diff options
| author | Dmitry Torokhov <[email protected]> | 2023-08-30 16:06:38 -0700 |
|---|---|---|
| committer | Dmitry Torokhov <[email protected]> | 2023-08-30 16:06:38 -0700 |
| commit | 1ac731c529cd4d6adbce134754b51ff7d822b145 (patch) | |
| tree | 143ab3f35ca5f3b69f583c84e6964b17139c2ec1 /drivers/net/ethernet/intel | |
| parent | 07b4c950f27bef0362dc6ad7ee713aab61d58149 (diff) | |
| parent | 54116d442e001e1b6bd482122043b1870998a1f3 (diff) | |
Merge branch 'next' into for-linus
Prepare input updates for 6.6 merge window.
Diffstat (limited to 'drivers/net/ethernet/intel')
77 files changed, 1162 insertions, 7365 deletions
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index c18c3b373846..9bc0a9519899 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -139,23 +139,6 @@ config IGBVF To compile this driver as a module, choose M here. The module will be called igbvf. -config IXGB - tristate "Intel(R) PRO/10GbE support" - depends on PCI - help - This driver supports Intel(R) PRO/10GbE family of adapters for - PCI-X type cards. For PCI-E type cards, use the "ixgbe" driver - instead. For more information on how to identify your adapter, go - to the Adapter & Driver ID Guide that can be located at: - - <http://support.intel.com> - - More specific information on configuring the driver is in - <file:Documentation/networking/device_drivers/ethernet/intel/ixgb.rst>. - - To compile this driver as a module, choose M here. The module - will be called ixgb. - config IXGBE tristate "Intel(R) 10GbE PCI Express adapters support" depends on PCI diff --git a/drivers/net/ethernet/intel/Makefile b/drivers/net/ethernet/intel/Makefile index 3075290063f6..d80d04132073 100644 --- a/drivers/net/ethernet/intel/Makefile +++ b/drivers/net/ethernet/intel/Makefile @@ -12,7 +12,6 @@ obj-$(CONFIG_IGBVF) += igbvf/ obj-$(CONFIG_IXGBE) += ixgbe/ obj-$(CONFIG_IXGBEVF) += ixgbevf/ obj-$(CONFIG_I40E) += i40e/ -obj-$(CONFIG_IXGB) += ixgb/ obj-$(CONFIG_IAVF) += iavf/ obj-$(CONFIG_FM10K) += fm10k/ obj-$(CONFIG_ICE) += ice/ diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index e1eb1de88bf9..bd7ef59b1f2e 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -23,7 +23,6 @@ #include <linux/smp.h> #include <linux/pm_qos.h> #include <linux/pm_runtime.h> -#include <linux/aer.h> #include <linux/prefetch.h> #include <linux/suspend.h> @@ -5288,31 +5287,6 @@ static void e1000_watchdog_task(struct work_struct *work) ew32(TARC(0), tarc0); } - /* disable TSO for pcie and 10/100 speeds, to avoid - * some hardware issues - */ - if (!(adapter->flags & FLAG_TSO_FORCE)) { - switch (adapter->link_speed) { - case SPEED_10: - case SPEED_100: - e_info("10/100 speed: disabling TSO\n"); - netdev->features &= ~NETIF_F_TSO; - netdev->features &= ~NETIF_F_TSO6; - break; - case SPEED_1000: - netdev->features |= NETIF_F_TSO; - netdev->features |= NETIF_F_TSO6; - break; - default: - /* oops */ - break; - } - if (hw->mac.type == e1000_pch_spt) { - netdev->features &= ~NETIF_F_TSO; - netdev->features &= ~NETIF_F_TSO6; - } - } - /* enable transmits in the hardware, need to do this * after setting TARC(0) */ @@ -7526,6 +7500,32 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) NETIF_F_RXCSUM | NETIF_F_HW_CSUM); + /* disable TSO for pcie and 10/100 speeds to avoid + * some hardware issues and for i219 to fix transfer + * speed being capped at 60% + */ + if (!(adapter->flags & FLAG_TSO_FORCE)) { + switch (adapter->link_speed) { + case SPEED_10: + case SPEED_100: + e_info("10/100 speed: disabling TSO\n"); + netdev->features &= ~NETIF_F_TSO; + netdev->features &= ~NETIF_F_TSO6; + break; + case SPEED_1000: + netdev->features |= NETIF_F_TSO; + netdev->features |= NETIF_F_TSO6; + break; + default: + /* oops */ + break; + } + if (hw->mac.type == e1000_pch_spt) { + netdev->features &= ~NETIF_F_TSO; + netdev->features &= ~NETIF_F_TSO6; + } + } + /* Set user-changeable features (subset of all device features) */ netdev->hw_features = netdev->features; netdev->hw_features |= NETIF_F_RXFCS; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index 027d721feb18..d748b98274e7 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -3,7 +3,6 @@ #include <linux/module.h> #include <linux/interrupt.h> -#include <linux/aer.h> #include "fm10k.h" diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 60ce4d15d82a..6e310a539467 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -10,7 +10,6 @@ #include <linux/errno.h> #include <linux/module.h> #include <linux/pci.h> -#include <linux/aer.h> #include <linux/netdevice.h> #include <linux/ioport.h> #include <linux/iommu.h> diff --git a/drivers/net/ethernet/intel/i40e/i40e_diag.c b/drivers/net/ethernet/intel/i40e/i40e_diag.c index 5b3519c6e362..97fe1787a8f4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_diag.c +++ b/drivers/net/ethernet/intel/i40e/i40e_diag.c @@ -44,7 +44,7 @@ static int i40e_diag_reg_pattern_test(struct i40e_hw *hw, return 0; } -struct i40e_diag_reg_test_info i40e_reg_list[] = { +const struct i40e_diag_reg_test_info i40e_reg_list[] = { /* offset mask elements stride */ {I40E_QTX_CTL(0), 0x0000FFBF, 1, I40E_QTX_CTL(1) - I40E_QTX_CTL(0)}, @@ -78,27 +78,28 @@ int i40e_diag_reg_test(struct i40e_hw *hw) { int ret_code = 0; u32 reg, mask; + u32 elements; u32 i, j; for (i = 0; i40e_reg_list[i].offset != 0 && !ret_code; i++) { + elements = i40e_reg_list[i].elements; /* set actual reg range for dynamically allocated resources */ if (i40e_reg_list[i].offset == I40E_QTX_CTL(0) && hw->func_caps.num_tx_qp != 0) - i40e_reg_list[i].elements = hw->func_caps.num_tx_qp; + elements = hw->func_caps.num_tx_qp; if ((i40e_reg_list[i].offset == I40E_PFINT_ITRN(0, 0) || i40e_reg_list[i].offset == I40E_PFINT_ITRN(1, 0) || i40e_reg_list[i].offset == I40E_PFINT_ITRN(2, 0) || i40e_reg_list[i].offset == I40E_QINT_TQCTL(0) || i40e_reg_list[i].offset == I40E_QINT_RQCTL(0)) && hw->func_caps.num_msix_vectors != 0) - i40e_reg_list[i].elements = - hw->func_caps.num_msix_vectors - 1; + elements = hw->func_caps.num_msix_vectors - 1; /* test register access */ mask = i40e_reg_list[i].mask; - for (j = 0; j < i40e_reg_list[i].elements && !ret_code; j++) { + for (j = 0; j < elements && !ret_code; j++) { reg = i40e_reg_list[i].offset + (j * i40e_reg_list[i].stride); ret_code = i40e_diag_reg_pattern_test(hw, reg, mask); diff --git a/drivers/net/ethernet/intel/i40e/i40e_diag.h b/drivers/net/ethernet/intel/i40e/i40e_diag.h index e641035c7297..c3ce5f35211f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_diag.h +++ b/drivers/net/ethernet/intel/i40e/i40e_diag.h @@ -20,7 +20,7 @@ struct i40e_diag_reg_test_info { u32 stride; /* bytes between each element */ }; -extern struct i40e_diag_reg_test_info i40e_reg_list[]; +extern const struct i40e_diag_reg_test_info i40e_reg_list[]; int i40e_diag_reg_test(struct i40e_hw *hw); int i40e_diag_eeprom_test(struct i40e_hw *hw); diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 4934ff58332c..afc4fa8c66af 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -5402,6 +5402,13 @@ flags_complete: return -EOPNOTSUPP; } + if ((changed_flags & I40E_FLAG_LEGACY_RX) && + I40E_2K_TOO_SMALL_WITH_PADDING) { + dev_warn(&pf->pdev->dev, + "2k Rx buffer is too small to fit standard MTU and skb_shared_info\n"); + return -EOPNOTSUPP; + } + if ((changed_flags & new_flags & I40E_FLAG_LINK_DOWN_ON_CLOSE_ENABLED) && (new_flags & I40E_FLAG_MFP_ENABLED)) diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 467001db5070..b847bd105b16 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -2896,15 +2896,35 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf) } /** - * i40e_max_xdp_frame_size - returns the maximum allowed frame size for XDP + * i40e_calculate_vsi_rx_buf_len - Calculates buffer length + * + * @vsi: VSI to calculate rx_buf_len from + */ +static u16 i40e_calculate_vsi_rx_buf_len(struct i40e_vsi *vsi) +{ + if (!vsi->netdev || (vsi->back->flags & I40E_FLAG_LEGACY_RX)) + return SKB_WITH_OVERHEAD(I40E_RXBUFFER_2048); + + return PAGE_SIZE < 8192 ? I40E_RXBUFFER_3072 : I40E_RXBUFFER_2048; +} + +/** + * i40e_max_vsi_frame_size - returns the maximum allowed frame size for VSI * @vsi: the vsi + * @xdp_prog: XDP program **/ -static int i40e_max_xdp_frame_size(struct i40e_vsi *vsi) +static int i40e_max_vsi_frame_size(struct i40e_vsi *vsi, + struct bpf_prog *xdp_prog) { - if (PAGE_SIZE >= 8192 || (vsi->back->flags & I40E_FLAG_LEGACY_RX)) - return I40E_RXBUFFER_2048; + u16 rx_buf_len = i40e_calculate_vsi_rx_buf_len(vsi); + u16 chain_len; + + if (xdp_prog && !xdp_prog->aux->xdp_has_frags) + chain_len = 1; else - return I40E_RXBUFFER_3072; + chain_len = I40E_MAX_CHAINED_RX_BUFFERS; + + return min_t(u16, rx_buf_len * chain_len, I40E_MAX_RXBUFFER); } /** @@ -2919,12 +2939,13 @@ static int i40e_change_mtu(struct net_device *netdev, int new_mtu) struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; + int frame_size; - if (i40e_enabled_xdp_vsi(vsi)) { - int frame_size = new_mtu + I40E_PACKET_HDR_PAD; - - if (frame_size > i40e_max_xdp_frame_size(vsi)) - return -EINVAL; + frame_size = i40e_max_vsi_frame_size(vsi, vsi->xdp_prog); + if (new_mtu > frame_size - I40E_PACKET_HDR_PAD) { + netdev_err(netdev, "Error changing mtu to %d, Max is %d\n", + new_mtu, frame_size - I40E_PACKET_HDR_PAD); + return -EINVAL; } netdev_dbg(netdev, "changing MTU from %d to %d\n", @@ -3595,6 +3616,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) } } + xdp_init_buff(&ring->xdp, i40e_rx_pg_size(ring) / 2, &ring->xdp_rxq); + rx_ctx.dbuff = DIV_ROUND_UP(ring->rx_buf_len, BIT_ULL(I40E_RXQ_CTX_DBUFF_SHIFT)); @@ -3640,10 +3663,16 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring) } /* configure Rx buffer alignment */ - if (!vsi->netdev || (vsi->back->flags & I40E_FLAG_LEGACY_RX)) + if (!vsi->netdev || (vsi->back->flags & I40E_FLAG_LEGACY_RX)) { + if (I40E_2K_TOO_SMALL_WITH_PADDING) { + dev_info(&vsi->back->pdev->dev, + "2k Rx buffer is too small to fit standard MTU and skb_shared_info\n"); + return -EOPNOTSUPP; + } clear_ring_build_skb_enabled(ring); - else + } else { set_ring_build_skb_enabled(ring); + } ring->rx_offset = i40e_rx_offset(ring); @@ -3694,24 +3723,6 @@ static int i40e_vsi_configure_tx(struct i40e_vsi *vsi) } /** - * i40e_calculate_vsi_rx_buf_len - Calculates buffer length - * - * @vsi: VSI to calculate rx_buf_len from - */ -static u16 i40e_calculate_vsi_rx_buf_len(struct i40e_vsi *vsi) -{ - if (!vsi->netdev || (vsi->back->flags & I40E_FLAG_LEGACY_RX)) - return I40E_RXBUFFER_2048; - -#if (PAGE_SIZE < 8192) - if (!I40E_2K_TOO_SMALL_WITH_PADDING && vsi->netdev->mtu <= ETH_DATA_LEN) - return I40E_RXBUFFER_1536 - NET_IP_ALIGN; -#endif - - return PAGE_SIZE < 8192 ? I40E_RXBUFFER_3072 : I40E_RXBUFFER_2048; -} - -/** * i40e_vsi_configure_rx - Configure the VSI for Rx * @vsi: the VSI being configured * @@ -3722,13 +3733,15 @@ static int i40e_vsi_configure_rx(struct i40e_vsi *vsi) int err = 0; u16 i; - vsi->max_frame = I40E_MAX_RXBUFFER; + vsi->max_frame = i40e_max_vsi_frame_size(vsi, vsi->xdp_prog); vsi->rx_buf_len = i40e_calculate_vsi_rx_buf_len(vsi); #if (PAGE_SIZE < 8192) if (vsi->netdev && !I40E_2K_TOO_SMALL_WITH_PADDING && - vsi->netdev->mtu <= ETH_DATA_LEN) - vsi->max_frame = I40E_RXBUFFER_1536 - NET_IP_ALIGN; + vsi->netdev->mtu <= ETH_DATA_LEN) { + vsi->rx_buf_len = I40E_RXBUFFER_1536 - NET_IP_ALIGN; + vsi->max_frame = vsi->rx_buf_len; + } #endif /* set up individual rings */ @@ -11059,8 +11072,11 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired) pf->hw.aq.asq_last_status)); } /* reinit the misc interrupt */ - if (pf->flags & I40E_FLAG_MSIX_ENABLED) + if (pf->flags & I40E_FLAG_MSIX_ENABLED) { ret = i40e_setup_misc_vector(pf); + if (ret) + goto end_unlock; + } /* Add a filter to drop all Flow control frames from any VSI from being * transmitted. By doing so we stop a malicious VF from sending out @@ -13316,15 +13332,15 @@ out_err: static int i40e_xdp_setup(struct i40e_vsi *vsi, struct bpf_prog *prog, struct netlink_ext_ack *extack) { - int frame_size = vsi->netdev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; + int frame_size = i40e_max_vsi_frame_size(vsi, prog); struct i40e_pf *pf = vsi->back; struct bpf_prog *old_prog; bool need_reset; int i; /* Don't allow frames that span over multiple buffers */ - if (frame_size > i40e_calculate_vsi_rx_buf_len(vsi)) { - NL_SET_ERR_MSG_MOD(extack, "MTU too large to enable XDP"); + if (vsi->netdev->mtu > frame_size - I40E_PACKET_HDR_PAD) { + NL_SET_ERR_MSG_MOD(extack, "MTU too large for linear frames and XDP prog does not support frags"); return -EINVAL; } @@ -13810,7 +13826,8 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | - NETDEV_XDP_ACT_XSK_ZEROCOPY; + NETDEV_XDP_ACT_XSK_ZEROCOPY | + NETDEV_XDP_ACT_RX_SG; } else { /* Relate the VSI_VMDQ name to the VSI_MAIN name. Note that we * are still limited by IFNAMSIZ, but we're adding 'v%d\0' to @@ -14133,15 +14150,15 @@ static int i40e_add_vsi(struct i40e_vsi *vsi) vsi->id = ctxt.vsi_number; } - vsi->active_filters = 0; - clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); spin_lock_bh(&vsi->mac_filter_hash_lock); + vsi->active_filters = 0; /* If macvlan filters already exist, force them to get loaded */ hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { f->state = I40E_FILTER_NEW; f_count++; } spin_unlock_bh(&vsi->mac_filter_hash_lock); + clear_bit(__I40E_VSI_OVERFLOW_PROMISC, vsi->state); if (f_count) { vsi->flags |= I40E_VSI_FLAG_FILTER_CHANGED; @@ -15525,6 +15542,7 @@ static int i40e_init_recovery_mode(struct i40e_pf *pf, struct i40e_hw *hw) int err; int v_idx; + pci_set_drvdata(pf->pdev, pf); pci_save_state(pf->pdev); /* set up periodic task facility */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_trace.h b/drivers/net/ethernet/intel/i40e/i40e_trace.h index 79d587ad5409..33b4e30f5e00 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_trace.h +++ b/drivers/net/ethernet/intel/i40e/i40e_trace.h @@ -162,45 +162,45 @@ DECLARE_EVENT_CLASS( TP_PROTO(struct i40e_ring *ring, union i40e_16byte_rx_desc *desc, - struct sk_buff *skb), + struct xdp_buff *xdp), - TP_ARGS(ring, desc, skb), + TP_ARGS(ring, desc, xdp), TP_STRUCT__entry( __field(void*, ring) __field(void*, desc) - __field(void*, skb) + __field(void*, xdp) __string(devname, ring->netdev->name) ), TP_fast_assign( __entry->ring = ring; __entry->desc = desc; - __entry->skb = skb; + __entry->xdp = xdp; __assign_str(devname, ring->netdev->name); ), TP_printk( - "netdev: %s ring: %p desc: %p skb %p", + "netdev: %s ring: %p desc: %p xdp %p", __get_str(devname), __entry->ring, - __entry->desc, __entry->skb) + __entry->desc, __entry->xdp) ); DEFINE_EVENT( i40e_rx_template, i40e_clean_rx_irq, TP_PROTO(struct i40e_ring *ring, union i40e_16byte_rx_desc *desc, - struct sk_buff *skb), + struct xdp_buff *xdp), - TP_ARGS(ring, desc, skb)); + TP_ARGS(ring, desc, xdp)); DEFINE_EVENT( i40e_rx_template, i40e_clean_rx_irq_rx, TP_PROTO(struct i40e_ring *ring, union i40e_16byte_rx_desc *desc, - struct sk_buff *skb), + struct xdp_buff *xdp), - TP_ARGS(ring, desc, skb)); + TP_ARGS(ring, desc, xdp)); DECLARE_EVENT_CLASS( i40e_xmit_template, diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 924f972b91fa..8b8bf4880faa 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -171,10 +171,10 @@ static char *i40e_create_dummy_packet(u8 *dummy_packet, bool ipv4, u8 l4proto, struct i40e_fdir_filter *data) { bool is_vlan = !!data->vlan_tag; - struct vlan_hdr vlan; - struct ipv6hdr ipv6; - struct ethhdr eth; - struct iphdr ip; + struct vlan_hdr vlan = {}; + struct ipv6hdr ipv6 = {}; + struct ethhdr eth = {}; + struct iphdr ip = {}; u8 *tmp; if (ipv4) { @@ -1477,9 +1477,6 @@ void i40e_clean_rx_ring(struct i40e_ring *rx_ring) if (!rx_ring->rx_bi) return; - dev_kfree_skb(rx_ring->skb); - rx_ring->skb = NULL; - if (rx_ring->xsk_pool) { i40e_xsk_clean_rx_ring(rx_ring); goto skip_free; @@ -1524,6 +1521,7 @@ skip_free: rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; + rx_ring->next_to_process = 0; rx_ring->next_to_use = 0; } @@ -1576,6 +1574,7 @@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring) rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; + rx_ring->next_to_process = 0; rx_ring->next_to_use = 0; /* XDP RX-queue info only needed for RX rings exposed to XDP */ @@ -1617,21 +1616,19 @@ void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) writel(val, rx_ring->tail); } +#if (PAGE_SIZE >= 8192) static unsigned int i40e_rx_frame_truesize(struct i40e_ring *rx_ring, unsigned int size) { unsigned int truesize; -#if (PAGE_SIZE < 8192) - truesize = i40e_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */ -#else truesize = rx_ring->rx_offset ? SKB_DATA_ALIGN(size + rx_ring->rx_offset) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) : SKB_DATA_ALIGN(size); -#endif return truesize; } +#endif /** * i40e_alloc_mapped_page - recycle or make a new page @@ -1970,7 +1967,6 @@ static bool i40e_cleanup_headers(struct i40e_ring *rx_ring, struct sk_buff *skb, * i40e_can_reuse_rx_page - Determine if page can be reused for another Rx * @rx_buffer: buffer containing the page * @rx_stats: rx stats structure for the rx ring - * @rx_buffer_pgcnt: buffer page refcount pre xdp_do_redirect() call * * If page is reusable, we have a green light for calling i40e_reuse_rx_page, * which will assign the current buffer to the buffer that next_to_alloc is @@ -1981,8 +1977,7 @@ static bool i40e_cleanup_headers(struct i40e_ring *rx_ring, struct sk_buff *skb, * or busy if it could not be reused. */ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer, - struct i40e_rx_queue_stats *rx_stats, - int rx_buffer_pgcnt) + struct i40e_rx_queue_stats *rx_stats) { unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; struct page *page = rx_buffer->page; @@ -1995,7 +1990,7 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer, #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely((rx_buffer_pgcnt - pagecnt_bias) > 1)) { + if (unlikely((rx_buffer->page_count - pagecnt_bias) > 1)) { rx_stats->page_busy_count++; return false; } @@ -2021,33 +2016,14 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer, } /** - * i40e_add_rx_frag - Add contents of Rx buffer to sk_buff - * @rx_ring: rx descriptor ring to transact packets on - * @rx_buffer: buffer containing page to add - * @skb: sk_buff to place the data into - * @size: packet length from rx_desc - * - * This function will add the data contained in rx_buffer->page to the skb. - * It will just attach the page as a frag to the skb. - * - * The function will then update the page offset. + * i40e_rx_buffer_flip - adjusted rx_buffer to point to an unused region + * @rx_buffer: Rx buffer to adjust + * @truesize: Size of adjustment **/ -static void i40e_add_rx_frag(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *rx_buffer, - struct sk_buff *skb, - unsigned int size) +static void i40e_rx_buffer_flip(struct i40e_rx_buffer *rx_buffer, + unsigned int truesize) { #if (PAGE_SIZE < 8192) - unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; -#else - unsigned int truesize = SKB_DATA_ALIGN(size + rx_ring->rx_offset); -#endif - - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, - rx_buffer->page_offset, size, truesize); - - /* page is being used so we must update the page offset */ -#if (PAGE_SIZE < 8192) rx_buffer->page_offset ^= truesize; #else rx_buffer->page_offset += truesize; @@ -2058,19 +2034,17 @@ static void i40e_add_rx_frag(struct i40e_ring *rx_ring, * i40e_get_rx_buffer - Fetch Rx buffer and synchronize data for use * @rx_ring: rx descriptor ring to transact packets on * @size: size of buffer to add to skb - * @rx_buffer_pgcnt: buffer page refcount * * This function will pull an Rx buffer from the ring and synchronize it * for use by the CPU. */ static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring, - const unsigned int size, - int *rx_buffer_pgcnt) + const unsigned int size) { struct i40e_rx_buffer *rx_buffer; - rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean); - *rx_buffer_pgcnt = + rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_process); + rx_buffer->page_count = #if (PAGE_SIZE < 8192) page_count(rx_buffer->page); #else @@ -2092,25 +2066,82 @@ static struct i40e_rx_buffer *i40e_get_rx_buffer(struct i40e_ring *rx_ring, } /** - * i40e_construct_skb - Allocate skb and populate it + * i40e_put_rx_buffer - Clean up used buffer and either recycle or free * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: rx buffer to pull data from + * + * This function will clean up the contents of the rx_buffer. It will + * either recycle the buffer or unmap it and free the associated resources. + */ +static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, + struct i40e_rx_buffer *rx_buffer) +{ + if (i40e_can_reuse_rx_page(rx_buffer, &rx_ring->rx_stats)) { + /* hand second half of page back to the ring */ + i40e_reuse_rx_page(rx_ring, rx_buffer); + } else { + /* we are not reusing the buffer so unmap it */ + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, + i40e_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, I40E_RX_DMA_ATTR); + __page_frag_cache_drain(rx_buffer->page, + rx_buffer->pagecnt_bias); + /* clear contents of buffer_info */ + rx_buffer->page = NULL; + } +} + +/** + * i40e_process_rx_buffs- Processing of buffers post XDP prog or on error + * @rx_ring: Rx descriptor ring to transact packets on + * @xdp_res: Result of the XDP program + * @xdp: xdp_buff pointing to the data + **/ +static void i40e_process_rx_buffs(struct i40e_ring *rx_ring, int xdp_res, + struct xdp_buff *xdp) +{ + u32 next = rx_ring->next_to_clean; + struct i40e_rx_buffer *rx_buffer; + + xdp->flags = 0; + + while (1) { + rx_buffer = i40e_rx_bi(rx_ring, next); + if (++next == rx_ring->count) + next = 0; + + if (!rx_buffer->page) + continue; + + if (xdp_res == I40E_XDP_CONSUMED) + rx_buffer->pagecnt_bias++; + else + i40e_rx_buffer_flip(rx_buffer, xdp->frame_sz); + + /* EOP buffer will be put in i40e_clean_rx_irq() */ + if (next == rx_ring->next_to_process) + return; + + i40e_put_rx_buffer(rx_ring, rx_buffer); + } +} + +/** + * i40e_construct_skb - Allocate skb and populate it + * @rx_ring: rx descriptor ring to transact packets on * @xdp: xdp_buff pointing to the data + * @nr_frags: number of buffers for the packet * * This function allocates an skb. It then populates it with the page * data from the current receive descriptor, taking care to set up the * skb correctly. */ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *rx_buffer, - struct xdp_buff *xdp) + struct xdp_buff *xdp, + u32 nr_frags) { unsigned int size = xdp->data_end - xdp->data; -#if (PAGE_SIZE < 8192) - unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; -#else - unsigned int truesize = SKB_DATA_ALIGN(size); -#endif + struct i40e_rx_buffer *rx_buffer; unsigned int headlen; struct sk_buff *skb; @@ -2150,48 +2181,60 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, memcpy(__skb_put(skb, headlen), xdp->data, ALIGN(headlen, sizeof(long))); + rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean); /* update all of the pointers */ size -= headlen; if (size) { + if (unlikely(nr_frags >= MAX_SKB_FRAGS)) { + dev_kfree_skb(skb); + return NULL; + } skb_add_rx_frag(skb, 0, rx_buffer->page, rx_buffer->page_offset + headlen, - size, truesize); - + size, xdp->frame_sz); /* buffer is used by skb, update page_offset */ -#if (PAGE_SIZE < 8192) - rx_buffer->page_offset ^= truesize; -#else - rx_buffer->page_offset += truesize; -#endif + i40e_rx_buffer_flip(rx_buffer, xdp->frame_sz); } else { /* buffer is unused, reset bias back to rx_buffer */ rx_buffer->pagecnt_bias++; } + if (unlikely(xdp_buff_has_frags(xdp))) { + struct skb_shared_info *sinfo, *skinfo = skb_shinfo(skb); + + sinfo = xdp_get_shared_info_from_buff(xdp); + memcpy(&skinfo->frags[skinfo->nr_frags], &sinfo->frags[0], + sizeof(skb_frag_t) * nr_frags); + + xdp_update_skb_shared_info(skb, skinfo->nr_frags + nr_frags, + sinfo->xdp_frags_size, + nr_frags * xdp->frame_sz, + xdp_buff_is_frag_pfmemalloc(xdp)); + + /* First buffer has already been processed, so bump ntc */ + if (++rx_ring->next_to_clean == rx_ring->count) + rx_ring->next_to_clean = 0; + + i40e_process_rx_buffs(rx_ring, I40E_XDP_PASS, xdp); + } + return skb; } /** * i40e_build_skb - Build skb around an existing buffer * @rx_ring: Rx descriptor ring to transact packets on - * @rx_buffer: Rx buffer to pull data from * @xdp: xdp_buff pointing to the data + * @nr_frags: number of buffers for the packet * * This function builds an skb around an existing Rx buffer, taking care * to set up the skb correctly and avoid any memcpy overhead. */ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *rx_buffer, - struct xdp_buff *xdp) + struct xdp_buff *xdp, + u32 nr_frags) { unsigned int metasize = xdp->data - xdp->data_meta; -#if (PAGE_SIZE < 8192) - unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; -#else - unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + - SKB_DATA_ALIGN(xdp->data_end - - xdp->data_hard_start); -#endif struct sk_buff *skb; /* Prefetch first cache line of first page. If xdp->data_meta @@ -2202,7 +2245,7 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, net_prefetch(xdp->data_meta); /* build an skb around the page buffer */ - skb = napi_build_skb(xdp->data_hard_start, truesize); + skb = napi_build_skb(xdp->data_hard_start, xdp->frame_sz); if (unlikely(!skb)) return NULL; @@ -2212,42 +2255,25 @@ static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, if (metasize) skb_metadata_set(skb, metasize); - /* buffer is used by skb, update page_offset */ -#if (PAGE_SIZE < 8192) - rx_buffer->page_offset ^= truesize; -#else - rx_buffer->page_offset += truesize; -#endif + if (unlikely(xdp_buff_has_frags(xdp))) { + struct skb_shared_info *sinfo; - return skb; -} + sinfo = xdp_get_shared_info_from_buff(xdp); + xdp_update_skb_shared_info(skb, nr_frags, + sinfo->xdp_frags_size, + nr_frags * xdp->frame_sz, + xdp_buff_is_frag_pfmemalloc(xdp)); -/** - * i40e_put_rx_buffer - Clean up used buffer and either recycle or free - * @rx_ring: rx descriptor ring to transact packets on - * @rx_buffer: rx buffer to pull data from - * @rx_buffer_pgcnt: rx buffer page refcount pre xdp_do_redirect() call - * - * This function will clean up the contents of the rx_buffer. It will - * either recycle the buffer or unmap it and free the associated resources. - */ -static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *rx_buffer, - int rx_buffer_pgcnt) -{ - if (i40e_can_reuse_rx_page(rx_buffer, &rx_ring->rx_stats, rx_buffer_pgcnt)) { - /* hand second half of page back to the ring */ - i40e_reuse_rx_page(rx_ring, rx_buffer); + i40e_process_rx_buffs(rx_ring, I40E_XDP_PASS, xdp); } else { - /* we are not reusing the buffer so unmap it */ - dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, - i40e_rx_pg_size(rx_ring), - DMA_FROM_DEVICE, I40E_RX_DMA_ATTR); - __page_frag_cache_drain(rx_buffer->page, - rx_buffer->pagecnt_bias); - /* clear contents of buffer_info */ - rx_buffer->page = NULL; + struct i40e_rx_buffer *rx_buffer; + + rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean); + /* buffer is used by skb, update page_offset */ + i40e_rx_buffer_flip(rx_buffer, xdp->frame_sz); } + + return skb; } /** @@ -2333,25 +2359,6 @@ xdp_out: } /** - * i40e_rx_buffer_flip - adjusted rx_buffer to point to an unused region - * @rx_ring: Rx ring - * @rx_buffer: Rx buffer to adjust - * @size: Size of adjustment - **/ -static void i40e_rx_buffer_flip(struct i40e_ring *rx_ring, - struct i40e_rx_buffer *rx_buffer, - unsigned int size) -{ - unsigned int truesize = i40e_rx_frame_truesize(rx_ring, size); - -#if (PAGE_SIZE < 8192) - rx_buffer->page_offset ^= truesize; -#else - rx_buffer->page_offset += truesize; -#endif -} - -/** * i40e_xdp_ring_update_tail - Updates the XDP Tx ring tail register * @xdp_ring: XDP Tx ring * @@ -2409,16 +2416,65 @@ void i40e_finalize_xdp_rx(struct i40e_ring *rx_ring, unsigned int xdp_res) } /** - * i40e_inc_ntc: Advance the next_to_clean index + * i40e_inc_ntp: Advance the next_to_process index * @rx_ring: Rx ring **/ -static void i40e_inc_ntc(struct i40e_ring *rx_ring) +static void i40e_inc_ntp(struct i40e_ring *rx_ring) +{ + u32 ntp = rx_ring->next_to_process + 1; + + ntp = (ntp < rx_ring->count) ? ntp : 0; + rx_ring->next_to_process = ntp; + prefetch(I40E_RX_DESC(rx_ring, ntp)); +} + +/** + * i40e_add_xdp_frag: Add a frag to xdp_buff + * @xdp: xdp_buff pointing to the data + * @nr_frags: return number of buffers for the packet + * @rx_buffer: rx_buffer holding data of the current frag + * @size: size of data of current frag + */ +static int i40e_add_xdp_frag(struct xdp_buff *xdp, u32 *nr_frags, + struct i40e_rx_buffer *rx_buffer, u32 size) { - u32 ntc = rx_ring->next_to_clean + 1; + struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp); + + if (!xdp_buff_has_frags(xdp)) { + sinfo->nr_frags = 0; + sinfo->xdp_frags_size = 0; + xdp_buff_set_frags_flag(xdp); + } else if (unlikely(sinfo->nr_frags >= MAX_SKB_FRAGS)) { + /* Overflowing packet: All frags need to be dropped */ + return -ENOMEM; + } + + __skb_fill_page_desc_noacc(sinfo, sinfo->nr_frags++, rx_buffer->page, + rx_buffer->page_offset, size); + + sinfo->xdp_frags_size += size; - ntc = (ntc < rx_ring->count) ? ntc : 0; - rx_ring->next_to_clean = ntc; - prefetch(I40E_RX_DESC(rx_ring, ntc)); + if (page_is_pfmemalloc(rx_buffer->page)) + xdp_buff_set_frag_pfmemalloc(xdp); + *nr_frags = sinfo->nr_frags; + + return 0; +} + +/** + * i40e_consume_xdp_buff - Consume all the buffers of the packet and update ntc + * @rx_ring: rx descriptor ring to transact packets on + * @xdp: xdp_buff pointing to the data + * @rx_buffer: rx_buffer of eop desc + */ +static void i40e_consume_xdp_buff(struct i40e_ring *rx_ring, + struct xdp_buff *xdp, + struct i40e_rx_buffer *rx_buffer) +{ + i40e_process_rx_buffs(rx_ring, I40E_XDP_CONSUMED, xdp); + i40e_put_rx_buffer(rx_ring, rx_buffer); + rx_ring->next_to_clean = rx_ring->next_to_process; + xdp->data = NULL; } /** @@ -2437,38 +2493,36 @@ static void i40e_inc_ntc(struct i40e_ring *rx_ring) static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget, unsigned int *rx_cleaned) { - unsigned int total_rx_bytes = 0, total_rx_packets = 0, frame_sz = 0; + unsigned int total_rx_bytes = 0, total_rx_packets = 0; u16 cleaned_count = I40E_DESC_UNUSED(rx_ring); + u16 clean_threshold = rx_ring->count / 2; unsigned int offset = rx_ring->rx_offset; - struct sk_buff *skb = rx_ring->skb; + struct xdp_buff *xdp = &rx_ring->xdp; unsigned int xdp_xmit = 0; struct bpf_prog *xdp_prog; bool failure = false; - struct xdp_buff xdp; int xdp_res = 0; -#if (PAGE_SIZE < 8192) - frame_sz = i40e_rx_frame_truesize(rx_ring, 0); -#endif - xdp_init_buff(&xdp, frame_sz, &rx_ring->xdp_rxq); - xdp_prog = READ_ONCE(rx_ring->xdp_prog); while (likely(total_rx_packets < (unsigned int)budget)) { + u16 ntp = rx_ring->next_to_process; struct i40e_rx_buffer *rx_buffer; union i40e_rx_desc *rx_desc; - int rx_buffer_pgcnt; + struct sk_buff *skb; unsigned int size; + u32 nfrags = 0; + bool neop; u64 qword; /* return some buffers to hardware, one at a time is too slow */ - if (cleaned_count >= I40E_RX_BUFFER_WRITE) { + if (cleaned_count >= clean_threshold) { failure = failure || i40e_alloc_rx_buffers(rx_ring, cleaned_count); cleaned_count = 0; } - rx_desc = I40E_RX_DESC(rx_ring, rx_ring->next_to_clean); + rx_desc = I40E_RX_DESC(rx_ring, ntp); /* status_error_len will always be zero for unused descriptors * because it's cleared in cleanup, and overlaps with hdr_addr @@ -2487,8 +2541,8 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget, i40e_clean_programming_status(rx_ring, rx_desc->raw.qword[0], qword); - rx_buffer = i40e_rx_bi(rx_ring, rx_ring->next_to_clean); - i40e_inc_ntc(rx_ring); + rx_buffer = i40e_rx_bi(rx_ring, ntp); + i40e_inc_ntp(rx_ring); i40e_reuse_rx_page(rx_ring, rx_buffer); cleaned_count++; continue; @@ -2499,76 +2553,84 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget, if (!size) break; - i40e_trace(clean_rx_irq, rx_ring, rx_desc, skb); - rx_buffer = i40e_get_rx_buffer(rx_ring, size, &rx_buffer_pgcnt); - + i40e_trace(clean_rx_irq, rx_ring, rx_desc, xdp); /* retrieve a buffer from the ring */ - if (!skb) { + rx_buffer = i40e_get_rx_buffer(rx_ring, size); + + neop = i40e_is_non_eop(rx_ring, rx_desc); + i40e_inc_ntp(rx_ring); + + if (!xdp->data) { unsigned char *hard_start; hard_start = page_address(rx_buffer->page) + rx_buffer->page_offset - offset; - xdp_prepare_buff(&xdp, hard_start, offset, size, true); - xdp_buff_clear_frags_flag(&xdp); + xdp_prepare_buff(xdp, hard_start, offset, size, true); #if (PAGE_SIZE > 4096) /* At larger PAGE_SIZE, frame_sz depend on len size */ - xdp.frame_sz = i40e_rx_frame_truesize(rx_ring, size); + xdp->frame_sz = i40e_rx_frame_truesize(rx_ring, size); #endif - xdp_res = i40e_run_xdp(rx_ring, &xdp, xdp_prog); + } else if (i40e_add_xdp_frag(xdp, &nfrags, rx_buffer, size) && + !neop) { + /* Overflowing packet: Drop all frags on EOP */ + i40e_consume_xdp_buff(rx_ring, xdp, rx_buffer); + break; } + if (neop) + continue; + + xdp_res = i40e_run_xdp(rx_ring, xdp, xdp_prog); + if (xdp_res) { - if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) { - xdp_xmit |= xdp_res; - i40e_rx_buffer_flip(rx_ring, rx_buffer, size); + xdp_xmit |= xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR); + + if (unlikely(xdp_buff_has_frags(xdp))) { + i40e_process_rx_buffs(rx_ring, xdp_res, xdp); + size = xdp_get_buff_len(xdp); + } else if (xdp_res & (I40E_XDP_TX | I40E_XDP_REDIR)) { + i40e_rx_buffer_flip(rx_buffer, xdp->frame_sz); } else { rx_buffer->pagecnt_bias++; } total_rx_bytes += size; - total_rx_packets++; - } else if (skb) { - i40e_add_rx_frag(rx_ring, rx_buffer, skb, size); - } else if (ring_uses_build_skb(rx_ring)) { - skb = i40e_build_skb(rx_ring, rx_buffer, &xdp); } else { - skb = i40e_construct_skb(rx_ring, rx_buffer, &xdp); - } + if (ring_uses_build_skb(rx_ring)) + skb = i40e_build_skb(rx_ring, xdp, nfrags); + else + skb = i40e_construct_skb(rx_ring, xdp, nfrags); + + /* drop if we failed to retrieve a buffer */ + if (!skb) { + rx_ring->rx_stats.alloc_buff_failed++; + i40e_consume_xdp_buff(rx_ring, xdp, rx_buffer); + break; + } - /* exit if we failed to retrieve a buffer */ - if (!xdp_res && !skb) { - rx_ring->rx_stats.alloc_buff_failed++; - rx_buffer->pagecnt_bias++; - break; - } + if (i40e_cleanup_headers(rx_ring, skb, rx_desc)) + goto process_next; - i40e_put_rx_buffer(rx_ring, rx_buffer, rx_buffer_pgcnt); - cleaned_count++; + /* probably a little skewed due to removing CRC */ + total_rx_bytes += skb->len; - i40e_inc_ntc(rx_ring); - if (i40e_is_non_eop(rx_ring, rx_desc)) - continue; + /* populate checksum, VLAN, and protocol */ + i40e_process_skb_fields(rx_ring, rx_desc, skb); - if (xdp_res || i40e_cleanup_headers(rx_ring, skb, rx_desc)) { - skb = NULL; - continue; + i40e_trace(clean_rx_irq_rx, rx_ring, rx_desc, xdp); + napi_gro_receive(&rx_ring->q_vector->napi, skb); } - /* probably a little skewed due to removing CRC */ - total_rx_bytes += skb->len; - - /* populate checksum, VLAN, and protocol */ - i40e_process_skb_fields(rx_ring, rx_desc, skb); - - i40e_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb); - napi_gro_receive(&rx_ring->q_vector->napi, skb); - skb = NULL; - /* update budget accounting */ total_rx_packets++; +process_next: + cleaned_count += nfrags + 1; + i40e_put_rx_buffer(rx_ring, rx_buffer); + rx_ring->next_to_clean = rx_ring->next_to_process; + + xdp->data = NULL; } i40e_finalize_xdp_rx(rx_ring, xdp_xmit); - rx_ring->skb = skb; i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets); @@ -3001,7 +3063,7 @@ static inline int i40e_tx_prepare_vlan_flags(struct sk_buff *skb, rc = skb_cow_head(skb, 0); if (rc < 0) return rc; - vhdr = (struct vlan_ethhdr *)skb->data; + vhdr = skb_vlan_eth_hdr(skb); vhdr->h_vlan_TCI = htons(tx_flags >> I40E_TX_FLAGS_VLAN_SHIFT); } else { diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 768290dc6f48..8c3d24012c54 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -277,6 +277,7 @@ struct i40e_rx_buffer { struct page *page; __u32 page_offset; __u16 pagecnt_bias; + __u32 page_count; }; struct i40e_queue_stats { @@ -336,6 +337,17 @@ struct i40e_ring { u8 dcb_tc; /* Traffic class of ring */ u8 __iomem *tail; + /* Storing xdp_buff on ring helps in saving the state of partially built + * packet when i40e_clean_rx_ring_irq() must return before it sees EOP + * and to resume packet building for this ring in the next call to + * i40e_clean_rx_ring_irq(). + */ + struct xdp_buff xdp; + + /* Next descriptor to be processed; next_to_clean is updated only on + * processing EOP descriptor + */ + u16 next_to_process; /* high bit set means dynamic, use accessor routines to read/write. * hardware only supports 2us resolution for the ITR registers. * these values always store the USER setting, and must be converted @@ -380,14 +392,6 @@ struct i40e_ring { struct rcu_head rcu; /* to avoid race on free */ u16 next_to_alloc; - struct sk_buff *skb; /* When i40e_clean_rx_ring_irq() must - * return before it sees the EOP for - * the current packet, we save that skb - * here and resume receiving this - * packet the next time - * i40e_clean_rx_ring_irq() is called - * for this ring. - */ struct i40e_channel *ch; u16 rx_offset; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 8a4587585acd..be59ba3774e1 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -2915,6 +2915,72 @@ static inline int i40e_check_vf_permission(struct i40e_vf *vf, } /** + * i40e_vc_ether_addr_type - get type of virtchnl_ether_addr + * @vc_ether_addr: used to extract the type + **/ +static u8 +i40e_vc_ether_addr_type(struct virtchnl_ether_addr *vc_ether_addr) +{ + return vc_ether_addr->type & VIRTCHNL_ETHER_ADDR_TYPE_MASK; +} + +/** + * i40e_is_vc_addr_legacy + * @vc_ether_addr: VIRTCHNL structure that contains MAC and type + * + * check if the MAC address is from an older VF + **/ +static bool +i40e_is_vc_addr_legacy(struct virtchnl_ether_addr *vc_ether_addr) +{ + return i40e_vc_ether_addr_type(vc_ether_addr) == + VIRTCHNL_ETHER_ADDR_LEGACY; +} + +/** + * i40e_is_vc_addr_primary + * @vc_ether_addr: VIRTCHNL structure that contains MAC and type + * + * check if the MAC address is the VF's primary MAC + * This function should only be called when the MAC address in + * virtchnl_ether_addr is a valid unicast MAC + **/ +static bool +i40e_is_vc_addr_primary(struct virtchnl_ether_addr *vc_ether_addr) +{ + return i40e_vc_ether_addr_type(vc_ether_addr) == + VIRTCHNL_ETHER_ADDR_PRIMARY; +} + +/** + * i40e_update_vf_mac_addr + * @vf: VF to update + * @vc_ether_addr: structure from VIRTCHNL with MAC to add + * + * update the VF's cached hardware MAC if allowed + **/ +static void +i40e_update_vf_mac_addr(struct i40e_vf *vf, + struct virtchnl_ether_addr *vc_ether_addr) +{ + u8 *mac_addr = vc_ether_addr->addr; + + if (!is_valid_ether_addr(mac_addr)) + return; + + /* If request to add MAC filter is a primary request update its default + * MAC address with the requested one. If it is a legacy request then + * check if current default is empty if so update the default MAC + */ + if (i40e_is_vc_addr_primary(vc_ether_addr)) { + ether_addr_copy(vf->default_lan_addr.addr, mac_addr); + } else if (i40e_is_vc_addr_legacy(vc_ether_addr)) { + if (is_zero_ether_addr(vf->default_lan_addr.addr)) + ether_addr_copy(vf->default_lan_addr.addr, mac_addr); + } +} + +/** * i40e_vc_add_mac_addr_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -2965,11 +3031,8 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg) spin_unlock_bh(&vsi->mac_filter_hash_lock); goto error_param; } - if (is_valid_ether_addr(al->list[i].addr) && - is_zero_ether_addr(vf->default_lan_addr.addr)) - ether_addr_copy(vf->default_lan_addr.addr, - al->list[i].addr); } + i40e_update_vf_mac_addr(vf, &al->list[i]); } spin_unlock_bh(&vsi->mac_filter_hash_lock); @@ -3032,6 +3095,9 @@ static int i40e_vc_del_mac_addr_msg(struct i40e_vf *vf, u8 *msg) spin_unlock_bh(&vsi->mac_filter_hash_lock); + if (was_unimac_deleted) + eth_zero_addr(vf->default_lan_addr.addr); + /* program the updated filter list */ ret = i40e_sync_vsi_filters(vsi); if (ret) diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 232bc61d9eee..39d0fe76a38f 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -6,7 +6,6 @@ #include <linux/module.h> #include <linux/pci.h> -#include <linux/aer.h> #include <linux/netdevice.h> #include <linux/vmalloc.h> #include <linux/interrupt.h> @@ -59,8 +58,6 @@ enum iavf_vsi_state_t { struct iavf_vsi { struct iavf_adapter *back; struct net_device *netdev; - unsigned long active_cvlans[BITS_TO_LONGS(VLAN_N_VID)]; - unsigned long active_svlans[BITS_TO_LONGS(VLAN_N_VID)]; u16 seid; u16 id; DECLARE_BITMAP(state, __IAVF_VSI_STATE_SIZE__); @@ -158,15 +155,20 @@ struct iavf_vlan { u16 tpid; }; +enum iavf_vlan_state_t { + IAVF_VLAN_INVALID, + IAVF_VLAN_ADD, /* filter needs to be added */ + IAVF_VLAN_IS_NEW, /* filter is new, wait for PF answer */ + IAVF_VLAN_ACTIVE, /* filter is accepted by PF */ + IAVF_VLAN_DISABLE, /* filter needs to be deleted by PF, then marked INACTIVE */ + IAVF_VLAN_INACTIVE, /* filter is inactive, we are in IFF_DOWN */ + IAVF_VLAN_REMOVE, /* filter needs to be