err < 0) { + phylink_err(pl, "pcs_post_config failed: %pe\n", + ERR_PTR(err)); + + pl->major_config_failed = true; + } + } if (pl->pcs_state == PCS_STATE_STARTING || pcs_changed) phylink_pcs_enable(pl->pcs); @@ -1422,11 +1437,12 @@ static void phylink_major_config(struct phylink *pl, bool restart, err = phylink_pcs_config(pl->pcs, neg_mode, state, !!(pl->link_config.pause & MLO_PAUSE_AN)); - if (err < 0) - phylink_err(pl, "pcs_config failed: %pe\n", - ERR_PTR(err)); - else if (err > 0) + if (err < 0) { + phylink_err(pl, "pcs_config failed: %pe\n", ERR_PTR(err)); + pl->major_config_failed = true; + } else if (err > 0) { restart = true; + } if (restart) phylink_pcs_an_restart(pl); @@ -1434,16 +1450,22 @@ static void phylink_major_config(struct phylink *pl, bool restart, if (pl->mac_ops->mac_finish) { err = pl->mac_ops->mac_finish(pl->config, pl->act_link_an_mode, state->interface); - if (err < 0) + if (err < 0) { phylink_err(pl, "mac_finish failed: %pe\n", ERR_PTR(err)); + + pl->major_config_failed = true; + } } if (pl->phydev && pl->phy_ib_mode) { err = phy_config_inband(pl->phydev, pl->phy_ib_mode); - if (err < 0) + if (err < 0) { phylink_err(pl, "phy_config_inband: %pe\n", ERR_PTR(err)); + + pl->major_config_failed = true; + } } if (pl->sfp_bus) { @@ -1795,6 +1817,12 @@ static void phylink_resolve(struct work_struct *w) } } + /* If configuration of the interface failed, force the link down + * until we get a successful configuration. + */ + if (pl->major_config_failed) + link_state.link = false; + if (link_state.link != cur_link_state) { pl->old_link_state = link_state.link; if (!link_state.link) @@ -2595,6 +2623,64 @@ void phylink_stop(struct phylink *pl) EXPORT_SYMBOL_GPL(phylink_stop); /** + * phylink_rx_clk_stop_block() - block PHY ability to stop receive clock in LPI + * @pl: a pointer to a &struct phylink returned from phylink_create() + * + * Disable the PHY's ability to stop the receive clock while the receive path + * is in EEE LPI state, until the number of calls to phylink_rx_clk_stop_block() + * are balanced by calls to phylink_rx_clk_stop_unblock(). + */ +void phylink_rx_clk_stop_block(struct phylink *pl) +{ + ASSERT_RTNL(); + + if (pl->mac_rx_clk_stop_blocked == U8_MAX) { + phylink_warn(pl, "%s called too many times - ignoring\n", + __func__); + dump_stack(); + return; + } + + /* Disable PHY receive clock stop if this is the first time this + * function has been called and clock-stop was previously enabled. + */ + if (pl->mac_rx_clk_stop_blocked++ == 0 && + pl->mac_supports_eee_ops && pl->phydev && + pl->config->eee_rx_clk_stop_enable) + phy_eee_rx_clock_stop(pl->phydev, false); +} +EXPORT_SYMBOL_GPL(phylink_rx_clk_stop_block); + +/** + * phylink_rx_clk_stop_unblock() - unblock PHY ability to stop receive clock + * @pl: a pointer to a &struct phylink returned from phylink_create() + * + * All calls to phylink_rx_clk_stop_block() must be balanced with a + * corresponding call to phylink_rx_clk_stop_unblock() to restore the PHYs + * ability to stop the receive clock when the receive path is in EEE LPI mode. + */ +void phylink_rx_clk_stop_unblock(struct phylink *pl) +{ + ASSERT_RTNL(); + + if (pl->mac_rx_clk_stop_blocked == 0) { + phylink_warn(pl, "%s called too many times - ignoring\n", + __func__); + dump_stack(); + return; + } + + /* Re-enable PHY receive clock stop if the number of unblocks matches + * the number of calls to the block function above. + */ + if (--pl->mac_rx_clk_stop_blocked == 0 && + pl->mac_supports_eee_ops && pl->phydev && + pl->config->eee_rx_clk_stop_enable) + phy_eee_rx_clock_stop(pl->phydev, true); +} +EXPORT_SYMBOL_GPL(phylink_rx_clk_stop_unblock); + +/** * phylink_suspend() - handle a network device suspend event * @pl: a pointer to a &struct