diff options
Diffstat (limited to 'drivers/net/ethernet/intel/iavf/iavf_main.c')
| -rw-r--r-- | drivers/net/ethernet/intel/iavf/iavf_main.c | 4213 |
1 files changed, 2975 insertions, 1238 deletions
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 9f2b7b7adf6b..c2fbe443ef85 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1,9 +1,12 @@ // SPDX-License-Identifier: GPL-2.0 /* 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" -#include "iavf_client.h" /* All iavf tracepoints are defined by the include below, which must * be included exactly once across the whole kernel with * CREATE_TRACE_POINTS defined @@ -14,21 +17,13 @@ static int iavf_setup_all_tx_resources(struct iavf_adapter *adapter); static int iavf_setup_all_rx_resources(struct iavf_adapter *adapter); static int iavf_close(struct net_device *netdev); +static void iavf_init_get_resources(struct iavf_adapter *adapter); +static int iavf_check_reset_complete(struct iavf_hw *hw); char iavf_driver_name[] = "iavf"; static const char iavf_driver_string[] = "Intel(R) Ethernet Adaptive Virtual Function Network Driver"; -#define DRV_KERN "-k" - -#define DRV_VERSION_MAJOR 3 -#define DRV_VERSION_MINOR 2 -#define DRV_VERSION_BUILD 3 -#define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ - __stringify(DRV_VERSION_MINOR) "." \ - __stringify(DRV_VERSION_BUILD) \ - DRV_KERN -const char iavf_driver_version[] = DRV_VERSION; static const char iavf_copyright[] = "Copyright (c) 2013 - 2018 Intel Corporation."; @@ -52,12 +47,168 @@ static const struct pci_device_id iavf_pci_tbl[] = { MODULE_DEVICE_TABLE(pci, iavf_pci_tbl); MODULE_ALIAS("i40evf"); -MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION("Intel(R) Ethernet Adaptive Virtual Function Network Driver"); +MODULE_IMPORT_NS("LIBETH"); +MODULE_IMPORT_NS("LIBIE"); +MODULE_IMPORT_NS("LIBIE_ADMINQ"); MODULE_LICENSE("GPL v2"); -MODULE_VERSION(DRV_VERSION); -static struct workqueue_struct *iavf_wq; +static const struct net_device_ops iavf_netdev_ops; + +int iavf_status_to_errno(enum iavf_status status) +{ + switch (status) { + case IAVF_SUCCESS: + return 0; + case IAVF_ERR_PARAM: + case IAVF_ERR_MAC_TYPE: + case IAVF_ERR_INVALID_MAC_ADDR: + case IAVF_ERR_INVALID_LINK_SETTINGS: + case IAVF_ERR_INVALID_PD_ID: + case IAVF_ERR_INVALID_QP_ID: + case IAVF_ERR_INVALID_CQ_ID: + case IAVF_ERR_INVALID_CEQ_ID: + case IAVF_ERR_INVALID_AEQ_ID: + case IAVF_ERR_INVALID_SIZE: + case IAVF_ERR_INVALID_ARP_INDEX: + case IAVF_ERR_INVALID_FPM_FUNC_ID: + case IAVF_ERR_QP_INVALID_MSG_SIZE: + case IAVF_ERR_INVALID_FRAG_COUNT: + case IAVF_ERR_INVALID_ALIGNMENT: + case IAVF_ERR_INVALID_PUSH_PAGE_INDEX: + case IAVF_ERR_INVALID_IMM_DATA_SIZE: + case IAVF_ERR_INVALID_VF_ID: + case IAVF_ERR_INVALID_HMCFN_ID: + case IAVF_ERR_INVALID_PBLE_INDEX: + case IAVF_ERR_INVALID_SD_INDEX: + case IAVF_ERR_INVALID_PAGE_DESC_INDEX: + case IAVF_ERR_INVALID_SD_TYPE: + case IAVF_ERR_INVALID_HMC_OBJ_INDEX: + case IAVF_ERR_INVALID_HMC_OBJ_COUNT: + case IAVF_ERR_INVALID_SRQ_ARM_LIMIT: + return -EINVAL; + case IAVF_ERR_NVM: + case IAVF_ERR_NVM_CHECKSUM: + case IAVF_ERR_PHY: + case IAVF_ERR_CONFIG: + case IAVF_ERR_UNKNOWN_PHY: + case IAVF_ERR_LINK_SETUP: + case IAVF_ERR_ADAPTER_STOPPED: + case IAVF_ERR_PRIMARY_REQUESTS_PENDING: + case IAVF_ERR_AUTONEG_NOT_COMPLETE: + case IAVF_ERR_RESET_FAILED: + case IAVF_ERR_BAD_PTR: + case IAVF_ERR_SWFW_SYNC: + case IAVF_ERR_QP_TOOMANY_WRS_POSTED: + case IAVF_ERR_QUEUE_EMPTY: + case IAVF_ERR_FLUSHED_QUEUE: + case IAVF_ERR_OPCODE_MISMATCH: + case IAVF_ERR_CQP_COMPL_ERROR: + case IAVF_ERR_BACKING_PAGE_ERROR: + case IAVF_ERR_NO_PBLCHUNKS_AVAILABLE: + case IAVF_ERR_MEMCPY_FAILED: + case IAVF_ERR_SRQ_ENABLED: + case IAVF_ERR_ADMIN_QUEUE_ERROR: + case IAVF_ERR_ADMIN_QUEUE_FULL: + case IAVF_ERR_BAD_RDMA_CQE: + case IAVF_ERR_NVM_BLANK_MODE: + case IAVF_ERR_PE_DOORBELL_NOT_ENABLED: + case IAVF_ERR_DIAG_TEST_FAILED: + case IAVF_ERR_FIRMWARE_API_VERSION: + case IAVF_ERR_ADMIN_QUEUE_CRITICAL_ERROR: + return -EIO; + case IAVF_ERR_DEVICE_NOT_SUPPORTED: + return -ENODEV; + case IAVF_ERR_NO_AVAILABLE_VSI: + case IAVF_ERR_RING_FULL: + return -ENOSPC; + case IAVF_ERR_NO_MEMORY: + return -ENOMEM; + case IAVF_ERR_TIMEOUT: + case IAVF_ERR_ADMIN_QUEUE_TIMEOUT: + return -ETIMEDOUT; + case IAVF_ERR_NOT_IMPLEMENTED: + case IAVF_NOT_SUPPORTED: + return -EOPNOTSUPP; + case IAVF_ERR_ADMIN_QUEUE_NO_WORK: + return -EALREADY; + case IAVF_ERR_NOT_READY: + return -EBUSY; + case IAVF_ERR_BUF_TOO_SHORT: + return -EMSGSIZE; + } + + return -EIO; +} + +int virtchnl_status_to_errno(enum virtchnl_status_code v_status) +{ + switch (v_status) { + case VIRTCHNL_STATUS_SUCCESS: + return 0; + case VIRTCHNL_STATUS_ERR_PARAM: + case VIRTCHNL_STATUS_ERR_INVALID_VF_ID: + return -EINVAL; + case VIRTCHNL_STATUS_ERR_NO_MEMORY: + return -ENOMEM; + case VIRTCHNL_STATUS_ERR_OPCODE_MISMATCH: + case VIRTCHNL_STATUS_ERR_CQP_COMPL_ERROR: + case VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR: + return -EIO; + case VIRTCHNL_STATUS_ERR_NOT_SUPPORTED: + return -EOPNOTSUPP; + } + + return -EIO; +} + +/** + * iavf_pdev_to_adapter - go from pci_dev to adapter + * @pdev: pci_dev pointer + */ +static struct iavf_adapter *iavf_pdev_to_adapter(struct pci_dev *pdev) +{ + return netdev_priv(pci_get_drvdata(pdev)); +} + +/** + * iavf_is_reset_in_progress - Check if a reset is in progress + * @adapter: board private structure + */ +static bool iavf_is_reset_in_progress(struct iavf_adapter *adapter) +{ + if (adapter->state == __IAVF_RESETTING || + adapter->flags & (IAVF_FLAG_RESET_PENDING | + IAVF_FLAG_RESET_NEEDED)) + return true; + + return false; +} + +/** + * iavf_wait_for_reset - Wait for reset to finish. + * @adapter: board private structure + * + * Returns 0 if reset finished successfully, negative on timeout or interrupt. + */ +int iavf_wait_for_reset(struct iavf_adapter *adapter) +{ + int ret = wait_event_interruptible_timeout(adapter->reset_waitqueue, + !iavf_is_reset_in_progress(adapter), + msecs_to_jiffies(5000)); + + /* If ret < 0 then it means wait was interrupted. + * If ret == 0 then it means we got a timeout while waiting + * for reset to finish. + * If ret > 0 it means reset has finished. + */ + if (ret > 0) + return 0; + else if (ret < 0) + return -EINTR; + else + return -EBUSY; +} /** * iavf_allocate_dma_mem_d - OS specific memory alloc for shared code @@ -66,14 +217,14 @@ static struct workqueue_struct *iavf_wq; * @size: size of memory requested * @alignment: what to align the allocation to **/ -iavf_status iavf_allocate_dma_mem_d(struct iavf_hw *hw, - struct iavf_dma_mem *mem, - u64 size, u32 alignment) +enum iavf_status iavf_allocate_dma_mem_d(struct iavf_hw *hw, + struct iavf_dma_mem *mem, + u64 size, u32 alignment) { struct iavf_adapter *adapter = (struct iavf_adapter *)hw->back; if (!mem) - return I40E_ERR_PARAM; + return IAVF_ERR_PARAM; mem->size = ALIGN(size, alignment); mem->va = dma_alloc_coherent(&adapter->pdev->dev, mem->size, @@ -81,36 +232,36 @@ iavf_status iavf_allocate_dma_mem_d(struct iavf_hw *hw, if (mem->va) return 0; else - return I40E_ERR_NO_MEMORY; + return IAVF_ERR_NO_MEMORY; } /** - * iavf_free_dma_mem_d - OS specific memory free for shared code + * iavf_free_dma_mem - wrapper for DMA memory freeing * @hw: pointer to the HW structure * @mem: ptr to mem struct to free **/ -iavf_status iavf_free_dma_mem_d(struct iavf_hw *hw, struct iavf_dma_mem *mem) +enum iavf_status iavf_free_dma_mem(struct iavf_hw *hw, struct iavf_dma_mem *mem) { struct iavf_adapter *adapter = (struct iavf_adapter *)hw->back; if (!mem || !mem->va) - return I40E_ERR_PARAM; + return IAVF_ERR_PARAM; dma_free_coherent(&adapter->pdev->dev, mem->size, mem->va, (dma_addr_t)mem->pa); return 0; } /** - * iavf_allocate_virt_mem_d - OS specific memory alloc for shared code + * iavf_allocate_virt_mem - virt memory alloc wrapper * @hw: pointer to the HW structure * @mem: ptr to mem struct to fill out * @size: size of memory requested **/ -iavf_status iavf_allocate_virt_mem_d(struct iavf_hw *hw, - struct iavf_virt_mem *mem, u32 size) +enum iavf_status iavf_allocate_virt_mem(struct iavf_hw *hw, + struct iavf_virt_mem *mem, u32 size) { if (!mem) - return I40E_ERR_PARAM; + return IAVF_ERR_PARAM; mem->size = size; mem->va = kzalloc(size, GFP_KERNEL); @@ -118,70 +269,56 @@ iavf_status iavf_allocate_virt_mem_d(struct iavf_hw *hw, if (mem->va) return 0; else - return I40E_ERR_NO_MEMORY; + return IAVF_ERR_NO_MEMORY; } /** - * iavf_free_virt_mem_d - OS specific memory free for shared code + * iavf_free_virt_mem - virt memory free wrapper * @hw: pointer to the HW structure * @mem: ptr to mem struct to free **/ -iavf_status iavf_free_virt_mem_d(struct iavf_hw *hw, struct iavf_virt_mem *mem) +void iavf_free_virt_mem(struct iavf_hw *hw, struct iavf_virt_mem *mem) { - if (!mem) - return I40E_ERR_PARAM; - - /* it's ok to kfree a NULL pointer */ kfree(mem->va); - - return 0; } /** - * iavf_debug_d - OS dependent version of debug printing - * @hw: pointer to the HW structure - * @mask: debug level mask - * @fmt_str: printf-type format description + * iavf_schedule_reset - Set the flags and schedule a reset event + * @adapter: board private structure + * @flags: IAVF_FLAG_RESET_PENDING or IAVF_FLAG_RESET_NEEDED **/ -void iavf_debug_d(void *hw, u32 mask, char *fmt_str, ...) +void iavf_schedule_reset(struct iavf_adapter *adapter, u64 flags) { - char buf[512]; - va_list argptr; - - if (!(mask & ((struct iavf_hw *)hw)->debug_mask)) - return; - - va_start(argptr, fmt_str); - vsnprintf(buf, sizeof(buf), fmt_str, argptr); - va_end(argptr); - - /* the debug string is already formatted with a newline */ - pr_info("%s", buf); + if (!test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section) && + !(adapter->flags & + (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED))) { + adapter->flags |= flags; + queue_work(adapter->wq, &adapter->reset_task); + } } /** - * iavf_schedule_reset - Set the flags and schedule a reset event + * iavf_schedule_aq_request - Set the flags and schedule aq request * @adapter: board private structure + * @flags: requested aq flags **/ -void iavf_schedule_reset(struct iavf_adapter *adapter) +void iavf_schedule_aq_request(struct iavf_adapter *adapter, u64 flags) { - if (!(adapter->flags & - (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED))) { - adapter->flags |= IAVF_FLAG_RESET_NEEDED; - schedule_work(&adapter->reset_task); - } + adapter->aq_required |= flags; + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); } /** * iavf_tx_timeout - Respond to a Tx Hang * @netdev: network interface device structure + * @txqueue: queue number that is timing out **/ -static void iavf_tx_timeout(struct net_device *netdev) +static void iavf_tx_timeout(struct net_device *netdev, unsigned int txqueue) { struct iavf_adapter *adapter = netdev_priv(netdev); adapter->tx_timeout_count++; - iavf_schedule_reset(adapter); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); } /** @@ -237,21 +374,18 @@ static void iavf_irq_disable(struct iavf_adapter *adapter) } /** - * iavf_irq_enable_queues - Enable interrupt for specified queues + * iavf_irq_enable_queues - Enable interrupt for all queues * @adapter: board private structure - * @mask: bitmap of queues to enable **/ -void iavf_irq_enable_queues(struct iavf_adapter *adapter, u32 mask) +static void iavf_irq_enable_queues(struct iavf_adapter *adapter) { struct iavf_hw *hw = &adapter->hw; int i; for (i = 1; i < adapter->num_msix_vectors; i++) { - if (mask & BIT(i - 1)) { - wr32(hw, IAVF_VFINT_DYN_CTLN1(i - 1), - IAVF_VFINT_DYN_CTLN1_INTENA_MASK | - IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK); - } + wr32(hw, IAVF_VFINT_DYN_CTLN1(i - 1), + IAVF_VFINT_DYN_CTLN1_INTENA_MASK | + IAVF_VFINT_DYN_CTLN1_ITR_INDX_MASK); } } @@ -265,7 +399,7 @@ void iavf_irq_enable(struct iavf_adapter *adapter, bool flush) struct iavf_hw *hw = &adapter->hw; iavf_misc_irq_enable(adapter); - iavf_irq_enable_queues(adapter, ~0); + iavf_irq_enable_queues(adapter); if (flush) iavf_flush(hw); @@ -286,8 +420,9 @@ static irqreturn_t iavf_msix_aq(int irq, void *data) rd32(hw, IAVF_VFINT_ICR01); rd32(hw, IAVF_VFINT_ICR0_ENA1); - /* schedule work on the private workqueue */ - schedule_work(&adapter->adminq_task); + if (adapter->state != __IAVF_REMOVE) + /* schedule work on the private workqueue */ + queue_work(adapter->wq, &adapter->adminq_task); return IRQ_HANDLED; } @@ -331,7 +466,7 @@ iavf_map_vector_to_rxq(struct iavf_adapter *adapter, int v_idx, int r_idx) q_vector->rx.target_itr = ITR_TO_REG(rx_ring->itr_setting); q_vector->ring_mask |= BIT(r_idx); wr32(hw, IAVF_VFINT_ITRN1(IAVF_RX_ITR, q_vector->reg_idx), - q_vector->rx.current_itr); + q_vector->rx.current_itr >> 1); q_vector->rx.current_itr = q_vector->rx.target_itr; } @@ -357,7 +492,7 @@ iavf_map_vector_to_txq(struct iavf_adapter *adapter, int v_idx, int t_idx) q_vector->tx.target_itr = ITR_TO_REG(tx_ring->itr_setting); q_vector->num_ringpairs++; wr32(hw, IAVF_VFINT_ITRN1(IAVF_TX_ITR, q_vector->reg_idx), - q_vector->tx.target_itr); + q_vector->tx.target_itr >> 1); q_vector->tx.current_itr = q_vector->tx.target_itr; } @@ -394,33 +529,6 @@ static void iavf_map_rings_to_vectors(struct iavf_adapter *adapter) } /** - * iavf_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 iavf_irq_affinity_notify(struct irq_affinity_notify *notify, - const cpumask_t *mask) -{ - struct iavf_q_vector *q_vector = - container_of(notify, struct iavf_q_vector, affinity_notify); - - cpumask_copy(&q_vector->affinity_mask, mask); -} - -/** - * iavf_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 iavf_irq_affinity_release(struct kref *ref) {} - -/** * iavf_request_traffic_irqs - Initialize MSI-X interrupts * @adapter: board private structure * @basename: device basename @@ -434,7 +542,6 @@ iavf_request_traffic_irqs(struct iavf_adapter *adapter, char *basename) unsigned int vector, q_vectors; unsigned int rx_int_idx = 0, tx_int_idx = 0; int irq_num, err; - int cpu; iavf_irq_disable(adapter); /* Decrement for Other and TCP Timer vectors */ @@ -447,14 +554,14 @@ iavf_request_traffic_irqs(struct iavf_adapter *adapter, char *basename) if (q_vector->tx.ring && q_vector->rx.ring) { snprintf(q_vector->name, sizeof(q_vector->name), - "iavf-%s-TxRx-%d", basename, rx_int_idx++); + "iavf-%s-TxRx-%u", basename, rx_int_idx++); tx_int_idx++; } else if (q_vector->rx.ring) { snprintf(q_vector->name, sizeof(q_vector->name), - "iavf-%s-rx-%d", basename, rx_int_idx++); + "iavf-%s-rx-%u", basename, rx_int_idx++); } else if (q_vector->tx.ring) { snprintf(q_vector->name, sizeof(q_vector->name), - "iavf-%s-tx-%d", basename, tx_int_idx++); + "iavf-%s-tx-%u", basename, tx_int_idx++); } else { /* skip this unused q_vector */ continue; @@ -469,17 +576,6 @@ iavf_request_traffic_irqs(struct iavf_adapter *adapter, char *basename) "Request_irq failed, error: %d\n", err); goto free_queue_irqs; } - /* register for affinity change notifications */ - q_vector->affinity_notify.notify = iavf_irq_affinity_notify; - q_vector->affinity_notify.release = - iavf_irq_affinity_release; - irq_set_affinity_notifier(irq_num, &q_vector->affinity_notify); - /* Spread the IRQ affinity hints across online CPUs. Note that - * get_cpu_mask returns a mask with a permanent lifetime so - * it's safe to use as a hint for irq_set_affinity_hint. - */ - cpu = cpumask_local_spread(q_vector->v_idx, -1); - irq_set_affinity_hint(irq_num, get_cpu_mask(cpu)); } return 0; @@ -488,8 +584,6 @@ free_queue_irqs: while (vector) { vector--; irq_num = adapter->msix_entries[vector + NONQ_VECS].vector; - irq_set_affinity_notifier(irq_num, NULL); - irq_set_affinity_hint(irq_num, NULL); free_irq(irq_num, &adapter->q_vectors[vector]); } return err; @@ -531,6 +625,7 @@ static int iavf_request_misc_irq(struct iavf_adapter *adapter) **/ static void iavf_free_traffic_irqs(struct iavf_adapter *adapter) { + struct iavf_q_vector *q_vector; int vector, irq_num, q_vectors; if (!adapter->msix_entries) @@ -539,10 +634,10 @@ static void iavf_free_traffic_irqs(struct iavf_adapter *adapter) q_vectors = adapter->num_msix_vectors - NONQ_VECS; for (vector = 0; vector < q_vectors; vector++) { + q_vector = &adapter->q_vectors[vector]; + netif_napi_set_irq_locked(&q_vector->napi, -1); irq_num = adapter->msix_entries[vector + NONQ_VECS].vector; - irq_set_affinity_notifier(irq_num, NULL); - irq_set_affinity_hint(irq_num, NULL); - free_irq(irq_num, &adapter->q_vectors[vector]); + free_irq(irq_num, q_vector); } } @@ -578,6 +673,47 @@ 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 * @@ -585,39 +721,13 @@ static void iavf_configure_tx(struct iavf_adapter *adapter) **/ static void iavf_configure_rx(struct iavf_adapter *adapter) { - unsigned int rx_buf_len = IAVF_RXBUFFER_2048; struct iavf_hw *hw = &adapter->hw; - int i; - - /* Legacy Rx will always default to a 2048 buffer size. */ -#if (PAGE_SIZE < 8192) - if (!(adapter->flags & IAVF_FLAG_LEGACY_RX)) { - struct net_device *netdev = adapter->netdev; - - /* For jumbo frames on systems with 4K pages we have to use - * an order 1 page, so we might as well increase the size - * of our Rx buffer to make better use of the available space - */ - rx_buf_len = IAVF_RXBUFFER_3072; - /* We use a 1536 buffer size for configurations with - * standard Ethernet mtu. On x86 this gives us enough room - * for shared info and 192 bytes of padding. - */ - if (!IAVF_2K_TOO_SMALL_WITH_PADDING && - (netdev->mtu <= ETH_DATA_LEN)) - rx_buf_len = IAVF_RXBUFFER_1536 - NET_IP_ALIGN; - } -#endif + adapter->rxdid = iavf_select_rx_desc_format(adapter); - for (i = 0; i < adapter->num_active_queues; i++) { + 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].rx_buf_len = rx_buf_len; - - if (adapter->flags & IAVF_FLAG_LEGACY_RX) - clear_ring_build_skb_enabled(&adapter->rx_rings[i]); - else - set_ring_build_skb_enabled(&adapter->rx_rings[i]); + adapter->rx_rings[i].rxdid = adapter->rxdid; } } @@ -630,14 +740,17 @@ static void iavf_configure_rx(struct iavf_adapter *adapter) * mac_vlan_list_lock. **/ static struct -iavf_vlan_filter *iavf_find_vlan(struct iavf_adapter *adapter, u16 vlan) +iavf_vlan_filter *iavf_find_vlan(struct iavf_adapter *adapter, + struct iavf_vlan vlan) { struct iavf_vlan_filter *f; list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (vlan == f->vlan) + if (f->vlan.vid == vlan.vid && + f->vlan.tpid == vlan.tpid) return f; } + return NULL; } @@ -649,7 +762,8 @@ iavf_vlan_filter *iavf_find_vlan(struct iavf_adapter *adapter, u16 vlan) * Returns ptr to the filter object or NULL when no memory available. **/ static struct -iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, u16 vlan) +iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, + struct iavf_vlan vlan) { struct iavf_vlan_filter *f = NULL; @@ -657,16 +771,21 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, u16 vlan) f = iavf_find_vlan(adapter, vlan); if (!f) { - f = kzalloc(sizeof(*f), GFP_KERNEL); + f = kzalloc(sizeof(*f), GFP_ATOMIC); if (!f) goto clearout; f->vlan = vlan; - INIT_LIST_HEAD(&f->list); - list_add(&f->list, &adapter->vlan_filter_list); - f->add = true; - adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; + list_add_tail(&f->list, &adapter->vlan_filter_list); + f->state = IAVF_VLAN_ADD; + adapter->num_vlan_filters++; + iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_VLAN_FILTER); + } else if (f->state == IAVF_VLAN_REMOVE) { + /* IAVF_VLAN_REMOVE means that VLAN wasn't yet removed. + * We can safely only change the state here. + */ + f->state = IAVF_VLAN_ACTIVE; } clearout: @@ -679,7 +798,7 @@ clearout: * @adapter: board private structure * @vlan: VLAN tag **/ -static void iavf_del_vlan(struct iavf_adapter *adapter, u16 vlan) +static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan) { struct iavf_vlan_filter *f; @@ -687,14 +806,89 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, u16 vlan) f = iavf_find_vlan(adapter, vlan); if (f) { - f->remove = true; - adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER; + /* IAVF_ADD_VLAN means that VLAN wasn't even added yet. + * Remove it from the list. + */ + if (f->state == IAVF_VLAN_ADD) { + list_del(&f->list); + kfree(f); + adapter->num_vlan_filters--; + } else { + f->state = IAVF_VLAN_REMOVE; + iavf_schedule_aq_request(adapter, + IAVF_FLAG_AQ_DEL_VLAN_FILTER); + } } spin_unlock_bh(&adapter->mac_vlan_list_lock); } /** + * iavf_restore_filters + * @adapter: board private structure + * + * Restore existing non MAC filters when VF netdev comes back up + **/ +static void iavf_restore_filters(struct iavf_adapter *adapter) +{ + struct iavf_vlan_filter *f; + + /* re-add all VLAN filters */ + spin_lock_bh(&adapter->mac_vlan_list_lock); + + list_for_each_entry(f, &adapter->vlan_filter_list, list) { + if (f->state == IAVF_VLAN_INACTIVE) + f->state = IAVF_VLAN_ADD; + } + + spin_unlock_bh(&adapter->mac_vlan_list_lock); + adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; +} + +/** + * iavf_get_num_vlans_added - get number of VLANs added + * @adapter: board private structure + */ +u16 iavf_get_num_vlans_added(struct iavf_adapter *adapter) +{ + return adapter->num_vlan_filters; +} + +/** + * iavf_get_max_vlans_allowed - get maximum VLANs allowed for this VF + * @adapter: board private structure + * + * This depends on the negotiated VLAN capability. For VIRTCHNL_VF_OFFLOAD_VLAN, + * do not impose a limit as that maintains current behavior and for + * VIRTCHNL_VF_OFFLOAD_VLAN_V2, use the maximum allowed sent from the PF. + **/ +static u16 iavf_get_max_vlans_allowed(struct iavf_adapter *adapter) +{ + /* don't impose any limit for VIRTCHNL_VF_OFFLOAD_VLAN since there has + * never been a limit on the VF driver side + */ + if (VLAN_ALLOWED(adapter)) + return VLAN_N_VID; + else if (VLAN_V2_ALLOWED(adapter)) + return adapter->vlan_v2_caps.filtering.max_filters; + + return 0; +} + +/** + * iavf_max_vlans_added - check if maximum VLANs allowed already exist + * @adapter: board private structure + **/ +static bool iavf_max_vlans_added(struct iavf_adapter *adapter) +{ + if (iavf_get_num_vlans_added(adapter) < + iavf_get_max_vlans_allowed(adapter)) + return false; + + return true; +} + +/** * iavf_vlan_rx_add_vid - Add a VLAN filter to a device * @netdev: network device struct * @proto: unused protocol data @@ -705,10 +899,22 @@ static int iavf_vlan_rx_add_vid(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); - if (!VLAN_ALLOWED(adapter)) + /* Do not track VLAN 0 filter, always added by the PF on VF init */ + if (!vid) + return 0; + + if (!VLAN_FILTERING_ALLOWED(adapter)) return -EIO; - if (iavf_add_vlan(adapter, vid) == NULL) + + if (iavf_max_vlans_added(adapter)) { + netdev_err(netdev, "Max allowed VLAN filters %u. Remove existing VLANs or disable filtering via Ethtool if supported.