diff options
Diffstat (limited to 'drivers/net/ethernet/intel')
68 files changed, 3038 insertions, 1654 deletions
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index 24ec9a4f1ffa..1640d2f27833 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -264,6 +264,7 @@ config I40EVF tristate "Intel(R) Ethernet Adaptive Virtual Function support" select IAVF depends on PCI_MSI + depends on PTP_1588_CLOCK_OPTIONAL help This driver supports virtual functions for Intel XL710, X710, X722, XXV710, and all devices advertising support for @@ -336,7 +337,7 @@ config ICE_SWITCHDEV config ICE_HWTS bool "Support HW cross-timestamp on platforms with PTM support" default y - depends on ICE && X86 + depends on ICE && X86 && PCIE_PTM help Say Y to enable hardware supported cross-timestamping on platforms with PCIe PTM support. The cross-timestamp is available through diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c index d7df2a0ed629..44249dd91bd6 100644 --- a/drivers/net/ethernet/intel/e1000e/mac.c +++ b/drivers/net/ethernet/intel/e1000e/mac.c @@ -331,8 +331,21 @@ void e1000e_update_mc_addr_list_generic(struct e1000_hw *hw, } /* replace the entire MTA table */ - for (i = hw->mac.mta_reg_count - 1; i >= 0; i--) + for (i = hw->mac.mta_reg_count - 1; i >= 0; i--) { E1000_WRITE_REG_ARRAY(hw, E1000_MTA, i, hw->mac.mta_shadow[i]); + + if (IS_ENABLED(CONFIG_PREEMPT_RT)) { + /* + * Do not queue up too many posted writes to prevent + * increased latency for other devices on the + * interconnect. Flush after each 8th posted write, + * to keep additional execution time low while still + * preventing increased latency. + */ + if (!(i % 8) && i) + e1e_flush(); + } + } e1e_flush(); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index e28f1905a4a0..9f47388eaba5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -2,6 +2,7 @@ /* Copyright(c) 2018 Intel Corporation. */ #include <linux/bpf_trace.h> +#include <linux/unroll.h> #include <net/xdp_sock_drv.h> #include "i40e_txrx_common.h" #include "i40e_xsk.h" @@ -529,7 +530,8 @@ static void i40e_xmit_pkt_batch(struct i40e_ring *xdp_ring, struct xdp_desc *des dma_addr_t dma; u32 i; - loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) { + unrolled_count(PKTS_PER_BATCH) + for (i = 0; i < PKTS_PER_BATCH; i++) { u32 cmd = I40E_TX_DESC_CMD_ICRC | xsk_is_eop_desc(&desc[i]); dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc[i].addr); diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h index ef156fad52f2..dd16351a7af8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h @@ -6,7 +6,7 @@ #include <linux/types.h> -/* This value should match the pragma in the loop_unrolled_for +/* This value should match the pragma in the unrolled_count() * macro. Why 4? It is strictly empirical. It seems to be a good * compromise between the advantage of having simultaneous outstanding * reads to the DMA array that can hide each others latency and the @@ -14,14 +14,6 @@ */ #define PKTS_PER_BATCH 4 -#ifdef __clang__ -#define loop_unrolled_for _Pragma("clang loop unroll_count(4)") for -#elif __GNUC__ >= 8 -#define loop_unrolled_for _Pragma("GCC unroll 4") for -#else -#define loop_unrolled_for for -#endif - struct i40e_ring; struct i40e_vsi; struct net_device; diff --git a/drivers/net/ethernet/intel/iavf/Makefile b/drivers/net/ethernet/intel/iavf/Makefile index 356ac9faa5bf..e13720a728ff 100644 --- a/drivers/net/ethernet/intel/iavf/Makefile +++ b/drivers/net/ethernet/intel/iavf/Makefile @@ -13,3 +13,5 @@ obj-$(CONFIG_IAVF) += iavf.o iavf-y := iavf_main.o iavf_ethtool.o iavf_virtchnl.o iavf_fdir.o \ iavf_adv_rss.o iavf_txrx.o iavf_common.o iavf_adminq.o + +iavf-$(CONFIG_PTP_1588_CLOCK) += iavf_ptp.o diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 532a0a595fe8..9de3e0ba3731 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -41,6 +41,7 @@ #include "iavf_txrx.h" #include "iavf_fdir.h" #include "iavf_adv_rss.h" +#include "iavf_types.h" #include <linux/bitmap.h> #define DEFAULT_DEBUG_LEVEL_SHIFT 3 @@ -82,7 +83,7 @@ struct iavf_vsi { #define MAXIMUM_ETHERNET_VLAN_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN) -#define IAVF_RX_DESC(R, i) (&(((union iavf_32byte_rx_desc *)((R)->desc))[i])) +#define IAVF_RX_DESC(R, i) (&(((struct iavf_rx_desc *)((R)->desc))[i])) #define IAVF_TX_DESC(R, i) (&(((struct iavf_tx_desc *)((R)->desc))[i])) #define IAVF_TX_CTXTDESC(R, i) \ (&(((struct iavf_tx_context_desc *)((R)->desc))[i])) @@ -271,6 +272,7 @@ struct iavf_adapter { /* Lock to protect accesses to MAC and VLAN lists */ spinlock_t mac_vlan_list_lock; char misc_vector_name[IFNAMSIZ + 9]; + u8 rxdid; int num_active_queues; int num_req_queues; @@ -343,6 +345,17 @@ struct iavf_adapter { #define IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW BIT_ULL(39) #define IAVF_FLAG_AQ_CFG_QUEUES_QUANTA_SIZE BIT_ULL(40) #define IAVF_FLAG_AQ_GET_QOS_CAPS BIT_ULL(41) +#define IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS BIT_ULL(42) +#define IAVF_FLAG_AQ_GET_PTP_CAPS BIT_ULL(43) +#define IAVF_FLAG_AQ_SEND_PTP_CMD BIT_ULL(44) + + /* AQ messages that must be sent after IAVF_FLAG_AQ_GET_CONFIG, in + * order to negotiated extended capabilities. + */ +#define IAVF_FLAG_AQ_EXTENDED_CAPS \ + (IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS | \ + IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS | \ + IAVF_FLAG_AQ_GET_PTP_CAPS) /* flags for processing extended capability messages during * __IAVF_INIT_EXTENDED_CAPS. Each capability exchange requires @@ -354,10 +367,18 @@ struct iavf_adapter { u64 extended_caps; #define IAVF_EXTENDED_CAP_SEND_VLAN_V2 BIT_ULL(0) #define IAVF_EXTENDED_CAP_RECV_VLAN_V2 BIT_ULL(1) +#define IAVF_EXTENDED_CAP_SEND_RXDID BIT_ULL(2) +#define IAVF_EXTENDED_CAP_RECV_RXDID BIT_ULL(3) +#define IAVF_EXTENDED_CAP_SEND_PTP BIT_ULL(4) +#define IAVF_EXTENDED_CAP_RECV_PTP BIT_ULL(5) #define IAVF_EXTENDED_CAPS \ (IAVF_EXTENDED_CAP_SEND_VLAN_V2 | \ - IAVF_EXTENDED_CAP_RECV_VLAN_V2) + IAVF_EXTENDED_CAP_RECV_VLAN_V2 | \ + IAVF_EXTENDED_CAP_SEND_RXDID | \ + IAVF_EXTENDED_CAP_RECV_RXDID | \ + IAVF_EXTENDED_CAP_SEND_PTP | \ + IAVF_EXTENDED_CAP_RECV_PTP) /* Lock to prevent possible clobbering of * current_netdev_promisc_flags @@ -417,12 +438,18 @@ struct iavf_adapter { VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF) #define QOS_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \ VIRTCHNL_VF_OFFLOAD_QOS) +#define IAVF_RXDID_ALLOWED(a) \ + ((a)->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) +#define IAVF_PTP_ALLOWED(a) \ + ((a)->vf_res->vf_cap_flags & VIRTCHNL_VF_CAP_PTP) struct virtchnl_vf_resource *vf_res; /* incl. all VSIs */ struct virtchnl_vsi_resource *vsi_res; /* our LAN VSI */ struct virtchnl_version_info pf_version; #define PF_IS_V11(_a) (((_a)->pf_version.major == 1) && \ ((_a)->pf_version.minor == 1)) struct virtchnl_vlan_caps vlan_v2_caps; + u64 supp_rxdids; + struct iavf_ptp ptp; u16 msg_enable; struct iavf_eth_stats current_stats; struct virtchnl_qos_cap_list *qos_caps; @@ -555,6 +582,10 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter); int iavf_get_vf_config(struct iavf_adapter *adapter); int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter); int iavf_send_vf_offload_vlan_v2_msg(struct iavf_adapter *adapter); +int iavf_send_vf_supported_rxdids_msg(struct iavf_adapter *adapter); +int iavf_get_vf_supported_rxdids(struct iavf_adapter *adapter); +int iavf_send_vf_ptp_caps_msg(struct iavf_adapter *adapter); +int iavf_get_vf_ptp_caps(struct iavf_adapter *adapter); void iavf_set_queue_vlan_tag_loc(struct iavf_adapter *adapter); u16 iavf_get_num_vlans_added(struct iavf_adapter *adapter); void iavf_irq_enable(struct iavf_adapter *adapter, bool flush); diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 74a1e9fe1821..288bb5b2e72e 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -1808,7 +1808,7 @@ static int iavf_set_rxfh(struct net_device *netdev, static const struct ethtool_ops iavf_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_USE_ADAPTIVE, - .cap_rss_sym_xor_supported = true, + .supported_input_xfrm = RXH_XFRM_SYM_XOR, .get_drvinfo = iavf_get_drvinfo, .get_link = ethtool_op_get_link, .get_ringparam = iavf_get_ringparam, diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 6faa62bced3a..6d7ba4d67a19 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -2,8 +2,10 @@ /* Copyright(c) 2013 - 2018 Intel Corporation. */ #include <linux/net/intel/libie/rx.h> +#include <net/netdev_lock.h> #include "iavf.h" +#include "iavf_ptp.h" #include "iavf_prototype.h" /* All iavf tracepoints are defined by the include below, which must * be included exactly once across the whole kernel with @@ -710,6 +712,47 @@ static void iavf_configure_tx(struct iavf_adapter *adapter) } /** + * iavf_select_rx_desc_format - Select Rx descriptor format + * @adapter: adapter private structure + * + * Select what Rx descriptor format based on availability and enabled + * features. + * + * Return: the desired RXDID to select for a given Rx queue, as defined by + * enum virtchnl_rxdid_format. + */ +static u8 iavf_select_rx_desc_format(const struct iavf_adapter *adapter) +{ + u64 rxdids = adapter->supp_rxdids; + + /* If we did not negotiate VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC, we must + * stick with the default value of the legacy 32 byte format. + */ + if (!IAVF_RXDID_ALLOWED(adapter)) + return VIRTCHNL_RXDID_1_32B_BASE; + + /* Rx timestamping requires the use of flexible NIC descriptors */ + if (iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP)) { + if (rxdids & BIT(VIRTCHNL_RXDID_2_FLEX_SQ_NIC)) + return VIRTCHNL_RXDID_2_FLEX_SQ_NIC; + + pci_warn(adapter->pdev, + "Unable to negotiate flexible descriptor format\n"); + } + + /* Warn if the PF does not list support for the default legacy + * descriptor format. This shouldn't happen, as this is the format + * used if VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC is not supported. It is + * likely caused by a bug in the PF implementation failing to indicate + * support for the format. + */ + if (!(rxdids & VIRTCHNL_RXDID_1_32B_BASE_M)) + netdev_warn(adapter->netdev, "PF does not list support for default Rx descriptor format\n"); + + return VIRTCHNL_RXDID_1_32B_BASE; +} + +/** * iavf_configure_rx - Configure Receive Unit after Reset * @adapter: board private structure * @@ -719,8 +762,12 @@ static void iavf_configure_rx(struct iavf_adapter *adapter) { struct iavf_hw *hw = &adapter->hw; - for (u32 i = 0; i < adapter->num_active_queues; i++) + adapter->rxdid = iavf_select_rx_desc_format(adapter); + + for (u32 i = 0; i < adapter->num_active_queues; i++) { adapter->rx_rings[i].tail = hw->hw_addr + IAVF_QRX_TAIL1(i); + adapter->rx_rings[i].rxdid = adapter->rxdid; + } } /** @@ -2075,6 +2122,10 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter) return iavf_send_vf_config_msg(adapter); if (adapter->aq_required & IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS) return iavf_send_vf_offload_vlan_v2_msg(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS) + return iavf_send_vf_supported_rxdids_msg(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_GET_PTP_CAPS) + return iavf_send_vf_ptp_caps_msg(adapter); if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_QUEUES) { iavf_disable_queues(adapter); return 0; @@ -2239,7 +2290,10 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter) iavf_enable_vlan_insertion_v2(adapter, ETH_P_8021AD); return 0; } - + if (adapter->aq_required & IAVF_FLAG_AQ_SEND_PTP_CMD) { + iavf_virtchnl_send_ptp_cmd(adapter); + return IAVF_SUCCESS; + } if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_STATS) { iavf_request_stats(adapter); return 0; @@ -2604,6 +2658,112 @@ err: } /** + * iavf_init_send_supported_rxdids - part of querying for supported RXDID + * formats + * @adapter: board private structure + * + * Function processes send of the request for supported RXDIDs to the PF. + * Must clear IAVF_EXTENDED_CAP_RECV_RXDID if the message is not sent, e.g. + * due to the PF not negotiating VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC. + */ +static void iavf_init_send_supported_rxdids(struct iavf_adapter *adapter) +{ + int ret; + + ret = iavf_send_vf_supported_rxdids_msg(adapter); + if (ret == -EOPNOTSUPP) { + /* PF does not support VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC. In this + * case, we did not send the capability exchange message and + * do not expect a response. + */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_RXDID; + } + + /* We sent the message, so move on to the next step */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_SEND_RXDID; +} + +/** + * iavf_init_recv_supported_rxdids - part of querying for supported RXDID + * formats + * @adapter: board private structure + * + * Function processes receipt of the supported RXDIDs message from the PF. + **/ +static void iavf_init_recv_supported_rxdids(struct iavf_adapter *adapter) +{ + int ret; + + memset(&adapter->supp_rxdids, 0, sizeof(adapter->supp_rxdids)); + + ret = iavf_get_vf_supported_rxdids(adapter); + if (ret) + goto err; + + /* We've processed the PF response to the + * VIRTCHNL_OP_GET_SUPPORTED_RXDIDS message we sent previously. + */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_RXDID; + return; + +err: + /* We didn't receive a reply. Make sure we try sending again when + * __IAVF_INIT_FAILED attempts to recover. + */ + adapter->extended_caps |= IAVF_EXTENDED_CAP_SEND_RXDID; + iavf_change_state(adapter, __IAVF_INIT_FAILED); +} + +/** + * iavf_init_send_ptp_caps - part of querying for extended PTP capabilities + * @adapter: board private structure + * + * Function processes send of the request for 1588 PTP capabilities to the PF. + * Must clear IAVF_EXTENDED_CAP_SEND_PTP if the message is not sent, e.g. + * due to the PF not negotiating VIRTCHNL_VF_PTP_CAP + */ +static void iavf_init_send_ptp_caps(struct iavf_adapter *adapter) +{ + if (iavf_send_vf_ptp_caps_msg(adapter) == -EOPNOTSUPP) { + /* PF does not support VIRTCHNL_VF_PTP_CAP. In this case, we + * did not send the capability exchange message and do not + * expect a response. + */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_PTP; + } + + /* We sent the message, so move on to the next step */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_SEND_PTP; +} + +/** + * iavf_init_recv_ptp_caps - part of querying for supported PTP capabilities + * @adapter: board private structure + * + * Function processes receipt of the PTP capabilities supported on this VF. + **/ +static void iavf_init_recv_ptp_caps(struct iavf_adapter *adapter) +{ + memset(&adapter->ptp.hw_caps, 0, sizeof(adapter->ptp.hw_caps)); + + if (iavf_get_vf_ptp_caps(adapter)) + goto err; + + /* We've processed the PF response to the VIRTCHNL_OP_1588_PTP_GET_CAPS + * message we sent previously. + */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_PTP; + return; + +err: + /* We didn't receive a reply. Make sure we try sending again when + * __IAVF_INIT_FAILED attempts to recover. + */ + adapter->extended_caps |= IAVF_EXTENDED_CAP_SEND_PTP; + iavf_change_state(adapter, __IAVF_INIT_FAILED); +} + +/** * iavf_init_process_extended_caps - Part of driver startup * @adapter: board private structure * @@ -2627,6 +2787,24 @@ static void iavf_init_process_extended_caps(struct iavf_adapter *adapter) return; } + /* Process capability exchange for RXDID formats */ + if (adapter->extended_caps & IAVF_EXTENDED_CAP_SEND_RXDID) { + iavf_init_send_supported_rxdids(adapter); + return; + } else if (adapter->extended_caps & IAVF_EXTENDED_CAP_RECV_RXDID) { + iavf_init_recv_supported_rxdids(adapter); + return; + } + + /* Process capability exchange for PTP features */ + if (adapter->extended_caps & IAVF_EXTENDED_CAP_SEND_PTP) { + iavf_init_send_ptp_caps(adapter); + return; + } else if (adapter->extended_caps & IAVF_EXTENDED_CAP_RECV_PTP) { + iavf_init_recv_ptp_caps(adapter); + return; + } + /* When we reach here, no further extended capabilities exchanges are * necessary, so we finally transition into __IAVF_INIT_CONFIG_ADAPTER */ @@ -2718,6 +2896,9 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) if (QOS_ALLOWED(adapter)) adapter->aq_required |= IAVF_FLAG_AQ_GET_QOS_CAPS; + /* Setup initial PTP configuration */ + iavf_ptp_init(adapter); + iavf_schedule_finish_config(adapter); return; @@ -3143,15 +3324,18 @@ continue_reset: } adapter->aq_required |= IAVF_FLAG_AQ_GET_CONFIG; - /* always set since VIRTCHNL_OP_GET_VF_RESOURCES has not been - * sent/received yet, so VLAN_V2_ALLOWED() cannot is not reliable here, - * however the VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS won't be sent until - * VIRTCHNL_OP_GET_VF_RESOURCES and VIRTCHNL_VF_OFFLOAD_VLAN_V2 have - * been successfully sent and negotiated - */ - adapter->aq_required |= IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS; adapter->aq_required |= IAVF_FLAG_AQ_MAP_VECTORS; + /* Certain capabilities require an extended negotiation process using + * extra messages that must be processed after getting the VF + * configuration. The related checks such as VLAN_V2_ALLOWED() are not + * reliable here, since the configuration has not yet been negotiated. + * + * Always set these flags, since them related VIRTCHNL messages won't + * be sent until after VIRTCHNL_OP_GET_VF_RESOURCES. + */ + adapter->aq_required |= IAVF_FLAG_AQ_EXTENDED_CAPS; + spin_lock_bh(&adapter->mac_vlan_list_lock); /* Delete filter for the current MAC address, it could have @@ -3711,10 +3895,8 @@ exit: if (test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) return 0; - netdev_lock(netdev); netif_set_real_num_rx_queues(netdev, total_qps); netif_set_real_num_tx_queues(netdev, total_qps); - netdev_unlock(netdev); return ret; } @@ -4379,22 +4561,21 @@ static int iavf_open(struct net_device *netdev) struct iavf_adapter *adapter = netdev_priv(netdev); int err; + netdev_assert_locked(netdev); + if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) { dev_err(&adapter->pdev->dev, "Unable to open device due to PF driver failure.\n"); return -EIO; } - netdev_lock(netdev); while (!mutex_trylock(&adapter->crit_lock)) { /* If we are in __IAVF_INIT_CONFIG_ADAPTER state the crit_lock * is already taken and iavf_open is called from an upper * device's notifier reacting on NETDEV_REGISTER event. * We have to leave here to avoid dead lock. */ - if (adapter->state == __IAVF_INIT_CONFIG_ADAPTER) { - netdev_unlock(netdev); + if (adapter->state == __IAVF_INIT_CONFIG_ADAPTER) return -EBUSY; - } usleep_range(500, 1000); } @@ -4443,7 +4624,6 @@ static int iavf_open(struct net_device *netdev) iavf_irq_enable(adapter, true); mutex_unlock(&adapter->crit_lock); - netdev_unlock(netdev); return 0; @@ -4456,7 +4636,6 @@ err_setup_tx: iavf_free_all_tx_resources(adapter); err_unlock: mutex_unlock(&adapter->crit_lock); - netdev_unlock(netdev); return err; } @@ -4478,12 +4657,12 @@ static int iavf_close(struct net_device *netdev) u64 aq_to_restore; int status; - netdev_lock(netdev); + netdev_assert_locked(netdev); + mutex_lock(&adapter->crit_lock); if (adapter->state <= __IAVF_DOWN_PENDING) { mutex_unlock(&adapter->crit_lock); - netdev_unlock(netdev); return 0; } @@ -4536,6 +4715,7 @@ static int iavf_close(struct net_device *netdev) if (!status) netdev_warn(netdev, "Device resources not yet released\n"); + netdev_lock(netdev); mutex_lock(&adapter->crit_lock); adapter->aq_required |= aq_to_restore; mutex_unlock(&adapter->crit_lock); @@ -5000,6 +5180,25 @@ static netdev_features_t iavf_fix_features(struct net_device *netdev, return iavf_fix_strip_features(adapter, features); } +static int iavf_hwstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *config) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + *config = adapter->ptp.hwtstamp_config; + + return 0; +} + +static int iavf_hwstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + return iavf_ptp_set_ts_config(adapter, config, extack); +} + static int iavf_verify_shaper(struct net_shaper_binding *binding, const struct net_shaper *shaper, @@ -5108,6 +5307,8 @@ static const struct net_device_ops iavf_netdev_ops = { .ndo_set_features = iavf_set_features, .ndo_setup_tc = iavf_setup_tc, .net_shaper_ops = &iavf_shaper_ops, + .ndo_hwtstamp_get = iavf_hwstamp_get, + .ndo_hwtstamp_set = iavf_hwstamp_set, }; /** @@ -5362,6 +5563,10 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Setup the wait queue for indicating virtchannel events */ init_waitqueue_head(&adapter->vc_waitqueue); + INIT_LIST_HEAD(&adapter->ptp.aq_cmds); + init_waitqueue_head(&adapter->ptp.phc_time_waitqueue); + mutex_init(&adapter->ptp.aq_cmd_lock); + queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(5 * (pdev->devfn & 0x07))); /* Initialization goes on in the work. Do not add more of it below. */ @@ -5518,6 +5723,8 @@ static void iavf_remove(struct pci_dev *pdev) msleep(50); } + iavf_ptp_release(adapter); + iavf_misc_irq_disable(adapter); /* Shut down all the garbage mashers on the detention level */ cancel_work_sync(&adapter->reset_task); diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.c b/drivers/net/ethernet/intel/iavf/iavf_ptp.c new file mode 100644 index 000000000000..b4d5eda2e84f --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.c @@ -0,0 +1,485 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2024 Intel Corporation. */ + +#include "iavf.h" +#include "iavf_ptp.h" + +#define iavf_clock_to_adapter(info) \ + container_of_const(info, struct iavf_adapter, ptp.info) + +/** + * iavf_ptp_disable_rx_tstamp - Disable timestamping in Rx rings + * @adapter: private adapter structure + * + * Disable timestamp reporting for all Rx rings. + */ +static void iavf_ptp_disable_rx_tstamp(struct iavf_adapter *adapter) +{ + for (u32 i = 0; i < adapter->num_active_queues; i++) + adapter->rx_rings[i].flags &= ~IAVF_TXRX_FLAGS_HW_TSTAMP; +} + +/** + * iavf_ptp_enable_rx_tstamp - Enable timestamping in Rx rings + * @adapter: private adapter structure + * + * Enable timestamp reporting for all Rx rings. + */ +static void iavf_ptp_enable_rx_tstamp(struct iavf_adapter *adapter) +{ + for (u32 i = 0; i < adapter->num_active_queues; i++) + adapter->rx_rings[i].flags |= IAVF_TXRX_FLAGS_HW_TSTAMP; +} + +/** + * iavf_ptp_set_timestamp_mode - Set device timestamping mode + * @adapter: private adapter structure + * @config: pointer to kernel_hwtstamp_config + * + * Set the timestamping mode requested from the userspace. + * + * Note: this function always translates Rx timestamp requests for any packet + * category into HWTSTAMP_FILTER_ALL. + * + * Return: 0 on success, negative error code otherwise. + */ +static int iavf_ptp_set_timestamp_mode(struct iavf_adapter *adapter, + struct kernel_hwtstamp_config *config) +{ + /* Reserved for future extensions. */ + if (config->flags) + return -EINVAL; + + switch (config->tx_type) { + case HWTSTAMP_TX_OFF: + break; + case HWTSTAMP_TX_ON: + return -EOPNOTSUPP; + default: + return -ERANGE; + } + + if (config->rx_filter == HWTSTAMP_FILTER_NONE) { + iavf_ptp_disable_rx_tstamp(adapter); + return 0; + } else if (config->rx_filter > HWTSTAMP_FILTER_NTP_ALL) { + return -ERANGE; + } else if (!(iavf_ptp_cap_supported(adapter, + VIRTCHNL_1588_PTP_CAP_RX_TSTAMP))) { + return -EOPNOTSUPP; + } + + config->rx_filter = HWTSTAMP_FILTER_ALL; + iavf_ptp_enable_rx_tstamp(adapter); + + return 0; +} + +/** + * iavf_ptp_set_ts_config - Set timestamping configuration + * @adapter: private adapter structure + * @config: pointer to kernel_hwtstamp_config structure + * @extack: pointer to netlink_ext_ack structure + * + * Program the requested timestamping configuration to the device. + * + * Return: 0 on success, negative error code otherwise. + */ +int iavf_ptp_set_ts_config(struct iavf_adapter *adapter, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + int err; + + err = iavf_ptp_set_timestamp_mode(adapter, config); + if (err) + return err; + + /* Save successful settings for future reference */ + adapter->ptp.hwtstamp_config = *config; + + return 0; +} + +/** + * iavf_ptp_cap_supported - Check if a PTP capability is supported + * @adapter: private adapter structure + * @cap: the capability bitmask to check + * + * Return: true if every capability set in cap is also set in the enabled + * capabilities reported by the PF, false otherwise. + */ +bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, u32 cap) +{ + if (!IAVF_PTP_ALLOWED(adapter)) + return false; + + /* Only return true if every bit in cap is set in hw_caps.caps */ + return (adapter->ptp.hw_caps.caps & cap) == cap; +} + +/** + * iavf_allocate_ptp_cmd - Allocate a PTP command message structure + * @v_opcode: the virtchnl opcode + * @msglen: length in bytes of the associated virtchnl structure + * + * Allocates a PTP command message and pre-fills it with the provided message + * length and opcode. + * + * Return: allocated PTP command. + */ +static struct iavf_ptp_aq_cmd *iavf_allocate_ptp_cmd(enum virtchnl_ops v_opcode, + u16 msglen) +{ + struct iavf_ptp_aq_cmd *cmd; + + cmd = kzalloc(struct_size(cmd, msg, msglen), GFP_KERNEL); + if (!cmd) + return NULL; + + cmd->v_opcode = v_opcode; + cmd->msglen = msglen; + + return cmd; +} + +/** + * iavf_queue_ptp_cmd - Queue PTP command for sending over virtchnl + * @adapter: private adapter structure + * @cmd: the command structure to send + * + * Queue the given command structure into the PTP virtchnl command queue tos + * end to the PF. + */ +static void iavf_queue_ptp_cmd(struct iavf_adapter *adapter, + struct iavf_ptp_aq_cmd *cmd) +{ + mutex_lock(&adapter->ptp.aq_cmd_lock); + list_add_tail(&cmd->list, &adapter->ptp.aq_cmds); + mutex_unlock(&adapter->ptp.aq_cmd_lock); + + adapter->aq_required |= IAVF_FLAG_AQ_SEND_PTP_CMD; + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); +} + +/** + * iavf_send_phc_read - Send request to read PHC time + * @adapter: private adapter structure + * + * Send a request to obtain the PTP hardware clock time. This allocates the + * VIRTCHNL_OP_1588_PTP_GET_TIME message and queues it up to send to + * indirectly read the PHC time. + * + * This function does not wait for the reply from the PF. + * + * Return: 0 if success, error code otherwise. + */ +static int iavf_send_phc_read(struct iavf_adapter *adapter) +{ + struct iavf_ptp_aq_cmd *cmd; + + if (!adapter->ptp.clock) + return -EOPNOTSUPP; + + cmd = iavf_allocate_ptp_cmd(VIRTCHNL_OP_1588_PTP_GET_TIME, + sizeof(struct virtchnl_phc_time)); + if (!cmd) + return -ENOMEM; + + iavf_queue_ptp_cmd(adapter, cmd); + + return 0; +} + +/** + * iavf_read_phc_indirect - Indirectly read the PHC time via virtchnl + * @adapter: private adapter structure + * @ts: storage for the timestamp value + * @sts: system timestamp values before and after the read + * + * Used when the device does not have direct register access to the PHC time. + * Indirectly reads the time via the VIRTCHNL_OP_1588_PTP_GET_TIME, and waits + * for the reply from the PF. + * + * Based on some simple measurements using ftrace and phc2sys, this clock + * access method has about a ~110 usec latency even when the system is not + * under load. In order to achieve acceptable results when using phc2sys with + * the indirect clock access method, it is recommended to use more + * conservative proportional and integration constants with the P/I servo. + * + * Return: 0 if success, error code otherwise. + */ +static int iavf_read_phc_indirect(struct iavf_adapter *adapter, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + long ret; + int err; + + adapter->ptp.phc_time_ready = false; + + ptp_read_system_prets(sts); + + err = iavf_send_phc_read(adapter); + if (err) + return err; + + ret = wait_event_interruptible_timeout(adapter->ptp.phc_time_waitqueue, + adapter->ptp.phc_time_ready, + HZ); + + ptp_read_system_postts(sts); + + if (ret < 0) + return ret; + else if (!ret) + return -EBUSY; + + *ts = ns_to_timespec64(adapter->ptp.cached_phc_time); + + return 0; +} + +static int iavf_ptp_gettimex64(struct ptp_clock_info *info, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + struct iavf_adapter *adapter = iavf_clock_to_adapter(info); + + if (!adapter->ptp.clock) + return -EOPNOTSUPP; + + return iavf_read_phc_indirect(adapter, ts, sts); +} + +/** + * iavf_ptp_cache_phc_time - Cache PHC time for performing timestamp extension + * @adapter: private adapter structure + * + * Periodically cache the PHC time in order to allow for timestamp extension. + * This is required because the Tx and Rx timestamps only contain 32bits of + * nanoseconds. Timestamp extension allows calculating the corrected 64bit + * timestamp. This algorithm relies on the cached time being within ~1 second + * of the timestamp. + */ +static void iavf_ptp_cache_phc_time(struct iavf_adapter *adapter) +{ + if (!time_is_before_jiffies(adapter->ptp.cached_phc_updated + HZ)) + return; + + /* The response from virtchnl will store the time into + * cached_phc_time. + */ + iavf_send_phc_read(adapter); +} + +/** + * iavf_ptp_do_aux_work - Perform periodic work required for PTP support + * @info: PTP clock info structure + * + * Handler to take care of periodic work required for PTP operation. This + * includes the following tasks: + * + * 1) updating cached_phc_time + * + * cached_phc_time is used by the Tx and Rx timestamp flows in order to + * perform timestamp extension, by carefully comparing the timestamp + * 32bit nanosecond timestamps and determining the corrected 64bit + * timestamp value to report to userspace. This algorithm only works if + * the cached_phc_time is within ~1 second of the Tx or Rx timestamp + * event. This task periodically reads the PHC time and stores it, to + * ensure that timestamp extension operates correctly. + * + * Returns: time in jiffies until the periodic task should be re-scheduled. + */ +static long iavf_ptp_do_aux_work(struct ptp_clock_info *info) +{ + struct iavf_adapter *adapter = iavf_clock_to_adapter(info); + + iavf_ptp_cache_phc_time(adapter); + + /* Check work about twice a second */ + return msecs_to_jiffies(500); +} + +/** + * iavf_ptp_register_clock - Register a new PTP for userspace + * @adapter: private adapter structure + * + * Allocate and register a new PTP clock device if necessary. + * + * Return: 0 if success, error otherwise. + */ +static int iavf_ptp_register_clock(struct iavf_adapter *adapter) +{ + struct