removed from list */ +}; + struct iavf_vlan_filter { struct list_head list; struct iavf_vlan vlan; - struct { - u8 is_new_vlan:1; /* filter is new, wait for PF answer */ - u8 remove:1; /* filter needs to be removed */ - u8 add:1; /* filter needs to be added */ - u8 padding:5; - }; + enum iavf_vlan_state_t state; }; #define IAVF_MAX_TRAFFIC_CLASS 4 @@ -258,6 +260,7 @@ struct iavf_adapter { wait_queue_head_t vc_waitqueue; struct iavf_q_vector *q_vectors; struct list_head vlan_filter_list; + int num_vlan_filters; struct list_head mac_filter_list; struct mutex crit_lock; struct mutex client_lock; @@ -522,7 +525,7 @@ void iavf_set_ethtool_ops(struct net_device *netdev); void iavf_update_stats(struct iavf_adapter *adapter); void iavf_reset_interrupt_capability(struct iavf_adapter *adapter); int iavf_init_interrupt_scheme(struct iavf_adapter *adapter); -void iavf_irq_enable_queues(struct iavf_adapter *adapter, u32 mask); +void iavf_irq_enable_queues(struct iavf_adapter *adapter); void iavf_free_all_tx_resources(struct iavf_adapter *adapter); void iavf_free_all_rx_resources(struct iavf_adapter *adapter); diff --git a/drivers/net/ethernet/intel/iavf/iavf_common.c b/drivers/net/ethernet/intel/iavf/iavf_common.c index 16c490965b61..dd11dbbd5551 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_common.c +++ b/drivers/net/ethernet/intel/iavf/iavf_common.c @@ -661,7 +661,7 @@ struct iavf_rx_ptype_decoded iavf_ptype_lookup[BIT(8)] = { /* Non Tunneled IPv6 */ IAVF_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3), IAVF_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY3), + IAVF_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY4), IAVF_PTT_UNUSED_ENTRY(91), IAVF_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP, PAY4), IAVF_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4), diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 3273aeb8fa67..4a66873882d1 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -359,21 +359,18 @@ 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) +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); } } @@ -387,7 +384,7 @@ 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); @@ -791,7 +788,8 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, f->vlan = vlan; list_add_tail(&f->list, &adapter->vlan_filter_list); - f->add = true; + f->state = IAVF_VLAN_ADD; + adapter->num_vlan_filters++; adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; } @@ -813,7 +811,7 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan) f = iavf_find_vlan(adapter, vlan); if (f) { - f->remove = true; + f->state = IAVF_VLAN_REMOVE; adapter->aq_required |= IAVF_FLAG_AQ_DEL_VLAN_FILTER; } @@ -828,14 +826,18 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan) **/ static void iavf_restore_filters(struct iavf_adapter *adapter) { - u16 vid; + struct iavf_vlan_filter *f; /* re-add all VLAN filters */ - for_each_set_bit(vid, adapter->vsi.active_cvlans, VLAN_N_VID) - iavf_add_vlan(adapter, IAVF_VLAN(vid, ETH_P_8021Q)); + 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; + } - for_each_set_bit(vid, adapter->vsi.active_svlans, VLAN_N_VID) - iavf_add_vlan(adapter, IAVF_VLAN(vid, ETH_P_8021AD)); + spin_unlock_bh(&adapter->mac_vlan_list_lock); + adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; } /** @@ -844,8 +846,7 @@ static void iavf_restore_filters(struct iavf_adapter *adapter) */ u16 iavf_get_num_vlans_added(struct iavf_adapter *adapter) { - return bitmap_weight(adapter->vsi.active_cvlans, VLAN_N_VID) + - bitmap_weight(adapter->vsi.active_svlans, VLAN_N_VID); + return adapter->num_vlan_filters; } /** @@ -893,6 +894,10 @@ static int iavf_vlan_rx_add_vid(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); + /* 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; @@ -919,12 +924,11 @@ static int iavf_vlan_rx_kill_vid(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); - iavf_del_vlan(adapter, IAVF_VLAN(vid, be16_to_cpu(proto))); - if (proto == cpu_to_be16(ETH_P_8021Q)) - clear_bit(vid, adapter->vsi.active_cvlans); - else - clear_bit(vid, adapter->vsi.active_svlans); + /* We do not track VLAN 0 filter */ + if (!vid) + return 0; + iavf_del_vlan(adapter, IAVF_VLAN(vid, be16_to_cpu(proto))); return 0; } @@ -1285,16 +1289,11 @@ static void iavf_clear_mac_vlan_filters(struct iavf_adapter *adapter) } } - /* remove all VLAN filters */ + /* disable all VLAN filters */ list_for_each_entry_safe(vlf, vlftmp, &adapter->vlan_filter_list, - list) { - if (vlf->add) { - list_del(&vlf->list); - kfree(vlf); - } else { - vlf->remove = true; - } - } + list) + vlf->state = IAVF_VLAN_DISABLE; + spin_unlock_bh(&adapter->mac_vlan_list_lock); } @@ -2906,6 +2905,7 @@ 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); @@ -3123,9 +3123,6 @@ continue_reset: adapter->aq_required |= IAVF_FLAG_AQ_ADD_CLOUD_FILTER; iavf_misc_irq_enable(adapter); - bitmap_clear(adapter->vsi.active_cvlans, 0, VLAN_N_VID); - bitmap_clear(adapter->vsi.active_svlans, 0, VLAN_N_VID); - mod_delayed_work(adapter->wq, &adapter->watchdog_task, 2); /* We were running when the reset started, so we need to restore some @@ -5066,6 +5063,11 @@ static void iavf_remove(struct pci_dev *pdev) mutex_unlock(&adapter->crit_lock); break; } + /* Simply return if we already went through iavf_shutdown */ + if (adapter->state == __IAVF_REMOVE) { + mutex_unlock(&adapter->crit_lock); + return; + } mutex_unlock(&adapter->crit_lock); usleep_range(500, 1000); diff --git a/drivers/net/ethernet/intel/iavf/iavf_register.h b/drivers/net/ethernet/intel/iavf/iavf_register.h index bf793332fc9d..a19e88898a0b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_register.h +++ b/drivers/net/ethernet/intel/iavf/iavf_register.h @@ -40,7 +40,7 @@ #define IAVF_VFINT_DYN_CTL01_INTENA_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTL01_INTENA_SHIFT) #define IAVF_VFINT_DYN_CTL01_ITR_INDX_SHIFT 3 #define IAVF_VFINT_DYN_CTL01_ITR_INDX_MASK IAVF_MASK(0x3, IAVF_VFINT_DYN_CTL01_ITR_INDX_SHIFT) -#define IAVF_VFINT_DYN_CTLN1(_INTVF) (0x00003800 + ((_INTVF) * 4)) /* _i=0...15 */ /* Reset: VFR */ +#define IAVF_VFINT_DYN_CTLN1(_INTVF) (0x00003800 + ((_INTVF) * 4)) /* _i=0...63 */ /* Reset: VFR */ #define IAVF_VFINT_DYN_CTLN1_INTENA_SHIFT 0 #define IAVF_VFINT_DYN_CTLN1_INTENA_MASK IAVF_MASK(0x1, IAVF_VFINT_DYN_CTLN1_INTENA_SHIFT) #define IAVF_VFINT_DYN_CTLN1_SWINT_TRIG_SHIFT 2 diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index 18b6a702a1d6..e989feda133c 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -1096,7 +1096,7 @@ static inline void iavf_rx_hash(struct iavf_ring *ring, cpu_to_le64((u64)IAVF_RX_DESC_FLTSTAT_RSS_HASH << IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT); - if (ring->netdev->features & NETIF_F_RXHASH) + if (!(ring->netdev->features & NETIF_F_RXHASH)) return; if ((rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask) { diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 6d23338604bb..7c0578b5457b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -642,16 +642,10 @@ static void iavf_vlan_add_reject(struct iavf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->is_new_vlan) { - if (f->vlan.tpid == ETH_P_8021Q) - clear_bit(f->vlan.vid, - adapter->vsi.active_cvlans); - else - clear_bit(f->vlan.vid, - adapter->vsi.active_svlans); - + if (f->state == IAVF_VLAN_IS_NEW) { list_del(&f->list); kfree(f); + adapter->num_vlan_filters--; } } spin_unlock_bh(&adapter->mac_vlan_list_lock); @@ -679,7 +673,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->add) + if (f->state == IAVF_VLAN_ADD) count++; } if (!count || !VLAN_FILTERING_ALLOWED(adapter)) { @@ -710,11 +704,10 @@ void iavf_add_vlans(struct iavf_adapter *adapter) vvfl->vsi_id = adapter->vsi_res->vsi_id; vvfl->num_elements = count; list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->add) { + if (f->state == IAVF_VLAN_ADD) { vvfl->vlan_id[i] = f->vlan.vid; i++; - f->add = false; - f->is_new_vlan = true; + f->state = IAVF_VLAN_IS_NEW; if (i == count) break; } @@ -760,7 +753,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) vvfl_v2->vport_id = adapter->vsi_res->vsi_id; vvfl_v2->num_elements = count; list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->add) { + if (f->state == IAVF_VLAN_ADD) { struct virtchnl_vlan_supported_caps *filtering_support = &adapter->vlan_v2_caps.filtering.filtering_support; struct virtchnl_vlan *vlan; @@ -778,8 +771,7 @@ void iavf_add_vlans(struct iavf_adapter *adapter) vlan->tpid = f->vlan.tpid; i++; - f->add = false; - f->is_new_vlan = true; + f->state = IAVF_VLAN_IS_NEW; } } @@ -822,10 +814,16 @@ void iavf_del_vlans(struct iavf_adapter *adapter) * filters marked for removal to enable bailing out before * sending a virtchnl message */ - if (f->remove && !VLAN_FILTERING_ALLOWED(adapter)) { + if (f->state == IAVF_VLAN_REMOVE && + !VLAN_FILTERING_ALLOWED(adapter)) { list_del(&f->list); kfree(f); - } else if (f->remove) { + adapter->num_vlan_filters--; + } else if (f->state == IAVF_VLAN_DISABLE && + !VLAN_FILTERING_ALLOWED(adapter)) { + f->state = IAVF_VLAN_INACTIVE; + } else if (f->state == IAVF_VLAN_REMOVE || + f->state == IAVF_VLAN_DISABLE) { count++; } } @@ -857,11 +855,18 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vvfl->vsi_id = adapter->vsi_res->vsi_id; vvfl->num_elements = count; list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->remove) { + if (f->state == IAVF_VLAN_DISABLE) { vvfl->vlan_id[i] = f->vlan.vid; + f->state = IAVF_VLAN_INACTIVE; i++; + if (i == count) + break; + } else if (f->state == IAVF_VLAN_REMOVE) { + vvfl->vlan_id[i] = f->vlan.vid; list_del(&f->list); kfree(f); + adapter->num_vlan_filters--; + i++; if (i == count) break; } @@ -901,7 +906,8 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vvfl_v2->vport_id = adapter->vsi_res->vsi_id; vvfl_v2->num_elements = count; list_for_each_entry_safe(f, ftmp, &adapter->vlan_filter_list, list) { - if (f->remove) { + if (f->state == IAVF_VLAN_DISABLE || + f->state == IAVF_VLAN_REMOVE) { struct virtchnl_vlan_supported_caps *filtering_support = &adapter->vlan_v2_caps.filtering.filtering_support; struct virtchnl_vlan *vlan; @@ -915,8 +921,13 @@ void iavf_del_vlans(struct iavf_adapter *adapter) vlan->tci = f->vlan.vid; vlan->tpid = f->vlan.tpid; - list_del(&f->list); - kfree(f); + if (f->state == IAVF_VLAN_DISABLE) { + f->state = IAVF_VLAN_INACTIVE; + } else { + list_del(&f->list); + kfree(f); + adapter->num_vlan_filters--; + } i++; if (i == count) break; @@ -2192,7 +2203,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, list_for_each_entry(vlf, &adapter->vlan_filter_list, list) - vlf->add = true; + vlf->state = IAVF_VLAN_ADD; adapter->aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; @@ -2227,11 +2238,6 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, iavf_process_config(adapter); adapter->flags |= IAVF_FLAG_SETUP_NETDEV_FEATURES; - /* Request VLAN offload settings */ - if (VLAN_V2_ALLOWED(adapter)) - iavf_set_vlan_offload_features(adapter, 0, - netdev->features); - iavf_set_queue_vlan_tag_loc(adapter); was_mac_changed = !ether_addr_equal(netdev->dev_addr, @@ -2260,7 +2266,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, list_for_each_entry(vlf, &adapter->vlan_filter_list, list) - vlf->add = true; + vlf->state = IAVF_VLAN_ADD; aq_required |= IAVF_FLAG_AQ_ADD_VLAN_FILTER; } @@ -2444,17 +2450,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, spin_lock_bh(&adapter->mac_vlan_list_lock); list_for_each_entry(f, &adapter->vlan_filter_list, list) { - if (f->is_new_vlan) { - f->is_new_vlan = false; - if (!f->vlan.vid) - continue; - if (f->vlan.tpid == ETH_P_8021Q) - set_bit(f->vlan.vid, - adapter->vsi.active_cvlans); - else - set_bit(f->vlan.vid, - adapter->vsi.active_svlans); - } + if (f->state == IAVF_VLAN_IS_NEW) + f->state = IAVF_VLAN_ACTIVE; } spin_unlock_bh(&adapter->mac_vlan_list_lock); } diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index b0e29e342401..aa32111afd6e 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -20,7 +20,6 @@ #include <linux/pci.h> #include <linux/workqueue.h> #include <linux/wait.h> -#include <linux/aer.h> #include <linux/interrupt.h> #include <linux/ethtool.h> #include <linux/timer.h> @@ -509,6 +508,7 @@ enum ice_pf_flags { ICE_FLAG_VF_VLAN_PRUNING, ICE_FLAG_LINK_LENIENT_MODE_ENA, ICE_FLAG_PLUG_AUX_DEV, + ICE_FLAG_UNPLUG_AUX_DEV, ICE_FLAG_MTU_CHANGED, ICE_FLAG_GNSS, /* GNSS successfully initialized */ ICE_PF_FLAGS_NBITS /* must be last */ @@ -955,16 +955,11 @@ static inline void ice_set_rdma_cap(struct ice_pf *pf) */ static inline void ice_clear_rdma_cap(struct ice_pf *pf) { - /* We can directly unplug aux device here only if the flag bit - * ICE_FLAG_PLUG_AUX_DEV is not set because ice_unplug_aux_dev() - * could race with ice_plug_aux_dev() called from - * ice_service_task(). In this case we only clear that bit now and - * aux device will be unplugged later once ice_plug_aux_device() - * called from ice_service_task() finishes (see ice_service_task()). + /* defer unplug to service task to avoid RTNL lock and + * clear PLUG bit so that pending plugs don't interfere */ - if (!test_and_clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) - ice_unplug_aux_dev(pf); - + clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags); + set_bit(ICE_FLAG_UNPLUG_AUX_DEV, pf->flags); clear_bit(ICE_FLAG_RDMA_ENA, pf->flags); } #endif /* _ICE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index c2fda4fa4188..eb2dc0983776 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -1619,7 +1619,6 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq, { struct ice_aq_desc desc_cpy; bool is_cmd_for_retry; - u8 *buf_cpy = NULL; u8 idx = 0; u16 opcode; int status; @@ -1629,11 +1628,8 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq, memset(&desc_cpy, 0, sizeof(desc_cpy)); if (is_cmd_for_retry) { - if (buf) { - buf_cpy = kzalloc(buf_size, GFP_KERNEL); - if (!buf_cpy) - return -ENOMEM; - } + /* All retryable cmds are direct, without buf. */ + WARN_ON(buf); memcpy(&desc_cpy, desc, sizeof(desc_cpy)); } @@ -1645,17 +1641,12 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq, hw->adminq.sq_last_status != ICE_AQ_RC_EBUSY) break; - if (buf_cpy) - memcpy(buf, buf_cpy, buf_size); - memcpy(desc, &desc_cpy, sizeof(desc_cpy)); - mdelay(ICE_SQ_SEND_DELAY_TIME_MS); + msleep(ICE_SQ_SEND_DELAY_TIME_MS); } while (++idx < ICE_SQ_SEND_MAX_EXECUTE); - kfree(buf_cpy); - return status; } @@ -1992,19 +1983,19 @@ ice_acquire_res_exit: */ void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res) { - u32 total_delay = 0; + unsigned long timeout; int status; - status = ice_aq_release_res(hw, res, 0, NULL); - /* there are some rare cases when trying to release the resource * results in an admin queue timeout, so handle them correctly */ - while ((status == -EIO) && (total_delay < hw->adminq.sq_cmd_timeout)) { - mdelay(1); + timeout = jiffies + 10 * ICE_CTL_Q_SQ_CMD_TIMEOUT; + do { status = ice_aq_release_res(hw, res, 0, NULL); - total_delay++; - } + if (status != -EIO) + break; + usleep_range(1000, 2000); + } while (time_before(jiffies, timeout)); } /** @@ -5169,7 +5160,7 @@ ice_aq_read_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, */ int ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, - u16 bus_addr, __le16 addr, u8 params, u8 *data, + u16 bus_addr, __le16 addr, u8 params, const u8 *data, struct ice_sq_cd *cd) { struct ice_aq_desc desc = { 0 }; diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index 8ba5f935a092..81961a7d6598 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -229,7 +229,7 @@ ice_aq_read_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, struct ice_sq_cd *cd); int ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr, - u16 bus_addr, __le16 addr, u8 params, u8 *data, + u16 bus_addr, __le16 addr, u8 params, const u8 *data, struct ice_sq_cd *cd); bool ice_fw_supports_report_dflt_cfg(struct ice_hw *hw); #endif /* _ICE_COMMON_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c index 6bcfee295991..d2faf1baad2f 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.c +++ b/drivers/net/ethernet/intel/ice/ice_controlq.c @@ -637,9 +637,6 @@ static int ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) return -EIO; } - /* setup SQ command write back timeout */ - cq->sq_cmd_timeout = ICE_CTL_Q_SQ_CMD_TIMEOUT; - /* allocate the ATQ */ ret_code = ice_init_sq(hw, cq); if (ret_code) @@ -967,7 +964,7 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, struct ice_aq_desc *desc_on_ring; bool cmd_completed = false; struct ice_sq_cd *details; - u32 total_delay = 0; + unsigned long timeout; int status = 0; u16 retval = 0; u32 val = 0; @@ -1060,13 +1057,14 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, cq->sq.next_to_use = 0; wr32(hw, cq->sq.tail, cq->sq.next_to_use); + timeout = jiffies + ICE_CTL_Q_SQ_CMD_TIMEOUT; do { if (ice_sq_done(hw, cq)) break; - udelay(ICE_CTL_Q_SQ_CMD_USEC); - total_delay++; - } while (total_delay < cq->sq_cmd_timeout); + usleep_range(ICE_CTL_Q_SQ_CMD_USEC, + ICE_CTL_Q_SQ_CMD_USEC * 3 / 2); + } while (time_before(jiffies, timeout)); /* if ready, copy the desc back to temp */ if (ice_sq_done(hw, cq)) { diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.h b/drivers/net/ethernet/intel/ice/ice_controlq.h index c07e9cc9fc6e..950b7f4a7a05 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.h +++ b/drivers/net/ethernet/intel/ice/ice_controlq.h @@ -34,7 +34,7 @@ enum ice_ctl_q { }; /* Control Queue timeout settings - max delay 1s */ -#define ICE_CTL_Q_SQ_CMD_TIMEOUT 10000 /* Count 10000 times */ +#define ICE_CTL_Q_SQ_CMD_TIMEOUT HZ /* Wait max 1s */ #define ICE_CTL_Q_SQ_CMD_USEC 100 /* Check every 100usec */ #define ICE_CTL_Q_ADMIN_INIT_TIMEOUT 10 /* Count 10 times */ #define ICE_CTL_Q_ADMIN_INIT_MSEC 100 /* Check every 100msec */ @@ -87,7 +87,6 @@ struct ice_ctl_q_info { enum ice_ctl_q qtype; struct ice_ctl_q_ring rq; /* receive queue */ struct ice_ctl_q_ring sq; /* send queue */ - u32 sq_cmd_timeout; /* send queue cmd write back timeout */ u16 num_rq_entries; /* receive queue depth */ u16 num_sq_entries; /* send queue depth */ u16 rq_buf_size; /* receive queue buffer size */ diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index c6d4926f0fcf..850db8e0e6b0 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -932,10 +932,9 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_tx_ring *tx_ring, if ((first->tx_flags & ICE_TX_FLAGS_HW_VLAN || first->tx_flags & ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN) || skb->priority != TC_PRIO_CONTROL) { - first->tx_flags &= ~ICE_TX_FLAGS_VLAN_PR_M; + first->vid &= ~VLAN_PRIO_MASK; /* Mask the lower 3 bits to set the 802.1p priority */ - first->tx_flags |= (skb->priority & 0x7) << - ICE_TX_FLAGS_VLAN_PR_S; + first->vid |= (skb->priority << VLAN_PRIO_SHIFT) & VLAN_PRIO_MASK; /* if this is not already set it means a VLAN 0 + priority needs * to be offloaded */ diff --git a/drivers/net/ethernet/intel/ice/ice_devlink.c b/drivers/net/ethernet/intel/ice/ice_devlink.c index 05f216af8c81..bc44cc220818 100644 --- a/drivers/net/ethernet/intel/ice/ice_devlink.c +++ b/drivers/net/ethernet/intel/ice/ice_devlink.c @@ -1254,7 +1254,6 @@ static const struct devlink_ops ice_devlink_ops = { .supported_flash_update_params = DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK, .reload_actions = BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) | BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE), - /* The ice driver currently does not support driver reinit */ .reload_down = ice_devlink_reload_down, .reload_up = ice_devlink_reload_up, .port_split = ice_devlink_port_split, diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c index 8dec748bb53a..75c9de675f20 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.c +++ b/drivers/net/ethernet/intel/ice/ice_gnss.c @@ -16,8 +16,8 @@ * * number of bytes written - success * * negative - error code */ -static unsigned int -ice_gnss_do_write(struct ice_pf *pf, unsigned char *buf, unsigned int size) +static int +ice_gnss_do_write(struct ice_pf *pf, const unsigned char *buf, unsigned int size) { struct ice_aqc_link_topo_addr link_topo; struct ice_hw *hw = &pf->hw; @@ -72,39 +72,7 @@ err_out: dev_err(ice_pf_to_dev(pf), "GNSS failed to write, offset=%u, size=%u, err=%d\n", offset, size, err); - return offset; -} - -/** - * ice_gnss_write_pending - Write all pending data to internal GNSS - * @work: GNSS write work structure - */ -static void ice_gnss_write_pending(struct kthread_work *work) -{ - struct gnss_serial *gnss = container_of(work, struct gnss_serial, - write_work); - struct ice_pf *pf = gnss->back; - - if (!pf) - return; - - if (!test_bit(ICE_FLAG_GNSS, pf->flags)) - return; - - if (!list_empty(&gnss->queue)) { - struct gnss_write_buf *write_buf = NULL; - unsigned int bytes; - - write_buf = list_first_entry(&gnss->queue, - struct gnss_write_buf, queue); - - bytes = ice_gnss_do_write(pf, write_buf->buf, write_buf->size); - dev_dbg(ice_pf_to_dev(pf), "%u bytes written to GNSS\n", bytes); - - list_del(&write_buf->queue); - kfree(write_buf->buf); - kfree(write_buf); - } + return err; } /** @@ -117,6 +85,7 @@ static void ice_gnss_read(struct kthread_work *work) { struct gnss_serial *gnss = container_of(work, struct gnss_serial, read_work.work); + unsigned long delay = ICE_GNSS_POLL_DATA_DELAY_TIME; unsigned int i, bytes_read, data_len, count; struct ice_aqc_link_topo_addr link_topo; struct ice_pf *pf; @@ -127,20 +96,10 @@ static void ice_gnss_read(struct kthread_work *work) int err = 0; pf = gnss->back; - if (!pf) { - err = -EFAULT; - goto exit; - } - - if (!test_bit(ICE_FLAG_GNSS, pf->flags)) + if (!pf || !test_bit(ICE_FLAG_GNSS, pf->flags)) return; hw = &pf->hw; - buf = (char *)get_zeroed_page(GFP_KERNEL); - if (!buf) { - err = -ENOMEM; - goto exit; - } memset(&link_topo, 0, sizeof(struct ice_aqc_link_topo_addr)); link_topo.topo_params.index = ICE_E810T_GNSS_I2C_BUS; @@ -151,25 +110,24 @@ static void ice_gnss_read(struct kthread_work *work) i2c_params = ICE_GNSS_UBX_DATA_LEN_WIDTH | ICE_AQC_I2C_USE_REPEATED_START; - /* Read data length in a loop, when it's not 0 the data is ready */ - for (i = 0; i < ICE_MAX_UBX_READ_TRIES; i++) { - err = ice_aq_read_i2c(hw, link_topo, ICE_GNSS_UBX_I2C_BUS_ADDR, - cpu_to_le16(ICE_GNSS_UBX_DATA_LEN_H), - i2c_params, (u8 *)&data_len_b, NULL); - if (err) - goto exit_buf; + err = ice_aq_read_i2c(hw, link_topo, ICE_GNSS_UBX_I2C_BUS_ADDR, + cpu_to_le16(ICE_GNSS_UBX_DATA_LEN_H), + i2c_params, (u8 *)&data_len_b, NULL); + if (err) + goto requeue; - data_len = be16_to_cpu(data_len_b); - if (data_len != 0 && data_len != U16_MAX) - break; + data_len = be16_to_cpu(data_len_b); + if (data_len == 0 || data_len == U16_MAX) + goto requeue; - mdelay(10); - } + /* The u-blox has data_len bytes for us to read */ data_len = min_t(typeof(data_len), data_len, PAGE_SIZE); - if (!data_len) { + + buf = (char *)get_zeroed_page(GFP_KERNEL); + if (!buf) { err = -ENOMEM; - goto exit_buf; + goto requeue; } /* Read received data */ @@ -183,7 +141,7 @@ static void ice_gnss_read(struct kthread_work *work) cpu_to_le16(ICE_GNSS_UBX_EMPTY_DATA), bytes_read, &buf[i], NULL); if (err) - goto exit_buf; + goto free_buf; } count = gnss_insert_raw(pf->gnss_dev, buf, i); @@ -191,11 +149,11 @@ static void ice_gnss_read(struct kthread_work *work) dev_warn(ice_pf_to_dev(pf), "gnss_insert_raw ret=%d size=%d\n", count, i); -exit_buf: + delay = ICE_GNSS_TIMER_DELAY_TIME; +free_buf: free_page((unsigned long)buf); - kthread_queue_delayed_work(gnss->kworker, &gnss->read_work, - ICE_GNSS_TIMER_DELAY_TIME); -exit: +requeue: + kthread_queue_delayed_work(gnss->kworker, &gnss->read_work, delay); if (err) dev_dbg(ice_pf_to_dev(pf), "GNSS failed to read err=%d\n", err); } @@ -224,8 +182,6 @@ static struct gnss_serial *ice_gnss_struct_init(struct ice_pf *pf) pf->gnss_serial = gnss; kthread_init_delayed_work(&gnss->read_work, ice_gnss_read); - INIT_LIST_HEAD(&gnss->queue); - kthread_init_work(&gnss->write_work, ice_gnss_write_pending); kworker = kthread_create_worker(0, "ice-gnss-%s", dev_name(dev)); if (IS_ERR(kworker)) { kfree(gnss); @@ -285,7 +241,6 @@ static void ice_gnss_close(struct gnss_device *gdev) if (!gnss) return; - kthread_cancel_work_sync(&gnss->write_work); kthread_cancel_delayed_work_sync(&gnss->read_work); } @@ -304,10 +259,7 @@ ice_gnss_write(struct gnss_device *gdev, const unsigned char *buf, size_t count) { struct ice_pf *pf = gnss_get_drvdata(gdev); - struct gnss_write_buf *write_buf; struct gnss_serial *gnss; - unsigned char *cmd_buf; - int err = count; /* We cannot write a single byte using our I2C implementation. */ if (count <= 1 || count > ICE_GNSS_TTY_WRITE_BUF) @@ -323,24 +275,7 @@ ice_gnss_write(struct gnss_device *gdev, const unsigned char *buf, if (!gnss) return -ENODEV; - cmd_buf = kcalloc(count, sizeof(*buf), GFP_KERNEL); - if (!cmd_buf) - return -ENOMEM; - - memcpy(cmd_buf, buf, count); - write_buf = kzalloc(sizeof(*write_buf), GFP_KERNEL); - if (!write_buf) { - kfree(cmd_buf); - return -ENOMEM; - } - - write_buf->buf = cmd_buf; - write_buf->size = count; - INIT_LIST_HEAD(&write_buf->queue); - list_add_tail(&write_buf->queue, &gnss->queue); - kthread_queue_work(gnss->kworker, &gnss->write_work); - - return err; + return ice_gnss_do_write(pf, buf, count); } static const struct gnss_operations ice_gnss_ops = { @@ -436,7 +371,6 @@ void ice_gnss_exit(struct ice_pf *pf) if (pf->gnss_serial) { struct gnss_serial *gnss = pf->gnss_serial; - kthread_cancel_work_sync(&gnss->write_work); kthread_cancel_delayed_work_sync(&gnss->read_work); kthread_destroy_worker(gnss->kworker); gnss->kworker = NULL; diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.h b/drivers/net/ethernet/intel/ice/ice_gnss.h index 4d49e5b0b4b8..75e567ad7059 100644 --- a/drivers/net/ethernet/intel/ice/ice_gnss.h +++ b/drivers/net/ethernet/intel/ice/ice_gnss.h @@ -5,6 +5,7 @@ #define _ICE_GNSS_H_ #define ICE_E810T_GNSS_I2C_BUS 0x2 +#define ICE_GNSS_POLL_DATA_DELAY_TIME (HZ / 50) /* poll every 20 ms */ #define ICE_GNSS_TIMER_DELAY_TIME (HZ / 10) /* 0.1 second per message */ #define ICE_GNSS_TTY_WRITE_BUF 250 #define ICE_MAX_I2C_DATA_SIZE FIELD_MAX(ICE_AQC_I2C_DATA_SIZE_M) @@ -20,29 +21,17 @@ * passed as I2C addr parameter. */ #define ICE_GNSS_UBX_WRITE_BYTES (ICE_MAX_I2C_WRITE_BYTES + 1) -#define ICE_MAX_UBX_READ_TRIES 255 -#define ICE_MAX_UBX_ACK_READ_TRIES 4095 - -struct gnss_write_buf { - struct list_head queue; - unsigned int size; - unsigned char *buf; -}; /** * struct gnss_serial - data used to initialize GNSS TTY port * @back: back pointer to PF * @kworker: kwork thread for handling periodic work * @read_work: read_work function for handling GNSS reads - * @write_work: write_work function for handling GNSS writes - * @queue: write buffers queue */ struct gnss_serial { struct ice_pf *back; struct kthread_worker *kworker; struct kthread_delayed_work read_work; - struct kthread_work write_work; - struct list_head queue; }; #if IS_ENABLED(CONFIG_GNSS) diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 0f52ea38b6f3..11ae0e41f518 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -291,6 +291,7 @@ static void ice_vsi_delete_from_hw(struct ice_vsi *vsi) struct ice_vsi_ctx *ctxt; int status; + ice_fltr_remove_all(vsi); ctxt = kzalloc(sizeof(*ctxt), GFP_KERNEL); if (!ctxt) return; @@ -2744,6 +2745,8 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) goto unroll_vector_base; ice_vsi_map_rings_to_vectors(vsi); + vsi->stat_offsets_loaded = false; + if (ice_is_xdp_ena_vsi(vsi)) { ret = ice_vsi_determine_xdp_res(vsi); if (ret) @@ -2792,6 +2795,9 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params) ret = ice_vsi_alloc_ring_stats(vsi); if (ret) goto unroll_vector_base; + + vsi->stat_offsets_loaded = false; + /* Do not exit if configuring RSS had an issue, at least * receive traffic on first queue. Hence no need to capture * return value @@ -2892,7 +2898,6 @@ void ice_vsi_decfg(struct ice_vsi *vsi) !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags)) ice_cfg_sw_lldp(vsi, false, false); - ice_fltr_remove_all(vsi); ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx); if (err) diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 567694bf098b..42c318ceff61 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -1393,6 +1393,8 @@ static void ice_aq_cancel_waiting_tasks(struct ice_pf *pf) wake_up(&pf->aq_wait_queue); } +#define ICE_MBX_OVERFLOW_WATERMARK 64 + /** * __ice_clean_ctrlq - helper function to clean controlq rings * @pf: ptr to struct ice_pf @@ -1483,6 +1485,7 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) return 0; do { + struct ice_mbx_data data = {}; u16 opcode; int ret; @@ -1509,8 +1512,12 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type) ice_vf_lan_overflow_event(pf, &event); break; case ice_mbx_opc_send_msg_to_pf: - if (!ice_is_malicious_vf(pf, &event, i, pending)) - ice_vc_process_vf_msg(pf, &event); + data.num_msg_proc = i; + data.num_pending_arq = pending; + data.max_num_msgs_mbx = hw->mailboxq.num_rq_entries; + data.async_watermark_val = ICE_MBX_OVERFLOW_WATERMARK; + + ice_vc_process_vf_msg(pf, &event, &data); break; case ice_aqc_opc_fw_logging: ice_output_fw_log(hw, &event.desc, event.msg_buf); @@ -2316,18 +2323,15 @@ static void ice_service_task(struct work_struct *work) } } - if (test_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) { - /* Plug aux device per request */ - ice_plug_aux_dev(pf); + /* unplug aux dev per request, if an unplug request came in + * while processing a plug request, this will handle it + */ + if (test_and_clear_bit(ICE_FLAG_UNPLUG_AUX_DEV, pf->flags)) + ice_unplug_aux_dev(pf); - /* Mark plugging as done but check whether unplug was - * requested during ice_plug_aux_dev() call - * (e.g. from ice_clear_rdma_cap()) and if so then - * plug aux device. - */ - if (!test_and_clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) - ice_unplug_aux_dev(pf); - } + /* Plug aux device per request */ + if (test_and_clear_bit(ICE_FLAG_PLUG_AUX_DEV, pf->flags)) + ice_plug_aux_dev(pf); if (test_and_clear_bit(ICE_FLAG_MTU_CHANGED, pf->flags)) { struct iidc_event *event; @@ -3891,6 +3895,7 @@ static int ice_init_pf(struct ice_pf *pf) mutex_init(&pf->vfs.table_lock); hash_init(pf->vfs.table); + ice_mbx_init_snapshot(&pf->hw); return 0; } @@ -4644,6 +4649,12 @@ static int ice_start_eth(struct ice_vsi *vsi) return err; } +static void ice_stop_eth(struct ice_vsi *vsi) +{ + ice_fltr_remove_all(vsi); + ice_vsi_close(vsi); +} + static int ice_init_eth(struct ice_pf *pf) { struct ice_vsi *vsi = ice_get_main_vsi(pf); @@ -4791,9 +4802,13 @@ err_init_pf: static void ice_deinit_dev(struct ice_pf *pf) { ice_free_irq_msix_misc(pf); - ice_clear_interrupt_scheme(pf); ice_deinit_pf(pf); ice_deinit_hw(&pf->hw); + + /* Service task is already stopped, so call reset directly. */ + ice_reset(&pf->hw, ICE_RESET_PFR); + pci_wait_for_pending_transaction(pf->pdev); + ice_clear_interrupt_scheme(pf); } static void ice_init_features(struct ice_pf *pf) @@ -5083,10 +5098,6 @@ int ice_load(struct ice_pf *pf) struct ice_vsi *vsi; int err; - err = ice_reset(&pf->hw, ICE_RESET_PFR); - if (err) - return err; - err = ice_init_dev(pf); if (err) return err; @@ -5132,7 +5143,7 @@ void ice_unload(struct ice_pf *pf) { ice_deinit_features(pf); ice_deinit_rdma(pf); - ice_vsi_close(ice_get_main_vsi(pf)); + ice_stop_eth(ice_get_main_vsi(pf)); ice_vsi_decfg(ice_get_main_vsi(pf)); ice_deinit_dev(pf); } @@ -5343,12 +5354,6 @@ static void ice_remove(struct pci_dev *pdev) ice_setup_mc_magic_wake(pf); ice_set_wake(pf); - /* Issue a PFR as part of the prescribed driver unload flow. Do not - * do it via ice_schedule_reset() since there is no need to rebuild - * and the service task is already stopped. - */ - ice_reset(&pf->hw, ICE_RESET_PFR); - pci_wait_for_pending_transaction(pdev); pci_disable_device(pdev); } @@ -7045,6 +7050,10 @@ int ice_down(struct ice_vsi *vsi) ice_for_each_txq(vsi, i) ice_clean_tx_ring(vsi->tx_rings[i]); + if (ice_is_xdp_ena_vsi(vsi)) + ice_for_each_xdp_txq(vsi, i) + ice_clean_tx_ring(vsi->xdp_rings[i]); + ice_for_each_rxq(vsi, i) ice_clean_rx_ring(vsi->rx_rings[i]); diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index 4eca8d195ef0..b7682de0ae05 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -2788,7 +2788,7 @@ static int ice_sched_assoc_vsi_to_agg(struct ice_port_info *pi, u32 agg_id, u16 vsi_handle, unsigned long *tc_bitmap) { - struct ice_sched_agg_vsi_info *agg_vsi_info, *old_agg_vsi_info = NULL; + struct ice_sched_agg_vsi_info *agg_vsi_info, *iter, *old_agg_vsi_info = NULL; struct ice_sched_agg_info *agg_info, *old_agg_info; struct ice_hw *hw = pi->hw; int status = 0; @@ -2806,11 +2806,13 @@ ice_sched_assoc_vsi_to_agg(struct ice_port_info *pi, u32 agg_id, if (old_agg_info && old_agg_info != agg_info) { struct ice_sched_agg_vsi_info *vtmp; - list_for_each_entry_safe(old_agg_vsi_info, vtmp, + list_for_each_entry_safe(iter, vtmp, &old_agg_info->agg_vsi_list, list_entry) - if (old_agg_vsi_info->vsi_handle == vsi_handle) + if (iter->vsi_handle == vsi_handle) { + old_agg_vsi_info = iter; break; + } } /* check if entry already exist */ diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index 96a64c25e2ef..588ad8696756 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -204,10 +204,7 @@ void ice_free_vfs(struct ice_pf *pf) } /* clear malicious info since the VF is getting released */ - if (ice_mbx_clear_malvf(&hw->mbx_snapshot, pf->vfs.malvfs, - ICE_MAX_SRIOV_VFS, vf->vf_id)) - dev_dbg(dev, "failed to clear malicious VF state for VF %u\n", - vf->vf_id); + list_del(&vf->mbx_info.list_entry); mutex_unlock(&vf->cfg_lock); } @@ -1017,7 +1014,6 @@ int ice_sriov_configure(struct pci_dev *pdev, int num_vfs) if (!num_vfs) { if (!pci_vfs_assigned(pdev)) { ice_free_vfs(pf); - ice_mbx_deinit_snapshot(&pf->hw); if (pf->lag) ice_enable_lag(pf->lag); return 0; @@ -1027,16 +1023,10 @@ int ice_sriov_configure(struct pci_dev *pdev, int num_vfs) return -EBUSY; } - err = ice_mbx_init_snapshot(&pf->hw, num_vfs); + err = ice_pci_sriov_ena(pf, num_vfs); if (err) return err; - err = ice_pci_sriov_ena(pf, num_vfs); - if (err) { - ice_mbx_deinit_snapshot(&pf->hw); - return err; - } - if (pf->lag) ice_disable_lag(pf->lag); return num_vfs; @@ -1181,7 +1171,7 @@ int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena) if (!vf) return -EINVAL; - ret = ice_check_vf_ready_for_cfg(vf); + ret = ice_check_vf_ready_for_reset(vf); if (ret) goto out_put_vf; @@ -1296,7 +1286,7 @@ int ice_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) goto out_put_vf; } - ret = ice_check_vf_ready_for_cfg(vf); + ret = ice_check_vf_ready_for_reset(vf); if (ret) goto out_put_vf; @@ -1341,16 +1331,16 @@ int ice_set_vf_trust(struct net_device *netdev, int vf_id, bool trusted) struct ice_vf *vf; int ret; + vf = ice_get_vf_by_id(pf, vf_id); + if (!vf) + return -EINVAL; + if (ice_is_eswitch_mode_switchdev(pf)) { dev_info(ice_pf_to_dev(pf), "Trusted VF is forbidden in switchdev mode\n"); return -EOPNOTSUPP; } - vf = ice_get_vf_by_id(pf, vf_id); - if (!vf) - return -EINVAL; - - ret = ice_check_vf_ready_for_cfg(vf); + ret = ice_check_vf_ready_for_reset(vf); if (ret) goto out_put_vf; @@ -1663,7 +1653,7 @@ ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, if (!vf) return -EINVAL; - ret = ice_check_vf_ready_for_cfg(vf); + ret = ice_check_vf_ready_for_reset(vf); if (ret) goto out_put_vf; @@ -1787,66 +1777,3 @@ void ice_restore_all_vfs_msi_state(struct pci_dev *pdev) } } } - -/** - * ice_is_malicious_vf - helper function to detect a malicious VF - * @pf: ptr to struct ice_pf - * @event: pointer to the AQ event - * @num_msg_proc: the number of messages processed so far - * @num_msg_pending: the number of messages peinding in admin queue - */ -bool -ice_is_malicious_vf(struct ice_pf *pf, struct ice_rq_event_info *event, - u16 num_msg_proc, u16 num_msg_pending) -{ - s16 vf_id = le16_to_cpu(event->desc.retval); - struct device *dev = ice_pf_to_dev(pf); - struct ice_mbx_data mbxdata; - bool malvf = false; - struct ice_vf *vf; - int status; - - vf = ice_get_vf_by_id(pf, vf_id); - if (!vf) - return false; - - if (test_bit(ICE_VF_STATE_DIS, vf->vf_states)) - goto out_put_vf; - - mbxdata.num_msg_proc = num_msg_proc; - mbxdata.num_pending_arq = num_msg_pending; - mbxdata.max_num_msgs_mbx = pf->hw.mailboxq.num_rq_entries; -#define ICE_MBX_OVERFLOW_WATERMARK 64 - mbxdata.async_watermark_val = ICE_MBX_OVERFLOW_WATERMARK; - - /* check to see if we have a malicious VF */ - status = ice_mbx_vf_state_handler(&pf->hw, &mbxdata, vf_id, &malvf); - if (status) - goto out_put_vf; - - if (malvf) { - bool report_vf = false; - - /* if the VF is malicious and we haven't let the user - * know about it, then let them know now - */ - status = ice_mbx_report_malvf(&pf->hw, pf->vfs.malvfs, - ICE_MAX_SRIOV_VFS, vf_id, - &report_vf); - if (status) - dev_dbg(dev, "Error reporting malicious VF\n"); - - if (report_vf) { - struct ice_vsi *pf_vsi = ice_get_main_vsi(pf); - - if (pf_vsi) - dev_warn(dev, "VF MAC %pM on PF MAC %pM is generating asynchronous messages and may be overflowing the PF message queue. Please see the Adapter User Guide for more information\n", - &vf->dev_lan_addr[0], - pf_vsi->netdev->dev_addr); - } - } - -out_put_vf: - ice_put_vf(vf); - return malvf; -} diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.h b/drivers/net/ethernet/intel/ice/ice_sriov.h index 955ab810a198..346cb2666f3a 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.h +++ b/drivers/net/ethernet/intel/ice/ice_sriov.h @@ -33,11 +33,7 @@ int ice_get_vf_cfg(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi); void ice_free_vfs(struct ice_pf *pf); -void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event); void ice_restore_all_vfs_msi_state(struct pci_dev *pdev); -bool -ice_is_malicious_vf(struct ice_pf *pf, struct ice_rq_event_info *event, - u16 num_msg_proc, u16 num_msg_pending); int ice_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos, @@ -68,22 +64,11 @@ ice_vc_validate_pattern(struct ice_vf *vf, struct virtchnl_proto_hdrs *proto); static inline void ice_process_vflr_event(struct ice_pf *pf) { } static inline void ice_free_vfs(struct ice_pf *pf) { } static inline -void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) { } -static inline void ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event) { } static inline void ice_print_vfs_mdd_events(struct ice_pf *pf) { } static inline void ice_print_vf_rx_mdd_event(struct ice_vf *vf) { } static inline void ice_restore_all_vfs_msi_state(struct pci_dev *pdev) { } -static inline bool -ice_is_malicious_vf(struct ice_pf __always_unused *pf, - struct ice_rq_event_info __always_unused *event, - u16 __always_unused num_msg_proc, - u16 __always_unused num_msg_pending) -{ - return false; -} - static inline int ice_sriov_configure(struct pci_dev __always_unused *pdev, int __always_unused num_vfs) diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 61f844d22512..46b36851af46 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -1780,18 +1780,36 @@ ice_update_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx, int ice_cfg_rdma_fltr(struct ice_hw *hw, u16 vsi_handle, bool enable) { - struct ice_vsi_ctx *ctx; + struct ice_vsi_ctx *ctx, *cached_ctx; + int status; + + cached_ctx = ice_get_vsi_ctx(hw, vsi_handle); + if (!cached_ctx) + return -ENOENT; - ctx = ice_get_vsi_ctx(hw, vsi_handle); + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) - return -EIO; + return -ENOMEM; + + ctx->info.q_opt_rss = cached_ctx->info.q_opt_rss; + ctx->info.q_opt_tc = cached_ctx->info.q_opt_tc; + ctx->info.q_opt_flags = cached_ctx->info.q_opt_flags; + + ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_Q_OPT_VALID); if (enable) ctx->info.q_opt_flags |= ICE_AQ_VSI_Q_OPT_PE_FLTR_EN; else ctx->info.q_opt_flags &= ~ICE_AQ_VSI_Q_OPT_PE_FLTR_EN; - return ice_update_vsi(hw, vsi_handle, ctx, NULL); + status = ice_update_vsi(hw, vsi_handle, ctx, NULL); + if (!status) { + cached_ctx->info.q_opt_flags = ctx->info.q_opt_flags; + cached_ctx->info.valid_sections |= ctx->info.valid_sections; + } + + kfree(ctx); + return status; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_tc_lib.c b/drivers/net/ethernet/intel/ice/ice_tc_lib.c index 76f29a5bf8d7..d1a31f236d26 100644 --- a/drivers/net/ethernet/intel/ice/ice_tc_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_tc_lib.c @@ -693,17 +693,18 @@ ice_eswitch_add_tc_fltr(struct ice_vsi *vsi, struct ice_tc_flower_fltr *fltr) * results into order of switch rule evaluation. */ rule_info.priority = 7; + rule_info.flags_info.act_valid = true; if (fltr->direction == ICE_ESWITCH_FLTR_INGRESS) { rule_info.sw_act.flag |= ICE_FLTR_RX; rule_info.sw_act.src = hw->pf_id; rule_info.rx = true; + rule_info.flags_info.act = ICE_SINGLE_ACT_LB_ENABLE; } else { rule_info.sw_act.flag |= ICE_FLTR_TX; rule_info.sw_act.src = vsi->idx; rule_info.rx = false; rule_info.flags_info.act = ICE_SINGLE_ACT_LAN_ENABLE; - rule_info.flags_info.act_valid = true; } /* specify the cookie as filter_rule_id */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index dfd22862e926..52d0a126eb61 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -938,6 +938,7 @@ ice_reuse_rx_page(struct ice_rx_ring *rx_ring, struct ice_rx_buf *old_buf) * ice_get_rx_buf - Fetch Rx buffer and synchronize data for use * @rx_ring: Rx descriptor ring to transact packets on * @size: size of buffer to add to skb + * @ntc: index of next to clean element * * This function will pull an Rx buffer from the ring and synchronize it * for use by the CPU. @@ -1026,7 +1027,6 @@ ice_build_skb(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp) /** * ice_construct_skb - Allocate skb and populate it * @rx_ring: Rx descriptor ring to transact packets on - * @rx_buf: Rx buffer to pull data from * @xdp: xdp_buff pointing to the data * * This function allocates an skb. It then populates it with the page @@ -1152,11 +1152,11 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) unsigned int total_rx_bytes = 0, total_rx_pkts = 0; unsigned int offset = rx_ring->rx_offset; struct xdp_buff *xdp = &rx_ring->xdp; + u32 cached_ntc = rx_ring->first_desc; struct ice_tx_ring *xdp_ring = NULL; struct bpf_prog *xdp_prog = NULL; u32 ntc = rx_ring->next_to_clean; u32 cnt = rx_ring->count; - u32 cached_ntc = ntc; u32 xdp_xmit = 0; u32 cached_ntu; bool failure; @@ -1210,6 +1210,7 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget) ice_vc_fdir_irq_handler(ctrl_vsi, rx_desc); if (++ntc == cnt) ntc = 0; + rx_ring->first_desc = ntc; continue; } @@ -1663,8 +1664,7 @@ ice_tx_map(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first, if (first->tx_flags & ICE_TX_FLAGS_HW_VLAN) { td_cmd |= (u64)ICE_TX_DESC_CMD_IL2TAG1; - td_tag = (first->tx_flags & ICE_TX_FLAGS_VLAN_M) >> - ICE_TX_FLAGS_VLAN_S; + td_tag = first->vid; } dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE); @@ -1997,7 +1997,7 @@ ice_tx_prepare_vlan_flags(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first) * VLAN offloads exclusively so we only care about the VLAN ID here */ if (skb_vlan_tag_present(skb)) { - first->tx_flags |= skb_vlan_tag_get(skb) << ICE_TX_FLAGS_VLAN_S; + first->vid = skb_vlan_tag_get(skb); if (tx_ring->flags & ICE_TX_FLAGS_RING_VLAN_L2TAG2) first->tx_flags |= ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN; else @@ -2387,8 +2387,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring) offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX | (ICE_TX_CTX_DESC_IL2TAG2 << ICE_TXD_CTX_QW1_CMD_S)); - offload.cd_l2tag2 = (first->tx_flags & ICE_TX_FLAGS_VLAN_M) >> - ICE_TX_FLAGS_VLAN_S; + offload.cd_l2tag2 = first->vid; } /* set up TSO offload */ diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index fff0efe28373..166413fc33f4 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -127,10 +127,6 @@ static inline int ice_skb_pad(void) #define ICE_TX_FLAGS_IPV6 BIT(6) #define ICE_TX_FLAGS_TUNNEL BIT(7) #define ICE_TX_FLAGS_HW_OUTER_SINGLE_VLAN BIT(8) -#define ICE_TX_FLAGS_VLAN_M 0xffff0000 -#define ICE_TX_FLAGS_VLAN_PR_M 0xe0000000 -#define ICE_TX_FLAGS_VLAN_PR_S 29 -#define ICE_TX_FLAGS_VLAN_S 16 #define ICE_XDP_PASS 0 #define ICE_XDP_CONSUMED BIT(0) @@ -182,8 +178,9 @@ struct ice_tx_buf { unsigned int gso_segs; unsigned int nr_frags; /* used for mbuf XDP */ }; - u32 type:16; /* &ice_tx_buf_type */ - u32 tx_flags:16; + u32 tx_flags:12; + u32 type:4; /* &ice_tx_buf_type */ + u32 vid:16; DEFINE_DMA_UNMAP_LEN(len); DEFINE_DMA_UNMAP_ADDR(dma); }; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c index 7bc5aa340c7d..c8322fb6f2b3 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c @@ -438,6 +438,7 @@ busy: * ice_finalize_xdp_rx - Bump XDP Tx tail and/or flush redirect map * @xdp_ring: XDP ring * @xdp_res: Result of the receive batch + * @first_idx: index to write from caller * * This function bumps XDP Tx tail and/or flush redirect map, and * should be called when a batch of packets has been processed in the diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index e3f622cad425..a09556e57803 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -784,14 +784,15 @@ struct ice_mbx_snap_buffer_data { u16 max_num_msgs_mbx; }; -/* Structure to track messages sent by VFs on mailbox: - * 1. vf_cntr: a counter array of VFs to track the number of - * asynchronous messages sent by each VF - * 2. vfcntr_len: number of entries in VF counter array +/* Structure used to track a single VF's messages on the mailbox: + * 1. list_entry: linked list entry node + * 2. msg_count: the number of asynchronous messages sent by this VF + * 3. malicious: whether this VF has been detected as malicious before */ -struct ice_mbx_vf_counter { - u32 *vf_cntr; - u32 vfcntr_len; +struct ice_mbx_vf_info { + struct list_head list_entry; + u32 msg_count; + u8 malicious : 1; }; /* Structure to hold data relevant to the captured static snapshot @@ -799,7 +800,7 @@ struct ice_mbx_vf_counter { */ struct ice_mbx_snapshot { struct ice_mbx_snap_buffer_data mbx_buf; - struct ice_mbx_vf_counter mbx_vf; + struct list_head mbx_vf; }; /* Structure to hold data to be used for capturing or updating a diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c index 0e57bd1b85fd..bf74a2f3a4f8 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c @@ -186,6 +186,25 @@ int ice_check_vf_ready_for_cfg(struct ice_vf *vf) } /** + * ice_check_vf_ready_for_reset - check if VF is ready to be reset + * @vf: VF to check if it's ready to be reset + * + * The purpose of this function is to ensure that the VF is not in reset, + * disabled, and is both initialized and active, thus enabling us to safely + * initialize another reset. + */ +int ice_check_vf_ready_for_reset(struct ice_vf *vf) +{ + int ret; + + ret = ice_check_vf_ready_for_cfg(vf); + if (!ret && !test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) + ret = -EAGAIN; + + return ret; +} + +/** * ice_trigger_vf_reset - Reset a VF on HW * @vf: pointer to the VF structure * @is_vflr: true if VFLR was issued, false if not @@ -496,10 +515,7 @@ void ice_reset_all_vfs(struct ice_pf *pf) /* clear all malicious info if the VFs are getting reset */ ice_for_each_vf(pf, bkt, vf) - if (ice_mbx_clear_malvf(&hw->mbx_snapshot, pf->vfs.malvfs, - ICE_MAX_SRIOV_VFS, vf->vf_id)) - dev_dbg(dev, "failed to clear malicious VF state for VF %u\n", - vf->vf_id); + ice_mbx_clear_malvf(&vf->mbx_info); /* If VFs have been disabled, there is no need to reset */ if (test_and_set_bit(ICE_VF_DIS, pf->state)) { @@ -601,12 +617,10 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; struct device *dev; - struct ice_hw *hw; int err = 0; bool rsd; dev = ice_pf_to_dev(pf); - hw = &pf->hw; if (flags & ICE_VF_RESET_NOTIFY) ice_notify_vf_reset(vf); @@ -705,10 +719,7 @@ int ice_reset_vf(struct ice_vf *vf, u32 flags) ice_eswitch_replay_vf_mac_rule(vf); /* if the VF has been reset allow it to come up again */ - if (ice_mbx_clear_malvf(&hw->mbx_snapshot, pf->vfs.malvfs, - ICE_MAX_SRIOV_VFS, vf->vf_id)) - dev_dbg(dev, "failed to clear malicious VF state for VF %u\n", - vf->vf_id); + ice_mbx_clear_malvf(&vf->mbx_info); out_unlock: if (flags & ICE_VF_RESET_LOCK) @@ -764,6 +775,9 @@ void ice_initialize_vf_entry(struct ice_vf *vf) ice_vf_ctrl_invalidate_vsi(vf); ice_vf_fdir_init(vf); + /* Initialize mailbox info for this VF */ + ice_mbx_init_vf_info(&pf->hw, &vf->mbx_info); + mutex_init(&vf->cfg_lock); } diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h index ef30f05b5d02..a38ef00a3679 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h @@ -74,7 +74,6 @@ struct ice_vfs { u16 num_qps_per; /* number of queue pairs per VF */ u16 num_msix_per; /* number of MSI-X vectors per VF */ unsigned long last_printed_mdd_jiffies; /* MDD message rate limit */ - DECLARE_BITMAP(malvfs, ICE_MAX_SRIOV_VFS); /* malicious VF indicator */ }; /* VF information structure */ @@ -105,6 +104,7 @@ struct ice_vf { DECLARE_BITMAP(rxq_ena, ICE_MAX_RSS_QS_PER_VF); struct ice_vlan port_vlan_info; /* Port VLAN ID, QoS, and TPID */ struct virtchnl_vlan_caps vlan_v2_caps; + struct ice_mbx_vf_info mbx_info; u8 pf_set_mac:1; /* VF MAC address set by VMM admin */ u8 trusted:1; u8 spoofchk:1; @@ -215,6 +215,7 @@ u16 ice_get_num_vfs(struct ice_pf *pf); struct ice_vsi *ice_get_vf_vsi(struct ice_vf *vf); bool ice_is_vf_disabled(struct ice_vf *vf); int ice_check_vf_ready_for_cfg(struct ice_vf *vf); +int ice_check_vf_ready_for_reset(struct ice_vf *vf); void ice_set_vf_state_dis(struct ice_vf *vf); bool ice_is_any_vf_in_unicast_promisc(struct ice_pf *pf); void diff --git a/drivers/net/ethernet/intel/ice/ice_vf_mbx.c b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c index f56fa94ff3d0..40cb4ba0789c 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_mbx.c +++ b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c @@ -93,36 +93,31 @@ u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed) * * 2. When the caller starts processing its mailbox queue in response to an * interrupt, the structure ice_mbx_snapshot is expected to be cleared before - * the algorithm can be run for the first time for that interrupt. This can be - * done via ice_mbx_reset_snapshot(). + * the algorithm can be run for the first time for that interrupt. This + * requires calling ice_mbx_reset_snapshot() as well as calling + * ice_mbx_reset_vf_info() for each VF tracking structure. * * 3. For every message read by the caller from the MBX Queue, the caller must * call the detection algorithm's entry function ice_mbx_vf_state_handler(). * Before every call to ice_mbx_vf_state_handler() the struct ice_mbx_data is * filled as it is required to be passed to the algorithm. * - * 4. Every time a message is read from the MBX queue, a VFId is received which - * is passed to the state handler. The boolean output is_malvf of the state - * handler ice_mbx_vf_state_handler() serves as an indicator to the caller - * whether this VF is malicious or not. + * 4. Every time a message is read from the MBX queue, a tracking structure + * for the VF must be passed to the state handler. The boolean output + * report_malvf from ice_mbx_vf_state_handler() serves as an indicator to the + * caller whether it must report this VF as malicious or not. * * 5. When a VF is identified to be malicious, the caller can send a message - * to the system administrator. The caller can invoke ice_mbx_report_malvf() - * to help determine if a malicious VF is to be reported or not. This function - * requires the caller to maintain a global bitmap to track all malicious VFs - * and pass that to ice_mbx_report_malvf() along with the VFID which was identified - * to be malicious by ice_mbx_vf_state_handler(). + * to the system administrator. * - * 6. The global bitmap maintained by PF can be cleared completely if PF is in - * reset or the bit corresponding to a VF can be cleared if that VF is in reset. - * When a VF is shut down and brought back up, we assume that the new VF - * brought up is not malicious and hence report it if found malicious. + * 6. The PF is responsible for maintaining the struct ice_mbx_vf_info + * structure for each VF. The PF should clear the VF tracking structure if the + * VF is reset. When a VF is shut down and brought back up, we will then + * assume that the new VF is not malicious and may report it again if we + * detect it again. * * 7. The function ice_mbx_reset_snapshot() is called to reset the information * in ice_mbx_snapshot for every new mailbox interrupt handled. - * - * 8. The memory allocated for variables in ice_mbx_snapshot is de-allocated - * when driver is unloaded. */ #define ICE_RQ_DATA_MASK(rq_data) ((rq_data) & PF_MBX_ARQH_ARQH_M) /* Using the highest value for an unsigned 16-bit value 0xFFFF to indicate that @@ -131,6 +126,25 @@ u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed) #define ICE_IGNORE_MAX_MSG_CNT 0xFFFF /** + * ice_mbx_reset_snapshot - Reset mailbox snapshot structure + * @snap: pointer to the mailbox snapshot + */ +static void ice_mbx_reset_snapshot(struct ice_mbx_snapshot *snap) +{ + struct ice_mbx_vf_info *vf_info; + + /* Clear mbx_buf in the mailbox snaphot structure and setting the + * mailbox snapshot state to a new capture. + */ + memset(&snap->mbx_buf, 0, sizeof(snap->mbx_buf)); + snap->mbx_buf.state = ICE_MAL_VF_DETECT_STATE_NEW_SNAPSHOT; + + /* Reset message counts for all VFs to zero */ + list_for_each_entry(vf_info, &snap->mbx_vf, list_entry) + vf_info->msg_count = 0; +} + +/** * ice_mbx_traverse - Pass through mailbox snapshot * @hw: pointer to the HW struct * @new_state: new algorithm state @@ -171,7 +185,7 @@ ice_mbx_traverse(struct ice_hw *hw, /** * ice_mbx_detect_malvf - Detect malicious VF in snapshot * @hw: pointer to the HW struct - * @vf_id: relative virtual function ID + * @vf_info: mailbox tracking structure for a VF * @new_state: new algorithm state * @is_malvf: boolean output to indicate if VF is malicious * @@ -180,19 +194,14 @@ ice_mbx_traverse(struct ice_hw *hw, * the permissible number of messages to send. */ static int -ice_mbx_detect_malvf(struct ice_hw *hw, u16 vf_id, +ice_mbx_detect_malvf(struct ice_hw *hw, struct ice_mbx_vf_info *vf_info, enum ice_mbx_snapshot_state *new_state, bool *is_malvf) { - struct ice_mbx_snapshot *snap = &hw->mbx_snapshot; - - if (vf_id >= snap->mbx_vf.vfcntr_len) - return -EIO; - - /* increment the message count in the VF array */ - snap->mbx_vf.vf_cntr[vf_id]++; + /* increment the message count for this VF */ + vf_info->msg_count++; - if (snap->mbx_vf.vf_cntr[vf_id] >= ICE_ASYNC_VF_MSG_THRESHOLD) + if (vf_info->msg_count >= ICE_ASYNC_VF_MSG_THRESHOLD) *is_malvf = true; /* continue to iterate through the mailbox snapshot */ @@ -202,35 +211,11 @@ ice_mbx_detect_malvf(struct ice_hw *hw, u16 vf_id, } /** - * ice_mbx_reset_snapshot - Reset mailbox snapshot structure - * @snap: pointer to mailbox snapshot structure in the ice_hw struct - * - * Reset the mailbox snapshot structure and clear VF counter array. - */ -static void ice_mbx_reset_snapshot(struct ice_mbx_snapshot *snap) -{ - u32 vfcntr_len; - - if (!snap || !snap->mbx_vf.vf_cntr) - return; - - /* Clear VF counters. */ - vfcntr_len = snap->mbx_vf.vfcntr_len; - if (vfcntr_len) - memset(snap->mbx_vf.vf_cntr, 0, - (vfcntr_len * sizeof(*snap->mbx_vf.vf_cntr))); - - /* Reset mailbox snapshot for a new capture. */ - memset(&snap->mbx_buf, 0, sizeof(snap->mbx_buf)); - snap->mbx_buf.state = ICE_MAL_VF_DETECT_STATE_NEW_SNAPSHOT; -} - -/** * ice_mbx_vf_state_handler - Handle states of the overflow algorithm * @hw: pointer to the HW struct * @mbx_data: pointer to structure containing mailbox data - * @vf_id: relative virtual function (VF) ID - * @is_malvf: boolean output to indicate if VF is malicious + * @vf_info: mailbox tracking structure for the VF in question + * @report_malvf: boolean output to indicate whether VF should be reported * * The function serves as an entry point for the malicious VF * detection algorithm by handling the different states and state @@ -249,24 +234,24 @@ static void ice_mbx_reset_snapshot(struct ice_mbx_snapshot *snap) * the static snapshot and look for a malicious VF. */ int -ice_mbx_vf_state_handler(struct ice_hw *hw, - struct ice_mbx_data *mbx_data, u16 vf_id, - bool *is_malvf) +ice_mbx_vf_state_handler(struct ice_hw *hw, struct ice_mbx_data *mbx_data, + struct ice_mbx_vf_info *vf_info, bool *report_malvf) { struct ice_mbx_snapshot *snap = &hw->mbx_snapshot; struct ice_mbx_snap_buffer_data *snap_buf; struct ice_ctl_q_info *cq = &hw->mailboxq; enum ice_mbx_snapshot_state new_state; + bool is_malvf = false; int status = 0; - if (!is_malvf || !mbx_data) + if (!report_malvf || !mbx_data || !vf_info) return -EINVAL; + *report_malvf = false; + /* When entering the mailbox state machine assume that the VF * is not malicious until detected. */ - *is_malvf = false; - /* Checking if max messages allowed to be processed while servicing current * interrupt is not less than the defined AVF message threshold. */ @@ -315,7 +300,7 @@ ice_mbx_vf_state_handler(struct ice_hw *hw, if (snap_buf->num_pending_arq >= mbx_data->async_watermark_val) { new_state = ICE_MAL_VF_DETECT_STATE_DETECT; - status = ice_mbx_detect_malvf(hw, vf_id, &new_state, is_malvf); + status = ice_mbx_detect_malvf(hw, vf_info, &new_state, &is_malvf); } else { new_state = ICE_MAL_VF_DETECT_STATE_TRAVERSE; ice_mbx_traverse(hw, &new_state); @@ -329,7 +314,7 @@ ice_mbx_vf_state_handler(struct ice_hw *hw, case ICE_MAL_VF_DETECT_STATE_DETECT: new_state = ICE_MAL_VF_DETECT_STATE_DETECT; - status = ice_mbx_detect_malvf(hw, vf_id, &new_state, is_malvf); + status = ice_mbx_detect_malvf(hw, vf_info, &new_state, &is_malvf); break; default: @@ -339,145 +324,57 @@ ice_mbx_vf_state_handler(struct ice_hw *hw, snap_buf->state = new_state; - return status; -} - -/** - * ice_mbx_report_malvf - Track and note malicious VF - * @hw: pointer to the HW struct - * @all_malvfs: all malicious VFs tracked by PF - * @bitmap_len: length of bitmap in bits - * @vf_id: relative virtual function ID of the malicious VF - * @report_malvf: boolean to indicate if malicious VF must be reported - * - * This function will update a bitmap that keeps track of the malicious - * VFs attached to the PF. A malicious VF must be reported only once if - * discovered between VF resets or loading so the function checks - * the input vf_id against the bitmap to verify if the VF has been - * detected in any previous mailbox iterations. - */ -int -ice_mbx_report_malvf(struct ice_hw *hw, unsigned long *all_malvfs, - u16 bitmap_len, u16 vf_id, bool *report_malvf) -{ - if (!all_malvfs || !report_malvf) - return -EINVAL; - - *report_malvf = false; - - if (bitmap_len < hw->mbx_snapshot.mbx_vf.vfcntr_len) - return -EINVAL; - - if (vf_id >= bitmap_len) - return -EIO; - - /* If the vf_id is found in the bitmap set bit and boolean to true */ - if (!test_and_set_bit(vf_id, all_malvfs)) + /* Only report VFs as malicious the first time we detect it */ + if (is_malvf && !vf_info->malicious) { + vf_info->malicious = 1; *report_malvf = true; + } - return 0; + return status; } /** - * ice_mbx_clear_malvf - Clear VF bitmap and counter for VF ID - * @snap: pointer to the mailbox snapshot structure - * @all_malvfs: all malicious VFs tracked by PF - * @bitmap_len: length of bitmap in bits - * @vf_id: relative virtual function ID of the malicious VF + * ice_mbx_clear_malvf - Clear VF mailbox info + * @vf_info: the mailbox tracking structure for a VF * - * In case of a VF reset, this function can be called to clear - * the bit corresponding to the VF ID in the bitmap tracking all - * malicious VFs attached to the PF. The function also clears the - * VF counter array at the index of the VF ID. This is to ensure - * that the new VF loaded is not considered malicious before going - * through the overflow detection algorithm. + * In case of a VF reset, this function shall be called to clear the VF's + * current mailbox tracking state. */ -int -ice_mbx_clear_malvf(struct ice_mbx_snapshot *snap, unsigned long *all_malvfs, - u16 bitmap_len, u16 vf_id) +void ice_mbx_clear_malvf(struct ice_mbx_vf_info *vf_info) { - if (!snap || !all_malvfs) - return -EINVAL; - - if (bitmap_len < snap->mbx_vf.vfcntr_len) - return -EINVAL; - - /* Ensure VF ID value is not larger than bitmap or VF counter length */ - if (vf_id >= bitmap_len || vf_id >= snap->mbx_vf.vfcntr_len) - return -EIO; - - /* Clear VF ID bit in the bitmap tracking malicious VFs attached to PF */ - clear_bit(vf_id, all_malvfs); - - /* Clear the VF counter in the mailbox snapshot structure for that VF ID. - * This is to ensure that if a VF is unloaded and a new one brought back - * up with the same VF ID for a snapshot currently in traversal or detect - * state the counter for that VF ID does not increment on top of existing - * values in the mailbox overflow detection algorithm. - */ - snap->mbx_vf.vf_cntr[vf_id] = 0; - - return 0; + vf_info->malicious = 0; + vf_info->msg_count = 0; } /** - * ice_mbx_init_snapshot - Initialize mailbox snapshot structure + * ice_mbx_init_vf_info - Initialize a new VF mailbox tracking info * @hw: pointer to the hardware structure - * @vf_count: number of VFs allocated on a PF + * @vf_info: the mailbox tracking info structure for a VF * - * Clear the mailbox snapshot structure and allocate memory - * for the VF counter array based on the number of VFs allocated - * on that PF. + * Initialize a VF mailbox tracking info structure and insert it into the + * snapshot list. * - * Assumption: This function will assume ice_get_caps() has already been - * called to ensure that the vf_count can be compared against the number - * of VFs supported as defined in the functional capabilities of the device. + * If you remove the VF, you must also delete the associated VF info structure + * from the linked list. */ -int ice_mbx_init_snapshot(struct ice_hw *hw, u16 vf_count) +void ice_mbx_init_vf_info(struct ice_hw *hw, struct ice_mbx_vf_info *vf_info) { struct ice_mbx_snapshot *snap = &hw->mbx_snapshot; - /* Ensure that the number of VFs allocated is non-zero and - * is not greater than the number of supported VFs defined in - * the functional capabilities of the PF. - */ - if (!vf_count || vf_count > hw->func_caps.num_allocd_vfs) - return -EINVAL; - - snap->mbx_vf.vf_cntr = devm_kcalloc(ice_hw_to_dev(hw), vf_count, - sizeof(*snap->mbx_vf.vf_cntr), - GFP_KERNEL); - if (!snap->mbx_vf.vf_cntr) - return -ENOMEM; - - /* Setting the VF counter length to the number of allocated - * VFs for given PF's functional capabilities. - */ - snap->mbx_vf.vfcntr_len = vf_count; - - /* Clear mbx_buf in the mailbox snaphot structure and setting the - * mailbox snapshot state to a new capture. - */ - memset(&snap->mbx_buf, 0, sizeof(snap->mbx_buf)); - snap->mbx_buf.state = ICE_MAL_VF_DETECT_STATE_NEW_SNAPSHOT; - - return 0; + ice_mbx_clear_malvf(vf_info); + list_add(&vf_info->list_entry, &snap->mbx_vf); } /** - * ice_mbx_deinit_snapshot - Free mailbox snapshot structure + * ice_mbx_init_snapshot - Initialize mailbox snapshot data * @hw: pointer to the hardware structure * - * Clear the mailbox snapshot structure and free the VF counter array. + * Clear the mailbox snapshot structure and initialize the VF mailbox list. */ -void ice_mbx_deinit_snapshot(struct ice_hw *hw) +void ice_mbx_init_snapshot(struct ice_hw *hw) { struct ice_mbx_snapshot *snap = &hw->mbx_snapshot; - /* Free VF counter array and reset VF counter length */ - devm_kfree(ice_hw_to_dev(hw), snap->mbx_vf.vf_cntr); - snap->mbx_vf.vfcntr_len = 0; - - /* Clear mbx_buf in the mailbox snaphot structure */ - memset(&snap->mbx_buf, 0, sizeof(snap->mbx_buf)); + INIT_LIST_HEAD(&snap->mbx_vf); + ice_mbx_reset_snapshot(snap); } diff --git a/drivers/net/ethernet/intel/ice/ice_vf_mbx.h b/drivers/net/ethernet/intel/ice/ice_vf_mbx.h index 582716e6d5f9..44bc030d17e0 100644 --- a/drivers/net/ethernet/intel/ice/ice_vf_mbx.h +++ b/drivers/net/ethernet/intel/ice/ice_vf_mbx.h @@ -21,15 +21,10 @@ ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, u32 ice_conv_link_speed_to_virtchnl(bool adv_link_support, u16 link_speed); int ice_mbx_vf_state_handler(struct ice_hw *hw, struct ice_mbx_data *mbx_data, - u16 vf_id, bool *is_mal_vf); -int -ice_mbx_clear_malvf(struct ice_mbx_snapshot *snap, unsigned long *all_malvfs, - u16 bitmap_len, u16 vf_id); -int ice_mbx_init_snapshot(struct ice_hw *hw, u16 vf_count); -void ice_mbx_deinit_snapshot(struct ice_hw *hw); -int -ice_mbx_report_malvf(struct ice_hw *hw, unsigned long *all_malvfs, - u16 bitmap_len, u16 vf_id, bool *report_malvf); + struct ice_mbx_vf_info *vf_info, bool *report_malvf); +void ice_mbx_clear_malvf(struct ice_mbx_vf_info *vf_info); +void ice_mbx_init_vf_info(struct ice_hw *hw, struct ice_mbx_vf_info *vf_info); +void ice_mbx_init_snapshot(struct ice_hw *hw); #else /* CONFIG_PCI_IOV */ static inline int ice_aq_send_msg_to_vf(struct ice_hw __always_unused *hw, @@ -48,5 +43,9 @@ ice_conv_link_speed_to_virtchnl(bool __always_unused adv_link_support, return 0; } +static inline void ice_mbx_init_snapshot(struct ice_hw *hw) +{ +} + #endif /* CONFIG_PCI_IOV */ #endif /* _ICE_VF_MBX_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c index e24e3f5017ca..f4a524f80b11 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c @@ -3834,14 +3834,57 @@ void ice_virtchnl_set_repr_ops(struct ice_vf *vf) } /** + * ice_is_malicious_vf - check if this vf might be overflowing mailbox + * @vf: the VF to check + * @mbxdata: data about the state of the mailbox + * + * Detect if a given VF might be malicious and attempting to overflow the PF + * mailbox. If so, log a warning message and ignore this event. + */ +static bool +ice_is_malicious_vf(struct ice_vf *vf, struct ice_mbx_data *mbxdata) +{ + bool report_malvf = false; + struct device *dev; + struct ice_pf *pf; + int status; + + pf = vf->pf; + dev = ice_pf_to_dev(pf); + + if (test_bit(ICE_VF_STATE_DIS, vf->vf_states)) + return vf->mbx_info.malicious; + + /* check to see if we have a newly malicious VF */ + status = ice_mbx_vf_state_handler(&pf->hw, mbxdata, &vf->mbx_info, + &report_malvf); + if (status) + dev_warn_ratelimited(dev, "Unable to check status of mailbox overflow for VF %u MAC %pM, status %d\n", + vf->vf_id, vf->dev_lan_addr, status); + + if (report_malvf) { + struct ice_vsi *pf_vsi = ice_get_main_vsi(pf); + u8 zero_addr[ETH_ALEN] = {}; + + dev_warn(dev, "VF MAC %pM on PF MAC %pM is generating asynchronous messages and may be overflowing the PF message queue. Please see the Adapter User Guide for more information\n", + vf->dev_lan_addr, + pf_vsi ? pf_vsi->netdev->dev_addr : zero_addr); + } + + return vf->mbx_info.malicious; +} + +/** * ice_vc_process_vf_msg - Process request from VF * @pf: pointer to the PF structure * @event: pointer to the AQ event + * @mbxdata: information used to detect VF attempting mailbox overflow * * called from the common asq/arq handler to * process request from VF */ -void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) +void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event, + struct ice_mbx_data *mbxdata) { u32 v_opcode = le32_to_cpu(event->desc.cookie_high); s16 vf_id = le16_to_cpu(event->desc.retval); @@ -3863,6 +3906,10 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) mutex_lock(&vf->cfg_lock); + /* Check if the VF is trying to overflow the mailbox */ + if (ice_is_malicious_vf(vf, mbxdata)) + goto finish; + /* Check if VF is disabled. */ if (test_bit(ICE_VF_STATE_DIS, vf->vf_states)) { err = -EPERM; @@ -3908,6 +3955,7 @@ error_handler: ice_vc_notify_vf_link_state(vf); break; case VIRTCHNL_OP_RESET_VF: + clear_bit(ICE_VF_STATE_ACTIVE, vf->vf_states); ops->reset_vf(vf); break; case VIRTCHNL_OP_ADD_ETH_ADDR: diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.h b/drivers/net/ethernet/intel/ice/ice_virtchnl.h index b454654d7b0c..cd747718de73 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.h @@ -63,6 +63,8 @@ int ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, enum virtchnl_status_code v_retval, u8 *msg, u16 msglen); bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id); +void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event, + struct ice_mbx_data *mbxdata); #else /* CONFIG_PCI_IOV */ static inline void ice_virtchnl_set_dflt_ops(struct ice_vf *vf) { } static inline void ice_virtchnl_set_repr_ops(struct ice_vf *vf) { } @@ -81,6 +83,12 @@ static inline bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id) { return false; } + +static inline void +ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event, + struct ice_mbx_data *mbxdata) +{ +} #endif /* !CONFIG_PCI_IOV */ #endif /* _ICE_VIRTCHNL_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c index e6ef6b303222..daa6a1e894cf 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c @@ -542,6 +542,87 @@ static void ice_vc_fdir_rem_prof_all(struct ice_vf *vf) } /** + * ice_vc_fdir_reset_cnt_all - reset all FDIR counters for this VF FDIR + * @fdir: pointer to the VF FDIR structure + */ +static void ice_vc_fdir_reset_cnt_all(struct ice_vf_fdir *fdir) +{ + enum ice_fltr_ptype flow; + + for (flow = ICE_FLTR_PTYPE_NONF_NONE; + flow < ICE_FLTR_PTYPE_MAX; flow++) { + fdir->fdir_fltr_cnt[flow][0] = 0; + fdir->fdir_fltr_cnt[flow][1] = 0; + } +} + +/** + * ice_vc_fdir_has_prof_conflict + * @vf: pointer to the VF structure + * @conf: FDIR configuration for each filter + * + * Check if @conf has conflicting profile with existing profiles + * + * Return: true on success, and false on error. + */ +static bool +ice_vc_fdir_has_prof_conflict(struct ice_vf *vf, + struct virtchnl_fdir_fltr_conf *conf) +{ + struct ice_fdir_fltr *desc; + + list_for_each_entry(desc, &vf->fdir.fdir_rule_list, fltr_node) { + struct virtchnl_fdir_fltr_conf *existing_conf; + enum ice_fltr_ptype flow_type_a, flow_type_b; + struct ice_fdir_fltr *a, *b; + + existing_conf = to_fltr_conf_from_desc(desc); + a = &existing_conf->input; + b = &conf->input; + flow_type_a = a->flow_type; + flow_type_b = b->flow_type; + + /* No need to compare two rules with different tunnel types or + * with the same protocol type. + */ + if (existing_conf->ttype != conf->ttype || + flow_type_a == flow_type_b) + continue; + + switch (flow_type_a) { + case ICE_FLTR_PTYPE_NONF_IPV4_UDP: + case ICE_FLTR_PTYPE_NONF_IPV4_TCP: + case ICE_FLTR_PTYPE_NONF_IPV4_SCTP: + if (flow_type_b == ICE_FLTR_PTYPE_NONF_IPV4_OTHER) + return true; + break; + case ICE_FLTR_PTYPE_NONF_IPV4_OTHER: + if (flow_type_b == ICE_FLTR_PTYPE_NONF_IPV4_UDP || + flow_type_b == ICE_FLTR_PTYPE_NONF_IPV4_TCP || + flow_type_b == ICE_FLTR_PTYPE_NONF_IPV4_SCTP) + return true; + break; + case ICE_FLTR_PTYPE_NONF_IPV6_UDP: + case ICE_FLTR_PTYPE_NONF_IPV6_TCP: + case ICE_FLTR_PTYPE_NONF_IPV6_SCTP: + if (flow_type_b == ICE_FLTR_PTYPE_NONF_IPV6_OTHER) + return true; + break; + case ICE_FLTR_PTYPE_NONF_IPV6_OTHER: + if (flow_type_b == ICE_FLTR_PTYPE_NONF_IPV6_UDP || + flow_type_b == ICE_FLTR_PTYPE_NONF_IPV6_TCP || + flow_type_b == ICE_FLTR_PTYPE_NONF_IPV6_SCTP) + return true; + break; + default: + break; + } + } + + return false; +} + +/** * ice_vc_fdir_write_flow_prof * @vf: pointer to the VF structure * @flow: filter flow type @@ -677,6 +758,13 @@ ice_vc_fdir_config_input_set(struct ice_vf *vf, struct virtchnl_fdir_add *fltr, enum ice_fltr_ptype flow; int ret; + ret = ice_vc_fdir_has_prof_conflict(vf, conf); + if (ret) { + dev_dbg(dev, "Found flow profile conflict for VF %d\n", + vf->vf_id); + return ret; + } + flow = input->flow_type; ret = ice_vc_fdir_alloc_prof(vf, flow); if (ret) { @@ -1798,7 +1886,7 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg) v_ret = VIRTCHNL_STATUS_SUCCESS; stat->status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE; dev_dbg(dev, "VF %d: set FDIR context failed\n", vf->vf_id); - goto err_free_conf; + goto err_rem_entry; } ret = ice_vc_fdir_write_fltr(vf, conf, true, is_tun); @@ -1807,15 +1895,16 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg) stat->status = VIRTCHNL_FDIR_FAILURE_RULE_NORESOURCE; dev_err(dev, "VF %d: writing FDIR rule failed, ret:%d\n", vf->vf_id, ret); - goto err_rem_entry; + goto err_clr_irq; } exit: kfree(stat); return ret; -err_rem_entry: +err_clr_irq: ice_vc_fdir_clear_irq_ctx(vf); +err_rem_entry: ice_vc_fdir_remove_entry(vf, conf, conf->flow_id); err_free_conf: devm_kfree(dev, conf); @@ -1924,6 +2013,7 @@ void ice_vf_fdir_init(struct ice_vf *vf) spin_lock_init(&fdir->ctx_lock); fdir->ctx_irq.flags = 0; fdir->ctx_done.flags = 0; + ice_vc_fdir_reset_cnt_all(fdir); } /** diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c index 31565bbafa22..d1e489da7363 100644 --- a/drivers/net/ethernet/intel/ice/ice_xsk.c +++ b/drivers/net/ethernet/intel/ice/ice_xsk.c @@ -184,8 +184,6 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) } netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx)); - ice_qvec_dis_irq(vsi, rx_ring, q_vector); - ice_fill_txq_meta(vsi, tx_ring, &txq_meta); err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, tx_ring, &txq_meta); if (err) @@ -200,10 +198,11 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx) if (err) return err; } + ice_qvec_dis_irq(vsi, rx_ring, q_vector); + err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true); if (err) return err; - ice_clean_rx_ring(rx_ring); ice_qvec_toggle_napi(vsi, q_vector, false); ice_qp_clean_rings(vsi, q_idx); diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.c b/drivers/net/ethernet/intel/igb/e1000_mac.c index 205d577bdbba..caf91c6f52b4 100644 --- a/drivers/net/ethernet/intel/igb/e1000_mac.c +++ b/drivers/net/ethernet/intel/igb/e1000_mac.c @@ -426,7 +426,7 @@ void igb_mta_set(struct e1000_hw *hw, u32 hash_value) static u32 igb_hash_mc_addr(struct e1000_hw *hw, u8 *mc_addr) { u32 hash_value, hash_mask; - u8 bit_shift = 0; + u8 bit_shift = 1; /* Register count multiplied by bits per register */ hash_mask = (hw->mac.mta_reg_count * 32) - 1; @@ -434,7 +434,7 @@ static u32 igb_hash_mc_addr(struct e1000_hw *hw, u8 *mc_addr) /* For a mc_filter_type of 0, bit_shift is the number of left-shifts * where 0xFF would still fall within the hash mask. */ - while (hash_mask >> bit_shift != 0xFF) + while (hash_mask >> bit_shift != 0xFF && bit_shift < 4) bit_shift++; /* The portion of the address that is used for the hash table diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 7d60da1b7bf4..319ed601eaa1 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -822,6 +822,8 @@ static int igb_set_eeprom(struct net_device *netdev, */ ret_val = hw->nvm.ops.read(hw, last_word, 1, &eeprom_buff[last_word - first_word]); + if (ret_val) + goto out; } /* Device's eeprom is always little-endian, word addressable */ @@ -841,6 +843,7 @@ static int igb_set_eeprom(struct net_device *netdev, hw->nvm.ops.update(hw); igb_set_fw_version(adapter); +out: kfree(eeprom_buff); return ret_val; } diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 03bc1e8af575..bb3db387d49c 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -28,7 +28,6 @@ #include <linux/tcp.h> #include <linux/sctp.h> #include <linux/if_ether.h> -#include <linux/aer.h> #include <linux/prefetch.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> @@ -109,6 +108,7 @@ static void igb_free_all_rx_resources(struct igb_adapter *); static void igb_setup_mrqc(struct igb_adapter *); static int igb_probe(struct pci_dev *, const struct pci_device_id *); static void igb_remove(struct pci_dev *pdev); +static void igb_init_queue_configuration(struct igb_adapter *adapter); static int igb_sw_init(struct igb_adapter *); int igb_open(struct net_device *); int igb_close(struct net_device *); @@ -175,9 +175,7 @@ static void igb_nfc_filter_restore(struct igb_adapter *adapter); #ifdef CONFIG_PCI_IOV static int igb_vf_configure(struct igb_adapter *adapter, int vf); -static int igb_pci_enable_sriov(struct pci_dev *dev, int num_vfs); -static int igb_disable_sriov(struct pci_dev *dev); -static int igb_pci_disable_sriov(struct pci_dev *dev); +static int igb_disable_sriov(struct pci_dev *dev, bool reinit); #endif static int igb_suspend(struct device *); @@ -3665,7 +3663,7 @@ err_sw_init: kfree(adapter->shadow_vfta); igb_clear_interrupt_scheme(adapter); #ifdef CONFIG_PCI_IOV - igb_disable_sriov(pdev); + igb_disable_sriov(pdev, false); #endif pci_iounmap(pdev, adapter->io_addr); err_ioremap: @@ -3679,7 +3677,38 @@ err_dma: } #ifdef CONFIG_PCI_IOV -static int igb_disable_sriov(struct pci_dev *pdev) +static int igb_sriov_reinit(struct pci_dev *dev) +{ + struct net_device *netdev = pci_get_drvdata(dev); + struct igb_adapter *adapter = netdev_priv(netdev); + struct pci_dev *pdev = adapter->pdev; + + rtnl_lock(); + + if (netif_running(netdev)) + igb_close(netdev); + else + igb_reset(adapter); + + igb_clear_interrupt_scheme(adapter); + + igb_init_queue_configuration(adapter); + + if (igb_init_interrupt_scheme(adapter, true)) { + rtnl_unlock(); + dev_err(&pdev->dev, "Unable to allocate memory for queues\n"); + return -ENOMEM; + } + + if (netif_running(netdev)) + igb_open(netdev); + + rtnl_unlock(); + + return 0; +} + +static int igb_disable_sriov(struct pci_dev *pdev, bool reinit) { struct net_device *netdev = pci_get_drvdata(pdev); struct igb_adapter *adapter = netdev_priv(netdev); @@ -3713,10 +3742,10 @@ static int igb_disable_sriov(struct pci_dev *pdev) adapter->flags |= IGB_FLAG_DMAC; } - return 0; + return reinit ? igb_sriov_reinit(pdev) : 0; } -static int igb_enable_sriov(struct pci_dev *pdev, int num_vfs) +static int igb_enable_sriov(struct pci_dev *pdev, int num_vfs, bool reinit) { struct net_device *netdev = pci_get_drvdata(pdev); struct igb_adapter *adapter = netdev_priv(netdev); @@ -3781,12 +3810,6 @@ static int igb_enable_sriov(struct pci_dev *pdev, int num_vfs) "Unable to allocate memory for VF MAC filter list\n"); } - /* only call pci_enable_sriov() if no VFs are allocated already */ - if (!old_vfs) { - err = pci_enable_sriov(pdev, adapter->vfs_allocated_count); - if (err) - goto err_out; - } dev_info(&pdev->dev, "%d VFs allocated\n", adapter->vfs_allocated_count); for (i = 0; i < adapter->vfs_allocated_count; i++) @@ -3794,6 +3817,17 @@ static int igb_enable_sriov(struct pci_dev *pdev, int num_vfs) /* DMA Coalescing is not supported in IOV mode. */ adapter->flags &= ~IGB_FLAG_DMAC; + + if (reinit) { + err = igb_sriov_reinit(pdev); + if (err) + goto err_out; + } + + /* only call pci_enable_sriov() if no VFs are allocated already */ + if (!old_vfs) + err = pci_enable_sriov(pdev, adapter->vfs_allocated_count); + goto out; err_out: @@ -3863,9 +3897,7 @@ static void igb_remove(struct pci_dev *pdev) igb_release_hw_control(adapter); #ifdef CONFIG_PCI_IOV - rtnl_lock(); - igb_disable_sriov(pdev); - rtnl_unlock(); + igb_disable_sriov(pdev, false); #endif unregister_netdev(netdev); @@ -3911,7 +3943,7 @@ static void igb_probe_vfs(struct igb_adapter *adapter) igb_reset_interrupt_capability(adapter); pci_sriov_set_totalvfs(pdev, 7); - igb_enable_sriov(pdev, max_vfs); + igb_enable_sriov(pdev, max_vfs, false); #endif /* CONFIG_PCI_IOV */ } @@ -6915,6 +6947,7 @@ static void igb_extts(struct igb_adapter *adapter, int tsintr_tt) struct e1000_hw *hw = &adapter->hw; struct ptp_clock_event event; struct timespec64 ts; + unsigned long flags; if (pin < 0 || pin >= IGB_N_SDP) return; @@ -6922,9 +6955,12 @@ static void igb_extts(struct igb_adapter *adapter, int tsintr_tt) if (hw->mac.type == e1000_82580 || hw->mac.type == e1000_i354 || hw->mac.type == e1000_i350) { - s64 ns = rd32(auxstmpl); + u64 ns = rd32(auxstmpl); - ns += ((s64)(rd32(auxstmph) & 0xFF)) << 32; + ns += ((u64)(rd32(auxstmph) & 0xFF)) << 32; + spin_lock_irqsave(&adapter->tmreg_lock, flags); + ns = timecounter_cyc2time(&adapter->tc, ns); + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); ts = ns_to_timespec64(ns); } else { ts.tv_nsec = rd32(auxstmpl); @@ -9520,71 +9556,17 @@ static void igb_shutdown(struct pci_dev *pdev) } } -#ifdef CONFIG_PCI_IOV -static int igb_sriov_reinit(struct pci_dev *dev) -{ - struct net_device *netdev = pci_get_drvdata(dev); - struct igb_adapter *adapter = netdev_priv(netdev); - struct pci_dev *pdev = adapter->pdev; - - rtnl_lock(); - - if (netif_running(netdev)) - igb_close(netdev); - else - igb_reset(adapter); - - igb_clear_interrupt_scheme(adapter); - - igb_init_queue_configuration(adapter); - - if (igb_init_interrupt_scheme(adapter, true)) { - rtnl_unlock(); - dev_err(&pdev->dev, "Unable to allocate memory for queues\n"); - return -ENOMEM; - } - - if (netif_running(netdev)) - igb_open(netdev); - - rtnl_unlock(); - - return 0; -} - -static int igb_pci_disable_sriov(struct pci_dev *dev) -{ - int err = igb_disable_sriov(dev); - - if (!err) - err = igb_sriov_reinit(dev); - - return err; -} - -static int igb_pci_enable_sriov(struct pci_dev *dev, int num_vfs) -{ - int err = igb_enable_sriov(dev, num_vfs); - - if (err) - goto out; - - err = igb_sriov_reinit(dev); - if (!err) - return num_vfs; - -out: - return err; -} - -#endif static int igb_pci_sriov_configure(struct pci_dev *dev, int num_vfs) { #ifdef CONFIG_PCI_IOV - if (num_vfs == 0) - return igb_pci_disable_sriov(dev); - else - return igb_pci_enable_sriov(dev, num_vfs); + int err; + + if (num_vfs == 0) { + return igb_disable_sriov(dev, true); + } else { + err = igb_enable_sriov(dev, num_vfs, true); + return err ? err : num_vfs; + } #endif return 0; } diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 6f471b91f562..405886ee5261 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -67,6 +67,7 @@ #define INCVALUE_82576_MASK GENMASK(E1000_TIMINCA_16NS_SHIFT - 1, 0) #define INCVALUE_82576 (16u << IGB_82576_TSYNC_SHIFT) #define IGB_NBITS_82580 40 +#define IGB_82580_BASE_PERIOD 0x800000000 static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter); static void igb_ptp_sdp_init(struct igb_adapter *adapter); @@ -209,17 +210,11 @@ static int igb_ptp_adjfine_82580(struct ptp_clock_info *ptp, long scaled_ppm) struct igb_adapter *igb = container_of(ptp, struct igb_adapter, ptp_caps); struct e1000_hw *hw = &igb->hw; - int neg_adj = 0; + bool neg_adj; u64 rate; u32 inca; - if (scaled_ppm < 0) { - neg_adj = 1; - scaled_ppm = -scaled_ppm; - } - rate = scaled_ppm; - rate <<= 13; - rate = div_u64(rate, 15625); + neg_adj = diff_by_scaled_ppm(IGB_82580_BASE_PERIOD, scaled_ppm, &rate); inca = rate & INCVALUE_MASK; if (neg_adj) diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 3a32809510fc..7ff2752dd763 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -1074,7 +1074,7 @@ static int igbvf_request_msix(struct igbvf_adapter *adapter) igbvf_intr_msix_rx, 0, adapter->rx_ring->name, netdev); if (err) - goto out; + goto free_irq_tx; adapter->rx_ring->itr_register = E1000_EITR(vector); adapter->rx_ring->itr_val = adapter->current_itr; @@ -1083,10 +1083,14 @@ static int igbvf_request_msix(struct igbvf_adapter *adapter) err = request_irq(adapter->msix_entries[vector].vector, igbvf_msix_other, 0, netdev->name, netdev); if (err) - goto out; + goto free_irq_rx; igbvf_configure_msix(adapter); return 0; +free_irq_rx: + free_irq(adapter->msix_entries[--vector].vector, netdev); +free_irq_tx: + free_irq(adapter->msix_entries[--vector].vector, netdev); out: return err; } @@ -2589,6 +2593,33 @@ static void igbvf_io_resume(struct pci_dev *pdev) netif_device_attach(netdev); } +/** + * igbvf_io_prepare - prepare device driver for PCI reset + * @pdev: PCI device information struct + */ +static void igbvf_io_prepare(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct igbvf_adapter *adapter = netdev_priv(netdev); + + while (test_and_set_bit(__IGBVF_RESETTING, &adapter->state)) + usleep_range(1000, 2000); + igbvf_down(adapter); +} + +/** + * igbvf_io_reset_done - PCI reset done, device driver reset can begin + * @pdev: PCI device information struct + */ +static void igbvf_io_reset_done(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct igbvf_adapter *adapter = netdev_priv(netdev); + + igbvf_up(adapter); + clear_bit(__IGBVF_RESETTING, &adapter->state); +} + static void igbvf_print_device_info(struct igbvf_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; @@ -2916,6 +2947,8 @@ static const struct pci_error_handlers igbvf_err_handler = { .error_detected = igbvf_io_error_detected, .slot_reset = igbvf_io_slot_reset, .resume = igbvf_io_resume, + .reset_prepare = igbvf_io_prepare, + .reset_done = igbvf_io_reset_done, }; static const struct pci_device_id igbvf_pci_tbl[] = { diff --git a/drivers/net/ethernet/intel/igbvf/vf.c b/drivers/net/ethernet/intel/igbvf/vf.c index b8ba3f94c363..a47a2e3e548c 100644 --- a/drivers/net/ethernet/intel/igbvf/vf.c +++ b/drivers/net/ethernet/intel/igbvf/vf.