\n", + iavf_get_max_vlans_allowed(adapter)); + return -EIO; + } + + if (!iavf_add_vlan(adapter, IAVF_VLAN(vid, be16_to_cpu(proto)))) return -ENOMEM; + return 0; } @@ -723,11 +929,12 @@ static int iavf_vlan_rx_kill_vid(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); - if (VLAN_ALLOWED(adapter)) { - iavf_del_vlan(adapter, vid); + /* We do not track VLAN 0 filter */ + if (!vid) return 0; - } - return -EIO; + + iavf_del_vlan(adapter, IAVF_VLAN(vid, be16_to_cpu(proto))); + return 0; } /** @@ -761,9 +968,8 @@ iavf_mac_filter *iavf_find_filter(struct iavf_adapter *adapter, * * Returns ptr to the filter object or NULL when no memory available. **/ -static struct -iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter, - const u8 *macaddr) +struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter, + const u8 *macaddr) { struct iavf_mac_filter *f; @@ -780,6 +986,9 @@ iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter, list_add_tail(&f->list, &adapter->mac_filter_list); f->add = true; + f->add_handled = false; + f->is_new_mac = true; + f->is_primary = ether_addr_equal(macaddr, adapter->hw.mac.addr); adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER; } else { f->remove = false; @@ -789,46 +998,118 @@ iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter, } /** - * iavf_set_mac - NDO callback to set port mac address + * iavf_replace_primary_mac - Replace current primary address + * @adapter: board private structure + * @new_mac: new MAC address to be applied + * + * Replace current dev_addr and send request to PF for removal of previous + * primary MAC address filter and addition of new primary MAC filter. + * Return 0 for success, -ENOMEM for failure. + * + * Do not call this with mac_vlan_list_lock! + **/ +static int iavf_replace_primary_mac(struct iavf_adapter *adapter, + const u8 *new_mac) +{ + struct iavf_hw *hw = &adapter->hw; + struct iavf_mac_filter *new_f; + struct iavf_mac_filter *old_f; + + spin_lock_bh(&adapter->mac_vlan_list_lock); + + new_f = iavf_add_filter(adapter, new_mac); + if (!new_f) { + spin_unlock_bh(&adapter->mac_vlan_list_lock); + return -ENOMEM; + } + + old_f = iavf_find_filter(adapter, hw->mac.addr); + if (old_f) { + old_f->is_primary = false; + old_f->remove = true; + adapter->aq_required |= IAVF_FLAG_AQ_DEL_MAC_FILTER; + } + /* Always send the request to add if changing primary MAC, + * even if filter is already present on the list + */ + new_f->is_primary = true; + new_f->add = true; + ether_addr_copy(hw->mac.addr, new_mac); + + spin_unlock_bh(&adapter->mac_vlan_list_lock); + + /* schedule the watchdog task to immediately process the request */ + iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_MAC_FILTER); + return 0; +} + +/** + * iavf_is_mac_set_handled - wait for a response to set MAC from PF + * @netdev: network interface device structure + * @macaddr: MAC address to set + * + * Returns true on success, false on failure + */ +static bool iavf_is_mac_set_handled(struct net_device *netdev, + const u8 *macaddr) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_mac_filter *f; + bool ret = false; + + spin_lock_bh(&adapter->mac_vlan_list_lock); + + f = iavf_find_filter(adapter, macaddr); + + if (!f || (!f->add && f->add_handled)) + ret = true; + + spin_unlock_bh(&adapter->mac_vlan_list_lock); + + return ret; +} + +/** + * iavf_set_mac - NDO callback to set port MAC address * @netdev: network interface device structure * @p: pointer to an address structure * * Returns 0 on success, negative on failure - **/ + */ static int iavf_set_mac(struct net_device *netdev, void *p) { struct iavf_adapter *adapter = netdev_priv(netdev); - struct iavf_hw *hw = &adapter->hw; - struct iavf_mac_filter *f; struct sockaddr *addr = p; + int ret; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; - if (ether_addr_equal(netdev->dev_addr, addr->sa_data)) - return 0; + ret = iavf_replace_primary_mac(adapter, addr->sa_data); - if (adapter->flags & IAVF_FLAG_ADDR_SET_BY_PF) - return -EPERM; - - spin_lock_bh(&adapter->mac_vlan_list_lock); + if (ret) + return ret; - f = iavf_find_filter(adapter, hw->mac.addr); - if (f) { - f->remove = true; - adapter->aq_required |= IAVF_FLAG_AQ_DEL_MAC_FILTER; - } + ret = wait_event_interruptible_timeout(adapter->vc_waitqueue, + iavf_is_mac_set_handled(netdev, addr->sa_data), + msecs_to_jiffies(2500)); - f = iavf_add_filter(adapter, addr->sa_data); + /* If ret < 0 then it means wait was interrupted. + * If ret == 0 then it means we got a timeout. + * else it means we got response for set MAC from PF, + * check if netdev MAC was updated to requested MAC, + * if yes then set MAC succeeded otherwise it failed return -EACCES + */ + if (ret < 0) + return ret; - spin_unlock_bh(&adapter->mac_vlan_list_lock); + if (!ret) + return -EAGAIN; - if (f) { - ether_addr_copy(hw->mac.addr, addr->sa_data); - ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr); - } + if (!ether_addr_equal(netdev->dev_addr, addr->sa_data)) + return -EACCES; - return (f == NULL) ? -ENOMEM : 0; + return 0; } /** @@ -879,6 +1160,16 @@ static int iavf_addr_unsync(struct net_device *netdev, const u8 *addr) } /** + * iavf_promiscuous_mode_changed - check if promiscuous mode bits changed + * @adapter: device specific adapter + */ +bool iavf_promiscuous_mode_changed(struct iavf_adapter *adapter) +{ + return (adapter->current_netdev_promisc_flags ^ adapter->netdev->flags) & + (IFF_PROMISC | IFF_ALLMULTI); +} + +/** * iavf_set_rx_mode - NDO callback to set the netdev filters * @netdev: network interface device structure **/ @@ -891,19 +1182,10 @@ static void iavf_set_rx_mode(struct net_device *netdev) __dev_mc_sync(netdev, iavf_addr_sync, iavf_addr_unsync); spin_unlock_bh(&adapter->mac_vlan_list_lock); - if (netdev->flags & IFF_PROMISC && - !(adapter->flags & IAVF_FLAG_PROMISC_ON)) - adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_PROMISC; - else if (!(netdev->flags & IFF_PROMISC) && - adapter->flags & IAVF_FLAG_PROMISC_ON) - adapter->aq_required |= IAVF_FLAG_AQ_RELEASE_PROMISC; - - if (netdev->flags & IFF_ALLMULTI && - !(adapter->flags & IAVF_FLAG_ALLMULTI_ON)) - adapter->aq_required |= IAVF_FLAG_AQ_REQUEST_ALLMULTI; - else if (!(netdev->flags & IFF_ALLMULTI) && - adapter->flags & IAVF_FLAG_ALLMULTI_ON) - adapter->aq_required |= IAVF_FLAG_AQ_RELEASE_ALLMULTI; + spin_lock_bh(&adapter->current_netdev_promisc_flags_lock); + if (iavf_promiscuous_mode_changed(adapter)) + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_PROMISC_MODE; + spin_unlock_bh(&adapter->current_netdev_promisc_flags_lock); } /** @@ -921,7 +1203,7 @@ static void iavf_napi_enable_all(struct iavf_adapter *adapter) q_vector = &adapter->q_vectors[q_idx]; napi = &q_vector->napi; - napi_enable(napi); + napi_enable_locked(napi); } } @@ -937,7 +1219,7 @@ static void iavf_napi_disable_all(struct iavf_adapter *adapter) for (q_idx = 0; q_idx < q_vectors; q_idx++) { q_vector = &adapter->q_vectors[q_idx]; - napi_disable(&q_vector->napi); + napi_disable_locked(&q_vector->napi); } } @@ -966,84 +1248,173 @@ static void iavf_configure(struct iavf_adapter *adapter) /** * iavf_up_complete - Finish the last steps of bringing up a connection * @adapter: board private structure - * - * Expects to be called while holding the __IAVF_IN_CRITICAL_TASK bit lock. - **/ + */ static void iavf_up_complete(struct iavf_adapter *adapter) { - adapter->state = __IAVF_RUNNING; + netdev_assert_locked(adapter->netdev); + + iavf_change_state(adapter, __IAVF_RUNNING); clear_bit(__IAVF_VSI_DOWN, adapter->vsi.state); iavf_napi_enable_all(adapter); - adapter->aq_required |= IAVF_FLAG_AQ_ENABLE_QUEUES; - if (CLIENT_ENABLED(adapter)) - adapter->flags |= IAVF_FLAG_CLIENT_NEEDS_OPEN; - mod_timer_pending(&adapter->watchdog_timer, jiffies + 1); + iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ENABLE_QUEUES); } /** - * iavf_down - Shutdown the connection processing + * iavf_clear_mac_vlan_filters - Remove mac and vlan filters not sent to PF + * yet and mark other to be removed. * @adapter: board private structure - * - * Expects to be called while holding the __IAVF_IN_CRITICAL_TASK bit lock. **/ -void iavf_down(struct iavf_adapter *adapter) +static void iavf_clear_mac_vlan_filters(struct iavf_adapter *adapter) { - struct net_device *netdev = adapter->netdev; - struct iavf_vlan_filter *vlf; - struct iavf_mac_filter *f; - struct iavf_cloud_filter *cf; - - if (adapter->state <= __IAVF_DOWN_PENDING) - return; - - netif_carrier_off(netdev); - netif_tx_disable(netdev); - adapter->link_up = false; - iavf_napi_disable_all(adapter); - iavf_irq_disable(adapter); + struct iavf_vlan_filter *vlf, *vlftmp; + struct iavf_mac_filter *f, *ftmp; spin_lock_bh(&adapter->mac_vlan_list_lock); - /* clear the sync flag on all filters */ __dev_uc_unsync(adapter->netdev, NULL); __dev_mc_unsync(adapter->netdev, NULL); /* remove all MAC filters */ - list_for_each_entry(f, &adapter->mac_filter_list, list) { - f->remove = true; + list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, + list) { + if (f->add) { + list_del(&f->list); + kfree(f); + } else { + f->remove = true; + } } - /* remove all VLAN filters */ - list_for_each_entry(vlf, &adapter->vlan_filter_list, list) { - vlf->remove = true; - } + /* disable all VLAN filters */ + list_for_each_entry_safe(vlf, vlftmp, &adapter->vlan_filter_list, + list) + vlf->state = IAVF_VLAN_DISABLE; spin_unlock_bh(&adapter->mac_vlan_list_lock); +} + +/** + * iavf_clear_cloud_filters - Remove cloud filters not sent to PF yet and + * mark other to be removed. + * @adapter: board private structure + **/ +static void iavf_clear_cloud_filters(struct iavf_adapter *adapter) +{ + struct iavf_cloud_filter *cf, *cftmp; /* remove all cloud filters */ spin_lock_bh(&adapter->cloud_filter_list_lock); - list_for_each_entry(cf, &adapter->cloud_filter_list, list) { - cf->del = true; + list_for_each_entry_safe(cf, cftmp, &adapter->cloud_filter_list, + list) { + if (cf->add) { + list_del(&cf->list); + kfree(cf); + adapter->num_cloud_filters--; + } else { + cf->del = true; + } } spin_unlock_bh(&adapter->cloud_filter_list_lock); +} + +/** + * iavf_clear_fdir_filters - Remove fdir filters not sent to PF yet and mark + * other to be removed. + * @adapter: board private structure + **/ +static void iavf_clear_fdir_filters(struct iavf_adapter *adapter) +{ + struct iavf_fdir_fltr *fdir; + + /* remove all Flow Director filters */ + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry(fdir, &adapter->fdir_list_head, list) { + if (fdir->state == IAVF_FDIR_FLTR_ADD_REQUEST) { + /* Cancel a request, keep filter as inactive */ + fdir->state = IAVF_FDIR_FLTR_INACTIVE; + } else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING || + fdir->state == IAVF_FDIR_FLTR_ACTIVE) { + /* Disable filters which are active or have a pending + * request to PF to be added + */ + fdir->state = IAVF_FDIR_FLTR_DIS_REQUEST; + } + } + spin_unlock_bh(&adapter->fdir_fltr_lock); +} - if (!(adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) && - adapter->state != __IAVF_RESETTING) { +/** + * iavf_clear_adv_rss_conf - Remove adv rss conf not sent to PF yet and mark + * other to be removed. + * @adapter: board private structure + **/ +static void iavf_clear_adv_rss_conf(struct iavf_adapter *adapter) +{ + struct iavf_adv_rss *rss, *rsstmp; + + /* remove all advance RSS configuration */ + spin_lock_bh(&adapter->adv_rss_lock); + list_for_each_entry_safe(rss, rsstmp, &adapter->adv_rss_list_head, + list) { + if (rss->state == IAVF_ADV_RSS_ADD_REQUEST) { + list_del(&rss->list); + kfree(rss); + } else { + rss->state = IAVF_ADV_RSS_DEL_REQUEST; + } + } + spin_unlock_bh(&adapter->adv_rss_lock); +} + +/** + * iavf_down - Shutdown the connection processing + * @adapter: board private structure + */ +void iavf_down(struct iavf_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + + netdev_assert_locked(netdev); + + if (adapter->state <= __IAVF_DOWN_PENDING) + return; + + netif_carrier_off(netdev); + netif_tx_disable(netdev); + adapter->link_up = false; + iavf_napi_disable_all(adapter); + iavf_irq_disable(adapter); + + iavf_clear_mac_vlan_filters(adapter); + iavf_clear_cloud_filters(adapter); + iavf_clear_fdir_filters(adapter); + iavf_clear_adv_rss_conf(adapter); + + if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) + return; + + if (!test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) { /* cancel any current operation */ adapter->current_op = VIRTCHNL_OP_UNKNOWN; /* Schedule operations to close down the HW. Don't wait * here for this to complete. The watchdog is still running * and it will take care of this. */ - adapter->aq_required = IAVF_FLAG_AQ_DEL_MAC_FILTER; - adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER; - adapter->aq_required |= IAVF_FLAG_AQ_DEL_CLOUD_FILTER; - adapter->aq_required |= IAVF_FLAG_AQ_DISABLE_QUEUES; - } - - mod_timer_pending(&adapter->watchdog_timer, jiffies + 1); + if (!list_empty(&adapter->mac_filter_list)) + adapter->aq_required |= IAVF_FLAG_AQ_DEL_MAC_FILTER; + if (!list_empty(&adapter->vlan_filter_list)) + adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER; + if (!list_empty(&adapter->cloud_filter_list)) + adapter->aq_required |= IAVF_FLAG_AQ_DEL_CLOUD_FILTER; + if (!list_empty(&adapter->fdir_list_head)) + adapter->aq_required |= IAVF_FLAG_AQ_DEL_FDIR_FILTER; + if (!list_empty(&adapter->adv_rss_list_head)) + adapter->aq_required |= IAVF_FLAG_AQ_DEL_ADV_RSS_CFG; + } + + iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DISABLE_QUEUES); } /** @@ -1107,6 +1478,86 @@ static void iavf_free_queues(struct iavf_adapter *adapter) } /** + * iavf_set_queue_vlan_tag_loc - set location for VLAN tag offload + * @adapter: board private structure + * + * Based on negotiated capabilities, the VLAN tag needs to be inserted and/or + * stripped in certain descriptor fields. Instead of checking the offload + * capability bits in the hot path, cache the location the ring specific + * flags. + */ +void iavf_set_queue_vlan_tag_loc(struct iavf_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_active_queues; i++) { + struct iavf_ring *tx_ring = &adapter->tx_rings[i]; + struct iavf_ring *rx_ring = &adapter->rx_rings[i]; + + /* prevent multiple L2TAG bits being set after VFR */ + tx_ring->flags &= + ~(IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1 | + IAVF_TXR_FLAGS_VLAN_TAG_LOC_L2TAG2); + rx_ring->flags &= + ~(IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1 | + IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2); + + if (VLAN_ALLOWED(adapter)) { + tx_ring->flags |= IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1; + rx_ring->flags |= IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1; + } else if (VLAN_V2_ALLOWED(adapter)) { + struct virtchnl_vlan_supported_caps *stripping_support; + struct virtchnl_vlan_supported_caps *insertion_support; + + stripping_support = + &adapter->vlan_v2_caps.offloads.stripping_support; + insertion_support = + &adapter->vlan_v2_caps.offloads.insertion_support; + + if (stripping_support->outer) { + if (stripping_support->outer & + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1) + rx_ring->flags |= + IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1; + else if (stripping_support->outer & + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2_2) + rx_ring->flags |= + IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2; + } else if (stripping_support->inner) { + if (stripping_support->inner & + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1) + rx_ring->flags |= + IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1; + else if (stripping_support->inner & + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2_2) + rx_ring->flags |= + IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2; + } + + if (insertion_support->outer) { + if (insertion_support->outer & + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1) + tx_ring->flags |= + IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1; + else if (insertion_support->outer & + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2) + tx_ring->flags |= + IAVF_TXR_FLAGS_VLAN_TAG_LOC_L2TAG2; + } else if (insertion_support->inner) { + if (insertion_support->inner & + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG1) + tx_ring->flags |= + IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1; + else if (insertion_support->inner & + VIRTCHNL_VLAN_TAG_LOCATION_L2TAG2) + tx_ring->flags |= + IAVF_TXR_FLAGS_VLAN_TAG_LOC_L2TAG2; + } + } + } +} + +/** * iavf_alloc_queues - Allocate memory for all rings * @adapter: board private structure to initialize * @@ -1160,13 +1611,14 @@ static int iavf_alloc_queues(struct iavf_adapter *adapter) rx_ring = &adapter->rx_rings[i]; rx_ring->queue_index = i; rx_ring->netdev = adapter->netdev; - rx_ring->dev = &adapter->pdev->dev; rx_ring->count = adapter->rx_desc_count; rx_ring->itr_setting = IAVF_ITR_RX_DEF; } adapter->num_active_queues = num_active_queues; + iavf_set_queue_vlan_tag_loc(adapter); + return 0; err_out: @@ -1212,10 +1664,10 @@ static int iavf_set_interrupt_capability(struct iavf_adapter *adapter) adapter->msix_entries[vector].entry = vector; err = iavf_acquire_msix_vectors(adapter, v_budget); + if (!err) + iavf_schedule_finish_config(adapter); out: - netif_set_real_num_rx_queues(adapter->netdev, pairs); - netif_set_real_num_tx_queues(adapter->netdev, pairs); return err; } @@ -1227,10 +1679,10 @@ out: **/ static int iavf_config_rss_aq(struct iavf_adapter *adapter) { - struct i40e_aqc_get_set_rss_key_data *rss_key = - (struct i40e_aqc_get_set_rss_key_data *)adapter->rss_key; + struct iavf_aqc_get_set_rss_key_data *rss_key = + (struct iavf_aqc_get_set_rss_key_data *)adapter->rss_key; struct iavf_hw *hw = &adapter->hw; - int ret = 0; + enum iavf_status status; if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { /* bail because we already have a command pending */ @@ -1239,24 +1691,25 @@ static int iavf_config_rss_aq(struct iavf_adapter *adapter) return -EBUSY; } - ret = iavf_aq_set_rss_key(hw, adapter->vsi.id, rss_key); - if (ret) { + status = iavf_aq_set_rss_key(hw, adapter->vsi.id, rss_key); + if (status) { dev_err(&adapter->pdev->dev, "Cannot set RSS key, err %s aq_err %s\n", - iavf_stat_str(hw, ret), - iavf_aq_str(hw, hw->aq.asq_last_status)); - return