ptp_clock_info *ptp_info = &adapter->ptp.info; + struct device *dev = &adapter->pdev->dev; + struct ptp_clock *clock; + + snprintf(ptp_info->name, sizeof(ptp_info->name), "%s-%s-clk", + KBUILD_MODNAME, dev_name(dev)); + ptp_info->owner = THIS_MODULE; + ptp_info->gettimex64 = iavf_ptp_gettimex64; + ptp_info->do_aux_work = iavf_ptp_do_aux_work; + + clock = ptp_clock_register(ptp_info, dev); + if (IS_ERR(clock)) + return PTR_ERR(clock); + + adapter->ptp.clock = clock; + + dev_dbg(&adapter->pdev->dev, "PTP clock %s registered\n", + adapter->ptp.info.name); + + return 0; +} + +/** + * iavf_ptp_init - Initialize PTP support if capability was negotiated + * @adapter: private adapter structure + * + * Initialize PTP functionality, based on the capabilities that the PF has + * enabled for this VF. + */ +void iavf_ptp_init(struct iavf_adapter *adapter) +{ + int err; + + if (!iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_READ_PHC)) { + pci_notice(adapter->pdev, + "Device does not have PTP clock support\n"); + return; + } + + err = iavf_ptp_register_clock(adapter); + if (err) { + pci_err(adapter->pdev, + "Failed to register PTP clock device (%p)\n", + ERR_PTR(err)); + return; + } + + for (int i = 0; i < adapter->num_active_queues; i++) { + struct iavf_ring *rx_ring = &adapter->rx_rings[i]; + + rx_ring->ptp = &adapter->ptp; + } + + ptp_schedule_worker(adapter->ptp.clock, 0); +} + +/** + * iavf_ptp_release - Disable PTP support + * @adapter: private adapter structure + * + * Release all PTP resources that were previously initialized. + */ +void iavf_ptp_release(struct iavf_adapter *adapter) +{ + struct iavf_ptp_aq_cmd *cmd, *tmp; + + if (!adapter->ptp.clock) + return; + + pci_dbg(adapter->pdev, "removing PTP clock %s\n", + adapter->ptp.info.name); + ptp_clock_unregister(adapter->ptp.clock); + adapter->ptp.clock = NULL; + + /* Cancel any remaining uncompleted PTP clock commands */ + mutex_lock(&adapter->ptp.aq_cmd_lock); + list_for_each_entry_safe(cmd, tmp, &adapter->ptp.aq_cmds, list) { + list_del(&cmd->list); + kfree(cmd); + } + adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD; + mutex_unlock(&adapter->ptp.aq_cmd_lock); + + adapter->ptp.hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; + iavf_ptp_disable_rx_tstamp(adapter); +} + +/** + * iavf_ptp_process_caps - Handle change in PTP capabilities + * @adapter: private adapter structure + * + * Handle any state changes necessary due to change in PTP capabilities, such + * as after a device reset or change in configuration from the PF. + */ +void iavf_ptp_process_caps(struct iavf_adapter *adapter) +{ + bool phc = iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_READ_PHC); + + /* Check if the device gained or lost necessary access to support the + * PTP hardware clock. If so, driver must respond appropriately by + * creating or destroying the PTP clock device. + */ + if (adapter->ptp.clock && !phc) + iavf_ptp_release(adapter); + else if (!adapter->ptp.clock && phc) + iavf_ptp_init(adapter); + + /* Check if the device lost access to Rx timestamp incoming packets */ + if (!iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP)) { + adapter->ptp.hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; + iavf_ptp_disable_rx_tstamp(adapter); + } +} + +/** + * iavf_ptp_extend_32b_timestamp - Convert a 32b nanoseconds timestamp to 64b + * nanoseconds + * @cached_phc_time: recently cached copy of PHC time + * @in_tstamp: Ingress/egress 32b nanoseconds timestamp value + * + * Hardware captures timestamps which contain only 32 bits of nominal + * nanoseconds, as opposed to the 64bit timestamps that the stack expects. + * + * Extend the 32bit nanosecond timestamp using the following algorithm and + * assumptions: + * + * 1) have a recently cached copy of the PHC time + * 2) assume that the in_tstamp was captured 2^31 nanoseconds (~2.1 + * seconds) before or after the PHC time was captured. + * 3) calculate the delta between the cached time and the timestamp + * 4) if the delta is smaller than 2^31 nanoseconds, then the timestamp was + * captured after the PHC time. In this case, the full timestamp is just + * the cached PHC time plus the delta. + * 5) otherwise, if the delta is larger than 2^31 nanoseconds, then the + * timestamp was captured *before* the PHC time, i.e. because the PHC + * cache was updated after the timestamp was captured by hardware. In this + * case, the full timestamp is the cached time minus the inverse delta. + * + * This algorithm works even if the PHC time was updated after a Tx timestamp + * was requested, but before the Tx timestamp event was reported from + * hardware. + * + * This calculation primarily relies on keeping the cached PHC time up to + * date. If the timestamp was captured more than 2^31 nanoseconds after the + * PHC time, it is possible that the lower 32bits of PHC time have + * overflowed more than once, and we might generate an incorrect timestamp. + * + * This is prevented by (a) periodically updating the cached PHC time once + * a second, and (b) discarding any Tx timestamp packet if it has waited for + * a timestamp for more than one second. + * + * Return: extended timestamp (to 64b). + */ +u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time, u32 in_tstamp) +{ + u32 low = lower_32_bits(cached_phc_time); + u32 delta = in_tstamp - low; + u64 ns; + + /* Do not assume that the in_tstamp is always more recent than the + * cached PHC time. If the delta is large, it indicates that the + * in_tstamp was taken in the past, and should be converted + * forward. + */ + if (delta > S32_MAX) + ns = cached_phc_time - (low - in_tstamp); + else + ns = cached_phc_time + delta; + + return ns; +} diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.h b/drivers/net/ethernet/intel/iavf/iavf_ptp.h new file mode 100644 index 000000000000..783b8f287cd9 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2024 Intel Corporation. */ + +#ifndef _IAVF_PTP_H_ +#define _IAVF_PTP_H_ + +#include "iavf_types.h" + +/* bit indicating whether a 40bit timestamp is valid */ +#define IAVF_PTP_40B_TSTAMP_VALID BIT(24) + +#if IS_ENABLED(CONFIG_PTP_1588_CLOCK) +void iavf_ptp_init(struct iavf_adapter *adapter); +void iavf_ptp_release(struct iavf_adapter *adapter); +void iavf_ptp_process_caps(struct iavf_adapter *adapter); +bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, u32 cap); +void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter); +int iavf_ptp_set_ts_config(struct iavf_adapter *adapter, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); +u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time, u32 in_tstamp); +#else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ +static inline void iavf_ptp_init(struct iavf_adapter *adapter) { } +static inline void iavf_ptp_release(struct iavf_adapter *adapter) { } +static inline void iavf_ptp_process_caps(struct iavf_adapter *adapter) { } +static inline bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, + u32 cap) +{ + return false; +} + +static inline void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter) { } +static inline int iavf_ptp_set_ts_config(struct iavf_adapter *adapter, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + return -1; +} + +static inline u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time, + u32 in_tstamp) +{ + return 0; +} + +#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ +#endif /* _IAVF_PTP_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_trace.h b/drivers/net/ethernet/intel/iavf/iavf_trace.h index 62212011c807..c5e4d1823886 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_trace.h +++ b/drivers/net/ethernet/intel/iavf/iavf_trace.h @@ -112,7 +112,7 @@ DECLARE_EVENT_CLASS( iavf_rx_template, TP_PROTO(struct iavf_ring *ring, - union iavf_32byte_rx_desc *desc, + struct iavf_rx_desc *desc, struct sk_buff *skb), TP_ARGS(ring, desc, skb), @@ -140,7 +140,7 @@ DECLARE_EVENT_CLASS( DEFINE_EVENT( iavf_rx_template, iavf_clean_rx_irq, TP_PROTO(struct iavf_ring *ring, - union iavf_32byte_rx_desc *desc, + struct iavf_rx_desc *desc, struct sk_buff *skb), TP_ARGS(ring, desc, skb)); @@ -148,7 +148,7 @@ DEFINE_EVENT( DEFINE_EVENT( iavf_rx_template, iavf_clean_rx_irq_rx, TP_PROTO(struct iavf_ring *ring, - union iavf_32byte_rx_desc *desc, + struct iavf_rx_desc *desc, struct sk_buff *skb), TP_ARGS(ring, desc, skb)); diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index 26b424fd6718..422312b8b54a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -8,6 +8,26 @@ #include "iavf.h" #include "iavf_trace.h" #include "iavf_prototype.h" +#include "iavf_ptp.h" + +/** + * iavf_is_descriptor_done - tests DD bit in Rx descriptor + * @qw1: quad word 1 from descriptor to get Descriptor Done field from + * @flex: is the descriptor flex or legacy + * + * This function tests the descriptor done bit in specified descriptor. Because + * there are two types of descriptors (legacy and flex) the parameter rx_ring + * is used to distinguish. + * + * Return: true or false based on the state of DD bit in Rx descriptor. + */ +static bool iavf_is_descriptor_done(u64 qw1, bool flex) +{ + if (flex) + return FIELD_GET(IAVF_RXD_FLEX_DD_M, qw1); + else + return FIELD_GET(IAVF_RXD_LEGACY_DD_M, qw1); +} static __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size, u32 td_tag) @@ -766,7 +786,7 @@ int iavf_setup_rx_descriptors(struct iavf_ring *rx_ring) u64_stats_init(&rx_ring->syncp); /* Round up to nearest 4K */ - rx_ring->size = rx_ring->count * sizeof(union iavf_32byte_rx_desc); + rx_ring->size = rx_ring->count * sizeof(struct iavf_rx_desc); rx_ring->size = ALIGN(rx_ring->size, 4096); rx_ring->desc = dma_alloc_coherent(fq.pp->p.dev, rx_ring->size, &rx_ring->dma, GFP_KERNEL); @@ -845,7 +865,7 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count) .count = rx_ring->count, }; u16 ntu = rx_ring->next_to_use; - union iavf_rx_desc *rx_desc; + struct iavf_rx_desc *rx_desc; /* do nothing if no valid netdev defined */ if (!rx_ring->netdev || !cleaned_count) @@ -863,7 +883,7 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count) /* Refresh the desc even if buffer_addrs didn't change * because each write-back erases this info. */ - rx_desc->read.pkt_addr = cpu_to_le64(addr); + rx_desc->qw0 = cpu_to_le64(addr); rx_desc++; ntu++; @@ -873,7 +893,7 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count) } /* clear the status bits for the next_to_use descriptor */ - rx_desc->wb.qword1.status_error_len = 0; + rx_desc->qw1 = 0; cleaned_count--; } while (cleaned_count); @@ -896,60 +916,43 @@ no_buffers: } /** - * iavf_rx_checksum - Indicate in skb if hw indicated a good cksum + * iavf_rx_csum - Indicate in skb if hw indicated a good checksum * @vsi: the VSI we care about * @skb: skb currently being received and modified - * @rx_desc: the receive descriptor + * @decoded_pt: decoded ptype information + * @csum_bits: decoded Rx descriptor information **/ -static void iavf_rx_checksum(struct iavf_vsi *vsi, - struct sk_buff *skb, - union iavf_rx_desc *rx_desc) +static void iavf_rx_csum(const struct iavf_vsi *vsi, struct sk_buff *skb, + struct libeth_rx_pt decoded_pt, + struct libeth_rx_csum csum_bits) { - struct libeth_rx_pt decoded; - u32 rx_error, rx_status; bool ipv4, ipv6; - u8 ptype; - u64 qword; skb->ip_summed = CHECKSUM_NONE; - qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword); - - decoded = libie_rx_pt_parse(ptype); - if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded)) - return; - - rx_error = FIELD_GET(IAVF_RXD_QW1_ERROR_MASK, qword); - rx_status = FIELD_GET(IAVF_RXD_QW1_STATUS_MASK, qword); - /* did the hardware decode the packet and checksum? */ - if (!(rx_status & BIT(IAVF_RX_DESC_STATUS_L3L4P_SHIFT))) + if (unlikely(!csum_bits.l3l4p)) return; - ipv4 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV4; - ipv6 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV6; + ipv4 = libeth_rx_pt_get_ip_ver(decoded_pt) == LIBETH_RX_PT_OUTER_IPV4; + ipv6 = libeth_rx_pt_get_ip_ver(decoded_pt) == LIBETH_RX_PT_OUTER_IPV6; - if (ipv4 && - (rx_error & (BIT(IAVF_RX_DESC_ERROR_IPE_SHIFT) | - BIT(IAVF_RX_DESC_ERROR_EIPE_SHIFT)))) + if (unlikely(ipv4 && (csum_bits.ipe || csum_bits.eipe))) goto checksum_fail; /* likely incorrect csum if alternate IP extension headers found */ - if (ipv6 && - rx_status & BIT(IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT)) - /* don't increment checksum err here, non-fatal err */ + if (unlikely(ipv6 && csum_bits.ipv6exadd)) return; /* there was some L4 error, count error and punt packet to the stack */ - if (rx_error & BIT(IAVF_RX_DESC_ERROR_L4E_SHIFT)) + if (unlikely(csum_bits.l4e)) goto checksum_fail; /* handle packets that were not able to be checksummed due * to arrival speed, in this case the stack can compute * the csum. */ - if (rx_error & BIT(IAVF_RX_DESC_ERROR_PPRS_SHIFT)) + if (unlikely(csum_bits.pprs)) return; skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -960,52 +963,196 @@ checksum_fail: } /** - * iavf_rx_hash - set the hash value in the skb + * iavf_legacy_rx_csum - Indicate in skb if hw indicated a good checksum + * @vsi: the VSI we care about + * @qw1: quad word 1 + * @decoded_pt: decoded packet type + * + * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte + * descriptor writeback format. + * + * Return: decoded checksum bits. + **/ +static struct libeth_rx_csum +iavf_legacy_rx_csum(const struct iavf_vsi *vsi, u64 qw1, + const struct libeth_rx_pt decoded_pt) +{ + struct libeth_rx_csum csum_bits = {}; + + if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded_pt)) + return csum_bits; + + csum_bits.ipe = FIELD_GET(IAVF_RXD_LEGACY_IPE_M, qw1); + csum_bits.eipe = FIELD_GET(IAVF_RXD_LEGACY_EIPE_M, qw1); + csum_bits.l4e = FIELD_GET(IAVF_RXD_LEGACY_L4E_M, qw1); + csum_bits.pprs = FIELD_GET(IAVF_RXD_LEGACY_PPRS_M, qw1); + csum_bits.l3l4p = FIELD_GET(IAVF_RXD_LEGACY_L3L4P_M, qw1); + csum_bits.ipv6exadd = FIELD_GET(IAVF_RXD_LEGACY_IPV6EXADD_M, qw1); + + return csum_bits; +} + +/** + * iavf_flex_rx_csum - Indicate in skb if hw indicated a good checksum + * @vsi: the VSI we care about + * @qw1: quad word 1 + * @decoded_pt: decoded packet type + * + * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible + * descriptor writeback format. + * + * Return: decoded checksum bits. + **/ +static struct libeth_rx_csum +iavf_flex_rx_csum(const struct iavf_vsi *vsi, u64 qw1, + const struct libeth_rx_pt decoded_pt) +{ + struct libeth_rx_csum csum_bits = {}; + + if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded_pt)) + return csum_bits; + + csum_bits.ipe = FIELD_GET(IAVF_RXD_FLEX_XSUM_IPE_M, qw1); + csum_bits.eipe = FIELD_GET(IAVF_RXD_FLEX_XSUM_EIPE_M, qw1); + csum_bits.l4e = FIELD_GET(IAVF_RXD_FLEX_XSUM_L4E_M, qw1); + csum_bits.eudpe = FIELD_GET(IAVF_RXD_FLEX_XSUM_EUDPE_M, qw1); + csum_bits.l3l4p = FIELD_GET(IAVF_RXD_FLEX_L3L4P_M, qw1); + csum_bits.ipv6exadd = FIELD_GET(IAVF_RXD_FLEX_IPV6EXADD_M, qw1); + csum_bits.nat = FIELD_GET(IAVF_RXD_FLEX_NAT_M, qw1); + + return csum_bits; +} + +/** + * iavf_legacy_rx_hash - set the hash value in the skb + * @ring: descriptor ring + * @qw0: quad word 0 + * @qw1: quad word 1 + * @skb: skb currently being received and modified + * @decoded_pt: decoded packet type + * + * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte + * descriptor writeback format. + **/ +static void iavf_legacy_rx_hash(const struct iavf_ring *ring, __le64 qw0, + __le64 qw1, struct sk_buff *skb, + const struct libeth_rx_pt decoded_pt) +{ + const __le64 rss_mask = cpu_to_le64(IAVF_RXD_LEGACY_FLTSTAT_M); + u32 hash; + + if (!libeth_rx_pt_has_hash(ring->netdev, decoded_pt)) + return; + + if ((qw1 & rss_mask) == rss_mask) { + hash = le64_get_bits(qw0, IAVF_RXD_LEGACY_RSS_M); + libeth_rx_pt_set_hash(skb, hash, decoded_pt); + } +} + +/** + * iavf_flex_rx_hash - set the hash value in the skb * @ring: descriptor ring - * @rx_desc: specific descriptor + * @qw1: quad word 1 * @skb: skb currently being received and modified - * @rx_ptype: Rx packet type + * @decoded_pt: decoded packet type + * + * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible + * descriptor writeback format. **/ -static void iavf_rx_hash(struct iavf_ring *ring, - union iavf_rx_desc *rx_desc, - struct sk_buff *skb, - u8 rx_ptype) +static void iavf_flex_rx_hash(const struct iavf_ring *ring, __le64 qw1, + struct sk_buff *skb, + const struct libeth_rx_pt decoded_pt) { - struct libeth_rx_pt decoded; + bool rss_valid; u32 hash; - const __le64 rss_mask = - cpu_to_le64((u64)IAVF_RX_DESC_FLTSTAT_RSS_HASH << - IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT); - decoded = libie_rx_pt_parse(rx_ptype); - if (!libeth_rx_pt_has_hash(ring->netdev, decoded)) + if (!libeth_rx_pt_has_hash(ring->netdev, decoded_pt)) return; - if ((rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask) { - hash = le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss); - libeth_rx_pt_set_hash(skb, hash, decoded); + rss_valid = le64_get_bits(qw1, IAVF_RXD_FLEX_RSS_VALID_M); + if (rss_valid) { + hash = le64_get_bits(qw1, IAVF_RXD_FLEX_RSS_HASH_M); + libeth_rx_pt_set_hash(skb, hash, decoded_pt); } } /** + * iavf_flex_rx_tstamp - Capture Rx timestamp from the descriptor + * @rx_ring: descriptor ring + * @qw2: quad word 2 of descriptor + * @qw3: quad word 3 of descriptor + * @skb: skb currently being received + * + * Read the Rx timestamp value from the descriptor and pass it to the stack. + * + * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible + * descriptor writeback format. + */ +static void iavf_flex_rx_tstamp(const struct iavf_ring *rx_ring, __le64 qw2, + __le64 qw3, struct sk_buff *skb) +{ + u32 tstamp; + u64 ns; + + /* Skip processing if timestamps aren't enabled */ + if (!(rx_ring->flags & IAVF_TXRX_FLAGS_HW_TSTAMP)) + return; + + /* Check if this Rx descriptor has a valid timestamp */ + if (!le64_get_bits(qw2, IAVF_PTP_40B_TSTAMP_VALID)) + return; + + /* the ts_low field only contains the valid bit and sub-nanosecond + * precision, so we don't need to extract it. + */ + tstamp = le64_get_bits(qw3, IAVF_RXD_FLEX_QW3_TSTAMP_HIGH_M); + + ns = iavf_ptp_extend_32b_timestamp(rx_ring->ptp->cached_phc_time, + tstamp); + + *skb_hwtstamps(skb) = (struct skb_shared_hwtstamps) { + .hwtstamp = ns_to_ktime(ns), + }; +} + +/** * iavf_process_skb_fields - Populate skb header fields from Rx descriptor * @rx_ring: rx descriptor ring packet is being transacted on * @rx_desc: pointer to the EOP Rx descriptor * @skb: pointer to current skb being populated - * @rx_ptype: the packet type decoded by hardware + * @ptype: the packet type decoded by hardware + * @flex: is the descriptor flex or legacy * * This function checks the ring, descriptor, and packet information in * order to populate the hash, checksum, VLAN, protocol, and * other fields within the skb. **/ -static void -iavf_process_skb_fields(struct iavf_ring *rx_ring, - union iavf_rx_desc *rx_desc, struct sk_buff *skb, - u8 rx_ptype) +static void iavf_process_skb_fields(const struct iavf_ring *rx_ring, + const struct iavf_rx_desc *rx_desc, + struct sk_buff *skb, u32 ptype, + bool flex) { - iavf_rx_hash(rx_ring, rx_desc, skb, rx_ptype); - - iavf_rx_checksum(rx_ring->vsi, skb, rx_desc); + struct libeth_rx_csum csum_bits; + struct libeth_rx_pt decoded_pt; + __le64 qw0 = rx_desc->qw0; + __le64 qw1 = rx_desc->qw1; + __le64 qw2 = rx_desc->qw2; + __le64 qw3 = rx_desc->qw3; + + decoded_pt = libie_rx_pt_parse(ptype); + + if (flex) { + iavf_flex_rx_hash(rx_ring, qw1, skb, decoded_pt); + iavf_flex_rx_tstamp(rx_ring, qw2, qw3, skb); + csum_bits = iavf_flex_rx_csum(rx_ring->vsi, le64_to_cpu(qw1), + decoded_pt); + } else { + iavf_legacy_rx_hash(rx_ring, qw0, qw1, skb, decoded_pt); + csum_bits = iavf_legacy_rx_csum(rx_ring->vsi, le64_to_cpu(qw1), + decoded_pt); + } + iavf_rx_csum(rx_ring->vsi, skb, decoded_pt, csum_bits); skb_record_rx_queue(skb, rx_ring->queue_index); @@ -1092,8 +1239,7 @@ static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer, /** * iavf_is_non_eop - process handling of non-EOP buffers * @rx_ring: Rx ring being processed - * @rx_desc: Rx descriptor for current buffer - * @skb: Current socket buffer containing buffer in progress + * @fields: Rx descriptor extracted fields * * This function updates next to clean. If the buffer is an EOP buffer * this function exits returning false, otherwise it will place the @@ -1101,8 +1247,7 @@ static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer, * that this is in fact a non-EOP buffer. **/ static bool iavf_is_non_eop(struct iavf_ring *rx_ring, - union iavf_rx_desc *rx_desc, - struct sk_buff *skb) + struct libeth_rqe_info fields) { u32 ntc = rx_ring->next_to_clean + 1; @@ -1113,8 +1258,7 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring, prefetch(IAVF_RX_DESC(rx_ring, ntc)); /* if we are the last buffer then there is nothing else to do */ -#define IAVF_RXD_EOF BIT(IAVF_RX_DESC_STATUS_EOF_SHIFT) - if (likely(iavf_test_staterr(rx_desc, IAVF_RXD_EOF))) + if (likely(fields.eop)) return false; rx_ring->rx_stats.non_eop_descs++; @@ -1123,6 +1267,109 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring, } /** + * iavf_extract_legacy_rx_fields - Extract fields from the Rx descriptor + * @rx_ring: rx descriptor ring + * @rx_desc: the descriptor to process + * + * Decode the Rx descriptor and extract relevant information including the + * size, VLAN tag, Rx packet type, end of packet field and RXE field value. + * + * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte + * descriptor writeback format. + * + * Return: fields extracted from the Rx descriptor. + */ +static struct libeth_rqe_info +iavf_extract_legacy_rx_fields(const struct iavf_ring *rx_ring, + const struct iavf_rx_desc *rx_desc) +{ + u64 qw0 = le64_to_cpu(rx_desc->qw0); + u64 qw1 = le64_to_cpu(rx_desc->qw1); + u64 qw2 = le64_to_cpu(rx_desc->qw2); + struct libeth_rqe_info fields; + bool l2tag1p, l2tag2p; + + fields.eop = FIELD_GET(IAVF_RXD_LEGACY_EOP_M, qw1); + fields.len = FIELD_GET(IAVF_RXD_LEGACY_LENGTH_M, qw1); + + if (!fields.eop) + return fields; + + fields.rxe = FIELD_GET(IAVF_RXD_LEGACY_RXE_M, qw1); + fields.ptype = FIELD_GET(IAVF_RXD_LEGACY_PTYPE_M, qw1); + fields.vlan = 0; + + if (rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1) { + l2tag1p = FIELD_GET(IAVF_RXD_LEGACY_L2TAG1P_M, qw1); + if (l2tag1p) + fields.vlan = FIELD_GET(IAVF_RXD_LEGACY_L2TAG1_M, qw0); + } else if (rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2) { + l2tag2p = FIELD_GET(IAVF_RXD_LEGACY_L2TAG2P_M, qw2); + if (l2tag2p) + fields.vlan = FIELD_GET(IAVF_RXD_LEGACY_L2TAG2_M, qw2); + } + + return fields; +} + +/** + * iavf_extract_flex_rx_fields - Extract fields from the Rx descriptor + * @rx_ring: rx descriptor ring + * @rx_desc: the descriptor to process + * + * Decode the Rx descriptor and extract relevant information including the + * size, VLAN tag, Rx packet type, end of packet field and RXE field value. + * + * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible + * descriptor writeback format. + * + * Return: fields extracted from the Rx descriptor. + */ +static struct libeth_rqe_info +iavf_extract_flex_rx_fields(const struct iavf_ring *rx_ring, + const struct iavf_rx_desc *rx_desc) +{ + struct libeth_rqe_info fields = {}; + u64 qw0 = le64_to_cpu(rx_desc->qw0); + u64 qw1 = le64_to_cpu(rx_desc->qw1); + u64 qw2 = le64_to_cpu(rx_desc->qw2); + bool l2tag1p, l2tag2p; + + fields.eop = FIELD_GET(IAVF_RXD_FLEX_EOP_M, qw1); + fields.len = FIELD_GET(IAVF_RXD_FLEX_PKT_LEN_M, qw0); + + if (!fields.eop) + return fields; + + fields.rxe = FIELD_GET(IAVF_RXD_FLEX_RXE_M, qw1); + fields.ptype = FIELD_GET(IAVF_RXD_FLEX_PTYPE_M, qw0); + fields.vlan = 0; + + if (rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1) { + l2tag1p = FIELD_GET(IAVF_RXD_FLEX_L2TAG1P_M, qw1); + if (l2tag1p) + fields.vlan = FIELD_GET(IAVF_RXD_FLEX_L2TAG1_M, qw1); + } else if (rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2) { + l2tag2p = FIELD_GET(IAVF_RXD_FLEX_L2TAG2P_M, qw2); + if (l2tag2p) + fields.vlan = FIELD_GET(IAVF_RXD_FLEX_L2TAG2_2_M, qw2); + } + + return fields; +} + +static struct libeth_rqe_info +iavf_extract_rx_fields(const struct iavf_ring *rx_ring, + const struct iavf_rx_desc *rx_desc, + bool flex) +{ + if (flex) + return iavf_extract_flex_rx_fields(rx_ring, rx_desc); + else + return iavf_extract_legacy_rx_fields(rx_ring, rx_desc); +} + +/** * iavf_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf * @rx_ring: rx descriptor ring to transact packets on * @budget: Total limit on number of packets to process @@ -1136,18 +1383,17 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring, **/ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget) { + bool flex = rx_ring->rxdid == VIRTCHNL_RXDID_2_FLEX_SQ_NIC; unsigned int total_rx_bytes = 0, total_rx_packets = 0; struct sk_buff *skb = rx_ring->skb; u16 cleaned_count = IAVF_DESC_UNUSED(rx_ring); bool failure = false; while (likely(total_rx_packets < (unsigned int)budget)) { + struct libeth_rqe_info fields; struct libeth_fqe *rx_buffer; - union iavf_rx_desc *rx_desc; - unsigned int size; - u16 vlan_tag = 0; - u8 rx_ptype; - u64 qword; + struct iavf_rx_desc *rx_desc; + u64 qw1; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= IAVF_RX_BUFFER_WRITE) { @@ -1158,35 +1404,32 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget) rx_desc = IAVF_RX_DESC(rx_ring, rx_ring->next_to_clean); - /* status_error_len will always be zero for unused descriptors - * because it's cleared in cleanup, and overlaps with hdr_addr - * which is always zero because packet split isn't used, if the - * hardware wrote DD then the length will be non-zero - */ - 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(); -#define IAVF_RXD_DD BIT(IAVF_RX_DESC_STATUS_DD_SHIFT) - if (!iavf_test_staterr(rx_desc, IAVF_RXD_DD)) + + qw1 = le64_to_cpu(rx_desc->qw1); + /* If DD field (descriptor done) is unset then other fields are + * not valid + */ + if (!iavf_is_descriptor_done(qw1, flex)) break; - size = FIELD_GET(IAVF_RXD_QW1_LENGTH_PBUF_MASK, qword); + fields = iavf_extract_rx_fields(rx_ring, rx_desc, flex); iavf_trace(clean_rx_irq, rx_ring, rx_desc, skb); rx_buffer = &rx_ring->rx_fqes[rx_ring->next_to_clean]; - if (!libeth_rx_sync_for_cpu(rx_buffer, size)) + if (!libeth_rx_sync_for_cpu(rx_buffer, fields.len)) goto skip_data; /* retrieve a buffer from the ring */ if (skb) - iavf_add_rx_frag(skb, rx_buffer, size); + iavf_add_rx_frag(skb, rx_buffer, fields.len); else - skb = iavf_build_skb(rx_buffer, size); + skb = iavf_build_skb(rx_buffer, fields.len); /* exit if we failed to retrieve a buffer */ if (!skb) { @@ -1197,15 +1440,14 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget) skip_data: cleaned_count++; - if (iavf_is_non_eop(rx_ring, rx_desc, skb) || unlikely(!skb)) + if (iavf_is_non_eop(rx_ring, fields) || unlikely(!skb)) continue; - /* ERR_MASK will only have valid bits if EOP set, and - * what we are doing here is actually checking - * IAVF_RX_DESC_ERROR_RXE_SHIFT, since it is the zeroth bit in - * the error field + /* RXE field in descriptor is an indication of the MAC errors + * (like CRC, alignment, oversize etc). If it is set then iavf + * should finish. */ - if (unlikely(iavf_test_staterr(rx_desc, BIT(IAVF_RXD_QW1_ERROR_SHIFT)))) { + if (unlikely(fields.rxe)) { dev_kfree_skb_any(skb); skb = NULL; continue; @@ -1219,22 +1461,11 @@ skip_data: /* probably a little skewed due to removing CRC */ total_rx_bytes += skb->len; - qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - rx_ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword); - /* populate checksum, VLAN, and protocol */ - iavf_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); - - if (qword & BIT(IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT) && - rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1) - vlan_tag = le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1); - if (rx_desc->wb.qword2.ext_status & - cpu_to_le16(BIT(IAVF_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT)) && - rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2) - vlan_tag = le16_to_cpu(rx_desc->wb.qword2.l2tag2_2); + iavf_process_skb_fields(rx_ring, rx_desc, skb, fields.ptype, flex); iavf_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb); - iavf_receive_skb(rx_ring, skb, vlan_tag); + iavf_receive_skb(rx_ring, skb, fields.vlan); skb = NULL; /* update budget accounting */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h index f97c702c0802..79ad554f2d53 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h @@ -80,25 +80,6 @@ enum iavf_dyn_idx_t { BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \ BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP)) -#define iavf_rx_desc iavf_32byte_rx_desc - -/** - * iavf_test_staterr - tests bits in Rx descriptor status and error fields - * @rx_desc: pointer to receive descriptor (in le64 format) - * @stat_err_bits: value to mask - * - * This function does some fast chicanery in order to return the - * value of the mask which is really only used for boolean tests. - * The status_error_len doesn't need to be shifted because it begins - * at offset zero. - */ -static inline bool iavf_test_staterr(union iavf_rx_desc *rx_desc, - const u64 stat_err_bits) -{ - return !!