phylink returned from phylink_create() * @mac_wol: true if the MAC needs to receive packets for Wake-on-Lan @@ -2619,14 +2705,16 @@ void phylink_suspend(struct phylink *pl, bool mac_wol) /* Stop the resolver bringing the link up */ __set_bit(PHYLINK_DISABLE_MAC_WOL, &pl->phylink_disable_state); - /* Disable the carrier, to prevent transmit timeouts, - * but one would hope all packets have been sent. This - * also means phylink_resolve() will do nothing. - */ - if (pl->netdev) - netif_carrier_off(pl->netdev); - else + pl->suspend_link_up = phylink_link_is_up(pl); + if (pl->suspend_link_up) { + /* Disable the carrier, to prevent transmit timeouts, + * but one would hope all packets have been sent. This + * also means phylink_resolve() will do nothing. + */ + if (pl->netdev) + netif_carrier_off(pl->netdev); pl->old_link_state = false; + } /* We do not call mac_link_down() here as we want the * link to remain up to receive the WoL packets. @@ -2639,6 +2727,31 @@ void phylink_suspend(struct phylink *pl, bool mac_wol) EXPORT_SYMBOL_GPL(phylink_suspend); /** + * phylink_prepare_resume() - prepare to resume a network device + * @pl: a pointer to a &struct phylink returned from phylink_create() + * + * Optional, but if called must be called prior to phylink_resume(). + * + * Prepare to resume a network device, preparing the PHY as necessary. + */ +void phylink_prepare_resume(struct phylink *pl) +{ + struct phy_device *phydev = pl->phydev; + + ASSERT_RTNL(); + + /* IEEE 802.3 22.2.4.1.5 allows PHYs to stop their receive clock + * when PDOWN is set. However, some MACs require RXC to be running + * in order to resume. If the MAC requires RXC, and we have a PHY, + * then resume the PHY. Note that 802.3 allows PHYs 500ms before + * the clock meets requirements. We do not implement this delay. + */ + if (pl->config->mac_requires_rxc && phydev && phydev->suspended) + phy_resume(phydev); +} +EXPORT_SYMBOL_GPL(phylink_prepare_resume); + +/** * phylink_resume() - handle a network device resume event * @pl: a pointer to a &struct phylink returned from phylink_create() * @@ -2652,15 +2765,18 @@ void phylink_resume(struct phylink *pl) if (test_bit(PHYLINK_DISABLE_MAC_WOL, &pl->phylink_disable_state)) { /* Wake-on-Lan enabled, MAC handling */ - /* Call mac_link_down() so we keep the overall state balanced. - * Do this under the state_mutex lock for consistency. This - * will cause a "Link Down" message to be printed during - * resume, which is harmless - the true link state will be - * printed when we run a resolve. - */ - mutex_lock(&pl->state_mutex); - phylink_link_down(pl); - mutex_unlock(&pl->state_mutex); + if (pl->suspend_link_up) { + /* Call mac_link_down() so we keep the overall state + * balanced. Do this under the state_mutex lock for + * consistency. This will cause a "Link Down" message + * to be printed during resume, which is harmless - + * the true link state will be printed when we run a + * resolve. + */ + mutex_lock(&pl->state_mutex); + phylink_link_down(pl); + mutex_unlock(&pl->state_mutex); + } /* Re-apply the link parameters so that all the settings get * restored to the MAC. diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index d1ed544ba03a..3e4896d9537e 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -2789,7 +2789,8 @@ static void skb_recv_done(struct virtqueue *rvq) virtqueue_napi_schedule(&rq->napi, rvq); } -static void virtnet_napi_enable(struct virtqueue *vq, struct napi_struct *napi) +static void virtnet_napi_do_enable(struct virtqueue *vq, + struct napi_struct *napi) { napi_enable(napi); @@ -2802,10 +2803,16 @@ static void virtnet_napi_enable(struct virtqueue *vq, struct napi_struct *napi) local_bh_enable(); } -static void virtnet_napi_tx_enable(struct virtnet_info *vi, - struct virtqueue *vq, - struct napi_struct *napi) +static void virtnet_napi_enable(struct receive_queue *rq) { + virtnet_napi_do_enable(rq->vq, &rq->napi); +} + +static void virtnet_napi_tx_enable(struct send_queue *sq) +{ + struct virtnet_info *vi = sq->vq->vdev->priv; + struct napi_struct *napi = &sq->napi; + if (!napi->weight) return; @@ -2817,15 +2824,24 @@ static void virtnet_napi_tx_enable(struct virtnet_info *vi, return; } - return virtnet_napi_enable(vq, napi); + virtnet_napi_do_enable(sq->vq, napi); } -static void virtnet_napi_tx_disable(struct napi_struct *napi) +static void virtnet_napi_tx_disable(struct send_queue *sq) { + struct napi_struct *napi = &sq->napi; + if (napi->weight) napi_disable(napi); } +static void virtnet_napi_disable(struct receive_queue *rq) +{ + struct napi_struct *napi = &rq->napi; + + napi_disable(napi); +} + static void refill_work(struct work_struct *work) { struct virtnet_info *vi = @@ -2836,9 +2852,9 @@ static void refill_work(struct work_struct *work) for (i = 0; i < vi->curr_queue_pairs; i++) { struct receive_queue *rq = &vi->rq[i]; - napi_disable(&rq->napi); + virtnet_napi_disable(rq); still_empty = !try_fill_recv(vi, rq, GFP_KERNEL); - virtnet_napi_enable(rq->vq, &rq->napi); + virtnet_napi_enable(rq); /* In theory, this can happen: if we don't get any buffers in * we will *never* try to fill again. @@ -3035,8 +3051,8 @@ static int virtnet_poll(struct napi_struct *napi, int budget) static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index) { - virtnet_napi_tx_disable(&vi->sq[qp_index].napi); - napi_disable(&vi->rq[qp_index].napi); + virtnet_napi_tx_disable(&vi->sq[qp_index]); + virtnet_napi_disable(&vi->rq[qp_index]); xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq); } @@ -3055,8 +3071,8 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index) if (err < 0) goto err_xdp_reg_mem_model; - virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi); - virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi); + virtnet_napi_enable(&vi->rq[qp_index]); + virtnet_napi_tx_enable(&vi->sq[qp_index]); return 0; @@ -3302,25 +3318,72 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_OK; } -static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq) +static void __virtnet_rx_pause(struct virtnet_info *vi, + struct receive_queue *rq) { bool running = netif_running(vi->dev); if (running) { - napi_disable(&rq->napi); + virtnet_napi_disable(rq); virtnet_cancel_dim(vi, &rq->dim); } } -static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq) +static void virtnet_rx_pause_all(struct virtnet_info *vi) +{ + int i; + + /* + * Make sure refill_work does not run concurrently to + * avoid napi_disable race which leads to deadlock. + */ + disable_delayed_refill(vi); + cancel_delayed_work_sync(&vi->refill); + for (i = 0; i < vi->max_queue_pairs; i++) + __virtnet_rx_pause(vi, &vi->rq[i]); +} + +static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq) +{ + /* + * Make sure refill_work does not run concurrently to + * avoid napi_disable race which leads to deadlock. + */ + disable_delayed_refill(vi); + cancel_delayed_work_sync(&vi->refill); + __virtnet_rx_pause(vi, rq); +} + +static void __virtnet_rx_resume(struct virtnet_info *vi, + struct receive_queue *rq, + bool refill) { bool running = netif_running(vi->dev); - if (!try_fill_recv(vi, rq, GFP_KERNEL)) + if (refill && !try_fill_recv(vi, rq, GFP_KERNEL)) schedule_delayed_work(&vi->refill, 0); if (running) - virtnet_napi_enable(rq->vq, &rq->napi); + virtnet_napi_enable(rq); +} + +static void virtnet_rx_resume_all(struct virtnet_info *vi) +{ + int i; + + enable_delayed_refill(vi); + for (i = 0; i < vi->max_queue_pairs; i++) { + if (i < vi->curr_queue_pairs) + __virtnet_rx_resume(vi, &vi->rq[i], true); + else + __virtnet_rx_resume(vi, &vi->rq[i], false); + } +} + +static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq) +{ + enable_delayed_refill(vi); + __virtnet_rx_resume(vi, rq, true); } static int virtnet_rx_resize(struct virtnet_info *vi, @@ -3349,7 +3412,7 @@ static void virtnet_tx_pause(struct virtnet_info *vi, struct send_queue *sq) qindex = sq - vi->sq; if (running) - virtnet_napi_tx_disable(&sq->napi); + virtnet_napi_tx_disable(sq); txq = netdev_get_tx_queue(vi->dev, qindex); @@ -3383,7 +3446,7 @@ static void virtnet_tx_resume(struct virtnet_info *vi, struct send_queue *sq) __netif_tx_unlock_bh(txq); if (running) - virtnet_napi_tx_enable(vi, sq->vq, &sq->napi); + virtnet_napi_tx_enable(sq); } static int virtnet_tx_resize(struct virtnet_info *vi, struct send_queue *sq, @@ -5923,12 +5986,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, if (prog) bpf_prog_add(prog, vi->max_queue_pairs - 1); + virtnet_rx_pause_all(vi); + /* Make sure NAPI is not using any XDP TX queues for RX. */ if (netif_running(dev)) { - for (i = 0; i < vi->max_queue_pairs; i++) { - napi_disable(&vi->rq[i].napi); - virtnet_napi_tx_disable(&vi->sq[i].napi); - } + for (i = 0; i < vi->max_queue_pairs; i++) + virtnet_napi_tx_disable(&vi->sq[i]); } if (!prog) { @@ -5960,14 +6023,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog, vi->xdp_enabled = false; } + virtnet_rx_resume_all(vi); for (i = 0; i < vi->max_queue_pairs; i++) { if (old_prog) bpf_prog_put(old_prog); - if (netif_running(dev)) { - virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); - virtnet_napi_tx_enable(vi, vi->sq[i].vq, - &vi->sq[i].napi); - } + if (netif_running(dev)) + virtnet_napi_tx_enable(&vi->sq[i]); } return 0; @@ -5979,12 +6040,10 @@ err: rcu_assign_pointer(vi->rq[i].xdp_prog, old_prog); } + virtnet_rx_resume_all(vi); if (netif_running(dev)) { - for (i = 0; i < vi->max_queue_pairs; i++) { - virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); - virtnet_napi_tx_enable(vi, vi->sq[i].vq, - &vi->sq[i].napi); - } + for (i = 0; i < vi->max_queue_pairs; i++) + virtnet_napi_tx_enable(&vi->sq[i]); } if (prog) bpf_prog_sub(prog, vi->max_queue_pairs - 1); diff --git a/drivers/net/vmxnet3/vmxnet3_xdp.c b/drivers/net/vmxnet3/vmxnet3_xdp.c index 616ecc38d172..5f470499e600 100644 --- a/drivers/net/vmxnet3/vmxnet3_xdp.c +++ b/drivers/net/vmxnet3/vmxnet3_xdp.c @@ -397,7 +397,7 @@ vmxnet3_process_xdp(struct vmxnet3_adapter *adapter, xdp_init_buff(&xdp, PAGE_SIZE, &rq->xdp_rxq); xdp_prepare_buff(&xdp, page_address(page), rq->page_pool->p.offset, - rbi->len, false); + rcd->len, false); xdp_buff_clear_frags_flag(&xdp); xdp_prog = rcu_dereference(rq->adapter->xdp_bpf_prog); diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 63fe51d0e64d..809b407cece1 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -985,20 +985,27 @@ static u32 xennet_run_xdp(struct netfront_queue *queue, struct page *pdata, act = bpf_prog_run_xdp(prog, xdp); switch (act) { case XDP_TX: - get_page(pdata); xdpf = xdp_convert_buff_to_frame(xdp); + if (unlikely(!xdpf)) { + trace_xdp_exception(queue->info->netdev, prog, act); + break; + } + get_page(pdata); err = xennet_xdp_xmit(queue->info->netdev, 1, &xdpf, 0); - if (unlikely(!err)) + if (unlikely(err <= 0)) { + if (err < 0) + trace_xdp_exception(queue->info->netdev, prog, act); xdp_return_frame_rx_napi(xdpf); - else if (unlikely(err < 0)) - trace_xdp_exception(queue->info->netdev, prog, act); + } break; case XDP_REDIRECT: get_page(pdata); err = xdp_do_redirect(queue->info->netdev, xdp, prog); *need_xdp_flush = true; - if (unlikely(err)) + if (unlikely(err)) { trace_xdp_exception(queue->info->netdev, prog, act); + xdp_return_buff(xdp); + } break; case XDP_PASS: case XDP_DROP: |