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2009 - 2018 Intel Corporation. */ +#include <linux/etherdevice.h> + #include "vf.h" static s32 e1000_check_for_link_vf(struct e1000_hw *hw); @@ -131,11 +133,16 @@ static s32 e1000_reset_hw_vf(struct e1000_hw *hw) /* set our "perm_addr" based on info provided by PF */ ret_val = mbx->ops.read_posted(hw, msgbuf, 3); if (!ret_val) { - if (msgbuf[0] == (E1000_VF_RESET | - E1000_VT_MSGTYPE_ACK)) + switch (msgbuf[0]) { + case E1000_VF_RESET | E1000_VT_MSGTYPE_ACK: memcpy(hw->mac.perm_addr, addr, ETH_ALEN); - else + break; + case E1000_VF_RESET | E1000_VT_MSGTYPE_NACK: + eth_zero_addr(hw->mac.perm_addr); + break; + default: ret_val = -E1000_ERR_MAC_INIT; + } } } diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index df3e26c0cf01..34aebf00a512 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -99,6 +99,7 @@ struct igc_ring { u32 start_time; u32 end_time; + u32 max_sdu; /* CBS parameters */ bool cbs_enable; /* indicates if CBS is enabled */ @@ -185,6 +186,7 @@ struct igc_adapter { ktime_t base_time; ktime_t cycle_time; bool qbv_enable; + u32 qbv_config_change_errors; /* OS defined structs */ struct pci_dev *pdev; @@ -292,8 +294,6 @@ extern char igc_driver_name[]; #define IGC_FLAG_PTP BIT(8) #define IGC_FLAG_WOL_SUPPORTED BIT(8) #define IGC_FLAG_NEED_LINK_UPDATE BIT(9) -#define IGC_FLAG_MEDIA_RESET BIT(10) -#define IGC_FLAG_MAS_ENABLE BIT(12) #define IGC_FLAG_HAS_MSIX BIT(13) #define IGC_FLAG_EEE BIT(14) #define IGC_FLAG_VLAN_PROMISC BIT(15) diff --git a/drivers/net/ethernet/intel/igc/igc_base.h b/drivers/net/ethernet/intel/igc/igc_base.h index 7a992befca24..9f3827eda157 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.h +++ b/drivers/net/ethernet/intel/igc/igc_base.h @@ -87,8 +87,13 @@ union igc_adv_rx_desc { #define IGC_RXDCTL_SWFLUSH 0x04000000 /* Receive Software Flush */ /* SRRCTL bit definitions */ -#define IGC_SRRCTL_BSIZEPKT_SHIFT 10 /* Shift _right_ */ -#define IGC_SRRCTL_BSIZEHDRSIZE_SHIFT 2 /* Shift _left_ */ -#define IGC_SRRCTL_DESCTYPE_ADV_ONEBUF 0x02000000 +#define IGC_SRRCTL_BSIZEPKT_MASK GENMASK(6, 0) +#define IGC_SRRCTL_BSIZEPKT(x) FIELD_PREP(IGC_SRRCTL_BSIZEPKT_MASK, \ + (x) / 1024) /* in 1 KB resolution */ +#define IGC_SRRCTL_BSIZEHDR_MASK GENMASK(13, 8) +#define IGC_SRRCTL_BSIZEHDR(x) FIELD_PREP(IGC_SRRCTL_BSIZEHDR_MASK, \ + (x) / 64) /* in 64 bytes resolution */ +#define IGC_SRRCTL_DESCTYPE_MASK GENMASK(27, 25) +#define IGC_SRRCTL_DESCTYPE_ADV_ONEBUF FIELD_PREP(IGC_SRRCTL_DESCTYPE_MASK, 1) #endif /* _IGC_BASE_H */ diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index 9dec3563ce3a..44a507029946 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -662,9 +662,6 @@ */ #define IGC_TW_SYSTEM_100_MASK 0x0000FF00 #define IGC_TW_SYSTEM_100_SHIFT 8 -#define IGC_DMACR_DMAC_EN 0x80000000 /* Enable DMA Coalescing */ -#define IGC_DMACR_DMACTHR_MASK 0x00FF0000 -#define IGC_DMACR_DMACTHR_SHIFT 16 /* Reg val to set scale to 1024 nsec */ #define IGC_LTRMINV_SCALE_1024 2 /* Reg val to set scale to 32768 nsec */ diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index 5a26a7805ef8..0e2cb00622d1 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -67,6 +67,7 @@ static const struct igc_stats igc_gstrings_stats[] = { IGC_STAT("rx_hwtstamp_cleared", rx_hwtstamp_cleared), IGC_STAT("tx_lpi_counter", stats.tlpic), IGC_STAT("rx_lpi_counter", stats.rlpic), + IGC_STAT("qbv_config_change_errors", qbv_config_change_errors), }; #define IGC_NETDEV_STAT(_net_stat) { \ diff --git a/drivers/net/ethernet/intel/igc/igc_hw.h b/drivers/net/ethernet/intel/igc/igc_hw.h index 88680e3d613d..e1c572e0d4ef 100644 --- a/drivers/net/ethernet/intel/igc/igc_hw.h +++ b/drivers/net/ethernet/intel/igc/igc_hw.h @@ -273,6 +273,7 @@ struct igc_hw_stats { u64 o2bspc; u64 b2ospc; u64 b2ogprc; + u64 txdrop; }; struct net_device *igc_get_hw_dev(struct igc_hw *hw); diff --git a/drivers/net/ethernet/intel/igc/igc_i225.c b/drivers/net/ethernet/intel/igc/igc_i225.c index 59d5c467ea6e..17546a035ab1 100644 --- a/drivers/net/ethernet/intel/igc/igc_i225.c +++ b/drivers/net/ethernet/intel/igc/igc_i225.c @@ -593,20 +593,11 @@ s32 igc_set_ltr_i225(struct igc_hw *hw, bool link) size = rd32(IGC_RXPBS) & IGC_RXPBS_SIZE_I225_MASK; - /* Calculations vary based on DMAC settings. */ - if (rd32(IGC_DMACR) & IGC_DMACR_DMAC_EN) { - size -= (rd32(IGC_DMACR) & - IGC_DMACR_DMACTHR_MASK) >> - IGC_DMACR_DMACTHR_SHIFT; - /* Convert size to bits. */ - size *= 1024 * 8; - } else { - /* Convert size to bytes, subtract the MTU, and then - * convert the size to bits. - */ - size *= 1024; - size *= 8; - } + /* Convert size to bytes, subtract the MTU, and then + * convert the size to bits. + */ + size *= 1024; + size *= 8; if (size < 0) { hw_dbg("Invalid effective Rx buffer size %d\n", diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 2928a6c73692..fa764190f270 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -4,7 +4,6 @@ #include <linux/module.h> #include <linux/types.h> #include <linux/if_vlan.h> -#include <linux/aer.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/ip.h> @@ -255,6 +254,13 @@ static void igc_clean_tx_ring(struct igc_ring *tx_ring) /* reset BQL for queue */ netdev_tx_reset_queue(txring_txq(tx_ring)); + /* Zero out the buffer ring */ + memset(tx_ring->tx_buffer_info, 0, + sizeof(*tx_ring->tx_buffer_info) * tx_ring->count); + + /* Zero out the descriptor ring */ + memset(tx_ring->desc, 0, tx_ring->size); + /* reset next_to_use and next_to_clean */ tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; @@ -268,7 +274,7 @@ static void igc_clean_tx_ring(struct igc_ring *tx_ring) */ void igc_free_tx_resources(struct igc_ring *tx_ring) { - igc_clean_tx_ring(tx_ring); + igc_disable_tx_ring(tx_ring); vfree(tx_ring->tx_buffer_info); tx_ring->tx_buffer_info = NULL; @@ -641,8 +647,11 @@ static void igc_configure_rx_ring(struct igc_adapter *adapter, else buf_size = IGC_RXBUFFER_2048; - srrctl = IGC_RX_HDR_LEN << IGC_SRRCTL_BSIZEHDRSIZE_SHIFT; - srrctl |= buf_size >> IGC_SRRCTL_BSIZEPKT_SHIFT; + srrctl = rd32(IGC_SRRCTL(reg_idx)); + srrctl &= ~(IGC_SRRCTL_BSIZEPKT_MASK | IGC_SRRCTL_BSIZEHDR_MASK | + IGC_SRRCTL_DESCTYPE_MASK); + srrctl |= IGC_SRRCTL_BSIZEHDR(IGC_RX_HDR_LEN); + srrctl |= IGC_SRRCTL_BSIZEPKT(buf_size); srrctl |= IGC_SRRCTL_DESCTYPE_ADV_ONEBUF; wr32(IGC_SRRCTL(reg_idx), srrctl); @@ -1501,6 +1510,7 @@ static int igc_tso(struct igc_ring *tx_ring, static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, struct igc_ring *tx_ring) { + struct igc_adapter *adapter = netdev_priv(tx_ring->netdev); bool first_flag = false, insert_empty = false; u16 count = TXD_USE_COUNT(skb_headlen(skb)); __be16 protocol = vlan_get_protocol(skb); @@ -1563,9 +1573,19 @@ done: first->bytecount = skb->len; first->gso_segs = 1; - if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { - struct igc_adapter *adapter = netdev_priv(tx_ring->netdev); + if (tx_ring->max_sdu > 0) { + u32 max_sdu = 0; + + max_sdu = tx_ring->max_sdu + + (skb_vlan_tagged(first->skb) ? VLAN_HLEN : 0); + + if (first->bytecount > max_sdu) { + adapter->stats.txdrop++; + goto out_drop; + } + } + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { /* FIXME: add support for retrieving timestamps from * the other timer registers before skipping the * timestamping request. @@ -4920,7 +4940,8 @@ void igc_update_stats(struct igc_adapter *adapter) net_stats->tx_window_errors = adapter->stats.latecol; net_stats->tx_carrier_errors = adapter->stats.tncrs; - /* Tx Dropped needs to be maintained elsewhere */ + /* Tx Dropped */ + net_stats->tx_dropped = adapter->stats.txdrop; /* Management Stats */ adapter->stats.mgptc += rd32(IGC_MGTPTC); @@ -5566,25 +5587,8 @@ no_wait: mod_timer(&adapter->phy_info_timer, round_jiffies(jiffies + 2 * HZ)); - /* link is down, time to check for alternate media */ - if (adapter->flags & IGC_FLAG_MAS_ENABLE) { - if (adapter->flags & IGC_FLAG_MEDIA_RESET) { - schedule_work(&adapter->reset_task); - /* return immediately */ - return; - } - } pm_schedule_suspend(netdev->dev.parent, MSEC_PER_SEC * 5); - - /* also check for alternate media here */ - } else if (!netif_carrier_ok(netdev) && - (adapter->flags & IGC_FLAG_MAS_ENABLE)) { - if (adapter->flags & IGC_FLAG_MEDIA_RESET) { - schedule_work(&adapter->reset_task); - /* return immediately */ - return; - } } } @@ -6010,18 +6014,18 @@ static bool validate_schedule(struct igc_adapter *adapter, if (e->command != TC_TAPRIO_CMD_SET_GATES) return false; - for (i = 0; i < adapter->num_tx_queues; i++) { - if (e->gate_mask & BIT(i)) + for (i = 0; i < adapter->num_tx_queues; i++) + if (e->gate_mask & BIT(i)) { queue_uses[i]++; - /* There are limitations: A single queue cannot be - * opened and closed multiple times per cycle unless the - * gate stays open. Check for it. - */ - if (queue_uses[i] > 1 && - !(prev->gate_mask & BIT(i))) - return false; - } + /* There are limitations: A single queue cannot + * be opened and closed multiple times per cycle + * unless the gate stays open. Check for it. + */ + if (queue_uses[i] > 1 && + !(prev->gate_mask & BIT(i))) + return false; + } } return true; @@ -6049,12 +6053,14 @@ static int igc_tsn_clear_schedule(struct igc_adapter *adapter) adapter->base_time = 0; adapter->cycle_time = NSEC_PER_SEC; + adapter->qbv_config_change_errors = 0; for (i = 0; i < adapter->num_tx_queues; i++) { struct igc_ring *ring = adapter->tx_ring[i]; ring->start_time = 0; ring->end_time = NSEC_PER_SEC; + ring->max_sdu = 0; } return 0; @@ -6138,6 +6144,16 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, } } + for (i = 0; i < adapter->num_tx_queues; i++) { + struct igc_ring *ring = adapter->tx_ring[i]; + struct net_device *dev = adapter->netdev; + + if (qopt->max_sdu[i]) + ring->max_sdu = qopt->max_sdu[i] + dev->hard_header_len; + else + ring->max_sdu = 0; + } + return 0; } @@ -6236,8 +6252,10 @@ static int igc_tc_query_caps(struct igc_adapter *adapter, caps->broken_mqprio = true; - if (hw->mac.type == igc_i225) + if (hw->mac.type == igc_i225) { + caps->supports_queue_max_sdu = true; caps->gate_mask_per_txq = true; + } return 0; } @@ -6712,6 +6730,9 @@ static void igc_remove(struct pci_dev *pdev) igc_ptp_stop(adapter); + pci_disable_ptm(pdev); + pci_clear_master(pdev); + set_bit(__IGC_DOWN, &adapter->state); del_timer_sync(&adapter->watchdog_timer); diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h index 01c86d36856d..dba5a5759b1c 100644 --- a/drivers/net/ethernet/intel/igc/igc_regs.h +++ b/drivers/net/ethernet/intel/igc/igc_regs.h @@ -292,7 +292,6 @@ /* LTR registers */ #define IGC_LTRC 0x01A0 /* Latency Tolerance Reporting Control */ -#define IGC_DMACR 0x02508 /* DMA Coalescing Control Register */ #define IGC_LTRMINV 0x5BB0 /* LTR Minimum Value */ #define IGC_LTRMAXV 0x5BB4 /* LTR Maximum Value */ diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index a386c8d61dbf..94a2b0dfb54d 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -114,6 +114,7 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) static int igc_tsn_enable_offload(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; + bool tsn_mode_reconfig = false; u32 tqavctrl, baset_l, baset_h; u32 sec, nsec, cycle; ktime_t base_time, systim; @@ -226,6 +227,10 @@ skip_cbs: } tqavctrl = rd32(IGC_TQAVCTRL) & ~IGC_TQAVCTRL_FUTSCDDIS; + + if (tqavctrl & IGC_TQAVCTRL_TRANSMIT_MODE_TSN) + tsn_mode_reconfig = true; + tqavctrl |= IGC_TQAVCTRL_TRANSMIT_MODE_TSN | IGC_TQAVCTRL_ENHANCED_QAV; cycle = adapter->cycle_time; @@ -239,6 +244,13 @@ skip_cbs: s64 n = div64_s64(ktime_sub_ns(systim, base_time), cycle); base_time = ktime_add_ns(base_time, (n + 1) * cycle); + + /* Increase the counter if scheduling into the past while + * Gate Control List (GCL) is running. + */ + if ((rd32(IGC_BASET_H) || rd32(IGC_BASET_L)) && + tsn_mode_reconfig) + adapter->qbv_config_change_errors++; } else { /* According to datasheet section 7.5.2.9.3.3, FutScdDis bit * has to be configured before the cycle time and base time. diff --git a/drivers/net/ethernet/intel/ixgb/Makefile b/drivers/net/ethernet/intel/ixgb/Makefile deleted file mode 100644 index 2433e9300a33..000000000000 --- a/drivers/net/ethernet/intel/ixgb/Makefile +++ /dev/null @@ -1,9 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0 -# Copyright(c) 1999 - 2008 Intel Corporation. -# -# Makefile for the Intel(R) PRO/10GbE ethernet driver -# - -obj-$(CONFIG_IXGB) += ixgb.o - -ixgb-objs := ixgb_main.o ixgb_hw.o ixgb_ee.o ixgb_ethtool.o ixgb_param.o diff --git a/drivers/net/ethernet/intel/ixgb/ixgb.h b/drivers/net/ethernet/intel/ixgb/ixgb.h deleted file mode 100644 index 81ac39576803..000000000000 --- a/drivers/net/ethernet/intel/ixgb/ixgb.h +++ /dev/null @@ -1,179 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 1999 - 2008 Intel Corporation. */ - -#ifndef _IXGB_H_ -#define _IXGB_H_ - -#include <linux/stddef.h> -#include <linux/module.h> -#include <linux/types.h> -#include <asm/byteorder.h> -#include <linux/mm.h> -#include <linux/errno.h> -#include <linux/ioport.h> -#include <linux/pci.h> -#include <linux/kernel.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/skbuff.h> -#include <linux/delay.h> -#include <linux/timer.h> -#include <linux/slab.h> -#include <linux/vmalloc.h> -#include <linux/interrupt.h> -#include <linux/string.h> -#include <linux/pagemap.h> -#include <linux/dma-mapping.h> -#include <linux/bitops.h> -#include <asm/io.h> -#include <asm/irq.h> -#include <linux/capability.h> -#include <linux/in.h> -#include <linux/ip.h> -#include <linux/tcp.h> -#include <linux/udp.h> -#include <net/pkt_sched.h> -#include <linux/list.h> -#include <linux/reboot.h> -#include <net/checksum.h> - -#include <linux/ethtool.h> -#include <linux/if_vlan.h> - -#define BAR_0 0 -#define BAR_1 1 - -struct ixgb_adapter; -#include "ixgb_hw.h" -#include "ixgb_ee.h" -#include "ixgb_ids.h" - -/* TX/RX descriptor defines */ -#define DEFAULT_TXD 256 -#define MAX_TXD 4096 -#define MIN_TXD 64 - -/* hardware cannot reliably support more than 512 descriptors owned by - * hardware descriptor cache otherwise an unreliable ring under heavy - * receive load may result */ -#define DEFAULT_RXD 512 -#define MAX_RXD 512 -#define MIN_RXD 64 - -/* Supported Rx Buffer Sizes */ -#define IXGB_RXBUFFER_2048 2048 -#define IXGB_RXBUFFER_4096 4096 -#define IXGB_RXBUFFER_8192 8192 -#define IXGB_RXBUFFER_16384 16384 - -/* How many Rx Buffers do we bundle into one write to the hardware ? */ -#define IXGB_RX_BUFFER_WRITE 8 /* Must be power of 2 */ - -/* wrapper around a pointer to a socket buffer, - * so a DMA handle can be stored along with the buffer */ -struct ixgb_buffer { - struct sk_buff *skb; - dma_addr_t dma; - unsigned long time_stamp; - u16 length; - u16 next_to_watch; - u16 mapped_as_page; -}; - -struct ixgb_desc_ring { - /* pointer to the descriptor ring memory */ - void *desc; - /* physical address of the descriptor ring */ - dma_addr_t dma; - /* length of descriptor ring in bytes */ - unsigned int size; - /* number of descriptors in the ring */ - unsigned int count; - /* next descriptor to associate a buffer with */ - unsigned int next_to_use; - /* next descriptor to check for DD status bit */ - unsigned int next_to_clean; - /* array of buffer information structs */ - struct ixgb_buffer *buffer_info; -}; - -#define IXGB_DESC_UNUSED(R) \ - ((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \ - (R)->next_to_clean - (R)->next_to_use - 1) - -#define IXGB_GET_DESC(R, i, type) (&(((struct type *)((R).desc))[i])) -#define IXGB_RX_DESC(R, i) IXGB_GET_DESC(R, i, ixgb_rx_desc) -#define IXGB_TX_DESC(R, i) IXGB_GET_DESC(R, i, ixgb_tx_desc) -#define IXGB_CONTEXT_DESC(R, i) IXGB_GET_DESC(R, i, ixgb_context_desc) - -/* board specific private data structure */ - -struct ixgb_adapter { - struct timer_list watchdog_timer; - unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; - u32 bd_number; - u32 rx_buffer_len; - u32 part_num; - u16 link_speed; - u16 link_duplex; - struct work_struct tx_timeout_task; - - /* TX */ - struct ixgb_desc_ring tx_ring ____cacheline_aligned_in_smp; - unsigned int restart_queue; - unsigned long timeo_start; - u32 tx_cmd_type; - u64 hw_csum_tx_good; - u64 hw_csum_tx_error; - u32 tx_int_delay; - u32 tx_timeout_count; - bool tx_int_delay_enable; - bool detect_tx_hung; - - /* RX */ - struct ixgb_desc_ring rx_ring; - u64 hw_csum_rx_error; - u64 hw_csum_rx_good; - u32 rx_int_delay; - bool rx_csum; - - /* OS defined structs */ - struct napi_struct napi; - struct net_device *netdev; - struct pci_dev *pdev; - - /* structs defined in ixgb_hw.h */ - struct ixgb_hw hw; - u16 msg_enable; - struct ixgb_hw_stats stats; - u32 alloc_rx_buff_failed; - bool have_msi; - unsigned long flags; -}; - -enum ixgb_state_t { - /* TBD - __IXGB_TESTING, - __IXGB_RESETTING, - */ - __IXGB_DOWN -}; - -/* Exported from other modules */ -void ixgb_check_options(struct ixgb_adapter *adapter); -void ixgb_set_ethtool_ops(struct net_device *netdev); -extern char ixgb_driver_name[]; - -void ixgb_set_speed_duplex(struct net_device *netdev); - -int ixgb_up(struct ixgb_adapter *adapter); -void ixgb_down(struct ixgb_adapter *adapter, bool kill_watchdog); -void ixgb_reset(struct ixgb_adapter *adapter); -int ixgb_setup_rx_resources(struct ixgb_adapter *adapter); -int ixgb_setup_tx_resources(struct ixgb_adapter *adapter); -void ixgb_free_rx_resources(struct ixgb_adapter *adapter); -void ixgb_free_tx_resources(struct ixgb_adapter *adapter); -void ixgb_update_stats(struct ixgb_adapter *adapter); - - -#endif /* _IXGB_H_ */ diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ee.c b/drivers/net/ethernet/intel/ixgb/ixgb_ee.c deleted file mode 100644 index 129286fc1634..000000000000 --- a/drivers/net/ethernet/intel/ixgb/ixgb_ee.c +++ /dev/null @@ -1,580 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2008 Intel Corporation. */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include "ixgb_hw.h" -#include "ixgb_ee.h" -/* Local prototypes */ -static u16 ixgb_shift_in_bits(struct ixgb_hw *hw); - -static void ixgb_shift_out_bits(struct ixgb_hw *hw, - u16 data, - u16 count); -static void ixgb_standby_eeprom(struct ixgb_hw *hw); - -static bool ixgb_wait_eeprom_command(struct ixgb_hw *hw); - -static void ixgb_cleanup_eeprom(struct ixgb_hw *hw); - -/****************************************************************************** - * Raises the EEPROM's clock input. - * - * hw - Struct containing variables accessed by shared code - * eecd_reg - EECD's current value - *****************************************************************************/ -static void -ixgb_raise_clock(struct ixgb_hw *hw, - u32 *eecd_reg) -{ - /* Raise the clock input to the EEPROM (by setting the SK bit), and then - * wait 50 microseconds. - */ - *eecd_reg = *eecd_reg | IXGB_EECD_SK; - IXGB_WRITE_REG(hw, EECD, *eecd_reg); - IXGB_WRITE_FLUSH(hw); - udelay(50); -} - -/****************************************************************************** - * Lowers the EEPROM's clock input. - * - * hw - Struct containing variables accessed by shared code - * eecd_reg - EECD's current value - *****************************************************************************/ -static void -ixgb_lower_clock(struct ixgb_hw *hw, - u32 *eecd_reg) -{ - /* Lower the clock input to the EEPROM (by clearing the SK bit), and then - * wait 50 microseconds. - */ - *eecd_reg = *eecd_reg & ~IXGB_EECD_SK; - IXGB_WRITE_REG(hw, EECD, *eecd_reg); - IXGB_WRITE_FLUSH(hw); - udelay(50); -} - -/****************************************************************************** - * Shift data bits out to the EEPROM. - * - * hw - Struct containing variables accessed by shared code - * data - data to send to the EEPROM - * count - number of bits to shift out - *****************************************************************************/ -static void -ixgb_shift_out_bits(struct ixgb_hw *hw, - u16 data, - u16 count) -{ - u32 eecd_reg; - u32 mask; - - /* We need to shift "count" bits out to the EEPROM. So, value in the - * "data" parameter will be shifted out to the EEPROM one bit at a time. - * In order to do this, "data" must be broken down into bits. - */ - mask = 0x01 << (count - 1); - eecd_reg = IXGB_READ_REG(hw, EECD); - eecd_reg &= ~(IXGB_EECD_DO | IXGB_EECD_DI); - do { - /* A "1" is shifted out to the EEPROM by setting bit "DI" to a "1", - * and then raising and then lowering the clock (the SK bit controls - * the clock input to the EEPROM). A "0" is shifted out to the EEPROM - * by setting "DI" to "0" and then raising and then lowering the clock. - */ - eecd_reg &= ~IXGB_EECD_DI; - - if (data & mask) - eecd_reg |= IXGB_EECD_DI; - - IXGB_WRITE_REG(hw, EECD, eecd_reg); - IXGB_WRITE_FLUSH(hw); - - udelay(50); - - ixgb_raise_clock(hw, &eecd_reg); - ixgb_lower_clock(hw, &eecd_reg); - - mask = mask >> 1; - - } while (mask); - - /* We leave the "DI" bit set to "0" when we leave this routine. */ - eecd_reg &= ~IXGB_EECD_DI; - IXGB_WRITE_REG(hw, EECD, eecd_reg); -} - -/****************************************************************************** - * Shift data bits in from the EEPROM - * - * hw - Struct containing variables accessed by shared code - *****************************************************************************/ -static u16 -ixgb_shift_in_bits(struct ixgb_hw *hw) -{ - u32 eecd_reg; - u32 i; - u16 data; - - /* In order to read a register from the EEPROM, we need to shift 16 bits - * in from the EEPROM. Bits are "shifted in" by raising the clock input to - * the EEPROM (setting the SK bit), and then reading the value of the "DO" - * bit. During this "shifting in" process the "DI" bit should always be - * clear.. - */ - - eecd_reg = IXGB_READ_REG(hw, EECD); - - eecd_reg &= ~(IXGB_EECD_DO | IXGB_EECD_DI); - data = 0; - - for (i = 0; i < 16; i++) { - data = data << 1; - ixgb_raise_clock(hw, &eecd_reg); - - eecd_reg = IXGB_READ_REG(hw, EECD); - - eecd_reg &= ~(IXGB_EECD_DI); - if (eecd_reg & IXGB_EECD_DO) - data |= 1; - - ixgb_lower_clock(hw, &eecd_reg); - } - - return data; -} - -/****************************************************************************** - * Prepares EEPROM for access - * - * hw - Struct containing variables accessed by shared code - * - * Lowers EEPROM clock. Clears input pin. Sets the chip select pin. This - * function should be called before issuing a command to the EEPROM. - *****************************************************************************/ -static void -ixgb_setup_eeprom(struct ixgb_hw *hw) -{ - u32 eecd_reg; - - eecd_reg = IXGB_READ_REG(hw, EECD); - - /* Clear SK and DI */ - eecd_reg &= ~(IXGB_EECD_SK | IXGB_EECD_DI); - IXGB_WRITE_REG(hw, EECD, eecd_reg); - - /* Set CS */ - eecd_reg |= IXGB_EECD_CS; - IXGB_WRITE_REG(hw, EECD, eecd_reg); -} - -/****************************************************************************** - * Returns EEPROM to a "standby" state - * - * hw - Struct containing variables accessed by shared code - *****************************************************************************/ -static void -ixgb_standby_eeprom(struct ixgb_hw *hw) -{ - u32 eecd_reg; - - eecd_reg = IXGB_READ_REG(hw, EECD); - - /* Deselect EEPROM */ - eecd_reg &= ~(IXGB_EECD_CS | IXGB_EECD_SK); - IXGB_WRITE_REG(hw, EECD, eecd_reg); - IXGB_WRITE_FLUSH(hw); - udelay(50); - - /* Clock high */ - eecd_reg |= IXGB_EECD_SK; - IXGB_WRITE_REG(hw, EECD, eecd_reg); - IXGB_WRITE_FLUSH(hw); - udelay(50); - - /* Select EEPROM */ - eecd_reg |= IXGB_EECD_CS; - IXGB_WRITE_REG(hw, EECD, eecd_reg); - IXGB_WRITE_FLUSH(hw); - udelay(50); - - /* Clock low */ - eecd_reg &= ~IXGB_EECD_SK; - IXGB_WRITE_REG(hw, EECD, eecd_reg); - IXGB_WRITE_FLUSH(hw); - udelay(50); -} - -/****************************************************************************** - * Raises then lowers the EEPROM's clock pin - * - * hw - Struct containing variables accessed by shared code - *****************************************************************************/ -static void -ixgb_clock_eeprom(struct ixgb_hw *hw) -{ - u32 eecd_reg; - - eecd_reg = IXGB_READ_REG(hw, EECD); - - /* Rising edge of clock */ - eecd_reg |= IXGB_EECD_SK; - IXGB_WRITE_REG(hw, EECD, eecd_reg); - IXGB_WRITE_FLUSH(hw); - udelay(50); - - /* Falling edge of clock */ - eecd_reg &= ~IXGB_EECD_SK; - IXGB_WRITE_REG(hw, EECD, eecd_reg); - IXGB_WRITE_FLUSH(hw); - udelay(50); -} - -/****************************************************************************** - * Terminates a command by lowering the EEPROM's chip select pin - * - * hw - Struct containing variables accessed by shared code - *****************************************************************************/ -static void -ixgb_cleanup_eeprom(struct ixgb_hw *hw) -{ - u32 eecd_reg; - - eecd_reg = IXGB_READ_REG(hw, EECD); - - eecd_reg &= ~(IXGB_EECD_CS | IXGB_EECD_DI); - - IXGB_WRITE_REG(hw, EECD, eecd_reg); - - ixgb_clock_eeprom(hw); -} - -/****************************************************************************** - * Waits for the EEPROM to finish the current command. - * - * hw - Struct containing variables accessed by shared code - * - * The command is done when the EEPROM's data out pin goes high. - * - * Returns: - * true: EEPROM data pin is high before timeout. - * false: Time expired. - *****************************************************************************/ -static bool -ixgb_wait_eeprom_command(struct ixgb_hw *hw) -{ - u32 eecd_reg; - u32 i; - - /* Toggle the CS line. This in effect tells to EEPROM to actually execute - * the command in question. - */ - ixgb_standby_eeprom(hw); - - /* Now read DO repeatedly until is high (equal to '1'). The EEPROM will - * signal that the command has been completed by raising the DO signal. - * If DO does not go high in 10 milliseconds, then error out. - */ - for (i = 0; i < 200; i++) { - eecd_reg = IXGB_READ_REG(hw, EECD); - - if (eecd_reg & IXGB_EECD_DO) - return true; - - udelay(50); - } - ASSERT(0); - return false; -} - -/****************************************************************************** - * Verifies that the EEPROM has a valid checksum - * - * hw - Struct containing variables accessed by shared code - * - * Reads the first 64 16 bit words of the EEPROM and sums the values read. - * If the sum of the 64 16 bit words is 0xBABA, the EEPROM's checksum is - * valid. - * - * Returns: - * true: Checksum is valid - * false: Checksum is not valid. - *****************************************************************************/ -bool -ixgb_validate_eeprom_checksum(struct ixgb_hw *hw) -{ - u16 checksum = 0; - u16 i; - - for (i = 0; i < (EEPROM_CHECKSUM_REG + 1); i++) - checksum += ixgb_read_eeprom(hw, i); - - if (checksum == (u16) EEPROM_SUM) - return true; - else - return false; -} - -/****************************************************************************** - * Calculates the EEPROM checksum and writes it to the EEPROM - * - * hw - Struct containing variables accessed by shared code - * - * Sums the first 63 16 bit words of the EEPROM. Subtracts the sum from 0xBABA. - * Writes the difference to word offset 63 of the EEPROM. - *****************************************************************************/ -void -ixgb_update_eeprom_checksum(struct ixgb_hw *hw) -{ - u16 checksum = 0; - u16 i; - - for (i = 0; i < EEPROM_CHECKSUM_REG; i++) - checksum += ixgb_read_eeprom(hw, i); - - checksum = (u16) EEPROM_SUM - checksum; - - ixgb_write_eeprom(hw, EEPROM_CHECKSUM_REG, checksum); -} - -/****************************************************************************** - * Writes a 16 bit word to a given offset in the EEPROM. - * - * hw - Struct containing variables accessed by shared code - * reg - offset within the EEPROM to be written to - * data - 16 bit word to be written to the EEPROM - * - * If ixgb_update_eeprom_checksum is not called after this function, the - * EEPROM will most likely contain an invalid checksum. - * - *****************************************************************************/ -void -ixgb_write_eeprom(struct ixgb_hw *hw, u16 offset, u16 data) -{ - struct ixgb_ee_map_type *ee_map = (struct ixgb_ee_map_type *)hw->eeprom; - - /* Prepare the EEPROM for writing */ - ixgb_setup_eeprom(hw); - - /* Send the 9-bit EWEN (write enable) command to the EEPROM (5-bit opcode - * plus 4-bit dummy). This puts the EEPROM into write/erase mode. - */ - ixgb_shift_out_bits(hw, EEPROM_EWEN_OPCODE, 5); - ixgb_shift_out_bits(hw, 0, 4); - - /* Prepare the EEPROM */ - ixgb_standby_eeprom(hw); - - /* Send the Write command (3-bit opcode + 6-bit addr) */ - ixgb_shift_out_bits(hw, EEPROM_WRITE_OPCODE, 3); - ixgb_shift_out_bits(hw, offset, 6); - - /* Send the data */ - ixgb_shift_out_bits(hw, data, 16); - - ixgb_wait_eeprom_command(hw); - - /* Recover from write */ - ixgb_standby_eeprom(hw); - - /* Send the 9-bit EWDS (write disable) command to the EEPROM (5-bit - * opcode plus 4-bit dummy). This takes the EEPROM out of write/erase - * mode. - */ - ixgb_shift_out_bits(hw, EEPROM_EWDS_OPCODE, 5); - ixgb_shift_out_bits(hw, 0, 4); - - /* Done with writing */ - ixgb_cleanup_eeprom(hw); - - /* clear the init_ctrl_reg_1 to signify that the cache is invalidated */ - ee_map->init_ctrl_reg_1 = cpu_to_le16(EEPROM_ICW1_SIGNATURE_CLEAR); -} - -/****************************************************************************** - * Reads a 16 bit word from the EEPROM. - * - * hw - Struct containing variables accessed by shared code - * offset - offset of 16 bit word in the EEPROM to read - * - * Returns: - * The 16-bit value read from the eeprom - *****************************************************************************/ -u16 -ixgb_read_eeprom(struct ixgb_hw *hw, - u16 offset) -{ - u16 data; - - /* Prepare the EEPROM for reading */ - ixgb_setup_eeprom(hw); - - /* Send the READ command (opcode + addr) */ - ixgb_shift_out_bits(hw, EEPROM_READ_OPCODE, 3); - /* - * We have a 64 word EEPROM, there are 6 address bits - */ - ixgb_shift_out_bits(hw, offset, 6); - - /* Read the data */ - data = ixgb_shift_in_bits(hw); - - /* End this read operation */ - ixgb_standby_eeprom(hw); - - return data; -} - -/****************************************************************************** - * Reads eeprom and stores data in shared structure. - * Validates eeprom checksum and eeprom signature. - * - * hw - Struct containing variables accessed by shared code - * - * Returns: - * true: if eeprom read is successful - * false: otherwise. - *****************************************************************************/ -bool -ixgb_get_eeprom_data(struct ixgb_hw *hw) -{ - u16 i; - u16 checksum = 0; - struct ixgb_ee_map_type *ee_map; - - ENTER(); - - ee_map = (struct ixgb_ee_map_type *)hw->eeprom; - - pr_debug("Reading eeprom data\n"); - for (i = 0; i < IXGB_EEPROM_SIZE ; i++) { - u16 ee_data; - ee_data = ixgb_read_eeprom(hw, i); - checksum += ee_data; - hw->eeprom[i] = cpu_to_le16(ee_data); - } - - if (checksum != (u16) EEPROM_SUM) { - pr_debug("Checksum invalid\n"); - /* clear the init_ctrl_reg_1 to signify that the cache is - * invalidated */ - ee_map->init_ctrl_reg_1 = cpu_to_le16(EEPROM_ICW1_SIGNATURE_CLEAR); - return false; - } - - if ((ee_map->init_ctrl_reg_1 & cpu_to_le16(EEPROM_ICW1_SIGNATURE_MASK)) - != cpu_to_le16(EEPROM_ICW1_SIGNATURE_VALID)) { - pr_debug("Signature invalid\n"); - return false; - } - - return true; -} - -/****************************************************************************** - * Local function to check if the eeprom signature is good - * If the eeprom signature is good, calls ixgb)get_eeprom_data. - * - * hw - Struct containing variables accessed by shared code - * - * Returns: - * true: eeprom signature was good and the eeprom read was successful - * false: otherwise. - ******************************************************************************/ -static bool -ixgb_check_and_get_eeprom_data (struct ixgb_hw* hw) -{ - struct ixgb_ee_map_type *ee_map = (struct ixgb_ee_map_type *)hw->eeprom; - - if ((ee_map->init_ctrl_reg_1 & cpu_to_le16(EEPROM_ICW1_SIGNATURE_MASK)) - == cpu_to_le16(EEPROM_ICW1_SIGNATURE_VALID)) { - return true; - } else { - return ixgb_get_eeprom_data(hw); - } -} - -/****************************************************************************** - * return a word from the eeprom - * - * hw - Struct containing variables accessed by shared code - * index - Offset of eeprom word - * - * Returns: - * Word at indexed offset in eeprom, if valid, 0 otherwise. - ******************************************************************************/ -__le16 -ixgb_get_eeprom_word(struct ixgb_hw *hw, u16 index) -{ - - if (index < IXGB_EEPROM_SIZE && ixgb_check_and_get_eeprom_data(hw)) - return hw->eeprom[index]; - - return 0; -} - -/****************************************************************************** - * return the mac address from EEPROM - * - * hw - Struct containing variables accessed by shared code - * mac_addr - Ethernet Address if EEPROM contents are valid, 0 otherwise - * - * Returns: None. - ******************************************************************************/ -void -ixgb_get_ee_mac_addr(struct ixgb_hw *hw, - u8 *mac_addr) -{ - int i; - struct ixgb_ee_map_type *ee_map = (struct ixgb_ee_map_type *)hw->eeprom; - - ENTER(); - - if (ixgb_check_and_get_eeprom_data(hw)) { - for (i = 0; i < ETH_ALEN; i++) { - mac_addr[i] = ee_map->mac_addr[i]; - } - pr_debug("eeprom mac address = %pM\n", mac_addr); - } -} - - -/****************************************************************************** - * return the Printed Board Assembly number from EEPROM - * - * hw - Struct containing variables accessed by shared code - * - * Returns: - * PBA number if EEPROM contents are valid, 0 otherwise - ******************************************************************************/ -u32 -ixgb_get_ee_pba_number(struct ixgb_hw *hw) -{ - if (ixgb_check_and_get_eeprom_data(hw)) - return le16_to_cpu(hw->eeprom[EEPROM_PBA_1_2_REG]) - | (le16_to_cpu(hw->eeprom[EEPROM_PBA_3_4_REG])<<16); - - return 0; -} - - -/****************************************************************************** - * return the Device Id from EEPROM - * - * hw - Struct containing variables accessed by shared code - * - * Returns: - * Device Id if EEPROM contents are valid, 0 otherwise - ******************************************************************************/ -u16 -ixgb_get_ee_device_id(struct ixgb_hw *hw) -{ - struct ixgb_ee_map_type *ee_map = (struct ixgb_ee_map_type *)hw->eeprom; - - if (ixgb_check_and_get_eeprom_data(hw)) - return le16_to_cpu(ee_map->device_id); - - return 0; -} - diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ee.h b/drivers/net/ethernet/intel/ixgb/ixgb_ee.h deleted file mode 100644 index 3ee0a09e5d0a..000000000000 --- a/drivers/net/ethernet/intel/ixgb/ixgb_ee.h +++ /dev/null @@ -1,79 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 1999 - 2008 Intel Corporation. */ - -#ifndef _IXGB_EE_H_ -#define _IXGB_EE_H_ - -#define IXGB_EEPROM_SIZE 64 /* Size in words */ - -/* EEPROM Commands */ -#define EEPROM_READ_OPCODE 0x6 /* EEPROM read opcode */ -#define EEPROM_WRITE_OPCODE 0x5 /* EEPROM write opcode */ -#define EEPROM_ERASE_OPCODE 0x7 /* EEPROM erase opcode */ -#define EEPROM_EWEN_OPCODE 0x13 /* EEPROM erase/write enable */ -#define EEPROM_EWDS_OPCODE 0x10 /* EEPROM erase/write disable */ - -/* EEPROM MAP (Word Offsets) */ -#define EEPROM_IA_1_2_REG 0x0000 -#define EEPROM_IA_3_4_REG 0x0001 -#define EEPROM_IA_5_6_REG 0x0002 -#define EEPROM_COMPATIBILITY_REG 0x0003 -#define EEPROM_PBA_1_2_REG 0x0008 -#define EEPROM_PBA_3_4_REG 0x0009 -#define EEPROM_INIT_CONTROL1_REG 0x000A -#define EEPROM_SUBSYS_ID_REG 0x000B -#define EEPROM_SUBVEND_ID_REG 0x000C -#define EEPROM_DEVICE_ID_REG 0x000D -#define EEPROM_VENDOR_ID_REG 0x000E -#define EEPROM_INIT_CONTROL2_REG 0x000F -#define EEPROM_SWDPINS_REG 0x0020 -#define EEPROM_CIRCUIT_CTRL_REG 0x0021 -#define EEPROM_D0_D3_POWER_REG 0x0022 -#define EEPROM_FLASH_VERSION 0x0032 -#define EEPROM_CHECKSUM_REG 0x003F - -/* Mask bits for fields in Word 0x0a of the EEPROM */ - -#define EEPROM_ICW1_SIGNATURE_MASK 0xC000 -#define EEPROM_ICW1_SIGNATURE_VALID 0x4000 -#define EEPROM_ICW1_SIGNATURE_CLEAR 0x0000 - -/* For checksumming, the sum of all words in the EEPROM should equal 0xBABA. */ -#define EEPROM_SUM 0xBABA - -/* EEPROM Map Sizes (Byte Counts) */ -#define PBA_SIZE 4 - -/* EEPROM Map defines (WORD OFFSETS)*/ - -/* EEPROM structure */ -struct ixgb_ee_map_type { - u8 mac_addr[ETH_ALEN]; - __le16 compatibility; - __le16 reserved1[4]; - __le32 pba_number; - __le16 init_ctrl_reg_1; - __le16 subsystem_id; - __le16 subvendor_id; - __le16 device_id; - __le16 vendor_id; - __le16 init_ctrl_reg_2; - __le16 oem_reserved[16]; - __le16 swdpins_reg; - __le16 circuit_ctrl_reg; - u8 d3_power; - u8 d0_power; - __le16 reserved2[28]; - __le16 checksum; -}; - -/* EEPROM Functions */ -u16 ixgb_read_eeprom(struct ixgb_hw *hw, u16 reg); - -bool ixgb_validate_eeprom_checksum(struct ixgb_hw *hw); - -void ixgb_update_eeprom_checksum(struct ixgb_hw *hw); - -void ixgb_write_eeprom(struct ixgb_hw *hw, u16 reg, u16 data); - -#endif /* IXGB_EE_H */ diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c deleted file mode 100644 index efa980514944..000000000000 --- a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c +++ /dev/null @@ -1,642 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2008 Intel Corporation. */ - -/* ethtool support for ixgb */ - -#include "ixgb.h" - -#include <linux/uaccess.h> - -#define IXGB_ALL_RAR_ENTRIES 16 - -enum {NETDEV_STATS, IXGB_STATS}; - -struct ixgb_stats { - char stat_string[ETH_GSTRING_LEN]; - int type; - int sizeof_stat; - int stat_offset; -}; - -#define IXGB_STAT(m) IXGB_STATS, \ - sizeof_field(struct ixgb_adapter, m), \ - offsetof(struct ixgb_adapter, m) -#define IXGB_NETDEV_STAT(m) NETDEV_STATS, \ - sizeof_field(struct net_device, m), \ - offsetof(struct net_device, m) - -static struct ixgb_stats ixgb_gstrings_stats[] = { - {"rx_packets", IXGB_NETDEV_STAT(stats.rx_packets)}, - {"tx_packets", IXGB_NETDEV_STAT(stats.tx_packets)}, - {"rx_bytes", IXGB_NETDEV_STAT(stats.rx_bytes)}, - {"tx_bytes", IXGB_NETDEV_STAT(stats.tx_bytes)}, - {"rx_errors", IXGB_NETDEV_STAT(stats.rx_errors)}, - {"tx_errors", IXGB_NETDEV_STAT(stats.tx_errors)}, - {"rx_dropped", IXGB_NETDEV_STAT(stats.rx_dropped)}, - {"tx_dropped", IXGB_NETDEV_STAT(stats.tx_dropped)}, - {"multicast", IXGB_NETDEV_STAT(stats.multicast)}, - {"collisions", IXGB_NETDEV_STAT(stats.collisions)}, - -/* { "rx_length_errors", IXGB_NETDEV_STAT(stats.rx_length_errors) }, */ - {"rx_over_errors", IXGB_NETDEV_STAT(stats.rx_over_errors)}, - {"rx_crc_errors", IXGB_NETDEV_STAT(stats.rx_crc_errors)}, - {"rx_frame_errors", IXGB_NETDEV_STAT(stats.rx_frame_errors)}, - {"rx_no_buffer_count", IXGB_STAT(stats.rnbc)}, - {"rx_fifo_errors", IXGB_NETDEV_STAT(stats.rx_fifo_errors)}, - {"rx_missed_errors", IXGB_NETDEV_STAT(stats.rx_missed_errors)}, - {"tx_aborted_errors", IXGB_NETDEV_STAT(stats.tx_aborted_errors)}, - {"tx_carrier_errors", IXGB_NETDEV_STAT(stats.tx_carrier_errors)}, - {"tx_fifo_errors", IXGB_NETDEV_STAT(stats.tx_fifo_errors)}, - {"tx_heartbeat_errors", IXGB_NETDEV_STAT(stats.tx_heartbeat_errors)}, - {"tx_window_errors", IXGB_NETDEV_STAT(stats.tx_window_errors)}, - {"tx_deferred_ok", IXGB_STAT(stats.dc)}, - {"tx_timeout_count", IXGB_STAT(tx_timeout_count) }, - {"tx_restart_queue", IXGB_STAT(restart_queue) }, - {"rx_long_length_errors", IXGB_STAT(stats.roc)}, - {"rx_short_length_errors", IXGB_STAT(stats.ruc)}, - {"tx_tcp_seg_good", IXGB_STAT(stats.tsctc)}, - {"tx_tcp_seg_failed", IXGB_STAT(stats.tsctfc)}, - {"rx_flow_control_xon", IXGB_STAT(stats.xonrxc)}, - {"rx_flow_control_xoff", IXGB_STAT(stats.xoffrxc)}, - {"tx_flow_control_xon", IXGB_STAT(stats.xontxc)}, - {"tx_flow_control_xoff", IXGB_STAT(stats.xofftxc)}, - {"rx_csum_offload_good", IXGB_STAT(hw_csum_rx_good)}, - {"rx_csum_offload_errors", IXGB_STAT(hw_csum_rx_error)}, - {"tx_csum_offload_good", IXGB_STAT(hw_csum_tx_good)}, - {"tx_csum_offload_errors", IXGB_STAT(hw_csum_tx_error)} -}; - -#define IXGB_STATS_LEN ARRAY_SIZE(ixgb_gstrings_stats) - -static int -ixgb_get_link_ksettings(struct net_device *netdev, - struct ethtool_link_ksettings *cmd) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - - ethtool_link_ksettings_zero_link_mode(cmd, supported); - ethtool_link_ksettings_add_link_mode(cmd, supported, 10000baseT_Full); - ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE); - - ethtool_link_ksettings_zero_link_mode(cmd, advertising); - ethtool_link_ksettings_add_link_mode(cmd, advertising, 10000baseT_Full); - ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE); - - cmd->base.port = PORT_FIBRE; - - if (netif_carrier_ok(adapter->netdev)) { - cmd->base.speed = SPEED_10000; - cmd->base.duplex = DUPLEX_FULL; - } else { - cmd->base.speed = SPEED_UNKNOWN; - cmd->base.duplex = DUPLEX_UNKNOWN; - } - - cmd->base.autoneg = AUTONEG_DISABLE; - return 0; -} - -void ixgb_set_speed_duplex(struct net_device *netdev) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - /* be optimistic about our link, since we were up before */ - adapter->link_speed = 10000; - adapter->link_duplex = FULL_DUPLEX; - netif_carrier_on(netdev); - netif_wake_queue(netdev); -} - -static int -ixgb_set_link_ksettings(struct net_device *netdev, - const struct ethtool_link_ksettings *cmd) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - u32 speed = cmd->base.speed; - - if (cmd->base.autoneg == AUTONEG_ENABLE || - (speed + cmd->base.duplex != SPEED_10000 + DUPLEX_FULL)) - return -EINVAL; - - if (netif_running(adapter->netdev)) { - ixgb_down(adapter, true); - ixgb_reset(adapter); - ixgb_up(adapter); - ixgb_set_speed_duplex(netdev); - } else - ixgb_reset(adapter); - - return 0; -} - -static void -ixgb_get_pauseparam(struct net_device *netdev, - struct ethtool_pauseparam *pause) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - struct ixgb_hw *hw = &adapter->hw; - - pause->autoneg = AUTONEG_DISABLE; - - if (hw->fc.type == ixgb_fc_rx_pause) - pause->rx_pause = 1; - else if (hw->fc.type == ixgb_fc_tx_pause) - pause->tx_pause = 1; - else if (hw->fc.type == ixgb_fc_full) { - pause->rx_pause = 1; - pause->tx_pause = 1; - } -} - -static int -ixgb_set_pauseparam(struct net_device *netdev, - struct ethtool_pauseparam *pause) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - struct ixgb_hw *hw = &adapter->hw; - - if (pause->autoneg == AUTONEG_ENABLE) - return -EINVAL; - - if (pause->rx_pause && pause->tx_pause) - hw->fc.type = ixgb_fc_full; - else if (pause->rx_pause && !pause->tx_pause) - hw->fc.type = ixgb_fc_rx_pause; - else if (!pause->rx_pause && pause->tx_pause) - hw->fc.type = ixgb_fc_tx_pause; - else if (!pause->rx_pause && !pause->tx_pause) - hw->fc.type = ixgb_fc_none; - - if (netif_running(adapter->netdev)) { - ixgb_down(adapter, true); - ixgb_up(adapter); - ixgb_set_speed_duplex(netdev); - } else - ixgb_reset(adapter); - - return 0; -} - -static u32 -ixgb_get_msglevel(struct net_device *netdev) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - return adapter->msg_enable; -} - -static void -ixgb_set_msglevel(struct net_device *netdev, u32 data) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - adapter->msg_enable = data; -} -#define IXGB_GET_STAT(_A_, _R_) _A_->stats._R_ - -static int -ixgb_get_regs_len(struct net_device *netdev) -{ -#define IXGB_REG_DUMP_LEN 136*sizeof(u32) - return IXGB_REG_DUMP_LEN; -} - -static void -ixgb_get_regs(struct net_device *netdev, - struct ethtool_regs *regs, void *p) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - struct ixgb_hw *hw = &adapter->hw; - u32 *reg = p; - u32 *reg_start = reg; - u8 i; - - /* the 1 (one) below indicates an attempt at versioning, if the - * interface in ethtool or the driver changes, this 1 should be - * incremented */ - regs->version = (1<<24) | hw->revision_id << 16 | hw->device_id; - - /* General Registers */ - *reg++ = IXGB_READ_REG(hw, CTRL0); /* 0 */ - *reg++ = IXGB_READ_REG(hw, CTRL1); /* 1 */ - *reg++ = IXGB_READ_REG(hw, STATUS); /* 2 */ - *reg++ = IXGB_READ_REG(hw, EECD); /* 3 */ - *reg++ = IXGB_READ_REG(hw, MFS); /* 4 */ - - /* Interrupt */ - *reg++ = IXGB_READ_REG(hw, ICR); /* 5 */ - *reg++ = IXGB_READ_REG(hw, ICS); /* 6 */ - *reg++ = IXGB_READ_REG(hw, IMS); /* 7 */ - *reg++ = IXGB_READ_REG(hw, IMC); /* 8 */ - - /* Receive */ - *reg++ = IXGB_READ_REG(hw, RCTL); /* 9 */ - *reg++ = IXGB_READ_REG(hw, FCRTL); /* 10 */ - *reg++ = IXGB_READ_REG(hw, FCRTH); /* 11 */ - *reg++ = IXGB_READ_REG(hw, RDBAL); /* 12 */ - *reg++ = IXGB_READ_REG(hw, RDBAH); /* 13 */ - *reg++ = IXGB_READ_REG(hw, RDLEN); /* 14 */ - *reg++ = IXGB_READ_REG(hw, RDH); /* 15 */ - *reg++ = IXGB_READ_REG(hw, RDT); /* 16 */ - *reg++ = IXGB_READ_REG(hw, RDTR); /* 17 */ - *reg++ = IXGB_READ_REG(hw, RXDCTL); /* 18 */ - *reg++ = IXGB_READ_REG(hw, RAIDC); /* 19 */ - *reg++ = IXGB_READ_REG(hw, RXCSUM); /* 20 */ - - /* there are 16 RAR entries in hardware, we only use 3 */ - for (i = 0; i < IXGB_ALL_RAR_ENTRIES; i++) { - *reg++ = IXGB_READ_REG_ARRAY(hw, RAL, (i << 1)); /*21,...,51 */ - *reg++ = IXGB_READ_REG_ARRAY(hw, RAH, (i << 1)); /*22,...,52 */ - } - - /* Transmit */ - *reg++ = IXGB_READ_REG(hw, TCTL); /* 53 */ - *reg++ = IXGB_READ_REG(hw, TDBAL); /* 54 */ - *reg++ = IXGB_READ_REG(hw, TDBAH); /* 55 */ - *reg++ = IXGB_READ_REG(hw, TDLEN); /* 56 */ - *reg++ = IXGB_READ_REG(hw, TDH); /* 57 */ - *reg++ = IXGB_READ_REG(hw, TDT); /* 58 */ - *reg++ = IXGB_READ_REG(hw, TIDV); /* 59 */ - *reg++ = IXGB_READ_REG(hw, TXDCTL); /* 60 */ - *reg++ = IXGB_READ_REG(hw, TSPMT); /* 61 */ - *reg++ = IXGB_READ_REG(hw, PAP); /* 62 */ - - /* Physical */ - *reg++ = IXGB_READ_REG(hw, PCSC1); /* 63 */ - *reg++ = IXGB_READ_REG(hw, PCSC2); /* 64 */ - *reg++ = IXGB_READ_REG(hw, PCSS1); /* 65 */ - *reg++ = IXGB_READ_REG(hw, PCSS2); /* 66 */ - *reg++ = IXGB_READ_REG(hw, XPCSS); /* 67 */ - *reg++ = IXGB_READ_REG(hw, UCCR); /* 68 */ - *reg++ = IXGB_READ_REG(hw, XPCSTC); /* 69 */ - *reg++ = IXGB_READ_REG(hw, MACA); /* 70 */ - *reg++ = IXGB_READ_REG(hw, APAE); /* 71 */ - *reg++ = IXGB_READ_REG(hw, ARD); /* 72 */ - *reg++ = IXGB_READ_REG(hw, AIS); /* 73 */ - *reg++ = IXGB_READ_REG(hw, MSCA); /* 74 */ - *reg++ = IXGB_READ_REG(hw, MSRWD); /* 75 */ - - /* Statistics */ - *reg++ = IXGB_GET_STAT(adapter, tprl); /* 76 */ - *reg++ = IXGB_GET_STAT(adapter, tprh); /* 77 */ - *reg++ = IXGB_GET_STAT(adapter, gprcl); /* 78 */ - *reg++ = IXGB_GET_STAT(adapter, gprch); /* 79 */ - *reg++ = IXGB_GET_STAT(adapter, bprcl); /* 80 */ - *reg++ = IXGB_GET_STAT(adapter, bprch); /* 81 */ - *reg++ = IXGB_GET_STAT(adapter, mprcl); /* 82 */ - *reg++ = IXGB_GET_STAT(adapter, mprch); /* 83 */ - *reg++ = IXGB_GET_STAT(adapter, uprcl); /* 84 */ - *reg++ = IXGB_GET_STAT(adapter, uprch); /* 85 */ - *reg++ = IXGB_GET_STAT(adapter, vprcl); /* 86 */ - *reg++ = IXGB_GET_STAT(adapter, vprch); /* 87 */ - *reg++ = IXGB_GET_STAT(adapter, jprcl); /* 88 */ - *reg++ = IXGB_GET_STAT(adapter, jprch); /* 89 */ - *reg++ = IXGB_GET_STAT(adapter, gorcl); /* 90 */ - *reg++ = IXGB_GET_STAT(adapter, gorch); /* 91 */ - *reg++ = IXGB_GET_STAT(adapter, torl); /* 92 */ - *reg++ = IXGB_GET_STAT(adapter, torh); /* 93 */ - *reg++ = IXGB_GET_STAT(adapter, rnbc); /* 94 */ - *reg++ = IXGB_GET_STAT(adapter, ruc); /* 95 */ - *reg++ = IXGB_GET_STAT(adapter, roc); /* 96 */ - *reg++ = IXGB_GET_STAT(adapter, rlec); /* 97 */ - *reg++ = IXGB_GET_STAT(adapter, crcerrs); /* 98 */ - *reg++ = IXGB_GET_STAT(adapter, icbc); /* 99 */ - *reg++ = IXGB_GET_STAT(adapter, ecbc); /* 100 */ - *reg++ = IXGB_GET_STAT(adapter, mpc); /* 101 */ - *reg++ = IXGB_GET_STAT(adapter, tptl); /* 102 */ - *reg++ = IXGB_GET_STAT(adapter, tpth); /* 103 */ - *reg++ = IXGB_GET_STAT(adapter, gptcl); /* 104 */ - *reg++ = IXGB_GET_STAT(adapter, gptch); /* 105 */ - *reg++ = IXGB_GET_STAT(adapter, bptcl); /* 106 */ - *reg++ = IXGB_GET_STAT(adapter, bptch); /* 107 */ - *reg++ = IXGB_GET_STAT(adapter, mptcl); /* 108 */ - *reg++ = IXGB_GET_STAT(adapter, mptch); /* 109 */ - *reg++ = IXGB_GET_STAT(adapter, uptcl); /* 110 */ - *reg++ = IXGB_GET_STAT(adapter, uptch); /* 111 */ - *reg++ = IXGB_GET_STAT(adapter, vptcl); /* 112 */ - *reg++ = IXGB_GET_STAT(adapter, vptch); /* 113 */ - *reg++ = IXGB_GET_STAT(adapter, jptcl); /* 114 */ - *reg++ = IXGB_GET_STAT(adapter, jptch); /* 115 */ - *reg++ = IXGB_GET_STAT(adapter, gotcl); /* 116 */ - *reg++ = IXGB_GET_STAT(adapter, gotch); /* 117 */ - *reg++ = IXGB_GET_STAT(adapter, totl); /* 118 */ - *reg++ = IXGB_GET_STAT(adapter, toth); /* 119 */ - *reg++ = IXGB_GET_STAT(adapter, dc); /* 120 */ - *reg++ = IXGB_GET_STAT(adapter, plt64c); /* 121 */ - *reg++ = IXGB_GET_STAT(adapter, tsctc); /* 122 */ - *reg++ = IXGB_GET_STAT(adapter, tsctfc); /* 123 */ - *reg++ = IXGB_GET_STAT(adapter, ibic); /* 124 */ - *reg++ = IXGB_GET_STAT(adapter, rfc); /* 125 */ - *reg++ = IXGB_GET_STAT(adapter, lfc); /* 126 */ - *reg++ = IXGB_GET_STAT(adapter, pfrc); /* 127 */ - *reg++ = IXGB_GET_STAT(adapter, pftc); /* 128 */ - *reg++ = IXGB_GET_STAT(adapter, mcfrc); /* 129 */ - *reg++ = IXGB_GET_STAT(adapter, mcftc); /* 130 */ - *reg++ = IXGB_GET_STAT(adapter, xonrxc); /* 131 */ - *reg++ = IXGB_GET_STAT(adapter, xontxc); /* 132 */ - *reg++ = IXGB_GET_STAT(adapter, xoffrxc); /* 133 */ - *reg++ = IXGB_GET_STAT(adapter, xofftxc); /* 134 */ - *reg++ = IXGB_GET_STAT(adapter, rjc); /* 135 */ - - regs->len = (reg - reg_start) * sizeof(u32); -} - -static int -ixgb_get_eeprom_len(struct net_device *netdev) -{ - /* return size in bytes */ - return IXGB_EEPROM_SIZE << 1; -} - -static int -ixgb_get_eeprom(struct net_device *netdev, - struct ethtool_eeprom *eeprom, u8 *bytes) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - struct ixgb_hw *hw = &adapter->hw; - __le16 *eeprom_buff; - int i, max_len, first_word, last_word; - int ret_val = 0; - - if (eeprom->len == 0) { - ret_val = -EINVAL; - goto geeprom_error; - } - - eeprom->magic = hw->vendor_id | (hw->device_id << 16); - - max_len = ixgb_get_eeprom_len(netdev); - - if (eeprom->offset > eeprom->offset + eeprom->len) { - ret_val = -EINVAL; - goto geeprom_error; - } - - if ((eeprom->offset + eeprom->len) > max_len) - eeprom->len = (max_len - eeprom->offset); - - first_word = eeprom->offset >> 1; - last_word = (eeprom->offset + eeprom->len - 1) >> 1; - - eeprom_buff = kmalloc_array(last_word - first_word + 1, - sizeof(__le16), - GFP_KERNEL); - if (!eeprom_buff) - return -ENOMEM; - - /* note the eeprom was good because the driver loaded */ - for (i = 0; i <= (last_word - first_word); i++) - eeprom_buff[i] = ixgb_get_eeprom_word(hw, (first_word + i)); - - memcpy(bytes, (u8 *)eeprom_buff + (eeprom->offset & 1), eeprom->len); - kfree(eeprom_buff); - -geeprom_error: - return ret_val; -} - -static int -ixgb_set_eeprom(struct net_device *netdev, - struct ethtool_eeprom *eeprom, u8 *bytes) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - struct ixgb_hw *hw = &adapter->hw; - u16 *eeprom_buff; - void *ptr; - int max_len, first_word, last_word; - u16 i; - - if (eeprom->len == 0) - return -EINVAL; - - if (eeprom->magic != (hw->vendor_id | (hw->device_id << 16))) - return -EFAULT; - - max_len = ixgb_get_eeprom_len(netdev); - - if (eeprom->offset > eeprom->offset + eeprom->len) - return -EINVAL; - - if ((eeprom->offset + eeprom->len) > max_len) - eeprom->len = (max_len - eeprom->offset); - - first_word = eeprom->offset >> 1; - last_word = (eeprom->offset + eeprom->len - 1) >> 1; - eeprom_buff = kmalloc(max_len, GFP_KERNEL); - if (!eeprom_buff) - return -ENOMEM; - - ptr = (void *)eeprom_buff; - - if (eeprom->offset & 1) { - /* need read/modify/write of first changed EEPROM word */ - /* only the second byte of the word is being modified */ - eeprom_buff[0] = ixgb_read_eeprom(hw, first_word); - ptr++; - } - if ((eeprom->offset + eeprom->len) & 1) { - /* need read/modify/write of last changed EEPROM word */ - /* only the first byte of the word is being modified */ - eeprom_buff[last_word - first_word] - = ixgb_read_eeprom(hw, last_word); - } - - memcpy(ptr, bytes, eeprom->len); - for (i = 0; i <= (last_word - first_word); i++) - ixgb_write_eeprom(hw, first_word + i, eeprom_buff[i]); - - /* Update the checksum over the first part of the EEPROM if needed */ - if (first_word <= EEPROM_CHECKSUM_REG) - ixgb_update_eeprom_checksum(hw); - - kfree(eeprom_buff); - return 0; -} - -static void -ixgb_get_drvinfo(struct net_device *netdev, - struct ethtool_drvinfo *drvinfo) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - - strscpy(drvinfo->driver, ixgb_driver_name, - sizeof(drvinfo->driver)); - strscpy(drvinfo->bus_info, pci_name(adapter->pdev), - sizeof(drvinfo->bus_info)); -} - -static void -ixgb_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring, - struct kernel_ethtool_ringparam *kernel_ring, - struct netlink_ext_ack *extack) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - struct ixgb_desc_ring *txdr = &adapter->tx_ring; - struct ixgb_desc_ring *rxdr = &adapter->rx_ring; - - ring->rx_max_pending = MAX_RXD; - ring->tx_max_pending = MAX_TXD; - ring->rx_pending = rxdr->count; - ring->tx_pending = txdr->count; -} - -static int -ixgb_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring, - struct kernel_ethtool_ringparam *kernel_ring, - struct netlink_ext_ack *extack) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - struct ixgb_desc_ring *txdr = &adapter->tx_ring; - struct ixgb_desc_ring *rxdr = &adapter->rx_ring; - struct ixgb_desc_ring tx_old, tx_new, rx_old, rx_new; - int err; - - tx_old = adapter->tx_ring; - rx_old = adapter->rx_ring; - - if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) - return -EINVAL; - - if (netif_running(adapter->netdev)) - ixgb_down(adapter, true); - - rxdr->count = max(ring->rx_pending,(u32)MIN_RXD); - rxdr->count = min(rxdr->count,(u32)MAX_RXD); - rxdr->count = ALIGN(rxdr->count, IXGB_REQ_RX_DESCRIPTOR_MULTIPLE); - - txdr->count = max(ring->tx_pending,(u32)MIN_TXD); - txdr->count = min(txdr->count,(u32)MAX_TXD); - txdr->count = ALIGN(txdr->count, IXGB_REQ_TX_DESCRIPTOR_MULTIPLE); - - if (netif_running(adapter->netdev)) { - /* Try to get new resources before deleting old */ - if ((err = ixgb_setup_rx_resources(adapter))) - goto err_setup_rx; - if ((err = ixgb_setup_tx_resources(adapter))) - goto err_setup_tx; - - /* save the new, restore the old in order to free it, - * then restore the new back again */ - - rx_new = adapter->rx_ring; - tx_new = adapter->tx_ring; - adapter->rx_ring = rx_old; - adapter->tx_ring = tx_old; - ixgb_free_rx_resources(adapter); - ixgb_free_tx_resources(adapter); - adapter->rx_ring = rx_new; - adapter->tx_ring = tx_new; - if ((err = ixgb_up(adapter))) - return err; - ixgb_set_speed_duplex(netdev); - } - - return 0; -err_setup_tx: - ixgb_free_rx_resources(adapter); -err_setup_rx: - adapter->rx_ring = rx_old; - adapter->tx_ring = tx_old; - ixgb_up(adapter); - return err; -} - -static int -ixgb_set_phys_id(struct net_device *netdev, enum ethtool_phys_id_state state) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - - switch (state) { - case ETHTOOL_ID_ACTIVE: - return 2; - - case ETHTOOL_ID_ON: - ixgb_led_on(&adapter->hw); - break; - - case ETHTOOL_ID_OFF: - case ETHTOOL_ID_INACTIVE: - ixgb_led_off(&adapter->hw); - } - - return 0; -} - -static int -ixgb_get_sset_count(struct net_device *netdev, int sset) -{ - switch (sset) { - case ETH_SS_STATS: - return IXGB_STATS_LEN; - default: - return -EOPNOTSUPP; - } -} - -static void -ixgb_get_ethtool_stats(struct net_device *netdev, - struct ethtool_stats *stats, u64 *data) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - int i; - char *p = NULL; - - ixgb_update_stats(adapter); - for (i = 0; i < IXGB_STATS_LEN; i++) { - switch (ixgb_gstrings_stats[i].type) { - case NETDEV_STATS: - p = (char *) netdev + - ixgb_gstrings_stats[i].stat_offset; - break; - case IXGB_STATS: - p = (char *) adapter + - ixgb_gstrings_stats[i].stat_offset; - break; - } - - data[i] = (ixgb_gstrings_stats[i].sizeof_stat == - sizeof(u64)) ? *(u64 *)p : *(u32 *)p; - } -} - -static void -ixgb_get_strings(struct net_device *netdev, u32 stringset, u8 *data) -{ - int i; - - switch(stringset) { - case ETH_SS_STATS: - for (i = 0; i < IXGB_STATS_LEN; i++) { - memcpy(data + i * ETH_GSTRING_LEN, - ixgb_gstrings_stats[i].stat_string, - ETH_GSTRING_LEN); - } - break; - } -} - -static const struct ethtool_ops ixgb_ethtool_ops = { - .get_drvinfo = ixgb_get_drvinfo, - .get_regs_len = ixgb_get_regs_len, - .get_regs = ixgb_get_regs, - .get_link = ethtool_op_get_link, - .get_eeprom_len = ixgb_get_eeprom_len, - .get_eeprom = ixgb_get_eeprom, - .set_eeprom = ixgb_set_eeprom, - .get_ringparam = ixgb_get_ringparam, - .set_ringparam = ixgb_set_ringparam, - .get_pauseparam = ixgb_get_pauseparam, - .set_pauseparam = ixgb_set_pauseparam, - .get_msglevel = ixgb_get_msglevel, - .set_msglevel = ixgb_set_msglevel, - .get_strings = ixgb_get_strings, - .set_phys_id = ixgb_set_phys_id, - .get_sset_count = ixgb_get_sset_count, - .get_ethtool_stats = ixgb_get_ethtool_stats, - .get_link_ksettings = ixgb_get_link_ksettings, - .set_link_ksettings = ixgb_set_link_ksettings, -}; - -void ixgb_set_ethtool_ops(struct net_device *netdev) -{ - netdev->ethtool_ops = &ixgb_ethtool_ops; -} diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_hw.c b/drivers/net/ethernet/intel/ixgb/ixgb_hw.c deleted file mode 100644 index 98bd3267b99b..000000000000 --- a/drivers/net/ethernet/intel/ixgb/ixgb_hw.c +++ /dev/null @@ -1,1229 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2008 Intel Corporation. */ - -/* ixgb_hw.c - * Shared functions for accessing and configuring the adapter - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/pci_ids.h> -#include "ixgb_hw.h" -#include "ixgb_ids.h" - -#include <linux/etherdevice.h> - -/* Local function prototypes */ - -static u32 ixgb_hash_mc_addr(struct ixgb_hw *hw, u8 * mc_addr); - -static void ixgb_mta_set(struct ixgb_hw *hw, u32 hash_value); - -static void ixgb_get_bus_info(struct ixgb_hw *hw); - -static bool ixgb_link_reset(struct ixgb_hw *hw); - -static void ixgb_optics_reset(struct ixgb_hw *hw); - -static void ixgb_optics_reset_bcm(struct ixgb_hw *hw); - -static ixgb_phy_type ixgb_identify_phy(struct ixgb_hw *hw); - -static void ixgb_clear_hw_cntrs(struct ixgb_hw *hw); - -static void ixgb_clear_vfta(struct ixgb_hw *hw); - -static void ixgb_init_rx_addrs(struct ixgb_hw *hw); - -static u16 ixgb_read_phy_reg(struct ixgb_hw *hw, - u32 reg_address, - u32 phy_address, - u32 device_type); - -static bool ixgb_setup_fc(struct ixgb_hw *hw); - -static bool mac_addr_valid(u8 *mac_addr); - -static u32 ixgb_mac_reset(struct ixgb_hw *hw) -{ - u32 ctrl_reg; - - ctrl_reg = IXGB_CTRL0_RST | - IXGB_CTRL0_SDP3_DIR | /* All pins are Output=1 */ - IXGB_CTRL0_SDP2_DIR | - IXGB_CTRL0_SDP1_DIR | - IXGB_CTRL0_SDP0_DIR | - IXGB_CTRL0_SDP3 | /* Initial value 1101 */ - IXGB_CTRL0_SDP2 | - IXGB_CTRL0_SDP0; - -#ifdef HP_ZX1 - /* Workaround for 82597EX reset errata */ - IXGB_WRITE_REG_IO(hw, CTRL0, ctrl_reg); -#else - IXGB_WRITE_REG(hw, CTRL0, ctrl_reg); -#endif - - /* Delay a few ms just to allow the reset to complete */ - msleep(IXGB_DELAY_AFTER_RESET); - ctrl_reg = IXGB_READ_REG(hw, CTRL0); -#ifdef DBG - /* Make sure the self-clearing global reset bit did self clear */ - ASSERT(!(ctrl_reg & IXGB_CTRL0_RST)); -#endif - - if (hw->subsystem_vendor_id == PCI_VENDOR_ID_SUN) { - ctrl_reg = /* Enable interrupt from XFP and SerDes */ - IXGB_CTRL1_GPI0_EN | - IXGB_CTRL1_SDP6_DIR | - IXGB_CTRL1_SDP7_DIR | - IXGB_CTRL1_SDP6 | - IXGB_CTRL1_SDP7; - IXGB_WRITE_REG(hw, CTRL1, ctrl_reg); - ixgb_optics_reset_bcm(hw); - } - - if (hw->phy_type == ixgb_phy_type_txn17401) - ixgb_optics_reset(hw); - - return ctrl_reg; -} - -/****************************************************************************** - * Reset the transmit and receive units; mask and clear all interrupts. - * - * hw - Struct containing variables accessed by shared code - *****************************************************************************/ -bool -ixgb_adapter_stop(struct ixgb_hw *hw) -{ - u32 ctrl_reg; - - ENTER(); - - /* If we are stopped or resetting exit gracefully and wait to be - * started again before accessing the hardware. - */ - if (hw->adapter_stopped) { - pr_debug("Exiting because the adapter is already stopped!!!\n"); - return false; - } - - /* Set the Adapter Stopped flag so other driver functions stop - * touching the Hardware. - */ - hw->adapter_stopped = true; - - /* Clear interrupt mask to stop board from generating interrupts */ - pr_debug("Masking off all interrupts\n"); - IXGB_WRITE_REG(hw, IMC, 0xFFFFFFFF); - - /* Disable the Transmit and Receive units. Then delay to allow - * any pending transactions to complete before we hit the MAC with - * the global reset. - */ - IXGB_WRITE_REG(hw, RCTL, IXGB_READ_REG(hw, RCTL) & ~IXGB_RCTL_RXEN); - IXGB_WRITE_REG(hw, TCTL, IXGB_READ_REG(hw, TCTL) & ~IXGB_TCTL_TXEN); - IXGB_WRITE_FLUSH(hw); - msleep(IXGB_DELAY_BEFORE_RESET); - - /* Issue a global reset to the MAC. This will reset the chip's - * transmit, receive, DMA, and link units. It will not effect - * the current PCI configuration. The global reset bit is self- - * clearing, and should clear within a microsecond. - */ - pr_debug("Issuing a global reset to MAC\n"); - - ctrl_reg = ixgb_mac_reset(hw); - - /* Clear interrupt mask to stop board from generating interrupts */ - pr_debug("Masking off all interrupts\n"); - IXGB_WRITE_REG(hw, IMC, 0xffffffff); - - /* Clear any pending interrupt events. */ - IXGB_READ_REG(hw, ICR); - - return ctrl_reg & IXGB_CTRL0_RST; -} - - -/****************************************************************************** - * Identifies the vendor of the optics module on the adapter. The SR adapters - * support two different types of XPAK optics, so it is necessary to determine - * which optics are present before applying any optics-specific workarounds. - * - * hw - Struct containing variables accessed by shared code. - * - * Returns: the vendor of the XPAK optics module. - *****************************************************************************/ -static ixgb_xpak_vendor -ixgb_identify_xpak_vendor(struct ixgb_hw *hw) -{ - u32 i; - u16 vendor_name[5]; - ixgb_xpak_vendor xpak_vendor; - - ENTER(); - - /* Read the first few bytes of the vendor string from the XPAK NVR - * registers. These are standard XENPAK/XPAK registers, so all XPAK - * devices should implement them. */ - for (i = 0; i < 5; i++) { - vendor_name[i] = ixgb_read_phy_reg(hw, - MDIO_PMA_PMD_XPAK_VENDOR_NAME - + i, IXGB_PHY_ADDRESS, - MDIO_MMD_PMAPMD); - } - - /* Determine the actual vendor */ - if (vendor_name[0] == 'I' && - vendor_name[1] == 'N' && - vendor_name[2] == 'T' && - vendor_name[3] == 'E' && vendor_name[4] == 'L') { - xpak_vendor = ixgb_xpak_vendor_intel; - } else { - xpak_vendor = ixgb_xpak_vendor_infineon; - } - - return xpak_vendor; -} - -/****************************************************************************** - * Determine the physical layer module on the adapter. - * - * hw - Struct containing variables accessed by shared code. The device_id - * field must be (correctly) populated before calling this routine. - * - * Returns: the phy type of the adapter. - *****************************************************************************/ -static ixgb_phy_type -ixgb_identify_phy(struct ixgb_hw *hw) -{ - ixgb_phy_type phy_type; - ixgb_xpak_vendor xpak_vendor; - - ENTER(); - - /* Infer the transceiver/phy type from the device id */ - switch (hw->device_id) { - case IXGB_DEVICE_ID_82597EX: - pr_debug("Identified TXN17401 optics\n"); - phy_type = ixgb_phy_type_txn17401; - break; - - case IXGB_DEVICE_ID_82597EX_SR: - /* The SR adapters carry two different types of XPAK optics - * modules; read the vendor identifier to determine the exact - * type of optics. */ - xpak_vendor = ixgb_identify_xpak_vendor(hw); - if (xpak_vendor == ixgb_xpak_vendor_intel) { - pr_debug("Identified TXN17201 optics\n"); - phy_type = ixgb_phy_type_txn17201; - } else { - pr_debug("Identified G6005 optics\n"); - phy_type = ixgb_phy_type_g6005; - } - break; - case IXGB_DEVICE_ID_82597EX_LR: - pr_debug("Identified G6104 optics\n"); - phy_type = ixgb_phy_type_g6104; - break; - case IXGB_DEVICE_ID_82597EX_CX4: - pr_debug("Identified CX4\n"); - xpak_vendor = ixgb_identify_xpak_vendor(hw); - if (xpak_vendor == ixgb_xpak_vendor_intel) { - pr_debug("Identified TXN17201 optics\n"); - phy_type = ixgb_phy_type_txn17201; - } else { - pr_debug("Identified G6005 optics\n"); - phy_type = ixgb_phy_type_g6005; - } - break; - default: - pr_debug("Unknown physical layer module\n"); - phy_type = ixgb_phy_type_unknown; - break; - } - - /* update phy type for sun specific board */ - if (hw->subsystem_vendor_id == PCI_VENDOR_ID_SUN) - phy_type = ixgb_phy_type_bcm; - - return phy_type; -} - -/****************************************************************************** - * Performs basic configuration of the adapter. - * - * hw - Struct containing variables accessed by shared code - * - * Resets the controller. - * Reads and validates the EEPROM. - * Initializes the receive address registers. - * Initializes the multicast table. - * Clears all on-chip counters. - * Calls routine to setup flow control settings. - * Leaves the transmit and receive units disabled and uninitialized. - * - * Returns: - * true if successful, - * false if unrecoverable problems were encountered. - *****************************************************************************/ -bool -ixgb_init_hw(struct ixgb_hw *hw) -{ - u32 i; - bool status; - - ENTER(); - - /* Issue a global reset to the MAC. This will reset the chip's - * transmit, receive, DMA, and link units. It will not effect - * the current PCI configuration. The global reset bit is self- - * clearing, and should clear within a microsecond. - */ - pr_debug("Issuing a global reset to MAC\n"); - - ixgb_mac_reset(hw); - - pr_debug("Issuing an EE reset to MAC\n"); -#ifdef HP_ZX1 - /* Workaround for 82597EX reset errata */ - IXGB_WRITE_REG_IO(hw, CTRL1, IXGB_CTRL1_EE_RST); -#else - IXGB_WRITE_REG(hw, CTRL1, IXGB_CTRL1_EE_RST); -#endif - - /* Delay a few ms just to allow the reset to complete */ - msleep(IXGB_DELAY_AFTER_EE_RESET); - - if (!ixgb_get_eeprom_data(hw)) - return false; - - /* Use the device id to determine the type of phy/transceiver. */ - hw->device_id = ixgb_get_ee_device_id(hw); - hw->phy_type = ixgb_identify_phy(hw); - - /* Setup the receive addresses. - * Receive Address Registers (RARs 0 - 15). - */ - ixgb_init_rx_addrs(hw); - - /* - * Check that a valid MAC address has been set. - * If it is not valid, we fail hardware init. - */ - if (!mac_addr_valid(hw->curr_mac_addr)) { - pr_debug("MAC address invalid after ixgb_init_rx_addrs\n"); - return(false); - } - - /* tell the routines in this file they can access hardware again */ - hw->adapter_stopped = false; - - /* Fill in the bus_info structure */ - ixgb_get_bus_info(hw); - - /* Zero out the Multicast HASH table */ - pr_debug("Zeroing the MTA\n"); - for (i = 0; i < IXGB_MC_TBL_SIZE; i++) - IXGB_WRITE_REG_ARRAY(hw, MTA, i, 0); - - /* Zero out the VLAN Filter Table Array */ - ixgb_clear_vfta(hw); - - /* Zero all of the hardware counters */ - ixgb_clear_hw_cntrs(hw); - - /* Call a subroutine to setup flow control. */ - status = ixgb_setup_fc(hw); - - /* 82597EX errata: Call check-for-link in case lane deskew is locked */ - ixgb_check_for_link(hw); - - return status; -} - -/****************************************************************************** - * Initializes receive address filters. - * - * hw - Struct containing variables accessed by shared code - * - * Places the MAC address in receive address register 0 and clears the rest - * of the receive address registers. Clears the multicast table. Assumes - * the receiver is in reset when the routine is called. - *****************************************************************************/ -static void -ixgb_init_rx_addrs(struct ixgb_hw *hw) -{ - u32 i; - - ENTER(); - - /* - * If the current mac address is valid, assume it is a software override - * to the permanent address. - * Otherwise, use the permanent address from the eeprom. - */ - if (!mac_addr_valid(hw->curr_mac_addr)) { - - /* Get the MAC address from the eeprom for later reference */ - ixgb_get_ee_mac_addr(hw, hw->curr_mac_addr); - - pr_debug("Keeping Permanent MAC Addr = %pM\n", - hw->curr_mac_addr); - } else { - - /* Setup the receive address. */ - pr_debug("Overriding MAC Address in RAR[0]\n"); - pr_debug("New MAC Addr = %pM\n", hw->curr_mac_addr); - - ixgb_rar_set(hw, hw->curr_mac_addr, 0); - } - - /* Zero out the other 15 receive addresses. */ - pr_debug("Clearing RAR[1-15]\n"); - for (i = 1; i < IXGB_RAR_ENTRIES; i++) { - /* Write high reg first to disable the AV bit first */ - IXGB_WRITE_REG_ARRAY(hw, RA, ((i << 1) + 1), 0); - IXGB_WRITE_REG_ARRAY(hw, RA, (i << 1), 0); - } -} - -/****************************************************************************** - * Updates the MAC's list of multicast addresses. - * - * hw - Struct containing variables accessed by shared code - * mc_addr_list - the list of new multicast addresses - * mc_addr_count - number of addresses - * pad - number of bytes between addresses in the list - * - * The given list replaces any existing list. Clears the last 15 receive - * address registers and the multicast table. Uses receive address registers - * for the first 15 multicast addresses, and hashes the rest into the - * multicast table. - *****************************************************************************/ -void -ixgb_mc_addr_list_update(struct ixgb_hw *hw, - u8 *mc_addr_list, - u32 mc_addr_count, - u32 pad) -{ - u32 hash_value; - u32 i; - u32 rar_used_count = 1; /* RAR[0] is used for our MAC address */ - u8 *mca; - - ENTER(); - - /* Set the new number of MC addresses that we are being requested to use. */ - hw->num_mc_addrs = mc_addr_count; - - /* Clear RAR[1-15] */ - pr_debug("Clearing RAR[1-15]\n"); - for (i = rar_used_count; i < IXGB_RAR_ENTRIES; i++) { - IXGB_WRITE_REG_ARRAY(hw, RA, (i << 1), 0); - IXGB_WRITE_REG_ARRAY(hw, RA, ((i << 1) + 1), 0); - } - - /* Clear the MTA */ - pr_debug("Clearing MTA\n"); - for (i = 0; i < IXGB_MC_TBL_SIZE; i++) - IXGB_WRITE_REG_ARRAY(hw, MTA, i, 0); - - /* Add the new addresses */ - mca = mc_addr_list; - for (i = 0; i < mc_addr_count; i++) { - pr_debug("Adding the multicast addresses:\n"); - pr_debug("MC Addr #%d = %pM\n", i, mca); - - /* Place this multicast address in the RAR if there is room, * - * else put it in the MTA - */ - if (rar_used_count < IXGB_RAR_ENTRIES) { - ixgb_rar_set(hw, mca, rar_used_count); - pr_debug("Added a multicast address to RAR[%d]\n", i); - rar_used_count++; - } else { - hash_value = ixgb_hash_mc_addr(hw, mca); - - pr_debug("Hash value = 0x%03X\n", hash_value); - - ixgb_mta_set(hw, hash_value); - } - - mca += ETH_ALEN + pad; - } - - pr_debug("MC Update Complete\n"); -} - -/****************************************************************************** - * Hashes an address to determine its location in the multicast table - * - * hw - Struct containing variables accessed by shared code - * mc_addr - the multicast address to hash - * - * Returns: - * The hash value - *****************************************************************************/ -static u32 -ixgb_hash_mc_addr(struct ixgb_hw *hw, - u8 *mc_addr) -{ - u32 hash_value = 0; - - ENTER(); - - /* The portion of the address that is used for the hash table is - * determined by the mc_filter_type setting. - */ - switch (hw->mc_filter_type) { - /* [0] [1] [2] [3] [4] [5] - * 01 AA 00 12 34 56 - * LSB MSB - According to H/W docs */ - case 0: - /* [47:36] i.e. 0x563 for above example address */ - hash_value = - ((mc_addr[4] >> 4) | (((u16) mc_addr[5]) << 4)); - break; - case 1: /* [46:35] i.e. 0xAC6 for above example address */ - hash_value = - ((mc_addr[4] >> 3) | (((u16) mc_addr[5]) << 5)); - break; - case 2: /* [45:34] i.e. 0x5D8 for above example address */ - hash_value = - ((mc_addr[4] >> 2) | (((u16) mc_addr[5]) << 6)); - break; - case 3: /* [43:32] i.e. 0x634 for above example address */ - hash_value = ((mc_addr[4]) | (((u16) mc_addr[5]) << 8)); - break; - default: - /* Invalid mc_filter_type, what should we do? */ - pr_debug("MC filter type param set incorrectly\n"); - ASSERT(0); - break; - } - - hash_value &= 0xFFF; - return hash_value; -} - -/****************************************************************************** - * Sets the bit in the multicast table corresponding to the hash value. - * - * hw - Struct containing variables accessed by shared code - * hash_value - Multicast address hash value - *****************************************************************************/ -static void -ixgb_mta_set(struct ixgb_hw *hw, - u32 hash_value) -{ - u32 hash_bit, hash_reg; - u32 mta_reg; - - /* The MTA is a register array of 128 32-bit registers. - * It is treated like an array of 4096 bits. We want to set - * bit BitArray[hash_value]. So we figure out what register - * the bit is in, read it, OR in the new bit, then write - * back the new value. The register is determined by the - * upper 7 bits of the hash value and the bit within that - * register are determined by the lower 5 bits of the value. - */ - hash_reg = (hash_value >> 5) & 0x7F; - hash_bit = hash_value & 0x1F; - - mta_reg = IXGB_READ_REG_ARRAY(hw, MTA, hash_reg); - - mta_reg |= (1 << hash_bit); - - IXGB_WRITE_REG_ARRAY(hw, MTA, hash_reg, mta_reg); -} - -/****************************************************************************** - * Puts an ethernet address into a receive address register. - * - * hw - Struct containing variables accessed by shared code - * addr - Address to put into receive address register - * index - Receive address register to write - *****************************************************************************/ -void -ixgb_rar_set(struct ixgb_hw *hw, - const u8 *addr, - u32 index) -{ - u32 rar_low, rar_high; - - ENTER(); - - /* HW expects these in little endian so we reverse the byte order - * from network order (big endian) to little endian - */ - rar_low = ((u32) addr[0] | - ((u32)addr[1] << 8) | - ((u32)addr[2] << 16) | - ((u32)addr[3] << 24)); - - rar_high = ((u32) addr[4] | - ((u32)addr[5] << 8) | - IXGB_RAH_AV); - - IXGB_WRITE_REG_ARRAY(hw, RA, (index << 1), rar_low); - IXGB_WRITE_REG_ARRAY(hw, RA, ((index << 1) + 1), rar_high); -} - -/****************************************************************************** - * Writes a value to the specified offset in the VLAN filter table. - * - * hw - Struct containing variables accessed by shared code - * offset - Offset in VLAN filter table to write - * value - Value to write into VLAN filter table - *****************************************************************************/ -void -ixgb_write_vfta(struct ixgb_hw *hw, - u32 offset, - u32 value) -{ - IXGB_WRITE_REG_ARRAY(hw, VFTA, offset, value); -} - -/****************************************************************************** - * Clears the VLAN filter table - * - * hw - Struct containing variables accessed by shared code - *****************************************************************************/ -static void -ixgb_clear_vfta(struct ixgb_hw *hw) -{ - u32 offset; - - for (offset = 0; offset < IXGB_VLAN_FILTER_TBL_SIZE; offset++) - IXGB_WRITE_REG_ARRAY(hw, VFTA, offset, 0); -} - -/****************************************************************************** - * Configures the flow control settings based on SW configuration. - * - * hw - Struct containing variables accessed by shared code - *****************************************************************************/ - -static bool -ixgb_setup_fc(struct ixgb_hw *hw) -{ - u32 ctrl_reg; - u32 pap_reg = 0; /* by default, assume no pause time */ - bool status = true; - - ENTER(); - - /* Get the current control reg 0 settings */ - ctrl_reg = IXGB_READ_REG(hw, CTRL0); - - /* Clear the Receive Pause Enable and Transmit Pause Enable bits */ - ctrl_reg &= ~(IXGB_CTRL0_RPE | IXGB_CTRL0_TPE); - - /* The possible values of the "flow_control" parameter are: - * 0: Flow control is completely disabled - * 1: Rx flow control is enabled (we can receive pause frames - * but not send pause frames). - * 2: Tx flow control is enabled (we can send pause frames - * but we do not support receiving pause frames). - * 3: Both Rx and TX flow control (symmetric) are enabled. - * other: Invalid. - */ - switch (hw->fc.type) { - case ixgb_fc_none: /* 0 */ - /* Set CMDC bit to disable Rx Flow control */ - ctrl_reg |= (IXGB_CTRL0_CMDC); - break; - case ixgb_fc_rx_pause: /* 1 */ - /* RX Flow control is enabled, and TX Flow control is - * disabled. - */ - ctrl_reg |= (IXGB_CTRL0_RPE); - break; - case ixgb_fc_tx_pause: /* 2 */ - /* TX Flow control is enabled, and RX Flow control is - * disabled, by a software over-ride. - */ - ctrl_reg |= (IXGB_CTRL0_TPE); - pap_reg = hw->fc.pause_time; - break; - case ixgb_fc_full: /* 3 */ - /* Flow control (both RX and TX) is enabled by a software - * over-ride. - */ - ctrl_reg |= (IXGB_CTRL0_RPE | IXGB_CTRL0_TPE); - pap_reg = hw->fc.pause_time; - break; - default: - /* We should never get here. The value should be 0-3. */ - pr_debug("Flow control param set incorrectly\n"); - ASSERT(0); - break; - } - - /* Write the new settings */ - IXGB_WRITE_REG(hw, CTRL0, ctrl_reg); - - if (pap_reg != 0) - IXGB_WRITE_REG(hw, PAP, pap_reg); - - /* Set the flow control receive threshold registers. Normally, - * these registers will be set to a default threshold that may be - * adjusted later by the driver's runtime code. However, if the - * ability to transmit pause frames in not enabled, then these - * registers will be set to 0. - */ - if (!