ret; + iavf_stat_str(hw, status), + libie_aq_str(hw->aq.asq_last_status)); + return iavf_status_to_errno(status); } - ret = iavf_aq_set_rss_lut(hw, adapter->vsi.id, false, - adapter->rss_lut, adapter->rss_lut_size); - if (ret) { + status = iavf_aq_set_rss_lut(hw, adapter->vsi.id, false, + adapter->rss_lut, adapter->rss_lut_size); + if (status) { dev_err(&adapter->pdev->dev, "Cannot set RSS lut, err %s aq_err %s\n", - iavf_stat_str(hw, ret), - iavf_aq_str(hw, hw->aq.asq_last_status)); + iavf_stat_str(hw, status), + libie_aq_str(hw->aq.asq_last_status)); + return iavf_status_to_errno(status); } - return ret; + return 0; } @@ -1326,25 +1779,24 @@ static void iavf_fill_rss_lut(struct iavf_adapter *adapter) static int iavf_init_rss(struct iavf_adapter *adapter) { struct iavf_hw *hw = &adapter->hw; - int ret; if (!RSS_PF(adapter)) { /* Enable PCTYPES for RSS, TCP/UDP with IPv4/IPv6 */ if (adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2) - adapter->hena = IAVF_DEFAULT_RSS_HENA_EXPANDED; + adapter->rss_hashcfg = + IAVF_DEFAULT_RSS_HASHCFG_EXPANDED; else - adapter->hena = IAVF_DEFAULT_RSS_HENA; + adapter->rss_hashcfg = IAVF_DEFAULT_RSS_HASHCFG; - wr32(hw, IAVF_VFQF_HENA(0), (u32)adapter->hena); - wr32(hw, IAVF_VFQF_HENA(1), (u32)(adapter->hena >> 32)); + wr32(hw, IAVF_VFQF_HENA(0), (u32)adapter->rss_hashcfg); + wr32(hw, IAVF_VFQF_HENA(1), (u32)(adapter->rss_hashcfg >> 32)); } iavf_fill_rss_lut(adapter); netdev_rss_key_fill((void *)adapter->rss_key, adapter->rss_key_size); - ret = iavf_config_rss(adapter); - return ret; + return iavf_config_rss(adapter); } /** @@ -1356,7 +1808,7 @@ static int iavf_init_rss(struct iavf_adapter *adapter) **/ static int iavf_alloc_q_vectors(struct iavf_adapter *adapter) { - int q_idx = 0, num_q_vectors; + int q_idx = 0, num_q_vectors, irq_num; struct iavf_q_vector *q_vector; num_q_vectors = adapter->num_msix_vectors - NONQ_VECS; @@ -1366,14 +1818,15 @@ static int iavf_alloc_q_vectors(struct iavf_adapter *adapter) return -ENOMEM; for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { + irq_num = adapter->msix_entries[q_idx + NONQ_VECS].vector; q_vector = &adapter->q_vectors[q_idx]; q_vector->adapter = adapter; q_vector->vsi = &adapter->vsi; q_vector->v_idx = q_idx; q_vector->reg_idx = q_idx; - cpumask_copy(&q_vector->affinity_mask, cpu_possible_mask); - netif_napi_add(adapter->netdev, &q_vector->napi, - iavf_napi_poll, NAPI_POLL_WEIGHT); + netif_napi_add_config_locked(adapter->netdev, &q_vector->napi, + iavf_napi_poll, q_idx); + netif_napi_set_irq_locked(&q_vector->napi, irq_num); } return 0; @@ -1390,19 +1843,16 @@ static int iavf_alloc_q_vectors(struct iavf_adapter *adapter) static void iavf_free_q_vectors(struct iavf_adapter *adapter) { int q_idx, num_q_vectors; - int napi_vectors; if (!adapter->q_vectors) return; num_q_vectors = adapter->num_msix_vectors - NONQ_VECS; - napi_vectors = adapter->num_active_queues; for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { struct iavf_q_vector *q_vector = &adapter->q_vectors[q_idx]; - if (q_idx < napi_vectors) - netif_napi_del(&q_vector->napi); + netif_napi_del_locked(&q_vector->napi); } kfree(adapter->q_vectors); adapter->q_vectors = NULL; @@ -1413,7 +1863,7 @@ static void iavf_free_q_vectors(struct iavf_adapter *adapter) * @adapter: board private structure * **/ -void iavf_reset_interrupt_capability(struct iavf_adapter *adapter) +static void iavf_reset_interrupt_capability(struct iavf_adapter *adapter) { if (!adapter->msix_entries) return; @@ -1428,7 +1878,7 @@ void iavf_reset_interrupt_capability(struct iavf_adapter *adapter) * @adapter: board private structure to initialize * **/ -int iavf_init_interrupt_scheme(struct iavf_adapter *adapter) +static int iavf_init_interrupt_scheme(struct iavf_adapter *adapter) { int err; @@ -1439,9 +1889,7 @@ int iavf_init_interrupt_scheme(struct iavf_adapter *adapter) goto err_alloc_queues; } - rtnl_lock(); err = iavf_set_interrupt_capability(adapter); - rtnl_unlock(); if (err) { dev_err(&adapter->pdev->dev, "Unable to setup interrupt capabilities\n"); @@ -1479,6 +1927,17 @@ err_alloc_queues: } /** + * iavf_free_interrupt_scheme - Undo what iavf_init_interrupt_scheme does + * @adapter: board private structure + **/ +static void iavf_free_interrupt_scheme(struct iavf_adapter *adapter) +{ + iavf_free_q_vectors(adapter); + iavf_reset_interrupt_capability(adapter); + iavf_free_queues(adapter); +} + +/** * iavf_free_rss - Free memory used by RSS structs * @adapter: board private structure **/ @@ -1494,22 +1953,21 @@ static void iavf_free_rss(struct iavf_adapter *adapter) /** * iavf_reinit_interrupt_scheme - Reallocate queues and vectors * @adapter: board private structure + * @running: true if adapter->state == __IAVF_RUNNING * * Returns 0 on success, negative on failure **/ -static int iavf_reinit_interrupt_scheme(struct iavf_adapter *adapter) +static int iavf_reinit_interrupt_scheme(struct iavf_adapter *adapter, bool running) { struct net_device *netdev = adapter->netdev; int err; - if (netif_running(netdev)) + if (running) iavf_free_traffic_irqs(adapter); iavf_free_misc_irq(adapter); - iavf_reset_interrupt_capability(adapter); - iavf_free_q_vectors(adapter); - iavf_free_queues(adapter); + iavf_free_interrupt_scheme(adapter); - err = iavf_init_interrupt_scheme(adapter); + err = iavf_init_interrupt_scheme(adapter); if (err) goto err; @@ -1522,146 +1980,174 @@ static int iavf_reinit_interrupt_scheme(struct iavf_adapter *adapter) set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); iavf_map_rings_to_vectors(adapter); - - if (RSS_AQ(adapter)) - adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_RSS; - else - err = iavf_init_rss(adapter); err: return err; } /** - * iavf_watchdog_timer - Periodic call-back timer - * @data: pointer to adapter disguised as unsigned long - **/ -static void iavf_watchdog_timer(struct timer_list *t) + * iavf_finish_config - do all netdev work that needs RTNL + * @work: our work_struct + * + * Do work that needs RTNL. + */ +static void iavf_finish_config(struct work_struct *work) { - struct iavf_adapter *adapter = from_timer(adapter, t, - watchdog_timer); + struct iavf_adapter *adapter; + bool netdev_released = false; + int pairs, err; - schedule_work(&adapter->watchdog_task); - /* timer will be rescheduled in watchdog task */ -} + adapter = container_of(work, struct iavf_adapter, finish_config); -/** - * iavf_watchdog_task - Periodic call-back task - * @work: pointer to work_struct - **/ -static void iavf_watchdog_task(struct work_struct *work) -{ - struct iavf_adapter *adapter = container_of(work, - struct iavf_adapter, - watchdog_task); - struct iavf_hw *hw = &adapter->hw; - u32 reg_val; - - if (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section)) - goto restart_watchdog; + /* Always take RTNL first to prevent circular lock dependency; + * the dev->lock (== netdev lock) is needed to update the queue number. + */ + rtnl_lock(); + netdev_lock(adapter->netdev); - if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) { - reg_val = rd32(hw, IAVF_VFGEN_RSTAT) & - IAVF_VFGEN_RSTAT_VFR_STATE_MASK; - if ((reg_val == VIRTCHNL_VFR_VFACTIVE) || - (reg_val == VIRTCHNL_VFR_COMPLETED)) { - /* A chance for redemption! */ - dev_err(&adapter->pdev->dev, "Hardware came out of reset. Attempting reinit.\n"); - adapter->state = __IAVF_STARTUP; - adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; - schedule_delayed_work(&adapter->init_task, 10); - clear_bit(__IAVF_IN_CRITICAL_TASK, - &adapter->crit_section); - /* Don't reschedule the watchdog, since we've restarted - * the init task. When init_task contacts the PF and - * gets everything set up again, it'll restart the - * watchdog for us. Down, boy. Sit. Stay. Woof. - */ - return; - } - adapter->aq_required = 0; - adapter->current_op = VIRTCHNL_OP_UNKNOWN; - goto watchdog_done; + if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES) && + adapter->netdev->reg_state == NETREG_REGISTERED && + !test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) { + netdev_update_features(adapter->netdev); + adapter->flags &= ~IAVF_FLAG_SETUP_NETDEV_FEATURES; } - if ((adapter->state < __IAVF_DOWN) || - (adapter->flags & IAVF_FLAG_RESET_PENDING)) - goto watchdog_done; + switch (adapter->state) { + case __IAVF_DOWN: + /* Set the real number of queues when reset occurs while + * state == __IAVF_DOWN + */ + pairs = adapter->num_active_queues; + netif_set_real_num_rx_queues(adapter->netdev, pairs); + netif_set_real_num_tx_queues(adapter->netdev, pairs); + + if (adapter->netdev->reg_state != NETREG_REGISTERED) { + netdev_unlock(adapter->netdev); + netdev_released = true; + err = register_netdevice(adapter->netdev); + if (err) { + dev_err(&adapter->pdev->dev, "Unable to register netdev (%d)\n", + err); + + /* go back and try again.*/ + netdev_lock(adapter->netdev); + iavf_free_rss(adapter); + iavf_free_misc_irq(adapter); + iavf_reset_interrupt_capability(adapter); + iavf_change_state(adapter, + __IAVF_INIT_CONFIG_ADAPTER); + netdev_unlock(adapter->netdev); + goto out; + } + } + break; + case __IAVF_RUNNING: + pairs = adapter->num_active_queues; + netif_set_real_num_rx_queues(adapter->netdev, pairs); + netif_set_real_num_tx_queues(adapter->netdev, pairs); + break; - /* check for reset */ - reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK; - if (!(adapter->flags & IAVF_FLAG_RESET_PENDING) && !reg_val) { - adapter->state = __IAVF_RESETTING; - adapter->flags |= IAVF_FLAG_RESET_PENDING; - dev_err(&adapter->pdev->dev, "Hardware reset detected\n"); - schedule_work(&adapter->reset_task); - adapter->aq_required = 0; - adapter->current_op = VIRTCHNL_OP_UNKNOWN; - goto watchdog_done; + default: + break; } - /* Process admin queue tasks. After init, everything gets done - * here so we don't race on the admin queue. - */ - if (adapter->current_op) { - if (!iavf_asq_done(hw)) { - dev_dbg(&adapter->pdev->dev, "Admin queue timeout\n"); - iavf_send_api_ver(adapter); - } - goto watchdog_done; - } - if (adapter->aq_required & IAVF_FLAG_AQ_GET_CONFIG) { - iavf_send_vf_config_msg(adapter); - goto watchdog_done; - } +out: + if (!netdev_released) + netdev_unlock(adapter->netdev); + rtnl_unlock(); +} +/** + * iavf_schedule_finish_config - Set the flags and schedule a reset event + * @adapter: board private structure + **/ +void iavf_schedule_finish_config(struct iavf_adapter *adapter) +{ + if (!test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) + queue_work(adapter->wq, &adapter->finish_config); +} + +/** + * iavf_process_aq_command - process aq_required flags + * and sends aq command + * @adapter: pointer to iavf adapter structure + * + * Returns 0 on success + * Returns error code if no command was sent + * or error code if the command failed. + **/ +static int iavf_process_aq_command(struct iavf_adapter *adapter) +{ + if (adapter->aq_required & IAVF_FLAG_AQ_GET_CONFIG) + 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); - goto watchdog_done; + return 0; } if (adapter->aq_required & IAVF_FLAG_AQ_MAP_VECTORS) { iavf_map_queues(adapter); - goto watchdog_done; + return 0; } if (adapter->aq_required & IAVF_FLAG_AQ_ADD_MAC_FILTER) { iavf_add_ether_addrs(adapter); - goto watchdog_done; + return 0; } if (adapter->aq_required & IAVF_FLAG_AQ_ADD_VLAN_FILTER) { iavf_add_vlans(adapter); - goto watchdog_done; + return 0; } if (adapter->aq_required & IAVF_FLAG_AQ_DEL_MAC_FILTER) { iavf_del_ether_addrs(adapter); - goto watchdog_done; + return 0; } if (adapter->aq_required & IAVF_FLAG_AQ_DEL_VLAN_FILTER) { iavf_del_vlans(adapter); - goto watchdog_done; + return 0; } if (adapter->aq_required & IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING) { iavf_enable_vlan_stripping(adapter); - goto watchdog_done; + return 0; } if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING) { iavf_disable_vlan_stripping(adapter); - goto watchdog_done; + return 0; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW) { + iavf_cfg_queues_bw(adapter); + return 0; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_GET_QOS_CAPS) { + iavf_get_qos_caps(adapter); + return 0; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_CFG_QUEUES_QUANTA_SIZE) { + iavf_cfg_queues_quanta_size(adapter); + return 0; } if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_QUEUES) { iavf_configure_queues(adapter); - goto watchdog_done; + return 0; } if (adapter->aq_required & IAVF_FLAG_AQ_ENABLE_QUEUES) { iavf_enable_queues(adapter); - goto watchdog_done; + return 0; } if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_RSS) { @@ -1669,89 +2155,874 @@ static void iavf_watchdog_task(struct work_struct *work) * PF, so we don't have to set current_op as we will * not get a response through the ARQ. */ - iavf_init_rss(adapter); adapter->aq_required &= ~IAVF_FLAG_AQ_CONFIGURE_RSS; - goto watchdog_done; + return 0; } - if (adapter->aq_required & IAVF_FLAG_AQ_GET_HENA) { - iavf_get_hena(adapter); - goto watchdog_done; + if (adapter->aq_required & IAVF_FLAG_AQ_GET_RSS_HASHCFG) { + iavf_get_rss_hashcfg(adapter); + return 0; } - if (adapter->aq_required & IAVF_FLAG_AQ_SET_HENA) { - iavf_set_hena(adapter); - goto watchdog_done; + if (adapter->aq_required & IAVF_FLAG_AQ_SET_RSS_HASHCFG) { + iavf_set_rss_hashcfg(adapter); + return 0; } if (adapter->aq_required & IAVF_FLAG_AQ_SET_RSS_KEY) { iavf_set_rss_key(adapter); - goto watchdog_done; + return 0; } if (adapter->aq_required & IAVF_FLAG_AQ_SET_RSS_LUT) { iavf_set_rss_lut(adapter); - goto watchdog_done; - } - - if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_PROMISC) { - iavf_set_promiscuous(adapter, FLAG_VF_UNICAST_PROMISC | - FLAG_VF_MULTICAST_PROMISC); - goto watchdog_done; + return 0; } - - if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_ALLMULTI) { - iavf_set_promiscuous(adapter, FLAG_VF_MULTICAST_PROMISC); - goto watchdog_done; + if (adapter->aq_required & IAVF_FLAG_AQ_SET_RSS_HFUNC) { + iavf_set_rss_hfunc(adapter); + return 0; } - if ((adapter->aq_required & IAVF_FLAG_AQ_RELEASE_PROMISC) && - (adapter->aq_required & IAVF_FLAG_AQ_RELEASE_ALLMULTI)) { - iavf_set_promiscuous(adapter, 0); - goto watchdog_done; + if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_PROMISC_MODE) { + iavf_set_promiscuous(adapter); + return 0; } if (adapter->aq_required & IAVF_FLAG_AQ_ENABLE_CHANNELS) { iavf_enable_channels(adapter); - goto watchdog_done; + return 0; } if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_CHANNELS) { iavf_disable_channels(adapter); - goto watchdog_done; + return 0; } - if (adapter->aq_required & IAVF_FLAG_AQ_ADD_CLOUD_FILTER) { iavf_add_cloud_filter(adapter); - goto watchdog_done; + return 0; } - if (adapter->aq_required & IAVF_FLAG_AQ_DEL_CLOUD_FILTER) { iavf_del_cloud_filter(adapter); - goto watchdog_done; + return 0; + } + if (adapter->aq_required & IAVF_FLAG_AQ_ADD_FDIR_FILTER) { + iavf_add_fdir_filter(adapter); + return IAVF_SUCCESS; + } + if (adapter->aq_required & IAVF_FLAG_AQ_DEL_FDIR_FILTER) { + iavf_del_fdir_filter(adapter); + return IAVF_SUCCESS; } + if (adapter->aq_required & IAVF_FLAG_AQ_ADD_ADV_RSS_CFG) { + iavf_add_adv_rss_cfg(adapter); + return 0; + } + if (adapter->aq_required & IAVF_FLAG_AQ_DEL_ADV_RSS_CFG) { + iavf_del_adv_rss_cfg(adapter); + return 0; + } + if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_CTAG_VLAN_STRIPPING) { + iavf_disable_vlan_stripping_v2(adapter, ETH_P_8021Q); + return 0; + } + if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_STAG_VLAN_STRIPPING) { + iavf_disable_vlan_stripping_v2(adapter, ETH_P_8021AD); + return 0; + } + if (adapter->aq_required & IAVF_FLAG_AQ_ENABLE_CTAG_VLAN_STRIPPING) { + iavf_enable_vlan_stripping_v2(adapter, ETH_P_8021Q); + return 0; + } + if (adapter->aq_required & IAVF_FLAG_AQ_ENABLE_STAG_VLAN_STRIPPING) { + iavf_enable_vlan_stripping_v2(adapter, ETH_P_8021AD); + return 0; + } + if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_CTAG_VLAN_INSERTION) { + iavf_disable_vlan_insertion_v2(adapter, ETH_P_8021Q); + return 0; + } + if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_STAG_VLAN_INSERTION) { + iavf_disable_vlan_insertion_v2(adapter, ETH_P_8021AD); + return 0; + } + if (adapter->aq_required & IAVF_FLAG_AQ_ENABLE_CTAG_VLAN_INSERTION) { + iavf_enable_vlan_insertion_v2(adapter, ETH_P_8021Q); + return 0; + } + if (adapter->aq_required & IAVF_FLAG_AQ_ENABLE_STAG_VLAN_INSERTION) { + 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; + } + + return -EAGAIN; +} - schedule_delayed_work(&adapter->client_task, msecs_to_jiffies(5)); +/** + * iavf_set_vlan_offload_features - set VLAN offload configuration + * @adapter: board private structure + * @prev_features: previous features used for comparison + * @features: updated features used for configuration + * + * Set the aq_required bit(s) based on the requested features passed in to + * configure VLAN stripping and/or VLAN insertion if supported. Also, schedule + * the watchdog if any changes are requested to expedite the request via + * virtchnl. + **/ +static void +iavf_set_vlan_offload_features(struct iavf_adapter *adapter, + netdev_features_t prev_features, + netdev_features_t features) +{ + bool enable_stripping = true, enable_insertion = true; + u16 vlan_ethertype = 0; + u64 aq_required = 0; + + /* keep cases separate because one ethertype for offloads can be + * disabled at the same time as another is disabled, so check for an + * enabled ethertype first, then check for disabled. Default to + * ETH_P_8021Q so an ethertype is specified if disabling insertion and + * stripping. + */ + if (features & (NETIF_F_HW_VLAN_STAG_RX | NETIF_F_HW_VLAN_STAG_TX)) + vlan_ethertype = ETH_P_8021AD; + else if (features & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_TX)) + vlan_ethertype = ETH_P_8021Q; + else if (prev_features & (NETIF_F_HW_VLAN_STAG_RX | NETIF_F_HW_VLAN_STAG_TX)) + vlan_ethertype = ETH_P_8021AD; + else if (prev_features & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_TX)) + vlan_ethertype = ETH_P_8021Q; + else + vlan_ethertype = ETH_P_8021Q; - if (adapter->state == __IAVF_RUNNING) - iavf_request_stats(adapter); -watchdog_done: - if (adapter->state == __IAVF_RUNNING) - iavf_detect_recover_hung(&adapter->vsi); - clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); -restart_watchdog: - if (adapter->state == __IAVF_REMOVE) + if (!(features & (NETIF_F_HW_VLAN_STAG_RX | NETIF_F_HW_VLAN_CTAG_RX))) + enable_stripping = false; + if (!(features & (NETIF_F_HW_VLAN_STAG_TX | NETIF_F_HW_VLAN_CTAG_TX))) + enable_insertion = false; + + if (VLAN_ALLOWED(adapter)) { + /* VIRTCHNL_VF_OFFLOAD_VLAN only has support for toggling VLAN + * stripping via virtchnl. VLAN insertion can be toggled on the + * netdev, but it doesn't require a virtchnl message + */ + if (enable_stripping) + aq_required |= IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING; + else + aq_required |= IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING; + + } else if (VLAN_V2_ALLOWED(adapter)) { + switch (vlan_ethertype) { + case ETH_P_8021Q: + if (enable_stripping) + aq_required |= IAVF_FLAG_AQ_ENABLE_CTAG_VLAN_STRIPPING; + else + aq_required |= IAVF_FLAG_AQ_DISABLE_CTAG_VLAN_STRIPPING; + + if (enable_insertion) + aq_required |= IAVF_FLAG_AQ_ENABLE_CTAG_VLAN_INSERTION; + else + aq_required |= IAVF_FLAG_AQ_DISABLE_CTAG_VLAN_INSERTION; + break; + case ETH_P_8021AD: + if (enable_stripping) + aq_required |= IAVF_FLAG_AQ_ENABLE_STAG_VLAN_STRIPPING; + else + aq_required |= IAVF_FLAG_AQ_DISABLE_STAG_VLAN_STRIPPING; + + if (enable_insertion) + aq_required |= IAVF_FLAG_AQ_ENABLE_STAG_VLAN_INSERTION; + else + aq_required |= IAVF_FLAG_AQ_DISABLE_STAG_VLAN_INSERTION; + break; + } + } + + if (aq_required) + iavf_schedule_aq_request(adapter, aq_required); +} + +/** + * iavf_startup - first step of driver startup + * @adapter: board private structure + * + * Function process __IAVF_STARTUP driver state. + * When success the state is changed to __IAVF_INIT_VERSION_CHECK + * when fails the state is changed to __IAVF_INIT_FAILED + **/ +static void iavf_startup(struct iavf_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + struct iavf_hw *hw = &adapter->hw; + enum iavf_status status; + int ret; + + WARN_ON(adapter->state != __IAVF_STARTUP); + + /* driver loaded, probe complete */ + adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; + adapter->flags &= ~IAVF_FLAG_RESET_PENDING; + + ret = iavf_check_reset_complete(hw); + if (ret) { + dev_info(&pdev->dev, "Device is still in reset (%d), retrying\n", + ret); + goto err; + } + hw->aq.num_arq_entries = IAVF_AQ_LEN; + hw->aq.num_asq_entries = IAVF_AQ_LEN; + hw->aq.arq_buf_size = IAVF_MAX_AQ_BUF_SIZE; + hw->aq.asq_buf_size = IAVF_MAX_AQ_BUF_SIZE; + + status = iavf_init_adminq(hw); + if (status) { + dev_err(&pdev->dev, "Failed to init Admin Queue (%d)\n", + status); + goto err; + } + ret = iavf_send_api_ver(adapter); + if (ret) { + dev_err(&pdev->dev, "Unable to send to PF (%d)\n", ret); + iavf_shutdown_adminq(hw); + goto err; + } + iavf_change_state(adapter, __IAVF_INIT_VERSION_CHECK); + return; +err: + iavf_change_state(adapter, __IAVF_INIT_FAILED); +} + +/** + * iavf_init_version_check - second step of driver startup + * @adapter: board private structure + * + * Function process __IAVF_INIT_VERSION_CHECK driver state. + * When success the state is changed to __IAVF_INIT_GET_RESOURCES + * when fails the state is changed to __IAVF_INIT_FAILED + **/ +static void iavf_init_version_check(struct iavf_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + struct iavf_hw *hw = &adapter->hw; + int err = -EAGAIN; + + WARN_ON(adapter->state != __IAVF_INIT_VERSION_CHECK); + + if (!iavf_asq_done(hw)) { + dev_err(&pdev->dev, "Admin queue command never completed\n"); + iavf_shutdown_adminq(hw); + iavf_change_state(adapter, __IAVF_STARTUP); + goto err; + } + + /* aq msg sent, awaiting reply */ + err = iavf_verify_api_ver(adapter); + if (err) { + if (err == -EALREADY) + err = iavf_send_api_ver(adapter); + else + dev_err(&pdev->dev, "Unsupported PF API version %d.