diff options
Diffstat (limited to '')
48 files changed, 56000 insertions, 0 deletions
diff --git a/drivers/net/ethernet/intel/ixgbe/Makefile b/drivers/net/ethernet/intel/ixgbe/Makefile new file mode 100644 index 000000000..4fb0d9e3f --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/Makefile @@ -0,0 +1,20 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright(c) 1999 - 2018 Intel Corporation. +# +# Makefile for the Intel(R) 10GbE PCI Express ethernet driver +# + +obj-$(CONFIG_IXGBE) += ixgbe.o + +ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \ + ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \ + ixgbe_mbx.o ixgbe_x540.o ixgbe_x550.o ixgbe_lib.o ixgbe_ptp.o \ + ixgbe_xsk.o + +ixgbe-$(CONFIG_IXGBE_DCB) += ixgbe_dcb.o ixgbe_dcb_82598.o \ + ixgbe_dcb_82599.o ixgbe_dcb_nl.o + +ixgbe-$(CONFIG_IXGBE_HWMON) += ixgbe_sysfs.o +ixgbe-$(CONFIG_DEBUG_FS) += ixgbe_debugfs.o +ixgbe-$(CONFIG_FCOE:m=y) += ixgbe_fcoe.o +ixgbe-$(CONFIG_IXGBE_IPSEC) += ixgbe_ipsec.o diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h new file mode 100644 index 000000000..18251edbf --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -0,0 +1,1040 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#ifndef _IXGBE_H_ +#define _IXGBE_H_ + +#include <linux/bitops.h> +#include <linux/types.h> +#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> + +#include <linux/timecounter.h> +#include <linux/net_tstamp.h> +#include <linux/ptp_clock_kernel.h> + +#include "ixgbe_type.h" +#include "ixgbe_common.h" +#include "ixgbe_dcb.h" +#if IS_ENABLED(CONFIG_FCOE) +#define IXGBE_FCOE +#include "ixgbe_fcoe.h" +#endif /* IS_ENABLED(CONFIG_FCOE) */ +#ifdef CONFIG_IXGBE_DCA +#include <linux/dca.h> +#endif +#include "ixgbe_ipsec.h" + +#include <net/xdp.h> + +/* common prefix used by pr_<> macros */ +#undef pr_fmt +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +/* TX/RX descriptor defines */ +#define IXGBE_DEFAULT_TXD 512 +#define IXGBE_DEFAULT_TX_WORK 256 +#define IXGBE_MAX_TXD 4096 +#define IXGBE_MIN_TXD 64 + +#if (PAGE_SIZE < 8192) +#define IXGBE_DEFAULT_RXD 512 +#else +#define IXGBE_DEFAULT_RXD 128 +#endif +#define IXGBE_MAX_RXD 4096 +#define IXGBE_MIN_RXD 64 + +/* flow control */ +#define IXGBE_MIN_FCRTL 0x40 +#define IXGBE_MAX_FCRTL 0x7FF80 +#define IXGBE_MIN_FCRTH 0x600 +#define IXGBE_MAX_FCRTH 0x7FFF0 +#define IXGBE_DEFAULT_FCPAUSE 0xFFFF +#define IXGBE_MIN_FCPAUSE 0 +#define IXGBE_MAX_FCPAUSE 0xFFFF + +/* Supported Rx Buffer Sizes */ +#define IXGBE_RXBUFFER_256 256 /* Used for skb receive header */ +#define IXGBE_RXBUFFER_1536 1536 +#define IXGBE_RXBUFFER_2K 2048 +#define IXGBE_RXBUFFER_3K 3072 +#define IXGBE_RXBUFFER_4K 4096 +#define IXGBE_MAX_RXBUFFER 16384 /* largest size for a single descriptor */ + +#define IXGBE_PKT_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2)) + +/* Attempt to maximize the headroom available for incoming frames. We + * use a 2K buffer for receives and need 1536/1534 to store the data for + * the frame. This leaves us with 512 bytes of room. From that we need + * to deduct the space needed for the shared info and the padding needed + * to IP align the frame. + * + * Note: For cache line sizes 256 or larger this value is going to end + * up negative. In these cases we should fall back to the 3K + * buffers. + */ +#if (PAGE_SIZE < 8192) +#define IXGBE_MAX_2K_FRAME_BUILD_SKB (IXGBE_RXBUFFER_1536 - NET_IP_ALIGN) +#define IXGBE_2K_TOO_SMALL_WITH_PADDING \ +((NET_SKB_PAD + IXGBE_RXBUFFER_1536) > SKB_WITH_OVERHEAD(IXGBE_RXBUFFER_2K)) + +static inline int ixgbe_compute_pad(int rx_buf_len) +{ + int page_size, pad_size; + + page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2); + pad_size = SKB_WITH_OVERHEAD(page_size) - rx_buf_len; + + return pad_size; +} + +static inline int ixgbe_skb_pad(void) +{ + int rx_buf_len; + + /* If a 2K buffer cannot handle a standard Ethernet frame then + * optimize padding for a 3K buffer instead of a 1.5K buffer. + * + * For a 3K buffer we need to add enough padding to allow for + * tailroom due to NET_IP_ALIGN possibly shifting us out of + * cache-line alignment. + */ + if (IXGBE_2K_TOO_SMALL_WITH_PADDING) + rx_buf_len = IXGBE_RXBUFFER_3K + SKB_DATA_ALIGN(NET_IP_ALIGN); + else + rx_buf_len = IXGBE_RXBUFFER_1536; + + /* if needed make room for NET_IP_ALIGN */ + rx_buf_len -= NET_IP_ALIGN; + + return ixgbe_compute_pad(rx_buf_len); +} + +#define IXGBE_SKB_PAD ixgbe_skb_pad() +#else +#define IXGBE_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) +#endif + +/* + * NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we + * reserve 64 more, and skb_shared_info adds an additional 320 bytes more, + * this adds up to 448 bytes of extra data. + * + * Since netdev_alloc_skb now allocates a page fragment we can use a value + * of 256 and the resultant skb will have a truesize of 960 or less. + */ +#define IXGBE_RX_HDR_SIZE IXGBE_RXBUFFER_256 + +/* How many Rx Buffers do we bundle into one write to the hardware ? */ +#define IXGBE_RX_BUFFER_WRITE 16 /* Must be power of 2 */ + +#define IXGBE_RX_DMA_ATTR \ + (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) + +enum ixgbe_tx_flags { + /* cmd_type flags */ + IXGBE_TX_FLAGS_HW_VLAN = 0x01, + IXGBE_TX_FLAGS_TSO = 0x02, + IXGBE_TX_FLAGS_TSTAMP = 0x04, + + /* olinfo flags */ + IXGBE_TX_FLAGS_CC = 0x08, + IXGBE_TX_FLAGS_IPV4 = 0x10, + IXGBE_TX_FLAGS_CSUM = 0x20, + IXGBE_TX_FLAGS_IPSEC = 0x40, + + /* software defined flags */ + IXGBE_TX_FLAGS_SW_VLAN = 0x80, + IXGBE_TX_FLAGS_FCOE = 0x100, +}; + +/* VLAN info */ +#define IXGBE_TX_FLAGS_VLAN_MASK 0xffff0000 +#define IXGBE_TX_FLAGS_VLAN_PRIO_MASK 0xe0000000 +#define IXGBE_TX_FLAGS_VLAN_PRIO_SHIFT 29 +#define IXGBE_TX_FLAGS_VLAN_SHIFT 16 + +#define IXGBE_MAX_VF_MC_ENTRIES 30 +#define IXGBE_MAX_VF_FUNCTIONS 64 +#define IXGBE_MAX_VFTA_ENTRIES 128 +#define MAX_EMULATION_MAC_ADDRS 16 +#define IXGBE_MAX_PF_MACVLANS 15 +#define VMDQ_P(p) ((p) + adapter->ring_feature[RING_F_VMDQ].offset) +#define IXGBE_82599_VF_DEVICE_ID 0x10ED +#define IXGBE_X540_VF_DEVICE_ID 0x1515 + +struct vf_data_storage { + struct pci_dev *vfdev; + unsigned char vf_mac_addresses[ETH_ALEN]; + u16 vf_mc_hashes[IXGBE_MAX_VF_MC_ENTRIES]; + u16 num_vf_mc_hashes; + bool clear_to_send; + bool pf_set_mac; + u16 pf_vlan; /* When set, guest VLAN config not allowed. */ + u16 pf_qos; + u16 tx_rate; + u8 spoofchk_enabled; + bool rss_query_enabled; + u8 trusted; + int xcast_mode; + unsigned int vf_api; +}; + +enum ixgbevf_xcast_modes { + IXGBEVF_XCAST_MODE_NONE = 0, + IXGBEVF_XCAST_MODE_MULTI, + IXGBEVF_XCAST_MODE_ALLMULTI, + IXGBEVF_XCAST_MODE_PROMISC, +}; + +struct vf_macvlans { + struct list_head l; + int vf; + bool free; + bool is_macvlan; + u8 vf_macvlan[ETH_ALEN]; +}; + +#define IXGBE_MAX_TXD_PWR 14 +#define IXGBE_MAX_DATA_PER_TXD (1u << IXGBE_MAX_TXD_PWR) + +/* Tx Descriptors needed, worst case */ +#define TXD_USE_COUNT(S) DIV_ROUND_UP((S), IXGBE_MAX_DATA_PER_TXD) +#define DESC_NEEDED (MAX_SKB_FRAGS + 4) + +/* wrapper around a pointer to a socket buffer, + * so a DMA handle can be stored along with the buffer */ +struct ixgbe_tx_buffer { + union ixgbe_adv_tx_desc *next_to_watch; + unsigned long time_stamp; + union { + struct sk_buff *skb; + struct xdp_frame *xdpf; + }; + unsigned int bytecount; + unsigned short gso_segs; + __be16 protocol; + DEFINE_DMA_UNMAP_ADDR(dma); + DEFINE_DMA_UNMAP_LEN(len); + u32 tx_flags; +}; + +struct ixgbe_rx_buffer { + union { + struct { + struct sk_buff *skb; + dma_addr_t dma; + struct page *page; + __u32 page_offset; + __u16 pagecnt_bias; + }; + struct { + bool discard; + struct xdp_buff *xdp; + }; + }; +}; + +struct ixgbe_queue_stats { + u64 packets; + u64 bytes; +}; + +struct ixgbe_tx_queue_stats { + u64 restart_queue; + u64 tx_busy; + u64 tx_done_old; +}; + +struct ixgbe_rx_queue_stats { + u64 rsc_count; + u64 rsc_flush; + u64 non_eop_descs; + u64 alloc_rx_page; + u64 alloc_rx_page_failed; + u64 alloc_rx_buff_failed; + u64 csum_err; +}; + +#define IXGBE_TS_HDR_LEN 8 + +enum ixgbe_ring_state_t { + __IXGBE_RX_3K_BUFFER, + __IXGBE_RX_BUILD_SKB_ENABLED, + __IXGBE_RX_RSC_ENABLED, + __IXGBE_RX_CSUM_UDP_ZERO_ERR, + __IXGBE_RX_FCOE, + __IXGBE_TX_FDIR_INIT_DONE, + __IXGBE_TX_XPS_INIT_DONE, + __IXGBE_TX_DETECT_HANG, + __IXGBE_HANG_CHECK_ARMED, + __IXGBE_TX_XDP_RING, + __IXGBE_TX_DISABLED, +}; + +#define ring_uses_build_skb(ring) \ + test_bit(__IXGBE_RX_BUILD_SKB_ENABLED, &(ring)->state) + +struct ixgbe_fwd_adapter { + unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + struct net_device *netdev; + unsigned int tx_base_queue; + unsigned int rx_base_queue; + int pool; +}; + +#define check_for_tx_hang(ring) \ + test_bit(__IXGBE_TX_DETECT_HANG, &(ring)->state) +#define set_check_for_tx_hang(ring) \ + set_bit(__IXGBE_TX_DETECT_HANG, &(ring)->state) +#define clear_check_for_tx_hang(ring) \ + clear_bit(__IXGBE_TX_DETECT_HANG, &(ring)->state) +#define ring_is_rsc_enabled(ring) \ + test_bit(__IXGBE_RX_RSC_ENABLED, &(ring)->state) +#define set_ring_rsc_enabled(ring) \ + set_bit(__IXGBE_RX_RSC_ENABLED, &(ring)->state) +#define clear_ring_rsc_enabled(ring) \ + clear_bit(__IXGBE_RX_RSC_ENABLED, &(ring)->state) +#define ring_is_xdp(ring) \ + test_bit(__IXGBE_TX_XDP_RING, &(ring)->state) +#define set_ring_xdp(ring) \ + set_bit(__IXGBE_TX_XDP_RING, &(ring)->state) +#define clear_ring_xdp(ring) \ + clear_bit(__IXGBE_TX_XDP_RING, &(ring)->state) +struct ixgbe_ring { + struct ixgbe_ring *next; /* pointer to next ring in q_vector */ + struct ixgbe_q_vector *q_vector; /* backpointer to host q_vector */ + struct net_device *netdev; /* netdev ring belongs to */ + struct bpf_prog *xdp_prog; + struct device *dev; /* device for DMA mapping */ + void *desc; /* descriptor ring memory */ + union { + struct ixgbe_tx_buffer *tx_buffer_info; + struct ixgbe_rx_buffer *rx_buffer_info; + }; + unsigned long state; + u8 __iomem *tail; + dma_addr_t dma; /* phys. address of descriptor ring */ + unsigned int size; /* length in bytes */ + + u16 count; /* amount of descriptors */ + + u8 queue_index; /* needed for multiqueue queue management */ + u8 reg_idx; /* holds the special value that gets + * the hardware register offset + * associated with this ring, which is + * different for DCB and RSS modes + */ + u16 next_to_use; + u16 next_to_clean; + + unsigned long last_rx_timestamp; + + union { + u16 next_to_alloc; + struct { + u8 atr_sample_rate; + u8 atr_count; + }; + }; + + u8 dcb_tc; + struct ixgbe_queue_stats stats; + struct u64_stats_sync syncp; + union { + struct ixgbe_tx_queue_stats tx_stats; + struct ixgbe_rx_queue_stats rx_stats; + }; + struct xdp_rxq_info xdp_rxq; + struct xsk_buff_pool *xsk_pool; + u16 ring_idx; /* {rx,tx,xdp}_ring back reference idx */ + u16 rx_buf_len; +} ____cacheline_internodealigned_in_smp; + +enum ixgbe_ring_f_enum { + RING_F_NONE = 0, + RING_F_VMDQ, /* SR-IOV uses the same ring feature */ + RING_F_RSS, + RING_F_FDIR, +#ifdef IXGBE_FCOE + RING_F_FCOE, +#endif /* IXGBE_FCOE */ + + RING_F_ARRAY_SIZE /* must be last in enum set */ +}; + +#define IXGBE_MAX_RSS_INDICES 16 +#define IXGBE_MAX_RSS_INDICES_X550 63 +#define IXGBE_MAX_VMDQ_INDICES 64 +#define IXGBE_MAX_FDIR_INDICES 63 /* based on q_vector limit */ +#define IXGBE_MAX_FCOE_INDICES 8 +#define MAX_RX_QUEUES (IXGBE_MAX_FDIR_INDICES + 1) +#define MAX_TX_QUEUES (IXGBE_MAX_FDIR_INDICES + 1) +#define MAX_XDP_QUEUES (IXGBE_MAX_FDIR_INDICES + 1) +#define IXGBE_MAX_L2A_QUEUES 4 +#define IXGBE_BAD_L2A_QUEUE 3 +#define IXGBE_MAX_MACVLANS 63 + +struct ixgbe_ring_feature { + u16 limit; /* upper limit on feature indices */ + u16 indices; /* current value of indices */ + u16 mask; /* Mask used for feature to ring mapping */ + u16 offset; /* offset to start of feature */ +} ____cacheline_internodealigned_in_smp; + +#define IXGBE_82599_VMDQ_8Q_MASK 0x78 +#define IXGBE_82599_VMDQ_4Q_MASK 0x7C +#define IXGBE_82599_VMDQ_2Q_MASK 0x7E + +/* + * FCoE requires that all Rx buffers be over 2200 bytes in length. Since + * this is twice the size of a half page we need to double the page order + * for FCoE enabled Rx queues. + */ +static inline unsigned int ixgbe_rx_bufsz(struct ixgbe_ring *ring) +{ + if (test_bit(__IXGBE_RX_3K_BUFFER, &ring->state)) + return IXGBE_RXBUFFER_3K; +#if (PAGE_SIZE < 8192) + if (ring_uses_build_skb(ring)) + return IXGBE_MAX_2K_FRAME_BUILD_SKB; +#endif + return IXGBE_RXBUFFER_2K; +} + +static inline unsigned int ixgbe_rx_pg_order(struct ixgbe_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (test_bit(__IXGBE_RX_3K_BUFFER, &ring->state)) + return 1; +#endif + return 0; +} +#define ixgbe_rx_pg_size(_ring) (PAGE_SIZE << ixgbe_rx_pg_order(_ring)) + +#define IXGBE_ITR_ADAPTIVE_MIN_INC 2 +#define IXGBE_ITR_ADAPTIVE_MIN_USECS 10 +#define IXGBE_ITR_ADAPTIVE_MAX_USECS 126 +#define IXGBE_ITR_ADAPTIVE_LATENCY 0x80 +#define IXGBE_ITR_ADAPTIVE_BULK 0x00 + +struct ixgbe_ring_container { + struct ixgbe_ring *ring; /* pointer to linked list of rings */ + unsigned long next_update; /* jiffies value of last update */ + unsigned int total_bytes; /* total bytes processed this int */ + unsigned int total_packets; /* total packets processed this int */ + u16 work_limit; /* total work allowed per interrupt */ + u8 count; /* total number of rings in vector */ + u8 itr; /* current ITR setting for ring */ +}; + +/* iterator for handling rings in ring container */ +#define ixgbe_for_each_ring(pos, head) \ + for (pos = (head).ring; pos != NULL; pos = pos->next) + +#define MAX_RX_PACKET_BUFFERS ((adapter->flags & IXGBE_FLAG_DCB_ENABLED) \ + ? 8 : 1) +#define MAX_TX_PACKET_BUFFERS MAX_RX_PACKET_BUFFERS + +/* MAX_Q_VECTORS of these are allocated, + * but we only use one per queue-specific vector. + */ +struct ixgbe_q_vector { + struct ixgbe_adapter *adapter; +#ifdef CONFIG_IXGBE_DCA + int cpu; /* CPU for DCA */ +#endif + u16 v_idx; /* index of q_vector within array, also used for + * finding the bit in EICR and friends that + * represents the vector for this ring */ + u16 itr; /* Interrupt throttle rate written to EITR */ + struct ixgbe_ring_container rx, tx; + + struct napi_struct napi; + cpumask_t affinity_mask; + int numa_node; + struct rcu_head rcu; /* to avoid race with update stats on free */ + char name[IFNAMSIZ + 9]; + + /* for dynamic allocation of rings associated with this q_vector */ + struct ixgbe_ring ring[] ____cacheline_internodealigned_in_smp; +}; + +#ifdef CONFIG_IXGBE_HWMON + +#define IXGBE_HWMON_TYPE_LOC 0 +#define IXGBE_HWMON_TYPE_TEMP 1 +#define IXGBE_HWMON_TYPE_CAUTION 2 +#define IXGBE_HWMON_TYPE_MAX 3 + +struct hwmon_attr { + struct device_attribute dev_attr; + struct ixgbe_hw *hw; + struct ixgbe_thermal_diode_data *sensor; + char name[12]; +}; + +struct hwmon_buff { + struct attribute_group group; + const struct attribute_group *groups[2]; + struct attribute *attrs[IXGBE_MAX_SENSORS * 4 + 1]; + struct hwmon_attr hwmon_list[IXGBE_MAX_SENSORS * 4]; + unsigned int n_hwmon; +}; +#endif /* CONFIG_IXGBE_HWMON */ + +/* + * microsecond values for various ITR rates shifted by 2 to fit itr register + * with the first 3 bits reserved 0 + */ +#define IXGBE_MIN_RSC_ITR 24 +#define IXGBE_100K_ITR 40 +#define IXGBE_20K_ITR 200 +#define IXGBE_12K_ITR 336 + +/* ixgbe_test_staterr - tests bits in Rx descriptor status and error fields */ +static inline __le32 ixgbe_test_staterr(union ixgbe_adv_rx_desc *rx_desc, + const u32 stat_err_bits) +{ + return rx_desc->wb.upper.status_error & cpu_to_le32(stat_err_bits); +} + +static inline u16 ixgbe_desc_unused(struct ixgbe_ring *ring) +{ + u16 ntc = ring->next_to_clean; + u16 ntu = ring->next_to_use; + + return ((ntc > ntu) ? 0 : ring->count) + ntc - ntu - 1; +} + +#define IXGBE_RX_DESC(R, i) \ + (&(((union ixgbe_adv_rx_desc *)((R)->desc))[i])) +#define IXGBE_TX_DESC(R, i) \ + (&(((union ixgbe_adv_tx_desc *)((R)->desc))[i])) +#define IXGBE_TX_CTXTDESC(R, i) \ + (&(((struct ixgbe_adv_tx_context_desc *)((R)->desc))[i])) + +#define IXGBE_MAX_JUMBO_FRAME_SIZE 9728 /* Maximum Supported Size 9.5KB */ +#ifdef IXGBE_FCOE +/* Use 3K as the baby jumbo frame size for FCoE */ +#define IXGBE_FCOE_JUMBO_FRAME_SIZE 3072 +#endif /* IXGBE_FCOE */ + +#define OTHER_VECTOR 1 +#define NON_Q_VECTORS (OTHER_VECTOR) + +#define MAX_MSIX_VECTORS_82599 64 +#define MAX_Q_VECTORS_82599 64 +#define MAX_MSIX_VECTORS_82598 18 +#define MAX_Q_VECTORS_82598 16 + +struct ixgbe_mac_addr { + u8 addr[ETH_ALEN]; + u16 pool; + u16 state; /* bitmask */ +}; + +#define IXGBE_MAC_STATE_DEFAULT 0x1 +#define IXGBE_MAC_STATE_MODIFIED 0x2 +#define IXGBE_MAC_STATE_IN_USE 0x4 + +#define MAX_Q_VECTORS MAX_Q_VECTORS_82599 +#define MAX_MSIX_COUNT MAX_MSIX_VECTORS_82599 + +#define MIN_MSIX_Q_VECTORS 1 +#define MIN_MSIX_COUNT (MIN_MSIX_Q_VECTORS + NON_Q_VECTORS) + +/* default to trying for four seconds */ +#define IXGBE_TRY_LINK_TIMEOUT (4 * HZ) +#define IXGBE_SFP_POLL_JIFFIES (2 * HZ) /* SFP poll every 2 seconds */ + +/* board specific private data structure */ +struct ixgbe_adapter { + unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + /* OS defined structs */ + struct net_device *netdev; + struct bpf_prog *xdp_prog; + struct pci_dev *pdev; + struct mii_bus *mii_bus; + + unsigned long state; + + /* Some features need tri-state capability, + * thus the additional *_CAPABLE flags. + */ + u32 flags; +#define IXGBE_FLAG_MSI_ENABLED BIT(1) +#define IXGBE_FLAG_MSIX_ENABLED BIT(3) +#define IXGBE_FLAG_RX_1BUF_CAPABLE BIT(4) +#define IXGBE_FLAG_RX_PS_CAPABLE BIT(5) +#define IXGBE_FLAG_RX_PS_ENABLED BIT(6) +#define IXGBE_FLAG_DCA_ENABLED BIT(8) +#define IXGBE_FLAG_DCA_CAPABLE BIT(9) +#define IXGBE_FLAG_IMIR_ENABLED BIT(10) +#define IXGBE_FLAG_MQ_CAPABLE BIT(11) +#define IXGBE_FLAG_DCB_ENABLED BIT(12) +#define IXGBE_FLAG_VMDQ_CAPABLE BIT(13) +#define IXGBE_FLAG_VMDQ_ENABLED BIT(14) +#define IXGBE_FLAG_FAN_FAIL_CAPABLE BIT(15) +#define IXGBE_FLAG_NEED_LINK_UPDATE BIT(16) +#define IXGBE_FLAG_NEED_LINK_CONFIG BIT(17) +#define IXGBE_FLAG_FDIR_HASH_CAPABLE BIT(18) +#define IXGBE_FLAG_FDIR_PERFECT_CAPABLE BIT(19) +#define IXGBE_FLAG_FCOE_CAPABLE BIT(20) +#define IXGBE_FLAG_FCOE_ENABLED BIT(21) +#define IXGBE_FLAG_SRIOV_CAPABLE BIT(22) +#define IXGBE_FLAG_SRIOV_ENABLED BIT(23) +#define IXGBE_FLAG_RX_HWTSTAMP_ENABLED BIT(25) +#define IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER BIT(26) +#define IXGBE_FLAG_DCB_CAPABLE BIT(27) + + u32 flags2; +#define IXGBE_FLAG2_RSC_CAPABLE BIT(0) +#define IXGBE_FLAG2_RSC_ENABLED BIT(1) +#define IXGBE_FLAG2_TEMP_SENSOR_CAPABLE BIT(2) +#define IXGBE_FLAG2_TEMP_SENSOR_EVENT BIT(3) +#define IXGBE_FLAG2_SEARCH_FOR_SFP BIT(4) +#define IXGBE_FLAG2_SFP_NEEDS_RESET BIT(5) +#define IXGBE_FLAG2_FDIR_REQUIRES_REINIT BIT(7) +#define IXGBE_FLAG2_RSS_FIELD_IPV4_UDP BIT(8) +#define IXGBE_FLAG2_RSS_FIELD_IPV6_UDP BIT(9) +#define IXGBE_FLAG2_PTP_PPS_ENABLED BIT(10) +#define IXGBE_FLAG2_PHY_INTERRUPT BIT(11) +#define IXGBE_FLAG2_VLAN_PROMISC BIT(13) +#define IXGBE_FLAG2_EEE_CAPABLE BIT(14) +#define IXGBE_FLAG2_EEE_ENABLED BIT(15) +#define IXGBE_FLAG2_RX_LEGACY BIT(16) +#define IXGBE_FLAG2_IPSEC_ENABLED BIT(17) +#define IXGBE_FLAG2_VF_IPSEC_ENABLED BIT(18) + + /* Tx fast path data */ + int num_tx_queues; + u16 tx_itr_setting; + u16 tx_work_limit; + u64 tx_ipsec; + + /* Rx fast path data */ + int num_rx_queues; + u16 rx_itr_setting; + u64 rx_ipsec; + + /* Port number used to identify VXLAN traffic */ + __be16 vxlan_port; + __be16 geneve_port; + + /* XDP */ + int num_xdp_queues; + struct ixgbe_ring *xdp_ring[MAX_XDP_QUEUES]; + unsigned long *af_xdp_zc_qps; /* tracks AF_XDP ZC enabled rings */ + + /* TX */ + struct ixgbe_ring *tx_ring[MAX_TX_QUEUES] ____cacheline_aligned_in_smp; + + u64 restart_queue; + u64 lsc_int; + u32 tx_timeout_count; + + /* RX */ + struct ixgbe_ring *rx_ring[MAX_RX_QUEUES]; + int num_rx_pools; /* == num_rx_queues in 82598 */ + int num_rx_queues_per_pool; /* 1 if 82598, can be many if 82599 */ + u64 hw_csum_rx_error; + u64 hw_rx_no_dma_resources; + u64 rsc_total_count; + u64 rsc_total_flush; + u64 non_eop_descs; + u32 alloc_rx_page; + u32 alloc_rx_page_failed; + u32 alloc_rx_buff_failed; + + struct ixgbe_q_vector *q_vector[MAX_Q_VECTORS]; + + /* DCB parameters */ + struct ieee_pfc *ixgbe_ieee_pfc; + struct ieee_ets *ixgbe_ieee_ets; + struct ixgbe_dcb_config dcb_cfg; + struct ixgbe_dcb_config temp_dcb_cfg; + u8 hw_tcs; + u8 dcb_set_bitmap; + u8 dcbx_cap; + enum ixgbe_fc_mode last_lfc_mode; + + int num_q_vectors; /* current number of q_vectors for device */ + int max_q_vectors; /* true count of q_vectors for device */ + struct ixgbe_ring_feature ring_feature[RING_F_ARRAY_SIZE]; + struct msix_entry *msix_entries; + + u32 test_icr; + struct ixgbe_ring test_tx_ring; + struct ixgbe_ring test_rx_ring; + + /* structs defined in ixgbe_hw.h */ + struct ixgbe_hw hw; + u16 msg_enable; + struct ixgbe_hw_stats stats; + + u64 tx_busy; + unsigned int tx_ring_count; + unsigned int xdp_ring_count; + unsigned int rx_ring_count; + + u32 link_speed; + bool link_up; + unsigned long sfp_poll_time; + unsigned long link_check_timeout; + + struct timer_list service_timer; + struct work_struct service_task; + + struct hlist_head fdir_filter_list; + unsigned long fdir_overflow; /* number of times ATR was backed off */ + union ixgbe_atr_input fdir_mask; + int fdir_filter_count; + u32 fdir_pballoc; + u32 atr_sample_rate; + spinlock_t fdir_perfect_lock; + +#ifdef IXGBE_FCOE + struct ixgbe_fcoe fcoe; +#endif /* IXGBE_FCOE */ + u8 __iomem *io_addr; /* Mainly for iounmap use */ + u32 wol; + + u16 bridge_mode; + + char eeprom_id[NVM_VER_SIZE]; + u16 eeprom_cap; + + u32 interrupt_event; + u32 led_reg; + + struct ptp_clock *ptp_clock; + struct ptp_clock_info ptp_caps; + struct work_struct ptp_tx_work; + struct sk_buff *ptp_tx_skb; + struct hwtstamp_config tstamp_config; + unsigned long ptp_tx_start; + unsigned long last_overflow_check; + unsigned long last_rx_ptp_check; + unsigned long last_rx_timestamp; + spinlock_t tmreg_lock; + struct cyclecounter hw_cc; + struct timecounter hw_tc; + u32 base_incval; + u32 tx_hwtstamp_timeouts; + u32 tx_hwtstamp_skipped; + u32 rx_hwtstamp_cleared; + void (*ptp_setup_sdp)(struct ixgbe_adapter *); + + /* SR-IOV */ + DECLARE_BITMAP(active_vfs, IXGBE_MAX_VF_FUNCTIONS); + unsigned int num_vfs; + struct vf_data_storage *vfinfo; + int vf_rate_link_speed; + struct vf_macvlans vf_mvs; + struct vf_macvlans *mv_list; + + u32 timer_event_accumulator; + u32 vferr_refcount; + struct ixgbe_mac_addr *mac_table; + struct kobject *info_kobj; +#ifdef CONFIG_IXGBE_HWMON + struct hwmon_buff *ixgbe_hwmon_buff; +#endif /* CONFIG_IXGBE_HWMON */ +#ifdef CONFIG_DEBUG_FS + struct dentry *ixgbe_dbg_adapter; +#endif /*CONFIG_DEBUG_FS*/ + + u8 default_up; + /* Bitmask indicating in use pools */ + DECLARE_BITMAP(fwd_bitmask, IXGBE_MAX_MACVLANS + 1); + +#define IXGBE_MAX_LINK_HANDLE 10 + struct ixgbe_jump_table *jump_tables[IXGBE_MAX_LINK_HANDLE]; + unsigned long tables; + +/* maximum number of RETA entries among all devices supported by ixgbe + * driver: currently it's x550 device in non-SRIOV mode + */ +#define IXGBE_MAX_RETA_ENTRIES 512 + u8 rss_indir_tbl[IXGBE_MAX_RETA_ENTRIES]; + +#define IXGBE_RSS_KEY_SIZE 40 /* size of RSS Hash Key in bytes */ + u32 *rss_key; + +#ifdef CONFIG_IXGBE_IPSEC + struct ixgbe_ipsec *ipsec; +#endif /* CONFIG_IXGBE_IPSEC */ + spinlock_t vfs_lock; +}; + +static inline u8 ixgbe_max_rss_indices(struct ixgbe_adapter *adapter) +{ + switch (adapter->hw.mac.type) { + case ixgbe_mac_82598EB: + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + return IXGBE_MAX_RSS_INDICES; + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + return IXGBE_MAX_RSS_INDICES_X550; + default: + return 0; + } +} + +struct ixgbe_fdir_filter { + struct hlist_node fdir_node; + union ixgbe_atr_input filter; + u16 sw_idx; + u64 action; +}; + +enum ixgbe_state_t { + __IXGBE_TESTING, + __IXGBE_RESETTING, + __IXGBE_DOWN, + __IXGBE_DISABLED, + __IXGBE_REMOVING, + __IXGBE_SERVICE_SCHED, + __IXGBE_SERVICE_INITED, + __IXGBE_IN_SFP_INIT, + __IXGBE_PTP_RUNNING, + __IXGBE_PTP_TX_IN_PROGRESS, + __IXGBE_RESET_REQUESTED, +}; + +struct ixgbe_cb { + union { /* Union defining head/tail partner */ + struct sk_buff *head; + struct sk_buff *tail; + }; + dma_addr_t dma; + u16 append_cnt; + bool page_released; +}; +#define IXGBE_CB(skb) ((struct ixgbe_cb *)(skb)->cb) + +enum ixgbe_boards { + board_82598, + board_82599, + board_X540, + board_X550, + board_X550EM_x, + board_x550em_x_fw, + board_x550em_a, + board_x550em_a_fw, +}; + +extern const struct ixgbe_info ixgbe_82598_info; +extern const struct ixgbe_info ixgbe_82599_info; +extern const struct ixgbe_info ixgbe_X540_info; +extern const struct ixgbe_info ixgbe_X550_info; +extern const struct ixgbe_info ixgbe_X550EM_x_info; +extern const struct ixgbe_info ixgbe_x550em_x_fw_info; +extern const struct ixgbe_info ixgbe_x550em_a_info; +extern const struct ixgbe_info ixgbe_x550em_a_fw_info; +#ifdef CONFIG_IXGBE_DCB +extern const struct dcbnl_rtnl_ops ixgbe_dcbnl_ops; +#endif + +extern char ixgbe_driver_name[]; +#ifdef IXGBE_FCOE +extern char ixgbe_default_device_descr[]; +#endif /* IXGBE_FCOE */ + +int ixgbe_open(struct net_device *netdev); +int ixgbe_close(struct net_device *netdev); +void ixgbe_up(struct ixgbe_adapter *adapter); +void ixgbe_down(struct ixgbe_adapter *adapter); +void ixgbe_reinit_locked(struct ixgbe_adapter *adapter); +void ixgbe_reset(struct ixgbe_adapter *adapter); +void ixgbe_set_ethtool_ops(struct net_device *netdev); +int ixgbe_setup_rx_resources(struct ixgbe_adapter *, struct ixgbe_ring *); +int ixgbe_setup_tx_resources(struct ixgbe_ring *); +void ixgbe_free_rx_resources(struct ixgbe_ring *); +void ixgbe_free_tx_resources(struct ixgbe_ring *); +void ixgbe_configure_rx_ring(struct ixgbe_adapter *, struct ixgbe_ring *); +void ixgbe_configure_tx_ring(struct ixgbe_adapter *, struct ixgbe_ring *); +void ixgbe_disable_rx(struct ixgbe_adapter *adapter); +void ixgbe_disable_tx(struct ixgbe_adapter *adapter); +void ixgbe_update_stats(struct ixgbe_adapter *adapter); +int ixgbe_init_interrupt_scheme(struct ixgbe_adapter *adapter); +bool ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id, + u16 subdevice_id); +#ifdef CONFIG_PCI_IOV +void ixgbe_full_sync_mac_table(struct ixgbe_adapter *adapter); +#endif +int ixgbe_add_mac_filter(struct ixgbe_adapter *adapter, + const u8 *addr, u16 queue); +int ixgbe_del_mac_filter(struct ixgbe_adapter *adapter, + const u8 *addr, u16 queue); +void ixgbe_update_pf_promisc_vlvf(struct ixgbe_adapter *adapter, u32 vid); +void ixgbe_clear_interrupt_scheme(struct ixgbe_adapter *adapter); +netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *, struct ixgbe_adapter *, + struct ixgbe_ring *); +void ixgbe_unmap_and_free_tx_resource(struct ixgbe_ring *, + struct ixgbe_tx_buffer *); +void ixgbe_alloc_rx_buffers(struct ixgbe_ring *, u16); +void ixgbe_write_eitr(struct ixgbe_q_vector *); +int ixgbe_poll(struct napi_struct *napi, int budget); +int ethtool_ioctl(struct ifreq *ifr); +s32 ixgbe_reinit_fdir_tables_82599(struct ixgbe_hw *hw); +s32 ixgbe_init_fdir_signature_82599(struct ixgbe_hw *hw, u32 fdirctrl); +s32 ixgbe_init_fdir_perfect_82599(struct ixgbe_hw *hw, u32 fdirctrl); +s32 ixgbe_fdir_add_signature_filter_82599(struct ixgbe_hw *hw, + union ixgbe_atr_hash_dword input, + union ixgbe_atr_hash_dword common, + u8 queue); +s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, + union ixgbe_atr_input *input_mask); +s32 ixgbe_fdir_write_perfect_filter_82599(struct ixgbe_hw *hw, + union ixgbe_atr_input *input, + u16 soft_id, u8 queue); +s32 ixgbe_fdir_erase_perfect_filter_82599(struct ixgbe_hw *hw, + union ixgbe_atr_input *input, + u16 soft_id); +void ixgbe_atr_compute_perfect_hash_82599(union ixgbe_atr_input *input, + union ixgbe_atr_input *mask); +int ixgbe_update_ethtool_fdir_entry(struct ixgbe_adapter *adapter, + struct ixgbe_fdir_filter *input, + u16 sw_idx); +void ixgbe_set_rx_mode(struct net_device *netdev); +#ifdef CONFIG_IXGBE_DCB +void ixgbe_set_rx_drop_en(struct ixgbe_adapter *adapter); +#endif +int ixgbe_setup_tc(struct net_device *dev, u8 tc); +void ixgbe_tx_ctxtdesc(struct ixgbe_ring *, u32, u32, u32, u32); +void ixgbe_do_reset(struct net_device *netdev); +#ifdef CONFIG_IXGBE_HWMON +void ixgbe_sysfs_exit(struct ixgbe_adapter *adapter); +int ixgbe_sysfs_init(struct ixgbe_adapter *adapter); +#endif /* CONFIG_IXGBE_HWMON */ +#ifdef IXGBE_FCOE +void ixgbe_configure_fcoe(struct ixgbe_adapter *adapter); +int ixgbe_fso(struct ixgbe_ring *tx_ring, struct ixgbe_tx_buffer *first, + u8 *hdr_len); +int ixgbe_fcoe_ddp(struct ixgbe_adapter *adapter, + union ixgbe_adv_rx_desc *rx_desc, struct sk_buff *skb); +int ixgbe_fcoe_ddp_get(struct net_device *netdev, u16 xid, + struct scatterlist *sgl, unsigned int sgc); +int ixgbe_fcoe_ddp_target(struct net_device *netdev, u16 xid, + struct scatterlist *sgl, unsigned int sgc); +int ixgbe_fcoe_ddp_put(struct net_device *netdev, u16 xid); +int ixgbe_setup_fcoe_ddp_resources(struct ixgbe_adapter *adapter); +void ixgbe_free_fcoe_ddp_resources(struct ixgbe_adapter *adapter); +int ixgbe_fcoe_enable(struct net_device *netdev); +int ixgbe_fcoe_disable(struct net_device *netdev); +#ifdef CONFIG_IXGBE_DCB +u8 ixgbe_fcoe_getapp(struct ixgbe_adapter *adapter); +u8 ixgbe_fcoe_setapp(struct ixgbe_adapter *adapter, u8 up); +#endif /* CONFIG_IXGBE_DCB */ +int ixgbe_fcoe_get_wwn(struct net_device *netdev, u64 *wwn, int type); +int ixgbe_fcoe_get_hbainfo(struct net_device *netdev, + struct netdev_fcoe_hbainfo *info); +u8 ixgbe_fcoe_get_tc(struct ixgbe_adapter *adapter); +#endif /* IXGBE_FCOE */ +#ifdef CONFIG_DEBUG_FS +void ixgbe_dbg_adapter_init(struct ixgbe_adapter *adapter); +void ixgbe_dbg_adapter_exit(struct ixgbe_adapter *adapter); +void ixgbe_dbg_init(void); +void ixgbe_dbg_exit(void); +#else +static inline void ixgbe_dbg_adapter_init(struct ixgbe_adapter *adapter) {} +static inline void ixgbe_dbg_adapter_exit(struct ixgbe_adapter *adapter) {} +static inline void ixgbe_dbg_init(void) {} +static inline void ixgbe_dbg_exit(void) {} +#endif /* CONFIG_DEBUG_FS */ +static inline struct netdev_queue *txring_txq(const struct ixgbe_ring *ring) +{ + return netdev_get_tx_queue(ring->netdev, ring->queue_index); +} + +void ixgbe_ptp_init(struct ixgbe_adapter *adapter); +void ixgbe_ptp_suspend(struct ixgbe_adapter *adapter); +void ixgbe_ptp_stop(struct ixgbe_adapter *adapter); +void ixgbe_ptp_overflow_check(struct ixgbe_adapter *adapter); +void ixgbe_ptp_rx_hang(struct ixgbe_adapter *adapter); +void ixgbe_ptp_tx_hang(struct ixgbe_adapter *adapter); +void ixgbe_ptp_rx_pktstamp(struct ixgbe_q_vector *, struct sk_buff *); +void ixgbe_ptp_rx_rgtstamp(struct ixgbe_q_vector *, struct sk_buff *skb); +static inline void ixgbe_ptp_rx_hwtstamp(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + if (unlikely(ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_TSIP))) { + ixgbe_ptp_rx_pktstamp(rx_ring->q_vector, skb); + return; + } + + if (unlikely(!ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_STAT_TS))) + return; + + ixgbe_ptp_rx_rgtstamp(rx_ring->q_vector, skb); + + /* Update the last_rx_timestamp timer in order to enable watchdog check + * for error case of latched timestamp on a dropped packet. + */ + rx_ring->last_rx_timestamp = jiffies; +} + +int ixgbe_ptp_set_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr); +int ixgbe_ptp_get_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr); +void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter); +void ixgbe_ptp_reset(struct ixgbe_adapter *adapter); +void ixgbe_ptp_check_pps_event(struct ixgbe_adapter *adapter); +#ifdef CONFIG_PCI_IOV +void ixgbe_sriov_reinit(struct ixgbe_adapter *adapter); +#endif + +netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, + struct ixgbe_adapter *adapter, + struct ixgbe_ring *tx_ring); +u32 ixgbe_rss_indir_tbl_entries(struct ixgbe_adapter *adapter); +void ixgbe_store_key(struct ixgbe_adapter *adapter); +void ixgbe_store_reta(struct ixgbe_adapter *adapter); +s32 ixgbe_negotiate_fc(struct ixgbe_hw *hw, u32 adv_reg, u32 lp_reg, + u32 adv_sym, u32 adv_asm, u32 lp_sym, u32 lp_asm); +#ifdef CONFIG_IXGBE_IPSEC +void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter); +void ixgbe_stop_ipsec_offload(struct ixgbe_adapter *adapter); +void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter); +void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb); +int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring, struct ixgbe_tx_buffer *first, + struct ixgbe_ipsec_tx_data *itd); +void ixgbe_ipsec_vf_clear(struct ixgbe_adapter *adapter, u32 vf); +int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *mbuf, u32 vf); +int ixgbe_ipsec_vf_del_sa(struct ixgbe_adapter *adapter, u32 *mbuf, u32 vf); +#else +static inline void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter) { } +static inline void ixgbe_stop_ipsec_offload(struct ixgbe_adapter *adapter) { } +static inline void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter) { } +static inline void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) { } +static inline int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring, + struct ixgbe_tx_buffer *first, + struct ixgbe_ipsec_tx_data *itd) { return 0; } +static inline void ixgbe_ipsec_vf_clear(struct ixgbe_adapter *adapter, + u32 vf) { } +static inline int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, + u32 *mbuf, u32 vf) { return -EACCES; } +static inline int ixgbe_ipsec_vf_del_sa(struct ixgbe_adapter *adapter, + u32 *mbuf, u32 vf) { return -EACCES; } +#endif /* CONFIG_IXGBE_IPSEC */ + +static inline bool ixgbe_enabled_xdp_adapter(struct ixgbe_adapter *adapter) +{ + return !!adapter->xdp_prog; +} + +#endif /* _IXGBE_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c new file mode 100644 index 000000000..95c92fe89 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c @@ -0,0 +1,1196 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#include <linux/pci.h> +#include <linux/delay.h> +#include <linux/sched.h> + +#include "ixgbe.h" +#include "ixgbe_phy.h" + +#define IXGBE_82598_MAX_TX_QUEUES 32 +#define IXGBE_82598_MAX_RX_QUEUES 64 +#define IXGBE_82598_RAR_ENTRIES 16 +#define IXGBE_82598_MC_TBL_SIZE 128 +#define IXGBE_82598_VFT_TBL_SIZE 128 +#define IXGBE_82598_RX_PB_SIZE 512 + +static s32 ixgbe_setup_copper_link_82598(struct ixgbe_hw *hw, + ixgbe_link_speed speed, + bool autoneg_wait_to_complete); +static s32 ixgbe_read_i2c_eeprom_82598(struct ixgbe_hw *hw, u8 byte_offset, + u8 *eeprom_data); + +/** + * ixgbe_set_pcie_completion_timeout - set pci-e completion timeout + * @hw: pointer to the HW structure + * + * The defaults for 82598 should be in the range of 50us to 50ms, + * however the hardware default for these parts is 500us to 1ms which is less + * than the 10ms recommended by the pci-e spec. To address this we need to + * increase the value to either 10ms to 250ms for capability version 1 config, + * or 16ms to 55ms for version 2. + **/ +static void ixgbe_set_pcie_completion_timeout(struct ixgbe_hw *hw) +{ + u32 gcr = IXGBE_READ_REG(hw, IXGBE_GCR); + u16 pcie_devctl2; + + if (ixgbe_removed(hw->hw_addr)) + return; + + /* only take action if timeout value is defaulted to 0 */ + if (gcr & IXGBE_GCR_CMPL_TMOUT_MASK) + goto out; + + /* + * if capababilities version is type 1 we can write the + * timeout of 10ms to 250ms through the GCR register + */ + if (!(gcr & IXGBE_GCR_CAP_VER2)) { + gcr |= IXGBE_GCR_CMPL_TMOUT_10ms; + goto out; + } + + /* + * for version 2 capabilities we need to write the config space + * directly in order to set the completion timeout value for + * 16ms to 55ms + */ + pcie_devctl2 = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_DEVICE_CONTROL2); + pcie_devctl2 |= IXGBE_PCI_DEVICE_CONTROL2_16ms; + ixgbe_write_pci_cfg_word(hw, IXGBE_PCI_DEVICE_CONTROL2, pcie_devctl2); +out: + /* disable completion timeout resend */ + gcr &= ~IXGBE_GCR_CMPL_TMOUT_RESEND; + IXGBE_WRITE_REG(hw, IXGBE_GCR, gcr); +} + +static s32 ixgbe_get_invariants_82598(struct ixgbe_hw *hw) +{ + struct ixgbe_mac_info *mac = &hw->mac; + + /* Call PHY identify routine to get the phy type */ + ixgbe_identify_phy_generic(hw); + + mac->mcft_size = IXGBE_82598_MC_TBL_SIZE; + mac->vft_size = IXGBE_82598_VFT_TBL_SIZE; + mac->num_rar_entries = IXGBE_82598_RAR_ENTRIES; + mac->rx_pb_size = IXGBE_82598_RX_PB_SIZE; + mac->max_rx_queues = IXGBE_82598_MAX_RX_QUEUES; + mac->max_tx_queues = IXGBE_82598_MAX_TX_QUEUES; + mac->max_msix_vectors = ixgbe_get_pcie_msix_count_generic(hw); + + return 0; +} + +/** + * ixgbe_init_phy_ops_82598 - PHY/SFP specific init + * @hw: pointer to hardware structure + * + * Initialize any function pointers that were not able to be + * set during get_invariants because the PHY/SFP type was + * not known. Perform the SFP init if necessary. + * + **/ +static s32 ixgbe_init_phy_ops_82598(struct ixgbe_hw *hw) +{ + struct ixgbe_mac_info *mac = &hw->mac; + struct ixgbe_phy_info *phy = &hw->phy; + s32 ret_val; + u16 list_offset, data_offset; + + /* Identify the PHY */ + phy->ops.identify(hw); + + /* Overwrite the link function pointers if copper PHY */ + if (mac->ops.get_media_type(hw) == ixgbe_media_type_copper) { + mac->ops.setup_link = &ixgbe_setup_copper_link_82598; + mac->ops.get_link_capabilities = + &ixgbe_get_copper_link_capabilities_generic; + } + + switch (hw->phy.type) { + case ixgbe_phy_tn: + phy->ops.setup_link = &ixgbe_setup_phy_link_tnx; + phy->ops.check_link = &ixgbe_check_phy_link_tnx; + break; + case ixgbe_phy_nl: + phy->ops.reset = &ixgbe_reset_phy_nl; + + /* Call SFP+ identify routine to get the SFP+ module type */ + ret_val = phy->ops.identify_sfp(hw); + if (ret_val) + return ret_val; + if (hw->phy.sfp_type == ixgbe_sfp_type_unknown) + return IXGBE_ERR_SFP_NOT_SUPPORTED; + + /* Check to see if SFP+ module is supported */ + ret_val = ixgbe_get_sfp_init_sequence_offsets(hw, + &list_offset, + &data_offset); + if (ret_val) + return IXGBE_ERR_SFP_NOT_SUPPORTED; + break; + default: + break; + } + + return 0; +} + +/** + * ixgbe_start_hw_82598 - Prepare hardware for Tx/Rx + * @hw: pointer to hardware structure + * + * Starts the hardware using the generic start_hw function. + * Disables relaxed ordering for archs other than SPARC + * Then set pcie completion timeout + * + **/ +static s32 ixgbe_start_hw_82598(struct ixgbe_hw *hw) +{ + s32 ret_val; + + ret_val = ixgbe_start_hw_generic(hw); + if (ret_val) + return ret_val; + + /* set the completion timeout for interface */ + ixgbe_set_pcie_completion_timeout(hw); + + return 0; +} + +/** + * ixgbe_get_link_capabilities_82598 - Determines link capabilities + * @hw: pointer to hardware structure + * @speed: pointer to link speed + * @autoneg: boolean auto-negotiation value + * + * Determines the link capabilities by reading the AUTOC register. + **/ +static s32 ixgbe_get_link_capabilities_82598(struct ixgbe_hw *hw, + ixgbe_link_speed *speed, + bool *autoneg) +{ + u32 autoc = 0; + + /* + * Determine link capabilities based on the stored value of AUTOC, + * which represents EEPROM defaults. If AUTOC value has not been + * stored, use the current register value. + */ + if (hw->mac.orig_link_settings_stored) + autoc = hw->mac.orig_autoc; + else + autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC); + + switch (autoc & IXGBE_AUTOC_LMS_MASK) { + case IXGBE_AUTOC_LMS_1G_LINK_NO_AN: + *speed = IXGBE_LINK_SPEED_1GB_FULL; + *autoneg = false; + break; + + case IXGBE_AUTOC_LMS_10G_LINK_NO_AN: + *speed = IXGBE_LINK_SPEED_10GB_FULL; + *autoneg = false; + break; + + case IXGBE_AUTOC_LMS_1G_AN: + *speed = IXGBE_LINK_SPEED_1GB_FULL; + *autoneg = true; + break; + + case IXGBE_AUTOC_LMS_KX4_AN: + case IXGBE_AUTOC_LMS_KX4_AN_1G_AN: + *speed = IXGBE_LINK_SPEED_UNKNOWN; + if (autoc & IXGBE_AUTOC_KX4_SUPP) + *speed |= IXGBE_LINK_SPEED_10GB_FULL; + if (autoc & IXGBE_AUTOC_KX_SUPP) + *speed |= IXGBE_LINK_SPEED_1GB_FULL; + *autoneg = true; + break; + + default: + return IXGBE_ERR_LINK_SETUP; + } + + return 0; +} + +/** + * ixgbe_get_media_type_82598 - Determines media type + * @hw: pointer to hardware structure + * + * Returns the media type (fiber, copper, backplane) + **/ +static enum ixgbe_media_type ixgbe_get_media_type_82598(struct ixgbe_hw *hw) +{ + /* Detect if there is a copper PHY attached. */ + switch (hw->phy.type) { + case ixgbe_phy_cu_unknown: + case ixgbe_phy_tn: + return ixgbe_media_type_copper; + + default: + break; + } + + /* Media type for I82598 is based on device ID */ + switch (hw->device_id) { + case IXGBE_DEV_ID_82598: + case IXGBE_DEV_ID_82598_BX: + /* Default device ID is mezzanine card KX/KX4 */ + return ixgbe_media_type_backplane; + + case IXGBE_DEV_ID_82598AF_DUAL_PORT: + case IXGBE_DEV_ID_82598AF_SINGLE_PORT: + case IXGBE_DEV_ID_82598_DA_DUAL_PORT: + case IXGBE_DEV_ID_82598_SR_DUAL_PORT_EM: + case IXGBE_DEV_ID_82598EB_XF_LR: + case IXGBE_DEV_ID_82598EB_SFP_LOM: + return ixgbe_media_type_fiber; + + case IXGBE_DEV_ID_82598EB_CX4: + case IXGBE_DEV_ID_82598_CX4_DUAL_PORT: + return ixgbe_media_type_cx4; + + case IXGBE_DEV_ID_82598AT: + case IXGBE_DEV_ID_82598AT2: + return ixgbe_media_type_copper; + + default: + return ixgbe_media_type_unknown; + } +} + +/** + * ixgbe_fc_enable_82598 - Enable flow control + * @hw: pointer to hardware structure + * + * Enable flow control according to the current settings. + **/ +static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw) +{ + u32 fctrl_reg; + u32 rmcs_reg; + u32 reg; + u32 fcrtl, fcrth; + u32 link_speed = 0; + int i; + bool link_up; + + /* Validate the water mark configuration */ + if (!hw->fc.pause_time) + return IXGBE_ERR_INVALID_LINK_SETTINGS; + + /* Low water mark of zero causes XOFF floods */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + if ((hw->fc.current_mode & ixgbe_fc_tx_pause) && + hw->fc.high_water[i]) { + if (!hw->fc.low_water[i] || + hw->fc.low_water[i] >= hw->fc.high_water[i]) { + hw_dbg(hw, "Invalid water mark configuration\n"); + return IXGBE_ERR_INVALID_LINK_SETTINGS; + } + } + } + + /* + * On 82598 having Rx FC on causes resets while doing 1G + * so if it's on turn it off once we know link_speed. For + * more details see 82598 Specification update. + */ + hw->mac.ops.check_link(hw, &link_speed, &link_up, false); + if (link_up && link_speed == IXGBE_LINK_SPEED_1GB_FULL) { + switch (hw->fc.requested_mode) { + case ixgbe_fc_full: + hw->fc.requested_mode = ixgbe_fc_tx_pause; + break; + case ixgbe_fc_rx_pause: + hw->fc.requested_mode = ixgbe_fc_none; + break; + default: + /* no change */ + break; + } + } + + /* Negotiate the fc mode to use */ + hw->mac.ops.fc_autoneg(hw); + + /* Disable any previous flow control settings */ + fctrl_reg = IXGBE_READ_REG(hw, IXGBE_FCTRL); + fctrl_reg &= ~(IXGBE_FCTRL_RFCE | IXGBE_FCTRL_RPFCE); + + rmcs_reg = IXGBE_READ_REG(hw, IXGBE_RMCS); + rmcs_reg &= ~(IXGBE_RMCS_TFCE_PRIORITY | IXGBE_RMCS_TFCE_802_3X); + + /* + * The possible values of fc.current_mode 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.current_mode) { + case ixgbe_fc_none: + /* + * Flow control is disabled by software override or autoneg. + * The code below will actually disable it in the HW. + */ + break; + case ixgbe_fc_rx_pause: + /* + * Rx Flow control is enabled and Tx Flow control is + * disabled by software override. Since there really + * isn't a way to advertise that we are capable of RX + * Pause ONLY, we will advertise that we support both + * symmetric and asymmetric Rx PAUSE. Later, we will + * disable the adapter's ability to send PAUSE frames. + */ + fctrl_reg |= IXGBE_FCTRL_RFCE; + break; + case ixgbe_fc_tx_pause: + /* + * Tx Flow control is enabled, and Rx Flow control is + * disabled by software override. + */ + rmcs_reg |= IXGBE_RMCS_TFCE_802_3X; + break; + case ixgbe_fc_full: + /* Flow control (both Rx and Tx) is enabled by SW override. */ + fctrl_reg |= IXGBE_FCTRL_RFCE; + rmcs_reg |= IXGBE_RMCS_TFCE_802_3X; + break; + default: + hw_dbg(hw, "Flow control param set incorrectly\n"); + return IXGBE_ERR_CONFIG; + } + + /* Set 802.3x based flow control settings. */ + fctrl_reg |= IXGBE_FCTRL_DPF; + IXGBE_WRITE_REG(hw, IXGBE_FCTRL, fctrl_reg); + IXGBE_WRITE_REG(hw, IXGBE_RMCS, rmcs_reg); + + /* Set up and enable Rx high/low water mark thresholds, enable XON. */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + if ((hw->fc.current_mode & ixgbe_fc_tx_pause) && + hw->fc.high_water[i]) { + fcrtl = (hw->fc.low_water[i] << 10) | IXGBE_FCRTL_XONE; + fcrth = (hw->fc.high_water[i] << 10) | IXGBE_FCRTH_FCEN; + IXGBE_WRITE_REG(hw, IXGBE_FCRTL(i), fcrtl); + IXGBE_WRITE_REG(hw, IXGBE_FCRTH(i), fcrth); + } else { + IXGBE_WRITE_REG(hw, IXGBE_FCRTL(i), 0); + IXGBE_WRITE_REG(hw, IXGBE_FCRTH(i), 0); + } + + } + + /* Configure pause time (2 TCs per register) */ + reg = hw->fc.pause_time * 0x00010001; + for (i = 0; i < (MAX_TRAFFIC_CLASS / 2); i++) + IXGBE_WRITE_REG(hw, IXGBE_FCTTV(i), reg); + + /* Configure flow control refresh threshold value */ + IXGBE_WRITE_REG(hw, IXGBE_FCRTV, hw->fc.pause_time / 2); + + return 0; +} + +/** + * ixgbe_start_mac_link_82598 - Configures MAC link settings + * @hw: pointer to hardware structure + * @autoneg_wait_to_complete: true when waiting for completion is needed + * + * Configures link settings based on values in the ixgbe_hw struct. + * Restarts the link. Performs autonegotiation if needed. + **/ +static s32 ixgbe_start_mac_link_82598(struct ixgbe_hw *hw, + bool autoneg_wait_to_complete) +{ + u32 autoc_reg; + u32 links_reg; + u32 i; + s32 status = 0; + + /* Restart link */ + autoc_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC); + autoc_reg |= IXGBE_AUTOC_AN_RESTART; + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc_reg); + + /* Only poll for autoneg to complete if specified to do so */ + if (autoneg_wait_to_complete) { + if ((autoc_reg & IXGBE_AUTOC_LMS_MASK) == + IXGBE_AUTOC_LMS_KX4_AN || + (autoc_reg & IXGBE_AUTOC_LMS_MASK) == + IXGBE_AUTOC_LMS_KX4_AN_1G_AN) { + links_reg = 0; /* Just in case Autoneg time = 0 */ + for (i = 0; i < IXGBE_AUTO_NEG_TIME; i++) { + links_reg = IXGBE_READ_REG(hw, IXGBE_LINKS); + if (links_reg & IXGBE_LINKS_KX_AN_COMP) + break; + msleep(100); + } + if (!(links_reg & IXGBE_LINKS_KX_AN_COMP)) { + status = IXGBE_ERR_AUTONEG_NOT_COMPLETE; + hw_dbg(hw, "Autonegotiation did not complete.\n"); + } + } + } + + /* Add delay to filter out noises during initial link setup */ + msleep(50); + + return status; +} + +/** + * ixgbe_validate_link_ready - Function looks for phy link + * @hw: pointer to hardware structure + * + * Function indicates success when phy link is available. If phy is not ready + * within 5 seconds of MAC indicating link, the function returns error. + **/ +static s32 ixgbe_validate_link_ready(struct ixgbe_hw *hw) +{ + u32 timeout; + u16 an_reg; + + if (hw->device_id != IXGBE_DEV_ID_82598AT2) + return 0; + + for (timeout = 0; + timeout < IXGBE_VALIDATE_LINK_READY_TIMEOUT; timeout++) { + hw->phy.ops.read_reg(hw, MDIO_STAT1, MDIO_MMD_AN, &an_reg); + + if ((an_reg & MDIO_AN_STAT1_COMPLETE) && + (an_reg & MDIO_STAT1_LSTATUS)) + break; + + msleep(100); + } + + if (timeout == IXGBE_VALIDATE_LINK_READY_TIMEOUT) { + hw_dbg(hw, "Link was indicated but link is down\n"); + return IXGBE_ERR_LINK_SETUP; + } + + return 0; +} + +/** + * ixgbe_check_mac_link_82598 - Get link/speed status + * @hw: pointer to hardware structure + * @speed: pointer to link speed + * @link_up: true is link is up, false otherwise + * @link_up_wait_to_complete: bool used to wait for link up or not + * + * Reads the links register to determine if link is up and the current speed + **/ +static s32 ixgbe_check_mac_link_82598(struct ixgbe_hw *hw, + ixgbe_link_speed *speed, bool *link_up, + bool link_up_wait_to_complete) +{ + u32 links_reg; + u32 i; + u16 link_reg, adapt_comp_reg; + + /* + * SERDES PHY requires us to read link status from register 0xC79F. + * Bit 0 set indicates link is up/ready; clear indicates link down. + * 0xC00C is read to check that the XAUI lanes are active. Bit 0 + * clear indicates active; set indicates inactive. + */ + if (hw->phy.type == ixgbe_phy_nl) { + hw->phy.ops.read_reg(hw, 0xC79F, MDIO_MMD_PMAPMD, &link_reg); + hw->phy.ops.read_reg(hw, 0xC79F, MDIO_MMD_PMAPMD, &link_reg); + hw->phy.ops.read_reg(hw, 0xC00C, MDIO_MMD_PMAPMD, + &adapt_comp_reg); + if (link_up_wait_to_complete) { + for (i = 0; i < IXGBE_LINK_UP_TIME; i++) { + if ((link_reg & 1) && + ((adapt_comp_reg & 1) == 0)) { + *link_up = true; + break; + } else { + *link_up = false; + } + msleep(100); + hw->phy.ops.read_reg(hw, 0xC79F, + MDIO_MMD_PMAPMD, + &link_reg); + hw->phy.ops.read_reg(hw, 0xC00C, + MDIO_MMD_PMAPMD, + &adapt_comp_reg); + } + } else { + if ((link_reg & 1) && ((adapt_comp_reg & 1) == 0)) + *link_up = true; + else + *link_up = false; + } + + if (!*link_up) + return 0; + } + + links_reg = IXGBE_READ_REG(hw, IXGBE_LINKS); + if (link_up_wait_to_complete) { + for (i = 0; i < IXGBE_LINK_UP_TIME; i++) { + if (links_reg & IXGBE_LINKS_UP) { + *link_up = true; + break; + } else { + *link_up = false; + } + msleep(100); + links_reg = IXGBE_READ_REG(hw, IXGBE_LINKS); + } + } else { + if (links_reg & IXGBE_LINKS_UP) + *link_up = true; + else + *link_up = false; + } + + if (links_reg & IXGBE_LINKS_SPEED) + *speed = IXGBE_LINK_SPEED_10GB_FULL; + else + *speed = IXGBE_LINK_SPEED_1GB_FULL; + + if ((hw->device_id == IXGBE_DEV_ID_82598AT2) && *link_up && + (ixgbe_validate_link_ready(hw) != 0)) + *link_up = false; + + return 0; +} + +/** + * ixgbe_setup_mac_link_82598 - Set MAC link speed + * @hw: pointer to hardware structure + * @speed: new link speed + * @autoneg_wait_to_complete: true when waiting for completion is needed + * + * Set the link speed in the AUTOC register and restarts link. + **/ +static s32 ixgbe_setup_mac_link_82598(struct ixgbe_hw *hw, + ixgbe_link_speed speed, + bool autoneg_wait_to_complete) +{ + bool autoneg = false; + ixgbe_link_speed link_capabilities = IXGBE_LINK_SPEED_UNKNOWN; + u32 curr_autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC); + u32 autoc = curr_autoc; + u32 link_mode = autoc & IXGBE_AUTOC_LMS_MASK; + + /* Check to see if speed passed in is supported. */ + ixgbe_get_link_capabilities_82598(hw, &link_capabilities, &autoneg); + speed &= link_capabilities; + + if (speed == IXGBE_LINK_SPEED_UNKNOWN) + return IXGBE_ERR_LINK_SETUP; + + /* Set KX4/KX support according to speed requested */ + else if (link_mode == IXGBE_AUTOC_LMS_KX4_AN || + link_mode == IXGBE_AUTOC_LMS_KX4_AN_1G_AN) { + autoc &= ~IXGBE_AUTOC_KX4_KX_SUPP_MASK; + if (speed & IXGBE_LINK_SPEED_10GB_FULL) + autoc |= IXGBE_AUTOC_KX4_SUPP; + if (speed & IXGBE_LINK_SPEED_1GB_FULL) + autoc |= IXGBE_AUTOC_KX_SUPP; + if (autoc != curr_autoc) + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc); + } + + /* Setup and restart the link based on the new values in + * ixgbe_hw This will write the AUTOC register based on the new + * stored values + */ + return ixgbe_start_mac_link_82598(hw, autoneg_wait_to_complete); +} + + +/** + * ixgbe_setup_copper_link_82598 - Set the PHY autoneg advertised field + * @hw: pointer to hardware structure + * @speed: new link speed + * @autoneg_wait_to_complete: true if waiting is needed to complete + * + * Sets the link speed in the AUTOC register in the MAC and restarts link. + **/ +static s32 ixgbe_setup_copper_link_82598(struct ixgbe_hw *hw, + ixgbe_link_speed speed, + bool autoneg_wait_to_complete) +{ + s32 status; + + /* Setup the PHY according to input speed */ + status = hw->phy.ops.setup_link_speed(hw, speed, + autoneg_wait_to_complete); + /* Set up MAC */ + ixgbe_start_mac_link_82598(hw, autoneg_wait_to_complete); + + return status; +} + +/** + * ixgbe_reset_hw_82598 - Performs hardware reset + * @hw: pointer to hardware structure + * + * Resets the hardware by resetting the transmit and receive units, masks and + * clears all interrupts, performing a PHY reset, and performing a link (MAC) + * reset. + **/ +static s32 ixgbe_reset_hw_82598(struct ixgbe_hw *hw) +{ + s32 status; + s32 phy_status = 0; + u32 ctrl; + u32 gheccr; + u32 i; + u32 autoc; + u8 analog_val; + + /* Call adapter stop to disable tx/rx and clear interrupts */ + status = hw->mac.ops.stop_adapter(hw); + if (status) + return status; + + /* + * Power up the Atlas Tx lanes if they are currently powered down. + * Atlas Tx lanes are powered down for MAC loopback tests, but + * they are not automatically restored on reset. + */ + hw->mac.ops.read_analog_reg8(hw, IXGBE_ATLAS_PDN_LPBK, &analog_val); + if (analog_val & IXGBE_ATLAS_PDN_TX_REG_EN) { + /* Enable Tx Atlas so packets can be transmitted again */ + hw->mac.ops.read_analog_reg8(hw, IXGBE_ATLAS_PDN_LPBK, + &analog_val); + analog_val &= ~IXGBE_ATLAS_PDN_TX_REG_EN; + hw->mac.ops.write_analog_reg8(hw, IXGBE_ATLAS_PDN_LPBK, + analog_val); + + hw->mac.ops.read_analog_reg8(hw, IXGBE_ATLAS_PDN_10G, + &analog_val); + analog_val &= ~IXGBE_ATLAS_PDN_TX_10G_QL_ALL; + hw->mac.ops.write_analog_reg8(hw, IXGBE_ATLAS_PDN_10G, + analog_val); + + hw->mac.ops.read_analog_reg8(hw, IXGBE_ATLAS_PDN_1G, + &analog_val); + analog_val &= ~IXGBE_ATLAS_PDN_TX_1G_QL_ALL; + hw->mac.ops.write_analog_reg8(hw, IXGBE_ATLAS_PDN_1G, + analog_val); + + hw->mac.ops.read_analog_reg8(hw, IXGBE_ATLAS_PDN_AN, + &analog_val); + analog_val &= ~IXGBE_ATLAS_PDN_TX_AN_QL_ALL; + hw->mac.ops.write_analog_reg8(hw, IXGBE_ATLAS_PDN_AN, + analog_val); + } + + /* Reset PHY */ + if (hw->phy.reset_disable == false) { + /* PHY ops must be identified and initialized prior to reset */ + + /* Init PHY and function pointers, perform SFP setup */ + phy_status = hw->phy.ops.init(hw); + if (phy_status == IXGBE_ERR_SFP_NOT_SUPPORTED) + return phy_status; + if (phy_status == IXGBE_ERR_SFP_NOT_PRESENT) + goto mac_reset_top; + + hw->phy.ops.reset(hw); + } + +mac_reset_top: + /* + * Issue global reset to the MAC. This needs to be a SW reset. + * If link reset is used, it might reset the MAC when mng is using it + */ + ctrl = IXGBE_READ_REG(hw, IXGBE_CTRL) | IXGBE_CTRL_RST; + IXGBE_WRITE_REG(hw, IXGBE_CTRL, ctrl); + IXGBE_WRITE_FLUSH(hw); + usleep_range(1000, 1200); + + /* Poll for reset bit to self-clear indicating reset is complete */ + for (i = 0; i < 10; i++) { + ctrl = IXGBE_READ_REG(hw, IXGBE_CTRL); + if (!(ctrl & IXGBE_CTRL_RST)) + break; + udelay(1); + } + if (ctrl & IXGBE_CTRL_RST) { + status = IXGBE_ERR_RESET_FAILED; + hw_dbg(hw, "Reset polling failed to complete.\n"); + } + + msleep(50); + + /* + * Double resets are required for recovery from certain error + * conditions. Between resets, it is necessary to stall to allow time + * for any pending HW events to complete. + */ + if (hw->mac.flags & IXGBE_FLAGS_DOUBLE_RESET_REQUIRED) { + hw->mac.flags &= ~IXGBE_FLAGS_DOUBLE_RESET_REQUIRED; + goto mac_reset_top; + } + + gheccr = IXGBE_READ_REG(hw, IXGBE_GHECCR); + gheccr &= ~(BIT(21) | BIT(18) | BIT(9) | BIT(6)); + IXGBE_WRITE_REG(hw, IXGBE_GHECCR, gheccr); + + /* + * Store the original AUTOC value if it has not been + * stored off yet. Otherwise restore the stored original + * AUTOC value since the reset operation sets back to deaults. + */ + autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC); + if (hw->mac.orig_link_settings_stored == false) { + hw->mac.orig_autoc = autoc; + hw->mac.orig_link_settings_stored = true; + } else if (autoc != hw->mac.orig_autoc) { + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, hw->mac.orig_autoc); + } + + /* Store the permanent mac address */ + hw->mac.ops.get_mac_addr(hw, hw->mac.perm_addr); + + /* + * Store MAC address from RAR0, clear receive address registers, and + * clear the multicast table + */ + hw->mac.ops.init_rx_addrs(hw); + + if (phy_status) + status = phy_status; + + return status; +} + +/** + * ixgbe_set_vmdq_82598 - Associate a VMDq set index with a rx address + * @hw: pointer to hardware struct + * @rar: receive address register index to associate with a VMDq index + * @vmdq: VMDq set index + **/ +static s32 ixgbe_set_vmdq_82598(struct ixgbe_hw *hw, u32 rar, u32 vmdq) +{ + u32 rar_high; + u32 rar_entries = hw->mac.num_rar_entries; + + /* Make sure we are using a valid rar index range */ + if (rar >= rar_entries) { + hw_dbg(hw, "RAR index %d is out of range.\n", rar); + return IXGBE_ERR_INVALID_ARGUMENT; + } + + rar_high = IXGBE_READ_REG(hw, IXGBE_RAH(rar)); + rar_high &= ~IXGBE_RAH_VIND_MASK; + rar_high |= ((vmdq << IXGBE_RAH_VIND_SHIFT) & IXGBE_RAH_VIND_MASK); + IXGBE_WRITE_REG(hw, IXGBE_RAH(rar), rar_high); + return 0; +} + +/** + * ixgbe_clear_vmdq_82598 - Disassociate a VMDq set index from an rx address + * @hw: pointer to hardware struct + * @rar: receive address register index to associate with a VMDq index + * @vmdq: VMDq clear index (not used in 82598, but elsewhere) + **/ +static s32 ixgbe_clear_vmdq_82598(struct ixgbe_hw *hw, u32 rar, u32 vmdq) +{ + u32 rar_high; + u32 rar_entries = hw->mac.num_rar_entries; + + + /* Make sure we are using a valid rar index range */ + if (rar >= rar_entries) { + hw_dbg(hw, "RAR index %d is out of range.\n", rar); + return IXGBE_ERR_INVALID_ARGUMENT; + } + + rar_high = IXGBE_READ_REG(hw, IXGBE_RAH(rar)); + if (rar_high & IXGBE_RAH_VIND_MASK) { + rar_high &= ~IXGBE_RAH_VIND_MASK; + IXGBE_WRITE_REG(hw, IXGBE_RAH(rar), rar_high); + } + + return 0; +} + +/** + * ixgbe_set_vfta_82598 - Set VLAN filter table + * @hw: pointer to hardware structure + * @vlan: VLAN id to write to VLAN filter + * @vind: VMDq output index that maps queue to VLAN id in VFTA + * @vlan_on: boolean flag to turn on/off VLAN in VFTA + * @vlvf_bypass: boolean flag - unused + * + * Turn on/off specified VLAN in the VLAN filter table. + **/ +static s32 ixgbe_set_vfta_82598(struct ixgbe_hw *hw, u32 vlan, u32 vind, + bool vlan_on, bool vlvf_bypass) +{ + u32 regindex; + u32 bitindex; + u32 bits; + u32 vftabyte; + + if (vlan > 4095) + return IXGBE_ERR_PARAM; + + /* Determine 32-bit word position in array */ + regindex = (vlan >> 5) & 0x7F; /* upper seven bits */ + + /* Determine the location of the (VMD) queue index */ + vftabyte = ((vlan >> 3) & 0x03); /* bits (4:3) indicating byte array */ + bitindex = (vlan & 0x7) << 2; /* lower 3 bits indicate nibble */ + + /* Set the nibble for VMD queue index */ + bits = IXGBE_READ_REG(hw, IXGBE_VFTAVIND(vftabyte, regindex)); + bits &= (~(0x0F << bitindex)); + bits |= (vind << bitindex); + IXGBE_WRITE_REG(hw, IXGBE_VFTAVIND(vftabyte, regindex), bits); + + /* Determine the location of the bit for this VLAN id */ + bitindex = vlan & 0x1F; /* lower five bits */ + + bits = IXGBE_READ_REG(hw, IXGBE_VFTA(regindex)); + if (vlan_on) + /* Turn on this VLAN id */ + bits |= BIT(bitindex); + else + /* Turn off this VLAN id */ + bits &= ~BIT(bitindex); + IXGBE_WRITE_REG(hw, IXGBE_VFTA(regindex), bits); + + return 0; +} + +/** + * ixgbe_clear_vfta_82598 - Clear VLAN filter table + * @hw: pointer to hardware structure + * + * Clears the VLAN filer table, and the VMDq index associated with the filter + **/ +static s32 ixgbe_clear_vfta_82598(struct ixgbe_hw *hw) +{ + u32 offset; + u32 vlanbyte; + + for (offset = 0; offset < hw->mac.vft_size; offset++) + IXGBE_WRITE_REG(hw, IXGBE_VFTA(offset), 0); + + for (vlanbyte = 0; vlanbyte < 4; vlanbyte++) + for (offset = 0; offset < hw->mac.vft_size; offset++) + IXGBE_WRITE_REG(hw, IXGBE_VFTAVIND(vlanbyte, offset), + 0); + + return 0; +} + +/** + * ixgbe_read_analog_reg8_82598 - Reads 8 bit Atlas analog register + * @hw: pointer to hardware structure + * @reg: analog register to read + * @val: read value + * + * Performs read operation to Atlas analog register specified. + **/ +static s32 ixgbe_read_analog_reg8_82598(struct ixgbe_hw *hw, u32 reg, u8 *val) +{ + u32 atlas_ctl; + + IXGBE_WRITE_REG(hw, IXGBE_ATLASCTL, + IXGBE_ATLASCTL_WRITE_CMD | (reg << 8)); + IXGBE_WRITE_FLUSH(hw); + udelay(10); + atlas_ctl = IXGBE_READ_REG(hw, IXGBE_ATLASCTL); + *val = (u8)atlas_ctl; + + return 0; +} + +/** + * ixgbe_write_analog_reg8_82598 - Writes 8 bit Atlas analog register + * @hw: pointer to hardware structure + * @reg: atlas register to write + * @val: value to write + * + * Performs write operation to Atlas analog register specified. + **/ +static s32 ixgbe_write_analog_reg8_82598(struct ixgbe_hw *hw, u32 reg, u8 val) +{ + u32 atlas_ctl; + + atlas_ctl = (reg << 8) | val; + IXGBE_WRITE_REG(hw, IXGBE_ATLASCTL, atlas_ctl); + IXGBE_WRITE_FLUSH(hw); + udelay(10); + + return 0; +} + +/** + * ixgbe_read_i2c_phy_82598 - Reads 8 bit word over I2C interface. + * @hw: pointer to hardware structure + * @dev_addr: address to read from + * @byte_offset: byte offset to read from dev_addr + * @eeprom_data: value read + * + * Performs 8 byte read operation to SFP module's data over I2C interface. + **/ +static s32 ixgbe_read_i2c_phy_82598(struct ixgbe_hw *hw, u8 dev_addr, + u8 byte_offset, u8 *eeprom_data) +{ + s32 status = 0; + u16 sfp_addr = 0; + u16 sfp_data = 0; + u16 sfp_stat = 0; + u16 gssr; + u32 i; + + if (IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_LAN_ID_1) + gssr = IXGBE_GSSR_PHY1_SM; + else + gssr = IXGBE_GSSR_PHY0_SM; + + if (hw->mac.ops.acquire_swfw_sync(hw, gssr) != 0) + return IXGBE_ERR_SWFW_SYNC; + + if (hw->phy.type == ixgbe_phy_nl) { + /* + * phy SDA/SCL registers are at addresses 0xC30A to + * 0xC30D. These registers are used to talk to the SFP+ + * module's EEPROM through the SDA/SCL (I2C) interface. + */ + sfp_addr = (dev_addr << 8) + byte_offset; + sfp_addr = (sfp_addr | IXGBE_I2C_EEPROM_READ_MASK); + hw->phy.ops.write_reg_mdi(hw, + IXGBE_MDIO_PMA_PMD_SDA_SCL_ADDR, + MDIO_MMD_PMAPMD, + sfp_addr); + + /* Poll status */ + for (i = 0; i < 100; i++) { + hw->phy.ops.read_reg_mdi(hw, + IXGBE_MDIO_PMA_PMD_SDA_SCL_STAT, + MDIO_MMD_PMAPMD, + &sfp_stat); + sfp_stat = sfp_stat & IXGBE_I2C_EEPROM_STATUS_MASK; + if (sfp_stat != IXGBE_I2C_EEPROM_STATUS_IN_PROGRESS) + break; + usleep_range(10000, 20000); + } + + if (sfp_stat != IXGBE_I2C_EEPROM_STATUS_PASS) { + hw_dbg(hw, "EEPROM read did not pass.\n"); + status = IXGBE_ERR_SFP_NOT_PRESENT; + goto out; + } + + /* Read data */ + hw->phy.ops.read_reg_mdi(hw, IXGBE_MDIO_PMA_PMD_SDA_SCL_DATA, + MDIO_MMD_PMAPMD, &sfp_data); + + *eeprom_data = (u8)(sfp_data >> 8); + } else { + status = IXGBE_ERR_PHY; + } + +out: + hw->mac.ops.release_swfw_sync(hw, gssr); + return status; +} + +/** + * ixgbe_read_i2c_eeprom_82598 - Reads 8 bit word over I2C interface. + * @hw: pointer to hardware structure + * @byte_offset: EEPROM byte offset to read + * @eeprom_data: value read + * + * Performs 8 byte read operation to SFP module's EEPROM over I2C interface. + **/ +static s32 ixgbe_read_i2c_eeprom_82598(struct ixgbe_hw *hw, u8 byte_offset, + u8 *eeprom_data) +{ + return ixgbe_read_i2c_phy_82598(hw, IXGBE_I2C_EEPROM_DEV_ADDR, + byte_offset, eeprom_data); +} + +/** + * ixgbe_read_i2c_sff8472_82598 - Reads 8 bit word over I2C interface. + * @hw: pointer to hardware structure + * @byte_offset: byte offset at address 0xA2 + * @sff8472_data: value read + * + * Performs 8 byte read operation to SFP module's SFF-8472 data over I2C + **/ +static s32 ixgbe_read_i2c_sff8472_82598(struct ixgbe_hw *hw, u8 byte_offset, + u8 *sff8472_data) +{ + return ixgbe_read_i2c_phy_82598(hw, IXGBE_I2C_EEPROM_DEV_ADDR2, + byte_offset, sff8472_data); +} + +/** + * ixgbe_set_lan_id_multi_port_pcie_82598 - Set LAN id for PCIe multiple + * port devices. + * @hw: pointer to the HW structure + * + * Calls common function and corrects issue with some single port devices + * that enable LAN1 but not LAN0. + **/ +static void ixgbe_set_lan_id_multi_port_pcie_82598(struct ixgbe_hw *hw) +{ + struct ixgbe_bus_info *bus = &hw->bus; + u16 pci_gen = 0; + u16 pci_ctrl2 = 0; + + ixgbe_set_lan_id_multi_port_pcie(hw); + + /* check if LAN0 is disabled */ + hw->eeprom.ops.read(hw, IXGBE_PCIE_GENERAL_PTR, &pci_gen); + if ((pci_gen != 0) && (pci_gen != 0xFFFF)) { + + hw->eeprom.ops.read(hw, pci_gen + IXGBE_PCIE_CTRL2, &pci_ctrl2); + + /* if LAN0 is completely disabled force function to 0 */ + if ((pci_ctrl2 & IXGBE_PCIE_CTRL2_LAN_DISABLE) && + !(pci_ctrl2 & IXGBE_PCIE_CTRL2_DISABLE_SELECT) && + !(pci_ctrl2 & IXGBE_PCIE_CTRL2_DUMMY_ENABLE)) { + + bus->func = 0; + } + } +} + +/** + * ixgbe_set_rxpba_82598 - Initialize RX packet buffer + * @hw: pointer to hardware structure + * @num_pb: number of packet buffers to allocate + * @headroom: reserve n KB of headroom + * @strategy: packet buffer allocation strategy + **/ +static void ixgbe_set_rxpba_82598(struct ixgbe_hw *hw, int num_pb, + u32 headroom, int strategy) +{ + u32 rxpktsize = IXGBE_RXPBSIZE_64KB; + u8 i = 0; + + if (!num_pb) + return; + + /* Setup Rx packet buffer sizes */ + switch (strategy) { + case PBA_STRATEGY_WEIGHTED: + /* Setup the first four at 80KB */ + rxpktsize = IXGBE_RXPBSIZE_80KB; + for (; i < 4; i++) + IXGBE_WRITE_REG(hw, IXGBE_RXPBSIZE(i), rxpktsize); + /* Setup the last four at 48KB...don't re-init i */ + rxpktsize = IXGBE_RXPBSIZE_48KB; + fallthrough; + case PBA_STRATEGY_EQUAL: + default: + /* Divide the remaining Rx packet buffer evenly among the TCs */ + for (; i < IXGBE_MAX_PACKET_BUFFERS; i++) + IXGBE_WRITE_REG(hw, IXGBE_RXPBSIZE(i), rxpktsize); + break; + } + + /* Setup Tx packet buffer sizes */ + for (i = 0; i < IXGBE_MAX_PACKET_BUFFERS; i++) + IXGBE_WRITE_REG(hw, IXGBE_TXPBSIZE(i), IXGBE_TXPBSIZE_40KB); +} + +static const struct ixgbe_mac_operations mac_ops_82598 = { + .init_hw = &ixgbe_init_hw_generic, + .reset_hw = &ixgbe_reset_hw_82598, + .start_hw = &ixgbe_start_hw_82598, + .clear_hw_cntrs = &ixgbe_clear_hw_cntrs_generic, + .get_media_type = &ixgbe_get_media_type_82598, + .enable_rx_dma = &ixgbe_enable_rx_dma_generic, + .get_mac_addr = &ixgbe_get_mac_addr_generic, + .stop_adapter = &ixgbe_stop_adapter_generic, + .get_bus_info = &ixgbe_get_bus_info_generic, + .set_lan_id = &ixgbe_set_lan_id_multi_port_pcie_82598, + .read_analog_reg8 = &ixgbe_read_analog_reg8_82598, + .write_analog_reg8 = &ixgbe_write_analog_reg8_82598, + .setup_link = &ixgbe_setup_mac_link_82598, + .set_rxpba = &ixgbe_set_rxpba_82598, + .check_link = &ixgbe_check_mac_link_82598, + .get_link_capabilities = &ixgbe_get_link_capabilities_82598, + .led_on = &ixgbe_led_on_generic, + .led_off = &ixgbe_led_off_generic, + .init_led_link_act = ixgbe_init_led_link_act_generic, + .blink_led_start = &ixgbe_blink_led_start_generic, + .blink_led_stop = &ixgbe_blink_led_stop_generic, + .set_rar = &ixgbe_set_rar_generic, + .clear_rar = &ixgbe_clear_rar_generic, + .set_vmdq = &ixgbe_set_vmdq_82598, + .clear_vmdq = &ixgbe_clear_vmdq_82598, + .init_rx_addrs = &ixgbe_init_rx_addrs_generic, + .update_mc_addr_list = &ixgbe_update_mc_addr_list_generic, + .enable_mc = &ixgbe_enable_mc_generic, + .disable_mc = &ixgbe_disable_mc_generic, + .clear_vfta = &ixgbe_clear_vfta_82598, + .set_vfta = &ixgbe_set_vfta_82598, + .fc_enable = &ixgbe_fc_enable_82598, + .setup_fc = ixgbe_setup_fc_generic, + .fc_autoneg = ixgbe_fc_autoneg, + .set_fw_drv_ver = NULL, + .acquire_swfw_sync = &ixgbe_acquire_swfw_sync, + .release_swfw_sync = &ixgbe_release_swfw_sync, + .init_swfw_sync = NULL, + .get_thermal_sensor_data = NULL, + .init_thermal_sensor_thresh = NULL, + .prot_autoc_read = &prot_autoc_read_generic, + .prot_autoc_write = &prot_autoc_write_generic, + .enable_rx = &ixgbe_enable_rx_generic, + .disable_rx = &ixgbe_disable_rx_generic, +}; + +static const struct ixgbe_eeprom_operations eeprom_ops_82598 = { + .init_params = &ixgbe_init_eeprom_params_generic, + .read = &ixgbe_read_eerd_generic, + .write = &ixgbe_write_eeprom_generic, + .write_buffer = &ixgbe_write_eeprom_buffer_bit_bang_generic, + .read_buffer = &ixgbe_read_eerd_buffer_generic, + .calc_checksum = &ixgbe_calc_eeprom_checksum_generic, + .validate_checksum = &ixgbe_validate_eeprom_checksum_generic, + .update_checksum = &ixgbe_update_eeprom_checksum_generic, +}; + +static const struct ixgbe_phy_operations phy_ops_82598 = { + .identify = &ixgbe_identify_phy_generic, + .identify_sfp = &ixgbe_identify_module_generic, + .init = &ixgbe_init_phy_ops_82598, + .reset = &ixgbe_reset_phy_generic, + .read_reg = &ixgbe_read_phy_reg_generic, + .write_reg = &ixgbe_write_phy_reg_generic, + .read_reg_mdi = &ixgbe_read_phy_reg_mdi, + .write_reg_mdi = &ixgbe_write_phy_reg_mdi, + .setup_link = &ixgbe_setup_phy_link_generic, + .setup_link_speed = &ixgbe_setup_phy_link_speed_generic, + .read_i2c_sff8472 = &ixgbe_read_i2c_sff8472_82598, + .read_i2c_eeprom = &ixgbe_read_i2c_eeprom_82598, + .check_overtemp = &ixgbe_tn_check_overtemp, +}; + +const struct ixgbe_info ixgbe_82598_info = { + .mac = ixgbe_mac_82598EB, + .get_invariants = &ixgbe_get_invariants_82598, + .mac_ops = &mac_ops_82598, + .eeprom_ops = &eeprom_ops_82598, + .phy_ops = &phy_ops_82598, + .mvals = ixgbe_mvals_8259X, +}; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c new file mode 100644 index 000000000..8d3798a32 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -0,0 +1,2256 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#include <linux/pci.h> +#include <linux/delay.h> +#include <linux/sched.h> + +#include "ixgbe.h" +#include "ixgbe_phy.h" +#include "ixgbe_mbx.h" + +#define IXGBE_82599_MAX_TX_QUEUES 128 +#define IXGBE_82599_MAX_RX_QUEUES 128 +#define IXGBE_82599_RAR_ENTRIES 128 +#define IXGBE_82599_MC_TBL_SIZE 128 +#define IXGBE_82599_VFT_TBL_SIZE 128 +#define IXGBE_82599_RX_PB_SIZE 512 + +static void ixgbe_disable_tx_laser_multispeed_fiber(struct ixgbe_hw *hw); +static void ixgbe_enable_tx_laser_multispeed_fiber(struct ixgbe_hw *hw); +static void ixgbe_flap_tx_laser_multispeed_fiber(struct ixgbe_hw *hw); +static void +ixgbe_set_hard_rate_select_speed(struct ixgbe_hw *, ixgbe_link_speed); +static s32 ixgbe_setup_mac_link_smartspeed(struct ixgbe_hw *hw, + ixgbe_link_speed speed, + bool autoneg_wait_to_complete); +static void ixgbe_stop_mac_link_on_d3_82599(struct ixgbe_hw *hw); +static s32 ixgbe_start_mac_link_82599(struct ixgbe_hw *hw, + bool autoneg_wait_to_complete); +static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw, + ixgbe_link_speed speed, + bool autoneg_wait_to_complete); +static s32 ixgbe_setup_copper_link_82599(struct ixgbe_hw *hw, + ixgbe_link_speed speed, + bool autoneg_wait_to_complete); +static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw); +static s32 ixgbe_read_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 *data); +static s32 ixgbe_write_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 data); +static s32 ixgbe_reset_pipeline_82599(struct ixgbe_hw *hw); +static bool ixgbe_verify_lesm_fw_enabled_82599(struct ixgbe_hw *hw); + +bool ixgbe_mng_enabled(struct ixgbe_hw *hw) +{ + u32 fwsm, manc, factps; + + fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw)); + if ((fwsm & IXGBE_FWSM_MODE_MASK) != IXGBE_FWSM_FW_MODE_PT) + return false; + + manc = IXGBE_READ_REG(hw, IXGBE_MANC); + if (!(manc & IXGBE_MANC_RCV_TCO_EN)) + return false; + + factps = IXGBE_READ_REG(hw, IXGBE_FACTPS(hw)); + if (factps & IXGBE_FACTPS_MNGCG) + return false; + + return true; +} + +static void ixgbe_init_mac_link_ops_82599(struct ixgbe_hw *hw) +{ + struct ixgbe_mac_info *mac = &hw->mac; + + /* enable the laser control functions for SFP+ fiber + * and MNG not enabled + */ + if ((mac->ops.get_media_type(hw) == ixgbe_media_type_fiber) && + !ixgbe_mng_enabled(hw)) { + mac->ops.disable_tx_laser = + &ixgbe_disable_tx_laser_multispeed_fiber; + mac->ops.enable_tx_laser = + &ixgbe_enable_tx_laser_multispeed_fiber; + mac->ops.flap_tx_laser = &ixgbe_flap_tx_laser_multispeed_fiber; + } else { + mac->ops.disable_tx_laser = NULL; + mac->ops.enable_tx_laser = NULL; + mac->ops.flap_tx_laser = NULL; + } + + if (hw->phy.multispeed_fiber) { + /* Set up dual speed SFP+ support */ + mac->ops.setup_link = &ixgbe_setup_mac_link_multispeed_fiber; + mac->ops.setup_mac_link = ixgbe_setup_mac_link_82599; + mac->ops.set_rate_select_speed = + ixgbe_set_hard_rate_select_speed; + } else { + if ((mac->ops.get_media_type(hw) == + ixgbe_media_type_backplane) && + (hw->phy.smart_speed == ixgbe_smart_speed_auto || + hw->phy.smart_speed == ixgbe_smart_speed_on) && + !ixgbe_verify_lesm_fw_enabled_82599(hw)) + mac->ops.setup_link = &ixgbe_setup_mac_link_smartspeed; + else + mac->ops.setup_link = &ixgbe_setup_mac_link_82599; + } +} + +static s32 ixgbe_setup_sfp_modules_82599(struct ixgbe_hw *hw) +{ + s32 ret_val; + u16 list_offset, data_offset, data_value; + + if (hw->phy.sfp_type != ixgbe_sfp_type_unknown) { + ixgbe_init_mac_link_ops_82599(hw); + + hw->phy.ops.reset = NULL; + + ret_val = ixgbe_get_sfp_init_sequence_offsets(hw, &list_offset, + &data_offset); + if (ret_val) + return ret_val; + + /* PHY config will finish before releasing the semaphore */ + ret_val = hw->mac.ops.acquire_swfw_sync(hw, + IXGBE_GSSR_MAC_CSR_SM); + if (ret_val) + return IXGBE_ERR_SWFW_SYNC; + + if (hw->eeprom.ops.read(hw, ++data_offset, &data_value)) + goto setup_sfp_err; + while (data_value != 0xffff) { + IXGBE_WRITE_REG(hw, IXGBE_CORECTL, data_value); + IXGBE_WRITE_FLUSH(hw); + if (hw->eeprom.ops.read(hw, ++data_offset, &data_value)) + goto setup_sfp_err; + } + + /* Release the semaphore */ + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_MAC_CSR_SM); + /* + * Delay obtaining semaphore again to allow FW access, + * semaphore_delay is in ms usleep_range needs us. + */ + usleep_range(hw->eeprom.semaphore_delay * 1000, + hw->eeprom.semaphore_delay * 2000); + + /* Restart DSP and set SFI mode */ + ret_val = hw->mac.ops.prot_autoc_write(hw, + hw->mac.orig_autoc | IXGBE_AUTOC_LMS_10G_SERIAL, + false); + + if (ret_val) { + hw_dbg(hw, " sfp module setup not complete\n"); + return IXGBE_ERR_SFP_SETUP_NOT_COMPLETE; + } + } + + return 0; + +setup_sfp_err: + /* Release the semaphore */ + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_MAC_CSR_SM); + /* Delay obtaining semaphore again to allow FW access, + * semaphore_delay is in ms usleep_range needs us. + */ + usleep_range(hw->eeprom.semaphore_delay * 1000, + hw->eeprom.semaphore_delay * 2000); + hw_err(hw, "eeprom read at offset %d failed\n", data_offset); + return IXGBE_ERR_SFP_SETUP_NOT_COMPLETE; +} + +/** + * prot_autoc_read_82599 - Hides MAC differences needed for AUTOC read + * @hw: pointer to hardware structure + * @locked: Return the if we locked for this read. + * @reg_val: Value we read from AUTOC + * + * For this part (82599) we need to wrap read-modify-writes with a possible + * FW/SW lock. It is assumed this lock will be freed with the next + * prot_autoc_write_82599(). Note, that locked can only be true in cases + * where this function doesn't return an error. + **/ +static s32 prot_autoc_read_82599(struct ixgbe_hw *hw, bool *locked, + u32 *reg_val) +{ + s32 ret_val; + + *locked = false; + /* If LESM is on then we need to hold the SW/FW semaphore. */ + if (ixgbe_verify_lesm_fw_enabled_82599(hw)) { + ret_val = hw->mac.ops.acquire_swfw_sync(hw, + IXGBE_GSSR_MAC_CSR_SM); + if (ret_val) + return IXGBE_ERR_SWFW_SYNC; + + *locked = true; + } + + *reg_val = IXGBE_READ_REG(hw, IXGBE_AUTOC); + return 0; +} + +/** + * prot_autoc_write_82599 - Hides MAC differences needed for AUTOC write + * @hw: pointer to hardware structure + * @autoc: value to write to AUTOC + * @locked: bool to indicate whether the SW/FW lock was already taken by + * previous proc_autoc_read_82599. + * + * This part (82599) may need to hold a the SW/FW lock around all writes to + * AUTOC. Likewise after a write we need to do a pipeline reset. + **/ +static s32 prot_autoc_write_82599(struct ixgbe_hw *hw, u32 autoc, bool locked) +{ + s32 ret_val = 0; + + /* Blocked by MNG FW so bail */ + if (ixgbe_check_reset_blocked(hw)) + goto out; + + /* We only need to get the lock if: + * - We didn't do it already (in the read part of a read-modify-write) + * - LESM is enabled. + */ + if (!locked && ixgbe_verify_lesm_fw_enabled_82599(hw)) { + ret_val = hw->mac.ops.acquire_swfw_sync(hw, + IXGBE_GSSR_MAC_CSR_SM); + if (ret_val) + return IXGBE_ERR_SWFW_SYNC; + + locked = true; + } + + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc); + ret_val = ixgbe_reset_pipeline_82599(hw); + +out: + /* Free the SW/FW semaphore as we either grabbed it here or + * already had it when this function was called. + */ + if (locked) + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_MAC_CSR_SM); + + return ret_val; +} + +static s32 ixgbe_get_invariants_82599(struct ixgbe_hw *hw) +{ + struct ixgbe_mac_info *mac = &hw->mac; + + ixgbe_init_mac_link_ops_82599(hw); + + mac->mcft_size = IXGBE_82599_MC_TBL_SIZE; + mac->vft_size = IXGBE_82599_VFT_TBL_SIZE; + mac->num_rar_entries = IXGBE_82599_RAR_ENTRIES; + mac->rx_pb_size = IXGBE_82599_RX_PB_SIZE; + mac->max_rx_queues = IXGBE_82599_MAX_RX_QUEUES; + mac->max_tx_queues = IXGBE_82599_MAX_TX_QUEUES; + mac->max_msix_vectors = ixgbe_get_pcie_msix_count_generic(hw); + + return 0; +} + +/** + * ixgbe_init_phy_ops_82599 - PHY/SFP specific init + * @hw: pointer to hardware structure + * + * Initialize any function pointers that were not able to be + * set during get_invariants because the PHY/SFP type was + * not known. Perform the SFP init if necessary. + * + **/ +static s32 ixgbe_init_phy_ops_82599(struct ixgbe_hw *hw) +{ + struct ixgbe_mac_info *mac = &hw->mac; + struct ixgbe_phy_info *phy = &hw->phy; + s32 ret_val; + u32 esdp; + + if (hw->device_id == IXGBE_DEV_ID_82599_QSFP_SF_QP) { + /* Store flag indicating I2C bus access control unit. */ + hw->phy.qsfp_shared_i2c_bus = true; + + /* Initialize access to QSFP+ I2C bus */ + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + esdp |= IXGBE_ESDP_SDP0_DIR; + esdp &= ~IXGBE_ESDP_SDP1_DIR; + esdp &= ~IXGBE_ESDP_SDP0; + esdp &= ~IXGBE_ESDP_SDP0_NATIVE; + esdp &= ~IXGBE_ESDP_SDP1_NATIVE; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp); + IXGBE_WRITE_FLUSH(hw); + + phy->ops.read_i2c_byte = &ixgbe_read_i2c_byte_82599; + phy->ops.write_i2c_byte = &ixgbe_write_i2c_byte_82599; + } + + /* Identify the PHY or SFP module */ + ret_val = phy->ops.identify(hw); + + /* Setup function pointers based on detected SFP module and speeds */ + ixgbe_init_mac_link_ops_82599(hw); + + /* If copper media, overwrite with copper function pointers */ + if (mac->ops.get_media_type(hw) == ixgbe_media_type_copper) { + mac->ops.setup_link = &ixgbe_setup_copper_link_82599; + mac->ops.get_link_capabilities = + &ixgbe_get_copper_link_capabilities_generic; + } + + /* Set necessary function pointers based on phy type */ + switch (hw->phy.type) { + case ixgbe_phy_tn: + phy->ops.check_link = &ixgbe_check_phy_link_tnx; + phy->ops.setup_link = &ixgbe_setup_phy_link_tnx; + break; + default: + break; + } + + return ret_val; +} + +/** + * ixgbe_get_link_capabilities_82599 - Determines link capabilities + * @hw: pointer to hardware structure + * @speed: pointer to link speed + * @autoneg: true when autoneg or autotry is enabled + * + * Determines the link capabilities by reading the AUTOC register. + **/ +static s32 ixgbe_get_link_capabilities_82599(struct ixgbe_hw *hw, + ixgbe_link_speed *speed, + bool *autoneg) +{ + u32 autoc = 0; + + /* Determine 1G link capabilities off of SFP+ type */ + if (hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core1 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core1 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1) { + *speed = IXGBE_LINK_SPEED_1GB_FULL; + *autoneg = true; + return 0; + } + + /* + * Determine link capabilities based on the stored value of AUTOC, + * which represents EEPROM defaults. If AUTOC value has not been + * stored, use the current register value. + */ + if (hw->mac.orig_link_settings_stored) + autoc = hw->mac.orig_autoc; + else + autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC); + + switch (autoc & IXGBE_AUTOC_LMS_MASK) { + case IXGBE_AUTOC_LMS_1G_LINK_NO_AN: + *speed = IXGBE_LINK_SPEED_1GB_FULL; + *autoneg = false; + break; + + case IXGBE_AUTOC_LMS_10G_LINK_NO_AN: + *speed = IXGBE_LINK_SPEED_10GB_FULL; + *autoneg = false; + break; + + case IXGBE_AUTOC_LMS_1G_AN: + *speed = IXGBE_LINK_SPEED_1GB_FULL; + *autoneg = true; + break; + + case IXGBE_AUTOC_LMS_10G_SERIAL: + *speed = IXGBE_LINK_SPEED_10GB_FULL; + *autoneg = false; + break; + + case IXGBE_AUTOC_LMS_KX4_KX_KR: + case IXGBE_AUTOC_LMS_KX4_KX_KR_1G_AN: + *speed = IXGBE_LINK_SPEED_UNKNOWN; + if (autoc & IXGBE_AUTOC_KR_SUPP) + *speed |= IXGBE_LINK_SPEED_10GB_FULL; + if (autoc & IXGBE_AUTOC_KX4_SUPP) + *speed |= IXGBE_LINK_SPEED_10GB_FULL; + if (autoc & IXGBE_AUTOC_KX_SUPP) + *speed |= IXGBE_LINK_SPEED_1GB_FULL; + *autoneg = true; + break; + + case IXGBE_AUTOC_LMS_KX4_KX_KR_SGMII: + *speed = IXGBE_LINK_SPEED_100_FULL; + if (autoc & IXGBE_AUTOC_KR_SUPP) + *speed |= IXGBE_LINK_SPEED_10GB_FULL; + if (autoc & IXGBE_AUTOC_KX4_SUPP) + *speed |= IXGBE_LINK_SPEED_10GB_FULL; + if (autoc & IXGBE_AUTOC_KX_SUPP) + *speed |= IXGBE_LINK_SPEED_1GB_FULL; + *autoneg = true; + break; + + case IXGBE_AUTOC_LMS_SGMII_1G_100M: + *speed = IXGBE_LINK_SPEED_1GB_FULL | IXGBE_LINK_SPEED_100_FULL; + *autoneg = false; + break; + + default: + return IXGBE_ERR_LINK_SETUP; + } + + if (hw->phy.multispeed_fiber) { + *speed |= IXGBE_LINK_SPEED_10GB_FULL | + IXGBE_LINK_SPEED_1GB_FULL; + + /* QSFP must not enable auto-negotiation */ + if (hw->phy.media_type == ixgbe_media_type_fiber_qsfp) + *autoneg = false; + else + *autoneg = true; + } + + return 0; +} + +/** + * ixgbe_get_media_type_82599 - Get media type + * @hw: pointer to hardware structure + * + * Returns the media type (fiber, copper, backplane) + **/ +static enum ixgbe_media_type ixgbe_get_media_type_82599(struct ixgbe_hw *hw) +{ + /* Detect if there is a copper PHY attached. */ + switch (hw->phy.type) { + case ixgbe_phy_cu_unknown: + case ixgbe_phy_tn: + return ixgbe_media_type_copper; + + default: + break; + } + + switch (hw->device_id) { + case IXGBE_DEV_ID_82599_KX4: + case IXGBE_DEV_ID_82599_KX4_MEZZ: + case IXGBE_DEV_ID_82599_COMBO_BACKPLANE: + case IXGBE_DEV_ID_82599_KR: + case IXGBE_DEV_ID_82599_BACKPLANE_FCOE: + case IXGBE_DEV_ID_82599_XAUI_LOM: + /* Default device ID is mezzanine card KX/KX4 */ + return ixgbe_media_type_backplane; + + case IXGBE_DEV_ID_82599_SFP: + case IXGBE_DEV_ID_82599_SFP_FCOE: + case IXGBE_DEV_ID_82599_SFP_EM: + case IXGBE_DEV_ID_82599_SFP_SF2: + case IXGBE_DEV_ID_82599_SFP_SF_QP: + case IXGBE_DEV_ID_82599EN_SFP: + return ixgbe_media_type_fiber; + + case IXGBE_DEV_ID_82599_CX4: + return ixgbe_media_type_cx4; + + case IXGBE_DEV_ID_82599_T3_LOM: + return ixgbe_media_type_copper; + + case IXGBE_DEV_ID_82599_LS: + return ixgbe_media_type_fiber_lco; + + case IXGBE_DEV_ID_82599_QSFP_SF_QP: + return ixgbe_media_type_fiber_qsfp; + + default: + return ixgbe_media_type_unknown; + } +} + +/** + * ixgbe_stop_mac_link_on_d3_82599 - Disables link on D3 + * @hw: pointer to hardware structure + * + * Disables link, should be called during D3 power down sequence. + * + **/ +static void ixgbe_stop_mac_link_on_d3_82599(struct ixgbe_hw *hw) +{ + u32 autoc2_reg; + u16 ee_ctrl_2 = 0; + + hw->eeprom.ops.read(hw, IXGBE_EEPROM_CTRL_2, &ee_ctrl_2); + + if (!ixgbe_mng_present(hw) && !hw->wol_enabled && + ee_ctrl_2 & IXGBE_EEPROM_CCD_BIT) { + autoc2_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC2); + autoc2_reg |= IXGBE_AUTOC2_LINK_DISABLE_ON_D3_MASK; + IXGBE_WRITE_REG(hw, IXGBE_AUTOC2, autoc2_reg); + } +} + +/** + * ixgbe_start_mac_link_82599 - Setup MAC link settings + * @hw: pointer to hardware structure + * @autoneg_wait_to_complete: true when waiting for completion is needed + * + * Configures link settings based on values in the ixgbe_hw struct. + * Restarts the link. Performs autonegotiation if needed. + **/ +static s32 ixgbe_start_mac_link_82599(struct ixgbe_hw *hw, + bool autoneg_wait_to_complete) +{ + u32 autoc_reg; + u32 links_reg; + u32 i; + s32 status = 0; + bool got_lock = false; + + if (ixgbe_verify_lesm_fw_enabled_82599(hw)) { + status = hw->mac.ops.acquire_swfw_sync(hw, + IXGBE_GSSR_MAC_CSR_SM); + if (status) + return status; + + got_lock = true; + } + + /* Restart link */ + ixgbe_reset_pipeline_82599(hw); + + if (got_lock) + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_MAC_CSR_SM); + + /* Only poll for autoneg to complete if specified to do so */ + if (autoneg_wait_to_complete) { + autoc_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC); + if ((autoc_reg & IXGBE_AUTOC_LMS_MASK) == + IXGBE_AUTOC_LMS_KX4_KX_KR || + (autoc_reg & IXGBE_AUTOC_LMS_MASK) == + IXGBE_AUTOC_LMS_KX4_KX_KR_1G_AN || + (autoc_reg & IXGBE_AUTOC_LMS_MASK) == + IXGBE_AUTOC_LMS_KX4_KX_KR_SGMII) { + links_reg = 0; /* Just in case Autoneg time = 0 */ + for (i = 0; i < IXGBE_AUTO_NEG_TIME; i++) { + links_reg = IXGBE_READ_REG(hw, IXGBE_LINKS); + if (links_reg & IXGBE_LINKS_KX_AN_COMP) + break; + msleep(100); + } + if (!(links_reg & IXGBE_LINKS_KX_AN_COMP)) { + status = IXGBE_ERR_AUTONEG_NOT_COMPLETE; + hw_dbg(hw, "Autoneg did not complete.\n"); + } + } + } + + /* Add delay to filter out noises during initial link setup */ + msleep(50); + + return status; +} + +/** + * ixgbe_disable_tx_laser_multispeed_fiber - Disable Tx laser + * @hw: pointer to hardware structure + * + * The base drivers may require better control over SFP+ module + * PHY states. This includes selectively shutting down the Tx + * laser on the PHY, effectively halting physical link. + **/ +static void ixgbe_disable_tx_laser_multispeed_fiber(struct ixgbe_hw *hw) +{ + u32 esdp_reg = IXGBE_READ_REG(hw, IXGBE_ESDP); + + /* Blocked by MNG FW so bail */ + if (ixgbe_check_reset_blocked(hw)) + return; + + /* Disable tx laser; allow 100us to go dark per spec */ + esdp_reg |= IXGBE_ESDP_SDP3; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp_reg); + IXGBE_WRITE_FLUSH(hw); + udelay(100); +} + +/** + * ixgbe_enable_tx_laser_multispeed_fiber - Enable Tx laser + * @hw: pointer to hardware structure + * + * The base drivers may require better control over SFP+ module + * PHY states. This includes selectively turning on the Tx + * laser on the PHY, effectively starting physical link. + **/ +static void ixgbe_enable_tx_laser_multispeed_fiber(struct ixgbe_hw *hw) +{ + u32 esdp_reg = IXGBE_READ_REG(hw, IXGBE_ESDP); + + /* Enable tx laser; allow 100ms to light up */ + esdp_reg &= ~IXGBE_ESDP_SDP3; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp_reg); + IXGBE_WRITE_FLUSH(hw); + msleep(100); +} + +/** + * ixgbe_flap_tx_laser_multispeed_fiber - Flap Tx laser + * @hw: pointer to hardware structure + * + * When the driver changes the link speeds that it can support, + * it sets autotry_restart to true to indicate that we need to + * initiate a new autotry session with the link partner. To do + * so, we set the speed then disable and re-enable the tx laser, to + * alert the link partner that it also needs to restart autotry on its + * end. This is consistent with true clause 37 autoneg, which also + * involves a loss of signal. + **/ +static void ixgbe_flap_tx_laser_multispeed_fiber(struct ixgbe_hw *hw) +{ + /* Blocked by MNG FW so bail */ + if (ixgbe_check_reset_blocked(hw)) + return; + + if (hw->mac.autotry_restart) { + ixgbe_disable_tx_laser_multispeed_fiber(hw); + ixgbe_enable_tx_laser_multispeed_fiber(hw); + hw->mac.autotry_restart = false; + } +} + +/** + * ixgbe_set_hard_rate_select_speed - Set module link speed + * @hw: pointer to hardware structure + * @speed: link speed to set + * + * Set module link speed via RS0/RS1 rate select pins. + */ +static void +ixgbe_set_hard_rate_select_speed(struct ixgbe_hw *hw, ixgbe_link_speed speed) +{ + u32 esdp_reg = IXGBE_READ_REG(hw, IXGBE_ESDP); + + switch (speed) { + case IXGBE_LINK_SPEED_10GB_FULL: + esdp_reg |= (IXGBE_ESDP_SDP5_DIR | IXGBE_ESDP_SDP5); + break; + case IXGBE_LINK_SPEED_1GB_FULL: + esdp_reg &= ~IXGBE_ESDP_SDP5; + esdp_reg |= IXGBE_ESDP_SDP5_DIR; + break; + default: + hw_dbg(hw, "Invalid fixed module speed\n"); + return; + } + + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp_reg); + IXGBE_WRITE_FLUSH(hw); +} + +/** + * ixgbe_setup_mac_link_smartspeed - Set MAC link speed using SmartSpeed + * @hw: pointer to hardware structure + * @speed: new link speed + * @autoneg_wait_to_complete: true when waiting for completion is needed + * + * Implements the Intel SmartSpeed algorithm. + **/ +static s32 ixgbe_setup_mac_link_smartspeed(struct ixgbe_hw *hw, + ixgbe_link_speed speed, + bool autoneg_wait_to_complete) +{ + s32 status = 0; + ixgbe_link_speed link_speed = IXGBE_LINK_SPEED_UNKNOWN; + s32 i, j; + bool link_up = false; + u32 autoc_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC); + + /* Set autoneg_advertised value based on input link speed */ + hw->phy.autoneg_advertised = 0; + + if (speed & IXGBE_LINK_SPEED_10GB_FULL) + hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_10GB_FULL; + + if (speed & IXGBE_LINK_SPEED_1GB_FULL) + hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_1GB_FULL; + + if (speed & IXGBE_LINK_SPEED_100_FULL) + hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_100_FULL; + + /* + * Implement Intel SmartSpeed algorithm. SmartSpeed will reduce the + * autoneg advertisement if link is unable to be established at the + * highest negotiated rate. This can sometimes happen due to integrity + * issues with the physical media connection. + */ + + /* First, try to get link with full advertisement */ + hw->phy.smart_speed_active = false; + for (j = 0; j < IXGBE_SMARTSPEED_MAX_RETRIES; j++) { + status = ixgbe_setup_mac_link_82599(hw, speed, + autoneg_wait_to_complete); + if (status != 0) + goto out; + + /* + * Wait for the controller to acquire link. Per IEEE 802.3ap, + * Section 73.10.2, we may have to wait up to 500ms if KR is + * attempted, or 200ms if KX/KX4/BX/BX4 is attempted, per + * Table 9 in the AN MAS. + */ + for (i = 0; i < 5; i++) { + mdelay(100); + + /* If we have link, just jump out */ + status = hw->mac.ops.check_link(hw, &link_speed, + &link_up, false); + if (status != 0) + goto out; + + if (link_up) + goto out; + } + } + + /* + * We didn't get link. If we advertised KR plus one of KX4/KX + * (or BX4/BX), then disable KR and try again. + */ + if (((autoc_reg & IXGBE_AUTOC_KR_SUPP) == 0) || + ((autoc_reg & IXGBE_AUTOC_KX4_KX_SUPP_MASK) == 0)) + goto out; + + /* Turn SmartSpeed on to disable KR support */ + hw->phy.smart_speed_active = true; + status = ixgbe_setup_mac_link_82599(hw, speed, + autoneg_wait_to_complete); + if (status != 0) + goto out; + + /* + * Wait for the controller to acquire link. 600ms will allow for + * the AN link_fail_inhibit_timer as well for multiple cycles of + * parallel detect, both 10g and 1g. This allows for the maximum + * connect attempts as defined in the AN MAS table 73-7. + */ + for (i = 0; i < 6; i++) { + mdelay(100); + + /* If we have link, just jump out */ + status = hw->mac.ops.check_link(hw, &link_speed, + &link_up, false); + if (status != 0) + goto out; + + if (link_up) + goto out; + } + + /* We didn't get link. Turn SmartSpeed back off. */ + hw->phy.smart_speed_active = false; + status = ixgbe_setup_mac_link_82599(hw, speed, + autoneg_wait_to_complete); + +out: + if (link_up && (link_speed == IXGBE_LINK_SPEED_1GB_FULL)) + hw_dbg(hw, "Smartspeed has downgraded the link speed from the maximum advertised\n"); + return status; +} + +/** + * ixgbe_setup_mac_link_82599 - Set MAC link speed + * @hw: pointer to hardware structure + * @speed: new link speed + * @autoneg_wait_to_complete: true when waiting for completion is needed + * + * Set the link speed in the AUTOC register and restarts link. + **/ +static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw, + ixgbe_link_speed speed, + bool autoneg_wait_to_complete) +{ + bool autoneg = false; + s32 status; + u32 pma_pmd_1g, link_mode, links_reg, i; + u32 autoc2 = IXGBE_READ_REG(hw, IXGBE_AUTOC2); + u32 pma_pmd_10g_serial = autoc2 & IXGBE_AUTOC2_10G_SERIAL_PMA_PMD_MASK; + ixgbe_link_speed link_capabilities = IXGBE_LINK_SPEED_UNKNOWN; + + /* holds the value of AUTOC register at this current point in time */ + u32 current_autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC); + /* holds the cached value of AUTOC register */ + u32 orig_autoc = 0; + /* temporary variable used for comparison purposes */ + u32 autoc = current_autoc; + + /* Check to see if speed passed in is supported. */ + status = hw->mac.ops.get_link_capabilities(hw, &link_capabilities, + &autoneg); + if (status) + return status; + + speed &= link_capabilities; + + if (speed == IXGBE_LINK_SPEED_UNKNOWN) + return IXGBE_ERR_LINK_SETUP; + + /* Use stored value (EEPROM defaults) of AUTOC to find KR/KX4 support*/ + if (hw->mac.orig_link_settings_stored) + orig_autoc = hw->mac.orig_autoc; + else + orig_autoc = autoc; + + link_mode = autoc & IXGBE_AUTOC_LMS_MASK; + pma_pmd_1g = autoc & IXGBE_AUTOC_1G_PMA_PMD_MASK; + + if (link_mode == IXGBE_AUTOC_LMS_KX4_KX_KR || + link_mode == IXGBE_AUTOC_LMS_KX4_KX_KR_1G_AN || + link_mode == IXGBE_AUTOC_LMS_KX4_KX_KR_SGMII) { + /* Set KX4/KX/KR support according to speed requested */ + autoc &= ~(IXGBE_AUTOC_KX4_KX_SUPP_MASK | IXGBE_AUTOC_KR_SUPP); + if (speed & IXGBE_LINK_SPEED_10GB_FULL) { + if (orig_autoc & IXGBE_AUTOC_KX4_SUPP) + autoc |= IXGBE_AUTOC_KX4_SUPP; + if ((orig_autoc & IXGBE_AUTOC_KR_SUPP) && + (hw->phy.smart_speed_active == false)) + autoc |= IXGBE_AUTOC_KR_SUPP; + } + if (speed & IXGBE_LINK_SPEED_1GB_FULL) + autoc |= IXGBE_AUTOC_KX_SUPP; + } else if ((pma_pmd_1g == IXGBE_AUTOC_1G_SFI) && + (link_mode == IXGBE_AUTOC_LMS_1G_LINK_NO_AN || + link_mode == IXGBE_AUTOC_LMS_1G_AN)) { + /* Switch from 1G SFI to 10G SFI if requested */ + if ((speed == IXGBE_LINK_SPEED_10GB_FULL) && + (pma_pmd_10g_serial == IXGBE_AUTOC2_10G_SFI)) { + autoc &= ~IXGBE_AUTOC_LMS_MASK; + autoc |= IXGBE_AUTOC_LMS_10G_SERIAL; + } + } else if ((pma_pmd_10g_serial == IXGBE_AUTOC2_10G_SFI) && + (link_mode == IXGBE_AUTOC_LMS_10G_SERIAL)) { + /* Switch from 10G SFI to 1G SFI if requested */ + if ((speed == IXGBE_LINK_SPEED_1GB_FULL) && + (pma_pmd_1g == IXGBE_AUTOC_1G_SFI)) { + autoc &= ~IXGBE_AUTOC_LMS_MASK; + if (autoneg) + autoc |= IXGBE_AUTOC_LMS_1G_AN; + else + autoc |= IXGBE_AUTOC_LMS_1G_LINK_NO_AN; + } + } + + if (autoc != current_autoc) { + /* Restart link */ + status = hw->mac.ops.prot_autoc_write(hw, autoc, false); + if (status) + return status; + + /* Only poll for autoneg to complete if specified to do so */ + if (autoneg_wait_to_complete) { + if (link_mode == IXGBE_AUTOC_LMS_KX4_KX_KR || + link_mode == IXGBE_AUTOC_LMS_KX4_KX_KR_1G_AN || + link_mode == IXGBE_AUTOC_LMS_KX4_KX_KR_SGMII) { + links_reg = 0; /*Just in case Autoneg time=0*/ + for (i = 0; i < IXGBE_AUTO_NEG_TIME; i++) { + links_reg = + IXGBE_READ_REG(hw, IXGBE_LINKS); + if (links_reg & IXGBE_LINKS_KX_AN_COMP) + break; + msleep(100); + } + if (!(links_reg & IXGBE_LINKS_KX_AN_COMP)) { + status = + IXGBE_ERR_AUTONEG_NOT_COMPLETE; + hw_dbg(hw, "Autoneg did not complete.\n"); + } + } + } + + /* Add delay to filter out noises during initial link setup */ + msleep(50); + } + + return status; +} + +/** + * ixgbe_setup_copper_link_82599 - Set the PHY autoneg advertised field + * @hw: pointer to hardware structure + * @speed: new link speed + * @autoneg_wait_to_complete: true if waiting is needed to complete + * + * Restarts link on PHY and MAC based on settings passed in. + **/ +static s32 ixgbe_setup_copper_link_82599(struct ixgbe_hw *hw, + ixgbe_link_speed speed, + bool autoneg_wait_to_complete) +{ + s32 status; + + /* Setup the PHY according to input speed */ + status = hw->phy.ops.setup_link_speed(hw, speed, + autoneg_wait_to_complete); + /* Set up MAC */ + ixgbe_start_mac_link_82599(hw, autoneg_wait_to_complete); + + return status; +} + +/** + * ixgbe_reset_hw_82599 - Perform hardware reset + * @hw: pointer to hardware structure + * + * Resets the hardware by resetting the transmit and receive units, masks + * and clears all interrupts, perform a PHY reset, and perform a link (MAC) + * reset. + **/ +static s32 ixgbe_reset_hw_82599(struct ixgbe_hw *hw) +{ + ixgbe_link_speed link_speed; + s32 status; + u32 ctrl, i, autoc, autoc2; + u32 curr_lms; + bool link_up = false; + + /* Call adapter stop to disable tx/rx and clear interrupts */ + status = hw->mac.ops.stop_adapter(hw); + if (status) + return status; + + /* flush pending Tx transactions */ + ixgbe_clear_tx_pending(hw); + + /* PHY ops must be identified and initialized prior to reset */ + + /* Identify PHY and related function pointers */ + status = hw->phy.ops.init(hw); + + if (status == IXGBE_ERR_SFP_NOT_SUPPORTED) + return status; + + /* Setup SFP module if there is one present. */ + if (hw->phy.sfp_setup_needed) { + status = hw->mac.ops.setup_sfp(hw); + hw->phy.sfp_setup_needed = false; + } + + if (status == IXGBE_ERR_SFP_NOT_SUPPORTED) + return status; + + /* Reset PHY */ + if (hw->phy.reset_disable == false && hw->phy.ops.reset != NULL) + hw->phy.ops.reset(hw); + + /* remember AUTOC from before we reset */ + curr_lms = IXGBE_READ_REG(hw, IXGBE_AUTOC) & IXGBE_AUTOC_LMS_MASK; + +mac_reset_top: + /* + * Issue global reset to the MAC. Needs to be SW reset if link is up. + * If link reset is used when link is up, it might reset the PHY when + * mng is using it. If link is down or the flag to force full link + * reset is set, then perform link reset. + */ + ctrl = IXGBE_CTRL_LNK_RST; + if (!hw->force_full_reset) { + hw->mac.ops.check_link(hw, &link_speed, &link_up, false); + if (link_up) + ctrl = IXGBE_CTRL_RST; + } + + ctrl |= IXGBE_READ_REG(hw, IXGBE_CTRL); + IXGBE_WRITE_REG(hw, IXGBE_CTRL, ctrl); + IXGBE_WRITE_FLUSH(hw); + usleep_range(1000, 1200); + + /* Poll for reset bit to self-clear indicating reset is complete */ + for (i = 0; i < 10; i++) { + ctrl = IXGBE_READ_REG(hw, IXGBE_CTRL); + if (!(ctrl & IXGBE_CTRL_RST_MASK)) + break; + udelay(1); + } + + if (ctrl & IXGBE_CTRL_RST_MASK) { + status = IXGBE_ERR_RESET_FAILED; + hw_dbg(hw, "Reset polling failed to complete.