(hw->fc.type & ixgb_fc_tx_pause)) { - IXGB_WRITE_REG(hw, FCRTL, 0); - IXGB_WRITE_REG(hw, FCRTH, 0); - } else { - /* We need to set up the Receive Threshold high and low water - * marks as well as (optionally) enabling the transmission of XON - * frames. */ - if (hw->fc.send_xon) { - IXGB_WRITE_REG(hw, FCRTL, - (hw->fc.low_water | IXGB_FCRTL_XONE)); - } else { - IXGB_WRITE_REG(hw, FCRTL, hw->fc.low_water); - } - IXGB_WRITE_REG(hw, FCRTH, hw->fc.high_water); - } - return status; -} - -/****************************************************************************** - * Reads a word from a device over the Management Data Interface (MDI) bus. - * This interface is used to manage Physical layer devices. - * - * hw - Struct containing variables accessed by hw code - * reg_address - Offset of device register being read. - * phy_address - Address of device on MDI. - * - * Returns: Data word (16 bits) from MDI device. - * - * The 82597EX has support for several MDI access methods. This routine - * uses the new protocol MDI Single Command and Address Operation. - * This requires that first an address cycle command is sent, followed by a - * read command. - *****************************************************************************/ -static u16 -ixgb_read_phy_reg(struct ixgb_hw *hw, - u32 reg_address, - u32 phy_address, - u32 device_type) -{ - u32 i; - u32 data; - u32 command = 0; - - ASSERT(reg_address <= IXGB_MAX_PHY_REG_ADDRESS); - ASSERT(phy_address <= IXGB_MAX_PHY_ADDRESS); - ASSERT(device_type <= IXGB_MAX_PHY_DEV_TYPE); - - /* Setup and write the address cycle command */ - command = ((reg_address << IXGB_MSCA_NP_ADDR_SHIFT) | - (device_type << IXGB_MSCA_DEV_TYPE_SHIFT) | - (phy_address << IXGB_MSCA_PHY_ADDR_SHIFT) | - (IXGB_MSCA_ADDR_CYCLE | IXGB_MSCA_MDI_COMMAND)); - - IXGB_WRITE_REG(hw, MSCA, command); - - /************************************************************** - ** Check every 10 usec to see if the address cycle completed - ** The COMMAND bit will clear when the operation is complete. - ** This may take as long as 64 usecs (we'll wait 100 usecs max) - ** from the CPU Write to the Ready bit assertion. - **************************************************************/ - - for (i = 0; i < 10; i++) - { - udelay(10); - - command = IXGB_READ_REG(hw, MSCA); - - if ((command & IXGB_MSCA_MDI_COMMAND) == 0) - break; - } - - ASSERT((command & IXGB_MSCA_MDI_COMMAND) == 0); - - /* Address cycle complete, setup and write the read command */ - command = ((reg_address << IXGB_MSCA_NP_ADDR_SHIFT) | - (device_type << IXGB_MSCA_DEV_TYPE_SHIFT) | - (phy_address << IXGB_MSCA_PHY_ADDR_SHIFT) | - (IXGB_MSCA_READ | IXGB_MSCA_MDI_COMMAND)); - - IXGB_WRITE_REG(hw, MSCA, command); - - /************************************************************** - ** Check every 10 usec to see if the read command completed - ** The COMMAND bit will clear when the operation is complete. - ** The read may take as long as 64 usecs (we'll wait 100 usecs max) - ** from the CPU Write to the Ready bit assertion. - **************************************************************/ - - for (i = 0; i < 10; i++) - { - udelay(10); - - command = IXGB_READ_REG(hw, MSCA); - - if ((command & IXGB_MSCA_MDI_COMMAND) == 0) - break; - } - - ASSERT((command & IXGB_MSCA_MDI_COMMAND) == 0); - - /* Operation is complete, get the data from the MDIO Read/Write Data - * register and return. - */ - data = IXGB_READ_REG(hw, MSRWD); - data >>= IXGB_MSRWD_READ_DATA_SHIFT; - return((u16) data); -} - -/****************************************************************************** - * Writes a word to a device over the Management Data Interface (MDI) bus. - * This interface is used to manage Physical layer devices. - * - * hw - Struct containing variables accessed by hw code - * reg_address - Offset of device register being read. - * phy_address - Address of device on MDI. - * device_type - Also known as the Device ID or DID. - * data - 16-bit value to be written - * - * Returns: void. - * - * The 82597EX has support for several MDI access methods. This routine - * uses the new protocol MDI Single Command and Address Operation. - * This requires that first an address cycle command is sent, followed by a - * write command. - *****************************************************************************/ -static void -ixgb_write_phy_reg(struct ixgb_hw *hw, - u32 reg_address, - u32 phy_address, - u32 device_type, - u16 data) -{ - u32 i; - u32 command = 0; - - ASSERT(reg_address <= IXGB_MAX_PHY_REG_ADDRESS); - ASSERT(phy_address <= IXGB_MAX_PHY_ADDRESS); - ASSERT(device_type <= IXGB_MAX_PHY_DEV_TYPE); - - /* Put the data in the MDIO Read/Write Data register */ - IXGB_WRITE_REG(hw, MSRWD, (u32)data); - - /* Setup and write the address cycle command */ - command = ((reg_address << IXGB_MSCA_NP_ADDR_SHIFT) | - (device_type << IXGB_MSCA_DEV_TYPE_SHIFT) | - (phy_address << IXGB_MSCA_PHY_ADDR_SHIFT) | - (IXGB_MSCA_ADDR_CYCLE | IXGB_MSCA_MDI_COMMAND)); - - IXGB_WRITE_REG(hw, MSCA, command); - - /************************************************************** - ** Check every 10 usec to see if the address cycle completed - ** The COMMAND bit will clear when the operation is complete. - ** This may take as long as 64 usecs (we'll wait 100 usecs max) - ** from the CPU Write to the Ready bit assertion. - **************************************************************/ - - for (i = 0; i < 10; i++) - { - udelay(10); - - command = IXGB_READ_REG(hw, MSCA); - - if ((command & IXGB_MSCA_MDI_COMMAND) == 0) - break; - } - - ASSERT((command & IXGB_MSCA_MDI_COMMAND) == 0); - - /* Address cycle complete, setup and write the write command */ - command = ((reg_address << IXGB_MSCA_NP_ADDR_SHIFT) | - (device_type << IXGB_MSCA_DEV_TYPE_SHIFT) | - (phy_address << IXGB_MSCA_PHY_ADDR_SHIFT) | - (IXGB_MSCA_WRITE | IXGB_MSCA_MDI_COMMAND)); - - IXGB_WRITE_REG(hw, MSCA, command); - - /************************************************************** - ** Check every 10 usec to see if the read command completed - ** The COMMAND bit will clear when the operation is complete. - ** The write may take as long as 64 usecs (we'll wait 100 usecs max) - ** from the CPU Write to the Ready bit assertion. - **************************************************************/ - - for (i = 0; i < 10; i++) - { - udelay(10); - - command = IXGB_READ_REG(hw, MSCA); - - if ((command & IXGB_MSCA_MDI_COMMAND) == 0) - break; - } - - ASSERT((command & IXGB_MSCA_MDI_COMMAND) == 0); - - /* Operation is complete, return. */ -} - -/****************************************************************************** - * Checks to see if the link status of the hardware has changed. - * - * hw - Struct containing variables accessed by hw code - * - * Called by any function that needs to check the link status of the adapter. - *****************************************************************************/ -void -ixgb_check_for_link(struct ixgb_hw *hw) -{ - u32 status_reg; - u32 xpcss_reg; - - ENTER(); - - xpcss_reg = IXGB_READ_REG(hw, XPCSS); - status_reg = IXGB_READ_REG(hw, STATUS); - - if ((xpcss_reg & IXGB_XPCSS_ALIGN_STATUS) && - (status_reg & IXGB_STATUS_LU)) { - hw->link_up = true; - } else if (!(xpcss_reg & IXGB_XPCSS_ALIGN_STATUS) && - (status_reg & IXGB_STATUS_LU)) { - pr_debug("XPCSS Not Aligned while Status:LU is set\n"); - hw->link_up = ixgb_link_reset(hw); - } else { - /* - * 82597EX errata. Since the lane deskew problem may prevent - * link, reset the link before reporting link down. - */ - hw->link_up = ixgb_link_reset(hw); - } - /* Anything else for 10 Gig?? */ -} - -/****************************************************************************** - * Check for a bad link condition that may have occurred. - * The indication is that the RFC / LFC registers may be incrementing - * continually. A full adapter reset is required to recover. - * - * hw - Struct containing variables accessed by hw code - * - * Called by any function that needs to check the link status of the adapter. - *****************************************************************************/ -bool ixgb_check_for_bad_link(struct ixgb_hw *hw) -{ - u32 newLFC, newRFC; - bool bad_link_returncode = false; - - if (hw->phy_type == ixgb_phy_type_txn17401) { - newLFC = IXGB_READ_REG(hw, LFC); - newRFC = IXGB_READ_REG(hw, RFC); - if ((hw->lastLFC + 250 < newLFC) - || (hw->lastRFC + 250 < newRFC)) { - pr_debug("BAD LINK! too many LFC/RFC since last check\n"); - bad_link_returncode = true; - } - hw->lastLFC = newLFC; - hw->lastRFC = newRFC; - } - - return bad_link_returncode; -} - -/****************************************************************************** - * Clears all hardware statistics counters. - * - * hw - Struct containing variables accessed by shared code - *****************************************************************************/ -static void -ixgb_clear_hw_cntrs(struct ixgb_hw *hw) -{ - ENTER(); - - /* if we are stopped or resetting exit gracefully */ - if (hw->adapter_stopped) { - pr_debug("Exiting because the adapter is stopped!!!\n"); - return; - } - - IXGB_READ_REG(hw, TPRL); - IXGB_READ_REG(hw, TPRH); - IXGB_READ_REG(hw, GPRCL); - IXGB_READ_REG(hw, GPRCH); - IXGB_READ_REG(hw, BPRCL); - IXGB_READ_REG(hw, BPRCH); - IXGB_READ_REG(hw, MPRCL); - IXGB_READ_REG(hw, MPRCH); - IXGB_READ_REG(hw, UPRCL); - IXGB_READ_REG(hw, UPRCH); - IXGB_READ_REG(hw, VPRCL); - IXGB_READ_REG(hw, VPRCH); - IXGB_READ_REG(hw, JPRCL); - IXGB_READ_REG(hw, JPRCH); - IXGB_READ_REG(hw, GORCL); - IXGB_READ_REG(hw, GORCH); - IXGB_READ_REG(hw, TORL); - IXGB_READ_REG(hw, TORH); - IXGB_READ_REG(hw, RNBC); - IXGB_READ_REG(hw, RUC); - IXGB_READ_REG(hw, ROC); - IXGB_READ_REG(hw, RLEC); - IXGB_READ_REG(hw, CRCERRS); - IXGB_READ_REG(hw, ICBC); - IXGB_READ_REG(hw, ECBC); - IXGB_READ_REG(hw, MPC); - IXGB_READ_REG(hw, TPTL); - IXGB_READ_REG(hw, TPTH); - IXGB_READ_REG(hw, GPTCL); - IXGB_READ_REG(hw, GPTCH); - IXGB_READ_REG(hw, BPTCL); - IXGB_READ_REG(hw, BPTCH); - IXGB_READ_REG(hw, MPTCL); - IXGB_READ_REG(hw, MPTCH); - IXGB_READ_REG(hw, UPTCL); - IXGB_READ_REG(hw, UPTCH); - IXGB_READ_REG(hw, VPTCL); - IXGB_READ_REG(hw, VPTCH); - IXGB_READ_REG(hw, JPTCL); - IXGB_READ_REG(hw, JPTCH); - IXGB_READ_REG(hw, GOTCL); - IXGB_READ_REG(hw, GOTCH); - IXGB_READ_REG(hw, TOTL); - IXGB_READ_REG(hw, TOTH); - IXGB_READ_REG(hw, DC); - IXGB_READ_REG(hw, PLT64C); - IXGB_READ_REG(hw, TSCTC); - IXGB_READ_REG(hw, TSCTFC); - IXGB_READ_REG(hw, IBIC); - IXGB_READ_REG(hw, RFC); - IXGB_READ_REG(hw, LFC); - IXGB_READ_REG(hw, PFRC); - IXGB_READ_REG(hw, PFTC); - IXGB_READ_REG(hw, MCFRC); - IXGB_READ_REG(hw, MCFTC); - IXGB_READ_REG(hw, XONRXC); - IXGB_READ_REG(hw, XONTXC); - IXGB_READ_REG(hw, XOFFRXC); - IXGB_READ_REG(hw, XOFFTXC); - IXGB_READ_REG(hw, RJC); -} - -/****************************************************************************** - * Turns on the software controllable LED - * - * hw - Struct containing variables accessed by shared code - *****************************************************************************/ -void -ixgb_led_on(struct ixgb_hw *hw) -{ - u32 ctrl0_reg = IXGB_READ_REG(hw, CTRL0); - - /* To turn on the LED, clear software-definable pin 0 (SDP0). */ - ctrl0_reg &= ~IXGB_CTRL0_SDP0; - IXGB_WRITE_REG(hw, CTRL0, ctrl0_reg); -} - -/****************************************************************************** - * Turns off the software controllable LED - * - * hw - Struct containing variables accessed by shared code - *****************************************************************************/ -void -ixgb_led_off(struct ixgb_hw *hw) -{ - u32 ctrl0_reg = IXGB_READ_REG(hw, CTRL0); - - /* To turn off the LED, set software-definable pin 0 (SDP0). */ - ctrl0_reg |= IXGB_CTRL0_SDP0; - IXGB_WRITE_REG(hw, CTRL0, ctrl0_reg); -} - -/****************************************************************************** - * Gets the current PCI bus type, speed, and width of the hardware - * - * hw - Struct containing variables accessed by shared code - *****************************************************************************/ -static void -ixgb_get_bus_info(struct ixgb_hw *hw) -{ - u32 status_reg; - - status_reg = IXGB_READ_REG(hw, STATUS); - - hw->bus.type = (status_reg & IXGB_STATUS_PCIX_MODE) ? - ixgb_bus_type_pcix : ixgb_bus_type_pci; - - if (hw->bus.type == ixgb_bus_type_pci) { - hw->bus.speed = (status_reg & IXGB_STATUS_PCI_SPD) ? - ixgb_bus_speed_66 : ixgb_bus_speed_33; - } else { - switch (status_reg & IXGB_STATUS_PCIX_SPD_MASK) { - case IXGB_STATUS_PCIX_SPD_66: - hw->bus.speed = ixgb_bus_speed_66; - break; - case IXGB_STATUS_PCIX_SPD_100: - hw->bus.speed = ixgb_bus_speed_100; - break; - case IXGB_STATUS_PCIX_SPD_133: - hw->bus.speed = ixgb_bus_speed_133; - break; - default: - hw->bus.speed = ixgb_bus_speed_reserved; - break; - } - } - - hw->bus.width = (status_reg & IXGB_STATUS_BUS64) ? - ixgb_bus_width_64 : ixgb_bus_width_32; -} - -/****************************************************************************** - * Tests a MAC address to ensure it is a valid Individual Address - * - * mac_addr - pointer to MAC address. - * - *****************************************************************************/ -static bool -mac_addr_valid(u8 *mac_addr) -{ - bool is_valid = true; - ENTER(); - - /* Make sure it is not a multicast address */ - if (is_multicast_ether_addr(mac_addr)) { - pr_debug("MAC address is multicast\n"); - is_valid = false; - } - /* Not a broadcast address */ - else if (is_broadcast_ether_addr(mac_addr)) { - pr_debug("MAC address is broadcast\n"); - is_valid = false; - } - /* Reject the zero address */ - else if (is_zero_ether_addr(mac_addr)) { - pr_debug("MAC address is all zeros\n"); - is_valid = false; - } - return is_valid; -} - -/****************************************************************************** - * Resets the 10GbE link. Waits the settle time and returns the state of - * the link. - * - * hw - Struct containing variables accessed by shared code - *****************************************************************************/ -static bool -ixgb_link_reset(struct ixgb_hw *hw) -{ - bool link_status = false; - u8 wait_retries = MAX_RESET_ITERATIONS; - u8 lrst_retries = MAX_RESET_ITERATIONS; - - do { - /* Reset the link */ - IXGB_WRITE_REG(hw, CTRL0, - IXGB_READ_REG(hw, CTRL0) | IXGB_CTRL0_LRST); - - /* Wait for link-up and lane re-alignment */ - do { - udelay(IXGB_DELAY_USECS_AFTER_LINK_RESET); - link_status = - ((IXGB_READ_REG(hw, STATUS) & IXGB_STATUS_LU) - && (IXGB_READ_REG(hw, XPCSS) & - IXGB_XPCSS_ALIGN_STATUS)) ? true : false; - } while (!link_status && --wait_retries); - - } while (!link_status && --lrst_retries); - - return link_status; -} - -/****************************************************************************** - * Resets the 10GbE optics module. - * - * hw - Struct containing variables accessed by shared code - *****************************************************************************/ -static void -ixgb_optics_reset(struct ixgb_hw *hw) -{ - if (hw->phy_type == ixgb_phy_type_txn17401) { - ixgb_write_phy_reg(hw, - MDIO_CTRL1, - IXGB_PHY_ADDRESS, - MDIO_MMD_PMAPMD, - MDIO_CTRL1_RESET); - - ixgb_read_phy_reg(hw, MDIO_CTRL1, IXGB_PHY_ADDRESS, MDIO_MMD_PMAPMD); - } -} - -/****************************************************************************** - * Resets the 10GbE optics module for Sun variant NIC. - * - * hw - Struct containing variables accessed by shared code - *****************************************************************************/ - -#define IXGB_BCM8704_USER_PMD_TX_CTRL_REG 0xC803 -#define IXGB_BCM8704_USER_PMD_TX_CTRL_REG_VAL 0x0164 -#define IXGB_BCM8704_USER_CTRL_REG 0xC800 -#define IXGB_BCM8704_USER_CTRL_REG_VAL 0x7FBF -#define IXGB_BCM8704_USER_DEV3_ADDR 0x0003 -#define IXGB_SUN_PHY_ADDRESS 0x0000 -#define IXGB_SUN_PHY_RESET_DELAY 305 - -static void -ixgb_optics_reset_bcm(struct ixgb_hw *hw) -{ - u32 ctrl = IXGB_READ_REG(hw, CTRL0); - ctrl &= ~IXGB_CTRL0_SDP2; - ctrl |= IXGB_CTRL0_SDP3; - IXGB_WRITE_REG(hw, CTRL0, ctrl); - IXGB_WRITE_FLUSH(hw); - - /* SerDes needs extra delay */ - msleep(IXGB_SUN_PHY_RESET_DELAY); - - /* Broadcom 7408L configuration */ - /* Reference clock config */ - ixgb_write_phy_reg(hw, - IXGB_BCM8704_USER_PMD_TX_CTRL_REG, - IXGB_SUN_PHY_ADDRESS, - IXGB_BCM8704_USER_DEV3_ADDR, - IXGB_BCM8704_USER_PMD_TX_CTRL_REG_VAL); - /* we must read the registers twice */ - ixgb_read_phy_reg(hw, - IXGB_BCM8704_USER_PMD_TX_CTRL_REG, - IXGB_SUN_PHY_ADDRESS, - IXGB_BCM8704_USER_DEV3_ADDR); - ixgb_read_phy_reg(hw, - IXGB_BCM8704_USER_PMD_TX_CTRL_REG, - IXGB_SUN_PHY_ADDRESS, - IXGB_BCM8704_USER_DEV3_ADDR); - - ixgb_write_phy_reg(hw, - IXGB_BCM8704_USER_CTRL_REG, - IXGB_SUN_PHY_ADDRESS, - IXGB_BCM8704_USER_DEV3_ADDR, - IXGB_BCM8704_USER_CTRL_REG_VAL); - ixgb_read_phy_reg(hw, - IXGB_BCM8704_USER_CTRL_REG, - IXGB_SUN_PHY_ADDRESS, - IXGB_BCM8704_USER_DEV3_ADDR); - ixgb_read_phy_reg(hw, - IXGB_BCM8704_USER_CTRL_REG, - IXGB_SUN_PHY_ADDRESS, - IXGB_BCM8704_USER_DEV3_ADDR); - - /* SerDes needs extra delay */ - msleep(IXGB_SUN_PHY_RESET_DELAY); -} diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_hw.h b/drivers/net/ethernet/intel/ixgb/ixgb_hw.h deleted file mode 100644 index 70bcff5fb3db..000000000000 --- a/drivers/net/ethernet/intel/ixgb/ixgb_hw.h +++ /dev/null @@ -1,767 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 1999 - 2008 Intel Corporation. */ - -#ifndef _IXGB_HW_H_ -#define _IXGB_HW_H_ - -#include <linux/mdio.h> - -#include "ixgb_osdep.h" - -/* Enums */ -typedef enum { - ixgb_mac_unknown = 0, - ixgb_82597, - ixgb_num_macs -} ixgb_mac_type; - -/* Types of physical layer modules */ -typedef enum { - ixgb_phy_type_unknown = 0, - ixgb_phy_type_g6005, /* 850nm, MM fiber, XPAK transceiver */ - ixgb_phy_type_g6104, /* 1310nm, SM fiber, XPAK transceiver */ - ixgb_phy_type_txn17201, /* 850nm, MM fiber, XPAK transceiver */ - ixgb_phy_type_txn17401, /* 1310nm, SM fiber, XENPAK transceiver */ - ixgb_phy_type_bcm /* SUN specific board */ -} ixgb_phy_type; - -/* XPAK transceiver vendors, for the SR adapters */ -typedef enum { - ixgb_xpak_vendor_intel, - ixgb_xpak_vendor_infineon -} ixgb_xpak_vendor; - -/* Media Types */ -typedef enum { - ixgb_media_type_unknown = 0, - ixgb_media_type_fiber = 1, - ixgb_media_type_copper = 2, - ixgb_num_media_types -} ixgb_media_type; - -/* Flow Control Settings */ -typedef enum { - ixgb_fc_none = 0, - ixgb_fc_rx_pause = 1, - ixgb_fc_tx_pause = 2, - ixgb_fc_full = 3, - ixgb_fc_default = 0xFF -} ixgb_fc_type; - -/* PCI bus types */ -typedef enum { - ixgb_bus_type_unknown = 0, - ixgb_bus_type_pci, - ixgb_bus_type_pcix -} ixgb_bus_type; - -/* PCI bus speeds */ -typedef enum { - ixgb_bus_speed_unknown = 0, - ixgb_bus_speed_33, - ixgb_bus_speed_66, - ixgb_bus_speed_100, - ixgb_bus_speed_133, - ixgb_bus_speed_reserved -} ixgb_bus_speed; - -/* PCI bus widths */ -typedef enum { - ixgb_bus_width_unknown = 0, - ixgb_bus_width_32, - ixgb_bus_width_64 -} ixgb_bus_width; - -#define IXGB_EEPROM_SIZE 64 /* Size in words */ - -#define SPEED_10000 10000 -#define FULL_DUPLEX 2 - -#define MIN_NUMBER_OF_DESCRIPTORS 8 -#define MAX_NUMBER_OF_DESCRIPTORS 0xFFF8 /* 13 bits in RDLEN/TDLEN, 128B aligned */ - -#define IXGB_DELAY_BEFORE_RESET 10 /* allow 10ms after idling rx/tx units */ -#define IXGB_DELAY_AFTER_RESET 1 /* allow 1ms after the reset */ -#define IXGB_DELAY_AFTER_EE_RESET 10 /* allow 10ms after the EEPROM reset */ - -#define IXGB_DELAY_USECS_AFTER_LINK_RESET 13 /* allow 13 microseconds after the reset */ - /* NOTE: this is MICROSECONDS */ -#define MAX_RESET_ITERATIONS 8 /* number of iterations to get things right */ - -/* General Registers */ -#define IXGB_CTRL0 0x00000 /* Device Control Register 0 - RW */ -#define IXGB_CTRL1 0x00008 /* Device Control Register 1 - RW */ -#define IXGB_STATUS 0x00010 /* Device Status Register - RO */ -#define IXGB_EECD 0x00018 /* EEPROM/Flash Control/Data Register - RW */ -#define IXGB_MFS 0x00020 /* Maximum Frame Size - RW */ - -/* Interrupt */ -#define IXGB_ICR 0x00080 /* Interrupt Cause Read - R/clr */ -#define IXGB_ICS 0x00088 /* Interrupt Cause Set - RW */ -#define IXGB_IMS 0x00090 /* Interrupt Mask Set/Read - RW */ -#define IXGB_IMC 0x00098 /* Interrupt Mask Clear - WO */ - -/* Receive */ -#define IXGB_RCTL 0x00100 /* RX Control - RW */ -#define IXGB_FCRTL 0x00108 /* Flow Control Receive Threshold Low - RW */ -#define IXGB_FCRTH 0x00110 /* Flow Control Receive Threshold High - RW */ -#define IXGB_RDBAL 0x00118 /* RX Descriptor Base Low - RW */ -#define IXGB_RDBAH 0x0011C /* RX Descriptor Base High - RW */ -#define IXGB_RDLEN 0x00120 /* RX Descriptor Length - RW */ -#define IXGB_RDH 0x00128 /* RX Descriptor Head - RW */ -#define IXGB_RDT 0x00130 /* RX Descriptor Tail - RW */ -#define IXGB_RDTR 0x00138 /* RX Delay Timer Ring - RW */ -#define IXGB_RXDCTL 0x00140 /* Receive Descriptor Control - RW */ -#define IXGB_RAIDC 0x00148 /* Receive Adaptive Interrupt Delay Control - RW */ -#define IXGB_RXCSUM 0x00158 /* Receive Checksum Control - RW */ -#define IXGB_RA 0x00180 /* Receive Address Array Base - RW */ -#define IXGB_RAL 0x00180 /* Receive Address Low [0:15] - RW */ -#define IXGB_RAH 0x00184 /* Receive Address High [0:15] - RW */ -#define IXGB_MTA 0x00200 /* Multicast Table Array [0:127] - RW */ -#define IXGB_VFTA 0x00400 /* VLAN Filter Table Array [0:127] - RW */ -#define IXGB_REQ_RX_DESCRIPTOR_MULTIPLE 8 - -/* Transmit */ -#define IXGB_TCTL 0x00600 /* TX Control - RW */ -#define IXGB_TDBAL 0x00608 /* TX Descriptor Base Low - RW */ -#define IXGB_TDBAH 0x0060C /* TX Descriptor Base High - RW */ -#define IXGB_TDLEN 0x00610 /* TX Descriptor Length - RW */ -#define IXGB_TDH 0x00618 /* TX Descriptor Head - RW */ -#define IXGB_TDT 0x00620 /* TX Descriptor Tail - RW */ -#define IXGB_TIDV 0x00628 /* TX Interrupt Delay Value - RW */ -#define IXGB_TXDCTL 0x00630 /* Transmit Descriptor Control - RW */ -#define IXGB_TSPMT 0x00638 /* TCP Segmentation PAD & Min Threshold - RW */ -#define IXGB_PAP 0x00640 /* Pause and Pace - RW */ -#define IXGB_REQ_TX_DESCRIPTOR_MULTIPLE 8 - -/* Physical */ -#define IXGB_PCSC1 0x00700 /* PCS Control 1 - RW */ -#define IXGB_PCSC2 0x00708 /* PCS Control 2 - RW */ -#define IXGB_PCSS1 0x00710 /* PCS Status 1 - RO */ -#define IXGB_PCSS2 0x00718 /* PCS Status 2 - RO */ -#define IXGB_XPCSS 0x00720 /* 10GBASE-X PCS Status (or XGXS Lane Status) - RO */ -#define IXGB_UCCR 0x00728 /* Unilink Circuit Control Register */ -#define IXGB_XPCSTC 0x00730 /* 10GBASE-X PCS Test Control */ -#define IXGB_MACA 0x00738 /* MDI Autoscan Command and Address - RW */ -#define IXGB_APAE 0x00740 /* Autoscan PHY Address Enable - RW */ -#define IXGB_ARD 0x00748 /* Autoscan Read Data - RO */ -#define IXGB_AIS 0x00750 /* Autoscan Interrupt Status - RO */ -#define IXGB_MSCA 0x00758 /* MDI Single Command and Address - RW */ -#define IXGB_MSRWD 0x00760 /* MDI Single Read and Write Data - RW, RO */ - -/* Wake-up */ -#define IXGB_WUFC 0x00808 /* Wake Up Filter Control - RW */ -#define IXGB_WUS 0x00810 /* Wake Up Status - RO */ -#define IXGB_FFLT 0x01000 /* Flexible Filter Length Table - RW */ -#define IXGB_FFMT 0x01020 /* Flexible Filter Mask Table - RW */ -#define IXGB_FTVT 0x01420 /* Flexible Filter Value Table - RW */ - -/* Statistics */ -#define IXGB_TPRL 0x02000 /* Total Packets Received (Low) */ -#define IXGB_TPRH 0x02004 /* Total Packets Received (High) */ -#define IXGB_GPRCL 0x02008 /* Good Packets Received Count (Low) */ -#define IXGB_GPRCH 0x0200C /* Good Packets Received Count (High) */ -#define IXGB_BPRCL 0x02010 /* Broadcast Packets Received Count (Low) */ -#define IXGB_BPRCH 0x02014 /* Broadcast Packets Received Count (High) */ -#define IXGB_MPRCL 0x02018 /* Multicast Packets Received Count (Low) */ -#define IXGB_MPRCH 0x0201C /* Multicast Packets Received Count (High) */ -#define IXGB_UPRCL 0x02020 /* Unicast Packets Received Count (Low) */ -#define IXGB_UPRCH 0x02024 /* Unicast Packets Received Count (High) */ -#define IXGB_VPRCL 0x02028 /* VLAN Packets Received Count (Low) */ -#define IXGB_VPRCH 0x0202C /* VLAN Packets Received Count (High) */ -#define IXGB_JPRCL 0x02030 /* Jumbo Packets Received Count (Low) */ -#define IXGB_JPRCH 0x02034 /* Jumbo Packets Received Count (High) */ -#define IXGB_GORCL 0x02038 /* Good Octets Received Count (Low) */ -#define IXGB_GORCH 0x0203C /* Good Octets Received Count (High) */ -#define IXGB_TORL 0x02040 /* Total Octets Received (Low) */ -#define IXGB_TORH 0x02044 /* Total Octets Received (High) */ -#define IXGB_RNBC 0x02048 /* Receive No Buffers Count */ -#define IXGB_RUC 0x02050 /* Receive Undersize Count */ -#define IXGB_ROC 0x02058 /* Receive Oversize Count */ -#define IXGB_RLEC 0x02060 /* Receive Length Error Count */ -#define IXGB_CRCERRS 0x02068 /* CRC Error Count */ -#define IXGB_ICBC 0x02070 /* Illegal control byte in mid-packet Count */ -#define IXGB_ECBC 0x02078 /* Error Control byte in mid-packet Count */ -#define IXGB_MPC 0x02080 /* Missed Packets Count */ -#define IXGB_TPTL 0x02100 /* Total Packets Transmitted (Low) */ -#define IXGB_TPTH 0x02104 /* Total Packets Transmitted (High) */ -#define IXGB_GPTCL 0x02108 /* Good Packets Transmitted Count (Low) */ -#define IXGB_GPTCH 0x0210C /* Good Packets Transmitted Count (High) */ -#define IXGB_BPTCL 0x02110 /* Broadcast Packets Transmitted Count (Low) */ -#define IXGB_BPTCH 0x02114 /* Broadcast Packets Transmitted Count (High) */ -#define IXGB_MPTCL 0x02118 /* Multicast Packets Transmitted Count (Low) */ -#define IXGB_MPTCH 0x0211C /* Multicast Packets Transmitted Count (High) */ -#define IXGB_UPTCL 0x02120 /* Unicast Packets Transmitted Count (Low) */ -#define IXGB_UPTCH 0x02124 /* Unicast Packets Transmitted Count (High) */ -#define IXGB_VPTCL 0x02128 /* VLAN Packets Transmitted Count (Low) */ -#define IXGB_VPTCH 0x0212C /* VLAN Packets Transmitted Count (High) */ -#define IXGB_JPTCL 0x02130 /* Jumbo Packets Transmitted Count (Low) */ -#define IXGB_JPTCH 0x02134 /* Jumbo Packets Transmitted Count (High) */ -#define IXGB_GOTCL 0x02138 /* Good Octets Transmitted Count (Low) */ -#define IXGB_GOTCH 0x0213C /* Good Octets Transmitted Count (High) */ -#define IXGB_TOTL 0x02140 /* Total Octets Transmitted Count (Low) */ -#define IXGB_TOTH 0x02144 /* Total Octets Transmitted Count (High) */ -#define IXGB_DC 0x02148 /* Defer Count */ -#define IXGB_PLT64C 0x02150 /* Packet Transmitted was less than 64 bytes Count */ -#define IXGB_TSCTC 0x02170 /* TCP Segmentation Context Transmitted Count */ -#define IXGB_TSCTFC 0x02178 /* TCP Segmentation Context Tx Fail Count */ -#define IXGB_IBIC 0x02180 /* Illegal byte during Idle stream count */ -#define IXGB_RFC 0x02188 /* Remote Fault Count */ -#define IXGB_LFC 0x02190 /* Local Fault Count */ -#define IXGB_PFRC 0x02198 /* Pause Frame Receive Count */ -#define IXGB_PFTC 0x021A0 /* Pause Frame Transmit Count */ -#define IXGB_MCFRC 0x021A8 /* MAC Control Frames (non-Pause) Received Count */ -#define IXGB_MCFTC 0x021B0 /* MAC Control Frames (non-Pause) Transmitted Count */ -#define IXGB_XONRXC 0x021B8 /* XON Received Count */ -#define IXGB_XONTXC 0x021C0 /* XON Transmitted Count */ -#define IXGB_XOFFRXC 0x021C8 /* XOFF Received Count */ -#define IXGB_XOFFTXC 0x021D0 /* XOFF Transmitted Count */ -#define IXGB_RJC 0x021D8 /* Receive Jabber Count */ - -/* CTRL0 Bit Masks */ -#define IXGB_CTRL0_LRST 0x00000008 -#define IXGB_CTRL0_JFE 0x00000010 -#define IXGB_CTRL0_XLE 0x00000020 -#define IXGB_CTRL0_MDCS 0x00000040 -#define IXGB_CTRL0_CMDC 0x00000080 -#define IXGB_CTRL0_SDP0 0x00040000 -#define IXGB_CTRL0_SDP1 0x00080000 -#define IXGB_CTRL0_SDP2 0x00100000 -#define IXGB_CTRL0_SDP3 0x00200000 -#define IXGB_CTRL0_SDP0_DIR 0x00400000 -#define IXGB_CTRL0_SDP1_DIR 0x00800000 -#define IXGB_CTRL0_SDP2_DIR 0x01000000 -#define IXGB_CTRL0_SDP3_DIR 0x02000000 -#define IXGB_CTRL0_RST 0x04000000 -#define IXGB_CTRL0_RPE 0x08000000 -#define IXGB_CTRL0_TPE 0x10000000 -#define IXGB_CTRL0_VME 0x40000000 - -/* CTRL1 Bit Masks */ -#define IXGB_CTRL1_GPI0_EN 0x00000001 -#define IXGB_CTRL1_GPI1_EN 0x00000002 -#define IXGB_CTRL1_GPI2_EN 0x00000004 -#define IXGB_CTRL1_GPI3_EN 0x00000008 -#define IXGB_CTRL1_SDP4 0x00000010 -#define IXGB_CTRL1_SDP5 0x00000020 -#define IXGB_CTRL1_SDP6 0x00000040 -#define IXGB_CTRL1_SDP7 0x00000080 -#define IXGB_CTRL1_SDP4_DIR 0x00000100 -#define IXGB_CTRL1_SDP5_DIR 0x00000200 -#define IXGB_CTRL1_SDP6_DIR 0x00000400 -#define IXGB_CTRL1_SDP7_DIR 0x00000800 -#define IXGB_CTRL1_EE_RST 0x00002000 -#define IXGB_CTRL1_RO_DIS 0x00020000 -#define IXGB_CTRL1_PCIXHM_MASK 0x00C00000 -#define IXGB_CTRL1_PCIXHM_1_2 0x00000000 -#define IXGB_CTRL1_PCIXHM_5_8 0x00400000 -#define IXGB_CTRL1_PCIXHM_3_4 0x00800000 -#define IXGB_CTRL1_PCIXHM_7_8 0x00C00000 - -/* STATUS Bit Masks */ -#define IXGB_STATUS_LU 0x00000002 -#define IXGB_STATUS_AIP 0x00000004 -#define IXGB_STATUS_TXOFF 0x00000010 -#define IXGB_STATUS_XAUIME 0x00000020 -#define IXGB_STATUS_RES 0x00000040 -#define IXGB_STATUS_RIS 0x00000080 -#define IXGB_STATUS_RIE 0x00000100 -#define IXGB_STATUS_RLF 0x00000200 -#define IXGB_STATUS_RRF 0x00000400 -#define IXGB_STATUS_PCI_SPD 0x00000800 -#define IXGB_STATUS_BUS64 0x00001000 -#define IXGB_STATUS_PCIX_MODE 0x00002000 -#define IXGB_STATUS_PCIX_SPD_MASK 0x0000C000 -#define IXGB_STATUS_PCIX_SPD_66 0x00000000 -#define IXGB_STATUS_PCIX_SPD_100 0x00004000 -#define IXGB_STATUS_PCIX_SPD_133 0x00008000 -#define IXGB_STATUS_REV_ID_MASK 0x000F0000 -#define IXGB_STATUS_REV_ID_SHIFT 16 - -/* EECD Bit Masks */ -#define IXGB_EECD_SK 0x00000001 -#define IXGB_EECD_CS 0x00000002 -#define IXGB_EECD_DI 0x00000004 -#define IXGB_EECD_DO 0x00000008 -#define IXGB_EECD_FWE_MASK 0x00000030 -#define IXGB_EECD_FWE_DIS 0x00000010 -#define IXGB_EECD_FWE_EN 0x00000020 - -/* MFS */ -#define IXGB_MFS_SHIFT 16 - -/* Interrupt Register Bit Masks (used for ICR, ICS, IMS, and IMC) */ -#define IXGB_INT_TXDW 0x00000001 -#define IXGB_INT_TXQE 0x00000002 -#define IXGB_INT_LSC 0x00000004 -#define IXGB_INT_RXSEQ 0x00000008 -#define IXGB_INT_RXDMT0 0x00000010 -#define IXGB_INT_RXO 0x00000040 -#define IXGB_INT_RXT0 0x00000080 -#define IXGB_INT_AUTOSCAN 0x00000200 -#define IXGB_INT_GPI0 0x00000800 -#define IXGB_INT_GPI1 0x00001000 -#define IXGB_INT_GPI2 0x00002000 -#define IXGB_INT_GPI3 0x00004000 - -/* RCTL Bit Masks */ -#define IXGB_RCTL_RXEN 0x00000002 -#define IXGB_RCTL_SBP 0x00000004 -#define IXGB_RCTL_UPE 0x00000008 -#define IXGB_RCTL_MPE 0x00000010 -#define IXGB_RCTL_RDMTS_MASK 0x00000300 -#define IXGB_RCTL_RDMTS_1_2 0x00000000 -#define IXGB_RCTL_RDMTS_1_4 0x00000100 -#define IXGB_RCTL_RDMTS_1_8 0x00000200 -#define IXGB_RCTL_MO_MASK 0x00003000 -#define IXGB_RCTL_MO_47_36 0x00000000 -#define IXGB_RCTL_MO_46_35 0x00001000 -#define IXGB_RCTL_MO_45_34 0x00002000 -#define IXGB_RCTL_MO_43_32 0x00003000 -#define IXGB_RCTL_MO_SHIFT 12 -#define IXGB_RCTL_BAM 0x00008000 -#define IXGB_RCTL_BSIZE_MASK 0x00030000 -#define IXGB_RCTL_BSIZE_2048 0x00000000 -#define IXGB_RCTL_BSIZE_4096 0x00010000 -#define IXGB_RCTL_BSIZE_8192 0x00020000 -#define IXGB_RCTL_BSIZE_16384 0x00030000 -#define IXGB_RCTL_VFE 0x00040000 -#define IXGB_RCTL_CFIEN 0x00080000 -#define IXGB_RCTL_CFI 0x00100000 -#define IXGB_RCTL_RPDA_MASK 0x00600000 -#define IXGB_RCTL_RPDA_MC_MAC 0x00000000 -#define IXGB_RCTL_MC_ONLY 0x00400000 -#define IXGB_RCTL_CFF 0x00800000 -#define IXGB_RCTL_SECRC 0x04000000 -#define IXGB_RDT_FPDB 0x80000000 - -#define IXGB_RCTL_IDLE_RX_UNIT 0 - -/* FCRTL Bit Masks */ -#define IXGB_FCRTL_XONE 0x80000000 - -/* RXDCTL Bit Masks */ -#define IXGB_RXDCTL_PTHRESH_MASK 0x000001FF -#define IXGB_RXDCTL_PTHRESH_SHIFT 0 -#define IXGB_RXDCTL_HTHRESH_MASK 0x0003FE00 -#define IXGB_RXDCTL_HTHRESH_SHIFT 9 -#define IXGB_RXDCTL_WTHRESH_MASK 0x07FC0000 -#define IXGB_RXDCTL_WTHRESH_SHIFT 18 - -/* RAIDC Bit Masks */ -#define IXGB_RAIDC_HIGHTHRS_MASK 0x0000003F -#define IXGB_RAIDC_DELAY_MASK 0x000FF800 -#define IXGB_RAIDC_DELAY_SHIFT 11 -#define IXGB_RAIDC_POLL_MASK 0x1FF00000 -#define IXGB_RAIDC_POLL_SHIFT 20 -#define IXGB_RAIDC_RXT_GATE 0x40000000 -#define IXGB_RAIDC_EN 0x80000000 - -#define IXGB_RAIDC_POLL_1000_INTERRUPTS_PER_SECOND 1220 -#define IXGB_RAIDC_POLL_5000_INTERRUPTS_PER_SECOND 244 -#define IXGB_RAIDC_POLL_10000_INTERRUPTS_PER_SECOND 122 -#define IXGB_RAIDC_POLL_20000_INTERRUPTS_PER_SECOND 61 - -/* RXCSUM Bit Masks */ -#define IXGB_RXCSUM_IPOFL 0x00000100 -#define IXGB_RXCSUM_TUOFL 0x00000200 - -/* RAH Bit Masks */ -#define IXGB_RAH_ASEL_MASK 0x00030000 -#define IXGB_RAH_ASEL_DEST 0x00000000 -#define IXGB_RAH_ASEL_SRC 0x00010000 -#define IXGB_RAH_AV 0x80000000 - -/* TCTL Bit Masks */ -#define IXGB_TCTL_TCE 0x00000001 -#define IXGB_TCTL_TXEN 0x00000002 -#define IXGB_TCTL_TPDE 0x00000004 - -#define IXGB_TCTL_IDLE_TX_UNIT 0 - -/* TXDCTL Bit Masks */ -#define IXGB_TXDCTL_PTHRESH_MASK 0x0000007F -#define IXGB_TXDCTL_HTHRESH_MASK 0x00007F00 -#define IXGB_TXDCTL_HTHRESH_SHIFT 8 -#define IXGB_TXDCTL_WTHRESH_MASK 0x007F0000 -#define IXGB_TXDCTL_WTHRESH_SHIFT 16 - -/* TSPMT Bit Masks */ -#define IXGB_TSPMT_TSMT_MASK 0x0000FFFF -#define IXGB_TSPMT_TSPBP_MASK 0xFFFF0000 -#define IXGB_TSPMT_TSPBP_SHIFT 16 - -/* PAP Bit Masks */ -#define IXGB_PAP_TXPC_MASK 0x0000FFFF -#define IXGB_PAP_TXPV_MASK 0x000F0000 -#define IXGB_PAP_TXPV_10G 0x00000000 -#define IXGB_PAP_TXPV_1G 0x00010000 -#define IXGB_PAP_TXPV_2G 0x00020000 -#define IXGB_PAP_TXPV_3G 0x00030000 -#define IXGB_PAP_TXPV_4G 0x00040000 -#define IXGB_PAP_TXPV_5G 0x00050000 -#define IXGB_PAP_TXPV_6G 0x00060000 -#define IXGB_PAP_TXPV_7G 0x00070000 -#define IXGB_PAP_TXPV_8G 0x00080000 -#define IXGB_PAP_TXPV_9G 0x00090000 -#define IXGB_PAP_TXPV_WAN 0x000F0000 - -/* PCSC1 Bit Masks */ -#define IXGB_PCSC1_LOOPBACK 0x00004000 - -/* PCSC2 Bit Masks */ -#define IXGB_PCSC2_PCS_TYPE_MASK 0x00000003 -#define IXGB_PCSC2_PCS_TYPE_10GBX 0x00000001 - -/* PCSS1 Bit Masks */ -#define IXGB_PCSS1_LOCAL_FAULT 0x00000080 -#define IXGB_PCSS1_RX_LINK_STATUS 0x00000004 - -/* PCSS2 Bit Masks */ -#define IXGB_PCSS2_DEV_PRES_MASK 0x0000C000 -#define IXGB_PCSS2_DEV_PRES 0x00004000 -#define IXGB_PCSS2_TX_LF 0x00000800 -#define IXGB_PCSS2_RX_LF 0x00000400 -#define IXGB_PCSS2_10GBW 0x00000004 -#define IXGB_PCSS2_10GBX 0x00000002 -#define IXGB_PCSS2_10GBR 0x00000001 - -/* XPCSS Bit Masks */ -#define IXGB_XPCSS_ALIGN_STATUS 0x00001000 -#define IXGB_XPCSS_PATTERN_TEST 0x00000800 -#define IXGB_XPCSS_LANE_3_SYNC 0x00000008 -#define IXGB_XPCSS_LANE_2_SYNC 0x00000004 -#define IXGB_XPCSS_LANE_1_SYNC 0x00000002 -#define IXGB_XPCSS_LANE_0_SYNC 0x00000001 - -/* XPCSTC Bit Masks */ -#define IXGB_XPCSTC_BERT_TRIG 0x00200000 -#define IXGB_XPCSTC_BERT_SST 0x00100000 -#define IXGB_XPCSTC_BERT_PSZ_MASK 0x000C0000 -#define IXGB_XPCSTC_BERT_PSZ_SHIFT 17 -#define IXGB_XPCSTC_BERT_PSZ_INF 0x00000003 -#define IXGB_XPCSTC_BERT_PSZ_68 0x00000001 -#define IXGB_XPCSTC_BERT_PSZ_1028 0x00000000 - -/* MSCA bit Masks */ -/* New Protocol Address */ -#define IXGB_MSCA_NP_ADDR_MASK 0x0000FFFF -#define IXGB_MSCA_NP_ADDR_SHIFT 0 -/* Either Device Type or Register Address,depending on ST_CODE */ -#define IXGB_MSCA_DEV_TYPE_MASK 0x001F0000 -#define IXGB_MSCA_DEV_TYPE_SHIFT 16 -#define IXGB_MSCA_PHY_ADDR_MASK 0x03E00000 -#define IXGB_MSCA_PHY_ADDR_SHIFT 21 -#define IXGB_MSCA_OP_CODE_MASK 0x0C000000 -/* OP_CODE == 00, Address cycle, New Protocol */ -/* OP_CODE == 01, Write operation */ -/* OP_CODE == 10, Read operation */ -/* OP_CODE == 11, Read, auto increment, New Protocol */ -#define IXGB_MSCA_ADDR_CYCLE 0x00000000 -#define IXGB_MSCA_WRITE 0x04000000 -#define IXGB_MSCA_READ 0x08000000 -#define IXGB_MSCA_READ_AUTOINC 0x0C000000 -#define IXGB_MSCA_OP_CODE_SHIFT 26 -#define IXGB_MSCA_ST_CODE_MASK 0x30000000 -/* ST_CODE == 00, New Protocol */ -/* ST_CODE == 01, Old Protocol */ -#define IXGB_MSCA_NEW_PROTOCOL 0x00000000 -#define IXGB_MSCA_OLD_PROTOCOL 0x10000000 -#define IXGB_MSCA_ST_CODE_SHIFT 28 -/* Initiate command, self-clearing when command completes */ -#define IXGB_MSCA_MDI_COMMAND 0x40000000 -/*MDI In Progress Enable. */ -#define IXGB_MSCA_MDI_IN_PROG_EN 0x80000000 - -/* MSRWD bit masks */ -#define IXGB_MSRWD_WRITE_DATA_MASK 0x0000FFFF -#define IXGB_MSRWD_WRITE_DATA_SHIFT 0 -#define IXGB_MSRWD_READ_DATA_MASK 0xFFFF0000 -#define IXGB_MSRWD_READ_DATA_SHIFT 16 - -/* Definitions for the optics devices on the MDIO bus. */ -#define IXGB_PHY_ADDRESS 0x0 /* Single PHY, multiple "Devices" */ - -#define MDIO_PMA_PMD_XPAK_VENDOR_NAME 0x803A /* XPAK/XENPAK devices only */ - -/* Vendor-specific MDIO registers */ -#define G6XXX_PMA_PMD_VS1 0xC001 /* Vendor-specific register */ -#define G6XXX_XGXS_XAUI_VS2 0x18 /* Vendor-specific register */ - -#define G6XXX_PMA_PMD_VS1_PLL_RESET 0x80 -#define G6XXX_PMA_PMD_VS1_REMOVE_PLL_RESET 0x00 -#define G6XXX_XGXS_XAUI_VS2_INPUT_MASK 0x0F /* XAUI lanes synchronized */ - -/* Layout of a single receive descriptor. The controller assumes that this - * structure is packed into 16 bytes, which is a safe assumption with most - * compilers. However, some compilers may insert padding between the fields, - * in which case the structure must be packed in some compiler-specific - * manner. */ -struct ixgb_rx_desc { - __le64 buff_addr; - __le16 length; - __le16 reserved; - u8 status; - u8 errors; - __le16 special; -}; - -#define IXGB_RX_DESC_STATUS_DD 0x01 -#define IXGB_RX_DESC_STATUS_EOP 0x02 -#define IXGB_RX_DESC_STATUS_IXSM 0x04 -#define IXGB_RX_DESC_STATUS_VP 0x08 -#define IXGB_RX_DESC_STATUS_TCPCS 0x20 -#define IXGB_RX_DESC_STATUS_IPCS 0x40 -#define IXGB_RX_DESC_STATUS_PIF 0x80 - -#define IXGB_RX_DESC_ERRORS_CE 0x01 -#define IXGB_RX_DESC_ERRORS_SE 0x02 -#define IXGB_RX_DESC_ERRORS_P 0x08 -#define IXGB_RX_DESC_ERRORS_TCPE 0x20 -#define IXGB_RX_DESC_ERRORS_IPE 0x40 -#define IXGB_RX_DESC_ERRORS_RXE 0x80 - -#define IXGB_RX_DESC_SPECIAL_VLAN_MASK 0x0FFF /* VLAN ID is in lower 12 bits */ -#define IXGB_RX_DESC_SPECIAL_PRI_MASK 0xE000 /* Priority is in upper 3 bits */ -#define IXGB_RX_DESC_SPECIAL_PRI_SHIFT 0x000D /* Priority is in upper 3 of 16 */ - -/* Layout of a single transmit descriptor. The controller assumes that this - * structure is packed into 16 bytes, which is a safe assumption with most - * compilers. However, some compilers may insert padding between the fields, - * in which case the structure must be packed in some compiler-specific - * manner. */ -struct ixgb_tx_desc { - __le64 buff_addr; - __le32 cmd_type_len; - u8 status; - u8 popts; - __le16 vlan; -}; - -#define IXGB_TX_DESC_LENGTH_MASK 0x000FFFFF -#define IXGB_TX_DESC_TYPE_MASK 0x00F00000 -#define IXGB_TX_DESC_TYPE_SHIFT 20 -#define IXGB_TX_DESC_CMD_MASK 0xFF000000 -#define IXGB_TX_DESC_CMD_SHIFT 24 -#define IXGB_TX_DESC_CMD_EOP 0x01000000 -#define IXGB_TX_DESC_CMD_TSE 0x04000000 -#define IXGB_TX_DESC_CMD_RS 0x08000000 -#define IXGB_TX_DESC_CMD_VLE 0x40000000 -#define IXGB_TX_DESC_CMD_IDE 0x80000000 - -#define IXGB_TX_DESC_TYPE 0x00100000 - -#define IXGB_TX_DESC_STATUS_DD 0x01 - -#define IXGB_TX_DESC_POPTS_IXSM 0x01 -#define IXGB_TX_DESC_POPTS_TXSM 0x02 -#define IXGB_TX_DESC_SPECIAL_PRI_SHIFT IXGB_RX_DESC_SPECIAL_PRI_SHIFT /* Priority is in upper 3 of 16 */ - -struct ixgb_context_desc { - u8 ipcss; - u8 ipcso; - __le16 ipcse; - u8 tucss; - u8 tucso; - __le16 tucse; - __le32 cmd_type_len; - u8 status; - u8 hdr_len; - __le16 mss; -}; - -#define IXGB_CONTEXT_DESC_CMD_TCP 0x01000000 -#define IXGB_CONTEXT_DESC_CMD_IP 0x02000000 -#define IXGB_CONTEXT_DESC_CMD_TSE 0x04000000 -#define IXGB_CONTEXT_DESC_CMD_RS 0x08000000 -#define IXGB_CONTEXT_DESC_CMD_IDE 0x80000000 - -#define IXGB_CONTEXT_DESC_TYPE 0x00000000 - -#define IXGB_CONTEXT_DESC_STATUS_DD 0x01 - -/* Filters */ -#define IXGB_MC_TBL_SIZE 128 /* Multicast Filter Table (4096 bits) */ -#define IXGB_VLAN_FILTER_TBL_SIZE 128 /* VLAN Filter Table (4096 bits) */ -#define IXGB_RAR_ENTRIES 3 /* Number of entries in Rx Address array */ - -#define IXGB_MEMORY_REGISTER_BASE_ADDRESS 0 -#define ENET_HEADER_SIZE 14 -#define ENET_FCS_LENGTH 4 -#define IXGB_MAX_NUM_MULTICAST_ADDRESSES 128 -#define IXGB_MIN_ENET_FRAME_SIZE_WITHOUT_FCS 60 -#define IXGB_MAX_ENET_FRAME_SIZE_WITHOUT_FCS 1514 -#define IXGB_MAX_JUMBO_FRAME_SIZE 0x3F00 - -/* Phy Addresses */ -#define IXGB_OPTICAL_PHY_ADDR 0x0 /* Optical Module phy address */ -#define IXGB_XAUII_PHY_ADDR 0x1 /* Xauii transceiver phy address */ -#define IXGB_DIAG_PHY_ADDR 0x1F /* Diagnostic Device phy address */ - -/* This structure takes a 64k flash and maps it for identification commands */ -struct ixgb_flash_buffer { - u8 manufacturer_id; - u8 device_id; - u8 filler1[0x2AA8]; - u8 cmd2; - u8 filler2[0x2AAA]; - u8 cmd1; - u8 filler3[0xAAAA]; -}; - -/* Flow control parameters */ -struct ixgb_fc { - u32 high_water; /* Flow Control High-water */ - u32 low_water; /* Flow Control Low-water */ - u16 pause_time; /* Flow Control Pause timer */ - bool send_xon; /* Flow control send XON */ - ixgb_fc_type type; /* Type of flow control */ -}; - -/* The historical defaults for the flow control values are given below. */ -#define FC_DEFAULT_HI_THRESH (0x8000) /* 32KB */ -#define FC_DEFAULT_LO_THRESH (0x4000) /* 16KB */ -#define FC_DEFAULT_TX_TIMER (0x100) /* ~130 us */ - -/* Phy definitions */ -#define IXGB_MAX_PHY_REG_ADDRESS 0xFFFF -#define IXGB_MAX_PHY_ADDRESS 31 -#define IXGB_MAX_PHY_DEV_TYPE 31 - -/* Bus parameters */ -struct ixgb_bus { - ixgb_bus_speed speed; - ixgb_bus_width width; - ixgb_bus_type type; -}; - -struct ixgb_hw { - u8 __iomem *hw_addr;/* Base Address of the hardware */ - void *back; /* Pointer to OS-dependent struct */ - struct ixgb_fc fc; /* Flow control parameters */ - struct ixgb_bus bus; /* Bus parameters */ - u32 phy_id; /* Phy Identifier */ - u32 phy_addr; /* XGMII address of Phy */ - ixgb_mac_type mac_type; /* Identifier for MAC controller */ - ixgb_phy_type phy_type; /* Transceiver/phy identifier */ - u32 max_frame_size; /* Maximum frame size supported */ - u32 mc_filter_type; /* Multicast filter hash type */ - u32 num_mc_addrs; /* Number of current Multicast addrs */ - u8 curr_mac_addr[ETH_ALEN]; /* Individual address currently programmed in MAC */ - u32 num_tx_desc; /* Number of Transmit descriptors */ - u32 num_rx_desc; /* Number of Receive descriptors */ - u32 rx_buffer_size; /* Size of Receive buffer */ - bool link_up; /* true if link is valid */ - bool adapter_stopped; /* State of adapter */ - u16 device_id; /* device id from PCI configuration space */ - u16 vendor_id; /* vendor id from PCI configuration space */ - u8 revision_id; /* revision id from PCI configuration space */ - u16 subsystem_vendor_id; /* subsystem vendor id from PCI configuration space */ - u16 subsystem_id; /* subsystem id from PCI configuration space */ - u32 bar0; /* Base Address registers */ - u32 bar1; - u32 bar2; - u32 bar3; - u16 pci_cmd_word; /* PCI command register id from PCI configuration space */ - __le16 eeprom[IXGB_EEPROM_SIZE]; /* EEPROM contents read at init time */ - unsigned long io_base; /* Our I/O mapped location */ - u32 lastLFC; - u32 lastRFC; -}; - -/* Statistics reported by the hardware */ -struct ixgb_hw_stats { - u64 tprl; - u64 tprh; - u64 gprcl; - u64 gprch; - u64 bprcl; - u64 bprch; - u64 mprcl; - u64 mprch; - u64 uprcl; - u64 uprch; - u64 vprcl; - u64 vprch; - u64 jprcl; - u64 jprch; - u64 gorcl; - u64 gorch; - u64 torl; - u64 torh; - u64 rnbc; - u64 ruc; - u64 roc; - u64 rlec; - u64 crcerrs; - u64 icbc; - u64 ecbc; - u64 mpc; - u64 tptl; - u64 tpth; - u64 gptcl; - u64 gptch; - u64 bptcl; - u64 bptch; - u64 mptcl; - u64 mptch; - u64 uptcl; - u64 uptch; - u64 vptcl; - u64 vptch; - u64 jptcl; - u64 jptch; - u64 gotcl; - u64 gotch; - u64 totl; - u64 toth; - u64 dc; - u64 plt64c; - u64 tsctc; - u64 tsctfc; - u64 ibic; - u64 rfc; - u64 lfc; - u64 pfrc; - u64 pftc; - u64 mcfrc; - u64 mcftc; - u64 xonrxc; - u64 xontxc; - u64 xoffrxc; - u64 xofftxc; - u64 rjc; -}; - -/* Function Prototypes */ -bool ixgb_adapter_stop(struct ixgb_hw *hw); -bool ixgb_init_hw(struct ixgb_hw *hw); -bool ixgb_adapter_start(struct ixgb_hw *hw); -void ixgb_check_for_link(struct ixgb_hw *hw); -bool ixgb_check_for_bad_link(struct ixgb_hw *hw); - -void ixgb_rar_set(struct ixgb_hw *hw, const u8 *addr, u32 index); - -/* Filters (multicast, vlan, receive) */ -void