%d, expected %d.%d\n", + adapter->pf_version.major, + adapter->pf_version.minor, + VIRTCHNL_VERSION_MAJOR, + VIRTCHNL_VERSION_MINOR); + goto err; + } + err = iavf_send_vf_config_msg(adapter); + if (err) { + dev_err(&pdev->dev, "Unable to send config request (%d)\n", + err); + goto err; + } + iavf_change_state(adapter, __IAVF_INIT_GET_RESOURCES); + return; +err: + iavf_change_state(adapter, __IAVF_INIT_FAILED); +} + +/** + * iavf_parse_vf_resource_msg - parse response from VIRTCHNL_OP_GET_VF_RESOURCES + * @adapter: board private structure + */ +int iavf_parse_vf_resource_msg(struct iavf_adapter *adapter) +{ + int i, num_req_queues = adapter->num_req_queues; + struct iavf_vsi *vsi = &adapter->vsi; + + for (i = 0; i < adapter->vf_res->num_vsis; i++) { + if (adapter->vf_res->vsi_res[i].vsi_type == VIRTCHNL_VSI_SRIOV) + adapter->vsi_res = &adapter->vf_res->vsi_res[i]; + } + if (!adapter->vsi_res) { + dev_err(&adapter->pdev->dev, "No LAN VSI found\n"); + return -ENODEV; + } + + if (num_req_queues && + num_req_queues > adapter->vsi_res->num_queue_pairs) { + /* Problem. The PF gave us fewer queues than what we had + * negotiated in our request. Need a reset to see if we can't + * get back to a working state. + */ + dev_err(&adapter->pdev->dev, + "Requested %d queues, but PF only gave us %d.\n", + num_req_queues, + adapter->vsi_res->num_queue_pairs); + adapter->flags |= IAVF_FLAG_REINIT_MSIX_NEEDED; + adapter->num_req_queues = adapter->vsi_res->num_queue_pairs; + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); + + return -EAGAIN; + } + adapter->num_req_queues = 0; + adapter->vsi.id = adapter->vsi_res->vsi_id; + + adapter->vsi.back = adapter; + adapter->vsi.base_vector = 1; + vsi->netdev = adapter->netdev; + vsi->qs_handle = adapter->vsi_res->qset_handle; + if (adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF) { + adapter->rss_key_size = adapter->vf_res->rss_key_size; + adapter->rss_lut_size = adapter->vf_res->rss_lut_size; + } else { + adapter->rss_key_size = IAVF_HKEY_ARRAY_SIZE; + adapter->rss_lut_size = IAVF_HLUT_ARRAY_SIZE; + } + + return 0; +} + +/** + * iavf_init_get_resources - third step of driver startup + * @adapter: board private structure + * + * Function process __IAVF_INIT_GET_RESOURCES driver state and + * finishes driver initialization procedure. + * When success the state is changed to __IAVF_DOWN + * when fails the state is changed to __IAVF_INIT_FAILED + **/ +static void iavf_init_get_resources(struct iavf_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + struct iavf_hw *hw = &adapter->hw; + int err; + + WARN_ON(adapter->state != __IAVF_INIT_GET_RESOURCES); + /* aq msg sent, awaiting reply */ + if (!adapter->vf_res) { + adapter->vf_res = kzalloc(IAVF_VIRTCHNL_VF_RESOURCE_SIZE, + GFP_KERNEL); + if (!adapter->vf_res) { + err = -ENOMEM; + goto err; + } + } + err = iavf_get_vf_config(adapter); + if (err == -EALREADY) { + err = iavf_send_vf_config_msg(adapter); + goto err; + } else if (err == -EINVAL) { + /* We only get -EINVAL if the device is in a very bad + * state or if we've been disabled for previous bad + * behavior. Either way, we're done now. + */ + iavf_shutdown_adminq(hw); + dev_err(&pdev->dev, "Unable to get VF config due to PF error condition, not retrying\n"); return; - if (adapter->aq_required) - mod_timer(&adapter->watchdog_timer, - jiffies + msecs_to_jiffies(20)); + } + if (err) { + dev_err(&pdev->dev, "Unable to get VF config (%d)\n", err); + goto err_alloc; + } + + err = iavf_parse_vf_resource_msg(adapter); + if (err) { + dev_err(&pdev->dev, "Failed to parse VF resource message from PF (%d)\n", + err); + goto err_alloc; + } + /* Some features require additional messages to negotiate extended + * capabilities. These are processed in sequence by the + * __IAVF_INIT_EXTENDED_CAPS driver state. + */ + adapter->extended_caps = IAVF_EXTENDED_CAPS; + + iavf_change_state(adapter, __IAVF_INIT_EXTENDED_CAPS); + return; + +err_alloc: + kfree(adapter->vf_res); + adapter->vf_res = NULL; +err: + iavf_change_state(adapter, __IAVF_INIT_FAILED); +} + +/** + * iavf_init_send_offload_vlan_v2_caps - part of initializing VLAN V2 caps + * @adapter: board private structure + * + * Function processes send of the extended VLAN V2 capability message to the + * PF. Must clear IAVF_EXTENDED_CAP_RECV_VLAN_V2 if the message is not sent, + * e.g. due to PF not negotiating VIRTCHNL_VF_OFFLOAD_VLAN_V2. + */ +static void iavf_init_send_offload_vlan_v2_caps(struct iavf_adapter *adapter) +{ + int ret; + + WARN_ON(!(adapter->extended_caps & IAVF_EXTENDED_CAP_SEND_VLAN_V2)); + + ret = iavf_send_vf_offload_vlan_v2_msg(adapter); + if (ret && ret == -EOPNOTSUPP) { + /* PF does not support VIRTCHNL_VF_OFFLOAD_V2. In this case, + * we did not send the capability exchange message and do not + * expect a response. + */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_VLAN_V2; + } + + /* We sent the message, so move on to the next step */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_SEND_VLAN_V2; +} + +/** + * iavf_init_recv_offload_vlan_v2_caps - part of initializing VLAN V2 caps + * @adapter: board private structure + * + * Function processes receipt of the extended VLAN V2 capability message from + * the PF. + **/ +static void iavf_init_recv_offload_vlan_v2_caps(struct iavf_adapter *adapter) +{ + int ret; + + WARN_ON(!(adapter->extended_caps & IAVF_EXTENDED_CAP_RECV_VLAN_V2)); + + memset(&adapter->vlan_v2_caps, 0, sizeof(adapter->vlan_v2_caps)); + + ret = iavf_get_vf_vlan_v2_caps(adapter); + if (ret) + goto err; + + /* We've processed receipt of the VLAN V2 caps message */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_VLAN_V2; + 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_VLAN_V2; + iavf_change_state(adapter, __IAVF_INIT_FAILED); +} + +/** + * 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 + * + * Function processes __IAVF_INIT_EXTENDED_CAPS driver state. This state + * handles negotiating capabilities for features which require an additional + * message. + * + * Once all extended capabilities exchanges are finished, the driver will + * transition into __IAVF_INIT_CONFIG_ADAPTER. + */ +static void iavf_init_process_extended_caps(struct iavf_adapter *adapter) +{ + WARN_ON(adapter->state != __IAVF_INIT_EXTENDED_CAPS); + + /* Process capability exchange for VLAN V2 */ + if (adapter->extended_caps & IAVF_EXTENDED_CAP_SEND_VLAN_V2) { + iavf_init_send_offload_vlan_v2_caps(adapter); + return; + } else if (adapter->extended_caps & IAVF_EXTENDED_CAP_RECV_VLAN_V2) { + iavf_init_recv_offload_vlan_v2_caps(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 + */ + iavf_change_state(adapter, __IAVF_INIT_CONFIG_ADAPTER); +} + +/** + * iavf_init_config_adapter - last part of driver startup + * @adapter: board private structure + * + * After all the supported capabilities are negotiated, then the + * __IAVF_INIT_CONFIG_ADAPTER state will finish driver initialization. + */ +static void iavf_init_config_adapter(struct iavf_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct pci_dev *pdev = adapter->pdev; + int err; + + WARN_ON(adapter->state != __IAVF_INIT_CONFIG_ADAPTER); + + if (iavf_process_config(adapter)) + goto err; + + adapter->current_op = VIRTCHNL_OP_UNKNOWN; + + adapter->flags |= IAVF_FLAG_RX_CSUM_ENABLED; + + netdev->netdev_ops = &iavf_netdev_ops; + iavf_set_ethtool_ops(netdev); + netdev->watchdog_timeo = 5 * HZ; + + netdev->min_mtu = ETH_MIN_MTU; + netdev->max_mtu = LIBIE_MAX_MTU; + + if (!is_valid_ether_addr(adapter->hw.mac.addr)) { + dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n", + adapter->hw.mac.addr); + eth_hw_addr_random(netdev); + ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr); + } else { + eth_hw_addr_set(netdev, adapter->hw.mac.addr); + ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); + } + + adapter->tx_desc_count = IAVF_DEFAULT_TXD; + adapter->rx_desc_count = IAVF_DEFAULT_RXD; + err = iavf_init_interrupt_scheme(adapter); + if (err) + goto err_sw_init; + iavf_map_rings_to_vectors(adapter); + if (adapter->vf_res->vf_cap_flags & + VIRTCHNL_VF_OFFLOAD_WB_ON_ITR) + adapter->flags |= IAVF_FLAG_WB_ON_ITR_CAPABLE; + + err = iavf_request_misc_irq(adapter); + if (err) + goto err_sw_init; + + netif_carrier_off(netdev); + adapter->link_up = false; + netif_tx_stop_all_queues(netdev); + + dev_info(&pdev->dev, "MAC address: %pM\n", adapter->hw.mac.addr); + if (netdev->features & NETIF_F_GRO) + dev_info(&pdev->dev, "GRO is enabled\n"); + + iavf_change_state(adapter, __IAVF_DOWN); + set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); + + iavf_misc_irq_enable(adapter); + wake_up(&adapter->down_waitqueue); + + adapter->rss_key = kzalloc(adapter->rss_key_size, GFP_KERNEL); + adapter->rss_lut = kzalloc(adapter->rss_lut_size, GFP_KERNEL); + if (!adapter->rss_key || !adapter->rss_lut) { + err = -ENOMEM; + goto err_mem; + } + if (RSS_AQ(adapter)) + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_RSS; else - mod_timer(&adapter->watchdog_timer, jiffies + (HZ * 2)); - schedule_work(&adapter->adminq_task); + iavf_init_rss(adapter); + + if (VLAN_V2_ALLOWED(adapter)) + /* request initial VLAN offload settings */ + iavf_set_vlan_offload_features(adapter, 0, netdev->features); + + 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; + +err_mem: + iavf_free_rss(adapter); + iavf_free_misc_irq(adapter); +err_sw_init: + iavf_reset_interrupt_capability(adapter); +err: + iavf_change_state(adapter, __IAVF_INIT_FAILED); } +static const int IAVF_NO_RESCHED = -1; + +/* return: msec delay for requeueing itself */ +static int iavf_watchdog_step(struct iavf_adapter *adapter) +{ + struct iavf_hw *hw = &adapter->hw; + u32 reg_val; + + netdev_assert_locked(adapter->netdev); + + if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) + iavf_change_state(adapter, __IAVF_COMM_FAILED); + + switch (adapter->state) { + case __IAVF_STARTUP: + iavf_startup(adapter); + return 30; + case __IAVF_INIT_VERSION_CHECK: + iavf_init_version_check(adapter); + return 30; + case __IAVF_INIT_GET_RESOURCES: + iavf_init_get_resources(adapter); + return 1; + case __IAVF_INIT_EXTENDED_CAPS: + iavf_init_process_extended_caps(adapter); + return 1; + case __IAVF_INIT_CONFIG_ADAPTER: + iavf_init_config_adapter(adapter); + return 1; + case __IAVF_INIT_FAILED: + if (test_bit(__IAVF_IN_REMOVE_TASK, + &adapter->crit_section)) { + /* Do not update the state and do not reschedule + * watchdog task, iavf_remove should handle this state + * as it can loop forever + */ + return IAVF_NO_RESCHED; + } + if (++adapter->aq_wait_count > IAVF_AQ_MAX_ERR) { + dev_err(&adapter->pdev->dev, + "Failed to communicate with PF; waiting before retry\n"); + adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED; + iavf_shutdown_adminq(hw); + return 5000; + } + /* Try again from failed step*/ + iavf_change_state(adapter, adapter->last_state); + return 1000; + case __IAVF_COMM_FAILED: + if (test_bit(__IAVF_IN_REMOVE_TASK, + &adapter->crit_section)) { + /* Set state to __IAVF_INIT_FAILED and perform remove + * steps. Remove IAVF_FLAG_PF_COMMS_FAILED so the task + * doesn't bring the state back to __IAVF_COMM_FAILED. + */ + iavf_change_state(adapter, __IAVF_INIT_FAILED); + adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; + return IAVF_NO_RESCHED; + } + reg_val = rd32(hw, IAVF_VFGEN_RSTAT) & + IAVF_VFGEN_RSTAT_VFR_STATE_MASK; + if (reg_val == VIRTCHNL_VFR_VFACTIVE || + reg_val == VIRTCHNL_VFR_COMPLETED) { + /* A chance for redemption! */ + dev_err(&adapter->pdev->dev, + "Hardware came out of reset. Attempting reinit.\n"); + /* When init task contacts the PF and + * gets everything set up again, it'll restart the + * watchdog for us. Down, boy. Sit. Stay. Woof. + */ + iavf_change_state(adapter, __IAVF_STARTUP); + adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; + } + adapter->aq_required = 0; + adapter->current_op = VIRTCHNL_OP_UNKNOWN; + return 10; + case __IAVF_RESETTING: + return 2000; + case __IAVF_DOWN: + case __IAVF_DOWN_PENDING: + case __IAVF_TESTING: + case __IAVF_RUNNING: + if (adapter->current_op) { + if (!iavf_asq_done(hw)) { + dev_dbg(&adapter->pdev->dev, + "Admin queue timeout\n"); + iavf_send_api_ver(adapter); + } + } else { + int ret = iavf_process_aq_command(adapter); + + /* An error will be returned if no commands were + * processed; use this opportunity to update stats + * if the error isn't -ENOTSUPP + */ + if (ret && ret != -EOPNOTSUPP && + adapter->state == __IAVF_RUNNING) + iavf_request_stats(adapter); + } + if (adapter->state == __IAVF_RUNNING) + iavf_detect_recover_hung(&adapter->vsi); + break; + case __IAVF_REMOVE: + default: + return IAVF_NO_RESCHED; + } + + /* check for hw reset */ + reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK; + if (!reg_val) { + adapter->aq_required = 0; + adapter->current_op = VIRTCHNL_OP_UNKNOWN; + dev_err(&adapter->pdev->dev, "Hardware reset detected\n"); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_PENDING); + } + + return adapter->aq_required ? 20 : 2000; +} + +static void iavf_watchdog_task(struct work_struct *work) +{ + struct iavf_adapter *adapter = container_of(work, + struct iavf_adapter, + watchdog_task.work); + struct net_device *netdev = adapter->netdev; + int msec_delay; + + netdev_lock(netdev); + msec_delay = iavf_watchdog_step(adapter); + /* note that we schedule a different task */ + if (adapter->state >= __IAVF_DOWN) + queue_work(adapter->wq, &adapter->adminq_task); + + if (msec_delay != IAVF_NO_RESCHED) + queue_delayed_work(adapter->wq, &adapter->watchdog_task, + msecs_to_jiffies(msec_delay)); + netdev_unlock(netdev); +} + +/** + * iavf_disable_vf - disable VF + * @adapter: board private structure + * + * Set communication failed flag and free all resources. + */ static void iavf_disable_vf(struct iavf_adapter *adapter) { struct iavf_mac_filter *f, *ftmp; struct iavf_vlan_filter *fv, *fvtmp; struct iavf_cloud_filter *cf, *cftmp; + netdev_assert_locked(adapter->netdev); + adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED; /* We don't use netif_running() because it may be true prior to @@ -1782,6 +3053,7 @@ static void iavf_disable_vf(struct iavf_adapter *adapter) list_del(&fv->list); kfree(fv); } + adapter->num_vlan_filters = 0; spin_unlock_bh(&adapter->mac_vlan_list_lock); @@ -1794,21 +3066,39 @@ static void iavf_disable_vf(struct iavf_adapter *adapter) spin_unlock_bh(&adapter->cloud_filter_list_lock); iavf_free_misc_irq(adapter); - iavf_reset_interrupt_capability(adapter); - iavf_free_queues(adapter); - iavf_free_q_vectors(adapter); - kfree(adapter->vf_res); + iavf_free_interrupt_scheme(adapter); + memset(adapter->vf_res, 0, IAVF_VIRTCHNL_VF_RESOURCE_SIZE); iavf_shutdown_adminq(&adapter->hw); - adapter->netdev->flags &= ~IFF_UP; - clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); adapter->flags &= ~IAVF_FLAG_RESET_PENDING; - adapter->state = __IAVF_DOWN; + iavf_change_state(adapter, __IAVF_DOWN); wake_up(&adapter->down_waitqueue); dev_info(&adapter->pdev->dev, "Reset task did not complete, VF disabled\n"); } -#define IAVF_RESET_WAIT_MS 10 -#define IAVF_RESET_WAIT_COUNT 500 +/** + * iavf_reconfig_qs_bw - Call-back task to handle hardware reset + * @adapter: board private structure + * + * After a reset, the shaper parameters of queues need to be replayed again. + * Since the net_shaper object inside TX rings persists across reset, + * set the update flag for all queues so that the virtchnl message is triggered + * for all queues. + **/ +static void iavf_reconfig_qs_bw(struct iavf_adapter *adapter) +{ + int i, num = 0; + + for (i = 0; i < adapter->num_active_queues; i++) + if (adapter->tx_rings[i].q_shaper.bw_min || + adapter->tx_rings[i].q_shaper.bw_max) { + adapter->tx_rings[i].q_shaper_update = true; + num++; + } + + if (num) + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW; +} + /** * iavf_reset_task - Call-back task to handle hardware reset * @work: pointer to work_struct @@ -1825,30 +3115,15 @@ static void iavf_reset_task(struct work_struct *work) struct virtchnl_vf_resource *vfres = adapter->vf_res; struct net_device *netdev = adapter->netdev; struct iavf_hw *hw = &adapter->hw; - struct iavf_vlan_filter *vlf; + struct iavf_mac_filter *f, *ftmp; struct iavf_cloud_filter *cf; - struct iavf_mac_filter *f; + enum iavf_status status; u32 reg_val; int i = 0, err; bool running; - /* When device is being removed it doesn't make sense to run the reset - * task, just return in such a case. - */ - if (test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) - return; + netdev_lock(netdev); - while (test_and_set_bit(__IAVF_IN_CLIENT_TASK, - &adapter->crit_section)) - usleep_range(500, 1000); - if (CLIENT_ENABLED(adapter)) { - adapter->flags &= ~(IAVF_FLAG_CLIENT_NEEDS_OPEN | - IAVF_FLAG_CLIENT_NEEDS_CLOSE | - IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS | - IAVF_FLAG_SERVICE_CLIENT_REQUESTED); - cancel_delayed_work_sync(&adapter->client_task); - iavf_notify_client_close(&adapter->vsi, true); - } iavf_misc_irq_disable(adapter); if (adapter->flags & IAVF_FLAG_RESET_NEEDED) { adapter->flags &= ~IAVF_FLAG_RESET_NEEDED; @@ -1862,20 +3137,20 @@ static void iavf_reset_task(struct work_struct *work) adapter->flags |= IAVF_FLAG_RESET_PENDING; /* poll until we see the reset actually happen */ - for (i = 0; i < IAVF_RESET_WAIT_COUNT; i++) { + for (i = 0; i < IAVF_RESET_WAIT_DETECTED_COUNT; i++) { reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK; if (!reg_val) break; usleep_range(5000, 10000); } - if (i == IAVF_RESET_WAIT_COUNT) { + if (i == IAVF_RESET_WAIT_DETECTED_COUNT) { dev_info(&adapter->pdev->dev, "Never saw reset\n"); goto continue_reset; /* act like the reset happened */ } /* wait until the reset is complete and the PF is responding to us */ - for (i = 0; i < IAVF_RESET_WAIT_COUNT; i++) { + for (i = 0; i < IAVF_RESET_WAIT_COMPLETE_COUNT; i++) { /* sleep first to make sure a minimum wait time is met */ msleep(IAVF_RESET_WAIT_MS); @@ -1886,22 +3161,33 @@ static void iavf_reset_task(struct work_struct *work) } pci_set_master(adapter->pdev); + pci_restore_msi_state(adapter->pdev); - if (i == IAVF_RESET_WAIT_COUNT) { + if (i == IAVF_RESET_WAIT_COMPLETE_COUNT) { dev_err(&adapter->pdev->dev, "Reset never finished (%x)\n", reg_val); iavf_disable_vf(adapter); - clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section); + netdev_unlock(netdev); return; /* Do not attempt to reinit. It's dead, Jim. */ } continue_reset: + /* If we are still early in the state machine, just restart. */ + if (adapter->state <= __IAVF_INIT_FAILED) { + iavf_shutdown_adminq(hw); + iavf_change_state(adapter, __IAVF_STARTUP); + iavf_startup(adapter); + queue_delayed_work(adapter->wq, &adapter->watchdog_task, + msecs_to_jiffies(30)); + netdev_unlock(netdev); + return; + } + /* We don't use netif_running() because it may be true prior to * ndo_open() returning, so we can't assume it means all our open * tasks have finished, since we're not holding the rtnl_lock here. */ - running = ((adapter->state == __IAVF_RUNNING) || - (adapter->state == __IAVF_RESETTING)); + running = adapter->state == __IAVF_RUNNING; if (running) { netif_carrier_off(netdev); @@ -1911,7 +3197,7 @@ continue_reset: } iavf_irq_disable(adapter); - adapter->state = __IAVF_RESETTING; + iavf_change_state(adapter, __IAVF_RESETTING); adapter->flags &= ~IAVF_FLAG_RESET_PENDING; /* free the Tx/Rx rings and descriptors, might be better to just @@ -1924,14 +3210,25 @@ continue_reset: /* kill and reinit the admin queue */ iavf_shutdown_adminq(hw); adapter->current_op = VIRTCHNL_OP_UNKNOWN; - err = iavf_init_adminq(hw); - if (err) + status = iavf_init_adminq(hw); + if (status) { dev_info(&adapter->pdev->dev, "Failed to init adminq: %d\n", - err); + status); + goto reset_err; + } adapter->aq_required = 0; - if (adapter->flags & IAVF_FLAG_REINIT_ITR_NEEDED) { - err = iavf_reinit_interrupt_scheme(adapter); + if ((adapter->flags & IAVF_FLAG_REINIT_MSIX_NEEDED) || + (adapter->flags & IAVF_FLAG_REINIT_ITR_NEEDED)) { + err = iavf_reinit_interrupt_scheme(adapter, running); + if (err) + goto reset_err; + } + + if (RSS_AQ(adapter)) { + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_RSS; + } else { + err = iavf_init_rss(adapter); if (err) goto reset_err; } @@ -1939,17 +3236,32 @@ continue_reset: adapter->aq_required |= IAVF_FLAG_AQ_GET_CONFIG; 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 + * been changed by the PF via administratively set MAC. + * Will be re-added via VIRTCHNL_OP_GET_VF_RESOURCES. + */ + list_for_each_entry_safe(f, ftmp, &adapter->mac_filter_list, list) { + if (ether_addr_equal(f->macaddr, adapter->hw.mac.addr)) { + list_del(&f->list); + kfree(f); + } + } /* re-add all MAC filters */ list_for_each_entry(f, &adapter->mac_filter_list, list) { f->add = true; } - /* re-add all VLAN filters */ - list_for_each_entry(vlf, &adapter->vlan_filter_list, list) { - vlf->add = true; - } - spin_unlock_bh(&adapter->mac_vlan_list_lock); /* check if TCs are running and re-add all cloud filters */ @@ -1963,11 +3275,10 @@ continue_reset: spin_unlock_bh(&adapter->cloud_filter_list_lock); adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER; - adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; adapter->aq_required |= IAVF_FLAG_AQ_ADD_CLOUD_FILTER; iavf_misc_irq_enable(adapter); - mod_timer(&adapter->watchdog_timer, jiffies + 2); + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 2); /* We were running when the reset started, so we need to restore some * state here. @@ -1983,32 +3294,45 @@ continue_reset: if (err) goto reset_err; - if (adapter->flags & IAVF_FLAG_REINIT_ITR_NEEDED) { + if ((adapter->flags & IAVF_FLAG_REINIT_MSIX_NEEDED) || + (adapter->flags & IAVF_FLAG_REINIT_ITR_NEEDED)) { err = iavf_request_traffic_irqs(adapter, netdev->name); if (err) goto reset_err; - adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + adapter->flags &= ~IAVF_FLAG_REINIT_MSIX_NEEDED; } iavf_configure(adapter); + /* iavf_up_complete() will switch device back + * to __IAVF_RUNNING + */ iavf_up_complete(adapter); iavf_irq_enable(adapter, true); + + iavf_reconfig_qs_bw(adapter); } else { - adapter->state = __IAVF_DOWN; + iavf_change_state(adapter, __IAVF_DOWN); wake_up(&adapter->down_waitqueue); } - clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section); - clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); + + adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + + wake_up(&adapter->reset_waitqueue); + netdev_unlock(netdev); return; reset_err: - clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section); - clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); + if (running) { + set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); + iavf_free_traffic_irqs(adapter); + } + iavf_disable_vf(adapter); + + netdev_unlock(netdev); dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); - iavf_close(netdev); } /** @@ -2019,25 +3343,28 @@ static void iavf_adminq_task(struct work_struct *work) { struct iavf_adapter *adapter = container_of(work, struct iavf_adapter, adminq_task); + struct net_device *netdev = adapter->netdev; struct iavf_hw *hw = &adapter->hw; - struct i40e_arq_event_info event; + struct iavf_arq_event_info event; enum virtchnl_ops v_op; - iavf_status ret, v_ret; + enum iavf_status ret, v_ret; u32 val, oldval; u16 pending; + netdev_lock(netdev); + if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) - goto out; + goto unlock; event.buf_len = IAVF_MAX_AQ_BUF_SIZE; event.msg_buf = kzalloc(event.buf_len, GFP_KERNEL); if (!event.msg_buf) - goto out; + goto unlock; do { ret = iavf_clean_arq_element(hw, &event, &pending); v_op = (enum virtchnl_ops)le32_to_cpu(event.desc.cookie_high); - v_ret = (iavf_status)le32_to_cpu(event.desc.cookie_low); + v_ret = (enum iavf_status)le32_to_cpu(event.desc.cookie_low); if (ret || !v_op) break; /* No event to process or error cleaning ARQ */ @@ -2048,14 +3375,12 @@ static void iavf_adminq_task(struct work_struct *work) memset(event.msg_buf, 0, IAVF_MAX_AQ_BUF_SIZE); } while (pending); - if ((adapter->flags & - (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED)) || - adapter->state == __IAVF_RESETTING) + if (iavf_is_reset_in_progress(adapter)) goto freedom; /* check for error indications */ - val = rd32(hw, hw->aq.arq.len); - if (val == 0xdeadbeef) /* indicates device in reset */ + val = rd32(hw, IAVF_VF_ARQLEN1); + if (val == 0xdeadbeef || val == 0xffffffff) /* device in reset */ goto freedom; oldval = val; if (val & IAVF_VF_ARQLEN1_ARQVFE_MASK) { @@ -2071,9 +3396,9 @@ static void iavf_adminq_task(struct work_struct *work) val &= ~IAVF_VF_ARQLEN1_ARQCRIT_MASK; } if (oldval != val) - wr32(hw, hw->aq.arq.len, val); + wr32(hw, IAVF_VF_ARQLEN1, val); - val = rd32(hw, hw->aq.asq.len); + val = rd32(hw, IAVF_VF_ATQLEN1); oldval = val; if (val & IAVF_VF_ATQLEN1_ATQVFE_MASK) { dev_info(&adapter->pdev->dev, "ASQ VF Error detected\n"); @@ -2088,58 +3413,17 @@ static void iavf_adminq_task(struct work_struct *work) val &= ~IAVF_VF_ATQLEN1_ATQCRIT_MASK; } if (oldval != val) - wr32(hw, hw->aq.asq.len, val); + wr32(hw, IAVF_VF_ATQLEN1, val); freedom: kfree(event.msg_buf); -out: +unlock: + netdev_unlock(netdev); /* re-enable Admin queue interrupt cause */ iavf_misc_irq_enable(adapter); } /** - * iavf_client_task - worker thread to perform client work - * @work: pointer to work_struct containing our data - * - * This task handles client interactions. Because client calls can be - * reentrant, we can't handle them in the watchdog. - **/ -static void iavf_client_task(struct work_struct *work) -{ - struct iavf_adapter *adapter = - container_of(work, struct iavf_adapter, client_task.work); - - /* If we can't get the client bit, just give up. We'll be rescheduled - * later. - */ - - if (test_and_set_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section)) - return; - - if (adapter->flags & IAVF_FLAG_SERVICE_CLIENT_REQUESTED) { - iavf_client_subtask(adapter); - adapter->flags &= ~IAVF_FLAG_SERVICE_CLIENT_REQUESTED; - goto out; - } - if (adapter->flags & IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS) { - iavf_notify_client_l2_params(&adapter->vsi); - adapter->flags &= ~IAVF_FLAG_CLIENT_NEEDS_L2_PARAMS; - goto out; - } - if (adapter->flags & IAVF_FLAG_CLIENT_NEEDS_CLOSE) { - iavf_notify_client_close(&adapter->vsi, false); - adapter->flags &= ~IAVF_FLAG_CLIENT_NEEDS_CLOSE; - goto out; - } - if (adapter->flags & IAVF_FLAG_CLIENT_NEEDS_OPEN) { - iavf_notify_client_open(&adapter->vsi); - adapter->flags &= ~IAVF_FLAG_CLIENT_NEEDS_OPEN; - } -out: - clear_bit(__IAVF_IN_CLIENT_TASK, &adapter->crit_section); -} - -/** * iavf_free_all_tx_resources - Free Tx Resources for All Queues * @adapter: board private structure * @@ -2238,29 +3522,46 @@ static int iavf_validate_tx_bandwidth(struct iavf_adapter *adapter, { int speed = 0, ret = 0; + if (ADV_LINK_SUPPORT(adapter)) { + if (adapter->link_speed_mbps < U32_MAX) { + speed = adapter->link_speed_mbps; + goto validate_bw; + } else { + dev_err(&adapter->pdev->dev, "Unknown link speed\n"); + return -EINVAL; + } + } + switch (adapter->link_speed) { - case I40E_LINK_SPEED_40GB: - speed = 40000; + case VIRTCHNL_LINK_SPEED_40GB: + speed = SPEED_40000; break; - case I40E_LINK_SPEED_25GB: - speed = 25000; + case VIRTCHNL_LINK_SPEED_25GB: + speed = SPEED_25000; break; - case I40E_LINK_SPEED_20GB: - speed = 20000; + case VIRTCHNL_LINK_SPEED_20GB: + speed = SPEED_20000; break; - case I40E_LINK_SPEED_10GB: - speed = 10000; + case VIRTCHNL_LINK_SPEED_10GB: + speed = SPEED_10000; break; - case I40E_LINK_SPEED_1GB: - speed = 1000; + case VIRTCHNL_LINK_SPEED_5GB: + speed = SPEED_5000; break; - case I40E_LINK_SPEED_100MB: - speed = 100; + case VIRTCHNL_LINK_SPEED_2_5GB: + speed = SPEED_2500; + break; + case VIRTCHNL_LINK_SPEED_1GB: + speed = SPEED_1000; + break; + case VIRTCHNL_LINK_SPEED_100MB: + speed = SPEED_100; break; default: break; } +validate_bw: if (max_tx_rate > speed) { dev_err(&adapter->pdev->dev, "Invalid tx rate specified\n"); @@ -2271,7 +3572,7 @@ static int iavf_validate_tx_bandwidth(struct iavf_adapter *adapter, } /** - * iavf_validate_channel_config - validate queue mapping info + * iavf_validate_ch_config - validate queue mapping info * @adapter: board private structure * @mqprio_qopt: queue parameters * @@ -2283,6 +3584,7 @@ static int iavf_validate_ch_config(struct iavf_adapter *adapter, struct tc_mqprio_qopt_offload *mqprio_qopt) { u64 total_max_rate = 0; + u32 tx_rate_rem = 0; int i, num_qps = 0; u64 tx_rate = 0; int ret = 0; @@ -2297,25 +3599,48 @@ static int iavf_validate_ch_config(struct iavf_adapter *adapter, return -EINVAL; if (mqprio_qopt->min_rate[i]) { dev_err(&adapter->pdev->dev, - "Invalid min tx rate (greater than 0) specified\n"); + "Invalid min tx rate (greater than 0) specified for TC%d\n", + i); return -EINVAL; } - /*convert to Mbps */ + + /* convert to Mbps */ tx_rate = div_u64(mqprio_qopt->max_rate[i], IAVF_MBPS_DIVISOR); + + if (mqprio_qopt->max_rate[i] && + tx_rate < IAVF_MBPS_QUANTA) { + dev_err(&adapter->pdev->dev, + "Invalid max tx rate for TC%d, minimum %dMbps\n", + i, IAVF_MBPS_QUANTA); + return -EINVAL; + } + + (void)div_u64_rem(tx_rate, IAVF_MBPS_QUANTA, &tx_rate_rem); + + if (tx_rate_rem != 0) { + dev_err(&adapter->pdev->dev, + "Invalid max tx rate for TC%d, not divisible by %d\n", + i, IAVF_MBPS_QUANTA); + return -EINVAL; + } + total_max_rate += tx_rate; num_qps += mqprio_qopt->qopt.count[i]; } - if (num_qps > IAVF_MAX_REQ_QUEUES) + if (num_qps > adapter->num_active_queues) { + dev_err(&adapter->pdev->dev, + "Cannot support requested number of queues\n"); return -EINVAL; + } ret = iavf_validate_tx_bandwidth(adapter, total_max_rate); return ret; } /** - * iavf_del_all_cloud_filters - delete all cloud filters - * on the traffic classes + * iavf_del_all_cloud_filters - delete all cloud filters on the traffic classes + * @adapter: board private structure **/ static void iavf_del_all_cloud_filters(struct iavf_adapter *adapter) { @@ -2332,9 +3657,37 @@ static void iavf_del_all_cloud_filters(struct iavf_adapter *adapter) } /** + * iavf_is_tc_config_same - Compare the mqprio TC config with the + * TC config already configured on this adapter. + * @adapter: board private structure + * @mqprio_qopt: TC config received from kernel. + * + * This function compares the TC config received from the kernel + * with the config already configured on the adapter. + * + * Return: True if configuration is same, false otherwise. + **/ +static bool iavf_is_tc_config_same(struct iavf_adapter *adapter, + struct tc_mqprio_qopt *mqprio_qopt) +{ + struct virtchnl_channel_info *ch = &adapter->ch_config.ch_info[0]; + int i; + + if (adapter->num_tc != mqprio_qopt->num_tc) + return false; + + for (i = 0; i < adapter->num_tc; i++) { + if (ch[i].count != mqprio_qopt->count[i] || + ch[i].offset != mqprio_qopt->offset[i]) + return false; + } + return true; +} + +/** * __iavf_setup_tc - configure multiple traffic classes * @netdev: network interface device structure - * @type_date: tc offload data + * @type_data: tc offload data * * This function processes the config information provided by the * user to configure traffic classes/queue channels and packages the @@ -2366,6 +3719,7 @@ static int __iavf_setup_tc(struct net_device *netdev, void *type_data) netif_tx_disable(netdev); iavf_del_all_cloud_filters(adapter); adapter->aq_required = IAVF_FLAG_AQ_DISABLE_CHANNELS; + total_qps = adapter->orig_num_active_queues; goto exit; } else { return -EINVAL; @@ -2387,7 +3741,7 @@ static int __iavf_setup_tc(struct net_device *netdev, void *type_data) if (ret) return ret; /* Return if same TC config is requested */ - if (adapter->num_tc == num_tc) + if (iavf_is_tc_config_same(adapter, &mqprio_qopt->qopt)) return 0; adapter->num_tc = num_tc; @@ -2409,7 +3763,21 @@ static int __iavf_setup_tc(struct net_device *netdev, void *type_data) adapter->ch_config.ch_info[i].offset = 0; } } + + /* Take snapshot of original config such as "num_active_queues" + * It is used later when delete ADQ flow is exercised, so that + * once delete ADQ flow completes, VF shall go back to its + * original queue configuration + */ + + adapter->orig_num_active_queues = adapter->num_active_queues; + + /* Store queue info based on TC so that VF gets configured + * with correct number of queues when VF completes ADQ config + * flow + */ adapter->ch_config.total_qps = total_qps; + netif_tx_stop_all_queues(netdev); netif_tx_disable(netdev); adapter->aq_required |= IAVF_FLAG_AQ_ENABLE_CHANNELS; @@ -2426,19 +3794,27 @@ static int __iavf_setup_tc(struct net_device *netdev, void *type_data) } } exit: + if (test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) + return 0; + + netif_set_real_num_rx_queues(netdev, total_qps); + netif_set_real_num_tx_queues(netdev, total_qps); + return ret; } /** * iavf_parse_cls_flower - Parse tc flower filters provided by kernel * @adapter: board private structure - * @cls_flower: pointer to struct tc_cls_flower_offload + * @f: pointer to struct flow_cls_offload * @filter: pointer to cloud filter structure */ static int iavf_parse_cls_flower(struct iavf_adapter *adapter, - struct tc_cls_flower_offload *f, + struct flow_cls_offload *f, struct iavf_cloud_filter *filter) { + struct flow_rule *rule = flow_cls_offload_flow_rule(f); + struct flow_dissector *dissector = rule->match.dissector; u16 n_proto_mask = 0; u16 n_proto_key = 0; u8 field_flags = 0; @@ -2447,42 +3823,34 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter, int i = 0; struct virtchnl_filter *vf = &filter->f; - if (f->dissector->used_keys & - ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) | - BIT(FLOW_DISSECTOR_KEY_BASIC) | - BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_VLAN) | - BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | - BIT(FLOW_DISSECTOR_KEY_PORTS) | - BIT(FLOW_DISSECTOR_KEY_ENC_KEYID))) { - dev_err(&adapter->pdev->dev, "Unsupported key used: 0x%x\n", - f->dissector->used_keys); + if (dissector->used_keys & + ~(BIT_ULL(FLOW_DISSECTOR_KEY_CONTROL) | + BIT_ULL(FLOW_DISSECTOR_KEY_BASIC) | + BIT_ULL(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_VLAN) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV4_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_IPV6_ADDRS) | + BIT_ULL(FLOW_DISSECTOR_KEY_PORTS) | + BIT_ULL(FLOW_DISSECTOR_KEY_ENC_KEYID))) { + dev_err(&adapter->pdev->dev, "Unsupported key used: 0x%llx\n", + dissector->used_keys); return -EOPNOTSUPP; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_KEYID)) { - struct flow_dissector_key_keyid *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ENC_KEYID, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ENC_KEYID)) { + struct flow_match_enc_keyid match; - if (mask->keyid != 0) + flow_rule_match_enc_keyid(rule, &match); + if (match.mask->keyid != 0) field_flags |= IAVF_CLOUD_FIELD_TEN_ID; } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { - struct flow_dissector_key_basic *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->key); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_match_basic match; - struct flow_dissector_key_basic *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_BASIC, - f->mask); - n_proto_key = ntohs(key->n_proto); - n_proto_mask = ntohs(mask->n_proto); + flow_rule_match_basic(rule, &match); + n_proto_key = ntohs(match.key->n_proto); + n_proto_mask = ntohs(match.mask->n_proto); if (n_proto_key == ETH_P_ALL) { n_proto_key = 0; @@ -2496,215 +3864,190 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter, vf->flow_type = VIRTCHNL_TCP_V6_FLOW; } - if (key->ip_proto != IPPROTO_TCP) { + if (match.key->ip_proto != IPPROTO_TCP) { dev_info(&adapter->pdev->dev, "Only TCP transport is supported\n"); return -EINVAL; } } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { - struct flow_dissector_key_eth_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - f->key); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_match_eth_addrs match; + + flow_rule_match_eth_addrs(rule, &match); - struct flow_dissector_key_eth_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_ETH_ADDRS, - f->mask); /* use is_broadcast and is_zero to check for all 0xf or 0 */ - if (!is_zero_ether_addr(mask->dst)) { - if (is_broadcast_ether_addr(mask->dst)) { + if (!is_zero_ether_addr(match.mask->dst)) { + if (is_broadcast_ether_addr(match.mask->dst)) { field_flags |= IAVF_CLOUD_FIELD_OMAC; } else { dev_err(&adapter->pdev->dev, "Bad ether dest mask %pM\n", - mask->dst); - return I40E_ERR_CONFIG; + match.mask->dst); + return -EINVAL; } } - if (!is_zero_ether_addr(mask->src)) { - if (is_broadcast_ether_addr(mask->src)) { + if (!is_zero_ether_addr(match.mask->src)) { + if (is_broadcast_ether_addr(match.mask->src)) { field_flags |= IAVF_CLOUD_FIELD_IMAC; } else { dev_err(&adapter->pdev->dev, "Bad ether src mask %pM\n", - mask->src); - return I40E_ERR_CONFIG; + match.mask->src); + return -EINVAL; } } - if (!is_zero_ether_addr(key->dst)) - if (is_valid_ether_addr(key->dst) || - is_multicast_ether_addr(key->dst)) { + if (!is_zero_ether_addr(match.key->dst)) + if (is_valid_ether_addr(match.key->dst) || + is_multicast_ether_addr(match.key->dst)) { /* set the mask if a valid dst_mac address */ for (i = 0; i < ETH_ALEN; i++) vf->mask.tcp_spec.dst_mac[i] |= 0xff; ether_addr_copy(vf->data.tcp_spec.dst_mac, - key->dst); + match.key->dst); } - if (!is_zero_ether_addr(key->src)) - if (is_valid_ether_addr(key->src) || - is_multicast_ether_addr(key->src)) { + if (!is_zero_ether_addr(match.key->src)) + if (is_valid_ether_addr(match.key->src) || + is_multicast_ether_addr(match.key->src)) { /* set the mask if a valid dst_mac address */ for (i = 0; i < ETH_ALEN; i++) vf->mask.tcp_spec.src_mac[i] |= 0xff; ether_addr_copy(vf->data.tcp_spec.src_mac, - key->src); + match.key->src); } } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) { - struct flow_dissector_key_vlan *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_VLAN, - f->key); - struct flow_dissector_key_vlan *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_VLAN, - f->mask); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_match_vlan match; - if (mask->vlan_id) { - if (mask->vlan_id == VLAN_VID_MASK) { + flow_rule_match_vlan(rule, &match); + if (match.mask->vlan_id) { + if (match.mask->vlan_id == VLAN_VID_MASK) { field_flags |= IAVF_CLOUD_FIELD_IVLAN; } else { dev_err(&adapter->pdev->dev, "Bad vlan mask %u\n", - mask->vlan_id); - return I40E_ERR_CONFIG; + match.mask->vlan_id); + return -EINVAL; } } vf->mask.tcp_spec.vlan_id |= cpu_to_be16(0xffff); - vf->data.tcp_spec.vlan_id = cpu_to_be16(key->vlan_id); + vf->data.tcp_spec.vlan_id = cpu_to_be16(match.key->vlan_id); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CONTROL)) { - struct flow_dissector_key_control *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_CONTROL, - f->key); + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) { + struct flow_match_control match; + + flow_rule_match_control(rule, &match); + addr_type = match.key->addr_type; - addr_type = key->addr_type; + if (flow_rule_has_control_flags(match.mask->flags, + f->common.extack)) + return -EOPNOTSUPP; } if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { - struct flow_dissector_key_ipv4_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - f->key); - struct flow_dissector_key_ipv4_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV4_ADDRS, - f->mask); - - if (mask->dst) { - if (mask->dst == cpu_to_be32(0xffffffff)) { + struct