\n"); + } + + msleep(50); + + /* + * Double resets are required for recovery from certain error + * conditions. Between resets, it is necessary to stall to allow time + * for any pending HW events to complete. + */ + if (hw->mac.flags & IXGBE_FLAGS_DOUBLE_RESET_REQUIRED) { + hw->mac.flags &= ~IXGBE_FLAGS_DOUBLE_RESET_REQUIRED; + goto mac_reset_top; + } + + /* + * Store the original AUTOC/AUTOC2 values if they have not been + * stored off yet. Otherwise restore the stored original + * values since the reset operation sets back to defaults. + */ + autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC); + autoc2 = IXGBE_READ_REG(hw, IXGBE_AUTOC2); + + /* Enable link if disabled in NVM */ + if (autoc2 & IXGBE_AUTOC2_LINK_DISABLE_MASK) { + autoc2 &= ~IXGBE_AUTOC2_LINK_DISABLE_MASK; + IXGBE_WRITE_REG(hw, IXGBE_AUTOC2, autoc2); + IXGBE_WRITE_FLUSH(hw); + } + + if (hw->mac.orig_link_settings_stored == false) { + hw->mac.orig_autoc = autoc; + hw->mac.orig_autoc2 = autoc2; + hw->mac.orig_link_settings_stored = true; + } else { + + /* If MNG FW is running on a multi-speed device that + * doesn't autoneg with out driver support we need to + * leave LMS in the state it was before we MAC reset. + * Likewise if we support WoL we don't want change the + * LMS state either. + */ + if ((hw->phy.multispeed_fiber && ixgbe_mng_enabled(hw)) || + hw->wol_enabled) + hw->mac.orig_autoc = + (hw->mac.orig_autoc & ~IXGBE_AUTOC_LMS_MASK) | + curr_lms; + + if (autoc != hw->mac.orig_autoc) { + status = hw->mac.ops.prot_autoc_write(hw, + hw->mac.orig_autoc, + false); + if (status) + return status; + } + + if ((autoc2 & IXGBE_AUTOC2_UPPER_MASK) != + (hw->mac.orig_autoc2 & IXGBE_AUTOC2_UPPER_MASK)) { + autoc2 &= ~IXGBE_AUTOC2_UPPER_MASK; + autoc2 |= (hw->mac.orig_autoc2 & + IXGBE_AUTOC2_UPPER_MASK); + IXGBE_WRITE_REG(hw, IXGBE_AUTOC2, autoc2); + } + } + + /* Store the permanent mac address */ + hw->mac.ops.get_mac_addr(hw, hw->mac.perm_addr); + + /* + * Store MAC address from RAR0, clear receive address registers, and + * clear the multicast table. Also reset num_rar_entries to 128, + * since we modify this value when programming the SAN MAC address. + */ + hw->mac.num_rar_entries = IXGBE_82599_RAR_ENTRIES; + hw->mac.ops.init_rx_addrs(hw); + + /* Store the permanent SAN mac address */ + hw->mac.ops.get_san_mac_addr(hw, hw->mac.san_addr); + + /* Add the SAN MAC address to the RAR only if it's a valid address */ + if (is_valid_ether_addr(hw->mac.san_addr)) { + /* Save the SAN MAC RAR index */ + hw->mac.san_mac_rar_index = hw->mac.num_rar_entries - 1; + + hw->mac.ops.set_rar(hw, hw->mac.san_mac_rar_index, + hw->mac.san_addr, 0, IXGBE_RAH_AV); + + /* clear VMDq pool/queue selection for this RAR */ + hw->mac.ops.clear_vmdq(hw, hw->mac.san_mac_rar_index, + IXGBE_CLEAR_VMDQ_ALL); + + /* Reserve the last RAR for the SAN MAC address */ + hw->mac.num_rar_entries--; + } + + /* Store the alternative WWNN/WWPN prefix */ + hw->mac.ops.get_wwn_prefix(hw, &hw->mac.wwnn_prefix, + &hw->mac.wwpn_prefix); + + return status; +} + +/** + * ixgbe_fdir_check_cmd_complete - poll to check whether FDIRCMD is complete + * @hw: pointer to hardware structure + * @fdircmd: current value of FDIRCMD register + */ +static s32 ixgbe_fdir_check_cmd_complete(struct ixgbe_hw *hw, u32 *fdircmd) +{ + int i; + + for (i = 0; i < IXGBE_FDIRCMD_CMD_POLL; i++) { + *fdircmd = IXGBE_READ_REG(hw, IXGBE_FDIRCMD); + if (!(*fdircmd & IXGBE_FDIRCMD_CMD_MASK)) + return 0; + udelay(10); + } + + return IXGBE_ERR_FDIR_CMD_INCOMPLETE; +} + +/** + * ixgbe_reinit_fdir_tables_82599 - Reinitialize Flow Director tables. + * @hw: pointer to hardware structure + **/ +s32 ixgbe_reinit_fdir_tables_82599(struct ixgbe_hw *hw) +{ + int i; + u32 fdirctrl = IXGBE_READ_REG(hw, IXGBE_FDIRCTRL); + u32 fdircmd; + s32 err; + + fdirctrl &= ~IXGBE_FDIRCTRL_INIT_DONE; + + /* + * Before starting reinitialization process, + * FDIRCMD.CMD must be zero. + */ + err = ixgbe_fdir_check_cmd_complete(hw, &fdircmd); + if (err) { + hw_dbg(hw, "Flow Director previous command did not complete, aborting table re-initialization.\n"); + return err; + } + + IXGBE_WRITE_REG(hw, IXGBE_FDIRFREE, 0); + IXGBE_WRITE_FLUSH(hw); + /* + * 82599 adapters flow director init flow cannot be restarted, + * Workaround 82599 silicon errata by performing the following steps + * before re-writing the FDIRCTRL control register with the same value. + * - write 1 to bit 8 of FDIRCMD register & + * - write 0 to bit 8 of FDIRCMD register + */ + IXGBE_WRITE_REG(hw, IXGBE_FDIRCMD, + (IXGBE_READ_REG(hw, IXGBE_FDIRCMD) | + IXGBE_FDIRCMD_CLEARHT)); + IXGBE_WRITE_FLUSH(hw); + IXGBE_WRITE_REG(hw, IXGBE_FDIRCMD, + (IXGBE_READ_REG(hw, IXGBE_FDIRCMD) & + ~IXGBE_FDIRCMD_CLEARHT)); + IXGBE_WRITE_FLUSH(hw); + /* + * Clear FDIR Hash register to clear any leftover hashes + * waiting to be programmed. + */ + IXGBE_WRITE_REG(hw, IXGBE_FDIRHASH, 0x00); + IXGBE_WRITE_FLUSH(hw); + + IXGBE_WRITE_REG(hw, IXGBE_FDIRCTRL, fdirctrl); + IXGBE_WRITE_FLUSH(hw); + + /* Poll init-done after we write FDIRCTRL register */ + for (i = 0; i < IXGBE_FDIR_INIT_DONE_POLL; i++) { + if (IXGBE_READ_REG(hw, IXGBE_FDIRCTRL) & + IXGBE_FDIRCTRL_INIT_DONE) + break; + usleep_range(1000, 2000); + } + if (i >= IXGBE_FDIR_INIT_DONE_POLL) { + hw_dbg(hw, "Flow Director Signature poll time exceeded!\n"); + return IXGBE_ERR_FDIR_REINIT_FAILED; + } + + /* Clear FDIR statistics registers (read to clear) */ + IXGBE_READ_REG(hw, IXGBE_FDIRUSTAT); + IXGBE_READ_REG(hw, IXGBE_FDIRFSTAT); + IXGBE_READ_REG(hw, IXGBE_FDIRMATCH); + IXGBE_READ_REG(hw, IXGBE_FDIRMISS); + IXGBE_READ_REG(hw, IXGBE_FDIRLEN); + + return 0; +} + +/** + * ixgbe_fdir_enable_82599 - Initialize Flow Director control registers + * @hw: pointer to hardware structure + * @fdirctrl: value to write to flow director control register + **/ +static void ixgbe_fdir_enable_82599(struct ixgbe_hw *hw, u32 fdirctrl) +{ + int i; + + /* Prime the keys for hashing */ + IXGBE_WRITE_REG(hw, IXGBE_FDIRHKEY, IXGBE_ATR_BUCKET_HASH_KEY); + IXGBE_WRITE_REG(hw, IXGBE_FDIRSKEY, IXGBE_ATR_SIGNATURE_HASH_KEY); + + /* + * Poll init-done after we write the register. Estimated times: + * 10G: PBALLOC = 11b, timing is 60us + * 1G: PBALLOC = 11b, timing is 600us + * 100M: PBALLOC = 11b, timing is 6ms + * + * Multiple these timings by 4 if under full Rx load + * + * So we'll poll for IXGBE_FDIR_INIT_DONE_POLL times, sleeping for + * 1 msec per poll time. If we're at line rate and drop to 100M, then + * this might not finish in our poll time, but we can live with that + * for now. + */ + IXGBE_WRITE_REG(hw, IXGBE_FDIRCTRL, fdirctrl); + IXGBE_WRITE_FLUSH(hw); + for (i = 0; i < IXGBE_FDIR_INIT_DONE_POLL; i++) { + if (IXGBE_READ_REG(hw, IXGBE_FDIRCTRL) & + IXGBE_FDIRCTRL_INIT_DONE) + break; + usleep_range(1000, 2000); + } + + if (i >= IXGBE_FDIR_INIT_DONE_POLL) + hw_dbg(hw, "Flow Director poll time exceeded!\n"); +} + +/** + * ixgbe_init_fdir_signature_82599 - Initialize Flow Director signature filters + * @hw: pointer to hardware structure + * @fdirctrl: value to write to flow director control register, initially + * contains just the value of the Rx packet buffer allocation + **/ +s32 ixgbe_init_fdir_signature_82599(struct ixgbe_hw *hw, u32 fdirctrl) +{ + /* + * Continue setup of fdirctrl register bits: + * Move the flexible bytes to use the ethertype - shift 6 words + * Set the maximum length per hash bucket to 0xA filters + * Send interrupt when 64 filters are left + */ + fdirctrl |= (0x6 << IXGBE_FDIRCTRL_FLEX_SHIFT) | + (0xA << IXGBE_FDIRCTRL_MAX_LENGTH_SHIFT) | + (4 << IXGBE_FDIRCTRL_FULL_THRESH_SHIFT); + + /* write hashes and fdirctrl register, poll for completion */ + ixgbe_fdir_enable_82599(hw, fdirctrl); + + return 0; +} + +/** + * ixgbe_init_fdir_perfect_82599 - Initialize Flow Director perfect filters + * @hw: pointer to hardware structure + * @fdirctrl: value to write to flow director control register, initially + * contains just the value of the Rx packet buffer allocation + **/ +s32 ixgbe_init_fdir_perfect_82599(struct ixgbe_hw *hw, u32 fdirctrl) +{ + /* + * Continue setup of fdirctrl register bits: + * Turn perfect match filtering on + * Initialize the drop queue + * Move the flexible bytes to use the ethertype - shift 6 words + * Set the maximum length per hash bucket to 0xA filters + * Send interrupt when 64 (0x4 * 16) filters are left + */ + fdirctrl |= IXGBE_FDIRCTRL_PERFECT_MATCH | + (IXGBE_FDIR_DROP_QUEUE << IXGBE_FDIRCTRL_DROP_Q_SHIFT) | + (0x6 << IXGBE_FDIRCTRL_FLEX_SHIFT) | + (0xA << IXGBE_FDIRCTRL_MAX_LENGTH_SHIFT) | + (4 << IXGBE_FDIRCTRL_FULL_THRESH_SHIFT); + + /* write hashes and fdirctrl register, poll for completion */ + ixgbe_fdir_enable_82599(hw, fdirctrl); + + return 0; +} + +/* + * These defines allow us to quickly generate all of the necessary instructions + * in the function below by simply calling out IXGBE_COMPUTE_SIG_HASH_ITERATION + * for values 0 through 15 + */ +#define IXGBE_ATR_COMMON_HASH_KEY \ + (IXGBE_ATR_BUCKET_HASH_KEY & IXGBE_ATR_SIGNATURE_HASH_KEY) +#define IXGBE_COMPUTE_SIG_HASH_ITERATION(_n) \ +do { \ + u32 n = (_n); \ + if (IXGBE_ATR_COMMON_HASH_KEY & BIT(n)) \ + common_hash ^= lo_hash_dword >> n; \ + else if (IXGBE_ATR_BUCKET_HASH_KEY & BIT(n)) \ + bucket_hash ^= lo_hash_dword >> n; \ + else if (IXGBE_ATR_SIGNATURE_HASH_KEY & BIT(n)) \ + sig_hash ^= lo_hash_dword << (16 - n); \ + if (IXGBE_ATR_COMMON_HASH_KEY & BIT(n + 16)) \ + common_hash ^= hi_hash_dword >> n; \ + else if (IXGBE_ATR_BUCKET_HASH_KEY & BIT(n + 16)) \ + bucket_hash ^= hi_hash_dword >> n; \ + else if (IXGBE_ATR_SIGNATURE_HASH_KEY & BIT(n + 16)) \ + sig_hash ^= hi_hash_dword << (16 - n); \ +} while (0) + +/** + * ixgbe_atr_compute_sig_hash_82599 - Compute the signature hash + * @input: input bitstream to compute the hash on + * @common: compressed common input dword + * + * This function is almost identical to the function above but contains + * several optimizations such as unwinding all of the loops, letting the + * compiler work out all of the conditional ifs since the keys are static + * defines, and computing two keys at once since the hashed dword stream + * will be the same for both keys. + **/ +static u32 ixgbe_atr_compute_sig_hash_82599(union ixgbe_atr_hash_dword input, + union ixgbe_atr_hash_dword common) +{ + u32 hi_hash_dword, lo_hash_dword, flow_vm_vlan; + u32 sig_hash = 0, bucket_hash = 0, common_hash = 0; + + /* record the flow_vm_vlan bits as they are a key part to the hash */ + flow_vm_vlan = ntohl(input.dword); + + /* generate common hash dword */ + hi_hash_dword = ntohl(common.dword); + + /* low dword is word swapped version of common */ + lo_hash_dword = (hi_hash_dword >> 16) | (hi_hash_dword << 16); + + /* apply flow ID/VM pool/VLAN ID bits to hash words */ + hi_hash_dword ^= flow_vm_vlan ^ (flow_vm_vlan >> 16); + + /* Process bits 0 and 16 */ + IXGBE_COMPUTE_SIG_HASH_ITERATION(0); + + /* + * apply flow ID/VM pool/VLAN ID bits to lo hash dword, we had to + * delay this because bit 0 of the stream should not be processed + * so we do not add the vlan until after bit 0 was processed + */ + lo_hash_dword ^= flow_vm_vlan ^ (flow_vm_vlan << 16); + + /* Process remaining 30 bit of the key */ + IXGBE_COMPUTE_SIG_HASH_ITERATION(1); + IXGBE_COMPUTE_SIG_HASH_ITERATION(2); + IXGBE_COMPUTE_SIG_HASH_ITERATION(3); + IXGBE_COMPUTE_SIG_HASH_ITERATION(4); + IXGBE_COMPUTE_SIG_HASH_ITERATION(5); + IXGBE_COMPUTE_SIG_HASH_ITERATION(6); + IXGBE_COMPUTE_SIG_HASH_ITERATION(7); + IXGBE_COMPUTE_SIG_HASH_ITERATION(8); + IXGBE_COMPUTE_SIG_HASH_ITERATION(9); + IXGBE_COMPUTE_SIG_HASH_ITERATION(10); + IXGBE_COMPUTE_SIG_HASH_ITERATION(11); + IXGBE_COMPUTE_SIG_HASH_ITERATION(12); + IXGBE_COMPUTE_SIG_HASH_ITERATION(13); + IXGBE_COMPUTE_SIG_HASH_ITERATION(14); + IXGBE_COMPUTE_SIG_HASH_ITERATION(15); + + /* combine common_hash result with signature and bucket hashes */ + bucket_hash ^= common_hash; + bucket_hash &= IXGBE_ATR_HASH_MASK; + + sig_hash ^= common_hash << 16; + sig_hash &= IXGBE_ATR_HASH_MASK << 16; + + /* return completed signature hash */ + return sig_hash ^ bucket_hash; +} + +/** + * ixgbe_atr_add_signature_filter_82599 - Adds a signature hash filter + * @hw: pointer to hardware structure + * @input: unique input dword + * @common: compressed common input dword + * @queue: queue index to direct traffic to + * + * Note that the tunnel bit in input must not be set when the hardware + * tunneling support does not exist. + **/ +s32 ixgbe_fdir_add_signature_filter_82599(struct ixgbe_hw *hw, + union ixgbe_atr_hash_dword input, + union ixgbe_atr_hash_dword common, + u8 queue) +{ + u64 fdirhashcmd; + u8 flow_type; + bool tunnel; + u32 fdircmd; + + /* + * Get the flow_type in order to program FDIRCMD properly + * lowest 2 bits are FDIRCMD.L4TYPE, third lowest bit is FDIRCMD.IPV6 + */ + tunnel = !!(input.formatted.flow_type & IXGBE_ATR_L4TYPE_TUNNEL_MASK); + flow_type = input.formatted.flow_type & + (IXGBE_ATR_L4TYPE_TUNNEL_MASK - 1); + switch (flow_type) { + case IXGBE_ATR_FLOW_TYPE_TCPV4: + case IXGBE_ATR_FLOW_TYPE_UDPV4: + case IXGBE_ATR_FLOW_TYPE_SCTPV4: + case IXGBE_ATR_FLOW_TYPE_TCPV6: + case IXGBE_ATR_FLOW_TYPE_UDPV6: + case IXGBE_ATR_FLOW_TYPE_SCTPV6: + break; + default: + hw_dbg(hw, " Error on flow type input\n"); + return IXGBE_ERR_CONFIG; + } + + /* configure FDIRCMD register */ + fdircmd = IXGBE_FDIRCMD_CMD_ADD_FLOW | IXGBE_FDIRCMD_FILTER_UPDATE | + IXGBE_FDIRCMD_LAST | IXGBE_FDIRCMD_QUEUE_EN; + fdircmd |= (u32)flow_type << IXGBE_FDIRCMD_FLOW_TYPE_SHIFT; + fdircmd |= (u32)queue << IXGBE_FDIRCMD_RX_QUEUE_SHIFT; + if (tunnel) + fdircmd |= IXGBE_FDIRCMD_TUNNEL_FILTER; + + /* + * The lower 32-bits of fdirhashcmd is for FDIRHASH, the upper 32-bits + * is for FDIRCMD. Then do a 64-bit register write from FDIRHASH. + */ + fdirhashcmd = (u64)fdircmd << 32; + fdirhashcmd |= ixgbe_atr_compute_sig_hash_82599(input, common); + IXGBE_WRITE_REG64(hw, IXGBE_FDIRHASH, fdirhashcmd); + + hw_dbg(hw, "Tx Queue=%x hash=%x\n", queue, (u32)fdirhashcmd); + + return 0; +} + +#define IXGBE_COMPUTE_BKT_HASH_ITERATION(_n) \ +do { \ + u32 n = (_n); \ + if (IXGBE_ATR_BUCKET_HASH_KEY & BIT(n)) \ + bucket_hash ^= lo_hash_dword >> n; \ + if (IXGBE_ATR_BUCKET_HASH_KEY & BIT(n + 16)) \ + bucket_hash ^= hi_hash_dword >> n; \ +} while (0) + +/** + * ixgbe_atr_compute_perfect_hash_82599 - Compute the perfect filter hash + * @input: input bitstream to compute the hash on + * @input_mask: mask for the input bitstream + * + * This function serves two main purposes. First it applies the input_mask + * to the atr_input resulting in a cleaned up atr_input data stream. + * Secondly it computes the hash and stores it in the bkt_hash field at + * the end of the input byte stream. This way it will be available for + * future use without needing to recompute the hash. + **/ +void ixgbe_atr_compute_perfect_hash_82599(union ixgbe_atr_input *input, + union ixgbe_atr_input *input_mask) +{ + + u32 hi_hash_dword, lo_hash_dword, flow_vm_vlan; + u32 bucket_hash = 0; + __be32 hi_dword = 0; + int i; + + /* Apply masks to input data */ + for (i = 0; i <= 10; i++) + input->dword_stream[i] &= input_mask->dword_stream[i]; + + /* record the flow_vm_vlan bits as they are a key part to the hash */ + flow_vm_vlan = ntohl(input->dword_stream[0]); + + /* generate common hash dword */ + for (i = 1; i <= 10; i++) + hi_dword ^= input->dword_stream[i]; + hi_hash_dword = ntohl(hi_dword); + + /* low dword is word swapped version of common */ + lo_hash_dword = (hi_hash_dword >> 16) | (hi_hash_dword << 16); + + /* apply flow ID/VM pool/VLAN ID bits to hash words */ + hi_hash_dword ^= flow_vm_vlan ^ (flow_vm_vlan >> 16); + + /* Process bits 0 and 16 */ + IXGBE_COMPUTE_BKT_HASH_ITERATION(0); + + /* + * apply flow ID/VM pool/VLAN ID bits to lo hash dword, we had to + * delay this because bit 0 of the stream should not be processed + * so we do not add the vlan until after bit 0 was processed + */ + lo_hash_dword ^= flow_vm_vlan ^ (flow_vm_vlan << 16); + + /* Process remaining 30 bit of the key */ + for (i = 1; i <= 15; i++) + IXGBE_COMPUTE_BKT_HASH_ITERATION(i); + + /* + * Limit hash to 13 bits since max bucket count is 8K. + * Store result at the end of the input stream. + */ + input->formatted.bkt_hash = (__force __be16)(bucket_hash & 0x1FFF); +} + +/** + * ixgbe_get_fdirtcpm_82599 - generate a tcp port from atr_input_masks + * @input_mask: mask to be bit swapped + * + * The source and destination port masks for flow director are bit swapped + * in that bit 15 effects bit 0, 14 effects 1, 13, 2 etc. In order to + * generate a correctly swapped value we need to bit swap the mask and that + * is what is accomplished by this function. + **/ +static u32 ixgbe_get_fdirtcpm_82599(union ixgbe_atr_input *input_mask) +{ + u32 mask = ntohs(input_mask->formatted.dst_port); + + mask <<= IXGBE_FDIRTCPM_DPORTM_SHIFT; + mask |= ntohs(input_mask->formatted.src_port); + mask = ((mask & 0x55555555) << 1) | ((mask & 0xAAAAAAAA) >> 1); + mask = ((mask & 0x33333333) << 2) | ((mask & 0xCCCCCCCC) >> 2); + mask = ((mask & 0x0F0F0F0F) << 4) | ((mask & 0xF0F0F0F0) >> 4); + return ((mask & 0x00FF00FF) << 8) | ((mask & 0xFF00FF00) >> 8); +} + +/* + * These two macros are meant to address the fact that we have registers + * that are either all or in part big-endian. As a result on big-endian + * systems we will end up byte swapping the value to little-endian before + * it is byte swapped again and written to the hardware in the original + * big-endian format. + */ +#define IXGBE_STORE_AS_BE32(_value) \ + (((u32)(_value) >> 24) | (((u32)(_value) & 0x00FF0000) >> 8) | \ + (((u32)(_value) & 0x0000FF00) << 8) | ((u32)(_value) << 24)) + +#define IXGBE_WRITE_REG_BE32(a, reg, value) \ + IXGBE_WRITE_REG((a), (reg), IXGBE_STORE_AS_BE32(ntohl(value))) + +#define IXGBE_STORE_AS_BE16(_value) \ + ntohs(((u16)(_value) >> 8) | ((u16)(_value) << 8)) + +s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, + union ixgbe_atr_input *input_mask) +{ + /* mask IPv6 since it is currently not supported */ + u32 fdirm = IXGBE_FDIRM_DIPv6; + u32 fdirtcpm; + + /* + * Program the relevant mask registers. If src/dst_port or src/dst_addr + * are zero, then assume a full mask for that field. Also assume that + * a VLAN of 0 is unspecified, so mask that out as well. L4type + * cannot be masked out in this implementation. + * + * This also assumes IPv4 only. IPv6 masking isn't supported at this + * point in time. + */ + + /* verify bucket hash is cleared on hash generation */ + if (input_mask->formatted.bkt_hash) + hw_dbg(hw, " bucket hash should always be 0 in mask\n"); + + /* Program FDIRM and verify partial masks */ + switch (input_mask->formatted.vm_pool & 0x7F) { + case 0x0: + fdirm |= IXGBE_FDIRM_POOL; + case 0x7F: + break; + default: + hw_dbg(hw, " Error on vm pool mask\n"); + return IXGBE_ERR_CONFIG; + } + + switch (input_mask->formatted.flow_type & IXGBE_ATR_L4TYPE_MASK) { + case 0x0: + fdirm |= IXGBE_FDIRM_L4P; + if (input_mask->formatted.dst_port || + input_mask->formatted.src_port) { + hw_dbg(hw, " Error on src/dst port mask\n"); + return IXGBE_ERR_CONFIG; + } + case IXGBE_ATR_L4TYPE_MASK: + break; + default: + hw_dbg(hw, " Error on flow type mask\n"); + return IXGBE_ERR_CONFIG; + } + + switch (ntohs(input_mask->formatted.vlan_id) & 0xEFFF) { + case 0x0000: + /* mask VLAN ID */ + fdirm |= IXGBE_FDIRM_VLANID; + fallthrough; + case 0x0FFF: + /* mask VLAN priority */ + fdirm |= IXGBE_FDIRM_VLANP; + break; + case 0xE000: + /* mask VLAN ID only */ + fdirm |= IXGBE_FDIRM_VLANID; + fallthrough; + case 0xEFFF: + /* no VLAN fields masked */ + break; + default: + hw_dbg(hw, " Error on VLAN mask\n"); + return IXGBE_ERR_CONFIG; + } + + switch ((__force u16)input_mask->formatted.flex_bytes & 0xFFFF) { + case 0x0000: + /* Mask Flex Bytes */ + fdirm |= IXGBE_FDIRM_FLEX; + fallthrough; + case 0xFFFF: + break; + default: + hw_dbg(hw, " Error on flexible byte mask\n"); + return IXGBE_ERR_CONFIG; + } + + /* Now mask VM pool and destination IPv6 - bits 5 and 2 */ + IXGBE_WRITE_REG(hw, IXGBE_FDIRM, fdirm); + + /* store the TCP/UDP port masks, bit reversed from port layout */ + fdirtcpm = ixgbe_get_fdirtcpm_82599(input_mask); + + /* write both the same so that UDP and TCP use the same mask */ + IXGBE_WRITE_REG(hw, IXGBE_FDIRTCPM, ~fdirtcpm); + IXGBE_WRITE_REG(hw, IXGBE_FDIRUDPM, ~fdirtcpm); + + /* also use it for SCTP */ + switch (hw->mac.type) { + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + IXGBE_WRITE_REG(hw, IXGBE_FDIRSCTPM, ~fdirtcpm); + break; + default: + break; + } + + /* store source and destination IP masks (big-enian) */ + IXGBE_WRITE_REG_BE32(hw, IXGBE_FDIRSIP4M, + ~input_mask->formatted.src_ip[0]); + IXGBE_WRITE_REG_BE32(hw, IXGBE_FDIRDIP4M, + ~input_mask->formatted.dst_ip[0]); + + return 0; +} + +s32 ixgbe_fdir_write_perfect_filter_82599(struct ixgbe_hw *hw, + union ixgbe_atr_input *input, + u16 soft_id, u8 queue) +{ + u32 fdirport, fdirvlan, fdirhash, fdircmd; + s32 err; + + /* currently IPv6 is not supported, must be programmed with 0 */ + IXGBE_WRITE_REG_BE32(hw, IXGBE_FDIRSIPv6(0), + input->formatted.src_ip[0]); + IXGBE_WRITE_REG_BE32(hw, IXGBE_FDIRSIPv6(1), + input->formatted.src_ip[1]); + IXGBE_WRITE_REG_BE32(hw, IXGBE_FDIRSIPv6(2), + input->formatted.src_ip[2]); + + /* record the source address (big-endian) */ + IXGBE_WRITE_REG_BE32(hw, IXGBE_FDIRIPSA, input->formatted.src_ip[0]); + + /* record the first 32 bits of the destination address (big-endian) */ + IXGBE_WRITE_REG_BE32(hw, IXGBE_FDIRIPDA, input->formatted.dst_ip[0]); + + /* record source and destination port (little-endian)*/ + fdirport = ntohs(input->formatted.dst_port); + fdirport <<= IXGBE_FDIRPORT_DESTINATION_SHIFT; + fdirport |= ntohs(input->formatted.src_port); + IXGBE_WRITE_REG(hw, IXGBE_FDIRPORT, fdirport); + + /* record vlan (little-endian) and flex_bytes(big-endian) */ + fdirvlan = IXGBE_STORE_AS_BE16((__force u16)input->formatted.flex_bytes); + fdirvlan <<= IXGBE_FDIRVLAN_FLEX_SHIFT; + fdirvlan |= ntohs(input->formatted.vlan_id); + IXGBE_WRITE_REG(hw, IXGBE_FDIRVLAN, fdirvlan); + + /* configure FDIRHASH register */ + fdirhash = (__force u32)input->formatted.bkt_hash; + fdirhash |= soft_id << IXGBE_FDIRHASH_SIG_SW_INDEX_SHIFT; + IXGBE_WRITE_REG(hw, IXGBE_FDIRHASH, fdirhash); + + /* + * flush all previous writes to make certain registers are + * programmed prior to issuing the command + */ + IXGBE_WRITE_FLUSH(hw); + + /* configure FDIRCMD register */ + fdircmd = IXGBE_FDIRCMD_CMD_ADD_FLOW | IXGBE_FDIRCMD_FILTER_UPDATE | + IXGBE_FDIRCMD_LAST | IXGBE_FDIRCMD_QUEUE_EN; + if (queue == IXGBE_FDIR_DROP_QUEUE) + fdircmd |= IXGBE_FDIRCMD_DROP; + fdircmd |= input->formatted.flow_type << IXGBE_FDIRCMD_FLOW_TYPE_SHIFT; + fdircmd |= (u32)queue << IXGBE_FDIRCMD_RX_QUEUE_SHIFT; + fdircmd |= (u32)input->formatted.vm_pool << IXGBE_FDIRCMD_VT_POOL_SHIFT; + + IXGBE_WRITE_REG(hw, IXGBE_FDIRCMD, fdircmd); + err = ixgbe_fdir_check_cmd_complete(hw, &fdircmd); + if (err) { + hw_dbg(hw, "Flow Director command did not complete!\n"); + return err; + } + + return 0; +} + +s32 ixgbe_fdir_erase_perfect_filter_82599(struct ixgbe_hw *hw, + union ixgbe_atr_input *input, + u16 soft_id) +{ + u32 fdirhash; + u32 fdircmd; + s32 err; + + /* configure FDIRHASH register */ + fdirhash = (__force u32)input->formatted.bkt_hash; + fdirhash |= soft_id << IXGBE_FDIRHASH_SIG_SW_INDEX_SHIFT; + IXGBE_WRITE_REG(hw, IXGBE_FDIRHASH, fdirhash); + + /* flush hash to HW */ + IXGBE_WRITE_FLUSH(hw); + + /* Query if filter is present */ + IXGBE_WRITE_REG(hw, IXGBE_FDIRCMD, IXGBE_FDIRCMD_CMD_QUERY_REM_FILT); + + err = ixgbe_fdir_check_cmd_complete(hw, &fdircmd); + if (err) { + hw_dbg(hw, "Flow Director command did not complete!\n"); + return err; + } + + /* if filter exists in hardware then remove it */ + if (fdircmd & IXGBE_FDIRCMD_FILTER_VALID) { + IXGBE_WRITE_REG(hw, IXGBE_FDIRHASH, fdirhash); + IXGBE_WRITE_FLUSH(hw); + IXGBE_WRITE_REG(hw, IXGBE_FDIRCMD, + IXGBE_FDIRCMD_CMD_REMOVE_FLOW); + } + + return 0; +} + +/** + * ixgbe_read_analog_reg8_82599 - Reads 8 bit Omer analog register + * @hw: pointer to hardware structure + * @reg: analog register to read + * @val: read value + * + * Performs read operation to Omer analog register specified. + **/ +static s32 ixgbe_read_analog_reg8_82599(struct ixgbe_hw *hw, u32 reg, u8 *val) +{ + u32 core_ctl; + + IXGBE_WRITE_REG(hw, IXGBE_CORECTL, IXGBE_CORECTL_WRITE_CMD | + (reg << 8)); + IXGBE_WRITE_FLUSH(hw); + udelay(10); + core_ctl = IXGBE_READ_REG(hw, IXGBE_CORECTL); + *val = (u8)core_ctl; + + return 0; +} + +/** + * ixgbe_write_analog_reg8_82599 - Writes 8 bit Omer analog register + * @hw: pointer to hardware structure + * @reg: atlas register to write + * @val: value to write + * + * Performs write operation to Omer analog register specified. + **/ +static s32 ixgbe_write_analog_reg8_82599(struct ixgbe_hw *hw, u32 reg, u8 val) +{ + u32 core_ctl; + + core_ctl = (reg << 8) | val; + IXGBE_WRITE_REG(hw, IXGBE_CORECTL, core_ctl); + IXGBE_WRITE_FLUSH(hw); + udelay(10); + + return 0; +} + +/** + * ixgbe_start_hw_82599 - Prepare hardware for Tx/Rx + * @hw: pointer to hardware structure + * + * Starts the hardware using the generic start_hw function + * and the generation start_hw function. + * Then performs revision-specific operations, if any. + **/ +static s32 ixgbe_start_hw_82599(struct ixgbe_hw *hw) +{ + s32 ret_val = 0; + + ret_val = ixgbe_start_hw_generic(hw); + if (ret_val) + return ret_val; + + ret_val = ixgbe_start_hw_gen2(hw); + if (ret_val) + return ret_val; + + /* We need to run link autotry after the driver loads */ + hw->mac.autotry_restart = true; + + return ixgbe_verify_fw_version_82599(hw); +} + +/** + * ixgbe_identify_phy_82599 - Get physical layer module + * @hw: pointer to hardware structure + * + * Determines the physical layer module found on the current adapter. + * If PHY already detected, maintains current PHY type in hw struct, + * otherwise executes the PHY detection routine. + **/ +static s32 ixgbe_identify_phy_82599(struct ixgbe_hw *hw) +{ + s32 status; + + /* Detect PHY if not unknown - returns success if already detected. */ + status = ixgbe_identify_phy_generic(hw); + if (status) { + /* 82599 10GBASE-T requires an external PHY */ + if (hw->mac.ops.get_media_type(hw) == ixgbe_media_type_copper) + return status; + status = ixgbe_identify_module_generic(hw); + } + + /* Set PHY type none if no PHY detected */ + if (hw->phy.type == ixgbe_phy_unknown) { + hw->phy.type = ixgbe_phy_none; + status = 0; + } + + /* Return error if SFP module has been detected but is not supported */ + if (hw->phy.type == ixgbe_phy_sfp_unsupported) + return IXGBE_ERR_SFP_NOT_SUPPORTED; + + return status; +} + +/** + * ixgbe_enable_rx_dma_82599 - Enable the Rx DMA unit on 82599 + * @hw: pointer to hardware structure + * @regval: register value to write to RXCTRL + * + * Enables the Rx DMA unit for 82599 + **/ +static s32 ixgbe_enable_rx_dma_82599(struct ixgbe_hw *hw, u32 regval) +{ + /* + * Workaround for 82599 silicon errata when enabling the Rx datapath. + * If traffic is incoming before we enable the Rx unit, it could hang + * the Rx DMA unit. Therefore, make sure the security engine is + * completely disabled prior to enabling the Rx unit. + */ + hw->mac.ops.disable_rx_buff(hw); + + if (regval & IXGBE_RXCTRL_RXEN) + hw->mac.ops.enable_rx(hw); + else + hw->mac.ops.disable_rx(hw); + + hw->mac.ops.enable_rx_buff(hw); + + return 0; +} + +/** + * ixgbe_verify_fw_version_82599 - verify fw version for 82599 + * @hw: pointer to hardware structure + * + * Verifies that installed the firmware version is 0.6 or higher + * for SFI devices. All 82599 SFI devices should have version 0.6 or higher. + * + * Returns IXGBE_ERR_EEPROM_VERSION if the FW is not present or + * if the FW version is not supported. + **/ +static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw) +{ + s32 status = IXGBE_ERR_EEPROM_VERSION; + u16 fw_offset, fw_ptp_cfg_offset; + u16 offset; + u16 fw_version = 0; + + /* firmware check is only necessary for SFI devices */ + if (hw->phy.media_type != ixgbe_media_type_fiber) + return 0; + + /* get the offset to the Firmware Module block */ + offset = IXGBE_FW_PTR; + if (hw->eeprom.ops.read(hw, offset, &fw_offset)) + goto fw_version_err; + + if (fw_offset == 0 || fw_offset == 0xFFFF) + return IXGBE_ERR_EEPROM_VERSION; + + /* get the offset to the Pass Through Patch Configuration block */ + offset = fw_offset + IXGBE_FW_PASSTHROUGH_PATCH_CONFIG_PTR; + if (hw->eeprom.ops.read(hw, offset, &fw_ptp_cfg_offset)) + goto fw_version_err; + + if (fw_ptp_cfg_offset == 0 || fw_ptp_cfg_offset == 0xFFFF) + return IXGBE_ERR_EEPROM_VERSION; + + /* get the firmware version */ + offset = fw_ptp_cfg_offset + IXGBE_FW_PATCH_VERSION_4; + if (hw->eeprom.ops.read(hw, offset, &fw_version)) + goto fw_version_err; + + if (fw_version > 0x5) + status = 0; + + return status; + +fw_version_err: + hw_err(hw, "eeprom read at offset %d failed\n", offset); + return IXGBE_ERR_EEPROM_VERSION; +} + +/** + * ixgbe_verify_lesm_fw_enabled_82599 - Checks LESM FW module state. + * @hw: pointer to hardware structure + * + * Returns true if the LESM FW module is present and enabled. Otherwise + * returns false. Smart Speed must be disabled if LESM FW module is enabled. + **/ +static bool ixgbe_verify_lesm_fw_enabled_82599(struct ixgbe_hw *hw) +{ + u16 fw_offset, fw_lesm_param_offset, fw_lesm_state; + s32 status; + + /* get the offset to the Firmware Module block */ + status = hw->eeprom.ops.read(hw, IXGBE_FW_PTR, &fw_offset); + + if (status || fw_offset == 0 || fw_offset == 0xFFFF) + return false; + + /* get the offset to the LESM Parameters block */ + status = hw->eeprom.ops.read(hw, (fw_offset + + IXGBE_FW_LESM_PARAMETERS_PTR), + &fw_lesm_param_offset); + + if (status || + fw_lesm_param_offset == 0 || fw_lesm_param_offset == 0xFFFF) + return false; + + /* get the lesm state word */ + status = hw->eeprom.ops.read(hw, (fw_lesm_param_offset + + IXGBE_FW_LESM_STATE_1), + &fw_lesm_state); + + if (!status && (fw_lesm_state & IXGBE_FW_LESM_STATE_ENABLED)) + return true; + + return false; +} + +/** + * ixgbe_read_eeprom_buffer_82599 - Read EEPROM word(s) using + * fastest available method + * + * @hw: pointer to hardware structure + * @offset: offset of word in EEPROM to read + * @words: number of words + * @data: word(s) read from the EEPROM + * + * Retrieves 16 bit word(s) read from EEPROM + **/ +static s32 ixgbe_read_eeprom_buffer_82599(struct ixgbe_hw *hw, u16 offset, + u16 words, u16 *data) +{ + struct ixgbe_eeprom_info *eeprom = &hw->eeprom; + + /* If EEPROM is detected and can be addressed using 14 bits, + * use EERD otherwise use bit bang + */ + if (eeprom->type == ixgbe_eeprom_spi && + offset + (words - 1) <= IXGBE_EERD_MAX_ADDR) + return ixgbe_read_eerd_buffer_generic(hw, offset, words, data); + + return ixgbe_read_eeprom_buffer_bit_bang_generic(hw, offset, words, + data); +} + +/** + * ixgbe_read_eeprom_82599 - Read EEPROM word using + * fastest available method + * + * @hw: pointer to hardware structure + * @offset: offset of word in the EEPROM to read + * @data: word read from the EEPROM + * + * Reads a 16 bit word from the EEPROM + **/ +static s32 ixgbe_read_eeprom_82599(struct ixgbe_hw *hw, + u16 offset, u16 *data) +{ + struct ixgbe_eeprom_info *eeprom = &hw->eeprom; + + /* + * If EEPROM is detected and can be addressed using 14 bits, + * use EERD otherwise use bit bang + */ + if (eeprom->type == ixgbe_eeprom_spi && offset <= IXGBE_EERD_MAX_ADDR) + return ixgbe_read_eerd_generic(hw, offset, data); + + return ixgbe_read_eeprom_bit_bang_generic(hw, offset, data); +} + +/** + * ixgbe_reset_pipeline_82599 - perform pipeline reset + * + * @hw: pointer to hardware structure + * + * Reset pipeline by asserting Restart_AN together with LMS change to ensure + * full pipeline reset. Note - We must hold the SW/FW semaphore before writing + * to AUTOC, so this function assumes the semaphore is held. + **/ +static s32 ixgbe_reset_pipeline_82599(struct ixgbe_hw *hw) +{ + s32 ret_val; + u32 anlp1_reg = 0; + u32 i, autoc_reg, autoc2_reg; + + /* Enable link if disabled in NVM */ + autoc2_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC2); + if (autoc2_reg & IXGBE_AUTOC2_LINK_DISABLE_MASK) { + autoc2_reg &= ~IXGBE_AUTOC2_LINK_DISABLE_MASK; + IXGBE_WRITE_REG(hw, IXGBE_AUTOC2, autoc2_reg); + IXGBE_WRITE_FLUSH(hw); + } + + autoc_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC); + autoc_reg |= IXGBE_AUTOC_AN_RESTART; + + /* Write AUTOC register with toggled LMS[2] bit and Restart_AN */ + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, + autoc_reg ^ (0x4 << IXGBE_AUTOC_LMS_SHIFT)); + + /* Wait for AN to leave state 0 */ + for (i = 0; i < 10; i++) { + usleep_range(4000, 8000); + anlp1_reg = IXGBE_READ_REG(hw, IXGBE_ANLP1); + if (anlp1_reg & IXGBE_ANLP1_AN_STATE_MASK) + break; + } + + if (!(anlp1_reg & IXGBE_ANLP1_AN_STATE_MASK)) { + hw_dbg(hw, "auto negotiation not completed\n"); + ret_val = IXGBE_ERR_RESET_FAILED; + goto reset_pipeline_out; + } + + ret_val = 0; + +reset_pipeline_out: + /* Write AUTOC register with original LMS field and Restart_AN */ + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc_reg); + IXGBE_WRITE_FLUSH(hw); + + return ret_val; +} + +/** + * ixgbe_read_i2c_byte_82599 - Reads 8 bit word over I2C + * @hw: pointer to hardware structure + * @byte_offset: byte offset to read + * @dev_addr: address to read from + * @data: value read + * + * Performs byte read operation to SFP module's EEPROM over I2C interface at + * a specified device address. + **/ +static s32 ixgbe_read_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 *data) +{ + u32 esdp; + s32 status; + s32 timeout = 200; + + if (hw->phy.qsfp_shared_i2c_bus == true) { + /* Acquire I2C bus ownership. */ + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + esdp |= IXGBE_ESDP_SDP0; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp); + IXGBE_WRITE_FLUSH(hw); + + while (timeout) { + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + if (esdp & IXGBE_ESDP_SDP1) + break; + + usleep_range(5000, 10000); + timeout--; + } + + if (!timeout) { + hw_dbg(hw, "Driver can't access resource, acquiring I2C bus timeout.\n"); + status = IXGBE_ERR_I2C; + goto release_i2c_access; + } + } + + status = ixgbe_read_i2c_byte_generic(hw, byte_offset, dev_addr, data); + +release_i2c_access: + if (hw->phy.qsfp_shared_i2c_bus == true) { + /* Release I2C bus ownership. */ + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + esdp &= ~IXGBE_ESDP_SDP0; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp); + IXGBE_WRITE_FLUSH(hw); + } + + return status; +} + +/** + * ixgbe_write_i2c_byte_82599 - Writes 8 bit word over I2C + * @hw: pointer to hardware structure + * @byte_offset: byte offset to write + * @dev_addr: address to write to + * @data: value to write + * + * Performs byte write operation to SFP module's EEPROM over I2C interface at + * a specified device address. + **/ +static s32 ixgbe_write_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 data) +{ + u32 esdp; + s32 status; + s32 timeout = 200; + + if (hw->phy.qsfp_shared_i2c_bus == true) { + /* Acquire I2C bus ownership. */ + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + esdp |= IXGBE_ESDP_SDP0; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp); + IXGBE_WRITE_FLUSH(hw); + + while (timeout) { + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + if (esdp & IXGBE_ESDP_SDP1) + break; + + usleep_range(5000, 10000); + timeout--; + } + + if (!timeout) { + hw_dbg(hw, "Driver can't access resource, acquiring I2C bus timeout.\n"); + status = IXGBE_ERR_I2C; + goto release_i2c_access; + } + } + + status = ixgbe_write_i2c_byte_generic(hw, byte_offset, dev_addr, data); + +release_i2c_access: + if (hw->phy.qsfp_shared_i2c_bus == true) { + /* Release I2C bus ownership. */ + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + esdp &= ~IXGBE_ESDP_SDP0; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp); + IXGBE_WRITE_FLUSH(hw); + } + + return status; +} + +static const struct ixgbe_mac_operations mac_ops_82599 = { + .init_hw = &ixgbe_init_hw_generic, + .reset_hw = &ixgbe_reset_hw_82599, + .start_hw = &ixgbe_start_hw_82599, + .clear_hw_cntrs = &ixgbe_clear_hw_cntrs_generic, + .get_media_type = &ixgbe_get_media_type_82599, + .enable_rx_dma = &ixgbe_enable_rx_dma_82599, + .disable_rx_buff = &ixgbe_disable_rx_buff_generic, + .enable_rx_buff = &ixgbe_enable_rx_buff_generic, + .get_mac_addr = &ixgbe_get_mac_addr_generic, + .get_san_mac_addr = &ixgbe_get_san_mac_addr_generic, + .get_device_caps = &ixgbe_get_device_caps_generic, + .get_wwn_prefix = &ixgbe_get_wwn_prefix_generic, + .stop_adapter = &ixgbe_stop_adapter_generic, + .get_bus_info = &ixgbe_get_bus_info_generic, + .set_lan_id = &ixgbe_set_lan_id_multi_port_pcie, + .read_analog_reg8 = &ixgbe_read_analog_reg8_82599, + .write_analog_reg8 = &ixgbe_write_analog_reg8_82599, + .stop_link_on_d3 = &ixgbe_stop_mac_link_on_d3_82599, + .setup_link = &ixgbe_setup_mac_link_82599, + .set_rxpba = &ixgbe_set_rxpba_generic, + .check_link = &ixgbe_check_mac_link_generic, + .get_link_capabilities = &ixgbe_get_link_capabilities_82599, + .led_on = &ixgbe_led_on_generic, + .led_off = &ixgbe_led_off_generic, + .init_led_link_act = ixgbe_init_led_link_act_generic, + .blink_led_start = &ixgbe_blink_led_start_generic, + .blink_led_stop = &ixgbe_blink_led_stop_generic, + .set_rar = &ixgbe_set_rar_generic, + .clear_rar = &ixgbe_clear_rar_generic, + .set_vmdq = &ixgbe_set_vmdq_generic, + .set_vmdq_san_mac = &ixgbe_set_vmdq_san_mac_generic, + .clear_vmdq = &ixgbe_clear_vmdq_generic, + .init_rx_addrs = &ixgbe_init_rx_addrs_generic, + .update_mc_addr_list = &ixgbe_update_mc_addr_list_generic, + .enable_mc = &ixgbe_enable_mc_generic, + .disable_mc = &ixgbe_disable_mc_generic, + .clear_vfta = &ixgbe_clear_vfta_generic, + .set_vfta = &ixgbe_set_vfta_generic, + .fc_enable = &ixgbe_fc_enable_generic, + .setup_fc = ixgbe_setup_fc_generic, + .fc_autoneg = ixgbe_fc_autoneg, + .set_fw_drv_ver = &ixgbe_set_fw_drv_ver_generic, + .init_uta_tables = &ixgbe_init_uta_tables_generic, + .setup_sfp = &ixgbe_setup_sfp_modules_82599, + .set_mac_anti_spoofing = &ixgbe_set_mac_anti_spoofing, + .set_vlan_anti_spoofing = &ixgbe_set_vlan_anti_spoofing, + .acquire_swfw_sync = &ixgbe_acquire_swfw_sync, + .release_swfw_sync = &ixgbe_release_swfw_sync, + .init_swfw_sync = NULL, + .get_thermal_sensor_data = &ixgbe_get_thermal_sensor_data_generic, + .init_thermal_sensor_thresh = &ixgbe_init_thermal_sensor_thresh_generic, + .prot_autoc_read = &prot_autoc_read_82599, + .prot_autoc_write = &prot_autoc_write_82599, + .enable_rx = &ixgbe_enable_rx_generic, + .disable_rx = &ixgbe_disable_rx_generic, +}; + +static const struct ixgbe_eeprom_operations eeprom_ops_82599 = { + .init_params = &ixgbe_init_eeprom_params_generic, + .read = &ixgbe_read_eeprom_82599, + .read_buffer = &ixgbe_read_eeprom_buffer_82599, + .write = &ixgbe_write_eeprom_generic, + .write_buffer = &ixgbe_write_eeprom_buffer_bit_bang_generic, + .calc_checksum = &ixgbe_calc_eeprom_checksum_generic, + .validate_checksum = &ixgbe_validate_eeprom_checksum_generic, + .update_checksum = &ixgbe_update_eeprom_checksum_generic, +}; + +static const struct ixgbe_phy_operations phy_ops_82599 = { + .identify = &ixgbe_identify_phy_82599, + .identify_sfp = &ixgbe_identify_module_generic, + .init = &ixgbe_init_phy_ops_82599, + .reset = &ixgbe_reset_phy_generic, + .read_reg = &ixgbe_read_phy_reg_generic, + .write_reg = &ixgbe_write_phy_reg_generic, + .setup_link = &ixgbe_setup_phy_link_generic, + .setup_link_speed = &ixgbe_setup_phy_link_speed_generic, + .read_i2c_byte = &ixgbe_read_i2c_byte_generic, + .write_i2c_byte = &ixgbe_write_i2c_byte_generic, + .read_i2c_sff8472 = &ixgbe_read_i2c_sff8472_generic, + .read_i2c_eeprom = &ixgbe_read_i2c_eeprom_generic, + .write_i2c_eeprom = &ixgbe_write_i2c_eeprom_generic, + .check_overtemp = &ixgbe_tn_check_overtemp, +}; + +const struct ixgbe_info ixgbe_82599_info = { + .mac = ixgbe_mac_82599EB, + .get_invariants = &ixgbe_get_invariants_82599, + .mac_ops = &mac_ops_82599, + .eeprom_ops = &eeprom_ops_82599, + .phy_ops = &phy_ops_82599, + .mbx_ops = &mbx_ops_generic, + .mvals = ixgbe_mvals_8259X, +}; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c new file mode 100644 index 000000000..62ddb452f --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -0,0 +1,4396 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#include <linux/pci.h> +#include <linux/delay.h> +#include <linux/sched.h> +#include <linux/netdevice.h> + +#include "ixgbe.h" +#include "ixgbe_common.h" +#include "ixgbe_phy.h" + +static s32 ixgbe_acquire_eeprom(struct ixgbe_hw *hw); +static s32 ixgbe_get_eeprom_semaphore(struct ixgbe_hw *hw); +static void ixgbe_release_eeprom_semaphore(struct ixgbe_hw *hw); +static s32 ixgbe_ready_eeprom(struct ixgbe_hw *hw); +static void ixgbe_standby_eeprom(struct ixgbe_hw *hw); +static void ixgbe_shift_out_eeprom_bits(struct ixgbe_hw *hw, u16 data, + u16 count); +static u16 ixgbe_shift_in_eeprom_bits(struct ixgbe_hw *hw, u16 count); +static void ixgbe_raise_eeprom_clk(struct ixgbe_hw *hw, u32 *eec); +static void ixgbe_lower_eeprom_clk(struct ixgbe_hw *hw, u32 *eec); +static void ixgbe_release_eeprom(struct ixgbe_hw *hw); + +static s32 ixgbe_mta_vector(struct ixgbe_hw *hw, u8 *mc_addr); +static s32 ixgbe_poll_eerd_eewr_done(struct ixgbe_hw *hw, u32 ee_reg); +static s32 ixgbe_read_eeprom_buffer_bit_bang(struct ixgbe_hw *hw, u16 offset, + u16 words, u16 *data); +static s32 ixgbe_write_eeprom_buffer_bit_bang(struct ixgbe_hw *hw, u16 offset, + u16 words, u16 *data); +static s32 ixgbe_detect_eeprom_page_size_generic(struct ixgbe_hw *hw, + u16 offset); +static s32 ixgbe_disable_pcie_master(struct ixgbe_hw *hw); + +/* Base table for registers values that change by MAC */ +const u32 ixgbe_mvals_8259X[IXGBE_MVALS_IDX_LIMIT] = { + IXGBE_MVALS_INIT(8259X) +}; + +/** + * ixgbe_device_supports_autoneg_fc - Check if phy supports autoneg flow + * control + * @hw: pointer to hardware structure + * + * There are several phys that do not support autoneg flow control. This + * function check the device id to see if the associated phy supports + * autoneg flow control. + **/ +bool ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw) +{ + bool supported = false; + ixgbe_link_speed speed; + bool link_up; + + switch (hw->phy.media_type) { + case ixgbe_media_type_fiber: + /* flow control autoneg black list */ + switch (hw->device_id) { + case IXGBE_DEV_ID_X550EM_A_SFP: + case IXGBE_DEV_ID_X550EM_A_SFP_N: + supported = false; + break; + default: + hw->mac.ops.check_link(hw, &speed, &link_up, false); + /* if link is down, assume supported */ + if (link_up) + supported = speed == IXGBE_LINK_SPEED_1GB_FULL; + else + supported = true; + } + + break; + case ixgbe_media_type_backplane: + if (hw->device_id == IXGBE_DEV_ID_X550EM_X_XFI) + supported = false; + else + supported = true; + break; + case ixgbe_media_type_copper: + /* only some copper devices support flow control autoneg */ + switch (hw->device_id) { + case IXGBE_DEV_ID_82599_T3_LOM: + case IXGBE_DEV_ID_X540T: + case IXGBE_DEV_ID_X540T1: + case IXGBE_DEV_ID_X550T: + case IXGBE_DEV_ID_X550T1: + case IXGBE_DEV_ID_X550EM_X_10G_T: + case IXGBE_DEV_ID_X550EM_A_10G_T: + case IXGBE_DEV_ID_X550EM_A_1G_T: + case IXGBE_DEV_ID_X550EM_A_1G_T_L: + supported = true; + break; + default: + break; + } + default: + break; + } + + if (!supported) + hw_dbg(hw, "Device %x does not support flow control autoneg\n", + hw->device_id); + + return supported; +} + +/** + * ixgbe_setup_fc_generic - Set up flow control + * @hw: pointer to hardware structure + * + * Called at init time to set up flow control. + **/ +s32 ixgbe_setup_fc_generic(struct ixgbe_hw *hw) +{ + s32 ret_val = 0; + u32 reg = 0, reg_bp = 0; + u16 reg_cu = 0; + bool locked = false; + + /* + * Validate the requested mode. Strict IEEE mode does not allow + * ixgbe_fc_rx_pause because it will cause us to fail at UNH. + */ + if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) { + hw_dbg(hw, "ixgbe_fc_rx_pause not valid in strict IEEE mode\n"); + return IXGBE_ERR_INVALID_LINK_SETTINGS; + } + + /* + * 10gig parts do not have a word in the EEPROM to determine the + * default flow control setting, so we explicitly set it to full. + */ + if (hw->fc.requested_mode == ixgbe_fc_default) + hw->fc.requested_mode = ixgbe_fc_full; + + /* + * Set up the 1G and 10G flow control advertisement registers so the + * HW will be able to do fc autoneg once the cable is plugged in. If + * we link at 10G, the 1G advertisement is harmless and vice versa. + */ + switch (hw->phy.media_type) { + case ixgbe_media_type_backplane: + /* some MAC's need RMW protection on AUTOC */ + ret_val = hw->mac.ops.prot_autoc_read(hw, &locked, ®_bp); + if (ret_val) + return ret_val; + + fallthrough; /* only backplane uses autoc */ + case ixgbe_media_type_fiber: + reg = IXGBE_READ_REG(hw, IXGBE_PCS1GANA); + + break; + case ixgbe_media_type_copper: + hw->phy.ops.read_reg(hw, MDIO_AN_ADVERTISE, + MDIO_MMD_AN, ®_cu); + break; + default: + break; + } + + /* + * The possible values of fc.requested_mode 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.requested_mode) { + case ixgbe_fc_none: + /* Flow control completely disabled by software override. */ + reg &= ~(IXGBE_PCS1GANA_SYM_PAUSE | IXGBE_PCS1GANA_ASM_PAUSE); + if (hw->phy.media_type == ixgbe_media_type_backplane) + reg_bp &= ~(IXGBE_AUTOC_SYM_PAUSE | + IXGBE_AUTOC_ASM_PAUSE); + else if (hw->phy.media_type == ixgbe_media_type_copper) + reg_cu &= ~(IXGBE_TAF_SYM_PAUSE | IXGBE_TAF_ASM_PAUSE); + break; + case ixgbe_fc_tx_pause: + /* + * Tx Flow control is enabled, and Rx Flow control is + * disabled by software override. + */ + reg |= IXGBE_PCS1GANA_ASM_PAUSE; + reg &= ~IXGBE_PCS1GANA_SYM_PAUSE; + if (hw->phy.media_type == ixgbe_media_type_backplane) { + reg_bp |= IXGBE_AUTOC_ASM_PAUSE; + reg_bp &= ~IXGBE_AUTOC_SYM_PAUSE; + } else if (hw->phy.media_type == ixgbe_media_type_copper) { + reg_cu |= IXGBE_TAF_ASM_PAUSE; + reg_cu &= ~IXGBE_TAF_SYM_PAUSE; + } + break; + case ixgbe_fc_rx_pause: + /* + * Rx Flow control is enabled and Tx Flow control is + * disabled by software override. Since there really + * isn't a way to advertise that we are capable of RX + * Pause ONLY, we will advertise that we support both + * symmetric and asymmetric Rx PAUSE, as such we fall + * through to the fc_full statement. Later, we will + * disable the adapter's ability to send PAUSE frames. + */ + case ixgbe_fc_full: + /* Flow control (both Rx and Tx) is enabled by SW override. */ + reg |= IXGBE_PCS1GANA_SYM_PAUSE | IXGBE_PCS1GANA_ASM_PAUSE; + if (hw->phy.media_type == ixgbe_media_type_backplane) + reg_bp |= IXGBE_AUTOC_SYM_PAUSE | + IXGBE_AUTOC_ASM_PAUSE; + else if (hw->phy.media_type == ixgbe_media_type_copper) + reg_cu |= IXGBE_TAF_SYM_PAUSE | IXGBE_TAF_ASM_PAUSE; + break; + default: + hw_dbg(hw, "Flow control param set incorrectly\n"); + return IXGBE_ERR_CONFIG; + } + + if (hw->mac.type != ixgbe_mac_X540) { + /* + * Enable auto-negotiation between the MAC & PHY; + * the MAC will advertise clause 37 flow control. + */ + IXGBE_WRITE_REG(hw, IXGBE_PCS1GANA, reg); + reg = IXGBE_READ_REG(hw, IXGBE_PCS1GLCTL); + + /* Disable AN timeout */ + if (hw->fc.strict_ieee) + reg &= ~IXGBE_PCS1GLCTL_AN_1G_TIMEOUT_EN; + + IXGBE_WRITE_REG(hw, IXGBE_PCS1GLCTL, reg); + hw_dbg(hw, "Set up FC; PCS1GLCTL = 0x%08X\n", reg); + } + + /* + * AUTOC restart handles negotiation of 1G and 10G on backplane + * and copper. There is no need to set the PCS1GCTL register. + * + */ + if (hw->phy.media_type == ixgbe_media_type_backplane) { + /* Need the SW/FW semaphore around AUTOC writes if 82599 and + * LESM is on, likewise reset_pipeline requries the lock as + * it also writes AUTOC. + */ + ret_val = hw->mac.ops.prot_autoc_write(hw, reg_bp, locked); + if (ret_val) + return ret_val; + + } else if ((hw->phy.media_type == ixgbe_media_type_copper) && + ixgbe_device_supports_autoneg_fc(hw)) { + hw->phy.ops.write_reg(hw, MDIO_AN_ADVERTISE, + MDIO_MMD_AN, reg_cu); + } + + hw_dbg(hw, "Set up FC; IXGBE_AUTOC = 0x%08X\n", reg); + return ret_val; +} + +/** + * ixgbe_start_hw_generic - Prepare hardware for Tx/Rx + * @hw: pointer to hardware structure + * + * Starts the hardware by filling the bus info structure and media type, clears + * all on chip counters, initializes receive address registers, multicast + * table, VLAN filter table, calls routine to set up link and flow control + * settings, and leaves transmit and receive units disabled and uninitialized + **/ +s32 ixgbe_start_hw_generic(struct ixgbe_hw *hw) +{ + s32 ret_val; + u32 ctrl_ext; + u16 device_caps; + + /* Set the media type */ + hw->phy.media_type = hw->mac.ops.get_media_type(hw); + + /* Identify the PHY */ + hw->phy.ops.identify(hw); + + /* Clear the VLAN filter table */ + hw->mac.ops.clear_vfta(hw); + + /* Clear statistics registers */ + hw->mac.ops.clear_hw_cntrs(hw); + + /* Set No Snoop Disable */ + ctrl_ext = IXGBE_READ_REG(hw, IXGBE_CTRL_EXT); + ctrl_ext |= IXGBE_CTRL_EXT_NS_DIS; + IXGBE_WRITE_REG(hw, IXGBE_CTRL_EXT, ctrl_ext); + IXGBE_WRITE_FLUSH(hw); + + /* Setup flow control if method for doing so */ + if (hw->mac.ops.setup_fc) { + ret_val = hw->mac.ops.setup_fc(hw); + if (ret_val) + return ret_val; + } + + /* Cashe bit indicating need for crosstalk fix */ + switch (hw->mac.type) { + case ixgbe_mac_82599EB: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + hw->mac.ops.get_device_caps(hw, &device_caps); + if (device_caps & IXGBE_DEVICE_CAPS_NO_CROSSTALK_WR) + hw->need_crosstalk_fix = false; + else + hw->need_crosstalk_fix = true; + break; + default: + hw->need_crosstalk_fix = false; + break; + } + + /* Clear adapter stopped flag */ + hw->adapter_stopped = false; + + return 0; +} + +/** + * ixgbe_start_hw_gen2 - Init sequence for common device family + * @hw: pointer to hw structure + * + * Performs the init sequence common to the second generation + * of 10 GbE devices. + * Devices in the second generation: + * 82599 + * X540 + **/ +s32 ixgbe_start_hw_gen2(struct ixgbe_hw *hw) +{ + u32 i; + + /* Clear the rate limiters */ + for (i = 0; i < hw->mac.max_tx_queues; i++) { + IXGBE_WRITE_REG(hw, IXGBE_RTTDQSEL, i); + IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRC, 0); + } + IXGBE_WRITE_FLUSH(hw); + + return 0; +} + +/** + * ixgbe_init_hw_generic - Generic hardware initialization + * @hw: pointer to hardware structure + * + * Initialize the hardware by resetting the hardware, filling the bus info + * structure and media type, clears all on chip counters, initializes receive + * address registers, multicast table, VLAN filter table, calls routine to set + * up link and flow control settings, and leaves transmit and receive units + * disabled and uninitialized + **/ +s32 ixgbe_init_hw_generic(struct ixgbe_hw *hw) +{ + s32 status; + + /* Reset the hardware */ + status = hw->mac.ops.reset_hw(hw); + + if (status == 0) { + /* Start the HW */ + status = hw->mac.ops.start_hw(hw); + } + + /* Initialize the LED link active for LED blink support */ + if (hw->mac.ops.init_led_link_act) + hw->mac.ops.init_led_link_act(hw); + + return status; +} + +/** + * ixgbe_clear_hw_cntrs_generic - Generic clear hardware counters + * @hw: pointer to hardware structure + * + * Clears all hardware statistics counters by reading them from the hardware + * Statistics counters are clear on read. + **/ +s32 ixgbe_clear_hw_cntrs_generic(struct ixgbe_hw *hw) +{ + u16 i = 0; + + IXGBE_READ_REG(hw, IXGBE_CRCERRS); + IXGBE_READ_REG(hw, IXGBE_ILLERRC); + IXGBE_READ_REG(hw, IXGBE_ERRBC); + IXGBE_READ_REG(hw, IXGBE_MSPDC); + for (i = 0; i < 8; i++) + IXGBE_READ_REG(hw, IXGBE_MPC(i)); + + IXGBE_READ_REG(hw, IXGBE_MLFC); + IXGBE_READ_REG(hw, IXGBE_MRFC); + IXGBE_READ_REG(hw, IXGBE_RLEC); + IXGBE_READ_REG(hw, IXGBE_LXONTXC); + IXGBE_READ_REG(hw, IXGBE_LXOFFTXC); + if (hw->mac.type >= ixgbe_mac_82599EB) { + IXGBE_READ_REG(hw, IXGBE_LXONRXCNT); + IXGBE_READ_REG(hw, IXGBE_LXOFFRXCNT); + } else { + IXGBE_READ_REG(hw, IXGBE_LXONRXC); + IXGBE_READ_REG(hw, IXGBE_LXOFFRXC); + } + + for (i = 0; i < 8; i++) { + IXGBE_READ_REG(hw, IXGBE_PXONTXC(i)); + IXGBE_READ_REG(hw, IXGBE_PXOFFTXC(i)); + if (hw->mac.type >= ixgbe_mac_82599EB) { + IXGBE_READ_REG(hw, IXGBE_PXONRXCNT(i)); + IXGBE_READ_REG(hw, IXGBE_PXOFFRXCNT(i)); + } else { + IXGBE_READ_REG(hw, IXGBE_PXONRXC(i)); + IXGBE_READ_REG(hw, IXGBE_PXOFFRXC(i)); + } + } + if (hw->mac.type >= ixgbe_mac_82599EB) + for (i = 0; i < 8; i++) + IXGBE_READ_REG(hw, IXGBE_PXON2OFFCNT(i)); + IXGBE_READ_REG(hw, IXGBE_PRC64); + IXGBE_READ_REG(hw, IXGBE_PRC127); + IXGBE_READ_REG(hw, IXGBE_PRC255); + IXGBE_READ_REG(hw, IXGBE_PRC511); + IXGBE_READ_REG(hw, IXGBE_PRC1023); + IXGBE_READ_REG(hw, IXGBE_PRC1522); + IXGBE_READ_REG(hw, IXGBE_GPRC); + IXGBE_READ_REG(hw, IXGBE_BPRC); + IXGBE_READ_REG(hw, IXGBE_MPRC); + IXGBE_READ_REG(hw, IXGBE_GPTC); + IXGBE_READ_REG(hw, IXGBE_GORCL); + IXGBE_READ_REG(hw, IXGBE_GORCH); + IXGBE_READ_REG(hw, IXGBE_GOTCL); + IXGBE_READ_REG(hw, IXGBE_GOTCH); + if (hw->mac.type == ixgbe_mac_82598EB) + for (i = 0; i < 8; i++) + IXGBE_READ_REG(hw, IXGBE_RNBC(i)); + IXGBE_READ_REG(hw, IXGBE_RUC); + IXGBE_READ_REG(hw, IXGBE_RFC); + IXGBE_READ_REG(hw, IXGBE_ROC); + IXGBE_READ_REG(hw, IXGBE_RJC); + IXGBE_READ_REG(hw, IXGBE_MNGPRC); + IXGBE_READ_REG(hw, IXGBE_MNGPDC); + IXGBE_READ_REG(hw, IXGBE_MNGPTC); + IXGBE_READ_REG(hw, IXGBE_TORL); + IXGBE_READ_REG(hw, IXGBE_TORH); + IXGBE_READ_REG(hw, IXGBE_TPR); + IXGBE_READ_REG(hw, IXGBE_TPT); + IXGBE_READ_REG(hw, IXGBE_PTC64); + IXGBE_READ_REG(hw, IXGBE_PTC127); + IXGBE_READ_REG(hw, IXGBE_PTC255); + IXGBE_READ_REG(hw, IXGBE_PTC511); + IXGBE_READ_REG(hw, IXGBE_PTC1023); + IXGBE_READ_REG(hw, IXGBE_PTC1522); + IXGBE_READ_REG(hw, IXGBE_MPTC); + IXGBE_READ_REG(hw, IXGBE_BPTC); + for (i = 0; i < 16; i++) { + IXGBE_READ_REG(hw, IXGBE_QPRC(i)); + IXGBE_READ_REG(hw, IXGBE_QPTC(i)); + if (hw->mac.type >= ixgbe_mac_82599EB) { + IXGBE_READ_REG(hw, IXGBE_QBRC_L(i)); + IXGBE_READ_REG(hw, IXGBE_QBRC_H(i)); + IXGBE_READ_REG(hw, IXGBE_QBTC_L(i)); + IXGBE_READ_REG(hw, IXGBE_QBTC_H(i)); + IXGBE_READ_REG(hw, IXGBE_QPRDC(i)); + } else { + IXGBE_READ_REG(hw, IXGBE_QBRC(i)); + IXGBE_READ_REG(hw, IXGBE_QBTC(i)); + } + } + + if (hw->mac.type == ixgbe_mac_X550 || hw->mac.type == ixgbe_mac_X540) { + if (hw->phy.id == 0) + hw->phy.ops.identify(hw); + hw->phy.ops.read_reg(hw, IXGBE_PCRC8ECL, MDIO_MMD_PCS, &i); + hw->phy.ops.read_reg(hw, IXGBE_PCRC8ECH, MDIO_MMD_PCS, &i); + hw->phy.ops.read_reg(hw, IXGBE_LDPCECL, MDIO_MMD_PCS, &i); + hw->phy.ops.read_reg(hw, IXGBE_LDPCECH, MDIO_MMD_PCS, &i); + } + + return 0; +} + +/** + * ixgbe_read_pba_string_generic - Reads part number string from EEPROM + * @hw: pointer to hardware structure + * @pba_num: stores the part number string from the EEPROM + * @pba_num_size: part number string buffer length + * + * Reads the part number string from the EEPROM. + **/ +s32 ixgbe_read_pba_string_generic(struct ixgbe_hw *hw, u8 *pba_num, + u32 pba_num_size) +{ + s32 ret_val; + u16 data; + u16 pba_ptr; + u16 offset; + u16 length; + + if (pba_num == NULL) { + hw_dbg(hw, "PBA string buffer was null\n"); + return IXGBE_ERR_INVALID_ARGUMENT; + } + + ret_val = hw->eeprom.ops.read(hw, IXGBE_PBANUM0_PTR, &data); + if (ret_val) { + hw_dbg(hw, "NVM Read Error\n"); + return ret_val; + } + + ret_val = hw->eeprom.ops.read(hw, IXGBE_PBANUM1_PTR, &pba_ptr); + if (ret_val) { + hw_dbg(hw, "NVM Read Error\n"); + return ret_val; + } + + /* + * if data is not ptr guard the PBA must be in legacy format which + * means pba_ptr is actually our second data word for the PBA number + * and we can decode it into an ascii string + */ + if (data != IXGBE_PBANUM_PTR_GUARD) { + hw_dbg(hw, "NVM PBA number is not stored as string\n"); + + /* we will need 11 characters to store the PBA */ + if (pba_num_size < 11) { + hw_dbg(hw, "PBA string buffer too small\n"); + return IXGBE_ERR_NO_SPACE; + } + + /* extract hex string from data and pba_ptr */ + pba_num[0] = (data >> 12) & 0xF; + pba_num[1] = (data >> 8) & 0xF; + pba_num[2] = (data >> 4) & 0xF; + pba_num[3] = data & 0xF; + pba_num[4] = (pba_ptr >> 12) & 0xF; + pba_num[5] = (pba_ptr >> 8) & 0xF; + pba_num[6] = '-'; + pba_num[7] = 0; + pba_num[8] = (pba_ptr >> 4) & 0xF; + pba_num[9] = pba_ptr & 0xF; + + /* put a null character on the end of our string */ + pba_num[10] = '\0'; + + /* switch all the data but the '-' to hex char */ + for (offset = 0; offset < 10; offset++) { + if (pba_num[offset] < 0xA) + pba_num[offset] += '0'; + else if (pba_num[offset] < 0x10) + pba_num[offset] += 'A' - 0xA; + } + + return 0; + } + + ret_val = hw->eeprom.ops.read(hw, pba_ptr, &length); + if (ret_val) { + hw_dbg(hw, "NVM Read Error\n"); + return ret_val; + } + + if (length == 0xFFFF || length == 0) { + hw_dbg(hw, "NVM PBA number section invalid length\n"); + return IXGBE_ERR_PBA_SECTION; + } + + /* check if pba_num buffer is big enough */ + if (pba_num_size < (((u32)length * 2) - 1)) { + hw_dbg(hw, "PBA string buffer too small\n"); + return IXGBE_ERR_NO_SPACE; + } + + /* trim pba length from start of string */ + pba_ptr++; + length--; + + for (offset = 0; offset < length; offset++) { + ret_val = hw->eeprom.ops.read(hw, pba_ptr + offset, &data); + if (ret_val) { + hw_dbg(hw, "NVM Read Error\n"); + return ret_val; + } + pba_num[offset * 2] = (u8)(data >> 8); + pba_num[(offset * 2) + 1] = (u8)(data & 0xFF); + } + pba_num[offset * 2] = '\0'; + + return 0; +} + +/** + * ixgbe_get_mac_addr_generic - Generic get MAC address + * @hw: pointer to hardware structure + * @mac_addr: Adapter MAC address + * + * Reads the adapter's MAC address from first Receive Address Register (RAR0) + * A reset of the adapter must be performed prior to calling this function + * in order for the MAC address to have been loaded from the EEPROM into RAR0 + **/ +s32 ixgbe_get_mac_addr_generic(struct ixgbe_hw *hw, u8 *mac_addr) +{ + u32 rar_high; + u32 rar_low; + u16 i; + + rar_high = IXGBE_READ_REG(hw, IXGBE_RAH(0)); + rar_low = IXGBE_READ_REG(hw, IXGBE_RAL(0)); + + for (i = 0; i < 4; i++) + mac_addr[i] = (u8)(rar_low >> (i*8)); + + for (i = 0; i < 2; i++) + mac_addr[i+4] = (u8)(rar_high >> (i*8)); + + return 0; +} + +enum ixgbe_bus_width ixgbe_convert_bus_width(u16 link_status) +{ + switch (link_status & IXGBE_PCI_LINK_WIDTH) { + case IXGBE_PCI_LINK_WIDTH_1: + return ixgbe_bus_width_pcie_x1; + case IXGBE_PCI_LINK_WIDTH_2: + return ixgbe_bus_width_pcie_x2; + case IXGBE_PCI_LINK_WIDTH_4: + return ixgbe_bus_width_pcie_x4; + case IXGBE_PCI_LINK_WIDTH_8: + return ixgbe_bus_width_pcie_x8; + default: + return ixgbe_bus_width_unknown; + } +} + +enum ixgbe_bus_speed ixgbe_convert_bus_speed(u16 link_status) +{ + switch (link_status & IXGBE_PCI_LINK_SPEED) { + case IXGBE_PCI_LINK_SPEED_2500: + return ixgbe_bus_speed_2500; + case IXGBE_PCI_LINK_SPEED_5000: + return ixgbe_bus_speed_5000; + case IXGBE_PCI_LINK_SPEED_8000: + return ixgbe_bus_speed_8000; + default: + return ixgbe_bus_speed_unknown; + } +} + +/** + * ixgbe_get_bus_info_generic - Generic set PCI bus info + * @hw: pointer to hardware structure + * + * Sets the PCI bus info (speed, width, type) within the ixgbe_hw structure + **/ +s32 ixgbe_get_bus_info_generic(struct ixgbe_hw *hw) +{ + u16 link_status; + + hw->bus.type = ixgbe_bus_type_pci_express; + + /* Get the negotiated link width and speed from PCI config space */ + link_status = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_LINK_STATUS); + + hw->bus.width = ixgbe_convert_bus_width(link_status); + hw->bus.speed = ixgbe_convert_bus_speed(link_status); + + hw->mac.ops.set_lan_id(hw); + + return 0; +} + +/** + * ixgbe_set_lan_id_multi_port_pcie - Set LAN id for PCIe multiple port devices + * @hw: pointer to the HW structure + * + * Determines the LAN function id by reading memory-mapped registers + * and swaps the port value if requested. + **/ +void ixgbe_set_lan_id_multi_port_pcie(struct ixgbe_hw *hw) +{ + struct ixgbe_bus_info *bus = &hw->bus; + u16 ee_ctrl_4; + u32 reg; + + reg = IXGBE_READ_REG(hw, IXGBE_STATUS); + bus->func = (reg & IXGBE_STATUS_LAN_ID) >> IXGBE_STATUS_LAN_ID_SHIFT; + bus->lan_id = bus->func; + + /* check for a port swap */ + reg = IXGBE_READ_REG(hw, IXGBE_FACTPS(hw)); + if (reg & IXGBE_FACTPS_LFS) + bus->func ^= 0x1; + + /* Get MAC instance from EEPROM for configuring CS4227 */ + if (hw->device_id == IXGBE_DEV_ID_X550EM_A_SFP) { + hw->eeprom.ops.read(hw, IXGBE_EEPROM_CTRL_4, &ee_ctrl_4); + bus->instance_id = (ee_ctrl_4 & IXGBE_EE_CTRL_4_INST_ID) >> + IXGBE_EE_CTRL_4_INST_ID_SHIFT; + } +} + +/** + * ixgbe_stop_adapter_generic - Generic stop Tx/Rx units + * @hw: pointer to hardware structure + * + * Sets the adapter_stopped flag within ixgbe_hw struct. Clears interrupts, + * disables transmit and receive units. The adapter_stopped flag is used by + * the shared code and drivers to determine if the adapter is in a stopped + * state and should not touch the hardware. + **/ +s32 ixgbe_stop_adapter_generic(struct ixgbe_hw *hw) +{ + u32 reg_val; + u16 i; + + /* + * Set the adapter_stopped flag so other driver functions stop touching + * the hardware + */ + hw->adapter_stopped = true; + + /* Disable the receive unit */ + hw->mac.ops.disable_rx(hw); + + /* Clear interrupt mask to stop interrupts from being generated */ + IXGBE_WRITE_REG(hw, IXGBE_EIMC, IXGBE_IRQ_CLEAR_MASK); + + /* Clear any pending interrupts, flush previous writes */ + IXGBE_READ_REG(hw, IXGBE_EICR); + + /* Disable the transmit unit. Each queue must be disabled. */ + for (i = 0; i < hw->mac.max_tx_queues; i++) + IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(i), IXGBE_TXDCTL_SWFLSH); + + /* Disable the receive unit by stopping each queue */ + for (i = 0; i < hw->mac.max_rx_queues; i++) { + reg_val = IXGBE_READ_REG(hw, IXGBE_RXDCTL(i)); + reg_val &= ~IXGBE_RXDCTL_ENABLE; + reg_val |= IXGBE_RXDCTL_SWFLSH; + IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(i), reg_val); + } + + /* flush all queues disables */ + IXGBE_WRITE_FLUSH(hw); + usleep_range(1000, 2000); + + /* + * Prevent the PCI-E bus from from hanging by disabling PCI-E master + * access and verify no pending requests + */ + return ixgbe_disable_pcie_master(hw); +} + +/** + * ixgbe_init_led_link_act_generic - Store the LED index link/activity. + * @hw: pointer to hardware structure + * + * Store the index for the link active LED. This will be used to support + * blinking the LED. + **/ +s32 ixgbe_init_led_link_act_generic(struct ixgbe_hw *hw) +{ + struct ixgbe_mac_info *mac = &hw->mac; + u32 led_reg, led_mode; + u16 i; + + led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); + + /* Get LED link active from the LEDCTL register */ + for (i = 0; i < 4; i++) { + led_mode = led_reg >> IXGBE_LED_MODE_SHIFT(i); + + if ((led_mode & IXGBE_LED_MODE_MASK_BASE) == + IXGBE_LED_LINK_ACTIVE) { + mac->led_link_act = i; + return 0; + } + } + + /* If LEDCTL register does not have the LED link active set, then use + * known MAC defaults. + */ + switch (hw->mac.type) { + case ixgbe_mac_x550em_a: + mac->led_link_act = 0; + break; + case ixgbe_mac_X550EM_x: + mac->led_link_act = 1; + break; + default: + mac->led_link_act = 2; + } + + return 0; +} + +/** + * ixgbe_led_on_generic - Turns on the software controllable LEDs. + * @hw: pointer to hardware structure + * @index: led number to turn on + **/ +s32 ixgbe_led_on_generic(struct ixgbe_hw *hw, u32 index) +{ + u32 led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); + + if (index > 3) + return IXGBE_ERR_PARAM; + + /* To turn on the LED, set mode to ON. */ + led_reg &= ~IXGBE_LED_MODE_MASK(index); + led_reg |= IXGBE_LED_ON << IXGBE_LED_MODE_SHIFT(index); + IXGBE_WRITE_REG(hw, IXGBE_LEDCTL, led_reg); + IXGBE_WRITE_FLUSH(hw); + + return 0; +} + +/** + * ixgbe_led_off_generic - Turns off the software controllable LEDs. + * @hw: pointer to hardware structure + * @index: led number to turn off + **/ +s32 ixgbe_led_off_generic(struct ixgbe_hw *hw, u32 index) +{ + u32 led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); + + if (index > 3) + return IXGBE_ERR_PARAM; + + /* To turn off the LED, set mode to OFF. */ + led_reg &= ~IXGBE_LED_MODE_MASK(index); + led_reg |= IXGBE_LED_OFF << IXGBE_LED_MODE_SHIFT(index); + IXGBE_WRITE_REG(hw, IXGBE_LEDCTL, led_reg); + IXGBE_WRITE_FLUSH(hw); + + return 0; +} + +/** + * ixgbe_init_eeprom_params_generic - Initialize EEPROM params + * @hw: pointer to hardware structure + * + * Initializes the EEPROM parameters ixgbe_eeprom_info within the + * ixgbe_hw struct in order to set up EEPROM access. + **/ +s32 ixgbe_init_eeprom_params_generic(struct ixgbe_hw *hw) +{ + struct ixgbe_eeprom_info *eeprom = &hw->eeprom; + u32 eec; + u16 eeprom_size; + + if (eeprom->type == ixgbe_eeprom_uninitialized) { + eeprom->type = ixgbe_eeprom_none; + /* Set default semaphore delay to 10ms which is a well + * tested value */ + eeprom->semaphore_delay = 10; + /* Clear EEPROM page size, it will be initialized as needed */ + eeprom->word_page_size = 0; + + /* + * Check for EEPROM present first. + * If not present leave as none + */ + eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw)); + if (eec & IXGBE_EEC_PRES) { + eeprom->type = ixgbe_eeprom_spi; + + /* + * SPI EEPROM is assumed here. This code would need to + * change if a future EEPROM is not SPI. + */ + eeprom_size = (u16)((eec & IXGBE_EEC_SIZE) >> + IXGBE_EEC_SIZE_SHIFT); + eeprom->word_size = BIT(eeprom_size + + IXGBE_EEPROM_WORD_SIZE_SHIFT); + } + + if (eec & IXGBE_EEC_ADDR_SIZE) + eeprom->address_bits = 16; + else + eeprom->address_bits = 8; + hw_dbg(hw, "Eeprom params: type = %d, size = %d, address bits: %d\n", + eeprom->type, eeprom->word_size, eeprom->address_bits); + } + + return 0; +} + +/** + * ixgbe_write_eeprom_buffer_bit_bang_generic - Write EEPROM using bit-bang + * @hw: pointer to hardware structure + * @offset: offset within the EEPROM to write + * @words: number of words + * @data: 16 bit word(s) to write to EEPROM + * + * Reads 16 bit word(s) from EEPROM through bit-bang method + **/ +s32 ixgbe_write_eeprom_buffer_bit_bang_generic(struct ixgbe_hw *hw, u16 offset, + u16 words, u16 *data) +{ + s32 status; + u16 i, count; + + hw->eeprom.ops.init_params(hw); + + if (words == 0) + return IXGBE_ERR_INVALID_ARGUMENT; + + if (offset + words > hw->eeprom.word_size) + return IXGBE_ERR_EEPROM; + + /* + * The EEPROM page size cannot be queried from the chip. We do lazy + * initialization. It is worth to do that when we write large buffer. + */ + if ((hw->eeprom.word_page_size == 0) && + (words > IXGBE_EEPROM_PAGE_SIZE_MAX)) + ixgbe_detect_eeprom_page_size_generic(hw, offset); + + /* + * We cannot hold synchronization semaphores for too long + * to avoid other entity starvation. However it is more efficient + * to read in bursts than synchronizing access for each word. + */ + for (i = 0; i < words; i += IXGBE_EEPROM_RD_BUFFER_MAX_COUNT) { + count = (words - i) / IXGBE_EEPROM_RD_BUFFER_MAX_COUNT > 0 ? + IXGBE_EEPROM_RD_BUFFER_MAX_COUNT : (words - i); + status = ixgbe_write_eeprom_buffer_bit_bang(hw, offset + i, + count, &data[i]); + + if (status != 0) + break; + } + + return status; +} + +/** + * ixgbe_write_eeprom_buffer_bit_bang - Writes 16 bit word(s) to EEPROM + * @hw: pointer to hardware structure + * @offset: offset within the EEPROM to be written to + * @words: number of word(s) + * @data: 16 bit word(s) to be written to the EEPROM + * + * If ixgbe_eeprom_update_checksum is not called after this function, the + * EEPROM will most likely contain an invalid checksum. + **/ +static s32 ixgbe_write_eeprom_buffer_bit_bang(struct ixgbe_hw *hw, u16 offset, + u16 words, u16 *data) +{ + s32 status; + u16 word; + u16 page_size; + u16 i; + u8 write_opcode = IXGBE_EEPROM_WRITE_OPCODE_SPI; + + /* Prepare the EEPROM for writing */ + status = ixgbe_acquire_eeprom(hw); + if (status) + return status; + + if (ixgbe_ready_eeprom(hw) != 0) { + ixgbe_release_eeprom(hw); + return IXGBE_ERR_EEPROM; + } + + for (i = 0; i < words; i++) { + ixgbe_standby_eeprom(hw); + + /* Send the WRITE ENABLE command (8 bit opcode) */ + ixgbe_shift_out_eeprom_bits(hw, + IXGBE_EEPROM_WREN_OPCODE_SPI, + IXGBE_EEPROM_OPCODE_BITS); + + ixgbe_standby_eeprom(hw); + + /* Some SPI eeproms use the 8th address bit embedded + * in the opcode + */ + if ((hw->eeprom.address_bits == 8) && + ((offset + i) >= 128)) + write_opcode |= IXGBE_EEPROM_A8_OPCODE_SPI; + + /* Send the Write command (8-bit opcode + addr) */ + ixgbe_shift_out_eeprom_bits(hw, write_opcode, + IXGBE_EEPROM_OPCODE_BITS); + ixgbe_shift_out_eeprom_bits(hw, (u16)((offset + i) * 2), + hw->eeprom.address_bits); + + page_size = hw->eeprom.word_page_size; + + /* Send the data in burst via SPI */ + do { + word = data[i]; + word = (word >> 8) | (word << 8); + ixgbe_shift_out_eeprom_bits(hw, word, 16); + + if (page_size == 0) + break; + + /* do not wrap around page */ + if (((offset + i) & (page_size - 1)) == + (page_size - 1)) + break; + } while (++i < words); + + ixgbe_standby_eeprom(hw); + usleep_range(10000, 20000); + } + /* Done with writing - release the EEPROM */ + ixgbe_release_eeprom(hw); + + return 0; +} + +/** + * ixgbe_write_eeprom_generic - Writes 16 bit value to EEPROM + * @hw: pointer to hardware structure + * @offset: offset within the EEPROM to be written to + * @data: 16 bit word to be written to the EEPROM + * + * If ixgbe_eeprom_update_checksum is not called after this function, the + * EEPROM will most likely contain an invalid checksum. + **/ +s32 ixgbe_write_eeprom_generic(struct ixgbe_hw *hw, u16 offset, u16 data) +{ + hw->eeprom.ops.init_params(hw); + + if (offset >= hw->eeprom.word_size) + return IXGBE_ERR_EEPROM; + + return ixgbe_write_eeprom_buffer_bit_bang(hw, offset, 1, &data); +} + +/** + * ixgbe_read_eeprom_buffer_bit_bang_generic - Read EEPROM using bit-bang + * @hw: pointer to hardware structure + * @offset: offset within the EEPROM to be read + * @words: number of word(s) + * @data: read 16 bit words(s) from EEPROM + * + * Reads 16 bit word(s) from EEPROM through bit-bang method + **/ +s32 ixgbe_read_eeprom_buffer_bit_bang_generic(struct ixgbe_hw *hw, u16 offset, + u16 words, u16 *data) +{ + s32 status; + u16 i, count; + + hw->eeprom.ops.init_params(hw); + + if (words == 0) + return IXGBE_ERR_INVALID_ARGUMENT; + + if (offset + words > hw->eeprom.word_size) + return IXGBE_ERR_EEPROM; + + /* + * We cannot hold synchronization semaphores for too long + * to avoid other entity starvation. However it is more efficient + * to read in bursts than synchronizing access for each word. + */ + for (i = 0; i < words; i += IXGBE_EEPROM_RD_BUFFER_MAX_COUNT) { + count = (words - i) / IXGBE_EEPROM_RD_BUFFER_MAX_COUNT > 0 ? + IXGBE_EEPROM_RD_BUFFER_MAX_COUNT : (words - i); + + status = ixgbe_read_eeprom_buffer_bit_bang(hw, offset + i, + count, &data[i]); + + if (status) + return status; + } + + return 0; +} + +/** + * ixgbe_read_eeprom_buffer_bit_bang - Read EEPROM using bit-bang + * @hw: pointer to hardware structure + * @offset: offset within the EEPROM to be read + * @words: number of word(s) + * @data: read 16 bit word(s) from EEPROM + * + * Reads 16 bit word(s) from EEPROM through bit-bang method + **/ +static s32 ixgbe_read_eeprom_buffer_bit_bang(struct ixgbe_hw *hw, u16 offset, + u16 words, u16 *data) +{ + s32 status; + u16 word_in; + u8 read_opcode = IXGBE_EEPROM_READ_OPCODE_SPI; + u16 i; + + /* Prepare the EEPROM for reading */ + status = ixgbe_acquire_eeprom(hw); + if (status) + return status; + + if (ixgbe_ready_eeprom(hw) != 0) { + ixgbe_release_eeprom(hw); + return IXGBE_ERR_EEPROM; + } + + for (i = 0; i < words; i++) { + ixgbe_standby_eeprom(hw); + /* Some SPI eeproms use the 8th address bit embedded + * in the opcode + */ + if ((hw->eeprom.address_bits == 8) && + ((offset + i) >= 128)) + read_opcode |= IXGBE_EEPROM_A8_OPCODE_SPI; + + /* Send the READ command (opcode + addr) */ + ixgbe_shift_out_eeprom_bits(hw, read_opcode, + IXGBE_EEPROM_OPCODE_BITS); + ixgbe_shift_out_eeprom_bits(hw, (u16)((offset + i) * 2), + hw->eeprom.address_bits); + + /* Read the data. */ + word_in = ixgbe_shift_in_eeprom_bits(hw, 16); + data[i] = (word_in >> 8) | (word_in << 8); + } + + /* End this read operation */ + ixgbe_release_eeprom(hw); + + return 0; +} + +/** + * ixgbe_read_eeprom_bit_bang_generic - Read EEPROM word using bit-bang + * @hw: pointer to hardware structure + * @offset: offset within the EEPROM to be read + * @data: read 16 bit value from EEPROM + * + * Reads 16 bit value from EEPROM through bit-bang method + **/ +s32 ixgbe_read_eeprom_bit_bang_generic(struct ixgbe_hw *hw, u16 offset, + u16 *data) +{ + hw->eeprom.ops.init_params(hw); + + if (offset >= hw->eeprom.word_size) + return IXGBE_ERR_EEPROM; + + return ixgbe_read_eeprom_buffer_bit_bang(hw, offset, 1, data); +} + +/** + * ixgbe_read_eerd_buffer_generic - Read EEPROM word(s) using EERD + * @hw: pointer to hardware structure + * @offset: offset of word in the EEPROM to read + * @words: number of word(s) + * @data: 16 bit word(s) from the EEPROM + * + * Reads a 16 bit word(s) from the EEPROM using the EERD register. + **/ +s32 ixgbe_read_eerd_buffer_generic(struct ixgbe_hw *hw, u16 offset, + u16 words, u16 *data) +{ + u32 eerd; + s32 status; + u32 i; + + hw->eeprom.ops.init_params(hw); + + if (words == 0) + return IXGBE_ERR_INVALID_ARGUMENT; + + if (offset >= hw->eeprom.word_size) + return IXGBE_ERR_EEPROM; + + for (i = 0; i < words; i++) { + eerd = ((offset + i) << IXGBE_EEPROM_RW_ADDR_SHIFT) | + IXGBE_EEPROM_RW_REG_START; + + IXGBE_WRITE_REG(hw, IXGBE_EERD, eerd); + status = ixgbe_poll_eerd_eewr_done(hw, IXGBE_NVM_POLL_READ); + + if (status == 0) { + data[i] = (IXGBE_READ_REG(hw, IXGBE_EERD) >> + IXGBE_EEPROM_RW_REG_DATA); + } else { + hw_dbg(hw, "Eeprom read timed out\n"); + return status; + } + } + + return 0; +} + +/** + * ixgbe_detect_eeprom_page_size_generic - Detect EEPROM page size + * @hw: pointer to hardware structure + * @offset: offset within the EEPROM to be used as a scratch pad + * + * Discover EEPROM page size by writing marching data at given offset. + * This function is called only when we are writing a new large buffer + * at given offset so the data would be overwritten anyway. + **/ +static s32 ixgbe_detect_eeprom_page_size_generic(struct ixgbe_hw *hw, + u16 offset) +{ + u16 data[IXGBE_EEPROM_PAGE_SIZE_MAX]; + s32 status; + u16 i; + + for (i = 0; i < IXGBE_EEPROM_PAGE_SIZE_MAX; i++) + data[i] = i; + + hw->eeprom.word_page_size = IXGBE_EEPROM_PAGE_SIZE_MAX; + status = ixgbe_write_eeprom_buffer_bit_bang(hw, offset, + IXGBE_EEPROM_PAGE_SIZE_MAX, data); + hw->eeprom.word_page_size = 0; + if (status) + return status; + + status = ixgbe_read_eeprom_buffer_bit_bang(hw, offset, 1, data); + if (status) + return status; + + /* + * When writing in burst more than the actual page size + * EEPROM address wraps around current page. + */ + hw->eeprom.word_page_size = IXGBE_EEPROM_PAGE_SIZE_MAX - data[0]; + + hw_dbg(hw, "Detected EEPROM page size = %d words.\n", + hw->eeprom.word_page_size); + return 0; +} + +/** + * ixgbe_read_eerd_generic - Read EEPROM word using EERD + * @hw: pointer to hardware structure + * @offset: offset of word in the EEPROM to read + * @data: word read from the EEPROM + * + * Reads a 16 bit word from the EEPROM using the EERD register. + **/ +s32 ixgbe_read_eerd_generic(struct ixgbe_hw *hw, u16 offset, u16 *data) +{ + return ixgbe_read_eerd_buffer_generic(hw, offset, 1, data); +} + +/** + * ixgbe_write_eewr_buffer_generic - Write EEPROM word(s) using EEWR + * @hw: pointer to hardware structure + * @offset: offset of word in the EEPROM to write + * @words: number of words + * @data: word(s) write to the EEPROM + * + * Write a 16 bit word(s) to the EEPROM using the EEWR register. + **/ +s32 ixgbe_write_eewr_buffer_generic(struct ixgbe_hw *hw, u16 offset, + u16 words, u16 *data) +{ + u32 eewr; + s32 status; + u16 i; + + hw->eeprom.ops.init_params(hw); + + if (words == 0) + return IXGBE_ERR_INVALID_ARGUMENT; + + if (offset >= hw->eeprom.word_size) + return IXGBE_ERR_EEPROM; + + for (i = 0; i < words; i++) { + eewr = ((offset + i) << IXGBE_EEPROM_RW_ADDR_SHIFT) | + (data[i] << IXGBE_EEPROM_RW_REG_DATA) | + IXGBE_EEPROM_RW_REG_START; + + status = ixgbe_poll_eerd_eewr_done(hw, IXGBE_NVM_POLL_WRITE); + if (status) { + hw_dbg(hw, "Eeprom write EEWR timed out\n"); + return status; + } + + IXGBE_WRITE_REG(hw, IXGBE_EEWR, eewr); + + status = ixgbe_poll_eerd_eewr_done(hw, IXGBE_NVM_POLL_WRITE); + if (status) { + hw_dbg(hw, "Eeprom write EEWR timed out\n"); + return status; + } + } + + return 0; +} + +/** + * ixgbe_write_eewr_generic - Write EEPROM word using EEWR + * @hw: pointer to hardware structure + * @offset: offset of word in the EEPROM to write + * @data: word write to the EEPROM + * + * Write a 16 bit word to the EEPROM using the EEWR register. + **/ +s32 ixgbe_write_eewr_generic(struct ixgbe_hw *hw, u16 offset, u16 data) +{ + return ixgbe_write_eewr_buffer_generic(hw, offset, 1, &data); +} + +/** + * ixgbe_poll_eerd_eewr_done - Poll EERD read or EEWR write status + * @hw: pointer to hardware structure + * @ee_reg: EEPROM flag for polling + * + * Polls the status bit (bit 1) of the EERD or EEWR to determine when the + * read or write is done respectively. + **/ +static s32 ixgbe_poll_eerd_eewr_done(struct ixgbe_hw *hw, u32 ee_reg) +{ + u32 i; + u32 reg; + + for (i = 0; i < IXGBE_EERD_EEWR_ATTEMPTS; i++) { + if (ee_reg == IXGBE_NVM_POLL_READ) + reg = IXGBE_READ_REG(hw, IXGBE_EERD); + else + reg = IXGBE_READ_REG(hw, IXGBE_EEWR); + + if (reg & IXGBE_EEPROM_RW_REG_DONE) { + return 0; + } + udelay(5); + } + return IXGBE_ERR_EEPROM; +} + +/** + * ixgbe_acquire_eeprom - Acquire EEPROM using bit-bang + * @hw: pointer to hardware structure + * + * Prepares EEPROM for access using bit-bang method. This function should + * be called before issuing a command to the EEPROM. + **/ +static s32 ixgbe_acquire_eeprom(struct ixgbe_hw *hw) +{ + u32 eec; + u32 i; + + if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM) != 0) + return IXGBE_ERR_SWFW_SYNC; + + eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw)); + + /* Request EEPROM Access */ + eec |= IXGBE_EEC_REQ; + IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), eec); + + for (i = 0; i < IXGBE_EEPROM_GRANT_ATTEMPTS; i++) { + eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw)); + if (eec & IXGBE_EEC_GNT) + break; + udelay(5); + } + + /* Release if grant not acquired */ + if (!(eec & IXGBE_EEC_GNT)) { + eec &= ~IXGBE_EEC_REQ; + IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), eec); + hw_dbg(hw, "Could not acquire EEPROM grant\n"); + + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM); + return IXGBE_ERR_EEPROM; + } + + /* Setup EEPROM for Read/Write */ + /* Clear CS and SK */ + eec &= ~(IXGBE_EEC_CS | IXGBE_EEC_SK); + IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), eec); + IXGBE_WRITE_FLUSH(hw); + udelay(1); + return 0; +} + +/** + * ixgbe_get_eeprom_semaphore - Get hardware semaphore + * @hw: pointer to hardware structure + * + * Sets the hardware semaphores so EEPROM access can occur for bit-bang method + **/ +static s32 ixgbe_get_eeprom_semaphore(struct ixgbe_hw *hw) +{ + u32 timeout = 2000; + u32 i; + u32 swsm; + + /* Get SMBI software semaphore between device drivers first */ + for (i = 0; i < timeout; i++) { + /* + * If the SMBI bit is 0 when we read it, then the bit will be + * set and we have the semaphore + */ + swsm = IXGBE_READ_REG(hw, IXGBE_SWSM(hw)); + if (!(swsm & IXGBE_SWSM_SMBI)) + break; + usleep_range(50, 100); + } + + if (i == timeout) { + hw_dbg(hw, "Driver can't access the Eeprom - SMBI Semaphore not granted.\n"); + /* this release is particularly important because our attempts + * above to get the semaphore may have succeeded, and if there + * was a timeout, we should unconditionally clear the semaphore + * bits to free the driver to make progress + */ + ixgbe_release_eeprom_semaphore(hw); + + usleep_range(50, 100); + /* one last try + * If the SMBI bit is 0 when we read it, then the bit will be + * set and we have the semaphore + */ + swsm = IXGBE_READ_REG(hw, IXGBE_SWSM(hw)); + if (swsm & IXGBE_SWSM_SMBI) { + hw_dbg(hw, "Software semaphore SMBI between device drivers not granted.\n"); + return IXGBE_ERR_EEPROM; + } + } + + /* Now get the semaphore between SW/FW through the SWESMBI bit */ + for (i = 0; i < timeout; i++) { + swsm = IXGBE_READ_REG(hw, IXGBE_SWSM(hw)); + + /* Set the SW EEPROM semaphore bit to request access */ + swsm |= IXGBE_SWSM_SWESMBI; + IXGBE_WRITE_REG(hw, IXGBE_SWSM(hw), swsm); + + /* If we set the bit successfully then we got the + * semaphore. + */ + swsm = IXGBE_READ_REG(hw, IXGBE_SWSM(hw)); + if (swsm & IXGBE_SWSM_SWESMBI) + break; + + usleep_range(50, 100); + } + + /* Release semaphores and return error if SW EEPROM semaphore + * was not granted because we don't have access to the EEPROM + */ + if (i >= timeout) { + hw_dbg(hw, "SWESMBI Software EEPROM semaphore not granted.\n"); + ixgbe_release_eeprom_semaphore(hw); + return IXGBE_ERR_EEPROM; + } + + return 0; +} + +/** + * ixgbe_release_eeprom_semaphore - Release hardware semaphore + * @hw: pointer to hardware structure + * + * This function clears hardware semaphore bits. + **/ +static void ixgbe_release_eeprom_semaphore(struct ixgbe_hw *hw) +{ + u32 swsm; + + swsm = IXGBE_READ_REG(hw, IXGBE_SWSM(hw)); + + /* Release both semaphores by writing 0 to the bits SWESMBI and SMBI */ + swsm &= ~(IXGBE_SWSM_SWESMBI | IXGBE_SWSM_SMBI); + IXGBE_WRITE_REG(hw, IXGBE_SWSM(hw), swsm); + IXGBE_WRITE_FLUSH(hw); +} + +/** + * ixgbe_ready_eeprom - Polls for EEPROM ready + * @hw: pointer to hardware structure + **/ +static s32 ixgbe_ready_eeprom(struct ixgbe_hw *hw) +{ + u16 i; + u8 spi_stat_reg; + + /* + * Read "Status Register" repeatedly until the LSB is cleared. The + * EEPROM will signal that the command has been completed by clearing + * bit 0 of the internal status register. If it's not cleared within + * 5 milliseconds, then error out. + */ + for (i = 0; i < IXGBE_EEPROM_MAX_RETRY_SPI; i += 5) { + ixgbe_shift_out_eeprom_bits(hw, IXGBE_EEPROM_RDSR_OPCODE_SPI, + IXGBE_EEPROM_OPCODE_BITS); + spi_stat_reg = (u8)ixgbe_shift_in_eeprom_bits(hw, 8); + if (!(spi_stat_reg & IXGBE_EEPROM_STATUS_RDY_SPI)) + break; + + udelay(5); + ixgbe_standby_eeprom(hw); + } + + /* + * On some parts, SPI write time could vary from 0-20mSec on 3.3V + * devices (and only 0-5mSec on 5V devices) + */ + if (i >= IXGBE_EEPROM_MAX_RETRY_SPI) { + hw_dbg(hw, "SPI EEPROM Status error\n"); + return IXGBE_ERR_EEPROM; + } + + return 0; +} + +/** + * ixgbe_standby_eeprom - Returns EEPROM to a "standby" state + * @hw: pointer to hardware structure + **/ +static void ixgbe_standby_eeprom(struct ixgbe_hw *hw) +{ + u32 eec; + + eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw)); + + /* Toggle CS to flush commands */ + eec |= IXGBE_EEC_CS; + IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), eec); + IXGBE_WRITE_FLUSH(hw); + udelay(1); + eec &= ~IXGBE_EEC_CS; + IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), eec); + IXGBE_WRITE_FLUSH(hw); + udelay(1); +} + +/** + * ixgbe_shift_out_eeprom_bits - Shift data bits out to the EEPROM. + * @hw: pointer to hardware structure + * @data: data to send to the EEPROM + * @count: number of bits to shift out + **/ +static void ixgbe_shift_out_eeprom_bits(struct ixgbe_hw *hw, u16 data, + u16 count) +{ + u32 eec; + u32 mask; + u32 i; + + eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw)); + + /* + * Mask is used to shift "count" bits of "data" out to the EEPROM + * one bit at a time. Determine the starting bit based on count + */ + mask = BIT(count - 1); + + for (i = 0; i < count; i++) { + /* + * 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. + */ + if (data & mask) + eec |= IXGBE_EEC_DI; + else + eec &= ~IXGBE_EEC_DI; + + IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), eec); + IXGBE_WRITE_FLUSH(hw); + + udelay(1); + + ixgbe_raise_eeprom_clk(hw, &eec); + ixgbe_lower_eeprom_clk(hw, &eec); + + /* + * Shift mask to signify next bit of data to shift in to the + * EEPROM + */ + mask = mask >> 1; + } + + /* We leave the "DI" bit set to "0" when we leave this routine. */ + eec &= ~IXGBE_EEC_DI; + IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), eec); + IXGBE_WRITE_FLUSH(hw); +} + +/** + * ixgbe_shift_in_eeprom_bits - Shift data bits in from the EEPROM + * @hw: pointer to hardware structure + * @count: number of bits to shift + **/ +static u16 ixgbe_shift_in_eeprom_bits(struct ixgbe_hw *hw, u16 count) +{ + u32 eec; + u32 i; + u16 data = 0; + + /* + * In order to read a register from the EEPROM, we need to shift + * 'count' 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. + */ + eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw)); + + eec &= ~(IXGBE_EEC_DO | IXGBE_EEC_DI); + + for (i = 0; i < count; i++) { + data = data << 1; + ixgbe_raise_eeprom_clk(hw, &eec); + + eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw)); + + eec &= ~(IXGBE_EEC_DI); + if (eec & IXGBE_EEC_DO) + data |= 1; + + ixgbe_lower_eeprom_clk(hw, &eec); + } + + return data; +} + +/** + * ixgbe_raise_eeprom_clk - Raises the EEPROM's clock input. + * @hw: pointer to hardware structure + * @eec: EEC register's current value + **/ +static void ixgbe_raise_eeprom_clk(struct ixgbe_hw *hw, u32 *eec) +{ + /* + * Raise the clock input to the EEPROM + * (setting the SK bit), then delay + */ + *eec = *eec | IXGBE_EEC_SK; + IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), *eec); + IXGBE_WRITE_FLUSH(hw); + udelay(1); +} + +/** + * ixgbe_lower_eeprom_clk - Lowers the EEPROM's clock input. + * @hw: pointer to hardware structure + * @eec: EEC's current value + **/ +static void ixgbe_lower_eeprom_clk(struct ixgbe_hw *hw, u32 *eec) +{ + /* + * Lower the clock input to the EEPROM (clearing the SK bit), then + * delay + */ + *eec = *eec & ~IXGBE_EEC_SK; + IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), *eec); + IXGBE_WRITE_FLUSH(hw); + udelay(1); +} + +/** + * ixgbe_release_eeprom - Release EEPROM, release semaphores + * @hw: pointer to hardware structure + **/ +static void ixgbe_release_eeprom(struct ixgbe_hw *hw) +{ + u32 eec; + + eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw)); + + eec |= IXGBE_EEC_CS; /* Pull CS high */ + eec &= ~IXGBE_EEC_SK; /* Lower SCK */ + + IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), eec); + IXGBE_WRITE_FLUSH(hw); + + udelay(1); + + /* Stop requesting EEPROM access */ + eec &= ~IXGBE_EEC_REQ; + IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), eec); + + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM); + + /* + * Delay before attempt to obtain semaphore again to allow FW + * access. semaphore_delay is in ms we need us for usleep_range + */ + usleep_range(hw->eeprom.semaphore_delay * 1000, + hw->eeprom.semaphore_delay * 2000); +} + +/** + * ixgbe_calc_eeprom_checksum_generic - Calculates and returns the checksum + * @hw: pointer to hardware structure + **/ +s32 ixgbe_calc_eeprom_checksum_generic(struct ixgbe_hw *hw) +{ + u16 i; + u16 j; + u16 checksum = 0; + u16 length = 0; + u16 pointer = 0; + u16 word = 0; + + /* Include 0x0-0x3F in the checksum */ + for (i = 0; i < IXGBE_EEPROM_CHECKSUM; i++) { + if (hw->eeprom.ops.read(hw, i, &word)) { + hw_dbg(hw, "EEPROM read failed\n"); + break; + } + checksum += word; + } + + /* Include all data from pointers except for the fw pointer */ + for (i = IXGBE_PCIE_ANALOG_PTR; i < IXGBE_FW_PTR; i++) { + if (hw->eeprom.ops.read(hw, i, &pointer)) { + hw_dbg(hw, "EEPROM read failed\n"); + return IXGBE_ERR_EEPROM; + } + + /* If the pointer seems invalid */ + if (pointer == 0xFFFF || pointer == 0) + continue; + + if (hw->eeprom.ops.read(hw, pointer, &length)) { + hw_dbg(hw, "EEPROM read failed\n"); + return IXGBE_ERR_EEPROM; + } + + if (length == 0xFFFF || length == 0) + continue; + + for (j = pointer + 1; j <= pointer + length; j++) { + if (hw->eeprom.ops.read(hw, j, &word)) { + hw_dbg(hw, "EEPROM read failed\n"); + return IXGBE_ERR_EEPROM; + } + checksum += word; + } + } + + checksum = (u16)IXGBE_EEPROM_SUM - checksum; + + return (s32)checksum; +} + +/** + * ixgbe_validate_eeprom_checksum_generic - Validate EEPROM checksum + * @hw: pointer to hardware structure + * @checksum_val: calculated checksum + * + * Performs checksum calculation and validates the EEPROM checksum. If the + * caller does not need checksum_val, the value can be NULL. + **/ +s32 ixgbe_validate_eeprom_checksum_generic(struct ixgbe_hw *hw, + u16 *checksum_val) +{ + s32 status; + u16 checksum; + u16 read_checksum = 0; + + /* + * Read the first word from the EEPROM. If this times out or fails, do + * not continue or we could be in for a very long wait while every + * EEPROM read fails + */ + status = hw->eeprom.ops.read(hw, 0, &checksum); + if (status) { + hw_dbg(hw, "EEPROM read failed\n"); + return status; + } + + status = hw->eeprom.ops.calc_checksum(hw); + if (status < 0) + return status; + + checksum = (u16)(status & 0xffff); + + status = hw->eeprom.ops.read(hw, IXGBE_EEPROM_CHECKSUM, &read_checksum); + if (status) { + hw_dbg(hw, "EEPROM read failed\n"); + return status; + } + + /* Verify read checksum from EEPROM is the same as + * calculated checksum + */ + if (read_checksum != checksum) + status = IXGBE_ERR_EEPROM_CHECKSUM; + + /* If the user cares, return the calculated checksum */ + if (checksum_val) + *checksum_val = checksum; + + return status; +} + +/** + * ixgbe_update_eeprom_checksum_generic - Updates the EEPROM checksum + * @hw: pointer to hardware structure + **/ +s32 ixgbe_update_eeprom_checksum_generic(struct ixgbe_hw *hw) +{ + s32 status; + u16 checksum; + + /* + * Read the first word from the EEPROM. If this times out or fails, do + * not continue or we could be in for a very long wait while every + * EEPROM read fails + */ + status = hw->eeprom.ops.read(hw, 0, &checksum); + if (status) { + hw_dbg(hw, "EEPROM read failed\n"); + return status; + } + + status = hw->eeprom.ops.calc_checksum(hw); + if (status < 0) + return status; + + checksum = (u16)(status & 0xffff); + + status = hw->eeprom.ops.write(hw, IXGBE_EEPROM_CHECKSUM, checksum); + + return status; +} + +/** + * ixgbe_set_rar_generic - Set Rx address register + * @hw: pointer to hardware structure + * @index: Receive address register to write + * @addr: Address to put into receive address register + * @vmdq: VMDq "set" or "pool" index + * @enable_addr: set flag that address is active + * + * Puts an ethernet address into a receive address register. + **/ +s32 ixgbe_set_rar_generic(struct ixgbe_hw *hw, u32 index, u8 *addr, u32 vmdq, + u32 enable_addr) +{ + u32 rar_low, rar_high; + u32 rar_entries = hw->mac.num_rar_entries; + + /* Make sure we are using a valid rar index range */ + if (index >= rar_entries) { + hw_dbg(hw, "RAR index %d is out of range.\n", index); + return IXGBE_ERR_INVALID_ARGUMENT; + } + + /* setup VMDq pool selection before this RAR gets enabled */ + hw->mac.ops.set_vmdq(hw, index, vmdq); + + /* + * 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)); + /* + * Some parts put the VMDq setting in the extra RAH bits, + * so save everything except the lower 16 bits that hold part + * of the address and the address valid bit. + */ + rar_high = IXGBE_READ_REG(hw, IXGBE_RAH(index)); + rar_high &= ~(0x0000FFFF | IXGBE_RAH_AV); + rar_high |= ((u32)addr[4] | ((u32)addr[5] << 8)); + + if (enable_addr != 0) + rar_high |= IXGBE_RAH_AV; + + /* Record lower 32 bits of MAC address and then make + * sure that write is flushed to hardware before writing + * the upper 16 bits and setting the valid bit. + */ + IXGBE_WRITE_REG(hw, IXGBE_RAL(index), rar_low); + IXGBE_WRITE_FLUSH(hw); + IXGBE_WRITE_REG(hw, IXGBE_RAH(index), rar_high); + + return 0; +} + +/** + * ixgbe_clear_rar_generic - Remove Rx address register + * @hw: pointer to hardware structure + * @index: Receive address register to write + * + * Clears an ethernet address from a receive address register. + **/ +s32 ixgbe_clear_rar_generic(struct ixgbe_hw *hw, u32 index) +{ + u32 rar_high; + u32 rar_entries = hw->mac.num_rar_entries; + + /* Make sure we are using a valid rar index range */ + if (index >= rar_entries) { + hw_dbg(hw, "RAR index %d is out of range.\n", index); + return IXGBE_ERR_INVALID_ARGUMENT; + } + + /* + * Some parts put the VMDq setting in the extra RAH bits, + * so save everything except the lower 16 bits that hold part + * of the address and the address valid bit. + */ + rar_high = IXGBE_READ_REG(hw, IXGBE_RAH(index)); + rar_high &= ~(0x0000FFFF | IXGBE_RAH_AV); + + /* Clear the address valid bit and upper 16 bits of the address + * before clearing the lower bits. This way we aren't updating + * a live filter. + */ + IXGBE_WRITE_REG(hw, IXGBE_RAH(index), rar_high); + IXGBE_WRITE_FLUSH(hw); + IXGBE_WRITE_REG(hw, IXGBE_RAL(index), 0); + + /* clear VMDq pool/queue selection for this RAR */ + hw->mac.ops.clear_vmdq(hw, index, IXGBE_CLEAR_VMDQ_ALL); + + return 0; +} + +/** + * ixgbe_init_rx_addrs_generic - Initializes receive address filters. + * @hw: pointer to hardware structure + * + * 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. + **/ +s32 ixgbe_init_rx_addrs_generic(struct ixgbe_hw *hw) +{ + u32 i; + u32 rar_entries = hw->mac.num_rar_entries; + + /* + * 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 (!is_valid_ether_addr(hw->mac.addr)) { + /* Get the MAC address from the RAR0 for later reference */ + hw->mac.ops.get_mac_addr(hw, hw->mac.addr); + + hw_dbg(hw, " Keeping Current RAR0 Addr =%pM\n", hw->mac.addr); + } else { + /* Setup the receive address. */ + hw_dbg(hw, "Overriding MAC Address in RAR[0]\n"); + hw_dbg(hw, " New MAC Addr =%pM\n", hw->mac.addr); + + hw->mac.ops.set_rar(hw, 0, hw->mac.addr, 0, IXGBE_RAH_AV); + } + + /* clear VMDq pool/queue selection for RAR 0 */ + hw->mac.ops.clear_vmdq(hw, 0, IXGBE_CLEAR_VMDQ_ALL); + + hw->addr_ctrl.overflow_promisc = 0; + + hw->addr_ctrl.rar_used_count = 1; + + /* Zero out the other receive addresses. */ + hw_dbg(hw, "Clearing RAR[1-%d]\n", rar_entries - 1); + for (i = 1; i < rar_entries; i++) { + IXGBE_WRITE_REG(hw, IXGBE_RAL(i), 0); + IXGBE_WRITE_REG(hw, IXGBE_RAH(i), 0); + } + + /* Clear the MTA */ + hw->addr_ctrl.mta_in_use = 0; + IXGBE_WRITE_REG(hw, IXGBE_MCSTCTRL, hw->mac.mc_filter_type); + + hw_dbg(hw, " Clearing MTA\n"); + for (i = 0; i < hw->mac.mcft_size; i++) + IXGBE_WRITE_REG(hw, IXGBE_MTA(i), 0); + + if (hw->mac.ops.init_uta_tables) + hw->mac.ops.init_uta_tables(hw); + + return 0; +} + +/** + * ixgbe_mta_vector - Determines bit-vector in multicast table to set + * @hw: pointer to hardware structure + * @mc_addr: the multicast address + * + * Extracts the 12 bits, from a multicast address, to determine which + * bit-vector to set in the multicast table. The hardware uses 12 bits, from + * incoming rx multicast addresses, to determine the bit-vector to check in + * the MTA. Which of the 4 combination, of 12-bits, the hardware uses is set + * by the MO field of the MCSTCTRL. The MO field is set during initialization + * to mc_filter_type. + **/ +static s32 ixgbe_mta_vector(struct ixgbe_hw *hw, u8 *mc_addr) +{ + u32 vector = 0; + + switch (hw->mac.mc_filter_type) { + case 0: /* use bits [47:36] of the address */ + vector = ((mc_addr[4] >> 4) | (((u16)mc_addr[5]) << 4)); + break; + case 1: /* use bits [46:35] of the address */ + vector = ((mc_addr[4] >> 3) | (((u16)mc_addr[5]) << 5)); + break; + case 2: /* use bits [45:34] of the address */ + vector = ((mc_addr[4] >> 2) | (((u16)mc_addr[5]) << 6)); + break; + case 3: /* use bits [43:32] of the address */ + vector = ((mc_addr[4]) | (((u16)mc_addr[5]) << 8)); + break; + default: /* Invalid mc_filter_type */ + hw_dbg(hw, "MC filter type param set incorrectly\n"); + break; + } + + /* vector can only be 12-bits or boundary will be exceeded */ + vector &= 0xFFF; + return vector; +} + +/** + * ixgbe_set_mta - Set bit-vector in multicast table + * @hw: pointer to hardware structure + * @mc_addr: Multicast address + * + * Sets the bit-vector in the multicast table. + **/ +static void ixgbe_set_mta(struct ixgbe_hw *hw, u8 *mc_addr) +{ + u32 vector; + u32 vector_bit; + u32 vector_reg; + + hw->addr_ctrl.mta_in_use++; + + vector = ixgbe_mta_vector(hw, mc_addr); + hw_dbg(hw, " bit-vector = 0x%03X\n", vector); + + /* + * 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[vector_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 vector value and + * the bit within that register are determined by the lower 5 bits of + * the value. + */ + vector_reg = (vector >> 5) & 0x7F; + vector_bit = vector & 0x1F; + hw->mac.mta_shadow[vector_reg] |= BIT(vector_bit); +} + +/** + * ixgbe_update_mc_addr_list_generic - Updates MAC list of multicast addresses + * @hw: pointer to hardware structure + * @netdev: pointer to net device structure + * + * The given list replaces any existing list. Clears the MC addrs from receive + * address registers and the multicast table. Uses unused receive address + * registers for the first multicast addresses, and hashes the rest into the + * multicast table. + **/ +s32 ixgbe_update_mc_addr_list_generic(struct ixgbe_hw *hw, + struct net_device *netdev) +{ + struct netdev_hw_addr *ha; + u32 i; + + /* + * Set the new number of MC addresses that we are being requested to + * use. + */ + hw->addr_ctrl.num_mc_addrs = netdev_mc_count(netdev); + hw->addr_ctrl.mta_in_use = 0; + + /* Clear mta_shadow */ + hw_dbg(hw, " Clearing MTA\n"); + memset(&hw->mac.mta_shadow, 0, sizeof(hw->mac.mta_shadow)); + + /* Update mta shadow */ + netdev_for_each_mc_addr(ha, netdev) { + hw_dbg(hw, " Adding the multicast addresses:\n"); + ixgbe_set_mta(hw, ha->addr); + } + + /* Enable mta */ + for (i = 0; i < hw->mac.mcft_size; i++) + IXGBE_WRITE_REG_ARRAY(hw, IXGBE_MTA(0), i, + hw->mac.mta_shadow[i]); + + if (hw->addr_ctrl.mta_in_use > 0) + IXGBE_WRITE_REG(hw, IXGBE_MCSTCTRL, + IXGBE_MCSTCTRL_MFE | hw->mac.mc_filter_type); + + hw_dbg(hw, "ixgbe_update_mc_addr_list_generic Complete\n"); + return 0; +} + +/** + * ixgbe_enable_mc_generic - Enable multicast address in RAR + * @hw: pointer to hardware structure + * + * Enables multicast address in RAR and the use of the multicast hash table. + **/ +s32 ixgbe_enable_mc_generic(struct ixgbe_hw *hw) +{ + struct ixgbe_addr_filter_info *a = &hw->addr_ctrl; + + if (a->mta_in_use > 0) + IXGBE_WRITE_REG(hw, IXGBE_MCSTCTRL, IXGBE_MCSTCTRL_MFE | + hw->mac.mc_filter_type); + + return 0; +} + +/** + * ixgbe_disable_mc_generic - Disable multicast address in RAR + * @hw: pointer to hardware structure + * + * Disables multicast address in RAR and the use of the multicast hash table. + **/ +s32 ixgbe_disable_mc_generic(struct ixgbe_hw *hw) +{ + struct ixgbe_addr_filter_info *a = &hw->addr_ctrl; + + if (a->mta_in_use > 0) + IXGBE_WRITE_REG(hw, IXGBE_MCSTCTRL, hw->mac.mc_filter_type); + + return 0; +} + +/** + * ixgbe_fc_enable_generic - Enable flow control + * @hw: pointer to hardware structure + * + * Enable flow control according to the current settings. + **/ +s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw) +{ + u32 mflcn_reg, fccfg_reg; + u32 reg; + u32 fcrtl, fcrth; + int i; + + /* Validate the water mark configuration. */ + if (!hw->fc.pause_time) + return IXGBE_ERR_INVALID_LINK_SETTINGS; + + /* Low water mark of zero causes XOFF floods */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + if ((hw->fc.current_mode & ixgbe_fc_tx_pause) && + hw->fc.high_water[i]) { + if (!hw->fc.low_water[i] || + hw->fc.low_water[i] >= hw->fc.high_water[i]) { + hw_dbg(hw, "Invalid water mark configuration\n"); + return IXGBE_ERR_INVALID_LINK_SETTINGS; + } + } + } + + /* Negotiate the fc mode to use */ + hw->mac.ops.fc_autoneg(hw); + + /* Disable any previous flow control settings */ + mflcn_reg = IXGBE_READ_REG(hw, IXGBE_MFLCN); + mflcn_reg &= ~(IXGBE_MFLCN_RPFCE_MASK | IXGBE_MFLCN_RFCE); + + fccfg_reg = IXGBE_READ_REG(hw, IXGBE_FCCFG); + fccfg_reg &= ~(IXGBE_FCCFG_TFCE_802_3X | IXGBE_FCCFG_TFCE_PRIORITY); + + /* + * The possible values of fc.current_mode 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.current_mode) { + case ixgbe_fc_none: + /* + * Flow control is disabled by software override or autoneg. + * The code below will actually disable it in the HW. + */ + break; + case ixgbe_fc_rx_pause: + /* + * Rx Flow control is enabled and Tx Flow control is + * disabled by software override. Since there really + * isn't a way to advertise that we are capable of RX + * Pause ONLY, we will advertise that we support both + * symmetric and asymmetric Rx PAUSE. Later, we will + * disable the adapter's ability to send PAUSE frames. + */ + mflcn_reg |= IXGBE_MFLCN_RFCE; + break; + case ixgbe_fc_tx_pause: + /* + * Tx Flow control is enabled, and Rx Flow control is + * disabled by software override. + */ + fccfg_reg |= IXGBE_FCCFG_TFCE_802_3X; + break; + case ixgbe_fc_full: + /* Flow control (both Rx and Tx) is enabled by SW override. */ + mflcn_reg |= IXGBE_MFLCN_RFCE; + fccfg_reg |= IXGBE_FCCFG_TFCE_802_3X; + break; + default: + hw_dbg(hw, "Flow control param set incorrectly\n"); + return IXGBE_ERR_CONFIG; + } + + /* Set 802.3x based flow control settings. */ + mflcn_reg |= IXGBE_MFLCN_DPF; + IXGBE_WRITE_REG(hw, IXGBE_MFLCN, mflcn_reg); + IXGBE_WRITE_REG(hw, IXGBE_FCCFG, fccfg_reg); + + /* Set up and enable Rx high/low water mark thresholds, enable XON. */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + if ((hw->fc.current_mode & ixgbe_fc_tx_pause) && + hw->fc.high_water[i]) { + fcrtl = (hw->fc.low_water[i] << 10) | IXGBE_FCRTL_XONE; + IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(i), fcrtl); + fcrth = (hw->fc.high_water[i] << 10) | IXGBE_FCRTH_FCEN; + } else { + IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(i), 0); + /* + * In order to prevent Tx hangs when the internal Tx + * switch is enabled we must set the high water mark + * to the Rx packet buffer size - 24KB. This allows + * the Tx switch to function even under heavy Rx + * workloads. + */ + fcrth = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(i)) - 24576; + } + + IXGBE_WRITE_REG(hw, IXGBE_FCRTH_82599(i), fcrth); + } + + /* Configure pause time (2 TCs per register) */ + reg = hw->fc.pause_time * 0x00010001U; + for (i = 0; i < (MAX_TRAFFIC_CLASS / 2); i++) + IXGBE_WRITE_REG(hw, IXGBE_FCTTV(i), reg); + + IXGBE_WRITE_REG(hw, IXGBE_FCRTV, hw->fc.pause_time / 2); + + return 0; +} + +/** + * ixgbe_negotiate_fc - Negotiate flow control + * @hw: pointer to hardware structure + * @adv_reg: flow control advertised settings + * @lp_reg: link partner's flow control settings + * @adv_sym: symmetric pause bit in advertisement + * @adv_asm: asymmetric pause bit in advertisement + * @lp_sym: symmetric pause bit in link partner advertisement + * @lp_asm: asymmetric pause bit in link partner advertisement + * + * Find the intersection between advertised settings and link partner's + * advertised settings + **/ +s32 ixgbe_negotiate_fc(struct ixgbe_hw *hw, u32 adv_reg, u32 lp_reg, + u32 adv_sym, u32 adv_asm, u32 lp_sym, u32 lp_asm) +{ + if ((!