ixgb_mc_addr_list_update(struct ixgb_hw *hw, u8 *mc_addr_list, - u32 mc_addr_count, u32 pad); - -/* Vfta functions */ -void ixgb_write_vfta(struct ixgb_hw *hw, u32 offset, u32 value); - -/* Access functions to eeprom data */ -void ixgb_get_ee_mac_addr(struct ixgb_hw *hw, u8 *mac_addr); -u32 ixgb_get_ee_pba_number(struct ixgb_hw *hw); -u16 ixgb_get_ee_device_id(struct ixgb_hw *hw); -bool ixgb_get_eeprom_data(struct ixgb_hw *hw); -__le16 ixgb_get_eeprom_word(struct ixgb_hw *hw, u16 index); - -/* Everything else */ -void ixgb_led_on(struct ixgb_hw *hw); -void ixgb_led_off(struct ixgb_hw *hw); -void ixgb_write_pci_cfg(struct ixgb_hw *hw, - u32 reg, - u16 * value); - - -#endif /* _IXGB_HW_H_ */ diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ids.h b/drivers/net/ethernet/intel/ixgb/ixgb_ids.h deleted file mode 100644 index 9695b8215f01..000000000000 --- a/drivers/net/ethernet/intel/ixgb/ixgb_ids.h +++ /dev/null @@ -1,23 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 1999 - 2008 Intel Corporation. */ - -#ifndef _IXGB_IDS_H_ -#define _IXGB_IDS_H_ - -/********************************************************************** -** The Device and Vendor IDs for 10 Gigabit MACs -**********************************************************************/ - -#define IXGB_DEVICE_ID_82597EX 0x1048 -#define IXGB_DEVICE_ID_82597EX_SR 0x1A48 -#define IXGB_DEVICE_ID_82597EX_LR 0x1B48 -#define IXGB_SUBDEVICE_ID_A11F 0xA11F -#define IXGB_SUBDEVICE_ID_A01F 0xA01F - -#define IXGB_DEVICE_ID_82597EX_CX4 0x109E -#define IXGB_SUBDEVICE_ID_A00C 0xA00C -#define IXGB_SUBDEVICE_ID_A01C 0xA01C -#define IXGB_SUBDEVICE_ID_7036 0x7036 - -#endif /* #ifndef _IXGB_IDS_H_ */ -/* End of File */ diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c deleted file mode 100644 index b4d47e7a76c8..000000000000 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ /dev/null @@ -1,2285 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2008 Intel Corporation. */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/prefetch.h> -#include "ixgb.h" - -char ixgb_driver_name[] = "ixgb"; -static char ixgb_driver_string[] = "Intel(R) PRO/10GbE Network Driver"; - -static const char ixgb_copyright[] = "Copyright (c) 1999-2008 Intel Corporation."; - -#define IXGB_CB_LENGTH 256 -static unsigned int copybreak __read_mostly = IXGB_CB_LENGTH; -module_param(copybreak, uint, 0644); -MODULE_PARM_DESC(copybreak, - "Maximum size of packet that is copied to a new buffer on receive"); - -/* ixgb_pci_tbl - PCI Device ID Table - * - * Wildcard entries (PCI_ANY_ID) should come last - * Last entry must be all 0s - * - * { Vendor ID, Device ID, SubVendor ID, SubDevice ID, - * Class, Class Mask, private data (not used) } - */ -static const struct pci_device_id ixgb_pci_tbl[] = { - {PCI_VENDOR_ID_INTEL, IXGB_DEVICE_ID_82597EX, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, - {PCI_VENDOR_ID_INTEL, IXGB_DEVICE_ID_82597EX_CX4, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, - {PCI_VENDOR_ID_INTEL, IXGB_DEVICE_ID_82597EX_SR, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, - {PCI_VENDOR_ID_INTEL, IXGB_DEVICE_ID_82597EX_LR, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0}, - - /* required last entry */ - {0,} -}; - -MODULE_DEVICE_TABLE(pci, ixgb_pci_tbl); - -/* Local Function Prototypes */ -static int ixgb_init_module(void); -static void ixgb_exit_module(void); -static int ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent); -static void ixgb_remove(struct pci_dev *pdev); -static int ixgb_sw_init(struct ixgb_adapter *adapter); -static int ixgb_open(struct net_device *netdev); -static int ixgb_close(struct net_device *netdev); -static void ixgb_configure_tx(struct ixgb_adapter *adapter); -static void ixgb_configure_rx(struct ixgb_adapter *adapter); -static void ixgb_setup_rctl(struct ixgb_adapter *adapter); -static void ixgb_clean_tx_ring(struct ixgb_adapter *adapter); -static void ixgb_clean_rx_ring(struct ixgb_adapter *adapter); -static void ixgb_set_multi(struct net_device *netdev); -static void ixgb_watchdog(struct timer_list *t); -static netdev_tx_t ixgb_xmit_frame(struct sk_buff *skb, - struct net_device *netdev); -static int ixgb_change_mtu(struct net_device *netdev, int new_mtu); -static int ixgb_set_mac(struct net_device *netdev, void *p); -static irqreturn_t ixgb_intr(int irq, void *data); -static bool ixgb_clean_tx_irq(struct ixgb_adapter *adapter); - -static int ixgb_clean(struct napi_struct *, int); -static bool ixgb_clean_rx_irq(struct ixgb_adapter *, int *, int); -static void ixgb_alloc_rx_buffers(struct ixgb_adapter *, int); - -static void ixgb_tx_timeout(struct net_device *dev, unsigned int txqueue); -static void ixgb_tx_timeout_task(struct work_struct *work); - -static void ixgb_vlan_strip_enable(struct ixgb_adapter *adapter); -static void ixgb_vlan_strip_disable(struct ixgb_adapter *adapter); -static int ixgb_vlan_rx_add_vid(struct net_device *netdev, - __be16 proto, u16 vid); -static int ixgb_vlan_rx_kill_vid(struct net_device *netdev, - __be16 proto, u16 vid); -static void ixgb_restore_vlan(struct ixgb_adapter *adapter); - -static pci_ers_result_t ixgb_io_error_detected (struct pci_dev *pdev, - pci_channel_state_t state); -static pci_ers_result_t ixgb_io_slot_reset (struct pci_dev *pdev); -static void ixgb_io_resume (struct pci_dev *pdev); - -static const struct pci_error_handlers ixgb_err_handler = { - .error_detected = ixgb_io_error_detected, - .slot_reset = ixgb_io_slot_reset, - .resume = ixgb_io_resume, -}; - -static struct pci_driver ixgb_driver = { - .name = ixgb_driver_name, - .id_table = ixgb_pci_tbl, - .probe = ixgb_probe, - .remove = ixgb_remove, - .err_handler = &ixgb_err_handler -}; - -MODULE_AUTHOR("Intel Corporation, <[email protected]>"); -MODULE_DESCRIPTION("Intel(R) PRO/10GbE Network Driver"); -MODULE_LICENSE("GPL v2"); - -#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK) -static int debug = -1; -module_param(debug, int, 0); -MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); - -/** - * ixgb_init_module - Driver Registration Routine - * - * ixgb_init_module is the first routine called when the driver is - * loaded. All it does is register with the PCI subsystem. - **/ - -static int __init -ixgb_init_module(void) -{ - pr_info("%s\n", ixgb_driver_string); - pr_info("%s\n", ixgb_copyright); - - return pci_register_driver(&ixgb_driver); -} - -module_init(ixgb_init_module); - -/** - * ixgb_exit_module - Driver Exit Cleanup Routine - * - * ixgb_exit_module is called just before the driver is removed - * from memory. - **/ - -static void __exit -ixgb_exit_module(void) -{ - pci_unregister_driver(&ixgb_driver); -} - -module_exit(ixgb_exit_module); - -/** - * ixgb_irq_disable - Mask off interrupt generation on the NIC - * @adapter: board private structure - **/ - -static void -ixgb_irq_disable(struct ixgb_adapter *adapter) -{ - IXGB_WRITE_REG(&adapter->hw, IMC, ~0); - IXGB_WRITE_FLUSH(&adapter->hw); - synchronize_irq(adapter->pdev->irq); -} - -/** - * ixgb_irq_enable - Enable default interrupt generation settings - * @adapter: board private structure - **/ - -static void -ixgb_irq_enable(struct ixgb_adapter *adapter) -{ - u32 val = IXGB_INT_RXT0 | IXGB_INT_RXDMT0 | - IXGB_INT_TXDW | IXGB_INT_LSC; - if (adapter->hw.subsystem_vendor_id == PCI_VENDOR_ID_SUN) - val |= IXGB_INT_GPI0; - IXGB_WRITE_REG(&adapter->hw, IMS, val); - IXGB_WRITE_FLUSH(&adapter->hw); -} - -int -ixgb_up(struct ixgb_adapter *adapter) -{ - struct net_device *netdev = adapter->netdev; - int err, irq_flags = IRQF_SHARED; - int max_frame = netdev->mtu + ENET_HEADER_SIZE + ENET_FCS_LENGTH; - struct ixgb_hw *hw = &adapter->hw; - - /* hardware has been reset, we need to reload some things */ - - ixgb_rar_set(hw, netdev->dev_addr, 0); - ixgb_set_multi(netdev); - - ixgb_restore_vlan(adapter); - - ixgb_configure_tx(adapter); - ixgb_setup_rctl(adapter); - ixgb_configure_rx(adapter); - ixgb_alloc_rx_buffers(adapter, IXGB_DESC_UNUSED(&adapter->rx_ring)); - - /* disable interrupts and get the hardware into a known state */ - IXGB_WRITE_REG(&adapter->hw, IMC, 0xffffffff); - - /* only enable MSI if bus is in PCI-X mode */ - if (IXGB_READ_REG(&adapter->hw, STATUS) & IXGB_STATUS_PCIX_MODE) { - err = pci_enable_msi(adapter->pdev); - if (!err) { - adapter->have_msi = true; - irq_flags = 0; - } - /* proceed to try to request regular interrupt */ - } - - err = request_irq(adapter->pdev->irq, ixgb_intr, irq_flags, - netdev->name, netdev); - if (err) { - if (adapter->have_msi) - pci_disable_msi(adapter->pdev); - netif_err(adapter, probe, adapter->netdev, - "Unable to allocate interrupt Error: %d\n", err); - return err; - } - - if ((hw->max_frame_size != max_frame) || - (hw->max_frame_size != - (IXGB_READ_REG(hw, MFS) >> IXGB_MFS_SHIFT))) { - - hw->max_frame_size = max_frame; - - IXGB_WRITE_REG(hw, MFS, hw->max_frame_size << IXGB_MFS_SHIFT); - - if (hw->max_frame_size > - IXGB_MAX_ENET_FRAME_SIZE_WITHOUT_FCS + ENET_FCS_LENGTH) { - u32 ctrl0 = IXGB_READ_REG(hw, CTRL0); - - if (!(ctrl0 & IXGB_CTRL0_JFE)) { - ctrl0 |= IXGB_CTRL0_JFE; - IXGB_WRITE_REG(hw, CTRL0, ctrl0); - } - } - } - - clear_bit(__IXGB_DOWN, &adapter->flags); - - napi_enable(&adapter->napi); - ixgb_irq_enable(adapter); - - netif_wake_queue(netdev); - - mod_timer(&adapter->watchdog_timer, jiffies); - - return 0; -} - -void -ixgb_down(struct ixgb_adapter *adapter, bool kill_watchdog) -{ - struct net_device *netdev = adapter->netdev; - - /* prevent the interrupt handler from restarting watchdog */ - set_bit(__IXGB_DOWN, &adapter->flags); - - netif_carrier_off(netdev); - - napi_disable(&adapter->napi); - /* waiting for NAPI to complete can re-enable interrupts */ - ixgb_irq_disable(adapter); - free_irq(adapter->pdev->irq, netdev); - - if (adapter->have_msi) - pci_disable_msi(adapter->pdev); - - if (kill_watchdog) - del_timer_sync(&adapter->watchdog_timer); - - adapter->link_speed = 0; - adapter->link_duplex = 0; - netif_stop_queue(netdev); - - ixgb_reset(adapter); - ixgb_clean_tx_ring(adapter); - ixgb_clean_rx_ring(adapter); -} - -void -ixgb_reset(struct ixgb_adapter *adapter) -{ - struct ixgb_hw *hw = &adapter->hw; - - ixgb_adapter_stop(hw); - if (!ixgb_init_hw(hw)) - netif_err(adapter, probe, adapter->netdev, "ixgb_init_hw failed\n"); - - /* restore frame size information */ - IXGB_WRITE_REG(hw, MFS, hw->max_frame_size << IXGB_MFS_SHIFT); - if (hw->max_frame_size > - IXGB_MAX_ENET_FRAME_SIZE_WITHOUT_FCS + ENET_FCS_LENGTH) { - u32 ctrl0 = IXGB_READ_REG(hw, CTRL0); - if (!(ctrl0 & IXGB_CTRL0_JFE)) { - ctrl0 |= IXGB_CTRL0_JFE; - IXGB_WRITE_REG(hw, CTRL0, ctrl0); - } - } -} - -static netdev_features_t -ixgb_fix_features(struct net_device *netdev, netdev_features_t features) -{ - /* - * Tx VLAN insertion does not work per HW design when Rx stripping is - * disabled. - */ - if (!(features & NETIF_F_HW_VLAN_CTAG_RX)) - features &= ~NETIF_F_HW_VLAN_CTAG_TX; - - return features; -} - -static int -ixgb_set_features(struct net_device *netdev, netdev_features_t features) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - netdev_features_t changed = features ^ netdev->features; - - if (!(changed & (NETIF_F_RXCSUM|NETIF_F_HW_VLAN_CTAG_RX))) - return 0; - - adapter->rx_csum = !!(features & NETIF_F_RXCSUM); - - if (netif_running(netdev)) { - ixgb_down(adapter, true); - ixgb_up(adapter); - ixgb_set_speed_duplex(netdev); - } else - ixgb_reset(adapter); - - return 0; -} - - -static const struct net_device_ops ixgb_netdev_ops = { - .ndo_open = ixgb_open, - .ndo_stop = ixgb_close, - .ndo_start_xmit = ixgb_xmit_frame, - .ndo_set_rx_mode = ixgb_set_multi, - .ndo_validate_addr = eth_validate_addr, - .ndo_set_mac_address = ixgb_set_mac, - .ndo_change_mtu = ixgb_change_mtu, - .ndo_tx_timeout = ixgb_tx_timeout, - .ndo_vlan_rx_add_vid = ixgb_vlan_rx_add_vid, - .ndo_vlan_rx_kill_vid = ixgb_vlan_rx_kill_vid, - .ndo_fix_features = ixgb_fix_features, - .ndo_set_features = ixgb_set_features, -}; - -/** - * ixgb_probe - Device Initialization Routine - * @pdev: PCI device information struct - * @ent: entry in ixgb_pci_tbl - * - * Returns 0 on success, negative on failure - * - * ixgb_probe initializes an adapter identified by a pci_dev structure. - * The OS initialization, configuring of the adapter private structure, - * and a hardware reset occur. - **/ - -static int -ixgb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) -{ - struct net_device *netdev = NULL; - struct ixgb_adapter *adapter; - static int cards_found = 0; - u8 addr[ETH_ALEN]; - int i; - int err; - - err = pci_enable_device(pdev); - if (err) - return err; - - err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64)); - if (err) { - pr_err("No usable DMA configuration, aborting\n"); - goto err_dma_mask; - } - - err = pci_request_regions(pdev, ixgb_driver_name); - if (err) - goto err_request_regions; - - pci_set_master(pdev); - - netdev = alloc_etherdev(sizeof(struct ixgb_adapter)); - if (!netdev) { - err = -ENOMEM; - goto err_alloc_etherdev; - } - - SET_NETDEV_DEV(netdev, &pdev->dev); - - pci_set_drvdata(pdev, netdev); - adapter = netdev_priv(netdev); - adapter->netdev = netdev; - adapter->pdev = pdev; - adapter->hw.back = adapter; - adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE); - - adapter->hw.hw_addr = pci_ioremap_bar(pdev, BAR_0); - if (!adapter->hw.hw_addr) { - err = -EIO; - goto err_ioremap; - } - - for (i = BAR_1; i < PCI_STD_NUM_BARS; i++) { - if (pci_resource_len(pdev, i) == 0) - continue; - if (pci_resource_flags(pdev, i) & IORESOURCE_IO) { - adapter->hw.io_base = pci_resource_start(pdev, i); - break; - } - } - - netdev->netdev_ops = &ixgb_netdev_ops; - ixgb_set_ethtool_ops(netdev); - netdev->watchdog_timeo = 5 * HZ; - netif_napi_add(netdev, &adapter->napi, ixgb_clean); - - strncpy(netdev->name, pci_name(pdev), sizeof(netdev->name) - 1); - - adapter->bd_number = cards_found; - adapter->link_speed = 0; - adapter->link_duplex = 0; - - /* setup the private structure */ - - err = ixgb_sw_init(adapter); - if (err) - goto err_sw_init; - - netdev->hw_features = NETIF_F_SG | - NETIF_F_TSO | - NETIF_F_HW_CSUM | - NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_CTAG_RX; - netdev->features = netdev->hw_features | - NETIF_F_HW_VLAN_CTAG_FILTER; - netdev->hw_features |= NETIF_F_RXCSUM; - - netdev->features |= NETIF_F_HIGHDMA; - netdev->vlan_features |= NETIF_F_HIGHDMA; - - /* MTU range: 68 - 16114 */ - netdev->min_mtu = ETH_MIN_MTU; - netdev->max_mtu = IXGB_MAX_JUMBO_FRAME_SIZE - ETH_HLEN; - - /* make sure the EEPROM is good */ - - if (!ixgb_validate_eeprom_checksum(&adapter->hw)) { - netif_err(adapter, probe, adapter->netdev, - "The EEPROM Checksum Is Not Valid\n"); - err = -EIO; - goto err_eeprom; - } - - ixgb_get_ee_mac_addr(&adapter->hw, addr); - eth_hw_addr_set(netdev, addr); - - if (!is_valid_ether_addr(netdev->dev_addr)) { - netif_err(adapter, probe, adapter->netdev, "Invalid MAC Address\n"); - err = -EIO; - goto err_eeprom; - } - - adapter->part_num = ixgb_get_ee_pba_number(&adapter->hw); - - timer_setup(&adapter->watchdog_timer, ixgb_watchdog, 0); - - INIT_WORK(&adapter->tx_timeout_task, ixgb_tx_timeout_task); - - strcpy(netdev->name, "eth%d"); - err = register_netdev(netdev); - if (err) - goto err_register; - - /* carrier off reporting is important to ethtool even BEFORE open */ - netif_carrier_off(netdev); - - netif_info(adapter, probe, adapter->netdev, - "Intel(R) PRO/10GbE Network Connection\n"); - ixgb_check_options(adapter); - /* reset the hardware with the new settings */ - - ixgb_reset(adapter); - - cards_found++; - return 0; - -err_register: -err_sw_init: -err_eeprom: - iounmap(adapter->hw.hw_addr); -err_ioremap: - free_netdev(netdev); -err_alloc_etherdev: - pci_release_regions(pdev); -err_request_regions: -err_dma_mask: - pci_disable_device(pdev); - return err; -} - -/** - * ixgb_remove - Device Removal Routine - * @pdev: PCI device information struct - * - * ixgb_remove is called by the PCI subsystem to alert the driver - * that it should release a PCI device. The could be caused by a - * Hot-Plug event, or because the driver is going to be removed from - * memory. - **/ - -static void -ixgb_remove(struct pci_dev *pdev) -{ - struct net_device *netdev = pci_get_drvdata(pdev); - struct ixgb_adapter *adapter = netdev_priv(netdev); - - cancel_work_sync(&adapter->tx_timeout_task); - - unregister_netdev(netdev); - - iounmap(adapter->hw.hw_addr); - pci_release_regions(pdev); - - free_netdev(netdev); - pci_disable_device(pdev); -} - -/** - * ixgb_sw_init - Initialize general software structures (struct ixgb_adapter) - * @adapter: board private structure to initialize - * - * ixgb_sw_init initializes the Adapter private data structure. - * Fields are initialized based on PCI device information and - * OS network device settings (MTU size). - **/ - -static int -ixgb_sw_init(struct ixgb_adapter *adapter) -{ - struct ixgb_hw *hw = &adapter->hw; - struct net_device *netdev = adapter->netdev; - struct pci_dev *pdev = adapter->pdev; - - /* PCI config space info */ - - hw->vendor_id = pdev->vendor; - hw->device_id = pdev->device; - hw->subsystem_vendor_id = pdev->subsystem_vendor; - hw->subsystem_id = pdev->subsystem_device; - - hw->max_frame_size = netdev->mtu + ENET_HEADER_SIZE + ENET_FCS_LENGTH; - adapter->rx_buffer_len = hw->max_frame_size + 8; /* + 8 for errata */ - - if ((hw->device_id == IXGB_DEVICE_ID_82597EX) || - (hw->device_id == IXGB_DEVICE_ID_82597EX_CX4) || - (hw->device_id == IXGB_DEVICE_ID_82597EX_LR) || - (hw->device_id == IXGB_DEVICE_ID_82597EX_SR)) - hw->mac_type = ixgb_82597; - else { - /* should never have loaded on this device */ - netif_err(adapter, probe, adapter->netdev, "unsupported device id\n"); - } - - /* enable flow control to be programmed */ - hw->fc.send_xon = 1; - - set_bit(__IXGB_DOWN, &adapter->flags); - return 0; -} - -/** - * ixgb_open - Called when a network interface is made active - * @netdev: network interface device structure - * - * Returns 0 on success, negative value on failure - * - * 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, - * and the stack is notified that the interface is ready. - **/ - -static int -ixgb_open(struct net_device *netdev) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - int err; - - /* allocate transmit descriptors */ - err = ixgb_setup_tx_resources(adapter); - if (err) - goto err_setup_tx; - - netif_carrier_off(netdev); - - /* allocate receive descriptors */ - - err = ixgb_setup_rx_resources(adapter); - if (err) - goto err_setup_rx; - - err = ixgb_up(adapter); - if (err) - goto err_up; - - netif_start_queue(netdev); - - return 0; - -err_up: - ixgb_free_rx_resources(adapter); -err_setup_rx: - ixgb_free_tx_resources(adapter); -err_setup_tx: - ixgb_reset(adapter); - - return err; -} - -/** - * ixgb_close - Disables a network interface - * @netdev: network interface device structure - * - * Returns 0, this is not allowed to fail - * - * The close entry point is called when an interface is de-activated - * by the OS. The hardware is still under the drivers control, but - * needs to be disabled. A global MAC reset is issued to stop the - * hardware, and all transmit and receive resources are freed. - **/ - -static int -ixgb_close(struct net_device *netdev) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - - ixgb_down(adapter, true); - - ixgb_free_tx_resources(adapter); - ixgb_free_rx_resources(adapter); - - return 0; -} - -/** - * ixgb_setup_tx_resources - allocate Tx resources (Descriptors) - * @adapter: board private structure - * - * Return 0 on success, negative on failure - **/ - -int -ixgb_setup_tx_resources(struct ixgb_adapter *adapter) -{ - struct ixgb_desc_ring *txdr = &adapter->tx_ring; - struct pci_dev *pdev = adapter->pdev; - int size; - - size = sizeof(struct ixgb_buffer) * txdr->count; - txdr->buffer_info = vzalloc(size); - if (!txdr->buffer_info) - return -ENOMEM; - - /* round up to nearest 4K */ - - txdr->size = txdr->count * sizeof(struct ixgb_tx_desc); - txdr->size = ALIGN(txdr->size, 4096); - - txdr->desc = dma_alloc_coherent(&pdev->dev, txdr->size, &txdr->dma, - GFP_KERNEL); - if (!txdr->desc) { - vfree(txdr->buffer_info); - return -ENOMEM; - } - - txdr->next_to_use = 0; - txdr->next_to_clean = 0; - - return 0; -} - -/** - * ixgb_configure_tx - Configure 82597 Transmit Unit after Reset. - * @adapter: board private structure - * - * Configure the Tx unit of the MAC after a reset. - **/ - -static void -ixgb_configure_tx(struct ixgb_adapter *adapter) -{ - u64 tdba = adapter->tx_ring.dma; - u32 tdlen = adapter->tx_ring.count * sizeof(struct ixgb_tx_desc); - u32 tctl; - struct ixgb_hw *hw = &adapter->hw; - - /* Setup the Base and Length of the Tx Descriptor Ring - * tx_ring.dma can be either a 32 or 64 bit value - */ - - IXGB_WRITE_REG(hw, TDBAL, (tdba & 0x00000000ffffffffULL)); - IXGB_WRITE_REG(hw, TDBAH, (tdba >> 32)); - - IXGB_WRITE_REG(hw, TDLEN, tdlen); - - /* Setup the HW Tx Head and Tail descriptor pointers */ - - IXGB_WRITE_REG(hw, TDH, 0); - IXGB_WRITE_REG(hw, TDT, 0); - - /* don't set up txdctl, it induces performance problems if configured - * incorrectly */ - /* Set the Tx Interrupt Delay register */ - - IXGB_WRITE_REG(hw, TIDV, adapter->tx_int_delay); - - /* Program the Transmit Control Register */ - - tctl = IXGB_TCTL_TCE | IXGB_TCTL_TXEN | IXGB_TCTL_TPDE; - IXGB_WRITE_REG(hw, TCTL, tctl); - - /* Setup Transmit Descriptor Settings for this adapter */ - adapter->tx_cmd_type = - IXGB_TX_DESC_TYPE | - (adapter->tx_int_delay_enable ? IXGB_TX_DESC_CMD_IDE : 0); -} - -/** - * ixgb_setup_rx_resources - allocate Rx resources (Descriptors) - * @adapter: board private structure - * - * Returns 0 on success, negative on failure - **/ - -int -ixgb_setup_rx_resources(struct ixgb_adapter *adapter) -{ - struct ixgb_desc_ring *rxdr = &adapter->rx_ring; - struct pci_dev *pdev = adapter->pdev; - int size; - - size = sizeof(struct ixgb_buffer) * rxdr->count; - rxdr->buffer_info = vzalloc(size); - if (!rxdr->buffer_info) - return -ENOMEM; - - /* Round up to nearest 4K */ - - rxdr->size = rxdr->count * sizeof(struct ixgb_rx_desc); - rxdr->size = ALIGN(rxdr->size, 4096); - - rxdr->desc = dma_alloc_coherent(&pdev->dev, rxdr->size, &rxdr->dma, - GFP_KERNEL); - - if (!rxdr->desc) { - vfree(rxdr->buffer_info); - return -ENOMEM; - } - - rxdr->next_to_clean = 0; - rxdr->next_to_use = 0; - - return 0; -} - -/** - * ixgb_setup_rctl - configure the receive control register - * @adapter: Board private structure - **/ - -static void -ixgb_setup_rctl(struct ixgb_adapter *adapter) -{ - u32 rctl; - - rctl = IXGB_READ_REG(&adapter->hw, RCTL); - - rctl &= ~(3 << IXGB_RCTL_MO_SHIFT); - - rctl |= - IXGB_RCTL_BAM | IXGB_RCTL_RDMTS_1_2 | - IXGB_RCTL_RXEN | IXGB_RCTL_CFF | - (adapter->hw.mc_filter_type << IXGB_RCTL_MO_SHIFT); - - rctl |= IXGB_RCTL_SECRC; - - if (adapter->rx_buffer_len <= IXGB_RXBUFFER_2048) - rctl |= IXGB_RCTL_BSIZE_2048; - else if (adapter->rx_buffer_len <= IXGB_RXBUFFER_4096) - rctl |= IXGB_RCTL_BSIZE_4096; - else if (adapter->rx_buffer_len <= IXGB_RXBUFFER_8192) - rctl |= IXGB_RCTL_BSIZE_8192; - else if (adapter->rx_buffer_len <= IXGB_RXBUFFER_16384) - rctl |= IXGB_RCTL_BSIZE_16384; - - IXGB_WRITE_REG(&adapter->hw, RCTL, rctl); -} - -/** - * ixgb_configure_rx - Configure 82597 Receive Unit after Reset. - * @adapter: board private structure - * - * Configure the Rx unit of the MAC after a reset. - **/ - -static void -ixgb_configure_rx(struct ixgb_adapter *adapter) -{ - u64 rdba = adapter->rx_ring.dma; - u32 rdlen = adapter->rx_ring.count * sizeof(struct ixgb_rx_desc); - struct ixgb_hw *hw = &adapter->hw; - u32 rctl; - u32 rxcsum; - - /* make sure receives are disabled while setting up the descriptors */ - - rctl = IXGB_READ_REG(hw, RCTL); - IXGB_WRITE_REG(hw, RCTL, rctl & ~IXGB_RCTL_RXEN); - - /* set the Receive Delay Timer Register */ - - IXGB_WRITE_REG(hw, RDTR, adapter->rx_int_delay); - - /* Setup the Base and Length of the Rx Descriptor Ring */ - - IXGB_WRITE_REG(hw, RDBAL, (rdba & 0x00000000ffffffffULL)); - IXGB_WRITE_REG(hw, RDBAH, (rdba >> 32)); - - IXGB_WRITE_REG(hw, RDLEN, rdlen); - - /* Setup the HW Rx Head and Tail Descriptor Pointers */ - IXGB_WRITE_REG(hw, RDH, 0); - IXGB_WRITE_REG(hw, RDT, 0); - - /* due to the hardware errata with RXDCTL, we are unable to use any of - * the performance enhancing features of it without causing other - * subtle bugs, some of the bugs could include receive length - * corruption at high data rates (WTHRESH > 0) and/or receive - * descriptor ring irregularites (particularly in hardware cache) */ - IXGB_WRITE_REG(hw, RXDCTL, 0); - - /* Enable Receive Checksum Offload for TCP and UDP */ - if (adapter->rx_csum) { - rxcsum = IXGB_READ_REG(hw, RXCSUM); - rxcsum |= IXGB_RXCSUM_TUOFL; - IXGB_WRITE_REG(hw, RXCSUM, rxcsum); - } - - /* Enable Receives */ - - IXGB_WRITE_REG(hw, RCTL, rctl); -} - -/** - * ixgb_free_tx_resources - Free Tx Resources - * @adapter: board private structure - * - * Free all transmit software resources - **/ - -void -ixgb_free_tx_resources(struct ixgb_adapter *adapter) -{ - struct pci_dev *pdev = adapter->pdev; - - ixgb_clean_tx_ring(adapter); - - vfree(adapter->tx_ring.buffer_info); - adapter->tx_ring.buffer_info = NULL; - - dma_free_coherent(&pdev->dev, adapter->tx_ring.size, - adapter->tx_ring.desc, adapter->tx_ring.dma); - - adapter->tx_ring.desc = NULL; -} - -static void -ixgb_unmap_and_free_tx_resource(struct ixgb_adapter *adapter, - struct ixgb_buffer *buffer_info) -{ - if (buffer_info->dma) { - if (buffer_info->mapped_as_page) - dma_unmap_page(&adapter->pdev->dev, buffer_info->dma, - buffer_info->length, DMA_TO_DEVICE); - else - dma_unmap_single(&adapter->pdev->dev, buffer_info->dma, - buffer_info->length, DMA_TO_DEVICE); - buffer_info->dma = 0; - } - - if (buffer_info->skb) { - dev_kfree_skb_any(buffer_info->skb); - buffer_info->skb = NULL; - } - buffer_info->time_stamp = 0; - /* these fields must always be initialized in tx - * buffer_info->length = 0; - * buffer_info->next_to_watch = 0; */ -} - -/** - * ixgb_clean_tx_ring - Free Tx Buffers - * @adapter: board private structure - **/ - -static void -ixgb_clean_tx_ring(struct ixgb_adapter *adapter) -{ - struct ixgb_desc_ring *tx_ring = &adapter->tx_ring; - struct ixgb_buffer *buffer_info; - unsigned long size; - unsigned int i; - - /* Free all the Tx ring sk_buffs */ - - for (i = 0; i < tx_ring->count; i++) { - buffer_info = &tx_ring->buffer_info[i]; - ixgb_unmap_and_free_tx_resource(adapter, buffer_info); - } - - size = sizeof(struct ixgb_buffer) * tx_ring->count; - memset(tx_ring->buffer_info, 0, size); - - /* Zero out the descriptor ring */ - - memset(tx_ring->desc, 0, tx_ring->size); - - tx_ring->next_to_use = 0; - tx_ring->next_to_clean = 0; - - IXGB_WRITE_REG(&adapter->hw, TDH, 0); - IXGB_WRITE_REG(&adapter->hw, TDT, 0); -} - -/** - * ixgb_free_rx_resources - Free Rx Resources - * @adapter: board private structure - * - * Free all receive software resources - **/ - -void -ixgb_free_rx_resources(struct ixgb_adapter *adapter) -{ - struct ixgb_desc_ring *rx_ring = &adapter->rx_ring; - struct pci_dev *pdev = adapter->pdev; - - ixgb_clean_rx_ring(adapter); - - vfree(rx_ring->buffer_info); - rx_ring->buffer_info = NULL; - - dma_free_coherent(&pdev->dev, rx_ring->size, rx_ring->desc, - rx_ring->dma); - - rx_ring->desc = NULL; -} - -/** - * ixgb_clean_rx_ring - Free Rx Buffers - * @adapter: board private structure - **/ - -static void -ixgb_clean_rx_ring(struct ixgb_adapter *adapter) -{ - struct ixgb_desc_ring *rx_ring = &adapter->rx_ring; - struct ixgb_buffer *buffer_info; - struct pci_dev *pdev = adapter->pdev; - unsigned long size; - unsigned int i; - - /* Free all the Rx ring sk_buffs */ - - for (i = 0; i < rx_ring->count; i++) { - buffer_info = &rx_ring->buffer_info[i]; - if (buffer_info->dma) { - dma_unmap_single(&pdev->dev, - buffer_info->dma, - buffer_info->length, - DMA_FROM_DEVICE); - buffer_info->dma = 0; - buffer_info->length = 0; - } - - if (buffer_info->skb) { - dev_kfree_skb(buffer_info->skb); - buffer_info->skb = NULL; - } - } - - size = sizeof(struct ixgb_buffer) * rx_ring->count; - memset(rx_ring->buffer_info, 0, size); - - /* Zero out the descriptor ring */ - - memset(rx_ring->desc, 0, rx_ring->size); - - rx_ring->next_to_clean = 0; - rx_ring->next_to_use = 0; - - IXGB_WRITE_REG(&adapter->hw, RDH, 0); - IXGB_WRITE_REG(&adapter->hw, RDT, 0); -} - -/** - * ixgb_set_mac - Change the Ethernet Address of the NIC - * @netdev: network interface device structure - * @p: pointer to an address structure - * - * Returns 0 on success, negative on failure - **/ - -static int -ixgb_set_mac(struct net_device *netdev, void *p) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - struct sockaddr *addr = p; - - if (!is_valid_ether_addr(addr->sa_data)) - return -EADDRNOTAVAIL; - - eth_hw_addr_set(netdev, addr->sa_data); - - ixgb_rar_set(&adapter->hw, addr->sa_data, 0); - - return 0; -} - -/** - * ixgb_set_multi - Multicast and Promiscuous mode set - * @netdev: network interface device structure - * - * The set_multi entry point is called whenever the multicast address - * list or the network interface flags are updated. This routine is - * responsible for configuring the hardware for proper multicast, - * promiscuous mode, and all-multi behavior. - **/ - -static void -ixgb_set_multi(struct net_device *netdev) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - struct ixgb_hw *hw = &adapter->hw; - struct netdev_hw_addr *ha; - u32 rctl; - - /* Check for Promiscuous and All Multicast modes */ - - rctl = IXGB_READ_REG(hw, RCTL); - - if (netdev->flags & IFF_PROMISC) { - rctl |= (IXGB_RCTL_UPE | IXGB_RCTL_MPE); - /* disable VLAN filtering */ - rctl &= ~IXGB_RCTL_CFIEN; - rctl &= ~IXGB_RCTL_VFE; - } else { - if (netdev->flags & IFF_ALLMULTI) { - rctl |= IXGB_RCTL_MPE; - rctl &= ~IXGB_RCTL_UPE; - } else { - rctl &= ~(IXGB_RCTL_UPE | IXGB_RCTL_MPE); - } - /* enable VLAN filtering */ - rctl |= IXGB_RCTL_VFE; - rctl &= ~IXGB_RCTL_CFIEN; - } - - if (netdev_mc_count(netdev) > IXGB_MAX_NUM_MULTICAST_ADDRESSES) { - rctl |= IXGB_RCTL_MPE; - IXGB_WRITE_REG(hw, RCTL, rctl); - } else { - u8 *mta = kmalloc_array(ETH_ALEN, - IXGB_MAX_NUM_MULTICAST_ADDRESSES, - GFP_ATOMIC); - u8 *addr; - if (!mta) - goto alloc_failed; - - IXGB_WRITE_REG(hw, RCTL, rctl); - - addr = mta; - netdev_for_each_mc_addr(ha, netdev) { - memcpy(addr, ha->addr, ETH_ALEN); - addr += ETH_ALEN; - } - - ixgb_mc_addr_list_update(hw, mta, netdev_mc_count(netdev), 0); - kfree(mta); - } - -alloc_failed: - if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX) - ixgb_vlan_strip_enable(adapter); - else - ixgb_vlan_strip_disable(adapter); - -} - -/** - * ixgb_watchdog - Timer Call-back - * @t: pointer to timer_list containing our private info pointer - **/ - -static void -ixgb_watchdog(struct timer_list *t) -{ - struct ixgb_adapter *adapter = from_timer(adapter, t, watchdog_timer); - struct net_device *netdev = adapter->netdev; - struct ixgb_desc_ring *txdr = &adapter->tx_ring; - - ixgb_check_for_link(&adapter->hw); - - if (ixgb_check_for_bad_link(&adapter->hw)) { - /* force the reset path */ - netif_stop_queue(netdev); - } - - if (adapter->hw.link_up) { - if (!netif_carrier_ok(netdev)) { - netdev_info(netdev, - "NIC Link is Up 10 Gbps Full Duplex, Flow Control: %s\n", - (adapter->hw.fc.type == ixgb_fc_full) ? - "RX/TX" : - (adapter->hw.fc.type == ixgb_fc_rx_pause) ? - "RX" : - (adapter->hw.fc.type == ixgb_fc_tx_pause) ? - "TX" : "None"); - adapter->link_speed = 10000; - adapter->link_duplex = FULL_DUPLEX; - netif_carrier_on(netdev); - } - } else { - if (netif_carrier_ok(netdev)) { - adapter->link_speed = 0; - adapter->link_duplex = 0; - netdev_info(netdev, "NIC Link is Down\n"); - netif_carrier_off(netdev); - } - } - - ixgb_update_stats(adapter); - - if (!netif_carrier_ok(netdev)) { - if (IXGB_DESC_UNUSED(txdr) + 1 < txdr->count) { - /* We've lost link, so the controller stops DMA, - * but we've got queued Tx work that's never going - * to get done, so reset controller to flush Tx. - * (Do the reset outside of interrupt context). */ - schedule_work(&adapter->tx_timeout_task); - /* return immediately since reset is imminent */ - return; - } - } - - /* Force detection of hung controller every watchdog period */ - adapter->detect_tx_hung = true; - - /* generate an interrupt to force clean up of any stragglers */ - IXGB_WRITE_REG(&adapter->hw, ICS, IXGB_INT_TXDW); - - /* Reset the timer */ - mod_timer(&adapter->watchdog_timer, jiffies + 2 * HZ); -} - -#define IXGB_TX_FLAGS_CSUM 0x00000001 -#define IXGB_TX_FLAGS_VLAN 0x00000002 -#define IXGB_TX_FLAGS_TSO 0x00000004 - -static int -ixgb_tso(struct ixgb_adapter *adapter, struct sk_buff *skb) -{ - struct ixgb_context_desc *context_desc; - unsigned int i; - u8 ipcss, ipcso, tucss, tucso, hdr_len; - u16 ipcse, tucse, mss; - - if (likely(skb_is_gso(skb))) { - struct ixgb_buffer *buffer_info; - struct iphdr *iph; - int err; - - err = skb_cow_head(skb, 0); - if (err < 0) - return err; - - hdr_len = skb_tcp_all_headers(skb); - mss = skb_shinfo(skb)->gso_size; - iph = ip_hdr(skb); - iph->tot_len = 0; - iph->check = 0; - tcp_hdr(skb)->check = ~csum_tcpudp_magic(iph->saddr, - iph->daddr, 0, - IPPROTO_TCP, 0); - ipcss = skb_network_offset(skb); - ipcso = (void *)&(iph->check) - (void *)skb->data; - ipcse = skb_transport_offset(skb) - 1; - tucss = skb_transport_offset(skb); - tucso = (void *)&(tcp_hdr(skb)->check) - (void *)skb->data; - tucse = 0; - - i = adapter->tx_ring.next_to_use; - context_desc = IXGB_CONTEXT_DESC(adapter->tx_ring, i); - buffer_info = &adapter->tx_ring.buffer_info[i]; - WARN_ON(buffer_info->dma != 0); - - context_desc->ipcss = ipcss; - context_desc->ipcso = ipcso; - context_desc->ipcse = cpu_to_le16(ipcse); - context_desc->tucss = tucss; - context_desc->tucso = tucso; - context_desc->tucse = cpu_to_le16(tucse); - context_desc->mss = cpu_to_le16(mss); - context_desc->hdr_len = hdr_len; - context_desc->status = 0; - context_desc->cmd_type_len = cpu_to_le32( - IXGB_CONTEXT_DESC_TYPE - | IXGB_CONTEXT_DESC_CMD_TSE - | IXGB_CONTEXT_DESC_CMD_IP - | IXGB_CONTEXT_DESC_CMD_TCP - | IXGB_CONTEXT_DESC_CMD_IDE - | (skb->len - (hdr_len))); - - - if (++i == adapter->tx_ring.count) i = 0; - adapter->tx_ring.next_to_use = i; - - return 1; - } - - return 0; -} - -static bool -ixgb_tx_csum(struct ixgb_adapter *adapter, struct sk_buff *skb) -{ - struct ixgb_context_desc *context_desc; - unsigned int i; - u8 css, cso; - - if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) { - struct ixgb_buffer *buffer_info; - css = skb_checksum_start_offset(skb); - cso = css + skb->csum_offset; - - i = adapter->tx_ring.next_to_use; - context_desc = IXGB_CONTEXT_DESC(adapter->tx_ring, i); - buffer_info = &adapter->tx_ring.buffer_info[i]; - WARN_ON(buffer_info->dma != 0); - - context_desc->tucss = css; - context_desc->tucso = cso; - context_desc->tucse = 0; - /* zero out any previously existing data in one instruction */ - *(u32 *)&(context_desc->ipcss) = 0; - context_desc->status = 0; - context_desc->hdr_len = 0; - context_desc->mss = 0; - context_desc->cmd_type_len = - cpu_to_le32(IXGB_CONTEXT_DESC_TYPE - | IXGB_TX_DESC_CMD_IDE); - - if (++i == adapter->tx_ring.count) i = 0; - adapter->tx_ring.next_to_use = i; - - return true; - } - - return false; -} - -#define IXGB_MAX_TXD_PWR 14 -#define IXGB_MAX_DATA_PER_TXD (1<<IXGB_MAX_TXD_PWR) - -static int -ixgb_tx_map(struct ixgb_adapter *adapter, struct sk_buff *skb, - unsigned int first) -{ - struct ixgb_desc_ring *tx_ring = &adapter->tx_ring; - struct pci_dev *pdev = adapter->pdev; - struct ixgb_buffer *buffer_info; - int len = skb_headlen(skb); - unsigned int offset = 0, size, count = 0, i; - unsigned int mss = skb_shinfo(skb)->gso_size; - unsigned int nr_frags = skb_shinfo(skb)->nr_frags; - unsigned int f; - - i = tx_ring->next_to_use; - - while (len) { - buffer_info = &tx_ring->buffer_info[i]; - size = min(len, IXGB_MAX_DATA_PER_TXD); - /* Workaround for premature desc write-backs - * in TSO mode. Append 4-byte sentinel desc */ - if (unlikely(mss && !nr_frags && size == len && size > 8)) - size -= 4; - - buffer_info->length = size; - WARN_ON(buffer_info->dma != 0); - buffer_info->time_stamp = jiffies; - buffer_info->mapped_as_page = false; - buffer_info->dma = dma_map_single(&pdev->dev, - skb->data + offset, - size, DMA_TO_DEVICE); - if (dma_mapping_error(&pdev->dev, buffer_info->dma)) - goto dma_error; - buffer_info->next_to_watch = 0; - - len -= size; - offset += size; - count++; - if (len) { - i++; - if (i == tx_ring->count) - i = 0; - } - } - - for (f = 0; f < nr_frags; f++) { - const skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; - len = skb_frag_size(frag); - offset = 0; - - while (len) { - i++; - if (i == tx_ring->count) - i = 0; - - buffer_info = &tx_ring->buffer_info[i]; - size = min(len, IXGB_MAX_DATA_PER_TXD); - - /* Workaround for premature desc write-backs - * in TSO mode. Append 4-byte sentinel desc */ - if (unlikely(mss && (f == (nr_frags - 1)) - && size == len && size > 8)) - size -= 4; - - buffer_info->length = size; - buffer_info->time_stamp = jiffies; - buffer_info->mapped_as_page = true; - buffer_info->dma = - skb_frag_dma_map(&pdev->dev, frag, offset, size, - DMA_TO_DEVICE); - if (dma_mapping_error(&pdev->dev, buffer_info->dma)) - goto dma_error; - buffer_info->next_to_watch = 0; - - len -= size; - offset += size; - count++; - } - } - tx_ring->buffer_info[i].skb = skb; - tx_ring->buffer_info[first].next_to_watch = i; - - return count; - -dma_error: - dev_err(&pdev->dev, "TX DMA map failed\n"); - buffer_info->dma = 0; - if (count) - count--; - - while (count--) { - if (i==0) - i += tx_ring->count; - i--; - buffer_info = &tx_ring->buffer_info[i]; - ixgb_unmap_and_free_tx_resource(adapter, buffer_info); - } - - return 0; -} - -static void -ixgb_tx_queue(struct ixgb_adapter *adapter, int count, int vlan_id,int tx_flags) -{ - struct ixgb_desc_ring *tx_ring = &adapter->tx_ring; - struct ixgb_tx_desc *tx_desc = NULL; - struct ixgb_buffer *buffer_info; - u32 cmd_type_len = adapter->tx_cmd_type; - u8 status = 0; - u8 popts = 0; - unsigned int i; - - if (tx_flags & IXGB_TX_FLAGS_TSO) { - cmd_type_len |= IXGB_TX_DESC_CMD_TSE; - popts |= (IXGB_TX_DESC_POPTS_IXSM | IXGB_TX_DESC_POPTS_TXSM); - } - - if (tx_flags & IXGB_TX_FLAGS_CSUM) - popts |= IXGB_TX_DESC_POPTS_TXSM; - - if (tx_flags & IXGB_TX_FLAGS_VLAN) - cmd_type_len |= IXGB_TX_DESC_CMD_VLE; - - i = tx_ring->next_to_use; - - while (count--) { - buffer_info = &tx_ring->buffer_info[i]; - tx_desc = IXGB_TX_DESC(*tx_ring, i); - tx_desc->buff_addr = cpu_to_le64(buffer_info->dma); - tx_desc->cmd_type_len = - cpu_to_le32(cmd_type_len | buffer_info->length); - tx_desc->status = status; - tx_desc->popts = popts; - tx_desc->vlan = cpu_to_le16(vlan_id); - - if (++i == tx_ring->count) i = 0; - } - - tx_desc->cmd_type_len |= - cpu_to_le32(IXGB_TX_DESC_CMD_EOP | IXGB_TX_DESC_CMD_RS); - - /* Force memory writes to complete before letting h/w - * know there are new descriptors to fetch. (Only - * applicable for weak-ordered memory model archs, - * such as IA-64). */ - wmb(); - - tx_ring->next_to_use = i; - IXGB_WRITE_REG(&adapter->hw, TDT, i); -} - -static int __ixgb_maybe_stop_tx(struct net_device *netdev, int size) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - struct ixgb_desc_ring *tx_ring = &adapter->tx_ring; - - netif_stop_queue(netdev); - /* Herbert's original patch had: - * smp_mb__after_netif_stop_queue(); - * but since that doesn't exist yet, just open code it. */ - smp_mb(); - - /* We need to check again in a case another CPU has just - * made room available. */ - if (likely(IXGB_DESC_UNUSED(tx_ring) < size)) - return -EBUSY; - - /* A reprieve! */ - netif_start_queue(netdev); - ++adapter->restart_queue; - return 0; -} - -static int ixgb_maybe_stop_tx(struct net_device *netdev, - struct ixgb_desc_ring *tx_ring, int size) -{ - if (likely(IXGB_DESC_UNUSED(tx_ring) >= size)) - return 0; - return __ixgb_maybe_stop_tx(netdev, size); -} - - -/* Tx Descriptors needed, worst case */ -#define TXD_USE_COUNT(S) (((S) >> IXGB_MAX_TXD_PWR) + \ - (((S) & (IXGB_MAX_DATA_PER_TXD - 1)) ? 