flow_match_ipv4_addrs match; + + flow_rule_match_ipv4_addrs(rule, &match); + if (match.mask->dst) { + if (match.mask->dst == cpu_to_be32(0xffffffff)) { field_flags |= IAVF_CLOUD_FIELD_IIP; } else { dev_err(&adapter->pdev->dev, "Bad ip dst mask 0x%08x\n", - be32_to_cpu(mask->dst)); - return I40E_ERR_CONFIG; + be32_to_cpu(match.mask->dst)); + return -EINVAL; } } - if (mask->src) { - if (mask->src == cpu_to_be32(0xffffffff)) { + if (match.mask->src) { + if (match.mask->src == cpu_to_be32(0xffffffff)) { field_flags |= IAVF_CLOUD_FIELD_IIP; } else { dev_err(&adapter->pdev->dev, "Bad ip src mask 0x%08x\n", - be32_to_cpu(mask->dst)); - return I40E_ERR_CONFIG; + be32_to_cpu(match.mask->src)); + return -EINVAL; } } if (field_flags & IAVF_CLOUD_FIELD_TEN_ID) { dev_info(&adapter->pdev->dev, "Tenant id not allowed for ip filter\n"); - return I40E_ERR_CONFIG; + return -EINVAL; } - if (key->dst) { + if (match.key->dst) { vf->mask.tcp_spec.dst_ip[0] |= cpu_to_be32(0xffffffff); - vf->data.tcp_spec.dst_ip[0] = key->dst; + vf->data.tcp_spec.dst_ip[0] = match.key->dst; } - if (key->src) { + if (match.key->src) { vf->mask.tcp_spec.src_ip[0] |= cpu_to_be32(0xffffffff); - vf->data.tcp_spec.src_ip[0] = key->src; + vf->data.tcp_spec.src_ip[0] = match.key->src; } } if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { - struct flow_dissector_key_ipv6_addrs *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - f->key); - struct flow_dissector_key_ipv6_addrs *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_IPV6_ADDRS, - f->mask); + struct flow_match_ipv6_addrs match; + + flow_rule_match_ipv6_addrs(rule, &match); /* validate mask, make sure it is not IPV6_ADDR_ANY */ - if (ipv6_addr_any(&mask->dst)) { + if (ipv6_addr_any(&match.mask->dst)) { dev_err(&adapter->pdev->dev, "Bad ipv6 dst mask 0x%02x\n", IPV6_ADDR_ANY); - return I40E_ERR_CONFIG; + return -EINVAL; } /* src and dest IPv6 address should not be LOOPBACK * (0:0:0:0:0:0:0:1) which can be represented as ::1 */ - if (ipv6_addr_loopback(&key->dst) || - ipv6_addr_loopback(&key->src)) { + if (ipv6_addr_loopback(&match.key->dst) || + ipv6_addr_loopback(&match.key->src)) { dev_err(&adapter->pdev->dev, "ipv6 addr should not be loopback\n"); - return I40E_ERR_CONFIG; + return -EINVAL; } - if (!ipv6_addr_any(&mask->dst) || !ipv6_addr_any(&mask->src)) + if (!ipv6_addr_any(&match.mask->dst) || + !ipv6_addr_any(&match.mask->src)) field_flags |= IAVF_CLOUD_FIELD_IIP; for (i = 0; i < 4; i++) vf->mask.tcp_spec.dst_ip[i] |= cpu_to_be32(0xffffffff); - memcpy(&vf->data.tcp_spec.dst_ip, &key->dst.s6_addr32, + memcpy(&vf->data.tcp_spec.dst_ip, &match.key->dst.s6_addr32, sizeof(vf->data.tcp_spec.dst_ip)); for (i = 0; i < 4; i++) vf->mask.tcp_spec.src_ip[i] |= cpu_to_be32(0xffffffff); - memcpy(&vf->data.tcp_spec.src_ip, &key->src.s6_addr32, + memcpy(&vf->data.tcp_spec.src_ip, &match.key->src.s6_addr32, sizeof(vf->data.tcp_spec.src_ip)); } - if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) { - struct flow_dissector_key_ports *key = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_PORTS, - f->key); - struct flow_dissector_key_ports *mask = - skb_flow_dissector_target(f->dissector, - FLOW_DISSECTOR_KEY_PORTS, - f->mask); - - if (mask->src) { - if (mask->src == cpu_to_be16(0xffff)) { + if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) { + struct flow_match_ports match; + + flow_rule_match_ports(rule, &match); + if (match.mask->src) { + if (match.mask->src == cpu_to_be16(0xffff)) { field_flags |= IAVF_CLOUD_FIELD_IIP; } else { dev_err(&adapter->pdev->dev, "Bad src port mask %u\n", - be16_to_cpu(mask->src)); - return I40E_ERR_CONFIG; + be16_to_cpu(match.mask->src)); + return -EINVAL; } } - if (mask->dst) { - if (mask->dst == cpu_to_be16(0xffff)) { + if (match.mask->dst) { + if (match.mask->dst == cpu_to_be16(0xffff)) { field_flags |= IAVF_CLOUD_FIELD_IIP; } else { dev_err(&adapter->pdev->dev, "Bad dst port mask %u\n", - be16_to_cpu(mask->dst)); - return I40E_ERR_CONFIG; + be16_to_cpu(match.mask->dst)); + return -EINVAL; } } - if (key->dst) { + if (match.key->dst) { vf->mask.tcp_spec.dst_port |= cpu_to_be16(0xffff); - vf->data.tcp_spec.dst_port = key->dst; + vf->data.tcp_spec.dst_port = match.key->dst; } - if (key->src) { + if (match.key->src) { vf->mask.tcp_spec.src_port |= cpu_to_be16(0xffff); - vf->data.tcp_spec.src_port = key->src; + vf->data.tcp_spec.src_port = match.key->src; } } vf->field_flags = field_flags; @@ -2737,16 +4080,39 @@ static int iavf_handle_tclass(struct iavf_adapter *adapter, u32 tc, } /** + * iavf_find_cf - Find the cloud filter in the list + * @adapter: Board private structure + * @cookie: filter specific cookie + * + * Returns ptr to the filter object or NULL. Must be called while holding the + * cloud_filter_list_lock. + */ +static struct iavf_cloud_filter *iavf_find_cf(struct iavf_adapter *adapter, + unsigned long *cookie) +{ + struct iavf_cloud_filter *filter = NULL; + + if (!cookie) + return NULL; + + list_for_each_entry(filter, &adapter->cloud_filter_list, list) { + if (!memcmp(cookie, &filter->cookie, sizeof(filter->cookie))) + return filter; + } + return NULL; +} + +/** * iavf_configure_clsflower - Add tc flower filters * @adapter: board private structure - * @cls_flower: Pointer to struct tc_cls_flower_offload + * @cls_flower: Pointer to struct flow_cls_offload */ static int iavf_configure_clsflower(struct iavf_adapter *adapter, - struct tc_cls_flower_offload *cls_flower) + struct flow_cls_offload *cls_flower) { int tc = tc_classid_to_hwtc(adapter->netdev, cls_flower->classid); - struct iavf_cloud_filter *filter = NULL; - int err = -EINVAL, count = 50; + struct iavf_cloud_filter *filter; + int err; if (tc < 0) { dev_err(&adapter->pdev->dev, "Invalid traffic class\n"); @@ -2756,26 +4122,29 @@ static int iavf_configure_clsflower(struct iavf_adapter *adapter, filter = kzalloc(sizeof(*filter), GFP_KERNEL); if (!filter) return -ENOMEM; + filter->cookie = cls_flower->cookie; - while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, - &adapter->crit_section)) { - if (--count == 0) - goto err; - udelay(1); - } + netdev_lock(adapter->netdev); - filter->cookie = cls_flower->cookie; + /* bail out here if filter already exists */ + spin_lock_bh(&adapter->cloud_filter_list_lock); + if (iavf_find_cf(adapter, &cls_flower->cookie)) { + dev_err(&adapter->pdev->dev, "Failed to add TC Flower filter, it already exists\n"); + err = -EEXIST; + goto spin_unlock; + } + spin_unlock_bh(&adapter->cloud_filter_list_lock); /* set the mask to all zeroes to begin with */ memset(&filter->f.mask.tcp_spec, 0, sizeof(struct virtchnl_l4_spec)); /* start out with flow type and eth type IPv4 to begin with */ filter->f.flow_type = VIRTCHNL_TCP_V4_FLOW; err = iavf_parse_cls_flower(adapter, cls_flower, filter); - if (err < 0) + if (err) goto err; err = iavf_handle_tclass(adapter, tc, filter); - if (err < 0) + if (err) goto err; /* add filter to the list */ @@ -2784,44 +4153,23 @@ static int iavf_configure_clsflower(struct iavf_adapter *adapter, adapter->num_cloud_filters++; filter->add = true; adapter->aq_required |= IAVF_FLAG_AQ_ADD_CLOUD_FILTER; +spin_unlock: spin_unlock_bh(&adapter->cloud_filter_list_lock); err: if (err) kfree(filter); - clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); + netdev_unlock(adapter->netdev); return err; } -/* iavf_find_cf - Find the cloud filter in the list - * @adapter: Board private structure - * @cookie: filter specific cookie - * - * Returns ptr to the filter object or NULL. Must be called while holding the - * cloud_filter_list_lock. - */ -static struct iavf_cloud_filter *iavf_find_cf(struct iavf_adapter *adapter, - unsigned long *cookie) -{ - struct iavf_cloud_filter *filter = NULL; - - if (!cookie) - return NULL; - - list_for_each_entry(filter, &adapter->cloud_filter_list, list) { - if (!memcmp(cookie, &filter->cookie, sizeof(filter->cookie))) - return filter; - } - return NULL; -} - /** * iavf_delete_clsflower - Remove tc flower filters * @adapter: board private structure - * @cls_flower: Pointer to struct tc_cls_flower_offload + * @cls_flower: Pointer to struct flow_cls_offload */ static int iavf_delete_clsflower(struct iavf_adapter *adapter, - struct tc_cls_flower_offload *cls_flower) + struct flow_cls_offload *cls_flower) { struct iavf_cloud_filter *filter = NULL; int err = 0; @@ -2841,21 +4189,18 @@ static int iavf_delete_clsflower(struct iavf_adapter *adapter, /** * iavf_setup_tc_cls_flower - flower classifier offloads - * @netdev: net device to configure - * @type_data: offload data + * @adapter: pointer to iavf adapter structure + * @cls_flower: pointer to flow_cls_offload struct with flow info */ static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter, - struct tc_cls_flower_offload *cls_flower) + struct flow_cls_offload *cls_flower) { - if (cls_flower->common.chain_index) - return -EOPNOTSUPP; - switch (cls_flower->command) { - case TC_CLSFLOWER_REPLACE: + case FLOW_CLS_REPLACE: return iavf_configure_clsflower(adapter, cls_flower); - case TC_CLSFLOWER_DESTROY: + case FLOW_CLS_DESTROY: return iavf_delete_clsflower(adapter, cls_flower); - case TC_CLSFLOWER_STATS: + case FLOW_CLS_STATS: return -EOPNOTSUPP; default: return -EOPNOTSUPP; @@ -2863,58 +4208,186 @@ static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter, } /** - * iavf_setup_tc_block_cb - block callback for tc - * @type: type of offload - * @type_data: offload data - * @cb_priv: + * iavf_add_cls_u32 - Add U32 classifier offloads + * @adapter: pointer to iavf adapter structure + * @cls_u32: pointer to tc_cls_u32_offload struct with flow info * - * This function is the block callback for traffic classes - **/ -static int iavf_setup_tc_block_cb(enum tc_setup_type type, void *type_data, - void *cb_priv) + * Return: 0 on success or negative errno on failure. + */ +static int iavf_add_cls_u32(struct iavf_adapter *adapter, + struct tc_cls_u32_offload *cls_u32) { - switch (type) { - case TC_SETUP_CLSFLOWER: - return iavf_setup_tc_cls_flower(cb_priv, type_data); + struct netlink_ext_ack *extack = cls_u32->common.extack; + struct virtchnl_fdir_rule *rule_cfg; + struct virtchnl_filter_action *vact; + struct virtchnl_proto_hdrs *hdrs; + struct ethhdr *spec_h, *mask_h; + const struct tc_action *act; + struct iavf_fdir_fltr *fltr; + struct tcf_exts *exts; + unsigned int q_index; + int i, status = 0; + int off_base = 0; + + if (cls_u32->knode.link_handle) { + NL_SET_ERR_MSG_MOD(extack, "Linking not supported"); + return -EOPNOTSUPP; + } + + fltr = kzalloc(sizeof(*fltr), GFP_KERNEL); + if (!fltr) + return -ENOMEM; + + rule_cfg = &fltr->vc_add_msg.rule_cfg; + hdrs = &rule_cfg->proto_hdrs; + hdrs->count = 0; + + /* The parser lib at the PF expects the packet starting with MAC hdr */ + switch (ntohs(cls_u32->common.protocol)) { + case ETH_P_802_3: + break; + case ETH_P_IP: + spec_h = (struct ethhdr *)hdrs->raw.spec; + mask_h = (struct ethhdr *)hdrs->raw.mask; + spec_h->h_proto = htons(ETH_P_IP); + mask_h->h_proto = htons(0xFFFF); + off_base += ETH_HLEN; + break; + default: + NL_SET_ERR_MSG_MOD(extack, "Only 802_3 and ip filter protocols are supported"); + status = -EOPNOTSUPP; + goto free_alloc; + } + + for (i = 0; i < cls_u32->knode.sel->nkeys; i++) { + __be32 val, mask; + int off; + + off = off_base + cls_u32->knode.sel->keys[i].off; + val = cls_u32->knode.sel->keys[i].val; + mask = cls_u32->knode.sel->keys[i].mask; + + if (off >= sizeof(hdrs->raw.spec)) { + NL_SET_ERR_MSG_MOD(extack, "Input exceeds maximum allowed."); + status = -EINVAL; + goto free_alloc; + } + + memcpy(&hdrs->raw.spec[off], &val, sizeof(val)); + memcpy(&hdrs->raw.mask[off], &mask, sizeof(mask)); + hdrs->raw.pkt_len = off + sizeof(val); + } + + /* Only one action is allowed */ + rule_cfg->action_set.count = 1; + vact = &rule_cfg->action_set.actions[0]; + exts = cls_u32->knode.exts; + + tcf_exts_for_each_action(i, act, exts) { + /* FDIR queue */ + if (is_tcf_skbedit_rx_queue_mapping(act)) { + q_index = tcf_skbedit_rx_queue_mapping(act); + if (q_index >= adapter->num_active_queues) { + status = -EINVAL; + goto free_alloc; + } + + vact->type = VIRTCHNL_ACTION_QUEUE; + vact->act_conf.queue.index = q_index; + break; + } + + /* Drop */ + if (is_tcf_gact_shot(act)) { + vact->type = VIRTCHNL_ACTION_DROP; + break; + } + + /* Unsupported action */ + NL_SET_ERR_MSG_MOD(extack, "Unsupported action."); + status = -EOPNOTSUPP; + goto free_alloc; + } + + fltr->vc_add_msg.vsi_id = adapter->vsi.id; + fltr->cls_u32_handle = cls_u32->knode.handle; + return iavf_fdir_add_fltr(adapter, fltr); + +free_alloc: + kfree(fltr); + return status; +} + +/** + * iavf_del_cls_u32 - Delete U32 classifier offloads + * @adapter: pointer to iavf adapter structure + * @cls_u32: pointer to tc_cls_u32_offload struct with flow info + * + * Return: 0 on success or negative errno on failure. + */ +static int iavf_del_cls_u32(struct iavf_adapter *adapter, + struct tc_cls_u32_offload *cls_u32) +{ + return iavf_fdir_del_fltr(adapter, true, cls_u32->knode.handle); +} + +/** + * iavf_setup_tc_cls_u32 - U32 filter offloads + * @adapter: pointer to iavf adapter structure + * @cls_u32: pointer to tc_cls_u32_offload struct with flow info + * + * Return: 0 on success or negative errno on failure. + */ +static int iavf_setup_tc_cls_u32(struct iavf_adapter *adapter, + struct tc_cls_u32_offload *cls_u32) +{ + if (!TC_U32_SUPPORT(adapter) || !FDIR_FLTR_SUPPORT(adapter)) + return -EOPNOTSUPP; + + switch (cls_u32->command) { + case TC_CLSU32_NEW_KNODE: + case TC_CLSU32_REPLACE_KNODE: + return iavf_add_cls_u32(adapter, cls_u32); + case TC_CLSU32_DELETE_KNODE: + return iavf_del_cls_u32(adapter, cls_u32); default: return -EOPNOTSUPP; } } /** - * iavf_setup_tc_block - register callbacks for tc - * @netdev: network interface device structure - * @f: tc offload data + * iavf_setup_tc_block_cb - block callback for tc + * @type: type of offload + * @type_data: offload data + * @cb_priv: * - * This function registers block callbacks for tc - * offloads + * This function is the block callback for traffic classes **/ -static int iavf_setup_tc_block(struct net_device *dev, - struct tc_block_offload *f) +static int iavf_setup_tc_block_cb(enum tc_setup_type type, void *type_data, + void *cb_priv) { - struct iavf_adapter *adapter = netdev_priv(dev); + struct iavf_adapter *adapter = cb_priv; - if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) + if (!tc_cls_can_offload_and_chain0(adapter->netdev, type_data)) return -EOPNOTSUPP; - switch (f->command) { - case TC_BLOCK_BIND: - return tcf_block_cb_register(f->block, iavf_setup_tc_block_cb, - adapter, adapter, f->extack); - case TC_BLOCK_UNBIND: - tcf_block_cb_unregister(f->block, iavf_setup_tc_block_cb, - adapter); - return 0; + switch (type) { + case TC_SETUP_CLSFLOWER: + return iavf_setup_tc_cls_flower(cb_priv, type_data); + case TC_SETUP_CLSU32: + return iavf_setup_tc_cls_u32(cb_priv, type_data); default: return -EOPNOTSUPP; } } +static LIST_HEAD(iavf_block_cb_list); + /** * iavf_setup_tc - configure multiple traffic classes * @netdev: network interface device structure * @type: type of offload - * @type_date: tc offload data + * @type_data: tc offload data * * This function is the callback to ndo_setup_tc in the * netdev_ops. @@ -2924,17 +4397,49 @@ static int iavf_setup_tc_block(struct net_device *dev, static int iavf_setup_tc(struct net_device *netdev, enum tc_setup_type type, void *type_data) { + struct iavf_adapter *adapter = netdev_priv(netdev); + switch (type) { case TC_SETUP_QDISC_MQPRIO: return __iavf_setup_tc(netdev, type_data); case TC_SETUP_BLOCK: - return iavf_setup_tc_block(netdev, type_data); + return flow_block_cb_setup_simple(type_data, + &iavf_block_cb_list, + iavf_setup_tc_block_cb, + adapter, adapter, true); default: return -EOPNOTSUPP; } } /** + * iavf_restore_fdir_filters + * @adapter: board private structure + * + * Restore existing FDIR filters when VF netdev comes back up. + **/ +static void iavf_restore_fdir_filters(struct iavf_adapter *adapter) +{ + struct iavf_fdir_fltr *f; + + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry(f, &adapter->fdir_list_head, list) { + if (f->state == IAVF_FDIR_FLTR_DIS_REQUEST) { + /* Cancel a request, keep filter as active */ + f->state = IAVF_FDIR_FLTR_ACTIVE; + } else if (f->state == IAVF_FDIR_FLTR_DIS_PENDING || + f->state == IAVF_FDIR_FLTR_INACTIVE) { + /* Add filters which are inactive or have a pending + * request to PF to be deleted + */ + f->state = IAVF_FDIR_FLTR_ADD_REQUEST; + adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER; + } + } + spin_unlock_bh(&adapter->fdir_fltr_lock); +} + +/** * iavf_open - Called when a network interface is made active * @netdev: network interface device structure * @@ -2943,7 +4448,7 @@ static int iavf_setup_tc(struct net_device *netdev, enum tc_setup_type type, * The open entry point is called when a network interface is made * active by the system (IFF_UP). At this point all resources needed * for transmit and receive operations are allocated, the interrupt - * handler is registered with the OS, the watchdog timer is started, + * handler is registered with the OS, the watchdog is started, * and the stack is notified that the interface is ready. **/ static int iavf_open(struct net_device *netdev) @@ -2951,18 +4456,20 @@ 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; } - while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, - &adapter->crit_section)) - usleep_range(500, 1000); + if (adapter->state != __IAVF_DOWN) + return -EBUSY; - if (adapter->state != __IAVF_DOWN) { - err = -EBUSY; - goto err_unlock; + if (adapter->state == __IAVF_RUNNING && + !test_bit(__IAVF_VSI_DOWN, adapter->vsi.state)) { + dev_dbg(&adapter->pdev->dev, "VF is already open.