(adv_reg)) || (!(lp_reg))) + return IXGBE_ERR_FC_NOT_NEGOTIATED; + + if ((adv_reg & adv_sym) && (lp_reg & lp_sym)) { + /* + * Now we need to check if the user selected Rx ONLY + * of pause frames. In this case, we had to advertise + * FULL flow control because we could not advertise RX + * ONLY. Hence, we must now check to see if we need to + * turn OFF the TRANSMISSION of PAUSE frames. + */ + if (hw->fc.requested_mode == ixgbe_fc_full) { + hw->fc.current_mode = ixgbe_fc_full; + hw_dbg(hw, "Flow Control = FULL.\n"); + } else { + hw->fc.current_mode = ixgbe_fc_rx_pause; + hw_dbg(hw, "Flow Control=RX PAUSE frames only\n"); + } + } else if (!(adv_reg & adv_sym) && (adv_reg & adv_asm) && + (lp_reg & lp_sym) && (lp_reg & lp_asm)) { + hw->fc.current_mode = ixgbe_fc_tx_pause; + hw_dbg(hw, "Flow Control = TX PAUSE frames only.\n"); + } else if ((adv_reg & adv_sym) && (adv_reg & adv_asm) && + !(lp_reg & lp_sym) && (lp_reg & lp_asm)) { + hw->fc.current_mode = ixgbe_fc_rx_pause; + hw_dbg(hw, "Flow Control = RX PAUSE frames only.\n"); + } else { + hw->fc.current_mode = ixgbe_fc_none; + hw_dbg(hw, "Flow Control = NONE.\n"); + } + return 0; +} + +/** + * ixgbe_fc_autoneg_fiber - Enable flow control on 1 gig fiber + * @hw: pointer to hardware structure + * + * Enable flow control according on 1 gig fiber. + **/ +static s32 ixgbe_fc_autoneg_fiber(struct ixgbe_hw *hw) +{ + u32 pcs_anadv_reg, pcs_lpab_reg, linkstat; + s32 ret_val; + + /* + * On multispeed fiber at 1g, bail out if + * - link is up but AN did not complete, or if + * - link is up and AN completed but timed out + */ + + linkstat = IXGBE_READ_REG(hw, IXGBE_PCS1GLSTA); + if ((!!(linkstat & IXGBE_PCS1GLSTA_AN_COMPLETE) == 0) || + (!!(linkstat & IXGBE_PCS1GLSTA_AN_TIMED_OUT) == 1)) + return IXGBE_ERR_FC_NOT_NEGOTIATED; + + pcs_anadv_reg = IXGBE_READ_REG(hw, IXGBE_PCS1GANA); + pcs_lpab_reg = IXGBE_READ_REG(hw, IXGBE_PCS1GANLP); + + ret_val = ixgbe_negotiate_fc(hw, pcs_anadv_reg, + pcs_lpab_reg, IXGBE_PCS1GANA_SYM_PAUSE, + IXGBE_PCS1GANA_ASM_PAUSE, + IXGBE_PCS1GANA_SYM_PAUSE, + IXGBE_PCS1GANA_ASM_PAUSE); + + return ret_val; +} + +/** + * ixgbe_fc_autoneg_backplane - Enable flow control IEEE clause 37 + * @hw: pointer to hardware structure + * + * Enable flow control according to IEEE clause 37. + **/ +static s32 ixgbe_fc_autoneg_backplane(struct ixgbe_hw *hw) +{ + u32 links2, anlp1_reg, autoc_reg, links; + s32 ret_val; + + /* + * On backplane, bail out if + * - backplane autoneg was not completed, or if + * - we are 82599 and link partner is not AN enabled + */ + links = IXGBE_READ_REG(hw, IXGBE_LINKS); + if ((links & IXGBE_LINKS_KX_AN_COMP) == 0) + return IXGBE_ERR_FC_NOT_NEGOTIATED; + + if (hw->mac.type == ixgbe_mac_82599EB) { + links2 = IXGBE_READ_REG(hw, IXGBE_LINKS2); + if ((links2 & IXGBE_LINKS2_AN_SUPPORTED) == 0) + return IXGBE_ERR_FC_NOT_NEGOTIATED; + } + /* + * Read the 10g AN autoc and LP ability registers and resolve + * local flow control settings accordingly + */ + autoc_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC); + anlp1_reg = IXGBE_READ_REG(hw, IXGBE_ANLP1); + + ret_val = ixgbe_negotiate_fc(hw, autoc_reg, + anlp1_reg, IXGBE_AUTOC_SYM_PAUSE, IXGBE_AUTOC_ASM_PAUSE, + IXGBE_ANLP1_SYM_PAUSE, IXGBE_ANLP1_ASM_PAUSE); + + return ret_val; +} + +/** + * ixgbe_fc_autoneg_copper - Enable flow control IEEE clause 37 + * @hw: pointer to hardware structure + * + * Enable flow control according to IEEE clause 37. + **/ +static s32 ixgbe_fc_autoneg_copper(struct ixgbe_hw *hw) +{ + u16 technology_ability_reg = 0; + u16 lp_technology_ability_reg = 0; + + hw->phy.ops.read_reg(hw, MDIO_AN_ADVERTISE, + MDIO_MMD_AN, + &technology_ability_reg); + hw->phy.ops.read_reg(hw, MDIO_AN_LPA, + MDIO_MMD_AN, + &lp_technology_ability_reg); + + return ixgbe_negotiate_fc(hw, (u32)technology_ability_reg, + (u32)lp_technology_ability_reg, + IXGBE_TAF_SYM_PAUSE, IXGBE_TAF_ASM_PAUSE, + IXGBE_TAF_SYM_PAUSE, IXGBE_TAF_ASM_PAUSE); +} + +/** + * ixgbe_fc_autoneg - Configure flow control + * @hw: pointer to hardware structure + * + * Compares our advertised flow control capabilities to those advertised by + * our link partner, and determines the proper flow control mode to use. + **/ +void ixgbe_fc_autoneg(struct ixgbe_hw *hw) +{ + s32 ret_val = IXGBE_ERR_FC_NOT_NEGOTIATED; + ixgbe_link_speed speed; + bool link_up; + + /* + * AN should have completed when the cable was plugged in. + * Look for reasons to bail out. Bail out if: + * - FC autoneg is disabled, or if + * - link is not up. + * + * Since we're being called from an LSC, link is already known to be up. + * So use link_up_wait_to_complete=false. + */ + if (hw->fc.disable_fc_autoneg) + goto out; + + hw->mac.ops.check_link(hw, &speed, &link_up, false); + if (!link_up) + goto out; + + switch (hw->phy.media_type) { + /* Autoneg flow control on fiber adapters */ + case ixgbe_media_type_fiber: + if (speed == IXGBE_LINK_SPEED_1GB_FULL) + ret_val = ixgbe_fc_autoneg_fiber(hw); + break; + + /* Autoneg flow control on backplane adapters */ + case ixgbe_media_type_backplane: + ret_val = ixgbe_fc_autoneg_backplane(hw); + break; + + /* Autoneg flow control on copper adapters */ + case ixgbe_media_type_copper: + if (ixgbe_device_supports_autoneg_fc(hw)) + ret_val = ixgbe_fc_autoneg_copper(hw); + break; + + default: + break; + } + +out: + if (ret_val == 0) { + hw->fc.fc_was_autonegged = true; + } else { + hw->fc.fc_was_autonegged = false; + hw->fc.current_mode = hw->fc.requested_mode; + } +} + +/** + * ixgbe_pcie_timeout_poll - Return number of times to poll for completion + * @hw: pointer to hardware structure + * + * System-wide timeout range is encoded in PCIe Device Control2 register. + * + * Add 10% to specified maximum and return the number of times to poll for + * completion timeout, in units of 100 microsec. Never return less than + * 800 = 80 millisec. + **/ +static u32 ixgbe_pcie_timeout_poll(struct ixgbe_hw *hw) +{ + s16 devctl2; + u32 pollcnt; + + devctl2 = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_DEVICE_CONTROL2); + devctl2 &= IXGBE_PCIDEVCTRL2_TIMEO_MASK; + + switch (devctl2) { + case IXGBE_PCIDEVCTRL2_65_130ms: + pollcnt = 1300; /* 130 millisec */ + break; + case IXGBE_PCIDEVCTRL2_260_520ms: + pollcnt = 5200; /* 520 millisec */ + break; + case IXGBE_PCIDEVCTRL2_1_2s: + pollcnt = 20000; /* 2 sec */ + break; + case IXGBE_PCIDEVCTRL2_4_8s: + pollcnt = 80000; /* 8 sec */ + break; + case IXGBE_PCIDEVCTRL2_17_34s: + pollcnt = 34000; /* 34 sec */ + break; + case IXGBE_PCIDEVCTRL2_50_100us: /* 100 microsecs */ + case IXGBE_PCIDEVCTRL2_1_2ms: /* 2 millisecs */ + case IXGBE_PCIDEVCTRL2_16_32ms: /* 32 millisec */ + case IXGBE_PCIDEVCTRL2_16_32ms_def: /* 32 millisec default */ + default: + pollcnt = 800; /* 80 millisec minimum */ + break; + } + + /* add 10% to spec maximum */ + return (pollcnt * 11) / 10; +} + +/** + * ixgbe_disable_pcie_master - Disable PCI-express master access + * @hw: pointer to hardware structure + * + * Disables PCI-Express master access and verifies there are no pending + * requests. IXGBE_ERR_MASTER_REQUESTS_PENDING is returned if master disable + * bit hasn't caused the master requests to be disabled, else 0 + * is returned signifying master requests disabled. + **/ +static s32 ixgbe_disable_pcie_master(struct ixgbe_hw *hw) +{ + u32 i, poll; + u16 value; + + /* Always set this bit to ensure any future transactions are blocked */ + IXGBE_WRITE_REG(hw, IXGBE_CTRL, IXGBE_CTRL_GIO_DIS); + + /* Poll for bit to read as set */ + for (i = 0; i < IXGBE_PCI_MASTER_DISABLE_TIMEOUT; i++) { + if (IXGBE_READ_REG(hw, IXGBE_CTRL) & IXGBE_CTRL_GIO_DIS) + break; + usleep_range(100, 120); + } + if (i >= IXGBE_PCI_MASTER_DISABLE_TIMEOUT) { + hw_dbg(hw, "GIO disable did not set - requesting resets\n"); + goto gio_disable_fail; + } + + /* Exit if master requests are blocked */ + if (!(IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_GIO) || + ixgbe_removed(hw->hw_addr)) + return 0; + + /* Poll for master request bit to clear */ + for (i = 0; i < IXGBE_PCI_MASTER_DISABLE_TIMEOUT; i++) { + udelay(100); + if (!(IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_GIO)) + return 0; + } + + /* + * Two consecutive resets are required via CTRL.RST per datasheet + * 5.2.5.3.2 Master Disable. We set a flag to inform the reset routine + * of this need. The first reset prevents new master requests from + * being issued by our device. We then must wait 1usec or more for any + * remaining completions from the PCIe bus to trickle in, and then reset + * again to clear out any effects they may have had on our device. + */ + hw_dbg(hw, "GIO Master Disable bit didn't clear - requesting resets\n"); +gio_disable_fail: + hw->mac.flags |= IXGBE_FLAGS_DOUBLE_RESET_REQUIRED; + + if (hw->mac.type >= ixgbe_mac_X550) + return 0; + + /* + * Before proceeding, make sure that the PCIe block does not have + * transactions pending. + */ + poll = ixgbe_pcie_timeout_poll(hw); + for (i = 0; i < poll; i++) { + udelay(100); + value = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_DEVICE_STATUS); + if (ixgbe_removed(hw->hw_addr)) + return 0; + if (!(value & IXGBE_PCI_DEVICE_STATUS_TRANSACTION_PENDING)) + return 0; + } + + hw_dbg(hw, "PCIe transaction pending bit also did not clear.\n"); + return IXGBE_ERR_MASTER_REQUESTS_PENDING; +} + +/** + * ixgbe_acquire_swfw_sync - Acquire SWFW semaphore + * @hw: pointer to hardware structure + * @mask: Mask to specify which semaphore to acquire + * + * Acquires the SWFW semaphore through the GSSR register for the specified + * function (CSR, PHY0, PHY1, EEPROM, Flash) + **/ +s32 ixgbe_acquire_swfw_sync(struct ixgbe_hw *hw, u32 mask) +{ + u32 gssr = 0; + u32 swmask = mask; + u32 fwmask = mask << 5; + u32 timeout = 200; + u32 i; + + for (i = 0; i < timeout; i++) { + /* + * SW NVM semaphore bit is used for access to all + * SW_FW_SYNC bits (not just NVM) + */ + if (ixgbe_get_eeprom_semaphore(hw)) + return IXGBE_ERR_SWFW_SYNC; + + gssr = IXGBE_READ_REG(hw, IXGBE_GSSR); + if (!(gssr & (fwmask | swmask))) { + gssr |= swmask; + IXGBE_WRITE_REG(hw, IXGBE_GSSR, gssr); + ixgbe_release_eeprom_semaphore(hw); + return 0; + } else { + /* Resource is currently in use by FW or SW */ + ixgbe_release_eeprom_semaphore(hw); + usleep_range(5000, 10000); + } + } + + /* If time expired clear the bits holding the lock and retry */ + if (gssr & (fwmask | swmask)) + ixgbe_release_swfw_sync(hw, gssr & (fwmask | swmask)); + + usleep_range(5000, 10000); + return IXGBE_ERR_SWFW_SYNC; +} + +/** + * ixgbe_release_swfw_sync - Release SWFW semaphore + * @hw: pointer to hardware structure + * @mask: Mask to specify which semaphore to release + * + * Releases the SWFW semaphore through the GSSR register for the specified + * function (CSR, PHY0, PHY1, EEPROM, Flash) + **/ +void ixgbe_release_swfw_sync(struct ixgbe_hw *hw, u32 mask) +{ + u32 gssr; + u32 swmask = mask; + + ixgbe_get_eeprom_semaphore(hw); + + gssr = IXGBE_READ_REG(hw, IXGBE_GSSR); + gssr &= ~swmask; + IXGBE_WRITE_REG(hw, IXGBE_GSSR, gssr); + + ixgbe_release_eeprom_semaphore(hw); +} + +/** + * prot_autoc_read_generic - Hides MAC differences needed for AUTOC read + * @hw: pointer to hardware structure + * @reg_val: Value we read from AUTOC + * @locked: bool to indicate whether the SW/FW lock should be taken. Never + * true in this the generic case. + * + * The default case requires no protection so just to the register read. + **/ +s32 prot_autoc_read_generic(struct ixgbe_hw *hw, bool *locked, u32 *reg_val) +{ + *locked = false; + *reg_val = IXGBE_READ_REG(hw, IXGBE_AUTOC); + return 0; +} + +/** + * prot_autoc_write_generic - Hides MAC differences needed for AUTOC write + * @hw: pointer to hardware structure + * @reg_val: value to write to AUTOC + * @locked: bool to indicate whether the SW/FW lock was already taken by + * previous read. + **/ +s32 prot_autoc_write_generic(struct ixgbe_hw *hw, u32 reg_val, bool locked) +{ + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, reg_val); + return 0; +} + +/** + * ixgbe_disable_rx_buff_generic - Stops the receive data path + * @hw: pointer to hardware structure + * + * Stops the receive data path and waits for the HW to internally + * empty the Rx security block. + **/ +s32 ixgbe_disable_rx_buff_generic(struct ixgbe_hw *hw) +{ +#define IXGBE_MAX_SECRX_POLL 40 + int i; + int secrxreg; + + secrxreg = IXGBE_READ_REG(hw, IXGBE_SECRXCTRL); + secrxreg |= IXGBE_SECRXCTRL_RX_DIS; + IXGBE_WRITE_REG(hw, IXGBE_SECRXCTRL, secrxreg); + for (i = 0; i < IXGBE_MAX_SECRX_POLL; i++) { + secrxreg = IXGBE_READ_REG(hw, IXGBE_SECRXSTAT); + if (secrxreg & IXGBE_SECRXSTAT_SECRX_RDY) + break; + else + /* Use interrupt-safe sleep just in case */ + udelay(1000); + } + + /* For informational purposes only */ + if (i >= IXGBE_MAX_SECRX_POLL) + hw_dbg(hw, "Rx unit being enabled before security path fully disabled. Continuing with init.\n"); + + return 0; + +} + +/** + * ixgbe_enable_rx_buff - Enables the receive data path + * @hw: pointer to hardware structure + * + * Enables the receive data path + **/ +s32 ixgbe_enable_rx_buff_generic(struct ixgbe_hw *hw) +{ + u32 secrxreg; + + secrxreg = IXGBE_READ_REG(hw, IXGBE_SECRXCTRL); + secrxreg &= ~IXGBE_SECRXCTRL_RX_DIS; + IXGBE_WRITE_REG(hw, IXGBE_SECRXCTRL, secrxreg); + IXGBE_WRITE_FLUSH(hw); + + return 0; +} + +/** + * ixgbe_enable_rx_dma_generic - Enable the Rx DMA unit + * @hw: pointer to hardware structure + * @regval: register value to write to RXCTRL + * + * Enables the Rx DMA unit + **/ +s32 ixgbe_enable_rx_dma_generic(struct ixgbe_hw *hw, u32 regval) +{ + if (regval & IXGBE_RXCTRL_RXEN) + hw->mac.ops.enable_rx(hw); + else + hw->mac.ops.disable_rx(hw); + + return 0; +} + +/** + * ixgbe_blink_led_start_generic - Blink LED based on index. + * @hw: pointer to hardware structure + * @index: led number to blink + **/ +s32 ixgbe_blink_led_start_generic(struct ixgbe_hw *hw, u32 index) +{ + ixgbe_link_speed speed = 0; + bool link_up = false; + u32 autoc_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC); + u32 led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); + bool locked = false; + s32 ret_val; + + if (index > 3) + return IXGBE_ERR_PARAM; + + /* + * Link must be up to auto-blink the LEDs; + * Force it if link is down. + */ + hw->mac.ops.check_link(hw, &speed, &link_up, false); + + if (!link_up) { + ret_val = hw->mac.ops.prot_autoc_read(hw, &locked, &autoc_reg); + if (ret_val) + return ret_val; + + autoc_reg |= IXGBE_AUTOC_AN_RESTART; + autoc_reg |= IXGBE_AUTOC_FLU; + + ret_val = hw->mac.ops.prot_autoc_write(hw, autoc_reg, locked); + if (ret_val) + return ret_val; + + IXGBE_WRITE_FLUSH(hw); + + usleep_range(10000, 20000); + } + + led_reg &= ~IXGBE_LED_MODE_MASK(index); + led_reg |= IXGBE_LED_BLINK(index); + IXGBE_WRITE_REG(hw, IXGBE_LEDCTL, led_reg); + IXGBE_WRITE_FLUSH(hw); + + return 0; +} + +/** + * ixgbe_blink_led_stop_generic - Stop blinking LED based on index. + * @hw: pointer to hardware structure + * @index: led number to stop blinking + **/ +s32 ixgbe_blink_led_stop_generic(struct ixgbe_hw *hw, u32 index) +{ + u32 autoc_reg = 0; + u32 led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); + bool locked = false; + s32 ret_val; + + if (index > 3) + return IXGBE_ERR_PARAM; + + ret_val = hw->mac.ops.prot_autoc_read(hw, &locked, &autoc_reg); + if (ret_val) + return ret_val; + + autoc_reg &= ~IXGBE_AUTOC_FLU; + autoc_reg |= IXGBE_AUTOC_AN_RESTART; + + ret_val = hw->mac.ops.prot_autoc_write(hw, autoc_reg, locked); + if (ret_val) + return ret_val; + + led_reg &= ~IXGBE_LED_MODE_MASK(index); + led_reg &= ~IXGBE_LED_BLINK(index); + led_reg |= IXGBE_LED_LINK_ACTIVE << IXGBE_LED_MODE_SHIFT(index); + IXGBE_WRITE_REG(hw, IXGBE_LEDCTL, led_reg); + IXGBE_WRITE_FLUSH(hw); + + return 0; +} + +/** + * ixgbe_get_san_mac_addr_offset - Get SAN MAC address offset from the EEPROM + * @hw: pointer to hardware structure + * @san_mac_offset: SAN MAC address offset + * + * This function will read the EEPROM location for the SAN MAC address + * pointer, and returns the value at that location. This is used in both + * get and set mac_addr routines. + **/ +static s32 ixgbe_get_san_mac_addr_offset(struct ixgbe_hw *hw, + u16 *san_mac_offset) +{ + s32 ret_val; + + /* + * First read the EEPROM pointer to see if the MAC addresses are + * available. + */ + ret_val = hw->eeprom.ops.read(hw, IXGBE_SAN_MAC_ADDR_PTR, + san_mac_offset); + if (ret_val) + hw_err(hw, "eeprom read at offset %d failed\n", + IXGBE_SAN_MAC_ADDR_PTR); + + return ret_val; +} + +/** + * ixgbe_get_san_mac_addr_generic - SAN MAC address retrieval from the EEPROM + * @hw: pointer to hardware structure + * @san_mac_addr: SAN MAC address + * + * Reads the SAN MAC address from the EEPROM, if it's available. This is + * per-port, so set_lan_id() must be called before reading the addresses. + * set_lan_id() is called by identify_sfp(), but this cannot be relied + * upon for non-SFP connections, so we must call it here. + **/ +s32 ixgbe_get_san_mac_addr_generic(struct ixgbe_hw *hw, u8 *san_mac_addr) +{ + u16 san_mac_data, san_mac_offset; + u8 i; + s32 ret_val; + + /* + * First read the EEPROM pointer to see if the MAC addresses are + * available. If they're not, no point in calling set_lan_id() here. + */ + ret_val = ixgbe_get_san_mac_addr_offset(hw, &san_mac_offset); + if (ret_val || san_mac_offset == 0 || san_mac_offset == 0xFFFF) + + goto san_mac_addr_clr; + + /* make sure we know which port we need to program */ + hw->mac.ops.set_lan_id(hw); + /* apply the port offset to the address offset */ + (hw->bus.func) ? (san_mac_offset += IXGBE_SAN_MAC_ADDR_PORT1_OFFSET) : + (san_mac_offset += IXGBE_SAN_MAC_ADDR_PORT0_OFFSET); + for (i = 0; i < 3; i++) { + ret_val = hw->eeprom.ops.read(hw, san_mac_offset, + &san_mac_data); + if (ret_val) { + hw_err(hw, "eeprom read at offset %d failed\n", + san_mac_offset); + goto san_mac_addr_clr; + } + san_mac_addr[i * 2] = (u8)(san_mac_data); + san_mac_addr[i * 2 + 1] = (u8)(san_mac_data >> 8); + san_mac_offset++; + } + return 0; + +san_mac_addr_clr: + /* No addresses available in this EEPROM. It's not necessarily an + * error though, so just wipe the local address and return. + */ + for (i = 0; i < 6; i++) + san_mac_addr[i] = 0xFF; + return ret_val; +} + +/** + * ixgbe_get_pcie_msix_count_generic - Gets MSI-X vector count + * @hw: pointer to hardware structure + * + * Read PCIe configuration space, and get the MSI-X vector count from + * the capabilities table. + **/ +u16 ixgbe_get_pcie_msix_count_generic(struct ixgbe_hw *hw) +{ + u16 msix_count; + u16 max_msix_count; + u16 pcie_offset; + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + pcie_offset = IXGBE_PCIE_MSIX_82598_CAPS; + max_msix_count = IXGBE_MAX_MSIX_VECTORS_82598; + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + pcie_offset = IXGBE_PCIE_MSIX_82599_CAPS; + max_msix_count = IXGBE_MAX_MSIX_VECTORS_82599; + break; + default: + return 1; + } + + msix_count = ixgbe_read_pci_cfg_word(hw, pcie_offset); + if (ixgbe_removed(hw->hw_addr)) + msix_count = 0; + msix_count &= IXGBE_PCIE_MSIX_TBL_SZ_MASK; + + /* MSI-X count is zero-based in HW */ + msix_count++; + + if (msix_count > max_msix_count) + msix_count = max_msix_count; + + return msix_count; +} + +/** + * ixgbe_clear_vmdq_generic - Disassociate a VMDq pool index from a rx address + * @hw: pointer to hardware struct + * @rar: receive address register index to disassociate + * @vmdq: VMDq pool index to remove from the rar + **/ +s32 ixgbe_clear_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq) +{ + u32 mpsar_lo, mpsar_hi; + u32 rar_entries = hw->mac.num_rar_entries; + + /* Make sure we are using a valid rar index range */ + if (rar >= rar_entries) { + hw_dbg(hw, "RAR index %d is out of range.\n", rar); + return IXGBE_ERR_INVALID_ARGUMENT; + } + + mpsar_lo = IXGBE_READ_REG(hw, IXGBE_MPSAR_LO(rar)); + mpsar_hi = IXGBE_READ_REG(hw, IXGBE_MPSAR_HI(rar)); + + if (ixgbe_removed(hw->hw_addr)) + return 0; + + if (!mpsar_lo && !mpsar_hi) + return 0; + + if (vmdq == IXGBE_CLEAR_VMDQ_ALL) { + if (mpsar_lo) { + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_LO(rar), 0); + mpsar_lo = 0; + } + if (mpsar_hi) { + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_HI(rar), 0); + mpsar_hi = 0; + } + } else if (vmdq < 32) { + mpsar_lo &= ~BIT(vmdq); + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_LO(rar), mpsar_lo); + } else { + mpsar_hi &= ~BIT(vmdq - 32); + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_HI(rar), mpsar_hi); + } + + /* was that the last pool using this rar? */ + if (mpsar_lo == 0 && mpsar_hi == 0 && + rar != 0 && rar != hw->mac.san_mac_rar_index) + hw->mac.ops.clear_rar(hw, rar); + + return 0; +} + +/** + * ixgbe_set_vmdq_generic - Associate a VMDq pool index with a rx address + * @hw: pointer to hardware struct + * @rar: receive address register index to associate with a VMDq index + * @vmdq: VMDq pool index + **/ +s32 ixgbe_set_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq) +{ + u32 mpsar; + u32 rar_entries = hw->mac.num_rar_entries; + + /* Make sure we are using a valid rar index range */ + if (rar >= rar_entries) { + hw_dbg(hw, "RAR index %d is out of range.\n", rar); + return IXGBE_ERR_INVALID_ARGUMENT; + } + + if (vmdq < 32) { + mpsar = IXGBE_READ_REG(hw, IXGBE_MPSAR_LO(rar)); + mpsar |= BIT(vmdq); + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_LO(rar), mpsar); + } else { + mpsar = IXGBE_READ_REG(hw, IXGBE_MPSAR_HI(rar)); + mpsar |= BIT(vmdq - 32); + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_HI(rar), mpsar); + } + return 0; +} + +/** + * This function should only be involved in the IOV mode. + * In IOV mode, Default pool is next pool after the number of + * VFs advertized and not 0. + * MPSAR table needs to be updated for SAN_MAC RAR [hw->mac.san_mac_rar_index] + * + * ixgbe_set_vmdq_san_mac - Associate default VMDq pool index with a rx address + * @hw: pointer to hardware struct + * @vmdq: VMDq pool index + **/ +s32 ixgbe_set_vmdq_san_mac_generic(struct ixgbe_hw *hw, u32 vmdq) +{ + u32 rar = hw->mac.san_mac_rar_index; + + if (vmdq < 32) { + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_LO(rar), BIT(vmdq)); + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_HI(rar), 0); + } else { + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_LO(rar), 0); + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_HI(rar), BIT(vmdq - 32)); + } + + return 0; +} + +/** + * ixgbe_init_uta_tables_generic - Initialize the Unicast Table Array + * @hw: pointer to hardware structure + **/ +s32 ixgbe_init_uta_tables_generic(struct ixgbe_hw *hw) +{ + int i; + + for (i = 0; i < 128; i++) + IXGBE_WRITE_REG(hw, IXGBE_UTA(i), 0); + + return 0; +} + +/** + * ixgbe_find_vlvf_slot - find the vlanid or the first empty slot + * @hw: pointer to hardware structure + * @vlan: VLAN id to write to VLAN filter + * @vlvf_bypass: true to find vlanid only, false returns first empty slot if + * vlanid not found + * + * return the VLVF index where this VLAN id should be placed + * + **/ +static s32 ixgbe_find_vlvf_slot(struct ixgbe_hw *hw, u32 vlan, bool vlvf_bypass) +{ + s32 regindex, first_empty_slot; + u32 bits; + + /* short cut the special case */ + if (vlan == 0) + return 0; + + /* if vlvf_bypass is set we don't want to use an empty slot, we + * will simply bypass the VLVF if there are no entries present in the + * VLVF that contain our VLAN + */ + first_empty_slot = vlvf_bypass ? IXGBE_ERR_NO_SPACE : 0; + + /* add VLAN enable bit for comparison */ + vlan |= IXGBE_VLVF_VIEN; + + /* Search for the vlan id in the VLVF entries. Save off the first empty + * slot found along the way. + * + * pre-decrement loop covering (IXGBE_VLVF_ENTRIES - 1) .. 1 + */ + for (regindex = IXGBE_VLVF_ENTRIES; --regindex;) { + bits = IXGBE_READ_REG(hw, IXGBE_VLVF(regindex)); + if (bits == vlan) + return regindex; + if (!first_empty_slot && !bits) + first_empty_slot = regindex; + } + + /* If we are here then we didn't find the VLAN. Return first empty + * slot we found during our search, else error. + */ + if (!first_empty_slot) + hw_dbg(hw, "No space in VLVF.\n"); + + return first_empty_slot ? : IXGBE_ERR_NO_SPACE; +} + +/** + * ixgbe_set_vfta_generic - Set VLAN filter table + * @hw: pointer to hardware structure + * @vlan: VLAN id to write to VLAN filter + * @vind: VMDq output index that maps queue to VLAN id in VFVFB + * @vlan_on: boolean flag to turn on/off VLAN in VFVF + * @vlvf_bypass: boolean flag indicating updating default pool is okay + * + * Turn on/off specified VLAN in the VLAN filter table. + **/ +s32 ixgbe_set_vfta_generic(struct ixgbe_hw *hw, u32 vlan, u32 vind, + bool vlan_on, bool vlvf_bypass) +{ + u32 regidx, vfta_delta, vfta, bits; + s32 vlvf_index; + + if ((vlan > 4095) || (vind > 63)) + return IXGBE_ERR_PARAM; + + /* + * this is a 2 part operation - first the VFTA, then the + * VLVF and VLVFB if VT Mode is set + * We don't write the VFTA until we know the VLVF part succeeded. + */ + + /* Part 1 + * The VFTA is a bitstring made up of 128 32-bit registers + * that enable the particular VLAN id, much like the MTA: + * bits[11-5]: which register + * bits[4-0]: which bit in the register + */ + regidx = vlan / 32; + vfta_delta = BIT(vlan % 32); + vfta = IXGBE_READ_REG(hw, IXGBE_VFTA(regidx)); + + /* vfta_delta represents the difference between the current value + * of vfta and the value we want in the register. Since the diff + * is an XOR mask we can just update vfta using an XOR. + */ + vfta_delta &= vlan_on ? ~vfta : vfta; + vfta ^= vfta_delta; + + /* Part 2 + * If VT Mode is set + * Either vlan_on + * make sure the vlan is in VLVF + * set the vind bit in the matching VLVFB + * Or !vlan_on + * clear the pool bit and possibly the vind + */ + if (!(IXGBE_READ_REG(hw, IXGBE_VT_CTL) & IXGBE_VT_CTL_VT_ENABLE)) + goto vfta_update; + + vlvf_index = ixgbe_find_vlvf_slot(hw, vlan, vlvf_bypass); + if (vlvf_index < 0) { + if (vlvf_bypass) + goto vfta_update; + return vlvf_index; + } + + bits = IXGBE_READ_REG(hw, IXGBE_VLVFB(vlvf_index * 2 + vind / 32)); + + /* set the pool bit */ + bits |= BIT(vind % 32); + if (vlan_on) + goto vlvf_update; + + /* clear the pool bit */ + bits ^= BIT(vind % 32); + + if (!bits && + !IXGBE_READ_REG(hw, IXGBE_VLVFB(vlvf_index * 2 + 1 - vind / 32))) { + /* Clear VFTA first, then disable VLVF. Otherwise + * we run the risk of stray packets leaking into + * the PF via the default pool + */ + if (vfta_delta) + IXGBE_WRITE_REG(hw, IXGBE_VFTA(regidx), vfta); + + /* disable VLVF and clear remaining bit from pool */ + IXGBE_WRITE_REG(hw, IXGBE_VLVF(vlvf_index), 0); + IXGBE_WRITE_REG(hw, IXGBE_VLVFB(vlvf_index * 2 + vind / 32), 0); + + return 0; + } + + /* If there are still bits set in the VLVFB registers + * for the VLAN ID indicated we need to see if the + * caller is requesting that we clear the VFTA entry bit. + * If the caller has requested that we clear the VFTA + * entry bit but there are still pools/VFs using this VLAN + * ID entry then ignore the request. We're not worried + * about the case where we're turning the VFTA VLAN ID + * entry bit on, only when requested to turn it off as + * there may be multiple pools and/or VFs using the + * VLAN ID entry. In that case we cannot clear the + * VFTA bit until all pools/VFs using that VLAN ID have also + * been cleared. This will be indicated by "bits" being + * zero. + */ + vfta_delta = 0; + +vlvf_update: + /* record pool change and enable VLAN ID if not already enabled */ + IXGBE_WRITE_REG(hw, IXGBE_VLVFB(vlvf_index * 2 + vind / 32), bits); + IXGBE_WRITE_REG(hw, IXGBE_VLVF(vlvf_index), IXGBE_VLVF_VIEN | vlan); + +vfta_update: + /* Update VFTA now that we are ready for traffic */ + if (vfta_delta) + IXGBE_WRITE_REG(hw, IXGBE_VFTA(regidx), vfta); + + return 0; +} + +/** + * ixgbe_clear_vfta_generic - Clear VLAN filter table + * @hw: pointer to hardware structure + * + * Clears the VLAN filer table, and the VMDq index associated with the filter + **/ +s32 ixgbe_clear_vfta_generic(struct ixgbe_hw *hw) +{ + u32 offset; + + for (offset = 0; offset < hw->mac.vft_size; offset++) + IXGBE_WRITE_REG(hw, IXGBE_VFTA(offset), 0); + + for (offset = 0; offset < IXGBE_VLVF_ENTRIES; offset++) { + IXGBE_WRITE_REG(hw, IXGBE_VLVF(offset), 0); + IXGBE_WRITE_REG(hw, IXGBE_VLVFB(offset * 2), 0); + IXGBE_WRITE_REG(hw, IXGBE_VLVFB(offset * 2 + 1), 0); + } + + return 0; +} + +/** + * ixgbe_need_crosstalk_fix - Determine if we need to do cross talk fix + * @hw: pointer to hardware structure + * + * Contains the logic to identify if we need to verify link for the + * crosstalk fix + **/ +static bool ixgbe_need_crosstalk_fix(struct ixgbe_hw *hw) +{ + /* Does FW say we need the fix */ + if (!hw->need_crosstalk_fix) + return false; + + /* Only consider SFP+ PHYs i.e. media type fiber */ + switch (hw->mac.ops.get_media_type(hw)) { + case ixgbe_media_type_fiber: + case ixgbe_media_type_fiber_qsfp: + break; + default: + return false; + } + + return true; +} + +/** + * ixgbe_check_mac_link_generic - Determine link and speed status + * @hw: pointer to hardware structure + * @speed: pointer to link speed + * @link_up: true when link is up + * @link_up_wait_to_complete: bool used to wait for link up or not + * + * Reads the links register to determine if link is up and the current speed + **/ +s32 ixgbe_check_mac_link_generic(struct ixgbe_hw *hw, ixgbe_link_speed *speed, + bool *link_up, bool link_up_wait_to_complete) +{ + u32 links_reg, links_orig; + u32 i; + + /* If Crosstalk fix enabled do the sanity check of making sure + * the SFP+ cage is full. + */ + if (ixgbe_need_crosstalk_fix(hw)) { + u32 sfp_cage_full; + + switch (hw->mac.type) { + case ixgbe_mac_82599EB: + sfp_cage_full = IXGBE_READ_REG(hw, IXGBE_ESDP) & + IXGBE_ESDP_SDP2; + break; + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + sfp_cage_full = IXGBE_READ_REG(hw, IXGBE_ESDP) & + IXGBE_ESDP_SDP0; + break; + default: + /* sanity check - No SFP+ devices here */ + sfp_cage_full = false; + break; + } + + if (!sfp_cage_full) { + *link_up = false; + *speed = IXGBE_LINK_SPEED_UNKNOWN; + return 0; + } + } + + /* clear the old state */ + links_orig = IXGBE_READ_REG(hw, IXGBE_LINKS); + + links_reg = IXGBE_READ_REG(hw, IXGBE_LINKS); + + if (links_orig != links_reg) { + hw_dbg(hw, "LINKS changed from %08X to %08X\n", + links_orig, links_reg); + } + + if (link_up_wait_to_complete) { + for (i = 0; i < IXGBE_LINK_UP_TIME; i++) { + if (links_reg & IXGBE_LINKS_UP) { + *link_up = true; + break; + } else { + *link_up = false; + } + msleep(100); + links_reg = IXGBE_READ_REG(hw, IXGBE_LINKS); + } + } else { + if (links_reg & IXGBE_LINKS_UP) + *link_up = true; + else + *link_up = false; + } + + switch (links_reg & IXGBE_LINKS_SPEED_82599) { + case IXGBE_LINKS_SPEED_10G_82599: + if ((hw->mac.type >= ixgbe_mac_X550) && + (links_reg & IXGBE_LINKS_SPEED_NON_STD)) + *speed = IXGBE_LINK_SPEED_2_5GB_FULL; + else + *speed = IXGBE_LINK_SPEED_10GB_FULL; + break; + case IXGBE_LINKS_SPEED_1G_82599: + *speed = IXGBE_LINK_SPEED_1GB_FULL; + break; + case IXGBE_LINKS_SPEED_100_82599: + if ((hw->mac.type >= ixgbe_mac_X550) && + (links_reg & IXGBE_LINKS_SPEED_NON_STD)) + *speed = IXGBE_LINK_SPEED_5GB_FULL; + else + *speed = IXGBE_LINK_SPEED_100_FULL; + break; + case IXGBE_LINKS_SPEED_10_X550EM_A: + *speed = IXGBE_LINK_SPEED_UNKNOWN; + if (hw->device_id == IXGBE_DEV_ID_X550EM_A_1G_T || + hw->device_id == IXGBE_DEV_ID_X550EM_A_1G_T_L) { + *speed = IXGBE_LINK_SPEED_10_FULL; + } + break; + default: + *speed = IXGBE_LINK_SPEED_UNKNOWN; + } + + return 0; +} + +/** + * ixgbe_get_wwn_prefix_generic - Get alternative WWNN/WWPN prefix from + * the EEPROM + * @hw: pointer to hardware structure + * @wwnn_prefix: the alternative WWNN prefix + * @wwpn_prefix: the alternative WWPN prefix + * + * This function will read the EEPROM from the alternative SAN MAC address + * block to check the support for the alternative WWNN/WWPN prefix support. + **/ +s32 ixgbe_get_wwn_prefix_generic(struct ixgbe_hw *hw, u16 *wwnn_prefix, + u16 *wwpn_prefix) +{ + u16 offset, caps; + u16 alt_san_mac_blk_offset; + + /* clear output first */ + *wwnn_prefix = 0xFFFF; + *wwpn_prefix = 0xFFFF; + + /* check if alternative SAN MAC is supported */ + offset = IXGBE_ALT_SAN_MAC_ADDR_BLK_PTR; + if (hw->eeprom.ops.read(hw, offset, &alt_san_mac_blk_offset)) + goto wwn_prefix_err; + + if ((alt_san_mac_blk_offset == 0) || + (alt_san_mac_blk_offset == 0xFFFF)) + return 0; + + /* check capability in alternative san mac address block */ + offset = alt_san_mac_blk_offset + IXGBE_ALT_SAN_MAC_ADDR_CAPS_OFFSET; + if (hw->eeprom.ops.read(hw, offset, &caps)) + goto wwn_prefix_err; + if (!(caps & IXGBE_ALT_SAN_MAC_ADDR_CAPS_ALTWWN)) + return 0; + + /* get the corresponding prefix for WWNN/WWPN */ + offset = alt_san_mac_blk_offset + IXGBE_ALT_SAN_MAC_ADDR_WWNN_OFFSET; + if (hw->eeprom.ops.read(hw, offset, wwnn_prefix)) + hw_err(hw, "eeprom read at offset %d failed\n", offset); + + offset = alt_san_mac_blk_offset + IXGBE_ALT_SAN_MAC_ADDR_WWPN_OFFSET; + if (hw->eeprom.ops.read(hw, offset, wwpn_prefix)) + goto wwn_prefix_err; + + return 0; + +wwn_prefix_err: + hw_err(hw, "eeprom read at offset %d failed\n", offset); + return 0; +} + +/** + * ixgbe_set_mac_anti_spoofing - Enable/Disable MAC anti-spoofing + * @hw: pointer to hardware structure + * @enable: enable or disable switch for MAC anti-spoofing + * @vf: Virtual Function pool - VF Pool to set for MAC anti-spoofing + * + **/ +void ixgbe_set_mac_anti_spoofing(struct ixgbe_hw *hw, bool enable, int vf) +{ + int vf_target_reg = vf >> 3; + int vf_target_shift = vf % 8; + u32 pfvfspoof; + + if (hw->mac.type == ixgbe_mac_82598EB) + return; + + pfvfspoof = IXGBE_READ_REG(hw, IXGBE_PFVFSPOOF(vf_target_reg)); + if (enable) + pfvfspoof |= BIT(vf_target_shift); + else + pfvfspoof &= ~BIT(vf_target_shift); + IXGBE_WRITE_REG(hw, IXGBE_PFVFSPOOF(vf_target_reg), pfvfspoof); +} + +/** + * ixgbe_set_vlan_anti_spoofing - Enable/Disable VLAN anti-spoofing + * @hw: pointer to hardware structure + * @enable: enable or disable switch for VLAN anti-spoofing + * @vf: Virtual Function pool - VF Pool to set for VLAN anti-spoofing + * + **/ +void ixgbe_set_vlan_anti_spoofing(struct ixgbe_hw *hw, bool enable, int vf) +{ + int vf_target_reg = vf >> 3; + int vf_target_shift = vf % 8 + IXGBE_SPOOF_VLANAS_SHIFT; + u32 pfvfspoof; + + if (hw->mac.type == ixgbe_mac_82598EB) + return; + + pfvfspoof = IXGBE_READ_REG(hw, IXGBE_PFVFSPOOF(vf_target_reg)); + if (enable) + pfvfspoof |= BIT(vf_target_shift); + else + pfvfspoof &= ~BIT(vf_target_shift); + IXGBE_WRITE_REG(hw, IXGBE_PFVFSPOOF(vf_target_reg), pfvfspoof); +} + +/** + * ixgbe_get_device_caps_generic - Get additional device capabilities + * @hw: pointer to hardware structure + * @device_caps: the EEPROM word with the extra device capabilities + * + * This function will read the EEPROM location for the device capabilities, + * and return the word through device_caps. + **/ +s32 ixgbe_get_device_caps_generic(struct ixgbe_hw *hw, u16 *device_caps) +{ + hw->eeprom.ops.read(hw, IXGBE_DEVICE_CAPS, device_caps); + + return 0; +} + +/** + * ixgbe_set_rxpba_generic - Initialize RX packet buffer + * @hw: pointer to hardware structure + * @num_pb: number of packet buffers to allocate + * @headroom: reserve n KB of headroom + * @strategy: packet buffer allocation strategy + **/ +void ixgbe_set_rxpba_generic(struct ixgbe_hw *hw, + int num_pb, + u32 headroom, + int strategy) +{ + u32 pbsize = hw->mac.rx_pb_size; + int i = 0; + u32 rxpktsize, txpktsize, txpbthresh; + + /* Reserve headroom */ + pbsize -= headroom; + + if (!num_pb) + num_pb = 1; + + /* Divide remaining packet buffer space amongst the number + * of packet buffers requested using supplied strategy. + */ + switch (strategy) { + case (PBA_STRATEGY_WEIGHTED): + /* pba_80_48 strategy weight first half of packet buffer with + * 5/8 of the packet buffer space. + */ + rxpktsize = ((pbsize * 5 * 2) / (num_pb * 8)); + pbsize -= rxpktsize * (num_pb / 2); + rxpktsize <<= IXGBE_RXPBSIZE_SHIFT; + for (; i < (num_pb / 2); i++) + IXGBE_WRITE_REG(hw, IXGBE_RXPBSIZE(i), rxpktsize); + fallthrough; /* configure remaining packet buffers */ + case (PBA_STRATEGY_EQUAL): + /* Divide the remaining Rx packet buffer evenly among the TCs */ + rxpktsize = (pbsize / (num_pb - i)) << IXGBE_RXPBSIZE_SHIFT; + for (; i < num_pb; i++) + IXGBE_WRITE_REG(hw, IXGBE_RXPBSIZE(i), rxpktsize); + break; + default: + break; + } + + /* + * Setup Tx packet buffer and threshold equally for all TCs + * TXPBTHRESH register is set in K so divide by 1024 and subtract + * 10 since the largest packet we support is just over 9K. + */ + txpktsize = IXGBE_TXPBSIZE_MAX / num_pb; + txpbthresh = (txpktsize / 1024) - IXGBE_TXPKT_SIZE_MAX; + for (i = 0; i < num_pb; i++) { + IXGBE_WRITE_REG(hw, IXGBE_TXPBSIZE(i), txpktsize); + IXGBE_WRITE_REG(hw, IXGBE_TXPBTHRESH(i), txpbthresh); + } + + /* Clear unused TCs, if any, to zero buffer size*/ + for (; i < IXGBE_MAX_PB; i++) { + IXGBE_WRITE_REG(hw, IXGBE_RXPBSIZE(i), 0); + IXGBE_WRITE_REG(hw, IXGBE_TXPBSIZE(i), 0); + IXGBE_WRITE_REG(hw, IXGBE_TXPBTHRESH(i), 0); + } +} + +/** + * ixgbe_calculate_checksum - Calculate checksum for buffer + * @buffer: pointer to EEPROM + * @length: size of EEPROM to calculate a checksum for + * + * Calculates the checksum for some buffer on a specified length. The + * checksum calculated is returned. + **/ +u8 ixgbe_calculate_checksum(u8 *buffer, u32 length) +{ + u32 i; + u8 sum = 0; + + if (!buffer) + return 0; + + for (i = 0; i < length; i++) + sum += buffer[i]; + + return (u8) (0 - sum); +} + +/** + * ixgbe_hic_unlocked - Issue command to manageability block unlocked + * @hw: pointer to the HW structure + * @buffer: command to write and where the return status will be placed + * @length: length of buffer, must be multiple of 4 bytes + * @timeout: time in ms to wait for command completion + * + * Communicates with the manageability block. On success return 0 + * else returns semaphore error when encountering an error acquiring + * semaphore or IXGBE_ERR_HOST_INTERFACE_COMMAND when command fails. + * + * This function assumes that the IXGBE_GSSR_SW_MNG_SM semaphore is held + * by the caller. + **/ +s32 ixgbe_hic_unlocked(struct ixgbe_hw *hw, u32 *buffer, u32 length, + u32 timeout) +{ + u32 hicr, i, fwsts; + u16 dword_len; + + if (!length || length > IXGBE_HI_MAX_BLOCK_BYTE_LENGTH) { + hw_dbg(hw, "Buffer length failure buffersize-%d.\n", length); + return IXGBE_ERR_HOST_INTERFACE_COMMAND; + } + + /* Set bit 9 of FWSTS clearing FW reset indication */ + fwsts = IXGBE_READ_REG(hw, IXGBE_FWSTS); + IXGBE_WRITE_REG(hw, IXGBE_FWSTS, fwsts | IXGBE_FWSTS_FWRI); + + /* Check that the host interface is enabled. */ + hicr = IXGBE_READ_REG(hw, IXGBE_HICR); + if (!(hicr & IXGBE_HICR_EN)) { + hw_dbg(hw, "IXGBE_HOST_EN bit disabled.\n"); + return IXGBE_ERR_HOST_INTERFACE_COMMAND; + } + + /* Calculate length in DWORDs. We must be DWORD aligned */ + if (length % sizeof(u32)) { + hw_dbg(hw, "Buffer length failure, not aligned to dword"); + return IXGBE_ERR_INVALID_ARGUMENT; + } + + dword_len = length >> 2; + + /* The device driver writes the relevant command block + * into the ram area. + */ + for (i = 0; i < dword_len; i++) + IXGBE_WRITE_REG_ARRAY(hw, IXGBE_FLEX_MNG, + i, (__force u32)cpu_to_le32(buffer[i])); + + /* Setting this bit tells the ARC that a new command is pending. */ + IXGBE_WRITE_REG(hw, IXGBE_HICR, hicr | IXGBE_HICR_C); + + for (i = 0; i < timeout; i++) { + hicr = IXGBE_READ_REG(hw, IXGBE_HICR); + if (!(hicr & IXGBE_HICR_C)) + break; + usleep_range(1000, 2000); + } + + /* Check command successful completion. */ + if ((timeout && i == timeout) || + !(IXGBE_READ_REG(hw, IXGBE_HICR) & IXGBE_HICR_SV)) + return IXGBE_ERR_HOST_INTERFACE_COMMAND; + + return 0; +} + +/** + * ixgbe_host_interface_command - Issue command to manageability block + * @hw: pointer to the HW structure + * @buffer: contains the command to write and where the return status will + * be placed + * @length: length of buffer, must be multiple of 4 bytes + * @timeout: time in ms to wait for command completion + * @return_data: read and return data from the buffer (true) or not (false) + * Needed because FW structures are big endian and decoding of + * these fields can be 8 bit or 16 bit based on command. Decoding + * is not easily understood without making a table of commands. + * So we will leave this up to the caller to read back the data + * in these cases. + * + * Communicates with the manageability block. On success return 0 + * else return IXGBE_ERR_HOST_INTERFACE_COMMAND. + **/ +s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *buffer, + u32 length, u32 timeout, + bool return_data) +{ + u32 hdr_size = sizeof(struct ixgbe_hic_hdr); + union { + struct ixgbe_hic_hdr hdr; + u32 u32arr[1]; + } *bp = buffer; + u16 buf_len, dword_len; + s32 status; + u32 bi; + + if (!length || length > IXGBE_HI_MAX_BLOCK_BYTE_LENGTH) { + hw_dbg(hw, "Buffer length failure buffersize-%d.\n", length); + return IXGBE_ERR_HOST_INTERFACE_COMMAND; + } + /* Take management host interface semaphore */ + status = hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_SW_MNG_SM); + if (status) + return status; + + status = ixgbe_hic_unlocked(hw, buffer, length, timeout); + if (status) + goto rel_out; + + if (!return_data) + goto rel_out; + + /* Calculate length in DWORDs */ + dword_len = hdr_size >> 2; + + /* first pull in the header so we know the buffer length */ + for (bi = 0; bi < dword_len; bi++) { + bp->u32arr[bi] = IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, bi); + le32_to_cpus(&bp->u32arr[bi]); + } + + /* If there is any thing in data position pull it in */ + buf_len = bp->hdr.buf_len; + if (!buf_len) + goto rel_out; + + if (length < round_up(buf_len, 4) + hdr_size) { + hw_dbg(hw, "Buffer not large enough for reply message.\n"); + status = IXGBE_ERR_HOST_INTERFACE_COMMAND; + goto rel_out; + } + + /* Calculate length in DWORDs, add 3 for odd lengths */ + dword_len = (buf_len + 3) >> 2; + + /* Pull in the rest of the buffer (bi is where we left off) */ + for (; bi <= dword_len; bi++) { + bp->u32arr[bi] = IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, bi); + le32_to_cpus(&bp->u32arr[bi]); + } + +rel_out: + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_SW_MNG_SM); + + return status; +} + +/** + * ixgbe_set_fw_drv_ver_generic - Sends driver version to firmware + * @hw: pointer to the HW structure + * @maj: driver version major number + * @min: driver version minor number + * @build: driver version build number + * @sub: driver version sub build number + * @len: length of driver_ver string + * @driver_ver: driver string + * + * Sends driver version number to firmware through the manageability + * block. On success return 0 + * else returns IXGBE_ERR_SWFW_SYNC when encountering an error acquiring + * semaphore or IXGBE_ERR_HOST_INTERFACE_COMMAND when command fails. + **/ +s32 ixgbe_set_fw_drv_ver_generic(struct ixgbe_hw *hw, u8 maj, u8 min, + u8 build, u8 sub, __always_unused u16 len, + __always_unused const char *driver_ver) +{ + struct ixgbe_hic_drv_info fw_cmd; + int i; + s32 ret_val; + + fw_cmd.hdr.cmd = FW_CEM_CMD_DRIVER_INFO; + fw_cmd.hdr.buf_len = FW_CEM_CMD_DRIVER_INFO_LEN; + fw_cmd.hdr.cmd_or_resp.cmd_resv = FW_CEM_CMD_RESERVED; + fw_cmd.port_num = hw->bus.func; + fw_cmd.ver_maj = maj; + fw_cmd.ver_min = min; + fw_cmd.ver_build = build; + fw_cmd.ver_sub = sub; + fw_cmd.hdr.checksum = 0; + fw_cmd.pad = 0; + fw_cmd.pad2 = 0; + fw_cmd.hdr.checksum = ixgbe_calculate_checksum((u8 *)&fw_cmd, + (FW_CEM_HDR_LEN + fw_cmd.hdr.buf_len)); + + for (i = 0; i <= FW_CEM_MAX_RETRIES; i++) { + ret_val = ixgbe_host_interface_command(hw, &fw_cmd, + sizeof(fw_cmd), + IXGBE_HI_COMMAND_TIMEOUT, + true); + if (ret_val != 0) + continue; + + if (fw_cmd.hdr.cmd_or_resp.ret_status == + FW_CEM_RESP_STATUS_SUCCESS) + ret_val = 0; + else + ret_val = IXGBE_ERR_HOST_INTERFACE_COMMAND; + + break; + } + + return ret_val; +} + +/** + * ixgbe_clear_tx_pending - Clear pending TX work from the PCIe fifo + * @hw: pointer to the hardware structure + * + * The 82599 and x540 MACs can experience issues if TX work is still pending + * when a reset occurs. This function prevents this by flushing the PCIe + * buffers on the system. + **/ +void ixgbe_clear_tx_pending(struct ixgbe_hw *hw) +{ + u32 gcr_ext, hlreg0, i, poll; + u16 value; + + /* + * If double reset is not requested then all transactions should + * already be clear and as such there is no work to do + */ + if (!(hw->mac.flags & IXGBE_FLAGS_DOUBLE_RESET_REQUIRED)) + return; + + /* + * Set loopback enable to prevent any transmits from being sent + * should the link come up. This assumes that the RXCTRL.RXEN bit + * has already been cleared. + */ + hlreg0 = IXGBE_READ_REG(hw, IXGBE_HLREG0); + IXGBE_WRITE_REG(hw, IXGBE_HLREG0, hlreg0 | IXGBE_HLREG0_LPBK); + + /* wait for a last completion before clearing buffers */ + IXGBE_WRITE_FLUSH(hw); + usleep_range(3000, 6000); + + /* Before proceeding, make sure that the PCIe block does not have + * transactions pending. + */ + poll = ixgbe_pcie_timeout_poll(hw); + for (i = 0; i < poll; i++) { + usleep_range(100, 200); + value = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_DEVICE_STATUS); + if (ixgbe_removed(hw->hw_addr)) + break; + if (!(value & IXGBE_PCI_DEVICE_STATUS_TRANSACTION_PENDING)) + break; + } + + /* initiate cleaning flow for buffers in the PCIe transaction layer */ + gcr_ext = IXGBE_READ_REG(hw, IXGBE_GCR_EXT); + IXGBE_WRITE_REG(hw, IXGBE_GCR_EXT, + gcr_ext | IXGBE_GCR_EXT_BUFFERS_CLEAR); + + /* Flush all writes and allow 20usec for all transactions to clear */ + IXGBE_WRITE_FLUSH(hw); + udelay(20); + + /* restore previous register values */ + IXGBE_WRITE_REG(hw, IXGBE_GCR_EXT, gcr_ext); + IXGBE_WRITE_REG(hw, IXGBE_HLREG0, hlreg0); +} + +static const u8 ixgbe_emc_temp_data[4] = { + IXGBE_EMC_INTERNAL_DATA, + IXGBE_EMC_DIODE1_DATA, + IXGBE_EMC_DIODE2_DATA, + IXGBE_EMC_DIODE3_DATA +}; +static const u8 ixgbe_emc_therm_limit[4] = { + IXGBE_EMC_INTERNAL_THERM_LIMIT, + IXGBE_EMC_DIODE1_THERM_LIMIT, + IXGBE_EMC_DIODE2_THERM_LIMIT, + IXGBE_EMC_DIODE3_THERM_LIMIT +}; + +/** + * ixgbe_get_ets_data - Extracts the ETS bit data + * @hw: pointer to hardware structure + * @ets_cfg: extected ETS data + * @ets_offset: offset of ETS data + * + * Returns error code. + **/ +static s32 ixgbe_get_ets_data(struct ixgbe_hw *hw, u16 *ets_cfg, + u16 *ets_offset) +{ + s32 status; + + status = hw->eeprom.ops.read(hw, IXGBE_ETS_CFG, ets_offset); + if (status) + return status; + + if ((*ets_offset == 0x0000) || (*ets_offset == 0xFFFF)) + return IXGBE_NOT_IMPLEMENTED; + + status = hw->eeprom.ops.read(hw, *ets_offset, ets_cfg); + if (status) + return status; + + if ((*ets_cfg & IXGBE_ETS_TYPE_MASK) != IXGBE_ETS_TYPE_EMC_SHIFTED) + return IXGBE_NOT_IMPLEMENTED; + + return 0; +} + +/** + * ixgbe_get_thermal_sensor_data - Gathers thermal sensor data + * @hw: pointer to hardware structure + * + * Returns the thermal sensor data structure + **/ +s32 ixgbe_get_thermal_sensor_data_generic(struct ixgbe_hw *hw) +{ + s32 status; + u16 ets_offset; + u16 ets_cfg; + u16 ets_sensor; + u8 num_sensors; + u8 i; + struct ixgbe_thermal_sensor_data *data = &hw->mac.thermal_sensor_data; + + /* Only support thermal sensors attached to physical port 0 */ + if ((IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_LAN_ID_1)) + return IXGBE_NOT_IMPLEMENTED; + + status = ixgbe_get_ets_data(hw, &ets_cfg, &ets_offset); + if (status) + return status; + + num_sensors = (ets_cfg & IXGBE_ETS_NUM_SENSORS_MASK); + if (num_sensors > IXGBE_MAX_SENSORS) + num_sensors = IXGBE_MAX_SENSORS; + + for (i = 0; i < num_sensors; i++) { + u8 sensor_index; + u8 sensor_location; + + status = hw->eeprom.ops.read(hw, (ets_offset + 1 + i), + &ets_sensor); + if (status) + return status; + + sensor_index = ((ets_sensor & IXGBE_ETS_DATA_INDEX_MASK) >> + IXGBE_ETS_DATA_INDEX_SHIFT); + sensor_location = ((ets_sensor & IXGBE_ETS_DATA_LOC_MASK) >> + IXGBE_ETS_DATA_LOC_SHIFT); + + if (sensor_location != 0) { + status = hw->phy.ops.read_i2c_byte(hw, + ixgbe_emc_temp_data[sensor_index], + IXGBE_I2C_THERMAL_SENSOR_ADDR, + &data->sensor[i].temp); + if (status) + return status; + } + } + + return 0; +} + +/** + * ixgbe_init_thermal_sensor_thresh_generic - Inits thermal sensor thresholds + * @hw: pointer to hardware structure + * + * Inits the thermal sensor thresholds according to the NVM map + * and save off the threshold and location values into mac.thermal_sensor_data + **/ +s32 ixgbe_init_thermal_sensor_thresh_generic(struct ixgbe_hw *hw) +{ + s32 status; + u16 ets_offset; + u16 ets_cfg; + u16 ets_sensor; + u8 low_thresh_delta; + u8 num_sensors; + u8 therm_limit; + u8 i; + struct ixgbe_thermal_sensor_data *data = &hw->mac.thermal_sensor_data; + + memset(data, 0, sizeof(struct ixgbe_thermal_sensor_data)); + + /* Only support thermal sensors attached to physical port 0 */ + if ((IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_LAN_ID_1)) + return IXGBE_NOT_IMPLEMENTED; + + status = ixgbe_get_ets_data(hw, &ets_cfg, &ets_offset); + if (status) + return status; + + low_thresh_delta = ((ets_cfg & IXGBE_ETS_LTHRES_DELTA_MASK) >> + IXGBE_ETS_LTHRES_DELTA_SHIFT); + num_sensors = (ets_cfg & IXGBE_ETS_NUM_SENSORS_MASK); + if (num_sensors > IXGBE_MAX_SENSORS) + num_sensors = IXGBE_MAX_SENSORS; + + for (i = 0; i < num_sensors; i++) { + u8 sensor_index; + u8 sensor_location; + + if (hw->eeprom.ops.read(hw, ets_offset + 1 + i, &ets_sensor)) { + hw_err(hw, "eeprom read at offset %d failed\n", + ets_offset + 1 + i); + continue; + } + sensor_index = ((ets_sensor & IXGBE_ETS_DATA_INDEX_MASK) >> + IXGBE_ETS_DATA_INDEX_SHIFT); + sensor_location = ((ets_sensor & IXGBE_ETS_DATA_LOC_MASK) >> + IXGBE_ETS_DATA_LOC_SHIFT); + therm_limit = ets_sensor & IXGBE_ETS_DATA_HTHRESH_MASK; + + hw->phy.ops.write_i2c_byte(hw, + ixgbe_emc_therm_limit[sensor_index], + IXGBE_I2C_THERMAL_SENSOR_ADDR, therm_limit); + + if (sensor_location == 0) + continue; + + data->sensor[i].location = sensor_location; + data->sensor[i].caution_thresh = therm_limit; + data->sensor[i].max_op_thresh = therm_limit - low_thresh_delta; + } + + return 0; +} + +/** + * ixgbe_get_orom_version - Return option ROM from EEPROM + * + * @hw: pointer to hardware structure + * @nvm_ver: pointer to output structure + * + * if valid option ROM version, nvm_ver->or_valid set to true + * else nvm_ver->or_valid is false. + **/ +void ixgbe_get_orom_version(struct ixgbe_hw *hw, + struct ixgbe_nvm_version *nvm_ver) +{ + u16 offset, eeprom_cfg_blkh, eeprom_cfg_blkl; + + nvm_ver->or_valid = false; + /* Option Rom may or may not be present. Start with pointer */ + hw->eeprom.ops.read(hw, NVM_OROM_OFFSET, &offset); + + /* make sure offset is valid */ + if (offset == 0x0 || offset == NVM_INVALID_PTR) + return; + + hw->eeprom.ops.read(hw, offset + NVM_OROM_BLK_HI, &eeprom_cfg_blkh); + hw->eeprom.ops.read(hw, offset + NVM_OROM_BLK_LOW, &eeprom_cfg_blkl); + + /* option rom exists and is valid */ + if ((eeprom_cfg_blkl | eeprom_cfg_blkh) == 0x0 || + eeprom_cfg_blkl == NVM_VER_INVALID || + eeprom_cfg_blkh == NVM_VER_INVALID) + return; + + nvm_ver->or_valid = true; + nvm_ver->or_major = eeprom_cfg_blkl >> NVM_OROM_SHIFT; + nvm_ver->or_build = (eeprom_cfg_blkl << NVM_OROM_SHIFT) | + (eeprom_cfg_blkh >> NVM_OROM_SHIFT); + nvm_ver->or_patch = eeprom_cfg_blkh & NVM_OROM_PATCH_MASK; +} + +/** + * ixgbe_get_oem_prod_version Etrack ID from EEPROM + * + * @hw: pointer to hardware structure + * @nvm_ver: pointer to output structure + * + * if valid OEM product version, nvm_ver->oem_valid set to true + * else nvm_ver->oem_valid is false. + **/ +void ixgbe_get_oem_prod_version(struct ixgbe_hw *hw, + struct ixgbe_nvm_version *nvm_ver) +{ + u16 rel_num, prod_ver, mod_len, cap, offset; + + nvm_ver->oem_valid = false; + hw->eeprom.ops.read(hw, NVM_OEM_PROD_VER_PTR, &offset); + + /* Return is offset to OEM Product Version block is invalid */ + if (offset == 0x0 || offset == NVM_INVALID_PTR) + return; + + /* Read product version block */ + hw->eeprom.ops.read(hw, offset, &mod_len); + hw->eeprom.ops.read(hw, offset + NVM_OEM_PROD_VER_CAP_OFF, &cap); + + /* Return if OEM product version block is invalid */ + if (mod_len != NVM_OEM_PROD_VER_MOD_LEN || + (cap & NVM_OEM_PROD_VER_CAP_MASK) != 0x0) + return; + + hw->eeprom.ops.read(hw, offset + NVM_OEM_PROD_VER_OFF_L, &prod_ver); + hw->eeprom.ops.read(hw, offset + NVM_OEM_PROD_VER_OFF_H, &rel_num); + + /* Return if version is invalid */ + if ((rel_num | prod_ver) == 0x0 || + rel_num == NVM_VER_INVALID || prod_ver == NVM_VER_INVALID) + return; + + nvm_ver->oem_major = prod_ver >> NVM_VER_SHIFT; + nvm_ver->oem_minor = prod_ver & NVM_VER_MASK; + nvm_ver->oem_release = rel_num; + nvm_ver->oem_valid = true; +} + +/** + * ixgbe_get_etk_id - Return Etrack ID from EEPROM + * + * @hw: pointer to hardware structure + * @nvm_ver: pointer to output structure + * + * word read errors will return 0xFFFF + **/ +void ixgbe_get_etk_id(struct ixgbe_hw *hw, + struct ixgbe_nvm_version *nvm_ver) +{ + u16 etk_id_l, etk_id_h; + + if (hw->eeprom.ops.read(hw, NVM_ETK_OFF_LOW, &etk_id_l)) + etk_id_l = NVM_VER_INVALID; + if (hw->eeprom.ops.read(hw, NVM_ETK_OFF_HI, &etk_id_h)) + etk_id_h = NVM_VER_INVALID; + + /* The word order for the version format is determined by high order + * word bit 15. + */ + if ((etk_id_h & NVM_ETK_VALID) == 0) { + nvm_ver->etk_id = etk_id_h; + nvm_ver->etk_id |= (etk_id_l << NVM_ETK_SHIFT); + } else { + nvm_ver->etk_id = etk_id_l; + nvm_ver->etk_id |= (etk_id_h << NVM_ETK_SHIFT); + } +} + +void ixgbe_disable_rx_generic(struct ixgbe_hw *hw) +{ + u32 rxctrl; + + rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL); + if (rxctrl & IXGBE_RXCTRL_RXEN) { + if (hw->mac.type != ixgbe_mac_82598EB) { + u32 pfdtxgswc; + + pfdtxgswc = IXGBE_READ_REG(hw, IXGBE_PFDTXGSWC); + if (pfdtxgswc & IXGBE_PFDTXGSWC_VT_LBEN) { + pfdtxgswc &= ~IXGBE_PFDTXGSWC_VT_LBEN; + IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, pfdtxgswc); + hw->mac.set_lben = true; + } else { + hw->mac.set_lben = false; + } + } + rxctrl &= ~IXGBE_RXCTRL_RXEN; + IXGBE_WRITE_REG(hw, IXGBE_RXCTRL, rxctrl); + } +} + +void ixgbe_enable_rx_generic(struct ixgbe_hw *hw) +{ + u32 rxctrl; + + rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL); + IXGBE_WRITE_REG(hw, IXGBE_RXCTRL, (rxctrl | IXGBE_RXCTRL_RXEN)); + + if (hw->mac.type != ixgbe_mac_82598EB) { + if (hw->mac.set_lben) { + u32 pfdtxgswc; + + pfdtxgswc = IXGBE_READ_REG(hw, IXGBE_PFDTXGSWC); + pfdtxgswc |= IXGBE_PFDTXGSWC_VT_LBEN; + IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, pfdtxgswc); + hw->mac.set_lben = false; + } + } +} + +/** ixgbe_mng_present - returns true when management capability is present + * @hw: pointer to hardware structure + **/ +bool ixgbe_mng_present(struct ixgbe_hw *hw) +{ + u32 fwsm; + + if (hw->mac.type < ixgbe_mac_82599EB) + return false; + + fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw)); + + return !!(fwsm & IXGBE_FWSM_FW_MODE_PT); +} + +/** + * ixgbe_setup_mac_link_multispeed_fiber - Set MAC link speed + * @hw: pointer to hardware structure + * @speed: new link speed + * @autoneg_wait_to_complete: true when waiting for completion is needed + * + * Set the link speed in the MAC and/or PHY register and restarts link. + */ +s32 ixgbe_setup_mac_link_multispeed_fiber(struct ixgbe_hw *hw, + ixgbe_link_speed speed, + bool autoneg_wait_to_complete) +{ + ixgbe_link_speed link_speed = IXGBE_LINK_SPEED_UNKNOWN; + ixgbe_link_speed highest_link_speed = IXGBE_LINK_SPEED_UNKNOWN; + s32 status = 0; + u32 speedcnt = 0; + u32 i = 0; + bool autoneg, link_up = false; + + /* Mask off requested but non-supported speeds */ + status = hw->mac.ops.get_link_capabilities(hw, &link_speed, &autoneg); + if (status) + return status; + + speed &= link_speed; + + /* Try each speed one by one, highest priority first. We do this in + * software because 10Gb fiber doesn't support speed autonegotiation. + */ + if (speed & IXGBE_LINK_SPEED_10GB_FULL) { + speedcnt++; + highest_link_speed = IXGBE_LINK_SPEED_10GB_FULL; + + /* Set the module link speed */ + switch (hw->phy.media_type) { + case ixgbe_media_type_fiber: + hw->mac.ops.set_rate_select_speed(hw, + IXGBE_LINK_SPEED_10GB_FULL); + break; + case ixgbe_media_type_fiber_qsfp: + /* QSFP module automatically detects MAC link speed */ + break; + default: + hw_dbg(hw, "Unexpected media type\n"); + break; + } + + /* Allow module to change analog characteristics (1G->10G) */ + msleep(40); + + status = hw->mac.ops.setup_mac_link(hw, + IXGBE_LINK_SPEED_10GB_FULL, + autoneg_wait_to_complete); + if (status) + return status; + + /* Flap the Tx laser if it has not already been done */ + if (hw->mac.ops.flap_tx_laser) + hw->mac.ops.flap_tx_laser(hw); + + /* Wait for the controller to acquire link. Per IEEE 802.3ap, + * Section 73.10.2, we may have to wait up to 500ms if KR is + * attempted. 82599 uses the same timing for 10g SFI. + */ + for (i = 0; i < 5; i++) { + /* Wait for the link partner to also set speed */ + msleep(100); + + /* If we have link, just jump out */ + status = hw->mac.ops.check_link(hw, &link_speed, + &link_up, false); + if (status) + return status; + + if (link_up) + goto out; + } + } + + if (speed & IXGBE_LINK_SPEED_1GB_FULL) { + speedcnt++; + if (highest_link_speed == IXGBE_LINK_SPEED_UNKNOWN) + highest_link_speed = IXGBE_LINK_SPEED_1GB_FULL; + + /* Set the module link speed */ + switch (hw->phy.media_type) { + case ixgbe_media_type_fiber: + hw->mac.ops.set_rate_select_speed(hw, + IXGBE_LINK_SPEED_1GB_FULL); + break; + case ixgbe_media_type_fiber_qsfp: + /* QSFP module automatically detects link speed */ + break; + default: + hw_dbg(hw, "Unexpected media type\n"); + break; + } + + /* Allow module to change analog characteristics (10G->1G) */ + msleep(40); + + status = hw->mac.ops.setup_mac_link(hw, + IXGBE_LINK_SPEED_1GB_FULL, + autoneg_wait_to_complete); + if (status) + return status; + + /* Flap the Tx laser if it has not already been done */ + if (hw->mac.ops.flap_tx_laser) + hw->mac.ops.flap_tx_laser(hw); + + /* Wait for the link partner to also set speed */ + msleep(100); + + /* If we have link, just jump out */ + status = hw->mac.ops.check_link(hw, &link_speed, &link_up, + false); + if (status) + return status; + + if (link_up) + goto out; + } + + /* We didn't get link. Configure back to the highest speed we tried, + * (if there was more than one). We call ourselves back with just the + * single highest speed that the user requested. + */ + if (speedcnt > 1) + status = ixgbe_setup_mac_link_multispeed_fiber(hw, + highest_link_speed, + autoneg_wait_to_complete); + +out: + /* Set autoneg_advertised value based on input link speed */ + hw->phy.autoneg_advertised = 0; + + if (speed & IXGBE_LINK_SPEED_10GB_FULL) + hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_10GB_FULL; + + if (speed & IXGBE_LINK_SPEED_1GB_FULL) + hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_1GB_FULL; + + return status; +} + +/** + * ixgbe_set_soft_rate_select_speed - Set module link speed + * @hw: pointer to hardware structure + * @speed: link speed to set + * + * Set module link speed via the soft rate select. + */ +void ixgbe_set_soft_rate_select_speed(struct ixgbe_hw *hw, + ixgbe_link_speed speed) +{ + s32 status; + u8 rs, eeprom_data; + + switch (speed) { + case IXGBE_LINK_SPEED_10GB_FULL: + /* one bit mask same as setting on */ + rs = IXGBE_SFF_SOFT_RS_SELECT_10G; + break; + case IXGBE_LINK_SPEED_1GB_FULL: + rs = IXGBE_SFF_SOFT_RS_SELECT_1G; + break; + default: + hw_dbg(hw, "Invalid fixed module speed\n"); + return; + } + + /* Set RS0 */ + status = hw->phy.ops.read_i2c_byte(hw, IXGBE_SFF_SFF_8472_OSCB, + IXGBE_I2C_EEPROM_DEV_ADDR2, + &eeprom_data); + if (status) { + hw_dbg(hw, "Failed to read Rx Rate Select RS0\n"); + return; + } + + eeprom_data = (eeprom_data & ~IXGBE_SFF_SOFT_RS_SELECT_MASK) | rs; + + status = hw->phy.ops.write_i2c_byte(hw, IXGBE_SFF_SFF_8472_OSCB, + IXGBE_I2C_EEPROM_DEV_ADDR2, + eeprom_data); + if (status) { + hw_dbg(hw, "Failed to write Rx Rate Select RS0\n"); + return; + } + + /* Set RS1 */ + status = hw->phy.ops.read_i2c_byte(hw, IXGBE_SFF_SFF_8472_ESCB, + IXGBE_I2C_EEPROM_DEV_ADDR2, + &eeprom_data); + if (status) { + hw_dbg(hw, "Failed to read Rx Rate Select RS1\n"); + return; + } + + eeprom_data = (eeprom_data & ~IXGBE_SFF_SOFT_RS_SELECT_MASK) | rs; + + status = hw->phy.ops.write_i2c_byte(hw, IXGBE_SFF_SFF_8472_ESCB, + IXGBE_I2C_EEPROM_DEV_ADDR2, + eeprom_data); + if (status) { + hw_dbg(hw, "Failed to write Rx Rate Select RS1\n"); + return; + } +} diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h new file mode 100644 index 000000000..4b531e8ae --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h @@ -0,0 +1,206 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#ifndef _IXGBE_COMMON_H_ +#define _IXGBE_COMMON_H_ + +#include "ixgbe_type.h" +#include "ixgbe.h" + +u16 ixgbe_get_pcie_msix_count_generic(struct ixgbe_hw *hw); +s32 ixgbe_init_ops_generic(struct ixgbe_hw *hw); +s32 ixgbe_init_hw_generic(struct ixgbe_hw *hw); +s32 ixgbe_start_hw_generic(struct ixgbe_hw *hw); +s32 ixgbe_start_hw_gen2(struct ixgbe_hw *hw); +s32 ixgbe_clear_hw_cntrs_generic(struct ixgbe_hw *hw); +s32 ixgbe_read_pba_string_generic(struct ixgbe_hw *hw, u8 *pba_num, + u32 pba_num_size); +s32 ixgbe_get_mac_addr_generic(struct ixgbe_hw *hw, u8 *mac_addr); +enum ixgbe_bus_width ixgbe_convert_bus_width(u16 link_status); +enum ixgbe_bus_speed ixgbe_convert_bus_speed(u16 link_status); +s32 ixgbe_get_bus_info_generic(struct ixgbe_hw *hw); +void ixgbe_set_lan_id_multi_port_pcie(struct ixgbe_hw *hw); +s32 ixgbe_stop_adapter_generic(struct ixgbe_hw *hw); + +s32 ixgbe_led_on_generic(struct ixgbe_hw *hw, u32 index); +s32 ixgbe_led_off_generic(struct ixgbe_hw *hw, u32 index); +s32 ixgbe_init_led_link_act_generic(struct ixgbe_hw *hw); + +s32 ixgbe_init_eeprom_params_generic(struct ixgbe_hw *hw); +s32 ixgbe_write_eeprom_generic(struct ixgbe_hw *hw, u16 offset, u16 data); +s32 ixgbe_write_eeprom_buffer_bit_bang_generic(struct ixgbe_hw *hw, u16 offset, + u16 words, u16 *data); +s32 ixgbe_read_eerd_generic(struct ixgbe_hw *hw, u16 offset, u16 *data); +s32 ixgbe_read_eerd_buffer_generic(struct ixgbe_hw *hw, u16 offset, + u16 words, u16 *data); +s32 ixgbe_write_eewr_generic(struct ixgbe_hw *hw, u16 offset, u16 data); +s32 ixgbe_write_eewr_buffer_generic(struct ixgbe_hw *hw, u16 offset, + u16 words, u16 *data); +s32 ixgbe_read_eeprom_bit_bang_generic(struct ixgbe_hw *hw, u16 offset, + u16 *data); +s32 ixgbe_read_eeprom_buffer_bit_bang_generic(struct ixgbe_hw *hw, u16 offset, + u16 words, u16 *data); +s32 ixgbe_calc_eeprom_checksum_generic(struct ixgbe_hw *hw); +s32 ixgbe_validate_eeprom_checksum_generic(struct ixgbe_hw *hw, + u16 *checksum_val); +s32 ixgbe_update_eeprom_checksum_generic(struct ixgbe_hw *hw); + +s32 ixgbe_set_rar_generic(struct ixgbe_hw *hw, u32 index, u8 *addr, u32 vmdq, + u32 enable_addr); +s32 ixgbe_clear_rar_generic(struct ixgbe_hw *hw, u32 index); +s32 ixgbe_init_rx_addrs_generic(struct ixgbe_hw *hw); +s32 ixgbe_update_mc_addr_list_generic(struct ixgbe_hw *hw, + struct net_device *netdev); +s32 ixgbe_enable_mc_generic(struct ixgbe_hw *hw); +s32 ixgbe_disable_mc_generic(struct ixgbe_hw *hw); +s32 ixgbe_disable_rx_buff_generic(struct ixgbe_hw *hw); +s32 ixgbe_enable_rx_buff_generic(struct ixgbe_hw *hw); +s32 ixgbe_enable_rx_dma_generic(struct ixgbe_hw *hw, u32 regval); +s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw); +s32 ixgbe_setup_fc_generic(struct ixgbe_hw *); +bool ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw); +void ixgbe_fc_autoneg(struct ixgbe_hw *hw); + +s32 ixgbe_acquire_swfw_sync(struct ixgbe_hw *hw, u32 mask); +void ixgbe_release_swfw_sync(struct ixgbe_hw *hw, u32 mask); +s32 ixgbe_get_san_mac_addr_generic(struct ixgbe_hw *hw, u8 *san_mac_addr); +s32 ixgbe_set_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq); +s32 ixgbe_set_vmdq_san_mac_generic(struct ixgbe_hw *hw, u32 vmdq); +s32 ixgbe_clear_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq); +s32 ixgbe_init_uta_tables_generic(struct ixgbe_hw *hw); +s32 ixgbe_set_vfta_generic(struct ixgbe_hw *hw, u32 vlan, + u32 vind, bool vlan_on, bool vlvf_bypass); +s32 ixgbe_clear_vfta_generic(struct ixgbe_hw *hw); +s32 ixgbe_check_mac_link_generic(struct ixgbe_hw *hw, + ixgbe_link_speed *speed, + bool *link_up, bool link_up_wait_to_complete); +s32 ixgbe_get_wwn_prefix_generic(struct ixgbe_hw *hw, u16 *wwnn_prefix, + u16 *wwpn_prefix); + +s32 prot_autoc_read_generic(struct ixgbe_hw *hw, bool *, u32 *reg_val); +s32 prot_autoc_write_generic(struct ixgbe_hw *hw, u32 reg_val, bool locked); + +s32 ixgbe_blink_led_start_generic(struct ixgbe_hw *hw, u32 index); +s32 ixgbe_blink_led_stop_generic(struct ixgbe_hw *hw, u32 index); +void ixgbe_set_mac_anti_spoofing(struct ixgbe_hw *hw, bool enable, int vf); +void ixgbe_set_vlan_anti_spoofing(struct ixgbe_hw *hw, bool enable, int vf); +s32 ixgbe_get_device_caps_generic(struct ixgbe_hw *hw, u16 *device_caps); +s32 ixgbe_set_fw_drv_ver_generic(struct ixgbe_hw *hw, u8 maj, u8 min, + u8 build, u8 ver, u16 len, const char *str); +u8 ixgbe_calculate_checksum(u8 *buffer, u32 length); +s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, void *, u32 length, + u32 timeout, bool return_data); +s32 ixgbe_hic_unlocked(struct ixgbe_hw *hw, u32 *buffer, u32 len, u32 timeout); +s32 ixgbe_fw_phy_activity(struct ixgbe_hw *hw, u16 activity, + u32 (*data)[FW_PHY_ACT_DATA_COUNT]); +void ixgbe_clear_tx_pending(struct ixgbe_hw *hw); +bool ixgbe_mng_present(struct ixgbe_hw *hw); +bool ixgbe_mng_enabled(struct ixgbe_hw *hw); + +void ixgbe_set_rxpba_generic(struct ixgbe_hw *hw, int num_pb, + u32 headroom, int strategy); + +extern const u32 ixgbe_mvals_8259X[IXGBE_MVALS_IDX_LIMIT]; + +#define IXGBE_I2C_THERMAL_SENSOR_ADDR 0xF8 +#define IXGBE_EMC_INTERNAL_DATA 0x00 +#define IXGBE_EMC_INTERNAL_THERM_LIMIT 0x20 +#define IXGBE_EMC_DIODE1_DATA 0x01 +#define IXGBE_EMC_DIODE1_THERM_LIMIT 0x19 +#define IXGBE_EMC_DIODE2_DATA 0x23 +#define IXGBE_EMC_DIODE2_THERM_LIMIT 0x1A +#define IXGBE_EMC_DIODE3_DATA 0x2A +#define IXGBE_EMC_DIODE3_THERM_LIMIT 0x30 + +s32 ixgbe_get_thermal_sensor_data_generic(struct ixgbe_hw *hw); +s32 ixgbe_init_thermal_sensor_thresh_generic(struct ixgbe_hw *hw); +void ixgbe_get_etk_id(struct ixgbe_hw *hw, + struct ixgbe_nvm_version *nvm_ver); +void ixgbe_get_oem_prod_version(struct ixgbe_hw *hw, + struct ixgbe_nvm_version *nvm_ver); +void ixgbe_get_orom_version(struct ixgbe_hw *hw, + struct ixgbe_nvm_version *nvm_ver); +void ixgbe_disable_rx_generic(struct ixgbe_hw *hw); +void ixgbe_enable_rx_generic(struct ixgbe_hw *hw); +s32 ixgbe_setup_mac_link_multispeed_fiber(struct ixgbe_hw *hw, + ixgbe_link_speed speed, + bool autoneg_wait_to_complete); +void ixgbe_set_soft_rate_select_speed(struct ixgbe_hw *hw, + ixgbe_link_speed speed); + +#define IXGBE_FAILED_READ_RETRIES 5 +#define IXGBE_FAILED_READ_REG 0xffffffffU +#define IXGBE_FAILED_READ_CFG_DWORD 0xffffffffU +#define IXGBE_FAILED_READ_CFG_WORD 0xffffU + +u16 ixgbe_read_pci_cfg_word(struct ixgbe_hw *hw, u32 reg); +void ixgbe_write_pci_cfg_word(struct ixgbe_hw *hw, u32 reg, u16 value); + +static inline bool ixgbe_removed(void __iomem *addr) +{ + return unlikely(!addr); +} + +static inline void ixgbe_write_reg(struct ixgbe_hw *hw, u32 reg, u32 value) +{ + u8 __iomem *reg_addr = READ_ONCE(hw->hw_addr); + + if (ixgbe_removed(reg_addr)) + return; + writel(value, reg_addr + reg); +} +#define IXGBE_WRITE_REG(a, reg, value) ixgbe_write_reg((a), (reg), (value)) + +#ifndef writeq +#define writeq writeq +static inline void writeq(u64 val, void __iomem *addr) +{ + writel((u32)val, addr); + writel((u32)(val >> 32), addr + 4); +} +#endif + +static inline void ixgbe_write_reg64(struct ixgbe_hw *hw, u32 reg, u64 value) +{ + u8 __iomem *reg_addr = READ_ONCE(hw->hw_addr); + + if (ixgbe_removed(reg_addr)) + return; + writeq(value, reg_addr + reg); +} +#define IXGBE_WRITE_REG64(a, reg, value) ixgbe_write_reg64((a), (reg), (value)) + +u32 ixgbe_read_reg(struct ixgbe_hw *hw, u32 reg); +#define IXGBE_READ_REG(a, reg) ixgbe_read_reg((a), (reg)) + +#define IXGBE_WRITE_REG_ARRAY(a, reg, offset, value) \ + ixgbe_write_reg((a), (reg) + ((offset) << 2), (value)) + +#define IXGBE_READ_REG_ARRAY(a, reg, offset) \ + ixgbe_read_reg((a), (reg) + ((offset) << 2)) + +#define IXGBE_WRITE_FLUSH(a) ixgbe_read_reg((a), IXGBE_STATUS) + +#define ixgbe_hw_to_netdev(hw) (((struct ixgbe_adapter *)(hw)->back)->netdev) + +#define hw_dbg(hw, format, arg...) \ + netdev_dbg(ixgbe_hw_to_netdev(hw), format, ## arg) +#define hw_err(hw, format, arg...) \ + netdev_err(ixgbe_hw_to_netdev(hw), format, ## arg) +#define e_dev_info(format, arg...) \ + dev_info(&adapter->pdev->dev, format, ## arg) +#define e_dev_warn(format, arg...) \ + dev_warn(&adapter->pdev->dev, format, ## arg) +#define e_dev_err(format, arg...) \ + dev_err(&adapter->pdev->dev, format, ## arg) +#define e_dev_notice(format, arg...) \ + dev_notice(&adapter->pdev->dev, format, ## arg) +#define e_info(msglvl, format, arg...) \ + netif_info(adapter, msglvl, adapter->netdev, format, ## arg) +#define e_err(msglvl, format, arg...) \ + netif_err(adapter, msglvl, adapter->netdev, format, ## arg) +#define e_warn(msglvl, format, arg...) \ + netif_warn(adapter, msglvl, adapter->netdev, format, ## arg) +#define e_crit(msglvl, format, arg...) \ + netif_crit(adapter, msglvl, adapter->netdev, format, ## arg) +#endif /* IXGBE_COMMON */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.c new file mode 100644 index 000000000..d26cea5b4 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.c @@ -0,0 +1,390 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#include "ixgbe.h" +#include "ixgbe_type.h" +#include "ixgbe_dcb.h" +#include "ixgbe_dcb_82598.h" +#include "ixgbe_dcb_82599.h" + +/** + * ixgbe_ieee_credits - This calculates the ieee traffic class + * credits from the configured bandwidth percentages. Credits + * are the smallest unit programmable into the underlying + * hardware. The IEEE 802.1Qaz specification do not use bandwidth + * groups so this is much simplified from the CEE case. + * @bw: bandwidth index by traffic class + * @refill: refill credits index by traffic class + * @max: max credits by traffic class + * @max_frame: maximum frame size + */ +static s32 ixgbe_ieee_credits(__u8 *bw, __u16 *refill, + __u16 *max, int max_frame) +{ + int min_percent = 100; + int min_credit, multiplier; + int i; + + min_credit = ((max_frame / 2) + DCB_CREDIT_QUANTUM - 1) / + DCB_CREDIT_QUANTUM; + + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + if (bw[i] < min_percent && bw[i]) + min_percent = bw[i]; + } + + multiplier = (min_credit / min_percent) + 1; + + /* Find out the hw credits for each TC */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + int val = min(bw[i] * multiplier, MAX_CREDIT_REFILL); + + if (val < min_credit) + val = min_credit; + refill[i] = val; + + max[i] = bw[i] ? (bw[i] * MAX_CREDIT)/100 : min_credit; + } + return 0; +} + +/** + * ixgbe_dcb_calculate_tc_credits - Calculates traffic class credits + * @hw: pointer to hardware structure + * @dcb_config: Struct containing DCB settings + * @max_frame: Maximum frame size + * @direction: Configuring either Tx or Rx + * + * This function calculates the credits allocated to each traffic class. + * It should be called only after the rules are checked by + * ixgbe_dcb_check_config(). + */ +s32 ixgbe_dcb_calculate_tc_credits(struct ixgbe_hw *hw, + struct ixgbe_dcb_config *dcb_config, + int max_frame, u8 direction) +{ + struct tc_bw_alloc *p; + int min_credit; + int min_multiplier; + int min_percent = 100; + /* Initialization values default for Tx settings */ + u32 credit_refill = 0; + u32 credit_max = 0; + u16 link_percentage = 0; + u8 bw_percent = 0; + u8 i; + + if (!dcb_config) + return DCB_ERR_CONFIG; + + min_credit = ((max_frame / 2) + DCB_CREDIT_QUANTUM - 1) / + DCB_CREDIT_QUANTUM; + + /* Find smallest link percentage */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + p = &dcb_config->tc_config[i].path[direction]; + bw_percent = dcb_config->bw_percentage[direction][p->bwg_id]; + link_percentage = p->bwg_percent; + + link_percentage = (link_percentage * bw_percent) / 100; + + if (link_percentage && link_percentage < min_percent) + min_percent = link_percentage; + } + + /* + * The ratio between traffic classes will control the bandwidth + * percentages seen on the wire. To calculate this ratio we use + * a multiplier. It is required that the refill credits must be + * larger than the max frame size so here we find the smallest + * multiplier that will allow all bandwidth percentages to be + * greater than the max frame size. + */ + min_multiplier = (min_credit / min_percent) + 1; + + /* Find out the link percentage for each TC first */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + p = &dcb_config->tc_config[i].path[direction]; + bw_percent = dcb_config->bw_percentage[direction][p->bwg_id]; + + link_percentage = p->bwg_percent; + /* Must be careful of integer division for very small nums */ + link_percentage = (link_percentage * bw_percent) / 100; + if (p->bwg_percent > 0 && link_percentage == 0) + link_percentage = 1; + + /* Save link_percentage for reference */ + p->link_percent = (u8)link_percentage; + + /* Calculate credit refill ratio using multiplier */ + credit_refill = min(link_percentage * min_multiplier, + MAX_CREDIT_REFILL); + + /* Refill at least minimum credit */ + if (credit_refill < min_credit) + credit_refill = min_credit; + + p->data_credits_refill = (u16)credit_refill; + + /* Calculate maximum credit for the TC */ + credit_max = (link_percentage * MAX_CREDIT) / 100; + + /* + * Adjustment based on rule checking, if the percentage + * of a TC is too small, the maximum credit may not be + * enough to send out a jumbo frame in data plane arbitration. + */ + if (credit_max < min_credit) + credit_max = min_credit; + + if (direction == DCB_TX_CONFIG) { + /* + * Adjustment based on rule checking, if the + * percentage of a TC is too small, the maximum + * credit may not be enough to send out a TSO + * packet in descriptor plane arbitration. + */ + if ((hw->mac.type == ixgbe_mac_82598EB) && + credit_max && + (credit_max < MINIMUM_CREDIT_FOR_TSO)) + credit_max = MINIMUM_CREDIT_FOR_TSO; + + dcb_config->tc_config[i].desc_credits_max = + (u16)credit_max; + } + + p->data_credits_max = (u16)credit_max; + } + + return 0; +} + +void ixgbe_dcb_unpack_pfc(struct ixgbe_dcb_config *cfg, u8 *pfc_en) +{ + struct tc_configuration *tc_config = &cfg->tc_config[0]; + int tc; + + for (*pfc_en = 0, tc = 0; tc < MAX_TRAFFIC_CLASS; tc++) { + if (tc_config[tc].dcb_pfc != pfc_disabled) + *pfc_en |= BIT(tc); + } +} + +void ixgbe_dcb_unpack_refill(struct ixgbe_dcb_config *cfg, int direction, + u16 *refill) +{ + struct tc_configuration *tc_config = &cfg->tc_config[0]; + int tc; + + for (tc = 0; tc < MAX_TRAFFIC_CLASS; tc++) + refill[tc] = tc_config[tc].path[direction].data_credits_refill; +} + +void ixgbe_dcb_unpack_max(struct ixgbe_dcb_config *cfg, u16 *max) +{ + struct tc_configuration *tc_config = &cfg->tc_config[0]; + int tc; + + for (tc = 0; tc < MAX_TRAFFIC_CLASS; tc++) + max[tc] = tc_config[tc].desc_credits_max; +} + +void ixgbe_dcb_unpack_bwgid(struct ixgbe_dcb_config *cfg, int direction, + u8 *bwgid) +{ + struct tc_configuration *tc_config = &cfg->tc_config[0]; + int tc; + + for (tc = 0; tc < MAX_TRAFFIC_CLASS; tc++) + bwgid[tc] = tc_config[tc].path[direction].bwg_id; +} + +void ixgbe_dcb_unpack_prio(struct ixgbe_dcb_config *cfg, int direction, + u8 *ptype) +{ + struct tc_configuration *tc_config = &cfg->tc_config[0]; + int tc; + + for (tc = 0; tc < MAX_TRAFFIC_CLASS; tc++) + ptype[tc] = tc_config[tc].path[direction].prio_type; +} + +u8 ixgbe_dcb_get_tc_from_up(struct ixgbe_dcb_config *cfg, int direction, u8 up) +{ + struct tc_configuration *tc_config = &cfg->tc_config[0]; + u8 prio_mask = BIT(up); + u8 tc = cfg->num_tcs.pg_tcs; + + /* If tc is 0 then DCB is likely not enabled or supported */ + if (!tc) + return 0; + + /* + * Test from maximum TC to 1 and report the first match we find. If + * we find no match we can assume that the TC is 0 since the TC must + * be set for all user priorities + */ + for (tc--; tc; tc--) { + if (prio_mask & tc_config[tc].path[direction].up_to_tc_bitmap) + break; + } + + return tc; +} + +void ixgbe_dcb_unpack_map(struct ixgbe_dcb_config *cfg, int direction, u8 *map) +{ + u8 up; + + for (up = 0; up < MAX_USER_PRIORITY; up++) + map[up] = ixgbe_dcb_get_tc_from_up(cfg, direction, up); +} + +/** + * ixgbe_dcb_hw_config - Config and enable DCB + * @hw: pointer to hardware structure + * @dcb_config: pointer to ixgbe_dcb_config structure + * + * Configure dcb settings and enable dcb mode. + */ +s32 ixgbe_dcb_hw_config(struct ixgbe_hw *hw, + struct ixgbe_dcb_config *dcb_config) +{ + u8 pfc_en; + u8 ptype[MAX_TRAFFIC_CLASS]; + u8 bwgid[MAX_TRAFFIC_CLASS]; + u8 prio_tc[MAX_TRAFFIC_CLASS]; + u16 refill[MAX_TRAFFIC_CLASS]; + u16 max[MAX_TRAFFIC_CLASS]; + + /* Unpack CEE standard containers */ + ixgbe_dcb_unpack_pfc(dcb_config, &pfc_en); + ixgbe_dcb_unpack_refill(dcb_config, DCB_TX_CONFIG, refill); + ixgbe_dcb_unpack_max(dcb_config, max); + ixgbe_dcb_unpack_bwgid(dcb_config, DCB_TX_CONFIG, bwgid); + ixgbe_dcb_unpack_prio(dcb_config, DCB_TX_CONFIG, ptype); + ixgbe_dcb_unpack_map(dcb_config, DCB_TX_CONFIG, prio_tc); + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + return ixgbe_dcb_hw_config_82598(hw, pfc_en, refill, max, + bwgid, ptype); + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + return ixgbe_dcb_hw_config_82599(hw, pfc_en, refill, max, + bwgid, ptype, prio_tc); + default: + break; + } + return 0; +} + +/* Helper routines to abstract HW specifics from DCB netlink ops */ +s32 ixgbe_dcb_hw_pfc_config(struct ixgbe_hw *hw, u8 pfc_en, u8 *prio_tc) +{ + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + return ixgbe_dcb_config_pfc_82598(hw, pfc_en); + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + return ixgbe_dcb_config_pfc_82599(hw, pfc_en, prio_tc); + default: + break; + } + return -EINVAL; +} + +s32 ixgbe_dcb_hw_ets(struct ixgbe_hw *hw, struct ieee_ets *ets, int max_frame) +{ + __u16 refill[IEEE_8021QAZ_MAX_TCS], max[IEEE_8021QAZ_MAX_TCS]; + __u8 prio_type[IEEE_8021QAZ_MAX_TCS]; + int i; + + /* naively give each TC a bwg to map onto CEE hardware */ + __u8 bwg_id[IEEE_8021QAZ_MAX_TCS] = {0, 1, 2, 3, 4, 5, 6, 7}; + + /* Map TSA onto CEE prio type */ + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + switch (ets->tc_tsa[i]) { + case IEEE_8021QAZ_TSA_STRICT: + prio_type[i] = 2; + break; + case IEEE_8021QAZ_TSA_ETS: + prio_type[i] = 0; + break; + default: + /* Hardware only supports priority strict or + * ETS transmission selection algorithms if + * we receive some other value from dcbnl + * throw an error + */ + return -EINVAL; + } + } + + ixgbe_ieee_credits(ets->tc_tx_bw, refill, max, max_frame); + return ixgbe_dcb_hw_ets_config(hw, refill, max, + bwg_id, prio_type, ets->prio_tc); +} + +s32 ixgbe_dcb_hw_ets_config(struct ixgbe_hw *hw, + u16 *refill, u16 *max, u8 *bwg_id, + u8 *prio_type, u8 *prio_tc) +{ + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + ixgbe_dcb_config_rx_arbiter_82598(hw, refill, max, + prio_type); + ixgbe_dcb_config_tx_desc_arbiter_82598(hw, refill, max, + bwg_id, prio_type); + ixgbe_dcb_config_tx_data_arbiter_82598(hw, refill, max, + bwg_id, prio_type); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + ixgbe_dcb_config_rx_arbiter_82599(hw, refill, max, + bwg_id, prio_type, prio_tc); + ixgbe_dcb_config_tx_desc_arbiter_82599(hw, refill, max, + bwg_id, prio_type); + ixgbe_dcb_config_tx_data_arbiter_82599(hw, refill, max, bwg_id, + prio_type, prio_tc); + break; + default: + break; + } + return 0; +} + +static void ixgbe_dcb_read_rtrup2tc_82599(struct ixgbe_hw *hw, u8 *map) +{ + u32 reg, i; + + reg = IXGBE_READ_REG(hw, IXGBE_RTRUP2TC); + for (i = 0; i < MAX_USER_PRIORITY; i++) + map[i] = IXGBE_RTRUP2TC_UP_MASK & + (reg >> (i * IXGBE_RTRUP2TC_UP_SHIFT)); +} + +void ixgbe_dcb_read_rtrup2tc(struct ixgbe_hw *hw, u8 *map) +{ + switch (hw->mac.type) { + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + ixgbe_dcb_read_rtrup2tc_82599(hw, map); + break; + default: + break; + } +} diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h new file mode 100644 index 000000000..60cd5863b --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h @@ -0,0 +1,146 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#ifndef _DCB_CONFIG_H_ +#define _DCB_CONFIG_H_ + +#include <linux/dcbnl.h> +#include "ixgbe_type.h" + +/* DCB data structures */ + +#define IXGBE_MAX_PACKET_BUFFERS 8 +#define MAX_USER_PRIORITY 8 +#define MAX_BW_GROUP 8 +#define BW_PERCENT 100 + +#define DCB_TX_CONFIG 0 +#define DCB_RX_CONFIG 1 + +/* DCB error Codes */ +#define DCB_SUCCESS 0 +#define DCB_ERR_CONFIG -1 +#define DCB_ERR_PARAM -2 + +/* Transmit and receive Errors */ +/* Error in bandwidth group allocation */ +#define DCB_ERR_BW_GROUP -3 +/* Error in traffic class bandwidth allocation */ +#define DCB_ERR_TC_BW -4 +/* Traffic class has both link strict and group strict enabled */ +#define DCB_ERR_LS_GS -5 +/* Link strict traffic class has non zero bandwidth */ +#define DCB_ERR_LS_BW_NONZERO -6 +/* Link strict bandwidth group has non zero bandwidth */ +#define DCB_ERR_LS_BWG_NONZERO -7 +/* Traffic class has zero bandwidth */ +#define DCB_ERR_TC_BW_ZERO -8 + +#define DCB_NOT_IMPLEMENTED 0x7FFFFFFF + +struct dcb_pfc_tc_debug { + u8 tc; + u8 pause_status; + u64 pause_quanta; +}; + +enum strict_prio_type { + prio_none = 0, + prio_group, + prio_link +}; + +/* DCB capability definitions */ +#define IXGBE_DCB_PG_SUPPORT 0x00000001 +#define IXGBE_DCB_PFC_SUPPORT 0x00000002 +#define IXGBE_DCB_BCN_SUPPORT 0x00000004 +#define IXGBE_DCB_UP2TC_SUPPORT 0x00000008 +#define IXGBE_DCB_GSP_SUPPORT 0x00000010 + +#define IXGBE_DCB_8_TC_SUPPORT 0x80 + +struct dcb_support { + /* DCB capabilities */ + u32 capabilities; + + /* Each bit represents a number of TCs configurable in the hw. + * If 8 traffic classes can be configured, the value is 0x80. + */ + u8 traffic_classes; + u8 pfc_traffic_classes; +}; + +/* Traffic class bandwidth allocation per direction */ +struct tc_bw_alloc { + u8 bwg_id; /* Bandwidth Group (BWG) ID */ + u8 bwg_percent; /* % of BWG's bandwidth */ + u8 link_percent; /* % of link bandwidth */ + u8 up_to_tc_bitmap; /* User Priority to Traffic Class mapping */ + u16 data_credits_refill; /* Credit refill amount in 64B granularity */ + u16 data_credits_max; /* Max credits for a configured packet buffer + * in 64B granularity.*/ + enum strict_prio_type prio_type; /* Link or Group Strict Priority */ +}; + +enum dcb_pfc_type { + pfc_disabled = 0, + pfc_enabled_full, + pfc_enabled_tx, + pfc_enabled_rx +}; + +/* Traffic class configuration */ +struct tc_configuration { + struct tc_bw_alloc path[2]; /* One each for Tx/Rx */ + enum dcb_pfc_type dcb_pfc; /* Class based flow control setting */ + + u16 desc_credits_max; /* For Tx Descriptor arbitration */ + u8 tc; /* Traffic class (TC) */ +}; + +struct dcb_num_tcs { + u8 pg_tcs; + u8 pfc_tcs; +}; + +struct ixgbe_dcb_config { + struct dcb_support support; + struct dcb_num_tcs num_tcs; + struct tc_configuration tc_config[MAX_TRAFFIC_CLASS]; + u8 bw_percentage[2][MAX_BW_GROUP]; /* One each for Tx/Rx */ + bool pfc_mode_enable; + + u32 dcb_cfg_version; /* Not used...OS-specific? */ + u32 link_speed; /* For bandwidth allocation validation purpose */ +}; + +/* DCB driver APIs */ +void ixgbe_dcb_unpack_pfc(struct ixgbe_dcb_config *cfg, u8 *pfc_en); +void ixgbe_dcb_unpack_refill(struct ixgbe_dcb_config *, int, u16 *); +void ixgbe_dcb_unpack_max(struct ixgbe_dcb_config *, u16 *); +void ixgbe_dcb_unpack_bwgid(struct ixgbe_dcb_config *, int, u8 *); +void ixgbe_dcb_unpack_prio(struct ixgbe_dcb_config *, int, u8 *); +void ixgbe_dcb_unpack_map(struct ixgbe_dcb_config *, int, u8 *); +u8 ixgbe_dcb_get_tc_from_up(struct ixgbe_dcb_config *, int, u8); + +/* DCB credits calculation */ +s32 ixgbe_dcb_calculate_tc_credits(struct ixgbe_hw *, + struct ixgbe_dcb_config *, int, u8); + +/* DCB hw initialization */ +s32 ixgbe_dcb_hw_ets(struct ixgbe_hw *hw, struct ieee_ets *ets, int max); +s32 ixgbe_dcb_hw_ets_config(struct ixgbe_hw *hw, u16 *refill, u16 *max, + u8 *bwg_id, u8 *prio_type, u8 *tc_prio); +s32 ixgbe_dcb_hw_pfc_config(struct ixgbe_hw *hw, u8 pfc_en, u8 *tc_prio); +s32 ixgbe_dcb_hw_config(struct ixgbe_hw *, struct ixgbe_dcb_config *); + +void ixgbe_dcb_read_rtrup2tc(struct ixgbe_hw *hw, u8 *map); + +/* DCB definitions for credit calculation */ +#define DCB_CREDIT_QUANTUM 64 /* DCB Quantum */ +#define MAX_CREDIT_REFILL 511 /* 0x1FF * 64B = 32704B */ +#define DCB_MAX_TSO_SIZE (32*1024) /* MAX TSO packet size supported in DCB mode */ +#define MINIMUM_CREDIT_FOR_TSO (DCB_MAX_TSO_SIZE/64 + 1) /* 513 for 32KB TSO packet */ +#define MAX_CREDIT 4095 /* Maximum credit supported: 256KB * 1204 / 64B */ + +#endif /* _DCB_CONFIG_H */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c new file mode 100644 index 000000000..379ae747c --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c @@ -0,0 +1,275 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#include "ixgbe.h" +#include "ixgbe_type.h" +#include "ixgbe_dcb.h" +#include "ixgbe_dcb_82598.h" + +/** + * ixgbe_dcb_config_rx_arbiter_82598 - Config Rx data arbiter + * @hw: pointer to hardware structure + * @refill: refill credits index by traffic class + * @max: max credits index by traffic class + * @prio_type: priority type indexed by traffic class + * + * Configure Rx Data Arbiter and credits for each traffic class. + */ +s32 ixgbe_dcb_config_rx_arbiter_82598(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *prio_type) +{ + u32 reg = 0; + u32 credit_refill = 0; + u32 credit_max = 0; + u8 i = 0; + + reg = IXGBE_READ_REG(hw, IXGBE_RUPPBMR) | IXGBE_RUPPBMR_MQA; + IXGBE_WRITE_REG(hw, IXGBE_RUPPBMR, reg); + + reg = IXGBE_READ_REG(hw, IXGBE_RMCS); + /* Enable Arbiter */ + reg &= ~IXGBE_RMCS_ARBDIS; + /* Enable Receive Recycle within the BWG */ + reg |= IXGBE_RMCS_RRM; + /* Enable Deficit Fixed Priority arbitration*/ + reg |= IXGBE_RMCS_DFP; + + IXGBE_WRITE_REG(hw, IXGBE_RMCS, reg); + + /* Configure traffic class credits and priority */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + credit_refill = refill[i]; + credit_max = max[i]; + + reg = credit_refill | (credit_max << IXGBE_RT2CR_MCL_SHIFT); + + if (prio_type[i] == prio_link) + reg |= IXGBE_RT2CR_LSP; + + IXGBE_WRITE_REG(hw, IXGBE_RT2CR(i), reg); + } + + reg = IXGBE_READ_REG(hw, IXGBE_RDRXCTL); + reg |= IXGBE_RDRXCTL_RDMTS_1_2; + reg |= IXGBE_RDRXCTL_MPBEN; + reg |= IXGBE_RDRXCTL_MCEN; + IXGBE_WRITE_REG(hw, IXGBE_RDRXCTL, reg); + + reg = IXGBE_READ_REG(hw, IXGBE_RXCTRL); + /* Make sure there is enough descriptors before arbitration */ + reg &= ~IXGBE_RXCTRL_DMBYPS; + IXGBE_WRITE_REG(hw, IXGBE_RXCTRL, reg); + + return 0; +} + +/** + * ixgbe_dcb_config_tx_desc_arbiter_82598 - Config Tx Desc. arbiter + * @hw: pointer to hardware structure + * @refill: refill credits index by traffic class + * @max: max credits index by traffic class + * @bwg_id: bandwidth grouping indexed by traffic class + * @prio_type: priority type indexed by traffic class + * + * Configure Tx Descriptor Arbiter and credits for each traffic class. + */ +s32 ixgbe_dcb_config_tx_desc_arbiter_82598(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *bwg_id, + u8 *prio_type) +{ + u32 reg, max_credits; + u8 i; + + reg = IXGBE_READ_REG(hw, IXGBE_DPMCS); + + /* Enable arbiter */ + reg &= ~IXGBE_DPMCS_ARBDIS; + reg |= IXGBE_DPMCS_TSOEF; + + /* Configure Max TSO packet size 34KB including payload and headers */ + reg |= (0x4 << IXGBE_DPMCS_MTSOS_SHIFT); + + IXGBE_WRITE_REG(hw, IXGBE_DPMCS, reg); + + /* Configure traffic class credits and priority */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + max_credits = max[i]; + reg = max_credits << IXGBE_TDTQ2TCCR_MCL_SHIFT; + reg |= refill[i]; + reg |= (u32)(bwg_id[i]) << IXGBE_TDTQ2TCCR_BWG_SHIFT; + + if (prio_type[i] == prio_group) + reg |= IXGBE_TDTQ2TCCR_GSP; + + if (prio_type[i] == prio_link) + reg |= IXGBE_TDTQ2TCCR_LSP; + + IXGBE_WRITE_REG(hw, IXGBE_TDTQ2TCCR(i), reg); + } + + return 0; +} + +/** + * ixgbe_dcb_config_tx_data_arbiter_82598 - Config Tx data arbiter + * @hw: pointer to hardware structure + * @refill: refill credits index by traffic class + * @max: max credits index by traffic class + * @bwg_id: bandwidth grouping indexed by traffic class + * @prio_type: priority type indexed by traffic class + * + * Configure Tx Data Arbiter and credits for each traffic class. + */ +s32 ixgbe_dcb_config_tx_data_arbiter_82598(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *bwg_id, + u8 *prio_type) +{ + u32 reg; + u8 i; + + reg = IXGBE_READ_REG(hw, IXGBE_PDPMCS); + /* Enable Data Plane Arbiter */ + reg &= ~IXGBE_PDPMCS_ARBDIS; + /* Enable DFP and Transmit Recycle Mode */ + reg |= (IXGBE_PDPMCS_TPPAC | IXGBE_PDPMCS_TRM); + + IXGBE_WRITE_REG(hw, IXGBE_PDPMCS, reg); + + /* Configure traffic class credits and priority */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + reg = refill[i]; + reg |= (u32)(max[i]) << IXGBE_TDPT2TCCR_MCL_SHIFT; + reg |= (u32)(bwg_id[i]) << IXGBE_TDPT2TCCR_BWG_SHIFT; + + if (prio_type[i] == prio_group) + reg |= IXGBE_TDPT2TCCR_GSP; + + if (prio_type[i] == prio_link) + reg |= IXGBE_TDPT2TCCR_LSP; + + IXGBE_WRITE_REG(hw, IXGBE_TDPT2TCCR(i), reg); + } + + /* Enable Tx packet buffer division */ + reg = IXGBE_READ_REG(hw, IXGBE_DTXCTL); + reg |= IXGBE_DTXCTL_ENDBUBD; + IXGBE_WRITE_REG(hw, IXGBE_DTXCTL, reg); + + return 0; +} + +/** + * ixgbe_dcb_config_pfc_82598 - Config priority flow control + * @hw: pointer to hardware structure + * @pfc_en: enabled pfc bitmask + * + * Configure Priority Flow Control for each traffic class. + */ +s32 ixgbe_dcb_config_pfc_82598(struct ixgbe_hw *hw, u8 pfc_en) +{ + u32 fcrtl, reg; + u8 i; + + /* Enable Transmit Priority Flow Control */ + reg = IXGBE_READ_REG(hw, IXGBE_RMCS); + reg &= ~IXGBE_RMCS_TFCE_802_3X; + reg |= IXGBE_RMCS_TFCE_PRIORITY; + IXGBE_WRITE_REG(hw, IXGBE_RMCS, reg); + + /* Enable Receive Priority Flow Control */ + reg = IXGBE_READ_REG(hw, IXGBE_FCTRL); + reg &= ~(IXGBE_FCTRL_RPFCE | IXGBE_FCTRL_RFCE); + + if (pfc_en) + reg |= IXGBE_FCTRL_RPFCE; + + IXGBE_WRITE_REG(hw, IXGBE_FCTRL, reg); + + /* Configure PFC Tx thresholds per TC */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + if (!