1 : 0)) -#define DESC_NEEDED TXD_USE_COUNT(IXGB_MAX_DATA_PER_TXD) /* skb->date */ + \ - MAX_SKB_FRAGS * TXD_USE_COUNT(PAGE_SIZE) + 1 /* for context */ \ - + 1 /* one more needed for sentinel TSO workaround */ - -static netdev_tx_t -ixgb_xmit_frame(struct sk_buff *skb, struct net_device *netdev) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - unsigned int first; - unsigned int tx_flags = 0; - int vlan_id = 0; - int count = 0; - int tso; - - if (test_bit(__IXGB_DOWN, &adapter->flags)) { - dev_kfree_skb_any(skb); - return NETDEV_TX_OK; - } - - if (skb->len <= 0) { - dev_kfree_skb_any(skb); - return NETDEV_TX_OK; - } - - if (unlikely(ixgb_maybe_stop_tx(netdev, &adapter->tx_ring, - DESC_NEEDED))) - return NETDEV_TX_BUSY; - - if (skb_vlan_tag_present(skb)) { - tx_flags |= IXGB_TX_FLAGS_VLAN; - vlan_id = skb_vlan_tag_get(skb); - } - - first = adapter->tx_ring.next_to_use; - - tso = ixgb_tso(adapter, skb); - if (tso < 0) { - dev_kfree_skb_any(skb); - return NETDEV_TX_OK; - } - - if (likely(tso)) - tx_flags |= IXGB_TX_FLAGS_TSO; - else if (ixgb_tx_csum(adapter, skb)) - tx_flags |= IXGB_TX_FLAGS_CSUM; - - count = ixgb_tx_map(adapter, skb, first); - - if (count) { - ixgb_tx_queue(adapter, count, vlan_id, tx_flags); - /* Make sure there is space in the ring for the next send. */ - ixgb_maybe_stop_tx(netdev, &adapter->tx_ring, DESC_NEEDED); - - } else { - dev_kfree_skb_any(skb); - adapter->tx_ring.buffer_info[first].time_stamp = 0; - adapter->tx_ring.next_to_use = first; - } - - return NETDEV_TX_OK; -} - -/** - * ixgb_tx_timeout - Respond to a Tx Hang - * @netdev: network interface device structure - * @txqueue: queue hanging (unused) - **/ - -static void -ixgb_tx_timeout(struct net_device *netdev, unsigned int __always_unused txqueue) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - - /* Do the reset outside of interrupt context */ - schedule_work(&adapter->tx_timeout_task); -} - -static void -ixgb_tx_timeout_task(struct work_struct *work) -{ - struct ixgb_adapter *adapter = - container_of(work, struct ixgb_adapter, tx_timeout_task); - - adapter->tx_timeout_count++; - ixgb_down(adapter, true); - ixgb_up(adapter); -} - -/** - * ixgb_change_mtu - Change the Maximum Transfer Unit - * @netdev: network interface device structure - * @new_mtu: new value for maximum frame size - * - * Returns 0 on success, negative on failure - **/ - -static int -ixgb_change_mtu(struct net_device *netdev, int new_mtu) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - int max_frame = new_mtu + ENET_HEADER_SIZE + ENET_FCS_LENGTH; - - if (netif_running(netdev)) - ixgb_down(adapter, true); - - adapter->rx_buffer_len = max_frame + 8; /* + 8 for errata */ - - netdev->mtu = new_mtu; - - if (netif_running(netdev)) - ixgb_up(adapter); - - return 0; -} - -/** - * ixgb_update_stats - Update the board statistics counters. - * @adapter: board private structure - **/ - -void -ixgb_update_stats(struct ixgb_adapter *adapter) -{ - struct net_device *netdev = adapter->netdev; - struct pci_dev *pdev = adapter->pdev; - - /* Prevent stats update while adapter is being reset */ - if (pci_channel_offline(pdev)) - return; - - if ((netdev->flags & IFF_PROMISC) || (netdev->flags & IFF_ALLMULTI) || - (netdev_mc_count(netdev) > IXGB_MAX_NUM_MULTICAST_ADDRESSES)) { - u64 multi = IXGB_READ_REG(&adapter->hw, MPRCL); - u32 bcast_l = IXGB_READ_REG(&adapter->hw, BPRCL); - u32 bcast_h = IXGB_READ_REG(&adapter->hw, BPRCH); - u64 bcast = ((u64)bcast_h << 32) | bcast_l; - - multi |= ((u64)IXGB_READ_REG(&adapter->hw, MPRCH) << 32); - /* fix up multicast stats by removing broadcasts */ - if (multi >= bcast) - multi -= bcast; - - adapter->stats.mprcl += (multi & 0xFFFFFFFF); - adapter->stats.mprch += (multi >> 32); - adapter->stats.bprcl += bcast_l; - adapter->stats.bprch += bcast_h; - } else { - adapter->stats.mprcl += IXGB_READ_REG(&adapter->hw, MPRCL); - adapter->stats.mprch += IXGB_READ_REG(&adapter->hw, MPRCH); - adapter->stats.bprcl += IXGB_READ_REG(&adapter->hw, BPRCL); - adapter->stats.bprch += IXGB_READ_REG(&adapter->hw, BPRCH); - } - adapter->stats.tprl += IXGB_READ_REG(&adapter->hw, TPRL); - adapter->stats.tprh += IXGB_READ_REG(&adapter->hw, TPRH); - adapter->stats.gprcl += IXGB_READ_REG(&adapter->hw, GPRCL); - adapter->stats.gprch += IXGB_READ_REG(&adapter->hw, GPRCH); - adapter->stats.uprcl += IXGB_READ_REG(&adapter->hw, UPRCL); - adapter->stats.uprch += IXGB_READ_REG(&adapter->hw, UPRCH); - adapter->stats.vprcl += IXGB_READ_REG(&adapter->hw, VPRCL); - adapter->stats.vprch += IXGB_READ_REG(&adapter->hw, VPRCH); - adapter->stats.jprcl += IXGB_READ_REG(&adapter->hw, JPRCL); - adapter->stats.jprch += IXGB_READ_REG(&adapter->hw, JPRCH); - adapter->stats.gorcl += IXGB_READ_REG(&adapter->hw, GORCL); - adapter->stats.gorch += IXGB_READ_REG(&adapter->hw, GORCH); - adapter->stats.torl += IXGB_READ_REG(&adapter->hw, TORL); - adapter->stats.torh += IXGB_READ_REG(&adapter->hw, TORH); - adapter->stats.rnbc += IXGB_READ_REG(&adapter->hw, RNBC); - adapter->stats.ruc += IXGB_READ_REG(&adapter->hw, RUC); - adapter->stats.roc += IXGB_READ_REG(&adapter->hw, ROC); - adapter->stats.rlec += IXGB_READ_REG(&adapter->hw, RLEC); - adapter->stats.crcerrs += IXGB_READ_REG(&adapter->hw, CRCERRS); - adapter->stats.icbc += IXGB_READ_REG(&adapter->hw, ICBC); - adapter->stats.ecbc += IXGB_READ_REG(&adapter->hw, ECBC); - adapter->stats.mpc += IXGB_READ_REG(&adapter->hw, MPC); - adapter->stats.tptl += IXGB_READ_REG(&adapter->hw, TPTL); - adapter->stats.tpth += IXGB_READ_REG(&adapter->hw, TPTH); - adapter->stats.gptcl += IXGB_READ_REG(&adapter->hw, GPTCL); - adapter->stats.gptch += IXGB_READ_REG(&adapter->hw, GPTCH); - adapter->stats.bptcl += IXGB_READ_REG(&adapter->hw, BPTCL); - adapter->stats.bptch += IXGB_READ_REG(&adapter->hw, BPTCH); - adapter->stats.mptcl += IXGB_READ_REG(&adapter->hw, MPTCL); - adapter->stats.mptch += IXGB_READ_REG(&adapter->hw, MPTCH); - adapter->stats.uptcl += IXGB_READ_REG(&adapter->hw, UPTCL); - adapter->stats.uptch += IXGB_READ_REG(&adapter->hw, UPTCH); - adapter->stats.vptcl += IXGB_READ_REG(&adapter->hw, VPTCL); - adapter->stats.vptch += IXGB_READ_REG(&adapter->hw, VPTCH); - adapter->stats.jptcl += IXGB_READ_REG(&adapter->hw, JPTCL); - adapter->stats.jptch += IXGB_READ_REG(&adapter->hw, JPTCH); - adapter->stats.gotcl += IXGB_READ_REG(&adapter->hw, GOTCL); - adapter->stats.gotch += IXGB_READ_REG(&adapter->hw, GOTCH); - adapter->stats.totl += IXGB_READ_REG(&adapter->hw, TOTL); - adapter->stats.toth += IXGB_READ_REG(&adapter->hw, TOTH); - adapter->stats.dc += IXGB_READ_REG(&adapter->hw, DC); - adapter->stats.plt64c += IXGB_READ_REG(&adapter->hw, PLT64C); - adapter->stats.tsctc += IXGB_READ_REG(&adapter->hw, TSCTC); - adapter->stats.tsctfc += IXGB_READ_REG(&adapter->hw, TSCTFC); - adapter->stats.ibic += IXGB_READ_REG(&adapter->hw, IBIC); - adapter->stats.rfc += IXGB_READ_REG(&adapter->hw, RFC); - adapter->stats.lfc += IXGB_READ_REG(&adapter->hw, LFC); - adapter->stats.pfrc += IXGB_READ_REG(&adapter->hw, PFRC); - adapter->stats.pftc += IXGB_READ_REG(&adapter->hw, PFTC); - adapter->stats.mcfrc += IXGB_READ_REG(&adapter->hw, MCFRC); - adapter->stats.mcftc += IXGB_READ_REG(&adapter->hw, MCFTC); - adapter->stats.xonrxc += IXGB_READ_REG(&adapter->hw, XONRXC); - adapter->stats.xontxc += IXGB_READ_REG(&adapter->hw, XONTXC); - adapter->stats.xoffrxc += IXGB_READ_REG(&adapter->hw, XOFFRXC); - adapter->stats.xofftxc += IXGB_READ_REG(&adapter->hw, XOFFTXC); - adapter->stats.rjc += IXGB_READ_REG(&adapter->hw, RJC); - - /* Fill out the OS statistics structure */ - - netdev->stats.rx_packets = adapter->stats.gprcl; - netdev->stats.tx_packets = adapter->stats.gptcl; - netdev->stats.rx_bytes = adapter->stats.gorcl; - netdev->stats.tx_bytes = adapter->stats.gotcl; - netdev->stats.multicast = adapter->stats.mprcl; - netdev->stats.collisions = 0; - - /* ignore RLEC as it reports errors for padded (<64bytes) frames - * with a length in the type/len field */ - netdev->stats.rx_errors = - /* adapter->stats.rnbc + */ adapter->stats.crcerrs + - adapter->stats.ruc + - adapter->stats.roc /*+ adapter->stats.rlec */ + - adapter->stats.icbc + - adapter->stats.ecbc + adapter->stats.mpc; - - /* see above - * netdev->stats.rx_length_errors = adapter->stats.rlec; - */ - - netdev->stats.rx_crc_errors = adapter->stats.crcerrs; - netdev->stats.rx_fifo_errors = adapter->stats.mpc; - netdev->stats.rx_missed_errors = adapter->stats.mpc; - netdev->stats.rx_over_errors = adapter->stats.mpc; - - netdev->stats.tx_errors = 0; - netdev->stats.rx_frame_errors = 0; - netdev->stats.tx_aborted_errors = 0; - netdev->stats.tx_carrier_errors = 0; - netdev->stats.tx_fifo_errors = 0; - netdev->stats.tx_heartbeat_errors = 0; - netdev->stats.tx_window_errors = 0; -} - -/** - * ixgb_intr - Interrupt Handler - * @irq: interrupt number - * @data: pointer to a network interface device structure - **/ - -static irqreturn_t -ixgb_intr(int irq, void *data) -{ - struct net_device *netdev = data; - struct ixgb_adapter *adapter = netdev_priv(netdev); - struct ixgb_hw *hw = &adapter->hw; - u32 icr = IXGB_READ_REG(hw, ICR); - - if (unlikely(!icr)) - return IRQ_NONE; /* Not our interrupt */ - - if (unlikely(icr & (IXGB_INT_RXSEQ | IXGB_INT_LSC))) - if (!test_bit(__IXGB_DOWN, &adapter->flags)) - mod_timer(&adapter->watchdog_timer, jiffies); - - if (napi_schedule_prep(&adapter->napi)) { - - /* Disable interrupts and register for poll. The flush - of the posted write is intentionally left out. - */ - - IXGB_WRITE_REG(&adapter->hw, IMC, ~0); - __napi_schedule(&adapter->napi); - } - return IRQ_HANDLED; -} - -/** - * ixgb_clean - NAPI Rx polling callback - * @napi: napi struct pointer - * @budget: max number of receives to clean - **/ - -static int -ixgb_clean(struct napi_struct *napi, int budget) -{ - struct ixgb_adapter *adapter = container_of(napi, struct ixgb_adapter, napi); - int work_done = 0; - - ixgb_clean_tx_irq(adapter); - ixgb_clean_rx_irq(adapter, &work_done, budget); - - /* If budget not fully consumed, exit the polling mode */ - if (work_done < budget) { - napi_complete_done(napi, work_done); - if (!test_bit(__IXGB_DOWN, &adapter->flags)) - ixgb_irq_enable(adapter); - } - - return work_done; -} - -/** - * ixgb_clean_tx_irq - Reclaim resources after transmit completes - * @adapter: board private structure - **/ - -static bool -ixgb_clean_tx_irq(struct ixgb_adapter *adapter) -{ - struct ixgb_desc_ring *tx_ring = &adapter->tx_ring; - struct net_device *netdev = adapter->netdev; - struct ixgb_tx_desc *tx_desc, *eop_desc; - struct ixgb_buffer *buffer_info; - unsigned int i, eop; - bool cleaned = false; - - i = tx_ring->next_to_clean; - eop = tx_ring->buffer_info[i].next_to_watch; - eop_desc = IXGB_TX_DESC(*tx_ring, eop); - - while (eop_desc->status & IXGB_TX_DESC_STATUS_DD) { - - rmb(); /* read buffer_info after eop_desc */ - for (cleaned = false; !cleaned; ) { - tx_desc = IXGB_TX_DESC(*tx_ring, i); - buffer_info = &tx_ring->buffer_info[i]; - - if (tx_desc->popts & - (IXGB_TX_DESC_POPTS_TXSM | - IXGB_TX_DESC_POPTS_IXSM)) - adapter->hw_csum_tx_good++; - - ixgb_unmap_and_free_tx_resource(adapter, buffer_info); - - *(u32 *)&(tx_desc->status) = 0; - - cleaned = (i == eop); - if (++i == tx_ring->count) i = 0; - } - - eop = tx_ring->buffer_info[i].next_to_watch; - eop_desc = IXGB_TX_DESC(*tx_ring, eop); - } - - tx_ring->next_to_clean = i; - - if (unlikely(cleaned && netif_carrier_ok(netdev) && - IXGB_DESC_UNUSED(tx_ring) >= DESC_NEEDED)) { - /* Make sure that anybody stopping the queue after this - * sees the new next_to_clean. */ - smp_mb(); - - if (netif_queue_stopped(netdev) && - !(test_bit(__IXGB_DOWN, &adapter->flags))) { - netif_wake_queue(netdev); - ++adapter->restart_queue; - } - } - - if (adapter->detect_tx_hung) { - /* detect a transmit hang in hardware, this serializes the - * check with the clearing of time_stamp and movement of i */ - adapter->detect_tx_hung = false; - if (tx_ring->buffer_info[eop].time_stamp && - time_after(jiffies, tx_ring->buffer_info[eop].time_stamp + HZ) - && !(IXGB_READ_REG(&adapter->hw, STATUS) & - IXGB_STATUS_TXOFF)) { - /* detected Tx unit hang */ - netif_err(adapter, drv, adapter->netdev, - "Detected Tx Unit Hang\n" - " TDH <%x>\n" - " TDT <%x>\n" - " next_to_use <%x>\n" - " next_to_clean <%x>\n" - "buffer_info[next_to_clean]\n" - " time_stamp <%lx>\n" - " next_to_watch <%x>\n" - " jiffies <%lx>\n" - " next_to_watch.status <%x>\n", - IXGB_READ_REG(&adapter->hw, TDH), - IXGB_READ_REG(&adapter->hw, TDT), - tx_ring->next_to_use, - tx_ring->next_to_clean, - tx_ring->buffer_info[eop].time_stamp, - eop, - jiffies, - eop_desc->status); - netif_stop_queue(netdev); - } - } - - return cleaned; -} - -/** - * ixgb_rx_checksum - Receive Checksum Offload for 82597. - * @adapter: board private structure - * @rx_desc: receive descriptor - * @skb: socket buffer with received data - **/ - -static void -ixgb_rx_checksum(struct ixgb_adapter *adapter, - struct ixgb_rx_desc *rx_desc, - struct sk_buff *skb) -{ - /* Ignore Checksum bit is set OR - * TCP Checksum has not been calculated - */ - if ((rx_desc->status & IXGB_RX_DESC_STATUS_IXSM) || - (!(rx_desc->status & IXGB_RX_DESC_STATUS_TCPCS))) { - skb_checksum_none_assert(skb); - return; - } - - /* At this point we know the hardware did the TCP checksum */ - /* now look at the TCP checksum error bit */ - if (rx_desc->errors & IXGB_RX_DESC_ERRORS_TCPE) { - /* let the stack verify checksum errors */ - skb_checksum_none_assert(skb); - adapter->hw_csum_rx_error++; - } else { - /* TCP checksum is good */ - skb->ip_summed = CHECKSUM_UNNECESSARY; - adapter->hw_csum_rx_good++; - } -} - -/* - * this should improve performance for small packets with large amounts - * of reassembly being done in the stack - */ -static void ixgb_check_copybreak(struct napi_struct *napi, - struct ixgb_buffer *buffer_info, - u32 length, struct sk_buff **skb) -{ - struct sk_buff *new_skb; - - if (length > copybreak) - return; - - new_skb = napi_alloc_skb(napi, length); - if (!new_skb) - return; - - skb_copy_to_linear_data_offset(new_skb, -NET_IP_ALIGN, - (*skb)->data - NET_IP_ALIGN, - length + NET_IP_ALIGN); - /* save the skb in buffer_info as good */ - buffer_info->skb = *skb; - *skb = new_skb; -} - -/** - * ixgb_clean_rx_irq - Send received data up the network stack, - * @adapter: board private structure - * @work_done: output pointer to amount of packets cleaned - * @work_to_do: how much work we can complete - **/ - -static bool -ixgb_clean_rx_irq(struct ixgb_adapter *adapter, int *work_done, int work_to_do) -{ - struct ixgb_desc_ring *rx_ring = &adapter->rx_ring; - struct net_device *netdev = adapter->netdev; - struct pci_dev *pdev = adapter->pdev; - struct ixgb_rx_desc *rx_desc, *next_rxd; - struct ixgb_buffer *buffer_info, *next_buffer, *next2_buffer; - u32 length; - unsigned int i, j; - int cleaned_count = 0; - bool cleaned = false; - - i = rx_ring->next_to_clean; - rx_desc = IXGB_RX_DESC(*rx_ring, i); - buffer_info = &rx_ring->buffer_info[i]; - - while (rx_desc->status & IXGB_RX_DESC_STATUS_DD) { - struct sk_buff *skb; - u8 status; - - if (*work_done >= work_to_do) - break; - - (*work_done)++; - rmb(); /* read descriptor and rx_buffer_info after status DD */ - status = rx_desc->status; - skb = buffer_info->skb; - buffer_info->skb = NULL; - - prefetch(skb->data - NET_IP_ALIGN); - - if (++i == rx_ring->count) - i = 0; - next_rxd = IXGB_RX_DESC(*rx_ring, i); - prefetch(next_rxd); - - j = i + 1; - if (j == rx_ring->count) - j = 0; - next2_buffer = &rx_ring->buffer_info[j]; - prefetch(next2_buffer); - - next_buffer = &rx_ring->buffer_info[i]; - - cleaned = true; - cleaned_count++; - - dma_unmap_single(&pdev->dev, - buffer_info->dma, - buffer_info->length, - DMA_FROM_DEVICE); - buffer_info->dma = 0; - - length = le16_to_cpu(rx_desc->length); - rx_desc->length = 0; - - if (unlikely(!(status & IXGB_RX_DESC_STATUS_EOP))) { - - /* All receives must fit into a single buffer */ - - pr_debug("Receive packet consumed multiple buffers length<%x>\n", - length); - - dev_kfree_skb_irq(skb); - goto rxdesc_done; - } - - if (unlikely(rx_desc->errors & - (IXGB_RX_DESC_ERRORS_CE | IXGB_RX_DESC_ERRORS_SE | - IXGB_RX_DESC_ERRORS_P | IXGB_RX_DESC_ERRORS_RXE))) { - dev_kfree_skb_irq(skb); - goto rxdesc_done; - } - - ixgb_check_copybreak(&adapter->napi, buffer_info, length, &skb); - - /* Good Receive */ - skb_put(skb, length); - - /* Receive Checksum Offload */ - ixgb_rx_checksum(adapter, rx_desc, skb); - - skb->protocol = eth_type_trans(skb, netdev); - if (status & IXGB_RX_DESC_STATUS_VP) - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), - le16_to_cpu(rx_desc->special)); - - netif_receive_skb(skb); - -rxdesc_done: - /* clean up descriptor, might be written over by hw */ - rx_desc->status = 0; - - /* return some buffers to hardware, one at a time is too slow */ - if (unlikely(cleaned_count >= IXGB_RX_BUFFER_WRITE)) { - ixgb_alloc_rx_buffers(adapter, cleaned_count); - cleaned_count = 0; - } - - /* use prefetched values */ - rx_desc = next_rxd; - buffer_info = next_buffer; - } - - rx_ring->next_to_clean = i; - - cleaned_count = IXGB_DESC_UNUSED(rx_ring); - if (cleaned_count) - ixgb_alloc_rx_buffers(adapter, cleaned_count); - - return cleaned; -} - -/** - * ixgb_alloc_rx_buffers - Replace used receive buffers - * @adapter: address of board private structure - * @cleaned_count: how many buffers to allocate - **/ - -static void -ixgb_alloc_rx_buffers(struct ixgb_adapter *adapter, int cleaned_count) -{ - struct ixgb_desc_ring *rx_ring = &adapter->rx_ring; - struct net_device *netdev = adapter->netdev; - struct pci_dev *pdev = adapter->pdev; - struct ixgb_rx_desc *rx_desc; - struct ixgb_buffer *buffer_info; - struct sk_buff *skb; - unsigned int i; - long cleancount; - - i = rx_ring->next_to_use; - buffer_info = &rx_ring->buffer_info[i]; - cleancount = IXGB_DESC_UNUSED(rx_ring); - - - /* leave three descriptors unused */ - while (--cleancount > 2 && cleaned_count--) { - /* recycle! its good for you */ - skb = buffer_info->skb; - if (skb) { - skb_trim(skb, 0); - goto map_skb; - } - - skb = netdev_alloc_skb_ip_align(netdev, adapter->rx_buffer_len); - if (unlikely(!skb)) { - /* Better luck next round */ - adapter->alloc_rx_buff_failed++; - break; - } - - buffer_info->skb = skb; - buffer_info->length = adapter->rx_buffer_len; -map_skb: - buffer_info->dma = dma_map_single(&pdev->dev, - skb->data, - adapter->rx_buffer_len, - DMA_FROM_DEVICE); - if (dma_mapping_error(&pdev->dev, buffer_info->dma)) { - adapter->alloc_rx_buff_failed++; - break; - } - - rx_desc = IXGB_RX_DESC(*rx_ring, i); - rx_desc->buff_addr = cpu_to_le64(buffer_info->dma); - /* guarantee DD bit not set now before h/w gets descriptor - * this is the rest of the workaround for h/w double - * writeback. */ - rx_desc->status = 0; - - - if (++i == rx_ring->count) - i = 0; - buffer_info = &rx_ring->buffer_info[i]; - } - - if (likely(rx_ring->next_to_use != i)) { - rx_ring->next_to_use = i; - if (unlikely(i-- == 0)) - i = (rx_ring->count - 1); - - /* Force memory writes to complete before letting h/w - * know there are new descriptors to fetch. (Only - * applicable for weak-ordered memory model archs, such - * as IA-64). */ - wmb(); - IXGB_WRITE_REG(&adapter->hw, RDT, i); - } -} - -static void -ixgb_vlan_strip_enable(struct ixgb_adapter *adapter) -{ - u32 ctrl; - - /* enable VLAN tag insert/strip */ - ctrl = IXGB_READ_REG(&adapter->hw, CTRL0); - ctrl |= IXGB_CTRL0_VME; - IXGB_WRITE_REG(&adapter->hw, CTRL0, ctrl); -} - -static void -ixgb_vlan_strip_disable(struct ixgb_adapter *adapter) -{ - u32 ctrl; - - /* disable VLAN tag insert/strip */ - ctrl = IXGB_READ_REG(&adapter->hw, CTRL0); - ctrl &= ~IXGB_CTRL0_VME; - IXGB_WRITE_REG(&adapter->hw, CTRL0, ctrl); -} - -static int -ixgb_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - u32 vfta, index; - - /* add VID to filter table */ - - index = (vid >> 5) & 0x7F; - vfta = IXGB_READ_REG_ARRAY(&adapter->hw, VFTA, index); - vfta |= (1 << (vid & 0x1F)); - ixgb_write_vfta(&adapter->hw, index, vfta); - set_bit(vid, adapter->active_vlans); - - return 0; -} - -static int -ixgb_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid) -{ - struct ixgb_adapter *adapter = netdev_priv(netdev); - u32 vfta, index; - - /* remove VID from filter table */ - - index = (vid >> 5) & 0x7F; - vfta = IXGB_READ_REG_ARRAY(&adapter->hw, VFTA, index); - vfta &= ~(1 << (vid & 0x1F)); - ixgb_write_vfta(&adapter->hw, index, vfta); - clear_bit(vid, adapter->active_vlans); - - return 0; -} - -static void -ixgb_restore_vlan(struct ixgb_adapter *adapter) -{ - u16 vid; - - for_each_set_bit(vid, adapter->active_vlans, VLAN_N_VID) - ixgb_vlan_rx_add_vid(adapter->netdev, htons(ETH_P_8021Q), vid); -} - -/** - * ixgb_io_error_detected - called when PCI error is detected - * @pdev: pointer to pci device with error - * @state: pci channel state after error - * - * This callback is called by the PCI subsystem whenever - * a PCI bus error is detected. - */ -static pci_ers_result_t ixgb_io_error_detected(struct pci_dev *pdev, - pci_channel_state_t state) -{ - struct net_device *netdev = pci_get_drvdata(pdev); - struct ixgb_adapter *adapter = netdev_priv(netdev); - - netif_device_detach(netdev); - - if (state == pci_channel_io_perm_failure) - return PCI_ERS_RESULT_DISCONNECT; - - if (netif_running(netdev)) - ixgb_down(adapter, true); - - pci_disable_device(pdev); - - /* Request a slot reset. */ - return PCI_ERS_RESULT_NEED_RESET; -} - -/** - * ixgb_io_slot_reset - called after the pci bus has been reset. - * @pdev: pointer to pci device with error - * - * This callback is called after the PCI bus has been reset. - * Basically, this tries to restart the card from scratch. - * This is a shortened version of the device probe/discovery code, - * it resembles the first-half of the ixgb_probe() routine. - */ -static pci_ers_result_t ixgb_io_slot_reset(struct pci_dev *pdev) -{ - struct net_device *netdev = pci_get_drvdata(pdev); - struct ixgb_adapter *adapter = netdev_priv(netdev); - u8 addr[ETH_ALEN]; - - if (pci_enable_device(pdev)) { - netif_err(adapter, probe, adapter->netdev, - "Cannot re-enable PCI device after reset\n"); - return PCI_ERS_RESULT_DISCONNECT; - } - - /* Perform card reset only on one instance of the card */ - if (0 != PCI_FUNC (pdev->devfn)) - return PCI_ERS_RESULT_RECOVERED; - - pci_set_master(pdev); - - netif_carrier_off(netdev); - netif_stop_queue(netdev); - ixgb_reset(adapter); - - /* Make sure the EEPROM is good */ - if (!ixgb_validate_eeprom_checksum(&adapter->hw)) { - netif_err(adapter, probe, adapter->netdev, - "After reset, the EEPROM checksum is not valid\n"); - return PCI_ERS_RESULT_DISCONNECT; - } - ixgb_get_ee_mac_addr(&adapter->hw, addr); - eth_hw_addr_set(netdev, addr); - memcpy(netdev->perm_addr, netdev->dev_addr, netdev->addr_len); - - if (!is_valid_ether_addr(netdev->perm_addr)) { - netif_err(adapter, probe, adapter->netdev, - "After reset, invalid MAC address\n"); - return PCI_ERS_RESULT_DISCONNECT; - } - - return PCI_ERS_RESULT_RECOVERED; -} - -/** - * ixgb_io_resume - called when its OK to resume normal operations - * @pdev: pointer to pci device with error - * - * The error recovery driver tells us that its OK to resume - * normal operation. Implementation resembles the second-half - * of the ixgb_probe() routine. - */ -static void ixgb_io_resume(struct pci_dev *pdev) -{ - struct net_device *netdev = pci_get_drvdata(pdev); - struct ixgb_adapter *adapter = netdev_priv(netdev); - - pci_set_master(pdev); - - if (netif_running(netdev)) { - if (ixgb_up(adapter)) { - pr_err("can't bring device back up after reset\n"); - return; - } - } - - netif_device_attach(netdev); - mod_timer(&adapter->watchdog_timer, jiffies); -} - -/* ixgb_main.c */ diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_osdep.h b/drivers/net/ethernet/intel/ixgb/ixgb_osdep.h deleted file mode 100644 index 7bd54efa698d..000000000000 --- a/drivers/net/ethernet/intel/ixgb/ixgb_osdep.h +++ /dev/null @@ -1,39 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 1999 - 2008 Intel Corporation. */ - -/* glue for the OS independent part of ixgb - * includes register access macros - */ - -#ifndef _IXGB_OSDEP_H_ -#define _IXGB_OSDEP_H_ - -#include <linux/types.h> -#include <linux/delay.h> -#include <asm/io.h> -#include <linux/interrupt.h> -#include <linux/sched.h> -#include <linux/if_ether.h> - -#undef ASSERT -#define ASSERT(x) BUG_ON(!(x)) - -#define ENTER() pr_debug("%s\n", __func__); - -#define IXGB_WRITE_REG(a, reg, value) ( \ - writel((value), ((a)->hw_addr + IXGB_##reg))) - -#define IXGB_READ_REG(a, reg) ( \ - readl((a)->hw_addr + IXGB_##reg)) - -#define IXGB_WRITE_REG_ARRAY(a, reg, offset, value) ( \ - writel((value), ((a)->hw_addr + IXGB_##reg + ((offset) << 2)))) - -#define IXGB_READ_REG_ARRAY(a, reg, offset) ( \ - readl((a)->hw_addr + IXGB_##reg + ((offset) << 2))) - -#define IXGB_WRITE_FLUSH(a) IXGB_READ_REG(a, STATUS) - -#define IXGB_MEMCPY memcpy - -#endif /* _IXGB_OSDEP_H_ */ diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_param.c b/drivers/net/ethernet/intel/ixgb/ixgb_param.c deleted file mode 100644 index d40f96250691..000000000000 --- a/drivers/net/ethernet/intel/ixgb/ixgb_param.c +++ /dev/null @@ -1,442 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 1999 - 2008 Intel Corporation. */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include "ixgb.h" - -/* This is the only thing that needs to be changed to adjust the - * maximum number of ports that the driver can manage. - */ - -#define IXGB_MAX_NIC 8 - -#define OPTION_UNSET -1 -#define OPTION_DISABLED 0 -#define OPTION_ENABLED 1 - -/* All parameters are treated the same, as an integer array of values. - * This macro just reduces the need to repeat the same declaration code - * over and over (plus this helps to avoid typo bugs). - */ - -#define IXGB_PARAM_INIT { [0 ... IXGB_MAX_NIC] = OPTION_UNSET } -#define IXGB_PARAM(X, desc) \ - static int X[IXGB_MAX_NIC+1] \ - = IXGB_PARAM_INIT; \ - static unsigned int num_##X = 0; \ - module_param_array_named(X, X, int, &num_##X, 0); \ - MODULE_PARM_DESC(X, desc); - -/* Transmit Descriptor Count - * - * Valid Range: 64-4096 - * - * Default Value: 256 - */ - -IXGB_PARAM(TxDescriptors, "Number of transmit descriptors"); - -/* Receive Descriptor Count - * - * Valid Range: 64-4096 - * - * Default Value: 1024 - */ - -IXGB_PARAM(RxDescriptors, "Number of receive descriptors"); - -/* User Specified Flow Control Override - * - * Valid Range: 0-3 - * - 0 - No Flow Control - * - 1 - Rx only, respond to PAUSE frames but do not generate them - * - 2 - Tx only, generate PAUSE frames but ignore them on receive - * - 3 - Full Flow Control Support - * - * Default Value: 2 - Tx only (silicon bug avoidance) - */ - -IXGB_PARAM(FlowControl, "Flow Control setting"); - -/* XsumRX - Receive Checksum Offload Enable/Disable - * - * Valid Range: 0, 1 - * - 0 - disables all checksum offload - * - 1 - enables receive IP/TCP/UDP checksum offload - * on 82597 based NICs - * - * Default Value: 1 - */ - -IXGB_PARAM(XsumRX, "Disable or enable Receive Checksum offload"); - -/* Transmit Interrupt Delay in units of 0.8192 microseconds - * - * Valid Range: 0-65535 - * - * Default Value: 32 - */ - -IXGB_PARAM(TxIntDelay, "Transmit Interrupt Delay"); - -/* Receive Interrupt Delay in units of 0.8192 microseconds - * - * Valid Range: 0-65535 - * - * Default Value: 72 - */ - -IXGB_PARAM(RxIntDelay, "Receive Interrupt Delay"); - -/* Receive Flow control high threshold (when we send a pause frame) - * (FCRTH) - * - * Valid Range: 1,536 - 262,136 (0x600 - 0x3FFF8, 8 byte granularity) - * - * Default Value: 196,608 (0x30000) - */ - -IXGB_PARAM(RxFCHighThresh, "Receive Flow Control High Threshold"); - -/* Receive Flow control low threshold (when we send a resume frame) - * (FCRTL) - * - * Valid Range: 64 - 262,136 (0x40 - 0x3FFF8, 8 byte granularity) - * must be less than high threshold by at least 8 bytes - * - * Default Value: 163,840 (0x28000) - */ - -IXGB_PARAM(RxFCLowThresh, "Receive Flow Control Low Threshold"); - -/* Flow control request timeout (how long to pause the link partner's tx) - * (PAP 15:0) - * - * Valid Range: 1 - 65535 - * - * Default Value: 65535 (0xffff) (we'll send an xon if we recover) - */ - -IXGB_PARAM(FCReqTimeout, "Flow Control Request Timeout"); - -/* Interrupt Delay Enable - * - * Valid Range: 0, 1 - * - * - 0 - disables transmit interrupt delay - * - 1 - enables transmmit interrupt delay - * - * Default Value: 1 - */ - -IXGB_PARAM(IntDelayEnable, "Transmit Interrupt Delay Enable"); - - -#define DEFAULT_TIDV 32 -#define MAX_TIDV 0xFFFF -#define MIN_TIDV 0 - -#define DEFAULT_RDTR 72 -#define MAX_RDTR 0xFFFF -#define MIN_RDTR 0 - -#define DEFAULT_FCRTL 0x28000 -#define DEFAULT_FCRTH 0x30000 -#define MIN_FCRTL 0 -#define MAX_FCRTL 0x3FFE8 -#define MIN_FCRTH 8 -#define MAX_FCRTH 0x3FFF0 - -#define MIN_FCPAUSE 1 -#define MAX_FCPAUSE 0xffff -#define DEFAULT_FCPAUSE 0xFFFF /* this may be too long */ - -struct ixgb_option { - enum { enable_option, range_option, list_option } type; - const char *name; - const char *err; - int def; - union { - struct { /* range_option info */ - int min; - int max; - } r; - struct { /* list_option info */ - int nr; - const struct ixgb_opt_list { - int i; - const char *str; - } *p; - } l; - } arg; -}; - -static int -ixgb_validate_option(unsigned int *value, const struct ixgb_option *opt) -{ - if (*value == OPTION_UNSET) { - *value = opt->def; - return 0; - } - - switch (opt->type) { - case enable_option: - switch (*value) { - case OPTION_ENABLED: - pr_info("%s Enabled\n", opt->name); - return 0; - case OPTION_DISABLED: - pr_info("%s Disabled\n", opt->name); - return 0; - } - break; - case range_option: - if (*value >= opt->arg.r.min && *value <= opt->arg.r.max) { - pr_info("%s set to %i\n", opt->name, *value); - return 0; - } - break; - case list_option: { - int i; - const struct ixgb_opt_list *ent; - - for (i = 0; i < opt->arg.l.nr; i++) { - ent = &opt->arg.l.p[i]; - if (*value == ent->i) { - if (ent->str[0] != '\0') - pr_info("%s\n", ent->str); - return 0; - } - } - } - break; - default: - BUG(); - } - - pr_info("Invalid %s specified (%i) %s\n", opt->name, *value, opt->err); - *value = opt->def; - return -1; -} - -/** - * ixgb_check_options - Range Checking for Command Line Parameters - * @adapter: board private structure - * - * This routine checks all command line parameters for valid user - * input. If an invalid value is given, or if no user specified - * value exists, a default value is used. The final value is stored - * in a variable in the adapter structure. - **/ - -void -ixgb_check_options(struct ixgb_adapter *adapter) -{ - int bd = adapter->bd_number; - if (bd >= IXGB_MAX_NIC) { - pr_notice("Warning: no configuration for board #%i\n", bd); - pr_notice("Using defaults for all values\n"); - } - - { /* Transmit Descriptor Count */ - static const struct ixgb_option opt = { - .type = range_option, - .name = "Transmit Descriptors", - .err = "using default of " __MODULE_STRING(DEFAULT_TXD), - .def = DEFAULT_TXD, - .arg = { .r = { .min = MIN_TXD, - .max = MAX_TXD}} - }; - struct ixgb_desc_ring *tx_ring = &adapter->tx_ring; - - if (num_TxDescriptors > bd) { - tx_ring->count = TxDescriptors[bd]; - ixgb_validate_option(&tx_ring->count, &opt); - } else { - tx_ring->count = opt.def; - } - tx_ring->count = ALIGN(tx_ring->count, IXGB_REQ_TX_DESCRIPTOR_MULTIPLE); - } - { /* Receive Descriptor Count */ - static const struct ixgb_option opt = { - .type = range_option, - .name = "Receive Descriptors", - .err = "using default of " __MODULE_STRING(DEFAULT_RXD), - .def = DEFAULT_RXD, - .arg = { .r = { .min = MIN_RXD, - .max = MAX_RXD}} - }; - struct ixgb_desc_ring *rx_ring = &adapter->rx_ring; - - if (num_RxDescriptors > bd) { - rx_ring->count = RxDescriptors[bd]; - ixgb_validate_option(&rx_ring->count, &opt); - } else { - rx_ring->count = opt.def; - } - rx_ring->count = ALIGN(rx_ring->count, IXGB_REQ_RX_DESCRIPTOR_MULTIPLE); - } - { /* Receive Checksum Offload Enable */ - static const struct ixgb_option opt = { - .type = enable_option, - .name = "Receive Checksum Offload", - .err = "defaulting to Enabled", - .def = OPTION_ENABLED - }; - - if (num_XsumRX > bd) { - unsigned int rx_csum = XsumRX[bd]; - ixgb_validate_option(&rx_csum, &opt); - adapter->rx_csum = rx_csum; - } else { - adapter->rx_csum = opt.def; - } - } - { /* Flow Control */ - - static const struct ixgb_opt_list fc_list[] = { - { ixgb_fc_none, "Flow Control Disabled" }, - { ixgb_fc_rx_pause, "Flow Control Receive Only" }, - { ixgb_fc_tx_pause, "Flow Control Transmit Only" }, - { ixgb_fc_full, "Flow Control Enabled" }, - { ixgb_fc_default, "Flow Control Hardware Default" } - }; - - static const struct ixgb_option opt = { - .type = list_option, - .name = "Flow Control", - .err = "reading default settings from EEPROM", - .def = ixgb_fc_tx_pause, - .arg = { .l = { .nr = ARRAY_SIZE(fc_list), - .p = fc_list }} - }; - - if (num_FlowControl > bd) { - unsigned int fc = FlowControl[bd]; - ixgb_validate_option(&fc, &opt); - adapter->hw.fc.type = fc; - } else { - adapter->hw.fc.type = opt.def; - } - } - { /* Receive Flow Control High Threshold */ - static const struct ixgb_option opt = { - .type = range_option, - .name = "Rx Flow Control High Threshold", - .err = "using default of " __MODULE_STRING(DEFAULT_FCRTH), - .def = DEFAULT_FCRTH, - .arg = { .r = { .min = MIN_FCRTH, - .max = MAX_FCRTH}} - }; - - if (num_RxFCHighThresh > bd) { - adapter->hw.fc.high_water = RxFCHighThresh[bd]; - ixgb_validate_option(&adapter->hw.fc.high_water, &opt); - } else { - adapter->hw.fc.high_water = opt.def; - } - if (!(adapter->hw.fc.type & ixgb_fc_tx_pause) ) - pr_info("Ignoring RxFCHighThresh when no RxFC\n"); - } - { /* Receive Flow Control Low Threshold */ - static const struct ixgb_option opt = { - .type = range_option, - .name = "Rx Flow Control Low Threshold", - .err = "using default of " __MODULE_STRING(DEFAULT_FCRTL), - .def = DEFAULT_FCRTL, - .arg = { .r = { .min = MIN_FCRTL, - .max = MAX_FCRTL}} - }; - - if (num_RxFCLowThresh > bd) { - adapter->hw.fc.low_water = RxFCLowThresh[bd]; - ixgb_validate_option(&adapter->hw.fc.low_water, &opt); - } else { - adapter->hw.fc.low_water = opt.def; - } - if (!(adapter->hw.fc.type & ixgb_fc_tx_pause) ) - pr_info("Ignoring RxFCLowThresh when no RxFC\n"); - } - { /* Flow Control Pause Time Request*/ - static const struct ixgb_option opt = { - .type = range_option, - .name = "Flow Control Pause Time Request", - .err = "using default of "__MODULE_STRING(DEFAULT_FCPAUSE), - .def = DEFAULT_FCPAUSE, - .arg = { .r = { .min = MIN_FCPAUSE, - .max = MAX_FCPAUSE}} - }; - - if (num_FCReqTimeout > bd) { - unsigned int pause_time = FCReqTimeout[bd]; - ixgb_validate_option(&pause_time, &opt); - adapter->hw.fc.pause_time = pause_time; - } else { - adapter->hw.fc.pause_time = opt.def; - } - if (!(adapter->hw.fc.type & ixgb_fc_tx_pause) ) - pr_info("Ignoring FCReqTimeout when no RxFC\n"); - } - /* high low and spacing check for rx flow control thresholds */ - if (adapter->hw.fc.type & ixgb_fc_tx_pause) { - /* high must be greater than low */ - if (adapter->hw.fc.high_water < (adapter->hw.fc.low_water + 8)) { - /* set defaults */ - pr_info("RxFCHighThresh must be >= (RxFCLowThresh + 8), Using Defaults\n"); - adapter->hw.fc.high_water = DEFAULT_FCRTH; - adapter->hw.fc.low_water = DEFAULT_FCRTL; - } - } - { /* Receive Interrupt Delay */ - static const struct ixgb_option opt = { - .type = range_option, - .name = "Receive Interrupt Delay", - .err = "using default of " __MODULE_STRING(DEFAULT_RDTR), - .def = DEFAULT_RDTR, - .arg = { .r = { .min = MIN_RDTR, - .max = MAX_RDTR}} - }; - - if (num_RxIntDelay > bd) { - adapter->rx_int_delay = RxIntDelay[bd]; - ixgb_validate_option(&adapter->rx_int_delay, &opt); - } else { - adapter->rx_int_delay = opt.def; - } - } - { /* Transmit Interrupt Delay */ - static const struct ixgb_option opt = { - .type = range_option, - .name = "Transmit Interrupt Delay", - .err = "using default of " __MODULE_STRING(DEFAULT_TIDV), - .def = DEFAULT_TIDV, - .arg = { .r = { .min = MIN_TIDV, - .max = MAX_TIDV}} - }; - - if (num_TxIntDelay > bd) { - adapter->tx_int_delay = TxIntDelay[bd]; - ixgb_validate_option(&adapter->tx_int_delay, &opt); - } else { - adapter->tx_int_delay = opt.def; - } - } - - { /* Transmit Interrupt Delay Enable */ - static const struct ixgb_option opt = { - .type = enable_option, - .name = "Tx Interrupt Delay Enable", - .err = "defaulting to Enabled", - .def = OPTION_ENABLED - }; - - if (num_IntDelayEnable > bd) { - unsigned int ide = IntDelayEnable[bd]; - ixgb_validate_option(&ide, &opt); - adapter->tx_int_delay_enable = ide; - } else { - adapter->tx_int_delay_enable = opt.def; - } - } -} diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 8736ca4b2628..63d4e32df029 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -9,7 +9,6 @@ #include <linux/pci.h> #include <linux/netdevice.h> #include <linux/cpumask.h> -#include <linux/aer.h> #include <linux/if_vlan.h> #include <linux/jiffies.h> #include <linux/phy.h> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 6cfc9dc16537..0bbad4a5cc2f 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -2665,6 +2665,14 @@ static int ixgbe_get_rss_hash_opts(struct ixgbe_adapter *adapter, return 0; } +static int ixgbe_rss_indir_tbl_max(struct ixgbe_adapter *adapter) +{ + if (adapter->hw.mac.type < ixgbe_mac_X550) + return 16; + else + return 64; +} + static int ixgbe_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, u32 *rule_locs) { @@ -2673,7 +2681,8 @@ static int ixgbe_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, switch (cmd->cmd) { case ETHTOOL_GRXRINGS: - cmd->data = adapter->num_rx_queues; + cmd->data = min_t(int, adapter->num_rx_queues, + ixgbe_rss_indir_tbl_max(adapter)); ret = 0; break; case ETHTOOL_GRXCLSRLCNT: @@ -3075,14 +3084,6 @@ static int ixgbe_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) return ret; } -static int ixgbe_rss_indir_tbl_max(struct ixgbe_adapter *adapter) -{ - if (adapter->hw.mac.type < ixgbe_mac_X550) - return 16; - else - return 64; -} - static u32 ixgbe_get_rxfh_key_size(struct net_device *netdev) { return IXGBE_RSS_KEY_SIZE; @@ -3131,8 +3132,8 @@ static int ixgbe_set_rxfh(struct net_device *netdev, const u32 *indir, int i; u32 reta_entries = ixgbe_rss_indir_tbl_entries(adapter); - if (hfunc) - return -EINVAL; + if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) + return -EOPNOTSUPP; /* Fill out the redirection table */ if (indir) { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index f8156fe4b1dc..0ee943db3dc9 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -1035,9 +1035,6 @@ static void ixgbe_free_q_vector(struct ixgbe_adapter *adapter, int v_idx) adapter->q_vector[v_idx] = NULL; __netif_napi_del(&q_vector->napi); - if (static_key_enabled(&ixgbe_xdp_locking_key)) - static_branch_dec(&ixgbe_xdp_locking_key); - /* * after a call to __netif_napi_del() napi may still be used and * ixgbe_get_stats64() might access the rings on this vector, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 773c35fecace..1726297f2e0d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -36,6 +36,7 @@ #include <net/tc_act/tc_mirred.h> #include <net/vxlan.h> #include <net/mpls.h> +#include <net/netdev_queues.h> #include <net/xdp_sock_drv.h> #include <net/xfrm.h> @@ -1119,6 +1120,7 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, unsigned int total_bytes = 0, total_packets = 0, total_ipsec = 0; unsigned int budget = q_vector->tx.work_limit; unsigned int i = tx_ring->next_to_clean; + struct netdev_queue *txq; if (test_bit(__IXGBE_DOWN, &adapter->state)) return true; @@ -1249,24 +1251,14 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, if (ring_is_xdp(tx_ring)) return !!budget; - netdev_tx_completed_queue(txring_txq(tx_ring), - total_packets, total_bytes); - #define TX_WAKE_THRESHOLD (DESC_NEEDED * 2) - if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) && - (ixgbe_desc_unused(tx_ring) >= TX_WAKE_THRESHOLD))) { - /* Make sure that anybody stopping the queue after this - * sees the new next_to_clean. - */ - smp_mb(); - if (__netif_subqueue_stopped(tx_ring->netdev, - tx_ring->queue_index) - && !test_bit(__IXGBE_DOWN, &adapter->state)) { - netif_wake_subqueue(tx_ring->netdev, - tx_ring->queue_index); - ++tx_ring->tx_stats.restart_queue; - } - } + txq = netdev_get_tx_queue(tx_ring->netdev, tx_ring->queue_index); + if (!__netif_txq_completed_wake(txq, total_packets, total_bytes, + ixgbe_desc_unused(tx_ring), + TX_WAKE_THRESHOLD, + !netif_carrier_ok(tx_ring->netdev) || + test_bit(__IXGBE_DOWN, &adapter->state))) + ++tx_ring->tx_stats.restart_queue; return !!budget; } @@ -6495,6 +6487,10 @@ static int ixgbe_sw_init(struct ixgbe_adapter *adapter, set_bit(0, adapter->fwd_bitmask); set_bit(__IXGBE_DOWN, &adapter->state); + /* enable locking for XDP_TX if we have more CPUs than queues */ + if (nr_cpu_ids > IXGBE_MAX_XDP_QS) + static_branch_enable(&ixgbe_xdp_locking_key); + return 0; } @@ -8270,22 +8266,10 @@ static void ixgbe_tx_olinfo_status(union ixgbe_adv_tx_desc *tx_desc, static int __ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size) { - netif_stop_subqueue(tx_ring->netdev, tx_ring->queue_index); - - /* Herbert's original patch had: - * smp_mb__after_netif_stop_queue(); - * but since that doesn't exist yet, just open code it. - */ - smp_mb(); - - /* We need to check again in a case another CPU has just - * made room available. - */ - if (likely(ixgbe_desc_unused(tx_ring) < size)) + if (!netif_subqueue_try_stop(tx_ring->netdev, tx_ring->queue_index, + ixgbe_desc_unused(tx_ring), size)) return -EBUSY; - /* A reprieve! - use start_queue because it doesn't call schedule */ - netif_start_subqueue(tx_ring->netdev, tx_ring->queue_index); ++tx_ring->tx_stats.restart_queue; return 0; } @@ -8818,7 +8802,7 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, if (skb_cow_head(skb, 0)) goto out_drop; - vhdr = (struct vlan_ethhdr *)skb->data; + vhdr = skb_vlan_eth_hdr(skb); vhdr->h_vlan_TCI = htons(tx_flags >> IXGBE_TX_FLAGS_VLAN_SHIFT); } else { @@ -10290,8 +10274,6 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) */ if (nr_cpu_ids > IXGBE_MAX_XDP_QS * 2) return -ENOMEM; - else if (nr_cpu_ids > IXGBE_MAX_XDP_QS) - static_branch_inc(&ixgbe_xdp_locking_key); old_prog = xchg(&adapter->xdp_prog, prog); need_reset = (!!prog != !!old_prog); |