(rx_desc->wb.qword1.status_error_len & - cpu_to_le64(stat_err_bits)); -} - /* How many Rx Buffers do we bundle into one write to the hardware ? */ #define IAVF_RX_INCREMENT(r, i) \ do { \ @@ -262,6 +243,8 @@ struct iavf_ring { u16 next_to_use; u16 next_to_clean; + u16 rxdid; /* Rx descriptor format */ + u16 flags; #define IAVF_TXR_FLAGS_WB_ON_ITR BIT(0) #define IAVF_TXR_FLAGS_ARM_WB BIT(1) @@ -269,6 +252,7 @@ struct iavf_ring { #define IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1 BIT(3) #define IAVF_TXR_FLAGS_VLAN_TAG_LOC_L2TAG2 BIT(4) #define IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2 BIT(5) +#define IAVF_TXRX_FLAGS_HW_TSTAMP BIT(6) /* stats structs */ struct iavf_queue_stats stats; @@ -295,6 +279,8 @@ struct iavf_ring { * for this ring. */ + struct iavf_ptp *ptp; + u32 rx_buf_len; struct net_shaper q_shaper; bool q_shaper_update; diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h index f6b09e57abce..f9e1319620f4 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_type.h +++ b/drivers/net/ethernet/intel/iavf/iavf_type.h @@ -178,110 +178,116 @@ struct iavf_hw { char err_str[16]; }; -/* RX Descriptors */ -union iavf_16byte_rx_desc { - struct { - __le64 pkt_addr; /* Packet buffer address */ - __le64 hdr_addr; /* Header buffer address */ - } read; - struct { - struct { - struct { - union { - __le16 mirroring_status; - __le16 fcoe_ctx_id; - } mirr_fcoe; - __le16 l2tag1; - } lo_dword; - union { - __le32 rss; /* RSS Hash */ - __le32 fd_id; /* Flow director filter id */ - __le32 fcoe_param; /* FCoE DDP Context id */ - } hi_dword; - } qword0; - struct { - /* ext status/error/pktype/length */ - __le64 status_error_len; - } qword1; - } wb; /* writeback */ -}; - -union iavf_32byte_rx_desc { - struct { - __le64 pkt_addr; /* Packet buffer address */ - __le64 hdr_addr; /* Header buffer address */ - /* bit 0 of hdr_buffer_addr is DD bit */ - __le64 rsvd1; - __le64 rsvd2; - } read; - struct { - struct { - struct { - union { - __le16 mirroring_status; - __le16 fcoe_ctx_id; - } mirr_fcoe; - __le16 l2tag1; - } lo_dword; - union { - __le32 rss; /* RSS Hash */ - __le32 fcoe_param; /* FCoE DDP Context id */ - /* Flow director filter id in case of - * Programming status desc WB - */ - __le32 fd_id; - } hi_dword; - } qword0; - struct { - /* status/error/pktype/length */ - __le64 status_error_len; - } qword1; - struct { - __le16 ext_status; /* extended status */ - __le16 rsvd; - __le16 l2tag2_1; - __le16 l2tag2_2; - } qword2; - struct { - union { - __le32 flex_bytes_lo; - __le32 pe_status; - } lo_dword; - union { - __le32 flex_bytes_hi; - __le32 fd_id; - } hi_dword; - } qword3; - } wb; /* writeback */ -}; - -enum iavf_rx_desc_status_bits { - /* Note: These are predefined bit offsets */ - IAVF_RX_DESC_STATUS_DD_SHIFT = 0, - IAVF_RX_DESC_STATUS_EOF_SHIFT = 1, - IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT = 2, - IAVF_RX_DESC_STATUS_L3L4P_SHIFT = 3, - IAVF_RX_DESC_STATUS_CRCP_SHIFT = 4, - IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT = 5, /* 2 BITS */ - IAVF_RX_DESC_STATUS_TSYNVALID_SHIFT = 7, - /* Note: Bit 8 is reserved in X710 and XL710 */ - IAVF_RX_DESC_STATUS_EXT_UDP_0_SHIFT = 8, - IAVF_RX_DESC_STATUS_UMBCAST_SHIFT = 9, /* 2 BITS */ - IAVF_RX_DESC_STATUS_FLM_SHIFT = 11, - IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT = 12, /* 2 BITS */ - IAVF_RX_DESC_STATUS_LPBK_SHIFT = 14, - IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT = 15, - IAVF_RX_DESC_STATUS_RESERVED_SHIFT = 16, /* 2 BITS */ - /* Note: For non-tunnel packets INT_UDP_0 is the right status for - * UDP header - */ - IAVF_RX_DESC_STATUS_INT_UDP_0_SHIFT = 18, - IAVF_RX_DESC_STATUS_LAST /* this entry must be last!!! */ -}; - -#define IAVF_RXD_QW1_STATUS_SHIFT 0 -#define IAVF_RXD_QW1_STATUS_MASK ((BIT(IAVF_RX_DESC_STATUS_LAST) - 1) \ - << IAVF_RXD_QW1_STATUS_SHIFT) +/** + * struct iavf_rx_desc - Receive descriptor (both legacy and flexible) + * @qw0: quad word 0 fields: + * Legacy: Descriptor Type; Mirror ID; L2TAG1P (S-TAG); Filter Status + * Flex: Descriptor Type; Mirror ID; UMBCAST; Packet Type; Flexible Flags + * Section 0; Packet Length; Header Length; Split Header Flag; + * Flexible Flags section 1 / Extended Status + * @qw1: quad word 1 fields: + * Legacy: Status Field; Error Field; Packet Type; Packet Length (packet, + * header, Split Header Flag) + * Flex: Status / Error 0 Field; L2TAG1P (S-TAG); Flexible Metadata + * Container #0; Flexible Metadata Container #1 + * @qw2: quad word 2 fields: + * Legacy: Extended Status; 1st L2TAG2P (C-TAG); 2nd L2TAG2P (C-TAG) + * Flex: Status / Error 1 Field; Flexible Flags section 2; Timestamp Low; + * 1st L2TAG2 (C-TAG); 2nd L2TAG2 (C-TAG) + * @qw3: quad word 3 fields: + * Legacy: FD Filter ID / Flexible Bytes + * Flex: Flexible Metadata Container #2; Flexible Metadata Container #3; + * Flexible Metadata Container #4 / Timestamp High 0; Flexible + * Metadata Container #5 / Timestamp High 1; + */ +struct iavf_rx_desc { + aligned_le64 qw0; +/* The hash signature (RSS) */ +#define IAVF_RXD_LEGACY_RSS_M GENMASK_ULL(63, 32) +/* Stripped C-TAG VLAN from the receive packet */ +#define IAVF_RXD_LEGACY_L2TAG1_M GENMASK_ULL(33, 16) +/* Packet type */ +#define IAVF_RXD_FLEX_PTYPE_M GENMASK_ULL(25, 16) +/* Packet length */ +#define IAVF_RXD_FLEX_PKT_LEN_M GENMASK_ULL(45, 32) + + aligned_le64 qw1; +/* Descriptor done indication flag. */ +#define IAVF_RXD_LEGACY_DD_M BIT(0) +/* End of packet. Set to 1 if this descriptor is the last one of the packet */ +#define IAVF_RXD_LEGACY_EOP_M BIT(1) +/* L2 TAG 1 presence indication */ +#define IAVF_RXD_LEGACY_L2TAG1P_M BIT(2) +/* Detectable L3 and L4 integrity check is processed by the HW */ +#define IAVF_RXD_LEGACY_L3L4P_M BIT(3) +/* Set when an IPv6 packet contains a Destination Options Header or a Routing + * Header. + */ +#define IAVF_RXD_LEGACY_IPV6EXADD_M BIT(15) +/* Receive MAC Errors: CRC; Alignment; Oversize; Undersizes; Length error */ +#define IAVF_RXD_LEGACY_RXE_M BIT(19) +/* Checksum reports: + * - IPE: IP checksum error + * - L4E: L4 integrity error + * - EIPE: External IP header (tunneled packets) + */ +#define IAVF_RXD_LEGACY_IPE_M BIT(22) +#define IAVF_RXD_LEGACY_L4E_M BIT(23) +#define IAVF_RXD_LEGACY_EIPE_M BIT(24) +/* Set for packets that skip checksum calculation in pre-parser */ +#define IAVF_RXD_LEGACY_PPRS_M BIT(26) +/* Indicates the content in the Filter Status field */ +#define IAVF_RXD_LEGACY_FLTSTAT_M GENMASK_ULL(13, 12) +/* Packet type */ +#define IAVF_RXD_LEGACY_PTYPE_M GENMASK_ULL(37, 30) +/* Packet length */ +#define IAVF_RXD_LEGACY_LENGTH_M GENMASK_ULL(51, 38) +/* Descriptor done indication flag */ +#define IAVF_RXD_FLEX_DD_M BIT(0) +/* End of packet. Set to 1 if this descriptor is the last one of the packet */ +#define IAVF_RXD_FLEX_EOP_M BIT(1) +/* Detectable L3 and L4 integrity check is processed by the HW */ +#define IAVF_RXD_FLEX_L3L4P_M BIT(3) +/* Checksum reports: + * - IPE: IP checksum error + * - L4E: L4 integrity error + * - EIPE: External IP header (tunneled packets) + * - EUDPE: External UDP checksum error (tunneled packets) + */ +#define IAVF_RXD_FLEX_XSUM_IPE_M BIT(4) +#define IAVF_RXD_FLEX_XSUM_L4E_M BIT(5) +#define IAVF_RXD_FLEX_XSUM_EIPE_M BIT(6) +#define IAVF_RXD_FLEX_XSUM_EUDPE_M BIT(7) +/* Set when an IPv6 packet contains a Destination Options Header or a Routing + * Header. + */ +#define IAVF_RXD_FLEX_IPV6EXADD_M BIT(9) +/* Receive MAC Errors: CRC; Alignment; Oversize; Undersizes; Length error */ +#define IAVF_RXD_FLEX_RXE_M BIT(10) +/* Indicates that the RSS/HASH result is valid */ +#define IAVF_RXD_FLEX_RSS_VALID_M BIT(12) +/* L2 TAG 1 presence indication */ +#define IAVF_RXD_FLEX_L2TAG1P_M BIT(13) +/* Stripped L2 Tag from the receive packet */ +#define IAVF_RXD_FLEX_L2TAG1_M GENMASK_ULL(31, 16) +/* The hash signature (RSS) */ +#define IAVF_RXD_FLEX_RSS_HASH_M GENMASK_ULL(63, 32) + + aligned_le64 qw2; +/* L2 Tag 2 Presence */ +#define IAVF_RXD_LEGACY_L2TAG2P_M BIT(0) +/* Stripped S-TAG VLAN from the receive packet */ +#define IAVF_RXD_LEGACY_L2TAG2_M GENMASK_ULL(63, 32) +/* Stripped S-TAG VLAN from the receive packet */ +#define IAVF_RXD_FLEX_L2TAG2_2_M GENMASK_ULL(63, 48) +/* The packet is a UDP tunneled packet */ +#define IAVF_RXD_FLEX_NAT_M BIT(4) +/* L2 Tag 2 Presence */ +#define IAVF_RXD_FLEX_L2TAG2P_M BIT(11) + aligned_le64 qw3; +#define IAVF_RXD_FLEX_QW3_TSTAMP_HIGH_M GENMASK_ULL(63, 32) +} __aligned(4 * sizeof(__le64)); +static_assert(sizeof(struct iavf_rx_desc) == 32); #define IAVF_RXD_QW1_STATUS_TSYNINDX_SHIFT IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT #define IAVF_RXD_QW1_STATUS_TSYNINDX_MASK (0x3UL << \ @@ -298,22 +304,6 @@ enum iavf_rx_desc_fltstat_values { IAVF_RX_DESC_FLTSTAT_RSS_HASH = 3, }; -#define IAVF_RXD_QW1_ERROR_SHIFT 19 -#define IAVF_RXD_QW1_ERROR_MASK (0xFFUL << IAVF_RXD_QW1_ERROR_SHIFT) - -enum iavf_rx_desc_error_bits { - /* Note: These are predefined bit offsets */ - IAVF_RX_DESC_ERROR_RXE_SHIFT = 0, - IAVF_RX_DESC_ERROR_RECIPE_SHIFT = 1, - IAVF_RX_DESC_ERROR_HBO_SHIFT = 2, - IAVF_RX_DESC_ERROR_L3L4E_SHIFT = 3, /* 3 BITS */ - IAVF_RX_DESC_ERROR_IPE_SHIFT = 3, - IAVF_RX_DESC_ERROR_L4E_SHIFT = 4, - IAVF_RX_DESC_ERROR_EIPE_SHIFT = 5, - IAVF_RX_DESC_ERROR_OVERSIZE_SHIFT = 6, - IAVF_RX_DESC_ERROR_PPRS_SHIFT = 7 -}; - enum iavf_rx_desc_error_l3l4e_fcoe_masks { IAVF_RX_DESC_ERROR_L3L4E_NONE = 0, IAVF_RX_DESC_ERROR_L3L4E_PROT = 1, @@ -322,13 +312,6 @@ enum iavf_rx_desc_error_l3l4e_fcoe_masks { IAVF_RX_DESC_ERROR_L3L4E_DMAC_WARN = 4 }; -#define IAVF_RXD_QW1_PTYPE_SHIFT 30 -#define IAVF_RXD_QW1_PTYPE_MASK (0xFFULL << IAVF_RXD_QW1_PTYPE_SHIFT) - -#define IAVF_RXD_QW1_LENGTH_PBUF_SHIFT 38 -#define IAVF_RXD_QW1_LENGTH_PBUF_MASK (0x3FFFULL << \ - IAVF_RXD_QW1_LENGTH_PBUF_SHIFT) - #define IAVF_RXD_QW1_LENGTH_HBUF_SHIFT 52 #define IAVF_RXD_QW1_LENGTH_HBUF_MASK (0x7FFULL << \ IAVF_RXD_QW1_LENGTH_HBUF_SHIFT) @@ -347,6 +330,8 @@ enum iavf_rx_desc_ext_status_bits { IAVF_RX_DESC_EXT_STATUS_PELONGB_SHIFT = 11, }; +#define IAVF_RX_DESC_EXT_STATUS_L2TAG2P_M BIT(IAVF_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT) + enum iavf_rx_desc_pe_status_bits { /* Note: These are predefined bit offsets */ IAVF_RX_DESC_PE_STATUS_QPID_SHIFT = 0, /* 18 BITS */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_types.h b/drivers/net/ethernet/intel/iavf/iavf_types.h new file mode 100644 index 000000000000..a095855122bf --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_types.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2024 Intel Corporation. */ + +#ifndef _IAVF_TYPES_H_ +#define _IAVF_TYPES_H_ + +#include "iavf_types.h" + +#include <linux/avf/virtchnl.h> +#include <linux/ptp_clock_kernel.h> + +/* structure used to queue PTP commands for processing */ +struct iavf_ptp_aq_cmd { + struct list_head list; + enum virtchnl_ops v_opcode:16; + u16 msglen; + u8 msg[] __counted_by(msglen); +}; + +struct iavf_ptp { + wait_queue_head_t phc_time_waitqueue; + struct virtchnl_ptp_caps hw_caps; + struct ptp_clock_info info; + struct ptp_clock *clock; + struct list_head aq_cmds; + u64 cached_phc_time; + unsigned long cached_phc_updated; + /* Lock protecting access to the AQ command list */ + struct mutex aq_cmd_lock; + struct kernel_hwtstamp_config hwtstamp_config; + bool phc_time_ready:1; +}; + +#endif /* _IAVF_TYPES_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 15d388b431c5..a6f0e5990be2 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -4,6 +4,7 @@ #include <linux/net/intel/libie/rx.h> #include "iavf.h" +#include "iavf_ptp.h" #include "iavf_prototype.h" /** @@ -144,9 +145,11 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter) VIRTCHNL_VF_OFFLOAD_ENCAP | VIRTCHNL_VF_OFFLOAD_TC_U32 | VIRTCHNL_VF_OFFLOAD_VLAN_V2 | + VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC | VIRTCHNL_VF_OFFLOAD_CRC | VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM | VIRTCHNL_VF_OFFLOAD_REQ_QUEUES | + VIRTCHNL_VF_CAP_PTP | VIRTCHNL_VF_OFFLOAD_ADQ | VIRTCHNL_VF_OFFLOAD_USO | VIRTCHNL_VF_OFFLOAD_FDIR_PF | @@ -177,6 +180,54 @@ int iavf_send_vf_offload_vlan_v2_msg(struct iavf_adapter *adapter) NULL, 0); } +int iavf_send_vf_supported_rxdids_msg(struct iavf_adapter *adapter) +{ + adapter->aq_required &= ~IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS; + + if (!IAVF_RXDID_ALLOWED(adapter)) + return -EOPNOTSUPP; + + adapter->current_op = VIRTCHNL_OP_GET_SUPPORTED_RXDIDS; + + return iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_SUPPORTED_RXDIDS, + NULL, 0); +} + +/** + * iavf_send_vf_ptp_caps_msg - Send request for PTP capabilities + * @adapter: private adapter structure + * + * Send the VIRTCHNL_OP_1588_PTP_GET_CAPS command to the PF to request the PTP + * capabilities available to this device. This includes the following + * potential access: + * + * * READ_PHC - access to read the PTP hardware clock time + * * RX_TSTAMP - access to request Rx timestamps on all received packets + * + * The PF will reply with the same opcode a filled out copy of the + * virtchnl_ptp_caps structure which defines the specifics of which features + * are accessible to this device. + * + * Return: 0 if success, error code otherwise. + */ +int iavf_send_vf_ptp_caps_msg(struct iavf_adapter *adapter) +{ + struct virtchnl_ptp_caps hw_caps = { + .caps = VIRTCHNL_1588_PTP_CAP_READ_PHC | + VIRTCHNL_1588_PTP_CAP_RX_TSTAMP + }; + + adapter->aq_required &= ~IAVF_FLAG_AQ_GET_PTP_CAPS; + + if (!IAVF_PTP_ALLOWED(adapter)) + return -EOPNOTSUPP; + + adapter->current_op = VIRTCHNL_OP_1588_PTP_GET_CAPS; + + return iavf_send_pf_msg(adapter, VIRTCHNL_OP_1588_PTP_GET_CAPS, + (u8 *)&hw_caps, sizeof(hw_caps)); +} + /** * iavf_validate_num_queues * @adapter: adapter structure @@ -263,6 +314,40 @@ int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter) return err; } +int iavf_get_vf_supported_rxdids(struct iavf_adapter *adapter) +{ + struct iavf_arq_event_info event; + u64 rxdids; + int err; + + event.msg_buf = (u8 *)&rxdids; + event.buf_len = sizeof(rxdids); + + err = iavf_poll_virtchnl_msg(&adapter->hw, &event, + VIRTCHNL_OP_GET_SUPPORTED_RXDIDS); + if (!err) + adapter->supp_rxdids = rxdids; + + return err; +} + +int iavf_get_vf_ptp_caps(struct iavf_adapter *adapter) +{ + struct virtchnl_ptp_caps caps = {}; + struct iavf_arq_event_info event; + int err; + + event.msg_buf = (u8 *)∩︀ + event.buf_len = sizeof(caps); + + err = iavf_poll_virtchnl_msg(&adapter->hw, &event, + VIRTCHNL_OP_1588_PTP_GET_CAPS); + if (!err) + adapter->ptp.hw_caps = caps; + + return err; +} + /** * iavf_configure_queues * @adapter: adapter structure @@ -275,6 +360,7 @@ void iavf_configure_queues(struct iavf_adapter *adapter) int pairs = adapter->num_active_queues; struct virtchnl_queue_pair_info *vqpi; u32 i, max_frame; + u8 rx_flags = 0; size_t len; max_frame = LIBIE_MAX_RX_FRM_LEN(adapter->rx_rings->pp->p.offset); @@ -292,6 +378,9 @@ void iavf_configure_queues(struct iavf_adapter *adapter) if (!vqci) return; + if (iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP)) + rx_flags |= VIRTCHNL_PTP_RX_TSTAMP; + vqci->vsi_id = adapter->vsi_res->vsi_id; vqci->num_queue_pairs = pairs; vqpi = vqci->qpair; @@ -309,9 +398,12 @@ void iavf_configure_queues(struct iavf_adapter *adapter) vqpi->rxq.dma_ring_addr = adapter->rx_rings[i].dma; vqpi->rxq.max_pkt_size = max_frame; vqpi->rxq.databuffer_size = adapter->rx_rings[i].rx_buf_len; + if (IAVF_RXDID_ALLOWED(adapter)) + vqpi->rxq.rxdid = adapter->rxdid; if (CRC_OFFLOAD_ALLOWED(adapter)) vqpi->rxq.crc_disable = !!(adapter->netdev->features & NETIF_F_RXFCS); + vqpi->rxq.flags = rx_flags; vqpi++; } @@ -1402,6 +1494,67 @@ void iavf_disable_vlan_insertion_v2(struct iavf_adapter *adapter, u16 tpid) VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2); } +#if IS_ENABLED(CONFIG_PTP_1588_CLOCK) +/** + * iavf_virtchnl_send_ptp_cmd - Send one queued PTP command + * @adapter: adapter private structure + * + * De-queue one PTP command request and send the command message to the PF. + * Clear IAVF_FLAG_AQ_SEND_PTP_CMD if no more messages are left to send. + */ +void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter) +{ + struct iavf_ptp_aq_cmd *cmd; + int err; + + if (!adapter->ptp.clock) { + /* This shouldn't be possible to hit, since no messages should + * be queued if PTP is not initialized. + */ + pci_err(adapter->pdev, "PTP is not initialized\n"); + adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD; + return; + } + + mutex_lock(&adapter->ptp.aq_cmd_lock); + cmd = list_first_entry_or_null(&adapter->ptp.aq_cmds, + struct iavf_ptp_aq_cmd, list); + if (!cmd) { + /* no further PTP messages to send */ + adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD; + goto out_unlock; + } + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + pci_err(adapter->pdev, + "Cannot send PTP command %d, command %d pending\n", + cmd->v_opcode, adapter->current_op); + goto out_unlock; + } + + err = iavf_send_pf_msg(adapter, cmd->v_opcode, cmd->msg, cmd->msglen); + if (!err) { + /* Command was sent without errors, so we can remove it from + * the list and discard it. + */ + list_del(&cmd->list); + kfree(cmd); + } else { + /* We failed to send the command, try again next cycle */ + pci_err(adapter->pdev, "Failed to send PTP command %d\n", + cmd->v_opcode); + } + + if (list_empty(&adapter->ptp.aq_cmds)) + /* no further PTP messages to send */ + adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD; + +out_unlock: + mutex_unlock(&adapter->ptp.aq_cmd_lock); +} +#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ + /** * iavf_print_link_message - print link up or down * @adapter: adapter structure @@ -2098,6 +2251,37 @@ static void iavf_activate_fdir_filters(struct iavf_adapter *adapter) } /** + * iavf_virtchnl_ptp_get_time - Respond to VIRTCHNL_OP_1588_PTP_GET_TIME + * @adapter: private adapter structure + * @data: the message from the PF + * @len: length of the message from the PF + * + * Handle the VIRTCHNL_OP_1588_PTP_GET_TIME message from the PF. This message + * is sent by the PF in response to the same op as a request from the VF. + * Extract the 64bit nanoseconds time from the message and store it in + * cached_phc_time. Then, notify any thread that is waiting for the update via + * the wait queue. + */ +static void iavf_virtchnl_ptp_get_time(struct iavf_adapter *adapter, + void *data, u16 len) +{ + struct virtchnl_phc_time *msg = data; + + if (len != sizeof(*msg)) { + dev_err_once(&adapter->pdev->dev, + "Invalid VIRTCHNL_OP_1588_PTP_GET_TIME from PF. Got size %u, expected %zu\n", + len, sizeof(*msg)); + return; + } + + adapter->ptp.cached_phc_time = msg->time; + adapter->ptp.cached_phc_updated = jiffies; + adapter->ptp.phc_time_ready = true; + + wake_up(&adapter->ptp.phc_time_waitqueue); +} + +/** * iavf_virtchnl_completion * @adapter: adapter structure * @v_opcode: opcode sent by PF @@ -2509,6 +2693,25 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, aq_required; } break; + case VIRTCHNL_OP_GET_SUPPORTED_RXDIDS: + if (msglen != sizeof(u64)) + return; + + adapter->supp_rxdids = *(u64 *)msg; + + break; + case VIRTCHNL_OP_1588_PTP_GET_CAPS: + if (msglen != sizeof(adapter->ptp.hw_caps)) + return; + + adapter->ptp.hw_caps = *(struct virtchnl_ptp_caps *)msg; + + /* process any state change needed due to new capabilities */ + iavf_ptp_process_caps(adapter); + break; + case VIRTCHNL_OP_1588_PTP_GET_TIME: + iavf_virtchnl_ptp_get_time(adapter, msg, msglen); + break; case VIRTCHNL_OP_ENABLE_QUEUES: /* enable transmits */ iavf_irq_enable(adapter, true); diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c index dbdb83567364..fcb199efbea5 100644 --- a/drivers/net/ethernet/intel/ice/devlink/devlink.c +++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c @@ -1205,6 +1205,25 @@ static int ice_devlink_set_parent(struct devlink_rate *devlink_rate, return status; } +static void ice_set_min_max_msix(struct ice_pf *pf) +{ + struct devlink *devlink = priv_to_devlink(pf); + union devlink_param_value val; + int err; + + err = devl_param_driverinit_value_get(devlink, + DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN, + &val); + if (!err) + pf->msix.min = val.vu32; + + err = devl_param_driverinit_value_get(devlink, + DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX, + &val); + if (!err) + pf->msix.max = val.vu32; +} + /** * ice_devlink_reinit_up - do reinit of the given PF * @pf: pointer to the PF struct @@ -1220,6 +1239,9 @@ static int ice_devlink_reinit_up(struct ice_pf *pf) return err; } + /* load MSI-X values */ + ice_set_min_max_msix(pf); + err = ice_init_dev(pf); if (err) goto unroll_hw_init; @@ -1533,6 +1555,43 @@ static int ice_devlink_local_fwd_validate(struct devlink *devlink, u32 id, return 0; } +static int +ice_devlink_msix_max_pf_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_priv(devlink); + + if (val.vu32 > pf->hw.func_caps.common_cap.num_msix_vectors) + return -EINVAL; + + return 0; +} + +static int +ice_devlink_msix_min_pf_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + if (val.vu32 < ICE_MIN_MSIX) + return -EINVAL; + + return 0; +} + +static int ice_devlink_enable_rdma_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + struct ice_pf *pf = devlink_priv(devlink); + bool new_state = val.vbool; + + if (new_state && !test_bit(ICE_FLAG_RDMA_ENA, pf->flags)) + return -EOPNOTSUPP; + + return 0; +} + enum ice_param_id { ICE_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS, @@ -1548,6 +1607,17 @@ static const struct devlink_param ice_dvl_rdma_params[] = { ice_devlink_enable_iw_get, ice_devlink_enable_iw_set, ice_devlink_enable_iw_validate), + DEVLINK_PARAM_GENERIC(ENABLE_RDMA, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, NULL, ice_devlink_enable_rdma_validate), +}; + +static const struct devlink_param ice_dvl_msix_params[] = { + DEVLINK_PARAM_GENERIC(MSIX_VEC_PER_PF_MAX, + BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, NULL, ice_devlink_msix_max_pf_validate), + DEVLINK_PARAM_GENERIC(MSIX_VEC_PER_PF_MIN, + BIT(DEVLINK_PARAM_CMODE_DRIVERINIT), + NULL, NULL, ice_devlink_msix_min_pf_validate), }; static const struct devlink_param ice_dvl_sched_params[] = { @@ -1651,6 +1721,7 @@ void ice_devlink_unregister(struct ice_pf *pf) int ice_devlink_register_params(struct ice_pf *pf) { struct devlink *devlink = priv_to_devlink(pf); + union devlink_param_value value; struct ice_hw *hw = &pf->hw; int status; @@ -1659,10 +1730,39 @@ int ice_devlink_register_params(struct ice_pf *pf) if (status) return status; + status = devl_params_register(devlink, ice_dvl_msix_params, + ARRAY_SIZE(ice_dvl_msix_params)); + if (status) + goto unregister_rdma_params; + if (hw->func_caps.common_cap.tx_sched_topo_comp_mode_en) status = devl_params_register(devlink, ice_dvl_sched_params, ARRAY_SIZE(ice_dvl_sched_params)); + if (status) + goto unregister_msix_params; + + value.vu32 = pf->msix.max; + devl_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX, + value); + value.vu32 = pf->msix.min; + devl_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN, + value); + + value.vbool = test_bit(ICE_FLAG_RDMA_ENA, pf->flags); + devl_param_driverinit_value_set(devlink, + DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA, + value); + + return 0; +unregister_msix_params: + devl_params_unregister(devlink, ice_dvl_msix_params, + ARRAY_SIZE(ice_dvl_msix_params)); +unregister_rdma_params: + devl_params_unregister(devlink, ice_dvl_rdma_params, + ARRAY_SIZE(ice_dvl_rdma_params)); return status; } @@ -1673,6 +1773,8 @@ void ice_devlink_unregister_params(struct ice_pf *pf) devl_params_unregister(devlink, ice_dvl_rdma_params, ARRAY_SIZE(ice_dvl_rdma_params)); + devl_params_unregister(devlink, ice_dvl_msix_params, + ARRAY_SIZE(ice_dvl_msix_params)); if (hw->func_caps.common_cap.tx_sched_topo_comp_mode_en) devl_params_unregister(devlink, ice_dvl_sched_params, diff --git a/drivers/net/ethernet/intel/ice/devlink/health.c b/drivers/net/ethernet/intel/ice/devlink/health.c index ea40f7941259..19c3d37aa768 100644 --- a/drivers/net/ethernet/intel/ice/devlink/health.c +++ b/drivers/net/ethernet/intel/ice/devlink/health.c @@ -25,10 +25,10 @@ struct ice_health_status { * The below lookup requires to be sorted by code. */ -static const char *const ice_common_port_solutions = +static const char ice_common_port_solutions[] = "Check your cable connection. Change or replace the module or cable. Manually set speed and duplex."; -static const char *const ice_port_number_label = "Port Number"; -static const char *const ice_update_nvm_solution = "Update to the latest NVM image."; +static const char ice_port_number_label[] = "Port Number"; +static const char ice_update_nvm_solution[] = "Update to the latest NVM image."; static const struct ice_health_status ice_health_status_lookup[] = { {ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_STRICT, "An unsupported module was detected.", diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 71e05d30f0fd..fd083647c14a 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -97,9 +97,6 @@ #define ICE_MIN_LAN_OICR_MSIX 1 #define ICE_MIN_MSIX (ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_LAN_OICR_MSIX) #define ICE_FDIR_MSIX 2 -#define ICE_RDMA_NUM_AEQ_MSIX 4 -#define ICE_MIN_RDMA_MSIX 2 -#define ICE_ESWITCH_MSIX 1 #define ICE_NO_VSI 0xffff #define ICE_VSI_MAP_CONTIG 0 #define ICE_VSI_MAP_SCATTER 1 @@ -204,6 +201,7 @@ enum ice_feature { ICE_F_SMA_CTRL, ICE_F_CGU, ICE_F_GNSS, + ICE_F_GCS, ICE_F_ROCE_LAG, ICE_F_SRIOV_LAG, ICE_F_MBX_LIMIT, @@ -478,9 +476,6 @@ struct ice_q_vector { struct ice_ring_container rx; struct ice_ring_container tx; - cpumask_t affinity_mask; - struct irq_affinity_notify affinity_notify; - struct ice_channel *ch; char name[ICE_INT_NAME_STR_LEN]; @@ -542,6 +537,14 @@ struct ice_agg_node { u8 valid; }; +struct ice_pf_msix { + u32 cur; + u32 min; + u32 max; + u32 total; + u32 rest; +}; + struct ice_pf { struct pci_dev *pdev; struct ice_adapter *adapter; @@ -556,13 +559,7 @@ struct ice_pf { /* OS reserved IRQ details */ struct msix_entry *msix_entries; struct ice_irq_tracker irq_tracker; - /* First MSIX vector used by SR-IOV VFs. Calculated by subtracting the - * number of MSIX vectors needed for all SR-IOV VFs from the number of - * MSIX vectors allowed on this PF. - */ - u16 sriov_base_vector; - unsigned long *sriov_irq_bm; /* bitmap to track irq usage */ - u16 sriov_irq_size; /* size of the irq_bm bitmap */ + struct ice_virt_irq_tracker virt_irq_tracker; u16 ctrl_vsi_idx; /* control VSI index in pf->vsi array */ @@ -612,7 +609,7 @@ struct ice_pf { struct msi_map ll_ts_irq; /* LL_TS interrupt MSIX vector */ u16 max_pf_txqs; /* Total Tx queues PF wide */ u16 max_pf_rxqs; /* Total Rx queues PF wide */ - u16 num_lan_msix; /* Total MSIX vectors for base driver */ + struct ice_pf_msix msix; u16 num_lan_tx; /* num LAN Tx queues setup */ u16 num_lan_rx; /* num LAN Rx queues setup */ u16 next_vsi; /* Next free slot in pf->vsi[] - 0-based! */ @@ -1047,10 +1044,5 @@ static inline void ice_clear_rdma_cap(struct ice_pf *pf) clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); } -static inline enum ice_phy_model ice_get_phy_model(const struct ice_hw *hw) -{ - return hw->ptp.phy_model; -} - extern const struct xdp_metadata_ops ice_xdp_md_ops; #endif /* _ICE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c index 405ddd17de1b..2bc5c7f59844 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.c +++ b/drivers/net/ethernet/intel/ice/ice_arfs.c @@ -571,25 +571,6 @@ void ice_clear_arfs(struct ice_vsi *vsi) } /** - * ice_free_cpu_rx_rmap - free setup CPU reverse map - * @vsi: the VSI to be forwarded to - */ -void ice_free_cpu_rx_rmap(struct ice_vsi *vsi) -{ - struct net_device *netdev; - - if (!vsi || vsi->type != ICE_VSI_PF) - return; - - netdev = vsi->netdev; - if (!netdev || !netdev->rx_cpu_rmap) - return; - - free_irq_cpu_rmap(netdev->rx_cpu_rmap); - netdev->rx_cpu_rmap = NULL; -} - -/** * ice_set_cpu_rx_rmap - setup CPU reverse map for each queue * @vsi: the VSI to be forwarded to */ @@ -597,7 +578,6 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi) { struct net_device *netdev; struct ice_pf *pf; - int i; if (!vsi || vsi->type != ICE_VSI_PF) return 0; @@ -610,18 +590,7 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi) netdev_dbg(netdev, "Setup CPU RMAP: vsi type 0x%x, ifname %s, q_vectors %d\n", vsi->type, netdev->name, vsi->num_q_vectors); - netdev->rx_cpu_rmap = alloc_irq_cpu_rmap(vsi->num_q_vectors); - if (unlikely(!netdev->rx_cpu_rmap)) - return -EINVAL; - - ice_for_each_q_vector(vsi, i) - if (irq_cpu_rmap_add(netdev->rx_cpu_rmap, - vsi->q_vectors[i]->irq.virq)) { - ice_free_cpu_rx_rmap(vsi); - return -EINVAL; - } - - return 0; + return netif_enable_cpu_rmap(netdev, vsi->num_q_vectors); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.h b/drivers/net/ethernet/intel/ice/ice_arfs.h index 9669ad9bf7b5..9706293128c3 100644 --- a/drivers/net/ethernet/intel/ice/ice_arfs.h +++ b/drivers/net/ethernet/intel/ice/ice_arfs.h @@ -45,7 +45,6 @@ int ice_rx_flow_steer(struct net_device *netdev, const struct sk_buff *skb, u16 rxq_idx, u32 flow_id); void ice_clear_arfs(struct ice_vsi *vsi); -void ice_free_cpu_rx_rmap(struct ice_vsi *vsi); void ice_init_arfs(struct ice_vsi *vsi); void ice_sync_arfs_fltrs(struct ice_pf *pf); int ice_set_cpu_rx_rmap(struct ice_vsi *vsi); @@ -56,7 +55,6 @@ ice_is_arfs_using_perfect_flow(struct ice_hw *hw, enum ice_fltr_ptype flow_type); #else static inline void ice_clear_arfs(struct ice_vsi *vsi) { } -static inline void ice_free_cpu_rx_rmap(struct ice_vsi *vsi) { } static inline void ice_init_arfs(struct ice_vsi *vsi) { } static inline void ice_sync_arfs_fltrs(struct ice_pf *pf) { } static inline void ice_remove_arfs(struct ice_pf *pf) { } diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index b2af8e3586f7..6db4ad8fc70b 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -147,10 +147,6 @@ skip_alloc: q_vector->reg_idx = q_vector->irq.index; q_vector->vf_reg_idx = q_vector->irq.index; - /* only set affinity_mask if the CPU is online */ - if (cpu_online(v_idx)) - cpumask_set_cpu(v_idx, &q_vector->affinity_mask); - /* This will not be called in the driver load path because the netdev * will not be created yet. All other cases with register the NAPI * handler here (i.e. resume, reset/rebuild, etc.) @@ -276,7 +272,8 @@ static void ice_cfg_xps_tx_ring(struct ice_tx_ring *ring) if (test_and_set_bit(ICE_TX_XPS_INIT_DONE, ring->xps_state)) return; - netif_set_xps_queue(ring->netdev, &ring->q_vector->affinity_mask, + netif_set_xps_queue(ring->netdev, + &ring->q_vector->napi.config->affinity_mask, ring->q_index); } @@ -473,9 +470,6 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring) */ if (vsi->type != ICE_VSI_VF) ice_write_qrxflxp_cntxt(hw, pf_q, rxdid, 0x3, true); - else - ice_write_qrxflxp_cntxt(hw, pf_q, ICE_RXDID_LEGACY_1, 0x3, - false); /* Absolute queue number out of 2K needs to be passed */ err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q); @@ -801,13 +795,11 @@ int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi) return 0; err_out: - while (v_idx--) - ice_free_q_vector(vsi, v_idx); - dev_err(dev, "Failed to allocate %d q_vector for VSI %d, ret=%d\n", - vsi->num_q_vectors, vsi->vsi_num, err); - vsi->num_q_vectors = 0; - return err; + dev_info(dev, "Failed to allocate %d q_vectors for VSI %d, new value %d", + vsi->num_q_vectors, vsi->vsi_num, v_idx); + vsi->num_q_vectors = v_idx; + return v_idx ? 