(pfc_en & BIT(i))) { + IXGBE_WRITE_REG(hw, IXGBE_FCRTL(i), 0); + IXGBE_WRITE_REG(hw, IXGBE_FCRTH(i), 0); + continue; + } + + fcrtl = (hw->fc.low_water[i] << 10) | IXGBE_FCRTL_XONE; + reg = (hw->fc.high_water[i] << 10) | IXGBE_FCRTH_FCEN; + IXGBE_WRITE_REG(hw, IXGBE_FCRTL(i), fcrtl); + IXGBE_WRITE_REG(hw, IXGBE_FCRTH(i), reg); + } + + /* Configure pause time */ + reg = hw->fc.pause_time * 0x00010001; + for (i = 0; i < (MAX_TRAFFIC_CLASS / 2); i++) + IXGBE_WRITE_REG(hw, IXGBE_FCTTV(i), reg); + + /* Configure flow control refresh threshold value */ + IXGBE_WRITE_REG(hw, IXGBE_FCRTV, hw->fc.pause_time / 2); + + + return 0; +} + +/** + * ixgbe_dcb_config_tc_stats_82598 - Configure traffic class statistics + * @hw: pointer to hardware structure + * + * Configure queue statistics registers, all queues belonging to same traffic + * class uses a single set of queue statistics counters. + */ +static s32 ixgbe_dcb_config_tc_stats_82598(struct ixgbe_hw *hw) +{ + u32 reg = 0; + u8 i = 0; + u8 j = 0; + + /* Receive Queues stats setting - 8 queues per statistics reg */ + for (i = 0, j = 0; i < 15 && j < 8; i = i + 2, j++) { + reg = IXGBE_READ_REG(hw, IXGBE_RQSMR(i)); + reg |= ((0x1010101) * j); + IXGBE_WRITE_REG(hw, IXGBE_RQSMR(i), reg); + reg = IXGBE_READ_REG(hw, IXGBE_RQSMR(i + 1)); + reg |= ((0x1010101) * j); + IXGBE_WRITE_REG(hw, IXGBE_RQSMR(i + 1), reg); + } + /* Transmit Queues stats setting - 4 queues per statistics reg */ + for (i = 0; i < 8; i++) { + reg = IXGBE_READ_REG(hw, IXGBE_TQSMR(i)); + reg |= ((0x1010101) * i); + IXGBE_WRITE_REG(hw, IXGBE_TQSMR(i), reg); + } + + return 0; +} + +/** + * ixgbe_dcb_hw_config_82598 - Config and enable DCB + * @hw: pointer to hardware structure + * @pfc_en: enabled pfc bitmask + * @refill: refill credits index by traffic class + * @max: max credits index by traffic class + * @bwg_id: bandwidth grouping indexed by traffic class + * @prio_type: priority type indexed by traffic class + * + * Configure dcb settings and enable dcb mode. + */ +s32 ixgbe_dcb_hw_config_82598(struct ixgbe_hw *hw, u8 pfc_en, u16 *refill, + u16 *max, u8 *bwg_id, u8 *prio_type) +{ + ixgbe_dcb_config_rx_arbiter_82598(hw, refill, max, prio_type); + ixgbe_dcb_config_tx_desc_arbiter_82598(hw, refill, max, + bwg_id, prio_type); + ixgbe_dcb_config_tx_data_arbiter_82598(hw, refill, max, + bwg_id, prio_type); + ixgbe_dcb_config_pfc_82598(hw, pfc_en); + ixgbe_dcb_config_tc_stats_82598(hw); + + return 0; +} diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.h new file mode 100644 index 000000000..fdca41abb --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#ifndef _DCB_82598_CONFIG_H_ +#define _DCB_82598_CONFIG_H_ + +/* DCB register definitions */ + +#define IXGBE_DPMCS_MTSOS_SHIFT 16 +#define IXGBE_DPMCS_TDPAC 0x00000001 /* 0 Round Robin, 1 DFP - Deficit Fixed Priority */ +#define IXGBE_DPMCS_TRM 0x00000010 /* Transmit Recycle Mode */ +#define IXGBE_DPMCS_ARBDIS 0x00000040 /* DCB arbiter disable */ +#define IXGBE_DPMCS_TSOEF 0x00080000 /* TSO Expand Factor: 0=x4, 1=x2 */ + +#define IXGBE_RUPPBMR_MQA 0x80000000 /* Enable UP to queue mapping */ + +#define IXGBE_RT2CR_MCL_SHIFT 12 /* Offset to Max Credit Limit setting */ +#define IXGBE_RT2CR_LSP 0x80000000 /* LSP enable bit */ + +#define IXGBE_RDRXCTL_MPBEN 0x00000010 /* DMA config for multiple packet buffers enable */ +#define IXGBE_RDRXCTL_MCEN 0x00000040 /* DMA config for multiple cores (RSS) enable */ + +#define IXGBE_TDTQ2TCCR_MCL_SHIFT 12 +#define IXGBE_TDTQ2TCCR_BWG_SHIFT 9 +#define IXGBE_TDTQ2TCCR_GSP 0x40000000 +#define IXGBE_TDTQ2TCCR_LSP 0x80000000 + +#define IXGBE_TDPT2TCCR_MCL_SHIFT 12 +#define IXGBE_TDPT2TCCR_BWG_SHIFT 9 +#define IXGBE_TDPT2TCCR_GSP 0x40000000 +#define IXGBE_TDPT2TCCR_LSP 0x80000000 + +#define IXGBE_PDPMCS_TPPAC 0x00000020 /* 0 Round Robin, 1 for DFP - Deficit Fixed Priority */ +#define IXGBE_PDPMCS_ARBDIS 0x00000040 /* Arbiter disable */ +#define IXGBE_PDPMCS_TRM 0x00000100 /* Transmit Recycle Mode enable */ + +#define IXGBE_DTXCTL_ENDBUBD 0x00000004 /* Enable DBU buffer division */ + +#define IXGBE_TXPBSIZE_40KB 0x0000A000 /* 40KB Packet Buffer */ +#define IXGBE_RXPBSIZE_48KB 0x0000C000 /* 48KB Packet Buffer */ +#define IXGBE_RXPBSIZE_64KB 0x00010000 /* 64KB Packet Buffer */ +#define IXGBE_RXPBSIZE_80KB 0x00014000 /* 80KB Packet Buffer */ + +#define IXGBE_RDRXCTL_RDMTS_1_2 0x00000000 + +/* DCB hardware-specific driver APIs */ + +/* DCB PFC functions */ +s32 ixgbe_dcb_config_pfc_82598(struct ixgbe_hw *, u8 pfc_en); + +/* DCB hw initialization */ +s32 ixgbe_dcb_config_rx_arbiter_82598(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *prio_type); + +s32 ixgbe_dcb_config_tx_desc_arbiter_82598(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *bwg_id, + u8 *prio_type); + +s32 ixgbe_dcb_config_tx_data_arbiter_82598(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *bwg_id, + u8 *prio_type); + +s32 ixgbe_dcb_hw_config_82598(struct ixgbe_hw *hw, u8 pfc_en, u16 *refill, + u16 *max, u8 *bwg_id, u8 *prio_type); + +#endif /* _DCB_82598_CONFIG_H */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c new file mode 100644 index 000000000..794884984 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c @@ -0,0 +1,347 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#include "ixgbe.h" +#include "ixgbe_type.h" +#include "ixgbe_dcb.h" +#include "ixgbe_dcb_82599.h" + +/** + * ixgbe_dcb_config_rx_arbiter_82599 - Config Rx Data arbiter + * @hw: pointer to hardware structure + * @refill: refill credits index by traffic class + * @max: max credits index by traffic class + * @bwg_id: bandwidth grouping indexed by traffic class + * @prio_type: priority type indexed by traffic class + * @prio_tc: priority to tc assignments indexed by priority + * + * Configure Rx Packet Arbiter and credits for each traffic class. + */ +s32 ixgbe_dcb_config_rx_arbiter_82599(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *bwg_id, + u8 *prio_type, + u8 *prio_tc) +{ + u32 reg = 0; + u32 credit_refill = 0; + u32 credit_max = 0; + u8 i = 0; + + /* + * Disable the arbiter before changing parameters + * (always enable recycle mode; WSP) + */ + reg = IXGBE_RTRPCS_RRM | IXGBE_RTRPCS_RAC | IXGBE_RTRPCS_ARBDIS; + IXGBE_WRITE_REG(hw, IXGBE_RTRPCS, reg); + + /* Map all traffic classes to their UP */ + reg = 0; + for (i = 0; i < MAX_USER_PRIORITY; i++) + reg |= (prio_tc[i] << (i * IXGBE_RTRUP2TC_UP_SHIFT)); + IXGBE_WRITE_REG(hw, IXGBE_RTRUP2TC, reg); + + /* Configure traffic class credits and priority */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + credit_refill = refill[i]; + credit_max = max[i]; + reg = credit_refill | (credit_max << IXGBE_RTRPT4C_MCL_SHIFT); + + reg |= (u32)(bwg_id[i]) << IXGBE_RTRPT4C_BWG_SHIFT; + + if (prio_type[i] == prio_link) + reg |= IXGBE_RTRPT4C_LSP; + + IXGBE_WRITE_REG(hw, IXGBE_RTRPT4C(i), reg); + } + + /* + * Configure Rx packet plane (recycle mode; WSP) and + * enable arbiter + */ + reg = IXGBE_RTRPCS_RRM | IXGBE_RTRPCS_RAC; + IXGBE_WRITE_REG(hw, IXGBE_RTRPCS, reg); + + return 0; +} + +/** + * ixgbe_dcb_config_tx_desc_arbiter_82599 - Config Tx Desc. arbiter + * @hw: pointer to hardware structure + * @refill: refill credits index by traffic class + * @max: max credits index by traffic class + * @bwg_id: bandwidth grouping indexed by traffic class + * @prio_type: priority type indexed by traffic class + * + * Configure Tx Descriptor Arbiter and credits for each traffic class. + */ +s32 ixgbe_dcb_config_tx_desc_arbiter_82599(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *bwg_id, + u8 *prio_type) +{ + u32 reg, max_credits; + u8 i; + + /* Clear the per-Tx queue credits; we use per-TC instead */ + for (i = 0; i < 128; i++) { + IXGBE_WRITE_REG(hw, IXGBE_RTTDQSEL, i); + IXGBE_WRITE_REG(hw, IXGBE_RTTDT1C, 0); + } + + /* Configure traffic class credits and priority */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + max_credits = max[i]; + reg = max_credits << IXGBE_RTTDT2C_MCL_SHIFT; + reg |= refill[i]; + reg |= (u32)(bwg_id[i]) << IXGBE_RTTDT2C_BWG_SHIFT; + + if (prio_type[i] == prio_group) + reg |= IXGBE_RTTDT2C_GSP; + + if (prio_type[i] == prio_link) + reg |= IXGBE_RTTDT2C_LSP; + + IXGBE_WRITE_REG(hw, IXGBE_RTTDT2C(i), reg); + } + + /* + * Configure Tx descriptor plane (recycle mode; WSP) and + * enable arbiter + */ + reg = IXGBE_RTTDCS_TDPAC | IXGBE_RTTDCS_TDRM; + IXGBE_WRITE_REG(hw, IXGBE_RTTDCS, reg); + + return 0; +} + +/** + * ixgbe_dcb_config_tx_data_arbiter_82599 - Config Tx Data arbiter + * @hw: pointer to hardware structure + * @refill: refill credits index by traffic class + * @max: max credits index by traffic class + * @bwg_id: bandwidth grouping indexed by traffic class + * @prio_type: priority type indexed by traffic class + * @prio_tc: priority to tc assignments indexed by priority + * + * Configure Tx Packet Arbiter and credits for each traffic class. + */ +s32 ixgbe_dcb_config_tx_data_arbiter_82599(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *bwg_id, + u8 *prio_type, + u8 *prio_tc) +{ + u32 reg; + u8 i; + + /* + * Disable the arbiter before changing parameters + * (always enable recycle mode; SP; arb delay) + */ + reg = IXGBE_RTTPCS_TPPAC | IXGBE_RTTPCS_TPRM | + (IXGBE_RTTPCS_ARBD_DCB << IXGBE_RTTPCS_ARBD_SHIFT) | + IXGBE_RTTPCS_ARBDIS; + IXGBE_WRITE_REG(hw, IXGBE_RTTPCS, reg); + + /* Map all traffic classes to their UP */ + reg = 0; + for (i = 0; i < MAX_USER_PRIORITY; i++) + reg |= (prio_tc[i] << (i * IXGBE_RTTUP2TC_UP_SHIFT)); + IXGBE_WRITE_REG(hw, IXGBE_RTTUP2TC, reg); + + /* Configure traffic class credits and priority */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + reg = refill[i]; + reg |= (u32)(max[i]) << IXGBE_RTTPT2C_MCL_SHIFT; + reg |= (u32)(bwg_id[i]) << IXGBE_RTTPT2C_BWG_SHIFT; + + if (prio_type[i] == prio_group) + reg |= IXGBE_RTTPT2C_GSP; + + if (prio_type[i] == prio_link) + reg |= IXGBE_RTTPT2C_LSP; + + IXGBE_WRITE_REG(hw, IXGBE_RTTPT2C(i), reg); + } + + /* + * Configure Tx packet plane (recycle mode; SP; arb delay) and + * enable arbiter + */ + reg = IXGBE_RTTPCS_TPPAC | IXGBE_RTTPCS_TPRM | + (IXGBE_RTTPCS_ARBD_DCB << IXGBE_RTTPCS_ARBD_SHIFT); + IXGBE_WRITE_REG(hw, IXGBE_RTTPCS, reg); + + return 0; +} + +/** + * ixgbe_dcb_config_pfc_82599 - Configure priority flow control + * @hw: pointer to hardware structure + * @pfc_en: enabled pfc bitmask + * @prio_tc: priority to tc assignments indexed by priority + * + * Configure Priority Flow Control (PFC) for each traffic class. + */ +s32 ixgbe_dcb_config_pfc_82599(struct ixgbe_hw *hw, u8 pfc_en, u8 *prio_tc) +{ + u32 i, j, fcrtl, reg; + u8 max_tc = 0; + + /* Enable Transmit Priority Flow Control */ + IXGBE_WRITE_REG(hw, IXGBE_FCCFG, IXGBE_FCCFG_TFCE_PRIORITY); + + /* Enable Receive Priority Flow Control */ + reg = IXGBE_READ_REG(hw, IXGBE_MFLCN); + reg |= IXGBE_MFLCN_DPF; + + /* + * X540 & X550 supports per TC Rx priority flow control. + * So clear all TCs and only enable those that should be + * enabled. + */ + reg &= ~(IXGBE_MFLCN_RPFCE_MASK | IXGBE_MFLCN_RFCE); + + if (hw->mac.type >= ixgbe_mac_X540) + reg |= pfc_en << IXGBE_MFLCN_RPFCE_SHIFT; + + if (pfc_en) + reg |= IXGBE_MFLCN_RPFCE; + + IXGBE_WRITE_REG(hw, IXGBE_MFLCN, reg); + + for (i = 0; i < MAX_USER_PRIORITY; i++) { + if (prio_tc[i] > max_tc) + max_tc = prio_tc[i]; + } + + + /* Configure PFC Tx thresholds per TC */ + for (i = 0; i <= max_tc; i++) { + int enabled = 0; + + for (j = 0; j < MAX_USER_PRIORITY; j++) { + if ((prio_tc[j] == i) && (pfc_en & BIT(j))) { + enabled = 1; + break; + } + } + + if (enabled) { + reg = (hw->fc.high_water[i] << 10) | IXGBE_FCRTH_FCEN; + fcrtl = (hw->fc.low_water[i] << 10) | IXGBE_FCRTL_XONE; + IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(i), fcrtl); + } else { + /* In order to prevent Tx hangs when the internal Tx + * switch is enabled we must set the high water mark + * to the Rx packet buffer size - 24KB. This allows + * the Tx switch to function even under heavy Rx + * workloads. + */ + reg = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(i)) - 24576; + IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(i), 0); + } + + IXGBE_WRITE_REG(hw, IXGBE_FCRTH_82599(i), reg); + } + + for (; i < MAX_TRAFFIC_CLASS; i++) { + IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(i), 0); + IXGBE_WRITE_REG(hw, IXGBE_FCRTH_82599(i), 0); + } + + /* Configure pause time (2 TCs per register) */ + reg = hw->fc.pause_time * 0x00010001; + for (i = 0; i < (MAX_TRAFFIC_CLASS / 2); i++) + IXGBE_WRITE_REG(hw, IXGBE_FCTTV(i), reg); + + /* Configure flow control refresh threshold value */ + IXGBE_WRITE_REG(hw, IXGBE_FCRTV, hw->fc.pause_time / 2); + + return 0; +} + +/** + * ixgbe_dcb_config_tc_stats_82599 - Config traffic class statistics + * @hw: pointer to hardware structure + * + * Configure queue statistics registers, all queues belonging to same traffic + * class uses a single set of queue statistics counters. + */ +static s32 ixgbe_dcb_config_tc_stats_82599(struct ixgbe_hw *hw) +{ + u32 reg = 0; + u8 i = 0; + + /* + * Receive Queues stats setting + * 32 RQSMR registers, each configuring 4 queues. + * Set all 16 queues of each TC to the same stat + * with TC 'n' going to stat 'n'. + */ + for (i = 0; i < 32; i++) { + reg = 0x01010101 * (i / 4); + IXGBE_WRITE_REG(hw, IXGBE_RQSMR(i), reg); + } + /* + * Transmit Queues stats setting + * 32 TQSM registers, each controlling 4 queues. + * Set all queues of each TC to the same stat + * with TC 'n' going to stat 'n'. + * Tx queues are allocated non-uniformly to TCs: + * 32, 32, 16, 16, 8, 8, 8, 8. + */ + for (i = 0; i < 32; i++) { + if (i < 8) + reg = 0x00000000; + else if (i < 16) + reg = 0x01010101; + else if (i < 20) + reg = 0x02020202; + else if (i < 24) + reg = 0x03030303; + else if (i < 26) + reg = 0x04040404; + else if (i < 28) + reg = 0x05050505; + else if (i < 30) + reg = 0x06060606; + else + reg = 0x07070707; + IXGBE_WRITE_REG(hw, IXGBE_TQSM(i), reg); + } + + return 0; +} + +/** + * ixgbe_dcb_hw_config_82599 - Configure and enable DCB + * @hw: pointer to hardware structure + * @pfc_en: enabled pfc bitmask + * @refill: refill credits index by traffic class + * @max: max credits index by traffic class + * @bwg_id: bandwidth grouping indexed by traffic class + * @prio_type: priority type indexed by traffic class + * @prio_tc: priority to tc assignments indexed by priority + * + * Configure dcb settings and enable dcb mode. + */ +s32 ixgbe_dcb_hw_config_82599(struct ixgbe_hw *hw, u8 pfc_en, u16 *refill, + u16 *max, u8 *bwg_id, u8 *prio_type, u8 *prio_tc) +{ + ixgbe_dcb_config_rx_arbiter_82599(hw, refill, max, bwg_id, + prio_type, prio_tc); + ixgbe_dcb_config_tx_desc_arbiter_82599(hw, refill, max, + bwg_id, prio_type); + ixgbe_dcb_config_tx_data_arbiter_82599(hw, refill, max, + bwg_id, prio_type, prio_tc); + ixgbe_dcb_config_pfc_82599(hw, pfc_en, prio_tc); + ixgbe_dcb_config_tc_stats_82599(hw); + + return 0; +} + diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.h new file mode 100644 index 000000000..c6f084883 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.h @@ -0,0 +1,100 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#ifndef _DCB_82599_CONFIG_H_ +#define _DCB_82599_CONFIG_H_ + +/* DCB register definitions */ +#define IXGBE_RTTDCS_TDPAC 0x00000001 /* 0 Round Robin, + * 1 WSP - Weighted Strict Priority + */ +#define IXGBE_RTTDCS_VMPAC 0x00000002 /* 0 Round Robin, + * 1 WRR - Weighted Round Robin + */ +#define IXGBE_RTTDCS_TDRM 0x00000010 /* Transmit Recycle Mode */ +#define IXGBE_RTTDCS_ARBDIS 0x00000040 /* DCB arbiter disable */ +#define IXGBE_RTTDCS_BDPM 0x00400000 /* Bypass Data Pipe - must clear! */ +#define IXGBE_RTTDCS_BPBFSM 0x00800000 /* Bypass PB Free Space - must + * clear! + */ +#define IXGBE_RTTDCS_SPEED_CHG 0x80000000 /* Link speed change */ + +/* Receive UP2TC mapping */ +#define IXGBE_RTRUP2TC_UP_SHIFT 3 +#define IXGBE_RTRUP2TC_UP_MASK 7 +/* Transmit UP2TC mapping */ +#define IXGBE_RTTUP2TC_UP_SHIFT 3 + +#define IXGBE_RTRPT4C_MCL_SHIFT 12 /* Offset to Max Credit Limit setting */ +#define IXGBE_RTRPT4C_BWG_SHIFT 9 /* Offset to BWG index */ +#define IXGBE_RTRPT4C_GSP 0x40000000 /* GSP enable bit */ +#define IXGBE_RTRPT4C_LSP 0x80000000 /* LSP enable bit */ + +#define IXGBE_RDRXCTL_MPBEN 0x00000010 /* DMA config for multiple packet + * buffers enable + */ +#define IXGBE_RDRXCTL_MCEN 0x00000040 /* DMA config for multiple cores + * (RSS) enable + */ + +/* RTRPCS Bit Masks */ +#define IXGBE_RTRPCS_RRM 0x00000002 /* Receive Recycle Mode enable */ +/* Receive Arbitration Control: 0 Round Robin, 1 DFP */ +#define IXGBE_RTRPCS_RAC 0x00000004 +#define IXGBE_RTRPCS_ARBDIS 0x00000040 /* Arbitration disable bit */ + +/* RTTDT2C Bit Masks */ +#define IXGBE_RTTDT2C_MCL_SHIFT 12 +#define IXGBE_RTTDT2C_BWG_SHIFT 9 +#define IXGBE_RTTDT2C_GSP 0x40000000 +#define IXGBE_RTTDT2C_LSP 0x80000000 + +#define IXGBE_RTTPT2C_MCL_SHIFT 12 +#define IXGBE_RTTPT2C_BWG_SHIFT 9 +#define IXGBE_RTTPT2C_GSP 0x40000000 +#define IXGBE_RTTPT2C_LSP 0x80000000 + +/* RTTPCS Bit Masks */ +#define IXGBE_RTTPCS_TPPAC 0x00000020 /* 0 Round Robin, + * 1 SP - Strict Priority + */ +#define IXGBE_RTTPCS_ARBDIS 0x00000040 /* Arbiter disable */ +#define IXGBE_RTTPCS_TPRM 0x00000100 /* Transmit Recycle Mode enable */ +#define IXGBE_RTTPCS_ARBD_SHIFT 22 +#define IXGBE_RTTPCS_ARBD_DCB 0x4 /* Arbitration delay in DCB mode */ + +/* SECTXMINIFG DCB */ +#define IXGBE_SECTX_DCB 0x00001F00 /* DCB TX Buffer IFG */ + + +/* DCB hardware-specific driver APIs */ + +/* DCB PFC functions */ +s32 ixgbe_dcb_config_pfc_82599(struct ixgbe_hw *hw, u8 pfc_en, u8 *prio_tc); + +/* DCB hw initialization */ +s32 ixgbe_dcb_config_rx_arbiter_82599(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *bwg_id, + u8 *prio_type, + u8 *prio_tc); + +s32 ixgbe_dcb_config_tx_desc_arbiter_82599(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *bwg_id, + u8 *prio_type); + +s32 ixgbe_dcb_config_tx_data_arbiter_82599(struct ixgbe_hw *hw, + u16 *refill, + u16 *max, + u8 *bwg_id, + u8 *prio_type, + u8 *prio_tc); + +s32 ixgbe_dcb_hw_config_82599(struct ixgbe_hw *hw, u8 pfc_en, u16 *refill, + u16 *max, u8 *bwg_id, u8 *prio_type, + u8 *prio_tc); + +#endif /* _DCB_82599_CONFIG_H */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c new file mode 100644 index 000000000..c00332d2e --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c @@ -0,0 +1,784 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#include "ixgbe.h" +#include <linux/dcbnl.h> +#include "ixgbe_dcb_82598.h" +#include "ixgbe_dcb_82599.h" +#include "ixgbe_sriov.h" + +/* Callbacks for DCB netlink in the kernel */ +#define BIT_DCB_MODE 0x01 +#define BIT_PFC 0x02 +#define BIT_PG_RX 0x04 +#define BIT_PG_TX 0x08 +#define BIT_APP_UPCHG 0x10 +#define BIT_LINKSPEED 0x80 + +/* Responses for the DCB_C_SET_ALL command */ +#define DCB_HW_CHG_RST 0 /* DCB configuration changed with reset */ +#define DCB_NO_HW_CHG 1 /* DCB configuration did not change */ +#define DCB_HW_CHG 2 /* DCB configuration changed, no reset */ + +static int ixgbe_copy_dcb_cfg(struct ixgbe_adapter *adapter, int tc_max) +{ + struct ixgbe_dcb_config *scfg = &adapter->temp_dcb_cfg; + struct ixgbe_dcb_config *dcfg = &adapter->dcb_cfg; + struct tc_configuration *src = NULL; + struct tc_configuration *dst = NULL; + int i, j; + int tx = DCB_TX_CONFIG; + int rx = DCB_RX_CONFIG; + int changes = 0; +#ifdef IXGBE_FCOE + struct dcb_app app = { + .selector = DCB_APP_IDTYPE_ETHTYPE, + .protocol = ETH_P_FCOE, + }; + u8 up = dcb_getapp(adapter->netdev, &app); + + if (up && !(up & BIT(adapter->fcoe.up))) + changes |= BIT_APP_UPCHG; +#endif + + for (i = DCB_PG_ATTR_TC_0; i < tc_max + DCB_PG_ATTR_TC_0; i++) { + src = &scfg->tc_config[i - DCB_PG_ATTR_TC_0]; + dst = &dcfg->tc_config[i - DCB_PG_ATTR_TC_0]; + + if (dst->path[tx].prio_type != src->path[tx].prio_type) { + dst->path[tx].prio_type = src->path[tx].prio_type; + changes |= BIT_PG_TX; + } + + if (dst->path[tx].bwg_id != src->path[tx].bwg_id) { + dst->path[tx].bwg_id = src->path[tx].bwg_id; + changes |= BIT_PG_TX; + } + + if (dst->path[tx].bwg_percent != src->path[tx].bwg_percent) { + dst->path[tx].bwg_percent = src->path[tx].bwg_percent; + changes |= BIT_PG_TX; + } + + if (dst->path[tx].up_to_tc_bitmap != + src->path[tx].up_to_tc_bitmap) { + dst->path[tx].up_to_tc_bitmap = + src->path[tx].up_to_tc_bitmap; + changes |= (BIT_PG_TX | BIT_PFC | BIT_APP_UPCHG); + } + + if (dst->path[rx].prio_type != src->path[rx].prio_type) { + dst->path[rx].prio_type = src->path[rx].prio_type; + changes |= BIT_PG_RX; + } + + if (dst->path[rx].bwg_id != src->path[rx].bwg_id) { + dst->path[rx].bwg_id = src->path[rx].bwg_id; + changes |= BIT_PG_RX; + } + + if (dst->path[rx].bwg_percent != src->path[rx].bwg_percent) { + dst->path[rx].bwg_percent = src->path[rx].bwg_percent; + changes |= BIT_PG_RX; + } + + if (dst->path[rx].up_to_tc_bitmap != + src->path[rx].up_to_tc_bitmap) { + dst->path[rx].up_to_tc_bitmap = + src->path[rx].up_to_tc_bitmap; + changes |= (BIT_PG_RX | BIT_PFC | BIT_APP_UPCHG); + } + } + + for (i = DCB_PG_ATTR_BW_ID_0; i < DCB_PG_ATTR_BW_ID_MAX; i++) { + j = i - DCB_PG_ATTR_BW_ID_0; + if (dcfg->bw_percentage[tx][j] != scfg->bw_percentage[tx][j]) { + dcfg->bw_percentage[tx][j] = scfg->bw_percentage[tx][j]; + changes |= BIT_PG_TX; + } + if (dcfg->bw_percentage[rx][j] != scfg->bw_percentage[rx][j]) { + dcfg->bw_percentage[rx][j] = scfg->bw_percentage[rx][j]; + changes |= BIT_PG_RX; + } + } + + for (i = DCB_PFC_UP_ATTR_0; i < DCB_PFC_UP_ATTR_MAX; i++) { + j = i - DCB_PFC_UP_ATTR_0; + if (dcfg->tc_config[j].dcb_pfc != scfg->tc_config[j].dcb_pfc) { + dcfg->tc_config[j].dcb_pfc = scfg->tc_config[j].dcb_pfc; + changes |= BIT_PFC; + } + } + + if (dcfg->pfc_mode_enable != scfg->pfc_mode_enable) { + dcfg->pfc_mode_enable = scfg->pfc_mode_enable; + changes |= BIT_PFC; + } + + return changes; +} + +static u8 ixgbe_dcbnl_get_state(struct net_device *netdev) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + return !!(adapter->flags & IXGBE_FLAG_DCB_ENABLED); +} + +static u8 ixgbe_dcbnl_set_state(struct net_device *netdev, u8 state) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + /* Fail command if not in CEE mode */ + if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_CEE)) + return 1; + + /* verify there is something to do, if not then exit */ + if (!state == !(adapter->flags & IXGBE_FLAG_DCB_ENABLED)) + return 0; + + return !!ixgbe_setup_tc(netdev, + state ? adapter->dcb_cfg.num_tcs.pg_tcs : 0); +} + +static void ixgbe_dcbnl_get_perm_hw_addr(struct net_device *netdev, + u8 *perm_addr) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + int i, j; + + memset(perm_addr, 0xff, MAX_ADDR_LEN); + + for (i = 0; i < netdev->addr_len; i++) + perm_addr[i] = adapter->hw.mac.perm_addr[i]; + + switch (adapter->hw.mac.type) { + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + for (j = 0; j < netdev->addr_len; j++, i++) + perm_addr[i] = adapter->hw.mac.san_addr[j]; + break; + default: + break; + } +} + +static void ixgbe_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc, + u8 prio, u8 bwg_id, u8 bw_pct, + u8 up_map) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + if (prio != DCB_ATTR_VALUE_UNDEFINED) + adapter->temp_dcb_cfg.tc_config[tc].path[0].prio_type = prio; + if (bwg_id != DCB_ATTR_VALUE_UNDEFINED) + adapter->temp_dcb_cfg.tc_config[tc].path[0].bwg_id = bwg_id; + if (bw_pct != DCB_ATTR_VALUE_UNDEFINED) + adapter->temp_dcb_cfg.tc_config[tc].path[0].bwg_percent = + bw_pct; + if (up_map != DCB_ATTR_VALUE_UNDEFINED) + adapter->temp_dcb_cfg.tc_config[tc].path[0].up_to_tc_bitmap = + up_map; +} + +static void ixgbe_dcbnl_set_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id, + u8 bw_pct) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + adapter->temp_dcb_cfg.bw_percentage[0][bwg_id] = bw_pct; +} + +static void ixgbe_dcbnl_set_pg_tc_cfg_rx(struct net_device *netdev, int tc, + u8 prio, u8 bwg_id, u8 bw_pct, + u8 up_map) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + if (prio != DCB_ATTR_VALUE_UNDEFINED) + adapter->temp_dcb_cfg.tc_config[tc].path[1].prio_type = prio; + if (bwg_id != DCB_ATTR_VALUE_UNDEFINED) + adapter->temp_dcb_cfg.tc_config[tc].path[1].bwg_id = bwg_id; + if (bw_pct != DCB_ATTR_VALUE_UNDEFINED) + adapter->temp_dcb_cfg.tc_config[tc].path[1].bwg_percent = + bw_pct; + if (up_map != DCB_ATTR_VALUE_UNDEFINED) + adapter->temp_dcb_cfg.tc_config[tc].path[1].up_to_tc_bitmap = + up_map; +} + +static void ixgbe_dcbnl_set_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id, + u8 bw_pct) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + adapter->temp_dcb_cfg.bw_percentage[1][bwg_id] = bw_pct; +} + +static void ixgbe_dcbnl_get_pg_tc_cfg_tx(struct net_device *netdev, int tc, + u8 *prio, u8 *bwg_id, u8 *bw_pct, + u8 *up_map) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + *prio = adapter->dcb_cfg.tc_config[tc].path[0].prio_type; + *bwg_id = adapter->dcb_cfg.tc_config[tc].path[0].bwg_id; + *bw_pct = adapter->dcb_cfg.tc_config[tc].path[0].bwg_percent; + *up_map = adapter->dcb_cfg.tc_config[tc].path[0].up_to_tc_bitmap; +} + +static void ixgbe_dcbnl_get_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id, + u8 *bw_pct) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + *bw_pct = adapter->dcb_cfg.bw_percentage[0][bwg_id]; +} + +static void ixgbe_dcbnl_get_pg_tc_cfg_rx(struct net_device *netdev, int tc, + u8 *prio, u8 *bwg_id, u8 *bw_pct, + u8 *up_map) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + *prio = adapter->dcb_cfg.tc_config[tc].path[1].prio_type; + *bwg_id = adapter->dcb_cfg.tc_config[tc].path[1].bwg_id; + *bw_pct = adapter->dcb_cfg.tc_config[tc].path[1].bwg_percent; + *up_map = adapter->dcb_cfg.tc_config[tc].path[1].up_to_tc_bitmap; +} + +static void ixgbe_dcbnl_get_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id, + u8 *bw_pct) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + *bw_pct = adapter->dcb_cfg.bw_percentage[1][bwg_id]; +} + +static void ixgbe_dcbnl_set_pfc_cfg(struct net_device *netdev, int priority, + u8 setting) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + adapter->temp_dcb_cfg.tc_config[priority].dcb_pfc = setting; + if (adapter->temp_dcb_cfg.tc_config[priority].dcb_pfc != + adapter->dcb_cfg.tc_config[priority].dcb_pfc) + adapter->temp_dcb_cfg.pfc_mode_enable = true; +} + +static void ixgbe_dcbnl_get_pfc_cfg(struct net_device *netdev, int priority, + u8 *setting) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + *setting = adapter->dcb_cfg.tc_config[priority].dcb_pfc; +} + +static void ixgbe_dcbnl_devreset(struct net_device *dev) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + + while (test_and_set_bit(__IXGBE_RESETTING, &adapter->state)) + usleep_range(1000, 2000); + + if (netif_running(dev)) + dev->netdev_ops->ndo_stop(dev); + + ixgbe_clear_interrupt_scheme(adapter); + ixgbe_init_interrupt_scheme(adapter); + + if (netif_running(dev)) + dev->netdev_ops->ndo_open(dev); + + clear_bit(__IXGBE_RESETTING, &adapter->state); +} + +static u8 ixgbe_dcbnl_set_all(struct net_device *netdev) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_dcb_config *dcb_cfg = &adapter->dcb_cfg; + struct ixgbe_hw *hw = &adapter->hw; + int ret = DCB_NO_HW_CHG; + int i; + + /* Fail command if not in CEE mode */ + if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_CEE)) + return DCB_NO_HW_CHG; + + adapter->dcb_set_bitmap |= ixgbe_copy_dcb_cfg(adapter, + MAX_TRAFFIC_CLASS); + if (!adapter->dcb_set_bitmap) + return DCB_NO_HW_CHG; + + if (adapter->dcb_set_bitmap & (BIT_PG_TX|BIT_PG_RX)) { + u16 refill[MAX_TRAFFIC_CLASS], max[MAX_TRAFFIC_CLASS]; + u8 bwg_id[MAX_TRAFFIC_CLASS], prio_type[MAX_TRAFFIC_CLASS]; + /* Priority to TC mapping in CEE case default to 1:1 */ + u8 prio_tc[MAX_USER_PRIORITY]; + int max_frame = adapter->netdev->mtu + ETH_HLEN + ETH_FCS_LEN; + +#ifdef IXGBE_FCOE + if (adapter->netdev->features & NETIF_F_FCOE_MTU) + max_frame = max(max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE); +#endif + + ixgbe_dcb_calculate_tc_credits(hw, dcb_cfg, max_frame, + DCB_TX_CONFIG); + ixgbe_dcb_calculate_tc_credits(hw, dcb_cfg, max_frame, + DCB_RX_CONFIG); + + ixgbe_dcb_unpack_refill(dcb_cfg, DCB_TX_CONFIG, refill); + ixgbe_dcb_unpack_max(dcb_cfg, max); + ixgbe_dcb_unpack_bwgid(dcb_cfg, DCB_TX_CONFIG, bwg_id); + ixgbe_dcb_unpack_prio(dcb_cfg, DCB_TX_CONFIG, prio_type); + ixgbe_dcb_unpack_map(dcb_cfg, DCB_TX_CONFIG, prio_tc); + + ixgbe_dcb_hw_ets_config(hw, refill, max, bwg_id, + prio_type, prio_tc); + + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) + netdev_set_prio_tc_map(netdev, i, prio_tc[i]); + + ret = DCB_HW_CHG_RST; + } + + if (adapter->dcb_set_bitmap & BIT_PFC) { + if (dcb_cfg->pfc_mode_enable) { + u8 pfc_en; + u8 prio_tc[MAX_USER_PRIORITY]; + + ixgbe_dcb_unpack_map(dcb_cfg, DCB_TX_CONFIG, prio_tc); + ixgbe_dcb_unpack_pfc(dcb_cfg, &pfc_en); + ixgbe_dcb_hw_pfc_config(hw, pfc_en, prio_tc); + } else { + hw->mac.ops.fc_enable(hw); + } + + ixgbe_set_rx_drop_en(adapter); + + ret = DCB_HW_CHG; + } + +#ifdef IXGBE_FCOE + /* Reprogam FCoE hardware offloads when the traffic class + * FCoE is using changes. This happens if the APP info + * changes or the up2tc mapping is updated. + */ + if (adapter->dcb_set_bitmap & BIT_APP_UPCHG) { + struct dcb_app app = { + .selector = DCB_APP_IDTYPE_ETHTYPE, + .protocol = ETH_P_FCOE, + }; + u8 up = dcb_getapp(netdev, &app); + + adapter->fcoe.up = ffs(up) - 1; + ixgbe_dcbnl_devreset(netdev); + ret = DCB_HW_CHG_RST; + } +#endif + + adapter->dcb_set_bitmap = 0x00; + return ret; +} + +static u8 ixgbe_dcbnl_getcap(struct net_device *netdev, int capid, u8 *cap) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + switch (capid) { + case DCB_CAP_ATTR_PG: + *cap = true; + break; + case DCB_CAP_ATTR_PFC: + *cap = true; + break; + case DCB_CAP_ATTR_UP2TC: + *cap = false; + break; + case DCB_CAP_ATTR_PG_TCS: + *cap = 0x80; + break; + case DCB_CAP_ATTR_PFC_TCS: + *cap = 0x80; + break; + case DCB_CAP_ATTR_GSP: + *cap = true; + break; + case DCB_CAP_ATTR_BCN: + *cap = false; + break; + case DCB_CAP_ATTR_DCBX: + *cap = adapter->dcbx_cap; + break; + default: + *cap = false; + break; + } + + return 0; +} + +static int ixgbe_dcbnl_getnumtcs(struct net_device *netdev, int tcid, u8 *num) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) { + switch (tcid) { + case DCB_NUMTCS_ATTR_PG: + *num = adapter->dcb_cfg.num_tcs.pg_tcs; + break; + case DCB_NUMTCS_ATTR_PFC: + *num = adapter->dcb_cfg.num_tcs.pfc_tcs; + break; + default: + return -EINVAL; + } + } else { + return -EINVAL; + } + + return 0; +} + +static int ixgbe_dcbnl_setnumtcs(struct net_device *netdev, int tcid, u8 num) +{ + return -EINVAL; +} + +static u8 ixgbe_dcbnl_getpfcstate(struct net_device *netdev) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + return adapter->dcb_cfg.pfc_mode_enable; +} + +static void ixgbe_dcbnl_setpfcstate(struct net_device *netdev, u8 state) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + adapter->temp_dcb_cfg.pfc_mode_enable = state; +} + +/** + * ixgbe_dcbnl_getapp - retrieve the DCBX application user priority + * @netdev : the corresponding netdev + * @idtype : identifies the id as ether type or TCP/UDP port number + * @id: id is either ether type or TCP/UDP port number + * + * Returns : on success, returns a non-zero 802.1p user priority bitmap + * otherwise returns -EINVAL as the invalid user priority bitmap to indicate an + * error. + */ +static int ixgbe_dcbnl_getapp(struct net_device *netdev, u8 idtype, u16 id) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct dcb_app app = { + .selector = idtype, + .protocol = id, + }; + + if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_CEE)) + return -EINVAL; + + return dcb_getapp(netdev, &app); +} + +static int ixgbe_dcbnl_ieee_getets(struct net_device *dev, + struct ieee_ets *ets) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ieee_ets *my_ets = adapter->ixgbe_ieee_ets; + + ets->ets_cap = adapter->dcb_cfg.num_tcs.pg_tcs; + + /* No IEEE PFC settings available */ + if (!my_ets) + return 0; + + ets->cbs = my_ets->cbs; + memcpy(ets->tc_tx_bw, my_ets->tc_tx_bw, sizeof(ets->tc_tx_bw)); + memcpy(ets->tc_rx_bw, my_ets->tc_rx_bw, sizeof(ets->tc_rx_bw)); + memcpy(ets->tc_tsa, my_ets->tc_tsa, sizeof(ets->tc_tsa)); + memcpy(ets->prio_tc, my_ets->prio_tc, sizeof(ets->prio_tc)); + return 0; +} + +static int ixgbe_dcbnl_ieee_setets(struct net_device *dev, + struct ieee_ets *ets) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + int max_frame = dev->mtu + ETH_HLEN + ETH_FCS_LEN; + int i, err; + __u8 max_tc = 0; + __u8 map_chg = 0; + + if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) + return -EINVAL; + + if (!adapter->ixgbe_ieee_ets) { + adapter->ixgbe_ieee_ets = kmalloc(sizeof(struct ieee_ets), + GFP_KERNEL); + if (!adapter->ixgbe_ieee_ets) + return -ENOMEM; + + /* initialize UP2TC mappings to invalid value */ + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) + adapter->ixgbe_ieee_ets->prio_tc[i] = + IEEE_8021QAZ_MAX_TCS; + /* if possible update UP2TC mappings from HW */ + ixgbe_dcb_read_rtrup2tc(&adapter->hw, + adapter->ixgbe_ieee_ets->prio_tc); + } + + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + if (ets->prio_tc[i] > max_tc) + max_tc = ets->prio_tc[i]; + if (ets->prio_tc[i] != adapter->ixgbe_ieee_ets->prio_tc[i]) + map_chg = 1; + } + + memcpy(adapter->ixgbe_ieee_ets, ets, sizeof(*adapter->ixgbe_ieee_ets)); + + if (max_tc) + max_tc++; + + if (max_tc > adapter->dcb_cfg.num_tcs.pg_tcs) + return -EINVAL; + + if (max_tc != adapter->hw_tcs) { + err = ixgbe_setup_tc(dev, max_tc); + if (err) + return err; + } else if (map_chg) { + ixgbe_dcbnl_devreset(dev); + } + + return ixgbe_dcb_hw_ets(&adapter->hw, ets, max_frame); +} + +static int ixgbe_dcbnl_ieee_getpfc(struct net_device *dev, + struct ieee_pfc *pfc) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ieee_pfc *my_pfc = adapter->ixgbe_ieee_pfc; + int i; + + pfc->pfc_cap = adapter->dcb_cfg.num_tcs.pfc_tcs; + + /* No IEEE PFC settings available */ + if (!my_pfc) + return 0; + + pfc->pfc_en = my_pfc->pfc_en; + pfc->mbc = my_pfc->mbc; + pfc->delay = my_pfc->delay; + + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + pfc->requests[i] = adapter->stats.pxoffrxc[i]; + pfc->indications[i] = adapter->stats.pxofftxc[i]; + } + + return 0; +} + +static int ixgbe_dcbnl_ieee_setpfc(struct net_device *dev, + struct ieee_pfc *pfc) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_hw *hw = &adapter->hw; + u8 *prio_tc; + int err; + + if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) + return -EINVAL; + + if (!adapter->ixgbe_ieee_pfc) { + adapter->ixgbe_ieee_pfc = kmalloc(sizeof(struct ieee_pfc), + GFP_KERNEL); + if (!adapter->ixgbe_ieee_pfc) + return -ENOMEM; + } + + prio_tc = adapter->ixgbe_ieee_ets->prio_tc; + memcpy(adapter->ixgbe_ieee_pfc, pfc, sizeof(*adapter->ixgbe_ieee_pfc)); + + /* Enable link flow control parameters if PFC is disabled */ + if (pfc->pfc_en) + err = ixgbe_dcb_hw_pfc_config(hw, pfc->pfc_en, prio_tc); + else + err = hw->mac.ops.fc_enable(hw); + + ixgbe_set_rx_drop_en(adapter); + + return err; +} + +static int ixgbe_dcbnl_ieee_setapp(struct net_device *dev, + struct dcb_app *app) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + int err; + + if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) + return -EINVAL; + + err = dcb_ieee_setapp(dev, app); + if (err) + return err; + +#ifdef IXGBE_FCOE + if (app->selector == IEEE_8021QAZ_APP_SEL_ETHERTYPE && + app->protocol == ETH_P_FCOE) { + u8 app_mask = dcb_ieee_getapp_mask(dev, app); + + if (app_mask & BIT(adapter->fcoe.up)) + return 0; + + adapter->fcoe.up = app->priority; + ixgbe_dcbnl_devreset(dev); + } +#endif + + /* VF devices should use default UP when available */ + if (app->selector == IEEE_8021QAZ_APP_SEL_ETHERTYPE && + app->protocol == 0) { + int vf; + + adapter->default_up = app->priority; + + for (vf = 0; vf < adapter->num_vfs; vf++) { + struct vf_data_storage *vfinfo = &adapter->vfinfo[vf]; + + if (!vfinfo->pf_qos) + ixgbe_set_vmvir(adapter, vfinfo->pf_vlan, + app->priority, vf); + } + } + + return 0; +} + +static int ixgbe_dcbnl_ieee_delapp(struct net_device *dev, + struct dcb_app *app) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + int err; + + if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) + return -EINVAL; + + err = dcb_ieee_delapp(dev, app); + +#ifdef IXGBE_FCOE + if (!err && app->selector == IEEE_8021QAZ_APP_SEL_ETHERTYPE && + app->protocol == ETH_P_FCOE) { + u8 app_mask = dcb_ieee_getapp_mask(dev, app); + + if (app_mask & BIT(adapter->fcoe.up)) + return 0; + + adapter->fcoe.up = app_mask ? + ffs(app_mask) - 1 : IXGBE_FCOE_DEFTC; + ixgbe_dcbnl_devreset(dev); + } +#endif + /* IF default priority is being removed clear VF default UP */ + if (app->selector == IEEE_8021QAZ_APP_SEL_ETHERTYPE && + app->protocol == 0 && adapter->default_up == app->priority) { + int vf; + long unsigned int app_mask = dcb_ieee_getapp_mask(dev, app); + int qos = app_mask ? find_first_bit(&app_mask, 8) : 0; + + adapter->default_up = qos; + + for (vf = 0; vf < adapter->num_vfs; vf++) { + struct vf_data_storage *vfinfo = &adapter->vfinfo[vf]; + + if (!vfinfo->pf_qos) + ixgbe_set_vmvir(adapter, vfinfo->pf_vlan, + qos, vf); + } + } + + return err; +} + +static u8 ixgbe_dcbnl_getdcbx(struct net_device *dev) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + return adapter->dcbx_cap; +} + +static u8 ixgbe_dcbnl_setdcbx(struct net_device *dev, u8 mode) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ieee_ets ets = {0}; + struct ieee_pfc pfc = {0}; + int err = 0; + + /* no support for LLD_MANAGED modes or CEE+IEEE */ + if ((mode & DCB_CAP_DCBX_LLD_MANAGED) || + ((mode & DCB_CAP_DCBX_VER_IEEE) && (mode & DCB_CAP_DCBX_VER_CEE)) || + !(mode & DCB_CAP_DCBX_HOST)) + return 1; + + if (mode == adapter->dcbx_cap) + return 0; + + adapter->dcbx_cap = mode; + + /* ETS and PFC defaults */ + ets.ets_cap = 8; + pfc.pfc_cap = 8; + + if (mode & DCB_CAP_DCBX_VER_IEEE) { + ixgbe_dcbnl_ieee_setets(dev, &ets); + ixgbe_dcbnl_ieee_setpfc(dev, &pfc); + } else if (mode & DCB_CAP_DCBX_VER_CEE) { + u8 mask = BIT_PFC | BIT_PG_TX | BIT_PG_RX | BIT_APP_UPCHG; + + adapter->dcb_set_bitmap |= mask; + ixgbe_dcbnl_set_all(dev); + } else { + /* Drop into single TC mode strict priority as this + * indicates CEE and IEEE versions are disabled + */ + ixgbe_dcbnl_ieee_setets(dev, &ets); + ixgbe_dcbnl_ieee_setpfc(dev, &pfc); + err = ixgbe_setup_tc(dev, 0); + } + + return err ? 1 : 0; +} + +const struct dcbnl_rtnl_ops ixgbe_dcbnl_ops = { + .ieee_getets = ixgbe_dcbnl_ieee_getets, + .ieee_setets = ixgbe_dcbnl_ieee_setets, + .ieee_getpfc = ixgbe_dcbnl_ieee_getpfc, + .ieee_setpfc = ixgbe_dcbnl_ieee_setpfc, + .ieee_setapp = ixgbe_dcbnl_ieee_setapp, + .ieee_delapp = ixgbe_dcbnl_ieee_delapp, + .getstate = ixgbe_dcbnl_get_state, + .setstate = ixgbe_dcbnl_set_state, + .getpermhwaddr = ixgbe_dcbnl_get_perm_hw_addr, + .setpgtccfgtx = ixgbe_dcbnl_set_pg_tc_cfg_tx, + .setpgbwgcfgtx = ixgbe_dcbnl_set_pg_bwg_cfg_tx, + .setpgtccfgrx = ixgbe_dcbnl_set_pg_tc_cfg_rx, + .setpgbwgcfgrx = ixgbe_dcbnl_set_pg_bwg_cfg_rx, + .getpgtccfgtx = ixgbe_dcbnl_get_pg_tc_cfg_tx, + .getpgbwgcfgtx = ixgbe_dcbnl_get_pg_bwg_cfg_tx, + .getpgtccfgrx = ixgbe_dcbnl_get_pg_tc_cfg_rx, + .getpgbwgcfgrx = ixgbe_dcbnl_get_pg_bwg_cfg_rx, + .setpfccfg = ixgbe_dcbnl_set_pfc_cfg, + .getpfccfg = ixgbe_dcbnl_get_pfc_cfg, + .setall = ixgbe_dcbnl_set_all, + .getcap = ixgbe_dcbnl_getcap, + .getnumtcs = ixgbe_dcbnl_getnumtcs, + .setnumtcs = ixgbe_dcbnl_setnumtcs, + .getpfcstate = ixgbe_dcbnl_getpfcstate, + .setpfcstate = ixgbe_dcbnl_setpfcstate, + .getapp = ixgbe_dcbnl_getapp, + .getdcbx = ixgbe_dcbnl_getdcbx, + .setdcbx = ixgbe_dcbnl_setdcbx, +}; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c new file mode 100644 index 000000000..5b1cf49df --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c @@ -0,0 +1,227 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#include <linux/debugfs.h> +#include <linux/module.h> + +#include "ixgbe.h" + +static struct dentry *ixgbe_dbg_root; + +static char ixgbe_dbg_reg_ops_buf[256] = ""; + +static ssize_t ixgbe_dbg_common_ops_read(struct file *filp, char __user *buffer, + size_t count, loff_t *ppos, + char *dbg_buf) +{ + struct ixgbe_adapter *adapter = filp->private_data; + char *buf; + int len; + + /* don't allow partial reads */ + if (*ppos != 0) + return 0; + + buf = kasprintf(GFP_KERNEL, "%s: %s\n", + adapter->netdev->name, dbg_buf); + if (!buf) + return -ENOMEM; + + if (count < strlen(buf)) { + kfree(buf); + return -ENOSPC; + } + + len = simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf)); + + kfree(buf); + return len; +} + +/** + * ixgbe_dbg_reg_ops_read - read for reg_ops datum + * @filp: the opened file + * @buffer: where to write the data for the user to read + * @count: the size of the user's buffer + * @ppos: file position offset + **/ +static ssize_t ixgbe_dbg_reg_ops_read(struct file *filp, char __user *buffer, + size_t count, loff_t *ppos) +{ + return ixgbe_dbg_common_ops_read(filp, buffer, count, ppos, + ixgbe_dbg_reg_ops_buf); +} + +/** + * ixgbe_dbg_reg_ops_write - write into reg_ops datum + * @filp: the opened file + * @buffer: where to find the user's data + * @count: the length of the user's data + * @ppos: file position offset + **/ +static ssize_t ixgbe_dbg_reg_ops_write(struct file *filp, + const char __user *buffer, + size_t count, loff_t *ppos) +{ + struct ixgbe_adapter *adapter = filp->private_data; + int len; + + /* don't allow partial writes */ + if (*ppos != 0) + return 0; + if (count >= sizeof(ixgbe_dbg_reg_ops_buf)) + return -ENOSPC; + + len = simple_write_to_buffer(ixgbe_dbg_reg_ops_buf, + sizeof(ixgbe_dbg_reg_ops_buf)-1, + ppos, + buffer, + count); + if (len < 0) + return len; + + ixgbe_dbg_reg_ops_buf[len] = '\0'; + + if (strncmp(ixgbe_dbg_reg_ops_buf, "write", 5) == 0) { + u32 reg, value; + int cnt; + cnt = sscanf(&ixgbe_dbg_reg_ops_buf[5], "%x %x", ®, &value); + if (cnt == 2) { + IXGBE_WRITE_REG(&adapter->hw, reg, value); + value = IXGBE_READ_REG(&adapter->hw, reg); + e_dev_info("write: 0x%08x = 0x%08x\n", reg, value); + } else { + e_dev_info("write <reg> <value>\n"); + } + } else if (strncmp(ixgbe_dbg_reg_ops_buf, "read", 4) == 0) { + u32 reg, value; + int cnt; + cnt = sscanf(&ixgbe_dbg_reg_ops_buf[4], "%x", ®); + if (cnt == 1) { + value = IXGBE_READ_REG(&adapter->hw, reg); + e_dev_info("read 0x%08x = 0x%08x\n", reg, value); + } else { + e_dev_info("read <reg>\n"); + } + } else { + e_dev_info("Unknown command %s\n", ixgbe_dbg_reg_ops_buf); + e_dev_info("Available commands:\n"); + e_dev_info(" read <reg>\n"); + e_dev_info(" write <reg> <value>\n"); + } + return count; +} + +static const struct file_operations ixgbe_dbg_reg_ops_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = ixgbe_dbg_reg_ops_read, + .write = ixgbe_dbg_reg_ops_write, +}; + +static char ixgbe_dbg_netdev_ops_buf[256] = ""; + +/** + * ixgbe_dbg_netdev_ops_read - read for netdev_ops datum + * @filp: the opened file + * @buffer: where to write the data for the user to read + * @count: the size of the user's buffer + * @ppos: file position offset + **/ +static ssize_t ixgbe_dbg_netdev_ops_read(struct file *filp, char __user *buffer, + size_t count, loff_t *ppos) +{ + return ixgbe_dbg_common_ops_read(filp, buffer, count, ppos, + ixgbe_dbg_netdev_ops_buf); +} + +/** + * ixgbe_dbg_netdev_ops_write - write into netdev_ops datum + * @filp: the opened file + * @buffer: where to find the user's data + * @count: the length of the user's data + * @ppos: file position offset + **/ +static ssize_t ixgbe_dbg_netdev_ops_write(struct file *filp, + const char __user *buffer, + size_t count, loff_t *ppos) +{ + struct ixgbe_adapter *adapter = filp->private_data; + int len; + + /* don't allow partial writes */ + if (*ppos != 0) + return 0; + if (count >= sizeof(ixgbe_dbg_netdev_ops_buf)) + return -ENOSPC; + + len = simple_write_to_buffer(ixgbe_dbg_netdev_ops_buf, + sizeof(ixgbe_dbg_netdev_ops_buf)-1, + ppos, + buffer, + count); + if (len < 0) + return len; + + ixgbe_dbg_netdev_ops_buf[len] = '\0'; + + if (strncmp(ixgbe_dbg_netdev_ops_buf, "tx_timeout", 10) == 0) { + /* TX Queue number below is wrong, but ixgbe does not use it */ + adapter->netdev->netdev_ops->ndo_tx_timeout(adapter->netdev, + UINT_MAX); + e_dev_info("tx_timeout called\n"); + } else { + e_dev_info("Unknown command: %s\n", ixgbe_dbg_netdev_ops_buf); + e_dev_info("Available commands:\n"); + e_dev_info(" tx_timeout\n"); + } + return count; +} + +static const struct file_operations ixgbe_dbg_netdev_ops_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = ixgbe_dbg_netdev_ops_read, + .write = ixgbe_dbg_netdev_ops_write, +}; + +/** + * ixgbe_dbg_adapter_init - setup the debugfs directory for the adapter + * @adapter: the adapter that is starting up + **/ +void ixgbe_dbg_adapter_init(struct ixgbe_adapter *adapter) +{ + const char *name = pci_name(adapter->pdev); + + adapter->ixgbe_dbg_adapter = debugfs_create_dir(name, ixgbe_dbg_root); + debugfs_create_file("reg_ops", 0600, adapter->ixgbe_dbg_adapter, + adapter, &ixgbe_dbg_reg_ops_fops); + debugfs_create_file("netdev_ops", 0600, adapter->ixgbe_dbg_adapter, + adapter, &ixgbe_dbg_netdev_ops_fops); +} + +/** + * ixgbe_dbg_adapter_exit - clear out the adapter's debugfs entries + * @adapter: the adapter that is exiting + **/ +void ixgbe_dbg_adapter_exit(struct ixgbe_adapter *adapter) +{ + debugfs_remove_recursive(adapter->ixgbe_dbg_adapter); + adapter->ixgbe_dbg_adapter = NULL; +} + +/** + * ixgbe_dbg_init - start up debugfs for the driver + **/ +void ixgbe_dbg_init(void) +{ + ixgbe_dbg_root = debugfs_create_dir(ixgbe_driver_name, NULL); +} + +/** + * ixgbe_dbg_exit - clean out the driver's debugfs entries + **/ +void ixgbe_dbg_exit(void) +{ + debugfs_remove_recursive(ixgbe_dbg_root); +} diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c new file mode 100644 index 000000000..2eb133183 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -0,0 +1,3594 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +/* ethtool support for ixgbe */ + +#include <linux/interrupt.h> +#include <linux/types.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/pci.h> +#include <linux/netdevice.h> +#include <linux/ethtool.h> +#include <linux/vmalloc.h> +#include <linux/highmem.h> +#include <linux/uaccess.h> + +#include "ixgbe.h" +#include "ixgbe_phy.h" + + +#define IXGBE_ALL_RAR_ENTRIES 16 + +enum {NETDEV_STATS, IXGBE_STATS}; + +struct ixgbe_stats { + char stat_string[ETH_GSTRING_LEN]; + int type; + int sizeof_stat; + int stat_offset; +}; + +#define IXGBE_STAT(m) IXGBE_STATS, \ + sizeof(((struct ixgbe_adapter *)0)->m), \ + offsetof(struct ixgbe_adapter, m) +#define IXGBE_NETDEV_STAT(m) NETDEV_STATS, \ + sizeof(((struct rtnl_link_stats64 *)0)->m), \ + offsetof(struct rtnl_link_stats64, m) + +static const struct ixgbe_stats ixgbe_gstrings_stats[] = { + {"rx_packets", IXGBE_NETDEV_STAT(rx_packets)}, + {"tx_packets", IXGBE_NETDEV_STAT(tx_packets)}, + {"rx_bytes", IXGBE_NETDEV_STAT(rx_bytes)}, + {"tx_bytes", IXGBE_NETDEV_STAT(tx_bytes)}, + {"rx_pkts_nic", IXGBE_STAT(stats.gprc)}, + {"tx_pkts_nic", IXGBE_STAT(stats.gptc)}, + {"rx_bytes_nic", IXGBE_STAT(stats.gorc)}, + {"tx_bytes_nic", IXGBE_STAT(stats.gotc)}, + {"lsc_int", IXGBE_STAT(lsc_int)}, + {"tx_busy", IXGBE_STAT(tx_busy)}, + {"non_eop_descs", IXGBE_STAT(non_eop_descs)}, + {"rx_errors", IXGBE_NETDEV_STAT(rx_errors)}, + {"tx_errors", IXGBE_NETDEV_STAT(tx_errors)}, + {"rx_dropped", IXGBE_NETDEV_STAT(rx_dropped)}, + {"tx_dropped", IXGBE_NETDEV_STAT(tx_dropped)}, + {"multicast", IXGBE_NETDEV_STAT(multicast)}, + {"broadcast", IXGBE_STAT(stats.bprc)}, + {"rx_no_buffer_count", IXGBE_STAT(stats.rnbc[0]) }, + {"collisions", IXGBE_NETDEV_STAT(collisions)}, + {"rx_over_errors", IXGBE_NETDEV_STAT(rx_over_errors)}, + {"rx_crc_errors", IXGBE_NETDEV_STAT(rx_crc_errors)}, + {"rx_frame_errors", IXGBE_NETDEV_STAT(rx_frame_errors)}, + {"hw_rsc_aggregated", IXGBE_STAT(rsc_total_count)}, + {"hw_rsc_flushed", IXGBE_STAT(rsc_total_flush)}, + {"fdir_match", IXGBE_STAT(stats.fdirmatch)}, + {"fdir_miss", IXGBE_STAT(stats.fdirmiss)}, + {"fdir_overflow", IXGBE_STAT(fdir_overflow)}, + {"rx_fifo_errors", IXGBE_NETDEV_STAT(rx_fifo_errors)}, + {"rx_missed_errors", IXGBE_NETDEV_STAT(rx_missed_errors)}, + {"tx_aborted_errors", IXGBE_NETDEV_STAT(tx_aborted_errors)}, + {"tx_carrier_errors", IXGBE_NETDEV_STAT(tx_carrier_errors)}, + {"tx_fifo_errors", IXGBE_NETDEV_STAT(tx_fifo_errors)}, + {"tx_heartbeat_errors", IXGBE_NETDEV_STAT(tx_heartbeat_errors)}, + {"tx_timeout_count", IXGBE_STAT(tx_timeout_count)}, + {"tx_restart_queue", IXGBE_STAT(restart_queue)}, + {"rx_length_errors", IXGBE_STAT(stats.rlec)}, + {"rx_long_length_errors", IXGBE_STAT(stats.roc)}, + {"rx_short_length_errors", IXGBE_STAT(stats.ruc)}, + {"tx_flow_control_xon", IXGBE_STAT(stats.lxontxc)}, + {"rx_flow_control_xon", IXGBE_STAT(stats.lxonrxc)}, + {"tx_flow_control_xoff", IXGBE_STAT(stats.lxofftxc)}, + {"rx_flow_control_xoff", IXGBE_STAT(stats.lxoffrxc)}, + {"rx_csum_offload_errors", IXGBE_STAT(hw_csum_rx_error)}, + {"alloc_rx_page", IXGBE_STAT(alloc_rx_page)}, + {"alloc_rx_page_failed", IXGBE_STAT(alloc_rx_page_failed)}, + {"alloc_rx_buff_failed", IXGBE_STAT(alloc_rx_buff_failed)}, + {"rx_no_dma_resources", IXGBE_STAT(hw_rx_no_dma_resources)}, + {"os2bmc_rx_by_bmc", IXGBE_STAT(stats.o2bgptc)}, + {"os2bmc_tx_by_bmc", IXGBE_STAT(stats.b2ospc)}, + {"os2bmc_tx_by_host", IXGBE_STAT(stats.o2bspc)}, + {"os2bmc_rx_by_host", IXGBE_STAT(stats.b2ogprc)}, + {"tx_hwtstamp_timeouts", IXGBE_STAT(tx_hwtstamp_timeouts)}, + {"tx_hwtstamp_skipped", IXGBE_STAT(tx_hwtstamp_skipped)}, + {"rx_hwtstamp_cleared", IXGBE_STAT(rx_hwtstamp_cleared)}, + {"tx_ipsec", IXGBE_STAT(tx_ipsec)}, + {"rx_ipsec", IXGBE_STAT(rx_ipsec)}, +#ifdef IXGBE_FCOE + {"fcoe_bad_fccrc", IXGBE_STAT(stats.fccrc)}, + {"rx_fcoe_dropped", IXGBE_STAT(stats.fcoerpdc)}, + {"rx_fcoe_packets", IXGBE_STAT(stats.fcoeprc)}, + {"rx_fcoe_dwords", IXGBE_STAT(stats.fcoedwrc)}, + {"fcoe_noddp", IXGBE_STAT(stats.fcoe_noddp)}, + {"fcoe_noddp_ext_buff", IXGBE_STAT(stats.fcoe_noddp_ext_buff)}, + {"tx_fcoe_packets", IXGBE_STAT(stats.fcoeptc)}, + {"tx_fcoe_dwords", IXGBE_STAT(stats.fcoedwtc)}, +#endif /* IXGBE_FCOE */ +}; + +/* ixgbe allocates num_tx_queues and num_rx_queues symmetrically so + * we set the num_rx_queues to evaluate to num_tx_queues. This is + * used because we do not have a good way to get the max number of + * rx queues with CONFIG_RPS disabled. + */ +#define IXGBE_NUM_RX_QUEUES netdev->num_tx_queues + +#define IXGBE_QUEUE_STATS_LEN ( \ + (netdev->num_tx_queues + IXGBE_NUM_RX_QUEUES) * \ + (sizeof(struct ixgbe_queue_stats) / sizeof(u64))) +#define IXGBE_GLOBAL_STATS_LEN ARRAY_SIZE(ixgbe_gstrings_stats) +#define IXGBE_PB_STATS_LEN ( \ + (sizeof(((struct ixgbe_adapter *)0)->stats.pxonrxc) + \ + sizeof(((struct ixgbe_adapter *)0)->stats.pxontxc) + \ + sizeof(((struct ixgbe_adapter *)0)->stats.pxoffrxc) + \ + sizeof(((struct ixgbe_adapter *)0)->stats.pxofftxc)) \ + / sizeof(u64)) +#define IXGBE_STATS_LEN (IXGBE_GLOBAL_STATS_LEN + \ + IXGBE_PB_STATS_LEN + \ + IXGBE_QUEUE_STATS_LEN) + +static const char ixgbe_gstrings_test[][ETH_GSTRING_LEN] = { + "Register test (offline)", "Eeprom test (offline)", + "Interrupt test (offline)", "Loopback test (offline)", + "Link test (on/offline)" +}; +#define IXGBE_TEST_LEN sizeof(ixgbe_gstrings_test) / ETH_GSTRING_LEN + +static const char ixgbe_priv_flags_strings[][ETH_GSTRING_LEN] = { +#define IXGBE_PRIV_FLAGS_LEGACY_RX BIT(0) + "legacy-rx", +#define IXGBE_PRIV_FLAGS_VF_IPSEC_EN BIT(1) + "vf-ipsec", +}; + +#define IXGBE_PRIV_FLAGS_STR_LEN ARRAY_SIZE(ixgbe_priv_flags_strings) + +#define ixgbe_isbackplane(type) ((type) == ixgbe_media_type_backplane) + +static void ixgbe_set_supported_10gtypes(struct ixgbe_hw *hw, + struct ethtool_link_ksettings *cmd) +{ + if (!ixgbe_isbackplane(hw->phy.media_type)) { + ethtool_link_ksettings_add_link_mode(cmd, supported, + 10000baseT_Full); + return; + } + + switch (hw->device_id) { + case IXGBE_DEV_ID_82598: + case IXGBE_DEV_ID_82599_KX4: + case IXGBE_DEV_ID_82599_KX4_MEZZ: + case IXGBE_DEV_ID_X550EM_X_KX4: + ethtool_link_ksettings_add_link_mode + (cmd, supported, 10000baseKX4_Full); + break; + case IXGBE_DEV_ID_82598_BX: + case IXGBE_DEV_ID_82599_KR: + case IXGBE_DEV_ID_X550EM_X_KR: + case IXGBE_DEV_ID_X550EM_X_XFI: + ethtool_link_ksettings_add_link_mode + (cmd, supported, 10000baseKR_Full); + break; + default: + ethtool_link_ksettings_add_link_mode + (cmd, supported, 10000baseKX4_Full); + ethtool_link_ksettings_add_link_mode + (cmd, supported, 10000baseKR_Full); + break; + } +} + +static void ixgbe_set_advertising_10gtypes(struct ixgbe_hw *hw, + struct ethtool_link_ksettings *cmd) +{ + if (!ixgbe_isbackplane(hw->phy.media_type)) { + ethtool_link_ksettings_add_link_mode(cmd, advertising, + 10000baseT_Full); + return; + } + + switch (hw->device_id) { + case IXGBE_DEV_ID_82598: + case IXGBE_DEV_ID_82599_KX4: + case IXGBE_DEV_ID_82599_KX4_MEZZ: + case IXGBE_DEV_ID_X550EM_X_KX4: + ethtool_link_ksettings_add_link_mode + (cmd, advertising, 10000baseKX4_Full); + break; + case IXGBE_DEV_ID_82598_BX: + case IXGBE_DEV_ID_82599_KR: + case IXGBE_DEV_ID_X550EM_X_KR: + case IXGBE_DEV_ID_X550EM_X_XFI: + ethtool_link_ksettings_add_link_mode + (cmd, advertising, 10000baseKR_Full); + break; + default: + ethtool_link_ksettings_add_link_mode + (cmd, advertising, 10000baseKX4_Full); + ethtool_link_ksettings_add_link_mode + (cmd, advertising, 10000baseKR_Full); + break; + } +} + +static int ixgbe_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + ixgbe_link_speed supported_link; + bool autoneg = false; + + ethtool_link_ksettings_zero_link_mode(cmd, supported); + ethtool_link_ksettings_zero_link_mode(cmd, advertising); + + hw->mac.ops.get_link_capabilities(hw, &supported_link, &autoneg); + + /* set the supported link speeds */ + if (supported_link & IXGBE_LINK_SPEED_10GB_FULL) { + ixgbe_set_supported_10gtypes(hw, cmd); + ixgbe_set_advertising_10gtypes(hw, cmd); + } + if (supported_link & IXGBE_LINK_SPEED_5GB_FULL) + ethtool_link_ksettings_add_link_mode(cmd, supported, + 5000baseT_Full); + + if (supported_link & IXGBE_LINK_SPEED_2_5GB_FULL) + ethtool_link_ksettings_add_link_mode(cmd, supported, + 2500baseT_Full); + + if (supported_link & IXGBE_LINK_SPEED_1GB_FULL) { + if (ixgbe_isbackplane(hw->phy.media_type)) { + ethtool_link_ksettings_add_link_mode(cmd, supported, + 1000baseKX_Full); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + 1000baseKX_Full); + } else { + ethtool_link_ksettings_add_link_mode(cmd, supported, + 1000baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + 1000baseT_Full); + } + } + if (supported_link & IXGBE_LINK_SPEED_100_FULL) { + ethtool_link_ksettings_add_link_mode(cmd, supported, + 100baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + 100baseT_Full); + } + if (supported_link & IXGBE_LINK_SPEED_10_FULL) { + ethtool_link_ksettings_add_link_mode(cmd, supported, + 10baseT_Full); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + 10baseT_Full); + } + + /* set the advertised speeds */ + if (hw->phy.autoneg_advertised) { + ethtool_link_ksettings_zero_link_mode(cmd, advertising); + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10_FULL) + ethtool_link_ksettings_add_link_mode(cmd, advertising, + 10baseT_Full); + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_100_FULL) + ethtool_link_ksettings_add_link_mode(cmd, advertising, + 100baseT_Full); + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL) + ixgbe_set_advertising_10gtypes(hw, cmd); + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL) { + if (ethtool_link_ksettings_test_link_mode + (cmd, supported, 1000baseKX_Full)) + ethtool_link_ksettings_add_link_mode + (cmd, advertising, 1000baseKX_Full); + else + ethtool_link_ksettings_add_link_mode + (cmd, advertising, 1000baseT_Full); + } + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_5GB_FULL) + ethtool_link_ksettings_add_link_mode(cmd, advertising, + 5000baseT_Full); + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_2_5GB_FULL) + ethtool_link_ksettings_add_link_mode(cmd, advertising, + 2500baseT_Full); + } else { + if (hw->phy.multispeed_fiber && !autoneg) { + if (supported_link & IXGBE_LINK_SPEED_10GB_FULL) + ethtool_link_ksettings_add_link_mode + (cmd, advertising, 10000baseT_Full); + } + } + + if (autoneg) { + ethtool_link_ksettings_add_link_mode(cmd, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(cmd, advertising, Autoneg); + cmd->base.autoneg = AUTONEG_ENABLE; + } else + cmd->base.autoneg = AUTONEG_DISABLE; + + /* Determine the remaining settings based on the PHY type. */ + switch (adapter->hw.phy.type) { + case ixgbe_phy_tn: + case ixgbe_phy_aq: + case ixgbe_phy_x550em_ext_t: + case ixgbe_phy_fw: + case ixgbe_phy_cu_unknown: + ethtool_link_ksettings_add_link_mode(cmd, supported, TP); + ethtool_link_ksettings_add_link_mode(cmd, advertising, TP); + cmd->base.port = PORT_TP; + break; + case ixgbe_phy_qt: + ethtool_link_ksettings_add_link_mode(cmd, supported, FIBRE); + ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE); + cmd->base.port = PORT_FIBRE; + break; + case ixgbe_phy_nl: + case ixgbe_phy_sfp_passive_tyco: + case ixgbe_phy_sfp_passive_unknown: + case ixgbe_phy_sfp_ftl: + case ixgbe_phy_sfp_avago: + case ixgbe_phy_sfp_intel: + case ixgbe_phy_sfp_unknown: + case ixgbe_phy_qsfp_passive_unknown: + case ixgbe_phy_qsfp_active_unknown: + case ixgbe_phy_qsfp_intel: + case ixgbe_phy_qsfp_unknown: + /* SFP+ devices, further checking needed */ + switch (adapter->hw.phy.sfp_type) { + case ixgbe_sfp_type_da_cu: + case ixgbe_sfp_type_da_cu_core0: + case ixgbe_sfp_type_da_cu_core1: + ethtool_link_ksettings_add_link_mode(cmd, supported, + FIBRE); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + FIBRE); + cmd->base.port = PORT_DA; + break; + case ixgbe_sfp_type_sr: + case ixgbe_sfp_type_lr: + case ixgbe_sfp_type_srlr_core0: + case ixgbe_sfp_type_srlr_core1: + case ixgbe_sfp_type_1g_sx_core0: + case ixgbe_sfp_type_1g_sx_core1: + case ixgbe_sfp_type_1g_lx_core0: + case ixgbe_sfp_type_1g_lx_core1: + ethtool_link_ksettings_add_link_mode(cmd, supported, + FIBRE); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + FIBRE); + cmd->base.port = PORT_FIBRE; + break; + case ixgbe_sfp_type_not_present: + ethtool_link_ksettings_add_link_mode(cmd, supported, + FIBRE); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + FIBRE); + cmd->base.port = PORT_NONE; + break; + case ixgbe_sfp_type_1g_cu_core0: + case ixgbe_sfp_type_1g_cu_core1: + ethtool_link_ksettings_add_link_mode(cmd, supported, + TP); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + TP); + cmd->base.port = PORT_TP; + break; + case ixgbe_sfp_type_unknown: + default: + ethtool_link_ksettings_add_link_mode(cmd, supported, + FIBRE); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + FIBRE); + cmd->base.port = PORT_OTHER; + break; + } + break; + case ixgbe_phy_xaui: + ethtool_link_ksettings_add_link_mode(cmd, supported, + FIBRE); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + FIBRE); + cmd->base.port = PORT_NONE; + break; + case ixgbe_phy_unknown: + case ixgbe_phy_generic: + case ixgbe_phy_sfp_unsupported: + default: + ethtool_link_ksettings_add_link_mode(cmd, supported, + FIBRE); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + FIBRE); + cmd->base.port = PORT_OTHER; + break; + } + + /* Indicate pause support */ + ethtool_link_ksettings_add_link_mode(cmd, supported, Pause); + + switch (hw->fc.requested_mode) { + case ixgbe_fc_full: + ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause); + break; + case ixgbe_fc_rx_pause: + ethtool_link_ksettings_add_link_mode(cmd, advertising, Pause); + ethtool_link_ksettings_add_link_mode(cmd, advertising, + Asym_Pause); + break; + case ixgbe_fc_tx_pause: + ethtool_link_ksettings_add_link_mode(cmd, advertising, + Asym_Pause); + break; + default: + ethtool_link_ksettings_del_link_mode(cmd, advertising, Pause); + ethtool_link_ksettings_del_link_mode(cmd, advertising, + Asym_Pause); + } + + if (netif_carrier_ok(netdev)) { + switch (adapter->link_speed) { + case IXGBE_LINK_SPEED_10GB_FULL: + cmd->base.speed = SPEED_10000; + break; + case IXGBE_LINK_SPEED_5GB_FULL: + cmd->base.speed = SPEED_5000; + break; + case IXGBE_LINK_SPEED_2_5GB_FULL: + cmd->base.speed = SPEED_2500; + break; + case IXGBE_LINK_SPEED_1GB_FULL: + cmd->base.speed = SPEED_1000; + break; + case IXGBE_LINK_SPEED_100_FULL: + cmd->base.speed = SPEED_100; + break; + case IXGBE_LINK_SPEED_10_FULL: + cmd->base.speed = SPEED_10; + break; + default: + break; + } + cmd->base.duplex = DUPLEX_FULL; + } else { + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; + } + + return 0; +} + +static int ixgbe_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *cmd) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + u32 advertised, old; + s32 err = 0; + + if ((hw->phy.media_type == ixgbe_media_type_copper) || + (hw->phy.multispeed_fiber)) { + /* + * this function does not support duplex forcing, but can + * limit the advertising of the adapter to the specified speed + */ + if (!bitmap_subset(cmd->link_modes.advertising, + cmd->link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NBITS)) + return -EINVAL; + + /* only allow one speed at a time if no autoneg */ + if (!cmd->base.autoneg && hw->phy.multispeed_fiber) { + if (ethtool_link_ksettings_test_link_mode(cmd, advertising, + 10000baseT_Full) && + ethtool_link_ksettings_test_link_mode(cmd, advertising, + 1000baseT_Full)) + return -EINVAL; + } + + old = hw->phy.autoneg_advertised; + advertised = 0; + if (ethtool_link_ksettings_test_link_mode(cmd, advertising, + 10000baseT_Full)) + advertised |= IXGBE_LINK_SPEED_10GB_FULL; + if (ethtool_link_ksettings_test_link_mode(cmd, advertising, + 5000baseT_Full)) + advertised |= IXGBE_LINK_SPEED_5GB_FULL; + if (ethtool_link_ksettings_test_link_mode(cmd, advertising, + 2500baseT_Full)) + advertised |= IXGBE_LINK_SPEED_2_5GB_FULL; + if (ethtool_link_ksettings_test_link_mode(cmd, advertising, + 1000baseT_Full)) + advertised |= IXGBE_LINK_SPEED_1GB_FULL; + + if (ethtool_link_ksettings_test_link_mode(cmd, advertising, + 100baseT_Full)) + advertised |= IXGBE_LINK_SPEED_100_FULL; + + if (ethtool_link_ksettings_test_link_mode(cmd, advertising, + 10baseT_Full)) + advertised |= IXGBE_LINK_SPEED_10_FULL; + + if (old == advertised) + return err; + /* this sets the link speed and restarts auto-neg */ + while (test_and_set_bit(__IXGBE_IN_SFP_INIT, &adapter->state)) + usleep_range(1000, 2000); + + hw->mac.autotry_restart = true; + err = hw->mac.ops.setup_link(hw, advertised, true); + if (err) { + e_info(probe, "setup link failed with code %d\n", err); + hw->mac.ops.setup_link(hw, old, true); + } + clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state); + } else { + /* in this case we currently only support 10Gb/FULL */ + u32 speed = cmd->base.speed; + + if ((cmd->base.autoneg == AUTONEG_ENABLE) || + (!ethtool_link_ksettings_test_link_mode(cmd, advertising, + 10000baseT_Full)) || + (speed + cmd->base.duplex != SPEED_10000 + DUPLEX_FULL)) + return -EINVAL; + } + + return err; +} + +static void ixgbe_get_pause_stats(struct net_device *netdev, + struct ethtool_pause_stats *stats) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw_stats *hwstats = &adapter->stats; + + stats->tx_pause_frames = hwstats->lxontxc + hwstats->lxofftxc; + stats->rx_pause_frames = hwstats->lxonrxc + hwstats->lxoffrxc; +} + +static void ixgbe_get_pauseparam(struct net_device *netdev, + struct ethtool_pauseparam *pause) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + + if (ixgbe_device_supports_autoneg_fc(hw) && + !hw->fc.disable_fc_autoneg) + pause->autoneg = 1; + else + pause->autoneg = 0; + + if (hw->fc.current_mode == ixgbe_fc_rx_pause) { + pause->rx_pause = 1; + } else if (hw->fc.current_mode == ixgbe_fc_tx_pause) { + pause->tx_pause = 1; + } else if (hw->fc.current_mode == ixgbe_fc_full) { + pause->rx_pause = 1; + pause->tx_pause = 1; + } +} + +static int ixgbe_set_pauseparam(struct net_device *netdev, + struct ethtool_pauseparam *pause) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_fc_info fc = hw->fc; + + /* 82598 does no support link flow control with DCB enabled */ + if ((hw->mac.type == ixgbe_mac_82598EB) && + (adapter->flags & IXGBE_FLAG_DCB_ENABLED)) + return -EINVAL; + + /* some devices do not support autoneg of link flow control */ + if ((pause->autoneg == AUTONEG_ENABLE) && + !ixgbe_device_supports_autoneg_fc(hw)) + return -EINVAL; + + fc.disable_fc_autoneg = (pause->autoneg != AUTONEG_ENABLE); + + if ((pause->rx_pause && pause->tx_pause) || pause->autoneg) + fc.requested_mode = ixgbe_fc_full; + else if (pause->rx_pause && !pause->tx_pause) + fc.requested_mode = ixgbe_fc_rx_pause; + else if (!pause->rx_pause && pause->tx_pause) + fc.requested_mode = ixgbe_fc_tx_pause; + else + fc.requested_mode = ixgbe_fc_none; + + /* if the thing changed then we'll update and use new autoneg */ + if (memcmp(&fc, &hw->fc, sizeof(struct ixgbe_fc_info))) { + hw->fc = fc; + if (netif_running(netdev)) + ixgbe_reinit_locked(adapter); + else + ixgbe_reset(adapter); + } + + return 0; +} + +static u32 ixgbe_get_msglevel(struct net_device *netdev) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + return adapter->msg_enable; +} + +static void ixgbe_set_msglevel(struct net_device *netdev, u32 data) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + adapter->msg_enable = data; +} + +static int ixgbe_get_regs_len(struct net_device *netdev) +{ +#define IXGBE_REGS_LEN 1145 + return IXGBE_REGS_LEN * sizeof(u32); +} + +#define IXGBE_GET_STAT(_A_, _R_) _A_->stats._R_ + +static void ixgbe_get_regs(struct net_device *netdev, + struct ethtool_regs *regs, void *p) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + u32 *regs_buff = p; + u8 i; + + memset(p, 0, IXGBE_REGS_LEN * sizeof(u32)); + + regs->version = hw->mac.type << 24 | hw->revision_id << 16 | + hw->device_id; + + /* General Registers */ + regs_buff[0] = IXGBE_READ_REG(hw, IXGBE_CTRL); + regs_buff[1] = IXGBE_READ_REG(hw, IXGBE_STATUS); + regs_buff[2] = IXGBE_READ_REG(hw, IXGBE_CTRL_EXT); + regs_buff[3] = IXGBE_READ_REG(hw, IXGBE_ESDP); + regs_buff[4] = IXGBE_READ_REG(hw, IXGBE_EODSDP); + regs_buff[5] = IXGBE_READ_REG(hw, IXGBE_LEDCTL); + regs_buff[6] = IXGBE_READ_REG(hw, IXGBE_FRTIMER); + regs_buff[7] = IXGBE_READ_REG(hw, IXGBE_TCPTIMER); + + /* NVM Register */ + regs_buff[8] = IXGBE_READ_REG(hw, IXGBE_EEC(hw)); + regs_buff[9] = IXGBE_READ_REG(hw, IXGBE_EERD); + regs_buff[10] = IXGBE_READ_REG(hw, IXGBE_FLA(hw)); + regs_buff[11] = IXGBE_READ_REG(hw, IXGBE_EEMNGCTL); + regs_buff[12] = IXGBE_READ_REG(hw, IXGBE_EEMNGDATA); + regs_buff[13] = IXGBE_READ_REG(hw, IXGBE_FLMNGCTL); + regs_buff[14] = IXGBE_READ_REG(hw, IXGBE_FLMNGDATA); + regs_buff[15] = IXGBE_READ_REG(hw, IXGBE_FLMNGCNT); + regs_buff[16] = IXGBE_READ_REG(hw, IXGBE_FLOP); + regs_buff[17] = IXGBE_READ_REG(hw, IXGBE_GRC(hw)); + + /* Interrupt */ + /* don't read EICR because it can clear interrupt causes, instead + * read EICS which is a shadow but doesn't clear EICR */ + regs_buff[18] = IXGBE_READ_REG(hw, IXGBE_EICS); + regs_buff[19] = IXGBE_READ_REG(hw, IXGBE_EICS); + regs_buff[20] = IXGBE_READ_REG(hw, IXGBE_EIMS); + regs_buff[21] = IXGBE_READ_REG(hw, IXGBE_EIMC); + regs_buff[22] = IXGBE_READ_REG(hw, IXGBE_EIAC); + regs_buff[23] = IXGBE_READ_REG(hw, IXGBE_EIAM); + regs_buff[24] = IXGBE_READ_REG(hw, IXGBE_EITR(0)); + regs_buff[25] = IXGBE_READ_REG(hw, IXGBE_IVAR(0)); + regs_buff[26] = IXGBE_READ_REG(hw, IXGBE_MSIXT); + regs_buff[27] = IXGBE_READ_REG(hw, IXGBE_MSIXPBA); + regs_buff[28] = IXGBE_READ_REG(hw, IXGBE_PBACL(0)); + regs_buff[29] = IXGBE_READ_REG(hw, IXGBE_GPIE); + + /* Flow Control */ + regs_buff[30] = IXGBE_READ_REG(hw, IXGBE_PFCTOP); + for (i = 0; i < 4; i++) + regs_buff[31 + i] = IXGBE_READ_REG(hw, IXGBE_FCTTV(i)); + for (i = 0; i < 8; i++) { + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + regs_buff[35 + i] = IXGBE_READ_REG(hw, IXGBE_FCRTL(i)); + regs_buff[43 + i] = IXGBE_READ_REG(hw, IXGBE_FCRTH(i)); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + regs_buff[35 + i] = IXGBE_READ_REG(hw, IXGBE_FCRTL_82599(i)); + regs_buff[43 + i] = IXGBE_READ_REG(hw, IXGBE_FCRTH_82599(i)); + break; + default: + break; + } + } + regs_buff[51] = IXGBE_READ_REG(hw, IXGBE_FCRTV); + regs_buff[52] = IXGBE_READ_REG(hw, IXGBE_TFCS); + + /* Receive DMA */ + for (i = 0; i < 64; i++) + regs_buff[53 + i] = IXGBE_READ_REG(hw, IXGBE_RDBAL(i)); + for (i = 0; i < 64; i++) + regs_buff[117 + i] = IXGBE_READ_REG(hw, IXGBE_RDBAH(i)); + for (i = 0; i < 64; i++) + regs_buff[181 + i] = IXGBE_READ_REG(hw, IXGBE_RDLEN(i)); + for (i = 0; i < 64; i++) + regs_buff[245 + i] = IXGBE_READ_REG(hw, IXGBE_RDH(i)); + for (i = 0; i < 64; i++) + regs_buff[309 + i] = IXGBE_READ_REG(hw, IXGBE_RDT(i)); + for (i = 0; i < 64; i++) + regs_buff[373 + i] = IXGBE_READ_REG(hw, IXGBE_RXDCTL(i)); + for (i = 0; i < 16; i++) + regs_buff[437 + i] = IXGBE_READ_REG(hw, IXGBE_SRRCTL(i)); + for (i = 0; i < 16; i++) + regs_buff[453 + i] = IXGBE_READ_REG(hw, IXGBE_DCA_RXCTRL(i)); + regs_buff[469] = IXGBE_READ_REG(hw, IXGBE_RDRXCTL); + for (i = 0; i < 8; i++) + regs_buff[470 + i] = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(i)); + regs_buff[478] = IXGBE_READ_REG(hw, IXGBE_RXCTRL); + regs_buff[479] = IXGBE_READ_REG(hw, IXGBE_DROPEN); + + /* Receive */ + regs_buff[480] = IXGBE_READ_REG(hw, IXGBE_RXCSUM); + regs_buff[481] = IXGBE_READ_REG(hw, IXGBE_RFCTL); + for (i = 0; i < 16; i++) + regs_buff[482 + i] = IXGBE_READ_REG(hw, IXGBE_RAL(i)); + for (i = 0; i < 16; i++) + regs_buff[498 + i] = IXGBE_READ_REG(hw, IXGBE_RAH(i)); + regs_buff[514] = IXGBE_READ_REG(hw, IXGBE_PSRTYPE(0)); + regs_buff[515] = IXGBE_READ_REG(hw, IXGBE_FCTRL); + regs_buff[516] = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); + regs_buff[517] = IXGBE_READ_REG(hw, IXGBE_MCSTCTRL); + regs_buff[518] = IXGBE_READ_REG(hw, IXGBE_MRQC); + regs_buff[519] = IXGBE_READ_REG(hw, IXGBE_VMD_CTL); + for (i = 0; i < 8; i++) + regs_buff[520 + i] = IXGBE_READ_REG(hw, IXGBE_IMIR(i)); + for (i = 0; i < 8; i++) + regs_buff[528 + i] = IXGBE_READ_REG(hw, IXGBE_IMIREXT(i)); + regs_buff[536] = IXGBE_READ_REG(hw, IXGBE_IMIRVP); + + /* Transmit */ + for (i = 0; i < 32; i++) + regs_buff[537 + i] = IXGBE_READ_REG(hw, IXGBE_TDBAL(i)); + for (i = 0; i < 32; i++) + regs_buff[569 + i] = IXGBE_READ_REG(hw, IXGBE_TDBAH(i)); + for (i = 0; i < 32; i++) + regs_buff[601 + i] = IXGBE_READ_REG(hw, IXGBE_TDLEN(i)); + for (i = 0; i < 32; i++) + regs_buff[633 + i] = IXGBE_READ_REG(hw, IXGBE_TDH(i)); + for (i = 0; i < 32; i++) + regs_buff[665 + i] = IXGBE_READ_REG(hw, IXGBE_TDT(i)); + for (i = 0; i < 32; i++) + regs_buff[697 + i] = IXGBE_READ_REG(hw, IXGBE_TXDCTL(i)); + for (i = 0; i < 32; i++) + regs_buff[729 + i] = IXGBE_READ_REG(hw, IXGBE_TDWBAL(i)); + for (i = 0; i < 32; i++) + regs_buff[761 + i] = IXGBE_READ_REG(hw, IXGBE_TDWBAH(i)); + regs_buff[793] = IXGBE_READ_REG(hw, IXGBE_DTXCTL); + for (i = 0; i < 16; i++) + regs_buff[794 + i] = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL(i)); + regs_buff[810] = IXGBE_READ_REG(hw, IXGBE_TIPG); + for (i = 0; i < 8; i++) + regs_buff[811 + i] = IXGBE_READ_REG(hw, IXGBE_TXPBSIZE(i)); + regs_buff[819] = IXGBE_READ_REG(hw, IXGBE_MNGTXMAP); + + /* Wake Up */ + regs_buff[820] = IXGBE_READ_REG(hw, IXGBE_WUC); + regs_buff[821] = IXGBE_READ_REG(hw, IXGBE_WUFC); + regs_buff[822] = IXGBE_READ_REG(hw, IXGBE_WUS); + regs_buff[823] = IXGBE_READ_REG(hw, IXGBE_IPAV); + regs_buff[824] = IXGBE_READ_REG(hw, IXGBE_IP4AT); + regs_buff[825] = IXGBE_READ_REG(hw, IXGBE_IP6AT); + regs_buff[826] = IXGBE_READ_REG(hw, IXGBE_WUPL); + regs_buff[827] = IXGBE_READ_REG(hw, IXGBE_WUPM); + regs_buff[828] = IXGBE_READ_REG(hw, IXGBE_FHFT(0)); + + /* DCB */ + regs_buff[829] = IXGBE_READ_REG(hw, IXGBE_RMCS); /* same as FCCFG */ + regs_buff[831] = IXGBE_READ_REG(hw, IXGBE_PDPMCS); /* same as RTTPCS */ + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + regs_buff[830] = IXGBE_READ_REG(hw, IXGBE_DPMCS); + regs_buff[832] = IXGBE_READ_REG(hw, IXGBE_RUPPBMR); + for (i = 0; i < 8; i++) + regs_buff[833 + i] = + IXGBE_READ_REG(hw, IXGBE_RT2CR(i)); + for (i = 0; i < 8; i++) + regs_buff[841 + i] = + IXGBE_READ_REG(hw, IXGBE_RT2SR(i)); + for (i = 0; i < 8; i++) + regs_buff[849 + i] = + IXGBE_READ_REG(hw, IXGBE_TDTQ2TCCR(i)); + for (i = 0; i < 8; i++) + regs_buff[857 + i] = + IXGBE_READ_REG(hw, IXGBE_TDTQ2TCSR(i)); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + regs_buff[830] = IXGBE_READ_REG(hw, IXGBE_RTTDCS); + regs_buff[832] = IXGBE_READ_REG(hw, IXGBE_RTRPCS); + for (i = 0; i < 8; i++) + regs_buff[833 + i] = + IXGBE_READ_REG(hw, IXGBE_RTRPT4C(i)); + for (i = 0; i < 8; i++) + regs_buff[841 + i] = + IXGBE_READ_REG(hw, IXGBE_RTRPT4S(i)); + for (i = 0; i < 8; i++) + regs_buff[849 + i] = + IXGBE_READ_REG(hw, IXGBE_RTTDT2C(i)); + for (i = 0; i < 8; i++) + regs_buff[857 + i] = + IXGBE_READ_REG(hw, IXGBE_RTTDT2S(i)); + break; + default: + break; + } + + for (i = 0; i < 8; i++) + regs_buff[865 + i] = + IXGBE_READ_REG(hw, IXGBE_TDPT2TCCR(i)); /* same as RTTPT2C */ + for (i = 0; i < 8; i++) + regs_buff[873 + i] = + IXGBE_READ_REG(hw, IXGBE_TDPT2TCSR(i)); /* same as RTTPT2S */ + + /* Statistics */ + regs_buff[881] = IXGBE_GET_STAT(adapter, crcerrs); + regs_buff[882] = IXGBE_GET_STAT(adapter, illerrc); + regs_buff[883] = IXGBE_GET_STAT(adapter, errbc); + regs_buff[884] = IXGBE_GET_STAT(adapter, mspdc); + for (i = 0; i < 8; i++) + regs_buff[885 + i] = IXGBE_GET_STAT(adapter, mpc[i]); + regs_buff[893] = IXGBE_GET_STAT(adapter, mlfc); + regs_buff[894] = IXGBE_GET_STAT(adapter, mrfc); + regs_buff[895] = IXGBE_GET_STAT(adapter, rlec); + regs_buff[896] = IXGBE_GET_STAT(adapter, lxontxc); + regs_buff[897] = IXGBE_GET_STAT(adapter, lxonrxc); + regs_buff[898] = IXGBE_GET_STAT(adapter, lxofftxc); + regs_buff[899] = IXGBE_GET_STAT(adapter, lxoffrxc); + for (i = 0; i < 8; i++) + regs_buff[900 + i] = IXGBE_GET_STAT(adapter, pxontxc[i]); + for (i = 0; i < 8; i++) + regs_buff[908 + i] = IXGBE_GET_STAT(adapter, pxonrxc[i]); + for (i = 0; i < 8; i++) + regs_buff[916 + i] = IXGBE_GET_STAT(adapter, pxofftxc[i]); + for (i = 0; i < 8; i++) + regs_buff[924 + i] = IXGBE_GET_STAT(adapter, pxoffrxc[i]); + regs_buff[932] = IXGBE_GET_STAT(adapter, prc64); + regs_buff[933] = IXGBE_GET_STAT(adapter, prc127); + regs_buff[934] = IXGBE_GET_STAT(adapter, prc255); + regs_buff[935] = IXGBE_GET_STAT(adapter, prc511); + regs_buff[936] = IXGBE_GET_STAT(adapter, prc1023); + regs_buff[937] = IXGBE_GET_STAT(adapter, prc1522); + regs_buff[938] = IXGBE_GET_STAT(adapter, gprc); + regs_buff[939] = IXGBE_GET_STAT(adapter, bprc); + regs_buff[940] = IXGBE_GET_STAT(adapter, mprc); + regs_buff[941] = IXGBE_GET_STAT(adapter, gptc); + regs_buff[942] = (u32)IXGBE_GET_STAT(adapter, gorc); + regs_buff[943] = (u32)(IXGBE_GET_STAT(adapter, gorc) >> 32); + regs_buff[944] = (u32)IXGBE_GET_STAT(adapter, gotc); + regs_buff[945] = (u32)(IXGBE_GET_STAT(adapter, gotc) >> 32); + for (i = 0; i < 8; i++) + regs_buff[946 + i] = IXGBE_GET_STAT(adapter, rnbc[i]); + regs_buff[954] = IXGBE_GET_STAT(adapter, ruc); + regs_buff[955] = IXGBE_GET_STAT(adapter, rfc); + regs_buff[956] = IXGBE_GET_STAT(adapter, roc); + regs_buff[957] = IXGBE_GET_STAT(adapter, rjc); + regs_buff[958] = IXGBE_GET_STAT(adapter, mngprc); + regs_buff[959] = IXGBE_GET_STAT(adapter, mngpdc); + regs_buff[960] = IXGBE_GET_STAT(adapter, mngptc); + regs_buff[961] = (u32)IXGBE_GET_STAT(adapter, tor); + regs_buff[962] = (u32)(IXGBE_GET_STAT(adapter, tor) >> 32); + regs_buff[963] = IXGBE_GET_STAT(adapter, tpr); + regs_buff[964] = IXGBE_GET_STAT(adapter, tpt); + regs_buff[965] = IXGBE_GET_STAT(adapter, ptc64); + regs_buff[966] = IXGBE_GET_STAT(adapter, ptc127); + regs_buff[967] = IXGBE_GET_STAT(adapter, ptc255); + regs_buff[968] = IXGBE_GET_STAT(adapter, ptc511); + regs_buff[969] = IXGBE_GET_STAT(adapter, ptc1023); + regs_buff[970] = IXGBE_GET_STAT(adapter, ptc1522); + regs_buff[971] = IXGBE_GET_STAT(adapter, mptc); + regs_buff[972] = IXGBE_GET_STAT(adapter, bptc); + regs_buff[973] = IXGBE_GET_STAT(adapter, xec); + for (i = 0; i < 16; i++) + regs_buff[974 + i] = IXGBE_GET_STAT(adapter, qprc[i]); + for (i = 0; i < 16; i++) + regs_buff[990 + i] = IXGBE_GET_STAT(adapter, qptc[i]); + for (i = 0; i < 16; i++) + regs_buff[1006 + i] = IXGBE_GET_STAT(adapter, qbrc[i]); + for (i = 0; i < 16; i++) + regs_buff[1022 + i] = IXGBE_GET_STAT(adapter, qbtc[i]); + + /* MAC */ + regs_buff[1038] = IXGBE_READ_REG(hw, IXGBE_PCS1GCFIG); + regs_buff[1039] = IXGBE_READ_REG(hw, IXGBE_PCS1GLCTL); + regs_buff[1040] = IXGBE_READ_REG(hw, IXGBE_PCS1GLSTA); + regs_buff[1041] = IXGBE_READ_REG(hw, IXGBE_PCS1GDBG0); + regs_buff[1042] = IXGBE_READ_REG(hw, IXGBE_PCS1GDBG1); + regs_buff[1043] = IXGBE_READ_REG(hw, IXGBE_PCS1GANA); + regs_buff[1044] = IXGBE_READ_REG(hw, IXGBE_PCS1GANLP); + regs_buff[1045] = IXGBE_READ_REG(hw, IXGBE_PCS1GANNP); + regs_buff[1046] = IXGBE_READ_REG(hw, IXGBE_PCS1GANLPNP); + regs_buff[1047] = IXGBE_READ_REG(hw, IXGBE_HLREG0); + regs_buff[1048] = IXGBE_READ_REG(hw, IXGBE_HLREG1); + regs_buff[1049] = IXGBE_READ_REG(hw, IXGBE_PAP); + regs_buff[1050] = IXGBE_READ_REG(hw, IXGBE_MACA); + regs_buff[1051] = IXGBE_READ_REG(hw, IXGBE_APAE); + regs_buff[1052] = IXGBE_READ_REG(hw, IXGBE_ARD); + regs_buff[1053] = IXGBE_READ_REG(hw, IXGBE_AIS); + regs_buff[1054] = IXGBE_READ_REG(hw, IXGBE_MSCA); + regs_buff[1055] = IXGBE_READ_REG(hw, IXGBE_MSRWD); + regs_buff[1056] = IXGBE_READ_REG(hw, IXGBE_MLADD); + regs_buff[1057] = IXGBE_READ_REG(hw, IXGBE_MHADD); + regs_buff[1058] = IXGBE_READ_REG(hw, IXGBE_TREG); + regs_buff[1059] = IXGBE_READ_REG(hw, IXGBE_PCSS1); + regs_buff[1060] = IXGBE_READ_REG(hw, IXGBE_PCSS2); + regs_buff[1061] = IXGBE_READ_REG(hw, IXGBE_XPCSS); + regs_buff[1062] = IXGBE_READ_REG(hw, IXGBE_SERDESC); + regs_buff[1063] = IXGBE_READ_REG(hw, IXGBE_MACS); + regs_buff[1064] = IXGBE_READ_REG(hw, IXGBE_AUTOC); + regs_buff[1065] = IXGBE_READ_REG(hw, IXGBE_LINKS); + regs_buff[1066] = IXGBE_READ_REG(hw, IXGBE_AUTOC2); + regs_buff[1067] = IXGBE_READ_REG(hw, IXGBE_AUTOC3); + regs_buff[1068] = IXGBE_READ_REG(hw, IXGBE_ANLP1); + regs_buff[1069] = IXGBE_READ_REG(hw, IXGBE_ANLP2); + regs_buff[1070] = IXGBE_READ_REG(hw, IXGBE_ATLASCTL); + + /* Diagnostic */ + regs_buff[1071] = IXGBE_READ_REG(hw, IXGBE_RDSTATCTL); + for (i = 0; i < 8; i++) + regs_buff[1072 + i] = IXGBE_READ_REG(hw, IXGBE_RDSTAT(i)); + regs_buff[1080] = IXGBE_READ_REG(hw, IXGBE_RDHMPN); + for (i = 0; i < 4; i++) + regs_buff[1081 + i] = IXGBE_READ_REG(hw, IXGBE_RIC_DW(i)); + regs_buff[1085] = IXGBE_READ_REG(hw, IXGBE_RDPROBE); + regs_buff[1086] = IXGBE_READ_REG(hw, IXGBE_TDSTATCTL); + for (i = 0; i < 8; i++) + regs_buff[1087 + i] = IXGBE_READ_REG(hw, IXGBE_TDSTAT(i)); + regs_buff[1095] = IXGBE_READ_REG(hw, IXGBE_TDHMPN); + for (i = 0; i < 4; i++) + regs_buff[1096 + i] = IXGBE_READ_REG(hw, IXGBE_TIC_DW(i)); + regs_buff[1100] = IXGBE_READ_REG(hw, IXGBE_TDPROBE); + regs_buff[1101] = IXGBE_READ_REG(hw, IXGBE_TXBUFCTRL); + for (i = 0; i < 4; i++) + regs_buff[1102 + i] = IXGBE_READ_REG(hw, IXGBE_TXBUFDATA(i)); + regs_buff[1106] = IXGBE_READ_REG(hw, IXGBE_RXBUFCTRL); + for (i = 0; i < 4; i++) + regs_buff[1107 + i] = IXGBE_READ_REG(hw, IXGBE_RXBUFDATA(i)); + for (i = 0; i < 8; i++) + regs_buff[1111 + i] = IXGBE_READ_REG(hw, IXGBE_PCIE_DIAG(i)); + regs_buff[1119] = IXGBE_READ_REG(hw, IXGBE_RFVAL); + regs_buff[1120] = IXGBE_READ_REG(hw, IXGBE_MDFTC1); + regs_buff[1121] = IXGBE_READ_REG(hw, IXGBE_MDFTC2); + regs_buff[1122] = IXGBE_READ_REG(hw, IXGBE_MDFTFIFO1); + regs_buff[1123] = IXGBE_READ_REG(hw, IXGBE_MDFTFIFO2); + regs_buff[1124] = IXGBE_READ_REG(hw, IXGBE_MDFTS); + regs_buff[1125] = IXGBE_READ_REG(hw, IXGBE_PCIEECCCTL); + regs_buff[1126] = IXGBE_READ_REG(hw, IXGBE_PBTXECC); + regs_buff[1127] = IXGBE_READ_REG(hw, IXGBE_PBRXECC); + + /* 82599 X540 specific registers */ + regs_buff[1128] = IXGBE_READ_REG(hw, IXGBE_MFLCN); + + /* 82599 X540 specific DCB registers */ + regs_buff[1129] = IXGBE_READ_REG(hw, IXGBE_RTRUP2TC); + regs_buff[1130] = IXGBE_READ_REG(hw, IXGBE_RTTUP2TC); + for (i = 0; i < 4; i++) + regs_buff[1131 + i] = IXGBE_READ_REG(hw, IXGBE_TXLLQ(i)); + regs_buff[1135] = IXGBE_READ_REG(hw, IXGBE_RTTBCNRM); + /* same as RTTQCNRM */ + regs_buff[1136] = IXGBE_READ_REG(hw, IXGBE_RTTBCNRD); + /* same as RTTQCNRR */ + + /* X540 specific DCB registers */ + regs_buff[1137] = IXGBE_READ_REG(hw, IXGBE_RTTQCNCR); + regs_buff[1138] = IXGBE_READ_REG(hw, IXGBE_RTTQCNTG); + + /* Security config registers */ + regs_buff[1139] = IXGBE_READ_REG(hw, IXGBE_SECTXCTRL); + regs_buff[1140] = IXGBE_READ_REG(hw, IXGBE_SECTXSTAT); + regs_buff[1141] = IXGBE_READ_REG(hw, IXGBE_SECTXBUFFAF); + regs_buff[1142] = IXGBE_READ_REG(hw, IXGBE_SECTXMINIFG); + regs_buff[1143] = IXGBE_READ_REG(hw, IXGBE_SECRXCTRL); + regs_buff[1144] = IXGBE_READ_REG(hw, IXGBE_SECRXSTAT); +} + +static int ixgbe_get_eeprom_len(struct net_device *netdev) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + return adapter->hw.eeprom.word_size * 2; +} + +static int ixgbe_get_eeprom(struct net_device *netdev, + struct ethtool_eeprom *eeprom, u8 *bytes) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + u16 *eeprom_buff; + int first_word, last_word, eeprom_len; + int ret_val = 0; + u16 i; + + if (eeprom->len == 0) + return -EINVAL; + + eeprom->magic = hw->vendor_id | (hw->device_id << 16); + + first_word = eeprom->offset >> 1; + last_word = (eeprom->offset + eeprom->len - 1) >> 1; + eeprom_len = last_word - first_word + 1; + + eeprom_buff = kmalloc_array(eeprom_len, sizeof(u16), GFP_KERNEL); + if (!eeprom_buff) + return -ENOMEM; + + ret_val = hw->eeprom.ops.read_buffer(hw, first_word, eeprom_len, + eeprom_buff); + + /* Device's eeprom is always little-endian, word addressable */ + for (i = 0; i < eeprom_len; i++) + le16_to_cpus(&eeprom_buff[i]); + + memcpy(bytes, (u8 *)eeprom_buff + (eeprom->offset & 1), eeprom->len); + kfree(eeprom_buff); + + return ret_val; +} + +static int ixgbe_set_eeprom(struct net_device *netdev, + struct ethtool_eeprom *eeprom, u8 *bytes) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + u16 *eeprom_buff; + void *ptr; + int max_len, first_word, last_word, ret_val = 0; + u16 i; + + if (eeprom->len == 0) + return -EINVAL; + + if (eeprom->magic != (hw->vendor_id | (hw->device_id << 16))) + return -EINVAL; + + max_len = hw->eeprom.word_size * 2; + + 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 = 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 + */ + ret_val = hw->eeprom.ops.read(hw, first_word, &eeprom_buff[0]); + if (ret_val) + goto err; + + 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 + */ + ret_val = hw->eeprom.ops.read(hw, last_word, + &eeprom_buff[last_word - first_word]); + if (ret_val) + goto err; + } + + /* Device's eeprom is always little-endian, word addressable */ + for (i = 0; i < last_word - first_word + 1; i++) + le16_to_cpus(&eeprom_buff[i]); + + memcpy(ptr, bytes, eeprom->len); + + for (i = 0; i < last_word - first_word + 1; i++) + cpu_to_le16s(&eeprom_buff[i]); + + ret_val = hw->eeprom.ops.write_buffer(hw, first_word, + last_word - first_word + 1, + eeprom_buff); + + /* Update the checksum */ + if (ret_val == 0) + hw->eeprom.ops.update_checksum(hw); + +err: + kfree(eeprom_buff); + return ret_val; +} + +static void ixgbe_get_drvinfo(struct net_device *netdev, + struct ethtool_drvinfo *drvinfo) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + strlcpy(drvinfo->driver, ixgbe_driver_name, sizeof(drvinfo->driver)); + + strlcpy(drvinfo->fw_version, adapter->eeprom_id, + sizeof(drvinfo->fw_version)); + + strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), + sizeof(drvinfo->bus_info)); + + drvinfo->n_priv_flags = IXGBE_PRIV_FLAGS_STR_LEN; +} + +static void ixgbe_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_ring *tx_ring = adapter->tx_ring[0]; + struct ixgbe_ring *rx_ring = adapter->rx_ring[0]; + + ring->rx_max_pending = IXGBE_MAX_RXD; + ring->tx_max_pending = IXGBE_MAX_TXD; + ring->rx_pending = rx_ring->count; + ring->tx_pending = tx_ring->count; +} + +static int ixgbe_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_ring *temp_ring; + int i, j, err = 0; + u32 new_rx_count, new_tx_count; + + if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) + return -EINVAL; + + new_tx_count = clamp_t(u32, ring->tx_pending, + IXGBE_MIN_TXD, IXGBE_MAX_TXD); + new_tx_count = ALIGN(new_tx_count, IXGBE_REQ_TX_DESCRIPTOR_MULTIPLE); + + new_rx_count = clamp_t(u32, ring->rx_pending, + IXGBE_MIN_RXD, IXGBE_MAX_RXD); + new_rx_count = ALIGN(new_rx_count, IXGBE_REQ_RX_DESCRIPTOR_MULTIPLE); + + if ((new_tx_count == adapter->tx_ring_count) && + (new_rx_count == adapter->rx_ring_count)) { + /* nothing to do */ + return 0; + } + + while (test_and_set_bit(__IXGBE_RESETTING, &adapter->state)) + usleep_range(1000, 2000); + + if (!netif_running(adapter->netdev)) { + for (i = 0; i < adapter->num_tx_queues; i++) + adapter->tx_ring[i]->count = new_tx_count; + for (i = 0; i < adapter->num_xdp_queues; i++) + adapter->xdp_ring[i]->count = new_tx_count; + for (i = 0; i < adapter->num_rx_queues; i++) + adapter->rx_ring[i]->count = new_rx_count; + adapter->tx_ring_count = new_tx_count; + adapter->xdp_ring_count = new_tx_count; + adapter->rx_ring_count = new_rx_count; + goto clear_reset; + } + + /* allocate temporary buffer to store rings in */ + i = max_t(int, adapter->num_tx_queues + adapter->num_xdp_queues, + adapter->num_rx_queues); + temp_ring = vmalloc(array_size(i, sizeof(struct ixgbe_ring))); + + if (!temp_ring) { + err = -ENOMEM; + goto clear_reset; + } + + ixgbe_down(adapter); + + /* + * Setup new Tx resources and free the old Tx resources in that order. + * We can then assign the new resources to the rings via a memcpy. + * The advantage to this approach is that we are guaranteed to still + * have resources even in the case of an allocation failure. + */ + if (new_tx_count != adapter->tx_ring_count) { + for (i = 0; i < adapter->num_tx_queues; i++) { + memcpy(&temp_ring[i], adapter->tx_ring[i], + sizeof(struct ixgbe_ring)); + + temp_ring[i].count = new_tx_count; + err = ixgbe_setup_tx_resources(&temp_ring[i]); + if (err) { + while (i) { + i--; + ixgbe_free_tx_resources(&temp_ring[i]); + } + goto err_setup; + } + } + + for (j = 0; j < adapter->num_xdp_queues; j++, i++) { + memcpy(&temp_ring[i], adapter->xdp_ring[j], + sizeof(struct ixgbe_ring)); + + temp_ring[i].count = new_tx_count; + err = ixgbe_setup_tx_resources(&temp_ring[i]); + if (err) { + while (i) { + i--; + ixgbe_free_tx_resources(&temp_ring[i]); + } + goto err_setup; + } + } + + for (i = 0; i < adapter->num_tx_queues; i++) { + ixgbe_free_tx_resources(adapter->tx_ring[i]); + + memcpy(adapter->tx_ring[i], &temp_ring[i], + sizeof(struct ixgbe_ring)); + } + for (j = 0; j < adapter->num_xdp_queues; j++, i++) { + ixgbe_free_tx_resources(adapter->xdp_ring[j]); + + memcpy(adapter->xdp_ring[j], &temp_ring[i], + sizeof(struct ixgbe_ring)); + } + + adapter->tx_ring_count = new_tx_count; + } + + /* Repeat the process for the Rx rings if needed */ + if (new_rx_count != adapter->rx_ring_count) { + for (i = 0; i < adapter->num_rx_queues; i++) { + memcpy(&temp_ring[i], adapter->rx_ring[i], + sizeof(struct ixgbe_ring)); + + /* Clear copied XDP RX-queue info */ + memset(&temp_ring[i].xdp_rxq, 0, + sizeof(temp_ring[i].xdp_rxq)); + + temp_ring[i].count = new_rx_count; + err = ixgbe_setup_rx_resources(adapter, &temp_ring[i]); + if (err) { + while (i) { + i--; + ixgbe_free_rx_resources(&temp_ring[i]); + } + goto err_setup; + } + + } + + for (i = 0; i < adapter->num_rx_queues; i++) { + ixgbe_free_rx_resources(adapter->rx_ring[i]); + + memcpy(adapter->rx_ring[i], &temp_ring[i], + sizeof(struct ixgbe_ring)); + } + + adapter->rx_ring_count = new_rx_count; + } + +err_setup: + ixgbe_up(adapter); + vfree(temp_ring); +clear_reset: + clear_bit(__IXGBE_RESETTING, &adapter->state); + return err; +} + +static int ixgbe_get_sset_count(struct net_device *netdev, int sset) +{ + switch (sset) { + case ETH_SS_TEST: + return IXGBE_TEST_LEN; + case ETH_SS_STATS: + return IXGBE_STATS_LEN; + case ETH_SS_PRIV_FLAGS: + return IXGBE_PRIV_FLAGS_STR_LEN; + default: + return -EOPNOTSUPP; + } +} + +static void ixgbe_get_ethtool_stats(struct net_device *netdev, + struct ethtool_stats *stats, u64 *data) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct rtnl_link_stats64 temp; + const struct rtnl_link_stats64 *net_stats; + unsigned int start; + struct ixgbe_ring *ring; + int i, j; + char *p = NULL; + + ixgbe_update_stats(adapter); + net_stats = dev_get_stats(netdev, &temp); + for (i = 0; i < IXGBE_GLOBAL_STATS_LEN; i++) { + switch (ixgbe_gstrings_stats[i].type) { + case NETDEV_STATS: + p = (char *) net_stats + + ixgbe_gstrings_stats[i].stat_offset; + break; + case IXGBE_STATS: + p = (char *) adapter + + ixgbe_gstrings_stats[i].stat_offset; + break; + default: + data[i] = 0; + continue; + } + + data[i] = (ixgbe_gstrings_stats[i].sizeof_stat == + sizeof(u64)) ? *(u64 *)p : *(u32 *)p; + } + for (j = 0; j < netdev->num_tx_queues; j++) { + ring = adapter->tx_ring[j]; + if (!ring) { + data[i] = 0; + data[i+1] = 0; + i += 2; + continue; + } + + do { + start = u64_stats_fetch_begin_irq(&ring->syncp); + data[i] = ring->stats.packets; + data[i+1] = ring->stats.bytes; + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + i += 2; + } + for (j = 0; j < IXGBE_NUM_RX_QUEUES; j++) { + ring = adapter->rx_ring[j]; + if (!ring) { + data[i] = 0; + data[i+1] = 0; + i += 2; + continue; + } + + do { + start = u64_stats_fetch_begin_irq(&ring->syncp); + data[i] = ring->stats.packets; + data[i+1] = ring->stats.bytes; + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + i += 2; + } + + for (j = 0; j < IXGBE_MAX_PACKET_BUFFERS; j++) { + data[i++] = adapter->stats.pxontxc[j]; + data[i++] = adapter->stats.pxofftxc[j]; + } + for (j = 0; j < IXGBE_MAX_PACKET_BUFFERS; j++) { + data[i++] = adapter->stats.pxonrxc[j]; + data[i++] = adapter->stats.pxoffrxc[j]; + } +} + +static void ixgbe_get_strings(struct net_device *netdev, u32 stringset, + u8 *data) +{ + char *p = (char *)data; + unsigned int i; + + switch (stringset) { + case ETH_SS_TEST: + for (i = 0; i < IXGBE_TEST_LEN; i++) { + memcpy(data, ixgbe_gstrings_test[i], ETH_GSTRING_LEN); + data += ETH_GSTRING_LEN; + } + break; + case ETH_SS_STATS: + for (i = 0; i < IXGBE_GLOBAL_STATS_LEN; i++) { + memcpy(p, ixgbe_gstrings_stats[i].stat_string, + ETH_GSTRING_LEN); + p += ETH_GSTRING_LEN; + } + for (i = 0; i < netdev->num_tx_queues; i++) { + sprintf(p, "tx_queue_%u_packets", i); + p += ETH_GSTRING_LEN; + sprintf(p, "tx_queue_%u_bytes", i); + p += ETH_GSTRING_LEN; + } + for (i = 0; i < IXGBE_NUM_RX_QUEUES; i++) { + sprintf(p, "rx_queue_%u_packets", i); + p += ETH_GSTRING_LEN; + sprintf(p, "rx_queue_%u_bytes", i); + p += ETH_GSTRING_LEN; + } + for (i = 0; i < IXGBE_MAX_PACKET_BUFFERS; i++) { + sprintf(p, "tx_pb_%u_pxon", i); + p += ETH_GSTRING_LEN; + sprintf(p, "tx_pb_%u_pxoff", i); + p += ETH_GSTRING_LEN; + } + for (i = 0; i < IXGBE_MAX_PACKET_BUFFERS; i++) { + sprintf(p, "rx_pb_%u_pxon", i); + p += ETH_GSTRING_LEN; + sprintf(p, "rx_pb_%u_pxoff", i); + p += ETH_GSTRING_LEN; + } + /* BUG_ON(p - data != IXGBE_STATS_LEN * ETH_GSTRING_LEN); */ + break; + case ETH_SS_PRIV_FLAGS: + memcpy(data, ixgbe_priv_flags_strings, + IXGBE_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN); + } +} + +static int ixgbe_link_test(struct ixgbe_adapter *adapter, u64 *data) +{ + struct ixgbe_hw *hw = &adapter->hw; + bool link_up; + u32 link_speed = 0; + + if (ixgbe_removed(hw->hw_addr)) { + *data = 1; + return 1; + } + *data = 0; + + hw->mac.ops.check_link(hw, &link_speed, &link_up, true); + if (link_up) + return *data; + else + *data = 1; + return *data; +} + +/* ethtool register test data */ +struct ixgbe_reg_test { + u16 reg; + u8 array_len; + u8 test_type; + u32 mask; + u32 write; +}; + +/* In the hardware, registers are laid out either singly, in arrays + * spaced 0x40 bytes apart, or in contiguous tables. We assume + * most tests take place on arrays or single registers (handled + * as a single-element array) and special-case the tables. + * Table tests are always pattern tests. + * + * We also make provision for some required setup steps by specifying + * registers to be written without any read-back testing. + */ + +#define PATTERN_TEST 1 +#define SET_READ_TEST 2 +#define WRITE_NO_TEST 3 +#define TABLE32_TEST 4 +#define TABLE64_TEST_LO 5 +#define TABLE64_TEST_HI 6 + +/* default 82599 register test */ +static const struct ixgbe_reg_test reg_test_82599[] = { + { IXGBE_FCRTL_82599(0), 1, PATTERN_TEST, 0x8007FFF0, 0x8007FFF0 }, + { IXGBE_FCRTH_82599(0), 1, PATTERN_TEST, 0x8007FFF0, 0x8007FFF0 }, + { IXGBE_PFCTOP, 1, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { IXGBE_VLNCTRL, 1, PATTERN_TEST, 0x00000000, 0x00000000 }, + { IXGBE_RDBAL(0), 4, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFF80 }, + { IXGBE_RDBAH(0), 4, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { IXGBE_RDLEN(0), 4, PATTERN_TEST, 0x000FFF80, 0x000FFFFF }, + { IXGBE_RXDCTL(0), 4, WRITE_NO_TEST, 0, IXGBE_RXDCTL_ENABLE }, + { IXGBE_RDT(0), 4, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF }, + { IXGBE_RXDCTL(0), 4, WRITE_NO_TEST, 0, 0 }, + { IXGBE_FCRTH(0), 1, PATTERN_TEST, 0x8007FFF0, 0x8007FFF0 }, + { IXGBE_FCTTV(0), 1, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { IXGBE_TDBAL(0), 4, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFFFF }, + { IXGBE_TDBAH(0), 4, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { IXGBE_TDLEN(0), 4, PATTERN_TEST, 0x000FFF80, 0x000FFF80 }, + { IXGBE_RXCTRL, 1, SET_READ_TEST, 0x00000001, 0x00000001 }, + { IXGBE_RAL(0), 16, TABLE64_TEST_LO, 0xFFFFFFFF, 0xFFFFFFFF }, + { IXGBE_RAL(0), 16, TABLE64_TEST_HI, 0x8001FFFF, 0x800CFFFF }, + { IXGBE_MTA(0), 128, TABLE32_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { .reg = 0 } +}; + +/* default 82598 register test */ +static const struct ixgbe_reg_test reg_test_82598[] = { + { IXGBE_FCRTL(0), 1, PATTERN_TEST, 0x8007FFF0, 0x8007FFF0 }, + { IXGBE_FCRTH(0), 1, PATTERN_TEST, 0x8007FFF0, 0x8007FFF0 }, + { IXGBE_PFCTOP, 1, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { IXGBE_VLNCTRL, 1, PATTERN_TEST, 0x00000000, 0x00000000 }, + { IXGBE_RDBAL(0), 4, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFFFF }, + { IXGBE_RDBAH(0), 4, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { IXGBE_RDLEN(0), 4, PATTERN_TEST, 0x000FFF80, 0x000FFFFF }, + /* Enable all four RX queues before testing. */ + { IXGBE_RXDCTL(0), 4, WRITE_NO_TEST, 0, IXGBE_RXDCTL_ENABLE }, + /* RDH is read-only for 82598, only test RDT. */ + { IXGBE_RDT(0), 4, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF }, + { IXGBE_RXDCTL(0), 4, WRITE_NO_TEST, 0, 0 }, + { IXGBE_FCRTH(0), 1, PATTERN_TEST, 0x8007FFF0, 0x8007FFF0 }, + { IXGBE_FCTTV(0), 1, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { IXGBE_TIPG, 1, PATTERN_TEST, 0x000000FF, 0x000000FF }, + { IXGBE_TDBAL(0), 4, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFFFF }, + { IXGBE_TDBAH(0), 4, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { IXGBE_TDLEN(0), 4, PATTERN_TEST, 0x000FFF80, 0x000FFFFF }, + { IXGBE_RXCTRL, 1, SET_READ_TEST, 0x00000003, 0x00000003 }, + { IXGBE_DTXCTL, 1, SET_READ_TEST, 0x00000005, 0x00000005 }, + { IXGBE_RAL(0), 16, TABLE64_TEST_LO, 0xFFFFFFFF, 0xFFFFFFFF }, + { IXGBE_RAL(0), 16, TABLE64_TEST_HI, 0x800CFFFF, 0x800CFFFF }, + { IXGBE_MTA(0), 128, TABLE32_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { .reg = 0 } +}; + +static bool reg_pattern_test(struct ixgbe_adapter *adapter, u64 *data, int reg, + u32 mask, u32 write) +{ + u32 pat, val, before; + static const u32 test_pattern[] = { + 0x5A5A5A5A, 0xA5A5A5A5, 0x00000000, 0xFFFFFFFF}; + + if (ixgbe_removed(adapter->hw.hw_addr)) { + *data = 1; + return true; + } + for (pat = 0; pat < ARRAY_SIZE(test_pattern); pat++) { + before = ixgbe_read_reg(&adapter->hw, reg); + ixgbe_write_reg(&adapter->hw, reg, test_pattern[pat] & write); + val = ixgbe_read_reg(&adapter->hw, reg); + if (val != (test_pattern[pat] & write & mask)) { + e_err(drv, "pattern test reg %04X failed: got 0x%08X expected 0x%08X\n", + reg, val, (test_pattern[pat] & write & mask)); + *data = reg; + ixgbe_write_reg(&adapter->hw, reg, before); + return true; + } + ixgbe_write_reg(&adapter->hw, reg, before); + } + return false; +} + +static bool reg_set_and_check(struct ixgbe_adapter *adapter, u64 *data, int reg, + u32 mask, u32 write) +{ + u32 val, before; + + if (ixgbe_removed(adapter->hw.hw_addr)) { + *data = 1; + return true; + } + before = ixgbe_read_reg(&adapter->hw, reg); + ixgbe_write_reg(&adapter->hw, reg, write & mask); + val = ixgbe_read_reg(&adapter->hw, reg); + if ((write & mask) != (val & mask)) { + e_err(drv, "set/check reg %04X test failed: got 0x%08X expected 0x%08X\n", + reg, (val & mask), (write & mask)); + *data = reg; + ixgbe_write_reg(&adapter->hw, reg, before); + return true; + } + ixgbe_write_reg(&adapter->hw, reg, before); + return false; +} + +static int ixgbe_reg_test(struct ixgbe_adapter *adapter, u64 *data) +{ + const struct ixgbe_reg_test *test; + u32 value, before, after; + u32 i, toggle; + + if (ixgbe_removed(adapter->hw.hw_addr)) { + e_err(drv, "Adapter removed - register test blocked\n"); + *data = 1; + return 1; + } + switch (adapter->hw.mac.type) { + case ixgbe_mac_82598EB: + toggle = 0x7FFFF3FF; + test = reg_test_82598; + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + toggle = 0x7FFFF30F; + test = reg_test_82599; + break; + default: + *data = 1; + return 1; + } + + /* + * Because the status register is such a special case, + * we handle it separately from the rest of the register + * tests. Some bits are read-only, some toggle, and some + * are writeable on newer MACs. + */ + before = ixgbe_read_reg(&adapter->hw, IXGBE_STATUS); + value = (ixgbe_read_reg(&adapter->hw, IXGBE_STATUS) & toggle); + ixgbe_write_reg(&adapter->hw, IXGBE_STATUS, toggle); + after = ixgbe_read_reg(&adapter->hw, IXGBE_STATUS) & toggle; + if (value != after) { + e_err(drv, "failed STATUS register test got: 0x%08X expected: 0x%08X\n", + after, value); + *data = 1; + return 1; + } + /* restore previous status */ + ixgbe_write_reg(&adapter->hw, IXGBE_STATUS, before); + + /* + * Perform the remainder of the register test, looping through + * the test table until we either fail or reach the null entry. + */ + while (test->reg) { + for (i = 0; i < test->array_len; i++) { + bool b = false; + + switch (test->test_type) { + case PATTERN_TEST: + b = reg_pattern_test(adapter, data, + test->reg + (i * 0x40), + test->mask, + test->write); + break; + case SET_READ_TEST: + b = reg_set_and_check(adapter, data, + test->reg + (i * 0x40), + test->mask, + test->write); + break; + case WRITE_NO_TEST: + ixgbe_write_reg(&adapter->hw, + test->reg + (i * 0x40), + test->write); + break; + case TABLE32_TEST: + b = reg_pattern_test(adapter, data, + test->reg + (i * 4), + test->mask, + test->write); + break; + case TABLE64_TEST_LO: + b = reg_pattern_test(adapter, data, + test->reg + (i * 8), + test->mask, + test->write); + break; + case TABLE64_TEST_HI: + b = reg_pattern_test(adapter, data, + (test->reg + 4) + (i * 8), + test->mask, + test->write); + break; + } + if (b) + return 1; + } + test++; + } + + *data = 0; + return 0; +} + +static int ixgbe_eeprom_test(struct ixgbe_adapter *adapter, u64 *data) +{ + struct ixgbe_hw *hw = &adapter->hw; + if (hw->eeprom.ops.validate_checksum(hw, NULL)) + *data = 1; + else + *data = 0; + return *data; +} + +static irqreturn_t ixgbe_test_intr(int irq, void *data) +{ + struct net_device *netdev = (struct net_device *) data; + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + adapter->test_icr |= IXGBE_READ_REG(&adapter->hw, IXGBE_EICR); + + return IRQ_HANDLED; +} + +static int ixgbe_intr_test(struct ixgbe_adapter *adapter, u64 *data) +{ + struct net_device *netdev = adapter->netdev; + u32 mask, i = 0, shared_int = true; + u32 irq = adapter->pdev->irq; + + *data = 0; + + /* Hook up test interrupt handler just for this test */ + if (adapter->msix_entries) { + /* NOTE: we don't test MSI-X interrupts here, yet */ + return 0; + } else if (adapter->flags & IXGBE_FLAG_MSI_ENABLED) { + shared_int = false; + if (request_irq(irq, ixgbe_test_intr, 0, netdev->name, + netdev)) { + *data = 1; + return -1; + } + } else if (!request_irq(irq, ixgbe_test_intr, IRQF_PROBE_SHARED, + netdev->name, netdev)) { + shared_int = false; + } else if (request_irq(irq, ixgbe_test_intr, IRQF_SHARED, + netdev->name, netdev)) { + *data = 1; + return -1; + } + e_info(hw, "testing %s interrupt\n", shared_int ? + "shared" : "unshared"); + + /* Disable all the interrupts */ + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, 0xFFFFFFFF); + IXGBE_WRITE_FLUSH(&adapter->hw); + usleep_range(10000, 20000); + + /* Test each interrupt */ + for (; i < 10; i++) { + /* Interrupt to test */ + mask = BIT(i); + + if (!shared_int) { + /* + * Disable the interrupts to be reported in + * the cause register and then force the same + * interrupt and see if one gets posted. If + * an interrupt was posted to the bus, the + * test failed. + */ + adapter->test_icr = 0; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, + ~mask & 0x00007FFF); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS, + ~mask & 0x00007FFF); + IXGBE_WRITE_FLUSH(&adapter->hw); + usleep_range(10000, 20000); + + if (adapter->test_icr & mask) { + *data = 3; + break; + } + } + + /* + * Enable the interrupt to be reported in the cause + * register and then force the same interrupt and see + * if one gets posted. If an interrupt was not posted + * to the bus, the test failed. + */ + adapter->test_icr = 0; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMS, mask); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS, mask); + IXGBE_WRITE_FLUSH(&adapter->hw); + usleep_range(10000, 20000); + + if (!