\n"); + return 0; } /* allocate transmit descriptors */ @@ -2981,19 +4488,19 @@ static int iavf_open(struct net_device *netdev) goto err_req_irq; spin_lock_bh(&adapter->mac_vlan_list_lock); - iavf_add_filter(adapter, adapter->hw.mac.addr); - spin_unlock_bh(&adapter->mac_vlan_list_lock); + /* Restore filters that were removed with IFF_DOWN */ + iavf_restore_filters(adapter); + iavf_restore_fdir_filters(adapter); + iavf_configure(adapter); iavf_up_complete(adapter); iavf_irq_enable(adapter, true); - clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); - return 0; err_req_irq: @@ -3003,8 +4510,6 @@ err_setup_rx: iavf_free_all_rx_resources(adapter); err_setup_tx: iavf_free_all_tx_resources(adapter); -err_unlock: - clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); return err; } @@ -3023,24 +4528,44 @@ err_unlock: static int iavf_close(struct net_device *netdev) { struct iavf_adapter *adapter = netdev_priv(netdev); + u64 aq_to_restore; int status; + netdev_assert_locked(netdev); + if (adapter->state <= __IAVF_DOWN_PENDING) return 0; - while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, - &adapter->crit_section)) - usleep_range(500, 1000); - set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); - if (CLIENT_ENABLED(adapter)) - adapter->flags |= IAVF_FLAG_CLIENT_NEEDS_CLOSE; + /* We cannot send IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS before + * IAVF_FLAG_AQ_DISABLE_QUEUES because in such case there is rtnl + * deadlock with adminq_task() until iavf_close timeouts. We must send + * IAVF_FLAG_AQ_GET_CONFIG before IAVF_FLAG_AQ_DISABLE_QUEUES to make + * disable queues possible for vf. Give only necessary flags to + * iavf_down and save other to set them right before iavf_close() + * returns, when IAVF_FLAG_AQ_DISABLE_QUEUES will be already sent and + * iavf will be in DOWN state. + */ + aq_to_restore = adapter->aq_required; + adapter->aq_required &= IAVF_FLAG_AQ_GET_CONFIG; + + /* Remove flags which we do not want to send after close or we want to + * send before disable queues. + */ + aq_to_restore &= ~(IAVF_FLAG_AQ_GET_CONFIG | + IAVF_FLAG_AQ_ENABLE_QUEUES | + IAVF_FLAG_AQ_CONFIGURE_QUEUES | + IAVF_FLAG_AQ_ADD_VLAN_FILTER | + IAVF_FLAG_AQ_ADD_MAC_FILTER | + IAVF_FLAG_AQ_ADD_CLOUD_FILTER | + IAVF_FLAG_AQ_ADD_FDIR_FILTER | + IAVF_FLAG_AQ_ADD_ADV_RSS_CFG); iavf_down(adapter); - adapter->state = __IAVF_DOWN_PENDING; + iavf_change_state(adapter, __IAVF_DOWN_PENDING); iavf_free_traffic_irqs(adapter); - clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); + netdev_unlock(netdev); /* We explicitly don't free resources here because the hardware is * still active and can DMA into memory. Resources are cleared in @@ -3055,9 +4580,13 @@ static int iavf_close(struct net_device *netdev) status = wait_event_timeout(adapter->down_waitqueue, adapter->state == __IAVF_DOWN, - msecs_to_jiffies(200)); + msecs_to_jiffies(500)); if (!status) netdev_warn(netdev, "Device resources not yet released\n"); + netdev_lock(netdev); + + adapter->aq_required |= aq_to_restore; + return 0; } @@ -3071,18 +4600,72 @@ static int iavf_close(struct net_device *netdev) static int iavf_change_mtu(struct net_device *netdev, int new_mtu) { struct iavf_adapter *adapter = netdev_priv(netdev); + int ret = 0; - netdev->mtu = new_mtu; - if (CLIENT_ENABLED(adapter)) { - iavf_notify_client_l2_params(&adapter->vsi); - adapter->flags |= IAVF_FLAG_SERVICE_CLIENT_REQUESTED; + netdev_dbg(netdev, "changing MTU from %d to %d\n", + netdev->mtu, new_mtu); + WRITE_ONCE(netdev->mtu, new_mtu); + + if (netif_running(netdev)) { + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); + ret = iavf_wait_for_reset(adapter); + if (ret < 0) + netdev_warn(netdev, "MTU change interrupted waiting for reset"); + else if (ret) + netdev_warn(netdev, "MTU change timed out waiting for reset"); } - adapter->flags |= IAVF_FLAG_RESET_NEEDED; - schedule_work(&adapter->reset_task); - return 0; + return ret; +} + +/** + * iavf_disable_fdir - disable Flow Director and clear existing filters + * @adapter: board private structure + **/ +static void iavf_disable_fdir(struct iavf_adapter *adapter) +{ + struct iavf_fdir_fltr *fdir, *fdirtmp; + bool del_filters = false; + + adapter->flags &= ~IAVF_FLAG_FDIR_ENABLED; + + /* remove all Flow Director filters */ + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry_safe(fdir, fdirtmp, &adapter->fdir_list_head, + list) { + if (fdir->state == IAVF_FDIR_FLTR_ADD_REQUEST || + fdir->state == IAVF_FDIR_FLTR_INACTIVE) { + /* Delete filters not registered in PF */ + list_del(&fdir->list); + iavf_dec_fdir_active_fltr(adapter, fdir); + kfree(fdir); + } else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING || + fdir->state == IAVF_FDIR_FLTR_DIS_REQUEST || + fdir->state == IAVF_FDIR_FLTR_ACTIVE) { + /* Filters registered in PF, schedule their deletion */ + fdir->state = IAVF_FDIR_FLTR_DEL_REQUEST; + del_filters = true; + } else if (fdir->state == IAVF_FDIR_FLTR_DIS_PENDING) { + /* Request to delete filter already sent to PF, change + * state to DEL_PENDING to delete filter after PF's + * response, not set as INACTIVE + */ + fdir->state = IAVF_FDIR_FLTR_DEL_PENDING; + } + } + spin_unlock_bh(&adapter->fdir_fltr_lock); + + if (del_filters) { + adapter->aq_required |= IAVF_FLAG_AQ_DEL_FDIR_FILTER; + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); + } } +#define NETIF_VLAN_OFFLOAD_FEATURES (NETIF_F_HW_VLAN_CTAG_RX | \ + NETIF_F_HW_VLAN_CTAG_TX | \ + NETIF_F_HW_VLAN_STAG_RX | \ + NETIF_F_HW_VLAN_STAG_TX) + /** * iavf_set_features - set the netdev feature flags * @netdev: ptr to the netdev being adjusted @@ -3094,19 +4677,20 @@ static int iavf_set_features(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); - /* Don't allow changing VLAN_RX flag when adapter is not capable - * of VLAN offload - */ - if (!VLAN_ALLOWED(adapter)) { - if ((netdev->features ^ features) & NETIF_F_HW_VLAN_CTAG_RX) - return -EINVAL; - } else if ((netdev->features ^ features) & NETIF_F_HW_VLAN_CTAG_RX) { - if (features & NETIF_F_HW_VLAN_CTAG_RX) - adapter->aq_required |= - IAVF_FLAG_AQ_ENABLE_VLAN_STRIPPING; + /* trigger update on any VLAN feature change */ + if ((netdev->features & NETIF_VLAN_OFFLOAD_FEATURES) ^ + (features & NETIF_VLAN_OFFLOAD_FEATURES)) + iavf_set_vlan_offload_features(adapter, netdev->features, + features); + if (CRC_OFFLOAD_ALLOWED(adapter) && + ((netdev->features & NETIF_F_RXFCS) ^ (features & NETIF_F_RXFCS))) + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); + + if ((netdev->features & NETIF_F_NTUPLE) ^ (features & NETIF_F_NTUPLE)) { + if (features & NETIF_F_NTUPLE) + adapter->flags |= IAVF_FLAG_FDIR_ENABLED; else - adapter->aq_required |= - IAVF_FLAG_AQ_DISABLE_VLAN_STRIPPING; + iavf_disable_fdir(adapter); } return 0; @@ -3138,12 +4722,12 @@ static netdev_features_t iavf_features_check(struct sk_buff *skb, features &= ~NETIF_F_GSO_MASK; /* MACLEN can support at most 63 words */ - len = skb_network_header(skb) - skb->data; + len = skb_network_offset(skb); if (len & ~(63 * 2)) goto out_err; /* IPLEN and EIPLEN can support at most 127 dwords */ - len = skb_transport_header(skb) - skb_network_header(skb); + len = skb_network_header_len(skb); if (len & ~(127 * 4)) goto out_err; @@ -3161,7 +4745,7 @@ static netdev_features_t iavf_features_check(struct sk_buff *skb, } /* No need to validate L4LEN as TCP is the only protocol with a - * a flexible value and we support all possible values supported + * flexible value and we support all possible values supported * by TCP, which is at most 15 dwords */ @@ -3171,6 +4755,280 @@ out_err: } /** + * iavf_get_netdev_vlan_hw_features - get NETDEV VLAN features that can toggle on/off + * @adapter: board private structure + * + * Depending on whether VIRTHCNL_VF_OFFLOAD_VLAN or VIRTCHNL_VF_OFFLOAD_VLAN_V2 + * were negotiated determine the VLAN features that can be toggled on and off. + **/ +static netdev_features_t +iavf_get_netdev_vlan_hw_features(struct iavf_adapter *adapter) +{ + netdev_features_t hw_features = 0; + + if (!adapter->vf_res || !adapter->vf_res->vf_cap_flags) + return hw_features; + + /* Enable VLAN features if supported */ + if (VLAN_ALLOWED(adapter)) { + hw_features |= (NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX); + } else if (VLAN_V2_ALLOWED(adapter)) { + struct virtchnl_vlan_caps *vlan_v2_caps = + &adapter->vlan_v2_caps; + struct virtchnl_vlan_supported_caps *stripping_support = + &vlan_v2_caps->offloads.stripping_support; + struct virtchnl_vlan_supported_caps *insertion_support = + &vlan_v2_caps->offloads.insertion_support; + + if (stripping_support->outer != VIRTCHNL_VLAN_UNSUPPORTED && + stripping_support->outer & VIRTCHNL_VLAN_TOGGLE) { + if (stripping_support->outer & + VIRTCHNL_VLAN_ETHERTYPE_8100) + hw_features |= NETIF_F_HW_VLAN_CTAG_RX; + if (stripping_support->outer & + VIRTCHNL_VLAN_ETHERTYPE_88A8) + hw_features |= NETIF_F_HW_VLAN_STAG_RX; + } else if (stripping_support->inner != + VIRTCHNL_VLAN_UNSUPPORTED && + stripping_support->inner & VIRTCHNL_VLAN_TOGGLE) { + if (stripping_support->inner & + VIRTCHNL_VLAN_ETHERTYPE_8100) + hw_features |= NETIF_F_HW_VLAN_CTAG_RX; + } + + if (insertion_support->outer != VIRTCHNL_VLAN_UNSUPPORTED && + insertion_support->outer & VIRTCHNL_VLAN_TOGGLE) { + if (insertion_support->outer & + VIRTCHNL_VLAN_ETHERTYPE_8100) + hw_features |= NETIF_F_HW_VLAN_CTAG_TX; + if (insertion_support->outer & + VIRTCHNL_VLAN_ETHERTYPE_88A8) + hw_features |= NETIF_F_HW_VLAN_STAG_TX; + } else if (insertion_support->inner && + insertion_support->inner & VIRTCHNL_VLAN_TOGGLE) { + if (insertion_support->inner & + VIRTCHNL_VLAN_ETHERTYPE_8100) + hw_features |= NETIF_F_HW_VLAN_CTAG_TX; + } + } + + if (CRC_OFFLOAD_ALLOWED(adapter)) + hw_features |= NETIF_F_RXFCS; + + return hw_features; +} + +/** + * iavf_get_netdev_vlan_features - get the enabled NETDEV VLAN fetures + * @adapter: board private structure + * + * Depending on whether VIRTHCNL_VF_OFFLOAD_VLAN or VIRTCHNL_VF_OFFLOAD_VLAN_V2 + * were negotiated determine the VLAN features that are enabled by default. + **/ +static netdev_features_t +iavf_get_netdev_vlan_features(struct iavf_adapter *adapter) +{ + netdev_features_t features = 0; + + if (!adapter->vf_res || !adapter->vf_res->vf_cap_flags) + return features; + + if (VLAN_ALLOWED(adapter)) { + features |= NETIF_F_HW_VLAN_CTAG_FILTER | + NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_TX; + } else if (VLAN_V2_ALLOWED(adapter)) { + struct virtchnl_vlan_caps *vlan_v2_caps = + &adapter->vlan_v2_caps; + struct virtchnl_vlan_supported_caps *filtering_support = + &vlan_v2_caps->filtering.filtering_support; + struct virtchnl_vlan_supported_caps *stripping_support = + &vlan_v2_caps->offloads.stripping_support; + struct virtchnl_vlan_supported_caps *insertion_support = + &vlan_v2_caps->offloads.insertion_support; + u32 ethertype_init; + + /* give priority to outer stripping and don't support both outer + * and inner stripping + */ + ethertype_init = vlan_v2_caps->offloads.ethertype_init; + if (stripping_support->outer != VIRTCHNL_VLAN_UNSUPPORTED) { + if (stripping_support->outer & + VIRTCHNL_VLAN_ETHERTYPE_8100 && + ethertype_init & VIRTCHNL_VLAN_ETHERTYPE_8100) + features |= NETIF_F_HW_VLAN_CTAG_RX; + else if (stripping_support->outer & + VIRTCHNL_VLAN_ETHERTYPE_88A8 && + ethertype_init & VIRTCHNL_VLAN_ETHERTYPE_88A8) + features |= NETIF_F_HW_VLAN_STAG_RX; + } else if (stripping_support->inner != + VIRTCHNL_VLAN_UNSUPPORTED) { + if (stripping_support->inner & + VIRTCHNL_VLAN_ETHERTYPE_8100 && + ethertype_init & VIRTCHNL_VLAN_ETHERTYPE_8100) + features |= NETIF_F_HW_VLAN_CTAG_RX; + } + + /* give priority to outer insertion and don't support both outer + * and inner insertion + */ + if (insertion_support->outer != VIRTCHNL_VLAN_UNSUPPORTED) { + if (insertion_support->outer & + VIRTCHNL_VLAN_ETHERTYPE_8100 && + ethertype_init & VIRTCHNL_VLAN_ETHERTYPE_8100) + features |= NETIF_F_HW_VLAN_CTAG_TX; + else if (insertion_support->outer & + VIRTCHNL_VLAN_ETHERTYPE_88A8 && + ethertype_init & VIRTCHNL_VLAN_ETHERTYPE_88A8) + features |= NETIF_F_HW_VLAN_STAG_TX; + } else if (insertion_support->inner != + VIRTCHNL_VLAN_UNSUPPORTED) { + if (insertion_support->inner & + VIRTCHNL_VLAN_ETHERTYPE_8100 && + ethertype_init & VIRTCHNL_VLAN_ETHERTYPE_8100) + features |= NETIF_F_HW_VLAN_CTAG_TX; + } + + /* give priority to outer filtering and don't bother if both + * outer and inner filtering are enabled + */ + ethertype_init = vlan_v2_caps->filtering.ethertype_init; + if (filtering_support->outer != VIRTCHNL_VLAN_UNSUPPORTED) { + if (filtering_support->outer & + VIRTCHNL_VLAN_ETHERTYPE_8100 && + ethertype_init & VIRTCHNL_VLAN_ETHERTYPE_8100) + features |= NETIF_F_HW_VLAN_CTAG_FILTER; + if (filtering_support->outer & + VIRTCHNL_VLAN_ETHERTYPE_88A8 && + ethertype_init & VIRTCHNL_VLAN_ETHERTYPE_88A8) + features |= NETIF_F_HW_VLAN_STAG_FILTER; + } else if (filtering_support->inner != + VIRTCHNL_VLAN_UNSUPPORTED) { + if (filtering_support->inner & + VIRTCHNL_VLAN_ETHERTYPE_8100 && + ethertype_init & VIRTCHNL_VLAN_ETHERTYPE_8100) + features |= NETIF_F_HW_VLAN_CTAG_FILTER; + if (filtering_support->inner & + VIRTCHNL_VLAN_ETHERTYPE_88A8 && + ethertype_init & VIRTCHNL_VLAN_ETHERTYPE_88A8) + features |= NETIF_F_HW_VLAN_STAG_FILTER; + } + } + + return features; +} + +#define IAVF_NETDEV_VLAN_FEATURE_ALLOWED(requested, allowed, feature_bit) \ + (!(((requested) & (feature_bit)) && \ + !((allowed) & (feature_bit)))) + +/** + * iavf_fix_netdev_vlan_features - fix NETDEV VLAN features based on support + * @adapter: board private structure + * @requested_features: stack requested NETDEV features + **/ +static netdev_features_t +iavf_fix_netdev_vlan_features(struct iavf_adapter *adapter, + netdev_features_t requested_features) +{ + netdev_features_t allowed_features; + + allowed_features = iavf_get_netdev_vlan_hw_features(adapter) | + iavf_get_netdev_vlan_features(adapter); + + if (!IAVF_NETDEV_VLAN_FEATURE_ALLOWED(requested_features, + allowed_features, + NETIF_F_HW_VLAN_CTAG_TX)) + requested_features &= ~NETIF_F_HW_VLAN_CTAG_TX; + + if (!IAVF_NETDEV_VLAN_FEATURE_ALLOWED(requested_features, + allowed_features, + NETIF_F_HW_VLAN_CTAG_RX)) + requested_features &= ~NETIF_F_HW_VLAN_CTAG_RX; + + if (!IAVF_NETDEV_VLAN_FEATURE_ALLOWED(requested_features, + allowed_features, + NETIF_F_HW_VLAN_STAG_TX)) + requested_features &= ~NETIF_F_HW_VLAN_STAG_TX; + if (!IAVF_NETDEV_VLAN_FEATURE_ALLOWED(requested_features, + allowed_features, + NETIF_F_HW_VLAN_STAG_RX)) + requested_features &= ~NETIF_F_HW_VLAN_STAG_RX; + + if (!IAVF_NETDEV_VLAN_FEATURE_ALLOWED(requested_features, + allowed_features, + NETIF_F_HW_VLAN_CTAG_FILTER)) + requested_features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; + + if (!IAVF_NETDEV_VLAN_FEATURE_ALLOWED(requested_features, + allowed_features, + NETIF_F_HW_VLAN_STAG_FILTER)) + requested_features &= ~NETIF_F_HW_VLAN_STAG_FILTER; + + if ((requested_features & + (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_TX)) && + (requested_features & + (NETIF_F_HW_VLAN_STAG_RX | NETIF_F_HW_VLAN_STAG_TX)) && + adapter->vlan_v2_caps.offloads.ethertype_match == + VIRTCHNL_ETHERTYPE_STRIPPING_MATCHES_INSERTION) { + netdev_warn(adapter->netdev, "cannot support CTAG and STAG VLAN stripping and/or insertion simultaneously since CTAG and STAG offloads are mutually exclusive, clearing STAG offload settings\n"); + requested_features &= ~(NETIF_F_HW_VLAN_STAG_RX | + NETIF_F_HW_VLAN_STAG_TX); + } + + return requested_features; +} + +/** + * iavf_fix_strip_features - fix NETDEV CRC and VLAN strip features + * @adapter: board private structure + * @requested_features: stack requested NETDEV features + * + * Returns fixed-up features bits + **/ +static netdev_features_t +iavf_fix_strip_features(struct iavf_adapter *adapter, + netdev_features_t requested_features) +{ + struct net_device *netdev = adapter->netdev; + bool crc_offload_req, is_vlan_strip; + netdev_features_t vlan_strip; + int num_non_zero_vlan; + + crc_offload_req = CRC_OFFLOAD_ALLOWED(adapter) && + (requested_features & NETIF_F_RXFCS); + num_non_zero_vlan = iavf_get_num_vlans_added(adapter); + vlan_strip = (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX); + is_vlan_strip = requested_features & vlan_strip; + + if (!crc_offload_req) + return requested_features; + + if (!num_non_zero_vlan && (netdev->features & vlan_strip) && + !(netdev->features & NETIF_F_RXFCS) && is_vlan_strip) { + requested_features &= ~vlan_strip; + netdev_info(netdev, "Disabling VLAN stripping as FCS/CRC stripping is also disabled and there is no VLAN configured\n"); + return requested_features; + } + + if ((netdev->features & NETIF_F_RXFCS) && is_vlan_strip) { + requested_features &= ~vlan_strip; + if (!(netdev->features & vlan_strip)) + netdev_info(netdev, "To enable VLAN stripping, first need to enable FCS/CRC stripping"); + + return requested_features; + } + + if (num_non_zero_vlan && is_vlan_strip && + !(netdev->features & NETIF_F_RXFCS)) { + requested_features &= ~NETIF_F_RXFCS; + netdev_info(netdev, "To disable FCS/CRC stripping, first need to disable VLAN stripping"); + } + + return requested_features; +} + +/** * iavf_fix_features - fix up the netdev feature bits * @netdev: our net device * @features: desired feature bits @@ -3182,14 +5040,123 @@ static netdev_features_t iavf_fix_features(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); - if (!(adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN)) - features &= ~(NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_VLAN_CTAG_FILTER); + features = iavf_fix_netdev_vlan_features(adapter, features); - return features; + if (!FDIR_FLTR_SUPPORT(adapter)) + features &= ~NETIF_F_NTUPLE; + + 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, + struct netlink_ext_ack *extack) +{ + struct iavf_adapter *adapter = netdev_priv(binding->netdev); + u64 vf_max; + + if (shaper->handle.scope == NET_SHAPER_SCOPE_QUEUE) { + vf_max = adapter->qos_caps->cap[0].shaper.peak; + if (vf_max && shaper->bw_max > vf_max) { + NL_SET_ERR_MSG_FMT(extack, "Max rate (%llu) of queue %d can't exceed max TX rate of VF (%llu kbps)", + shaper->bw_max, shaper->handle.id, + vf_max); + return -EINVAL; + } + } + return 0; +} + +static int +iavf_shaper_set(struct net_shaper_binding *binding, + const struct net_shaper *shaper, + struct netlink_ext_ack *extack) +{ + struct iavf_adapter *adapter = netdev_priv(binding->netdev); + const struct net_shaper_handle *handle = &shaper->handle; + struct iavf_ring *tx_ring; + int ret; + + netdev_assert_locked(adapter->netdev); + + if (handle->id >= adapter->num_active_queues) + return 0; + + ret = iavf_verify_shaper(binding, shaper, extack); + if (ret) + return ret; + + tx_ring = &adapter->tx_rings[handle->id]; + + tx_ring->q_shaper.bw_min = div_u64(shaper->bw_min, 1000); + tx_ring->q_shaper.bw_max = div_u64(shaper->bw_max, 1000); + tx_ring->q_shaper_update = true; + + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW; + + return 0; +} + +static int iavf_shaper_del(struct net_shaper_binding *binding, + const struct net_shaper_handle *handle, + struct netlink_ext_ack *extack) +{ + struct iavf_adapter *adapter = netdev_priv(binding->netdev); + struct iavf_ring *tx_ring; + + netdev_assert_locked(adapter->netdev); + + if (handle->id >= adapter->num_active_queues) + return 0; + + tx_ring = &adapter->tx_rings[handle->id]; + tx_ring->q_shaper.bw_min = 0; + tx_ring->q_shaper.bw_max = 0; + tx_ring->q_shaper_update = true; + + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW; + + return 0; +} + +static void iavf_shaper_cap(struct net_shaper_binding *binding, + enum net_shaper_scope scope, + unsigned long *flags) +{ + if (scope != NET_SHAPER_SCOPE_QUEUE) + return; + + *flags = BIT(NET_SHAPER_A_CAPS_SUPPORT_BW_MIN) | + BIT(NET_SHAPER_A_CAPS_SUPPORT_BW_MAX) | + BIT(NET_SHAPER_A_CAPS_SUPPORT_METRIC_BPS); +} + +static const struct net_shaper_ops iavf_shaper_ops = { + .set = iavf_shaper_set, + .delete = iavf_shaper_del, + .capabilities = iavf_shaper_cap, +}; + static const struct net_device_ops iavf_netdev_ops = { .ndo_open = iavf_open, .ndo_stop = iavf_close, @@ -3205,6 +5172,9 @@ static const struct net_device_ops iavf_netdev_ops = { .ndo_fix_features = iavf_fix_features, .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, }; /** @@ -3218,13 +5188,13 @@ static int iavf_check_reset_complete(struct iavf_hw *hw) u32 rstat; int i; - for (i = 0; i < 100; i++) { + for (i = 0; i < IAVF_RESET_WAIT_COMPLETE_COUNT; i++) { rstat = rd32(hw, IAVF_VFGEN_RSTAT) & IAVF_VFGEN_RSTAT_VFR_STATE_MASK; if ((rstat == VIRTCHNL_VFR_VFACTIVE) || (rstat == VIRTCHNL_VFR_COMPLETED)) return 0; - usleep_range(10, 20); + msleep(IAVF_RESET_WAIT_MS); } return -EBUSY; } @@ -3239,39 +5209,11 @@ static int iavf_check_reset_complete(struct iavf_hw *hw) int iavf_process_config(struct iavf_adapter *adapter) { struct virtchnl_vf_resource *vfres = adapter->vf_res; - int i, num_req_queues = adapter->num_req_queues; + netdev_features_t hw_vlan_features, vlan_features; struct net_device *netdev = adapter->netdev; - struct iavf_vsi *vsi = &adapter->vsi; netdev_features_t hw_enc_features; netdev_features_t hw_features; - /* got VF config message back from PF, now we can parse it */ - for (i = 0; i < vfres->num_vsis; i++) { - if (vfres->vsi_res[i].vsi_type == VIRTCHNL_VSI_SRIOV) - adapter->vsi_res = &vfres->vsi_res[i]; - } - if (!adapter->vsi_res) { - dev_err(&adapter->pdev->dev, "No LAN VSI found\n"); - return -ENODEV; - } - - if (num_req_queues && - num_req_queues != adapter->vsi_res->num_queue_pairs) { - /* Problem. The PF gave us fewer queues than what we had - * negotiated in our request. Need a reset to see if we can't - * get back to a working state. - */ - dev_err(&adapter->pdev->dev, - "Requested %d queues, but PF only gave us %d.