0 : err; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 7a2a2e8da8fa..59df31c2c83f 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -186,7 +186,7 @@ static int ice_set_mac_type(struct ice_hw *hw) * ice_is_generic_mac - check if device's mac_type is generic * @hw: pointer to the hardware structure * - * Return: true if mac_type is generic (with SBQ support), false if not + * Return: true if mac_type is ICE_MAC_GENERIC*, false otherwise. */ bool ice_is_generic_mac(struct ice_hw *hw) { @@ -195,120 +195,6 @@ bool ice_is_generic_mac(struct ice_hw *hw) } /** - * ice_is_e810 - * @hw: pointer to the hardware structure - * - * returns true if the device is E810 based, false if not. - */ -bool ice_is_e810(struct ice_hw *hw) -{ - return hw->mac_type == ICE_MAC_E810; -} - -/** - * ice_is_e810t - * @hw: pointer to the hardware structure - * - * returns true if the device is E810T based, false if not. - */ -bool ice_is_e810t(struct ice_hw *hw) -{ - switch (hw->device_id) { - case ICE_DEV_ID_E810C_SFP: - switch (hw->subsystem_device_id) { - case ICE_SUBDEV_ID_E810T: - case ICE_SUBDEV_ID_E810T2: - case ICE_SUBDEV_ID_E810T3: - case ICE_SUBDEV_ID_E810T4: - case ICE_SUBDEV_ID_E810T6: - case ICE_SUBDEV_ID_E810T7: - return true; - } - break; - case ICE_DEV_ID_E810C_QSFP: - switch (hw->subsystem_device_id) { - case ICE_SUBDEV_ID_E810T2: - case ICE_SUBDEV_ID_E810T3: - case ICE_SUBDEV_ID_E810T5: - return true; - } - break; - default: - break; - } - - return false; -} - -/** - * ice_is_e822 - Check if a device is E822 family device - * @hw: pointer to the hardware structure - * - * Return: true if the device is E822 based, false if not. - */ -bool ice_is_e822(struct ice_hw *hw) -{ - switch (hw->device_id) { - case ICE_DEV_ID_E822C_BACKPLANE: - case ICE_DEV_ID_E822C_QSFP: - case ICE_DEV_ID_E822C_SFP: - case ICE_DEV_ID_E822C_10G_BASE_T: - case ICE_DEV_ID_E822C_SGMII: - case ICE_DEV_ID_E822L_BACKPLANE: - case ICE_DEV_ID_E822L_SFP: - case ICE_DEV_ID_E822L_10G_BASE_T: - case ICE_DEV_ID_E822L_SGMII: - return true; - default: - return false; - } -} - -/** - * ice_is_e823 - * @hw: pointer to the hardware structure - * - * returns true if the device is E823-L or E823-C based, false if not. - */ -bool ice_is_e823(struct ice_hw *hw) -{ - switch (hw->device_id) { - case ICE_DEV_ID_E823L_BACKPLANE: - case ICE_DEV_ID_E823L_SFP: - case ICE_DEV_ID_E823L_10G_BASE_T: - case ICE_DEV_ID_E823L_1GBE: - case ICE_DEV_ID_E823L_QSFP: - case ICE_DEV_ID_E823C_BACKPLANE: - case ICE_DEV_ID_E823C_QSFP: - case ICE_DEV_ID_E823C_SFP: - case ICE_DEV_ID_E823C_10G_BASE_T: - case ICE_DEV_ID_E823C_SGMII: - return true; - default: - return false; - } -} - -/** - * ice_is_e825c - Check if a device is E825C family device - * @hw: pointer to the hardware structure - * - * Return: true if the device is E825-C based, false if not. - */ -bool ice_is_e825c(struct ice_hw *hw) -{ - switch (hw->device_id) { - case ICE_DEV_ID_E825C_BACKPLANE: - case ICE_DEV_ID_E825C_QSFP: - case ICE_DEV_ID_E825C_SFP: - case ICE_DEV_ID_E825C_SGMII: - return true; - default: - return false; - } -} - -/** * ice_is_pf_c827 - check if pf contains c827 phy * @hw: pointer to the hw struct * @@ -2271,7 +2157,8 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps, caps->nvm_unified_update); break; case ICE_AQC_CAPS_RDMA: - caps->rdma = (number == 1); + if (IS_ENABLED(CONFIG_INFINIBAND_IRDMA)) + caps->rdma = (number == 1); ice_debug(hw, ICE_DBG_INIT, "%s: rdma = %d\n", prefix, caps->rdma); break; case ICE_AQC_CAPS_MAX_MTU: @@ -2408,7 +2295,7 @@ ice_parse_1588_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p, info->tmr_index_owned = ((number & ICE_TS_TMR_IDX_OWND_M) != 0); info->tmr_index_assoc = ((number & ICE_TS_TMR_IDX_ASSOC_M) != 0); - if (!ice_is_e825c(hw)) { + if (hw->mac_type != ICE_MAC_GENERIC_3K_E825) { info->clk_freq = FIELD_GET(ICE_TS_CLK_FREQ_M, number); info->clk_src = ((number & ICE_TS_CLK_SRC_M) != 0); } else { @@ -5765,6 +5652,96 @@ ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, } /** + * ice_get_pca9575_handle - find and return the PCA9575 controller + * @hw: pointer to the hw struct + * @pca9575_handle: GPIO controller's handle + * + * Find and return the GPIO controller's handle in the netlist. + * When found - the value will be cached in the hw structure and following calls + * will return cached value. + * + * Return: 0 on success, -ENXIO when there's no PCA9575 present. + */ +int ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle) +{ + struct ice_aqc_get_link_topo *cmd; + struct ice_aq_desc desc; + int err; + u8 idx; + + /* If handle was read previously return cached value */ + if (hw->io_expander_handle) { + *pca9575_handle = hw->io_expander_handle; + return 0; + } + +#define SW_PCA9575_SFP_TOPO_IDX 2 +#define SW_PCA9575_QSFP_TOPO_IDX 1 + + /* Check if the SW IO expander controlling SMA exists in the netlist. */ + if (hw->device_id == ICE_DEV_ID_E810C_SFP) + idx = SW_PCA9575_SFP_TOPO_IDX; + else if (hw->device_id == ICE_DEV_ID_E810C_QSFP) + idx = SW_PCA9575_QSFP_TOPO_IDX; + else + return -ENXIO; + + /* If handle was not detected read it from the netlist */ + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo); + cmd = &desc.params.get_link_topo; + cmd->addr.topo_params.node_type_ctx = + ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL; + cmd->addr.topo_params.index = idx; + + err = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); + if (err) + return -ENXIO; + + /* Verify if we found the right IO expander type */ + if (desc.params.get_link_topo.node_part_num != + ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575) + return -ENXIO; + + /* If present save the handle and return it */ + hw->io_expander_handle = + le16_to_cpu(desc.params.get_link_topo.addr.handle); + *pca9575_handle = hw->io_expander_handle; + + return 0; +} + +/** + * ice_read_pca9575_reg - read the register from the PCA9575 controller + * @hw: pointer to the hw struct + * @offset: GPIO controller register offset + * @data: pointer to data to be read from the GPIO controller + * + * Return: 0 on success, negative error code otherwise. + */ +int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data) +{ + struct ice_aqc_link_topo_addr link_topo; + __le16 addr; + u16 handle; + int err; + + memset(&link_topo, 0, sizeof(link_topo)); + + err = ice_get_pca9575_handle(hw, &handle); + if (err) + return err; + + link_topo.handle = cpu_to_le16(handle); + link_topo.topo_params.node_type_ctx = + FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, + ICE_AQC_LINK_TOPO_NODE_CTX_PROVIDED); + + addr = cpu_to_le16((u16)offset); + + return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL); +} + +/** * ice_aq_set_gpio * @hw: pointer to the hw struct * @gpio_ctrl_handle: GPIO controller node handle diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 15ba38543738..9b00aa0ddf10 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -131,7 +131,6 @@ int ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags, struct ice_sq_cd *cd); bool ice_is_generic_mac(struct ice_hw *hw); -bool ice_is_e810(struct ice_hw *hw); int ice_clear_pf_cfg(struct ice_hw *hw); int ice_aq_set_phy_cfg(struct ice_hw *hw, struct ice_port_info *pi, @@ -276,10 +275,6 @@ ice_stat_update40(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, void ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat); -bool ice_is_e810t(struct ice_hw *hw); -bool ice_is_e822(struct ice_hw *hw); -bool ice_is_e823(struct ice_hw *hw); -bool ice_is_e825c(struct ice_hw *hw); int ice_sched_query_elem(struct ice_hw *hw, u32 node_teid, struct ice_aqc_txsched_elem_data *buf); @@ -306,5 +301,7 @@ int ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, u16 bus_addr, __le16 addr, u8 params, const u8 *data, struct ice_sq_cd *cd); +int ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle); +int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data); bool ice_fw_supports_report_dflt_cfg(struct ice_hw *hw); #endif /* _ICE_COMMON_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c index 03988be03729..69d5b1a28491 100644 --- a/drivers/net/ethernet/intel/ice/ice_ddp.c +++ b/drivers/net/ethernet/intel/ice/ice_ddp.c @@ -2345,14 +2345,14 @@ ice_get_set_tx_topo(struct ice_hw *hw, u8 *buf, u16 buf_size, cmd->set_flags |= ICE_AQC_TX_TOPO_FLAGS_SRC_RAM | ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW; - if (ice_is_e825c(hw)) + if (hw->mac_type == ICE_MAC_GENERIC_3K_E825) desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); } else { ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_tx_topo); cmd->get_flags = ICE_AQC_TX_TOPO_GET_RAM; } - if (!ice_is_e825c(hw)) + if (hw->mac_type != ICE_MAC_GENERIC_3K_E825) desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd); diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c index 8d806d8ad761..bce3ad6ca2a6 100644 --- a/drivers/net/ethernet/intel/ice/ice_dpll.c +++ b/drivers/net/ethernet/intel/ice/ice_dpll.c @@ -95,7 +95,7 @@ ice_dpll_pin_freq_set(struct ice_pf *pf, struct ice_dpll_pin *pin, } if (ret) { NL_SET_ERR_MSG_FMT(extack, - "err:%d %s failed to set pin freq:%u on pin:%u\n", + "err:%d %s failed to set pin freq:%u on pin:%u", ret, ice_aq_str(pf->hw.adminq.sq_last_status), freq, pin->idx); @@ -322,7 +322,7 @@ ice_dpll_pin_enable(struct ice_hw *hw, struct ice_dpll_pin *pin, } if (ret) NL_SET_ERR_MSG_FMT(extack, - "err:%d %s failed to enable %s pin:%u\n", + "err:%d %s failed to enable %s pin:%u", ret, ice_aq_str(hw->adminq.sq_last_status), pin_type_name[pin_type], pin->idx); @@ -367,7 +367,7 @@ ice_dpll_pin_disable(struct ice_hw *hw, struct ice_dpll_pin *pin, } if (ret) NL_SET_ERR_MSG_FMT(extack, - "err:%d %s failed to disable %s pin:%u\n", + "err:%d %s failed to disable %s pin:%u", ret, ice_aq_str(hw->adminq.sq_last_status), pin_type_name[pin_type], pin->idx); @@ -479,7 +479,7 @@ ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin, err: if (extack) NL_SET_ERR_MSG_FMT(extack, - "err:%d %s failed to update %s pin:%u\n", + "err:%d %s failed to update %s pin:%u", ret, ice_aq_str(pf->hw.adminq.sq_last_status), pin_type_name[pin_type], pin->idx); @@ -518,7 +518,7 @@ ice_dpll_hw_input_prio_set(struct ice_pf *pf, struct ice_dpll *dpll, (u8)prio); if (ret) NL_SET_ERR_MSG_FMT(extack, - "err:%d %s failed to set pin prio:%u on pin:%u\n", + "err:%d %s failed to set pin prio:%u on pin:%u", ret, ice_aq_str(pf->hw.adminq.sq_last_status), prio, pin->idx); @@ -1004,7 +1004,7 @@ ice_dpll_pin_phase_adjust_set(const struct dpll_pin *pin, void *pin_priv, mutex_unlock(&pf->dplls.lock); if (ret) NL_SET_ERR_MSG_FMT(extack, - "err:%d %s failed to set pin phase_adjust:%d for pin:%u on dpll:%u\n", + "err:%d %s failed to set pin phase_adjust:%d for pin:%u on dpll:%u", ret, ice_aq_str(pf->hw.adminq.sq_last_status), phase_adjust, p->idx, d->dpll_idx); @@ -1362,7 +1362,7 @@ ice_dpll_rclk_state_on_pin_set(const struct dpll_pin *pin, void *pin_priv, &p->freq); if (ret) NL_SET_ERR_MSG_FMT(extack, - "err:%d %s failed to set pin state:%u for pin:%u on parent:%u\n", + "err:%d %s failed to set pin state:%u for pin:%u on parent:%u", ret, ice_aq_str(pf->hw.adminq.sq_last_status), state, p->idx, parent->idx); diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index f241493a6ac8..7c2dc347e4e5 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -3788,8 +3788,7 @@ ice_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info) */ static int ice_get_max_txq(struct ice_pf *pf) { - return min3(pf->num_lan_msix, (u16)num_online_cpus(), - (u16)pf->hw.func_caps.common_cap.num_txq); + return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_txq); } /** @@ -3798,8 +3797,7 @@ static int ice_get_max_txq(struct ice_pf *pf) */ static int ice_get_max_rxq(struct ice_pf *pf) { - return min3(pf->num_lan_msix, (u16)num_online_cpus(), - (u16)pf->hw.func_caps.common_cap.num_rxq); + return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_rxq); } /** @@ -3817,8 +3815,7 @@ static u32 ice_get_combined_cnt(struct ice_vsi *vsi) ice_for_each_q_vector(vsi, q_idx) { struct ice_q_vector *q_vector = vsi->q_vectors[q_idx]; - if (q_vector->rx.rx_ring && q_vector->tx.tx_ring) - combined++; + combined += min(q_vector->num_ring_tx, q_vector->num_ring_rx); } return combined; @@ -4773,7 +4770,7 @@ static const struct ethtool_ops ice_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_USE_ADAPTIVE | ETHTOOL_COALESCE_RX_USECS_HIGH, - .cap_rss_sym_xor_supported = true, + .supported_input_xfrm = RXH_XFRM_SYM_XOR, .rxfh_per_ctx_key = true, .get_link_ksettings = ice_get_link_ksettings, .set_link_ksettings = ice_set_link_ksettings, diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c index ee9862ddfe15..1d118171de37 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c @@ -1605,22 +1605,19 @@ void ice_fdir_replay_fltrs(struct ice_pf *pf) */ int ice_fdir_create_dflt_rules(struct ice_pf *pf) { + const enum ice_fltr_ptype dflt_rules[] = { + ICE_FLTR_PTYPE_NONF_IPV4_TCP, ICE_FLTR_PTYPE_NONF_IPV4_UDP, + ICE_FLTR_PTYPE_NONF_IPV6_TCP, ICE_FLTR_PTYPE_NONF_IPV6_UDP, + }; int err; /* Create perfect TCP and UDP rules in hardware. */ - err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV4_TCP); - if (err) - return err; - - err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV4_UDP); - if (err) - return err; + for (int i = 0; i < ARRAY_SIZE(dflt_rules); i++) { + err = ice_create_init_fdir_rule(pf, dflt_rules[i]); - err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV6_TCP); - if (err) - return err; - - err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV6_UDP); + if (err) + break; + } return err; } diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c index b2148dbe49b2..6b26290452d4 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.c +++ b/drivers/net/ethernet/intel/ice/ice_gnss.c @@ -381,32 +381,23 @@ void ice_gnss_exit(struct ice_pf *pf) } /** - * ice_gnss_is_gps_present - Check if GPS HW is present + * ice_gnss_is_module_present - Check if GNSS HW is present * @hw: pointer to HW struct + * + * Return: true when GNSS is present, false otherwise. */ -bool ice_gnss_is_gps_present(struct ice_hw *hw) +bool ice_gnss_is_module_present(struct ice_hw *hw) { - if (!hw->func_caps.ts_func_info.src_tmr_owned) - return false; + int err; + u8 data; - if (!ice_is_gps_in_netlist(hw)) + if (!hw->func_caps.ts_func_info.src_tmr_owned || + !ice_is_gps_in_netlist(hw)) return false; -#if IS_ENABLED(CONFIG_PTP_1588_CLOCK) - if (ice_is_e810t(hw)) { - int err; - u8 data; - - err = ice_read_pca9575_reg(hw, ICE_PCA9575_P0_IN, &data); - if (err || !!(data & ICE_P0_GNSS_PRSNT_N)) - return false; - } else { - return false; - } -#else - if (!ice_is_e810t(hw)) + err = ice_read_pca9575_reg(hw, ICE_PCA9575_P0_IN, &data); + if (err || !!(data & ICE_P0_GNSS_PRSNT_N)) return false; -#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ return true; } diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.h b/drivers/net/ethernet/intel/ice/ice_gnss.h index 75e567ad7059..15daf603ed7b 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.h +++ b/drivers/net/ethernet/intel/ice/ice_gnss.h @@ -37,11 +37,11 @@ struct gnss_serial { #if IS_ENABLED(CONFIG_GNSS) void ice_gnss_init(struct ice_pf *pf); void ice_gnss_exit(struct ice_pf *pf); -bool ice_gnss_is_gps_present(struct ice_hw *hw); +bool ice_gnss_is_module_present(struct ice_hw *hw); #else static inline void ice_gnss_init(struct ice_pf *pf) { } static inline void ice_gnss_exit(struct ice_pf *pf) { } -static inline bool ice_gnss_is_gps_present(struct ice_hw *hw) +static inline bool ice_gnss_is_module_present(struct ice_hw *hw) { return false; } diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index dc88aea9f473..aa4bfbcf85d2 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -541,10 +541,22 @@ #define PFPM_WUS_MAG_M BIT(1) #define PFPM_WUS_MNG_M BIT(3) #define PFPM_WUS_FW_RST_WK_M BIT(31) +#define E830_PRTMAC_TS_TX_MEM_VALID_H 0x001E2020 +#define E830_PRTMAC_TS_TX_MEM_VALID_L 0x001E2000 #define E830_PRTMAC_CL01_PS_QNT 0x001E32A0 #define E830_PRTMAC_CL01_PS_QNT_CL0_M GENMASK(15, 0) #define E830_PRTMAC_CL01_QNT_THR 0x001E3320 #define E830_PRTMAC_CL01_QNT_THR_CL0_M GENMASK(15, 0) +#define E830_PRTTSYN_TXTIME_H(_i) (0x001E5800 + ((_i) * 32)) +#define E830_PRTTSYN_TXTIME_L(_i) (0x001E5000 + ((_i) * 32)) +#define E830_GLPTM_ART_CTL 0x00088B50 +#define E830_GLPTM_ART_CTL_ACTIVE_M BIT(0) +#define E830_GLPTM_ART_TIME_H 0x00088B54 +#define E830_GLPTM_ART_TIME_L 0x00088B58 +#define E830_GLTSYN_PTMTIME_H(_i) (0x00088B48 + ((_i) * 4)) +#define E830_GLTSYN_PTMTIME_L(_i) (0x00088B40 + ((_i) * 4)) +#define E830_PFPTM_SEM 0x00088B00 +#define E830_PFPTM_SEM_BUSY_M BIT(0) #define VFINT_DYN_CTLN(_i) (0x00003800 + ((_i) * 4)) #define VFINT_DYN_CTLN_CLEARPBA_M BIT(1) #define E830_MBX_PF_IN_FLIGHT_VF_MSGS_THRESH 0x00234000 diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c index 145b27f2a4ce..bab3e81cad5d 100644 --- a/drivers/net/ethernet/intel/ice/ice_idc.c +++ b/drivers/net/ethernet/intel/ice/ice_idc.c @@ -228,61 +228,34 @@ void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos) } EXPORT_SYMBOL_GPL(ice_get_qos_params); -/** - * ice_alloc_rdma_qvectors - Allocate vector resources for RDMA driver - * @pf: board private structure to initialize - */ -static int ice_alloc_rdma_qvectors(struct ice_pf *pf) +int ice_alloc_rdma_qvector(struct ice_pf *pf, struct msix_entry *entry) { - if (ice_is_rdma_ena(pf)) { - int i; - - pf->msix_entries = kcalloc(pf->num_rdma_msix, - sizeof(*pf->msix_entries), - GFP_KERNEL); - if (!pf->msix_entries) - return -ENOMEM; + struct msi_map map = ice_alloc_irq(pf, true); - /* RDMA is the only user of pf->msix_entries array */ - pf->rdma_base_vector = 0; - - for (i = 0; i < pf->num_rdma_msix; i++) { - struct msix_entry *entry = &pf->msix_entries[i]; - struct msi_map map; + if (map.index < 0) + return -ENOMEM; - map = ice_alloc_irq(pf, false); - if (map.index < 0) - break; + entry->entry = map.index; + entry->vector = map.virq; - entry->entry = map.index; - entry->vector = map.virq; - } - } return 0; } +EXPORT_SYMBOL_GPL(ice_alloc_rdma_qvector); /** * ice_free_rdma_qvector - free vector resources reserved for RDMA driver * @pf: board private structure to initialize + * @entry: MSI-X entry to be removed */ -static void ice_free_rdma_qvector(struct ice_pf *pf) +void ice_free_rdma_qvector(struct ice_pf *pf, struct msix_entry *entry) { - int i; - - if (!pf->msix_entries) - return; - - for (i = 0; i < pf->num_rdma_msix; i++) { - struct msi_map map; + struct msi_map map; - map.index = pf->msix_entries[i].entry; - map.virq = pf->msix_entries[i].vector; - ice_free_irq(pf, map); - } - - kfree(pf->msix_entries); - pf->msix_entries = NULL; + map.index = entry->entry; + map.virq = entry->vector; + ice_free_irq(pf, map); } +EXPORT_SYMBOL_GPL(ice_free_rdma_qvector); /** * ice_adev_release - function to be mapped to AUX dev's release op @@ -382,12 +355,6 @@ int ice_init_rdma(struct ice_pf *pf) return -ENOMEM; } - /* Reserve vector resources */ - ret = ice_alloc_rdma_qvectors(pf); - if (ret < 0) { - dev_err(dev, "failed to reserve vectors for RDMA\n"); - goto err_reserve_rdma_qvector; - } pf->rdma_mode |= IIDC_RDMA_PROTOCOL_ROCEV2; ret = ice_plug_aux_dev(pf); if (ret) @@ -395,8 +362,6 @@ int ice_init_rdma(struct ice_pf *pf) return 0; err_plug_aux_dev: - ice_free_rdma_qvector(pf); -err_reserve_rdma_qvector: pf->adev = NULL; xa_erase(&ice_aux_id, pf->aux_idx); return ret; @@ -412,6 +377,5 @@ void ice_deinit_rdma(struct ice_pf *pf) return; ice_unplug_aux_dev(pf); - ice_free_rdma_qvector(pf); xa_erase(&ice_aux_id, pf->aux_idx); } diff --git a/drivers/net/ethernet/intel/ice/ice_irq.c b/drivers/net/ethernet/intel/ice/ice_irq.c index ad82ff7d1995..30801fd375f0 100644 --- a/drivers/net/ethernet/intel/ice/ice_irq.c +++ b/drivers/net/ethernet/intel/ice/ice_irq.c @@ -20,6 +20,19 @@ ice_init_irq_tracker(struct ice_pf *pf, unsigned int max_vectors, xa_init_flags(&pf->irq_tracker.entries, XA_FLAGS_ALLOC); } +static int +ice_init_virt_irq_tracker(struct ice_pf *pf, u32 base, u32 num_entries) +{ + pf->virt_irq_tracker.bm = bitmap_zalloc(num_entries, GFP_KERNEL); + if (!pf->virt_irq_tracker.bm) + return -ENOMEM; + + pf->virt_irq_tracker.num_entries = num_entries; + pf->virt_irq_tracker.base = base; + + return 0; +} + /** * ice_deinit_irq_tracker - free xarray tracker * @pf: board private structure @@ -29,6 +42,11 @@ static void ice_deinit_irq_tracker(struct ice_pf *pf) xa_destroy(&pf->irq_tracker.entries); } +static void ice_deinit_virt_irq_tracker(struct ice_pf *pf) +{ + bitmap_free(pf->virt_irq_tracker.bm); +} + /** * ice_free_irq_res - free a block of resources * @pf: board private structure @@ -45,7 +63,7 @@ static void ice_free_irq_res(struct ice_pf *pf, u16 index) /** * ice_get_irq_res - get an interrupt resource * @pf: board private structure - * @dyn_only: force entry to be dynamically allocated + * @dyn_allowed: allow entry to be dynamically allocated * * Allocate new irq entry in the free slot of the tracker. Since xarray * is used, always allocate new entry at the lowest possible index. Set @@ -53,11 +71,12 @@ static void ice_free_irq_res(struct ice_pf *pf, u16 index) * * Returns allocated irq entry or NULL on failure. */ -static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only) +static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, + bool dyn_allowed) { - struct xa_limit limit = { .max = pf->irq_tracker.num_entries, + struct xa_limit limit = { .max = pf->irq_tracker.num_entries - 1, .min = 0 }; - unsigned int num_static = pf->irq_tracker.num_static; + unsigned int num_static = pf->irq_tracker.num_static - 1; struct ice_irq_entry *entry; unsigned int index; int ret; @@ -66,9 +85,9 @@ static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only) if (!entry) return NULL; - /* skip preallocated entries if the caller says so */ - if (dyn_only) - limit.min = num_static; + /* only already allocated if the caller says so */ + if (!dyn_allowed) + limit.max = num_static; ret = xa_alloc(&pf->irq_tracker.entries, &index, entry, limit, GFP_KERNEL); @@ -78,161 +97,18 @@ static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only) entry = NULL; } else { entry->index = index; - entry->dynamic = index >= num_static; + entry->dynamic = index > num_static; } return entry; } -/** - * ice_reduce_msix_usage - Reduce usage of MSI-X vectors - * @pf: board private structure - * @v_remain: number of remaining MSI-X vectors to be distributed - * - * Reduce the usage of MSI-X vectors when entire request cannot be fulfilled. - * pf->num_lan_msix and pf->num_rdma_msix values are set based on number of - * remaining vectors. - */ -static void ice_reduce_msix_usage(struct ice_pf *pf, int v_remain) -{ - int v_rdma; - - if (!ice_is_rdma_ena(pf)) { - pf->num_lan_msix = v_remain; - return; - } - - /* RDMA needs at least 1 interrupt in addition to AEQ MSIX */ - v_rdma = ICE_RDMA_NUM_AEQ_MSIX + 1; - - if (v_remain < ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_RDMA_MSIX) { - dev_warn(ice_pf_to_dev(pf), "Not enough MSI-X vectors to support RDMA.\n"); - clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); - - pf->num_rdma_msix = 0; - pf->num_lan_msix = ICE_MIN_LAN_TXRX_MSIX; - } else if ((v_remain < ICE_MIN_LAN_TXRX_MSIX + v_rdma) || - (v_remain - v_rdma < v_rdma)) { - /* Support minimum RDMA and give remaining vectors to LAN MSIX - */ - pf->num_rdma_msix = ICE_MIN_RDMA_MSIX; - pf->num_lan_msix = v_remain - ICE_MIN_RDMA_MSIX; - } else { - /* Split remaining MSIX with RDMA after accounting for AEQ MSIX - */ - pf->num_rdma_msix = (v_remain - ICE_RDMA_NUM_AEQ_MSIX) / 2 + - ICE_RDMA_NUM_AEQ_MSIX; - pf->num_lan_msix = v_remain - pf->num_rdma_msix; - } -} - -/** - * ice_ena_msix_range - Request a range of MSIX vectors from the OS - * @pf: board private structure - * - * Compute the number of MSIX vectors wanted and request from the OS. Adjust - * device usage if there are not enough vectors. Return the number of vectors - * reserved or negative on failure. - */ -static int ice_ena_msix_range(struct ice_pf *pf) +#define ICE_RDMA_AEQ_MSIX 1 +static int ice_get_default_msix_amount(struct ice_pf *pf) { - int num_cpus, hw_num_msix, v_other, v_wanted, v_actual; - struct device *dev = ice_pf_to_dev(pf); - int err; - - hw_num_msix = pf->hw.func_caps.common_cap.num_msix_vectors; - num_cpus = num_online_cpus(); - - /* LAN miscellaneous handler */ - v_other = ICE_MIN_LAN_OICR_MSIX; - - /* Flow Director */ - if (test_bit(ICE_FLAG_FD_ENA, pf->flags)) - v_other += ICE_FDIR_MSIX; - - /* switchdev */ - v_other += ICE_ESWITCH_MSIX; - - v_wanted = v_other; - - /* LAN traffic */ - pf->num_lan_msix = num_cpus; - v_wanted += pf->num_lan_msix; - - /* RDMA auxiliary driver */ - if (ice_is_rdma_ena(pf)) { - pf->num_rdma_msix = num_cpus + ICE_RDMA_NUM_AEQ_MSIX; - v_wanted += pf->num_rdma_msix; - } - - if (v_wanted > hw_num_msix) { - int v_remain; - - dev_warn(dev, "not enough device MSI-X vectors. wanted = %d, available = %d\n", - v_wanted, hw_num_msix); - - if (hw_num_msix < ICE_MIN_MSIX) { - err = -ERANGE; - goto exit_err; - } - - v_remain = hw_num_msix - v_other; - if (v_remain < ICE_MIN_LAN_TXRX_MSIX) { - v_other = ICE_MIN_MSIX - ICE_MIN_LAN_TXRX_MSIX; - v_remain = ICE_MIN_LAN_TXRX_MSIX; - } - - ice_reduce_msix_usage(pf, v_remain); - v_wanted = pf->num_lan_msix + pf->num_rdma_msix + v_other; - - dev_notice(dev, "Reducing request to %d MSI-X vectors for LAN traffic.\n", - pf->num_lan_msix); - if (ice_is_rdma_ena(pf)) - dev_notice(dev, "Reducing request to %d MSI-X vectors for RDMA.\n", - pf->num_rdma_msix); - } - - /* actually reserve the vectors */ - v_actual = pci_alloc_irq_vectors(pf->pdev, ICE_MIN_MSIX, v_wanted, - PCI_IRQ_MSIX); - if (v_actual < 0) { - dev_err(dev, "unable to reserve MSI-X vectors\n"); - err = v_actual; - goto exit_err; - } - - if (v_actual < v_wanted) { - dev_warn(dev, "not enough OS MSI-X vectors. requested = %d, obtained = %d\n", - v_wanted, v_actual); - - if (v_actual < ICE_MIN_MSIX) { - /* error if we can't get minimum vectors */ - pci_free_irq_vectors(pf->pdev); - err = -ERANGE; - goto exit_err; - } else { - int v_remain = v_actual - v_other; - - if (v_remain < ICE_MIN_LAN_TXRX_MSIX) - v_remain = ICE_MIN_LAN_TXRX_MSIX; - - ice_reduce_msix_usage(pf, v_remain); - - dev_notice(dev, "Enabled %d MSI-X vectors for LAN traffic.\n", - pf->num_lan_msix); - - if (ice_is_rdma_ena(pf)) - dev_notice(dev, "Enabled %d MSI-X vectors for RDMA.