(adapter->test_icr & mask)) { + *data = 4; + break; + } + + if (!shared_int) { + /* + * Disable the other interrupts to be reported in + * the cause register and then force the other + * interrupts and see if any get posted. If + * an interrupt was posted to the bus, the + * test failed. + */ + adapter->test_icr = 0; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, + ~mask & 0x00007FFF); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS, + ~mask & 0x00007FFF); + IXGBE_WRITE_FLUSH(&adapter->hw); + usleep_range(10000, 20000); + + if (adapter->test_icr) { + *data = 5; + break; + } + } + } + + /* Disable all the interrupts */ + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, 0xFFFFFFFF); + IXGBE_WRITE_FLUSH(&adapter->hw); + usleep_range(10000, 20000); + + /* Unhook test interrupt handler */ + free_irq(irq, netdev); + + return *data; +} + +static void ixgbe_free_desc_rings(struct ixgbe_adapter *adapter) +{ + /* Shut down the DMA engines now so they can be reinitialized later, + * since the test rings and normally used rings should overlap on + * queue 0 we can just use the standard disable Rx/Tx calls and they + * will take care of disabling the test rings for us. + */ + + /* first Rx */ + ixgbe_disable_rx(adapter); + + /* now Tx */ + ixgbe_disable_tx(adapter); + + ixgbe_reset(adapter); + + ixgbe_free_tx_resources(&adapter->test_tx_ring); + ixgbe_free_rx_resources(&adapter->test_rx_ring); +} + +static int ixgbe_setup_desc_rings(struct ixgbe_adapter *adapter) +{ + struct ixgbe_ring *tx_ring = &adapter->test_tx_ring; + struct ixgbe_ring *rx_ring = &adapter->test_rx_ring; + struct ixgbe_hw *hw = &adapter->hw; + u32 rctl, reg_data; + int ret_val; + int err; + + /* Setup Tx descriptor ring and Tx buffers */ + tx_ring->count = IXGBE_DEFAULT_TXD; + tx_ring->queue_index = 0; + tx_ring->dev = &adapter->pdev->dev; + tx_ring->netdev = adapter->netdev; + tx_ring->reg_idx = adapter->tx_ring[0]->reg_idx; + + err = ixgbe_setup_tx_resources(tx_ring); + if (err) + return 1; + + switch (adapter->hw.mac.type) { + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + reg_data = IXGBE_READ_REG(&adapter->hw, IXGBE_DMATXCTL); + reg_data |= IXGBE_DMATXCTL_TE; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_DMATXCTL, reg_data); + break; + default: + break; + } + + ixgbe_configure_tx_ring(adapter, tx_ring); + + /* Setup Rx Descriptor ring and Rx buffers */ + rx_ring->count = IXGBE_DEFAULT_RXD; + rx_ring->queue_index = 0; + rx_ring->dev = &adapter->pdev->dev; + rx_ring->netdev = adapter->netdev; + rx_ring->reg_idx = adapter->rx_ring[0]->reg_idx; + + err = ixgbe_setup_rx_resources(adapter, rx_ring); + if (err) { + ret_val = 4; + goto err_nomem; + } + + hw->mac.ops.disable_rx(hw); + + ixgbe_configure_rx_ring(adapter, rx_ring); + + rctl = IXGBE_READ_REG(&adapter->hw, IXGBE_RXCTRL); + rctl |= IXGBE_RXCTRL_DMBYPS; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_RXCTRL, rctl); + + hw->mac.ops.enable_rx(hw); + + return 0; + +err_nomem: + ixgbe_free_desc_rings(adapter); + return ret_val; +} + +static int ixgbe_setup_loopback_test(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 reg_data; + + + /* Setup MAC loopback */ + reg_data = IXGBE_READ_REG(hw, IXGBE_HLREG0); + reg_data |= IXGBE_HLREG0_LPBK; + IXGBE_WRITE_REG(hw, IXGBE_HLREG0, reg_data); + + reg_data = IXGBE_READ_REG(hw, IXGBE_FCTRL); + reg_data |= IXGBE_FCTRL_BAM | IXGBE_FCTRL_SBP | IXGBE_FCTRL_MPE; + IXGBE_WRITE_REG(hw, IXGBE_FCTRL, reg_data); + + /* X540 and X550 needs to set the MACC.FLU bit to force link up */ + switch (adapter->hw.mac.type) { + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + reg_data = IXGBE_READ_REG(hw, IXGBE_MACC); + reg_data |= IXGBE_MACC_FLU; + IXGBE_WRITE_REG(hw, IXGBE_MACC, reg_data); + break; + default: + if (hw->mac.orig_autoc) { + reg_data = hw->mac.orig_autoc | IXGBE_AUTOC_FLU; + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, reg_data); + } else { + return 10; + } + } + IXGBE_WRITE_FLUSH(hw); + usleep_range(10000, 20000); + + /* Disable Atlas Tx lanes; re-enabled in reset path */ + if (hw->mac.type == ixgbe_mac_82598EB) { + u8 atlas; + + hw->mac.ops.read_analog_reg8(hw, IXGBE_ATLAS_PDN_LPBK, &atlas); + atlas |= IXGBE_ATLAS_PDN_TX_REG_EN; + hw->mac.ops.write_analog_reg8(hw, IXGBE_ATLAS_PDN_LPBK, atlas); + + hw->mac.ops.read_analog_reg8(hw, IXGBE_ATLAS_PDN_10G, &atlas); + atlas |= IXGBE_ATLAS_PDN_TX_10G_QL_ALL; + hw->mac.ops.write_analog_reg8(hw, IXGBE_ATLAS_PDN_10G, atlas); + + hw->mac.ops.read_analog_reg8(hw, IXGBE_ATLAS_PDN_1G, &atlas); + atlas |= IXGBE_ATLAS_PDN_TX_1G_QL_ALL; + hw->mac.ops.write_analog_reg8(hw, IXGBE_ATLAS_PDN_1G, atlas); + + hw->mac.ops.read_analog_reg8(hw, IXGBE_ATLAS_PDN_AN, &atlas); + atlas |= IXGBE_ATLAS_PDN_TX_AN_QL_ALL; + hw->mac.ops.write_analog_reg8(hw, IXGBE_ATLAS_PDN_AN, atlas); + } + + return 0; +} + +static void ixgbe_loopback_cleanup(struct ixgbe_adapter *adapter) +{ + u32 reg_data; + + reg_data = IXGBE_READ_REG(&adapter->hw, IXGBE_HLREG0); + reg_data &= ~IXGBE_HLREG0_LPBK; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_HLREG0, reg_data); +} + +static void ixgbe_create_lbtest_frame(struct sk_buff *skb, + unsigned int frame_size) +{ + memset(skb->data, 0xFF, frame_size); + frame_size >>= 1; + memset(&skb->data[frame_size], 0xAA, frame_size / 2 - 1); + skb->data[frame_size + 10] = 0xBE; + skb->data[frame_size + 12] = 0xAF; +} + +static bool ixgbe_check_lbtest_frame(struct ixgbe_rx_buffer *rx_buffer, + unsigned int frame_size) +{ + unsigned char *data; + bool match = true; + + frame_size >>= 1; + + data = kmap(rx_buffer->page) + rx_buffer->page_offset; + + if (data[3] != 0xFF || + data[frame_size + 10] != 0xBE || + data[frame_size + 12] != 0xAF) + match = false; + + kunmap(rx_buffer->page); + + return match; +} + +static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring, + struct ixgbe_ring *tx_ring, + unsigned int size) +{ + union ixgbe_adv_rx_desc *rx_desc; + u16 rx_ntc, tx_ntc, count = 0; + + /* initialize next to clean and descriptor values */ + rx_ntc = rx_ring->next_to_clean; + tx_ntc = tx_ring->next_to_clean; + rx_desc = IXGBE_RX_DESC(rx_ring, rx_ntc); + + while (tx_ntc != tx_ring->next_to_use) { + union ixgbe_adv_tx_desc *tx_desc; + struct ixgbe_tx_buffer *tx_buffer; + + tx_desc = IXGBE_TX_DESC(tx_ring, tx_ntc); + + /* if DD is not set transmit has not completed */ + if (!(tx_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD))) + return count; + + /* unmap buffer on Tx side */ + tx_buffer = &tx_ring->tx_buffer_info[tx_ntc]; + + /* Free all the Tx ring sk_buffs */ + dev_kfree_skb_any(tx_buffer->skb); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + + /* increment Tx next to clean counter */ + tx_ntc++; + if (tx_ntc == tx_ring->count) + tx_ntc = 0; + } + + while (rx_desc->wb.upper.length) { + struct ixgbe_rx_buffer *rx_buffer; + + /* check Rx buffer */ + rx_buffer = &rx_ring->rx_buffer_info[rx_ntc]; + + /* sync Rx buffer for CPU read */ + dma_sync_single_for_cpu(rx_ring->dev, + rx_buffer->dma, + ixgbe_rx_bufsz(rx_ring), + DMA_FROM_DEVICE); + + /* verify contents of skb */ + if (ixgbe_check_lbtest_frame(rx_buffer, size)) + count++; + else + break; + + /* sync Rx buffer for device write */ + dma_sync_single_for_device(rx_ring->dev, + rx_buffer->dma, + ixgbe_rx_bufsz(rx_ring), + DMA_FROM_DEVICE); + + /* increment Rx next to clean counter */ + rx_ntc++; + if (rx_ntc == rx_ring->count) + rx_ntc = 0; + + /* fetch next descriptor */ + rx_desc = IXGBE_RX_DESC(rx_ring, rx_ntc); + } + + netdev_tx_reset_queue(txring_txq(tx_ring)); + + /* re-map buffers to ring, store next to clean values */ + ixgbe_alloc_rx_buffers(rx_ring, count); + rx_ring->next_to_clean = rx_ntc; + tx_ring->next_to_clean = tx_ntc; + + return count; +} + +static int ixgbe_run_loopback_test(struct ixgbe_adapter *adapter) +{ + struct ixgbe_ring *tx_ring = &adapter->test_tx_ring; + struct ixgbe_ring *rx_ring = &adapter->test_rx_ring; + int i, j, lc, good_cnt, ret_val = 0; + unsigned int size = 1024; + netdev_tx_t tx_ret_val; + struct sk_buff *skb; + u32 flags_orig = adapter->flags; + + /* DCB can modify the frames on Tx */ + adapter->flags &= ~IXGBE_FLAG_DCB_ENABLED; + + /* allocate test skb */ + skb = alloc_skb(size, GFP_KERNEL); + if (!skb) + return 11; + + /* place data into test skb */ + ixgbe_create_lbtest_frame(skb, size); + skb_put(skb, size); + + /* + * Calculate the loop count based on the largest descriptor ring + * The idea is to wrap the largest ring a number of times using 64 + * send/receive pairs during each loop + */ + + if (rx_ring->count <= tx_ring->count) + lc = ((tx_ring->count / 64) * 2) + 1; + else + lc = ((rx_ring->count / 64) * 2) + 1; + + for (j = 0; j <= lc; j++) { + /* reset count of good packets */ + good_cnt = 0; + + /* place 64 packets on the transmit queue*/ + for (i = 0; i < 64; i++) { + skb_get(skb); + tx_ret_val = ixgbe_xmit_frame_ring(skb, + adapter, + tx_ring); + if (tx_ret_val == NETDEV_TX_OK) + good_cnt++; + } + + if (good_cnt != 64) { + ret_val = 12; + break; + } + + /* allow 200 milliseconds for packets to go from Tx to Rx */ + msleep(200); + + good_cnt = ixgbe_clean_test_rings(rx_ring, tx_ring, size); + if (good_cnt != 64) { + ret_val = 13; + break; + } + } + + /* free the original skb */ + kfree_skb(skb); + adapter->flags = flags_orig; + + return ret_val; +} + +static int ixgbe_loopback_test(struct ixgbe_adapter *adapter, u64 *data) +{ + *data = ixgbe_setup_desc_rings(adapter); + if (*data) + goto out; + *data = ixgbe_setup_loopback_test(adapter); + if (*data) + goto err_loopback; + *data = ixgbe_run_loopback_test(adapter); + ixgbe_loopback_cleanup(adapter); + +err_loopback: + ixgbe_free_desc_rings(adapter); +out: + return *data; +} + +static void ixgbe_diag_test(struct net_device *netdev, + struct ethtool_test *eth_test, u64 *data) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + bool if_running = netif_running(netdev); + + if (ixgbe_removed(adapter->hw.hw_addr)) { + e_err(hw, "Adapter removed - test blocked\n"); + data[0] = 1; + data[1] = 1; + data[2] = 1; + data[3] = 1; + data[4] = 1; + eth_test->flags |= ETH_TEST_FL_FAILED; + return; + } + set_bit(__IXGBE_TESTING, &adapter->state); + if (eth_test->flags == ETH_TEST_FL_OFFLINE) { + struct ixgbe_hw *hw = &adapter->hw; + + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { + int i; + for (i = 0; i < adapter->num_vfs; i++) { + if (adapter->vfinfo[i].clear_to_send) { + netdev_warn(netdev, "offline diagnostic is not supported when VFs are present\n"); + data[0] = 1; + data[1] = 1; + data[2] = 1; + data[3] = 1; + data[4] = 1; + eth_test->flags |= ETH_TEST_FL_FAILED; + clear_bit(__IXGBE_TESTING, + &adapter->state); + return; + } + } + } + + /* Offline tests */ + e_info(hw, "offline testing starting\n"); + + /* Link test performed before hardware reset so autoneg doesn't + * interfere with test result + */ + if (ixgbe_link_test(adapter, &data[4])) + eth_test->flags |= ETH_TEST_FL_FAILED; + + if (if_running) + /* indicate we're in test mode */ + ixgbe_close(netdev); + else + ixgbe_reset(adapter); + + e_info(hw, "register testing starting\n"); + if (ixgbe_reg_test(adapter, &data[0])) + eth_test->flags |= ETH_TEST_FL_FAILED; + + ixgbe_reset(adapter); + e_info(hw, "eeprom testing starting\n"); + if (ixgbe_eeprom_test(adapter, &data[1])) + eth_test->flags |= ETH_TEST_FL_FAILED; + + ixgbe_reset(adapter); + e_info(hw, "interrupt testing starting\n"); + if (ixgbe_intr_test(adapter, &data[2])) + eth_test->flags |= ETH_TEST_FL_FAILED; + + /* If SRIOV or VMDq is enabled then skip MAC + * loopback diagnostic. */ + if (adapter->flags & (IXGBE_FLAG_SRIOV_ENABLED | + IXGBE_FLAG_VMDQ_ENABLED)) { + e_info(hw, "Skip MAC loopback diagnostic in VT mode\n"); + data[3] = 0; + goto skip_loopback; + } + + ixgbe_reset(adapter); + e_info(hw, "loopback testing starting\n"); + if (ixgbe_loopback_test(adapter, &data[3])) + eth_test->flags |= ETH_TEST_FL_FAILED; + +skip_loopback: + ixgbe_reset(adapter); + + /* clear testing bit and return adapter to previous state */ + clear_bit(__IXGBE_TESTING, &adapter->state); + if (if_running) + ixgbe_open(netdev); + else if (hw->mac.ops.disable_tx_laser) + hw->mac.ops.disable_tx_laser(hw); + } else { + e_info(hw, "online testing starting\n"); + + /* Online tests */ + if (ixgbe_link_test(adapter, &data[4])) + eth_test->flags |= ETH_TEST_FL_FAILED; + + /* Offline tests aren't run; pass by default */ + data[0] = 0; + data[1] = 0; + data[2] = 0; + data[3] = 0; + + clear_bit(__IXGBE_TESTING, &adapter->state); + } +} + +static int ixgbe_wol_exclusion(struct ixgbe_adapter *adapter, + struct ethtool_wolinfo *wol) +{ + struct ixgbe_hw *hw = &adapter->hw; + int retval = 0; + + /* WOL not supported for all devices */ + if (!ixgbe_wol_supported(adapter, hw->device_id, + hw->subsystem_device_id)) { + retval = 1; + wol->supported = 0; + } + + return retval; +} + +static void ixgbe_get_wol(struct net_device *netdev, + struct ethtool_wolinfo *wol) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + wol->supported = WAKE_UCAST | WAKE_MCAST | + WAKE_BCAST | WAKE_MAGIC; + wol->wolopts = 0; + + if (ixgbe_wol_exclusion(adapter, wol) || + !device_can_wakeup(&adapter->pdev->dev)) + return; + + if (adapter->wol & IXGBE_WUFC_EX) + wol->wolopts |= WAKE_UCAST; + if (adapter->wol & IXGBE_WUFC_MC) + wol->wolopts |= WAKE_MCAST; + if (adapter->wol & IXGBE_WUFC_BC) + wol->wolopts |= WAKE_BCAST; + if (adapter->wol & IXGBE_WUFC_MAG) + wol->wolopts |= WAKE_MAGIC; +} + +static int ixgbe_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + if (wol->wolopts & (WAKE_PHY | WAKE_ARP | WAKE_MAGICSECURE | + WAKE_FILTER)) + return -EOPNOTSUPP; + + if (ixgbe_wol_exclusion(adapter, wol)) + return wol->wolopts ? -EOPNOTSUPP : 0; + + adapter->wol = 0; + + if (wol->wolopts & WAKE_UCAST) + adapter->wol |= IXGBE_WUFC_EX; + if (wol->wolopts & WAKE_MCAST) + adapter->wol |= IXGBE_WUFC_MC; + if (wol->wolopts & WAKE_BCAST) + adapter->wol |= IXGBE_WUFC_BC; + if (wol->wolopts & WAKE_MAGIC) + adapter->wol |= IXGBE_WUFC_MAG; + + device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol); + + return 0; +} + +static int ixgbe_nway_reset(struct net_device *netdev) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + if (netif_running(netdev)) + ixgbe_reinit_locked(adapter); + + return 0; +} + +static int ixgbe_set_phys_id(struct net_device *netdev, + enum ethtool_phys_id_state state) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + + if (!hw->mac.ops.led_on || !hw->mac.ops.led_off) + return -EOPNOTSUPP; + + switch (state) { + case ETHTOOL_ID_ACTIVE: + adapter->led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); + return 2; + + case ETHTOOL_ID_ON: + hw->mac.ops.led_on(hw, hw->mac.led_link_act); + break; + + case ETHTOOL_ID_OFF: + hw->mac.ops.led_off(hw, hw->mac.led_link_act); + break; + + case ETHTOOL_ID_INACTIVE: + /* Restore LED settings */ + IXGBE_WRITE_REG(&adapter->hw, IXGBE_LEDCTL, adapter->led_reg); + break; + } + + return 0; +} + +static int ixgbe_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + /* only valid if in constant ITR mode */ + if (adapter->rx_itr_setting <= 1) + ec->rx_coalesce_usecs = adapter->rx_itr_setting; + else + ec->rx_coalesce_usecs = adapter->rx_itr_setting >> 2; + + /* if in mixed tx/rx queues per vector mode, report only rx settings */ + if (adapter->q_vector[0]->tx.count && adapter->q_vector[0]->rx.count) + return 0; + + /* only valid if in constant ITR mode */ + if (adapter->tx_itr_setting <= 1) + ec->tx_coalesce_usecs = adapter->tx_itr_setting; + else + ec->tx_coalesce_usecs = adapter->tx_itr_setting >> 2; + + return 0; +} + +/* + * this function must be called before setting the new value of + * rx_itr_setting + */ +static bool ixgbe_update_rsc(struct ixgbe_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + + /* nothing to do if LRO or RSC are not enabled */ + if (!(adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE) || + !(netdev->features & NETIF_F_LRO)) + return false; + + /* check the feature flag value and enable RSC if necessary */ + if (adapter->rx_itr_setting == 1 || + adapter->rx_itr_setting > IXGBE_MIN_RSC_ITR) { + if (!(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)) { + adapter->flags2 |= IXGBE_FLAG2_RSC_ENABLED; + e_info(probe, "rx-usecs value high enough to re-enable RSC\n"); + return true; + } + /* if interrupt rate is too high then disable RSC */ + } else if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) { + adapter->flags2 &= ~IXGBE_FLAG2_RSC_ENABLED; + e_info(probe, "rx-usecs set too low, disabling RSC\n"); + return true; + } + return false; +} + +static int ixgbe_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_q_vector *q_vector; + int i; + u16 tx_itr_param, rx_itr_param, tx_itr_prev; + bool need_reset = false; + + if (adapter->q_vector[0]->tx.count && adapter->q_vector[0]->rx.count) { + /* reject Tx specific changes in case of mixed RxTx vectors */ + if (ec->tx_coalesce_usecs) + return -EINVAL; + tx_itr_prev = adapter->rx_itr_setting; + } else { + tx_itr_prev = adapter->tx_itr_setting; + } + + if ((ec->rx_coalesce_usecs > (IXGBE_MAX_EITR >> 2)) || + (ec->tx_coalesce_usecs > (IXGBE_MAX_EITR >> 2))) + return -EINVAL; + + if (ec->rx_coalesce_usecs > 1) + adapter->rx_itr_setting = ec->rx_coalesce_usecs << 2; + else + adapter->rx_itr_setting = ec->rx_coalesce_usecs; + + if (adapter->rx_itr_setting == 1) + rx_itr_param = IXGBE_20K_ITR; + else + rx_itr_param = adapter->rx_itr_setting; + + if (ec->tx_coalesce_usecs > 1) + adapter->tx_itr_setting = ec->tx_coalesce_usecs << 2; + else + adapter->tx_itr_setting = ec->tx_coalesce_usecs; + + if (adapter->tx_itr_setting == 1) + tx_itr_param = IXGBE_12K_ITR; + else + tx_itr_param = adapter->tx_itr_setting; + + /* mixed Rx/Tx */ + if (adapter->q_vector[0]->tx.count && adapter->q_vector[0]->rx.count) + adapter->tx_itr_setting = adapter->rx_itr_setting; + + /* detect ITR changes that require update of TXDCTL.WTHRESH */ + if ((adapter->tx_itr_setting != 1) && + (adapter->tx_itr_setting < IXGBE_100K_ITR)) { + if ((tx_itr_prev == 1) || + (tx_itr_prev >= IXGBE_100K_ITR)) + need_reset = true; + } else { + if ((tx_itr_prev != 1) && + (tx_itr_prev < IXGBE_100K_ITR)) + need_reset = true; + } + + /* check the old value and enable RSC if necessary */ + need_reset |= ixgbe_update_rsc(adapter); + + for (i = 0; i < adapter->num_q_vectors; i++) { + q_vector = adapter->q_vector[i]; + if (q_vector->tx.count && !q_vector->rx.count) + /* tx only */ + q_vector->itr = tx_itr_param; + else + /* rx only or mixed */ + q_vector->itr = rx_itr_param; + ixgbe_write_eitr(q_vector); + } + + /* + * do reset here at the end to make sure EITR==0 case is handled + * correctly w.r.t stopping tx, and changing TXDCTL.WTHRESH settings + * also locks in RSC enable/disable which requires reset + */ + if (need_reset) + ixgbe_do_reset(netdev); + + return 0; +} + +static int ixgbe_get_ethtool_fdir_entry(struct ixgbe_adapter *adapter, + struct ethtool_rxnfc *cmd) +{ + union ixgbe_atr_input *mask = &adapter->fdir_mask; + struct ethtool_rx_flow_spec *fsp = + (struct ethtool_rx_flow_spec *)&cmd->fs; + struct hlist_node *node2; + struct ixgbe_fdir_filter *rule = NULL; + + /* report total rule count */ + cmd->data = (1024 << adapter->fdir_pballoc) - 2; + + hlist_for_each_entry_safe(rule, node2, + &adapter->fdir_filter_list, fdir_node) { + if (fsp->location <= rule->sw_idx) + break; + } + + if (!rule || fsp->location != rule->sw_idx) + return -EINVAL; + + /* fill out the flow spec entry */ + + /* set flow type field */ + switch (rule->filter.formatted.flow_type) { + case IXGBE_ATR_FLOW_TYPE_TCPV4: + fsp->flow_type = TCP_V4_FLOW; + break; + case IXGBE_ATR_FLOW_TYPE_UDPV4: + fsp->flow_type = UDP_V4_FLOW; + break; + case IXGBE_ATR_FLOW_TYPE_SCTPV4: + fsp->flow_type = SCTP_V4_FLOW; + break; + case IXGBE_ATR_FLOW_TYPE_IPV4: + fsp->flow_type = IP_USER_FLOW; + fsp->h_u.usr_ip4_spec.ip_ver = ETH_RX_NFC_IP4; + fsp->h_u.usr_ip4_spec.proto = 0; + fsp->m_u.usr_ip4_spec.proto = 0; + break; + default: + return -EINVAL; + } + + fsp->h_u.tcp_ip4_spec.psrc = rule->filter.formatted.src_port; + fsp->m_u.tcp_ip4_spec.psrc = mask->formatted.src_port; + fsp->h_u.tcp_ip4_spec.pdst = rule->filter.formatted.dst_port; + fsp->m_u.tcp_ip4_spec.pdst = mask->formatted.dst_port; + fsp->h_u.tcp_ip4_spec.ip4src = rule->filter.formatted.src_ip[0]; + fsp->m_u.tcp_ip4_spec.ip4src = mask->formatted.src_ip[0]; + fsp->h_u.tcp_ip4_spec.ip4dst = rule->filter.formatted.dst_ip[0]; + fsp->m_u.tcp_ip4_spec.ip4dst = mask->formatted.dst_ip[0]; + fsp->h_ext.vlan_tci = rule->filter.formatted.vlan_id; + fsp->m_ext.vlan_tci = mask->formatted.vlan_id; + fsp->h_ext.vlan_etype = rule->filter.formatted.flex_bytes; + fsp->m_ext.vlan_etype = mask->formatted.flex_bytes; + fsp->h_ext.data[1] = htonl(rule->filter.formatted.vm_pool); + fsp->m_ext.data[1] = htonl(mask->formatted.vm_pool); + fsp->flow_type |= FLOW_EXT; + + /* record action */ + if (rule->action == IXGBE_FDIR_DROP_QUEUE) + fsp->ring_cookie = RX_CLS_FLOW_DISC; + else + fsp->ring_cookie = rule->action; + + return 0; +} + +static int ixgbe_get_ethtool_fdir_all(struct ixgbe_adapter *adapter, + struct ethtool_rxnfc *cmd, + u32 *rule_locs) +{ + struct hlist_node *node2; + struct ixgbe_fdir_filter *rule; + int cnt = 0; + + /* report total rule count */ + cmd->data = (1024 << adapter->fdir_pballoc) - 2; + + hlist_for_each_entry_safe(rule, node2, + &adapter->fdir_filter_list, fdir_node) { + if (cnt == cmd->rule_cnt) + return -EMSGSIZE; + rule_locs[cnt] = rule->sw_idx; + cnt++; + } + + cmd->rule_cnt = cnt; + + return 0; +} + +static int ixgbe_get_rss_hash_opts(struct ixgbe_adapter *adapter, + struct ethtool_rxnfc *cmd) +{ + cmd->data = 0; + + /* Report default options for RSS on ixgbe */ + switch (cmd->flow_type) { + case TCP_V4_FLOW: + cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + fallthrough; + case UDP_V4_FLOW: + if (adapter->flags2 & IXGBE_FLAG2_RSS_FIELD_IPV4_UDP) + cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + fallthrough; + case SCTP_V4_FLOW: + case AH_ESP_V4_FLOW: + case AH_V4_FLOW: + case ESP_V4_FLOW: + case IPV4_FLOW: + cmd->data |= RXH_IP_SRC | RXH_IP_DST; + break; + case TCP_V6_FLOW: + cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + fallthrough; + case UDP_V6_FLOW: + if (adapter->flags2 & IXGBE_FLAG2_RSS_FIELD_IPV6_UDP) + cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + fallthrough; + case SCTP_V6_FLOW: + case AH_ESP_V6_FLOW: + case AH_V6_FLOW: + case ESP_V6_FLOW: + case IPV6_FLOW: + cmd->data |= RXH_IP_SRC | RXH_IP_DST; + break; + default: + return -EINVAL; + } + + 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) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + int ret = -EOPNOTSUPP; + + switch (cmd->cmd) { + case ETHTOOL_GRXRINGS: + cmd->data = min_t(int, adapter->num_rx_queues, + ixgbe_rss_indir_tbl_max(adapter)); + ret = 0; + break; + case ETHTOOL_GRXCLSRLCNT: + cmd->rule_cnt = adapter->fdir_filter_count; + ret = 0; + break; + case ETHTOOL_GRXCLSRULE: + ret = ixgbe_get_ethtool_fdir_entry(adapter, cmd); + break; + case ETHTOOL_GRXCLSRLALL: + ret = ixgbe_get_ethtool_fdir_all(adapter, cmd, rule_locs); + break; + case ETHTOOL_GRXFH: + ret = ixgbe_get_rss_hash_opts(adapter, cmd); + break; + default: + break; + } + + return ret; +} + +int ixgbe_update_ethtool_fdir_entry(struct ixgbe_adapter *adapter, + struct ixgbe_fdir_filter *input, + u16 sw_idx) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct hlist_node *node2; + struct ixgbe_fdir_filter *rule, *parent; + int err = -EINVAL; + + parent = NULL; + rule = NULL; + + hlist_for_each_entry_safe(rule, node2, + &adapter->fdir_filter_list, fdir_node) { + /* hash found, or no matching entry */ + if (rule->sw_idx >= sw_idx) + break; + parent = rule; + } + + /* if there is an old rule occupying our place remove it */ + if (rule && (rule->sw_idx == sw_idx)) { + if (!input || (rule->filter.formatted.bkt_hash != + input->filter.formatted.bkt_hash)) { + err = ixgbe_fdir_erase_perfect_filter_82599(hw, + &rule->filter, + sw_idx); + } + + hlist_del(&rule->fdir_node); + kfree(rule); + adapter->fdir_filter_count--; + } + + /* + * If no input this was a delete, err should be 0 if a rule was + * successfully found and removed from the list else -EINVAL + */ + if (!input) + return err; + + /* initialize node and set software index */ + INIT_HLIST_NODE(&input->fdir_node); + + /* add filter to the list */ + if (parent) + hlist_add_behind(&input->fdir_node, &parent->fdir_node); + else + hlist_add_head(&input->fdir_node, + &adapter->fdir_filter_list); + + /* update counts */ + adapter->fdir_filter_count++; + + return 0; +} + +static int ixgbe_flowspec_to_flow_type(struct ethtool_rx_flow_spec *fsp, + u8 *flow_type) +{ + switch (fsp->flow_type & ~FLOW_EXT) { + case TCP_V4_FLOW: + *flow_type = IXGBE_ATR_FLOW_TYPE_TCPV4; + break; + case UDP_V4_FLOW: + *flow_type = IXGBE_ATR_FLOW_TYPE_UDPV4; + break; + case SCTP_V4_FLOW: + *flow_type = IXGBE_ATR_FLOW_TYPE_SCTPV4; + break; + case IP_USER_FLOW: + switch (fsp->h_u.usr_ip4_spec.proto) { + case IPPROTO_TCP: + *flow_type = IXGBE_ATR_FLOW_TYPE_TCPV4; + break; + case IPPROTO_UDP: + *flow_type = IXGBE_ATR_FLOW_TYPE_UDPV4; + break; + case IPPROTO_SCTP: + *flow_type = IXGBE_ATR_FLOW_TYPE_SCTPV4; + break; + case 0: + if (!fsp->m_u.usr_ip4_spec.proto) { + *flow_type = IXGBE_ATR_FLOW_TYPE_IPV4; + break; + } + fallthrough; + default: + return 0; + } + break; + default: + return 0; + } + + return 1; +} + +static int ixgbe_add_ethtool_fdir_entry(struct ixgbe_adapter *adapter, + struct ethtool_rxnfc *cmd) +{ + struct ethtool_rx_flow_spec *fsp = + (struct ethtool_rx_flow_spec *)&cmd->fs; + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_fdir_filter *input; + union ixgbe_atr_input mask; + u8 queue; + int err; + + if (!(adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE)) + return -EOPNOTSUPP; + + /* ring_cookie is a masked into a set of queues and ixgbe pools or + * we use the drop index. + */ + if (fsp->ring_cookie == RX_CLS_FLOW_DISC) { + queue = IXGBE_FDIR_DROP_QUEUE; + } else { + u32 ring = ethtool_get_flow_spec_ring(fsp->ring_cookie); + u8 vf = ethtool_get_flow_spec_ring_vf(fsp->ring_cookie); + + if (!vf && (ring >= adapter->num_rx_queues)) + return -EINVAL; + else if (vf && + ((vf > adapter->num_vfs) || + ring >= adapter->num_rx_queues_per_pool)) + return -EINVAL; + + /* Map the ring onto the absolute queue index */ + if (!vf) + queue = adapter->rx_ring[ring]->reg_idx; + else + queue = ((vf - 1) * + adapter->num_rx_queues_per_pool) + ring; + } + + /* Don't allow indexes to exist outside of available space */ + if (fsp->location >= ((1024 << adapter->fdir_pballoc) - 2)) { + e_err(drv, "Location out of range\n"); + return -EINVAL; + } + + input = kzalloc(sizeof(*input), GFP_ATOMIC); + if (!input) + return -ENOMEM; + + memset(&mask, 0, sizeof(union ixgbe_atr_input)); + + /* set SW index */ + input->sw_idx = fsp->location; + + /* record flow type */ + if (!ixgbe_flowspec_to_flow_type(fsp, + &input->filter.formatted.flow_type)) { + e_err(drv, "Unrecognized flow type\n"); + goto err_out; + } + + mask.formatted.flow_type = IXGBE_ATR_L4TYPE_IPV6_MASK | + IXGBE_ATR_L4TYPE_MASK; + + if (input->filter.formatted.flow_type == IXGBE_ATR_FLOW_TYPE_IPV4) + mask.formatted.flow_type &= IXGBE_ATR_L4TYPE_IPV6_MASK; + + /* Copy input into formatted structures */ + input->filter.formatted.src_ip[0] = fsp->h_u.tcp_ip4_spec.ip4src; + mask.formatted.src_ip[0] = fsp->m_u.tcp_ip4_spec.ip4src; + input->filter.formatted.dst_ip[0] = fsp->h_u.tcp_ip4_spec.ip4dst; + mask.formatted.dst_ip[0] = fsp->m_u.tcp_ip4_spec.ip4dst; + input->filter.formatted.src_port = fsp->h_u.tcp_ip4_spec.psrc; + mask.formatted.src_port = fsp->m_u.tcp_ip4_spec.psrc; + input->filter.formatted.dst_port = fsp->h_u.tcp_ip4_spec.pdst; + mask.formatted.dst_port = fsp->m_u.tcp_ip4_spec.pdst; + + if (fsp->flow_type & FLOW_EXT) { + input->filter.formatted.vm_pool = + (unsigned char)ntohl(fsp->h_ext.data[1]); + mask.formatted.vm_pool = + (unsigned char)ntohl(fsp->m_ext.data[1]); + input->filter.formatted.vlan_id = fsp->h_ext.vlan_tci; + mask.formatted.vlan_id = fsp->m_ext.vlan_tci; + input->filter.formatted.flex_bytes = + fsp->h_ext.vlan_etype; + mask.formatted.flex_bytes = fsp->m_ext.vlan_etype; + } + + /* determine if we need to drop or route the packet */ + if (fsp->ring_cookie == RX_CLS_FLOW_DISC) + input->action = IXGBE_FDIR_DROP_QUEUE; + else + input->action = fsp->ring_cookie; + + spin_lock(&adapter->fdir_perfect_lock); + + if (hlist_empty(&adapter->fdir_filter_list)) { + /* save mask and program input mask into HW */ + memcpy(&adapter->fdir_mask, &mask, sizeof(mask)); + err = ixgbe_fdir_set_input_mask_82599(hw, &mask); + if (err) { + e_err(drv, "Error writing mask\n"); + goto err_out_w_lock; + } + } else if (memcmp(&adapter->fdir_mask, &mask, sizeof(mask))) { + e_err(drv, "Only one mask supported per port\n"); + goto err_out_w_lock; + } + + /* apply mask and compute/store hash */ + ixgbe_atr_compute_perfect_hash_82599(&input->filter, &mask); + + /* program filters to filter memory */ + err = ixgbe_fdir_write_perfect_filter_82599(hw, + &input->filter, input->sw_idx, queue); + if (err) + goto err_out_w_lock; + + ixgbe_update_ethtool_fdir_entry(adapter, input, input->sw_idx); + + spin_unlock(&adapter->fdir_perfect_lock); + + return err; +err_out_w_lock: + spin_unlock(&adapter->fdir_perfect_lock); +err_out: + kfree(input); + return -EINVAL; +} + +static int ixgbe_del_ethtool_fdir_entry(struct ixgbe_adapter *adapter, + struct ethtool_rxnfc *cmd) +{ + struct ethtool_rx_flow_spec *fsp = + (struct ethtool_rx_flow_spec *)&cmd->fs; + int err; + + spin_lock(&adapter->fdir_perfect_lock); + err = ixgbe_update_ethtool_fdir_entry(adapter, NULL, fsp->location); + spin_unlock(&adapter->fdir_perfect_lock); + + return err; +} + +#define UDP_RSS_FLAGS (IXGBE_FLAG2_RSS_FIELD_IPV4_UDP | \ + IXGBE_FLAG2_RSS_FIELD_IPV6_UDP) +static int ixgbe_set_rss_hash_opt(struct ixgbe_adapter *adapter, + struct ethtool_rxnfc *nfc) +{ + u32 flags2 = adapter->flags2; + + /* + * RSS does not support anything other than hashing + * to queues on src and dst IPs and ports + */ + if (nfc->data & ~(RXH_IP_SRC | RXH_IP_DST | + RXH_L4_B_0_1 | RXH_L4_B_2_3)) + return -EINVAL; + + switch (nfc->flow_type) { + case TCP_V4_FLOW: + case TCP_V6_FLOW: + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST) || + !(nfc->data & RXH_L4_B_0_1) || + !(nfc->data & RXH_L4_B_2_3)) + return -EINVAL; + break; + case UDP_V4_FLOW: + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST)) + return -EINVAL; + switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { + case 0: + flags2 &= ~IXGBE_FLAG2_RSS_FIELD_IPV4_UDP; + break; + case (RXH_L4_B_0_1 | RXH_L4_B_2_3): + flags2 |= IXGBE_FLAG2_RSS_FIELD_IPV4_UDP; + break; + default: + return -EINVAL; + } + break; + case UDP_V6_FLOW: + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST)) + return -EINVAL; + switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { + case 0: + flags2 &= ~IXGBE_FLAG2_RSS_FIELD_IPV6_UDP; + break; + case (RXH_L4_B_0_1 | RXH_L4_B_2_3): + flags2 |= IXGBE_FLAG2_RSS_FIELD_IPV6_UDP; + break; + default: + return -EINVAL; + } + break; + case AH_ESP_V4_FLOW: + case AH_V4_FLOW: + case ESP_V4_FLOW: + case SCTP_V4_FLOW: + case AH_ESP_V6_FLOW: + case AH_V6_FLOW: + case ESP_V6_FLOW: + case SCTP_V6_FLOW: + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST) || + (nfc->data & RXH_L4_B_0_1) || + (nfc->data & RXH_L4_B_2_3)) + return -EINVAL; + break; + default: + return -EINVAL; + } + + /* if we changed something we need to update flags */ + if (flags2 != adapter->flags2) { + struct ixgbe_hw *hw = &adapter->hw; + u32 mrqc; + unsigned int pf_pool = adapter->num_vfs; + + if ((hw->mac.type >= ixgbe_mac_X550) && + (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) + mrqc = IXGBE_READ_REG(hw, IXGBE_PFVFMRQC(pf_pool)); + else + mrqc = IXGBE_READ_REG(hw, IXGBE_MRQC); + + if ((flags2 & UDP_RSS_FLAGS) && + !(adapter->flags2 & UDP_RSS_FLAGS)) + e_warn(drv, "enabling UDP RSS: fragmented packets may arrive out of order to the stack above\n"); + + adapter->flags2 = flags2; + + /* Perform hash on these packet types */ + mrqc |= IXGBE_MRQC_RSS_FIELD_IPV4 + | IXGBE_MRQC_RSS_FIELD_IPV4_TCP + | IXGBE_MRQC_RSS_FIELD_IPV6 + | IXGBE_MRQC_RSS_FIELD_IPV6_TCP; + + mrqc &= ~(IXGBE_MRQC_RSS_FIELD_IPV4_UDP | + IXGBE_MRQC_RSS_FIELD_IPV6_UDP); + + if (flags2 & IXGBE_FLAG2_RSS_FIELD_IPV4_UDP) + mrqc |= IXGBE_MRQC_RSS_FIELD_IPV4_UDP; + + if (flags2 & IXGBE_FLAG2_RSS_FIELD_IPV6_UDP) + mrqc |= IXGBE_MRQC_RSS_FIELD_IPV6_UDP; + + if ((hw->mac.type >= ixgbe_mac_X550) && + (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) + IXGBE_WRITE_REG(hw, IXGBE_PFVFMRQC(pf_pool), mrqc); + else + IXGBE_WRITE_REG(hw, IXGBE_MRQC, mrqc); + } + + return 0; +} + +static int ixgbe_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + int ret = -EOPNOTSUPP; + + switch (cmd->cmd) { + case ETHTOOL_SRXCLSRLINS: + ret = ixgbe_add_ethtool_fdir_entry(adapter, cmd); + break; + case ETHTOOL_SRXCLSRLDEL: + ret = ixgbe_del_ethtool_fdir_entry(adapter, cmd); + break; + case ETHTOOL_SRXFH: + ret = ixgbe_set_rss_hash_opt(adapter, cmd); + break; + default: + break; + } + + return ret; +} + +static u32 ixgbe_get_rxfh_key_size(struct net_device *netdev) +{ + return IXGBE_RSS_KEY_SIZE; +} + +static u32 ixgbe_rss_indir_size(struct net_device *netdev) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + return ixgbe_rss_indir_tbl_entries(adapter); +} + +static void ixgbe_get_reta(struct ixgbe_adapter *adapter, u32 *indir) +{ + int i, reta_size = ixgbe_rss_indir_tbl_entries(adapter); + u16 rss_m = adapter->ring_feature[RING_F_RSS].mask; + + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) + rss_m = adapter->ring_feature[RING_F_RSS].indices - 1; + + for (i = 0; i < reta_size; i++) + indir[i] = adapter->rss_indir_tbl[i] & rss_m; +} + +static int ixgbe_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, + u8 *hfunc) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + if (hfunc) + *hfunc = ETH_RSS_HASH_TOP; + + if (indir) + ixgbe_get_reta(adapter, indir); + + if (key) + memcpy(key, adapter->rss_key, ixgbe_get_rxfh_key_size(netdev)); + + return 0; +} + +static int ixgbe_set_rxfh(struct net_device *netdev, const u32 *indir, + const u8 *key, const u8 hfunc) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + int i; + u32 reta_entries = ixgbe_rss_indir_tbl_entries(adapter); + + if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) + return -EOPNOTSUPP; + + /* Fill out the redirection table */ + if (indir) { + int max_queues = min_t(int, adapter->num_rx_queues, + ixgbe_rss_indir_tbl_max(adapter)); + + /*Allow at least 2 queues w/ SR-IOV.*/ + if ((adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) && + (max_queues < 2)) + max_queues = 2; + + /* Verify user input. */ + for (i = 0; i < reta_entries; i++) + if (indir[i] >= max_queues) + return -EINVAL; + + for (i = 0; i < reta_entries; i++) + adapter->rss_indir_tbl[i] = indir[i]; + + ixgbe_store_reta(adapter); + } + + /* Fill out the rss hash key */ + if (key) { + memcpy(adapter->rss_key, key, ixgbe_get_rxfh_key_size(netdev)); + ixgbe_store_key(adapter); + } + + return 0; +} + +static int ixgbe_get_ts_info(struct net_device *dev, + struct ethtool_ts_info *info) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + + /* we always support timestamping disabled */ + info->rx_filters = BIT(HWTSTAMP_FILTER_NONE); + + switch (adapter->hw.mac.type) { + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + info->rx_filters |= BIT(HWTSTAMP_FILTER_ALL); + break; + case ixgbe_mac_X540: + case ixgbe_mac_82599EB: + info->rx_filters |= + BIT(HWTSTAMP_FILTER_PTP_V1_L4_SYNC) | + BIT(HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) | + BIT(HWTSTAMP_FILTER_PTP_V2_EVENT); + break; + default: + return ethtool_op_get_ts_info(dev, info); + } + + info->so_timestamping = + SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + + if (adapter->ptp_clock) + info->phc_index = ptp_clock_index(adapter->ptp_clock); + else + info->phc_index = -1; + + info->tx_types = + BIT(HWTSTAMP_TX_OFF) | + BIT(HWTSTAMP_TX_ON); + + return 0; +} + +static unsigned int ixgbe_max_channels(struct ixgbe_adapter *adapter) +{ + unsigned int max_combined; + u8 tcs = adapter->hw_tcs; + + if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) { + /* We only support one q_vector without MSI-X */ + max_combined = 1; + } else if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { + /* Limit value based on the queue mask */ + max_combined = adapter->ring_feature[RING_F_RSS].mask + 1; + } else if (tcs > 1) { + /* For DCB report channels per traffic class */ + if (adapter->hw.mac.type == ixgbe_mac_82598EB) { + /* 8 TC w/ 4 queues per TC */ + max_combined = 4; + } else if (tcs > 4) { + /* 8 TC w/ 8 queues per TC */ + max_combined = 8; + } else { + /* 4 TC w/ 16 queues per TC */ + max_combined = 16; + } + } else if (adapter->atr_sample_rate) { + /* support up to 64 queues with ATR */ + max_combined = IXGBE_MAX_FDIR_INDICES; + } else { + /* support up to 16 queues with RSS */ + max_combined = ixgbe_max_rss_indices(adapter); + } + + return min_t(int, max_combined, num_online_cpus()); +} + +static void ixgbe_get_channels(struct net_device *dev, + struct ethtool_channels *ch) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + + /* report maximum channels */ + ch->max_combined = ixgbe_max_channels(adapter); + + /* report info for other vector */ + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) { + ch->max_other = NON_Q_VECTORS; + ch->other_count = NON_Q_VECTORS; + } + + /* record RSS queues */ + ch->combined_count = adapter->ring_feature[RING_F_RSS].indices; + + /* nothing else to report if RSS is disabled */ + if (ch->combined_count == 1) + return; + + /* we do not support ATR queueing if SR-IOV is enabled */ + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) + return; + + /* same thing goes for being DCB enabled */ + if (adapter->hw_tcs > 1) + return; + + /* if ATR is disabled we can exit */ + if (!adapter->atr_sample_rate) + return; + + /* report flow director queues as maximum channels */ + ch->combined_count = adapter->ring_feature[RING_F_FDIR].indices; +} + +static int ixgbe_set_channels(struct net_device *dev, + struct ethtool_channels *ch) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + unsigned int count = ch->combined_count; + u8 max_rss_indices = ixgbe_max_rss_indices(adapter); + + /* verify they are not requesting separate vectors */ + if (!count || ch->rx_count || ch->tx_count) + return -EINVAL; + + /* verify other_count has not changed */ + if (ch->other_count != NON_Q_VECTORS) + return -EINVAL; + + /* verify the number of channels does not exceed hardware limits */ + if (count > ixgbe_max_channels(adapter)) + return -EINVAL; + + /* update feature limits from largest to smallest supported values */ + adapter->ring_feature[RING_F_FDIR].limit = count; + + /* cap RSS limit */ + if (count > max_rss_indices) + count = max_rss_indices; + adapter->ring_feature[RING_F_RSS].limit = count; + +#ifdef IXGBE_FCOE + /* cap FCoE limit at 8 */ + if (count > IXGBE_FCRETA_SIZE) + count = IXGBE_FCRETA_SIZE; + adapter->ring_feature[RING_F_FCOE].limit = count; + +#endif + /* use setup TC to update any traffic class queue mapping */ + return ixgbe_setup_tc(dev, adapter->hw_tcs); +} + +static int ixgbe_get_module_info(struct net_device *dev, + struct ethtool_modinfo *modinfo) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_hw *hw = &adapter->hw; + s32 status; + u8 sff8472_rev, addr_mode; + bool page_swap = false; + + if (hw->phy.type == ixgbe_phy_fw) + return -ENXIO; + + /* Check whether we support SFF-8472 or not */ + status = hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_SFF_8472_COMP, + &sff8472_rev); + if (status) + return -EIO; + + /* addressing mode is not supported */ + status = hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_SFF_8472_SWAP, + &addr_mode); + if (status) + return -EIO; + + if (addr_mode & IXGBE_SFF_ADDRESSING_MODE) { + e_err(drv, "Address change required to access page 0xA2, but not supported. Please report the module type to the driver maintainers.\n"); + page_swap = true; + } + + if (sff8472_rev == IXGBE_SFF_SFF_8472_UNSUP || page_swap || + !(addr_mode & IXGBE_SFF_DDM_IMPLEMENTED)) { + /* We have a SFP, but it does not support SFF-8472 */ + modinfo->type = ETH_MODULE_SFF_8079; + modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN; + } else { + /* We have a SFP which supports a revision of SFF-8472. */ + modinfo->type = ETH_MODULE_SFF_8472; + modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; + } + + return 0; +} + +static int ixgbe_get_module_eeprom(struct net_device *dev, + struct ethtool_eeprom *ee, + u8 *data) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_hw *hw = &adapter->hw; + s32 status = IXGBE_ERR_PHY_ADDR_INVALID; + u8 databyte = 0xFF; + int i = 0; + + if (ee->len == 0) + return -EINVAL; + + if (hw->phy.type == ixgbe_phy_fw) + return -ENXIO; + + for (i = ee->offset; i < ee->offset + ee->len; i++) { + /* I2C reads can take long time */ + if (test_bit(__IXGBE_IN_SFP_INIT, &adapter->state)) + return -EBUSY; + + if (i < ETH_MODULE_SFF_8079_LEN) + status = hw->phy.ops.read_i2c_eeprom(hw, i, &databyte); + else + status = hw->phy.ops.read_i2c_sff8472(hw, i, &databyte); + + if (status) + return -EIO; + + data[i - ee->offset] = databyte; + } + + return 0; +} + +static const struct { + ixgbe_link_speed mac_speed; + u32 supported; +} ixgbe_ls_map[] = { + { IXGBE_LINK_SPEED_10_FULL, SUPPORTED_10baseT_Full }, + { IXGBE_LINK_SPEED_100_FULL, SUPPORTED_100baseT_Full }, + { IXGBE_LINK_SPEED_1GB_FULL, SUPPORTED_1000baseT_Full }, + { IXGBE_LINK_SPEED_2_5GB_FULL, SUPPORTED_2500baseX_Full }, + { IXGBE_LINK_SPEED_10GB_FULL, SUPPORTED_10000baseT_Full }, +}; + +static const struct { + u32 lp_advertised; + u32 mac_speed; +} ixgbe_lp_map[] = { + { FW_PHY_ACT_UD_2_100M_TX_EEE, SUPPORTED_100baseT_Full }, + { FW_PHY_ACT_UD_2_1G_T_EEE, SUPPORTED_1000baseT_Full }, + { FW_PHY_ACT_UD_2_10G_T_EEE, SUPPORTED_10000baseT_Full }, + { FW_PHY_ACT_UD_2_1G_KX_EEE, SUPPORTED_1000baseKX_Full }, + { FW_PHY_ACT_UD_2_10G_KX4_EEE, SUPPORTED_10000baseKX4_Full }, + { FW_PHY_ACT_UD_2_10G_KR_EEE, SUPPORTED_10000baseKR_Full}, +}; + +static int +ixgbe_get_eee_fw(struct ixgbe_adapter *adapter, struct ethtool_eee *edata) +{ + u32 info[FW_PHY_ACT_DATA_COUNT] = { 0 }; + struct ixgbe_hw *hw = &adapter->hw; + s32 rc; + u16 i; + + rc = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_UD_2, &info); + if (rc) + return rc; + + edata->lp_advertised = 0; + for (i = 0; i < ARRAY_SIZE(ixgbe_lp_map); ++i) { + if (info[0] & ixgbe_lp_map[i].lp_advertised) + edata->lp_advertised |= ixgbe_lp_map[i].mac_speed; + } + + edata->supported = 0; + for (i = 0; i < ARRAY_SIZE(ixgbe_ls_map); ++i) { + if (hw->phy.eee_speeds_supported & ixgbe_ls_map[i].mac_speed) + edata->supported |= ixgbe_ls_map[i].supported; + } + + edata->advertised = 0; + for (i = 0; i < ARRAY_SIZE(ixgbe_ls_map); ++i) { + if (hw->phy.eee_speeds_advertised & ixgbe_ls_map[i].mac_speed) + edata->advertised |= ixgbe_ls_map[i].supported; + } + + edata->eee_enabled = !!edata->advertised; + edata->tx_lpi_enabled = edata->eee_enabled; + if (edata->advertised & edata->lp_advertised) + edata->eee_active = true; + + return 0; +} + +static int ixgbe_get_eee(struct net_device *netdev, struct ethtool_eee *edata) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + + if (!(adapter->flags2 & IXGBE_FLAG2_EEE_CAPABLE)) + return -EOPNOTSUPP; + + if (hw->phy.eee_speeds_supported && hw->phy.type == ixgbe_phy_fw) + return ixgbe_get_eee_fw(adapter, edata); + + return -EOPNOTSUPP; +} + +static int ixgbe_set_eee(struct net_device *netdev, struct ethtool_eee *edata) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + struct ethtool_eee eee_data; + s32 ret_val; + + if (!(adapter->flags2 & IXGBE_FLAG2_EEE_CAPABLE)) + return -EOPNOTSUPP; + + memset(&eee_data, 0, sizeof(struct ethtool_eee)); + + ret_val = ixgbe_get_eee(netdev, &eee_data); + if (ret_val) + return ret_val; + + if (eee_data.eee_enabled && !edata->eee_enabled) { + if (eee_data.tx_lpi_enabled != edata->tx_lpi_enabled) { + e_err(drv, "Setting EEE tx-lpi is not supported\n"); + return -EINVAL; + } + + if (eee_data.tx_lpi_timer != edata->tx_lpi_timer) { + e_err(drv, + "Setting EEE Tx LPI timer is not supported\n"); + return -EINVAL; + } + + if (eee_data.advertised != edata->advertised) { + e_err(drv, + "Setting EEE advertised speeds is not supported\n"); + return -EINVAL; + } + } + + if (eee_data.eee_enabled != edata->eee_enabled) { + if (edata->eee_enabled) { + adapter->flags2 |= IXGBE_FLAG2_EEE_ENABLED; + hw->phy.eee_speeds_advertised = + hw->phy.eee_speeds_supported; + } else { + adapter->flags2 &= ~IXGBE_FLAG2_EEE_ENABLED; + hw->phy.eee_speeds_advertised = 0; + } + + /* reset link */ + if (netif_running(netdev)) + ixgbe_reinit_locked(adapter); + else + ixgbe_reset(adapter); + } + + return 0; +} + +static u32 ixgbe_get_priv_flags(struct net_device *netdev) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + u32 priv_flags = 0; + + if (adapter->flags2 & IXGBE_FLAG2_RX_LEGACY) + priv_flags |= IXGBE_PRIV_FLAGS_LEGACY_RX; + + if (adapter->flags2 & IXGBE_FLAG2_VF_IPSEC_ENABLED) + priv_flags |= IXGBE_PRIV_FLAGS_VF_IPSEC_EN; + + return priv_flags; +} + +static int ixgbe_set_priv_flags(struct net_device *netdev, u32 priv_flags) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + unsigned int flags2 = adapter->flags2; + + flags2 &= ~IXGBE_FLAG2_RX_LEGACY; + if (priv_flags & IXGBE_PRIV_FLAGS_LEGACY_RX) + flags2 |= IXGBE_FLAG2_RX_LEGACY; + + flags2 &= ~IXGBE_FLAG2_VF_IPSEC_ENABLED; + if (priv_flags & IXGBE_PRIV_FLAGS_VF_IPSEC_EN) + flags2 |= IXGBE_FLAG2_VF_IPSEC_ENABLED; + + if (flags2 != adapter->flags2) { + adapter->flags2 = flags2; + + /* reset interface to repopulate queues */ + if (netif_running(netdev)) + ixgbe_reinit_locked(adapter); + } + + return 0; +} + +static const struct ethtool_ops ixgbe_ethtool_ops = { + .supported_coalesce_params = ETHTOOL_COALESCE_USECS, + .get_drvinfo = ixgbe_get_drvinfo, + .get_regs_len = ixgbe_get_regs_len, + .get_regs = ixgbe_get_regs, + .get_wol = ixgbe_get_wol, + .set_wol = ixgbe_set_wol, + .nway_reset = ixgbe_nway_reset, + .get_link = ethtool_op_get_link, + .get_eeprom_len = ixgbe_get_eeprom_len, + .get_eeprom = ixgbe_get_eeprom, + .set_eeprom = ixgbe_set_eeprom, + .get_ringparam = ixgbe_get_ringparam, + .set_ringparam = ixgbe_set_ringparam, + .get_pause_stats = ixgbe_get_pause_stats, + .get_pauseparam = ixgbe_get_pauseparam, + .set_pauseparam = ixgbe_set_pauseparam, + .get_msglevel = ixgbe_get_msglevel, + .set_msglevel = ixgbe_set_msglevel, + .self_test = ixgbe_diag_test, + .get_strings = ixgbe_get_strings, + .set_phys_id = ixgbe_set_phys_id, + .get_sset_count = ixgbe_get_sset_count, + .get_ethtool_stats = ixgbe_get_ethtool_stats, + .get_coalesce = ixgbe_get_coalesce, + .set_coalesce = ixgbe_set_coalesce, + .get_rxnfc = ixgbe_get_rxnfc, + .set_rxnfc = ixgbe_set_rxnfc, + .get_rxfh_indir_size = ixgbe_rss_indir_size, + .get_rxfh_key_size = ixgbe_get_rxfh_key_size, + .get_rxfh = ixgbe_get_rxfh, + .set_rxfh = ixgbe_set_rxfh, + .get_eee = ixgbe_get_eee, + .set_eee = ixgbe_set_eee, + .get_channels = ixgbe_get_channels, + .set_channels = ixgbe_set_channels, + .get_priv_flags = ixgbe_get_priv_flags, + .set_priv_flags = ixgbe_set_priv_flags, + .get_ts_info = ixgbe_get_ts_info, + .get_module_info = ixgbe_get_module_info, + .get_module_eeprom = ixgbe_get_module_eeprom, + .get_link_ksettings = ixgbe_get_link_ksettings, + .set_link_ksettings = ixgbe_set_link_ksettings, +}; + +void ixgbe_set_ethtool_ops(struct net_device *netdev) +{ + netdev->ethtool_ops = &ixgbe_ethtool_ops; +} diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c new file mode 100644 index 000000000..0fcd82036 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c @@ -0,0 +1,1047 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#include "ixgbe.h" +#include <linux/if_ether.h> +#include <linux/gfp.h> +#include <linux/if_vlan.h> +#include <generated/utsrelease.h> +#include <scsi/scsi_cmnd.h> +#include <scsi/scsi_device.h> +#include <scsi/fc/fc_fs.h> +#include <scsi/fc/fc_fcoe.h> +#include <scsi/libfc.h> +#include <scsi/libfcoe.h> + +/** + * ixgbe_fcoe_clear_ddp - clear the given ddp context + * @ddp: ptr to the ixgbe_fcoe_ddp + * + * Returns : none + * + */ +static inline void ixgbe_fcoe_clear_ddp(struct ixgbe_fcoe_ddp *ddp) +{ + ddp->len = 0; + ddp->err = 1; + ddp->udl = NULL; + ddp->udp = 0UL; + ddp->sgl = NULL; + ddp->sgc = 0; +} + +/** + * ixgbe_fcoe_ddp_put - free the ddp context for a given xid + * @netdev: the corresponding net_device + * @xid: the xid that corresponding ddp will be freed + * + * This is the implementation of net_device_ops.ndo_fcoe_ddp_done + * and it is expected to be called by ULD, i.e., FCP layer of libfc + * to release the corresponding ddp context when the I/O is done. + * + * Returns : data length already ddp-ed in bytes + */ +int ixgbe_fcoe_ddp_put(struct net_device *netdev, u16 xid) +{ + int len; + struct ixgbe_fcoe *fcoe; + struct ixgbe_adapter *adapter; + struct ixgbe_fcoe_ddp *ddp; + struct ixgbe_hw *hw; + u32 fcbuff; + + if (!netdev) + return 0; + + if (xid >= netdev->fcoe_ddp_xid) + return 0; + + adapter = netdev_priv(netdev); + fcoe = &adapter->fcoe; + ddp = &fcoe->ddp[xid]; + if (!ddp->udl) + return 0; + + hw = &adapter->hw; + len = ddp->len; + /* if no error then skip ddp context invalidation */ + if (!ddp->err) + goto skip_ddpinv; + + if (hw->mac.type == ixgbe_mac_X550) { + /* X550 does not require DDP FCoE lock */ + + IXGBE_WRITE_REG(hw, IXGBE_FCDFC(0, xid), 0); + IXGBE_WRITE_REG(hw, IXGBE_FCDFC(3, xid), + (xid | IXGBE_FCFLTRW_WE)); + + /* program FCBUFF */ + IXGBE_WRITE_REG(hw, IXGBE_FCDDC(2, xid), 0); + + /* program FCDMARW */ + IXGBE_WRITE_REG(hw, IXGBE_FCDDC(3, xid), + (xid | IXGBE_FCDMARW_WE)); + + /* read FCBUFF to check context invalidated */ + IXGBE_WRITE_REG(hw, IXGBE_FCDDC(3, xid), + (xid | IXGBE_FCDMARW_RE)); + fcbuff = IXGBE_READ_REG(hw, IXGBE_FCDDC(2, xid)); + } else { + /* other hardware requires DDP FCoE lock */ + spin_lock_bh(&fcoe->lock); + IXGBE_WRITE_REG(hw, IXGBE_FCFLT, 0); + IXGBE_WRITE_REG(hw, IXGBE_FCFLTRW, + (xid | IXGBE_FCFLTRW_WE)); + IXGBE_WRITE_REG(hw, IXGBE_FCBUFF, 0); + IXGBE_WRITE_REG(hw, IXGBE_FCDMARW, + (xid | IXGBE_FCDMARW_WE)); + + /* guaranteed to be invalidated after 100us */ + IXGBE_WRITE_REG(hw, IXGBE_FCDMARW, + (xid | IXGBE_FCDMARW_RE)); + fcbuff = IXGBE_READ_REG(hw, IXGBE_FCBUFF); + spin_unlock_bh(&fcoe->lock); + } + + if (fcbuff & IXGBE_FCBUFF_VALID) + usleep_range(100, 150); + +skip_ddpinv: + if (ddp->sgl) + dma_unmap_sg(&adapter->pdev->dev, ddp->sgl, ddp->sgc, + DMA_FROM_DEVICE); + if (ddp->pool) { + dma_pool_free(ddp->pool, ddp->udl, ddp->udp); + ddp->pool = NULL; + } + + ixgbe_fcoe_clear_ddp(ddp); + + return len; +} + +/** + * ixgbe_fcoe_ddp_setup - called to set up ddp context + * @netdev: the corresponding net_device + * @xid: the exchange id requesting ddp + * @sgl: the scatter-gather list for this request + * @sgc: the number of scatter-gather items + * @target_mode: 1 to setup target mode, 0 to setup initiator mode + * + * Returns : 1 for success and 0 for no ddp + */ +static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid, + struct scatterlist *sgl, unsigned int sgc, + int target_mode) +{ + struct ixgbe_adapter *adapter; + struct ixgbe_hw *hw; + struct ixgbe_fcoe *fcoe; + struct ixgbe_fcoe_ddp *ddp; + struct ixgbe_fcoe_ddp_pool *ddp_pool; + struct scatterlist *sg; + unsigned int i, j, dmacount; + unsigned int len; + static const unsigned int bufflen = IXGBE_FCBUFF_MIN; + unsigned int firstoff = 0; + unsigned int lastsize; + unsigned int thisoff = 0; + unsigned int thislen = 0; + u32 fcbuff, fcdmarw, fcfltrw, fcrxctl; + dma_addr_t addr = 0; + + if (!netdev || !sgl) + return 0; + + adapter = netdev_priv(netdev); + if (xid >= netdev->fcoe_ddp_xid) { + e_warn(drv, "xid=0x%x out-of-range\n", xid); + return 0; + } + + /* no DDP if we are already down or resetting */ + if (test_bit(__IXGBE_DOWN, &adapter->state) || + test_bit(__IXGBE_RESETTING, &adapter->state)) + return 0; + + fcoe = &adapter->fcoe; + ddp = &fcoe->ddp[xid]; + if (ddp->sgl) { + e_err(drv, "xid 0x%x w/ non-null sgl=%p nents=%d\n", + xid, ddp->sgl, ddp->sgc); + return 0; + } + ixgbe_fcoe_clear_ddp(ddp); + + + if (!fcoe->ddp_pool) { + e_warn(drv, "No ddp_pool resources allocated\n"); + return 0; + } + + ddp_pool = per_cpu_ptr(fcoe->ddp_pool, get_cpu()); + if (!ddp_pool->pool) { + e_warn(drv, "xid=0x%x no ddp pool for fcoe\n", xid); + goto out_noddp; + } + + /* setup dma from scsi command sgl */ + dmacount = dma_map_sg(&adapter->pdev->dev, sgl, sgc, DMA_FROM_DEVICE); + if (dmacount == 0) { + e_err(drv, "xid 0x%x DMA map error\n", xid); + goto out_noddp; + } + + /* alloc the udl from per cpu ddp pool */ + ddp->udl = dma_pool_alloc(ddp_pool->pool, GFP_ATOMIC, &ddp->udp); + if (!ddp->udl) { + e_err(drv, "failed allocated ddp context\n"); + goto out_noddp_unmap; + } + ddp->pool = ddp_pool->pool; + ddp->sgl = sgl; + ddp->sgc = sgc; + + j = 0; + for_each_sg(sgl, sg, dmacount, i) { + addr = sg_dma_address(sg); + len = sg_dma_len(sg); + while (len) { + /* max number of buffers allowed in one DDP context */ + if (j >= IXGBE_BUFFCNT_MAX) { + ddp_pool->noddp++; + goto out_noddp_free; + } + + /* get the offset of length of current buffer */ + thisoff = addr & ((dma_addr_t)bufflen - 1); + thislen = min((bufflen - thisoff), len); + /* + * all but the 1st buffer (j == 0) + * must be aligned on bufflen + */ + if ((j != 0) && (thisoff)) + goto out_noddp_free; + /* + * all but the last buffer + * ((i == (dmacount - 1)) && (thislen == len)) + * must end at bufflen + */ + if (((i != (dmacount - 1)) || (thislen != len)) + && ((thislen + thisoff) != bufflen)) + goto out_noddp_free; + + ddp->udl[j] = (u64)(addr - thisoff); + /* only the first buffer may have none-zero offset */ + if (j == 0) + firstoff = thisoff; + len -= thislen; + addr += thislen; + j++; + } + } + /* only the last buffer may have non-full bufflen */ + lastsize = thisoff + thislen; + + /* + * lastsize can not be buffer len. + * If it is then adding another buffer with lastsize = 1. + */ + if (lastsize == bufflen) { + if (j >= IXGBE_BUFFCNT_MAX) { + ddp_pool->noddp_ext_buff++; + goto out_noddp_free; + } + + ddp->udl[j] = (u64)(fcoe->extra_ddp_buffer_dma); + j++; + lastsize = 1; + } + put_cpu(); + + fcbuff = (IXGBE_FCBUFF_4KB << IXGBE_FCBUFF_BUFFSIZE_SHIFT); + fcbuff |= ((j & 0xff) << IXGBE_FCBUFF_BUFFCNT_SHIFT); + fcbuff |= (firstoff << IXGBE_FCBUFF_OFFSET_SHIFT); + /* Set WRCONTX bit to allow DDP for target */ + if (target_mode) + fcbuff |= (IXGBE_FCBUFF_WRCONTX); + fcbuff |= (IXGBE_FCBUFF_VALID); + + fcdmarw = xid; + fcdmarw |= IXGBE_FCDMARW_WE; + fcdmarw |= (lastsize << IXGBE_FCDMARW_LASTSIZE_SHIFT); + + fcfltrw = xid; + fcfltrw |= IXGBE_FCFLTRW_WE; + + /* program DMA context */ + hw = &adapter->hw; + + /* turn on last frame indication for target mode as FCP_RSPtarget is + * supposed to send FCP_RSP when it is done. */ + if (target_mode && !test_bit(__IXGBE_FCOE_TARGET, &fcoe->mode)) { + set_bit(__IXGBE_FCOE_TARGET, &fcoe->mode); + fcrxctl = IXGBE_READ_REG(hw, IXGBE_FCRXCTRL); + fcrxctl |= IXGBE_FCRXCTRL_LASTSEQH; + IXGBE_WRITE_REG(hw, IXGBE_FCRXCTRL, fcrxctl); + } + + if (hw->mac.type == ixgbe_mac_X550) { + /* X550 does not require DDP lock */ + + IXGBE_WRITE_REG(hw, IXGBE_FCDDC(0, xid), + ddp->udp & DMA_BIT_MASK(32)); + IXGBE_WRITE_REG(hw, IXGBE_FCDDC(1, xid), (u64)ddp->udp >> 32); + IXGBE_WRITE_REG(hw, IXGBE_FCDDC(2, xid), fcbuff); + IXGBE_WRITE_REG(hw, IXGBE_FCDDC(3, xid), fcdmarw); + /* program filter context */ + IXGBE_WRITE_REG(hw, IXGBE_FCDFC(0, xid), IXGBE_FCFLT_VALID); + IXGBE_WRITE_REG(hw, IXGBE_FCDFC(1, xid), 0); + IXGBE_WRITE_REG(hw, IXGBE_FCDFC(3, xid), fcfltrw); + } else { + /* DDP lock for indirect DDP context access */ + spin_lock_bh(&fcoe->lock); + + IXGBE_WRITE_REG(hw, IXGBE_FCPTRL, ddp->udp & DMA_BIT_MASK(32)); + IXGBE_WRITE_REG(hw, IXGBE_FCPTRH, (u64)ddp->udp >> 32); + IXGBE_WRITE_REG(hw, IXGBE_FCBUFF, fcbuff); + IXGBE_WRITE_REG(hw, IXGBE_FCDMARW, fcdmarw); + /* program filter context */ + IXGBE_WRITE_REG(hw, IXGBE_FCPARAM, 0); + IXGBE_WRITE_REG(hw, IXGBE_FCFLT, IXGBE_FCFLT_VALID); + IXGBE_WRITE_REG(hw, IXGBE_FCFLTRW, fcfltrw); + + spin_unlock_bh(&fcoe->lock); + } + + return 1; + +out_noddp_free: + dma_pool_free(ddp->pool, ddp->udl, ddp->udp); + ixgbe_fcoe_clear_ddp(ddp); + +out_noddp_unmap: + dma_unmap_sg(&adapter->pdev->dev, sgl, sgc, DMA_FROM_DEVICE); +out_noddp: + put_cpu(); + return 0; +} + +/** + * ixgbe_fcoe_ddp_get - called to set up ddp context in initiator mode + * @netdev: the corresponding net_device + * @xid: the exchange id requesting ddp + * @sgl: the scatter-gather list for this request + * @sgc: the number of scatter-gather items + * + * This is the implementation of net_device_ops.ndo_fcoe_ddp_setup + * and is expected to be called from ULD, e.g., FCP layer of libfc + * to set up ddp for the corresponding xid of the given sglist for + * the corresponding I/O. + * + * Returns : 1 for success and 0 for no ddp + */ +int ixgbe_fcoe_ddp_get(struct net_device *netdev, u16 xid, + struct scatterlist *sgl, unsigned int sgc) +{ + return ixgbe_fcoe_ddp_setup(netdev, xid, sgl, sgc, 0); +} + +/** + * ixgbe_fcoe_ddp_target - called to set up ddp context in target mode + * @netdev: the corresponding net_device + * @xid: the exchange id requesting ddp + * @sgl: the scatter-gather list for this request + * @sgc: the number of scatter-gather items + * + * This is the implementation of net_device_ops.ndo_fcoe_ddp_target + * and is expected to be called from ULD, e.g., FCP layer of libfc + * to set up ddp for the corresponding xid of the given sglist for + * the corresponding I/O. The DDP in target mode is a write I/O request + * from the initiator. + * + * Returns : 1 for success and 0 for no ddp + */ +int ixgbe_fcoe_ddp_target(struct net_device *netdev, u16 xid, + struct scatterlist *sgl, unsigned int sgc) +{ + return ixgbe_fcoe_ddp_setup(netdev, xid, sgl, sgc, 1); +} + +/** + * ixgbe_fcoe_ddp - check ddp status and mark it done + * @adapter: ixgbe adapter + * @rx_desc: advanced rx descriptor + * @skb: the skb holding the received data + * + * This checks ddp status. + * + * Returns : < 0 indicates an error or not a FCiE ddp, 0 indicates + * not passing the skb to ULD, > 0 indicates is the length of data + * being ddped. + */ +int ixgbe_fcoe_ddp(struct ixgbe_adapter *adapter, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + int rc = -EINVAL; + struct ixgbe_fcoe *fcoe; + struct ixgbe_fcoe_ddp *ddp; + struct fc_frame_header *fh; + struct fcoe_crc_eof *crc; + __le32 fcerr = ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_FCERR); + __le32 ddp_err; + int ddp_max; + u32 fctl; + u16 xid; + + if (fcerr == cpu_to_le32(IXGBE_FCERR_BADCRC)) + skb->ip_summed = CHECKSUM_NONE; + else + skb->ip_summed = CHECKSUM_UNNECESSARY; + + if (eth_hdr(skb)->h_proto == htons(ETH_P_8021Q)) + fh = (struct fc_frame_header *)(skb->data + + sizeof(struct vlan_hdr) + sizeof(struct fcoe_hdr)); + else + fh = (struct fc_frame_header *)(skb->data + + sizeof(struct fcoe_hdr)); + + fctl = ntoh24(fh->fh_f_ctl); + if (fctl & FC_FC_EX_CTX) + xid = be16_to_cpu(fh->fh_ox_id); + else + xid = be16_to_cpu(fh->fh_rx_id); + + ddp_max = IXGBE_FCOE_DDP_MAX; + /* X550 has different DDP Max limit */ + if (adapter->hw.mac.type == ixgbe_mac_X550) + ddp_max = IXGBE_FCOE_DDP_MAX_X550; + if (xid >= ddp_max) + return -EINVAL; + + fcoe = &adapter->fcoe; + ddp = &fcoe->ddp[xid]; + if (!ddp->udl) + return -EINVAL; + + ddp_err = ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_FCEOFE | + IXGBE_RXDADV_ERR_FCERR); + if (ddp_err) + return -EINVAL; + + switch (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_STAT_FCSTAT)) { + /* return 0 to bypass going to ULD for DDPed data */ + case cpu_to_le32(IXGBE_RXDADV_STAT_FCSTAT_DDP): + /* update length of DDPed data */ + ddp->len = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss); + rc = 0; + break; + /* unmap the sg list when FCPRSP is received */ + case cpu_to_le32(IXGBE_RXDADV_STAT_FCSTAT_FCPRSP): + dma_unmap_sg(&adapter->pdev->dev, ddp->sgl, + ddp->sgc, DMA_FROM_DEVICE); + ddp->err = (__force u32)ddp_err; + ddp->sgl = NULL; + ddp->sgc = 0; + fallthrough; + /* if DDP length is present pass it through to ULD */ + case cpu_to_le32(IXGBE_RXDADV_STAT_FCSTAT_NODDP): + /* update length of DDPed data */ + ddp->len = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss); + if (ddp->len) + rc = ddp->len; + break; + /* no match will return as an error */ + case cpu_to_le32(IXGBE_RXDADV_STAT_FCSTAT_NOMTCH): + default: + break; + } + + /* In target mode, check the last data frame of the sequence. + * For DDP in target mode, data is already DDPed but the header + * indication of the last data frame ould allow is to tell if we + * got all the data and the ULP can send FCP_RSP back, as this is + * not a full fcoe frame, we fill the trailer here so it won't be + * dropped by the ULP stack. + */ + if ((fh->fh_r_ctl == FC_RCTL_DD_SOL_DATA) && + (fctl & FC_FC_END_SEQ)) { + skb_linearize(skb); + crc = skb_put(skb, sizeof(*crc)); + crc->fcoe_eof = FC_EOF_T; + } + + return rc; +} + +/** + * ixgbe_fso - ixgbe FCoE Sequence Offload (FSO) + * @tx_ring: tx desc ring + * @first: first tx_buffer structure containing skb, tx_flags, and protocol + * @hdr_len: hdr_len to be returned + * + * This sets up large send offload for FCoE + * + * Returns : 0 indicates success, < 0 for error + */ +int ixgbe_fso(struct ixgbe_ring *tx_ring, + struct ixgbe_tx_buffer *first, + u8 *hdr_len) +{ + struct sk_buff *skb = first->skb; + struct fc_frame_header *fh; + u32 vlan_macip_lens; + u32 fcoe_sof_eof = 0; + u32 mss_l4len_idx; + u32 type_tucmd = IXGBE_ADVTXT_TUCMD_FCOE; + u8 sof, eof; + + if (skb_is_gso(skb) && (skb_shinfo(skb)->gso_type != SKB_GSO_FCOE)) { + dev_err(tx_ring->dev, "Wrong gso type %d:expecting SKB_GSO_FCOE\n", + skb_shinfo(skb)->gso_type); + return -EINVAL; + } + + /* resets the header to point fcoe/fc */ + skb_set_network_header(skb, skb->mac_len); + skb_set_transport_header(skb, skb->mac_len + + sizeof(struct fcoe_hdr)); + + /* sets up SOF and ORIS */ + sof = ((struct fcoe_hdr *)skb_network_header(skb))->fcoe_sof; + switch (sof) { + case FC_SOF_I2: + fcoe_sof_eof = IXGBE_ADVTXD_FCOEF_ORIS; + break; + case FC_SOF_I3: + fcoe_sof_eof = IXGBE_ADVTXD_FCOEF_SOF | + IXGBE_ADVTXD_FCOEF_ORIS; + break; + case FC_SOF_N2: + break; + case FC_SOF_N3: + fcoe_sof_eof = IXGBE_ADVTXD_FCOEF_SOF; + break; + default: + dev_warn(tx_ring->dev, "unknown sof = 0x%x\n", sof); + return -EINVAL; + } + + /* the first byte of the last dword is EOF */ + skb_copy_bits(skb, skb->len - 4, &eof, 1); + /* sets up EOF and ORIE */ + switch (eof) { + case FC_EOF_N: + fcoe_sof_eof |= IXGBE_ADVTXD_FCOEF_EOF_N; + break; + case FC_EOF_T: + /* lso needs ORIE */ + if (skb_is_gso(skb)) + fcoe_sof_eof |= IXGBE_ADVTXD_FCOEF_EOF_N | + IXGBE_ADVTXD_FCOEF_ORIE; + else + fcoe_sof_eof |= IXGBE_ADVTXD_FCOEF_EOF_T; + break; + case FC_EOF_NI: + fcoe_sof_eof |= IXGBE_ADVTXD_FCOEF_EOF_NI; + break; + case FC_EOF_A: + fcoe_sof_eof |= IXGBE_ADVTXD_FCOEF_EOF_A; + break; + default: + dev_warn(tx_ring->dev, "unknown eof = 0x%x\n", eof); + return -EINVAL; + } + + /* sets up PARINC indicating data offset */ + fh = (struct fc_frame_header *)skb_transport_header(skb); + if (fh->fh_f_ctl[2] & FC_FC_REL_OFF) + fcoe_sof_eof |= IXGBE_ADVTXD_FCOEF_PARINC; + + /* include trailer in headlen as it is replicated per frame */ + *hdr_len = sizeof(struct fcoe_crc_eof); + + /* hdr_len includes fc_hdr if FCoE LSO is enabled */ + if (skb_is_gso(skb)) { + *hdr_len += skb_transport_offset(skb) + + sizeof(struct fc_frame_header); + /* update gso_segs and bytecount */ + first->gso_segs = DIV_ROUND_UP(skb->len - *hdr_len, + skb_shinfo(skb)->gso_size); + first->bytecount += (first->gso_segs - 1) * *hdr_len; + first->tx_flags |= IXGBE_TX_FLAGS_TSO; + /* Hardware expects L4T to be RSV for FCoE TSO */ + type_tucmd |= IXGBE_ADVTXD_TUCMD_L4T_RSV; + } + + /* set flag indicating FCOE to ixgbe_tx_map call */ + first->tx_flags |= IXGBE_TX_FLAGS_FCOE | IXGBE_TX_FLAGS_CC; + + /* mss_l4len_id: use 0 for FSO as TSO, no need for L4LEN */ + mss_l4len_idx = skb_shinfo(skb)->gso_size << IXGBE_ADVTXD_MSS_SHIFT; + + /* vlan_macip_lens: HEADLEN, MACLEN, VLAN tag */ + vlan_macip_lens = skb_transport_offset(skb) + + sizeof(struct fc_frame_header); + vlan_macip_lens |= (skb_transport_offset(skb) - 4) + << IXGBE_ADVTXD_MACLEN_SHIFT; + vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK; + + /* write context desc */ + ixgbe_tx_ctxtdesc(tx_ring, vlan_macip_lens, fcoe_sof_eof, + type_tucmd, mss_l4len_idx); + + return 0; +} + +static void ixgbe_fcoe_dma_pool_free(struct ixgbe_fcoe *fcoe, unsigned int cpu) +{ + struct ixgbe_fcoe_ddp_pool *ddp_pool; + + ddp_pool = per_cpu_ptr(fcoe->ddp_pool, cpu); + dma_pool_destroy(ddp_pool->pool); + ddp_pool->pool = NULL; +} + +static int ixgbe_fcoe_dma_pool_alloc(struct ixgbe_fcoe *fcoe, + struct device *dev, + unsigned int cpu) +{ + struct ixgbe_fcoe_ddp_pool *ddp_pool; + struct dma_pool *pool; + char pool_name[32]; + + snprintf(pool_name, 32, "ixgbe_fcoe_ddp_%u", cpu); + + pool = dma_pool_create(pool_name, dev, IXGBE_FCPTR_MAX, + IXGBE_FCPTR_ALIGN, PAGE_SIZE); + if (!pool) + return -ENOMEM; + + ddp_pool = per_cpu_ptr(fcoe->ddp_pool, cpu); + ddp_pool->pool = pool; + ddp_pool->noddp = 0; + ddp_pool->noddp_ext_buff = 0; + + return 0; +} + +/** + * ixgbe_configure_fcoe - configures registers for fcoe at start + * @adapter: ptr to ixgbe adapter + * + * This sets up FCoE related registers + * + * Returns : none + */ +void ixgbe_configure_fcoe(struct ixgbe_adapter *adapter) +{ + struct ixgbe_ring_feature *fcoe = &adapter->ring_feature[RING_F_FCOE]; + struct ixgbe_hw *hw = &adapter->hw; + int i, fcoe_q, fcoe_i, fcoe_q_h = 0; + int fcreta_size; + u32 etqf; + + /* Minimal functionality for FCoE requires at least CRC offloads */ + if (!(adapter->netdev->features & NETIF_F_FCOE_CRC)) + return; + + /* Enable L2 EtherType filter for FCoE, needed for FCoE CRC and DDP */ + etqf = ETH_P_FCOE | IXGBE_ETQF_FCOE | IXGBE_ETQF_FILTER_EN; + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { + etqf |= IXGBE_ETQF_POOL_ENABLE; + etqf |= VMDQ_P(0) << IXGBE_ETQF_POOL_SHIFT; + } + IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_FCOE), etqf); + IXGBE_WRITE_REG(hw, IXGBE_ETQS(IXGBE_ETQF_FILTER_FCOE), 0); + + /* leave registers un-configured if FCoE is disabled */ + if (!(adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) + return; + + /* Use one or more Rx queues for FCoE by redirection table */ + fcreta_size = IXGBE_FCRETA_SIZE; + if (adapter->hw.mac.type == ixgbe_mac_X550) + fcreta_size = IXGBE_FCRETA_SIZE_X550; + + for (i = 0; i < fcreta_size; i++) { + if (adapter->hw.mac.type == ixgbe_mac_X550) { + int fcoe_i_h = fcoe->offset + ((i + fcreta_size) % + fcoe->indices); + fcoe_q_h = adapter->rx_ring[fcoe_i_h]->reg_idx; + fcoe_q_h = (fcoe_q_h << IXGBE_FCRETA_ENTRY_HIGH_SHIFT) & + IXGBE_FCRETA_ENTRY_HIGH_MASK; + } + + fcoe_i = fcoe->offset + (i % fcoe->indices); + fcoe_i &= IXGBE_FCRETA_ENTRY_MASK; + fcoe_q = adapter->rx_ring[fcoe_i]->reg_idx; + fcoe_q |= fcoe_q_h; + IXGBE_WRITE_REG(hw, IXGBE_FCRETA(i), fcoe_q); + } + IXGBE_WRITE_REG(hw, IXGBE_FCRECTL, IXGBE_FCRECTL_ENA); + + /* Enable L2 EtherType filter for FIP */ + etqf = ETH_P_FIP | IXGBE_ETQF_FILTER_EN; + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { + etqf |= IXGBE_ETQF_POOL_ENABLE; + etqf |= VMDQ_P(0) << IXGBE_ETQF_POOL_SHIFT; + } + IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_FIP), etqf); + + /* Send FIP frames to the first FCoE queue */ + fcoe_q = adapter->rx_ring[fcoe->offset]->reg_idx; + IXGBE_WRITE_REG(hw, IXGBE_ETQS(IXGBE_ETQF_FILTER_FIP), + IXGBE_ETQS_QUEUE_EN | + (fcoe_q << IXGBE_ETQS_RX_QUEUE_SHIFT)); + + /* Configure FCoE Rx control */ + IXGBE_WRITE_REG(hw, IXGBE_FCRXCTRL, + IXGBE_FCRXCTRL_FCCRCBO | + (FC_FCOE_VER << IXGBE_FCRXCTRL_FCOEVER_SHIFT)); +} + +/** + * ixgbe_free_fcoe_ddp_resources - release all fcoe ddp context resources + * @adapter : ixgbe adapter + * + * Cleans up outstanding ddp context resources + * + * Returns : none + */ +void ixgbe_free_fcoe_ddp_resources(struct ixgbe_adapter *adapter) +{ + struct ixgbe_fcoe *fcoe = &adapter->fcoe; + int cpu, i, ddp_max; + + /* do nothing if no DDP pools were allocated */ + if (!fcoe->ddp_pool) + return; + + ddp_max = IXGBE_FCOE_DDP_MAX; + /* X550 has different DDP Max limit */ + if (adapter->hw.mac.type == ixgbe_mac_X550) + ddp_max = IXGBE_FCOE_DDP_MAX_X550; + + for (i = 0; i < ddp_max; i++) + ixgbe_fcoe_ddp_put(adapter->netdev, i); + + for_each_possible_cpu(cpu) + ixgbe_fcoe_dma_pool_free(fcoe, cpu); + + dma_unmap_single(&adapter->pdev->dev, + fcoe->extra_ddp_buffer_dma, + IXGBE_FCBUFF_MIN, + DMA_FROM_DEVICE); + kfree(fcoe->extra_ddp_buffer); + + fcoe->extra_ddp_buffer = NULL; + fcoe->extra_ddp_buffer_dma = 0; +} + +/** + * ixgbe_setup_fcoe_ddp_resources - setup all fcoe ddp context resources + * @adapter: ixgbe adapter + * + * Sets up ddp context resouces + * + * Returns : 0 indicates success or -EINVAL on failure + */ +int ixgbe_setup_fcoe_ddp_resources(struct ixgbe_adapter *adapter) +{ + struct ixgbe_fcoe *fcoe = &adapter->fcoe; + struct device *dev = &adapter->pdev->dev; + void *buffer; + dma_addr_t dma; + unsigned int cpu; + + /* do nothing if no DDP pools were allocated */ + if (!fcoe->ddp_pool) + return 0; + + /* Extra buffer to be shared by all DDPs for HW work around */ + buffer = kmalloc(IXGBE_FCBUFF_MIN, GFP_KERNEL); + if (!buffer) + return -ENOMEM; + + dma = dma_map_single(dev, buffer, IXGBE_FCBUFF_MIN, DMA_FROM_DEVICE); + if (dma_mapping_error(dev, dma)) { + e_err(drv, "failed to map extra DDP buffer\n"); + kfree(buffer); + return -ENOMEM; + } + + fcoe->extra_ddp_buffer = buffer; + fcoe->extra_ddp_buffer_dma = dma; + + /* allocate pci pool for each cpu */ + for_each_possible_cpu(cpu) { + int err = ixgbe_fcoe_dma_pool_alloc(fcoe, dev, cpu); + if (!err) + continue; + + e_err(drv, "failed to alloc DDP pool on cpu:%d\n", cpu); + ixgbe_free_fcoe_ddp_resources(adapter); + return -ENOMEM; + } + + return 0; +} + +static int ixgbe_fcoe_ddp_enable(struct ixgbe_adapter *adapter) +{ + struct ixgbe_fcoe *fcoe = &adapter->fcoe; + + if (!(adapter->flags & IXGBE_FLAG_FCOE_CAPABLE)) + return -EINVAL; + + fcoe->ddp_pool = alloc_percpu(struct ixgbe_fcoe_ddp_pool); + + if (!fcoe->ddp_pool) { + e_err(drv, "failed to allocate percpu DDP resources\n"); + return -ENOMEM; + } + + adapter->netdev->fcoe_ddp_xid = IXGBE_FCOE_DDP_MAX - 1; + /* X550 has different DDP Max limit */ + if (adapter->hw.mac.type == ixgbe_mac_X550) + adapter->netdev->fcoe_ddp_xid = IXGBE_FCOE_DDP_MAX_X550 - 1; + + return 0; +} + +static void ixgbe_fcoe_ddp_disable(struct ixgbe_adapter *adapter) +{ + struct ixgbe_fcoe *fcoe = &adapter->fcoe; + + adapter->netdev->fcoe_ddp_xid = 0; + + if (!fcoe->ddp_pool) + return; + + free_percpu(fcoe->ddp_pool); + fcoe->ddp_pool = NULL; +} + +/** + * ixgbe_fcoe_enable - turn on FCoE offload feature + * @netdev: the corresponding netdev + * + * Turns on FCoE offload feature in 82599. + * + * Returns : 0 indicates success or -EINVAL on failure + */ +int ixgbe_fcoe_enable(struct net_device *netdev) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_fcoe *fcoe = &adapter->fcoe; + + atomic_inc(&fcoe->refcnt); + + if (!(adapter->flags & IXGBE_FLAG_FCOE_CAPABLE)) + return -EINVAL; + + if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) + return -EINVAL; + + e_info(drv, "Enabling FCoE offload features.\n"); + + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) + e_warn(probe, "Enabling FCoE on PF will disable legacy VFs\n"); + + if (netif_running(netdev)) + netdev->netdev_ops->ndo_stop(netdev); + + /* Allocate per CPU memory to track DDP pools */ + ixgbe_fcoe_ddp_enable(adapter); + + /* enable FCoE and notify stack */ + adapter->flags |= IXGBE_FLAG_FCOE_ENABLED; + netdev->features |= NETIF_F_FCOE_MTU; + netdev_features_change(netdev); + + /* release existing queues and reallocate them */ + ixgbe_clear_interrupt_scheme(adapter); + ixgbe_init_interrupt_scheme(adapter); + + if (netif_running(netdev)) + netdev->netdev_ops->ndo_open(netdev); + + return 0; +} + +/** + * ixgbe_fcoe_disable - turn off FCoE offload feature + * @netdev: the corresponding netdev + * + * Turns off FCoE offload feature in 82599. + * + * Returns : 0 indicates success or -EINVAL on failure + */ +int ixgbe_fcoe_disable(struct net_device *netdev) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + if (!atomic_dec_and_test(&adapter->fcoe.refcnt)) + return -EINVAL; + + if (!(adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) + return -EINVAL; + + e_info(drv, "Disabling FCoE offload features.\n"); + if (netif_running(netdev)) + netdev->netdev_ops->ndo_stop(netdev); + + /* Free per CPU memory to track DDP pools */ + ixgbe_fcoe_ddp_disable(adapter); + + /* disable FCoE and notify stack */ + adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED; + netdev->features &= ~NETIF_F_FCOE_MTU; + + netdev_features_change(netdev); + + /* release existing queues and reallocate them */ + ixgbe_clear_interrupt_scheme(adapter); + ixgbe_init_interrupt_scheme(adapter); + + if (netif_running(netdev)) + netdev->netdev_ops->ndo_open(netdev); + + return 0; +} + +/** + * ixgbe_fcoe_get_wwn - get world wide name for the node or the port + * @netdev : ixgbe adapter + * @wwn : the world wide name + * @type: the type of world wide name + * + * Returns the node or port world wide name if both the prefix and the san + * mac address are valid, then the wwn is formed based on the NAA-2 for + * IEEE Extended name identifier (ref. to T10 FC-LS Spec., Sec. 15.3). + * + * Returns : 0 on success + */ +int ixgbe_fcoe_get_wwn(struct net_device *netdev, u64 *wwn, int type) +{ + u16 prefix = 0xffff; + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_mac_info *mac = &adapter->hw.mac; + + switch (type) { + case NETDEV_FCOE_WWNN: + prefix = mac->wwnn_prefix; + break; + case NETDEV_FCOE_WWPN: + prefix = mac->wwpn_prefix; + break; + default: + break; + } + + if ((prefix != 0xffff) && + is_valid_ether_addr(mac->san_addr)) { + *wwn = ((u64) prefix << 48) | + ((u64) mac->san_addr[0] << 40) | + ((u64) mac->san_addr[1] << 32) | + ((u64) mac->san_addr[2] << 24) | + ((u64) mac->san_addr[3] << 16) | + ((u64) mac->san_addr[4] << 8) | + ((u64) mac->san_addr[5]); + return 0; + } + return -EINVAL; +} + +/** + * ixgbe_fcoe_get_hbainfo - get FCoE HBA information + * @netdev : ixgbe adapter + * @info : HBA information + * + * Returns ixgbe HBA information + * + * Returns : 0 on success + */ +int ixgbe_fcoe_get_hbainfo(struct net_device *netdev, + struct netdev_fcoe_hbainfo *info) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + u64 dsn; + + if (!info) + return -EINVAL; + + /* Don't return information on unsupported devices */ + if (!(adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) + return -EINVAL; + + /* Manufacturer */ + snprintf(info->manufacturer, sizeof(info->manufacturer), + "Intel Corporation"); + + /* Serial Number */ + + /* Get the PCI-e Device Serial Number Capability */ + dsn = pci_get_dsn(adapter->pdev); + if (dsn) + snprintf(info->serial_number, sizeof(info->serial_number), + "%016llX", dsn); + else + snprintf(info->serial_number, sizeof(info->serial_number), + "Unknown"); + + /* Hardware Version */ + snprintf(info->hardware_version, + sizeof(info->hardware_version), + "Rev %d", hw->revision_id); + /* Driver Name/Version */ + snprintf(info->driver_version, + sizeof(info->driver_version), + "%s v%s", + ixgbe_driver_name, + UTS_RELEASE); + /* Firmware Version */ + strlcpy(info->firmware_version, adapter->eeprom_id, + sizeof(info->firmware_version)); + + /* Model */ + if (hw->mac.type == ixgbe_mac_82599EB) { + snprintf(info->model, + sizeof(info->model), + "Intel 82599"); + } else if (hw->mac.type == ixgbe_mac_X550) { + snprintf(info->model, + sizeof(info->model), + "Intel X550"); + } else { + snprintf(info->model, + sizeof(info->model), + "Intel X540"); + } + + /* Model Description */ + snprintf(info->model_description, + sizeof(info->model_description), + "%s", + ixgbe_default_device_descr); + + return 0; +} + +/** + * ixgbe_fcoe_get_tc - get the current TC that fcoe is mapped to + * @adapter: pointer to the device adapter structure + * + * Return : TC that FCoE is mapped to + */ +u8 ixgbe_fcoe_get_tc(struct ixgbe_adapter *adapter) +{ +#ifdef CONFIG_IXGBE_DCB + return netdev_get_prio_tc_map(adapter->netdev, adapter->fcoe.up); +#else + return 0; +#endif +} diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h new file mode 100644 index 000000000..724f53823 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h @@ -0,0 +1,63 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#ifndef _IXGBE_FCOE_H +#define _IXGBE_FCOE_H + +#include <scsi/fc/fc_fs.h> +#include <scsi/fc/fc_fcoe.h> + +/* shift bits within STAT fo FCSTAT */ +#define IXGBE_RXDADV_FCSTAT_SHIFT 4 + +/* ddp user buffer */ +#define IXGBE_BUFFCNT_MAX 256 /* 8 bits bufcnt */ +#define IXGBE_FCPTR_ALIGN 16 +#define IXGBE_FCPTR_MAX (IXGBE_BUFFCNT_MAX * sizeof(dma_addr_t)) +#define IXGBE_FCBUFF_4KB 0x0 +#define IXGBE_FCBUFF_8KB 0x1 +#define IXGBE_FCBUFF_16KB 0x2 +#define IXGBE_FCBUFF_64KB 0x3 +#define IXGBE_FCBUFF_MAX 65536 /* 64KB max */ +#define IXGBE_FCBUFF_MIN 4096 /* 4KB min */ +#define IXGBE_FCOE_DDP_MAX 512 /* 9 bits xid */ +#define IXGBE_FCOE_DDP_MAX_X550 2048 /* 11 bits xid */ + +/* Default traffic class to use for FCoE */ +#define IXGBE_FCOE_DEFTC 3 + +/* fcerr */ +#define IXGBE_FCERR_BADCRC 0x00100000 + +/* FCoE DDP for target mode */ +#define __IXGBE_FCOE_TARGET 1 + +struct ixgbe_fcoe_ddp { + int len; + u32 err; + unsigned int sgc; + struct scatterlist *sgl; + dma_addr_t udp; + u64 *udl; + struct dma_pool *pool; +}; + +/* per cpu variables */ +struct ixgbe_fcoe_ddp_pool { + struct dma_pool *pool; + u64 noddp; + u64 noddp_ext_buff; +}; + +struct ixgbe_fcoe { + struct ixgbe_fcoe_ddp_pool __percpu *ddp_pool; + atomic_t refcnt; + spinlock_t lock; + struct ixgbe_fcoe_ddp ddp[IXGBE_FCOE_DDP_MAX_X550]; + void *extra_ddp_buffer; + dma_addr_t extra_ddp_buffer_dma; + unsigned long mode; + u8 up; +}; + +#endif /* _IXGBE_FCOE_H */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c new file mode 100644 index 000000000..319620856 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c @@ -0,0 +1,1302 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 Oracle and/or its affiliates. All rights reserved. */ + +#include "ixgbe.h" +#include <net/xfrm.h> +#include <crypto/aead.h> +#include <linux/if_bridge.h> + +#define IXGBE_IPSEC_KEY_BITS 160 +static const char aes_gcm_name[] = "rfc4106(gcm(aes))"; + +static void ixgbe_ipsec_del_sa(struct xfrm_state *xs); + +/** + * ixgbe_ipsec_set_tx_sa - set the Tx SA registers + * @hw: hw specific details + * @idx: register index to write + * @key: key byte array + * @salt: salt bytes + **/ +static void ixgbe_ipsec_set_tx_sa(struct ixgbe_hw *hw, u16 idx, + u32 key[], u32 salt) +{ + u32 reg; + int i; + + for (i = 0; i < 4; i++) + IXGBE_WRITE_REG(hw, IXGBE_IPSTXKEY(i), + (__force u32)cpu_to_be32(key[3 - i])); + IXGBE_WRITE_REG(hw, IXGBE_IPSTXSALT, (__force u32)cpu_to_be32(salt)); + IXGBE_WRITE_FLUSH(hw); + + reg = IXGBE_READ_REG(hw, IXGBE_IPSTXIDX); + reg &= IXGBE_RXTXIDX_IPS_EN; + reg |= idx << IXGBE_RXTXIDX_IDX_SHIFT | IXGBE_RXTXIDX_WRITE; + IXGBE_WRITE_REG(hw, IXGBE_IPSTXIDX, reg); + IXGBE_WRITE_FLUSH(hw); +} + +/** + * ixgbe_ipsec_set_rx_item - set an Rx table item + * @hw: hw specific details + * @idx: register index to write + * @tbl: table selector + * + * Trigger the device to store into a particular Rx table the + * data that has already been loaded into the input register + **/ +static void ixgbe_ipsec_set_rx_item(struct ixgbe_hw *hw, u16 idx, + enum ixgbe_ipsec_tbl_sel tbl) +{ + u32 reg; + + reg = IXGBE_READ_REG(hw, IXGBE_IPSRXIDX); + reg &= IXGBE_RXTXIDX_IPS_EN; + reg |= tbl << IXGBE_RXIDX_TBL_SHIFT | + idx << IXGBE_RXTXIDX_IDX_SHIFT | + IXGBE_RXTXIDX_WRITE; + IXGBE_WRITE_REG(hw, IXGBE_IPSRXIDX, reg); + IXGBE_WRITE_FLUSH(hw); +} + +/** + * ixgbe_ipsec_set_rx_sa - set up the register bits to save SA info + * @hw: hw specific details + * @idx: register index to write + * @spi: security parameter index + * @key: key byte array + * @salt: salt bytes + * @mode: rx decrypt control bits + * @ip_idx: index into IP table for related IP address + **/ +static void ixgbe_ipsec_set_rx_sa(struct ixgbe_hw *hw, u16 idx, __be32 spi, + u32 key[], u32 salt, u32 mode, u32 ip_idx) +{ + int i; + + /* store the SPI (in bigendian) and IPidx */ + IXGBE_WRITE_REG(hw, IXGBE_IPSRXSPI, + (__force u32)cpu_to_le32((__force u32)spi)); + IXGBE_WRITE_REG(hw, IXGBE_IPSRXIPIDX, ip_idx); + IXGBE_WRITE_FLUSH(hw); + + ixgbe_ipsec_set_rx_item(hw, idx, ips_rx_spi_tbl); + + /* store the key, salt, and mode */ + for (i = 0; i < 4; i++) + IXGBE_WRITE_REG(hw, IXGBE_IPSRXKEY(i), + (__force u32)cpu_to_be32(key[3 - i])); + IXGBE_WRITE_REG(hw, IXGBE_IPSRXSALT, (__force u32)cpu_to_be32(salt)); + IXGBE_WRITE_REG(hw, IXGBE_IPSRXMOD, mode); + IXGBE_WRITE_FLUSH(hw); + + ixgbe_ipsec_set_rx_item(hw, idx, ips_rx_key_tbl); +} + +/** + * ixgbe_ipsec_set_rx_ip - set up the register bits to save SA IP addr info + * @hw: hw specific details + * @idx: register index to write + * @addr: IP address byte array + **/ +static void ixgbe_ipsec_set_rx_ip(struct ixgbe_hw *hw, u16 idx, __be32 addr[]) +{ + int i; + + /* store the ip address */ + for (i = 0; i < 4; i++) + IXGBE_WRITE_REG(hw, IXGBE_IPSRXIPADDR(i), + (__force u32)cpu_to_le32((__force u32)addr[i])); + IXGBE_WRITE_FLUSH(hw); + + ixgbe_ipsec_set_rx_item(hw, idx, ips_rx_ip_tbl); +} + +/** + * ixgbe_ipsec_clear_hw_tables - because some tables don't get cleared on reset + * @adapter: board private structure + **/ +static void ixgbe_ipsec_clear_hw_tables(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 buf[4] = {0, 0, 0, 0}; + u16 idx; + + /* disable Rx and Tx SA lookup */ + IXGBE_WRITE_REG(hw, IXGBE_IPSRXIDX, 0); + IXGBE_WRITE_REG(hw, IXGBE_IPSTXIDX, 0); + + /* scrub the tables - split the loops for the max of the IP table */ + for (idx = 0; idx < IXGBE_IPSEC_MAX_RX_IP_COUNT; idx++) { + ixgbe_ipsec_set_tx_sa(hw, idx, buf, 0); + ixgbe_ipsec_set_rx_sa(hw, idx, 0, buf, 0, 0, 0); + ixgbe_ipsec_set_rx_ip(hw, idx, (__be32 *)buf); + } + for (; idx < IXGBE_IPSEC_MAX_SA_COUNT; idx++) { + ixgbe_ipsec_set_tx_sa(hw, idx, buf, 0); + ixgbe_ipsec_set_rx_sa(hw, idx, 0, buf, 0, 0, 0); + } +} + +/** + * ixgbe_ipsec_stop_data + * @adapter: board private structure + **/ +static void ixgbe_ipsec_stop_data(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + bool link = adapter->link_up; + u32 t_rdy, r_rdy; + u32 limit; + u32 reg; + + /* halt data paths */ + reg = IXGBE_READ_REG(hw, IXGBE_SECTXCTRL); + reg |= IXGBE_SECTXCTRL_TX_DIS; + IXGBE_WRITE_REG(hw, IXGBE_SECTXCTRL, reg); + + reg = IXGBE_READ_REG(hw, IXGBE_SECRXCTRL); + reg |= IXGBE_SECRXCTRL_RX_DIS; + IXGBE_WRITE_REG(hw, IXGBE_SECRXCTRL, reg); + + /* If both Tx and Rx are ready there are no packets + * that we need to flush so the loopback configuration + * below is not necessary. + */ + t_rdy = IXGBE_READ_REG(hw, IXGBE_SECTXSTAT) & + IXGBE_SECTXSTAT_SECTX_RDY; + r_rdy = IXGBE_READ_REG(hw, IXGBE_SECRXSTAT) & + IXGBE_SECRXSTAT_SECRX_RDY; + if (t_rdy && r_rdy) + return; + + /* If the tx fifo doesn't have link, but still has data, + * we can't clear the tx sec block. Set the MAC loopback + * before block clear + */ + if (!link) { + reg = IXGBE_READ_REG(hw, IXGBE_MACC); + reg |= IXGBE_MACC_FLU; + IXGBE_WRITE_REG(hw, IXGBE_MACC, reg); + + reg = IXGBE_READ_REG(hw, IXGBE_HLREG0); + reg |= IXGBE_HLREG0_LPBK; + IXGBE_WRITE_REG(hw, IXGBE_HLREG0, reg); + + IXGBE_WRITE_FLUSH(hw); + mdelay(3); + } + + /* wait for the paths to empty */ + limit = 20; + do { + mdelay(10); + t_rdy = IXGBE_READ_REG(hw, IXGBE_SECTXSTAT) & + IXGBE_SECTXSTAT_SECTX_RDY; + r_rdy = IXGBE_READ_REG(hw, IXGBE_SECRXSTAT) & + IXGBE_SECRXSTAT_SECRX_RDY; + } while (!(t_rdy && r_rdy) && limit--); + + /* undo loopback if we played with it earlier */ + if (!link) { + reg = IXGBE_READ_REG(hw, IXGBE_MACC); + reg &= ~IXGBE_MACC_FLU; + IXGBE_WRITE_REG(hw, IXGBE_MACC, reg); + + reg = IXGBE_READ_REG(hw, IXGBE_HLREG0); + reg &= ~IXGBE_HLREG0_LPBK; + IXGBE_WRITE_REG(hw, IXGBE_HLREG0, reg); + + IXGBE_WRITE_FLUSH(hw); + } +} + +/** + * ixgbe_ipsec_stop_engine + * @adapter: board private structure + **/ +static void ixgbe_ipsec_stop_engine(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 reg; + + ixgbe_ipsec_stop_data(adapter); + + /* disable Rx and Tx SA lookup */ + IXGBE_WRITE_REG(hw, IXGBE_IPSTXIDX, 0); + IXGBE_WRITE_REG(hw, IXGBE_IPSRXIDX, 0); + + /* disable the Rx and Tx engines and full packet store-n-forward */ + reg = IXGBE_READ_REG(hw, IXGBE_SECTXCTRL); + reg |= IXGBE_SECTXCTRL_SECTX_DIS; + reg &= ~IXGBE_SECTXCTRL_STORE_FORWARD; + IXGBE_WRITE_REG(hw, IXGBE_SECTXCTRL, reg); + + reg = IXGBE_READ_REG(hw, IXGBE_SECRXCTRL); + reg |= IXGBE_SECRXCTRL_SECRX_DIS; + IXGBE_WRITE_REG(hw, IXGBE_SECRXCTRL, reg); + + /* restore the "tx security buffer almost full threshold" to 0x250 */ + IXGBE_WRITE_REG(hw, IXGBE_SECTXBUFFAF, 0x250); + + /* Set minimum IFG between packets back to the default 0x1 */ + reg = IXGBE_READ_REG(hw, IXGBE_SECTXMINIFG); + reg = (reg & 0xfffffff0) | 0x1; + IXGBE_WRITE_REG(hw, IXGBE_SECTXMINIFG, reg); + + /* final set for normal (no ipsec offload) processing */ + IXGBE_WRITE_REG(hw, IXGBE_SECTXCTRL, IXGBE_SECTXCTRL_SECTX_DIS); + IXGBE_WRITE_REG(hw, IXGBE_SECRXCTRL, IXGBE_SECRXCTRL_SECRX_DIS); + + IXGBE_WRITE_FLUSH(hw); +} + +/** + * ixgbe_ipsec_start_engine + * @adapter: board private structure + * + * NOTE: this increases power consumption whether being used or not + **/ +static void ixgbe_ipsec_start_engine(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 reg; + + ixgbe_ipsec_stop_data(adapter); + + /* Set minimum IFG between packets to 3 */ + reg = IXGBE_READ_REG(hw, IXGBE_SECTXMINIFG); + reg = (reg & 0xfffffff0) | 0x3; + IXGBE_WRITE_REG(hw, IXGBE_SECTXMINIFG, reg); + + /* Set "tx security buffer almost full threshold" to 0x15 so that the + * almost full indication is generated only after buffer contains at + * least an entire jumbo packet. + */ + reg = IXGBE_READ_REG(hw, IXGBE_SECTXBUFFAF); + reg = (reg & 0xfffffc00) | 0x15; + IXGBE_WRITE_REG(hw, IXGBE_SECTXBUFFAF, reg); + + /* restart the data paths by clearing the DISABLE bits */ + IXGBE_WRITE_REG(hw, IXGBE_SECRXCTRL, 0); + IXGBE_WRITE_REG(hw, IXGBE_SECTXCTRL, IXGBE_SECTXCTRL_STORE_FORWARD); + + /* enable Rx and Tx SA lookup */ + IXGBE_WRITE_REG(hw, IXGBE_IPSTXIDX, IXGBE_RXTXIDX_IPS_EN); + IXGBE_WRITE_REG(hw, IXGBE_IPSRXIDX, IXGBE_RXTXIDX_IPS_EN); + + IXGBE_WRITE_FLUSH(hw); +} + +/** + * ixgbe_ipsec_restore - restore the ipsec HW settings after a reset + * @adapter: board private structure + * + * Reload the HW tables from the SW tables after they've been bashed + * by a chip reset. + * + * Any VF entries are removed from the SW and HW tables since either + * (a) the VF also gets reset on PF reset and will ask again for the + * offloads, or (b) the VF has been removed by a change in the num_vfs. + **/ +void ixgbe_ipsec_restore(struct ixgbe_adapter *adapter) +{ + struct ixgbe_ipsec *ipsec = adapter->ipsec; + struct ixgbe_hw *hw = &adapter->hw; + int i; + + if (!(adapter->flags2 & IXGBE_FLAG2_IPSEC_ENABLED)) + return; + + /* clean up and restart the engine */ + ixgbe_ipsec_stop_engine(adapter); + ixgbe_ipsec_clear_hw_tables(adapter); + ixgbe_ipsec_start_engine(adapter); + + /* reload the Rx and Tx keys */ + for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) { + struct rx_sa *r = &ipsec->rx_tbl[i]; + struct tx_sa *t = &ipsec->tx_tbl[i]; + + if (r->used) { + if (r->mode & IXGBE_RXTXMOD_VF) + ixgbe_ipsec_del_sa(r->xs); + else + ixgbe_ipsec_set_rx_sa(hw, i, r->xs->id.spi, + r->key, r->salt, + r->mode, r->iptbl_ind); + } + + if (t->used) { + if (t->mode & IXGBE_RXTXMOD_VF) + ixgbe_ipsec_del_sa(t->xs); + else + ixgbe_ipsec_set_tx_sa(hw, i, t->key, t->salt); + } + } + + /* reload the IP addrs */ + for (i = 0; i < IXGBE_IPSEC_MAX_RX_IP_COUNT; i++) { + struct rx_ip_sa *ipsa = &ipsec->ip_tbl[i]; + + if (ipsa->used) + ixgbe_ipsec_set_rx_ip(hw, i, ipsa->ipaddr); + } +} + +/** + * ixgbe_ipsec_find_empty_idx - find the first unused security parameter index + * @ipsec: pointer to ipsec struct + * @rxtable: true if we need to look in the Rx table + * + * Returns the first unused index in either the Rx or Tx SA table + **/ +static int ixgbe_ipsec_find_empty_idx(struct ixgbe_ipsec *ipsec, bool rxtable) +{ + u32 i; + + if (rxtable) { + if (ipsec->num_rx_sa == IXGBE_IPSEC_MAX_SA_COUNT) + return -ENOSPC; + + /* search rx sa table */ + for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) { + if (!ipsec->rx_tbl[i].used) + return i; + } + } else { + if (ipsec->num_tx_sa == IXGBE_IPSEC_MAX_SA_COUNT) + return -ENOSPC; + + /* search tx sa table */ + for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) { + if (!ipsec->tx_tbl[i].used) + return i; + } + } + + return -ENOSPC; +} + +/** + * ixgbe_ipsec_find_rx_state - find the state that matches + * @ipsec: pointer to ipsec struct + * @daddr: inbound address to match + * @proto: protocol to match + * @spi: SPI to match + * @ip4: true if using an ipv4 address + * + * Returns a pointer to the matching SA state information + **/ +static struct xfrm_state *ixgbe_ipsec_find_rx_state(struct ixgbe_ipsec *ipsec, + __be32 *daddr, u8 proto, + __be32 spi, bool ip4) +{ + struct rx_sa *rsa; + struct xfrm_state *ret = NULL; + + rcu_read_lock(); + hash_for_each_possible_rcu(ipsec->rx_sa_list, rsa, hlist, + (__force u32)spi) { + if (rsa->mode & IXGBE_RXTXMOD_VF) + continue; + if (spi == rsa->xs->id.spi && + ((ip4 && *daddr == rsa->xs->id.daddr.a4) || + (!ip4 && !memcmp(daddr, &rsa->xs->id.daddr.a6, + sizeof(rsa->xs->id.daddr.a6)))) && + proto == rsa->xs->id.proto) { + ret = rsa->xs; + xfrm_state_hold(ret); + break; + } + } + rcu_read_unlock(); + return ret; +} + +/** + * ixgbe_ipsec_parse_proto_keys - find the key and salt based on the protocol + * @xs: pointer to xfrm_state struct + * @mykey: pointer to key array to populate + * @mysalt: pointer to salt value to populate + * + * This copies the protocol keys and salt to our own data tables. The + * 82599 family only supports the one algorithm. + **/ +static int ixgbe_ipsec_parse_proto_keys(struct xfrm_state *xs, + u32 *mykey, u32 *mysalt) +{ + struct net_device *dev = xs->xso.real_dev; + unsigned char *key_data; + char *alg_name = NULL; + int key_len; + + if (!xs->aead) { + netdev_err(dev, "Unsupported IPsec algorithm\n"); + return -EINVAL; + } + + if (xs->aead->alg_icv_len != IXGBE_IPSEC_AUTH_BITS) { + netdev_err(dev, "IPsec offload requires %d bit authentication\n", + IXGBE_IPSEC_AUTH_BITS); + return -EINVAL; + } + + key_data = &xs->aead->alg_key[0]; + key_len = xs->aead->alg_key_len; + alg_name = xs->aead->alg_name; + + if (strcmp(alg_name, aes_gcm_name)) { + netdev_err(dev, "Unsupported IPsec algorithm - please use %s\n", + aes_gcm_name); + return -EINVAL; + } + + /* The key bytes come down in a bigendian array of bytes, so + * we don't need to do any byteswapping. + * 160 accounts for 16 byte key and 4 byte salt + */ + if (key_len == IXGBE_IPSEC_KEY_BITS) { + *mysalt = ((u32 *)key_data)[4]; + } else if (key_len != (IXGBE_IPSEC_KEY_BITS - (sizeof(*mysalt) * 8))) { + netdev_err(dev, "IPsec hw offload only supports keys up to 128 bits with a 32 bit salt\n"); + return -EINVAL; + } else { + netdev_info(dev, "IPsec hw offload parameters missing 32 bit salt value\n"); + *mysalt = 0; + } + memcpy(mykey, key_data, 16); + + return 0; +} + +/** + * ixgbe_ipsec_check_mgmt_ip - make sure there is no clash with mgmt IP filters + * @xs: pointer to transformer state struct + **/ +static int ixgbe_ipsec_check_mgmt_ip(struct xfrm_state *xs) +{ + struct net_device *dev = xs->xso.real_dev; + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_hw *hw = &adapter->hw; + u32 mfval, manc, reg; + int num_filters = 4; + bool manc_ipv4; + u32 bmcipval; + int i, j; + +#define MANC_EN_IPV4_FILTER BIT(24) +#define MFVAL_IPV4_FILTER_SHIFT 16 +#define MFVAL_IPV6_FILTER_SHIFT 24 +#define MIPAF_ARR(_m, _n) (IXGBE_MIPAF + ((_m) * 0x10) + ((_n) * 4)) + +#define IXGBE_BMCIP(_n) (0x5050 + ((_n) * 4)) +#define IXGBE_BMCIPVAL 0x5060 +#define BMCIP_V4 0x2 +#define BMCIP_V6 0x3 +#define BMCIP_MASK 0x3 + + manc = IXGBE_READ_REG(hw, IXGBE_MANC); + manc_ipv4 = !!(manc & MANC_EN_IPV4_FILTER); + mfval = IXGBE_READ_REG(hw, IXGBE_MFVAL); + bmcipval = IXGBE_READ_REG(hw, IXGBE_BMCIPVAL); + + if (xs->props.family == AF_INET) { + /* are there any IPv4 filters to check? */ + if (manc_ipv4) { + /* the 4 ipv4 filters are all in MIPAF(3, i) */ + for (i = 0; i < num_filters; i++) { + if (!(mfval & BIT(MFVAL_IPV4_FILTER_SHIFT + i))) + continue; + + reg = IXGBE_READ_REG(hw, MIPAF_ARR(3, i)); + if (reg == xs->id.daddr.a4) + return 1; + } + } + + if ((bmcipval & BMCIP_MASK) == BMCIP_V4) { + reg = IXGBE_READ_REG(hw, IXGBE_BMCIP(3)); + if (reg == xs->id.daddr.a4) + return 1; + } + + } else { + /* if there are ipv4 filters, they are in the last ipv6 slot */ + if (manc_ipv4) + num_filters = 3; + + for (i = 0; i < num_filters; i++) { + if (!(mfval & BIT(MFVAL_IPV6_FILTER_SHIFT + i))) + continue; + + for (j = 0; j < 4; j++) { + reg = IXGBE_READ_REG(hw, MIPAF_ARR(i, j)); + if (reg != xs->id.daddr.a6[j]) + break; + } + if (j == 4) /* did we match all 4 words? */ + return 1; + } + + if ((bmcipval & BMCIP_MASK) == BMCIP_V6) { + for (j = 0; j < 4; j++) { + reg = IXGBE_READ_REG(hw, IXGBE_BMCIP(j)); + if (reg != xs->id.daddr.a6[j]) + break; + } + if (j == 4) /* did we match all 4 words? */ + return 1; + } + } + + return 0; +} + +/** + * ixgbe_ipsec_add_sa - program device with a security association + * @xs: pointer to transformer state struct + **/ +static int ixgbe_ipsec_add_sa(struct xfrm_state *xs) +{ + struct net_device *dev = xs->xso.real_dev; + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_ipsec *ipsec = adapter->ipsec; + struct ixgbe_hw *hw = &adapter->hw; + int checked, match, first; + u16 sa_idx; + int ret; + int i; + + if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) { + netdev_err(dev, "Unsupported protocol 0x%04x for ipsec offload\n", + xs->id.proto); + return -EINVAL; + } + + if (xs->props.mode != XFRM_MODE_TRANSPORT) { + netdev_err(dev, "Unsupported mode for ipsec offload\n"); + return -EINVAL; + } + + if (ixgbe_ipsec_check_mgmt_ip(xs)) { + netdev_err(dev, "IPsec IP addr clash with mgmt filters\n"); + return -EINVAL; + } + + if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) { + struct rx_sa rsa; + + if (xs->calg) { + netdev_err(dev, "Compression offload not supported\n"); + return -EINVAL; + } + + /* find the first unused index */ + ret = ixgbe_ipsec_find_empty_idx(ipsec, true); + if (ret < 0) { + netdev_err(dev, "No space for SA in Rx table!\n"); + return ret; + } + sa_idx = (u16)ret; + + memset(&rsa, 0, sizeof(rsa)); + rsa.used = true; + rsa.xs = xs; + + if (rsa.xs->id.proto & IPPROTO_ESP) + rsa.decrypt = xs->ealg || xs->aead; + + /* get the key and salt */ + ret = ixgbe_ipsec_parse_proto_keys(xs, rsa.key, &rsa.salt); + if (ret) { + netdev_err(dev, "Failed to get key data for Rx SA table\n"); + return ret; + } + + /* get ip for rx sa table */ + if (xs->props.family == AF_INET6) + memcpy(rsa.ipaddr, &xs->id.daddr.a6, 16); + else + memcpy(&rsa.ipaddr[3], &xs->id.daddr.a4, 4); + + /* The HW does not have a 1:1 mapping from keys to IP addrs, so + * check for a matching IP addr entry in the table. If the addr + * already exists, use it; else find an unused slot and add the + * addr. If one does not exist and there are no unused table + * entries, fail the request. + */ + + /* Find an existing match or first not used, and stop looking + * after we've checked all we know we have. + */ + checked = 0; + match = -1; + first = -1; + for (i = 0; + i < IXGBE_IPSEC_MAX_RX_IP_COUNT && + (checked < ipsec->num_rx_sa || first < 0); + i++) { + if (ipsec->ip_tbl[i].used) { + if (!memcmp(ipsec->ip_tbl[i].ipaddr, + rsa.ipaddr, sizeof(rsa.ipaddr))) { + match = i; + break; + } + checked++; + } else if (first < 0) { + first = i; /* track the first empty seen */ + } + } + + if (ipsec->num_rx_sa == 0) + first = 0; + + if (match >= 0) { + /* addrs are the same, we should use this one */ + rsa.iptbl_ind = match; + ipsec->ip_tbl[match].ref_cnt++; + + } else if (first >= 0) { + /* no matches, but here's an empty slot */ + rsa.iptbl_ind = first; + + memcpy(ipsec->ip_tbl[first].ipaddr, + rsa.ipaddr, sizeof(rsa.ipaddr)); + ipsec->ip_tbl[first].ref_cnt = 1; + ipsec->ip_tbl[first].used = true; + + ixgbe_ipsec_set_rx_ip(hw, rsa.iptbl_ind, rsa.ipaddr); + + } else { + /* no match and no empty slot */ + netdev_err(dev, "No space for SA in Rx IP SA table\n"); + memset(&rsa, 0, sizeof(rsa)); + return -ENOSPC; + } + + rsa.mode = IXGBE_RXMOD_VALID; + if (rsa.xs->id.proto & IPPROTO_ESP) + rsa.mode |= IXGBE_RXMOD_PROTO_ESP; + if (rsa.decrypt) + rsa.mode |= IXGBE_RXMOD_DECRYPT; + if (rsa.xs->props.family == AF_INET6) + rsa.mode |= IXGBE_RXMOD_IPV6; + + /* the preparations worked, so save the info */ + memcpy(&ipsec->rx_tbl[sa_idx], &rsa, sizeof(rsa)); + + ixgbe_ipsec_set_rx_sa(hw, sa_idx, rsa.xs->id.spi, rsa.key, + rsa.salt, rsa.mode, rsa.iptbl_ind); + xs->xso.offload_handle = sa_idx + IXGBE_IPSEC_BASE_RX_INDEX; + + ipsec->num_rx_sa++; + + /* hash the new entry for faster search in Rx path */ + hash_add_rcu(ipsec->rx_sa_list, &ipsec->rx_tbl[sa_idx].hlist, + (__force u32)rsa.xs->id.spi); + } else { + struct tx_sa tsa; + + if (adapter->num_vfs && + adapter->bridge_mode != BRIDGE_MODE_VEPA) + return -EOPNOTSUPP; + + /* find the first unused index */ + ret = ixgbe_ipsec_find_empty_idx(ipsec, false); + if (ret < 0) { + netdev_err(dev, "No space for SA in Tx table\n"); + return ret; + } + sa_idx = (u16)ret; + + memset(&tsa, 0, sizeof(tsa)); + tsa.used = true; + tsa.xs = xs; + + if (xs->id.proto & IPPROTO_ESP) + tsa.encrypt = xs->ealg || xs->aead; + + ret = ixgbe_ipsec_parse_proto_keys(xs, tsa.key, &tsa.salt); + if (ret) { + netdev_err(dev, "Failed to get key data for Tx SA table\n"); + memset(&tsa, 0, sizeof(tsa)); + return ret; + } + + /* the preparations worked, so save the info */ + memcpy(&ipsec->tx_tbl[sa_idx], &tsa, sizeof(tsa)); + + ixgbe_ipsec_set_tx_sa(hw, sa_idx, tsa.key, tsa.salt); + + xs->xso.offload_handle = sa_idx + IXGBE_IPSEC_BASE_TX_INDEX; + + ipsec->num_tx_sa++; + } + + /* enable the engine if not already warmed up */ + if (!