\n", - num_req_queues, - adapter->vsi_res->num_queue_pairs); - adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; - adapter->num_req_queues = adapter->vsi_res->num_queue_pairs; - iavf_schedule_reset(adapter); - return -ENODEV; - } - adapter->num_req_queues = 0; - hw_enc_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | @@ -3315,21 +5257,31 @@ int iavf_process_config(struct iavf_adapter *adapter) */ hw_features = hw_enc_features; - /* Enable VLAN features if supported */ - if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) - hw_features |= (NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_CTAG_RX); - /* Enable cloud filter if ADQ is supported */ - if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) + /* get HW VLAN features that can be toggled */ + hw_vlan_features = iavf_get_netdev_vlan_hw_features(adapter); + + /* Enable HW TC offload if ADQ or tc U32 is supported */ + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ || + TC_U32_SUPPORT(adapter)) hw_features |= NETIF_F_HW_TC; - netdev->hw_features |= hw_features; + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_USO) + hw_features |= NETIF_F_GSO_UDP_L4; + + netdev->hw_features |= hw_features | hw_vlan_features; + vlan_features = iavf_get_netdev_vlan_features(adapter); - netdev->features |= hw_features; + netdev->features |= hw_features | vlan_features; if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + if (FDIR_FLTR_SUPPORT(adapter)) { + netdev->hw_features |= NETIF_F_NTUPLE; + netdev->features |= NETIF_F_NTUPLE; + adapter->flags |= IAVF_FLAG_FDIR_ENABLED; + } + netdev->priv_flags |= IFF_UNICAST_FLT; /* Do not turn on offloads when they are requested to be turned off. @@ -3350,278 +5302,10 @@ int iavf_process_config(struct iavf_adapter *adapter) netdev->features &= ~NETIF_F_GSO; } - adapter->vsi.id = adapter->vsi_res->vsi_id; - - adapter->vsi.back = adapter; - adapter->vsi.base_vector = 1; - adapter->vsi.work_limit = IAVF_DEFAULT_IRQ_WORK; - vsi->netdev = adapter->netdev; - vsi->qs_handle = adapter->vsi_res->qset_handle; - if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RSS_PF) { - adapter->rss_key_size = vfres->rss_key_size; - adapter->rss_lut_size = vfres->rss_lut_size; - } else { - adapter->rss_key_size = IAVF_HKEY_ARRAY_SIZE; - adapter->rss_lut_size = IAVF_HLUT_ARRAY_SIZE; - } - return 0; } /** - * iavf_init_task - worker thread to perform delayed initialization - * @work: pointer to work_struct containing our data - * - * This task completes the work that was begun in probe. Due to the nature - * of VF-PF communications, we may need to wait tens of milliseconds to get - * responses back from the PF. Rather than busy-wait in probe and bog down the - * whole system, we'll do it in a task so we can sleep. - * This task only runs during driver init. Once we've established - * communications with the PF driver and set up our netdev, the watchdog - * takes over. - **/ -static void iavf_init_task(struct work_struct *work) -{ - struct iavf_adapter *adapter = container_of(work, - struct iavf_adapter, - init_task.work); - struct net_device *netdev = adapter->netdev; - struct iavf_hw *hw = &adapter->hw; - struct pci_dev *pdev = adapter->pdev; - int err, bufsz; - - switch (adapter->state) { - case __IAVF_STARTUP: - /* driver loaded, probe complete */ - adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; - adapter->flags &= ~IAVF_FLAG_RESET_PENDING; - err = iavf_set_mac_type(hw); - if (err) { - dev_err(&pdev->dev, "Failed to set MAC type (%d)\n", - err); - goto err; - } - err = iavf_check_reset_complete(hw); - if (err) { - dev_info(&pdev->dev, "Device is still in reset (%d), retrying\n", - err); - goto err; - } - hw->aq.num_arq_entries = IAVF_AQ_LEN; - hw->aq.num_asq_entries = IAVF_AQ_LEN; - hw->aq.arq_buf_size = IAVF_MAX_AQ_BUF_SIZE; - hw->aq.asq_buf_size = IAVF_MAX_AQ_BUF_SIZE; - - err = iavf_init_adminq(hw); - if (err) { - dev_err(&pdev->dev, "Failed to init Admin Queue (%d)\n", - err); - goto err; - } - err = iavf_send_api_ver(adapter); - if (err) { - dev_err(&pdev->dev, "Unable to send to PF (%d)\n", err); - iavf_shutdown_adminq(hw); - goto err; - } - adapter->state = __IAVF_INIT_VERSION_CHECK; - goto restart; - case __IAVF_INIT_VERSION_CHECK: - if (!iavf_asq_done(hw)) { - dev_err(&pdev->dev, "Admin queue command never completed\n"); - iavf_shutdown_adminq(hw); - adapter->state = __IAVF_STARTUP; - goto err; - } - - /* aq msg sent, awaiting reply */ - err = iavf_verify_api_ver(adapter); - if (err) { - if (err == I40E_ERR_ADMIN_QUEUE_NO_WORK) - err = iavf_send_api_ver(adapter); - else - dev_err(&pdev->dev, "Unsupported PF API version %d.%d, expected %d.%d\n", - adapter->pf_version.major, - adapter->pf_version.minor, - VIRTCHNL_VERSION_MAJOR, - VIRTCHNL_VERSION_MINOR); - goto err; - } - err = iavf_send_vf_config_msg(adapter); - if (err) { - dev_err(&pdev->dev, "Unable to send config request (%d)\n", - err); - goto err; - } - adapter->state = __IAVF_INIT_GET_RESOURCES; - goto restart; - case __IAVF_INIT_GET_RESOURCES: - /* aq msg sent, awaiting reply */ - if (!adapter->vf_res) { - bufsz = sizeof(struct virtchnl_vf_resource) + - (IAVF_MAX_VF_VSI * - sizeof(struct virtchnl_vsi_resource)); - adapter->vf_res = kzalloc(bufsz, GFP_KERNEL); - if (!adapter->vf_res) - goto err; - } - err = iavf_get_vf_config(adapter); - if (err == I40E_ERR_ADMIN_QUEUE_NO_WORK) { - err = iavf_send_vf_config_msg(adapter); - goto err; - } else if (err == I40E_ERR_PARAM) { - /* We only get ERR_PARAM if the device is in a very bad - * state or if we've been disabled for previous bad - * behavior. Either way, we're done now. - */ - iavf_shutdown_adminq(hw); - dev_err(&pdev->dev, "Unable to get VF config due to PF error condition, not retrying\n"); - return; - } - if (err) { - dev_err(&pdev->dev, "Unable to get VF config (%d)\n", - err); - goto err_alloc; - } - adapter->state = __IAVF_INIT_SW; - break; - default: - goto err_alloc; - } - - if (iavf_process_config(adapter)) - goto err_alloc; - adapter->current_op = VIRTCHNL_OP_UNKNOWN; - - adapter->flags |= IAVF_FLAG_RX_CSUM_ENABLED; - - netdev->netdev_ops = &iavf_netdev_ops; - iavf_set_ethtool_ops(netdev); - netdev->watchdog_timeo = 5 * HZ; - - /* MTU range: 68 - 9710 */ - netdev->min_mtu = ETH_MIN_MTU; - netdev->max_mtu = IAVF_MAX_RXBUFFER - IAVF_PACKET_HDR_PAD; - - if (!is_valid_ether_addr(adapter->hw.mac.addr)) { - dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n", - adapter->hw.mac.addr); - eth_hw_addr_random(netdev); - ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr); - } else { - adapter->flags |= IAVF_FLAG_ADDR_SET_BY_PF; - ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr); - ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); - } - - timer_setup(&adapter->watchdog_timer, iavf_watchdog_timer, 0); - mod_timer(&adapter->watchdog_timer, jiffies + 1); - - adapter->tx_desc_count = IAVF_DEFAULT_TXD; - adapter->rx_desc_count = IAVF_DEFAULT_RXD; - err = iavf_init_interrupt_scheme(adapter); - if (err) - goto err_sw_init; - iavf_map_rings_to_vectors(adapter); - if (adapter->vf_res->vf_cap_flags & - VIRTCHNL_VF_OFFLOAD_WB_ON_ITR) - adapter->flags |= IAVF_FLAG_WB_ON_ITR_CAPABLE; - - err = iavf_request_misc_irq(adapter); - if (err) - goto err_sw_init; - - netif_carrier_off(netdev); - adapter->link_up = false; - - if (!adapter->netdev_registered) { - err = register_netdev(netdev); - if (err) - goto err_register; - } - - adapter->netdev_registered = true; - - netif_tx_stop_all_queues(netdev); - if (CLIENT_ALLOWED(adapter)) { - err = iavf_lan_add_device(adapter); - if (err) - dev_info(&pdev->dev, "Failed to add VF to client API service list: %d\n", - err); - } - - dev_info(&pdev->dev, "MAC address: %pM\n", adapter->hw.mac.addr); - if (netdev->features & NETIF_F_GRO) - dev_info(&pdev->dev, "GRO is enabled\n"); - - adapter->state = __IAVF_DOWN; - set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); - iavf_misc_irq_enable(adapter); - wake_up(&adapter->down_waitqueue); - - adapter->rss_key = kzalloc(adapter->rss_key_size, GFP_KERNEL); - adapter->rss_lut = kzalloc(adapter->rss_lut_size, GFP_KERNEL); - if (!adapter->rss_key || !adapter->rss_lut) - goto err_mem; - - if (RSS_AQ(adapter)) { - adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_RSS; - mod_timer_pending(&adapter->watchdog_timer, jiffies + 1); - } else { - iavf_init_rss(adapter); - } - return; -restart: - schedule_delayed_work(&adapter->init_task, msecs_to_jiffies(30)); - return; -err_mem: - iavf_free_rss(adapter); -err_register: - iavf_free_misc_irq(adapter); -err_sw_init: - iavf_reset_interrupt_capability(adapter); -err_alloc: - kfree(adapter->vf_res); - adapter->vf_res = NULL; -err: - /* Things went into the weeds, so try again later */ - if (++adapter->aq_wait_count > IAVF_AQ_MAX_ERR) { - dev_err(&pdev->dev, "Failed to communicate with PF; waiting before retry\n"); - adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED; - iavf_shutdown_adminq(hw); - adapter->state = __IAVF_STARTUP; - schedule_delayed_work(&adapter->init_task, HZ * 5); - return; - } - schedule_delayed_work(&adapter->init_task, HZ); -} - -/** - * iavf_shutdown - Shutdown the device in preparation for a reboot - * @pdev: pci device structure - **/ -static void iavf_shutdown(struct pci_dev *pdev) -{ - struct net_device *netdev = pci_get_drvdata(pdev); - struct iavf_adapter *adapter = netdev_priv(netdev); - - netif_device_detach(netdev); - - if (netif_running(netdev)) - iavf_close(netdev); - - /* Prevent the watchdog from running. */ - adapter->state = __IAVF_REMOVE; - adapter->aq_required = 0; - -#ifdef CONFIG_PM - pci_save_state(pdev); - -#endif - pci_disable_device(pdev); -} - -/** * iavf_probe - Device Initialization Routine * @pdev: PCI device information struct * @ent: entry in iavf_pci_tbl @@ -3637,7 +5321,7 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct net_device *netdev; struct iavf_adapter *adapter = NULL; struct iavf_hw *hw = NULL; - int err; + int err, len; err = pci_enable_device(pdev); if (err) @@ -3645,12 +5329,9 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); if (err) { - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "DMA configuration failed: 0x%x\n", err); - goto err_dma; - } + dev_err(&pdev->dev, + "DMA configuration failed: 0x%x\n", err); + goto err_dma; } err = pci_request_regions(pdev, iavf_driver_name); @@ -3660,8 +5341,6 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_pci_reg; } - pci_enable_pcie_error_reporting(pdev); - pci_set_master(pdev); netdev = alloc_etherdev_mq(sizeof(struct iavf_adapter), @@ -3671,6 +5350,7 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_alloc_etherdev; } + netif_set_affinity_auto(netdev); SET_NETDEV_DEV(netdev, &pdev->dev); pci_set_drvdata(pdev, netdev); @@ -3682,8 +5362,15 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw = &adapter->hw; hw->back = adapter; + adapter->wq = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, + iavf_driver_name); + if (!adapter->wq) { + err = -ENOMEM; + goto err_alloc_wq; + } + adapter->msg_enable = BIT(DEFAULT_DEBUG_LEVEL_SHIFT) - 1; - adapter->state = __IAVF_STARTUP; + iavf_change_state(adapter, __IAVF_STARTUP); /* Call save state here because it relies on the adapter struct. */ pci_save_state(pdev); @@ -3703,33 +5390,56 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->bus.func = PCI_FUNC(pdev->devfn); hw->bus.bus_id = pdev->bus->number; - /* set up the locks for the AQ, do this only once in probe - * and destroy them only once in remove - */ + len = struct_size(adapter->qos_caps, cap, IAVF_MAX_QOS_TC_NUM); + adapter->qos_caps = kzalloc(len, GFP_KERNEL); + if (!adapter->qos_caps) { + err = -ENOMEM; + goto err_alloc_qos_cap; + } + mutex_init(&hw->aq.asq_mutex); mutex_init(&hw->aq.arq_mutex); spin_lock_init(&adapter->mac_vlan_list_lock); spin_lock_init(&adapter->cloud_filter_list_lock); + spin_lock_init(&adapter->fdir_fltr_lock); + spin_lock_init(&adapter->adv_rss_lock); + spin_lock_init(&adapter->current_netdev_promisc_flags_lock); INIT_LIST_HEAD(&adapter->mac_filter_list); INIT_LIST_HEAD(&adapter->vlan_filter_list); INIT_LIST_HEAD(&adapter->cloud_filter_list); + INIT_LIST_HEAD(&adapter->fdir_list_head); + INIT_LIST_HEAD(&adapter->adv_rss_list_head); INIT_WORK(&adapter->reset_task, iavf_reset_task); INIT_WORK(&adapter->adminq_task, iavf_adminq_task); - INIT_WORK(&adapter->watchdog_task, iavf_watchdog_task); - INIT_DELAYED_WORK(&adapter->client_task, iavf_client_task); - INIT_DELAYED_WORK(&adapter->init_task, iavf_init_task); - schedule_delayed_work(&adapter->init_task, - msecs_to_jiffies(5 * (pdev->devfn & 0x07))); + INIT_WORK(&adapter->finish_config, iavf_finish_config); + INIT_DELAYED_WORK(&adapter->watchdog_task, iavf_watchdog_task); /* Setup the wait queue for indicating transition to down status */ init_waitqueue_head(&adapter->down_waitqueue); + /* Setup the wait queue for indicating transition to running state */ + init_waitqueue_head(&adapter->reset_waitqueue); + + /* 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. */ return 0; +err_alloc_qos_cap: + iounmap(hw->hw_addr); err_ioremap: + destroy_workqueue(adapter->wq); +err_alloc_wq: free_netdev(netdev); err_alloc_etherdev: pci_release_regions(pdev); @@ -3739,69 +5449,52 @@ err_dma: return err; } -#ifdef CONFIG_PM /** * iavf_suspend - Power management suspend routine - * @pdev: PCI device information struct - * @state: unused + * @dev_d: device info pointer * * Called when the system (VM) is entering sleep/suspend. **/ -static int iavf_suspend(struct pci_dev *pdev, pm_message_t state) +static int iavf_suspend(struct device *dev_d) { - struct net_device *netdev = pci_get_drvdata(pdev); + struct net_device *netdev = dev_get_drvdata(dev_d); struct iavf_adapter *adapter = netdev_priv(netdev); - int retval = 0; + bool running; netif_device_detach(netdev); - while (test_and_set_bit(__IAVF_IN_CRITICAL_TASK, - &adapter->crit_section)) - usleep_range(500, 1000); - - if (netif_running(netdev)) { + running = netif_running(netdev); + if (running) rtnl_lock(); + netdev_lock(netdev); + + if (running) iavf_down(adapter); - rtnl_unlock(); - } + iavf_free_misc_irq(adapter); iavf_reset_interrupt_capability(adapter); - clear_bit(__IAVF_IN_CRITICAL_TASK, &adapter->crit_section); - - retval = pci_save_state(pdev); - if (retval) - return retval; - - pci_disable_device(pdev); + netdev_unlock(netdev); + if (running) + rtnl_unlock(); return 0; } /** * iavf_resume - Power management resume routine - * @pdev: PCI device information struct + * @dev_d: device info pointer * * Called when the system (VM) is resumed from sleep/suspend. **/ -static int iavf_resume(struct pci_dev *pdev) +static int iavf_resume(struct device *dev_d) { - struct iavf_adapter *adapter = pci_get_drvdata(pdev); - struct net_device *netdev = adapter->netdev; - u32 err; + struct pci_dev *pdev = to_pci_dev(dev_d); + struct iavf_adapter *adapter; + int err; - pci_set_power_state(pdev, PCI_D0); - pci_restore_state(pdev); - /* pci_restore_state clears dev->state_saved so call - * pci_save_state to restore it. - */ - pci_save_state(pdev); + adapter = iavf_pdev_to_adapter(pdev); - err = pci_enable_device_mem(pdev); - if (err) { - dev_err(&pdev->dev, "Cannot enable PCI device from suspend.\n"); - return err; - } pci_set_master(pdev); rtnl_lock(); @@ -3818,14 +5511,13 @@ static int iavf_resume(struct pci_dev *pdev) return err; } - schedule_work(&adapter->reset_task); + queue_work(adapter->wq, &adapter->reset_task); - netif_device_attach(netdev); + netif_device_attach(adapter->netdev); return err; } -#endif /* CONFIG_PM */ /** * iavf_remove - Device Removal Routine * @pdev: PCI device information struct @@ -3837,33 +5529,56 @@ static int iavf_resume(struct pci_dev *pdev) **/ static void iavf_remove(struct pci_dev *pdev) { - struct net_device *netdev = pci_get_drvdata(pdev); - struct iavf_adapter *adapter = netdev_priv(netdev); + struct iavf_fdir_fltr *fdir, *fdirtmp; struct iavf_vlan_filter *vlf, *vlftmp; - struct iavf_mac_filter *f, *ftmp; struct iavf_cloud_filter *cf, *cftmp; - struct iavf_hw *hw = &adapter->hw; - int err; - /* Indicate we are in remove and not to run reset_task */ - set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section); - cancel_delayed_work_sync(&adapter->init_task); - cancel_work_sync(&adapter->reset_task); - cancel_delayed_work_sync(&adapter->client_task); - if (adapter->netdev_registered) { - unregister_netdev(netdev); - adapter->netdev_registered = false; - } - if (CLIENT_ALLOWED(adapter)) { - err = iavf_lan_del_device(adapter); - if (err) - dev_warn(&pdev->dev, "Failed to delete client device: %d\n", - err); + struct iavf_adv_rss *rss, *rsstmp; + struct iavf_mac_filter *f, *ftmp; + struct iavf_adapter *adapter; + struct net_device *netdev; + struct iavf_hw *hw; + + /* Don't proceed with remove if netdev is already freed */ + netdev = pci_get_drvdata(pdev); + if (!netdev) + return; + + adapter = iavf_pdev_to_adapter(pdev); + hw = &adapter->hw; + + if (test_and_set_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) + return; + + /* Wait until port initialization is complete. + * There are flows where register/unregister netdev may race. + */ + while (1) { + netdev_lock(netdev); + if (adapter->state == __IAVF_RUNNING || + adapter->state == __IAVF_DOWN || + adapter->state == __IAVF_INIT_FAILED) { + netdev_unlock(netdev); + break; + } + /* Simply return if we already went through iavf_shutdown */ + if (adapter->state == __IAVF_REMOVE) { + netdev_unlock(netdev); + return; + } + + netdev_unlock(netdev); + usleep_range(500, 1000); } + cancel_delayed_work_sync(&adapter->watchdog_task); + cancel_work_sync(&adapter->finish_config); + + if (netdev->reg_state == NETREG_REGISTERED) + unregister_netdev(netdev); + + netdev_lock(netdev); + dev_info(&adapter->pdev->dev, "Removing device\n"); + iavf_change_state(adapter, __IAVF_REMOVE); - /* Shut down all the garbage mashers on the detention level */ - adapter->state = __IAVF_REMOVE; - adapter->aq_required = 0; - adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; iavf_request_reset(adapter); msleep(50); /* If the FW isn't responding, kick it once, but only once. */ @@ -3871,17 +5586,24 @@ static void iavf_remove(struct pci_dev *pdev) iavf_request_reset(adapter); msleep(50); } - iavf_free_all_tx_resources(adapter); - iavf_free_all_rx_resources(adapter); - iavf_misc_irq_disable(adapter); - iavf_free_misc_irq(adapter); - iavf_reset_interrupt_capability(adapter); - iavf_free_q_vectors(adapter); - if (adapter->watchdog_timer.function) - del_timer_sync(&adapter->watchdog_timer); + iavf_ptp_release(adapter); + iavf_misc_irq_disable(adapter); + /* Shut down all the garbage mashers on the detention level */ + netdev_unlock(netdev); + cancel_work_sync(&adapter->reset_task); + cancel_delayed_work_sync(&adapter->watchdog_task); cancel_work_sync(&adapter->adminq_task); + netdev_lock(netdev); + + adapter->aq_required = 0; + adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + + iavf_free_all_tx_resources(adapter); + iavf_free_all_rx_resources(adapter); + iavf_free_misc_irq(adapter); + iavf_free_interrupt_scheme(adapter); iavf_free_rss(adapter); @@ -3891,12 +5613,10 @@ static void iavf_remove(struct pci_dev *pdev) /* destroy the locks only once, here */ mutex_destroy(&hw->aq.arq_mutex); mutex_destroy(&hw->aq.asq_mutex); + netdev_unlock(netdev); iounmap(hw->hw_addr); pci_release_regions(pdev); - iavf_free_all_tx_resources(adapter); - iavf_free_all_rx_resources(adapter); - iavf_free_queues(adapter); kfree(adapter->vf_res); spin_lock_bh(&adapter->mac_vlan_list_lock); /* If we got removed before an up/down sequence, we've got a filter @@ -3921,23 +5641,51 @@ static void iavf_remove(struct pci_dev *pdev) } spin_unlock_bh(&adapter->cloud_filter_list_lock); - free_netdev(netdev); + spin_lock_bh(&adapter->fdir_fltr_lock); + list_for_each_entry_safe(fdir, fdirtmp, &adapter->fdir_list_head, list) { + list_del(&fdir->list); + kfree(fdir); + } + spin_unlock_bh(&adapter->fdir_fltr_lock); + + spin_lock_bh(&adapter->adv_rss_lock); + list_for_each_entry_safe(rss, rsstmp, &adapter->adv_rss_list_head, + list) { + list_del(&rss->list); + kfree(rss); + } + spin_unlock_bh(&adapter->adv_rss_lock); - pci_disable_pcie_error_reporting(pdev); + destroy_workqueue(adapter->wq); + + pci_set_drvdata(pdev, NULL); + + free_netdev(netdev); pci_disable_device(pdev); } +/** + * iavf_shutdown - Shutdown the device in preparation for a reboot + * @pdev: pci device structure + **/ +static void iavf_shutdown(struct pci_dev *pdev) +{ + iavf_remove(pdev); + + if (system_state == SYSTEM_POWER_OFF) + pci_set_power_state(pdev, PCI_D3hot); +} + +static DEFINE_SIMPLE_DEV_PM_OPS(iavf_pm_ops, iavf_suspend, iavf_resume); + static struct pci_driver iavf_driver = { - .name = iavf_driver_name, - .id_table = iavf_pci_tbl, - .probe = iavf_probe, - .remove = iavf_remove, -#ifdef CONFIG_PM - .suspend = iavf_suspend, - .resume = iavf_resume, -#endif - .shutdown = iavf_shutdown, + .name = iavf_driver_name, + .id_table = iavf_pci_tbl, + .probe = iavf_probe, + .remove = iavf_remove, + .driver.pm = pm_sleep_ptr(&iavf_pm_ops), + .shutdown = iavf_shutdown, }; /** @@ -3948,21 +5696,11 @@ static struct pci_driver iavf_driver = { **/ static int __init iavf_init_module(void) { - int ret; - - pr_info("iavf: %s - version %s\n", iavf_driver_string, - iavf_driver_version); + pr_info("iavf: %s\n", iavf_driver_string); pr_info("%s\n", iavf_copyright); - iavf_wq = alloc_workqueue("%s", WQ_UNBOUND | WQ_MEM_RECLAIM, 1, - iavf_driver_name); - if (!iavf_wq) { - pr_err("%s: Failed to create workqueue\n", iavf_driver_name); - return -ENOMEM; - } - ret = pci_register_driver(&iavf_driver); - return ret; + return pci_register_driver(&iavf_driver); } module_init(iavf_init_module); @@ -3976,7 +5714,6 @@ module_init(iavf_init_module); static void __exit iavf_exit_module(void) { pci_unregister_driver(&iavf_driver); - destroy_workqueue(iavf_wq); } module_exit(iavf_exit_module); |