\n", - pf->num_rdma_msix); - } - } - - return v_actual; - -exit_err: - pf->num_rdma_msix = 0; - pf->num_lan_msix = 0; - return err; + return ICE_MIN_LAN_OICR_MSIX + num_online_cpus() + + (test_bit(ICE_FLAG_FD_ENA, pf->flags) ? ICE_FDIR_MSIX : 0) + + (ice_is_rdma_ena(pf) ? num_online_cpus() + ICE_RDMA_AEQ_MSIX : 0); } /** @@ -243,6 +119,7 @@ void ice_clear_interrupt_scheme(struct ice_pf *pf) { pci_free_irq_vectors(pf->pdev); ice_deinit_irq_tracker(pf); + ice_deinit_virt_irq_tracker(pf); } /** @@ -252,27 +129,38 @@ void ice_clear_interrupt_scheme(struct ice_pf *pf) int ice_init_interrupt_scheme(struct ice_pf *pf) { int total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors; - int vectors, max_vectors; + int vectors; - vectors = ice_ena_msix_range(pf); + /* load default PF MSI-X range */ + if (!pf->msix.min) + pf->msix.min = ICE_MIN_MSIX; - if (vectors < 0) - return -ENOMEM; + if (!pf->msix.max) + pf->msix.max = min(total_vectors, + ice_get_default_msix_amount(pf)); + + pf->msix.total = total_vectors; + pf->msix.rest = total_vectors - pf->msix.max; if (pci_msix_can_alloc_dyn(pf->pdev)) - max_vectors = total_vectors; + vectors = pf->msix.min; else - max_vectors = vectors; + vectors = pf->msix.max; + + vectors = pci_alloc_irq_vectors(pf->pdev, pf->msix.min, vectors, + PCI_IRQ_MSIX); + if (vectors < 0) + return vectors; - ice_init_irq_tracker(pf, max_vectors, vectors); + ice_init_irq_tracker(pf, pf->msix.max, vectors); - return 0; + return ice_init_virt_irq_tracker(pf, pf->msix.max, pf->msix.rest); } /** * ice_alloc_irq - Allocate new interrupt vector * @pf: board private structure - * @dyn_only: force dynamic allocation of the interrupt + * @dyn_allowed: allow dynamic allocation of the interrupt * * Allocate new interrupt vector for a given owner id. * return struct msi_map with interrupt details and track @@ -285,27 +173,22 @@ int ice_init_interrupt_scheme(struct ice_pf *pf) * interrupt will be allocated with pci_msix_alloc_irq_at. * * Some callers may only support dynamically allocated interrupts. - * This is indicated with dyn_only flag. + * This is indicated with dyn_allowed flag. * * On failure, return map with negative .index. The caller * is expected to check returned map index. * */ -struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_only) +struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_allowed) { - int sriov_base_vector = pf->sriov_base_vector; struct msi_map map = { .index = -ENOENT }; struct device *dev = ice_pf_to_dev(pf); struct ice_irq_entry *entry; - entry = ice_get_irq_res(pf, dyn_only); + entry = ice_get_irq_res(pf, dyn_allowed); if (!entry) return map; - /* fail if we're about to violate SRIOV vectors space */ - if (sriov_base_vector && entry->index >= sriov_base_vector) - goto exit_free_res; - if (pci_msix_can_alloc_dyn(pf->pdev) && entry->dynamic) { map = pci_msix_alloc_irq_at(pf->pdev, entry->index, NULL); if (map.index < 0) @@ -353,26 +236,40 @@ void ice_free_irq(struct ice_pf *pf, struct msi_map map) } /** - * ice_get_max_used_msix_vector - Get the max used interrupt vector - * @pf: board private structure + * ice_virt_get_irqs - get irqs for SR-IOV usacase + * @pf: pointer to PF structure + * @needed: number of irqs to get * - * Return index of maximum used interrupt vectors with respect to the - * beginning of the MSIX table. Take into account that some interrupts - * may have been dynamically allocated after MSIX was initially enabled. + * This returns the first MSI-X vector index in PF space that is used by this + * VF. This index is used when accessing PF relative registers such as + * GLINT_VECT2FUNC and GLINT_DYN_CTL. + * This will always be the OICR index in the AVF driver so any functionality + * using vf->first_vector_idx for queue configuration_id: id of VF which will + * use this irqs */ -int ice_get_max_used_msix_vector(struct ice_pf *pf) +int ice_virt_get_irqs(struct ice_pf *pf, u32 needed) { - unsigned long start, index, max_idx; - void *entry; + int res = bitmap_find_next_zero_area(pf->virt_irq_tracker.bm, + pf->virt_irq_tracker.num_entries, + 0, needed, 0); - /* Treat all preallocated interrupts as used */ - start = pf->irq_tracker.num_static; - max_idx = start - 1; + if (res >= pf->virt_irq_tracker.num_entries) + return -ENOENT; - xa_for_each_start(&pf->irq_tracker.entries, index, entry, start) { - if (index > max_idx) - max_idx = index; - } + bitmap_set(pf->virt_irq_tracker.bm, res, needed); + + /* conversion from number in bitmap to global irq index */ + return res + pf->virt_irq_tracker.base; +} - return max_idx; +/** + * ice_virt_free_irqs - free irqs used by the VF + * @pf: pointer to PF structure + * @index: first index to be free + * @irqs: number of irqs to free + */ +void ice_virt_free_irqs(struct ice_pf *pf, u32 index, u32 irqs) +{ + bitmap_clear(pf->virt_irq_tracker.bm, index - pf->virt_irq_tracker.base, + irqs); } diff --git a/drivers/net/ethernet/intel/ice/ice_irq.h b/drivers/net/ethernet/intel/ice/ice_irq.h index f35efc08575e..b2f9dbafd57e 100644 --- a/drivers/net/ethernet/intel/ice/ice_irq.h +++ b/drivers/net/ethernet/intel/ice/ice_irq.h @@ -15,11 +15,22 @@ struct ice_irq_tracker { u16 num_static; /* preallocated entries */ }; +struct ice_virt_irq_tracker { + unsigned long *bm; /* bitmap to track irq usage */ + u32 num_entries; + /* First MSIX vector used by SR-IOV VFs. Calculated by subtracting the + * number of MSIX vectors needed for all SR-IOV VFs from the number of + * MSIX vectors allowed on this PF. + */ + u32 base; +}; + int ice_init_interrupt_scheme(struct ice_pf *pf); void ice_clear_interrupt_scheme(struct ice_pf *pf); struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_only); void ice_free_irq(struct ice_pf *pf, struct msi_map map); -int ice_get_max_used_msix_vector(struct ice_pf *pf); +int ice_virt_get_irqs(struct ice_pf *pf, u32 needed); +void ice_virt_free_irqs(struct ice_pf *pf, u32 index, u32 irqs); #endif diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index 1479b45738af..77ba26538b07 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -229,7 +229,7 @@ struct ice_32b_rx_flex_desc_nic { __le16 status_error1; u8 flexi_flags2; u8 ts_low; - __le16 l2tag2_1st; + __le16 raw_csum; __le16 l2tag2_2nd; /* Qword 3 */ @@ -478,10 +478,15 @@ enum ice_tx_desc_len_fields { struct ice_tx_ctx_desc { __le32 tunneling_params; __le16 l2tag2; - __le16 rsvd; + __le16 gcs; __le64 qw1; }; +#define ICE_TX_GCS_DESC_START_M GENMASK(7, 0) +#define ICE_TX_GCS_DESC_OFFSET_M GENMASK(11, 8) +#define ICE_TX_GCS_DESC_TYPE_M GENMASK(14, 12) +#define ICE_TX_GCS_DESC_CSUM_PSH 1 + #define ICE_TXD_CTX_QW1_CMD_S 4 #define ICE_TXD_CTX_QW1_CMD_M (0x7FUL << ICE_TXD_CTX_QW1_CMD_S) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index d0faa087793d..0bcf9d127ac9 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -157,6 +157,16 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi) } } +static u16 ice_get_rxq_count(struct ice_pf *pf) +{ + return min(ice_get_avail_rxq_count(pf), num_online_cpus()); +} + +static u16 ice_get_txq_count(struct ice_pf *pf) +{ + return min(ice_get_avail_txq_count(pf), num_online_cpus()); +} + /** * ice_vsi_set_num_qs - Set number of queues, descriptors and vectors for a VSI * @vsi: the VSI being configured @@ -178,9 +188,7 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi) vsi->alloc_txq = vsi->req_txq; vsi->num_txq = vsi->req_txq; } else { - vsi->alloc_txq = min3(pf->num_lan_msix, - ice_get_avail_txq_count(pf), - (u16)num_online_cpus()); + vsi->alloc_txq = ice_get_txq_count(pf); } pf->num_lan_tx = vsi->alloc_txq; @@ -193,17 +201,13 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi) vsi->alloc_rxq = vsi->req_rxq; vsi->num_rxq = vsi->req_rxq; } else { - vsi->alloc_rxq = min3(pf->num_lan_msix, - ice_get_avail_rxq_count(pf), - (u16)num_online_cpus()); + vsi->alloc_rxq = ice_get_rxq_count(pf); } } pf->num_lan_rx = vsi->alloc_rxq; - vsi->num_q_vectors = min_t(int, pf->num_lan_msix, - max_t(int, vsi->alloc_rxq, - vsi->alloc_txq)); + vsi->num_q_vectors = max(vsi->alloc_rxq, vsi->alloc_txq); break; case ICE_VSI_SF: vsi->alloc_txq = 1; @@ -567,6 +571,8 @@ ice_vsi_alloc_def(struct ice_vsi *vsi, struct ice_channel *ch) return -ENOMEM; } + vsi->irq_dyn_alloc = pci_msix_can_alloc_dyn(vsi->back->pdev); + switch (vsi->type) { case ICE_VSI_PF: case ICE_VSI_SF: @@ -827,7 +833,13 @@ bool ice_is_safe_mode(struct ice_pf *pf) */ bool ice_is_rdma_ena(struct ice_pf *pf) { - return test_bit(ICE_FLAG_RDMA_ENA, pf->flags); + union devlink_param_value value; + int err; + + err = devl_param_driverinit_value_get(priv_to_devlink(pf), + DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA, + &value); + return err ? test_bit(ICE_FLAG_RDMA_ENA, pf->flags) : value.vbool; } /** @@ -1173,12 +1185,11 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) static void ice_chnl_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) { - struct ice_pf *pf = vsi->back; u16 qcount, qmap; u8 offset = 0; int pow; - qcount = min_t(int, vsi->num_rxq, pf->num_lan_msix); + qcount = vsi->num_rxq; pow = order_base_2(qcount); qmap = FIELD_PREP(ICE_AQ_VSI_TC_Q_OFFSET_M, offset); @@ -1420,6 +1431,10 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) ring->dev = dev; ring->count = vsi->num_rx_desc; ring->cached_phctime = pf->ptp.cached_phc_time; + + if (ice_is_feature_supported(pf, ICE_F_GCS)) + ring->flags |= ICE_RX_FLAGS_RING_GCS; + WRITE_ONCE(vsi->rx_rings[i], ring); } @@ -1764,9 +1779,8 @@ void ice_update_eth_stats(struct ice_vsi *vsi) * @prio: priority for the RXDID for this queue * @ena_ts: true to enable timestamp and false to disable timestamp */ -void -ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio, - bool ena_ts) +void ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio, + bool ena_ts) { int regval = rd32(hw, QRXFLXP_CNTXT(pf_q)); @@ -2582,7 +2596,6 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) return; vsi->irqs_ready = false; - ice_free_cpu_rx_rmap(vsi); ice_for_each_q_vector(vsi, i) { int irq_num; @@ -2595,12 +2608,6 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) vsi->q_vectors[i]->num_ring_rx)) continue; - /* clear the affinity notifier in the IRQ descriptor */ - if (!IS_ENABLED(CONFIG_RFS_ACCEL)) - irq_set_affinity_notifier(irq_num, NULL); - - /* clear the affinity_hint in the IRQ descriptor */ - irq_update_affinity_hint(irq_num, NULL); synchronize_irq(irq_num); devm_free_irq(ice_pf_to_dev(pf), irq_num, vsi->q_vectors[i]); } @@ -2755,11 +2762,18 @@ void ice_vsi_set_napi_queues(struct ice_vsi *vsi) void ice_vsi_clear_napi_queues(struct ice_vsi *vsi) { struct net_device *netdev = vsi->netdev; - int q_idx; + int q_idx, v_idx; if (!netdev) return; + /* Clear the NAPI's interrupt number */ + ice_for_each_q_vector(vsi, v_idx) { + struct ice_q_vector *q_vector = vsi->q_vectors[v_idx]; + + netif_napi_set_irq(&q_vector->napi, -1); + } + ice_for_each_txq(vsi, q_idx) netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, NULL); @@ -3882,15 +3896,17 @@ void ice_init_feature_support(struct ice_pf *pf) ice_set_feature_support(pf, ICE_F_CGU); if (ice_is_clock_mux_in_netlist(&pf->hw)) ice_set_feature_support(pf, ICE_F_SMA_CTRL); - if (ice_gnss_is_gps_present(&pf->hw)) + if (ice_gnss_is_module_present(&pf->hw)) ice_set_feature_support(pf, ICE_F_GNSS); break; default: break; } - if (pf->hw.mac_type == ICE_MAC_E830) + if (pf->hw.mac_type == ICE_MAC_E830) { ice_set_feature_support(pf, ICE_F_MBX_LIMIT); + ice_set_feature_support(pf, ICE_F_GCS); + } } /** diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index e13bd5a6cb6c..049edeb60104 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -2528,34 +2528,6 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset) } /** - * ice_irq_affinity_notify - Callback for affinity changes - * @notify: context as to what irq was changed - * @mask: the new affinity mask - * - * This is a callback function used by the irq_set_affinity_notifier function - * so that we may register to receive changes to the irq affinity masks. - */ -static void -ice_irq_affinity_notify(struct irq_affinity_notify *notify, - const cpumask_t *mask) -{ - struct ice_q_vector *q_vector = - container_of(notify, struct ice_q_vector, affinity_notify); - - cpumask_copy(&q_vector->affinity_mask, mask); -} - -/** - * ice_irq_affinity_release - Callback for affinity notifier release - * @ref: internal core kernel usage - * - * This is a callback function used by the irq_set_affinity_notifier function - * to inform the current notification subscriber that they will no longer - * receive notifications. - */ -static void ice_irq_affinity_release(struct kref __always_unused *ref) {} - -/** * ice_vsi_ena_irq - Enable IRQ for the given VSI * @vsi: the VSI being configured */ @@ -2618,19 +2590,6 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) err); goto free_q_irqs; } - - /* register for affinity change notifications */ - if (!IS_ENABLED(CONFIG_RFS_ACCEL)) { - struct irq_affinity_notify *affinity_notify; - - affinity_notify = &q_vector->affinity_notify; - affinity_notify->notify = ice_irq_affinity_notify; - affinity_notify->release = ice_irq_affinity_release; - irq_set_affinity_notifier(irq_num, affinity_notify); - } - - /* assign the mask for this irq */ - irq_update_affinity_hint(irq_num, &q_vector->affinity_mask); } err = ice_set_cpu_rx_rmap(vsi); @@ -2646,9 +2605,6 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename) free_q_irqs: while (vector--) { irq_num = vsi->q_vectors[vector]->irq.virq; - if (!IS_ENABLED(CONFIG_RFS_ACCEL)) - irq_set_affinity_notifier(irq_num, NULL); - irq_update_affinity_hint(irq_num, NULL); devm_free_irq(dev, irq_num, &vsi->q_vectors[vector]); } return err; @@ -3304,22 +3260,8 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data) if (oicr & PFINT_OICR_TSYN_TX_M) { ena_mask &= ~PFINT_OICR_TSYN_TX_M; - if (ice_pf_state_is_nominal(pf) && - pf->hw.dev_caps.ts_dev_info.ts_ll_int_read) { - struct ice_ptp_tx *tx = &pf->ptp.port.tx; - unsigned long flags; - u8 idx; - - spin_lock_irqsave(&tx->lock, flags); - idx = find_next_bit_wrap(tx->in_use, tx->len, - tx->last_ll_ts_idx_read + 1); - if (idx != tx->len) - ice_ptp_req_tx_single_tstamp(tx, idx); - spin_unlock_irqrestore(&tx->lock, flags); - } else if (ice_ptp_pf_handles_tx_interrupt(pf)) { - set_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread); - ret = IRQ_WAKE_THREAD; - } + + ret = ice_ptp_ts_irq(pf); } if (oicr & PFINT_OICR_TSYN_EVNT_M) { @@ -3689,6 +3631,15 @@ void ice_set_netdev_features(struct net_device *netdev) */ netdev->hw_features |= NETIF_F_RXFCS; + /* Allow core to manage IRQs affinity */ + netif_set_affinity_auto(netdev); + + /* Mutual exclusivity for TSO and GCS is enforced by the set features + * ndo callback. + */ + if (ice_is_feature_supported(pf, ICE_F_GCS)) + netdev->hw_features |= NETIF_F_HW_CSUM; + netif_set_tso_max_size(netdev, ICE_MAX_TSO_SIZE); } @@ -4066,8 +4017,7 @@ static void ice_set_pf_caps(struct ice_pf *pf) } clear_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags); - if (func_caps->common_cap.ieee_1588 && - !(pf->hw.mac_type == ICE_MAC_E830)) + if (func_caps->common_cap.ieee_1588) set_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags); pf->max_pf_txqs = func_caps->common_cap.num_txq; @@ -5087,6 +5037,12 @@ static int ice_init(struct ice_pf *pf) if (err) return err; + if (pf->hw.mac_type == ICE_MAC_E830) { + err = pci_enable_ptm(pf->pdev, NULL); + if (err) + dev_dbg(ice_pf_to_dev(pf), "PCIe PTM not supported by PCIe bus/controller\n"); + } + err = ice_alloc_vsis(pf); if (err) goto err_alloc_vsis; @@ -5186,11 +5142,12 @@ int ice_load(struct ice_pf *pf) ice_napi_add(vsi); + ice_init_features(pf); + err = ice_init_rdma(pf); if (err) goto err_init_rdma; - ice_init_features(pf); ice_service_task_restart(pf); clear_bit(ICE_DOWN, pf->state); @@ -5198,6 +5155,7 @@ int ice_load(struct ice_pf *pf) return 0; err_init_rdma: + ice_deinit_features(pf); ice_tc_indir_block_unregister(vsi); err_tc_indir_block_register: ice_unregister_netdev(vsi); @@ -5221,8 +5179,8 @@ void ice_unload(struct ice_pf *pf) devl_assert_locked(priv_to_devlink(pf)); - ice_deinit_features(pf); ice_deinit_rdma(pf); + ice_deinit_features(pf); ice_tc_indir_block_unregister(vsi); ice_unregister_netdev(vsi); ice_devlink_destroy_pf_port(pf); @@ -6597,6 +6555,18 @@ ice_set_features(struct net_device *netdev, netdev_features_t features) if (changed & NETIF_F_LOOPBACK) ret = ice_set_loopback(vsi, !!(features & NETIF_F_LOOPBACK)); + /* Due to E830 hardware limitations, TSO (NETIF_F_ALL_TSO) with GCS + * (NETIF_F_HW_CSUM) is not supported. + */ + if (ice_is_feature_supported(pf, ICE_F_GCS) && + ((features & NETIF_F_HW_CSUM) && (features & NETIF_F_ALL_TSO))) { + if (netdev->features & NETIF_F_HW_CSUM) + dev_err(ice_pf_to_dev(pf), "To enable TSO, you must first disable HW checksum.\n"); + else + dev_err(ice_pf_to_dev(pf), "To enable HW checksum, you must first disable TSO.\n"); + return -EIO; + } + return ret; } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c index e26320ce52ca..1fd1ae03eb90 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp.c @@ -298,8 +298,8 @@ void ice_ptp_restore_timestamp_mode(struct ice_pf *pf) * @sts: Optional parameter for holding a pair of system timestamps from * the system clock. Will be ignored if NULL is given. */ -static u64 -ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts) +u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf, + struct ptp_system_timestamp *sts) { struct ice_hw *hw = &pf->hw; u32 hi, lo, lo2; @@ -310,6 +310,15 @@ ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts) /* Read the system timestamp pre PHC read */ ptp_read_system_prets(sts); + if (hw->mac_type == ICE_MAC_E830) { + u64 clk_time = rd64(hw, E830_GLTSYN_TIME_L(tmr_idx)); + + /* Read the system timestamp post PHC read */ + ptp_read_system_postts(sts); + + return clk_time; + } + lo = rd32(hw, GLTSYN_TIME_L(tmr_idx)); /* Read the system timestamp post PHC read */ @@ -972,28 +981,6 @@ ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx) } /** - * ice_ptp_init_tx_eth56g - Initialize tracking for Tx timestamps - * @pf: Board private structure - * @tx: the Tx tracking structure to initialize - * @port: the port this structure tracks - * - * Initialize the Tx timestamp tracker for this port. ETH56G PHYs - * have independent memory blocks for all ports. - * - * Return: 0 for success, -ENOMEM when failed to allocate Tx tracker - */ -static int ice_ptp_init_tx_eth56g(struct ice_pf *pf, struct ice_ptp_tx *tx, - u8 port) -{ - tx->block = port; - tx->offset = 0; - tx->len = INDEX_PER_PORT_ETH56G; - tx->has_ready_bitmap = 1; - - return ice_ptp_alloc_tx_tracker(tx); -} - -/** * ice_ptp_init_tx_e82x - Initialize tracking for Tx timestamps * @pf: Board private structure * @tx: the Tx tracking structure to initialize @@ -1003,9 +990,11 @@ static int ice_ptp_init_tx_eth56g(struct ice_pf *pf, struct ice_ptp_tx *tx, * the timestamp block is shared for all ports in the same quad. To avoid * ports using the same timestamp index, logically break the block of * registers into chunks based on the port number. + * + * Return: 0 on success, -ENOMEM when out of memory */ -static int -ice_ptp_init_tx_e82x(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port) +static int ice_ptp_init_tx_e82x(struct ice_pf *pf, struct ice_ptp_tx *tx, + u8 port) { tx->block = ICE_GET_QUAD_NUM(port); tx->offset = (port % ICE_PORTS_PER_QUAD) * INDEX_PER_PORT_E82X; @@ -1016,24 +1005,27 @@ ice_ptp_init_tx_e82x(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port) } /** - * ice_ptp_init_tx_e810 - Initialize tracking for Tx timestamps + * ice_ptp_init_tx - Initialize tracking for Tx timestamps * @pf: Board private structure * @tx: the Tx tracking structure to initialize + * @port: the port this structure tracks + * + * Initialize the Tx timestamp tracker for this PF. For all PHYs except E82X, + * each port has its own block of timestamps, independent of the other ports. * - * Initialize the Tx timestamp tracker for this PF. For E810 devices, each - * port has its own block of timestamps, independent of the other ports. + * Return: 0 on success, -ENOMEM when out of memory */ -static int -ice_ptp_init_tx_e810(struct ice_pf *pf, struct ice_ptp_tx *tx) +static int ice_ptp_init_tx(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port) { - tx->block = pf->hw.port_info->lport; + tx->block = port; tx->offset = 0; - tx->len = INDEX_PER_PORT_E810; + tx->len = INDEX_PER_PORT; + /* The E810 PHY does not provide a timestamp ready bitmap. Instead, * verify new timestamps against cached copy of the last read * timestamp. */ - tx->has_ready_bitmap = 0; + tx->has_ready_bitmap = pf->hw.mac_type != ICE_MAC_E810; return ice_ptp_alloc_tx_tracker(tx); } @@ -1318,20 +1310,21 @@ ice_ptp_port_phy_stop(struct ice_ptp_port *ptp_port) struct ice_hw *hw = &pf->hw; int err; - if (ice_is_e810(hw)) - return 0; - mutex_lock(&ptp_port->ps_lock); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - err = ice_stop_phy_timer_eth56g(hw, port, true); + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: + err = 0; break; - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: kthread_cancel_delayed_work_sync(&ptp_port->ov_work); err = ice_stop_phy_timer_e82x(hw, port, true); break; + case ICE_MAC_GENERIC_3K_E825: + err = ice_stop_phy_timer_eth56g(hw, port, true); + break; default: err = -ENODEV; } @@ -1361,19 +1354,17 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port) unsigned long flags; int err; - if (ice_is_e810(hw)) - return 0; - if (!ptp_port->link_up) return ice_ptp_port_phy_stop(ptp_port); mutex_lock(&ptp_port->ps_lock); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - err = ice_start_phy_timer_eth56g(hw, port); + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: + err = 0; break; - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: /* Start the PHY timer in Vernier mode */ kthread_cancel_delayed_work_sync(&ptp_port->ov_work); @@ -1398,6 +1389,9 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port) kthread_queue_delayed_work(pf->ptp.kworker, &ptp_port->ov_work, 0); break; + case ICE_MAC_GENERIC_3K_E825: + err = ice_start_phy_timer_eth56g(hw, port); + break; default: err = -ENODEV; } @@ -1432,12 +1426,14 @@ void ice_ptp_link_change(struct ice_pf *pf, bool linkup) /* Skip HW writes if reset is in progress */ if (pf->hw.reset_ongoing) return; - switch (ice_get_phy_model(hw)) { - case ICE_PHY_E810: - /* Do not reconfigure E810 PHY */ + + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: + /* Do not reconfigure E810 or E830 PHY */ return; - case ICE_PHY_ETH56G: - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: + case ICE_MAC_GENERIC_3K_E825: ice_ptp_port_phy_restart(ptp_port); return; default: @@ -1465,46 +1461,45 @@ static int ice_ptp_cfg_phy_interrupt(struct ice_pf *pf, bool ena, u32 threshold) ice_ptp_reset_ts_memory(hw); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: { - int port; + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: + return 0; + case ICE_MAC_GENERIC: { + int quad; - for (port = 0; port < hw->ptp.num_lports; port++) { + for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports); + quad++) { int err; - err = ice_phy_cfg_intr_eth56g(hw, port, ena, threshold); + err = ice_phy_cfg_intr_e82x(hw, quad, ena, threshold); if (err) { - dev_err(dev, "Failed to configure PHY interrupt for port %d, err %d\n", - port, err); + dev_err(dev, "Failed to configure PHY interrupt for quad %d, err %d\n", + quad, err); return err; } } return 0; } - case ICE_PHY_E82X: { - int quad; + case ICE_MAC_GENERIC_3K_E825: { + int port; - for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports); - quad++) { + for (port = 0; port < hw->ptp.num_lports; port++) { int err; - err = ice_phy_cfg_intr_e82x(hw, quad, ena, threshold); + err = ice_phy_cfg_intr_eth56g(hw, port, ena, threshold); if (err) { - dev_err(dev, "Failed to configure PHY interrupt for quad %d, err %d\n", - quad, err); + dev_err(dev, "Failed to configure PHY interrupt for port %d, err %d\n", + port, err); return err; } } return 0; } - case ICE_PHY_E810: - return 0; - case ICE_PHY_UNSUP: + case ICE_MAC_UNKNOWN: default: - dev_warn(dev, "%s: Unexpected PHY model %d\n", __func__, - ice_get_phy_model(hw)); return -EOPNOTSUPP; } } @@ -1740,7 +1735,7 @@ static int ice_ptp_write_perout(struct ice_hw *hw, unsigned int chan, /* 0. Reset mode & out_en in AUX_OUT */ wr32(hw, GLTSYN_AUX_OUT(chan, tmr_idx), 0); - if (ice_is_e825c(hw)) { + if (hw->mac_type == ICE_MAC_GENERIC_3K_E825) { int err; /* Enable/disable CGU 1PPS output for E825C */ @@ -1783,6 +1778,7 @@ static int ice_ptp_write_perout(struct ice_hw *hw, unsigned int chan, 8 + chan + (tmr_idx * 4)); wr32(hw, GLGEN_GPIO_CTL(gpio_pin), val); + ice_flush(hw); return 0; } @@ -1824,7 +1820,7 @@ static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq, return ice_ptp_write_perout(hw, rq->index, gpio_pin, 0, 0); if (strncmp(pf->ptp.pin_desc[pin_desc_idx].name, "1PPS", 64) == 0 && - period != NSEC_PER_SEC && hw->ptp.phy_model == ICE_PHY_E82X) { + period != NSEC_PER_SEC && hw->mac_type == ICE_MAC_GENERIC) { dev_err(ice_pf_to_dev(pf), "1PPS pin supports only 1 s period\n"); return -EOPNOTSUPP; } @@ -1843,9 +1839,10 @@ static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq, div64_u64_rem(start, period, &phase); /* If we have only phase or start time is in the past, start the timer - * at the next multiple of period, maintaining phase. + * at the next multiple of period, maintaining phase at least 0.5 second + * from now, so we have time to write it to HW. */ - clk = ice_ptp_read_src_clk_reg(pf, NULL); + clk = ice_ptp_read_src_clk_reg(pf, NULL) + NSEC_PER_MSEC * 500; if (rq->flags & PTP_PEROUT_PHASE || start <= clk - prop_delay_ns) start = div64_u64(clk + period - 1, period) * period + phase; @@ -2078,7 +2075,7 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts) /* For Vernier mode on E82X, we need to recalibrate after new settime. * Start with marking timestamps as invalid. */ - if (ice_get_phy_model(hw) == ICE_PHY_E82X) { + if (hw->mac_type == ICE_MAC_GENERIC) { err = ice_ptp_clear_phy_offset_ready_e82x(hw); if (err) dev_warn(ice_pf_to_dev(pf), "Failed to mark timestamps as invalid before settime\n"); @@ -2102,7 +2099,7 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts) ice_ptp_enable_all_perout(pf); /* Recalibrate and re-enable timestamp blocks for E822/E823 */ - if (ice_get_phy_model(hw) == ICE_PHY_E82X) + if (hw->mac_type == ICE_MAC_GENERIC) ice_ptp_restart_all_phy(pf); exit: if (err) { @@ -2180,93 +2177,157 @@ static int ice_ptp_adjtime(struct ptp_clock_info *info, s64 delta) return 0; } +/** + * struct ice_crosststamp_cfg - Device cross timestamp configuration + * @lock_reg: The hardware semaphore lock to use + * @lock_busy: Bit in the semaphore lock indicating the lock is busy + * @ctl_reg: The hardware register to request cross timestamp + * @ctl_active: Bit in the control register to request cross timestamp + * @art_time_l: Lower 32-bits of ART system time + * @art_time_h: Upper 32-bits of ART system time + * @dev_time_l: Lower 32-bits of device time (per timer index) + * @dev_time_h: Upper 32-bits of device time (per timer index) + */ +struct ice_crosststamp_cfg { + /* HW semaphore lock register */ + u32 lock_reg; + u32 lock_busy; + + /* Capture control register */ + u32 ctl_reg; + u32 ctl_active; + + /* Time storage */ + u32 art_time_l; + u32 art_time_h; + u32 dev_time_l[2]; + u32 dev_time_h[2]; +}; + +static const struct ice_crosststamp_cfg ice_crosststamp_cfg_e82x = { + .lock_reg = PFHH_SEM, + .lock_busy = PFHH_SEM_BUSY_M, + .ctl_reg = GLHH_ART_CTL, + .ctl_active = GLHH_ART_CTL_ACTIVE_M, + .art_time_l = GLHH_ART_TIME_L, + .art_time_h = GLHH_ART_TIME_H, + .dev_time_l[0] = GLTSYN_HHTIME_L(0), + .dev_time_h[0] = GLTSYN_HHTIME_H(0), + .dev_time_l[1] = GLTSYN_HHTIME_L(1), + .dev_time_h[1] = GLTSYN_HHTIME_H(1), +}; + #ifdef CONFIG_ICE_HWTS +static const struct ice_crosststamp_cfg ice_crosststamp_cfg_e830 = { + .lock_reg = E830_PFPTM_SEM, + .lock_busy = E830_PFPTM_SEM_BUSY_M, + .ctl_reg = E830_GLPTM_ART_CTL, + .ctl_active = E830_GLPTM_ART_CTL_ACTIVE_M, + .art_time_l = E830_GLPTM_ART_TIME_L, + .art_time_h = E830_GLPTM_ART_TIME_H, + .dev_time_l[0] = E830_GLTSYN_PTMTIME_L(0), + .dev_time_h[0] = E830_GLTSYN_PTMTIME_H(0), + .dev_time_l[1] = E830_GLTSYN_PTMTIME_L(1), + .dev_time_h[1] = E830_GLTSYN_PTMTIME_H(1), +}; + +#endif /* CONFIG_ICE_HWTS */ +/** + * struct ice_crosststamp_ctx - Device cross timestamp context + * @snapshot: snapshot of system clocks for historic interpolation + * @pf: pointer to the PF private structure + * @cfg: pointer to hardware configuration for cross timestamp + */ +struct ice_crosststamp_ctx { + struct system_time_snapshot snapshot; + struct ice_pf *pf; + const struct ice_crosststamp_cfg *cfg; +}; + /** - * ice_ptp_get_syncdevicetime - Get the cross time stamp info + * ice_capture_crosststamp - Capture a device/system cross timestamp * @device: Current device time * @system: System counter value read synchronously with device time - * @ctx: Context provided by timekeeping code + * @__ctx: Context passed from ice_ptp_getcrosststamp * * Read device and system (ART) clock simultaneously and return the corrected * clock values in ns. + * + * Return: zero on success, or a negative error code on failure. */ -static int -ice_ptp_get_syncdevicetime(ktime_t *device, - struct system_counterval_t *system, - void *ctx) +static int ice_capture_crosststamp(ktime_t *device, + struct system_counterval_t *system, + void *__ctx) { - struct ice_pf *pf = (struct ice_pf *)ctx; - struct ice_hw *hw = &pf->hw; - u32 hh_lock, hh_art_ctl; - int i; + struct ice_crosststamp_ctx *ctx = __ctx; + const struct ice_crosststamp_cfg *cfg; + u32 lock, ctl, ts_lo, ts_hi, tmr_idx; + struct ice_pf *pf; + struct ice_hw *hw; + int err; + u64 ts; -#define MAX_HH_HW_LOCK_TRIES 5 -#define MAX_HH_CTL_LOCK_TRIES 100 + cfg = ctx->cfg; + pf = ctx->pf; + hw = &pf->hw; - for (i = 0; i < MAX_HH_HW_LOCK_TRIES; i++) { - /* Get the HW lock */ - hh_lock = rd32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id)); - if (hh_lock & PFHH_SEM_BUSY_M) { - usleep_range(10000, 15000); - continue; - } - break; - } - if (hh_lock & PFHH_SEM_BUSY_M) { - dev_err(ice_pf_to_dev(pf), "PTP failed to get hh lock\n"); + tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc; + if (tmr_idx > 1) + return -EINVAL; + + /* Poll until we obtain the cross-timestamp hardware semaphore */ + err = rd32_poll_timeout(hw, cfg->lock_reg, lock, + !(lock & cfg->lock_busy), + 10 * USEC_PER_MSEC, 50 * USEC_PER_MSEC); + if (err) { + dev_err(ice_pf_to_dev(pf), "PTP failed to get cross timestamp lock\n"); return -EBUSY; } + /* Snapshot system time for historic interpolation */ + ktime_get_snapshot(&ctx->snapshot); + /* Program cmd to master timer */ ice_ptp_src_cmd(hw, ICE_PTP_READ_TIME); /* Start the ART and device clock sync sequence */ - hh_art_ctl = rd32(hw, GLHH_ART_CTL); - hh_art_ctl = hh_art_ctl | GLHH_ART_CTL_ACTIVE_M; - wr32(hw, GLHH_ART_CTL, hh_art_ctl); - - for (i = 0; i < MAX_HH_CTL_LOCK_TRIES; i++) { - /* Wait for sync to complete */ - hh_art_ctl = rd32(hw, GLHH_ART_CTL); - if (hh_art_ctl & GLHH_ART_CTL_ACTIVE_M) { - udelay(1); - continue; - } else { - u32 hh_ts_lo, hh_ts_hi, tmr_idx; - u64 hh_ts; - - tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc; - /* Read ART time */ - hh_ts_lo = rd32(hw, GLHH_ART_TIME_L); - hh_ts_hi = rd32(hw, GLHH_ART_TIME_H); - hh_ts = ((u64)hh_ts_hi << 32) | hh_ts_lo; - system->cycles = hh_ts; - system->cs_id = CSID_X86_ART; - /* Read Device source clock time */ - hh_ts_lo = rd32(hw, GLTSYN_HHTIME_L(tmr_idx)); - hh_ts_hi = rd32(hw, GLTSYN_HHTIME_H(tmr_idx)); - hh_ts = ((u64)hh_ts_hi << 32) | hh_ts_lo; - *device = ns_to_ktime(hh_ts); - break; - } - } + ctl = rd32(hw, cfg->ctl_reg); + ctl |= cfg->ctl_active; + wr32(hw, cfg->ctl_reg, ctl); + /* Poll until hardware completes the capture */ + err = rd32_poll_timeout(hw, cfg->ctl_reg, ctl, !