(adapter->flags2 & IXGBE_FLAG2_IPSEC_ENABLED)) { + ixgbe_ipsec_start_engine(adapter); + adapter->flags2 |= IXGBE_FLAG2_IPSEC_ENABLED; + } + + return 0; +} + +/** + * ixgbe_ipsec_del_sa - clear out this specific SA + * @xs: pointer to transformer state struct + **/ +static void ixgbe_ipsec_del_sa(struct xfrm_state *xs) +{ + struct net_device *dev = xs->xso.real_dev; + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_ipsec *ipsec = adapter->ipsec; + struct ixgbe_hw *hw = &adapter->hw; + u32 zerobuf[4] = {0, 0, 0, 0}; + u16 sa_idx; + + if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) { + struct rx_sa *rsa; + u8 ipi; + + sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_RX_INDEX; + rsa = &ipsec->rx_tbl[sa_idx]; + + if (!rsa->used) { + netdev_err(dev, "Invalid Rx SA selected sa_idx=%d offload_handle=%lu\n", + sa_idx, xs->xso.offload_handle); + return; + } + + ixgbe_ipsec_set_rx_sa(hw, sa_idx, 0, zerobuf, 0, 0, 0); + hash_del_rcu(&rsa->hlist); + + /* if the IP table entry is referenced by only this SA, + * i.e. ref_cnt is only 1, clear the IP table entry as well + */ + ipi = rsa->iptbl_ind; + if (ipsec->ip_tbl[ipi].ref_cnt > 0) { + ipsec->ip_tbl[ipi].ref_cnt--; + + if (!ipsec->ip_tbl[ipi].ref_cnt) { + memset(&ipsec->ip_tbl[ipi], 0, + sizeof(struct rx_ip_sa)); + ixgbe_ipsec_set_rx_ip(hw, ipi, + (__force __be32 *)zerobuf); + } + } + + memset(rsa, 0, sizeof(struct rx_sa)); + ipsec->num_rx_sa--; + } else { + sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_TX_INDEX; + + if (!ipsec->tx_tbl[sa_idx].used) { + netdev_err(dev, "Invalid Tx SA selected sa_idx=%d offload_handle=%lu\n", + sa_idx, xs->xso.offload_handle); + return; + } + + ixgbe_ipsec_set_tx_sa(hw, sa_idx, zerobuf, 0); + memset(&ipsec->tx_tbl[sa_idx], 0, sizeof(struct tx_sa)); + ipsec->num_tx_sa--; + } + + /* if there are no SAs left, stop the engine to save energy */ + if (ipsec->num_rx_sa == 0 && ipsec->num_tx_sa == 0) { + adapter->flags2 &= ~IXGBE_FLAG2_IPSEC_ENABLED; + ixgbe_ipsec_stop_engine(adapter); + } +} + +/** + * ixgbe_ipsec_offload_ok - can this packet use the xfrm hw offload + * @skb: current data packet + * @xs: pointer to transformer state struct + **/ +static bool ixgbe_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) +{ + if (xs->props.family == AF_INET) { + /* Offload with IPv4 options is not supported yet */ + if (ip_hdr(skb)->ihl != 5) + return false; + } else { + /* Offload with IPv6 extension headers is not support yet */ + if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr)) + return false; + } + + return true; +} + +static const struct xfrmdev_ops ixgbe_xfrmdev_ops = { + .xdo_dev_state_add = ixgbe_ipsec_add_sa, + .xdo_dev_state_delete = ixgbe_ipsec_del_sa, + .xdo_dev_offload_ok = ixgbe_ipsec_offload_ok, +}; + +/** + * ixgbe_ipsec_vf_clear - clear the tables of data for a VF + * @adapter: board private structure + * @vf: VF id to be removed + **/ +void ixgbe_ipsec_vf_clear(struct ixgbe_adapter *adapter, u32 vf) +{ + struct ixgbe_ipsec *ipsec = adapter->ipsec; + int i; + + if (!ipsec) + return; + + /* search rx sa table */ + for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT && ipsec->num_rx_sa; i++) { + if (!ipsec->rx_tbl[i].used) + continue; + if (ipsec->rx_tbl[i].mode & IXGBE_RXTXMOD_VF && + ipsec->rx_tbl[i].vf == vf) + ixgbe_ipsec_del_sa(ipsec->rx_tbl[i].xs); + } + + /* search tx sa table */ + for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT && ipsec->num_tx_sa; i++) { + if (!ipsec->tx_tbl[i].used) + continue; + if (ipsec->tx_tbl[i].mode & IXGBE_RXTXMOD_VF && + ipsec->tx_tbl[i].vf == vf) + ixgbe_ipsec_del_sa(ipsec->tx_tbl[i].xs); + } +} + +/** + * ixgbe_ipsec_vf_add_sa - translate VF request to SA add + * @adapter: board private structure + * @msgbuf: The message buffer + * @vf: the VF index + * + * Make up a new xs and algorithm info from the data sent by the VF. + * We only need to sketch in just enough to set up the HW offload. + * Put the resulting offload_handle into the return message to the VF. + * + * Returns 0 or error value + **/ +int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) +{ + struct ixgbe_ipsec *ipsec = adapter->ipsec; + struct xfrm_algo_desc *algo; + struct sa_mbx_msg *sam; + struct xfrm_state *xs; + size_t aead_len; + u16 sa_idx; + u32 pfsa; + int err; + + sam = (struct sa_mbx_msg *)(&msgbuf[1]); + if (!adapter->vfinfo[vf].trusted || + !(adapter->flags2 & IXGBE_FLAG2_VF_IPSEC_ENABLED)) { + e_warn(drv, "VF %d attempted to add an IPsec SA\n", vf); + err = -EACCES; + goto err_out; + } + + /* Tx IPsec offload doesn't seem to work on this + * device, so block these requests for now. + */ + sam->flags = sam->flags & ~XFRM_OFFLOAD_IPV6; + if (sam->flags != XFRM_OFFLOAD_INBOUND) { + err = -EOPNOTSUPP; + goto err_out; + } + + xs = kzalloc(sizeof(*xs), GFP_KERNEL); + if (unlikely(!xs)) { + err = -ENOMEM; + goto err_out; + } + + xs->xso.flags = sam->flags; + xs->id.spi = sam->spi; + xs->id.proto = sam->proto; + xs->props.family = sam->family; + if (xs->props.family == AF_INET6) + memcpy(&xs->id.daddr.a6, sam->addr, sizeof(xs->id.daddr.a6)); + else + memcpy(&xs->id.daddr.a4, sam->addr, sizeof(xs->id.daddr.a4)); + xs->xso.dev = adapter->netdev; + + algo = xfrm_aead_get_byname(aes_gcm_name, IXGBE_IPSEC_AUTH_BITS, 1); + if (unlikely(!algo)) { + err = -ENOENT; + goto err_xs; + } + + aead_len = sizeof(*xs->aead) + IXGBE_IPSEC_KEY_BITS / 8; + xs->aead = kzalloc(aead_len, GFP_KERNEL); + if (unlikely(!xs->aead)) { + err = -ENOMEM; + goto err_xs; + } + + xs->props.ealgo = algo->desc.sadb_alg_id; + xs->geniv = algo->uinfo.aead.geniv; + xs->aead->alg_icv_len = IXGBE_IPSEC_AUTH_BITS; + xs->aead->alg_key_len = IXGBE_IPSEC_KEY_BITS; + memcpy(xs->aead->alg_key, sam->key, sizeof(sam->key)); + memcpy(xs->aead->alg_name, aes_gcm_name, sizeof(aes_gcm_name)); + + /* set up the HW offload */ + err = ixgbe_ipsec_add_sa(xs); + if (err) + goto err_aead; + + pfsa = xs->xso.offload_handle; + if (pfsa < IXGBE_IPSEC_BASE_TX_INDEX) { + sa_idx = pfsa - IXGBE_IPSEC_BASE_RX_INDEX; + ipsec->rx_tbl[sa_idx].vf = vf; + ipsec->rx_tbl[sa_idx].mode |= IXGBE_RXTXMOD_VF; + } else { + sa_idx = pfsa - IXGBE_IPSEC_BASE_TX_INDEX; + ipsec->tx_tbl[sa_idx].vf = vf; + ipsec->tx_tbl[sa_idx].mode |= IXGBE_RXTXMOD_VF; + } + + msgbuf[1] = xs->xso.offload_handle; + + return 0; + +err_aead: + kfree_sensitive(xs->aead); +err_xs: + kfree_sensitive(xs); +err_out: + msgbuf[1] = err; + return err; +} + +/** + * ixgbe_ipsec_vf_del_sa - translate VF request to SA delete + * @adapter: board private structure + * @msgbuf: The message buffer + * @vf: the VF index + * + * Given the offload_handle sent by the VF, look for the related SA table + * entry and use its xs field to call for a delete of the SA. + * + * Note: We silently ignore requests to delete entries that are already + * set to unused because when a VF is set to "DOWN", the PF first + * gets a reset and clears all the VF's entries; then the VF's + * XFRM stack sends individual deletes for each entry, which the + * reset already removed. In the future it might be good to try to + * optimize this so not so many unnecessary delete messages are sent. + * + * Returns 0 or error value + **/ +int ixgbe_ipsec_vf_del_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) +{ + struct ixgbe_ipsec *ipsec = adapter->ipsec; + struct xfrm_state *xs; + u32 pfsa = msgbuf[1]; + u16 sa_idx; + + if (!adapter->vfinfo[vf].trusted) { + e_err(drv, "vf %d attempted to delete an SA\n", vf); + return -EPERM; + } + + if (pfsa < IXGBE_IPSEC_BASE_TX_INDEX) { + struct rx_sa *rsa; + + sa_idx = pfsa - IXGBE_IPSEC_BASE_RX_INDEX; + if (sa_idx >= IXGBE_IPSEC_MAX_SA_COUNT) { + e_err(drv, "vf %d SA index %d out of range\n", + vf, sa_idx); + return -EINVAL; + } + + rsa = &ipsec->rx_tbl[sa_idx]; + + if (!rsa->used) + return 0; + + if (!(rsa->mode & IXGBE_RXTXMOD_VF) || + rsa->vf != vf) { + e_err(drv, "vf %d bad Rx SA index %d\n", vf, sa_idx); + return -ENOENT; + } + + xs = ipsec->rx_tbl[sa_idx].xs; + } else { + struct tx_sa *tsa; + + sa_idx = pfsa - IXGBE_IPSEC_BASE_TX_INDEX; + if (sa_idx >= IXGBE_IPSEC_MAX_SA_COUNT) { + e_err(drv, "vf %d SA index %d out of range\n", + vf, sa_idx); + return -EINVAL; + } + + tsa = &ipsec->tx_tbl[sa_idx]; + + if (!tsa->used) + return 0; + + if (!(tsa->mode & IXGBE_RXTXMOD_VF) || + tsa->vf != vf) { + e_err(drv, "vf %d bad Tx SA index %d\n", vf, sa_idx); + return -ENOENT; + } + + xs = ipsec->tx_tbl[sa_idx].xs; + } + + ixgbe_ipsec_del_sa(xs); + + /* remove the xs that was made-up in the add request */ + kfree_sensitive(xs); + + return 0; +} + +/** + * ixgbe_ipsec_tx - setup Tx flags for ipsec offload + * @tx_ring: outgoing context + * @first: current data packet + * @itd: ipsec Tx data for later use in building context descriptor + **/ +int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring, + struct ixgbe_tx_buffer *first, + struct ixgbe_ipsec_tx_data *itd) +{ + struct ixgbe_adapter *adapter = netdev_priv(tx_ring->netdev); + struct ixgbe_ipsec *ipsec = adapter->ipsec; + struct xfrm_state *xs; + struct sec_path *sp; + struct tx_sa *tsa; + + sp = skb_sec_path(first->skb); + if (unlikely(!sp->len)) { + netdev_err(tx_ring->netdev, "%s: no xfrm state len = %d\n", + __func__, sp->len); + return 0; + } + + xs = xfrm_input_state(first->skb); + if (unlikely(!xs)) { + netdev_err(tx_ring->netdev, "%s: no xfrm_input_state() xs = %p\n", + __func__, xs); + return 0; + } + + itd->sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_TX_INDEX; + if (unlikely(itd->sa_idx >= IXGBE_IPSEC_MAX_SA_COUNT)) { + netdev_err(tx_ring->netdev, "%s: bad sa_idx=%d handle=%lu\n", + __func__, itd->sa_idx, xs->xso.offload_handle); + return 0; + } + + tsa = &ipsec->tx_tbl[itd->sa_idx]; + if (unlikely(!tsa->used)) { + netdev_err(tx_ring->netdev, "%s: unused sa_idx=%d\n", + __func__, itd->sa_idx); + return 0; + } + + first->tx_flags |= IXGBE_TX_FLAGS_IPSEC | IXGBE_TX_FLAGS_CC; + + if (xs->id.proto == IPPROTO_ESP) { + + itd->flags |= IXGBE_ADVTXD_TUCMD_IPSEC_TYPE_ESP | + IXGBE_ADVTXD_TUCMD_L4T_TCP; + if (first->protocol == htons(ETH_P_IP)) + itd->flags |= IXGBE_ADVTXD_TUCMD_IPV4; + + /* The actual trailer length is authlen (16 bytes) plus + * 2 bytes for the proto and the padlen values, plus + * padlen bytes of padding. This ends up not the same + * as the static value found in xs->props.trailer_len (21). + * + * ... but if we're doing GSO, don't bother as the stack + * doesn't add a trailer for those. + */ + if (!skb_is_gso(first->skb)) { + /* The "correct" way to get the auth length would be + * to use + * authlen = crypto_aead_authsize(xs->data); + * but since we know we only have one size to worry + * about * we can let the compiler use the constant + * and save us a few CPU cycles. + */ + const int authlen = IXGBE_IPSEC_AUTH_BITS / 8; + struct sk_buff *skb = first->skb; + u8 padlen; + int ret; + + ret = skb_copy_bits(skb, skb->len - (authlen + 2), + &padlen, 1); + if (unlikely(ret)) + return 0; + itd->trailer_len = authlen + 2 + padlen; + } + } + if (tsa->encrypt) + itd->flags |= IXGBE_ADVTXD_TUCMD_IPSEC_ENCRYPT_EN; + + return 1; +} + +/** + * ixgbe_ipsec_rx - decode ipsec bits from Rx descriptor + * @rx_ring: receiving ring + * @rx_desc: receive data descriptor + * @skb: current data packet + * + * Determine if there was an ipsec encapsulation noticed, and if so set up + * the resulting status for later in the receive stack. + **/ +void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + struct ixgbe_adapter *adapter = netdev_priv(rx_ring->netdev); + __le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info; + __le16 ipsec_pkt_types = cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPSEC_AH | + IXGBE_RXDADV_PKTTYPE_IPSEC_ESP); + struct ixgbe_ipsec *ipsec = adapter->ipsec; + struct xfrm_offload *xo = NULL; + struct xfrm_state *xs = NULL; + struct ipv6hdr *ip6 = NULL; + struct iphdr *ip4 = NULL; + struct sec_path *sp; + void *daddr; + __be32 spi; + u8 *c_hdr; + u8 proto; + + /* Find the ip and crypto headers in the data. + * We can assume no vlan header in the way, b/c the + * hw won't recognize the IPsec packet and anyway the + * currently vlan device doesn't support xfrm offload. + */ + if (pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPV4)) { + ip4 = (struct iphdr *)(skb->data + ETH_HLEN); + daddr = &ip4->daddr; + c_hdr = (u8 *)ip4 + ip4->ihl * 4; + } else if (pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPV6)) { + ip6 = (struct ipv6hdr *)(skb->data + ETH_HLEN); + daddr = &ip6->daddr; + c_hdr = (u8 *)ip6 + sizeof(struct ipv6hdr); + } else { + return; + } + + switch (pkt_info & ipsec_pkt_types) { + case cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPSEC_AH): + spi = ((struct ip_auth_hdr *)c_hdr)->spi; + proto = IPPROTO_AH; + break; + case cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPSEC_ESP): + spi = ((struct ip_esp_hdr *)c_hdr)->spi; + proto = IPPROTO_ESP; + break; + default: + return; + } + + xs = ixgbe_ipsec_find_rx_state(ipsec, daddr, proto, spi, !!ip4); + if (unlikely(!xs)) + return; + + sp = secpath_set(skb); + if (unlikely(!sp)) + return; + + sp->xvec[sp->len++] = xs; + sp->olen++; + xo = xfrm_offload(skb); + xo->flags = CRYPTO_DONE; + xo->status = CRYPTO_SUCCESS; + + adapter->rx_ipsec++; +} + +/** + * ixgbe_init_ipsec_offload - initialize security registers for IPSec operation + * @adapter: board private structure + **/ +void ixgbe_init_ipsec_offload(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_ipsec *ipsec; + u32 t_dis, r_dis; + size_t size; + + if (hw->mac.type == ixgbe_mac_82598EB) + return; + + /* If there is no support for either Tx or Rx offload + * we should not be advertising support for IPsec. + */ + t_dis = IXGBE_READ_REG(hw, IXGBE_SECTXSTAT) & + IXGBE_SECTXSTAT_SECTX_OFF_DIS; + r_dis = IXGBE_READ_REG(hw, IXGBE_SECRXSTAT) & + IXGBE_SECRXSTAT_SECRX_OFF_DIS; + if (t_dis || r_dis) + return; + + ipsec = kzalloc(sizeof(*ipsec), GFP_KERNEL); + if (!ipsec) + goto err1; + hash_init(ipsec->rx_sa_list); + + size = sizeof(struct rx_sa) * IXGBE_IPSEC_MAX_SA_COUNT; + ipsec->rx_tbl = kzalloc(size, GFP_KERNEL); + if (!ipsec->rx_tbl) + goto err2; + + size = sizeof(struct tx_sa) * IXGBE_IPSEC_MAX_SA_COUNT; + ipsec->tx_tbl = kzalloc(size, GFP_KERNEL); + if (!ipsec->tx_tbl) + goto err2; + + size = sizeof(struct rx_ip_sa) * IXGBE_IPSEC_MAX_RX_IP_COUNT; + ipsec->ip_tbl = kzalloc(size, GFP_KERNEL); + if (!ipsec->ip_tbl) + goto err2; + + ipsec->num_rx_sa = 0; + ipsec->num_tx_sa = 0; + + adapter->ipsec = ipsec; + ixgbe_ipsec_stop_engine(adapter); + ixgbe_ipsec_clear_hw_tables(adapter); + + adapter->netdev->xfrmdev_ops = &ixgbe_xfrmdev_ops; + + return; + +err2: + kfree(ipsec->ip_tbl); + kfree(ipsec->rx_tbl); + kfree(ipsec->tx_tbl); + kfree(ipsec); +err1: + netdev_err(adapter->netdev, "Unable to allocate memory for SA tables"); +} + +/** + * ixgbe_stop_ipsec_offload - tear down the ipsec offload + * @adapter: board private structure + **/ +void ixgbe_stop_ipsec_offload(struct ixgbe_adapter *adapter) +{ + struct ixgbe_ipsec *ipsec = adapter->ipsec; + + adapter->ipsec = NULL; + if (ipsec) { + kfree(ipsec->ip_tbl); + kfree(ipsec->rx_tbl); + kfree(ipsec->tx_tbl); + kfree(ipsec); + } +} diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.h new file mode 100644 index 000000000..d2b64ff8e --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.h @@ -0,0 +1,83 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2017 Oracle and/or its affiliates. All rights reserved. */ + +#ifndef _IXGBE_IPSEC_H_ +#define _IXGBE_IPSEC_H_ + +#define IXGBE_IPSEC_MAX_SA_COUNT 1024 +#define IXGBE_IPSEC_MAX_RX_IP_COUNT 128 +#define IXGBE_IPSEC_BASE_RX_INDEX 0 +#define IXGBE_IPSEC_BASE_TX_INDEX IXGBE_IPSEC_MAX_SA_COUNT +#define IXGBE_IPSEC_AUTH_BITS 128 + +#define IXGBE_RXTXIDX_IPS_EN 0x00000001 +#define IXGBE_RXIDX_TBL_SHIFT 1 +enum ixgbe_ipsec_tbl_sel { + ips_rx_ip_tbl = 0x01, + ips_rx_spi_tbl = 0x02, + ips_rx_key_tbl = 0x03, +}; + +#define IXGBE_RXTXIDX_IDX_SHIFT 3 +#define IXGBE_RXTXIDX_READ 0x40000000 +#define IXGBE_RXTXIDX_WRITE 0x80000000 + +#define IXGBE_RXMOD_VALID 0x00000001 +#define IXGBE_RXMOD_PROTO_ESP 0x00000004 +#define IXGBE_RXMOD_DECRYPT 0x00000008 +#define IXGBE_RXMOD_IPV6 0x00000010 +#define IXGBE_RXTXMOD_VF 0x00000020 + +struct rx_sa { + struct hlist_node hlist; + struct xfrm_state *xs; + __be32 ipaddr[4]; + u32 key[4]; + u32 salt; + u32 mode; + u8 iptbl_ind; + bool used; + bool decrypt; + u32 vf; +}; + +struct rx_ip_sa { + __be32 ipaddr[4]; + u32 ref_cnt; + bool used; +}; + +struct tx_sa { + struct xfrm_state *xs; + u32 key[4]; + u32 salt; + u32 mode; + bool encrypt; + bool used; + u32 vf; +}; + +struct ixgbe_ipsec_tx_data { + u32 flags; + u16 trailer_len; + u16 sa_idx; +}; + +struct ixgbe_ipsec { + u16 num_rx_sa; + u16 num_tx_sa; + struct rx_ip_sa *ip_tbl; + struct rx_sa *rx_tbl; + struct tx_sa *tx_tbl; + DECLARE_HASHTABLE(rx_sa_list, 10); +}; + +struct sa_mbx_msg { + __be32 spi; + u8 flags; + u8 proto; + u16 family; + __be32 addr[4]; + u32 key[5]; +}; +#endif /* _IXGBE_IPSEC_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c new file mode 100644 index 000000000..df389a11d --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -0,0 +1,1298 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#include "ixgbe.h" +#include "ixgbe_sriov.h" + +#ifdef CONFIG_IXGBE_DCB +/** + * ixgbe_cache_ring_dcb_sriov - Descriptor ring to register mapping for SR-IOV + * @adapter: board private structure to initialize + * + * Cache the descriptor ring offsets for SR-IOV to the assigned rings. It + * will also try to cache the proper offsets if RSS/FCoE are enabled along + * with VMDq. + * + **/ +static bool ixgbe_cache_ring_dcb_sriov(struct ixgbe_adapter *adapter) +{ +#ifdef IXGBE_FCOE + struct ixgbe_ring_feature *fcoe = &adapter->ring_feature[RING_F_FCOE]; +#endif /* IXGBE_FCOE */ + struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; + int i; + u16 reg_idx, pool; + u8 tcs = adapter->hw_tcs; + + /* verify we have DCB queueing enabled before proceeding */ + if (tcs <= 1) + return false; + + /* verify we have VMDq enabled before proceeding */ + if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) + return false; + + /* start at VMDq register offset for SR-IOV enabled setups */ + reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask); + for (i = 0, pool = 0; i < adapter->num_rx_queues; i++, reg_idx++) { + /* If we are greater than indices move to next pool */ + if ((reg_idx & ~vmdq->mask) >= tcs) { + pool++; + reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask); + } + adapter->rx_ring[i]->reg_idx = reg_idx; + adapter->rx_ring[i]->netdev = pool ? NULL : adapter->netdev; + } + + reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask); + for (i = 0; i < adapter->num_tx_queues; i++, reg_idx++) { + /* If we are greater than indices move to next pool */ + if ((reg_idx & ~vmdq->mask) >= tcs) + reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask); + adapter->tx_ring[i]->reg_idx = reg_idx; + } + +#ifdef IXGBE_FCOE + /* nothing to do if FCoE is disabled */ + if (!(adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) + return true; + + /* The work is already done if the FCoE ring is shared */ + if (fcoe->offset < tcs) + return true; + + /* The FCoE rings exist separately, we need to move their reg_idx */ + if (fcoe->indices) { + u16 queues_per_pool = __ALIGN_MASK(1, ~vmdq->mask); + u8 fcoe_tc = ixgbe_fcoe_get_tc(adapter); + + reg_idx = (vmdq->offset + vmdq->indices) * queues_per_pool; + for (i = fcoe->offset; i < adapter->num_rx_queues; i++) { + reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask) + fcoe_tc; + adapter->rx_ring[i]->reg_idx = reg_idx; + adapter->rx_ring[i]->netdev = adapter->netdev; + reg_idx++; + } + + reg_idx = (vmdq->offset + vmdq->indices) * queues_per_pool; + for (i = fcoe->offset; i < adapter->num_tx_queues; i++) { + reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask) + fcoe_tc; + adapter->tx_ring[i]->reg_idx = reg_idx; + reg_idx++; + } + } + +#endif /* IXGBE_FCOE */ + return true; +} + +/* ixgbe_get_first_reg_idx - Return first register index associated with ring */ +static void ixgbe_get_first_reg_idx(struct ixgbe_adapter *adapter, u8 tc, + unsigned int *tx, unsigned int *rx) +{ + struct ixgbe_hw *hw = &adapter->hw; + u8 num_tcs = adapter->hw_tcs; + + *tx = 0; + *rx = 0; + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + /* TxQs/TC: 4 RxQs/TC: 8 */ + *tx = tc << 2; /* 0, 4, 8, 12, 16, 20, 24, 28 */ + *rx = tc << 3; /* 0, 8, 16, 24, 32, 40, 48, 56 */ + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + if (num_tcs > 4) { + /* + * TCs : TC0/1 TC2/3 TC4-7 + * TxQs/TC: 32 16 8 + * RxQs/TC: 16 16 16 + */ + *rx = tc << 4; + if (tc < 3) + *tx = tc << 5; /* 0, 32, 64 */ + else if (tc < 5) + *tx = (tc + 2) << 4; /* 80, 96 */ + else + *tx = (tc + 8) << 3; /* 104, 112, 120 */ + } else { + /* + * TCs : TC0 TC1 TC2/3 + * TxQs/TC: 64 32 16 + * RxQs/TC: 32 32 32 + */ + *rx = tc << 5; + if (tc < 2) + *tx = tc << 6; /* 0, 64 */ + else + *tx = (tc + 4) << 4; /* 96, 112 */ + } + default: + break; + } +} + +/** + * ixgbe_cache_ring_dcb - Descriptor ring to register mapping for DCB + * @adapter: board private structure to initialize + * + * Cache the descriptor ring offsets for DCB to the assigned rings. + * + **/ +static bool ixgbe_cache_ring_dcb(struct ixgbe_adapter *adapter) +{ + u8 num_tcs = adapter->hw_tcs; + unsigned int tx_idx, rx_idx; + int tc, offset, rss_i, i; + + /* verify we have DCB queueing enabled before proceeding */ + if (num_tcs <= 1) + return false; + + rss_i = adapter->ring_feature[RING_F_RSS].indices; + + for (tc = 0, offset = 0; tc < num_tcs; tc++, offset += rss_i) { + ixgbe_get_first_reg_idx(adapter, tc, &tx_idx, &rx_idx); + for (i = 0; i < rss_i; i++, tx_idx++, rx_idx++) { + adapter->tx_ring[offset + i]->reg_idx = tx_idx; + adapter->rx_ring[offset + i]->reg_idx = rx_idx; + adapter->rx_ring[offset + i]->netdev = adapter->netdev; + adapter->tx_ring[offset + i]->dcb_tc = tc; + adapter->rx_ring[offset + i]->dcb_tc = tc; + } + } + + return true; +} + +#endif +/** + * ixgbe_cache_ring_sriov - Descriptor ring to register mapping for sriov + * @adapter: board private structure to initialize + * + * SR-IOV doesn't use any descriptor rings but changes the default if + * no other mapping is used. + * + */ +static bool ixgbe_cache_ring_sriov(struct ixgbe_adapter *adapter) +{ +#ifdef IXGBE_FCOE + struct ixgbe_ring_feature *fcoe = &adapter->ring_feature[RING_F_FCOE]; +#endif /* IXGBE_FCOE */ + struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; + struct ixgbe_ring_feature *rss = &adapter->ring_feature[RING_F_RSS]; + u16 reg_idx, pool; + int i; + + /* only proceed if VMDq is enabled */ + if (!(adapter->flags & IXGBE_FLAG_VMDQ_ENABLED)) + return false; + + /* start at VMDq register offset for SR-IOV enabled setups */ + pool = 0; + reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask); + for (i = 0; i < adapter->num_rx_queues; i++, reg_idx++) { +#ifdef IXGBE_FCOE + /* Allow first FCoE queue to be mapped as RSS */ + if (fcoe->offset && (i > fcoe->offset)) + break; +#endif + /* If we are greater than indices move to next pool */ + if ((reg_idx & ~vmdq->mask) >= rss->indices) { + pool++; + reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask); + } + adapter->rx_ring[i]->reg_idx = reg_idx; + adapter->rx_ring[i]->netdev = pool ? NULL : adapter->netdev; + } + +#ifdef IXGBE_FCOE + /* FCoE uses a linear block of queues so just assigning 1:1 */ + for (; i < adapter->num_rx_queues; i++, reg_idx++) { + adapter->rx_ring[i]->reg_idx = reg_idx; + adapter->rx_ring[i]->netdev = adapter->netdev; + } + +#endif + reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask); + for (i = 0; i < adapter->num_tx_queues; i++, reg_idx++) { +#ifdef IXGBE_FCOE + /* Allow first FCoE queue to be mapped as RSS */ + if (fcoe->offset && (i > fcoe->offset)) + break; +#endif + /* If we are greater than indices move to next pool */ + if ((reg_idx & rss->mask) >= rss->indices) + reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask); + adapter->tx_ring[i]->reg_idx = reg_idx; + } + +#ifdef IXGBE_FCOE + /* FCoE uses a linear block of queues so just assigning 1:1 */ + for (; i < adapter->num_tx_queues; i++, reg_idx++) + adapter->tx_ring[i]->reg_idx = reg_idx; + +#endif + + return true; +} + +/** + * ixgbe_cache_ring_rss - Descriptor ring to register mapping for RSS + * @adapter: board private structure to initialize + * + * Cache the descriptor ring offsets for RSS to the assigned rings. + * + **/ +static bool ixgbe_cache_ring_rss(struct ixgbe_adapter *adapter) +{ + int i, reg_idx; + + for (i = 0; i < adapter->num_rx_queues; i++) { + adapter->rx_ring[i]->reg_idx = i; + adapter->rx_ring[i]->netdev = adapter->netdev; + } + for (i = 0, reg_idx = 0; i < adapter->num_tx_queues; i++, reg_idx++) + adapter->tx_ring[i]->reg_idx = reg_idx; + for (i = 0; i < adapter->num_xdp_queues; i++, reg_idx++) + adapter->xdp_ring[i]->reg_idx = reg_idx; + + return true; +} + +/** + * ixgbe_cache_ring_register - Descriptor ring to register mapping + * @adapter: board private structure to initialize + * + * Once we know the feature-set enabled for the device, we'll cache + * the register offset the descriptor ring is assigned to. + * + * Note, the order the various feature calls is important. It must start with + * the "most" features enabled at the same time, then trickle down to the + * least amount of features turned on at once. + **/ +static void ixgbe_cache_ring_register(struct ixgbe_adapter *adapter) +{ + /* start with default case */ + adapter->rx_ring[0]->reg_idx = 0; + adapter->tx_ring[0]->reg_idx = 0; + +#ifdef CONFIG_IXGBE_DCB + if (ixgbe_cache_ring_dcb_sriov(adapter)) + return; + + if (ixgbe_cache_ring_dcb(adapter)) + return; + +#endif + if (ixgbe_cache_ring_sriov(adapter)) + return; + + ixgbe_cache_ring_rss(adapter); +} + +static int ixgbe_xdp_queues(struct ixgbe_adapter *adapter) +{ + return adapter->xdp_prog ? nr_cpu_ids : 0; +} + +#define IXGBE_RSS_64Q_MASK 0x3F +#define IXGBE_RSS_16Q_MASK 0xF +#define IXGBE_RSS_8Q_MASK 0x7 +#define IXGBE_RSS_4Q_MASK 0x3 +#define IXGBE_RSS_2Q_MASK 0x1 +#define IXGBE_RSS_DISABLED_MASK 0x0 + +#ifdef CONFIG_IXGBE_DCB +/** + * ixgbe_set_dcb_sriov_queues: Allocate queues for SR-IOV devices w/ DCB + * @adapter: board private structure to initialize + * + * When SR-IOV (Single Root IO Virtualiztion) is enabled, allocate queues + * and VM pools where appropriate. Also assign queues based on DCB + * priorities and map accordingly.. + * + **/ +static bool ixgbe_set_dcb_sriov_queues(struct ixgbe_adapter *adapter) +{ + int i; + u16 vmdq_i = adapter->ring_feature[RING_F_VMDQ].limit; + u16 vmdq_m = 0; +#ifdef IXGBE_FCOE + u16 fcoe_i = 0; +#endif + u8 tcs = adapter->hw_tcs; + + /* verify we have DCB queueing enabled before proceeding */ + if (tcs <= 1) + return false; + + /* verify we have VMDq enabled before proceeding */ + if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) + return false; + + /* limit VMDq instances on the PF by number of Tx queues */ + vmdq_i = min_t(u16, vmdq_i, MAX_TX_QUEUES / tcs); + + /* Add starting offset to total pool count */ + vmdq_i += adapter->ring_feature[RING_F_VMDQ].offset; + + /* 16 pools w/ 8 TC per pool */ + if (tcs > 4) { + vmdq_i = min_t(u16, vmdq_i, 16); + vmdq_m = IXGBE_82599_VMDQ_8Q_MASK; + /* 32 pools w/ 4 TC per pool */ + } else { + vmdq_i = min_t(u16, vmdq_i, 32); + vmdq_m = IXGBE_82599_VMDQ_4Q_MASK; + } + +#ifdef IXGBE_FCOE + /* queues in the remaining pools are available for FCoE */ + fcoe_i = (128 / __ALIGN_MASK(1, ~vmdq_m)) - vmdq_i; + +#endif + /* remove the starting offset from the pool count */ + vmdq_i -= adapter->ring_feature[RING_F_VMDQ].offset; + + /* save features for later use */ + adapter->ring_feature[RING_F_VMDQ].indices = vmdq_i; + adapter->ring_feature[RING_F_VMDQ].mask = vmdq_m; + + /* + * We do not support DCB, VMDq, and RSS all simultaneously + * so we will disable RSS since it is the lowest priority + */ + adapter->ring_feature[RING_F_RSS].indices = 1; + adapter->ring_feature[RING_F_RSS].mask = IXGBE_RSS_DISABLED_MASK; + + /* disable ATR as it is not supported when VMDq is enabled */ + adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; + + adapter->num_rx_pools = vmdq_i; + adapter->num_rx_queues_per_pool = tcs; + + adapter->num_tx_queues = vmdq_i * tcs; + adapter->num_xdp_queues = 0; + adapter->num_rx_queues = vmdq_i * tcs; + +#ifdef IXGBE_FCOE + if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) { + struct ixgbe_ring_feature *fcoe; + + fcoe = &adapter->ring_feature[RING_F_FCOE]; + + /* limit ourselves based on feature limits */ + fcoe_i = min_t(u16, fcoe_i, fcoe->limit); + + if (fcoe_i) { + /* alloc queues for FCoE separately */ + fcoe->indices = fcoe_i; + fcoe->offset = vmdq_i * tcs; + + /* add queues to adapter */ + adapter->num_tx_queues += fcoe_i; + adapter->num_rx_queues += fcoe_i; + } else if (tcs > 1) { + /* use queue belonging to FcoE TC */ + fcoe->indices = 1; + fcoe->offset = ixgbe_fcoe_get_tc(adapter); + } else { + adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED; + + fcoe->indices = 0; + fcoe->offset = 0; + } + } + +#endif /* IXGBE_FCOE */ + /* configure TC to queue mapping */ + for (i = 0; i < tcs; i++) + netdev_set_tc_queue(adapter->netdev, i, 1, i); + + return true; +} + +static bool ixgbe_set_dcb_queues(struct ixgbe_adapter *adapter) +{ + struct net_device *dev = adapter->netdev; + struct ixgbe_ring_feature *f; + int rss_i, rss_m, i; + int tcs; + + /* Map queue offset and counts onto allocated tx queues */ + tcs = adapter->hw_tcs; + + /* verify we have DCB queueing enabled before proceeding */ + if (tcs <= 1) + return false; + + /* determine the upper limit for our current DCB mode */ + rss_i = dev->num_tx_queues / tcs; + if (adapter->hw.mac.type == ixgbe_mac_82598EB) { + /* 8 TC w/ 4 queues per TC */ + rss_i = min_t(u16, rss_i, 4); + rss_m = IXGBE_RSS_4Q_MASK; + } else if (tcs > 4) { + /* 8 TC w/ 8 queues per TC */ + rss_i = min_t(u16, rss_i, 8); + rss_m = IXGBE_RSS_8Q_MASK; + } else { + /* 4 TC w/ 16 queues per TC */ + rss_i = min_t(u16, rss_i, 16); + rss_m = IXGBE_RSS_16Q_MASK; + } + + /* set RSS mask and indices */ + f = &adapter->ring_feature[RING_F_RSS]; + rss_i = min_t(int, rss_i, f->limit); + f->indices = rss_i; + f->mask = rss_m; + + /* disable ATR as it is not supported when multiple TCs are enabled */ + adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; + +#ifdef IXGBE_FCOE + /* FCoE enabled queues require special configuration indexed + * by feature specific indices and offset. Here we map FCoE + * indices onto the DCB queue pairs allowing FCoE to own + * configuration later. + */ + if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) { + u8 tc = ixgbe_fcoe_get_tc(adapter); + + f = &adapter->ring_feature[RING_F_FCOE]; + f->indices = min_t(u16, rss_i, f->limit); + f->offset = rss_i * tc; + } + +#endif /* IXGBE_FCOE */ + for (i = 0; i < tcs; i++) + netdev_set_tc_queue(dev, i, rss_i, rss_i * i); + + adapter->num_tx_queues = rss_i * tcs; + adapter->num_xdp_queues = 0; + adapter->num_rx_queues = rss_i * tcs; + + return true; +} + +#endif +/** + * ixgbe_set_sriov_queues - Allocate queues for SR-IOV devices + * @adapter: board private structure to initialize + * + * When SR-IOV (Single Root IO Virtualiztion) is enabled, allocate queues + * and VM pools where appropriate. If RSS is available, then also try and + * enable RSS and map accordingly. + * + **/ +static bool ixgbe_set_sriov_queues(struct ixgbe_adapter *adapter) +{ + u16 vmdq_i = adapter->ring_feature[RING_F_VMDQ].limit; + u16 vmdq_m = 0; + u16 rss_i = adapter->ring_feature[RING_F_RSS].limit; + u16 rss_m = IXGBE_RSS_DISABLED_MASK; +#ifdef IXGBE_FCOE + u16 fcoe_i = 0; +#endif + + /* only proceed if SR-IOV is enabled */ + if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) + return false; + + /* limit l2fwd RSS based on total Tx queue limit */ + rss_i = min_t(u16, rss_i, MAX_TX_QUEUES / vmdq_i); + + /* Add starting offset to total pool count */ + vmdq_i += adapter->ring_feature[RING_F_VMDQ].offset; + + /* double check we are limited to maximum pools */ + vmdq_i = min_t(u16, IXGBE_MAX_VMDQ_INDICES, vmdq_i); + + /* 64 pool mode with 2 queues per pool */ + if (vmdq_i > 32) { + vmdq_m = IXGBE_82599_VMDQ_2Q_MASK; + rss_m = IXGBE_RSS_2Q_MASK; + rss_i = min_t(u16, rss_i, 2); + /* 32 pool mode with up to 4 queues per pool */ + } else { + vmdq_m = IXGBE_82599_VMDQ_4Q_MASK; + rss_m = IXGBE_RSS_4Q_MASK; + /* We can support 4, 2, or 1 queues */ + rss_i = (rss_i > 3) ? 4 : (rss_i > 1) ? 2 : 1; + } + +#ifdef IXGBE_FCOE + /* queues in the remaining pools are available for FCoE */ + fcoe_i = 128 - (vmdq_i * __ALIGN_MASK(1, ~vmdq_m)); + +#endif + /* remove the starting offset from the pool count */ + vmdq_i -= adapter->ring_feature[RING_F_VMDQ].offset; + + /* save features for later use */ + adapter->ring_feature[RING_F_VMDQ].indices = vmdq_i; + adapter->ring_feature[RING_F_VMDQ].mask = vmdq_m; + + /* limit RSS based on user input and save for later use */ + adapter->ring_feature[RING_F_RSS].indices = rss_i; + adapter->ring_feature[RING_F_RSS].mask = rss_m; + + adapter->num_rx_pools = vmdq_i; + adapter->num_rx_queues_per_pool = rss_i; + + adapter->num_rx_queues = vmdq_i * rss_i; + adapter->num_tx_queues = vmdq_i * rss_i; + adapter->num_xdp_queues = 0; + + /* disable ATR as it is not supported when VMDq is enabled */ + adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; + +#ifdef IXGBE_FCOE + /* + * FCoE can use rings from adjacent buffers to allow RSS + * like behavior. To account for this we need to add the + * FCoE indices to the total ring count. + */ + if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) { + struct ixgbe_ring_feature *fcoe; + + fcoe = &adapter->ring_feature[RING_F_FCOE]; + + /* limit ourselves based on feature limits */ + fcoe_i = min_t(u16, fcoe_i, fcoe->limit); + + if (vmdq_i > 1 && fcoe_i) { + /* alloc queues for FCoE separately */ + fcoe->indices = fcoe_i; + fcoe->offset = vmdq_i * rss_i; + } else { + /* merge FCoE queues with RSS queues */ + fcoe_i = min_t(u16, fcoe_i + rss_i, num_online_cpus()); + + /* limit indices to rss_i if MSI-X is disabled */ + if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) + fcoe_i = rss_i; + + /* attempt to reserve some queues for just FCoE */ + fcoe->indices = min_t(u16, fcoe_i, fcoe->limit); + fcoe->offset = fcoe_i - fcoe->indices; + + fcoe_i -= rss_i; + } + + /* add queues to adapter */ + adapter->num_tx_queues += fcoe_i; + adapter->num_rx_queues += fcoe_i; + } + +#endif + /* To support macvlan offload we have to use num_tc to + * restrict the queues that can be used by the device. + * By doing this we can avoid reporting a false number of + * queues. + */ + if (vmdq_i > 1) + netdev_set_num_tc(adapter->netdev, 1); + + /* populate TC0 for use by pool 0 */ + netdev_set_tc_queue(adapter->netdev, 0, + adapter->num_rx_queues_per_pool, 0); + + return true; +} + +/** + * ixgbe_set_rss_queues - Allocate queues for RSS + * @adapter: board private structure to initialize + * + * This is our "base" multiqueue mode. RSS (Receive Side Scaling) will try + * to allocate one Rx queue per CPU, and if available, one Tx queue per CPU. + * + **/ +static bool ixgbe_set_rss_queues(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_ring_feature *f; + u16 rss_i; + + /* set mask for 16 queue limit of RSS */ + f = &adapter->ring_feature[RING_F_RSS]; + rss_i = f->limit; + + f->indices = rss_i; + + if (hw->mac.type < ixgbe_mac_X550) + f->mask = IXGBE_RSS_16Q_MASK; + else + f->mask = IXGBE_RSS_64Q_MASK; + + /* disable ATR by default, it will be configured below */ + adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; + + /* + * Use Flow Director in addition to RSS to ensure the best + * distribution of flows across cores, even when an FDIR flow + * isn't matched. + */ + if (rss_i > 1 && adapter->atr_sample_rate) { + f = &adapter->ring_feature[RING_F_FDIR]; + + rss_i = f->indices = f->limit; + + if (!(adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE)) + adapter->flags |= IXGBE_FLAG_FDIR_HASH_CAPABLE; + } + +#ifdef IXGBE_FCOE + /* + * FCoE can exist on the same rings as standard network traffic + * however it is preferred to avoid that if possible. In order + * to get the best performance we allocate as many FCoE queues + * as we can and we place them at the end of the ring array to + * avoid sharing queues with standard RSS on systems with 24 or + * more CPUs. + */ + if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) { + struct net_device *dev = adapter->netdev; + u16 fcoe_i; + + f = &adapter->ring_feature[RING_F_FCOE]; + + /* merge FCoE queues with RSS queues */ + fcoe_i = min_t(u16, f->limit + rss_i, num_online_cpus()); + fcoe_i = min_t(u16, fcoe_i, dev->num_tx_queues); + + /* limit indices to rss_i if MSI-X is disabled */ + if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) + fcoe_i = rss_i; + + /* attempt to reserve some queues for just FCoE */ + f->indices = min_t(u16, fcoe_i, f->limit); + f->offset = fcoe_i - f->indices; + rss_i = max_t(u16, fcoe_i, rss_i); + } + +#endif /* IXGBE_FCOE */ + adapter->num_rx_queues = rss_i; + adapter->num_tx_queues = rss_i; + adapter->num_xdp_queues = ixgbe_xdp_queues(adapter); + + return true; +} + +/** + * ixgbe_set_num_queues - Allocate queues for device, feature dependent + * @adapter: board private structure to initialize + * + * This is the top level queue allocation routine. The order here is very + * important, starting with the "most" number of features turned on at once, + * and ending with the smallest set of features. This way large combinations + * can be allocated if they're turned on, and smaller combinations are the + * fallthrough conditions. + * + **/ +static void ixgbe_set_num_queues(struct ixgbe_adapter *adapter) +{ + /* Start with base case */ + adapter->num_rx_queues = 1; + adapter->num_tx_queues = 1; + adapter->num_xdp_queues = 0; + adapter->num_rx_pools = 1; + adapter->num_rx_queues_per_pool = 1; + +#ifdef CONFIG_IXGBE_DCB + if (ixgbe_set_dcb_sriov_queues(adapter)) + return; + + if (ixgbe_set_dcb_queues(adapter)) + return; + +#endif + if (ixgbe_set_sriov_queues(adapter)) + return; + + ixgbe_set_rss_queues(adapter); +} + +/** + * ixgbe_acquire_msix_vectors - acquire MSI-X vectors + * @adapter: board private structure + * + * Attempts to acquire a suitable range of MSI-X vector interrupts. Will + * return a negative error code if unable to acquire MSI-X vectors for any + * reason. + */ +static int ixgbe_acquire_msix_vectors(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int i, vectors, vector_threshold; + + /* We start by asking for one vector per queue pair with XDP queues + * being stacked with TX queues. + */ + vectors = max(adapter->num_rx_queues, adapter->num_tx_queues); + vectors = max(vectors, adapter->num_xdp_queues); + + /* It is easy to be greedy for MSI-X vectors. However, it really + * doesn't do much good if we have a lot more vectors than CPUs. We'll + * be somewhat conservative and only ask for (roughly) the same number + * of vectors as there are CPUs. + */ + vectors = min_t(int, vectors, num_online_cpus()); + + /* Some vectors are necessary for non-queue interrupts */ + vectors += NON_Q_VECTORS; + + /* Hardware can only support a maximum of hw.mac->max_msix_vectors. + * With features such as RSS and VMDq, we can easily surpass the + * number of Rx and Tx descriptor queues supported by our device. + * Thus, we cap the maximum in the rare cases where the CPU count also + * exceeds our vector limit + */ + vectors = min_t(int, vectors, hw->mac.max_msix_vectors); + + /* We want a minimum of two MSI-X vectors for (1) a TxQ[0] + RxQ[0] + * handler, and (2) an Other (Link Status Change, etc.) handler. + */ + vector_threshold = MIN_MSIX_COUNT; + + adapter->msix_entries = kcalloc(vectors, + sizeof(struct msix_entry), + GFP_KERNEL); + if (!adapter->msix_entries) + return -ENOMEM; + + for (i = 0; i < vectors; i++) + adapter->msix_entries[i].entry = i; + + vectors = pci_enable_msix_range(adapter->pdev, adapter->msix_entries, + vector_threshold, vectors); + + if (vectors < 0) { + /* A negative count of allocated vectors indicates an error in + * acquiring within the specified range of MSI-X vectors + */ + e_dev_warn("Failed to allocate MSI-X interrupts. Err: %d\n", + vectors); + + adapter->flags &= ~IXGBE_FLAG_MSIX_ENABLED; + kfree(adapter->msix_entries); + adapter->msix_entries = NULL; + + return vectors; + } + + /* we successfully allocated some number of vectors within our + * requested range. + */ + adapter->flags |= IXGBE_FLAG_MSIX_ENABLED; + + /* Adjust for only the vectors we'll use, which is minimum + * of max_q_vectors, or the number of vectors we were allocated. + */ + vectors -= NON_Q_VECTORS; + adapter->num_q_vectors = min_t(int, vectors, adapter->max_q_vectors); + + return 0; +} + +static void ixgbe_add_ring(struct ixgbe_ring *ring, + struct ixgbe_ring_container *head) +{ + ring->next = head->ring; + head->ring = ring; + head->count++; + head->next_update = jiffies + 1; +} + +/** + * ixgbe_alloc_q_vector - Allocate memory for a single interrupt vector + * @adapter: board private structure to initialize + * @v_count: q_vectors allocated on adapter, used for ring interleaving + * @v_idx: index of vector in adapter struct + * @txr_count: total number of Tx rings to allocate + * @txr_idx: index of first Tx ring to allocate + * @xdp_count: total number of XDP rings to allocate + * @xdp_idx: index of first XDP ring to allocate + * @rxr_count: total number of Rx rings to allocate + * @rxr_idx: index of first Rx ring to allocate + * + * We allocate one q_vector. If allocation fails we return -ENOMEM. + **/ +static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, + int v_count, int v_idx, + int txr_count, int txr_idx, + int xdp_count, int xdp_idx, + int rxr_count, int rxr_idx) +{ + int node = dev_to_node(&adapter->pdev->dev); + struct ixgbe_q_vector *q_vector; + struct ixgbe_ring *ring; + int cpu = -1; + int ring_count; + u8 tcs = adapter->hw_tcs; + + ring_count = txr_count + rxr_count + xdp_count; + + /* customize cpu for Flow Director mapping */ + if ((tcs <= 1) && !(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) { + u16 rss_i = adapter->ring_feature[RING_F_RSS].indices; + if (rss_i > 1 && adapter->atr_sample_rate) { + cpu = cpumask_local_spread(v_idx, node); + node = cpu_to_node(cpu); + } + } + + /* allocate q_vector and rings */ + q_vector = kzalloc_node(struct_size(q_vector, ring, ring_count), + GFP_KERNEL, node); + if (!q_vector) + q_vector = kzalloc(struct_size(q_vector, ring, ring_count), + GFP_KERNEL); + if (!q_vector) + return -ENOMEM; + + /* setup affinity mask and node */ + if (cpu != -1) + cpumask_set_cpu(cpu, &q_vector->affinity_mask); + q_vector->numa_node = node; + +#ifdef CONFIG_IXGBE_DCA + /* initialize CPU for DCA */ + q_vector->cpu = -1; + +#endif + /* initialize NAPI */ + netif_napi_add(adapter->netdev, &q_vector->napi, + ixgbe_poll, 64); + + /* tie q_vector and adapter together */ + adapter->q_vector[v_idx] = q_vector; + q_vector->adapter = adapter; + q_vector->v_idx = v_idx; + + /* initialize work limits */ + q_vector->tx.work_limit = adapter->tx_work_limit; + + /* Initialize setting for adaptive ITR */ + q_vector->tx.itr = IXGBE_ITR_ADAPTIVE_MAX_USECS | + IXGBE_ITR_ADAPTIVE_LATENCY; + q_vector->rx.itr = IXGBE_ITR_ADAPTIVE_MAX_USECS | + IXGBE_ITR_ADAPTIVE_LATENCY; + + /* intialize ITR */ + if (txr_count && !rxr_count) { + /* tx only vector */ + if (adapter->tx_itr_setting == 1) + q_vector->itr = IXGBE_12K_ITR; + else + q_vector->itr = adapter->tx_itr_setting; + } else { + /* rx or rx/tx vector */ + if (adapter->rx_itr_setting == 1) + q_vector->itr = IXGBE_20K_ITR; + else + q_vector->itr = adapter->rx_itr_setting; + } + + /* initialize pointer to rings */ + ring = q_vector->ring; + + while (txr_count) { + /* assign generic ring traits */ + ring->dev = &adapter->pdev->dev; + ring->netdev = adapter->netdev; + + /* configure backlink on ring */ + ring->q_vector = q_vector; + + /* update q_vector Tx values */ + ixgbe_add_ring(ring, &q_vector->tx); + + /* apply Tx specific ring traits */ + ring->count = adapter->tx_ring_count; + ring->queue_index = txr_idx; + + /* assign ring to adapter */ + WRITE_ONCE(adapter->tx_ring[txr_idx], ring); + + /* update count and index */ + txr_count--; + txr_idx += v_count; + + /* push pointer to next ring */ + ring++; + } + + while (xdp_count) { + /* assign generic ring traits */ + ring->dev = &adapter->pdev->dev; + ring->netdev = adapter->netdev; + + /* configure backlink on ring */ + ring->q_vector = q_vector; + + /* update q_vector Tx values */ + ixgbe_add_ring(ring, &q_vector->tx); + + /* apply Tx specific ring traits */ + ring->count = adapter->tx_ring_count; + ring->queue_index = xdp_idx; + set_ring_xdp(ring); + + /* assign ring to adapter */ + WRITE_ONCE(adapter->xdp_ring[xdp_idx], ring); + + /* update count and index */ + xdp_count--; + xdp_idx++; + + /* push pointer to next ring */ + ring++; + } + + while (rxr_count) { + /* assign generic ring traits */ + ring->dev = &adapter->pdev->dev; + ring->netdev = adapter->netdev; + + /* configure backlink on ring */ + ring->q_vector = q_vector; + + /* update q_vector Rx values */ + ixgbe_add_ring(ring, &q_vector->rx); + + /* + * 82599 errata, UDP frames with a 0 checksum + * can be marked as checksum errors. + */ + if (adapter->hw.mac.type == ixgbe_mac_82599EB) + set_bit(__IXGBE_RX_CSUM_UDP_ZERO_ERR, &ring->state); + +#ifdef IXGBE_FCOE + if (adapter->netdev->features & NETIF_F_FCOE_MTU) { + struct ixgbe_ring_feature *f; + f = &adapter->ring_feature[RING_F_FCOE]; + if ((rxr_idx >= f->offset) && + (rxr_idx < f->offset + f->indices)) + set_bit(__IXGBE_RX_FCOE, &ring->state); + } + +#endif /* IXGBE_FCOE */ + /* apply Rx specific ring traits */ + ring->count = adapter->rx_ring_count; + ring->queue_index = rxr_idx; + + /* assign ring to adapter */ + WRITE_ONCE(adapter->rx_ring[rxr_idx], ring); + + /* update count and index */ + rxr_count--; + rxr_idx += v_count; + + /* push pointer to next ring */ + ring++; + } + + return 0; +} + +/** + * ixgbe_free_q_vector - Free memory allocated for specific interrupt vector + * @adapter: board private structure to initialize + * @v_idx: Index of vector to be freed + * + * This function frees the memory allocated to the q_vector. In addition if + * NAPI is enabled it will delete any references to the NAPI struct prior + * to freeing the q_vector. + **/ +static void ixgbe_free_q_vector(struct ixgbe_adapter *adapter, int v_idx) +{ + struct ixgbe_q_vector *q_vector = adapter->q_vector[v_idx]; + struct ixgbe_ring *ring; + + ixgbe_for_each_ring(ring, q_vector->tx) { + if (ring_is_xdp(ring)) + WRITE_ONCE(adapter->xdp_ring[ring->queue_index], NULL); + else + WRITE_ONCE(adapter->tx_ring[ring->queue_index], NULL); + } + + ixgbe_for_each_ring(ring, q_vector->rx) + WRITE_ONCE(adapter->rx_ring[ring->queue_index], NULL); + + adapter->q_vector[v_idx] = NULL; + __netif_napi_del(&q_vector->napi); + + /* + * after a call to __netif_napi_del() napi may still be used and + * ixgbe_get_stats64() might access the rings on this vector, + * we must wait a grace period before freeing it. + */ + kfree_rcu(q_vector, rcu); +} + +/** + * ixgbe_alloc_q_vectors - Allocate memory for interrupt vectors + * @adapter: board private structure to initialize + * + * We allocate one q_vector per queue interrupt. If allocation fails we + * return -ENOMEM. + **/ +static int ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter) +{ + int q_vectors = adapter->num_q_vectors; + int rxr_remaining = adapter->num_rx_queues; + int txr_remaining = adapter->num_tx_queues; + int xdp_remaining = adapter->num_xdp_queues; + int rxr_idx = 0, txr_idx = 0, xdp_idx = 0, v_idx = 0; + int err, i; + + /* only one q_vector if MSI-X is disabled. */ + if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) + q_vectors = 1; + + if (q_vectors >= (rxr_remaining + txr_remaining + xdp_remaining)) { + for (; rxr_remaining; v_idx++) { + err = ixgbe_alloc_q_vector(adapter, q_vectors, v_idx, + 0, 0, 0, 0, 1, rxr_idx); + + if (err) + goto err_out; + + /* update counts and index */ + rxr_remaining--; + rxr_idx++; + } + } + + for (; v_idx < q_vectors; v_idx++) { + int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - v_idx); + int tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - v_idx); + int xqpv = DIV_ROUND_UP(xdp_remaining, q_vectors - v_idx); + + err = ixgbe_alloc_q_vector(adapter, q_vectors, v_idx, + tqpv, txr_idx, + xqpv, xdp_idx, + rqpv, rxr_idx); + + if (err) + goto err_out; + + /* update counts and index */ + rxr_remaining -= rqpv; + txr_remaining -= tqpv; + xdp_remaining -= xqpv; + rxr_idx++; + txr_idx++; + xdp_idx += xqpv; + } + + for (i = 0; i < adapter->num_rx_queues; i++) { + if (adapter->rx_ring[i]) + adapter->rx_ring[i]->ring_idx = i; + } + + for (i = 0; i < adapter->num_tx_queues; i++) { + if (adapter->tx_ring[i]) + adapter->tx_ring[i]->ring_idx = i; + } + + for (i = 0; i < adapter->num_xdp_queues; i++) { + if (adapter->xdp_ring[i]) + adapter->xdp_ring[i]->ring_idx = i; + } + + return 0; + +err_out: + adapter->num_tx_queues = 0; + adapter->num_xdp_queues = 0; + adapter->num_rx_queues = 0; + adapter->num_q_vectors = 0; + + while (v_idx--) + ixgbe_free_q_vector(adapter, v_idx); + + return -ENOMEM; +} + +/** + * ixgbe_free_q_vectors - Free memory allocated for interrupt vectors + * @adapter: board private structure to initialize + * + * This function frees the memory allocated to the q_vectors. In addition if + * NAPI is enabled it will delete any references to the NAPI struct prior + * to freeing the q_vector. + **/ +static void ixgbe_free_q_vectors(struct ixgbe_adapter *adapter) +{ + int v_idx = adapter->num_q_vectors; + + adapter->num_tx_queues = 0; + adapter->num_xdp_queues = 0; + adapter->num_rx_queues = 0; + adapter->num_q_vectors = 0; + + while (v_idx--) + ixgbe_free_q_vector(adapter, v_idx); +} + +static void ixgbe_reset_interrupt_capability(struct ixgbe_adapter *adapter) +{ + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) { + adapter->flags &= ~IXGBE_FLAG_MSIX_ENABLED; + pci_disable_msix(adapter->pdev); + kfree(adapter->msix_entries); + adapter->msix_entries = NULL; + } else if (adapter->flags & IXGBE_FLAG_MSI_ENABLED) { + adapter->flags &= ~IXGBE_FLAG_MSI_ENABLED; + pci_disable_msi(adapter->pdev); + } +} + +/** + * ixgbe_set_interrupt_capability - set MSI-X or MSI if supported + * @adapter: board private structure to initialize + * + * Attempt to configure the interrupts using the best available + * capabilities of the hardware and the kernel. + **/ +static void ixgbe_set_interrupt_capability(struct ixgbe_adapter *adapter) +{ + int err; + + /* We will try to get MSI-X interrupts first */ + if (!ixgbe_acquire_msix_vectors(adapter)) + return; + + /* At this point, we do not have MSI-X capabilities. We need to + * reconfigure or disable various features which require MSI-X + * capability. + */ + + /* Disable DCB unless we only have a single traffic class */ + if (adapter->hw_tcs > 1) { + e_dev_warn("Number of DCB TCs exceeds number of available queues. Disabling DCB support.\n"); + netdev_reset_tc(adapter->netdev); + + if (adapter->hw.mac.type == ixgbe_mac_82598EB) + adapter->hw.fc.requested_mode = adapter->last_lfc_mode; + + adapter->flags &= ~IXGBE_FLAG_DCB_ENABLED; + adapter->temp_dcb_cfg.pfc_mode_enable = false; + adapter->dcb_cfg.pfc_mode_enable = false; + } + + adapter->hw_tcs = 0; + adapter->dcb_cfg.num_tcs.pg_tcs = 1; + adapter->dcb_cfg.num_tcs.pfc_tcs = 1; + + /* Disable SR-IOV support */ + e_dev_warn("Disabling SR-IOV support\n"); + ixgbe_disable_sriov(adapter); + + /* Disable RSS */ + e_dev_warn("Disabling RSS support\n"); + adapter->ring_feature[RING_F_RSS].limit = 1; + + /* recalculate number of queues now that many features have been + * changed or disabled. + */ + ixgbe_set_num_queues(adapter); + adapter->num_q_vectors = 1; + + err = pci_enable_msi(adapter->pdev); + if (err) + e_dev_warn("Failed to allocate MSI interrupt, falling back to legacy. Error: %d\n", + err); + else + adapter->flags |= IXGBE_FLAG_MSI_ENABLED; +} + +/** + * ixgbe_init_interrupt_scheme - Determine proper interrupt scheme + * @adapter: board private structure to initialize + * + * We determine which interrupt scheme to use based on... + * - Kernel support (MSI, MSI-X) + * - which can be user-defined (via MODULE_PARAM) + * - Hardware queue count (num_*_queues) + * - defined by miscellaneous hardware support/features (RSS, etc.) + **/ +int ixgbe_init_interrupt_scheme(struct ixgbe_adapter *adapter) +{ + int err; + + /* Number of supported queues */ + ixgbe_set_num_queues(adapter); + + /* Set interrupt mode */ + ixgbe_set_interrupt_capability(adapter); + + err = ixgbe_alloc_q_vectors(adapter); + if (err) { + e_dev_err("Unable to allocate memory for queue vectors\n"); + goto err_alloc_q_vectors; + } + + ixgbe_cache_ring_register(adapter); + + e_dev_info("Multiqueue %s: Rx Queue count = %u, Tx Queue count = %u XDP Queue count = %u\n", + (adapter->num_rx_queues > 1) ? "Enabled" : "Disabled", + adapter->num_rx_queues, adapter->num_tx_queues, + adapter->num_xdp_queues); + + set_bit(__IXGBE_DOWN, &adapter->state); + + return 0; + +err_alloc_q_vectors: + ixgbe_reset_interrupt_capability(adapter); + return err; +} + +/** + * ixgbe_clear_interrupt_scheme - Clear the current interrupt scheme settings + * @adapter: board private structure to clear interrupt scheme on + * + * We go through and clear interrupt specific resources and reset the structure + * to pre-load conditions + **/ +void ixgbe_clear_interrupt_scheme(struct ixgbe_adapter *adapter) +{ + adapter->num_tx_queues = 0; + adapter->num_xdp_queues = 0; + adapter->num_rx_queues = 0; + + ixgbe_free_q_vectors(adapter); + ixgbe_reset_interrupt_capability(adapter); +} + +void ixgbe_tx_ctxtdesc(struct ixgbe_ring *tx_ring, u32 vlan_macip_lens, + u32 fceof_saidx, u32 type_tucmd, u32 mss_l4len_idx) +{ + struct ixgbe_adv_tx_context_desc *context_desc; + u16 i = tx_ring->next_to_use; + + context_desc = IXGBE_TX_CTXTDESC(tx_ring, i); + + i++; + tx_ring->next_to_use = (i < tx_ring->count) ? i : 0; + + /* set bits to identify this as an advanced context descriptor */ + type_tucmd |= IXGBE_TXD_CMD_DEXT | IXGBE_ADVTXD_DTYP_CTXT; + + context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens); + context_desc->fceof_saidx = cpu_to_le32(fceof_saidx); + context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd); + context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx); +} + diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c new file mode 100644 index 000000000..5829d81f2 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -0,0 +1,11483 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#include <linux/types.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/netdevice.h> +#include <linux/vmalloc.h> +#include <linux/string.h> +#include <linux/in.h> +#include <linux/interrupt.h> +#include <linux/ip.h> +#include <linux/tcp.h> +#include <linux/sctp.h> +#include <linux/pkt_sched.h> +#include <linux/ipv6.h> +#include <linux/slab.h> +#include <net/checksum.h> +#include <net/ip6_checksum.h> +#include <linux/etherdevice.h> +#include <linux/ethtool.h> +#include <linux/if.h> +#include <linux/if_vlan.h> +#include <linux/if_macvlan.h> +#include <linux/if_bridge.h> +#include <linux/prefetch.h> +#include <linux/bpf.h> +#include <linux/bpf_trace.h> +#include <linux/atomic.h> +#include <linux/numa.h> +#include <generated/utsrelease.h> +#include <scsi/fc/fc_fcoe.h> +#include <net/udp_tunnel.h> +#include <net/pkt_cls.h> +#include <net/tc_act/tc_gact.h> +#include <net/tc_act/tc_mirred.h> +#include <net/vxlan.h> +#include <net/mpls.h> +#include <net/xdp_sock_drv.h> +#include <net/xfrm.h> + +#include "ixgbe.h" +#include "ixgbe_common.h" +#include "ixgbe_dcb_82599.h" +#include "ixgbe_phy.h" +#include "ixgbe_sriov.h" +#include "ixgbe_model.h" +#include "ixgbe_txrx_common.h" + +char ixgbe_driver_name[] = "ixgbe"; +static const char ixgbe_driver_string[] = + "Intel(R) 10 Gigabit PCI Express Network Driver"; +#ifdef IXGBE_FCOE +char ixgbe_default_device_descr[] = + "Intel(R) 10 Gigabit Network Connection"; +#else +static char ixgbe_default_device_descr[] = + "Intel(R) 10 Gigabit Network Connection"; +#endif +static const char ixgbe_copyright[] = + "Copyright (c) 1999-2016 Intel Corporation."; + +static const char ixgbe_overheat_msg[] = "Network adapter has been stopped because it has over heated. Restart the computer. If the problem persists, power off the system and replace the adapter"; + +static const struct ixgbe_info *ixgbe_info_tbl[] = { + [board_82598] = &ixgbe_82598_info, + [board_82599] = &ixgbe_82599_info, + [board_X540] = &ixgbe_X540_info, + [board_X550] = &ixgbe_X550_info, + [board_X550EM_x] = &ixgbe_X550EM_x_info, + [board_x550em_x_fw] = &ixgbe_x550em_x_fw_info, + [board_x550em_a] = &ixgbe_x550em_a_info, + [board_x550em_a_fw] = &ixgbe_x550em_a_fw_info, +}; + +/* ixgbe_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 ixgbe_pci_tbl[] = { + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598), board_82598 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AF_DUAL_PORT), board_82598 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AF_SINGLE_PORT), board_82598 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AT), board_82598 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598AT2), board_82598 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_CX4), board_82598 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_CX4_DUAL_PORT), board_82598 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_DA_DUAL_PORT), board_82598 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_SR_DUAL_PORT_EM), board_82598 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_XF_LR), board_82598 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598EB_SFP_LOM), board_82598 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82598_BX), board_82598 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KX4), board_82599 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_XAUI_LOM), board_82599 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KR), board_82599 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP), board_82599 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_EM), board_82599 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_KX4_MEZZ), board_82599 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_CX4), board_82599 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_BACKPLANE_FCOE), board_82599 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_FCOE), board_82599 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_T3_LOM), board_82599 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_COMBO_BACKPLANE), board_82599 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540T), board_X540 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_SF2), board_82599 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_LS), board_82599 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_QSFP_SF_QP), board_82599 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599EN_SFP), board_82599 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_SF_QP), board_82599 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540T1), board_X540 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550T), board_X550}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550T1), board_X550}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_KX4), board_X550EM_x}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_XFI), board_X550EM_x}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_KR), board_X550EM_x}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_10G_T), board_X550EM_x}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_SFP), board_X550EM_x}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_1G_T), board_x550em_x_fw}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_KR), board_x550em_a }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_KR_L), board_x550em_a }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_SFP_N), board_x550em_a }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_SGMII), board_x550em_a }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_SGMII_L), board_x550em_a }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_10G_T), board_x550em_a}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_SFP), board_x550em_a }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_1G_T), board_x550em_a_fw }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_1G_T_L), board_x550em_a_fw }, + /* required last entry */ + {0, } +}; +MODULE_DEVICE_TABLE(pci, ixgbe_pci_tbl); + +#ifdef CONFIG_IXGBE_DCA +static int ixgbe_notify_dca(struct notifier_block *, unsigned long event, + void *p); +static struct notifier_block dca_notifier = { + .notifier_call = ixgbe_notify_dca, + .next = NULL, + .priority = 0 +}; +#endif + +#ifdef CONFIG_PCI_IOV +static unsigned int max_vfs; +module_param(max_vfs, uint, 0); +MODULE_PARM_DESC(max_vfs, + "Maximum number of virtual functions to allocate per physical function - default is zero and maximum value is 63. (Deprecated)"); +#endif /* CONFIG_PCI_IOV */ + +static unsigned int allow_unsupported_sfp; +module_param(allow_unsupported_sfp, uint, 0); +MODULE_PARM_DESC(allow_unsupported_sfp, + "Allow unsupported and untested SFP+ modules on 82599-based adapters"); + +#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)"); + +MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); +MODULE_DESCRIPTION("Intel(R) 10 Gigabit PCI Express Network Driver"); +MODULE_LICENSE("GPL v2"); + +static struct workqueue_struct *ixgbe_wq; + +static bool ixgbe_check_cfg_remove(struct ixgbe_hw *hw, struct pci_dev *pdev); +static void ixgbe_watchdog_link_is_down(struct ixgbe_adapter *); + +static const struct net_device_ops ixgbe_netdev_ops; + +static bool netif_is_ixgbe(struct net_device *dev) +{ + return dev && (dev->netdev_ops == &ixgbe_netdev_ops); +} + +static int ixgbe_read_pci_cfg_word_parent(struct ixgbe_adapter *adapter, + u32 reg, u16 *value) +{ + struct pci_dev *parent_dev; + struct pci_bus *parent_bus; + + parent_bus = adapter->pdev->bus->parent; + if (!parent_bus) + return -1; + + parent_dev = parent_bus->self; + if (!parent_dev) + return -1; + + if (!pci_is_pcie(parent_dev)) + return -1; + + pcie_capability_read_word(parent_dev, reg, value); + if (*value == IXGBE_FAILED_READ_CFG_WORD && + ixgbe_check_cfg_remove(&adapter->hw, parent_dev)) + return -1; + return 0; +} + +static s32 ixgbe_get_parent_bus_info(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u16 link_status = 0; + int err; + + hw->bus.type = ixgbe_bus_type_pci_express; + + /* Get the negotiated link width and speed from PCI config space of the + * parent, as this device is behind a switch + */ + err = ixgbe_read_pci_cfg_word_parent(adapter, 18, &link_status); + + /* assume caller will handle error case */ + if (err) + return err; + + hw->bus.width = ixgbe_convert_bus_width(link_status); + hw->bus.speed = ixgbe_convert_bus_speed(link_status); + + return 0; +} + +/** + * ixgbe_check_from_parent - Determine whether PCIe info should come from parent + * @hw: hw specific details + * + * This function is used by probe to determine whether a device's PCI-Express + * bandwidth details should be gathered from the parent bus instead of from the + * device. Used to ensure that various locations all have the correct device ID + * checks. + */ +static inline bool ixgbe_pcie_from_parent(struct ixgbe_hw *hw) +{ + switch (hw->device_id) { + case IXGBE_DEV_ID_82599_SFP_SF_QP: + case IXGBE_DEV_ID_82599_QSFP_SF_QP: + return true; + default: + return false; + } +} + +static void ixgbe_check_minimum_link(struct ixgbe_adapter *adapter, + int expected_gts) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct pci_dev *pdev; + + /* Some devices are not connected over PCIe and thus do not negotiate + * speed. These devices do not have valid bus info, and thus any report + * we generate may not be correct. + */ + if (hw->bus.type == ixgbe_bus_type_internal) + return; + + /* determine whether to use the parent device */ + if (ixgbe_pcie_from_parent(&adapter->hw)) + pdev = adapter->pdev->bus->parent->self; + else + pdev = adapter->pdev; + + pcie_print_link_status(pdev); +} + +static void ixgbe_service_event_schedule(struct ixgbe_adapter *adapter) +{ + if (!test_bit(__IXGBE_DOWN, &adapter->state) && + !test_bit(__IXGBE_REMOVING, &adapter->state) && + !test_and_set_bit(__IXGBE_SERVICE_SCHED, &adapter->state)) + queue_work(ixgbe_wq, &adapter->service_task); +} + +static void ixgbe_remove_adapter(struct ixgbe_hw *hw) +{ + struct ixgbe_adapter *adapter = hw->back; + + if (!hw->hw_addr) + return; + hw->hw_addr = NULL; + e_dev_err("Adapter removed\n"); + if (test_bit(__IXGBE_SERVICE_INITED, &adapter->state)) + ixgbe_service_event_schedule(adapter); +} + +static u32 ixgbe_check_remove(struct ixgbe_hw *hw, u32 reg) +{ + u8 __iomem *reg_addr; + u32 value; + int i; + + reg_addr = READ_ONCE(hw->hw_addr); + if (ixgbe_removed(reg_addr)) + return IXGBE_FAILED_READ_REG; + + /* Register read of 0xFFFFFFF can indicate the adapter has been removed, + * so perform several status register reads to determine if the adapter + * has been removed. + */ + for (i = 0; i < IXGBE_FAILED_READ_RETRIES; i++) { + value = readl(reg_addr + IXGBE_STATUS); + if (value != IXGBE_FAILED_READ_REG) + break; + mdelay(3); + } + + if (value == IXGBE_FAILED_READ_REG) + ixgbe_remove_adapter(hw); + else + value = readl(reg_addr + reg); + return value; +} + +/** + * ixgbe_read_reg - Read from device register + * @hw: hw specific details + * @reg: offset of register to read + * + * Returns : value read or IXGBE_FAILED_READ_REG if removed + * + * This function is used to read device registers. It checks for device + * removal by confirming any read that returns all ones by checking the + * status register value for all ones. This function avoids reading from + * the hardware if a removal was previously detected in which case it + * returns IXGBE_FAILED_READ_REG (all ones). + */ +u32 ixgbe_read_reg(struct ixgbe_hw *hw, u32 reg) +{ + u8 __iomem *reg_addr = READ_ONCE(hw->hw_addr); + u32 value; + + if (ixgbe_removed(reg_addr)) + return IXGBE_FAILED_READ_REG; + if (unlikely(hw->phy.nw_mng_if_sel & + IXGBE_NW_MNG_IF_SEL_SGMII_ENABLE)) { + struct ixgbe_adapter *adapter; + int i; + + for (i = 0; i < 200; ++i) { + value = readl(reg_addr + IXGBE_MAC_SGMII_BUSY); + if (likely(!value)) + goto writes_completed; + if (value == IXGBE_FAILED_READ_REG) { + ixgbe_remove_adapter(hw); + return IXGBE_FAILED_READ_REG; + } + udelay(5); + } + + adapter = hw->back; + e_warn(hw, "register writes incomplete %08x\n", value); + } + +writes_completed: + value = readl(reg_addr + reg); + if (unlikely(value == IXGBE_FAILED_READ_REG)) + value = ixgbe_check_remove(hw, reg); + return value; +} + +static bool ixgbe_check_cfg_remove(struct ixgbe_hw *hw, struct pci_dev *pdev) +{ + u16 value; + + pci_read_config_word(pdev, PCI_VENDOR_ID, &value); + if (value == IXGBE_FAILED_READ_CFG_WORD) { + ixgbe_remove_adapter(hw); + return true; + } + return false; +} + +u16 ixgbe_read_pci_cfg_word(struct ixgbe_hw *hw, u32 reg) +{ + struct ixgbe_adapter *adapter = hw->back; + u16 value; + + if (ixgbe_removed(hw->hw_addr)) + return IXGBE_FAILED_READ_CFG_WORD; + pci_read_config_word(adapter->pdev, reg, &value); + if (value == IXGBE_FAILED_READ_CFG_WORD && + ixgbe_check_cfg_remove(hw, adapter->pdev)) + return IXGBE_FAILED_READ_CFG_WORD; + return value; +} + +#ifdef CONFIG_PCI_IOV +static u32 ixgbe_read_pci_cfg_dword(struct ixgbe_hw *hw, u32 reg) +{ + struct ixgbe_adapter *adapter = hw->back; + u32 value; + + if (ixgbe_removed(hw->hw_addr)) + return IXGBE_FAILED_READ_CFG_DWORD; + pci_read_config_dword(adapter->pdev, reg, &value); + if (value == IXGBE_FAILED_READ_CFG_DWORD && + ixgbe_check_cfg_remove(hw, adapter->pdev)) + return IXGBE_FAILED_READ_CFG_DWORD; + return value; +} +#endif /* CONFIG_PCI_IOV */ + +void ixgbe_write_pci_cfg_word(struct ixgbe_hw *hw, u32 reg, u16 value) +{ + struct ixgbe_adapter *adapter = hw->back; + + if (ixgbe_removed(hw->hw_addr)) + return; + pci_write_config_word(adapter->pdev, reg, value); +} + +static void ixgbe_service_event_complete(struct ixgbe_adapter *adapter) +{ + BUG_ON(!test_bit(__IXGBE_SERVICE_SCHED, &adapter->state)); + + /* flush memory to make sure state is correct before next watchdog */ + smp_mb__before_atomic(); + clear_bit(__IXGBE_SERVICE_SCHED, &adapter->state); +} + +struct ixgbe_reg_info { + u32 ofs; + char *name; +}; + +static const struct ixgbe_reg_info ixgbe_reg_info_tbl[] = { + + /* General Registers */ + {IXGBE_CTRL, "CTRL"}, + {IXGBE_STATUS, "STATUS"}, + {IXGBE_CTRL_EXT, "CTRL_EXT"}, + + /* Interrupt Registers */ + {IXGBE_EICR, "EICR"}, + + /* RX Registers */ + {IXGBE_SRRCTL(0), "SRRCTL"}, + {IXGBE_DCA_RXCTRL(0), "DRXCTL"}, + {IXGBE_RDLEN(0), "RDLEN"}, + {IXGBE_RDH(0), "RDH"}, + {IXGBE_RDT(0), "RDT"}, + {IXGBE_RXDCTL(0), "RXDCTL"}, + {IXGBE_RDBAL(0), "RDBAL"}, + {IXGBE_RDBAH(0), "RDBAH"}, + + /* TX Registers */ + {IXGBE_TDBAL(0), "TDBAL"}, + {IXGBE_TDBAH(0), "TDBAH"}, + {IXGBE_TDLEN(0), "TDLEN"}, + {IXGBE_TDH(0), "TDH"}, + {IXGBE_TDT(0), "TDT"}, + {IXGBE_TXDCTL(0), "TXDCTL"}, + + /* List Terminator */ + { .name = NULL } +}; + + +/* + * ixgbe_regdump - register printout routine + */ +static void ixgbe_regdump(struct ixgbe_hw *hw, struct ixgbe_reg_info *reginfo) +{ + int i; + char rname[16]; + u32 regs[64]; + + switch (reginfo->ofs) { + case IXGBE_SRRCTL(0): + for (i = 0; i < 64; i++) + regs[i] = IXGBE_READ_REG(hw, IXGBE_SRRCTL(i)); + break; + case IXGBE_DCA_RXCTRL(0): + for (i = 0; i < 64; i++) + regs[i] = IXGBE_READ_REG(hw, IXGBE_DCA_RXCTRL(i)); + break; + case IXGBE_RDLEN(0): + for (i = 0; i < 64; i++) + regs[i] = IXGBE_READ_REG(hw, IXGBE_RDLEN(i)); + break; + case IXGBE_RDH(0): + for (i = 0; i < 64; i++) + regs[i] = IXGBE_READ_REG(hw, IXGBE_RDH(i)); + break; + case IXGBE_RDT(0): + for (i = 0; i < 64; i++) + regs[i] = IXGBE_READ_REG(hw, IXGBE_RDT(i)); + break; + case IXGBE_RXDCTL(0): + for (i = 0; i < 64; i++) + regs[i] = IXGBE_READ_REG(hw, IXGBE_RXDCTL(i)); + break; + case IXGBE_RDBAL(0): + for (i = 0; i < 64; i++) + regs[i] = IXGBE_READ_REG(hw, IXGBE_RDBAL(i)); + break; + case IXGBE_RDBAH(0): + for (i = 0; i < 64; i++) + regs[i] = IXGBE_READ_REG(hw, IXGBE_RDBAH(i)); + break; + case IXGBE_TDBAL(0): + for (i = 0; i < 64; i++) + regs[i] = IXGBE_READ_REG(hw, IXGBE_TDBAL(i)); + break; + case IXGBE_TDBAH(0): + for (i = 0; i < 64; i++) + regs[i] = IXGBE_READ_REG(hw, IXGBE_TDBAH(i)); + break; + case IXGBE_TDLEN(0): + for (i = 0; i < 64; i++) + regs[i] = IXGBE_READ_REG(hw, IXGBE_TDLEN(i)); + break; + case IXGBE_TDH(0): + for (i = 0; i < 64; i++) + regs[i] = IXGBE_READ_REG(hw, IXGBE_TDH(i)); + break; + case IXGBE_TDT(0): + for (i = 0; i < 64; i++) + regs[i] = IXGBE_READ_REG(hw, IXGBE_TDT(i)); + break; + case IXGBE_TXDCTL(0): + for (i = 0; i < 64; i++) + regs[i] = IXGBE_READ_REG(hw, IXGBE_TXDCTL(i)); + break; + default: + pr_info("%-15s %08x\n", + reginfo->name, IXGBE_READ_REG(hw, reginfo->ofs)); + return; + } + + i = 0; + while (i < 64) { + int j; + char buf[9 * 8 + 1]; + char *p = buf; + + snprintf(rname, 16, "%s[%d-%d]", reginfo->name, i, i + 7); + for (j = 0; j < 8; j++) + p += sprintf(p, " %08x", regs[i++]); + pr_err("%-15s%s\n", rname, buf); + } + +} + +static void ixgbe_print_buffer(struct ixgbe_ring *ring, int n) +{ + struct ixgbe_tx_buffer *tx_buffer; + + tx_buffer = &ring->tx_buffer_info[ring->next_to_clean]; + pr_info(" %5d %5X %5X %016llX %08X %p %016llX\n", + n, ring->next_to_use, ring->next_to_clean, + (u64)dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + tx_buffer->next_to_watch, + (u64)tx_buffer->time_stamp); +} + +/* + * ixgbe_dump - Print registers, tx-rings and rx-rings + */ +static void ixgbe_dump(struct ixgbe_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_reg_info *reginfo; + int n = 0; + struct ixgbe_ring *ring; + struct ixgbe_tx_buffer *tx_buffer; + union ixgbe_adv_tx_desc *tx_desc; + struct my_u0 { u64 a; u64 b; } *u0; + struct ixgbe_ring *rx_ring; + union ixgbe_adv_rx_desc *rx_desc; + struct ixgbe_rx_buffer *rx_buffer_info; + int i = 0; + + if (!netif_msg_hw(adapter)) + return; + + /* Print netdevice Info */ + if (netdev) { + dev_info(&adapter->pdev->dev, "Net device Info\n"); + pr_info("Device Name state " + "trans_start\n"); + pr_info("%-15s %016lX %016lX\n", + netdev->name, + netdev->state, + dev_trans_start(netdev)); + } + + /* Print Registers */ + dev_info(&adapter->pdev->dev, "Register Dump\n"); + pr_info(" Register Name Value\n"); + for (reginfo = (struct ixgbe_reg_info *)ixgbe_reg_info_tbl; + reginfo->name; reginfo++) { + ixgbe_regdump(hw, reginfo); + } + + /* Print TX Ring Summary */ + if (!netdev || !netif_running(netdev)) + return; + + dev_info(&adapter->pdev->dev, "TX Rings Summary\n"); + pr_info(" %s %s %s %s\n", + "Queue [NTU] [NTC] [bi(ntc)->dma ]", + "leng", "ntw", "timestamp"); + for (n = 0; n < adapter->num_tx_queues; n++) { + ring = adapter->tx_ring[n]; + ixgbe_print_buffer(ring, n); + } + + for (n = 0; n < adapter->num_xdp_queues; n++) { + ring = adapter->xdp_ring[n]; + ixgbe_print_buffer(ring, n); + } + + /* Print TX Rings */ + if (!netif_msg_tx_done(adapter)) + goto rx_ring_summary; + + dev_info(&adapter->pdev->dev, "TX Rings Dump\n"); + + /* Transmit Descriptor Formats + * + * 82598 Advanced Transmit Descriptor + * +--------------------------------------------------------------+ + * 0 | Buffer Address [63:0] | + * +--------------------------------------------------------------+ + * 8 | PAYLEN | POPTS | IDX | STA | DCMD |DTYP | RSV | DTALEN | + * +--------------------------------------------------------------+ + * 63 46 45 40 39 36 35 32 31 24 23 20 19 0 + * + * 82598 Advanced Transmit Descriptor (Write-Back Format) + * +--------------------------------------------------------------+ + * 0 | RSV [63:0] | + * +--------------------------------------------------------------+ + * 8 | RSV | STA | NXTSEQ | + * +--------------------------------------------------------------+ + * 63 36 35 32 31 0 + * + * 82599+ Advanced Transmit Descriptor + * +--------------------------------------------------------------+ + * 0 | Buffer Address [63:0] | + * +--------------------------------------------------------------+ + * 8 |PAYLEN |POPTS|CC|IDX |STA |DCMD |DTYP |MAC |RSV |DTALEN | + * +--------------------------------------------------------------+ + * 63 46 45 40 39 38 36 35 32 31 24 23 20 19 18 17 16 15 0 + * + * 82599+ Advanced Transmit Descriptor (Write-Back Format) + * +--------------------------------------------------------------+ + * 0 | RSV [63:0] | + * +--------------------------------------------------------------+ + * 8 | RSV | STA | RSV | + * +--------------------------------------------------------------+ + * 63 36 35 32 31 0 + */ + + for (n = 0; n < adapter->num_tx_queues; n++) { + ring = adapter->tx_ring[n]; + pr_info("------------------------------------\n"); + pr_info("TX QUEUE INDEX = %d\n", ring->queue_index); + pr_info("------------------------------------\n"); + pr_info("%s%s %s %s %s %s\n", + "T [desc] [address 63:0 ] ", + "[PlPOIdStDDt Ln] [bi->dma ] ", + "leng", "ntw", "timestamp", "bi->skb"); + + for (i = 0; ring->desc && (i < ring->count); i++) { + tx_desc = IXGBE_TX_DESC(ring, i); + tx_buffer = &ring->tx_buffer_info[i]; + u0 = (struct my_u0 *)tx_desc; + if (dma_unmap_len(tx_buffer, len) > 0) { + const char *ring_desc; + + if (i == ring->next_to_use && + i == ring->next_to_clean) + ring_desc = " NTC/U"; + else if (i == ring->next_to_use) + ring_desc = " NTU"; + else if (i == ring->next_to_clean) + ring_desc = " NTC"; + else + ring_desc = ""; + pr_info("T [0x%03X] %016llX %016llX %016llX %08X %p %016llX %p%s", + i, + le64_to_cpu((__force __le64)u0->a), + le64_to_cpu((__force __le64)u0->b), + (u64)dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + tx_buffer->next_to_watch, + (u64)tx_buffer->time_stamp, + tx_buffer->skb, + ring_desc); + + if (netif_msg_pktdata(adapter) && + tx_buffer->skb) + print_hex_dump(KERN_INFO, "", + DUMP_PREFIX_ADDRESS, 16, 1, + tx_buffer->skb->data, + dma_unmap_len(tx_buffer, len), + true); + } + } + } + + /* Print RX Rings Summary */ +rx_ring_summary: + dev_info(&adapter->pdev->dev, "RX Rings Summary\n"); + pr_info("Queue [NTU] [NTC]\n"); + for (n = 0; n < adapter->num_rx_queues; n++) { + rx_ring = adapter->rx_ring[n]; + pr_info("%5d %5X %5X\n", + n, rx_ring->next_to_use, rx_ring->next_to_clean); + } + + /* Print RX Rings */ + if (!netif_msg_rx_status(adapter)) + return; + + dev_info(&adapter->pdev->dev, "RX Rings Dump\n"); + + /* Receive Descriptor Formats + * + * 82598 Advanced Receive Descriptor (Read) Format + * 63 1 0 + * +-----------------------------------------------------+ + * 0 | Packet Buffer Address [63:1] |A0/NSE| + * +----------------------------------------------+------+ + * 8 | Header Buffer Address [63:1] | DD | + * +-----------------------------------------------------+ + * + * + * 82598 Advanced Receive Descriptor (Write-Back) Format + * + * 63 48 47 32 31 30 21 20 16 15 4 3 0 + * +------------------------------------------------------+ + * 0 | RSS Hash / |SPH| HDR_LEN | RSV |Packet| RSS | + * | Packet | IP | | | | Type | Type | + * | Checksum | Ident | | | | | | + * +------------------------------------------------------+ + * 8 | VLAN Tag | Length | Extended Error | Extended Status | + * +------------------------------------------------------+ + * 63 48 47 32 31 20 19 0 + * + * 82599+ Advanced Receive Descriptor (Read) Format + * 63 1 0 + * +-----------------------------------------------------+ + * 0 | Packet Buffer Address [63:1] |A0/NSE| + * +----------------------------------------------+------+ + * 8 | Header Buffer Address [63:1] | DD | + * +-----------------------------------------------------+ + * + * + * 82599+ Advanced Receive Descriptor (Write-Back) Format + * + * 63 48 47 32 31 30 21 20 17 16 4 3 0 + * +------------------------------------------------------+ + * 0 |RSS / Frag Checksum|SPH| HDR_LEN |RSC- |Packet| RSS | + * |/ RTT / PCoE_PARAM | | | CNT | Type | Type | + * |/ Flow Dir Flt ID | | | | | | + * +------------------------------------------------------+ + * 8 | VLAN Tag | Length |Extended Error| Xtnd Status/NEXTP | + * +------------------------------------------------------+ + * 63 48 47 32 31 20 19 0 + */ + + for (n = 0; n < adapter->num_rx_queues; n++) { + rx_ring = adapter->rx_ring[n]; + pr_info("------------------------------------\n"); + pr_info("RX QUEUE INDEX = %d\n", rx_ring->queue_index); + pr_info("------------------------------------\n"); + pr_info("%s%s%s\n", + "R [desc] [ PktBuf A0] ", + "[ HeadBuf DD] [bi->dma ] [bi->skb ] ", + "<-- Adv Rx Read format"); + pr_info("%s%s%s\n", + "RWB[desc] [PcsmIpSHl PtRs] ", + "[vl er S cks ln] ---------------- [bi->skb ] ", + "<-- Adv Rx Write-Back format"); + + for (i = 0; i < rx_ring->count; i++) { + const char *ring_desc; + + if (i == rx_ring->next_to_use) + ring_desc = " NTU"; + else if (i == rx_ring->next_to_clean) + ring_desc = " NTC"; + else + ring_desc = ""; + + rx_buffer_info = &rx_ring->rx_buffer_info[i]; + rx_desc = IXGBE_RX_DESC(rx_ring, i); + u0 = (struct my_u0 *)rx_desc; + if (rx_desc->wb.upper.length) { + /* Descriptor Done */ + pr_info("RWB[0x%03X] %016llX %016llX ---------------- %p%s\n", + i, + le64_to_cpu((__force __le64)u0->a), + le64_to_cpu((__force __le64)u0->b), + rx_buffer_info->skb, + ring_desc); + } else { + pr_info("R [0x%03X] %016llX %016llX %016llX %p%s\n", + i, + le64_to_cpu((__force __le64)u0->a), + le64_to_cpu((__force __le64)u0->b), + (u64)rx_buffer_info->dma, + rx_buffer_info->skb, + ring_desc); + + if (netif_msg_pktdata(adapter) && + rx_buffer_info->dma) { + print_hex_dump(KERN_INFO, "", + DUMP_PREFIX_ADDRESS, 16, 1, + page_address(rx_buffer_info->page) + + rx_buffer_info->page_offset, + ixgbe_rx_bufsz(rx_ring), true); + } + } + } + } +} + +static void ixgbe_release_hw_control(struct ixgbe_adapter *adapter) +{ + u32 ctrl_ext; + + /* Let firmware take over control of h/w */ + ctrl_ext = IXGBE_READ_REG(&adapter->hw, IXGBE_CTRL_EXT); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_CTRL_EXT, + ctrl_ext & ~IXGBE_CTRL_EXT_DRV_LOAD); +} + +static void ixgbe_get_hw_control(struct ixgbe_adapter *adapter) +{ + u32 ctrl_ext; + + /* Let firmware know the driver has taken over */ + ctrl_ext = IXGBE_READ_REG(&adapter->hw, IXGBE_CTRL_EXT); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_CTRL_EXT, + ctrl_ext | IXGBE_CTRL_EXT_DRV_LOAD); +} + +/** + * ixgbe_set_ivar - set the IVAR registers, mapping interrupt causes to vectors + * @adapter: pointer to adapter struct + * @direction: 0 for Rx, 1 for Tx, -1 for other causes + * @queue: queue to map the corresponding interrupt to + * @msix_vector: the vector to map to the corresponding queue + * + */ +static void ixgbe_set_ivar(struct ixgbe_adapter *adapter, s8 direction, + u8 queue, u8 msix_vector) +{ + u32 ivar, index; + struct ixgbe_hw *hw = &adapter->hw; + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + msix_vector |= IXGBE_IVAR_ALLOC_VAL; + if (direction == -1) + direction = 0; + index = (((direction * 64) + queue) >> 2) & 0x1F; + ivar = IXGBE_READ_REG(hw, IXGBE_IVAR(index)); + ivar &= ~(0xFF << (8 * (queue & 0x3))); + ivar |= (msix_vector << (8 * (queue & 0x3))); + IXGBE_WRITE_REG(hw, IXGBE_IVAR(index), ivar); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + if (direction == -1) { + /* other causes */ + msix_vector |= IXGBE_IVAR_ALLOC_VAL; + index = ((queue & 1) * 8); + ivar = IXGBE_READ_REG(&adapter->hw, IXGBE_IVAR_MISC); + ivar &= ~(0xFF << index); + ivar |= (msix_vector << index); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_IVAR_MISC, ivar); + break; + } else { + /* tx or rx causes */ + msix_vector |= IXGBE_IVAR_ALLOC_VAL; + index = ((16 * (queue & 1)) + (8 * direction)); + ivar = IXGBE_READ_REG(hw, IXGBE_IVAR(queue >> 1)); + ivar &= ~(0xFF << index); + ivar |= (msix_vector << index); + IXGBE_WRITE_REG(hw, IXGBE_IVAR(queue >> 1), ivar); + break; + } + default: + break; + } +} + +void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter, + u64 qmask) +{ + u32 mask; + + switch (adapter->hw.mac.type) { + case ixgbe_mac_82598EB: + mask = (IXGBE_EIMS_RTX_QUEUE & qmask); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS, mask); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + mask = (qmask & 0xFFFFFFFF); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS_EX(0), mask); + mask = (qmask >> 32); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS_EX(1), mask); + break; + default: + break; + } +} + +static void ixgbe_update_xoff_rx_lfc(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_hw_stats *hwstats = &adapter->stats; + int i; + u32 data; + + if ((hw->fc.current_mode != ixgbe_fc_full) && + (hw->fc.current_mode != ixgbe_fc_rx_pause)) + return; + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + data = IXGBE_READ_REG(hw, IXGBE_LXOFFRXC); + break; + default: + data = IXGBE_READ_REG(hw, IXGBE_LXOFFRXCNT); + } + hwstats->lxoffrxc += data; + + /* refill credits (no tx hang) if we received xoff */ + if (!data) + return; + + for (i = 0; i < adapter->num_tx_queues; i++) + clear_bit(__IXGBE_HANG_CHECK_ARMED, + &adapter->tx_ring[i]->state); + + for (i = 0; i < adapter->num_xdp_queues; i++) + clear_bit(__IXGBE_HANG_CHECK_ARMED, + &adapter->xdp_ring[i]->state); +} + +static void ixgbe_update_xoff_received(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_hw_stats *hwstats = &adapter->stats; + u32 xoff[8] = {0}; + u8 tc; + int i; + bool pfc_en = adapter->dcb_cfg.pfc_mode_enable; + + if (adapter->ixgbe_ieee_pfc) + pfc_en |= !!(adapter->ixgbe_ieee_pfc->pfc_en); + + if (!(adapter->flags & IXGBE_FLAG_DCB_ENABLED) || !pfc_en) { + ixgbe_update_xoff_rx_lfc(adapter); + return; + } + + /* update stats for each tc, only valid with PFC enabled */ + for (i = 0; i < MAX_TX_PACKET_BUFFERS; i++) { + u32 pxoffrxc; + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + pxoffrxc = IXGBE_READ_REG(hw, IXGBE_PXOFFRXC(i)); + break; + default: + pxoffrxc = IXGBE_READ_REG(hw, IXGBE_PXOFFRXCNT(i)); + } + hwstats->pxoffrxc[i] += pxoffrxc; + /* Get the TC for given UP */ + tc = netdev_get_prio_tc_map(adapter->netdev, i); + xoff[tc] += pxoffrxc; + } + + /* disarm tx queues that have received xoff frames */ + for (i = 0; i < adapter->num_tx_queues; i++) { + struct ixgbe_ring *tx_ring = adapter->tx_ring[i]; + + tc = tx_ring->dcb_tc; + if (xoff[tc]) + clear_bit(__IXGBE_HANG_CHECK_ARMED, &tx_ring->state); + } + + for (i = 0; i < adapter->num_xdp_queues; i++) { + struct ixgbe_ring *xdp_ring = adapter->xdp_ring[i]; + + tc = xdp_ring->dcb_tc; + if (xoff[tc]) + clear_bit(__IXGBE_HANG_CHECK_ARMED, &xdp_ring->state); + } +} + +static u64 ixgbe_get_tx_completed(struct ixgbe_ring *ring) +{ + return ring->stats.packets; +} + +static u64 ixgbe_get_tx_pending(struct ixgbe_ring *ring) +{ + unsigned int head, tail; + + head = ring->next_to_clean; + tail = ring->next_to_use; + + return ((head <= tail) ? tail : tail + ring->count) - head; +} + +static inline bool ixgbe_check_tx_hang(struct ixgbe_ring *tx_ring) +{ + u32 tx_done = ixgbe_get_tx_completed(tx_ring); + u32 tx_done_old = tx_ring->tx_stats.tx_done_old; + u32 tx_pending = ixgbe_get_tx_pending(tx_ring); + + clear_check_for_tx_hang(tx_ring); + + /* + * Check for a hung queue, but be thorough. This verifies + * that a transmit has been completed since the previous + * check AND there is at least one packet pending. The + * ARMED bit is set to indicate a potential hang. The + * bit is cleared if a pause frame is received to remove + * false hang detection due to PFC or 802.3x frames. By + * requiring this to fail twice we avoid races with + * pfc clearing the ARMED bit and conditions where we + * run the check_tx_hang logic with a transmit completion + * pending but without time to complete it yet. + */ + if (tx_done_old == tx_done && tx_pending) + /* make sure it is true for two checks in a row */ + return test_and_set_bit(__IXGBE_HANG_CHECK_ARMED, + &tx_ring->state); + /* update completed stats and continue */ + tx_ring->tx_stats.tx_done_old = tx_done; + /* reset the countdown */ + clear_bit(__IXGBE_HANG_CHECK_ARMED, &tx_ring->state); + + return false; +} + +/** + * ixgbe_tx_timeout_reset - initiate reset due to Tx timeout + * @adapter: driver private struct + **/ +static void ixgbe_tx_timeout_reset(struct ixgbe_adapter *adapter) +{ + + /* Do the reset outside of interrupt context */ + if (!test_bit(__IXGBE_DOWN, &adapter->state)) { + set_bit(__IXGBE_RESET_REQUESTED, &adapter->state); + e_warn(drv, "initiating reset due to tx timeout\n"); + ixgbe_service_event_schedule(adapter); + } +} + +/** + * ixgbe_tx_maxrate - callback to set the maximum per-queue bitrate + * @netdev: network interface device structure + * @queue_index: Tx queue to set + * @maxrate: desired maximum transmit bitrate + **/ +static int ixgbe_tx_maxrate(struct net_device *netdev, + int queue_index, u32 maxrate) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + u32 bcnrc_val = ixgbe_link_mbps(adapter); + + if (!maxrate) + return 0; + + /* Calculate the rate factor values to set */ + bcnrc_val <<= IXGBE_RTTBCNRC_RF_INT_SHIFT; + bcnrc_val /= maxrate; + + /* clear everything but the rate factor */ + bcnrc_val &= IXGBE_RTTBCNRC_RF_INT_MASK | + IXGBE_RTTBCNRC_RF_DEC_MASK; + + /* enable the rate scheduler */ + bcnrc_val |= IXGBE_RTTBCNRC_RS_ENA; + + IXGBE_WRITE_REG(hw, IXGBE_RTTDQSEL, queue_index); + IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRC, bcnrc_val); + + return 0; +} + +/** + * ixgbe_clean_tx_irq - Reclaim resources after transmit completes + * @q_vector: structure containing interrupt and ring information + * @tx_ring: tx ring to clean + * @napi_budget: Used to determine if we are in netpoll + **/ +static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, + struct ixgbe_ring *tx_ring, int napi_budget) +{ + struct ixgbe_adapter *adapter = q_vector->adapter; + struct ixgbe_tx_buffer *tx_buffer; + union ixgbe_adv_tx_desc *tx_desc; + 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; + + if (test_bit(__IXGBE_DOWN, &adapter->state)) + return true; + + tx_buffer = &tx_ring->tx_buffer_info[i]; + tx_desc = IXGBE_TX_DESC(tx_ring, i); + i -= tx_ring->count; + + do { + union ixgbe_adv_tx_desc *eop_desc = tx_buffer->next_to_watch; + + /* if next_to_watch is not set then there is no work pending */ + if (!eop_desc) + break; + + /* prevent any other reads prior to eop_desc */ + smp_rmb(); + + /* if DD is not set pending work has not been completed */ + if (!(eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD))) + break; + + /* clear next_to_watch to prevent false hangs */ + tx_buffer->next_to_watch = NULL; + + /* update the statistics for this packet */ + total_bytes += tx_buffer->bytecount; + total_packets += tx_buffer->gso_segs; + if (tx_buffer->tx_flags & IXGBE_TX_FLAGS_IPSEC) + total_ipsec++; + + /* free the skb */ + if (ring_is_xdp(tx_ring)) + xdp_return_frame(tx_buffer->xdpf); + else + napi_consume_skb(tx_buffer->skb, napi_budget); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + + /* clear tx_buffer data */ + dma_unmap_len_set(tx_buffer, len, 0); + + /* unmap remaining buffers */ + while (tx_desc != eop_desc) { + tx_buffer++; + tx_desc++; + i++; + if (unlikely(!i)) { + i -= tx_ring->count; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = IXGBE_TX_DESC(tx_ring, 0); + } + + /* unmap any remaining paged data */ + if (dma_unmap_len(tx_buffer, len)) { + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + } + } + + /* move us one more past the eop_desc for start of next pkt */ + tx_buffer++; + tx_desc++; + i++; + if (unlikely(!i)) { + i -= tx_ring->count; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = IXGBE_TX_DESC(tx_ring, 0); + } + + /* issue prefetch for next Tx descriptor */ + prefetch(tx_desc); + + /* update budget accounting */ + budget--; + } while (likely(budget)); + + i += tx_ring->count; + tx_ring->next_to_clean = i; + u64_stats_update_begin(&tx_ring->syncp); + tx_ring->stats.bytes += total_bytes; + tx_ring->stats.packets += total_packets; + u64_stats_update_end(&tx_ring->syncp); + q_vector->tx.total_bytes += total_bytes; + q_vector->tx.total_packets += total_packets; + adapter->tx_ipsec += total_ipsec; + + if (check_for_tx_hang(tx_ring) && ixgbe_check_tx_hang(tx_ring)) { + /* schedule immediate reset if we believe we hung */ + struct ixgbe_hw *hw = &adapter->hw; + e_err(drv, "Detected Tx Unit Hang %s\n" + " Tx Queue <%d>\n" + " TDH, TDT <%x>, <%x>\n" + " next_to_use <%x>\n" + " next_to_clean <%x>\n" + "tx_buffer_info[next_to_clean]\n" + " time_stamp <%lx>\n" + " jiffies <%lx>\n", + ring_is_xdp(tx_ring) ? "(XDP)" : "", + tx_ring->queue_index, + IXGBE_READ_REG(hw, IXGBE_TDH(tx_ring->reg_idx)), + IXGBE_READ_REG(hw, IXGBE_TDT(tx_ring->reg_idx)), + tx_ring->next_to_use, i, + tx_ring->tx_buffer_info[i].time_stamp, jiffies); + + if (!ring_is_xdp(tx_ring)) + netif_stop_subqueue(tx_ring->netdev, + tx_ring->queue_index); + + e_info(probe, + "tx hang %d detected on queue %d, resetting adapter\n", + adapter->tx_timeout_count + 1, tx_ring->queue_index); + + /* schedule immediate reset if we believe we hung */ + ixgbe_tx_timeout_reset(adapter); + + /* the adapter is about to reset, no point in enabling stuff */ + return true; + } + + 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; + } + } + + return !!budget; +} + +#ifdef CONFIG_IXGBE_DCA +static void ixgbe_update_tx_dca(struct ixgbe_adapter *adapter, + struct ixgbe_ring *tx_ring, + int cpu) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 txctrl = 0; + u16 reg_offset; + + if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) + txctrl = dca3_get_tag(tx_ring->dev, cpu); + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + reg_offset = IXGBE_DCA_TXCTRL(tx_ring->reg_idx); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + reg_offset = IXGBE_DCA_TXCTRL_82599(tx_ring->reg_idx); + txctrl <<= IXGBE_DCA_TXCTRL_CPUID_SHIFT_82599; + break; + default: + /* for unknown hardware do not write register */ + return; + } + + /* + * We can enable relaxed ordering for reads, but not writes when + * DCA is enabled. This is due to a known issue in some chipsets + * which will cause the DCA tag to be cleared. + */ + txctrl |= IXGBE_DCA_TXCTRL_DESC_RRO_EN | + IXGBE_DCA_TXCTRL_DATA_RRO_EN | + IXGBE_DCA_TXCTRL_DESC_DCA_EN; + + IXGBE_WRITE_REG(hw, reg_offset, txctrl); +} + +static void ixgbe_update_rx_dca(struct ixgbe_adapter *adapter, + struct ixgbe_ring *rx_ring, + int cpu) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 rxctrl = 0; + u8 reg_idx = rx_ring->reg_idx; + + if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) + rxctrl = dca3_get_tag(rx_ring->dev, cpu); + + switch (hw->mac.type) { + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + rxctrl <<= IXGBE_DCA_RXCTRL_CPUID_SHIFT_82599; + break; + default: + break; + } + + /* + * We can enable relaxed ordering for reads, but not writes when + * DCA is enabled. This is due to a known issue in some chipsets + * which will cause the DCA tag to be cleared. + */ + rxctrl |= IXGBE_DCA_RXCTRL_DESC_RRO_EN | + IXGBE_DCA_RXCTRL_DATA_DCA_EN | + IXGBE_DCA_RXCTRL_DESC_DCA_EN; + + IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(reg_idx), rxctrl); +} + +static void ixgbe_update_dca(struct ixgbe_q_vector *q_vector) +{ + struct ixgbe_adapter *adapter = q_vector->adapter; + struct ixgbe_ring *ring; + int cpu = get_cpu(); + + if (q_vector->cpu == cpu) + goto out_no_update; + + ixgbe_for_each_ring(ring, q_vector->tx) + ixgbe_update_tx_dca(adapter, ring, cpu); + + ixgbe_for_each_ring(ring, q_vector->rx) + ixgbe_update_rx_dca(adapter, ring, cpu); + + q_vector->cpu = cpu; +out_no_update: + put_cpu(); +} + +static void ixgbe_setup_dca(struct ixgbe_adapter *adapter) +{ + int i; + + /* always use CB2 mode, difference is masked in the CB driver */ + if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) + IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL, + IXGBE_DCA_CTRL_DCA_MODE_CB2); + else + IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL, + IXGBE_DCA_CTRL_DCA_DISABLE); + + for (i = 0; i < adapter->num_q_vectors; i++) { + adapter->q_vector[i]->cpu = -1; + ixgbe_update_dca(adapter->q_vector[i]); + } +} + +static int __ixgbe_notify_dca(struct device *dev, void *data) +{ + struct ixgbe_adapter *adapter = dev_get_drvdata(dev); + unsigned long event = *(unsigned long *)data; + + if (!(adapter->flags & IXGBE_FLAG_DCA_CAPABLE)) + return 0; + + switch (event) { + case DCA_PROVIDER_ADD: + /* if we're already enabled, don't do it again */ + if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) + break; + if (dca_add_requester(dev) == 0) { + adapter->flags |= IXGBE_FLAG_DCA_ENABLED; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL, + IXGBE_DCA_CTRL_DCA_MODE_CB2); + break; + } + fallthrough; /* DCA is disabled. */ + case DCA_PROVIDER_REMOVE: + if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) { + dca_remove_requester(dev); + adapter->flags &= ~IXGBE_FLAG_DCA_ENABLED; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL, + IXGBE_DCA_CTRL_DCA_DISABLE); + } + break; + } + + return 0; +} + +#endif /* CONFIG_IXGBE_DCA */ + +#define IXGBE_RSS_L4_TYPES_MASK \ + ((1ul << IXGBE_RXDADV_RSSTYPE_IPV4_TCP) | \ + (1ul << IXGBE_RXDADV_RSSTYPE_IPV4_UDP) | \ + (1ul << IXGBE_RXDADV_RSSTYPE_IPV6_TCP) | \ + (1ul << IXGBE_RXDADV_RSSTYPE_IPV6_UDP)) + +static inline void ixgbe_rx_hash(struct ixgbe_ring *ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + u16 rss_type; + + if (!(ring->netdev->features & NETIF_F_RXHASH)) + return; + + rss_type = le16_to_cpu(rx_desc->wb.lower.lo_dword.hs_rss.pkt_info) & + IXGBE_RXDADV_RSSTYPE_MASK; + + if (!rss_type) + return; + + skb_set_hash(skb, le32_to_cpu(rx_desc->wb.lower.hi_dword.rss), + (IXGBE_RSS_L4_TYPES_MASK & (1ul << rss_type)) ? + PKT_HASH_TYPE_L4 : PKT_HASH_TYPE_L3); +} + +#ifdef IXGBE_FCOE +/** + * ixgbe_rx_is_fcoe - check the rx desc for incoming pkt type + * @ring: structure containing ring specific data + * @rx_desc: advanced rx descriptor + * + * Returns : true if it is FCoE pkt + */ +static inline bool ixgbe_rx_is_fcoe(struct ixgbe_ring *ring, + union ixgbe_adv_rx_desc *rx_desc) +{ + __le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info; + + return test_bit(__IXGBE_RX_FCOE, &ring->state) && + ((pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_ETQF_MASK)) == + (cpu_to_le16(IXGBE_ETQF_FILTER_FCOE << + IXGBE_RXDADV_PKTTYPE_ETQF_SHIFT))); +} + +#endif /* IXGBE_FCOE */ +/** + * ixgbe_rx_checksum - indicate in skb if hw indicated a good cksum + * @ring: structure containing ring specific data + * @rx_desc: current Rx descriptor being processed + * @skb: skb currently being received and modified + **/ +static inline void ixgbe_rx_checksum(struct ixgbe_ring *ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + __le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info; + bool encap_pkt = false; + + skb_checksum_none_assert(skb); + + /* Rx csum disabled */ + if (!