(ctl & cfg->ctl_active), + 5, 20 * USEC_PER_MSEC); + if (err) + goto err_timeout; + + /* Read ART system time */ + ts_lo = rd32(hw, cfg->art_time_l); + ts_hi = rd32(hw, cfg->art_time_h); + ts = ((u64)ts_hi << 32) | ts_lo; + system->cycles = ts; + system->cs_id = CSID_X86_ART; + + /* Read Device source clock time */ + ts_lo = rd32(hw, cfg->dev_time_l[tmr_idx]); + ts_hi = rd32(hw, cfg->dev_time_h[tmr_idx]); + ts = ((u64)ts_hi << 32) | ts_lo; + *device = ns_to_ktime(ts); + +err_timeout: /* Clear the master timer */ ice_ptp_src_cmd(hw, ICE_PTP_NOP); /* Release HW lock */ - hh_lock = rd32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id)); - hh_lock = hh_lock & ~PFHH_SEM_BUSY_M; - wr32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id), hh_lock); - - if (i == MAX_HH_CTL_LOCK_TRIES) - return -ETIMEDOUT; + lock = rd32(hw, cfg->lock_reg); + lock &= ~cfg->lock_busy; + wr32(hw, cfg->lock_reg, lock); - return 0; + return err; } /** - * ice_ptp_getcrosststamp_e82x - Capture a device cross timestamp + * ice_ptp_getcrosststamp - Capture a device cross timestamp * @info: the driver's PTP info structure * @cts: The memory to fill the cross timestamp info * @@ -2274,22 +2335,36 @@ ice_ptp_get_syncdevicetime(ktime_t *device, * clock. Fill the cross timestamp information and report it back to the * caller. * - * This is only valid for E822 and E823 devices which have support for - * generating the cross timestamp via PCIe PTM. - * * In order to correctly correlate the ART timestamp back to the TSC time, the * CPU must have X86_FEATURE_TSC_KNOWN_FREQ. + * + * Return: zero on success, or a negative error code on failure. */ -static int -ice_ptp_getcrosststamp_e82x(struct ptp_clock_info *info, - struct system_device_crosststamp *cts) +static int ice_ptp_getcrosststamp(struct ptp_clock_info *info, + struct system_device_crosststamp *cts) { struct ice_pf *pf = ptp_info_to_pf(info); + struct ice_crosststamp_ctx ctx = { + .pf = pf, + }; + + switch (pf->hw.mac_type) { + case ICE_MAC_GENERIC: + case ICE_MAC_GENERIC_3K_E825: + ctx.cfg = &ice_crosststamp_cfg_e82x; + break; +#ifdef CONFIG_ICE_HWTS + case ICE_MAC_E830: + ctx.cfg = &ice_crosststamp_cfg_e830; + break; +#endif /* CONFIG_ICE_HWTS */ + default: + return -EOPNOTSUPP; + } - return get_device_system_crosststamp(ice_ptp_get_syncdevicetime, - pf, NULL, cts); + return get_device_system_crosststamp(ice_capture_crosststamp, &ctx, + &ctx.snapshot, cts); } -#endif /* CONFIG_ICE_HWTS */ /** * ice_ptp_get_ts_config - ioctl interface to read the timestamping config @@ -2550,13 +2625,9 @@ static int ice_ptp_parse_sdp_entries(struct ice_pf *pf, __le16 *entries, */ static void ice_ptp_set_funcs_e82x(struct ice_pf *pf) { -#ifdef CONFIG_ICE_HWTS - if (boot_cpu_has(X86_FEATURE_ART) && - boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ)) - pf->ptp.info.getcrosststamp = ice_ptp_getcrosststamp_e82x; + pf->ptp.info.getcrosststamp = ice_ptp_getcrosststamp; -#endif /* CONFIG_ICE_HWTS */ - if (ice_is_e825c(&pf->hw)) { + if (pf->hw.mac_type == ICE_MAC_GENERIC_3K_E825) { pf->ptp.ice_pin_desc = ice_pin_desc_e825c; pf->ptp.info.n_pins = ICE_PIN_DESC_ARR_LEN(ice_pin_desc_e825c); } else { @@ -2623,6 +2694,28 @@ err: } /** + * ice_ptp_set_funcs_e830 - Set specialized functions for E830 support + * @pf: Board private structure + * + * Assign functions to the PTP capabiltiies structure for E830 devices. + * Functions which operate across all device families should be set directly + * in ice_ptp_set_caps. Only add functions here which are distinct for E830 + * devices. + */ +static void ice_ptp_set_funcs_e830(struct ice_pf *pf) +{ +#ifdef CONFIG_ICE_HWTS + if (pcie_ptm_enabled(pf->pdev) && boot_cpu_has(X86_FEATURE_ART)) + pf->ptp.info.getcrosststamp = ice_ptp_getcrosststamp; + +#endif /* CONFIG_ICE_HWTS */ + /* Rest of the config is the same as base E810 */ + pf->ptp.ice_pin_desc = ice_pin_desc_e810; + pf->ptp.info.n_pins = ICE_PIN_DESC_ARR_LEN(ice_pin_desc_e810); + ice_ptp_setup_pin_cfg(pf); +} + +/** * ice_ptp_set_caps - Set PTP capabilities * @pf: Board private structure */ @@ -2644,10 +2737,20 @@ static void ice_ptp_set_caps(struct ice_pf *pf) info->enable = ice_ptp_gpio_enable; info->verify = ice_verify_pin; - if (ice_is_e810(&pf->hw)) + switch (pf->hw.mac_type) { + case ICE_MAC_E810: ice_ptp_set_funcs_e810(pf); - else + return; + case ICE_MAC_E830: + ice_ptp_set_funcs_e830(pf); + return; + case ICE_MAC_GENERIC: + case ICE_MAC_GENERIC_3K_E825: ice_ptp_set_funcs_e82x(pf); + return; + default: + return; + } } /** @@ -2758,6 +2861,65 @@ enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf) } /** + * ice_ptp_ts_irq - Process the PTP Tx timestamps in IRQ context + * @pf: Board private structure + * + * Return: IRQ_WAKE_THREAD if Tx timestamp read has to be handled in the bottom + * half of the interrupt and IRQ_HANDLED otherwise. + */ +irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + + switch (hw->mac_type) { + case ICE_MAC_E810: + /* E810 capable of low latency timestamping with interrupt can + * request a single timestamp in the top half and wait for + * a second LL TS interrupt from the FW when it's ready. + */ + if (hw->dev_caps.ts_dev_info.ts_ll_int_read) { + struct ice_ptp_tx *tx = &pf->ptp.port.tx; + u8 idx; + + if (!ice_pf_state_is_nominal(pf)) + return IRQ_HANDLED; + + spin_lock(&tx->lock); + idx = find_next_bit_wrap(tx->in_use, tx->len, + tx->last_ll_ts_idx_read + 1); + if (idx != tx->len) + ice_ptp_req_tx_single_tstamp(tx, idx); + spin_unlock(&tx->lock); + + return IRQ_HANDLED; + } + fallthrough; /* non-LL_TS E810 */ + case ICE_MAC_GENERIC: + case ICE_MAC_GENERIC_3K_E825: + /* All other devices process timestamps in the bottom half due + * to sleeping or polling. + */ + if (!ice_ptp_pf_handles_tx_interrupt(pf)) + return IRQ_HANDLED; + + set_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread); + return IRQ_WAKE_THREAD; + case ICE_MAC_E830: + /* E830 can read timestamps in the top half using rd32() */ + if (ice_ptp_process_ts(pf) == ICE_TX_TSTAMP_WORK_PENDING) { + /* Process outstanding Tx timestamps. If there + * is more work, re-arm the interrupt to trigger again. + */ + wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M); + ice_flush(hw); + } + return IRQ_HANDLED; + default: + return IRQ_HANDLED; + } +} + +/** * ice_ptp_maybe_trigger_tx_interrupt - Trigger Tx timstamp interrupt * @pf: Board private structure * @@ -2777,7 +2939,7 @@ static void ice_ptp_maybe_trigger_tx_interrupt(struct ice_pf *pf) bool trigger_oicr = false; unsigned int i; - if (ice_is_e810(hw)) + if (!pf->ptp.port.tx.has_ready_bitmap) return; if (!ice_pf_src_tmr_owned(pf)) @@ -2912,14 +3074,12 @@ static int ice_ptp_rebuild_owner(struct ice_pf *pf) */ ice_ptp_flush_all_tx_tracker(pf); - if (!ice_is_e810(hw)) { - /* Enable quad interrupts */ - err = ice_ptp_cfg_phy_interrupt(pf, true, 1); - if (err) - return err; + /* Enable quad interrupts */ + err = ice_ptp_cfg_phy_interrupt(pf, true, 1); + if (err) + return err; - ice_ptp_restart_all_phy(pf); - } + ice_ptp_restart_all_phy(pf); /* Re-enable all periodic outputs and external timestamp events */ ice_ptp_enable_all_perout(pf); @@ -2971,8 +3131,9 @@ err: static bool ice_is_primary(struct ice_hw *hw) { - return ice_is_e825c(hw) && ice_is_dual(hw) ? - !!(hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_PRIMARY_M) : true; + return hw->mac_type == ICE_MAC_GENERIC_3K_E825 && ice_is_dual(hw) ? + !!(hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_PRIMARY_M) : + true; } static int ice_ptp_setup_adapter(struct ice_pf *pf) @@ -2990,7 +3151,7 @@ static int ice_ptp_setup_pf(struct ice_pf *pf) struct ice_ptp *ctrl_ptp = ice_get_ctrl_ptp(pf); struct ice_ptp *ptp = &pf->ptp; - if (WARN_ON(!ctrl_ptp) || ice_get_phy_model(&pf->hw) == ICE_PHY_UNSUP) + if (WARN_ON(!ctrl_ptp) || pf->hw.mac_type == ICE_MAC_UNKNOWN) return -ENODEV; INIT_LIST_HEAD(&ptp->port.list_node); @@ -3007,7 +3168,7 @@ static void ice_ptp_cleanup_pf(struct ice_pf *pf) { struct ice_ptp *ptp = &pf->ptp; - if (ice_get_phy_model(&pf->hw) != ICE_PHY_UNSUP) { + if (pf->hw.mac_type != ICE_MAC_UNKNOWN) { mutex_lock(&pf->adapter->ports.lock); list_del(&ptp->port.list_node); mutex_unlock(&pf->adapter->ports.lock); @@ -3127,6 +3288,8 @@ static int ice_ptp_init_work(struct ice_pf *pf, struct ice_ptp *ptp) * ice_ptp_init_port - Initialize PTP port structure * @pf: Board private structure * @ptp_port: PTP port structure + * + * Return: 0 on success, -ENODEV on invalid MAC type, -ENOMEM on failed alloc. */ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port) { @@ -3134,16 +3297,14 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port) mutex_init(&ptp_port->ps_lock); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_ptp_init_tx_eth56g(pf, &ptp_port->tx, - ptp_port->port_num); - case ICE_PHY_E810: - return ice_ptp_init_tx_e810(pf, &ptp_port->tx); - case ICE_PHY_E82X: + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: + case ICE_MAC_GENERIC_3K_E825: + return ice_ptp_init_tx(pf, &ptp_port->tx, ptp_port->port_num); + case ICE_MAC_GENERIC: kthread_init_delayed_work(&ptp_port->ov_work, ice_ptp_wait_for_offsets); - return ice_ptp_init_tx_e82x(pf, &ptp_port->tx, ptp_port->port_num); default: @@ -3162,8 +3323,8 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port) */ static void ice_ptp_init_tx_interrupt_mode(struct ice_pf *pf) { - switch (ice_get_phy_model(&pf->hw)) { - case ICE_PHY_E82X: + switch (pf->hw.mac_type) { + case ICE_MAC_GENERIC: /* E822 based PHY has the clock owner process the interrupt * for all ports. */ diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h index a1d0e988c084..3b769a0cad00 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp.h @@ -128,8 +128,7 @@ struct ice_ptp_tx { /* Quad and port information for initializing timestamp blocks */ #define INDEX_PER_QUAD 64 #define INDEX_PER_PORT_E82X 16 -#define INDEX_PER_PORT_E810 64 -#define INDEX_PER_PORT_ETH56G 64 +#define INDEX_PER_PORT 64 /** * struct ice_ptp_port - data used to initialize an external port for PTP @@ -304,6 +303,9 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb); void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx); void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx); enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf); +irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf); +u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf, + struct ptp_system_timestamp *sts); u64 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc, const struct ice_pkt_ctx *pkt_ctx); @@ -342,6 +344,17 @@ static inline bool ice_ptp_process_ts(struct ice_pf *pf) return true; } +static inline irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf) +{ + return IRQ_HANDLED; +} + +static inline u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf, + struct ptp_system_timestamp *sts) +{ + return 0; +} + static inline u64 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc, const struct ice_pkt_ctx *pkt_ctx) diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h index ac46d1183300..003cdfada3ca 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h @@ -10,70 +10,25 @@ /* Constants defined for the PTP 1588 clock hardware. */ const struct ice_phy_reg_info_eth56g eth56g_phy_res[NUM_ETH56G_PHY_RES] = { - /* ETH56G_PHY_REG_PTP */ - { - /* base_addr */ - { - 0x092000, - 0x126000, - 0x1BA000, - 0x24E000, - 0x2E2000, - }, - /* step */ - 0x98, + [ETH56G_PHY_REG_PTP] = { + .base_addr = 0x092000, + .step = 0x98, }, - /* ETH56G_PHY_MEM_PTP */ - { - /* base_addr */ - { - 0x093000, - 0x127000, - 0x1BB000, - 0x24F000, - 0x2E3000, - }, - /* step */ - 0x200, + [ETH56G_PHY_MEM_PTP] = { + .base_addr = 0x093000, + .step = 0x200, }, - /* ETH56G_PHY_REG_XPCS */ - { - /* base_addr */ - { - 0x000000, - 0x009400, - 0x128000, - 0x1BC000, - 0x250000, - }, - /* step */ - 0x21000, + [ETH56G_PHY_REG_XPCS] = { + .base_addr = 0x000000, + .step = 0x21000, }, - /* ETH56G_PHY_REG_MAC */ - { - /* base_addr */ - { - 0x085000, - 0x119000, - 0x1AD000, - 0x241000, - 0x2D5000, - }, - /* step */ - 0x1000, + [ETH56G_PHY_REG_MAC] = { + .base_addr = 0x085000, + .step = 0x1000, }, - /* ETH56G_PHY_REG_GPCS */ - { - /* base_addr */ - { - 0x084000, - 0x118000, - 0x1AC000, - 0x240000, - 0x2D4000, - }, - /* step */ - 0x400, + [ETH56G_PHY_REG_GPCS] = { + .base_addr = 0x084000, + .step = 0x400, }, }; diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c index ec91822e9280..89bb8461284a 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c @@ -746,7 +746,7 @@ static int ice_init_cgu_e82x(struct ice_hw *hw) int err; /* Disable sticky lock detection so lock err reported is accurate */ - if (ice_is_e825c(hw)) + if (hw->mac_type == ICE_MAC_GENERIC_3K_E825) err = ice_cfg_cgu_pll_dis_sticky_bits_e825c(hw); else err = ice_cfg_cgu_pll_dis_sticky_bits_e82x(hw); @@ -756,7 +756,7 @@ static int ice_init_cgu_e82x(struct ice_hw *hw) /* Configure the CGU PLL using the parameters from the function * capabilities. */ - if (ice_is_e825c(hw)) + if (hw->mac_type == ICE_MAC_GENERIC_3K_E825) err = ice_cfg_cgu_pll_e825c(hw, ts_info->time_ref, (enum ice_clk_src)ts_info->clk_src); else @@ -827,8 +827,9 @@ static u32 ice_ptp_tmr_cmd_to_port_reg(struct ice_hw *hw, /* Certain hardware families share the same register values for the * port register and source timer register. */ - switch (ice_get_phy_model(hw)) { - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: return ice_ptp_tmr_cmd_to_src_reg(hw, cmd) & TS_CMD_MASK_E810; default: break; @@ -895,6 +896,17 @@ static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw) ice_flush(hw); } +/** + * ice_ptp_cfg_sync_delay - Configure PHC to PHY synchronization delay + * @hw: pointer to HW struct + * @delay: delay between PHC and PHY SYNC command execution in nanoseconds + */ +static void ice_ptp_cfg_sync_delay(const struct ice_hw *hw, u32 delay) +{ + wr32(hw, GLTSYN_SYNC_DLAY, delay); + ice_flush(hw); +} + /* 56G PHY device functions * * The following functions operate on devices with the ETH 56G PHY. @@ -998,7 +1010,7 @@ static int ice_phy_res_address_eth56g(struct ice_hw *hw, u8 lane, /* Lanes 4..7 are in fact 0..3 on a second PHY */ lane %= hw->ptp.ports_per_phy; - *addr = eth56g_phy_res[res_type].base[0] + + *addr = eth56g_phy_res[res_type].base_addr + lane * eth56g_phy_res[res_type].step + offset; return 0; @@ -1228,7 +1240,7 @@ static int ice_write_quad_ptp_reg_eth56g(struct ice_hw *hw, u8 port, if (port >= hw->ptp.num_lports) return -EIO; - addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base[0] + offset; + addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base_addr + offset; return ice_write_phy_eth56g(hw, port, addr, val); } @@ -1253,7 +1265,7 @@ static int ice_read_quad_ptp_reg_eth56g(struct ice_hw *hw, u8 port, if (port >= hw->ptp.num_lports) return -EIO; - addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base[0] + offset; + addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base_addr + offset; return ice_read_phy_eth56g(hw, port, addr, val); } @@ -1576,9 +1588,8 @@ static int ice_read_ptp_tstamp_eth56g(struct ice_hw *hw, u8 port, u8 idx, * lower 8 bits in the low register, and the upper 32 bits in the high * register. */ - *tstamp = FIELD_PREP(TS_PHY_HIGH_M, hi) | - FIELD_PREP(TS_PHY_LOW_M, lo); - + *tstamp = FIELD_PREP(PHY_40B_HIGH_M, hi) | + FIELD_PREP(PHY_40B_LOW_M, lo); return 0; } @@ -2639,18 +2650,17 @@ static void ice_sb_access_ena_eth56g(struct ice_hw *hw, bool enable) } /** - * ice_ptp_init_phc_eth56g - Perform E82X specific PHC initialization + * ice_ptp_init_phc_e825 - Perform E825 specific PHC initialization * @hw: pointer to HW struct * - * Perform PHC initialization steps specific to E82X devices. + * Perform E825-specific PTP hardware clock initialization steps. * - * Return: - * * %0 - success - * * %other - failed to initialize CGU + * Return: 0 on success, negative error code otherwise. */ -static int ice_ptp_init_phc_eth56g(struct ice_hw *hw) +static int ice_ptp_init_phc_e825(struct ice_hw *hw) { ice_sb_access_ena_eth56g(hw, true); + /* Initialize the Clock Generation Unit */ return ice_init_cgu_e82x(hw); } @@ -2729,10 +2739,7 @@ static void ice_ptp_init_phy_e825(struct ice_hw *hw) { struct ice_ptp_hw *ptp = &hw->ptp; struct ice_eth56g_params *params; - u32 phy_rev; - int err; - ptp->phy_model = ICE_PHY_ETH56G; params = &ptp->phy.eth56g; params->onestep_ena = false; params->peer_delay = 0; @@ -2742,9 +2749,6 @@ static void ice_ptp_init_phy_e825(struct ice_hw *hw) ptp->num_lports = params->num_phys * ptp->ports_per_phy; ice_sb_access_ena_eth56g(hw, true); - err = ice_read_phy_eth56g(hw, hw->pf_id, PHY_REG_REVISION, &phy_rev); - if (err || phy_rev != PHY_REVISION_ETH56G) - ptp->phy_model = ICE_PHY_UNSUP; } /* E822 family functions @@ -3219,7 +3223,8 @@ ice_read_phy_tstamp_e82x(struct ice_hw *hw, u8 quad, u8 idx, u64 *tstamp) * lower 8 bits in the low register, and the upper 32 bits in the high * register. */ - *tstamp = FIELD_PREP(TS_PHY_HIGH_M, hi) | FIELD_PREP(TS_PHY_LOW_M, lo); + *tstamp = FIELD_PREP(PHY_40B_HIGH_M, hi) | + FIELD_PREP(PHY_40B_LOW_M, lo); return 0; } @@ -4792,7 +4797,6 @@ int ice_phy_cfg_intr_e82x(struct ice_hw *hw, u8 quad, bool ena, u8 threshold) */ static void ice_ptp_init_phy_e82x(struct ice_ptp_hw *ptp) { - ptp->phy_model = ICE_PHY_E82X; ptp->num_lports = 8; ptp->ports_per_phy = 8; } @@ -4986,7 +4990,8 @@ ice_read_phy_tstamp_e810(struct ice_hw *hw, u8 lport, u8 idx, u64 *tstamp) /* For E810 devices, the timestamp is reported with the lower 32 bits * in the low register, and the upper 8 bits in the high register. */ - *tstamp = ((u64)hi) << TS_HIGH_S | ((u64)lo & TS_LOW_M); + *tstamp = FIELD_PREP(PHY_EXT_40B_HIGH_M, hi) | + FIELD_PREP(PHY_EXT_40B_LOW_M, lo); return 0; } @@ -5049,8 +5054,7 @@ static int ice_ptp_init_phc_e810(struct ice_hw *hw) u8 tmr_idx; int err; - /* Ensure synchronization delay is zero */ - wr32(hw, GLTSYN_SYNC_DLAY, 0); + ice_ptp_cfg_sync_delay(hw, ICE_E810_E830_SYNC_DELAY); tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; err = ice_write_phy_reg_e810(hw, ETH_GLTSYN_ENA(tmr_idx), @@ -5316,68 +5320,6 @@ ice_get_phy_tx_tstamp_ready_e810(struct ice_hw *hw, u8 port, u64 *tstamp_ready) */ /** - * ice_get_pca9575_handle - * @hw: pointer to the hw struct - * @pca9575_handle: GPIO controller's handle - * - * Find and return the GPIO controller's handle in the netlist. - * When found - the value will be cached in the hw structure and following calls - * will return cached value - */ -static int -ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle) -{ - struct ice_aqc_get_link_topo *cmd; - struct ice_aq_desc desc; - int status; - u8 idx; - - /* If handle was read previously return cached value */ - if (hw->io_expander_handle) { - *pca9575_handle = hw->io_expander_handle; - return 0; - } - - /* If handle was not detected read it from the netlist */ - cmd = &desc.params.get_link_topo; - ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo); - - /* Set node type to GPIO controller */ - cmd->addr.topo_params.node_type_ctx = - (ICE_AQC_LINK_TOPO_NODE_TYPE_M & - ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL); - -#define SW_PCA9575_SFP_TOPO_IDX 2 -#define SW_PCA9575_QSFP_TOPO_IDX 1 - - /* Check if the SW IO expander controlling SMA exists in the netlist. */ - if (hw->device_id == ICE_DEV_ID_E810C_SFP) - idx = SW_PCA9575_SFP_TOPO_IDX; - else if (hw->device_id == ICE_DEV_ID_E810C_QSFP) - idx = SW_PCA9575_QSFP_TOPO_IDX; - else - return -EOPNOTSUPP; - - cmd->addr.topo_params.index = idx; - - status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); - if (status) - return -EOPNOTSUPP; - - /* Verify if we found the right IO expander type */ - if (desc.params.get_link_topo.node_part_num != - ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575) - return -EOPNOTSUPP; - - /* If present save the handle and return it */ - hw->io_expander_handle = - le16_to_cpu(desc.params.get_link_topo.addr.handle); - *pca9575_handle = hw->io_expander_handle; - - return 0; -} - -/** * ice_read_sma_ctrl * @hw: pointer to the hw struct * @data: pointer to data to be read from the GPIO controller @@ -5442,37 +5384,6 @@ int ice_write_sma_ctrl(struct ice_hw *hw, u8 data) } /** - * ice_read_pca9575_reg - * @hw: pointer to the hw struct - * @offset: GPIO controller register offset - * @data: pointer to data to be read from the GPIO controller - * - * Read the register from the GPIO controller - */ -int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data) -{ - struct ice_aqc_link_topo_addr link_topo; - __le16 addr; - u16 handle; - int err; - - memset(&link_topo, 0, sizeof(link_topo)); - - err = ice_get_pca9575_handle(hw, &handle); - if (err) - return err; - - link_topo.handle = cpu_to_le16(handle); - link_topo.topo_params.node_type_ctx = - FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M, - ICE_AQC_LINK_TOPO_NODE_CTX_PROVIDED); - - addr = cpu_to_le16((u16)offset); - - return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL); -} - -/** * ice_ptp_read_sdp_ac - read SDP available connections section from NVM * @hw: pointer to the HW struct * @entries: returns the SDP available connections section from NVM @@ -5538,18 +5449,138 @@ exit: */ static void ice_ptp_init_phy_e810(struct ice_ptp_hw *ptp) { - ptp->phy_model = ICE_PHY_E810; ptp->num_lports = 8; ptp->ports_per_phy = 4; init_waitqueue_head(&ptp->phy.e810.atqbal_wq); } +/* E830 functions + * + * The following functions operate on the E830 series devices. + * + */ + +/** + * ice_ptp_init_phc_e830 - Perform E830 specific PHC initialization + * @hw: pointer to HW struct + * + * Perform E830-specific PTP hardware clock initialization steps. + */ +static void ice_ptp_init_phc_e830(const struct ice_hw *hw) +{ + ice_ptp_cfg_sync_delay(hw, ICE_E810_E830_SYNC_DELAY); +} + +/** + * ice_ptp_write_direct_incval_e830 - Prep PHY port increment value change + * @hw: pointer to HW struct + * @incval: The new 40bit increment value to prepare + * + * Prepare the PHY port for a new increment value by programming the PHC + * GLTSYN_INCVAL_L and GLTSYN_INCVAL_H registers. The actual change is + * completed by FW automatically. + */ +static void ice_ptp_write_direct_incval_e830(const struct ice_hw *hw, + u64 incval) +{ + u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + + wr32(hw, GLTSYN_INCVAL_L(tmr_idx), lower_32_bits(incval)); + wr32(hw, GLTSYN_INCVAL_H(tmr_idx), upper_32_bits(incval)); +} + +/** + * ice_ptp_write_direct_phc_time_e830 - Prepare PHY port with initial time + * @hw: Board private structure + * @time: Time to initialize the PHY port clock to + * + * Program the PHY port ETH_GLTSYN_SHTIME registers in preparation setting the + * initial clock time. The time will not actually be programmed until the + * driver issues an ICE_PTP_INIT_TIME command. + * + * The time value is the upper 32 bits of the PHY timer, usually in units of + * nominal nanoseconds. + */ +static void ice_ptp_write_direct_phc_time_e830(const struct ice_hw *hw, + u64 time) +{ + u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + + wr32(hw, GLTSYN_TIME_0(tmr_idx), 0); + wr32(hw, GLTSYN_TIME_L(tmr_idx), lower_32_bits(time)); + wr32(hw, GLTSYN_TIME_H(tmr_idx), upper_32_bits(time)); +} + +/** + * ice_ptp_port_cmd_e830 - Prepare all external PHYs for a timer command + * @hw: pointer to HW struct + * @cmd: Command to be sent to the port + * + * Prepare the external PHYs connected to this device for a timer sync + * command. + * + * Return: 0 on success, negative error code when PHY write failed + */ +static int ice_ptp_port_cmd_e830(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) +{ + u32 val = ice_ptp_tmr_cmd_to_port_reg(hw, cmd); + + return ice_write_phy_reg_e810(hw, E830_ETH_GLTSYN_CMD, val); +} + +/** + * ice_read_phy_tstamp_e830 - Read a PHY timestamp out of the external PHY + * @hw: pointer to the HW struct + * @idx: the timestamp index to read + * @tstamp: on return, the 40bit timestamp value + * + * Read a 40bit timestamp value out of the timestamp block of the external PHY + * on the E830 device. + */ +static void ice_read_phy_tstamp_e830(const struct ice_hw *hw, u8 idx, + u64 *tstamp) +{ + u32 hi, lo; + + hi = rd32(hw, E830_PRTTSYN_TXTIME_H(idx)); + lo = rd32(hw, E830_PRTTSYN_TXTIME_L(idx)); + + /* For E830 devices, the timestamp is reported with the lower 32 bits + * in the low register, and the upper 8 bits in the high register. + */ + *tstamp = FIELD_PREP(PHY_EXT_40B_HIGH_M, hi) | + FIELD_PREP(PHY_EXT_40B_LOW_M, lo); +} + +/** + * ice_get_phy_tx_tstamp_ready_e830 - Read Tx memory status register + * @hw: pointer to the HW struct + * @port: the PHY port to read + * @tstamp_ready: contents of the Tx memory status register + */ +static void ice_get_phy_tx_tstamp_ready_e830(const struct ice_hw *hw, u8 port, + u64 *tstamp_ready) +{ + *tstamp_ready = rd32(hw, E830_PRTMAC_TS_TX_MEM_VALID_H); + *tstamp_ready <<= 32; + *tstamp_ready |= rd32(hw, E830_PRTMAC_TS_TX_MEM_VALID_L); +} + +/** + * ice_ptp_init_phy_e830 - initialize PHY parameters + * @ptp: pointer to the PTP HW struct + */ +static void ice_ptp_init_phy_e830(struct ice_ptp_hw *ptp) +{ + ptp->num_lports = 8; + ptp->ports_per_phy = 4; +} + /* Device agnostic functions * - * The following functions implement shared behavior common to both E822 and - * E810 devices, possibly calling a device specific implementation where - * necessary. + * The following functions implement shared behavior common to all devices, + * possibly calling a device specific implementation where necessary. */ /** @@ -5612,14 +5643,22 @@ void ice_ptp_init_hw(struct ice_hw *hw) { struct ice_ptp_hw *ptp = &hw->ptp; - if (ice_is_e822(hw) || ice_is_e823(hw)) - ice_ptp_init_phy_e82x(ptp); - else if (ice_is_e810(hw)) + switch (hw->mac_type) { + case ICE_MAC_E810: ice_ptp_init_phy_e810(ptp); - else if (ice_is_e825c(hw)) + break; + case ICE_MAC_E830: + ice_ptp_init_phy_e830(ptp); + break; + case ICE_MAC_GENERIC: + ice_ptp_init_phy_e82x(ptp); + break; + case ICE_MAC_GENERIC_3K_E825: ice_ptp_init_phy_e825(hw); - else - ptp->phy_model = ICE_PHY_UNSUP; + break; + default: + return; + } } /** @@ -5640,11 +5679,11 @@ void ice_ptp_init_hw(struct ice_hw *hw) static int ice_ptp_write_port_cmd(struct ice_hw *hw, u8 port, enum ice_ptp_tmr_cmd cmd) { - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_ptp_write_port_cmd_eth56g(hw, port, cmd); - case ICE_PHY_E82X: + switch (hw->mac_type) { + case ICE_MAC_GENERIC: return ice_ptp_write_port_cmd_e82x(hw, port, cmd); + case ICE_MAC_GENERIC_3K_E825: + return ice_ptp_write_port_cmd_eth56g(hw, port, cmd); default: return -EOPNOTSUPP; } @@ -5705,9 +5744,11 @@ static int ice_ptp_port_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd) u32 port; /* PHY models which can program all ports simultaneously */ - switch (ice_get_phy_model(hw)) { - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: return ice_ptp_port_cmd_e810(hw, cmd); + case ICE_MAC_E830: + return ice_ptp_port_cmd_e830(hw, cmd); default: break; } @@ -5778,23 +5819,29 @@ int ice_ptp_init_time(struct ice_hw *hw, u64 time) tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; /* Source timers */ + /* For E830 we don't need to use shadow registers, its automatic */ + if (hw->mac_type == ICE_MAC_E830) { + ice_ptp_write_direct_phc_time_e830(hw, time); + return 0; + } + wr32(hw, GLTSYN_SHTIME_L(tmr_idx), lower_32_bits(time)); wr32(hw, GLTSYN_SHTIME_H(tmr_idx), upper_32_bits(time)); wr32(hw, GLTSYN_SHTIME_0(tmr_idx), 0); /* PHY timers */ /* Fill Rx and Tx ports and send msg to PHY */ - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - err = ice_ptp_prep_phy_time_eth56g(hw, - (u32)(time & 0xFFFFFFFF)); - break; - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: err = ice_ptp_prep_phy_time_e810(hw, time & 0xFFFFFFFF); break; - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: err = ice_ptp_prep_phy_time_e82x(hw, time & 0xFFFFFFFF); break; + case ICE_MAC_GENERIC_3K_E825: + err = ice_ptp_prep_phy_time_eth56g(hw, + (u32)(time & 0xFFFFFFFF)); + break; default: err = -EOPNOTSUPP; } @@ -5826,20 +5873,26 @@ int ice_ptp_write_incval(struct ice_hw *hw, u64 incval) tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned; + /* For E830 we don't need to use shadow registers, its automatic */ + if (hw->mac_type == ICE_MAC_E830) { + ice_ptp_write_direct_incval_e830(hw, incval); + return 0; + } + /* Shadow Adjust */ wr32(hw, GLTSYN_SHADJ_L(tmr_idx), lower_32_bits(incval)); wr32(hw, GLTSYN_SHADJ_H(tmr_idx), upper_32_bits(incval)); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - err = ice_ptp_prep_phy_incval_eth56g(hw, incval); - break; - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: err = ice_ptp_prep_phy_incval_e810(hw, incval); break; - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: err = ice_ptp_prep_phy_incval_e82x(hw, incval); break; + case ICE_MAC_GENERIC_3K_E825: + err = ice_ptp_prep_phy_incval_eth56g(hw, incval); + break; default: err = -EOPNOTSUPP; } @@ -5899,16 +5952,19 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj) wr32(hw, GLTSYN_SHADJ_L(tmr_idx), 0); wr32(hw, GLTSYN_SHADJ_H(tmr_idx), adj); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - err = ice_ptp_prep_phy_adj_eth56g(hw, adj); - break; - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: err = ice_ptp_prep_phy_adj_e810(hw, adj); break; - case ICE_PHY_E82X: + case ICE_MAC_E830: + /* E830 sync PHYs automatically after setting GLTSYN_SHADJ */ + return 0; + case ICE_MAC_GENERIC: err = ice_ptp_prep_phy_adj_e82x(hw, adj); break; + case ICE_MAC_GENERIC_3K_E825: + err = ice_ptp_prep_phy_adj_eth56g(hw, adj); + break; default: err = -EOPNOTSUPP; } @@ -5932,13 +5988,16 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj) */ int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp) { - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_read_ptp_tstamp_eth56g(hw, block, idx, tstamp); - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: return ice_read_phy_tstamp_e810(hw, block, idx, tstamp); - case ICE_PHY_E82X: + case ICE_MAC_E830: + ice_read_phy_tstamp_e830(hw, idx, tstamp); + return 0; + case ICE_MAC_GENERIC: return ice_read_phy_tstamp_e82x(hw, block, idx, tstamp); + case ICE_MAC_GENERIC_3K_E825: + return ice_read_ptp_tstamp_eth56g(hw, block, idx, tstamp); default: return -EOPNOTSUPP; } @@ -5962,13 +6021,13 @@ int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp) */ int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx) { - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_clear_ptp_tstamp_eth56g(hw, block, idx); - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: return ice_clear_phy_tstamp_e810(hw, block, idx); - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: return ice_clear_phy_tstamp_e82x(hw, block, idx); + case ICE_MAC_GENERIC_3K_E825: + return ice_clear_ptp_tstamp_eth56g(hw, block, idx); default: return -EOPNOTSUPP; } @@ -6025,14 +6084,14 @@ static int ice_get_pf_c827_idx(struct ice_hw *hw, u8 *idx) */ void ice_ptp_reset_ts_memory(struct ice_hw *hw) { - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - ice_ptp_reset_ts_memory_eth56g(hw); - break; - case ICE_PHY_E82X: + switch (hw->mac_type) { + case ICE_MAC_GENERIC: ice_ptp_reset_ts_memory_e82x(hw); break; - case ICE_PHY_E810: + case ICE_MAC_GENERIC_3K_E825: + ice_ptp_reset_ts_memory_eth56g(hw); + break; + case ICE_MAC_E810: default: return; } @@ -6054,13 +6113,16 @@ int ice_ptp_init_phc(struct ice_hw *hw) /* Clear event err indications for auxiliary pins */ (void)rd32(hw, GLTSYN_STAT(src_idx)); - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_ptp_init_phc_eth56g(hw); - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: return ice_ptp_init_phc_e810(hw); - case ICE_PHY_E82X: + case ICE_MAC_E830: + ice_ptp_init_phc_e830(hw); + return 0; + case ICE_MAC_GENERIC: return ice_ptp_init_phc_e82x(hw); + case ICE_MAC_GENERIC_3K_E825: + return ice_ptp_init_phc_e825(hw); default: return -EOPNOTSUPP; } @@ -6079,17 +6141,19 @@ int ice_ptp_init_phc(struct ice_hw *hw) */ int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready) { - switch (ice_get_phy_model(hw)) { - case ICE_PHY_ETH56G: - return ice_get_phy_tx_tstamp_ready_eth56g(hw, block, - tstamp_ready); - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: return ice_get_phy_tx_tstamp_ready_e810(hw, block, tstamp_ready); - case ICE_PHY_E82X: + case ICE_MAC_E830: + ice_get_phy_tx_tstamp_ready_e830(hw, block, tstamp_ready); + return 0; + case ICE_MAC_GENERIC: return ice_get_phy_tx_tstamp_ready_e82x(hw, block, tstamp_ready); - break; + case ICE_MAC_GENERIC_3K_E825: + return ice_get_phy_tx_tstamp_ready_eth56g(hw, block, + tstamp_ready); default: return -EOPNOTSUPP; } diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h index 6779ce120515..e5925ccc2613 100644 --- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h +++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h @@ -65,14 +65,14 @@ enum ice_eth56g_link_spd { /** * struct ice_phy_reg_info_eth56g - ETH56G PHY register parameters - * @base: base address for each PHY block + * @base_addr: base address for each PHY block * @step: step between PHY lanes * * Characteristic information for the various PHY register parameters in the * ETH56G devices */ struct ice_phy_reg_info_eth56g { - u32 base[NUM_ETH56G_PHY_RES]; + u32 base_addr; u32 step; }; @@ -324,6 +324,7 @@ extern const struct ice_vernier_info_e82x e822_vernier[NUM_ICE_PTP_LNK_SPD]; */ #define ICE_E810_PLL_FREQ 812500000 #define ICE_PTP_NOMINAL_INCVAL_E810 0x13b13b13bULL +#define ICE_E810_E830_SYNC_DELAY 0 /* Device agnostic functions */ u8 ice_get_ptp_src_clock_index(struct ice_hw *hw); @@ -395,7 +396,6 @@ int ice_phy_cfg_intr_e82x(struct ice_hw *hw, u8 quad, bool ena, u8 threshold); /* E810 family functions */ int ice_read_sma_ctrl(struct ice_hw *hw, u8 *data); int ice_write_sma_ctrl(struct ice_hw *hw, u8 data); -int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data); int ice_ptp_read_sdp_ac(struct ice_hw *hw, __le16 *entries, uint *num_entries); int ice_cgu_get_num_pins(struct ice_hw *hw, bool input); enum dpll_pin_type ice_cgu_get_pin_type(struct ice_hw *hw, u8 pin, bool input); @@ -431,13 +431,14 @@ int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port); */ static inline u64 ice_get_base_incval(struct ice_hw *hw) { - switch (hw->ptp.phy_model) { - case ICE_PHY_ETH56G: - return ICE_ETH56G_NOMINAL_INCVAL; - case ICE_PHY_E810: + switch (hw->mac_type) { + case ICE_MAC_E810: + case ICE_MAC_E830: return ICE_PTP_NOMINAL_INCVAL_E810; - case ICE_PHY_E82X: + case ICE_MAC_GENERIC: return ice_e82x_nominal_incval(ice_e82x_time_ref(hw)); + case ICE_MAC_GENERIC_3K_E825: + return ICE_ETH56G_NOMINAL_INCVAL; default: return 0; } @@ -650,18 +651,25 @@ static inline bool ice_is_dual(struct ice_hw *hw) /* E810 timer command register */ #define E810_ETH_GLTSYN_CMD 0x03000344 +/* E830 timer command register */ +#define E830_ETH_GLTSYN_CMD 0x00088814 + +/* E810 PHC time register */ +#define E830_GLTSYN_TIME_L(_tmr_idx) (0x0008A000 + 0x1000 * (_tmr_idx)) + /* Source timer incval macros */ #define INCVAL_HIGH_M 0xFF -/* Timestamp block macros */ +/* PHY 40b registers macros */ +#define PHY_EXT_40B_LOW_M GENMASK(31, 0) +#define PHY_EXT_40B_HIGH_M GENMASK_ULL(39, 32) +#define PHY_40B_LOW_M GENMASK(7, 0) +#define PHY_40B_HIGH_M GENMASK_ULL(39, 8) #define TS_VALID BIT(0) #define TS_LOW_M 0xFFFFFFFF #define TS_HIGH_M 0xFF #define TS_HIGH_S 32 -#define TS_PHY_LOW_M GENMASK(7, 0) -#define TS_PHY_HIGH_M GENMASK_ULL(39, 8) - #define BYTES_PER_IDX_ADDR_L_U 8 #define BYTES_PER_IDX_ADDR_L 4 @@ -772,36 +780,19 @@ static inline bool ice_is_dual(struct ice_hw *hw) #define PHY_MAC_XIF_TS_SFD_ENA_M ICE_M(0x1, 20) #define PHY_MAC_XIF_GMII_TS_SEL_M ICE_M(0x1, 21) -/* GPCS config register */ -#define PHY_GPCS_CONFIG_REG0 0x268 -#define PHY_GPCS_CONFIG_REG0_TX_THR_M ICE_M(0xF, 24) -#define PHY_GPCS_BITSLIP 0x5C - #define PHY_TS_INT_CONFIG_THRESHOLD_M ICE_M(0x3F, 0) #define PHY_TS_INT_CONFIG_ENA_M BIT(6) -/* 1-step PTP config */ -#define PHY_PTP_1STEP_CONFIG 0x270 -#define PHY_PTP_1STEP_T1S_UP64_M ICE_M(0xF, 4) -#define PHY_PTP_1STEP_T1S_DELTA_M ICE_M(0xF, 8) -#define PHY_PTP_1STEP_PEER_DELAY(_port) (0x274 + 4 * (_port)) -#define PHY_PTP_1STEP_PD_ADD_PD_M ICE_M(0x1, 0) -#define PHY_PTP_1STEP_PD_DELAY_M ICE_M(0x3fffffff, 1) -#define PHY_PTP_1STEP_PD_DLY_V_M ICE_M(0x1, 31) - /* Macros to derive offsets for TimeStampLow and TimeStampHigh */ #define PHY_TSTAMP_L(x) (((x) * 8) + 0) #define PHY_TSTAMP_U(x) (((x) * 8) + 4) -#define PHY_REG_REVISION 0x85000 - #define PHY_REG_DESKEW_0 0x94 #define PHY_REG_DESKEW_0_RLEVEL GENMASK(6, 0) #define PHY_REG_DESKEW_0_RLEVEL_FRAC GENMASK(9, 7) #define PHY_REG_DESKEW_0_RLEVEL_FRAC_W 3 #define PHY_REG_DESKEW_0_VALID GENMASK(10, 10) -#define PHY_REG_GPCS_BITSLIP 0x5C #define PHY_REG_SD_BIT_SLIP(_port_offset) (0x29C + 4 * (_port_offset)) #define PHY_REVISION_ETH56G 0x10200 #define PHY_VENDOR_TXLANE_THRESH 0x2000C @@ -821,7 +812,21 @@ static inline bool ice_is_dual(struct ice_hw *hw) #define PHY_MAC_BLOCKTIME 0x50 #define PHY_MAC_MARKERTIME 0x54 #define PHY_MAC_TX_OFFSET 0x58 +#define PHY_GPCS_BITSLIP 0x5C #define PHY_PTP_INT_STATUS 0x7FD140 +/* ETH56G registers shared per quad */ +/* GPCS config register */ +#define PHY_GPCS_CONFIG_REG0 0x268 +#define PHY_GPCS_CONFIG_REG0_TX_THR_M GENMASK(27, 24) +/* 1-step PTP config */ +#define PHY_PTP_1STEP_CONFIG 0x270 +#define PHY_PTP_1STEP_T1S_UP64_M GENMASK(7, 4) +#define PHY_PTP_1STEP_T1S_DELTA_M GENMASK(11, 8) +#define PHY_PTP_1STEP_PEER_DELAY(_quad_lane) (0x274 + 4 * (_quad_lane)) +#define PHY_PTP_1STEP_PD_ADD_PD_M BIT(0) +#define PHY_PTP_1STEP_PD_DELAY_M GENMASK(30, 1) +#define PHY_PTP_1STEP_PD_DLY_V_M BIT(31) + #endif /* _ICE_PTP_HW_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index 8aabf7749aa5..f1648cf103b7 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -124,27 +124,6 @@ static void ice_dis_vf_mappings(struct ice_vf *vf) } /** - * ice_sriov_free_msix_res - Reset/free any used MSIX resources - * @pf: pointer to the PF structure - * - * Since no MSIX entries are taken from the pf->irq_tracker then just clear - * the pf->sriov_base_vector. - * - * Returns 0 on success, and -EINVAL on error. - */ -static int ice_sriov_free_msix_res(struct ice_pf *pf) -{ - if (!pf) - return -EINVAL; - - bitmap_free(pf->sriov_irq_bm); - pf->sriov_irq_size = 0; - pf->sriov_base_vector = 0; - - return 0; -} - -/** * ice_free_vfs - Free all VFs * @pf: pointer to the PF structure */ @@ -178,6 +157,7 @@ void ice_free_vfs(struct ice_pf *pf) ice_eswitch_detach_vf(pf, vf); ice_dis_vf_qs(vf); + ice_virt_free_irqs(pf, vf->first_vector_idx, vf->num_msix); if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) { /* disable VF qp mappings and set VF disable state */ @@ -197,9 +177,6 @@ void ice_free_vfs(struct ice_pf *pf) mutex_unlock(&vf->cfg_lock); } - if (ice_sriov_free_msix_res(pf)) - dev_err(dev, "Failed to free MSIX resources used by SR-IOV\n"); - vfs->num_qps_per = 0; ice_free_vf_entries(pf); @@ -369,40 +346,6 @@ void ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector) } /** - * ice_sriov_set_msix_res - Set any used MSIX resources - * @pf: pointer to PF structure - * @num_msix_needed: number of MSIX vectors needed for all SR-IOV VFs - * - * This function allows SR-IOV resources to be taken from the end of the PF's - * allowed HW MSIX vectors so that the irq_tracker will not be affected. We - * just set the pf->sriov_base_vector and return success. - * - * If there are not enough resources available, return an error. This should - * always be caught by ice_set_per_vf_res(). - * - * Return 0 on success, and -EINVAL when there are not enough MSIX vectors - * in the PF's space available for SR-IOV. - */ -static int ice_sriov_set_msix_res(struct ice_pf *pf, u16 num_msix_needed) -{ - u16 total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors; - int vectors_used = ice_get_max_used_msix_vector(pf); - int sriov_base_vector; - - sriov_base_vector = total_vectors - num_msix_needed; - - /* make sure we only grab irq_tracker entries from the list end and - * that we have enough available MSIX vectors - */ - if (sriov_base_vector < vectors_used) - return -EINVAL; - - pf->sriov_base_vector = sriov_base_vector; - - return 0; -} - -/** * ice_set_per_vf_res - check if vectors and queues are available * @pf: pointer to the PF structure * @num_vfs: the number of SR-IOV VFs being configured @@ -426,11 +369,9 @@ static int ice_sriov_set_msix_res(struct ice_pf *pf, u16 num_msix_needed) */ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs) { - int vectors_used = ice_get_max_used_msix_vector(pf); u16 num_msix_per_vf, num_txq, num_rxq, avail_qs; int msix_avail_per_vf, msix_avail_for_sriov; struct device *dev = ice_pf_to_dev(pf); - int err; lockdep_assert_held(&pf->vfs.table_lock); @@ -438,8 +379,7 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs) return -EINVAL; /* determine MSI-X resources per VF */ - msix_avail_for_sriov = pf->hw.func_caps.common_cap.num_msix_vectors - - vectors_used; + msix_avail_for_sriov = pf->virt_irq_tracker.num_entries; msix_avail_per_vf = msix_avail_for_sriov / num_vfs; if (msix_avail_per_vf >= ICE_NUM_VF_MSIX_MED) { num_msix_per_vf = ICE_NUM_VF_MSIX_MED; @@ -478,13 +418,6 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs) return -ENOSPC; } - err = ice_sriov_set_msix_res(pf, num_msix_per_vf * num_vfs); - if (err) { - dev_err(dev, "Unable to set MSI-X resources for %d VFs, err %d\n", - num_vfs, err); - return err; - } - /* only allow equal Tx/Rx queue count (i.e. queue pairs) */ pf->vfs.num_qps_per = min_t(int, num_txq, num_rxq); pf->vfs.num_msix_per = num_msix_per_vf; @@ -495,52 +428,6 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs) } /** - * ice_sriov_get_irqs - get irqs for SR-IOV usacase - * @pf: pointer to PF structure - * @needed: number of irqs to get - * - * This returns the first MSI-X vector index in PF space that is used by this - * VF. This index is used when accessing PF relative registers such as - * GLINT_VECT2FUNC and GLINT_DYN_CTL. - * This will always be the OICR index in the AVF driver so any functionality - * using vf->first_vector_idx for queue configuration_id: id of VF which will - * use this irqs - * - * Only SRIOV specific vectors are tracked in sriov_irq_bm. SRIOV vectors are - * allocated from the end of global irq index. First bit in sriov_irq_bm means - * last irq index etc. It simplifies extension of SRIOV vectors. - * They will be always located from sriov_base_vector to the last irq - * index. While increasing/decreasing sriov_base_vector can be moved. - */ -static int ice_sriov_get_irqs(struct ice_pf *pf, u16 needed) -{ - int res = bitmap_find_next_zero_area(pf->sriov_irq_bm, - pf->sriov_irq_size, 0, needed, 0); - /* conversion from number in bitmap to global irq index */ - int index = pf->sriov_irq_size - res - needed; - - if (res >= pf->sriov_irq_size || index < pf->sriov_base_vector) - return -ENOENT; - - bitmap_set(pf->sriov_irq_bm, res, needed); - return index; -} - -/** - * ice_sriov_free_irqs - free irqs used by the VF - * @pf: pointer to PF structure - * @vf: pointer to VF structure - */ -static void ice_sriov_free_irqs(struct ice_pf *pf, struct ice_vf *vf) -{ - /* Move back from first vector index to first index in bitmap */ - int bm_i = pf->sriov_irq_size - vf->first_vector_idx - vf->num_msix; - - bitmap_clear(pf->sriov_irq_bm, bm_i, vf->num_msix); - vf->first_vector_idx = 0; -} - -/** * ice_init_vf_vsi_res - initialize/setup VF VSI resources * @vf: VF to initialize/setup the VSI for * @@ -553,7 +440,7 @@ static int ice_init_vf_vsi_res(struct ice_vf *vf) struct ice_vsi *vsi; int err; - vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix); + vf->first_vector_idx = ice_virt_get_irqs(pf, vf->num_msix); if (vf->first_vector_idx < 0) return -ENOMEM; @@ -853,16 +740,10 @@ err_free_entries: */ static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs) { - int total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors; struct device *dev = ice_pf_to_dev(pf); struct ice_hw *hw = &pf->hw; int ret; - pf->sriov_irq_bm = bitmap_zalloc(total_vectors, GFP_KERNEL); - if (!pf->sriov_irq_bm) - return -ENOMEM; - pf->sriov_irq_size = total_vectors; - /* Disable global interrupt 0 so we don't try to handle the VFLR. */ wr32(hw, GLINT_DYN_CTL(pf->oicr_irq.index), ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S); @@ -915,7 +796,6 @@ err_unroll_intr: /* rearm interrupts here */ ice_irq_dynamic_ena(hw, NULL, NULL); clear_bit(ICE_OICR_INTR_DIS, pf->state); - bitmap_free(pf->sriov_irq_bm); return ret; } @@ -989,16 +869,7 @@ u32 ice_sriov_get_vf_total_msix(struct pci_dev *pdev) { struct ice_pf *pf = pci_get_drvdata(pdev); - return pf->sriov_irq_size - ice_get_max_used_msix_vector(pf); -} - -static int ice_sriov_move_base_vector(struct ice_pf *pf, int move) -{ - if (pf->sriov_base_vector - move < ice_get_max_used_msix_vector(pf)) - return -ENOMEM; - - pf->sriov_base_vector -= move; - return 0; + return pf->virt_irq_tracker.num_entries; } static void ice_sriov_remap_vectors(struct ice_pf *pf, u16 restricted_id) @@ -1017,7 +888,8 @@ static void ice_sriov_remap_vectors(struct ice_pf *pf, u16 restricted_id) continue; ice_dis_vf_mappings(tmp_vf); - ice_sriov_free_irqs(pf, tmp_vf); + ice_virt_free_irqs(pf, tmp_vf->first_vector_idx, + tmp_vf->num_msix); vf_ids[to_remap] = tmp_vf->vf_id; to_remap += 1; @@ -1029,7 +901,7 @@ static void ice_sriov_remap_vectors(struct ice_pf *pf, u16 restricted_id) continue; tmp_vf->first_vector_idx = - ice_sriov_get_irqs(pf, tmp_vf->num_msix); + ice_virt_get_irqs(pf, tmp_vf->num_msix); /* there is no need to rebuild VSI as we are only changing the * vector indexes not amount of MSI-X or queues */ @@ -1102,20 +974,15 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count) prev_msix = vf->num_msix; prev_queues = vf->num_vf_qs; - if (ice_sriov_move_base_vector(pf, msix_vec_count - prev_msix)) { - ice_put_vf(vf); - return -ENOSPC; - } - ice_dis_vf_mappings(vf); - ice_sriov_free_irqs(pf, vf); + ice_virt_free_irqs(pf, vf->first_vector_idx, vf->num_msix); /* Remap all VFs beside the one is now configured */ ice_sriov_remap_vectors(pf, vf->vf_id); vf->num_msix = msix_vec_count; vf->num_vf_qs = queues; - vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix); + vf->first_vector_idx = ice_virt_get_irqs(pf, vf->num_msix); if (vf->first_vector_idx < 0) goto unroll; @@ -1144,7 +1011,8 @@ unroll: vf->num_msix = prev_msix; vf->num_vf_qs = prev_queues; - vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix); + + vf->first_vector_idx = ice_virt_get_irqs(pf, vf->num_msix); if (vf->first_vector_idx < 0) { ice_put_vf(vf); return -EINVAL; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 380ba1e8b3b2..1e4f6f6ee449 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -1809,6 +1809,7 @@ dma_error: static int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off) { + const struct ice_tx_ring *tx_ring = off->tx_ring; u32 l4_len = 0, l3_len = 0, l2_len = 0; struct sk_buff *skb = first->skb; union { @@ -1958,6 +1959,30 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off) l3_len = l4.hdr - ip.hdr; offset |= (l3_len / 4) << ICE_TX_DESC_LEN_IPLEN_S; + if ((tx_ring->netdev->features & NETIF_F_HW_CSUM) && + !(first->tx_flags & ICE_TX_FLAGS_TSO) && + !skb_csum_is_sctp(skb)) { + /* Set GCS */ + u16 csum_start = (skb->csum_start - skb->mac_header) / 2; + u16 csum_offset = skb->csum_offset / 2; + u16 gcs_params; + + gcs_params = FIELD_PREP(ICE_TX_GCS_DESC_START_M, csum_start) | + FIELD_PREP(ICE_TX_GCS_DESC_OFFSET_M, csum_offset) | + FIELD_PREP(ICE_TX_GCS_DESC_TYPE_M, + ICE_TX_GCS_DESC_CSUM_PSH); + + /* Unlike legacy HW checksums, GCS requires a context + * descriptor. + */ + off->cd_qw1 |= ICE_TX_DESC_DTYPE_CTX; + off->cd_gcs_params = gcs_params; + /* Fill out CSO info in data descriptors */ + off->td_offset |= offset; + off->td_cmd |= cmd; + return 1; + } + /* Enable L4 checksum offloads */ switch (l4_proto) { case IPPROTO_TCP: @@ -2441,7 +2466,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) /* setup context descriptor */ cdesc->tunneling_params = cpu_to_le32(offload.cd_tunnel_params); cdesc->l2tag2 = cpu_to_le16(offload.cd_l2tag2); - cdesc->rsvd = cpu_to_le16(0); + cdesc->gcs = cpu_to_le16(offload.cd_gcs_params); cdesc->qw1 = cpu_to_le64(offload.cd_qw1); } diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index 806bce701df3..a4b1e9514632 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -193,6 +193,7 @@ struct ice_tx_offload_params { u32 td_l2tag1; u32 cd_tunnel_params; u16 cd_l2tag2; + u16 cd_gcs_params; u8 header_len; }; @@ -366,6 +367,7 @@ struct ice_rx_ring { #define ICE_RX_FLAGS_RING_BUILD_SKB BIT(1) #define ICE_RX_FLAGS_CRC_STRIP_DIS BIT(2) #define ICE_RX_FLAGS_MULTIDEV BIT(3) +#define ICE_RX_FLAGS_RING_GCS BIT(4) u8 flags; /* CL5 - 5th cacheline starts here */ struct xdp_rxq_info xdp_rxq; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index 2719f0e20933..45cfaabc41cb 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -81,6 +81,23 @@ ice_rx_hash_to_skb(const struct ice_rx_ring *rx_ring, } /** + * ice_rx_gcs - Set generic checksum in skb + * @skb: skb currently being received and modified + * @rx_desc: receive descriptor + */ +static void ice_rx_gcs(struct sk_buff *skb, + const union ice_32b_rx_flex_desc *rx_desc) +{ + const struct ice_32b_rx_flex_desc_nic *desc; + u16 csum; + + desc = (struct ice_32b_rx_flex_desc_nic *)rx_desc; + skb->ip_summed = CHECKSUM_COMPLETE; + csum = (__force u16)desc->raw_csum; + skb->csum = csum_unfold((__force __sum16)swab16(csum)); +} + +/** * ice_rx_csum - Indicate in skb if checksum is good * @ring: the ring we care about * @skb: skb currently being received and modified @@ -107,6 +124,15 @@ ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb, rx_status0 = le16_to_cpu(rx_desc->wb.status_error0); rx_status1 = le16_to_cpu(rx_desc->wb.status_error1); + if ((ring->flags & ICE_RX_FLAGS_RING_GCS) && + rx_desc->wb.rxdid == ICE_RXDID_FLEX_NIC && + (decoded.inner_prot == LIBETH_RX_PT_INNER_TCP || + decoded.inner_prot == LIBETH_RX_PT_INNER_UDP || + decoded.inner_prot == LIBETH_RX_PT_INNER_ICMP)) { + ice_rx_gcs(skb, rx_desc); + return; + } + /* check if HW has decoded the packet and checksum */ if (!(rx_status0 & BIT(ICE_RX_FLEX_DESC_STATUS0_L3L4P_S))) return; diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 33a1a5934c0d..0aab21113cc4 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -871,14 +871,6 @@ union ice_phy_params { struct ice_eth56g_params eth56g; }; -/* PHY model */ -enum ice_phy_model { - ICE_PHY_UNSUP = -1, - ICE_PHY_E810 = 1, - ICE_PHY_E82X, - ICE_PHY_ETH56G, -}; - /* Global Link Topology */ enum ice_global_link_topo { ICE_LINK_TOPO_UP_TO_2_LINKS, @@ -888,7 +880,6 @@ enum ice_global_link_topo { }; struct ice_ptp_hw { - enum ice_phy_model phy_model; union ice_phy_params phy; u8 num_lports; u8 ports_per_phy; diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index 4261fe1c2bcd..799b2c1f1184 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -124,6 +124,9 @@ struct ice_vf { u8 spoofchk:1; u8 link_forced:1; u8 link_up:1; /* only valid if VF link is forced */ + + u32 ptp_caps; + unsigned int min_tx_rate; /* Minimum Tx bandwidth limit in Mbps */ unsigned int max_tx_rate; /* Maximum Tx bandwidth limit in Mbps */ DECLARE_BITMAP(vf_states, ICE_VF_STATES_NBITS); /* VF runtime states */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index ff4ad788d96a..7c3006eb68dd 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -498,6 +498,9 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg) if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_QOS) vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_QOS; + if (vf->driver_caps & VIRTCHNL_VF_CAP_PTP) + vfres->vf_cap_flags |= VIRTCHNL_VF_CAP_PTP; + vfres->num_vsis = 1; /* Tx and Rx queue are equal for VF */ vfres->num_queue_pairs = vsi->num_txq; @@ -562,7 +565,7 @@ bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id) * * check for the valid queue ID */ -static bool ice_vc_isvalid_q_id(struct ice_vsi *vsi, u8 qid) +static bool ice_vc_isvalid_q_id(struct ice_vsi *vsi, u16 qid) { /* allocated Tx and Rx queues should be always equal for VF VSI */ return qid < vsi->alloc_txq; @@ -1862,15 +1865,33 @@ static int ice_vc_cfg_q_bw(struct ice_vf *vf, u8 *msg) for (i = 0; i < qbw->num_queues; i++) { if (qbw->cfg[i].shaper.peak != 0 && vf->max_tx_rate != 0 && - qbw->cfg[i].shaper.peak > vf->max_tx_rate) + qbw->cfg[i].shaper.peak > vf->max_tx_rate) { dev_warn(ice_pf_to_dev(vf->pf), "The maximum queue %d rate limit configuration may not take effect because the maximum TX rate for VF-%d is %d\n", qbw->cfg[i].queue_id, vf->vf_id, vf->max_tx_rate); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } if (qbw->cfg[i].shaper.committed != 0 && vf->min_tx_rate != 0 && - qbw->cfg[i].shaper.committed < vf->min_tx_rate) + qbw->cfg[i].shaper.committed < vf->min_tx_rate) { dev_warn(ice_pf_to_dev(vf->pf), "The minimum queue %d rate limit configuration may not take effect because the minimum TX rate for VF-%d is %d\n", qbw->cfg[i].queue_id, vf->vf_id, - vf->max_tx_rate); + vf->min_tx_rate); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + if (qbw->cfg[i].queue_id > vf->num_vf_qs) { + dev_warn(ice_pf_to_dev(vf->pf), "VF-%d trying to configure invalid queue_id\n", + vf->vf_id); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + if (qbw->cfg[i].tc >= ICE_MAX_TRAFFIC_CLASS) { + dev_warn(ice_pf_to_dev(vf->pf), "VF-%d trying to configure a traffic class higher than allowed\n", + vf->vf_id); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } } for (i = 0; i < qbw->num_queues; i++) { @@ -1900,13 +1921,21 @@ err: */ static int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg) { + u16 quanta_prof_id, quanta_size, start_qid, num_queues, end_qid, i; enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - u16 quanta_prof_id, quanta_size, start_qid, end_qid, i; struct virtchnl_quanta_cfg *qquanta = (struct virtchnl_quanta_cfg *)msg; struct ice_vsi *vsi; int ret; + start_qid = qquanta->queue_select.start_queue_id; + num_queues = qquanta->queue_select.num_queues; + + if (check_add_overflow(start_qid, num_queues, &end_qid)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto err; + } + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto err; @@ -1918,8 +1947,6 @@ static int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg) goto err; } - end_qid = qquanta->queue_select.start_queue_id + - qquanta->queue_select.num_queues; if (end_qid > ICE_MAX_RSS_QS_PER_VF || end_qid > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) { dev_err(ice_pf_to_dev(vf->pf), "VF-%d trying to configure more than allocated number of queues: %d\n", @@ -1948,7 +1975,6 @@ static int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg) goto err; } - start_qid = qquanta->queue_select.start_queue_id; for (i = start_qid; i < end_qid; i++) vsi->tx_rings[i]->quanta_prof_id = quanta_prof_id; @@ -1975,6 +2001,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) struct ice_vsi *vsi; u8 act_prt, pri_prt; int i = -1, q_idx; + bool ena_ts; lag = pf->lag; mutex_lock(&pf->lag_mutex); @@ -2104,9 +2131,14 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) rxdid = ICE_RXDID_LEGACY_1; } + ena_ts = ((vf->driver_caps & + VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) && + (vf->driver_caps & VIRTCHNL_VF_CAP_PTP) && + (qpi->rxq.flags & VIRTCHNL_PTP_RX_TSTAMP)); + ice_write_qrxflxp_cntxt(&vsi->back->hw, - vsi->rxq_map[q_idx], - rxdid, 0x03, false); + vsi->rxq_map[q_idx], rxdid, + ICE_RXDID_PRIO, ena_ts); } } @@ -3031,8 +3063,8 @@ err: static int ice_vc_query_rxdid(struct ice_vf *vf) { enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; - struct virtchnl_supported_rxdids rxdid = {}; struct ice_pf *pf = vf->pf; + u64 rxdid; if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; @@ -3044,7 +3076,7 @@ static int ice_vc_query_rxdid(struct ice_vf *vf) goto err; } - rxdid.supported_rxdids = pf->supported_rxdids; + rxdid = pf->supported_rxdids; err: return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_SUPPORTED_RXDIDS, @@ -4092,6 +4124,59 @@ out: v_ret, NULL, 0); } +static int ice_vc_get_ptp_cap(struct ice_vf *vf, + const struct virtchnl_ptp_caps *msg) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_ERR_PARAM; + u32 caps = VIRTCHNL_1588_PTP_CAP_RX_TSTAMP | + VIRTCHNL_1588_PTP_CAP_READ_PHC; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + goto err; + + v_ret = VIRTCHNL_STATUS_SUCCESS; + + if (msg->caps & caps) + vf->ptp_caps = caps; + +err: + /* send the response back to the VF */ + return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_1588_PTP_GET_CAPS, v_ret, + (u8 *)&vf->ptp_caps, + sizeof(struct virtchnl_ptp_caps)); +} + +static int ice_vc_get_phc_time(struct ice_vf *vf) +{ + enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_ERR_PARAM; + struct virtchnl_phc_time *phc_time = NULL; + struct ice_pf *pf = vf->pf; + u32 len = 0; + int ret; + + if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + goto err; + + v_ret = VIRTCHNL_STATUS_SUCCESS; + + phc_time = kzalloc(sizeof(*phc_time), GFP_KERNEL); + if (!phc_time) { + v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + goto err; + } + + len = sizeof(*phc_time); + + phc_time->time = ice_ptp_read_src_clk_reg(pf, NULL); + +err: + /* send the response back to the VF */ + ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_1588_PTP_GET_TIME, v_ret, + (u8 *)phc_time, len); + kfree(phc_time); + return ret; +} + static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = { .get_ver_msg = ice_vc_get_ver_msg, .get_vf_res_msg = ice_vc_get_vf_res_msg, @@ -4128,6 +4213,8 @@ static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = { .get_qos_caps = ice_vc_get_qos_caps, .cfg_q_bw = ice_vc_cfg_q_bw, .cfg_q_quanta = ice_vc_cfg_q_quanta, + .get_ptp_cap = ice_vc_get_ptp_cap, + .get_phc_time = ice_vc_get_phc_time, /* If you add a new op here please make sure to add it to * ice_virtchnl_repr_ops as well. */ @@ -4264,6 +4351,8 @@ static const struct ice_virtchnl_ops ice_virtchnl_repr_ops = { .get_qos_caps = ice_vc_get_qos_caps, .cfg_q_bw = ice_vc_cfg_q_bw, .cfg_q_quanta = ice_vc_cfg_q_quanta, + .get_ptp_cap = ice_vc_get_ptp_cap, + .get_phc_time = ice_vc_get_phc_time, }; /** @@ -4501,6 +4590,12 @@ error_handler: case VIRTCHNL_OP_CONFIG_QUANTA: err = ops->cfg_q_quanta(vf, msg); break; + case VIRTCHNL_OP_1588_PTP_GET_CAPS: + err = ops->get_ptp_cap(vf, (const void *)msg); + break; + case VIRTCHNL_OP_1588_PTP_GET_TIME: + err = ops->get_phc_time(vf); + break; case VIRTCHNL_OP_UNKNOWN: default: dev_err(dev, "Unsupported opcode %d from VF %d\n", v_opcode, diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.h b/drivers/net/ethernet/intel/ice/ice_virtchnl.h index 0c629aef9baf..222990f229d5 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.h @@ -26,6 +26,9 @@ #define ICE_MAX_MACADDR_PER_VF 18 #define ICE_FLEX_DESC_RXDID_MAX_NUM 64 +/* Priority to be compared against previous priority from the pipe */ +#define ICE_RXDID_PRIO 0x03 + /* VFs only get a single VSI. For ice hardware, the VF does not need to know * its VSI index. However, the virtchnl interface requires a VSI number, * mainly due to legacy hardware. @@ -72,6 +75,9 @@ struct ice_virtchnl_ops { int (*cfg_q_tc_map)(struct ice_vf *vf, u8 *msg); int (*cfg_q_bw)(struct ice_vf *vf, u8 *msg); int (*cfg_q_quanta)(struct ice_vf *vf, u8 *msg); + int (*get_ptp_cap)(struct ice_vf *vf, + const struct virtchnl_ptp_caps *msg); + int (*get_phc_time)(struct ice_vf *vf); }; #ifdef CONFIG_PCI_IOV diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c index c105a82ee136..a3d1579a619a 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c @@ -84,6 +84,12 @@ static const u32 fdir_pf_allowlist_opcodes[] = { VIRTCHNL_OP_ADD_FDIR_FILTER, VIRTCHNL_OP_DEL_FDIR_FILTER, }; +/* VIRTCHNL_VF_CAP_PTP */ +static const u32 ptp_allowlist_opcodes[] = { + VIRTCHNL_OP_1588_PTP_GET_CAPS, + VIRTCHNL_OP_1588_PTP_GET_TIME, +}; + static const u32 tc_allowlist_opcodes[] = { VIRTCHNL_OP_GET_QOS_CAPS, VIRTCHNL_OP_CONFIG_QUEUE_BW, VIRTCHNL_OP_CONFIG_QUANTA, @@ -110,6 +116,7 @@ static const struct allowlist_opcode_info allowlist_opcodes[] = { ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_FDIR_PF, fdir_pf_allowlist_opcodes), ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_VLAN_V2, vlan_v2_allowlist_opcodes), ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_QOS, tc_allowlist_opcodes), + ALLOW_ITEM(VIRTCHNL_VF_CAP_PTP, ptp_allowlist_opcodes), }; /** diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c index 14e3f0f89c78..9be4bd717512 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c @@ -832,21 +832,27 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf, struct virtchnl_proto_hdrs *proto, struct virtchnl_fdir_fltr_conf *conf) { - u8 *pkt_buf, *msk_buf __free(kfree); + u8 *pkt_buf, *msk_buf __free(kfree) = NULL; struct ice_parser_result rslt; struct ice_pf *pf = vf->pf; + u16 pkt_len, udp_port = 0; struct ice_parser *psr; int status = -ENOMEM; struct ice_hw *hw; - u16 udp_port = 0; - pkt_buf = kzalloc(proto->raw.pkt_len, GFP_KERNEL); - msk_buf = kzalloc(proto->raw.pkt_len, GFP_KERNEL); + pkt_len = proto->raw.pkt_len; + + if (!pkt_len || pkt_len > VIRTCHNL_MAX_SIZE_RAW_PACKET) + return -EINVAL; + + pkt_buf = kzalloc(pkt_len, GFP_KERNEL); + msk_buf = kzalloc(pkt_len, GFP_KERNEL); + if (!pkt_buf || !msk_buf) goto err_mem_alloc; - memcpy(pkt_buf, proto->raw.spec, proto->raw.pkt_len); - memcpy(msk_buf, proto->raw.mask, proto->raw.pkt_len); + memcpy(pkt_buf, proto->raw.spec, pkt_len); + memcpy(msk_buf, proto->raw.mask, pkt_len); hw = &pf->hw; @@ -862,7 +868,7 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf, if (ice_get_open_tunnel_port(hw, &udp_port, TNL_VXLAN)) ice_parser_vxlan_tunnel_set(psr, udp_port, true); - status = ice_parser_run(psr, pkt_buf, proto->raw.pkt_len, &rslt); + status = ice_parser_run(psr, pkt_buf, pkt_len, &rslt); if (status) goto err_parser_destroy; @@ -876,7 +882,7 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf, } status = ice_parser_profile_init(&rslt, pkt_buf, msk_buf, - proto->raw.pkt_len, ICE_BLK_FD, + pkt_len, ICE_BLK_FD, conf->prof); if (status) goto err_parser_profile_init; @@ -885,7 +891,7 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf, ice_parser_profile_dump(hw, conf->prof); /* Store raw flow info into @conf */ - conf->pkt_len = proto->raw.pkt_len; + conf->pkt_len = pkt_len; conf->pkt_buf = pkt_buf; conf->parser_ena = true; diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 8975d2971bc3..a3a4eaa17739 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -2,6 +2,7 @@ /* Copyright (c) 2019, Intel Corporation. */ #include <linux/bpf_trace.h> +#include <linux/unroll.h> #include <net/xdp_sock_drv.h> #include <net/xdp.h> #include "ice.h" @@ -989,7 +990,8 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct ice_tx_desc *tx_desc; u32 i; - loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) { + unrolled_count(PKTS_PER_BATCH) + for (i = 0; i < PKTS_PER_BATCH; i++) { dma_addr_t dma; dma = xsk_buff_raw_get_dma(xsk_pool, descs[i].addr); diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h index 45adeb513253..8dc5d55e26c5 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.h +++ b/drivers/net/ethernet/intel/ice/ice_xsk.h @@ -7,14 +7,6 @@ #define PKTS_PER_BATCH 8 -#ifdef __clang__ -#define loop_unrolled_for _Pragma("clang loop unroll_count(8)") for -#elif __GNUC__ >= 8 -#define loop_unrolled_for _Pragma("GCC unroll 8") for -#else -#define loop_unrolled_for for -#endif - struct ice_vsi; #ifdef CONFIG_XDP_SOCKETS diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c index a3d6b8f198a8..aa755dedb41d 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_lib.c +++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c @@ -814,6 +814,7 @@ static int idpf_cfg_netdev(struct idpf_vport *vport) netdev->hw_features |= dflt_features | offloads; netdev->hw_enc_features |= dflt_features | offloads; idpf_set_ethtool_ops(netdev); + netif_set_affinity_auto(netdev); SET_NETDEV_DEV(netdev, &adapter->pdev->dev); /* carrier off on init to avoid Tx hangs */ @@ -927,15 +928,19 @@ static int idpf_stop(struct net_device *netdev) static void idpf_decfg_netdev(struct idpf_vport *vport) { struct idpf_adapter *adapter = vport->adapter; + u16 idx = vport->idx; kfree(vport->rx_ptype_lkup); vport->rx_ptype_lkup = NULL; - unregister_netdev(vport->netdev); - free_netdev(vport->netdev); + if (test_and_clear_bit(IDPF_VPORT_REG_NETDEV, + adapter->vport_config[idx]->flags)) { + unregister_netdev(vport->netdev); + free_netdev(vport->netdev); + } vport->netdev = NULL; - adapter->netdevs[vport->idx] = NULL; + adapter->netdevs[idx] = NULL; } /** @@ -1536,13 +1541,22 @@ void idpf_init_task(struct work_struct *work) } for (index = 0; index < adapter->max_vports; index++) { - if (adapter->netdevs[index] && - !test_bit(IDPF_VPORT_REG_NETDEV, - adapter->vport_config[index]->flags)) { - register_netdev(adapter->netdevs[index]); - set_bit(IDPF_VPORT_REG_NETDEV, - adapter->vport_config[index]->flags); + struct net_device *netdev = adapter->netdevs[index]; + struct idpf_vport_config *vport_config; + + vport_config = adapter->vport_config[index]; + + if (!netdev || + test_bit(IDPF_VPORT_REG_NETDEV, vport_config->flags)) + continue; + + err = register_netdev(netdev); + if (err) { + dev_err(&pdev->dev, "failed to register netdev for vport %d: %pe\n", + index, ERR_PTR(err)); + continue; } + set_bit(IDPF_VPORT_REG_NETDEV, vport_config->flags); } /* As all the required vports are created, clear the reset flag diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c index dfd7cf1d9aa0..eae1b6f474e6 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c @@ -595,7 +595,7 @@ static bool idpf_rx_singleq_is_non_eop(const union virtchnl2_rx_desc *rx_desc) */ static void idpf_rx_singleq_csum(struct idpf_rx_queue *rxq, struct sk_buff *skb, - struct idpf_rx_csum_decoded csum_bits, + struct libeth_rx_csum csum_bits, struct libeth_rx_pt decoded) { bool ipv4, ipv6; @@ -661,10 +661,10 @@ checksum_fail: * * Return: parsed checksum status. **/ -static struct idpf_rx_csum_decoded +static struct libeth_rx_csum idpf_rx_singleq_base_csum(const union virtchnl2_rx_desc *rx_desc) { - struct idpf_rx_csum_decoded csum_bits = { }; + struct libeth_rx_csum csum_bits = { }; u32 rx_error, rx_status; u64 qword; @@ -696,10 +696,10 @@ idpf_rx_singleq_base_csum(const union virtchnl2_rx_desc *rx_desc) * * Return: parsed checksum status. **/ -static struct idpf_rx_csum_decoded +static struct libeth_rx_csum idpf_rx_singleq_flex_csum(const union virtchnl2_rx_desc *rx_desc) { - struct idpf_rx_csum_decoded csum_bits = { }; + struct libeth_rx_csum csum_bits = { }; u16 rx_status0, rx_status1; rx_status0 = le16_to_cpu(rx_desc->flex_nic_wb.status_error0); @@ -798,7 +798,7 @@ idpf_rx_singleq_process_skb_fields(struct idpf_rx_queue *rx_q, u16 ptype) { struct libeth_rx_pt decoded = rx_q->rx_ptype_lkup[ptype]; - struct idpf_rx_csum_decoded csum_bits; + struct libeth_rx_csum csum_bits; /* modifies the skb - consumes the enet header */ skb->protocol = eth_type_trans(skb, rx_q->netdev); @@ -891,6 +891,7 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_rx_queue *rx_q, * idpf_rx_singleq_extract_base_fields - Extract fields from the Rx descriptor * @rx_desc: the descriptor to process * @fields: storage for extracted values + * @ptype: pointer that will store packet type * * Decode the Rx descriptor and extract relevant information including the * size and Rx packet type. @@ -900,20 +901,21 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_rx_queue *rx_q, */ static void idpf_rx_singleq_extract_base_fields(const union virtchnl2_rx_desc *rx_desc, - struct idpf_rx_extracted *fields) + struct libeth_rqe_info *fields, u32 *ptype) { u64 qword; qword = le64_to_cpu(rx_desc->base_wb.qword1.status_error_ptype_len); - fields->size = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_LEN_PBUF_M, qword); - fields->rx_ptype = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_PTYPE_M, qword); + fields->len = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_LEN_PBUF_M, qword); + *ptype = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_PTYPE_M, qword); } /** * idpf_rx_singleq_extract_flex_fields - Extract fields from the Rx descriptor * @rx_desc: the descriptor to process * @fields: storage for extracted values + * @ptype: pointer that will store packet type * * Decode the Rx descriptor and extract relevant information including the * size and Rx packet type. @@ -923,12 +925,12 @@ idpf_rx_singleq_extract_base_fields(const union virtchnl2_rx_desc *rx_desc, */ static void idpf_rx_singleq_extract_flex_fields(const union virtchnl2_rx_desc *rx_desc, - struct idpf_rx_extracted *fields) + struct libeth_rqe_info *fields, u32 *ptype) { - fields->size = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PKT_LEN_M, - le16_to_cpu(rx_desc->flex_nic_wb.pkt_len)); - fields->rx_ptype = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PTYPE_M, - le16_to_cpu(rx_desc->flex_nic_wb.ptype_flex_flags0)); + fields->len = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PKT_LEN_M, + le16_to_cpu(rx_desc->flex_nic_wb.pkt_len)); + *ptype = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PTYPE_M, + le16_to_cpu(rx_desc->flex_nic_wb.ptype_flex_flags0)); } /** @@ -936,17 +938,18 @@ idpf_rx_singleq_extract_flex_fields(const union virtchnl2_rx_desc *rx_desc, * @rx_q: Rx descriptor queue * @rx_desc: the descriptor to process * @fields: storage for extracted values + * @ptype: pointer that will store packet type * */ static void idpf_rx_singleq_extract_fields(const struct idpf_rx_queue *rx_q, const union virtchnl2_rx_desc *rx_desc, - struct idpf_rx_extracted *fields) + struct libeth_rqe_info *fields, u32 *ptype) { if (rx_q->rxdids == VIRTCHNL2_RXDID_1_32B_BASE_M) - idpf_rx_singleq_extract_base_fields(rx_desc, fields); + idpf_rx_singleq_extract_base_fields(rx_desc, fields, ptype); else - idpf_rx_singleq_extract_flex_fields(rx_desc, fields); + idpf_rx_singleq_extract_flex_fields(rx_desc, fields, ptype); } /** @@ -966,9 +969,10 @@ static int idpf_rx_singleq_clean(struct idpf_rx_queue *rx_q, int budget) /* Process Rx packets bounded by budget */ while (likely(total_rx_pkts < (unsigned int)budget)) { - struct idpf_rx_extracted fields = { }; + struct libeth_rqe_info fields = { }; union virtchnl2_rx_desc *rx_desc; struct idpf_rx_buf *rx_buf; + u32 ptype; /* get the Rx desc from Rx queue based on 'next_to_clean' */ rx_desc = &rx_q->rx[ntc]; @@ -989,16 +993,16 @@ static int idpf_rx_singleq_clean(struct idpf_rx_queue *rx_q, int budget) */ dma_rmb(); - idpf_rx_singleq_extract_fields(rx_q, rx_desc, &fields); + idpf_rx_singleq_extract_fields(rx_q, rx_desc, &fields, &ptype); rx_buf = &rx_q->rx_buf[ntc]; - if (!libeth_rx_sync_for_cpu(rx_buf, fields.size)) + if (!libeth_rx_sync_for_cpu(rx_buf, fields.len)) goto skip_data; if (skb) - idpf_rx_add_frag(rx_buf, skb, fields.size); + idpf_rx_add_frag(rx_buf, skb, fields.len); else - skb = idpf_rx_build_skb(rx_buf, fields.size); + skb = idpf_rx_build_skb(rx_buf, fields.len); /* exit if we failed to retrieve a buffer */ if (!skb) @@ -1033,8 +1037,7 @@ skip_data: total_rx_bytes += skb->len; /* protocol */ - idpf_rx_singleq_process_skb_fields(rx_q, skb, - rx_desc, fields.rx_ptype); + idpf_rx_singleq_process_skb_fields(rx_q, skb, rx_desc, ptype); /* send completed skb up the stack */ napi_gro_receive(rx_q->pp->p.napi, skb); diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c index 977741c41498..bdf52cef3891 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c @@ -2895,7 +2895,7 @@ idpf_rx_hash(const struct idpf_rx_queue *rxq, struct sk_buff *skb, * skb->protocol must be set before this function is called */ static void idpf_rx_csum(struct idpf_rx_queue *rxq, struct sk_buff *skb, - struct idpf_rx_csum_decoded csum_bits, + struct libeth_rx_csum csum_bits, struct libeth_rx_pt decoded) { bool ipv4, ipv6; @@ -2923,7 +2923,7 @@ static void idpf_rx_csum(struct idpf_rx_queue *rxq, struct sk_buff *skb, if (unlikely(csum_bits.l4e)) goto checksum_fail; - if (csum_bits.raw_csum_inv || + if (!csum_bits.raw_csum_valid || decoded.inner_prot == LIBETH_RX_PT_INNER_SCTP) { skb->ip_summed = CHECKSUM_UNNECESSARY; return; @@ -2946,10 +2946,10 @@ checksum_fail: * * Return: parsed checksum status. **/ -static struct idpf_rx_csum_decoded +static struct libeth_rx_csum idpf_rx_splitq_extract_csum_bits(const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc) { - struct idpf_rx_csum_decoded csum = { }; + struct libeth_rx_csum csum = { }; u8 qword0, qword1; qword0 = rx_desc->status_err0_qw0; @@ -2965,9 +2965,9 @@ idpf_rx_splitq_extract_csum_bits(const struct virtchnl2_rx_flex_desc_adv_nic_3 * qword1); csum.ipv6exadd = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_IPV6EXADD_M, qword0); - csum.raw_csum_inv = - le16_get_bits(rx_desc->ptype_err_fflags0, - VIRTCHNL2_RX_FLEX_DESC_ADV_RAW_CSUM_INV_M); + csum.raw_csum_valid = + !le16_get_bits(rx_desc->ptype_err_fflags0, + VIRTCHNL2_RX_FLEX_DESC_ADV_RAW_CSUM_INV_M); csum.raw_csum = le16_to_cpu(rx_desc->misc.raw_cs); return csum; @@ -3059,7 +3059,7 @@ static int idpf_rx_process_skb_fields(struct idpf_rx_queue *rxq, struct sk_buff *skb, const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc) { - struct idpf_rx_csum_decoded csum_bits; + struct libeth_rx_csum csum_bits; struct libeth_rx_pt decoded; u16 rx_ptype; @@ -3552,8 +3552,6 @@ void idpf_vport_intr_rel(struct idpf_vport *vport) q_vector->tx = NULL; kfree(q_vector->rx); q_vector->rx = NULL; - - free_cpumask_var(q_vector->affinity_mask); } kfree(vport->q_vectors); @@ -3580,8 +3578,6 @@ static void idpf_vport_intr_rel_irq(struct idpf_vport *vport) vidx = vport->q_vector_idxs[vector]; irq_num = adapter->msix_entries[vidx].vector; - /* clear the affinity_mask in the IRQ descriptor */ - irq_set_affinity_hint(irq_num, NULL); kfree(free_irq(irq_num, q_vector)); } } @@ -3769,8 +3765,6 @@ static int idpf_vport_intr_req_irq(struct idpf_vport *vport) "Request_irq failed, error: %d\n", err); goto free_q_irqs; } - /* assign the mask for this irq */ - irq_set_affinity_hint(irq_num, q_vector->affinity_mask); } return 0; @@ -4182,7 +4176,8 @@ static int idpf_vport_intr_init_vec_idx(struct idpf_vport *vport) static void idpf_vport_intr_napi_add_all(struct idpf_vport *vport) { int (*napi_poll)(struct napi_struct *napi, int budget); - u16 v_idx; + u16 v_idx, qv_idx; + int irq_num; if (idpf_is_queue_model_split(vport->txq_model)) napi_poll = idpf_vport_splitq_napi_poll; @@ -4191,12 +4186,12 @@ static void idpf_vport_intr_napi_add_all(struct idpf_vport *vport) for (v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) { struct idpf_q_vector *q_vector = &vport->q_vectors[v_idx]; + qv_idx = vport->q_vector_idxs[v_idx]; + irq_num = vport->adapter->msix_entries[qv_idx].vector; - netif_napi_add(vport->netdev, &q_vector->napi, napi_poll); - - /* only set affinity_mask if the CPU is online */ - if (cpu_online(v_idx)) - cpumask_set_cpu(v_idx, q_vector->affinity_mask); + netif_napi_add_config(vport->netdev, &q_vector->napi, + napi_poll, v_idx); + netif_napi_set_irq(&q_vector->napi, irq_num); } } @@ -4240,9 +4235,6 @@ int idpf_vport_intr_alloc(struct idpf_vport *vport) q_vector->rx_intr_mode = IDPF_ITR_DYNAMIC; q_vector->rx_itr_idx = VIRTCHNL2_ITR_IDX_0; - if (!zalloc_cpumask_var(&q_vector->affinity_mask, GFP_KERNEL)) - goto error; - q_vector->tx = kcalloc(txqs_per_vector, sizeof(*q_vector->tx), GFP_KERNEL); if (!q_vector->tx) diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h index 0f71a6f5557b..b029f566e57c 100644 --- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h +++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h @@ -213,25 +213,6 @@ enum idpf_tx_ctx_desc_eipt_offload { IDPF_TX_CTX_EXT_IP_IPV4 = 0x3 }; -/* Checksum offload bits decoded from the receive descriptor. */ -struct idpf_rx_csum_decoded { - u32 l3l4p : 1; - u32 ipe : 1; - u32 eipe : 1; - u32 eudpe : 1; - u32 ipv6exadd : 1; - u32 l4e : 1; - u32 pprs : 1; - u32 nat : 1; - u32 raw_csum_inv : 1; - u32 raw_csum : 16; -}; - -struct idpf_rx_extracted { - unsigned int size; - u16 rx_ptype; -}; - #define IDPF_TX_COMPLQ_CLEAN_BUDGET 256 #define IDPF_TX_MIN_PKT_LEN 17 #define IDPF_TX_DESCS_FOR_SKB_DATA_PTR 1 @@ -401,7 +382,6 @@ struct idpf_intr_reg { * @rx_intr_mode: Dynamic ITR or not * @rx_itr_idx: RX ITR index * @v_idx: Vector index - * @affinity_mask: CPU affinity mask */ struct idpf_q_vector { __cacheline_group_begin_aligned(read_mostly); @@ -438,13 +418,12 @@ struct idpf_q_vector { __cacheline_group_begin_aligned(cold); u16 v_idx; - cpumask_var_t affinity_mask; __cacheline_group_end_aligned(cold); }; libeth_cacheline_set_assert(struct idpf_q_vector, 120, 24 + sizeof(struct napi_struct) + 2 * sizeof(struct dim), - 8 + sizeof(cpumask_var_t)); + 8); struct idpf_rx_queue_stats { u64_stats_t packets; @@ -940,7 +919,7 @@ static inline int idpf_q_vector_to_mem(const struct idpf_q_vector *q_vector) if (!q_vector) return NUMA_NO_NODE; - cpu = cpumask_first(q_vector->affinity_mask); + cpu = cpumask_first(&q_vector->napi.config->affinity_mask); return cpu < nr_cpu_ids ? cpu_to_mem(cpu) : NUMA_NO_NODE; } diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index f94570556120..f323e1c1989f 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -509,6 +509,12 @@ static int igb_ptp_feature_enable_82580(struct ptp_clock_info *ptp, PTP_STRICT_FLAGS)) return -EOPNOTSUPP; + /* Both the rising and falling edge are timestamped */ + if (rq->extts.flags & PTP_STRICT_FLAGS && + (rq->extts.flags & PTP_ENABLE_FEATURE) && + (rq->extts.flags & PTP_EXTTS_EDGES) != PTP_EXTTS_EDGES) + return -EOPNOTSUPP; + if (on) { pin = ptp_find_pin(igb->ptp_clock, PTP_PF_EXTTS, rq->extts.index); diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index b8111ad9a9a8..cd1d7b6c1782 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -579,6 +579,7 @@ struct igc_metadata_request { struct xsk_tx_metadata *meta; struct igc_ring *tx_ring; u32 cmd_type; + u16 used_desc; }; struct igc_q_vector { diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 84307bb7313e..491d942cefca 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -1092,7 +1092,8 @@ static int igc_init_empty_frame(struct igc_ring *ring, dma = dma_map_single(ring->dev, skb->data, size, DMA_TO_DEVICE); if (dma_mapping_error(ring->dev, dma)) { - netdev_err_once(ring->netdev, "Failed to map DMA for TX\n"); + net_err_ratelimited("%s: DMA mapping error for empty frame\n", + netdev_name(ring->netdev)); return -ENOMEM; } @@ -1108,20 +1109,12 @@ static int igc_init_empty_frame(struct igc_ring *ring, return 0; } -static int igc_init_tx_empty_descriptor(struct igc_ring *ring, - struct sk_buff *skb, - struct igc_tx_buffer *first) +static void igc_init_tx_empty_descriptor(struct igc_ring *ring, + struct sk_buff *skb, + struct igc_tx_buffer *first) { union igc_adv_tx_desc *desc; u32 cmd_type, olinfo_status; - int err; - - if (!igc_desc_unused(ring)) - return -EBUSY; - - err = igc_init_empty_frame(ring, first, skb); - if (err) - return err; cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT | IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD | @@ -1140,8 +1133,6 @@ static int igc_init_tx_empty_descriptor(struct igc_ring *ring, ring->next_to_use++; if (ring->next_to_use == ring->count) ring->next_to_use = 0; - - return 0; } #define IGC_EMPTY_FRAME_SIZE 60 @@ -1567,6 +1558,40 @@ static bool igc_request_tx_tstamp(struct igc_adapter *adapter, struct sk_buff *s return false; } +static int igc_insert_empty_frame(struct igc_ring *tx_ring) +{ + struct igc_tx_buffer *empty_info; + struct sk_buff *empty_skb; + void *data; + int ret; + + empty_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + empty_skb = alloc_skb(IGC_EMPTY_FRAME_SIZE, GFP_ATOMIC); + if (unlikely(!empty_skb)) { + net_err_ratelimited("%s: skb alloc error for empty frame\n", + netdev_name(tx_ring->netdev)); + return -ENOMEM; + } + + data = skb_put(empty_skb, IGC_EMPTY_FRAME_SIZE); + memset(data, 0, IGC_EMPTY_FRAME_SIZE); + + /* Prepare DMA mapping and Tx buffer information */ + ret = igc_init_empty_frame(tx_ring, empty_info, empty_skb); + if (unlikely(ret)) { + dev_kfree_skb_any(empty_skb); + return ret; + } + + /* Prepare advanced context descriptor for empty packet */ + igc_tx_ctxtdesc(tx_ring, 0, false, 0, 0, 0); + + /* Prepare advanced data descriptor for empty packet */ + igc_init_tx_empty_descriptor(tx_ring, empty_skb, empty_info); + + return 0; +} + static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, struct igc_ring *tx_ring) { @@ -1586,6 +1611,7 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, * + 1 desc for skb_headlen/IGC_MAX_DATA_PER_TXD, * + 2 desc gap to keep tail from touching head, * + 1 desc for context descriptor, + * + 2 desc for inserting an empty packet for launch time, * otherwise try next time */ for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) @@ -1605,24 +1631,16 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, launch_time = igc_tx_launchtime(tx_ring, txtime, &first_flag, &insert_empty); if (insert_empty) { - struct igc_tx_buffer *empty_info; - struct sk_buff *empty; - void *data; - - empty_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; - empty = alloc_skb(IGC_EMPTY_FRAME_SIZE, GFP_ATOMIC); - if (!empty) - goto done; - - data = skb_put(empty, IGC_EMPTY_FRAME_SIZE); - memset(data, 0, IGC_EMPTY_FRAME_SIZE); - - igc_tx_ctxtdesc(tx_ring, 0, false, 0, 0, 0); - - if (igc_init_tx_empty_descriptor(tx_ring, - empty, - empty_info) < 0) - dev_kfree_skb_any(empty); + /* Reset the launch time if the required empty frame fails to + * be inserted. However, this packet is not dropped, so it + * "dirties" the current Qbv cycle. This ensures that the + * upcoming packet, which is scheduled in the next Qbv cycle, + * does not require an empty frame. This way, the launch time + * continues to function correctly despite the current failure + * to insert the empty frame. + */ + if (igc_insert_empty_frame(tx_ring)) + launch_time = 0; } done: @@ -1650,7 +1668,8 @@ done: if (igc_request_tx_tstamp(adapter, skb, &tstamp_flags)) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; tx_flags |= IGC_TX_FLAGS_TSTAMP | tstamp_flags; - if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_USE_CYCLES) + if (skb->sk && + READ_ONCE(skb->sk->sk_tsflags) & SOF_TIMESTAMPING_BIND_PHC) tx_flags |= IGC_TX_FLAGS_TSTAMP_TIMER_1; } else { adapter->tx_hwtstamp_skipped++; @@ -2953,9 +2972,48 @@ static u64 igc_xsk_fill_timestamp(void *_priv) return *(u64 *)_priv; } +static void igc_xsk_request_launch_time(u64 launch_time, void *_priv) +{ + struct igc_metadata_request *meta_req = _priv; + struct igc_ring *tx_ring = meta_req->tx_ring; + __le32 launch_time_offset; + bool insert_empty = false; + bool first_flag = false; + u16 used_desc = 0; + + if (!tx_ring->launchtime_enable) + return; + + launch_time_offset = igc_tx_launchtime(tx_ring, + ns_to_ktime(launch_time), + &first_flag, &insert_empty); + if (insert_empty) { + /* Disregard the launch time request if the required empty frame + * fails to be inserted. + */ + if (igc_insert_empty_frame(tx_ring)) + return; + + meta_req->tx_buffer = + &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + /* Inserting an empty packet requires two descriptors: + * one data descriptor and one context descriptor. + */ + used_desc += 2; + } + + /* Use one context descriptor to specify launch time and first flag. */ + igc_tx_ctxtdesc(tx_ring, launch_time_offset, first_flag, 0, 0, 0); + used_desc += 1; + + /* Update the number of used descriptors in this request */ + meta_req->used_desc += used_desc; +} + const struct xsk_tx_metadata_ops igc_xsk_tx_metadata_ops = { .tmo_request_timestamp = igc_xsk_request_timestamp, .tmo_fill_timestamp = igc_xsk_fill_timestamp, + .tmo_request_launch_time = igc_xsk_request_launch_time, }; static void igc_xdp_xmit_zc(struct igc_ring *ring) @@ -2978,7 +3036,13 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) ntu = ring->next_to_use; budget = igc_desc_unused(ring); - while (xsk_tx_peek_desc(pool, &xdp_desc) && budget--) { + /* Packets with launch time require one data descriptor and one context + * descriptor. When the launch time falls into the next Qbv cycle, we + * may need to insert an empty packet, which requires two more + * descriptors. Therefore, to be safe, we always ensure we have at least + * 4 descriptors available. + */ + while (xsk_tx_peek_desc(pool, &xdp_desc) && budget >= 4) { struct igc_metadata_request meta_req; struct xsk_tx_metadata *meta = NULL; struct igc_tx_buffer *bi; @@ -2999,9 +3063,19 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) meta_req.tx_ring = ring; meta_req.tx_buffer = bi; meta_req.meta = meta; + meta_req.used_desc = 0; xsk_tx_metadata_request(meta, &igc_xsk_tx_metadata_ops, &meta_req); + /* xsk_tx_metadata_request() may have updated next_to_use */ + ntu = ring->next_to_use; + + /* xsk_tx_metadata_request() may have updated Tx buffer info */ + bi = meta_req.tx_buffer; + + /* xsk_tx_metadata_request() may use a few descriptors */ + budget -= meta_req.used_desc; + tx_desc = IGC_TX_DESC(ring, ntu); tx_desc->read.cmd_type_len = cpu_to_le32(meta_req.cmd_type); tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); @@ -3019,9 +3093,11 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) ntu++; if (ntu == ring->count) ntu = 0; + + ring->next_to_use = ntu; + budget--; } - ring->next_to_use = ntu; if (tx_desc) { igc_flush_tx_descriptors(ring); xsk_tx_release(pool); @@ -7090,8 +7166,8 @@ static int igc_probe(struct pci_dev *pdev, INIT_WORK(&adapter->reset_task, igc_reset_task); INIT_WORK(&adapter->watchdog_task, igc_watchdog_task); - hrtimer_init(&adapter->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - adapter->hrtimer.function = &igc_qbv_scheduling_timer; + hrtimer_setup(&adapter->hrtimer, &igc_qbv_scheduling_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL); /* Initialize link properties that are user-changeable */ adapter->fc_autoneg = true; diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.c b/drivers/net/ethernet/intel/igc/igc_xdp.c index 13bbd3346e01..c538e6b18aad 100644 --- a/drivers/net/ethernet/intel/igc/igc_xdp.c +++ b/drivers/net/ethernet/intel/igc/igc_xdp.c @@ -14,6 +14,7 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, bool if_running = netif_running(dev); struct bpf_prog *old_prog; bool need_update; + unsigned int i; if (dev->mtu > ETH_DATA_LEN) { /* For now, the driver doesn't support XDP functionality with @@ -24,8 +25,13 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, } need_update = !!adapter->xdp_prog != !!prog; - if (if_running && need_update) - igc_close(dev); + if (if_running && need_update) { + for (i = 0; i < adapter->num_rx_queues; i++) { + igc_disable_rx_ring(adapter->rx_ring[i]); + igc_disable_tx_ring(adapter->tx_ring[i]); + napi_disable(&adapter->rx_ring[i]->q_vector->napi); + } + } old_prog = xchg(&adapter->xdp_prog, prog); if (old_prog) @@ -36,8 +42,13 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, else xdp_features_clear_redirect_target(dev); - if (if_running && need_update) - igc_open(dev); + if (if_running && need_update) { + for (i = 0; i < adapter->num_rx_queues; i++) { + napi_enable(&adapter->rx_ring[i]->q_vector->napi); + igc_enable_tx_ring(adapter->tx_ring[i]); + igc_enable_rx_ring(adapter->rx_ring[i]); + } + } return 0; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index da91c582d439..f03925c1f521 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -3185,6 +3185,7 @@ static int ixgbe_get_ts_info(struct net_device *dev, case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: info->rx_filters |= BIT(HWTSTAMP_FILTER_ALL); break; case ixgbe_mac_X540: diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c index 866024f2b9ee..07ea1954a276 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c @@ -817,30 +817,9 @@ static void ixgbe_ipsec_del_sa(struct xfrm_state *xs) } } -/** - * ixgbe_ipsec_offload_ok - can this packet use the xfrm hw offload - * @skb: current data packet - * @xs: pointer to transformer state struct - **/ -static bool ixgbe_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) -{ - if (xs->props.family == AF_INET) { - /* Offload with IPv4 options is not supported yet */ - if (ip_hdr(skb)->ihl != 5) - return false; - } else { - /* Offload with IPv6 extension headers is not support yet */ - if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr)) - return false; - } - - return true; -} - static const struct xfrmdev_ops ixgbe_xfrmdev_ops = { .xdo_dev_state_add = ixgbe_ipsec_add_sa, .xdo_dev_state_delete = ixgbe_ipsec_del_sa, - .xdo_dev_offload_ok = ixgbe_ipsec_offload_ok, }; /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 467f81239e12..481f917f7ed2 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -3185,6 +3185,10 @@ static void ixgbe_handle_fw_event(struct ixgbe_adapter *adapter) case ixgbe_aci_opc_get_link_status: ixgbe_handle_link_status_event(adapter, &event); break; + case ixgbe_aci_opc_temp_tca_event: + e_crit(drv, "%s\n", ixgbe_overheat_msg); + ixgbe_down(adapter); + break; default: e_warn(hw, "unknown FW async event captured\n"); break; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index 9339edbd9082..eef25e11d938 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -140,6 +140,7 @@ * proper mult and shift to convert the cycles into nanoseconds of time. */ #define IXGBE_X550_BASE_PERIOD 0xC80000000ULL +#define IXGBE_E610_BASE_PERIOD 0x333333333ULL #define INCVALUE_MASK 0x7FFFFFFF #define ISGN 0x80000000 @@ -415,6 +416,7 @@ static void ixgbe_ptp_convert_to_hwtstamp(struct ixgbe_adapter *adapter, case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: /* Upper 32 bits represent billions of cycles, lower 32 bits * represent cycles. However, we use timespec64_to_ns for the * correct math even though the units haven't been corrected @@ -492,11 +494,13 @@ static int ixgbe_ptp_adjfine_X550(struct ptp_clock_info *ptp, long scaled_ppm) struct ixgbe_adapter *adapter = container_of(ptp, struct ixgbe_adapter, ptp_caps); struct ixgbe_hw *hw = &adapter->hw; + u64 rate, base; bool neg_adj; - u64 rate; u32 inca; - neg_adj = diff_by_scaled_ppm(IXGBE_X550_BASE_PERIOD, scaled_ppm, &rate); + base = hw->mac.type == ixgbe_mac_e610 ? IXGBE_E610_BASE_PERIOD : + IXGBE_X550_BASE_PERIOD; + neg_adj = diff_by_scaled_ppm(base, scaled_ppm, &rate); /* warn if rate is too large */ if (rate >= INCVALUE_MASK) @@ -559,6 +563,7 @@ static int ixgbe_ptp_gettimex(struct ptp_clock_info *ptp, case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: /* Upper 32 bits represent billions of cycles, lower 32 bits * represent cycles. However, we use timespec64_to_ns for the * correct math even though the units haven't been corrected @@ -1067,6 +1072,7 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: /* enable timestamping all packets only if at least some * packets were requested. Otherwise, play nice and disable * timestamping @@ -1233,6 +1239,7 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter) fallthrough; case ixgbe_mac_x550em_a: case ixgbe_mac_X550: + case ixgbe_mac_e610: cc.read = ixgbe_ptp_read_X550; break; case ixgbe_mac_X540: @@ -1280,6 +1287,7 @@ static void ixgbe_ptp_init_systime(struct ixgbe_adapter *adapter) case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: case ixgbe_mac_X550: + case ixgbe_mac_e610: tsauxc = IXGBE_READ_REG(hw, IXGBE_TSAUXC); /* Reset SYSTIME registers to 0 */ @@ -1407,6 +1415,7 @@ static long ixgbe_ptp_create_clock(struct ixgbe_adapter *adapter) case ixgbe_mac_X550: case ixgbe_mac_X550EM_x: case ixgbe_mac_x550em_a: + case ixgbe_mac_e610: snprintf(adapter->ptp_caps.name, 16, "%s", netdev->name); adapter->ptp_caps.owner = THIS_MODULE; adapter->ptp_caps.max_adj = 30000000; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h index 8d06ade3c7cd..617e07878e4f 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h @@ -171,6 +171,9 @@ enum ixgbe_aci_opc { ixgbe_aci_opc_done_alt_write = 0x0904, ixgbe_aci_opc_clear_port_alt_write = 0x0906, + /* TCA Events */ + ixgbe_aci_opc_temp_tca_event = 0x0C94, + /* debug commands */ ixgbe_aci_opc_debug_dump_internals = 0xFF08, diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.c b/drivers/net/ethernet/intel/ixgbevf/ipsec.c index f804b35d79c7..8ba037e3d9c2 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ipsec.c +++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.c @@ -428,30 +428,9 @@ static void ixgbevf_ipsec_del_sa(struct xfrm_state *xs) } } -/** - * ixgbevf_ipsec_offload_ok - can this packet use the xfrm hw offload - * @skb: current data packet - * @xs: pointer to transformer state struct - **/ -static bool ixgbevf_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) -{ - if (xs->props.family == AF_INET) { - /* Offload with IPv4 options is not supported yet */ - if (ip_hdr(skb)->ihl != 5) - return false; - } else { - /* Offload with IPv6 extension headers is not support yet */ - if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr)) - return false; - } - - return true; -} - static const struct xfrmdev_ops ixgbevf_xfrmdev_ops = { .xdo_dev_state_add = ixgbevf_ipsec_add_sa, .xdo_dev_state_delete = ixgbevf_ipsec_del_sa, - .xdo_dev_offload_ok = ixgbevf_ipsec_offload_ok, }; /** |