(ring->netdev->features & NETIF_F_RXCSUM)) + return; + + /* check for VXLAN and Geneve packets */ + if (pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_VXLAN)) { + encap_pkt = true; + skb->encapsulation = 1; + } + + /* if IP and error */ + if (ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_IPCS) && + ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_IPE)) { + ring->rx_stats.csum_err++; + return; + } + + if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_L4CS)) + return; + + if (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_TCPE)) { + /* + * 82599 errata, UDP frames with a 0 checksum can be marked as + * checksum errors. + */ + if ((pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_UDP)) && + test_bit(__IXGBE_RX_CSUM_UDP_ZERO_ERR, &ring->state)) + return; + + ring->rx_stats.csum_err++; + return; + } + + /* It must be a TCP or UDP packet with a valid checksum */ + skb->ip_summed = CHECKSUM_UNNECESSARY; + if (encap_pkt) { + if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_OUTERIPCS)) + return; + + if (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_OUTERIPER)) { + skb->ip_summed = CHECKSUM_NONE; + return; + } + /* If we checked the outer header let the stack know */ + skb->csum_level = 1; + } +} + +static inline unsigned int ixgbe_rx_offset(struct ixgbe_ring *rx_ring) +{ + return ring_uses_build_skb(rx_ring) ? IXGBE_SKB_PAD : 0; +} + +static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *bi) +{ + struct page *page = bi->page; + dma_addr_t dma; + + /* since we are recycling buffers we should seldom need to alloc */ + if (likely(page)) + return true; + + /* alloc new page for storage */ + page = dev_alloc_pages(ixgbe_rx_pg_order(rx_ring)); + if (unlikely(!page)) { + rx_ring->rx_stats.alloc_rx_page_failed++; + return false; + } + + /* map page for use */ + dma = dma_map_page_attrs(rx_ring->dev, page, 0, + ixgbe_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IXGBE_RX_DMA_ATTR); + + /* + * if mapping failed free memory back to system since + * there isn't much point in holding memory we can't use + */ + if (dma_mapping_error(rx_ring->dev, dma)) { + __free_pages(page, ixgbe_rx_pg_order(rx_ring)); + + rx_ring->rx_stats.alloc_rx_page_failed++; + return false; + } + + bi->dma = dma; + bi->page = page; + bi->page_offset = ixgbe_rx_offset(rx_ring); + page_ref_add(page, USHRT_MAX - 1); + bi->pagecnt_bias = USHRT_MAX; + rx_ring->rx_stats.alloc_rx_page++; + + return true; +} + +/** + * ixgbe_alloc_rx_buffers - Replace used receive buffers + * @rx_ring: ring to place buffers on + * @cleaned_count: number of buffers to replace + **/ +void ixgbe_alloc_rx_buffers(struct ixgbe_ring *rx_ring, u16 cleaned_count) +{ + union ixgbe_adv_rx_desc *rx_desc; + struct ixgbe_rx_buffer *bi; + u16 i = rx_ring->next_to_use; + u16 bufsz; + + /* nothing to do */ + if (!cleaned_count) + return; + + rx_desc = IXGBE_RX_DESC(rx_ring, i); + bi = &rx_ring->rx_buffer_info[i]; + i -= rx_ring->count; + + bufsz = ixgbe_rx_bufsz(rx_ring); + + do { + if (!ixgbe_alloc_mapped_page(rx_ring, bi)) + break; + + /* sync the buffer for use by the device */ + dma_sync_single_range_for_device(rx_ring->dev, bi->dma, + bi->page_offset, bufsz, + DMA_FROM_DEVICE); + + /* + * Refresh the desc even if buffer_addrs didn't change + * because each write-back erases this info. + */ + rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset); + + rx_desc++; + bi++; + i++; + if (unlikely(!i)) { + rx_desc = IXGBE_RX_DESC(rx_ring, 0); + bi = rx_ring->rx_buffer_info; + i -= rx_ring->count; + } + + /* clear the length for the next_to_use descriptor */ + rx_desc->wb.upper.length = 0; + + cleaned_count--; + } while (cleaned_count); + + i += rx_ring->count; + + if (rx_ring->next_to_use != i) { + rx_ring->next_to_use = i; + + /* update next to alloc since we have filled the ring */ + rx_ring->next_to_alloc = i; + + /* 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(); + writel(i, rx_ring->tail); + } +} + +static void ixgbe_set_rsc_gso_size(struct ixgbe_ring *ring, + struct sk_buff *skb) +{ + u16 hdr_len = skb_headlen(skb); + + /* set gso_size to avoid messing up TCP MSS */ + skb_shinfo(skb)->gso_size = DIV_ROUND_UP((skb->len - hdr_len), + IXGBE_CB(skb)->append_cnt); + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; +} + +static void ixgbe_update_rsc_stats(struct ixgbe_ring *rx_ring, + struct sk_buff *skb) +{ + /* if append_cnt is 0 then frame is not RSC */ + if (!IXGBE_CB(skb)->append_cnt) + return; + + rx_ring->rx_stats.rsc_count += IXGBE_CB(skb)->append_cnt; + rx_ring->rx_stats.rsc_flush++; + + ixgbe_set_rsc_gso_size(rx_ring, skb); + + /* gso_size is computed using append_cnt so always clear it last */ + IXGBE_CB(skb)->append_cnt = 0; +} + +/** + * ixgbe_process_skb_fields - Populate skb header fields from Rx descriptor + * @rx_ring: rx descriptor ring packet is being transacted on + * @rx_desc: pointer to the EOP Rx descriptor + * @skb: pointer to current skb being populated + * + * This function checks the ring, descriptor, and packet information in + * order to populate the hash, checksum, VLAN, timestamp, protocol, and + * other fields within the skb. + **/ +void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + struct net_device *dev = rx_ring->netdev; + u32 flags = rx_ring->q_vector->adapter->flags; + + ixgbe_update_rsc_stats(rx_ring, skb); + + ixgbe_rx_hash(rx_ring, rx_desc, skb); + + ixgbe_rx_checksum(rx_ring, rx_desc, skb); + + if (unlikely(flags & IXGBE_FLAG_RX_HWTSTAMP_ENABLED)) + ixgbe_ptp_rx_hwtstamp(rx_ring, rx_desc, skb); + + if ((dev->features & NETIF_F_HW_VLAN_CTAG_RX) && + ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_VP)) { + u16 vid = le16_to_cpu(rx_desc->wb.upper.vlan); + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid); + } + + if (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_STAT_SECP)) + ixgbe_ipsec_rx(rx_ring, rx_desc, skb); + + /* record Rx queue, or update MACVLAN statistics */ + if (netif_is_ixgbe(dev)) + skb_record_rx_queue(skb, rx_ring->queue_index); + else + macvlan_count_rx(netdev_priv(dev), skb->len + ETH_HLEN, true, + false); + + skb->protocol = eth_type_trans(skb, dev); +} + +void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector, + struct sk_buff *skb) +{ + napi_gro_receive(&q_vector->napi, skb); +} + +/** + * ixgbe_is_non_eop - process handling of non-EOP buffers + * @rx_ring: Rx ring being processed + * @rx_desc: Rx descriptor for current buffer + * @skb: Current socket buffer containing buffer in progress + * + * This function updates next to clean. If the buffer is an EOP buffer + * this function exits returning false, otherwise it will place the + * sk_buff in the next buffer to be chained and return true indicating + * that this is in fact a non-EOP buffer. + **/ +static bool ixgbe_is_non_eop(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + u32 ntc = rx_ring->next_to_clean + 1; + + /* fetch, update, and store next to clean */ + ntc = (ntc < rx_ring->count) ? ntc : 0; + rx_ring->next_to_clean = ntc; + + prefetch(IXGBE_RX_DESC(rx_ring, ntc)); + + /* update RSC append count if present */ + if (ring_is_rsc_enabled(rx_ring)) { + __le32 rsc_enabled = rx_desc->wb.lower.lo_dword.data & + cpu_to_le32(IXGBE_RXDADV_RSCCNT_MASK); + + if (unlikely(rsc_enabled)) { + u32 rsc_cnt = le32_to_cpu(rsc_enabled); + + rsc_cnt >>= IXGBE_RXDADV_RSCCNT_SHIFT; + IXGBE_CB(skb)->append_cnt += rsc_cnt - 1; + + /* update ntc based on RSC value */ + ntc = le32_to_cpu(rx_desc->wb.upper.status_error); + ntc &= IXGBE_RXDADV_NEXTP_MASK; + ntc >>= IXGBE_RXDADV_NEXTP_SHIFT; + } + } + + /* if we are the last buffer then there is nothing else to do */ + if (likely(ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))) + return false; + + /* place skb in next buffer to be received */ + rx_ring->rx_buffer_info[ntc].skb = skb; + rx_ring->rx_stats.non_eop_descs++; + + return true; +} + +/** + * ixgbe_pull_tail - ixgbe specific version of skb_pull_tail + * @rx_ring: rx descriptor ring packet is being transacted on + * @skb: pointer to current skb being adjusted + * + * This function is an ixgbe specific version of __pskb_pull_tail. The + * main difference between this version and the original function is that + * this function can make several assumptions about the state of things + * that allow for significant optimizations versus the standard function. + * As a result we can do things like drop a frag and maintain an accurate + * truesize for the skb. + */ +static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring, + struct sk_buff *skb) +{ + skb_frag_t *frag = &skb_shinfo(skb)->frags[0]; + unsigned char *va; + unsigned int pull_len; + + /* + * it is valid to use page_address instead of kmap since we are + * working with pages allocated out of the lomem pool per + * alloc_page(GFP_ATOMIC) + */ + va = skb_frag_address(frag); + + /* + * we need the header to contain the greater of either ETH_HLEN or + * 60 bytes if the skb->len is less than 60 for skb_pad. + */ + pull_len = eth_get_headlen(skb->dev, va, IXGBE_RX_HDR_SIZE); + + /* align pull length to size of long to optimize memcpy performance */ + skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long))); + + /* update all of the pointers */ + skb_frag_size_sub(frag, pull_len); + skb_frag_off_add(frag, pull_len); + skb->data_len -= pull_len; + skb->tail += pull_len; +} + +/** + * ixgbe_dma_sync_frag - perform DMA sync for first frag of SKB + * @rx_ring: rx descriptor ring packet is being transacted on + * @skb: pointer to current skb being updated + * + * This function provides a basic DMA sync up for the first fragment of an + * skb. The reason for doing this is that the first fragment cannot be + * unmapped until we have reached the end of packet descriptor for a buffer + * chain. + */ +static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring, + struct sk_buff *skb) +{ + if (ring_uses_build_skb(rx_ring)) { + unsigned long mask = (unsigned long)ixgbe_rx_pg_size(rx_ring) - 1; + unsigned long offset = (unsigned long)(skb->data) & mask; + + dma_sync_single_range_for_cpu(rx_ring->dev, + IXGBE_CB(skb)->dma, + offset, + skb_headlen(skb), + DMA_FROM_DEVICE); + } else { + skb_frag_t *frag = &skb_shinfo(skb)->frags[0]; + + dma_sync_single_range_for_cpu(rx_ring->dev, + IXGBE_CB(skb)->dma, + skb_frag_off(frag), + skb_frag_size(frag), + DMA_FROM_DEVICE); + } + + /* If the page was released, just unmap it. */ + if (unlikely(IXGBE_CB(skb)->page_released)) { + dma_unmap_page_attrs(rx_ring->dev, IXGBE_CB(skb)->dma, + ixgbe_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IXGBE_RX_DMA_ATTR); + } +} + +/** + * ixgbe_cleanup_headers - Correct corrupted or empty headers + * @rx_ring: rx descriptor ring packet is being transacted on + * @rx_desc: pointer to the EOP Rx descriptor + * @skb: pointer to current skb being fixed + * + * Check if the skb is valid in the XDP case it will be an error pointer. + * Return true in this case to abort processing and advance to next + * descriptor. + * + * Check for corrupted packet headers caused by senders on the local L2 + * embedded NIC switch not setting up their Tx Descriptors right. These + * should be very rare. + * + * Also address the case where we are pulling data in on pages only + * and as such no data is present in the skb header. + * + * In addition if skb is not at least 60 bytes we need to pad it so that + * it is large enough to qualify as a valid Ethernet frame. + * + * Returns true if an error was encountered and skb was freed. + **/ +bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + struct net_device *netdev = rx_ring->netdev; + + /* XDP packets use error pointer so abort at this point */ + if (IS_ERR(skb)) + return true; + + /* Verify netdev is present, and that packet does not have any + * errors that would be unacceptable to the netdev. + */ + if (!netdev || + (unlikely(ixgbe_test_staterr(rx_desc, + IXGBE_RXDADV_ERR_FRAME_ERR_MASK) && + !(netdev->features & NETIF_F_RXALL)))) { + dev_kfree_skb_any(skb); + return true; + } + + /* place header in linear portion of buffer */ + if (!skb_headlen(skb)) + ixgbe_pull_tail(rx_ring, skb); + +#ifdef IXGBE_FCOE + /* do not attempt to pad FCoE Frames as this will disrupt DDP */ + if (ixgbe_rx_is_fcoe(rx_ring, rx_desc)) + return false; + +#endif + /* if eth_skb_pad returns an error the skb was freed */ + if (eth_skb_pad(skb)) + return true; + + return false; +} + +/** + * ixgbe_reuse_rx_page - page flip buffer and store it back on the ring + * @rx_ring: rx descriptor ring to store buffers on + * @old_buff: donor buffer to have page reused + * + * Synchronizes page for reuse by the adapter + **/ +static void ixgbe_reuse_rx_page(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *old_buff) +{ + struct ixgbe_rx_buffer *new_buff; + u16 nta = rx_ring->next_to_alloc; + + new_buff = &rx_ring->rx_buffer_info[nta]; + + /* update, and store next to alloc */ + nta++; + rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; + + /* Transfer page from old buffer to new buffer. + * Move each member individually to avoid possible store + * forwarding stalls and unnecessary copy of skb. + */ + new_buff->dma = old_buff->dma; + new_buff->page = old_buff->page; + new_buff->page_offset = old_buff->page_offset; + new_buff->pagecnt_bias = old_buff->pagecnt_bias; +} + +static inline bool ixgbe_page_is_reserved(struct page *page) +{ + return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); +} + +static bool ixgbe_can_reuse_rx_page(struct ixgbe_rx_buffer *rx_buffer, + int rx_buffer_pgcnt) +{ + unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; + struct page *page = rx_buffer->page; + + /* avoid re-using remote pages */ + if (unlikely(ixgbe_page_is_reserved(page))) + return false; + +#if (PAGE_SIZE < 8192) + /* if we are only owner of page we can reuse it */ + if (unlikely((rx_buffer_pgcnt - pagecnt_bias) > 1)) + return false; +#else + /* The last offset is a bit aggressive in that we assume the + * worst case of FCoE being enabled and using a 3K buffer. + * However this should have minimal impact as the 1K extra is + * still less than one buffer in size. + */ +#define IXGBE_LAST_OFFSET \ + (SKB_WITH_OVERHEAD(PAGE_SIZE) - IXGBE_RXBUFFER_3K) + if (rx_buffer->page_offset > IXGBE_LAST_OFFSET) + return false; +#endif + + /* If we have drained the page fragment pool we need to update + * the pagecnt_bias and page count so that we fully restock the + * number of references the driver holds. + */ + if (unlikely(pagecnt_bias == 1)) { + page_ref_add(page, USHRT_MAX - 1); + rx_buffer->pagecnt_bias = USHRT_MAX; + } + + return true; +} + +/** + * ixgbe_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: size of data in rx_buffer + * + * This function will add the data contained in rx_buffer->page to the skb. + * This is done either through a direct copy if the data in the buffer is + * less than the skb header size, otherwise it will just attach the page as + * a frag to the skb. + * + * The function will then update the page offset if necessary and return + * true if the buffer can be reused by the adapter. + **/ +static void ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *rx_buffer, + struct sk_buff *skb, + unsigned int size) +{ +#if (PAGE_SIZE < 8192) + unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = ring_uses_build_skb(rx_ring) ? + SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) : + SKB_DATA_ALIGN(size); +#endif + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, + rx_buffer->page_offset, size, truesize); +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif +} + +static struct ixgbe_rx_buffer *ixgbe_get_rx_buffer(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff **skb, + const unsigned int size, + int *rx_buffer_pgcnt) +{ + struct ixgbe_rx_buffer *rx_buffer; + + rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + *rx_buffer_pgcnt = +#if (PAGE_SIZE < 8192) + page_count(rx_buffer->page); +#else + 0; +#endif + prefetchw(rx_buffer->page); + *skb = rx_buffer->skb; + + /* Delay unmapping of the first packet. It carries the header + * information, HW may still access the header after the writeback. + * Only unmap it when EOP is reached + */ + if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)) { + if (!*skb) + goto skip_sync; + } else { + if (*skb) + ixgbe_dma_sync_frag(rx_ring, *skb); + } + + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + size, + DMA_FROM_DEVICE); +skip_sync: + rx_buffer->pagecnt_bias--; + + return rx_buffer; +} + +static void ixgbe_put_rx_buffer(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *rx_buffer, + struct sk_buff *skb, + int rx_buffer_pgcnt) +{ + if (ixgbe_can_reuse_rx_page(rx_buffer, rx_buffer_pgcnt)) { + /* hand second half of page back to the ring */ + ixgbe_reuse_rx_page(rx_ring, rx_buffer); + } else { + if (!IS_ERR(skb) && IXGBE_CB(skb)->dma == rx_buffer->dma) { + /* the page has been released from the ring */ + IXGBE_CB(skb)->page_released = true; + } else { + /* we are not reusing the buffer so unmap it */ + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, + ixgbe_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IXGBE_RX_DMA_ATTR); + } + __page_frag_cache_drain(rx_buffer->page, + rx_buffer->pagecnt_bias); + } + + /* clear contents of rx_buffer */ + rx_buffer->page = NULL; + rx_buffer->skb = NULL; +} + +static struct sk_buff *ixgbe_construct_skb(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *rx_buffer, + struct xdp_buff *xdp, + union ixgbe_adv_rx_desc *rx_desc) +{ + unsigned int size = xdp->data_end - xdp->data; +#if (PAGE_SIZE < 8192) + unsigned int truesize = ixgbe_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(xdp->data_end - + xdp->data_hard_start); +#endif + struct sk_buff *skb; + + /* prefetch first cache line of first page */ + net_prefetch(xdp->data); + + /* Note, we get here by enabling legacy-rx via: + * + * ethtool --set-priv-flags <dev> legacy-rx on + * + * In this mode, we currently get 0 extra XDP headroom as + * opposed to having legacy-rx off, where we process XDP + * packets going to stack via ixgbe_build_skb(). The latter + * provides us currently with 192 bytes of headroom. + * + * For ixgbe_construct_skb() mode it means that the + * xdp->data_meta will always point to xdp->data, since + * the helper cannot expand the head. Should this ever + * change in future for legacy-rx mode on, then lets also + * add xdp->data_meta handling here. + */ + + /* allocate a skb to store the frags */ + skb = napi_alloc_skb(&rx_ring->q_vector->napi, IXGBE_RX_HDR_SIZE); + if (unlikely(!skb)) + return NULL; + + if (size > IXGBE_RX_HDR_SIZE) { + if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)) + IXGBE_CB(skb)->dma = rx_buffer->dma; + + skb_add_rx_frag(skb, 0, rx_buffer->page, + xdp->data - page_address(rx_buffer->page), + size, truesize); +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif + } else { + memcpy(__skb_put(skb, size), + xdp->data, ALIGN(size, sizeof(long))); + rx_buffer->pagecnt_bias++; + } + + return skb; +} + +static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *rx_buffer, + struct xdp_buff *xdp, + union ixgbe_adv_rx_desc *rx_desc) +{ + unsigned int metasize = xdp->data - xdp->data_meta; +#if (PAGE_SIZE < 8192) + unsigned int truesize = ixgbe_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 + * is unused, this points extactly as xdp->data, otherwise we + * likely have a consumer accessing first few bytes of meta + * data, and then actual data. + */ + net_prefetch(xdp->data_meta); + + /* build an skb to around the page buffer */ + skb = build_skb(xdp->data_hard_start, truesize); + if (unlikely(!skb)) + return NULL; + + /* update pointers within the skb to store the data */ + skb_reserve(skb, xdp->data - xdp->data_hard_start); + __skb_put(skb, xdp->data_end - xdp->data); + if (metasize) + skb_metadata_set(skb, metasize); + + /* record DMA address if this is the start of a chain of buffers */ + if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)) + IXGBE_CB(skb)->dma = rx_buffer->dma; + + /* update buffer offset */ +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif + + return skb; +} + +static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, + struct ixgbe_ring *rx_ring, + struct xdp_buff *xdp) +{ + int err, result = IXGBE_XDP_PASS; + struct bpf_prog *xdp_prog; + struct xdp_frame *xdpf; + u32 act; + + rcu_read_lock(); + xdp_prog = READ_ONCE(rx_ring->xdp_prog); + + if (!xdp_prog) + goto xdp_out; + + prefetchw(xdp->data_hard_start); /* xdp_frame write */ + + act = bpf_prog_run_xdp(xdp_prog, xdp); + switch (act) { + case XDP_PASS: + break; + case XDP_TX: + xdpf = xdp_convert_buff_to_frame(xdp); + if (unlikely(!xdpf)) + goto out_failure; + result = ixgbe_xmit_xdp_ring(adapter, xdpf); + if (result == IXGBE_XDP_CONSUMED) + goto out_failure; + break; + case XDP_REDIRECT: + err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog); + if (err) + goto out_failure; + result = IXGBE_XDP_REDIR; + break; + default: + bpf_warn_invalid_xdp_action(act); + fallthrough; + case XDP_ABORTED: +out_failure: + trace_xdp_exception(rx_ring->netdev, xdp_prog, act); + fallthrough; /* handle aborts by dropping packet */ + case XDP_DROP: + result = IXGBE_XDP_CONSUMED; + break; + } +xdp_out: + rcu_read_unlock(); + return ERR_PTR(-result); +} + +static unsigned int ixgbe_rx_frame_truesize(struct ixgbe_ring *rx_ring, + unsigned int size) +{ + unsigned int truesize; + +#if (PAGE_SIZE < 8192) + truesize = ixgbe_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */ +#else + truesize = ring_uses_build_skb(rx_ring) ? + SKB_DATA_ALIGN(IXGBE_SKB_PAD + size) + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) : + SKB_DATA_ALIGN(size); +#endif + return truesize; +} + +static void ixgbe_rx_buffer_flip(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *rx_buffer, + unsigned int size) +{ + unsigned int truesize = ixgbe_rx_frame_truesize(rx_ring, size); +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif +} + +/** + * ixgbe_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf + * @q_vector: structure containing interrupt and ring information + * @rx_ring: rx descriptor ring to transact packets on + * @budget: Total limit on number of packets to process + * + * This function provides a "bounce buffer" approach to Rx interrupt + * processing. The advantage to this is that on systems that have + * expensive overhead for IOMMU access this provides a means of avoiding + * it by maintaining the mapping of the page to the syste. + * + * Returns amount of work completed + **/ +static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, + struct ixgbe_ring *rx_ring, + const int budget) +{ + unsigned int total_rx_bytes = 0, total_rx_packets = 0; + struct ixgbe_adapter *adapter = q_vector->adapter; +#ifdef IXGBE_FCOE + int ddp_bytes; + unsigned int mss = 0; +#endif /* IXGBE_FCOE */ + u16 cleaned_count = ixgbe_desc_unused(rx_ring); + unsigned int xdp_xmit = 0; + struct xdp_buff xdp; + + xdp.rxq = &rx_ring->xdp_rxq; + + /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ +#if (PAGE_SIZE < 8192) + xdp.frame_sz = ixgbe_rx_frame_truesize(rx_ring, 0); +#endif + + while (likely(total_rx_packets < budget)) { + union ixgbe_adv_rx_desc *rx_desc; + struct ixgbe_rx_buffer *rx_buffer; + struct sk_buff *skb; + int rx_buffer_pgcnt; + unsigned int size; + + /* return some buffers to hardware, one at a time is too slow */ + if (cleaned_count >= IXGBE_RX_BUFFER_WRITE) { + ixgbe_alloc_rx_buffers(rx_ring, cleaned_count); + cleaned_count = 0; + } + + rx_desc = IXGBE_RX_DESC(rx_ring, rx_ring->next_to_clean); + size = le16_to_cpu(rx_desc->wb.upper.length); + if (!size) + break; + + /* This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc until we know the + * descriptor has been written back + */ + dma_rmb(); + + rx_buffer = ixgbe_get_rx_buffer(rx_ring, rx_desc, &skb, size, &rx_buffer_pgcnt); + + /* retrieve a buffer from the ring */ + if (!skb) { + xdp.data = page_address(rx_buffer->page) + + rx_buffer->page_offset; + xdp.data_meta = xdp.data; + xdp.data_hard_start = xdp.data - + ixgbe_rx_offset(rx_ring); + xdp.data_end = xdp.data + size; +#if (PAGE_SIZE > 4096) + /* At larger PAGE_SIZE, frame_sz depend on len size */ + xdp.frame_sz = ixgbe_rx_frame_truesize(rx_ring, size); +#endif + skb = ixgbe_run_xdp(adapter, rx_ring, &xdp); + } + + if (IS_ERR(skb)) { + unsigned int xdp_res = -PTR_ERR(skb); + + if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) { + xdp_xmit |= xdp_res; + ixgbe_rx_buffer_flip(rx_ring, rx_buffer, size); + } else { + rx_buffer->pagecnt_bias++; + } + total_rx_packets++; + total_rx_bytes += size; + } else if (skb) { + ixgbe_add_rx_frag(rx_ring, rx_buffer, skb, size); + } else if (ring_uses_build_skb(rx_ring)) { + skb = ixgbe_build_skb(rx_ring, rx_buffer, + &xdp, rx_desc); + } else { + skb = ixgbe_construct_skb(rx_ring, rx_buffer, + &xdp, rx_desc); + } + + /* exit if we failed to retrieve a buffer */ + if (!skb) { + rx_ring->rx_stats.alloc_rx_buff_failed++; + rx_buffer->pagecnt_bias++; + break; + } + + ixgbe_put_rx_buffer(rx_ring, rx_buffer, skb, rx_buffer_pgcnt); + cleaned_count++; + + /* place incomplete frames back on ring for completion */ + if (ixgbe_is_non_eop(rx_ring, rx_desc, skb)) + continue; + + /* verify the packet layout is correct */ + if (ixgbe_cleanup_headers(rx_ring, rx_desc, skb)) + continue; + + /* probably a little skewed due to removing CRC */ + total_rx_bytes += skb->len; + + /* populate checksum, timestamp, VLAN, and protocol */ + ixgbe_process_skb_fields(rx_ring, rx_desc, skb); + +#ifdef IXGBE_FCOE + /* if ddp, not passing to ULD unless for FCP_RSP or error */ + if (ixgbe_rx_is_fcoe(rx_ring, rx_desc)) { + ddp_bytes = ixgbe_fcoe_ddp(adapter, rx_desc, skb); + /* include DDPed FCoE data */ + if (ddp_bytes > 0) { + if (!mss) { + mss = rx_ring->netdev->mtu - + sizeof(struct fcoe_hdr) - + sizeof(struct fc_frame_header) - + sizeof(struct fcoe_crc_eof); + if (mss > 512) + mss &= ~511; + } + total_rx_bytes += ddp_bytes; + total_rx_packets += DIV_ROUND_UP(ddp_bytes, + mss); + } + if (!ddp_bytes) { + dev_kfree_skb_any(skb); + continue; + } + } + +#endif /* IXGBE_FCOE */ + ixgbe_rx_skb(q_vector, skb); + + /* update budget accounting */ + total_rx_packets++; + } + + if (xdp_xmit & IXGBE_XDP_REDIR) + xdp_do_flush_map(); + + if (xdp_xmit & IXGBE_XDP_TX) { + struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()]; + + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. + */ + wmb(); + writel(ring->next_to_use, ring->tail); + } + + u64_stats_update_begin(&rx_ring->syncp); + rx_ring->stats.packets += total_rx_packets; + rx_ring->stats.bytes += total_rx_bytes; + u64_stats_update_end(&rx_ring->syncp); + q_vector->rx.total_packets += total_rx_packets; + q_vector->rx.total_bytes += total_rx_bytes; + + return total_rx_packets; +} + +/** + * ixgbe_configure_msix - Configure MSI-X hardware + * @adapter: board private structure + * + * ixgbe_configure_msix sets up the hardware to properly generate MSI-X + * interrupts. + **/ +static void ixgbe_configure_msix(struct ixgbe_adapter *adapter) +{ + struct ixgbe_q_vector *q_vector; + int v_idx; + u32 mask; + + /* Populate MSIX to EITR Select */ + if (adapter->num_vfs > 32) { + u32 eitrsel = BIT(adapter->num_vfs - 32) - 1; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EITRSEL, eitrsel); + } + + /* + * Populate the IVAR table and set the ITR values to the + * corresponding register. + */ + for (v_idx = 0; v_idx < adapter->num_q_vectors; v_idx++) { + struct ixgbe_ring *ring; + q_vector = adapter->q_vector[v_idx]; + + ixgbe_for_each_ring(ring, q_vector->rx) + ixgbe_set_ivar(adapter, 0, ring->reg_idx, v_idx); + + ixgbe_for_each_ring(ring, q_vector->tx) + ixgbe_set_ivar(adapter, 1, ring->reg_idx, v_idx); + + ixgbe_write_eitr(q_vector); + } + + switch (adapter->hw.mac.type) { + case ixgbe_mac_82598EB: + ixgbe_set_ivar(adapter, -1, IXGBE_IVAR_OTHER_CAUSES_INDEX, + v_idx); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + ixgbe_set_ivar(adapter, -1, 1, v_idx); + break; + default: + break; + } + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EITR(v_idx), 1950); + + /* set up to autoclear timer, and the vectors */ + mask = IXGBE_EIMS_ENABLE_MASK; + mask &= ~(IXGBE_EIMS_OTHER | + IXGBE_EIMS_MAILBOX | + IXGBE_EIMS_LSC); + + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIAC, mask); +} + +/** + * ixgbe_update_itr - update the dynamic ITR value based on statistics + * @q_vector: structure containing interrupt and ring information + * @ring_container: structure containing ring performance data + * + * Stores a new ITR value based on packets and byte + * counts during the last interrupt. The advantage of per interrupt + * computation is faster updates and more accurate ITR for the current + * traffic pattern. Constants in this function were computed + * based on theoretical maximum wire speed and thresholds were set based + * on testing data as well as attempting to minimize response time + * while increasing bulk throughput. + **/ +static void ixgbe_update_itr(struct ixgbe_q_vector *q_vector, + struct ixgbe_ring_container *ring_container) +{ + unsigned int itr = IXGBE_ITR_ADAPTIVE_MIN_USECS | + IXGBE_ITR_ADAPTIVE_LATENCY; + unsigned int avg_wire_size, packets, bytes; + unsigned long next_update = jiffies; + + /* If we don't have any rings just leave ourselves set for maximum + * possible latency so we take ourselves out of the equation. + */ + if (!ring_container->ring) + return; + + /* If we didn't update within up to 1 - 2 jiffies we can assume + * that either packets are coming in so slow there hasn't been + * any work, or that there is so much work that NAPI is dealing + * with interrupt moderation and we don't need to do anything. + */ + if (time_after(next_update, ring_container->next_update)) + goto clear_counts; + + packets = ring_container->total_packets; + + /* We have no packets to actually measure against. This means + * either one of the other queues on this vector is active or + * we are a Tx queue doing TSO with too high of an interrupt rate. + * + * When this occurs just tick up our delay by the minimum value + * and hope that this extra delay will prevent us from being called + * without any work on our queue. + */ + if (!packets) { + itr = (q_vector->itr >> 2) + IXGBE_ITR_ADAPTIVE_MIN_INC; + if (itr > IXGBE_ITR_ADAPTIVE_MAX_USECS) + itr = IXGBE_ITR_ADAPTIVE_MAX_USECS; + itr += ring_container->itr & IXGBE_ITR_ADAPTIVE_LATENCY; + goto clear_counts; + } + + bytes = ring_container->total_bytes; + + /* If packets are less than 4 or bytes are less than 9000 assume + * insufficient data to use bulk rate limiting approach. We are + * likely latency driven. + */ + if (packets < 4 && bytes < 9000) { + itr = IXGBE_ITR_ADAPTIVE_LATENCY; + goto adjust_by_size; + } + + /* Between 4 and 48 we can assume that our current interrupt delay + * is only slightly too low. As such we should increase it by a small + * fixed amount. + */ + if (packets < 48) { + itr = (q_vector->itr >> 2) + IXGBE_ITR_ADAPTIVE_MIN_INC; + if (itr > IXGBE_ITR_ADAPTIVE_MAX_USECS) + itr = IXGBE_ITR_ADAPTIVE_MAX_USECS; + goto clear_counts; + } + + /* Between 48 and 96 is our "goldilocks" zone where we are working + * out "just right". Just report that our current ITR is good for us. + */ + if (packets < 96) { + itr = q_vector->itr >> 2; + goto clear_counts; + } + + /* If packet count is 96 or greater we are likely looking at a slight + * overrun of the delay we want. Try halving our delay to see if that + * will cut the number of packets in half per interrupt. + */ + if (packets < 256) { + itr = q_vector->itr >> 3; + if (itr < IXGBE_ITR_ADAPTIVE_MIN_USECS) + itr = IXGBE_ITR_ADAPTIVE_MIN_USECS; + goto clear_counts; + } + + /* The paths below assume we are dealing with a bulk ITR since number + * of packets is 256 or greater. We are just going to have to compute + * a value and try to bring the count under control, though for smaller + * packet sizes there isn't much we can do as NAPI polling will likely + * be kicking in sooner rather than later. + */ + itr = IXGBE_ITR_ADAPTIVE_BULK; + +adjust_by_size: + /* If packet counts are 256 or greater we can assume we have a gross + * overestimation of what the rate should be. Instead of trying to fine + * tune it just use the formula below to try and dial in an exact value + * give the current packet size of the frame. + */ + avg_wire_size = bytes / packets; + + /* The following is a crude approximation of: + * wmem_default / (size + overhead) = desired_pkts_per_int + * rate / bits_per_byte / (size + ethernet overhead) = pkt_rate + * (desired_pkt_rate / pkt_rate) * usecs_per_sec = ITR value + * + * Assuming wmem_default is 212992 and overhead is 640 bytes per + * packet, (256 skb, 64 headroom, 320 shared info), we can reduce the + * formula down to + * + * (170 * (size + 24)) / (size + 640) = ITR + * + * We first do some math on the packet size and then finally bitshift + * by 8 after rounding up. We also have to account for PCIe link speed + * difference as ITR scales based on this. + */ + if (avg_wire_size <= 60) { + /* Start at 50k ints/sec */ + avg_wire_size = 5120; + } else if (avg_wire_size <= 316) { + /* 50K ints/sec to 16K ints/sec */ + avg_wire_size *= 40; + avg_wire_size += 2720; + } else if (avg_wire_size <= 1084) { + /* 16K ints/sec to 9.2K ints/sec */ + avg_wire_size *= 15; + avg_wire_size += 11452; + } else if (avg_wire_size < 1968) { + /* 9.2K ints/sec to 8K ints/sec */ + avg_wire_size *= 5; + avg_wire_size += 22420; + } else { + /* plateau at a limit of 8K ints/sec */ + avg_wire_size = 32256; + } + + /* If we are in low latency mode half our delay which doubles the rate + * to somewhere between 100K to 16K ints/sec + */ + if (itr & IXGBE_ITR_ADAPTIVE_LATENCY) + avg_wire_size >>= 1; + + /* Resultant value is 256 times larger than it needs to be. This + * gives us room to adjust the value as needed to either increase + * or decrease the value based on link speeds of 10G, 2.5G, 1G, etc. + * + * Use addition as we have already recorded the new latency flag + * for the ITR value. + */ + switch (q_vector->adapter->link_speed) { + case IXGBE_LINK_SPEED_10GB_FULL: + case IXGBE_LINK_SPEED_100_FULL: + default: + itr += DIV_ROUND_UP(avg_wire_size, + IXGBE_ITR_ADAPTIVE_MIN_INC * 256) * + IXGBE_ITR_ADAPTIVE_MIN_INC; + break; + case IXGBE_LINK_SPEED_2_5GB_FULL: + case IXGBE_LINK_SPEED_1GB_FULL: + case IXGBE_LINK_SPEED_10_FULL: + if (avg_wire_size > 8064) + avg_wire_size = 8064; + itr += DIV_ROUND_UP(avg_wire_size, + IXGBE_ITR_ADAPTIVE_MIN_INC * 64) * + IXGBE_ITR_ADAPTIVE_MIN_INC; + break; + } + +clear_counts: + /* write back value */ + ring_container->itr = itr; + + /* next update should occur within next jiffy */ + ring_container->next_update = next_update + 1; + + ring_container->total_bytes = 0; + ring_container->total_packets = 0; +} + +/** + * ixgbe_write_eitr - write EITR register in hardware specific way + * @q_vector: structure containing interrupt and ring information + * + * This function is made to be called by ethtool and by the driver + * when it needs to update EITR registers at runtime. Hardware + * specific quirks/differences are taken care of here. + */ +void ixgbe_write_eitr(struct ixgbe_q_vector *q_vector) +{ + struct ixgbe_adapter *adapter = q_vector->adapter; + struct ixgbe_hw *hw = &adapter->hw; + int v_idx = q_vector->v_idx; + u32 itr_reg = q_vector->itr & IXGBE_MAX_EITR; + + switch (adapter->hw.mac.type) { + case ixgbe_mac_82598EB: + /* must write high and low 16 bits to reset counter */ + itr_reg |= (itr_reg << 16); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + /* + * set the WDIS bit to not clear the timer bits and cause an + * immediate assertion of the interrupt + */ + itr_reg |= IXGBE_EITR_CNT_WDIS; + break; + default: + break; + } + IXGBE_WRITE_REG(hw, IXGBE_EITR(v_idx), itr_reg); +} + +static void ixgbe_set_itr(struct ixgbe_q_vector *q_vector) +{ + u32 new_itr; + + ixgbe_update_itr(q_vector, &q_vector->tx); + ixgbe_update_itr(q_vector, &q_vector->rx); + + /* use the smallest value of new ITR delay calculations */ + new_itr = min(q_vector->rx.itr, q_vector->tx.itr); + + /* Clear latency flag if set, shift into correct position */ + new_itr &= ~IXGBE_ITR_ADAPTIVE_LATENCY; + new_itr <<= 2; + + if (new_itr != q_vector->itr) { + /* save the algorithm value here */ + q_vector->itr = new_itr; + + ixgbe_write_eitr(q_vector); + } +} + +/** + * ixgbe_check_overtemp_subtask - check for over temperature + * @adapter: pointer to adapter + **/ +static void ixgbe_check_overtemp_subtask(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 eicr = adapter->interrupt_event; + s32 rc; + + if (test_bit(__IXGBE_DOWN, &adapter->state)) + return; + + if (!(adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_EVENT)) + return; + + adapter->flags2 &= ~IXGBE_FLAG2_TEMP_SENSOR_EVENT; + + switch (hw->device_id) { + case IXGBE_DEV_ID_82599_T3_LOM: + /* + * Since the warning interrupt is for both ports + * we don't have to check if: + * - This interrupt wasn't for our port. + * - We may have missed the interrupt so always have to + * check if we got a LSC + */ + if (!(eicr & IXGBE_EICR_GPI_SDP0_8259X) && + !(eicr & IXGBE_EICR_LSC)) + return; + + if (!(eicr & IXGBE_EICR_LSC) && hw->mac.ops.check_link) { + u32 speed; + bool link_up = false; + + hw->mac.ops.check_link(hw, &speed, &link_up, false); + + if (link_up) + return; + } + + /* Check if this is not due to overtemp */ + if (hw->phy.ops.check_overtemp(hw) != IXGBE_ERR_OVERTEMP) + return; + + break; + case IXGBE_DEV_ID_X550EM_A_1G_T: + case IXGBE_DEV_ID_X550EM_A_1G_T_L: + rc = hw->phy.ops.check_overtemp(hw); + if (rc != IXGBE_ERR_OVERTEMP) + return; + break; + default: + if (adapter->hw.mac.type >= ixgbe_mac_X540) + return; + if (!(eicr & IXGBE_EICR_GPI_SDP0(hw))) + return; + break; + } + e_crit(drv, "%s\n", ixgbe_overheat_msg); + + adapter->interrupt_event = 0; +} + +static void ixgbe_check_fan_failure(struct ixgbe_adapter *adapter, u32 eicr) +{ + struct ixgbe_hw *hw = &adapter->hw; + + if ((adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE) && + (eicr & IXGBE_EICR_GPI_SDP1(hw))) { + e_crit(probe, "Fan has stopped, replace the adapter\n"); + /* write to clear the interrupt */ + IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP1(hw)); + } +} + +static void ixgbe_check_overtemp_event(struct ixgbe_adapter *adapter, u32 eicr) +{ + struct ixgbe_hw *hw = &adapter->hw; + + if (!(adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE)) + return; + + switch (adapter->hw.mac.type) { + case ixgbe_mac_82599EB: + /* + * Need to check link state so complete overtemp check + * on service task + */ + if (((eicr & IXGBE_EICR_GPI_SDP0(hw)) || + (eicr & IXGBE_EICR_LSC)) && + (!test_bit(__IXGBE_DOWN, &adapter->state))) { + adapter->interrupt_event = eicr; + adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_EVENT; + ixgbe_service_event_schedule(adapter); + return; + } + return; + case ixgbe_mac_x550em_a: + if (eicr & IXGBE_EICR_GPI_SDP0_X550EM_a) { + adapter->interrupt_event = eicr; + adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_EVENT; + ixgbe_service_event_schedule(adapter); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, + IXGBE_EICR_GPI_SDP0_X550EM_a); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICR, + IXGBE_EICR_GPI_SDP0_X550EM_a); + } + return; + case ixgbe_mac_X550: + case ixgbe_mac_X540: + if (!(eicr & IXGBE_EICR_TS)) + return; + break; + default: + return; + } + + e_crit(drv, "%s\n", ixgbe_overheat_msg); +} + +static inline bool ixgbe_is_sfp(struct ixgbe_hw *hw) +{ + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + if (hw->phy.type == ixgbe_phy_nl) + return true; + return false; + case ixgbe_mac_82599EB: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + switch (hw->mac.ops.get_media_type(hw)) { + case ixgbe_media_type_fiber: + case ixgbe_media_type_fiber_qsfp: + return true; + default: + return false; + } + default: + return false; + } +} + +static void ixgbe_check_sfp_event(struct ixgbe_adapter *adapter, u32 eicr) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 eicr_mask = IXGBE_EICR_GPI_SDP2(hw); + + if (!ixgbe_is_sfp(hw)) + return; + + /* Later MAC's use different SDP */ + if (hw->mac.type >= ixgbe_mac_X540) + eicr_mask = IXGBE_EICR_GPI_SDP0_X540; + + if (eicr & eicr_mask) { + /* Clear the interrupt */ + IXGBE_WRITE_REG(hw, IXGBE_EICR, eicr_mask); + if (!test_bit(__IXGBE_DOWN, &adapter->state)) { + adapter->flags2 |= IXGBE_FLAG2_SFP_NEEDS_RESET; + adapter->sfp_poll_time = 0; + ixgbe_service_event_schedule(adapter); + } + } + + if (adapter->hw.mac.type == ixgbe_mac_82599EB && + (eicr & IXGBE_EICR_GPI_SDP1(hw))) { + /* Clear the interrupt */ + IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP1(hw)); + if (!test_bit(__IXGBE_DOWN, &adapter->state)) { + adapter->flags |= IXGBE_FLAG_NEED_LINK_CONFIG; + ixgbe_service_event_schedule(adapter); + } + } +} + +static void ixgbe_check_lsc(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + + adapter->lsc_int++; + adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE; + adapter->link_check_timeout = jiffies; + if (!test_bit(__IXGBE_DOWN, &adapter->state)) { + IXGBE_WRITE_REG(hw, IXGBE_EIMC, IXGBE_EIMC_LSC); + IXGBE_WRITE_FLUSH(hw); + ixgbe_service_event_schedule(adapter); + } +} + +static inline void ixgbe_irq_enable_queues(struct ixgbe_adapter *adapter, + u64 qmask) +{ + u32 mask; + struct ixgbe_hw *hw = &adapter->hw; + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + mask = (IXGBE_EIMS_RTX_QUEUE & qmask); + IXGBE_WRITE_REG(hw, IXGBE_EIMS, mask); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + mask = (qmask & 0xFFFFFFFF); + if (mask) + IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(0), mask); + mask = (qmask >> 32); + if (mask) + IXGBE_WRITE_REG(hw, IXGBE_EIMS_EX(1), mask); + break; + default: + break; + } + /* skip the flush */ +} + +/** + * ixgbe_irq_enable - Enable default interrupt generation settings + * @adapter: board private structure + * @queues: enable irqs for queues + * @flush: flush register write + **/ +static inline void ixgbe_irq_enable(struct ixgbe_adapter *adapter, bool queues, + bool flush) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 mask = (IXGBE_EIMS_ENABLE_MASK & ~IXGBE_EIMS_RTX_QUEUE); + + /* don't reenable LSC while waiting for link */ + if (adapter->flags & IXGBE_FLAG_NEED_LINK_UPDATE) + mask &= ~IXGBE_EIMS_LSC; + + if (adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE) + switch (adapter->hw.mac.type) { + case ixgbe_mac_82599EB: + mask |= IXGBE_EIMS_GPI_SDP0(hw); + break; + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + mask |= IXGBE_EIMS_TS; + break; + default: + break; + } + if (adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE) + mask |= IXGBE_EIMS_GPI_SDP1(hw); + switch (adapter->hw.mac.type) { + case ixgbe_mac_82599EB: + mask |= IXGBE_EIMS_GPI_SDP1(hw); + mask |= IXGBE_EIMS_GPI_SDP2(hw); + fallthrough; + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + if (adapter->hw.device_id == IXGBE_DEV_ID_X550EM_X_SFP || + adapter->hw.device_id == IXGBE_DEV_ID_X550EM_A_SFP || + adapter->hw.device_id == IXGBE_DEV_ID_X550EM_A_SFP_N) + mask |= IXGBE_EIMS_GPI_SDP0(&adapter->hw); + if (adapter->hw.phy.type == ixgbe_phy_x550em_ext_t) + mask |= IXGBE_EICR_GPI_SDP0_X540; + mask |= IXGBE_EIMS_ECC; + mask |= IXGBE_EIMS_MAILBOX; + break; + default: + break; + } + + if ((adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) && + !(adapter->flags2 & IXGBE_FLAG2_FDIR_REQUIRES_REINIT)) + mask |= IXGBE_EIMS_FLOW_DIR; + + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMS, mask); + if (queues) + ixgbe_irq_enable_queues(adapter, ~0); + if (flush) + IXGBE_WRITE_FLUSH(&adapter->hw); +} + +static irqreturn_t ixgbe_msix_other(int irq, void *data) +{ + struct ixgbe_adapter *adapter = data; + struct ixgbe_hw *hw = &adapter->hw; + u32 eicr; + + /* + * Workaround for Silicon errata. Use clear-by-write instead + * of clear-by-read. Reading with EICS will return the + * interrupt causes without clearing, which later be done + * with the write to EICR. + */ + eicr = IXGBE_READ_REG(hw, IXGBE_EICS); + + /* The lower 16bits of the EICR register are for the queue interrupts + * which should be masked here in order to not accidentally clear them if + * the bits are high when ixgbe_msix_other is called. There is a race + * condition otherwise which results in possible performance loss + * especially if the ixgbe_msix_other interrupt is triggering + * consistently (as it would when PPS is turned on for the X540 device) + */ + eicr &= 0xFFFF0000; + + IXGBE_WRITE_REG(hw, IXGBE_EICR, eicr); + + if (eicr & IXGBE_EICR_LSC) + ixgbe_check_lsc(adapter); + + if (eicr & IXGBE_EICR_MAILBOX) + ixgbe_msg_task(adapter); + + switch (hw->mac.type) { + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + if (hw->phy.type == ixgbe_phy_x550em_ext_t && + (eicr & IXGBE_EICR_GPI_SDP0_X540)) { + adapter->flags2 |= IXGBE_FLAG2_PHY_INTERRUPT; + ixgbe_service_event_schedule(adapter); + IXGBE_WRITE_REG(hw, IXGBE_EICR, + IXGBE_EICR_GPI_SDP0_X540); + } + if (eicr & IXGBE_EICR_ECC) { + e_info(link, "Received ECC Err, initiating reset\n"); + set_bit(__IXGBE_RESET_REQUESTED, &adapter->state); + ixgbe_service_event_schedule(adapter); + IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_ECC); + } + /* Handle Flow Director Full threshold interrupt */ + if (eicr & IXGBE_EICR_FLOW_DIR) { + int reinit_count = 0; + int i; + for (i = 0; i < adapter->num_tx_queues; i++) { + struct ixgbe_ring *ring = adapter->tx_ring[i]; + if (test_and_clear_bit(__IXGBE_TX_FDIR_INIT_DONE, + &ring->state)) + reinit_count++; + } + if (reinit_count) { + /* no more flow director interrupts until after init */ + IXGBE_WRITE_REG(hw, IXGBE_EIMC, IXGBE_EIMC_FLOW_DIR); + adapter->flags2 |= IXGBE_FLAG2_FDIR_REQUIRES_REINIT; + ixgbe_service_event_schedule(adapter); + } + } + ixgbe_check_sfp_event(adapter, eicr); + ixgbe_check_overtemp_event(adapter, eicr); + break; + default: + break; + } + + ixgbe_check_fan_failure(adapter, eicr); + + if (unlikely(eicr & IXGBE_EICR_TIMESYNC)) + ixgbe_ptp_check_pps_event(adapter); + + /* re-enable the original interrupt state, no lsc, no queues */ + if (!test_bit(__IXGBE_DOWN, &adapter->state)) + ixgbe_irq_enable(adapter, false, false); + + return IRQ_HANDLED; +} + +static irqreturn_t ixgbe_msix_clean_rings(int irq, void *data) +{ + struct ixgbe_q_vector *q_vector = data; + + /* EIAM disabled interrupts (on this vector) for us */ + + if (q_vector->rx.ring || q_vector->tx.ring) + napi_schedule_irqoff(&q_vector->napi); + + return IRQ_HANDLED; +} + +/** + * ixgbe_poll - NAPI Rx polling callback + * @napi: structure for representing this polling device + * @budget: how many packets driver is allowed to clean + * + * This function is used for legacy and MSI, NAPI mode + **/ +int ixgbe_poll(struct napi_struct *napi, int budget) +{ + struct ixgbe_q_vector *q_vector = + container_of(napi, struct ixgbe_q_vector, napi); + struct ixgbe_adapter *adapter = q_vector->adapter; + struct ixgbe_ring *ring; + int per_ring_budget, work_done = 0; + bool clean_complete = true; + +#ifdef CONFIG_IXGBE_DCA + if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) + ixgbe_update_dca(q_vector); +#endif + + ixgbe_for_each_ring(ring, q_vector->tx) { + bool wd = ring->xsk_pool ? + ixgbe_clean_xdp_tx_irq(q_vector, ring, budget) : + ixgbe_clean_tx_irq(q_vector, ring, budget); + + if (!wd) + clean_complete = false; + } + + /* Exit if we are called by netpoll */ + if (budget <= 0) + return budget; + + /* attempt to distribute budget to each queue fairly, but don't allow + * the budget to go below 1 because we'll exit polling */ + if (q_vector->rx.count > 1) + per_ring_budget = max(budget/q_vector->rx.count, 1); + else + per_ring_budget = budget; + + ixgbe_for_each_ring(ring, q_vector->rx) { + int cleaned = ring->xsk_pool ? + ixgbe_clean_rx_irq_zc(q_vector, ring, + per_ring_budget) : + ixgbe_clean_rx_irq(q_vector, ring, + per_ring_budget); + + work_done += cleaned; + if (cleaned >= per_ring_budget) + clean_complete = false; + } + + /* If all work not completed, return budget and keep polling */ + if (!clean_complete) + return budget; + + /* all work done, exit the polling mode */ + if (likely(napi_complete_done(napi, work_done))) { + if (adapter->rx_itr_setting & 1) + ixgbe_set_itr(q_vector); + if (!test_bit(__IXGBE_DOWN, &adapter->state)) + ixgbe_irq_enable_queues(adapter, + BIT_ULL(q_vector->v_idx)); + } + + return min(work_done, budget - 1); +} + +/** + * ixgbe_request_msix_irqs - Initialize MSI-X interrupts + * @adapter: board private structure + * + * ixgbe_request_msix_irqs allocates MSI-X vectors and requests + * interrupts from the kernel. + **/ +static int ixgbe_request_msix_irqs(struct ixgbe_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + unsigned int ri = 0, ti = 0; + int vector, err; + + for (vector = 0; vector < adapter->num_q_vectors; vector++) { + struct ixgbe_q_vector *q_vector = adapter->q_vector[vector]; + struct msix_entry *entry = &adapter->msix_entries[vector]; + + if (q_vector->tx.ring && q_vector->rx.ring) { + snprintf(q_vector->name, sizeof(q_vector->name), + "%s-TxRx-%u", netdev->name, ri++); + ti++; + } else if (q_vector->rx.ring) { + snprintf(q_vector->name, sizeof(q_vector->name), + "%s-rx-%u", netdev->name, ri++); + } else if (q_vector->tx.ring) { + snprintf(q_vector->name, sizeof(q_vector->name), + "%s-tx-%u", netdev->name, ti++); + } else { + /* skip this unused q_vector */ + continue; + } + err = request_irq(entry->vector, &ixgbe_msix_clean_rings, 0, + q_vector->name, q_vector); + if (err) { + e_err(probe, "request_irq failed for MSIX interrupt " + "Error: %d\n", err); + goto free_queue_irqs; + } + /* If Flow Director is enabled, set interrupt affinity */ + if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) { + /* assign the mask for this irq */ + irq_set_affinity_hint(entry->vector, + &q_vector->affinity_mask); + } + } + + err = request_irq(adapter->msix_entries[vector].vector, + ixgbe_msix_other, 0, netdev->name, adapter); + if (err) { + e_err(probe, "request_irq for msix_other failed: %d\n", err); + goto free_queue_irqs; + } + + return 0; + +free_queue_irqs: + while (vector) { + vector--; + irq_set_affinity_hint(adapter->msix_entries[vector].vector, + NULL); + free_irq(adapter->msix_entries[vector].vector, + adapter->q_vector[vector]); + } + adapter->flags &= ~IXGBE_FLAG_MSIX_ENABLED; + pci_disable_msix(adapter->pdev); + kfree(adapter->msix_entries); + adapter->msix_entries = NULL; + return err; +} + +/** + * ixgbe_intr - legacy mode Interrupt Handler + * @irq: interrupt number + * @data: pointer to a network interface device structure + **/ +static irqreturn_t ixgbe_intr(int irq, void *data) +{ + struct ixgbe_adapter *adapter = data; + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_q_vector *q_vector = adapter->q_vector[0]; + u32 eicr; + + /* + * Workaround for silicon errata #26 on 82598. Mask the interrupt + * before the read of EICR. + */ + IXGBE_WRITE_REG(hw, IXGBE_EIMC, IXGBE_IRQ_CLEAR_MASK); + + /* for NAPI, using EIAM to auto-mask tx/rx interrupt bits on read + * therefore no explicit interrupt disable is necessary */ + eicr = IXGBE_READ_REG(hw, IXGBE_EICR); + if (!eicr) { + /* + * shared interrupt alert! + * make sure interrupts are enabled because the read will + * have disabled interrupts due to EIAM + * finish the workaround of silicon errata on 82598. Unmask + * the interrupt that we masked before the EICR read. + */ + if (!test_bit(__IXGBE_DOWN, &adapter->state)) + ixgbe_irq_enable(adapter, true, true); + return IRQ_NONE; /* Not our interrupt */ + } + + if (eicr & IXGBE_EICR_LSC) + ixgbe_check_lsc(adapter); + + switch (hw->mac.type) { + case ixgbe_mac_82599EB: + ixgbe_check_sfp_event(adapter, eicr); + fallthrough; + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + if (eicr & IXGBE_EICR_ECC) { + e_info(link, "Received ECC Err, initiating reset\n"); + set_bit(__IXGBE_RESET_REQUESTED, &adapter->state); + ixgbe_service_event_schedule(adapter); + IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_ECC); + } + ixgbe_check_overtemp_event(adapter, eicr); + break; + default: + break; + } + + ixgbe_check_fan_failure(adapter, eicr); + if (unlikely(eicr & IXGBE_EICR_TIMESYNC)) + ixgbe_ptp_check_pps_event(adapter); + + /* would disable interrupts here but EIAM disabled it */ + napi_schedule_irqoff(&q_vector->napi); + + /* + * re-enable link(maybe) and non-queue interrupts, no flush. + * ixgbe_poll will re-enable the queue interrupts + */ + if (!test_bit(__IXGBE_DOWN, &adapter->state)) + ixgbe_irq_enable(adapter, false, false); + + return IRQ_HANDLED; +} + +/** + * ixgbe_request_irq - initialize interrupts + * @adapter: board private structure + * + * Attempts to configure interrupts using the best available + * capabilities of the hardware and kernel. + **/ +static int ixgbe_request_irq(struct ixgbe_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + int err; + + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) + err = ixgbe_request_msix_irqs(adapter); + else if (adapter->flags & IXGBE_FLAG_MSI_ENABLED) + err = request_irq(adapter->pdev->irq, ixgbe_intr, 0, + netdev->name, adapter); + else + err = request_irq(adapter->pdev->irq, ixgbe_intr, IRQF_SHARED, + netdev->name, adapter); + + if (err) + e_err(probe, "request_irq failed, Error %d\n", err); + + return err; +} + +static void ixgbe_free_irq(struct ixgbe_adapter *adapter) +{ + int vector; + + if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) { + free_irq(adapter->pdev->irq, adapter); + return; + } + + if (!adapter->msix_entries) + return; + + for (vector = 0; vector < adapter->num_q_vectors; vector++) { + struct ixgbe_q_vector *q_vector = adapter->q_vector[vector]; + struct msix_entry *entry = &adapter->msix_entries[vector]; + + /* free only the irqs that were actually requested */ + if (!q_vector->rx.ring && !q_vector->tx.ring) + continue; + + /* clear the affinity_mask in the IRQ descriptor */ + irq_set_affinity_hint(entry->vector, NULL); + + free_irq(entry->vector, q_vector); + } + + free_irq(adapter->msix_entries[vector].vector, adapter); +} + +/** + * ixgbe_irq_disable - Mask off interrupt generation on the NIC + * @adapter: board private structure + **/ +static inline void ixgbe_irq_disable(struct ixgbe_adapter *adapter) +{ + switch (adapter->hw.mac.type) { + case ixgbe_mac_82598EB: + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, ~0); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, 0xFFFF0000); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(0), ~0); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC_EX(1), ~0); + break; + default: + break; + } + IXGBE_WRITE_FLUSH(&adapter->hw); + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) { + int vector; + + for (vector = 0; vector < adapter->num_q_vectors; vector++) + synchronize_irq(adapter->msix_entries[vector].vector); + + synchronize_irq(adapter->msix_entries[vector++].vector); + } else { + synchronize_irq(adapter->pdev->irq); + } +} + +/** + * ixgbe_configure_msi_and_legacy - Initialize PIN (INTA...) and MSI interrupts + * @adapter: board private structure + * + **/ +static void ixgbe_configure_msi_and_legacy(struct ixgbe_adapter *adapter) +{ + struct ixgbe_q_vector *q_vector = adapter->q_vector[0]; + + ixgbe_write_eitr(q_vector); + + ixgbe_set_ivar(adapter, 0, 0, 0); + ixgbe_set_ivar(adapter, 1, 0, 0); + + e_info(hw, "Legacy interrupt IVAR setup done\n"); +} + +/** + * ixgbe_configure_tx_ring - Configure 8259x Tx ring after Reset + * @adapter: board private structure + * @ring: structure containing ring specific data + * + * Configure the Tx descriptor ring after a reset. + **/ +void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter, + struct ixgbe_ring *ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + u64 tdba = ring->dma; + int wait_loop = 10; + u32 txdctl = IXGBE_TXDCTL_ENABLE; + u8 reg_idx = ring->reg_idx; + + ring->xsk_pool = NULL; + if (ring_is_xdp(ring)) + ring->xsk_pool = ixgbe_xsk_pool(adapter, ring); + + /* disable queue to avoid issues while updating state */ + IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), 0); + IXGBE_WRITE_FLUSH(hw); + + IXGBE_WRITE_REG(hw, IXGBE_TDBAL(reg_idx), + (tdba & DMA_BIT_MASK(32))); + IXGBE_WRITE_REG(hw, IXGBE_TDBAH(reg_idx), (tdba >> 32)); + IXGBE_WRITE_REG(hw, IXGBE_TDLEN(reg_idx), + ring->count * sizeof(union ixgbe_adv_tx_desc)); + IXGBE_WRITE_REG(hw, IXGBE_TDH(reg_idx), 0); + IXGBE_WRITE_REG(hw, IXGBE_TDT(reg_idx), 0); + ring->tail = adapter->io_addr + IXGBE_TDT(reg_idx); + + /* + * set WTHRESH to encourage burst writeback, it should not be set + * higher than 1 when: + * - ITR is 0 as it could cause false TX hangs + * - ITR is set to > 100k int/sec and BQL is enabled + * + * In order to avoid issues WTHRESH + PTHRESH should always be equal + * to or less than the number of on chip descriptors, which is + * currently 40. + */ + if (!ring->q_vector || (ring->q_vector->itr < IXGBE_100K_ITR)) + txdctl |= 1u << 16; /* WTHRESH = 1 */ + else + txdctl |= 8u << 16; /* WTHRESH = 8 */ + + /* + * Setting PTHRESH to 32 both improves performance + * and avoids a TX hang with DFP enabled + */ + txdctl |= (1u << 8) | /* HTHRESH = 1 */ + 32; /* PTHRESH = 32 */ + + /* reinitialize flowdirector state */ + if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) { + ring->atr_sample_rate = adapter->atr_sample_rate; + ring->atr_count = 0; + set_bit(__IXGBE_TX_FDIR_INIT_DONE, &ring->state); + } else { + ring->atr_sample_rate = 0; + } + + /* initialize XPS */ + if (!test_and_set_bit(__IXGBE_TX_XPS_INIT_DONE, &ring->state)) { + struct ixgbe_q_vector *q_vector = ring->q_vector; + + if (q_vector) + netif_set_xps_queue(ring->netdev, + &q_vector->affinity_mask, + ring->queue_index); + } + + clear_bit(__IXGBE_HANG_CHECK_ARMED, &ring->state); + + /* reinitialize tx_buffer_info */ + memset(ring->tx_buffer_info, 0, + sizeof(struct ixgbe_tx_buffer) * ring->count); + + /* enable queue */ + IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), txdctl); + + /* TXDCTL.EN will return 0 on 82598 if link is down, so skip it */ + if (hw->mac.type == ixgbe_mac_82598EB && + !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP)) + return; + + /* poll to verify queue is enabled */ + do { + usleep_range(1000, 2000); + txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx)); + } while (--wait_loop && !(txdctl & IXGBE_TXDCTL_ENABLE)); + if (!wait_loop) + hw_dbg(hw, "Could not enable Tx Queue %d\n", reg_idx); +} + +static void ixgbe_setup_mtqc(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 rttdcs, mtqc; + u8 tcs = adapter->hw_tcs; + + if (hw->mac.type == ixgbe_mac_82598EB) + return; + + /* disable the arbiter while setting MTQC */ + rttdcs = IXGBE_READ_REG(hw, IXGBE_RTTDCS); + rttdcs |= IXGBE_RTTDCS_ARBDIS; + IXGBE_WRITE_REG(hw, IXGBE_RTTDCS, rttdcs); + + /* set transmit pool layout */ + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { + mtqc = IXGBE_MTQC_VT_ENA; + if (tcs > 4) + mtqc |= IXGBE_MTQC_RT_ENA | IXGBE_MTQC_8TC_8TQ; + else if (tcs > 1) + mtqc |= IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ; + else if (adapter->ring_feature[RING_F_VMDQ].mask == + IXGBE_82599_VMDQ_4Q_MASK) + mtqc |= IXGBE_MTQC_32VF; + else + mtqc |= IXGBE_MTQC_64VF; + } else { + if (tcs > 4) { + mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_8TC_8TQ; + } else if (tcs > 1) { + mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ; + } else { + u8 max_txq = adapter->num_tx_queues + + adapter->num_xdp_queues; + if (max_txq > 63) + mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ; + else + mtqc = IXGBE_MTQC_64Q_1PB; + } + } + + IXGBE_WRITE_REG(hw, IXGBE_MTQC, mtqc); + + /* Enable Security TX Buffer IFG for multiple pb */ + if (tcs) { + u32 sectx = IXGBE_READ_REG(hw, IXGBE_SECTXMINIFG); + sectx |= IXGBE_SECTX_DCB; + IXGBE_WRITE_REG(hw, IXGBE_SECTXMINIFG, sectx); + } + + /* re-enable the arbiter */ + rttdcs &= ~IXGBE_RTTDCS_ARBDIS; + IXGBE_WRITE_REG(hw, IXGBE_RTTDCS, rttdcs); +} + +/** + * ixgbe_configure_tx - Configure 8259x Transmit Unit after Reset + * @adapter: board private structure + * + * Configure the Tx unit of the MAC after a reset. + **/ +static void ixgbe_configure_tx(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 dmatxctl; + u32 i; + + ixgbe_setup_mtqc(adapter); + + if (hw->mac.type != ixgbe_mac_82598EB) { + /* DMATXCTL.EN must be before Tx queues are enabled */ + dmatxctl = IXGBE_READ_REG(hw, IXGBE_DMATXCTL); + dmatxctl |= IXGBE_DMATXCTL_TE; + IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL, dmatxctl); + } + + /* Setup the HW Tx Head and Tail descriptor pointers */ + for (i = 0; i < adapter->num_tx_queues; i++) + ixgbe_configure_tx_ring(adapter, adapter->tx_ring[i]); + for (i = 0; i < adapter->num_xdp_queues; i++) + ixgbe_configure_tx_ring(adapter, adapter->xdp_ring[i]); +} + +static void ixgbe_enable_rx_drop(struct ixgbe_adapter *adapter, + struct ixgbe_ring *ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + u8 reg_idx = ring->reg_idx; + u32 srrctl = IXGBE_READ_REG(hw, IXGBE_SRRCTL(reg_idx)); + + srrctl |= IXGBE_SRRCTL_DROP_EN; + + IXGBE_WRITE_REG(hw, IXGBE_SRRCTL(reg_idx), srrctl); +} + +static void ixgbe_disable_rx_drop(struct ixgbe_adapter *adapter, + struct ixgbe_ring *ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + u8 reg_idx = ring->reg_idx; + u32 srrctl = IXGBE_READ_REG(hw, IXGBE_SRRCTL(reg_idx)); + + srrctl &= ~IXGBE_SRRCTL_DROP_EN; + + IXGBE_WRITE_REG(hw, IXGBE_SRRCTL(reg_idx), srrctl); +} + +#ifdef CONFIG_IXGBE_DCB +void ixgbe_set_rx_drop_en(struct ixgbe_adapter *adapter) +#else +static void ixgbe_set_rx_drop_en(struct ixgbe_adapter *adapter) +#endif +{ + int i; + bool pfc_en = adapter->dcb_cfg.pfc_mode_enable; + + if (adapter->ixgbe_ieee_pfc) + pfc_en |= !!(adapter->ixgbe_ieee_pfc->pfc_en); + + /* + * We should set the drop enable bit if: + * SR-IOV is enabled + * or + * Number of Rx queues > 1 and flow control is disabled + * + * This allows us to avoid head of line blocking for security + * and performance reasons. + */ + if (adapter->num_vfs || (adapter->num_rx_queues > 1 && + !(adapter->hw.fc.current_mode & ixgbe_fc_tx_pause) && !pfc_en)) { + for (i = 0; i < adapter->num_rx_queues; i++) + ixgbe_enable_rx_drop(adapter, adapter->rx_ring[i]); + } else { + for (i = 0; i < adapter->num_rx_queues; i++) + ixgbe_disable_rx_drop(adapter, adapter->rx_ring[i]); + } +} + +#define IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT 2 + +static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter, + struct ixgbe_ring *rx_ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 srrctl; + u8 reg_idx = rx_ring->reg_idx; + + if (hw->mac.type == ixgbe_mac_82598EB) { + u16 mask = adapter->ring_feature[RING_F_RSS].mask; + + /* + * if VMDq is not active we must program one srrctl register + * per RSS queue since we have enabled RDRXCTL.MVMEN + */ + reg_idx &= mask; + } + + /* configure header buffer length, needed for RSC */ + srrctl = IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT; + + /* configure the packet buffer length */ + if (rx_ring->xsk_pool) { + u32 xsk_buf_len = xsk_pool_get_rx_frame_size(rx_ring->xsk_pool); + + /* If the MAC support setting RXDCTL.RLPML, the + * SRRCTL[n].BSIZEPKT is set to PAGE_SIZE and + * RXDCTL.RLPML is set to the actual UMEM buffer + * size. If not, then we are stuck with a 1k buffer + * size resolution. In this case frames larger than + * the UMEM buffer size viewed in a 1k resolution will + * be dropped. + */ + if (hw->mac.type != ixgbe_mac_82599EB) + srrctl |= PAGE_SIZE >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; + else + srrctl |= xsk_buf_len >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; + } else if (test_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state)) { + srrctl |= IXGBE_RXBUFFER_3K >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; + } else { + srrctl |= IXGBE_RXBUFFER_2K >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; + } + + /* configure descriptor type */ + srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF; + + IXGBE_WRITE_REG(hw, IXGBE_SRRCTL(reg_idx), srrctl); +} + +/** + * ixgbe_rss_indir_tbl_entries - Return RSS indirection table entries + * @adapter: device handle + * + * - 82598/82599/X540: 128 + * - X550(non-SRIOV mode): 512 + * - X550(SRIOV mode): 64 + */ +u32 ixgbe_rss_indir_tbl_entries(struct ixgbe_adapter *adapter) +{ + if (adapter->hw.mac.type < ixgbe_mac_X550) + return 128; + else if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) + return 64; + else + return 512; +} + +/** + * ixgbe_store_key - Write the RSS key to HW + * @adapter: device handle + * + * Write the RSS key stored in adapter.rss_key to HW. + */ +void ixgbe_store_key(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int i; + + for (i = 0; i < 10; i++) + IXGBE_WRITE_REG(hw, IXGBE_RSSRK(i), adapter->rss_key[i]); +} + +/** + * ixgbe_init_rss_key - Initialize adapter RSS key + * @adapter: device handle + * + * Allocates and initializes the RSS key if it is not allocated. + **/ +static inline int ixgbe_init_rss_key(struct ixgbe_adapter *adapter) +{ + u32 *rss_key; + + if (!adapter->rss_key) { + rss_key = kzalloc(IXGBE_RSS_KEY_SIZE, GFP_KERNEL); + if (unlikely(!rss_key)) + return -ENOMEM; + + netdev_rss_key_fill(rss_key, IXGBE_RSS_KEY_SIZE); + adapter->rss_key = rss_key; + } + + return 0; +} + +/** + * ixgbe_store_reta - Write the RETA table to HW + * @adapter: device handle + * + * Write the RSS redirection table stored in adapter.rss_indir_tbl[] to HW. + */ +void ixgbe_store_reta(struct ixgbe_adapter *adapter) +{ + u32 i, reta_entries = ixgbe_rss_indir_tbl_entries(adapter); + struct ixgbe_hw *hw = &adapter->hw; + u32 reta = 0; + u32 indices_multi; + u8 *indir_tbl = adapter->rss_indir_tbl; + + /* Fill out the redirection table as follows: + * - 82598: 8 bit wide entries containing pair of 4 bit RSS + * indices. + * - 82599/X540: 8 bit wide entries containing 4 bit RSS index + * - X550: 8 bit wide entries containing 6 bit RSS index + */ + if (adapter->hw.mac.type == ixgbe_mac_82598EB) + indices_multi = 0x11; + else + indices_multi = 0x1; + + /* Write redirection table to HW */ + for (i = 0; i < reta_entries; i++) { + reta |= indices_multi * indir_tbl[i] << (i & 0x3) * 8; + if ((i & 3) == 3) { + if (i < 128) + IXGBE_WRITE_REG(hw, IXGBE_RETA(i >> 2), reta); + else + IXGBE_WRITE_REG(hw, IXGBE_ERETA((i >> 2) - 32), + reta); + reta = 0; + } + } +} + +/** + * ixgbe_store_vfreta - Write the RETA table to HW (x550 devices in SRIOV mode) + * @adapter: device handle + * + * Write the RSS redirection table stored in adapter.rss_indir_tbl[] to HW. + */ +static void ixgbe_store_vfreta(struct ixgbe_adapter *adapter) +{ + u32 i, reta_entries = ixgbe_rss_indir_tbl_entries(adapter); + struct ixgbe_hw *hw = &adapter->hw; + u32 vfreta = 0; + + /* Write redirection table to HW */ + for (i = 0; i < reta_entries; i++) { + u16 pool = adapter->num_rx_pools; + + vfreta |= (u32)adapter->rss_indir_tbl[i] << (i & 0x3) * 8; + if ((i & 3) != 3) + continue; + + while (pool--) + IXGBE_WRITE_REG(hw, + IXGBE_PFVFRETA(i >> 2, VMDQ_P(pool)), + vfreta); + vfreta = 0; + } +} + +static void ixgbe_setup_reta(struct ixgbe_adapter *adapter) +{ + u32 i, j; + u32 reta_entries = ixgbe_rss_indir_tbl_entries(adapter); + u16 rss_i = adapter->ring_feature[RING_F_RSS].indices; + + /* Program table for at least 4 queues w/ SR-IOV so that VFs can + * make full use of any rings they may have. We will use the + * PSRTYPE register to control how many rings we use within the PF. + */ + if ((adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) && (rss_i < 4)) + rss_i = 4; + + /* Fill out hash function seeds */ + ixgbe_store_key(adapter); + + /* Fill out redirection table */ + memset(adapter->rss_indir_tbl, 0, sizeof(adapter->rss_indir_tbl)); + + for (i = 0, j = 0; i < reta_entries; i++, j++) { + if (j == rss_i) + j = 0; + + adapter->rss_indir_tbl[i] = j; + } + + ixgbe_store_reta(adapter); +} + +static void ixgbe_setup_vfreta(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u16 rss_i = adapter->ring_feature[RING_F_RSS].indices; + int i, j; + + /* Fill out hash function seeds */ + for (i = 0; i < 10; i++) { + u16 pool = adapter->num_rx_pools; + + while (pool--) + IXGBE_WRITE_REG(hw, + IXGBE_PFVFRSSRK(i, VMDQ_P(pool)), + *(adapter->rss_key + i)); + } + + /* Fill out the redirection table */ + for (i = 0, j = 0; i < 64; i++, j++) { + if (j == rss_i) + j = 0; + + adapter->rss_indir_tbl[i] = j; + } + + ixgbe_store_vfreta(adapter); +} + +static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 mrqc = 0, rss_field = 0, vfmrqc = 0; + u32 rxcsum; + + /* Disable indicating checksum in descriptor, enables RSS hash */ + rxcsum = IXGBE_READ_REG(hw, IXGBE_RXCSUM); + rxcsum |= IXGBE_RXCSUM_PCSD; + IXGBE_WRITE_REG(hw, IXGBE_RXCSUM, rxcsum); + + if (adapter->hw.mac.type == ixgbe_mac_82598EB) { + if (adapter->ring_feature[RING_F_RSS].mask) + mrqc = IXGBE_MRQC_RSSEN; + } else { + u8 tcs = adapter->hw_tcs; + + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { + if (tcs > 4) + mrqc = IXGBE_MRQC_VMDQRT8TCEN; /* 8 TCs */ + else if (tcs > 1) + mrqc = IXGBE_MRQC_VMDQRT4TCEN; /* 4 TCs */ + else if (adapter->ring_feature[RING_F_VMDQ].mask == + IXGBE_82599_VMDQ_4Q_MASK) + mrqc = IXGBE_MRQC_VMDQRSS32EN; + else + mrqc = IXGBE_MRQC_VMDQRSS64EN; + + /* Enable L3/L4 for Tx Switched packets only for X550, + * older devices do not support this feature + */ + if (hw->mac.type >= ixgbe_mac_X550) + mrqc |= IXGBE_MRQC_L3L4TXSWEN; + } else { + if (tcs > 4) + mrqc = IXGBE_MRQC_RTRSS8TCEN; + else if (tcs > 1) + mrqc = IXGBE_MRQC_RTRSS4TCEN; + else + mrqc = IXGBE_MRQC_RSSEN; + } + } + + /* Perform hash on these packet types */ + rss_field |= IXGBE_MRQC_RSS_FIELD_IPV4 | + IXGBE_MRQC_RSS_FIELD_IPV4_TCP | + IXGBE_MRQC_RSS_FIELD_IPV6 | + IXGBE_MRQC_RSS_FIELD_IPV6_TCP; + + if (adapter->flags2 & IXGBE_FLAG2_RSS_FIELD_IPV4_UDP) + rss_field |= IXGBE_MRQC_RSS_FIELD_IPV4_UDP; + if (adapter->flags2 & IXGBE_FLAG2_RSS_FIELD_IPV6_UDP) + rss_field |= IXGBE_MRQC_RSS_FIELD_IPV6_UDP; + + if ((hw->mac.type >= ixgbe_mac_X550) && + (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) { + u16 pool = adapter->num_rx_pools; + + /* Enable VF RSS mode */ + mrqc |= IXGBE_MRQC_MULTIPLE_RSS; + IXGBE_WRITE_REG(hw, IXGBE_MRQC, mrqc); + + /* Setup RSS through the VF registers */ + ixgbe_setup_vfreta(adapter); + vfmrqc = IXGBE_MRQC_RSSEN; + vfmrqc |= rss_field; + + while (pool--) + IXGBE_WRITE_REG(hw, + IXGBE_PFVFMRQC(VMDQ_P(pool)), + vfmrqc); + } else { + ixgbe_setup_reta(adapter); + mrqc |= rss_field; + IXGBE_WRITE_REG(hw, IXGBE_MRQC, mrqc); + } +} + +/** + * ixgbe_configure_rscctl - enable RSC for the indicated ring + * @adapter: address of board private structure + * @ring: structure containing ring specific data + **/ +static void ixgbe_configure_rscctl(struct ixgbe_adapter *adapter, + struct ixgbe_ring *ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 rscctrl; + u8 reg_idx = ring->reg_idx; + + if (!ring_is_rsc_enabled(ring)) + return; + + rscctrl = IXGBE_READ_REG(hw, IXGBE_RSCCTL(reg_idx)); + rscctrl |= IXGBE_RSCCTL_RSCEN; + /* + * we must limit the number of descriptors so that the + * total size of max desc * buf_len is not greater + * than 65536 + */ + rscctrl |= IXGBE_RSCCTL_MAXDESC_16; + IXGBE_WRITE_REG(hw, IXGBE_RSCCTL(reg_idx), rscctrl); +} + +#define IXGBE_MAX_RX_DESC_POLL 10 +static void ixgbe_rx_desc_queue_enable(struct ixgbe_adapter *adapter, + struct ixgbe_ring *ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + int wait_loop = IXGBE_MAX_RX_DESC_POLL; + u32 rxdctl; + u8 reg_idx = ring->reg_idx; + + if (ixgbe_removed(hw->hw_addr)) + return; + /* RXDCTL.EN will return 0 on 82598 if link is down, so skip it */ + if (hw->mac.type == ixgbe_mac_82598EB && + !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP)) + return; + + do { + usleep_range(1000, 2000); + rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx)); + } while (--wait_loop && !(rxdctl & IXGBE_RXDCTL_ENABLE)); + + if (!wait_loop) { + e_err(drv, "RXDCTL.ENABLE on Rx queue %d not set within " + "the polling period\n", reg_idx); + } +} + +void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, + struct ixgbe_ring *ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + union ixgbe_adv_rx_desc *rx_desc; + u64 rdba = ring->dma; + u32 rxdctl; + u8 reg_idx = ring->reg_idx; + + xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq); + ring->xsk_pool = ixgbe_xsk_pool(adapter, ring); + if (ring->xsk_pool) { + WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_XSK_BUFF_POOL, + NULL)); + xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq); + } else { + WARN_ON(xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, + MEM_TYPE_PAGE_SHARED, NULL)); + } + + /* disable queue to avoid use of these values while updating state */ + rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx)); + rxdctl &= ~IXGBE_RXDCTL_ENABLE; + + /* write value back with RXDCTL.ENABLE bit cleared */ + IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl); + IXGBE_WRITE_FLUSH(hw); + + IXGBE_WRITE_REG(hw, IXGBE_RDBAL(reg_idx), (rdba & DMA_BIT_MASK(32))); + IXGBE_WRITE_REG(hw, IXGBE_RDBAH(reg_idx), (rdba >> 32)); + IXGBE_WRITE_REG(hw, IXGBE_RDLEN(reg_idx), + ring->count * sizeof(union ixgbe_adv_rx_desc)); + /* Force flushing of IXGBE_RDLEN to prevent MDD */ + IXGBE_WRITE_FLUSH(hw); + + IXGBE_WRITE_REG(hw, IXGBE_RDH(reg_idx), 0); + IXGBE_WRITE_REG(hw, IXGBE_RDT(reg_idx), 0); + ring->tail = adapter->io_addr + IXGBE_RDT(reg_idx); + + ixgbe_configure_srrctl(adapter, ring); + ixgbe_configure_rscctl(adapter, ring); + + if (hw->mac.type == ixgbe_mac_82598EB) { + /* + * enable cache line friendly hardware writes: + * PTHRESH=32 descriptors (half the internal cache), + * this also removes ugly rx_no_buffer_count increment + * HTHRESH=4 descriptors (to minimize latency on fetch) + * WTHRESH=8 burst writeback up to two cache lines + */ + rxdctl &= ~0x3FFFFF; + rxdctl |= 0x080420; +#if (PAGE_SIZE < 8192) + /* RXDCTL.RLPML does not work on 82599 */ + } else if (hw->mac.type != ixgbe_mac_82599EB) { + rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK | + IXGBE_RXDCTL_RLPML_EN); + + /* Limit the maximum frame size so we don't overrun the skb. + * This can happen in SRIOV mode when the MTU of the VF is + * higher than the MTU of the PF. + */ + if (ring_uses_build_skb(ring) && + !test_bit(__IXGBE_RX_3K_BUFFER, &ring->state)) + rxdctl |= IXGBE_MAX_2K_FRAME_BUILD_SKB | + IXGBE_RXDCTL_RLPML_EN; +#endif + } + + if (ring->xsk_pool && hw->mac.type != ixgbe_mac_82599EB) { + u32 xsk_buf_len = xsk_pool_get_rx_frame_size(ring->xsk_pool); + + rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK | + IXGBE_RXDCTL_RLPML_EN); + rxdctl |= xsk_buf_len | IXGBE_RXDCTL_RLPML_EN; + + ring->rx_buf_len = xsk_buf_len; + } + + /* initialize rx_buffer_info */ + memset(ring->rx_buffer_info, 0, + sizeof(struct ixgbe_rx_buffer) * ring->count); + + /* initialize Rx descriptor 0 */ + rx_desc = IXGBE_RX_DESC(ring, 0); + rx_desc->wb.upper.length = 0; + + /* enable receive descriptor ring */ + rxdctl |= IXGBE_RXDCTL_ENABLE; + IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl); + + ixgbe_rx_desc_queue_enable(adapter, ring); + if (ring->xsk_pool) + ixgbe_alloc_rx_buffers_zc(ring, ixgbe_desc_unused(ring)); + else + ixgbe_alloc_rx_buffers(ring, ixgbe_desc_unused(ring)); +} + +static void ixgbe_setup_psrtype(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int rss_i = adapter->ring_feature[RING_F_RSS].indices; + u16 pool = adapter->num_rx_pools; + + /* PSRTYPE must be initialized in non 82598 adapters */ + u32 psrtype = IXGBE_PSRTYPE_TCPHDR | + IXGBE_PSRTYPE_UDPHDR | + IXGBE_PSRTYPE_IPV4HDR | + IXGBE_PSRTYPE_L2HDR | + IXGBE_PSRTYPE_IPV6HDR; + + if (hw->mac.type == ixgbe_mac_82598EB) + return; + + if (rss_i > 3) + psrtype |= 2u << 29; + else if (rss_i > 1) + psrtype |= 1u << 29; + + while (pool--) + IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(VMDQ_P(pool)), psrtype); +} + +static void ixgbe_configure_virtualization(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u16 pool = adapter->num_rx_pools; + u32 reg_offset, vf_shift, vmolr; + u32 gcr_ext, vmdctl; + int i; + + if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) + return; + + vmdctl = IXGBE_READ_REG(hw, IXGBE_VT_CTL); + vmdctl |= IXGBE_VMD_CTL_VMDQ_EN; + vmdctl &= ~IXGBE_VT_CTL_POOL_MASK; + vmdctl |= VMDQ_P(0) << IXGBE_VT_CTL_POOL_SHIFT; + vmdctl |= IXGBE_VT_CTL_REPLEN; + IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, vmdctl); + + /* accept untagged packets until a vlan tag is + * specifically set for the VMDQ queue/pool + */ + vmolr = IXGBE_VMOLR_AUPE; + while (pool--) + IXGBE_WRITE_REG(hw, IXGBE_VMOLR(VMDQ_P(pool)), vmolr); + + vf_shift = VMDQ_P(0) % 32; + reg_offset = (VMDQ_P(0) >= 32) ? 1 : 0; + + /* Enable only the PF's pool for Tx/Rx */ + IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset), GENMASK(31, vf_shift)); + IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset ^ 1), reg_offset - 1); + IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset), GENMASK(31, vf_shift)); + IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset ^ 1), reg_offset - 1); + if (adapter->bridge_mode == BRIDGE_MODE_VEB) + IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, IXGBE_PFDTXGSWC_VT_LBEN); + + /* Map PF MAC address in RAR Entry 0 to first pool following VFs */ + hw->mac.ops.set_vmdq(hw, 0, VMDQ_P(0)); + + /* clear VLAN promisc flag so VFTA will be updated if necessary */ + adapter->flags2 &= ~IXGBE_FLAG2_VLAN_PROMISC; + + /* + * Set up VF register offsets for selected VT Mode, + * i.e. 32 or 64 VFs for SR-IOV + */ + switch (adapter->ring_feature[RING_F_VMDQ].mask) { + case IXGBE_82599_VMDQ_8Q_MASK: + gcr_ext = IXGBE_GCR_EXT_VT_MODE_16; + break; + case IXGBE_82599_VMDQ_4Q_MASK: + gcr_ext = IXGBE_GCR_EXT_VT_MODE_32; + break; + default: + gcr_ext = IXGBE_GCR_EXT_VT_MODE_64; + break; + } + + IXGBE_WRITE_REG(hw, IXGBE_GCR_EXT, gcr_ext); + + for (i = 0; i < adapter->num_vfs; i++) { + /* configure spoof checking */ + ixgbe_ndo_set_vf_spoofchk(adapter->netdev, i, + adapter->vfinfo[i].spoofchk_enabled); + + /* Enable/Disable RSS query feature */ + ixgbe_ndo_set_vf_rss_query_en(adapter->netdev, i, + adapter->vfinfo[i].rss_query_enabled); + } +} + +static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; + int max_frame = netdev->mtu + ETH_HLEN + ETH_FCS_LEN; + struct ixgbe_ring *rx_ring; + int i; + u32 mhadd, hlreg0; + +#ifdef IXGBE_FCOE + /* adjust max frame to be able to do baby jumbo for FCoE */ + if ((adapter->flags & IXGBE_FLAG_FCOE_ENABLED) && + (max_frame < IXGBE_FCOE_JUMBO_FRAME_SIZE)) + max_frame = IXGBE_FCOE_JUMBO_FRAME_SIZE; + +#endif /* IXGBE_FCOE */ + + /* adjust max frame to be at least the size of a standard frame */ + if (max_frame < (ETH_FRAME_LEN + ETH_FCS_LEN)) + max_frame = (ETH_FRAME_LEN + ETH_FCS_LEN); + + mhadd = IXGBE_READ_REG(hw, IXGBE_MHADD); + if (max_frame != (mhadd >> IXGBE_MHADD_MFS_SHIFT)) { + mhadd &= ~IXGBE_MHADD_MFS_MASK; + mhadd |= max_frame << IXGBE_MHADD_MFS_SHIFT; + + IXGBE_WRITE_REG(hw, IXGBE_MHADD, mhadd); + } + + hlreg0 = IXGBE_READ_REG(hw, IXGBE_HLREG0); + /* set jumbo enable since MHADD.MFS is keeping size locked at max_frame */ + hlreg0 |= IXGBE_HLREG0_JUMBOEN; + IXGBE_WRITE_REG(hw, IXGBE_HLREG0, hlreg0); + + /* + * Setup the HW Rx Head and Tail Descriptor Pointers and + * the Base and Length of the Rx Descriptor Ring + */ + for (i = 0; i < adapter->num_rx_queues; i++) { + rx_ring = adapter->rx_ring[i]; + + clear_ring_rsc_enabled(rx_ring); + clear_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state); + clear_bit(__IXGBE_RX_BUILD_SKB_ENABLED, &rx_ring->state); + + if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) + set_ring_rsc_enabled(rx_ring); + + if (test_bit(__IXGBE_RX_FCOE, &rx_ring->state)) + set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state); + + if (adapter->flags2 & IXGBE_FLAG2_RX_LEGACY) + continue; + + set_bit(__IXGBE_RX_BUILD_SKB_ENABLED, &rx_ring->state); + +#if (PAGE_SIZE < 8192) + if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) + set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state); + + if (IXGBE_2K_TOO_SMALL_WITH_PADDING || + (max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN))) + set_bit(__IXGBE_RX_3K_BUFFER, &rx_ring->state); +#endif + } +} + +static void ixgbe_setup_rdrxctl(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 rdrxctl = IXGBE_READ_REG(hw, IXGBE_RDRXCTL); + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + /* + * For VMDq support of different descriptor types or + * buffer sizes through the use of multiple SRRCTL + * registers, RDRXCTL.MVMEN must be set to 1 + * + * also, the manual doesn't mention it clearly but DCA hints + * will only use queue 0's tags unless this bit is set. Side + * effects of setting this bit are only that SRRCTL must be + * fully programmed [0..15] + */ + rdrxctl |= IXGBE_RDRXCTL_MVMEN; + break; + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + if (adapter->num_vfs) + rdrxctl |= IXGBE_RDRXCTL_PSP; + fallthrough; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + /* Disable RSC for ACK packets */ + IXGBE_WRITE_REG(hw, IXGBE_RSCDBU, + (IXGBE_RSCDBU_RSCACKDIS | IXGBE_READ_REG(hw, IXGBE_RSCDBU))); + rdrxctl &= ~IXGBE_RDRXCTL_RSCFRSTSIZE; + /* hardware requires some bits to be set by default */ + rdrxctl |= (IXGBE_RDRXCTL_RSCACKC | IXGBE_RDRXCTL_FCOE_WRFIX); + rdrxctl |= IXGBE_RDRXCTL_CRCSTRIP; + break; + default: + /* We should do nothing since we don't know this hardware */ + return; + } + + IXGBE_WRITE_REG(hw, IXGBE_RDRXCTL, rdrxctl); +} + +/** + * ixgbe_configure_rx - Configure 8259x Receive Unit after Reset + * @adapter: board private structure + * + * Configure the Rx unit of the MAC after a reset. + **/ +static void ixgbe_configure_rx(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int i; + u32 rxctrl, rfctl; + + /* disable receives while setting up the descriptors */ + hw->mac.ops.disable_rx(hw); + + ixgbe_setup_psrtype(adapter); + ixgbe_setup_rdrxctl(adapter); + + /* RSC Setup */ + rfctl = IXGBE_READ_REG(hw, IXGBE_RFCTL); + rfctl &= ~IXGBE_RFCTL_RSC_DIS; + if (!(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)) + rfctl |= IXGBE_RFCTL_RSC_DIS; + + /* disable NFS filtering */ + rfctl |= (IXGBE_RFCTL_NFSW_DIS | IXGBE_RFCTL_NFSR_DIS); + IXGBE_WRITE_REG(hw, IXGBE_RFCTL, rfctl); + + /* Program registers for the distribution of queues */ + ixgbe_setup_mrqc(adapter); + + /* set_rx_buffer_len must be called before ring initialization */ + ixgbe_set_rx_buffer_len(adapter); + + /* + * Setup the HW Rx Head and Tail Descriptor Pointers and + * the Base and Length of the Rx Descriptor Ring + */ + for (i = 0; i < adapter->num_rx_queues; i++) + ixgbe_configure_rx_ring(adapter, adapter->rx_ring[i]); + + rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL); + /* disable drop enable for 82598 parts */ + if (hw->mac.type == ixgbe_mac_82598EB) + rxctrl |= IXGBE_RXCTRL_DMBYPS; + + /* enable all receives */ + rxctrl |= IXGBE_RXCTRL_RXEN; + hw->mac.ops.enable_rx_dma(hw, rxctrl); +} + +static int ixgbe_vlan_rx_add_vid(struct net_device *netdev, + __be16 proto, u16 vid) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + + /* add VID to filter table */ + if (!vid || !(adapter->flags2 & IXGBE_FLAG2_VLAN_PROMISC)) + hw->mac.ops.set_vfta(&adapter->hw, vid, VMDQ_P(0), true, !!vid); + + set_bit(vid, adapter->active_vlans); + + return 0; +} + +static int ixgbe_find_vlvf_entry(struct ixgbe_hw *hw, u32 vlan) +{ + u32 vlvf; + int idx; + + /* short cut the special case */ + if (vlan == 0) + return 0; + + /* Search for the vlan id in the VLVF entries */ + for (idx = IXGBE_VLVF_ENTRIES; --idx;) { + vlvf = IXGBE_READ_REG(hw, IXGBE_VLVF(idx)); + if ((vlvf & VLAN_VID_MASK) == vlan) + break; + } + + return idx; +} + +void ixgbe_update_pf_promisc_vlvf(struct ixgbe_adapter *adapter, u32 vid) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 bits, word; + int idx; + + idx = ixgbe_find_vlvf_entry(hw, vid); + if (!idx) + return; + + /* See if any other pools are set for this VLAN filter + * entry other than the PF. + */ + word = idx * 2 + (VMDQ_P(0) / 32); + bits = ~BIT(VMDQ_P(0) % 32); + bits &= IXGBE_READ_REG(hw, IXGBE_VLVFB(word)); + + /* Disable the filter so this falls into the default pool. */ + if (!bits && !IXGBE_READ_REG(hw, IXGBE_VLVFB(word ^ 1))) { + if (!(adapter->flags2 & IXGBE_FLAG2_VLAN_PROMISC)) + IXGBE_WRITE_REG(hw, IXGBE_VLVFB(word), 0); + IXGBE_WRITE_REG(hw, IXGBE_VLVF(idx), 0); + } +} + +static int ixgbe_vlan_rx_kill_vid(struct net_device *netdev, + __be16 proto, u16 vid) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + + /* remove VID from filter table */ + if (vid && !(adapter->flags2 & IXGBE_FLAG2_VLAN_PROMISC)) + hw->mac.ops.set_vfta(hw, vid, VMDQ_P(0), false, true); + + clear_bit(vid, adapter->active_vlans); + + return 0; +} + +/** + * ixgbe_vlan_strip_disable - helper to disable hw vlan stripping + * @adapter: driver data + */ +static void ixgbe_vlan_strip_disable(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 vlnctrl; + int i, j; + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); + vlnctrl &= ~IXGBE_VLNCTRL_VME; + IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + for (i = 0; i < adapter->num_rx_queues; i++) { + struct ixgbe_ring *ring = adapter->rx_ring[i]; + + if (!netif_is_ixgbe(ring->netdev)) + continue; + + j = ring->reg_idx; + vlnctrl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(j)); + vlnctrl &= ~IXGBE_RXDCTL_VME; + IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(j), vlnctrl); + } + break; + default: + break; + } +} + +/** + * ixgbe_vlan_strip_enable - helper to enable hw vlan stripping + * @adapter: driver data + */ +static void ixgbe_vlan_strip_enable(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 vlnctrl; + int i, j; + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); + vlnctrl |= IXGBE_VLNCTRL_VME; + IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + for (i = 0; i < adapter->num_rx_queues; i++) { + struct ixgbe_ring *ring = adapter->rx_ring[i]; + + if (!netif_is_ixgbe(ring->netdev)) + continue; + + j = ring->reg_idx; + vlnctrl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(j)); + vlnctrl |= IXGBE_RXDCTL_VME; + IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(j), vlnctrl); + } + break; + default: + break; + } +} + +static void ixgbe_vlan_promisc_enable(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 vlnctrl, i; + + vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); + + if (adapter->flags & IXGBE_FLAG_VMDQ_ENABLED) { + /* For VMDq and SR-IOV we must leave VLAN filtering enabled */ + vlnctrl |= IXGBE_VLNCTRL_VFE; + IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); + } else { + vlnctrl &= ~IXGBE_VLNCTRL_VFE; + IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); + return; + } + + /* Nothing to do for 82598 */ + if (hw->mac.type == ixgbe_mac_82598EB) + return; + + /* We are already in VLAN promisc, nothing to do */ + if (adapter->flags2 & IXGBE_FLAG2_VLAN_PROMISC) + return; + + /* Set flag so we don't redo unnecessary work */ + adapter->flags2 |= IXGBE_FLAG2_VLAN_PROMISC; + + /* Add PF to all active pools */ + for (i = IXGBE_VLVF_ENTRIES; --i;) { + u32 reg_offset = IXGBE_VLVFB(i * 2 + VMDQ_P(0) / 32); + u32 vlvfb = IXGBE_READ_REG(hw, reg_offset); + + vlvfb |= BIT(VMDQ_P(0) % 32); + IXGBE_WRITE_REG(hw, reg_offset, vlvfb); + } + + /* Set all bits in the VLAN filter table array */ + for (i = hw->mac.vft_size; i--;) + IXGBE_WRITE_REG(hw, IXGBE_VFTA(i), ~0U); +} + +#define VFTA_BLOCK_SIZE 8 +static void ixgbe_scrub_vfta(struct ixgbe_adapter *adapter, u32 vfta_offset) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 vfta[VFTA_BLOCK_SIZE] = { 0 }; + u32 vid_start = vfta_offset * 32; + u32 vid_end = vid_start + (VFTA_BLOCK_SIZE * 32); + u32 i, vid, word, bits; + + for (i = IXGBE_VLVF_ENTRIES; --i;) { + u32 vlvf = IXGBE_READ_REG(hw, IXGBE_VLVF(i)); + + /* pull VLAN ID from VLVF */ + vid = vlvf & VLAN_VID_MASK; + + /* only concern outselves with a certain range */ + if (vid < vid_start || vid >= vid_end) + continue; + + if (vlvf) { + /* record VLAN ID in VFTA */ + vfta[(vid - vid_start) / 32] |= BIT(vid % 32); + + /* if PF is part of this then continue */ + if (test_bit(vid, adapter->active_vlans)) + continue; + } + + /* remove PF from the pool */ + word = i * 2 + VMDQ_P(0) / 32; + bits = ~BIT(VMDQ_P(0) % 32); + bits &= IXGBE_READ_REG(hw, IXGBE_VLVFB(word)); + IXGBE_WRITE_REG(hw, IXGBE_VLVFB(word), bits); + } + + /* extract values from active_vlans and write back to VFTA */ + for (i = VFTA_BLOCK_SIZE; i--;) { + vid = (vfta_offset + i) * 32; + word = vid / BITS_PER_LONG; + bits = vid % BITS_PER_LONG; + + vfta[i] |= adapter->active_vlans[word] >> bits; + + IXGBE_WRITE_REG(hw, IXGBE_VFTA(vfta_offset + i), vfta[i]); + } +} + +static void ixgbe_vlan_promisc_disable(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 vlnctrl, i; + + /* Set VLAN filtering to enabled */ + vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); + vlnctrl |= IXGBE_VLNCTRL_VFE; + IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); + + if (!(adapter->flags & IXGBE_FLAG_VMDQ_ENABLED) || + hw->mac.type == ixgbe_mac_82598EB) + return; + + /* We are not in VLAN promisc, nothing to do */ + if (!(adapter->flags2 & IXGBE_FLAG2_VLAN_PROMISC)) + return; + + /* Set flag so we don't redo unnecessary work */ + adapter->flags2 &= ~IXGBE_FLAG2_VLAN_PROMISC; + + for (i = 0; i < hw->mac.vft_size; i += VFTA_BLOCK_SIZE) + ixgbe_scrub_vfta(adapter, i); +} + +static void ixgbe_restore_vlan(struct ixgbe_adapter *adapter) +{ + u16 vid = 1; + + ixgbe_vlan_rx_add_vid(adapter->netdev, htons(ETH_P_8021Q), 0); + + for_each_set_bit_from(vid, adapter->active_vlans, VLAN_N_VID) + ixgbe_vlan_rx_add_vid(adapter->netdev, htons(ETH_P_8021Q), vid); +} + +/** + * ixgbe_write_mc_addr_list - write multicast addresses to MTA + * @netdev: network interface device structure + * + * Writes multicast address list to the MTA hash table. + * Returns: -ENOMEM on failure + * 0 on no addresses written + * X on writing X addresses to MTA + **/ +static int ixgbe_write_mc_addr_list(struct net_device *netdev) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + + if (!netif_running(netdev)) + return 0; + + if (hw->mac.ops.update_mc_addr_list) + hw->mac.ops.update_mc_addr_list(hw, netdev); + else + return -ENOMEM; + +#ifdef CONFIG_PCI_IOV + ixgbe_restore_vf_multicasts(adapter); +#endif + + return netdev_mc_count(netdev); +} + +#ifdef CONFIG_PCI_IOV +void ixgbe_full_sync_mac_table(struct ixgbe_adapter *adapter) +{ + struct ixgbe_mac_addr *mac_table = &adapter->mac_table[0]; + struct ixgbe_hw *hw = &adapter->hw; + int i; + + for (i = 0; i < hw->mac.num_rar_entries; i++, mac_table++) { + mac_table->state &= ~IXGBE_MAC_STATE_MODIFIED; + + if (mac_table->state & IXGBE_MAC_STATE_IN_USE) + hw->mac.ops.set_rar(hw, i, + mac_table->addr, + mac_table->pool, + IXGBE_RAH_AV); + else + hw->mac.ops.clear_rar(hw, i); + } +} + +#endif +static void ixgbe_sync_mac_table(struct ixgbe_adapter *adapter) +{ + struct ixgbe_mac_addr *mac_table = &adapter->mac_table[0]; + struct ixgbe_hw *hw = &adapter->hw; + int i; + + for (i = 0; i < hw->mac.num_rar_entries; i++, mac_table++) { + if (!(mac_table->state & IXGBE_MAC_STATE_MODIFIED)) + continue; + + mac_table->state &= ~IXGBE_MAC_STATE_MODIFIED; + + if (mac_table->state & IXGBE_MAC_STATE_IN_USE) + hw->mac.ops.set_rar(hw, i, + mac_table->addr, + mac_table->pool, + IXGBE_RAH_AV); + else + hw->mac.ops.clear_rar(hw, i); + } +} + +static void ixgbe_flush_sw_mac_table(struct ixgbe_adapter *adapter) +{ + struct ixgbe_mac_addr *mac_table = &adapter->mac_table[0]; + struct ixgbe_hw *hw = &adapter->hw; + int i; + + for (i = 0; i < hw->mac.num_rar_entries; i++, mac_table++) { + mac_table->state |= IXGBE_MAC_STATE_MODIFIED; + mac_table->state &= ~IXGBE_MAC_STATE_IN_USE; + } + + ixgbe_sync_mac_table(adapter); +} + +static int ixgbe_available_rars(struct ixgbe_adapter *adapter, u16 pool) +{ + struct ixgbe_mac_addr *mac_table = &adapter->mac_table[0]; + struct ixgbe_hw *hw = &adapter->hw; + int i, count = 0; + + for (i = 0; i < hw->mac.num_rar_entries; i++, mac_table++) { + /* do not count default RAR as available */ + if (mac_table->state & IXGBE_MAC_STATE_DEFAULT) + continue; + + /* only count unused and addresses that belong to us */ + if (mac_table->state & IXGBE_MAC_STATE_IN_USE) { + if (mac_table->pool != pool) + continue; + } + + count++; + } + + return count; +} + +/* this function destroys the first RAR entry */ +static void ixgbe_mac_set_default_filter(struct ixgbe_adapter *adapter) +{ + struct ixgbe_mac_addr *mac_table = &adapter->mac_table[0]; + struct ixgbe_hw *hw = &adapter->hw; + + memcpy(&mac_table->addr, hw->mac.addr, ETH_ALEN); + mac_table->pool = VMDQ_P(0); + + mac_table->state = IXGBE_MAC_STATE_DEFAULT | IXGBE_MAC_STATE_IN_USE; + + hw->mac.ops.set_rar(hw, 0, mac_table->addr, mac_table->pool, + IXGBE_RAH_AV); +} + +int ixgbe_add_mac_filter(struct ixgbe_adapter *adapter, + const u8 *addr, u16 pool) +{ + struct ixgbe_mac_addr *mac_table = &adapter->mac_table[0]; + struct ixgbe_hw *hw = &adapter->hw; + int i; + + if (is_zero_ether_addr(addr)) + return -EINVAL; + + for (i = 0; i < hw->mac.num_rar_entries; i++, mac_table++) { + if (mac_table->state & IXGBE_MAC_STATE_IN_USE) + continue; + + ether_addr_copy(mac_table->addr, addr); + mac_table->pool = pool; + + mac_table->state |= IXGBE_MAC_STATE_MODIFIED | + IXGBE_MAC_STATE_IN_USE; + + ixgbe_sync_mac_table(adapter); + + return i; + } + + return -ENOMEM; +} + +int ixgbe_del_mac_filter(struct ixgbe_adapter *adapter, + const u8 *addr, u16 pool) +{ + struct ixgbe_mac_addr *mac_table = &adapter->mac_table[0]; + struct ixgbe_hw *hw = &adapter->hw; + int i; + + if (is_zero_ether_addr(addr)) + return -EINVAL; + + /* search table for addr, if found clear IN_USE flag and sync */ + for (i = 0; i < hw->mac.num_rar_entries; i++, mac_table++) { + /* we can only delete an entry if it is in use */ + if (!(mac_table->state & IXGBE_MAC_STATE_IN_USE)) + continue; + /* we only care about entries that belong to the given pool */ + if (mac_table->pool != pool) + continue; + /* we only care about a specific MAC address */ + if (!ether_addr_equal(addr, mac_table->addr)) + continue; + + mac_table->state |= IXGBE_MAC_STATE_MODIFIED; + mac_table->state &= ~IXGBE_MAC_STATE_IN_USE; + + ixgbe_sync_mac_table(adapter); + + return 0; + } + + return -ENOMEM; +} + +static int ixgbe_uc_sync(struct net_device *netdev, const unsigned char *addr) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + int ret; + + ret = ixgbe_add_mac_filter(adapter, addr, VMDQ_P(0)); + + return min_t(int, ret, 0); +} + +static int ixgbe_uc_unsync(struct net_device *netdev, const unsigned char *addr) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + ixgbe_del_mac_filter(adapter, addr, VMDQ_P(0)); + + return 0; +} + +/** + * ixgbe_set_rx_mode - Unicast, Multicast and Promiscuous mode set + * @netdev: network interface device structure + * + * The set_rx_method entry point is called whenever the unicast/multicast + * address list or the network interface flags are updated. This routine is + * responsible for configuring the hardware for proper unicast, multicast and + * promiscuous mode. + **/ +void ixgbe_set_rx_mode(struct net_device *netdev) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + u32 fctrl, vmolr = IXGBE_VMOLR_BAM | IXGBE_VMOLR_AUPE; + netdev_features_t features = netdev->features; + int count; + + /* Check for Promiscuous and All Multicast modes */ + fctrl = IXGBE_READ_REG(hw, IXGBE_FCTRL); + + /* set all bits that we expect to always be set */ + fctrl &= ~IXGBE_FCTRL_SBP; /* disable store-bad-packets */ + fctrl |= IXGBE_FCTRL_BAM; + fctrl |= IXGBE_FCTRL_DPF; /* discard pause frames when FC enabled */ + fctrl |= IXGBE_FCTRL_PMCF; + + /* clear the bits we are changing the status of */ + fctrl &= ~(IXGBE_FCTRL_UPE | IXGBE_FCTRL_MPE); + if (netdev->flags & IFF_PROMISC) { + hw->addr_ctrl.user_set_promisc = true; + fctrl |= (IXGBE_FCTRL_UPE | IXGBE_FCTRL_MPE); + vmolr |= IXGBE_VMOLR_MPE; + features &= ~NETIF_F_HW_VLAN_CTAG_FILTER; + } else { + if (netdev->flags & IFF_ALLMULTI) { + fctrl |= IXGBE_FCTRL_MPE; + vmolr |= IXGBE_VMOLR_MPE; + } + hw->addr_ctrl.user_set_promisc = false; + } + + /* + * Write addresses to available RAR registers, if there is not + * sufficient space to store all the addresses then enable + * unicast promiscuous mode + */ + if (__dev_uc_sync(netdev, ixgbe_uc_sync, ixgbe_uc_unsync)) { + fctrl |= IXGBE_FCTRL_UPE; + vmolr |= IXGBE_VMOLR_ROPE; + } + + /* Write addresses to the MTA, if the attempt fails + * then we should just turn on promiscuous mode so + * that we can at least receive multicast traffic + */ + count = ixgbe_write_mc_addr_list(netdev); + if (count < 0) { + fctrl |= IXGBE_FCTRL_MPE; + vmolr |= IXGBE_VMOLR_MPE; + } else if (count) { + vmolr |= IXGBE_VMOLR_ROMPE; + } + + if (hw->mac.type != ixgbe_mac_82598EB) { + vmolr |= IXGBE_READ_REG(hw, IXGBE_VMOLR(VMDQ_P(0))) & + ~(IXGBE_VMOLR_MPE | IXGBE_VMOLR_ROMPE | + IXGBE_VMOLR_ROPE); + IXGBE_WRITE_REG(hw, IXGBE_VMOLR(VMDQ_P(0)), vmolr); + } + + /* This is useful for sniffing bad packets. */ + if (features & NETIF_F_RXALL) { + /* UPE and MPE will be handled by normal PROMISC logic + * in e1000e_set_rx_mode */ + fctrl |= (IXGBE_FCTRL_SBP | /* Receive bad packets */ + IXGBE_FCTRL_BAM | /* RX All Bcast Pkts */ + IXGBE_FCTRL_PMCF); /* RX All MAC Ctrl Pkts */ + + fctrl &= ~(IXGBE_FCTRL_DPF); + /* NOTE: VLAN filtering is disabled by setting PROMISC */ + } + + IXGBE_WRITE_REG(hw, IXGBE_FCTRL, fctrl); + + if (features & NETIF_F_HW_VLAN_CTAG_RX) + ixgbe_vlan_strip_enable(adapter); + else + ixgbe_vlan_strip_disable(adapter); + + if (features & NETIF_F_HW_VLAN_CTAG_FILTER) + ixgbe_vlan_promisc_disable(adapter); + else + ixgbe_vlan_promisc_enable(adapter); +} + +static void ixgbe_napi_enable_all(struct ixgbe_adapter *adapter) +{ + int q_idx; + + for (q_idx = 0; q_idx < adapter->num_q_vectors; q_idx++) + napi_enable(&adapter->q_vector[q_idx]->napi); +} + +static void ixgbe_napi_disable_all(struct ixgbe_adapter *adapter) +{ + int q_idx; + + for (q_idx = 0; q_idx < adapter->num_q_vectors; q_idx++) + napi_disable(&adapter->q_vector[q_idx]->napi); +} + +static int ixgbe_udp_tunnel_sync(struct net_device *dev, unsigned int table) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_hw *hw = &adapter->hw; + struct udp_tunnel_info ti; + + udp_tunnel_nic_get_port(dev, table, 0, &ti); + if (ti.type == UDP_TUNNEL_TYPE_VXLAN) + adapter->vxlan_port = ti.port; + else + adapter->geneve_port = ti.port; + + IXGBE_WRITE_REG(hw, IXGBE_VXLANCTRL, + ntohs(adapter->vxlan_port) | + ntohs(adapter->geneve_port) << + IXGBE_VXLANCTRL_GENEVE_UDPPORT_SHIFT); + return 0; +} + +static const struct udp_tunnel_nic_info ixgbe_udp_tunnels_x550 = { + .sync_table = ixgbe_udp_tunnel_sync, + .flags = UDP_TUNNEL_NIC_INFO_IPV4_ONLY, + .tables = { + { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, }, + }, +}; + +static const struct udp_tunnel_nic_info ixgbe_udp_tunnels_x550em_a = { + .sync_table = ixgbe_udp_tunnel_sync, + .flags = UDP_TUNNEL_NIC_INFO_IPV4_ONLY, + .tables = { + { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_VXLAN, }, + { .n_entries = 1, .tunnel_types = UDP_TUNNEL_TYPE_GENEVE, }, + }, +}; + +#ifdef CONFIG_IXGBE_DCB +/** + * ixgbe_configure_dcb - Configure DCB hardware + * @adapter: ixgbe adapter struct + * + * This is called by the driver on open to configure the DCB hardware. + * This is also called by the gennetlink interface when reconfiguring + * the DCB state. + */ +static void ixgbe_configure_dcb(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int max_frame = adapter->netdev->mtu + ETH_HLEN + ETH_FCS_LEN; + + if (!(adapter->flags & IXGBE_FLAG_DCB_ENABLED)) { + if (hw->mac.type == ixgbe_mac_82598EB) + netif_set_gso_max_size(adapter->netdev, 65536); + return; + } + + if (hw->mac.type == ixgbe_mac_82598EB) + netif_set_gso_max_size(adapter->netdev, 32768); + +#ifdef IXGBE_FCOE + if (adapter->netdev->features & NETIF_F_FCOE_MTU) + max_frame = max(max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE); +#endif + + /* reconfigure the hardware */ + if (adapter->dcbx_cap & DCB_CAP_DCBX_VER_CEE) { + ixgbe_dcb_calculate_tc_credits(hw, &adapter->dcb_cfg, max_frame, + DCB_TX_CONFIG); + ixgbe_dcb_calculate_tc_credits(hw, &adapter->dcb_cfg, max_frame, + DCB_RX_CONFIG); + ixgbe_dcb_hw_config(hw, &adapter->dcb_cfg); + } else if (adapter->ixgbe_ieee_ets && adapter->ixgbe_ieee_pfc) { + ixgbe_dcb_hw_ets(&adapter->hw, + adapter->ixgbe_ieee_ets, + max_frame); + ixgbe_dcb_hw_pfc_config(&adapter->hw, + adapter->ixgbe_ieee_pfc->pfc_en, + adapter->ixgbe_ieee_ets->prio_tc); + } + + /* Enable RSS Hash per TC */ + if (hw->mac.type != ixgbe_mac_82598EB) { + u32 msb = 0; + u16 rss_i = adapter->ring_feature[RING_F_RSS].indices - 1; + + while (rss_i) { + msb++; + rss_i >>= 1; + } + + /* write msb to all 8 TCs in one write */ + IXGBE_WRITE_REG(hw, IXGBE_RQTC, msb * 0x11111111); + } +} +#endif + +/* Additional bittime to account for IXGBE framing */ +#define IXGBE_ETH_FRAMING 20 + +/** + * ixgbe_hpbthresh - calculate high water mark for flow control + * + * @adapter: board private structure to calculate for + * @pb: packet buffer to calculate + */ +static int ixgbe_hpbthresh(struct ixgbe_adapter *adapter, int pb) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct net_device *dev = adapter->netdev; + int link, tc, kb, marker; + u32 dv_id, rx_pba; + + /* Calculate max LAN frame size */ + tc = link = dev->mtu + ETH_HLEN + ETH_FCS_LEN + IXGBE_ETH_FRAMING; + +#ifdef IXGBE_FCOE + /* FCoE traffic class uses FCOE jumbo frames */ + if ((dev->features & NETIF_F_FCOE_MTU) && + (tc < IXGBE_FCOE_JUMBO_FRAME_SIZE) && + (pb == ixgbe_fcoe_get_tc(adapter))) + tc = IXGBE_FCOE_JUMBO_FRAME_SIZE; +#endif + + /* Calculate delay value for device */ + switch (hw->mac.type) { + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + dv_id = IXGBE_DV_X540(link, tc); + break; + default: + dv_id = IXGBE_DV(link, tc); + break; + } + + /* Loopback switch introduces additional latency */ + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) + dv_id += IXGBE_B2BT(tc); + + /* Delay value is calculated in bit times convert to KB */ + kb = IXGBE_BT2KB(dv_id); + rx_pba = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(pb)) >> 10; + + marker = rx_pba - kb; + + /* It is possible that the packet buffer is not large enough + * to provide required headroom. In this case throw an error + * to user and a do the best we can. + */ + if (marker < 0) { + e_warn(drv, "Packet Buffer(%i) can not provide enough" + "headroom to support flow control." + "Decrease MTU or number of traffic classes\n", pb); + marker = tc + 1; + } + + return marker; +} + +/** + * ixgbe_lpbthresh - calculate low water mark for for flow control + * + * @adapter: board private structure to calculate for + * @pb: packet buffer to calculate + */ +static int ixgbe_lpbthresh(struct ixgbe_adapter *adapter, int pb) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct net_device *dev = adapter->netdev; + int tc; + u32 dv_id; + + /* Calculate max LAN frame size */ + tc = dev->mtu + ETH_HLEN + ETH_FCS_LEN; + +#ifdef IXGBE_FCOE + /* FCoE traffic class uses FCOE jumbo frames */ + if ((dev->features & NETIF_F_FCOE_MTU) && + (tc < IXGBE_FCOE_JUMBO_FRAME_SIZE) && + (pb == netdev_get_prio_tc_map(dev, adapter->fcoe.up))) + tc = IXGBE_FCOE_JUMBO_FRAME_SIZE; +#endif + + /* Calculate delay value for device */ + switch (hw->mac.type) { + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + dv_id = IXGBE_LOW_DV_X540(tc); + break; + default: + dv_id = IXGBE_LOW_DV(tc); + break; + } + + /* Delay value is calculated in bit times convert to KB */ + return IXGBE_BT2KB(dv_id); +} + +/* + * ixgbe_pbthresh_setup - calculate and setup high low water marks + */ +static void ixgbe_pbthresh_setup(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int num_tc = adapter->hw_tcs; + int i; + + if (!num_tc) + num_tc = 1; + + for (i = 0; i < num_tc; i++) { + hw->fc.high_water[i] = ixgbe_hpbthresh(adapter, i); + hw->fc.low_water[i] = ixgbe_lpbthresh(adapter, i); + + /* Low water marks must not be larger than high water marks */ + if (hw->fc.low_water[i] > hw->fc.high_water[i]) + hw->fc.low_water[i] = 0; + } + + for (; i < MAX_TRAFFIC_CLASS; i++) + hw->fc.high_water[i] = 0; +} + +static void ixgbe_configure_pb(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int hdrm; + u8 tc = adapter->hw_tcs; + + if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE || + adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE) + hdrm = 32 << adapter->fdir_pballoc; + else + hdrm = 0; + + hw->mac.ops.set_rxpba(hw, tc, hdrm, PBA_STRATEGY_EQUAL); + ixgbe_pbthresh_setup(adapter); +} + +static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct hlist_node *node2; + struct ixgbe_fdir_filter *filter; + u8 queue; + + spin_lock(&adapter->fdir_perfect_lock); + + if (!hlist_empty(&adapter->fdir_filter_list)) + ixgbe_fdir_set_input_mask_82599(hw, &adapter->fdir_mask); + + hlist_for_each_entry_safe(filter, node2, + &adapter->fdir_filter_list, fdir_node) { + if (filter->action == IXGBE_FDIR_DROP_QUEUE) { + queue = IXGBE_FDIR_DROP_QUEUE; + } else { + u32 ring = ethtool_get_flow_spec_ring(filter->action); + u8 vf = ethtool_get_flow_spec_ring_vf(filter->action); + + if (!vf && (ring >= adapter->num_rx_queues)) { + e_err(drv, "FDIR restore failed without VF, ring: %u\n", + ring); + continue; + } else if (vf && + ((vf > adapter->num_vfs) || + ring >= adapter->num_rx_queues_per_pool)) { + e_err(drv, "FDIR restore failed with VF, vf: %hhu, ring: %u\n", + vf, ring); + continue; + } + + /* Map the ring onto the absolute queue index */ + if (!vf) + queue = adapter->rx_ring[ring]->reg_idx; + else + queue = ((vf - 1) * + adapter->num_rx_queues_per_pool) + ring; + } + + ixgbe_fdir_write_perfect_filter_82599(hw, + &filter->filter, filter->sw_idx, queue); + } + + spin_unlock(&adapter->fdir_perfect_lock); +} + +/** + * ixgbe_clean_rx_ring - Free Rx Buffers per Queue + * @rx_ring: ring to free buffers from + **/ +static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring) +{ + u16 i = rx_ring->next_to_clean; + struct ixgbe_rx_buffer *rx_buffer = &rx_ring->rx_buffer_info[i]; + + if (rx_ring->xsk_pool) { + ixgbe_xsk_clean_rx_ring(rx_ring); + goto skip_free; + } + + /* Free all the Rx ring sk_buffs */ + while (i != rx_ring->next_to_alloc) { + if (rx_buffer->skb) { + struct sk_buff *skb = rx_buffer->skb; + if (IXGBE_CB(skb)->page_released) + dma_unmap_page_attrs(rx_ring->dev, + IXGBE_CB(skb)->dma, + ixgbe_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IXGBE_RX_DMA_ATTR); + dev_kfree_skb(skb); + } + + /* Invalidate cache lines that may have been written to by + * device so that we avoid corrupting memory. + */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + ixgbe_rx_bufsz(rx_ring), + DMA_FROM_DEVICE); + + /* free resources associated with mapping */ + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, + ixgbe_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IXGBE_RX_DMA_ATTR); + __page_frag_cache_drain(rx_buffer->page, + rx_buffer->pagecnt_bias); + + i++; + rx_buffer++; + if (i == rx_ring->count) { + i = 0; + rx_buffer = rx_ring->rx_buffer_info; + } + } + +skip_free: + rx_ring->next_to_alloc = 0; + rx_ring->next_to_clean = 0; + rx_ring->next_to_use = 0; +} + +static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter, + struct ixgbe_fwd_adapter *accel) +{ + u16 rss_i = adapter->ring_feature[RING_F_RSS].indices; + int num_tc = netdev_get_num_tc(adapter->netdev); + struct net_device *vdev = accel->netdev; + int i, baseq, err; + + baseq = accel->pool * adapter->num_rx_queues_per_pool; + netdev_dbg(vdev, "pool %i:%i queues %i:%i\n", + accel->pool, adapter->num_rx_pools, + baseq, baseq + adapter->num_rx_queues_per_pool); + + accel->rx_base_queue = baseq; + accel->tx_base_queue = baseq; + + /* record configuration for macvlan interface in vdev */ + for (i = 0; i < num_tc; i++) + netdev_bind_sb_channel_queue(adapter->netdev, vdev, + i, rss_i, baseq + (rss_i * i)); + + for (i = 0; i < adapter->num_rx_queues_per_pool; i++) + adapter->rx_ring[baseq + i]->netdev = vdev; + + /* Guarantee all rings are updated before we update the + * MAC address filter. + */ + wmb(); + + /* ixgbe_add_mac_filter will return an index if it succeeds, so we + * need to only treat it as an error value if it is negative. + */ + err = ixgbe_add_mac_filter(adapter, vdev->dev_addr, + VMDQ_P(accel->pool)); + if (err >= 0) + return 0; + + /* if we cannot add the MAC rule then disable the offload */ + macvlan_release_l2fw_offload(vdev); + + for (i = 0; i < adapter->num_rx_queues_per_pool; i++) + adapter->rx_ring[baseq + i]->netdev = NULL; + + netdev_err(vdev, "L2FW offload disabled due to L2 filter error\n"); + + /* unbind the queues and drop the subordinate channel config */ + netdev_unbind_sb_channel(adapter->netdev, vdev); + netdev_set_sb_channel(vdev, 0); + + clear_bit(accel->pool, adapter->fwd_bitmask); + kfree(accel); + + return err; +} + +static int ixgbe_macvlan_up(struct net_device *vdev, + struct netdev_nested_priv *priv) +{ + struct ixgbe_adapter *adapter = (struct ixgbe_adapter *)priv->data; + struct ixgbe_fwd_adapter *accel; + + if (!netif_is_macvlan(vdev)) + return 0; + + accel = macvlan_accel_priv(vdev); + if (!accel) + return 0; + + ixgbe_fwd_ring_up(adapter, accel); + + return 0; +} + +static void ixgbe_configure_dfwd(struct ixgbe_adapter *adapter) +{ + struct netdev_nested_priv priv = { + .data = (void *)adapter, + }; + + netdev_walk_all_upper_dev_rcu(adapter->netdev, + ixgbe_macvlan_up, &priv); +} + +static void ixgbe_configure(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + + ixgbe_configure_pb(adapter); +#ifdef CONFIG_IXGBE_DCB + ixgbe_configure_dcb(adapter); +#endif + /* + * We must restore virtualization before VLANs or else + * the VLVF registers will not be populated + */ + ixgbe_configure_virtualization(adapter); + + ixgbe_set_rx_mode(adapter->netdev); + ixgbe_restore_vlan(adapter); + ixgbe_ipsec_restore(adapter); + + switch (hw->mac.type) { + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + hw->mac.ops.disable_rx_buff(hw); + break; + default: + break; + } + + if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) { + ixgbe_init_fdir_signature_82599(&adapter->hw, + adapter->fdir_pballoc); + } else if (adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE) { + ixgbe_init_fdir_perfect_82599(&adapter->hw, + adapter->fdir_pballoc); + ixgbe_fdir_filter_restore(adapter); + } + + switch (hw->mac.type) { + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + hw->mac.ops.enable_rx_buff(hw); + break; + default: + break; + } + +#ifdef CONFIG_IXGBE_DCA + /* configure DCA */ + if (adapter->flags & IXGBE_FLAG_DCA_CAPABLE) + ixgbe_setup_dca(adapter); +#endif /* CONFIG_IXGBE_DCA */ + +#ifdef IXGBE_FCOE + /* configure FCoE L2 filters, redirection table, and Rx control */ + ixgbe_configure_fcoe(adapter); + +#endif /* IXGBE_FCOE */ + ixgbe_configure_tx(adapter); + ixgbe_configure_rx(adapter); + ixgbe_configure_dfwd(adapter); +} + +/** + * ixgbe_sfp_link_config - set up SFP+ link + * @adapter: pointer to private adapter struct + **/ +static void ixgbe_sfp_link_config(struct ixgbe_adapter *adapter) +{ + /* + * We are assuming the worst case scenario here, and that + * is that an SFP was inserted/removed after the reset + * but before SFP detection was enabled. As such the best + * solution is to just start searching as soon as we start + */ + if (adapter->hw.mac.type == ixgbe_mac_82598EB) + adapter->flags2 |= IXGBE_FLAG2_SEARCH_FOR_SFP; + + adapter->flags2 |= IXGBE_FLAG2_SFP_NEEDS_RESET; + adapter->sfp_poll_time = 0; +} + +/** + * ixgbe_non_sfp_link_config - set up non-SFP+ link + * @hw: pointer to private hardware struct + * + * Returns 0 on success, negative on failure + **/ +static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw) +{ + u32 speed; + bool autoneg, link_up = false; + int ret = IXGBE_ERR_LINK_SETUP; + + if (hw->mac.ops.check_link) + ret = hw->mac.ops.check_link(hw, &speed, &link_up, false); + + if (ret) + return ret; + + speed = hw->phy.autoneg_advertised; + if (!speed && hw->mac.ops.get_link_capabilities) { + ret = hw->mac.ops.get_link_capabilities(hw, &speed, + &autoneg); + /* remove NBASE-T speeds from default autonegotiation + * to accommodate broken network switches in the field + * which cannot cope with advertised NBASE-T speeds + */ + speed &= ~(IXGBE_LINK_SPEED_5GB_FULL | + IXGBE_LINK_SPEED_2_5GB_FULL); + } + + if (ret) + return ret; + + if (hw->mac.ops.setup_link) + ret = hw->mac.ops.setup_link(hw, speed, link_up); + + return ret; +} + +static void ixgbe_setup_gpie(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 gpie = 0; + + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) { + gpie = IXGBE_GPIE_MSIX_MODE | IXGBE_GPIE_PBA_SUPPORT | + IXGBE_GPIE_OCD; + gpie |= IXGBE_GPIE_EIAME; + /* + * use EIAM to auto-mask when MSI-X interrupt is asserted + * this saves a register write for every interrupt + */ + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + IXGBE_WRITE_REG(hw, IXGBE_EIAM, IXGBE_EICS_RTX_QUEUE); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + default: + IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(0), 0xFFFFFFFF); + IXGBE_WRITE_REG(hw, IXGBE_EIAM_EX(1), 0xFFFFFFFF); + break; + } + } else { + /* legacy interrupts, use EIAM to auto-mask when reading EICR, + * specifically only auto mask tx and rx interrupts */ + IXGBE_WRITE_REG(hw, IXGBE_EIAM, IXGBE_EICS_RTX_QUEUE); + } + + /* XXX: to interrupt immediately for EICS writes, enable this */ + /* gpie |= IXGBE_GPIE_EIMEN; */ + + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { + gpie &= ~IXGBE_GPIE_VTMODE_MASK; + + switch (adapter->ring_feature[RING_F_VMDQ].mask) { + case IXGBE_82599_VMDQ_8Q_MASK: + gpie |= IXGBE_GPIE_VTMODE_16; + break; + case IXGBE_82599_VMDQ_4Q_MASK: + gpie |= IXGBE_GPIE_VTMODE_32; + break; + default: + gpie |= IXGBE_GPIE_VTMODE_64; + break; + } + } + + /* Enable Thermal over heat sensor interrupt */ + if (adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE) { + switch (adapter->hw.mac.type) { + case ixgbe_mac_82599EB: + gpie |= IXGBE_SDP0_GPIEN_8259X; + break; + default: + break; + } + } + + /* Enable fan failure interrupt */ + if (adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE) + gpie |= IXGBE_SDP1_GPIEN(hw); + + switch (hw->mac.type) { + case ixgbe_mac_82599EB: + gpie |= IXGBE_SDP1_GPIEN_8259X | IXGBE_SDP2_GPIEN_8259X; + break; + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + gpie |= IXGBE_SDP0_GPIEN_X540; + break; + default: + break; + } + + IXGBE_WRITE_REG(hw, IXGBE_GPIE, gpie); +} + +static void ixgbe_up_complete(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int err; + u32 ctrl_ext; + + ixgbe_get_hw_control(adapter); + ixgbe_setup_gpie(adapter); + + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) + ixgbe_configure_msix(adapter); + else + ixgbe_configure_msi_and_legacy(adapter); + + /* enable the optics for 82599 SFP+ fiber */ + if (hw->mac.ops.enable_tx_laser) + hw->mac.ops.enable_tx_laser(hw); + + if (hw->phy.ops.set_phy_power) + hw->phy.ops.set_phy_power(hw, true); + + smp_mb__before_atomic(); + clear_bit(__IXGBE_DOWN, &adapter->state); + ixgbe_napi_enable_all(adapter); + + if (ixgbe_is_sfp(hw)) { + ixgbe_sfp_link_config(adapter); + } else { + err = ixgbe_non_sfp_link_config(hw); + if (err) + e_err(probe, "link_config FAILED %d\n", err); + } + + /* clear any pending interrupts, may auto mask */ + IXGBE_READ_REG(hw, IXGBE_EICR); + ixgbe_irq_enable(adapter, true, true); + + /* + * If this adapter has a fan, check to see if we had a failure + * before we enabled the interrupt. + */ + if (adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE) { + u32 esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + if (esdp & IXGBE_ESDP_SDP1) + e_crit(drv, "Fan has stopped, replace the adapter\n"); + } + + /* bring the link up in the watchdog, this could race with our first + * link up interrupt but shouldn't be a problem */ + adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE; + adapter->link_check_timeout = jiffies; + mod_timer(&adapter->service_timer, jiffies); + + /* Set PF Reset Done bit so PF/VF Mail Ops can work */ + ctrl_ext = IXGBE_READ_REG(hw, IXGBE_CTRL_EXT); + ctrl_ext |= IXGBE_CTRL_EXT_PFRSTD; + IXGBE_WRITE_REG(hw, IXGBE_CTRL_EXT, ctrl_ext); +} + +void ixgbe_reinit_locked(struct ixgbe_adapter *adapter) +{ + /* put off any impending NetWatchDogTimeout */ + netif_trans_update(adapter->netdev); + + while (test_and_set_bit(__IXGBE_RESETTING, &adapter->state)) + usleep_range(1000, 2000); + if (adapter->hw.phy.type == ixgbe_phy_fw) + ixgbe_watchdog_link_is_down(adapter); + ixgbe_down(adapter); + /* + * If SR-IOV enabled then wait a bit before bringing the adapter + * back up to give the VFs time to respond to the reset. The + * two second wait is based upon the watchdog timer cycle in + * the VF driver. + */ + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) + msleep(2000); + ixgbe_up(adapter); + clear_bit(__IXGBE_RESETTING, &adapter->state); +} + +void ixgbe_up(struct ixgbe_adapter *adapter) +{ + /* hardware has been reset, we need to reload some things */ + ixgbe_configure(adapter); + + ixgbe_up_complete(adapter); +} + +static unsigned long ixgbe_get_completion_timeout(struct ixgbe_adapter *adapter) +{ + u16 devctl2; + + pcie_capability_read_word(adapter->pdev, PCI_EXP_DEVCTL2, &devctl2); + + switch (devctl2 & IXGBE_PCIDEVCTRL2_TIMEO_MASK) { + case IXGBE_PCIDEVCTRL2_17_34s: + case IXGBE_PCIDEVCTRL2_4_8s: + /* For now we cap the upper limit on delay to 2 seconds + * as we end up going up to 34 seconds of delay in worst + * case timeout value. + */ + case IXGBE_PCIDEVCTRL2_1_2s: + return 2000000ul; /* 2.0 s */ + case IXGBE_PCIDEVCTRL2_260_520ms: + return 520000ul; /* 520 ms */ + case IXGBE_PCIDEVCTRL2_65_130ms: + return 130000ul; /* 130 ms */ + case IXGBE_PCIDEVCTRL2_16_32ms: + return 32000ul; /* 32 ms */ + case IXGBE_PCIDEVCTRL2_1_2ms: + return 2000ul; /* 2 ms */ + case IXGBE_PCIDEVCTRL2_50_100us: + return 100ul; /* 100 us */ + case IXGBE_PCIDEVCTRL2_16_32ms_def: + return 32000ul; /* 32 ms */ + default: + break; + } + + /* We shouldn't need to hit this path, but just in case default as + * though completion timeout is not supported and support 32ms. + */ + return 32000ul; +} + +void ixgbe_disable_rx(struct ixgbe_adapter *adapter) +{ + unsigned long wait_delay, delay_interval; + struct ixgbe_hw *hw = &adapter->hw; + int i, wait_loop; + u32 rxdctl; + + /* disable receives */ + hw->mac.ops.disable_rx(hw); + + if (ixgbe_removed(hw->hw_addr)) + return; + + /* disable all enabled Rx queues */ + for (i = 0; i < adapter->num_rx_queues; i++) { + struct ixgbe_ring *ring = adapter->rx_ring[i]; + u8 reg_idx = ring->reg_idx; + + rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx)); + rxdctl &= ~IXGBE_RXDCTL_ENABLE; + rxdctl |= IXGBE_RXDCTL_SWFLSH; + + /* write value back with RXDCTL.ENABLE bit cleared */ + IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl); + } + + /* RXDCTL.EN may not change on 82598 if link is down, so skip it */ + if (hw->mac.type == ixgbe_mac_82598EB && + !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP)) + return; + + /* Determine our minimum delay interval. We will increase this value + * with each subsequent test. This way if the device returns quickly + * we should spend as little time as possible waiting, however as + * the time increases we will wait for larger periods of time. + * + * The trick here is that we increase the interval using the + * following pattern: 1x 3x 5x 7x 9x 11x 13x 15x 17x 19x. The result + * of that wait is that it totals up to 100x whatever interval we + * choose. Since our minimum wait is 100us we can just divide the + * total timeout by 100 to get our minimum delay interval. + */ + delay_interval = ixgbe_get_completion_timeout(adapter) / 100; + + wait_loop = IXGBE_MAX_RX_DESC_POLL; + wait_delay = delay_interval; + + while (wait_loop--) { + usleep_range(wait_delay, wait_delay + 10); + wait_delay += delay_interval * 2; + rxdctl = 0; + + /* OR together the reading of all the active RXDCTL registers, + * and then test the result. We need the disable to complete + * before we start freeing the memory and invalidating the + * DMA mappings. + */ + for (i = 0; i < adapter->num_rx_queues; i++) { + struct ixgbe_ring *ring = adapter->rx_ring[i]; + u8 reg_idx = ring->reg_idx; + + rxdctl |= IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx)); + } + + if (!(rxdctl & IXGBE_RXDCTL_ENABLE)) + return; + } + + e_err(drv, + "RXDCTL.ENABLE for one or more queues not cleared within the polling period\n"); +} + +void ixgbe_disable_tx(struct ixgbe_adapter *adapter) +{ + unsigned long wait_delay, delay_interval; + struct ixgbe_hw *hw = &adapter->hw; + int i, wait_loop; + u32 txdctl; + + if (ixgbe_removed(hw->hw_addr)) + return; + + /* disable all enabled Tx queues */ + for (i = 0; i < adapter->num_tx_queues; i++) { + struct ixgbe_ring *ring = adapter->tx_ring[i]; + u8 reg_idx = ring->reg_idx; + + IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH); + } + + /* disable all enabled XDP Tx queues */ + for (i = 0; i < adapter->num_xdp_queues; i++) { + struct ixgbe_ring *ring = adapter->xdp_ring[i]; + u8 reg_idx = ring->reg_idx; + + IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH); + } + + /* If the link is not up there shouldn't be much in the way of + * pending transactions. Those that are left will be flushed out + * when the reset logic goes through the flush sequence to clean out + * the pending Tx transactions. + */ + if (!(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP)) + goto dma_engine_disable; + + /* Determine our minimum delay interval. We will increase this value + * with each subsequent test. This way if the device returns quickly + * we should spend as little time as possible waiting, however as + * the time increases we will wait for larger periods of time. + * + * The trick here is that we increase the interval using the + * following pattern: 1x 3x 5x 7x 9x 11x 13x 15x 17x 19x. The result + * of that wait is that it totals up to 100x whatever interval we + * choose. Since our minimum wait is 100us we can just divide the + * total timeout by 100 to get our minimum delay interval. + */ + delay_interval = ixgbe_get_completion_timeout(adapter) / 100; + + wait_loop = IXGBE_MAX_RX_DESC_POLL; + wait_delay = delay_interval; + + while (wait_loop--) { + usleep_range(wait_delay, wait_delay + 10); + wait_delay += delay_interval * 2; + txdctl = 0; + + /* OR together the reading of all the active TXDCTL registers, + * and then test the result. We need the disable to complete + * before we start freeing the memory and invalidating the + * DMA mappings. + */ + for (i = 0; i < adapter->num_tx_queues; i++) { + struct ixgbe_ring *ring = adapter->tx_ring[i]; + u8 reg_idx = ring->reg_idx; + + txdctl |= IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx)); + } + for (i = 0; i < adapter->num_xdp_queues; i++) { + struct ixgbe_ring *ring = adapter->xdp_ring[i]; + u8 reg_idx = ring->reg_idx; + + txdctl |= IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx)); + } + + if (!(txdctl & IXGBE_TXDCTL_ENABLE)) + goto dma_engine_disable; + } + + e_err(drv, + "TXDCTL.ENABLE for one or more queues not cleared within the polling period\n"); + +dma_engine_disable: + /* Disable the Tx DMA engine on 82599 and later MAC */ + switch (hw->mac.type) { + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL, + (IXGBE_READ_REG(hw, IXGBE_DMATXCTL) & + ~IXGBE_DMATXCTL_TE)); + fallthrough; + default: + break; + } +} + +void ixgbe_reset(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; + int err; + + if (ixgbe_removed(hw->hw_addr)) + return; + /* lock SFP init bit to prevent race conditions with the watchdog */ + while (test_and_set_bit(__IXGBE_IN_SFP_INIT, &adapter->state)) + usleep_range(1000, 2000); + + /* clear all SFP and link config related flags while holding SFP_INIT */ + adapter->flags2 &= ~(IXGBE_FLAG2_SEARCH_FOR_SFP | + IXGBE_FLAG2_SFP_NEEDS_RESET); + adapter->flags &= ~IXGBE_FLAG_NEED_LINK_CONFIG; + + err = hw->mac.ops.init_hw(hw); + switch (err) { + case 0: + case IXGBE_ERR_SFP_NOT_PRESENT: + case IXGBE_ERR_SFP_NOT_SUPPORTED: + break; + case IXGBE_ERR_MASTER_REQUESTS_PENDING: + e_dev_err("master disable timed out\n"); + break; + case IXGBE_ERR_EEPROM_VERSION: + /* We are running on a pre-production device, log a warning */ + e_dev_warn("This device is a pre-production adapter/LOM. " + "Please be aware there may be issues associated with " + "your hardware. If you are experiencing problems " + "please contact your Intel or hardware " + "representative who provided you with this " + "hardware.\n"); + break; + default: + e_dev_err("Hardware Error: %d\n", err); + } + + clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state); + + /* flush entries out of MAC table */ + ixgbe_flush_sw_mac_table(adapter); + __dev_uc_unsync(netdev, NULL); + + /* do not flush user set addresses */ + ixgbe_mac_set_default_filter(adapter); + + /* update SAN MAC vmdq pool selection */ + if (hw->mac.san_mac_rar_index) + hw->mac.ops.set_vmdq_san_mac(hw, VMDQ_P(0)); + + if (test_bit(__IXGBE_PTP_RUNNING, &adapter->state)) + ixgbe_ptp_reset(adapter); + + if (hw->phy.ops.set_phy_power) { + if (!netif_running(adapter->netdev) && !adapter->wol) + hw->phy.ops.set_phy_power(hw, false); + else + hw->phy.ops.set_phy_power(hw, true); + } +} + +/** + * ixgbe_clean_tx_ring - Free Tx Buffers + * @tx_ring: ring to be cleaned + **/ +static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring) +{ + u16 i = tx_ring->next_to_clean; + struct ixgbe_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i]; + + if (tx_ring->xsk_pool) { + ixgbe_xsk_clean_tx_ring(tx_ring); + goto out; + } + + while (i != tx_ring->next_to_use) { + union ixgbe_adv_tx_desc *eop_desc, *tx_desc; + + /* Free all the Tx ring sk_buffs */ + if (ring_is_xdp(tx_ring)) + xdp_return_frame(tx_buffer->xdpf); + else + dev_kfree_skb_any(tx_buffer->skb); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + + /* check for eop_desc to determine the end of the packet */ + eop_desc = tx_buffer->next_to_watch; + tx_desc = IXGBE_TX_DESC(tx_ring, i); + + /* unmap remaining buffers */ + while (tx_desc != eop_desc) { + tx_buffer++; + tx_desc++; + i++; + if (unlikely(i == tx_ring->count)) { + i = 0; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = IXGBE_TX_DESC(tx_ring, 0); + } + + /* unmap any remaining paged data */ + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + } + + /* move us one more past the eop_desc for start of next pkt */ + tx_buffer++; + i++; + if (unlikely(i == tx_ring->count)) { + i = 0; + tx_buffer = tx_ring->tx_buffer_info; + } + } + + /* reset BQL for queue */ + if (!ring_is_xdp(tx_ring)) + netdev_tx_reset_queue(txring_txq(tx_ring)); + +out: + /* reset next_to_use and next_to_clean */ + tx_ring->next_to_use = 0; + tx_ring->next_to_clean = 0; +} + +/** + * ixgbe_clean_all_rx_rings - Free Rx Buffers for all queues + * @adapter: board private structure + **/ +static void ixgbe_clean_all_rx_rings(struct ixgbe_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_rx_queues; i++) + ixgbe_clean_rx_ring(adapter->rx_ring[i]); +} + +/** + * ixgbe_clean_all_tx_rings - Free Tx Buffers for all queues + * @adapter: board private structure + **/ +static void ixgbe_clean_all_tx_rings(struct ixgbe_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) + ixgbe_clean_tx_ring(adapter->tx_ring[i]); + for (i = 0; i < adapter->num_xdp_queues; i++) + ixgbe_clean_tx_ring(adapter->xdp_ring[i]); +} + +static void ixgbe_fdir_filter_exit(struct ixgbe_adapter *adapter) +{ + struct hlist_node *node2; + struct ixgbe_fdir_filter *filter; + + spin_lock(&adapter->fdir_perfect_lock); + + hlist_for_each_entry_safe(filter, node2, + &adapter->fdir_filter_list, fdir_node) { + hlist_del(&filter->fdir_node); + kfree(filter); + } + adapter->fdir_filter_count = 0; + + spin_unlock(&adapter->fdir_perfect_lock); +} + +void ixgbe_down(struct ixgbe_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct ixgbe_hw *hw = &adapter->hw; + int i; + + /* signal that we are down to the interrupt handler */ + if (test_and_set_bit(__IXGBE_DOWN, &adapter->state)) + return; /* do nothing if already down */ + + /* Shut off incoming Tx traffic */ + netif_tx_stop_all_queues(netdev); + + /* call carrier off first to avoid false dev_watchdog timeouts */ + netif_carrier_off(netdev); + netif_tx_disable(netdev); + + /* Disable Rx */ + ixgbe_disable_rx(adapter); + + /* synchronize_rcu() needed for pending XDP buffers to drain */ + if (adapter->xdp_ring[0]) + synchronize_rcu(); + + ixgbe_irq_disable(adapter); + + ixgbe_napi_disable_all(adapter); + + clear_bit(__IXGBE_RESET_REQUESTED, &adapter->state); + adapter->flags2 &= ~IXGBE_FLAG2_FDIR_REQUIRES_REINIT; + adapter->flags &= ~IXGBE_FLAG_NEED_LINK_UPDATE; + + del_timer_sync(&adapter->service_timer); + + if (adapter->num_vfs) { + /* Clear EITR Select mapping */ + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EITRSEL, 0); + + /* Mark all the VFs as inactive */ + for (i = 0 ; i < adapter->num_vfs; i++) + adapter->vfinfo[i].clear_to_send = false; + + /* ping all the active vfs to let them know we are going down */ + ixgbe_ping_all_vfs(adapter); + + /* Disable all VFTE/VFRE TX/RX */ + ixgbe_disable_tx_rx(adapter); + } + + /* disable transmits in the hardware now that interrupts are off */ + ixgbe_disable_tx(adapter); + + if (!pci_channel_offline(adapter->pdev)) + ixgbe_reset(adapter); + + /* power down the optics for 82599 SFP+ fiber */ + if (hw->mac.ops.disable_tx_laser) + hw->mac.ops.disable_tx_laser(hw); + + ixgbe_clean_all_tx_rings(adapter); + ixgbe_clean_all_rx_rings(adapter); +} + +/** + * ixgbe_eee_capable - helper function to determine EEE support on X550 + * @adapter: board private structure + */ +static void ixgbe_set_eee_capable(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + + switch (hw->device_id) { + case IXGBE_DEV_ID_X550EM_A_1G_T: + case IXGBE_DEV_ID_X550EM_A_1G_T_L: + if (!hw->phy.eee_speeds_supported) + break; + adapter->flags2 |= IXGBE_FLAG2_EEE_CAPABLE; + if (!hw->phy.eee_speeds_advertised) + break; + adapter->flags2 |= IXGBE_FLAG2_EEE_ENABLED; + break; + default: + adapter->flags2 &= ~IXGBE_FLAG2_EEE_CAPABLE; + adapter->flags2 &= ~IXGBE_FLAG2_EEE_ENABLED; + break; + } +} + +/** + * ixgbe_tx_timeout - Respond to a Tx Hang + * @netdev: network interface device structure + * @txqueue: queue number that timed out + **/ +static void ixgbe_tx_timeout(struct net_device *netdev, unsigned int __always_unused txqueue) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + /* Do the reset outside of interrupt context */ + ixgbe_tx_timeout_reset(adapter); +} + +#ifdef CONFIG_IXGBE_DCB +static void ixgbe_init_dcb(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct tc_configuration *tc; + int j; + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + case ixgbe_mac_82599EB: + adapter->dcb_cfg.num_tcs.pg_tcs = MAX_TRAFFIC_CLASS; + adapter->dcb_cfg.num_tcs.pfc_tcs = MAX_TRAFFIC_CLASS; + break; + case ixgbe_mac_X540: + case ixgbe_mac_X550: + adapter->dcb_cfg.num_tcs.pg_tcs = X540_TRAFFIC_CLASS; + adapter->dcb_cfg.num_tcs.pfc_tcs = X540_TRAFFIC_CLASS; + break; + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + default: + adapter->dcb_cfg.num_tcs.pg_tcs = DEF_TRAFFIC_CLASS; + adapter->dcb_cfg.num_tcs.pfc_tcs = DEF_TRAFFIC_CLASS; + break; + } + + /* Configure DCB traffic classes */ + for (j = 0; j < MAX_TRAFFIC_CLASS; j++) { + tc = &adapter->dcb_cfg.tc_config[j]; + tc->path[DCB_TX_CONFIG].bwg_id = 0; + tc->path[DCB_TX_CONFIG].bwg_percent = 12 + (j & 1); + tc->path[DCB_RX_CONFIG].bwg_id = 0; + tc->path[DCB_RX_CONFIG].bwg_percent = 12 + (j & 1); + tc->dcb_pfc = pfc_disabled; + } + + /* Initialize default user to priority mapping, UPx->TC0 */ + tc = &adapter->dcb_cfg.tc_config[0]; + tc->path[DCB_TX_CONFIG].up_to_tc_bitmap = 0xFF; + tc->path[DCB_RX_CONFIG].up_to_tc_bitmap = 0xFF; + + adapter->dcb_cfg.bw_percentage[DCB_TX_CONFIG][0] = 100; + adapter->dcb_cfg.bw_percentage[DCB_RX_CONFIG][0] = 100; + adapter->dcb_cfg.pfc_mode_enable = false; + adapter->dcb_set_bitmap = 0x00; + if (adapter->flags & IXGBE_FLAG_DCB_CAPABLE) + adapter->dcbx_cap = DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_CEE; + memcpy(&adapter->temp_dcb_cfg, &adapter->dcb_cfg, + sizeof(adapter->temp_dcb_cfg)); +} +#endif + +/** + * ixgbe_sw_init - Initialize general software structures (struct ixgbe_adapter) + * @adapter: board private structure to initialize + * @ii: pointer to ixgbe_info for device + * + * ixgbe_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 ixgbe_sw_init(struct ixgbe_adapter *adapter, + const struct ixgbe_info *ii) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct pci_dev *pdev = adapter->pdev; + unsigned int rss, fdir; + u32 fwsm; + int i; + + /* PCI config space info */ + + hw->vendor_id = pdev->vendor; + hw->device_id = pdev->device; + hw->revision_id = pdev->revision; + hw->subsystem_vendor_id = pdev->subsystem_vendor; + hw->subsystem_device_id = pdev->subsystem_device; + + /* get_invariants needs the device IDs */ + ii->get_invariants(hw); + + /* Set common capability flags and settings */ + rss = min_t(int, ixgbe_max_rss_indices(adapter), num_online_cpus()); + adapter->ring_feature[RING_F_RSS].limit = rss; + adapter->flags2 |= IXGBE_FLAG2_RSC_CAPABLE; + adapter->max_q_vectors = MAX_Q_VECTORS_82599; + adapter->atr_sample_rate = 20; + fdir = min_t(int, IXGBE_MAX_FDIR_INDICES, num_online_cpus()); + adapter->ring_feature[RING_F_FDIR].limit = fdir; + adapter->fdir_pballoc = IXGBE_FDIR_PBALLOC_64K; + adapter->ring_feature[RING_F_VMDQ].limit = 1; +#ifdef CONFIG_IXGBE_DCA + adapter->flags |= IXGBE_FLAG_DCA_CAPABLE; +#endif +#ifdef CONFIG_IXGBE_DCB + adapter->flags |= IXGBE_FLAG_DCB_CAPABLE; + adapter->flags &= ~IXGBE_FLAG_DCB_ENABLED; +#endif +#ifdef IXGBE_FCOE + adapter->flags |= IXGBE_FLAG_FCOE_CAPABLE; + adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED; +#ifdef CONFIG_IXGBE_DCB + /* Default traffic class to use for FCoE */ + adapter->fcoe.up = IXGBE_FCOE_DEFTC; +#endif /* CONFIG_IXGBE_DCB */ +#endif /* IXGBE_FCOE */ + + /* initialize static ixgbe jump table entries */ + adapter->jump_tables[0] = kzalloc(sizeof(*adapter->jump_tables[0]), + GFP_KERNEL); + if (!adapter->jump_tables[0]) + return -ENOMEM; + adapter->jump_tables[0]->mat = ixgbe_ipv4_fields; + + for (i = 1; i < IXGBE_MAX_LINK_HANDLE; i++) + adapter->jump_tables[i] = NULL; + + adapter->mac_table = kcalloc(hw->mac.num_rar_entries, + sizeof(struct ixgbe_mac_addr), + GFP_KERNEL); + if (!adapter->mac_table) + return -ENOMEM; + + if (ixgbe_init_rss_key(adapter)) + return -ENOMEM; + + adapter->af_xdp_zc_qps = bitmap_zalloc(MAX_XDP_QUEUES, GFP_KERNEL); + if (!adapter->af_xdp_zc_qps) + return -ENOMEM; + + /* Set MAC specific capability flags and exceptions */ + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + adapter->flags2 &= ~IXGBE_FLAG2_RSC_CAPABLE; + + if (hw->device_id == IXGBE_DEV_ID_82598AT) + adapter->flags |= IXGBE_FLAG_FAN_FAIL_CAPABLE; + + adapter->max_q_vectors = MAX_Q_VECTORS_82598; + adapter->ring_feature[RING_F_FDIR].limit = 0; + adapter->atr_sample_rate = 0; + adapter->fdir_pballoc = 0; +#ifdef IXGBE_FCOE + adapter->flags &= ~IXGBE_FLAG_FCOE_CAPABLE; + adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED; +#ifdef CONFIG_IXGBE_DCB + adapter->fcoe.up = 0; +#endif /* IXGBE_DCB */ +#endif /* IXGBE_FCOE */ + break; + case ixgbe_mac_82599EB: + if (hw->device_id == IXGBE_DEV_ID_82599_T3_LOM) + adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE; + break; + case ixgbe_mac_X540: + fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw)); + if (fwsm & IXGBE_FWSM_TS_ENABLED) + adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE; + break; + case ixgbe_mac_x550em_a: + switch (hw->device_id) { + case IXGBE_DEV_ID_X550EM_A_1G_T: + case IXGBE_DEV_ID_X550EM_A_1G_T_L: + adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE; + break; + default: + break; + } + fallthrough; + case ixgbe_mac_X550EM_x: +#ifdef CONFIG_IXGBE_DCB + adapter->flags &= ~IXGBE_FLAG_DCB_CAPABLE; +#endif +#ifdef IXGBE_FCOE + adapter->flags &= ~IXGBE_FLAG_FCOE_CAPABLE; +#ifdef CONFIG_IXGBE_DCB + adapter->fcoe.up = 0; +#endif /* IXGBE_DCB */ +#endif /* IXGBE_FCOE */ + fallthrough; + case ixgbe_mac_X550: + if (hw->mac.type == ixgbe_mac_X550) + adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE; +#ifdef CONFIG_IXGBE_DCA + adapter->flags &= ~IXGBE_FLAG_DCA_CAPABLE; +#endif + break; + default: + break; + } + +#ifdef IXGBE_FCOE + /* FCoE support exists, always init the FCoE lock */ + spin_lock_init(&adapter->fcoe.lock); + +#endif + /* n-tuple support exists, always init our spinlock */ + spin_lock_init(&adapter->fdir_perfect_lock); + + /* init spinlock to avoid concurrency of VF resources */ + spin_lock_init(&adapter->vfs_lock); + +#ifdef CONFIG_IXGBE_DCB + ixgbe_init_dcb(adapter); +#endif + ixgbe_init_ipsec_offload(adapter); + + /* default flow control settings */ + hw->fc.requested_mode = ixgbe_fc_full; + hw->fc.current_mode = ixgbe_fc_full; /* init for ethtool output */ + ixgbe_pbthresh_setup(adapter); + hw->fc.pause_time = IXGBE_DEFAULT_FCPAUSE; + hw->fc.send_xon = true; + hw->fc.disable_fc_autoneg = ixgbe_device_supports_autoneg_fc(hw); + +#ifdef CONFIG_PCI_IOV + if (max_vfs > 0) + e_dev_warn("Enabling SR-IOV VFs using the max_vfs module parameter is deprecated - please use the pci sysfs interface instead.\n"); + + /* assign number of SR-IOV VFs */ + if (hw->mac.type != ixgbe_mac_82598EB) { + if (max_vfs > IXGBE_MAX_VFS_DRV_LIMIT) { + max_vfs = 0; + e_dev_warn("max_vfs parameter out of range. Not assigning any SR-IOV VFs\n"); + } + } +#endif /* CONFIG_PCI_IOV */ + + /* enable itr by default in dynamic mode */ + adapter->rx_itr_setting = 1; + adapter->tx_itr_setting = 1; + + /* set default ring sizes */ + adapter->tx_ring_count = IXGBE_DEFAULT_TXD; + adapter->rx_ring_count = IXGBE_DEFAULT_RXD; + + /* set default work limits */ + adapter->tx_work_limit = IXGBE_DEFAULT_TX_WORK; + + /* initialize eeprom parameters */ + if (ixgbe_init_eeprom_params_generic(hw)) { + e_dev_err("EEPROM initialization failed\n"); + return -EIO; + } + + /* PF holds first pool slot */ + set_bit(0, adapter->fwd_bitmask); + set_bit(__IXGBE_DOWN, &adapter->state); + + return 0; +} + +/** + * ixgbe_setup_tx_resources - allocate Tx resources (Descriptors) + * @tx_ring: tx descriptor ring (for a specific queue) to setup + * + * Return 0 on success, negative on failure + **/ +int ixgbe_setup_tx_resources(struct ixgbe_ring *tx_ring) +{ + struct device *dev = tx_ring->dev; + int orig_node = dev_to_node(dev); + int ring_node = NUMA_NO_NODE; + int size; + + size = sizeof(struct ixgbe_tx_buffer) * tx_ring->count; + + if (tx_ring->q_vector) + ring_node = tx_ring->q_vector->numa_node; + + tx_ring->tx_buffer_info = vmalloc_node(size, ring_node); + if (!tx_ring->tx_buffer_info) + tx_ring->tx_buffer_info = vmalloc(size); + if (!tx_ring->tx_buffer_info) + goto err; + + /* round up to nearest 4K */ + tx_ring->size = tx_ring->count * sizeof(union ixgbe_adv_tx_desc); + tx_ring->size = ALIGN(tx_ring->size, 4096); + + set_dev_node(dev, ring_node); + tx_ring->desc = dma_alloc_coherent(dev, + tx_ring->size, + &tx_ring->dma, + GFP_KERNEL); + set_dev_node(dev, orig_node); + if (!tx_ring->desc) + tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size, + &tx_ring->dma, GFP_KERNEL); + if (!tx_ring->desc) + goto err; + + tx_ring->next_to_use = 0; + tx_ring->next_to_clean = 0; + return 0; + +err: + vfree(tx_ring->tx_buffer_info); + tx_ring->tx_buffer_info = NULL; + dev_err(dev, "Unable to allocate memory for the Tx descriptor ring\n"); + return -ENOMEM; +} + +/** + * ixgbe_setup_all_tx_resources - allocate all queues Tx resources + * @adapter: board private structure + * + * If this function returns with an error, then it's possible one or + * more of the rings is populated (while the rest are not). It is the + * callers duty to clean those orphaned rings. + * + * Return 0 on success, negative on failure + **/ +static int ixgbe_setup_all_tx_resources(struct ixgbe_adapter *adapter) +{ + int i, j = 0, err = 0; + + for (i = 0; i < adapter->num_tx_queues; i++) { + err = ixgbe_setup_tx_resources(adapter->tx_ring[i]); + if (!err) + continue; + + e_err(probe, "Allocation for Tx Queue %u failed\n", i); + goto err_setup_tx; + } + for (j = 0; j < adapter->num_xdp_queues; j++) { + err = ixgbe_setup_tx_resources(adapter->xdp_ring[j]); + if (!err) + continue; + + e_err(probe, "Allocation for Tx Queue %u failed\n", j); + goto err_setup_tx; + } + + return 0; +err_setup_tx: + /* rewind the index freeing the rings as we go */ + while (j--) + ixgbe_free_tx_resources(adapter->xdp_ring[j]); + while (i--) + ixgbe_free_tx_resources(adapter->tx_ring[i]); + return err; +} + +/** + * ixgbe_setup_rx_resources - allocate Rx resources (Descriptors) + * @adapter: pointer to ixgbe_adapter + * @rx_ring: rx descriptor ring (for a specific queue) to setup + * + * Returns 0 on success, negative on failure + **/ +int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter, + struct ixgbe_ring *rx_ring) +{ + struct device *dev = rx_ring->dev; + int orig_node = dev_to_node(dev); + int ring_node = NUMA_NO_NODE; + int size; + + size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count; + + if (rx_ring->q_vector) + ring_node = rx_ring->q_vector->numa_node; + + rx_ring->rx_buffer_info = vmalloc_node(size, ring_node); + if (!rx_ring->rx_buffer_info) + rx_ring->rx_buffer_info = vmalloc(size); + if (!rx_ring->rx_buffer_info) + goto err; + + /* Round up to nearest 4K */ + rx_ring->size = rx_ring->count * sizeof(union ixgbe_adv_rx_desc); + rx_ring->size = ALIGN(rx_ring->size, 4096); + + set_dev_node(dev, ring_node); + rx_ring->desc = dma_alloc_coherent(dev, + rx_ring->size, + &rx_ring->dma, + GFP_KERNEL); + set_dev_node(dev, orig_node); + if (!rx_ring->desc) + rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size, + &rx_ring->dma, GFP_KERNEL); + if (!rx_ring->desc) + goto err; + + rx_ring->next_to_clean = 0; + rx_ring->next_to_use = 0; + + /* XDP RX-queue info */ + if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, adapter->netdev, + rx_ring->queue_index) < 0) + goto err; + + rx_ring->xdp_prog = adapter->xdp_prog; + + return 0; +err: + vfree(rx_ring->rx_buffer_info); + rx_ring->rx_buffer_info = NULL; + dev_err(dev, "Unable to allocate memory for the Rx descriptor ring\n"); + return -ENOMEM; +} + +/** + * ixgbe_setup_all_rx_resources - allocate all queues Rx resources + * @adapter: board private structure + * + * If this function returns with an error, then it's possible one or + * more of the rings is populated (while the rest are not). It is the + * callers duty to clean those orphaned rings. + * + * Return 0 on success, negative on failure + **/ +static int ixgbe_setup_all_rx_resources(struct ixgbe_adapter *adapter) +{ + int i, err = 0; + + for (i = 0; i < adapter->num_rx_queues; i++) { + err = ixgbe_setup_rx_resources(adapter, adapter->rx_ring[i]); + if (!err) + continue; + + e_err(probe, "Allocation for Rx Queue %u failed\n", i); + goto err_setup_rx; + } + +#ifdef IXGBE_FCOE + err = ixgbe_setup_fcoe_ddp_resources(adapter); + if (!err) +#endif + return 0; +err_setup_rx: + /* rewind the index freeing the rings as we go */ + while (i--) + ixgbe_free_rx_resources(adapter->rx_ring[i]); + return err; +} + +/** + * ixgbe_free_tx_resources - Free Tx Resources per Queue + * @tx_ring: Tx descriptor ring for a specific queue + * + * Free all transmit software resources + **/ +void ixgbe_free_tx_resources(struct ixgbe_ring *tx_ring) +{ + ixgbe_clean_tx_ring(tx_ring); + + vfree(tx_ring->tx_buffer_info); + tx_ring->tx_buffer_info = NULL; + + /* if not set, then don't free */ + if (!tx_ring->desc) + return; + + dma_free_coherent(tx_ring->dev, tx_ring->size, + tx_ring->desc, tx_ring->dma); + + tx_ring->desc = NULL; +} + +/** + * ixgbe_free_all_tx_resources - Free Tx Resources for All Queues + * @adapter: board private structure + * + * Free all transmit software resources + **/ +static void ixgbe_free_all_tx_resources(struct ixgbe_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) + if (adapter->tx_ring[i]->desc) + ixgbe_free_tx_resources(adapter->tx_ring[i]); + for (i = 0; i < adapter->num_xdp_queues; i++) + if (adapter->xdp_ring[i]->desc) + ixgbe_free_tx_resources(adapter->xdp_ring[i]); +} + +/** + * ixgbe_free_rx_resources - Free Rx Resources + * @rx_ring: ring to clean the resources from + * + * Free all receive software resources + **/ +void ixgbe_free_rx_resources(struct ixgbe_ring *rx_ring) +{ + ixgbe_clean_rx_ring(rx_ring); + + rx_ring->xdp_prog = NULL; + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); + vfree(rx_ring->rx_buffer_info); + rx_ring->rx_buffer_info = NULL; + + /* if not set, then don't free */ + if (!rx_ring->desc) + return; + + dma_free_coherent(rx_ring->dev, rx_ring->size, + rx_ring->desc, rx_ring->dma); + + rx_ring->desc = NULL; +} + +/** + * ixgbe_free_all_rx_resources - Free Rx Resources for All Queues + * @adapter: board private structure + * + * Free all receive software resources + **/ +static void ixgbe_free_all_rx_resources(struct ixgbe_adapter *adapter) +{ + int i; + +#ifdef IXGBE_FCOE + ixgbe_free_fcoe_ddp_resources(adapter); + +#endif + for (i = 0; i < adapter->num_rx_queues; i++) + if (adapter->rx_ring[i]->desc) + ixgbe_free_rx_resources(adapter->rx_ring[i]); +} + +/** + * ixgbe_max_xdp_frame_size - returns the maximum allowed frame size for XDP + * @adapter: device handle, pointer to adapter + */ +static int ixgbe_max_xdp_frame_size(struct ixgbe_adapter *adapter) +{ + if (PAGE_SIZE >= 8192 || adapter->flags2 & IXGBE_FLAG2_RX_LEGACY) + return IXGBE_RXBUFFER_2K; + else + return IXGBE_RXBUFFER_3K; +} + +/** + * ixgbe_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 ixgbe_change_mtu(struct net_device *netdev, int new_mtu) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + if (ixgbe_enabled_xdp_adapter(adapter)) { + int new_frame_size = new_mtu + IXGBE_PKT_HDR_PAD; + + if (new_frame_size > ixgbe_max_xdp_frame_size(adapter)) { + e_warn(probe, "Requested MTU size is not supported with XDP\n"); + return -EINVAL; + } + } + + /* + * For 82599EB we cannot allow legacy VFs to enable their receive + * paths when MTU greater than 1500 is configured. So display a + * warning that legacy VFs will be disabled. + */ + if ((adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) && + (adapter->hw.mac.type == ixgbe_mac_82599EB) && + (new_mtu > ETH_DATA_LEN)) + e_warn(probe, "Setting MTU > 1500 will disable legacy VFs\n"); + + netdev_dbg(netdev, "changing MTU from %d to %d\n", + netdev->mtu, new_mtu); + + /* must set new MTU before calling down or up */ + netdev->mtu = new_mtu; + + if (netif_running(netdev)) + ixgbe_reinit_locked(adapter); + + return 0; +} + +/** + * ixgbe_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. + **/ +int ixgbe_open(struct net_device *netdev) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + int err, queues; + + /* disallow open during test */ + if (test_bit(__IXGBE_TESTING, &adapter->state)) + return -EBUSY; + + netif_carrier_off(netdev); + + /* allocate transmit descriptors */ + err = ixgbe_setup_all_tx_resources(adapter); + if (err) + goto err_setup_tx; + + /* allocate receive descriptors */ + err = ixgbe_setup_all_rx_resources(adapter); + if (err) + goto err_setup_rx; + + ixgbe_configure(adapter); + + err = ixgbe_request_irq(adapter); + if (err) + goto err_req_irq; + + /* Notify the stack of the actual queue counts. */ + queues = adapter->num_tx_queues; + err = netif_set_real_num_tx_queues(netdev, queues); + if (err) + goto err_set_queues; + + queues = adapter->num_rx_queues; + err = netif_set_real_num_rx_queues(netdev, queues); + if (err) + goto err_set_queues; + + ixgbe_ptp_init(adapter); + + ixgbe_up_complete(adapter); + + udp_tunnel_nic_reset_ntf(netdev); + + return 0; + +err_set_queues: + ixgbe_free_irq(adapter); +err_req_irq: + ixgbe_free_all_rx_resources(adapter); + if (hw->phy.ops.set_phy_power && !adapter->wol) + hw->phy.ops.set_phy_power(&adapter->hw, false); +err_setup_rx: + ixgbe_free_all_tx_resources(adapter); +err_setup_tx: + ixgbe_reset(adapter); + + return err; +} + +static void ixgbe_close_suspend(struct ixgbe_adapter *adapter) +{ + ixgbe_ptp_suspend(adapter); + + if (adapter->hw.phy.ops.enter_lplu) { + adapter->hw.phy.reset_disable = true; + ixgbe_down(adapter); + adapter->hw.phy.ops.enter_lplu(&adapter->hw); + adapter->hw.phy.reset_disable = false; + } else { + ixgbe_down(adapter); + } + + ixgbe_free_irq(adapter); + + ixgbe_free_all_tx_resources(adapter); + ixgbe_free_all_rx_resources(adapter); +} + +/** + * ixgbe_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. + **/ +int ixgbe_close(struct net_device *netdev) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + ixgbe_ptp_stop(adapter); + + if (netif_device_present(netdev)) + ixgbe_close_suspend(adapter); + + ixgbe_fdir_filter_exit(adapter); + + ixgbe_release_hw_control(adapter); + + return 0; +} + +static int __maybe_unused ixgbe_resume(struct device *dev_d) +{ + struct pci_dev *pdev = to_pci_dev(dev_d); + struct ixgbe_adapter *adapter = pci_get_drvdata(pdev); + struct net_device *netdev = adapter->netdev; + u32 err; + + adapter->hw.hw_addr = adapter->io_addr; + + err = pci_enable_device_mem(pdev); + if (err) { + e_dev_err("Cannot enable PCI device from suspend\n"); + return err; + } + smp_mb__before_atomic(); + clear_bit(__IXGBE_DISABLED, &adapter->state); + pci_set_master(pdev); + + device_wakeup_disable(dev_d); + + ixgbe_reset(adapter); + + IXGBE_WRITE_REG(&adapter->hw, IXGBE_WUS, ~0); + + rtnl_lock(); + err = ixgbe_init_interrupt_scheme(adapter); + if (!err && netif_running(netdev)) + err = ixgbe_open(netdev); + + + if (!err) + netif_device_attach(netdev); + rtnl_unlock(); + + return err; +} + +static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) +{ + struct ixgbe_adapter *adapter = pci_get_drvdata(pdev); + struct net_device *netdev = adapter->netdev; + struct ixgbe_hw *hw = &adapter->hw; + u32 ctrl; + u32 wufc = adapter->wol; + + rtnl_lock(); + netif_device_detach(netdev); + + if (netif_running(netdev)) + ixgbe_close_suspend(adapter); + + ixgbe_clear_interrupt_scheme(adapter); + rtnl_unlock(); + + if (hw->mac.ops.stop_link_on_d3) + hw->mac.ops.stop_link_on_d3(hw); + + if (wufc) { + u32 fctrl; + + ixgbe_set_rx_mode(netdev); + + /* enable the optics for 82599 SFP+ fiber as we can WoL */ + if (hw->mac.ops.enable_tx_laser) + hw->mac.ops.enable_tx_laser(hw); + + /* enable the reception of multicast packets */ + fctrl = IXGBE_READ_REG(hw, IXGBE_FCTRL); + fctrl |= IXGBE_FCTRL_MPE; + IXGBE_WRITE_REG(hw, IXGBE_FCTRL, fctrl); + + ctrl = IXGBE_READ_REG(hw, IXGBE_CTRL); + ctrl |= IXGBE_CTRL_GIO_DIS; + IXGBE_WRITE_REG(hw, IXGBE_CTRL, ctrl); + + IXGBE_WRITE_REG(hw, IXGBE_WUFC, wufc); + } else { + IXGBE_WRITE_REG(hw, IXGBE_WUC, 0); + IXGBE_WRITE_REG(hw, IXGBE_WUFC, 0); + } + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + pci_wake_from_d3(pdev, false); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + pci_wake_from_d3(pdev, !!wufc); + break; + default: + break; + } + + *enable_wake = !!wufc; + if (hw->phy.ops.set_phy_power && !*enable_wake) + hw->phy.ops.set_phy_power(hw, false); + + ixgbe_release_hw_control(adapter); + + if (!test_and_set_bit(__IXGBE_DISABLED, &adapter->state)) + pci_disable_device(pdev); + + return 0; +} + +static int __maybe_unused ixgbe_suspend(struct device *dev_d) +{ + struct pci_dev *pdev = to_pci_dev(dev_d); + int retval; + bool wake; + + retval = __ixgbe_shutdown(pdev, &wake); + + device_set_wakeup_enable(dev_d, wake); + + return retval; +} + +static void ixgbe_shutdown(struct pci_dev *pdev) +{ + bool wake; + + __ixgbe_shutdown(pdev, &wake); + + if (system_state == SYSTEM_POWER_OFF) { + pci_wake_from_d3(pdev, wake); + pci_set_power_state(pdev, PCI_D3hot); + } +} + +/** + * ixgbe_update_stats - Update the board statistics counters. + * @adapter: board private structure + **/ +void ixgbe_update_stats(struct ixgbe_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_hw_stats *hwstats = &adapter->stats; + u64 total_mpc = 0; + u32 i, missed_rx = 0, mpc, bprc, lxon, lxoff, xon_off_tot; + u64 non_eop_descs = 0, restart_queue = 0, tx_busy = 0; + u64 alloc_rx_page_failed = 0, alloc_rx_buff_failed = 0; + u64 alloc_rx_page = 0; + u64 bytes = 0, packets = 0, hw_csum_rx_error = 0; + + if (test_bit(__IXGBE_DOWN, &adapter->state) || + test_bit(__IXGBE_RESETTING, &adapter->state)) + return; + + if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) { + u64 rsc_count = 0; + u64 rsc_flush = 0; + for (i = 0; i < adapter->num_rx_queues; i++) { + rsc_count += adapter->rx_ring[i]->rx_stats.rsc_count; + rsc_flush += adapter->rx_ring[i]->rx_stats.rsc_flush; + } + adapter->rsc_total_count = rsc_count; + adapter->rsc_total_flush = rsc_flush; + } + + for (i = 0; i < adapter->num_rx_queues; i++) { + struct ixgbe_ring *rx_ring = READ_ONCE(adapter->rx_ring[i]); + + if (!rx_ring) + continue; + non_eop_descs += rx_ring->rx_stats.non_eop_descs; + alloc_rx_page += rx_ring->rx_stats.alloc_rx_page; + alloc_rx_page_failed += rx_ring->rx_stats.alloc_rx_page_failed; + alloc_rx_buff_failed += rx_ring->rx_stats.alloc_rx_buff_failed; + hw_csum_rx_error += rx_ring->rx_stats.csum_err; + bytes += rx_ring->stats.bytes; + packets += rx_ring->stats.packets; + } + adapter->non_eop_descs = non_eop_descs; + adapter->alloc_rx_page = alloc_rx_page; + adapter->alloc_rx_page_failed = alloc_rx_page_failed; + adapter->alloc_rx_buff_failed = alloc_rx_buff_failed; + adapter->hw_csum_rx_error = hw_csum_rx_error; + netdev->stats.rx_bytes = bytes; + netdev->stats.rx_packets = packets; + + bytes = 0; + packets = 0; + /* gather some stats to the adapter struct that are per queue */ + for (i = 0; i < adapter->num_tx_queues; i++) { + struct ixgbe_ring *tx_ring = READ_ONCE(adapter->tx_ring[i]); + + if (!tx_ring) + continue; + restart_queue += tx_ring->tx_stats.restart_queue; + tx_busy += tx_ring->tx_stats.tx_busy; + bytes += tx_ring->stats.bytes; + packets += tx_ring->stats.packets; + } + for (i = 0; i < adapter->num_xdp_queues; i++) { + struct ixgbe_ring *xdp_ring = READ_ONCE(adapter->xdp_ring[i]); + + if (!xdp_ring) + continue; + restart_queue += xdp_ring->tx_stats.restart_queue; + tx_busy += xdp_ring->tx_stats.tx_busy; + bytes += xdp_ring->stats.bytes; + packets += xdp_ring->stats.packets; + } + adapter->restart_queue = restart_queue; + adapter->tx_busy = tx_busy; + netdev->stats.tx_bytes = bytes; + netdev->stats.tx_packets = packets; + + hwstats->crcerrs += IXGBE_READ_REG(hw, IXGBE_CRCERRS); + + /* 8 register reads */ + for (i = 0; i < 8; i++) { + /* for packet buffers not used, the register should read 0 */ + mpc = IXGBE_READ_REG(hw, IXGBE_MPC(i)); + missed_rx += mpc; + hwstats->mpc[i] += mpc; + total_mpc += hwstats->mpc[i]; + hwstats->pxontxc[i] += IXGBE_READ_REG(hw, IXGBE_PXONTXC(i)); + hwstats->pxofftxc[i] += IXGBE_READ_REG(hw, IXGBE_PXOFFTXC(i)); + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + hwstats->rnbc[i] += IXGBE_READ_REG(hw, IXGBE_RNBC(i)); + hwstats->qbtc[i] += IXGBE_READ_REG(hw, IXGBE_QBTC(i)); + hwstats->qbrc[i] += IXGBE_READ_REG(hw, IXGBE_QBRC(i)); + hwstats->pxonrxc[i] += + IXGBE_READ_REG(hw, IXGBE_PXONRXC(i)); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + hwstats->pxonrxc[i] += + IXGBE_READ_REG(hw, IXGBE_PXONRXCNT(i)); + break; + default: + break; + } + } + + /*16 register reads */ + for (i = 0; i < 16; i++) { + hwstats->qptc[i] += IXGBE_READ_REG(hw, IXGBE_QPTC(i)); + hwstats->qprc[i] += IXGBE_READ_REG(hw, IXGBE_QPRC(i)); + if ((hw->mac.type == ixgbe_mac_82599EB) || + (hw->mac.type == ixgbe_mac_X540) || + (hw->mac.type == ixgbe_mac_X550) || + (hw->mac.type == ixgbe_mac_X550EM_x) || + (hw->mac.type == ixgbe_mac_x550em_a)) { + hwstats->qbtc[i] += IXGBE_READ_REG(hw, IXGBE_QBTC_L(i)); + IXGBE_READ_REG(hw, IXGBE_QBTC_H(i)); /* to clear */ + hwstats->qbrc[i] += IXGBE_READ_REG(hw, IXGBE_QBRC_L(i)); + IXGBE_READ_REG(hw, IXGBE_QBRC_H(i)); /* to clear */ + } + } + + hwstats->gprc += IXGBE_READ_REG(hw, IXGBE_GPRC); + /* work around hardware counting issue */ + hwstats->gprc -= missed_rx; + + ixgbe_update_xoff_received(adapter); + + /* 82598 hardware only has a 32 bit counter in the high register */ + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + hwstats->lxonrxc += IXGBE_READ_REG(hw, IXGBE_LXONRXC); + hwstats->gorc += IXGBE_READ_REG(hw, IXGBE_GORCH); + hwstats->gotc += IXGBE_READ_REG(hw, IXGBE_GOTCH); + hwstats->tor += IXGBE_READ_REG(hw, IXGBE_TORH); + break; + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + /* OS2BMC stats are X540 and later */ + hwstats->o2bgptc += IXGBE_READ_REG(hw, IXGBE_O2BGPTC); + hwstats->o2bspc += IXGBE_READ_REG(hw, IXGBE_O2BSPC); + hwstats->b2ospc += IXGBE_READ_REG(hw, IXGBE_B2OSPC); + hwstats->b2ogprc += IXGBE_READ_REG(hw, IXGBE_B2OGPRC); + fallthrough; + case ixgbe_mac_82599EB: + for (i = 0; i < 16; i++) + adapter->hw_rx_no_dma_resources += + IXGBE_READ_REG(hw, IXGBE_QPRDC(i)); + hwstats->gorc += IXGBE_READ_REG(hw, IXGBE_GORCL); + IXGBE_READ_REG(hw, IXGBE_GORCH); /* to clear */ + hwstats->gotc += IXGBE_READ_REG(hw, IXGBE_GOTCL); + IXGBE_READ_REG(hw, IXGBE_GOTCH); /* to clear */ + hwstats->tor += IXGBE_READ_REG(hw, IXGBE_TORL); + IXGBE_READ_REG(hw, IXGBE_TORH); /* to clear */ + hwstats->lxonrxc += IXGBE_READ_REG(hw, IXGBE_LXONRXCNT); + hwstats->fdirmatch += IXGBE_READ_REG(hw, IXGBE_FDIRMATCH); + hwstats->fdirmiss += IXGBE_READ_REG(hw, IXGBE_FDIRMISS); +#ifdef IXGBE_FCOE + hwstats->fccrc += IXGBE_READ_REG(hw, IXGBE_FCCRC); + hwstats->fcoerpdc += IXGBE_READ_REG(hw, IXGBE_FCOERPDC); + hwstats->fcoeprc += IXGBE_READ_REG(hw, IXGBE_FCOEPRC); + hwstats->fcoeptc += IXGBE_READ_REG(hw, IXGBE_FCOEPTC); + hwstats->fcoedwrc += IXGBE_READ_REG(hw, IXGBE_FCOEDWRC); + hwstats->fcoedwtc += IXGBE_READ_REG(hw, IXGBE_FCOEDWTC); + /* Add up per cpu counters for total ddp aloc fail */ + if (adapter->fcoe.ddp_pool) { + struct ixgbe_fcoe *fcoe = &adapter->fcoe; + struct ixgbe_fcoe_ddp_pool *ddp_pool; + unsigned int cpu; + u64 noddp = 0, noddp_ext_buff = 0; + for_each_possible_cpu(cpu) { + ddp_pool = per_cpu_ptr(fcoe->ddp_pool, cpu); + noddp += ddp_pool->noddp; + noddp_ext_buff += ddp_pool->noddp_ext_buff; + } + hwstats->fcoe_noddp = noddp; + hwstats->fcoe_noddp_ext_buff = noddp_ext_buff; + } +#endif /* IXGBE_FCOE */ + break; + default: + break; + } + bprc = IXGBE_READ_REG(hw, IXGBE_BPRC); + hwstats->bprc += bprc; + hwstats->mprc += IXGBE_READ_REG(hw, IXGBE_MPRC); + if (hw->mac.type == ixgbe_mac_82598EB) + hwstats->mprc -= bprc; + hwstats->roc += IXGBE_READ_REG(hw, IXGBE_ROC); + hwstats->prc64 += IXGBE_READ_REG(hw, IXGBE_PRC64); + hwstats->prc127 += IXGBE_READ_REG(hw, IXGBE_PRC127); + hwstats->prc255 += IXGBE_READ_REG(hw, IXGBE_PRC255); + hwstats->prc511 += IXGBE_READ_REG(hw, IXGBE_PRC511); + hwstats->prc1023 += IXGBE_READ_REG(hw, IXGBE_PRC1023); + hwstats->prc1522 += IXGBE_READ_REG(hw, IXGBE_PRC1522); + hwstats->rlec += IXGBE_READ_REG(hw, IXGBE_RLEC); + lxon = IXGBE_READ_REG(hw, IXGBE_LXONTXC); + hwstats->lxontxc += lxon; + lxoff = IXGBE_READ_REG(hw, IXGBE_LXOFFTXC); + hwstats->lxofftxc += lxoff; + hwstats->gptc += IXGBE_READ_REG(hw, IXGBE_GPTC); + hwstats->mptc += IXGBE_READ_REG(hw, IXGBE_MPTC); + /* + * 82598 errata - tx of flow control packets is included in tx counters + */ + xon_off_tot = lxon + lxoff; + hwstats->gptc -= xon_off_tot; + hwstats->mptc -= xon_off_tot; + hwstats->gotc -= (xon_off_tot * (ETH_ZLEN + ETH_FCS_LEN)); + hwstats->ruc += IXGBE_READ_REG(hw, IXGBE_RUC); + hwstats->rfc += IXGBE_READ_REG(hw, IXGBE_RFC); + hwstats->rjc += IXGBE_READ_REG(hw, IXGBE_RJC); + hwstats->tpr += IXGBE_READ_REG(hw, IXGBE_TPR); + hwstats->ptc64 += IXGBE_READ_REG(hw, IXGBE_PTC64); + hwstats->ptc64 -= xon_off_tot; + hwstats->ptc127 += IXGBE_READ_REG(hw, IXGBE_PTC127); + hwstats->ptc255 += IXGBE_READ_REG(hw, IXGBE_PTC255); + hwstats->ptc511 += IXGBE_READ_REG(hw, IXGBE_PTC511); + hwstats->ptc1023 += IXGBE_READ_REG(hw, IXGBE_PTC1023); + hwstats->ptc1522 += IXGBE_READ_REG(hw, IXGBE_PTC1522); + hwstats->bptc += IXGBE_READ_REG(hw, IXGBE_BPTC); + + /* Fill out the OS statistics structure */ + netdev->stats.multicast = hwstats->mprc; + + /* Rx Errors */ + netdev->stats.rx_errors = hwstats->crcerrs + hwstats->rlec; + netdev->stats.rx_dropped = 0; + netdev->stats.rx_length_errors = hwstats->rlec; + netdev->stats.rx_crc_errors = hwstats->crcerrs; + netdev->stats.rx_missed_errors = total_mpc; +} + +/** + * ixgbe_fdir_reinit_subtask - worker thread to reinit FDIR filter table + * @adapter: pointer to the device adapter structure + **/ +static void ixgbe_fdir_reinit_subtask(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int i; + + if (!(adapter->flags2 & IXGBE_FLAG2_FDIR_REQUIRES_REINIT)) + return; + + adapter->flags2 &= ~IXGBE_FLAG2_FDIR_REQUIRES_REINIT; + + /* if interface is down do nothing */ + if (test_bit(__IXGBE_DOWN, &adapter->state)) + return; + + /* do nothing if we are not using signature filters */ + if (!(adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE)) + return; + + adapter->fdir_overflow++; + + if (ixgbe_reinit_fdir_tables_82599(hw) == 0) { + for (i = 0; i < adapter->num_tx_queues; i++) + set_bit(__IXGBE_TX_FDIR_INIT_DONE, + &(adapter->tx_ring[i]->state)); + for (i = 0; i < adapter->num_xdp_queues; i++) + set_bit(__IXGBE_TX_FDIR_INIT_DONE, + &adapter->xdp_ring[i]->state); + /* re-enable flow director interrupts */ + IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_FLOW_DIR); + } else { + e_err(probe, "failed to finish FDIR re-initialization, " + "ignored adding FDIR ATR filters\n"); + } +} + +/** + * ixgbe_check_hang_subtask - check for hung queues and dropped interrupts + * @adapter: pointer to the device adapter structure + * + * This function serves two purposes. First it strobes the interrupt lines + * in order to make certain interrupts are occurring. Secondly it sets the + * bits needed to check for TX hangs. As a result we should immediately + * determine if a hang has occurred. + */ +static void ixgbe_check_hang_subtask(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u64 eics = 0; + int i; + + /* If we're down, removing or resetting, just bail */ + if (test_bit(__IXGBE_DOWN, &adapter->state) || + test_bit(__IXGBE_REMOVING, &adapter->state) || + test_bit(__IXGBE_RESETTING, &adapter->state)) + return; + + /* Force detection of hung controller */ + if (netif_carrier_ok(adapter->netdev)) { + for (i = 0; i < adapter->num_tx_queues; i++) + set_check_for_tx_hang(adapter->tx_ring[i]); + for (i = 0; i < adapter->num_xdp_queues; i++) + set_check_for_tx_hang(adapter->xdp_ring[i]); + } + + if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) { + /* + * for legacy and MSI interrupts don't set any bits + * that are enabled for EIAM, because this operation + * would set *both* EIMS and EICS for any bit in EIAM + */ + IXGBE_WRITE_REG(hw, IXGBE_EICS, + (IXGBE_EICS_TCP_TIMER | IXGBE_EICS_OTHER)); + } else { + /* get one bit for every active tx/rx interrupt vector */ + for (i = 0; i < adapter->num_q_vectors; i++) { + struct ixgbe_q_vector *qv = adapter->q_vector[i]; + if (qv->rx.ring || qv->tx.ring) + eics |= BIT_ULL(i); + } + } + + /* Cause software interrupt to ensure rings are cleaned */ + ixgbe_irq_rearm_queues(adapter, eics); +} + +/** + * ixgbe_watchdog_update_link - update the link status + * @adapter: pointer to the device adapter structure + **/ +static void ixgbe_watchdog_update_link(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 link_speed = adapter->link_speed; + bool link_up = adapter->link_up; + bool pfc_en = adapter->dcb_cfg.pfc_mode_enable; + + if (!(adapter->flags & IXGBE_FLAG_NEED_LINK_UPDATE)) + return; + + if (hw->mac.ops.check_link) { + hw->mac.ops.check_link(hw, &link_speed, &link_up, false); + } else { + /* always assume link is up, if no check link function */ + link_speed = IXGBE_LINK_SPEED_10GB_FULL; + link_up = true; + } + + if (adapter->ixgbe_ieee_pfc) + pfc_en |= !!(adapter->ixgbe_ieee_pfc->pfc_en); + + if (link_up && !((adapter->flags & IXGBE_FLAG_DCB_ENABLED) && pfc_en)) { + hw->mac.ops.fc_enable(hw); + ixgbe_set_rx_drop_en(adapter); + } + + if (link_up || + time_after(jiffies, (adapter->link_check_timeout + + IXGBE_TRY_LINK_TIMEOUT))) { + adapter->flags &= ~IXGBE_FLAG_NEED_LINK_UPDATE; + IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMC_LSC); + IXGBE_WRITE_FLUSH(hw); + } + + adapter->link_up = link_up; + adapter->link_speed = link_speed; +} + +static void ixgbe_update_default_up(struct ixgbe_adapter *adapter) +{ +#ifdef CONFIG_IXGBE_DCB + struct net_device *netdev = adapter->netdev; + struct dcb_app app = { + .selector = IEEE_8021QAZ_APP_SEL_ETHERTYPE, + .protocol = 0, + }; + u8 up = 0; + + if (adapter->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) + up = dcb_ieee_getapp_mask(netdev, &app); + + adapter->default_up = (up > 1) ? (ffs(up) - 1) : 0; +#endif +} + +/** + * ixgbe_watchdog_link_is_up - update netif_carrier status and + * print link up message + * @adapter: pointer to the device adapter structure + **/ +static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct ixgbe_hw *hw = &adapter->hw; + u32 link_speed = adapter->link_speed; + const char *speed_str; + bool flow_rx, flow_tx; + + /* only continue if link was previously down */ + if (netif_carrier_ok(netdev)) + return; + + adapter->flags2 &= ~IXGBE_FLAG2_SEARCH_FOR_SFP; + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: { + u32 frctl = IXGBE_READ_REG(hw, IXGBE_FCTRL); + u32 rmcs = IXGBE_READ_REG(hw, IXGBE_RMCS); + flow_rx = !!(frctl & IXGBE_FCTRL_RFCE); + flow_tx = !!(rmcs & IXGBE_RMCS_TFCE_802_3X); + } + break; + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + case ixgbe_mac_82599EB: { + u32 mflcn = IXGBE_READ_REG(hw, IXGBE_MFLCN); + u32 fccfg = IXGBE_READ_REG(hw, IXGBE_FCCFG); + flow_rx = !!(mflcn & IXGBE_MFLCN_RFCE); + flow_tx = !!(fccfg & IXGBE_FCCFG_TFCE_802_3X); + } + break; + default: + flow_tx = false; + flow_rx = false; + break; + } + + adapter->last_rx_ptp_check = jiffies; + + if (test_bit(__IXGBE_PTP_RUNNING, &adapter->state)) + ixgbe_ptp_start_cyclecounter(adapter); + + switch (link_speed) { + case IXGBE_LINK_SPEED_10GB_FULL: + speed_str = "10 Gbps"; + break; + case IXGBE_LINK_SPEED_5GB_FULL: + speed_str = "5 Gbps"; + break; + case IXGBE_LINK_SPEED_2_5GB_FULL: + speed_str = "2.5 Gbps"; + break; + case IXGBE_LINK_SPEED_1GB_FULL: + speed_str = "1 Gbps"; + break; + case IXGBE_LINK_SPEED_100_FULL: + speed_str = "100 Mbps"; + break; + case IXGBE_LINK_SPEED_10_FULL: + speed_str = "10 Mbps"; + break; + default: + speed_str = "unknown speed"; + break; + } + e_info(drv, "NIC Link is Up %s, Flow Control: %s\n", speed_str, + ((flow_rx && flow_tx) ? "RX/TX" : + (flow_rx ? "RX" : + (flow_tx ? "TX" : "None")))); + + netif_carrier_on(netdev); + ixgbe_check_vf_rate_limit(adapter); + + /* enable transmits */ + netif_tx_wake_all_queues(adapter->netdev); + + /* update the default user priority for VFs */ + ixgbe_update_default_up(adapter); + + /* ping all the active vfs to let them know link has changed */ + ixgbe_ping_all_vfs(adapter); +} + +/** + * ixgbe_watchdog_link_is_down - update netif_carrier status and + * print link down message + * @adapter: pointer to the adapter structure + **/ +static void ixgbe_watchdog_link_is_down(struct ixgbe_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct ixgbe_hw *hw = &adapter->hw; + + adapter->link_up = false; + adapter->link_speed = 0; + + /* only continue if link was up previously */ + if (!netif_carrier_ok(netdev)) + return; + + /* poll for SFP+ cable when link is down */ + if (ixgbe_is_sfp(hw) && hw->mac.type == ixgbe_mac_82598EB) + adapter->flags2 |= IXGBE_FLAG2_SEARCH_FOR_SFP; + + if (test_bit(__IXGBE_PTP_RUNNING, &adapter->state)) + ixgbe_ptp_start_cyclecounter(adapter); + + e_info(drv, "NIC Link is Down\n"); + netif_carrier_off(netdev); + + /* ping all the active vfs to let them know link has changed */ + ixgbe_ping_all_vfs(adapter); +} + +static bool ixgbe_ring_tx_pending(struct ixgbe_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) { + struct ixgbe_ring *tx_ring = adapter->tx_ring[i]; + + if (tx_ring->next_to_use != tx_ring->next_to_clean) + return true; + } + + for (i = 0; i < adapter->num_xdp_queues; i++) { + struct ixgbe_ring *ring = adapter->xdp_ring[i]; + + if (ring->next_to_use != ring->next_to_clean) + return true; + } + + return false; +} + +static bool ixgbe_vf_tx_pending(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; + u32 q_per_pool = __ALIGN_MASK(1, ~vmdq->mask); + + int i, j; + + if (!adapter->num_vfs) + return false; + + /* resetting the PF is only needed for MAC before X550 */ + if (hw->mac.type >= ixgbe_mac_X550) + return false; + + for (i = 0; i < adapter->num_vfs; i++) { + for (j = 0; j < q_per_pool; j++) { + u32 h, t; + + h = IXGBE_READ_REG(hw, IXGBE_PVFTDHN(q_per_pool, i, j)); + t = IXGBE_READ_REG(hw, IXGBE_PVFTDTN(q_per_pool, i, j)); + + if (h != t) + return true; + } + } + + return false; +} + +/** + * ixgbe_watchdog_flush_tx - flush queues on link down + * @adapter: pointer to the device adapter structure + **/ +static void ixgbe_watchdog_flush_tx(struct ixgbe_adapter *adapter) +{ + if (!netif_carrier_ok(adapter->netdev)) { + if (ixgbe_ring_tx_pending(adapter) || + ixgbe_vf_tx_pending(adapter)) { + /* 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). + */ + e_warn(drv, "initiating reset to clear Tx work after link loss\n"); + set_bit(__IXGBE_RESET_REQUESTED, &adapter->state); + } + } +} + +#ifdef CONFIG_PCI_IOV +static void ixgbe_check_for_bad_vf(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct pci_dev *pdev = adapter->pdev; + unsigned int vf; + u32 gpc; + + if (!(netif_carrier_ok(adapter->netdev))) + return; + + gpc = IXGBE_READ_REG(hw, IXGBE_TXDGPC); + if (gpc) /* If incrementing then no need for the check below */ + return; + /* Check to see if a bad DMA write target from an errant or + * malicious VF has caused a PCIe error. If so then we can + * issue a VFLR to the offending VF(s) and then resume without + * requesting a full slot reset. + */ + + if (!pdev) + return; + + /* check status reg for all VFs owned by this PF */ + for (vf = 0; vf < adapter->num_vfs; ++vf) { + struct pci_dev *vfdev = adapter->vfinfo[vf].vfdev; + u16 status_reg; + + if (!vfdev) + continue; + pci_read_config_word(vfdev, PCI_STATUS, &status_reg); + if (status_reg != IXGBE_FAILED_READ_CFG_WORD && + status_reg & PCI_STATUS_REC_MASTER_ABORT) + pcie_flr(vfdev); + } +} + +static void ixgbe_spoof_check(struct ixgbe_adapter *adapter) +{ + u32 ssvpc; + + /* Do not perform spoof check for 82598 or if not in IOV mode */ + if (adapter->hw.mac.type == ixgbe_mac_82598EB || + adapter->num_vfs == 0) + return; + + ssvpc = IXGBE_READ_REG(&adapter->hw, IXGBE_SSVPC); + + /* + * ssvpc register is cleared on read, if zero then no + * spoofed packets in the last interval. + */ + if (!ssvpc) + return; + + e_warn(drv, "%u Spoofed packets detected\n", ssvpc); +} +#else +static void ixgbe_spoof_check(struct ixgbe_adapter __always_unused *adapter) +{ +} + +static void +ixgbe_check_for_bad_vf(struct ixgbe_adapter __always_unused *adapter) +{ +} +#endif /* CONFIG_PCI_IOV */ + + +/** + * ixgbe_watchdog_subtask - check and bring link up + * @adapter: pointer to the device adapter structure + **/ +static void ixgbe_watchdog_subtask(struct ixgbe_adapter *adapter) +{ + /* if interface is down, removing or resetting, do nothing */ + if (test_bit(__IXGBE_DOWN, &adapter->state) || + test_bit(__IXGBE_REMOVING, &adapter->state) || + test_bit(__IXGBE_RESETTING, &adapter->state)) + return; + + ixgbe_watchdog_update_link(adapter); + + if (adapter->link_up) + ixgbe_watchdog_link_is_up(adapter); + else + ixgbe_watchdog_link_is_down(adapter); + + ixgbe_check_for_bad_vf(adapter); + ixgbe_spoof_check(adapter); + ixgbe_update_stats(adapter); + + ixgbe_watchdog_flush_tx(adapter); +} + +/** + * ixgbe_sfp_detection_subtask - poll for SFP+ cable + * @adapter: the ixgbe adapter structure + **/ +static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + s32 err; + + /* not searching for SFP so there is nothing to do here */ + if (!(adapter->flags2 & IXGBE_FLAG2_SEARCH_FOR_SFP) && + !(adapter->flags2 & IXGBE_FLAG2_SFP_NEEDS_RESET)) + return; + + if (adapter->sfp_poll_time && + time_after(adapter->sfp_poll_time, jiffies)) + return; /* If not yet time to poll for SFP */ + + /* someone else is in init, wait until next service event */ + if (test_and_set_bit(__IXGBE_IN_SFP_INIT, &adapter->state)) + return; + + adapter->sfp_poll_time = jiffies + IXGBE_SFP_POLL_JIFFIES - 1; + + err = hw->phy.ops.identify_sfp(hw); + if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) + goto sfp_out; + + if (err == IXGBE_ERR_SFP_NOT_PRESENT) { + /* If no cable is present, then we need to reset + * the next time we find a good cable. */ + adapter->flags2 |= IXGBE_FLAG2_SFP_NEEDS_RESET; + } + + /* exit on error */ + if (err) + goto sfp_out; + + /* exit if reset not needed */ + if (!(adapter->flags2 & IXGBE_FLAG2_SFP_NEEDS_RESET)) + goto sfp_out; + + adapter->flags2 &= ~IXGBE_FLAG2_SFP_NEEDS_RESET; + + /* + * A module may be identified correctly, but the EEPROM may not have + * support for that module. setup_sfp() will fail in that case, so + * we should not allow that module to load. + */ + if (hw->mac.type == ixgbe_mac_82598EB) + err = hw->phy.ops.reset(hw); + else + err = hw->mac.ops.setup_sfp(hw); + + if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) + goto sfp_out; + + adapter->flags |= IXGBE_FLAG_NEED_LINK_CONFIG; + e_info(probe, "detected SFP+: %d\n", hw->phy.sfp_type); + +sfp_out: + clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state); + + if ((err == IXGBE_ERR_SFP_NOT_SUPPORTED) && + (adapter->netdev->reg_state == NETREG_REGISTERED)) { + e_dev_err("failed to initialize because an unsupported " + "SFP+ module type was detected.\n"); + e_dev_err("Reload the driver after installing a " + "supported module.\n"); + unregister_netdev(adapter->netdev); + } +} + +/** + * ixgbe_sfp_link_config_subtask - set up link SFP after module install + * @adapter: the ixgbe adapter structure + **/ +static void ixgbe_sfp_link_config_subtask(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 cap_speed; + u32 speed; + bool autoneg = false; + + if (!(adapter->flags & IXGBE_FLAG_NEED_LINK_CONFIG)) + return; + + /* someone else is in init, wait until next service event */ + if (test_and_set_bit(__IXGBE_IN_SFP_INIT, &adapter->state)) + return; + + adapter->flags &= ~IXGBE_FLAG_NEED_LINK_CONFIG; + + hw->mac.ops.get_link_capabilities(hw, &cap_speed, &autoneg); + + /* advertise highest capable link speed */ + if (!autoneg && (cap_speed & IXGBE_LINK_SPEED_10GB_FULL)) + speed = IXGBE_LINK_SPEED_10GB_FULL; + else + speed = cap_speed & (IXGBE_LINK_SPEED_10GB_FULL | + IXGBE_LINK_SPEED_1GB_FULL); + + if (hw->mac.ops.setup_link) + hw->mac.ops.setup_link(hw, speed, true); + + adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE; + adapter->link_check_timeout = jiffies; + clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state); +} + +/** + * ixgbe_service_timer - Timer Call-back + * @t: pointer to timer_list structure + **/ +static void ixgbe_service_timer(struct timer_list *t) +{ + struct ixgbe_adapter *adapter = from_timer(adapter, t, service_timer); + unsigned long next_event_offset; + + /* poll faster when waiting for link */ + if (adapter->flags & IXGBE_FLAG_NEED_LINK_UPDATE) + next_event_offset = HZ / 10; + else + next_event_offset = HZ * 2; + + /* Reset the timer */ + mod_timer(&adapter->service_timer, next_event_offset + jiffies); + + ixgbe_service_event_schedule(adapter); +} + +static void ixgbe_phy_interrupt_subtask(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 status; + + if (!(adapter->flags2 & IXGBE_FLAG2_PHY_INTERRUPT)) + return; + + adapter->flags2 &= ~IXGBE_FLAG2_PHY_INTERRUPT; + + if (!hw->phy.ops.handle_lasi) + return; + + status = hw->phy.ops.handle_lasi(&adapter->hw); + if (status != IXGBE_ERR_OVERTEMP) + return; + + e_crit(drv, "%s\n", ixgbe_overheat_msg); +} + +static void ixgbe_reset_subtask(struct ixgbe_adapter *adapter) +{ + if (!test_and_clear_bit(__IXGBE_RESET_REQUESTED, &adapter->state)) + return; + + rtnl_lock(); + /* If we're already down, removing or resetting, just bail */ + if (test_bit(__IXGBE_DOWN, &adapter->state) || + test_bit(__IXGBE_REMOVING, &adapter->state) || + test_bit(__IXGBE_RESETTING, &adapter->state)) { + rtnl_unlock(); + return; + } + + ixgbe_dump(adapter); + netdev_err(adapter->netdev, "Reset adapter\n"); + adapter->tx_timeout_count++; + + ixgbe_reinit_locked(adapter); + rtnl_unlock(); +} + +/** + * ixgbe_check_fw_error - Check firmware for errors + * @adapter: the adapter private structure + * + * Check firmware errors in register FWSM + */ +static bool ixgbe_check_fw_error(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 fwsm; + + /* read fwsm.ext_err_ind register and log errors */ + fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw)); + + if (fwsm & IXGBE_FWSM_EXT_ERR_IND_MASK || + !(fwsm & IXGBE_FWSM_FW_VAL_BIT)) + e_dev_warn("Warning firmware error detected FWSM: 0x%08X\n", + fwsm); + + if (hw->mac.ops.fw_recovery_mode && hw->mac.ops.fw_recovery_mode(hw)) { + e_dev_err("Firmware recovery mode detected. Limiting functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode.\n"); + return true; + } + + return false; +} + +/** + * ixgbe_service_task - manages and runs subtasks + * @work: pointer to work_struct containing our data + **/ +static void ixgbe_service_task(struct work_struct *work) +{ + struct ixgbe_adapter *adapter = container_of(work, + struct ixgbe_adapter, + service_task); + if (ixgbe_removed(adapter->hw.hw_addr)) { + if (!test_bit(__IXGBE_DOWN, &adapter->state)) { + rtnl_lock(); + ixgbe_down(adapter); + rtnl_unlock(); + } + ixgbe_service_event_complete(adapter); + return; + } + if (ixgbe_check_fw_error(adapter)) { + if (!test_bit(__IXGBE_DOWN, &adapter->state)) + unregister_netdev(adapter->netdev); + ixgbe_service_event_complete(adapter); + return; + } + ixgbe_reset_subtask(adapter); + ixgbe_phy_interrupt_subtask(adapter); + ixgbe_sfp_detection_subtask(adapter); + ixgbe_sfp_link_config_subtask(adapter); + ixgbe_check_overtemp_subtask(adapter); + ixgbe_watchdog_subtask(adapter); + ixgbe_fdir_reinit_subtask(adapter); + ixgbe_check_hang_subtask(adapter); + + if (test_bit(__IXGBE_PTP_RUNNING, &adapter->state)) { + ixgbe_ptp_overflow_check(adapter); + if (adapter->flags & IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER) + ixgbe_ptp_rx_hang(adapter); + ixgbe_ptp_tx_hang(adapter); + } + + ixgbe_service_event_complete(adapter); +} + +static int ixgbe_tso(struct ixgbe_ring *tx_ring, + struct ixgbe_tx_buffer *first, + u8 *hdr_len, + struct ixgbe_ipsec_tx_data *itd) +{ + u32 vlan_macip_lens, type_tucmd, mss_l4len_idx; + struct sk_buff *skb = first->skb; + union { + struct iphdr *v4; + struct ipv6hdr *v6; + unsigned char *hdr; + } ip; + union { + struct tcphdr *tcp; + struct udphdr *udp; + unsigned char *hdr; + } l4; + u32 paylen, l4_offset; + u32 fceof_saidx = 0; + int err; + + if (skb->ip_summed != CHECKSUM_PARTIAL) + return 0; + + if (!skb_is_gso(skb)) + return 0; + + err = skb_cow_head(skb, 0); + if (err < 0) + return err; + + if (eth_p_mpls(first->protocol)) + ip.hdr = skb_inner_network_header(skb); + else + ip.hdr = skb_network_header(skb); + l4.hdr = skb_checksum_start(skb); + + /* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */ + type_tucmd = (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) ? + IXGBE_ADVTXD_TUCMD_L4T_UDP : IXGBE_ADVTXD_TUCMD_L4T_TCP; + + /* initialize outer IP header fields */ + if (ip.v4->version == 4) { + unsigned char *csum_start = skb_checksum_start(skb); + unsigned char *trans_start = ip.hdr + (ip.v4->ihl * 4); + int len = csum_start - trans_start; + + /* IP header will have to cancel out any data that + * is not a part of the outer IP header, so set to + * a reverse csum if needed, else init check to 0. + */ + ip.v4->check = (skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) ? + csum_fold(csum_partial(trans_start, + len, 0)) : 0; + type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4; + + ip.v4->tot_len = 0; + first->tx_flags |= IXGBE_TX_FLAGS_TSO | + IXGBE_TX_FLAGS_CSUM | + IXGBE_TX_FLAGS_IPV4; + } else { + ip.v6->payload_len = 0; + first->tx_flags |= IXGBE_TX_FLAGS_TSO | + IXGBE_TX_FLAGS_CSUM; + } + + /* determine offset of inner transport header */ + l4_offset = l4.hdr - skb->data; + + /* remove payload length from inner checksum */ + paylen = skb->len - l4_offset; + + if (type_tucmd & IXGBE_ADVTXD_TUCMD_L4T_TCP) { + /* compute length of segmentation header */ + *hdr_len = (l4.tcp->doff * 4) + l4_offset; + csum_replace_by_diff(&l4.tcp->check, + (__force __wsum)htonl(paylen)); + } else { + /* compute length of segmentation header */ + *hdr_len = sizeof(*l4.udp) + l4_offset; + csum_replace_by_diff(&l4.udp->check, + (__force __wsum)htonl(paylen)); + } + + /* update gso size and bytecount with header size */ + first->gso_segs = skb_shinfo(skb)->gso_segs; + first->bytecount += (first->gso_segs - 1) * *hdr_len; + + /* mss_l4len_id: use 0 as index for TSO */ + mss_l4len_idx = (*hdr_len - l4_offset) << IXGBE_ADVTXD_L4LEN_SHIFT; + mss_l4len_idx |= skb_shinfo(skb)->gso_size << IXGBE_ADVTXD_MSS_SHIFT; + + fceof_saidx |= itd->sa_idx; + type_tucmd |= itd->flags | itd->trailer_len; + + /* vlan_macip_lens: HEADLEN, MACLEN, VLAN tag */ + vlan_macip_lens = l4.hdr - ip.hdr; + vlan_macip_lens |= (ip.hdr - skb->data) << IXGBE_ADVTXD_MACLEN_SHIFT; + vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK; + + ixgbe_tx_ctxtdesc(tx_ring, vlan_macip_lens, fceof_saidx, type_tucmd, + mss_l4len_idx); + + return 1; +} + +static inline bool ixgbe_ipv6_csum_is_sctp(struct sk_buff *skb) +{ + unsigned int offset = 0; + + ipv6_find_hdr(skb, &offset, IPPROTO_SCTP, NULL, NULL); + + return offset == skb_checksum_start_offset(skb); +} + +static void ixgbe_tx_csum(struct ixgbe_ring *tx_ring, + struct ixgbe_tx_buffer *first, + struct ixgbe_ipsec_tx_data *itd) +{ + struct sk_buff *skb = first->skb; + u32 vlan_macip_lens = 0; + u32 fceof_saidx = 0; + u32 type_tucmd = 0; + + if (skb->ip_summed != CHECKSUM_PARTIAL) { +csum_failed: + if (!(first->tx_flags & (IXGBE_TX_FLAGS_HW_VLAN | + IXGBE_TX_FLAGS_CC))) + return; + goto no_csum; + } + + switch (skb->csum_offset) { + case offsetof(struct tcphdr, check): + type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_TCP; + fallthrough; + case offsetof(struct udphdr, check): + break; + case offsetof(struct sctphdr, checksum): + /* validate that this is actually an SCTP request */ + if (((first->protocol == htons(ETH_P_IP)) && + (ip_hdr(skb)->protocol == IPPROTO_SCTP)) || + ((first->protocol == htons(ETH_P_IPV6)) && + ixgbe_ipv6_csum_is_sctp(skb))) { + type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_SCTP; + break; + } + fallthrough; + default: + skb_checksum_help(skb); + goto csum_failed; + } + + /* update TX checksum flag */ + first->tx_flags |= IXGBE_TX_FLAGS_CSUM; + vlan_macip_lens = skb_checksum_start_offset(skb) - + skb_network_offset(skb); +no_csum: + /* vlan_macip_lens: MACLEN, VLAN tag */ + vlan_macip_lens |= skb_network_offset(skb) << IXGBE_ADVTXD_MACLEN_SHIFT; + vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK; + + fceof_saidx |= itd->sa_idx; + type_tucmd |= itd->flags | itd->trailer_len; + + ixgbe_tx_ctxtdesc(tx_ring, vlan_macip_lens, fceof_saidx, type_tucmd, 0); +} + +#define IXGBE_SET_FLAG(_input, _flag, _result) \ + ((_flag <= _result) ? \ + ((u32)(_input & _flag) * (_result / _flag)) : \ + ((u32)(_input & _flag) / (_flag / _result))) + +static u32 ixgbe_tx_cmd_type(struct sk_buff *skb, u32 tx_flags) +{ + /* set type for advanced descriptor with frame checksum insertion */ + u32 cmd_type = IXGBE_ADVTXD_DTYP_DATA | + IXGBE_ADVTXD_DCMD_DEXT | + IXGBE_ADVTXD_DCMD_IFCS; + + /* set HW vlan bit if vlan is present */ + cmd_type |= IXGBE_SET_FLAG(tx_flags, IXGBE_TX_FLAGS_HW_VLAN, + IXGBE_ADVTXD_DCMD_VLE); + + /* set segmentation enable bits for TSO/FSO */ + cmd_type |= IXGBE_SET_FLAG(tx_flags, IXGBE_TX_FLAGS_TSO, + IXGBE_ADVTXD_DCMD_TSE); + + /* set timestamp bit if present */ + cmd_type |= IXGBE_SET_FLAG(tx_flags, IXGBE_TX_FLAGS_TSTAMP, + IXGBE_ADVTXD_MAC_TSTAMP); + + /* insert frame checksum */ + cmd_type ^= IXGBE_SET_FLAG(skb->no_fcs, 1, IXGBE_ADVTXD_DCMD_IFCS); + + return cmd_type; +} + +static void ixgbe_tx_olinfo_status(union ixgbe_adv_tx_desc *tx_desc, + u32 tx_flags, unsigned int paylen) +{ + u32 olinfo_status = paylen << IXGBE_ADVTXD_PAYLEN_SHIFT; + + /* enable L4 checksum for TSO and TX checksum offload */ + olinfo_status |= IXGBE_SET_FLAG(tx_flags, + IXGBE_TX_FLAGS_CSUM, + IXGBE_ADVTXD_POPTS_TXSM); + + /* enable IPv4 checksum for TSO */ + olinfo_status |= IXGBE_SET_FLAG(tx_flags, + IXGBE_TX_FLAGS_IPV4, + IXGBE_ADVTXD_POPTS_IXSM); + + /* enable IPsec */ + olinfo_status |= IXGBE_SET_FLAG(tx_flags, + IXGBE_TX_FLAGS_IPSEC, + IXGBE_ADVTXD_POPTS_IPSEC); + + /* + * Check Context must be set if Tx switch is enabled, which it + * always is for case where virtual functions are running + */ + olinfo_status |= IXGBE_SET_FLAG(tx_flags, + IXGBE_TX_FLAGS_CC, + IXGBE_ADVTXD_CC); + + tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); +} + +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)) + 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; +} + +static inline int ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size) +{ + if (likely(ixgbe_desc_unused(tx_ring) >= size)) + return 0; + + return __ixgbe_maybe_stop_tx(tx_ring, size); +} + +static int ixgbe_tx_map(struct ixgbe_ring *tx_ring, + struct ixgbe_tx_buffer *first, + const u8 hdr_len) +{ + struct sk_buff *skb = first->skb; + struct ixgbe_tx_buffer *tx_buffer; + union ixgbe_adv_tx_desc *tx_desc; + skb_frag_t *frag; + dma_addr_t dma; + unsigned int data_len, size; + u32 tx_flags = first->tx_flags; + u32 cmd_type = ixgbe_tx_cmd_type(skb, tx_flags); + u16 i = tx_ring->next_to_use; + + tx_desc = IXGBE_TX_DESC(tx_ring, i); + + ixgbe_tx_olinfo_status(tx_desc, tx_flags, skb->len - hdr_len); + + size = skb_headlen(skb); + data_len = skb->data_len; + +#ifdef IXGBE_FCOE + if (tx_flags & IXGBE_TX_FLAGS_FCOE) { + if (data_len < sizeof(struct fcoe_crc_eof)) { + size -= sizeof(struct fcoe_crc_eof) - data_len; + data_len = 0; + } else { + data_len -= sizeof(struct fcoe_crc_eof); + } + } + +#endif + dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE); + + tx_buffer = first; + + for (frag = &skb_shinfo(skb)->frags[0];; frag++) { + if (dma_mapping_error(tx_ring->dev, dma)) + goto dma_error; + + /* record length, and DMA address */ + dma_unmap_len_set(tx_buffer, len, size); + dma_unmap_addr_set(tx_buffer, dma, dma); + + tx_desc->read.buffer_addr = cpu_to_le64(dma); + + while (unlikely(size > IXGBE_MAX_DATA_PER_TXD)) { + tx_desc->read.cmd_type_len = + cpu_to_le32(cmd_type ^ IXGBE_MAX_DATA_PER_TXD); + + i++; + tx_desc++; + if (i == tx_ring->count) { + tx_desc = IXGBE_TX_DESC(tx_ring, 0); + i = 0; + } + tx_desc->read.olinfo_status = 0; + + dma += IXGBE_MAX_DATA_PER_TXD; + size -= IXGBE_MAX_DATA_PER_TXD; + + tx_desc->read.buffer_addr = cpu_to_le64(dma); + } + + if (likely(!data_len)) + break; + + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type ^ size); + + i++; + tx_desc++; + if (i == tx_ring->count) { + tx_desc = IXGBE_TX_DESC(tx_ring, 0); + i = 0; + } + tx_desc->read.olinfo_status = 0; + +#ifdef IXGBE_FCOE + size = min_t(unsigned int, data_len, skb_frag_size(frag)); +#else + size = skb_frag_size(frag); +#endif + data_len -= size; + + dma = skb_frag_dma_map(tx_ring->dev, frag, 0, size, + DMA_TO_DEVICE); + + tx_buffer = &tx_ring->tx_buffer_info[i]; + } + + /* write last descriptor with RS and EOP bits */ + cmd_type |= size | IXGBE_TXD_CMD; + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); + + netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount); + + /* set the timestamp */ + first->time_stamp = jiffies; + + skb_tx_timestamp(skb); + + /* + * 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). + * + * We also need this memory barrier to make certain all of the + * status bits have been updated before next_to_watch is written. + */ + wmb(); + + /* set next_to_watch value indicating a packet is present */ + first->next_to_watch = tx_desc; + + i++; + if (i == tx_ring->count) + i = 0; + + tx_ring->next_to_use = i; + + ixgbe_maybe_stop_tx(tx_ring, DESC_NEEDED); + + if (netif_xmit_stopped(txring_txq(tx_ring)) || !netdev_xmit_more()) { + writel(i, tx_ring->tail); + } + + return 0; +dma_error: + dev_err(tx_ring->dev, "TX DMA map failed\n"); + + /* clear dma mappings for failed tx_buffer_info map */ + for (;;) { + tx_buffer = &tx_ring->tx_buffer_info[i]; + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + if (tx_buffer == first) + break; + if (i == 0) + i += tx_ring->count; + i--; + } + + dev_kfree_skb_any(first->skb); + first->skb = NULL; + + tx_ring->next_to_use = i; + + return -1; +} + +static void ixgbe_atr(struct ixgbe_ring *ring, + struct ixgbe_tx_buffer *first) +{ + struct ixgbe_q_vector *q_vector = ring->q_vector; + union ixgbe_atr_hash_dword input = { .dword = 0 }; + union ixgbe_atr_hash_dword common = { .dword = 0 }; + union { + unsigned char *network; + struct iphdr *ipv4; + struct ipv6hdr *ipv6; + } hdr; + struct tcphdr *th; + unsigned int hlen; + struct sk_buff *skb; + __be16 vlan_id; + int l4_proto; + + /* if ring doesn't have a interrupt vector, cannot perform ATR */ + if (!q_vector) + return; + + /* do nothing if sampling is disabled */ + if (!ring->atr_sample_rate) + return; + + ring->atr_count++; + + /* currently only IPv4/IPv6 with TCP is supported */ + if ((first->protocol != htons(ETH_P_IP)) && + (first->protocol != htons(ETH_P_IPV6))) + return; + + /* snag network header to get L4 type and address */ + skb = first->skb; + hdr.network = skb_network_header(skb); + if (unlikely(hdr.network <= skb->data)) + return; + if (skb->encapsulation && + first->protocol == htons(ETH_P_IP) && + hdr.ipv4->protocol == IPPROTO_UDP) { + struct ixgbe_adapter *adapter = q_vector->adapter; + + if (unlikely(skb_tail_pointer(skb) < hdr.network + + vxlan_headroom(0))) + return; + + /* verify the port is recognized as VXLAN */ + if (adapter->vxlan_port && + udp_hdr(skb)->dest == adapter->vxlan_port) + hdr.network = skb_inner_network_header(skb); + + if (adapter->geneve_port && + udp_hdr(skb)->dest == adapter->geneve_port) + hdr.network = skb_inner_network_header(skb); + } + + /* Make sure we have at least [minimum IPv4 header + TCP] + * or [IPv6 header] bytes + */ + if (unlikely(skb_tail_pointer(skb) < hdr.network + 40)) + return; + + /* Currently only IPv4/IPv6 with TCP is supported */ + switch (hdr.ipv4->version) { + case IPVERSION: + /* access ihl as u8 to avoid unaligned access on ia64 */ + hlen = (hdr.network[0] & 0x0F) << 2; + l4_proto = hdr.ipv4->protocol; + break; + case 6: + hlen = hdr.network - skb->data; + l4_proto = ipv6_find_hdr(skb, &hlen, IPPROTO_TCP, NULL, NULL); + hlen -= hdr.network - skb->data; + break; + default: + return; + } + + if (l4_proto != IPPROTO_TCP) + return; + + if (unlikely(skb_tail_pointer(skb) < hdr.network + + hlen + sizeof(struct tcphdr))) + return; + + th = (struct tcphdr *)(hdr.network + hlen); + + /* skip this packet since the socket is closing */ + if (th->fin) + return; + + /* sample on all syn packets or once every atr sample count */ + if (!th->syn && (ring->atr_count < ring->atr_sample_rate)) + return; + + /* reset sample count */ + ring->atr_count = 0; + + vlan_id = htons(first->tx_flags >> IXGBE_TX_FLAGS_VLAN_SHIFT); + + /* + * src and dst are inverted, think how the receiver sees them + * + * The input is broken into two sections, a non-compressed section + * containing vm_pool, vlan_id, and flow_type. The rest of the data + * is XORed together and stored in the compressed dword. + */ + input.formatted.vlan_id = vlan_id; + + /* + * since src port and flex bytes occupy the same word XOR them together + * and write the value to source port portion of compressed dword + */ + if (first->tx_flags & (IXGBE_TX_FLAGS_SW_VLAN | IXGBE_TX_FLAGS_HW_VLAN)) + common.port.src ^= th->dest ^ htons(ETH_P_8021Q); + else + common.port.src ^= th->dest ^ first->protocol; + common.port.dst ^= th->source; + + switch (hdr.ipv4->version) { + case IPVERSION: + input.formatted.flow_type = IXGBE_ATR_FLOW_TYPE_TCPV4; + common.ip ^= hdr.ipv4->saddr ^ hdr.ipv4->daddr; + break; + case 6: + input.formatted.flow_type = IXGBE_ATR_FLOW_TYPE_TCPV6; + common.ip ^= hdr.ipv6->saddr.s6_addr32[0] ^ + hdr.ipv6->saddr.s6_addr32[1] ^ + hdr.ipv6->saddr.s6_addr32[2] ^ + hdr.ipv6->saddr.s6_addr32[3] ^ + hdr.ipv6->daddr.s6_addr32[0] ^ + hdr.ipv6->daddr.s6_addr32[1] ^ + hdr.ipv6->daddr.s6_addr32[2] ^ + hdr.ipv6->daddr.s6_addr32[3]; + break; + default: + break; + } + + if (hdr.network != skb_network_header(skb)) + input.formatted.flow_type |= IXGBE_ATR_L4TYPE_TUNNEL_MASK; + + /* This assumes the Rx queue and Tx queue are bound to the same CPU */ + ixgbe_fdir_add_signature_filter_82599(&q_vector->adapter->hw, + input, common, ring->queue_index); +} + +#ifdef IXGBE_FCOE +static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, + struct net_device *sb_dev) +{ + struct ixgbe_adapter *adapter; + struct ixgbe_ring_feature *f; + int txq; + + if (sb_dev) { + u8 tc = netdev_get_prio_tc_map(dev, skb->priority); + struct net_device *vdev = sb_dev; + + txq = vdev->tc_to_txq[tc].offset; + txq += reciprocal_scale(skb_get_hash(skb), + vdev->tc_to_txq[tc].count); + + return txq; + } + + /* + * only execute the code below if protocol is FCoE + * or FIP and we have FCoE enabled on the adapter + */ + switch (vlan_get_protocol(skb)) { + case htons(ETH_P_FCOE): + case htons(ETH_P_FIP): + adapter = netdev_priv(dev); + + if (!sb_dev && (adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) + break; + fallthrough; + default: + return netdev_pick_tx(dev, skb, sb_dev); + } + + f = &adapter->ring_feature[RING_F_FCOE]; + + txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : + smp_processor_id(); + + while (txq >= f->indices) + txq -= f->indices; + + return txq + f->offset; +} + +#endif +int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, + struct xdp_frame *xdpf) +{ + struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()]; + struct ixgbe_tx_buffer *tx_buffer; + union ixgbe_adv_tx_desc *tx_desc; + u32 len, cmd_type; + dma_addr_t dma; + u16 i; + + len = xdpf->len; + + if (unlikely(!ixgbe_desc_unused(ring))) + return IXGBE_XDP_CONSUMED; + + dma = dma_map_single(ring->dev, xdpf->data, len, DMA_TO_DEVICE); + if (dma_mapping_error(ring->dev, dma)) + return IXGBE_XDP_CONSUMED; + + /* record the location of the first descriptor for this packet */ + tx_buffer = &ring->tx_buffer_info[ring->next_to_use]; + tx_buffer->bytecount = len; + tx_buffer->gso_segs = 1; + tx_buffer->protocol = 0; + + i = ring->next_to_use; + tx_desc = IXGBE_TX_DESC(ring, i); + + dma_unmap_len_set(tx_buffer, len, len); + dma_unmap_addr_set(tx_buffer, dma, dma); + tx_buffer->xdpf = xdpf; + + tx_desc->read.buffer_addr = cpu_to_le64(dma); + + /* put descriptor type bits */ + cmd_type = IXGBE_ADVTXD_DTYP_DATA | + IXGBE_ADVTXD_DCMD_DEXT | + IXGBE_ADVTXD_DCMD_IFCS; + cmd_type |= len | IXGBE_TXD_CMD; + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); + tx_desc->read.olinfo_status = + cpu_to_le32(len << IXGBE_ADVTXD_PAYLEN_SHIFT); + + /* Avoid any potential race with xdp_xmit and cleanup */ + smp_wmb(); + + /* set next_to_watch value indicating a packet is present */ + i++; + if (i == ring->count) + i = 0; + + tx_buffer->next_to_watch = tx_desc; + ring->next_to_use = i; + + return IXGBE_XDP_TX; +} + +netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, + struct ixgbe_adapter *adapter, + struct ixgbe_ring *tx_ring) +{ + struct ixgbe_tx_buffer *first; + int tso; + u32 tx_flags = 0; + unsigned short f; + u16 count = TXD_USE_COUNT(skb_headlen(skb)); + struct ixgbe_ipsec_tx_data ipsec_tx = { 0 }; + __be16 protocol = skb->protocol; + u8 hdr_len = 0; + + /* + * need: 1 descriptor per page * PAGE_SIZE/IXGBE_MAX_DATA_PER_TXD, + * + 1 desc for skb_headlen/IXGBE_MAX_DATA_PER_TXD, + * + 2 desc gap to keep tail from touching head, + * + 1 desc for context descriptor, + * otherwise try next time + */ + for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) + count += TXD_USE_COUNT(skb_frag_size( + &skb_shinfo(skb)->frags[f])); + + if (ixgbe_maybe_stop_tx(tx_ring, count + 3)) { + tx_ring->tx_stats.tx_busy++; + return NETDEV_TX_BUSY; + } + + /* record the location of the first descriptor for this packet */ + first = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + first->skb = skb; + first->bytecount = skb->len; + first->gso_segs = 1; + + /* if we have a HW VLAN tag being added default to the HW one */ + if (skb_vlan_tag_present(skb)) { + tx_flags |= skb_vlan_tag_get(skb) << IXGBE_TX_FLAGS_VLAN_SHIFT; + tx_flags |= IXGBE_TX_FLAGS_HW_VLAN; + /* else if it is a SW VLAN check the next protocol and store the tag */ + } else if (protocol == htons(ETH_P_8021Q)) { + struct vlan_hdr *vhdr, _vhdr; + vhdr = skb_header_pointer(skb, ETH_HLEN, sizeof(_vhdr), &_vhdr); + if (!vhdr) + goto out_drop; + + tx_flags |= ntohs(vhdr->h_vlan_TCI) << + IXGBE_TX_FLAGS_VLAN_SHIFT; + tx_flags |= IXGBE_TX_FLAGS_SW_VLAN; + } + protocol = vlan_get_protocol(skb); + + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && + adapter->ptp_clock) { + if (adapter->tstamp_config.tx_type == HWTSTAMP_TX_ON && + !test_and_set_bit_lock(__IXGBE_PTP_TX_IN_PROGRESS, + &adapter->state)) { + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + tx_flags |= IXGBE_TX_FLAGS_TSTAMP; + + /* schedule check for Tx timestamp */ + adapter->ptp_tx_skb = skb_get(skb); + adapter->ptp_tx_start = jiffies; + schedule_work(&adapter->ptp_tx_work); + } else { + adapter->tx_hwtstamp_skipped++; + } + } + +#ifdef CONFIG_PCI_IOV + /* + * Use the l2switch_enable flag - would be false if the DMA + * Tx switch had been disabled. + */ + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) + tx_flags |= IXGBE_TX_FLAGS_CC; + +#endif + /* DCB maps skb priorities 0-7 onto 3 bit PCP of VLAN tag. */ + if ((adapter->flags & IXGBE_FLAG_DCB_ENABLED) && + ((tx_flags & (IXGBE_TX_FLAGS_HW_VLAN | IXGBE_TX_FLAGS_SW_VLAN)) || + (skb->priority != TC_PRIO_CONTROL))) { + tx_flags &= ~IXGBE_TX_FLAGS_VLAN_PRIO_MASK; + tx_flags |= (skb->priority & 0x7) << + IXGBE_TX_FLAGS_VLAN_PRIO_SHIFT; + if (tx_flags & IXGBE_TX_FLAGS_SW_VLAN) { + struct vlan_ethhdr *vhdr; + + if (skb_cow_head(skb, 0)) + goto out_drop; + vhdr = skb_vlan_eth_hdr(skb); + vhdr->h_vlan_TCI = htons(tx_flags >> + IXGBE_TX_FLAGS_VLAN_SHIFT); + } else { + tx_flags |= IXGBE_TX_FLAGS_HW_VLAN; + } + } + + /* record initial flags and protocol */ + first->tx_flags = tx_flags; + first->protocol = protocol; + +#ifdef IXGBE_FCOE + /* setup tx offload for FCoE */ + if ((protocol == htons(ETH_P_FCOE)) && + (tx_ring->netdev->features & (NETIF_F_FSO | NETIF_F_FCOE_CRC))) { + tso = ixgbe_fso(tx_ring, first, &hdr_len); + if (tso < 0) + goto out_drop; + + goto xmit_fcoe; + } + +#endif /* IXGBE_FCOE */ + +#ifdef CONFIG_IXGBE_IPSEC + if (xfrm_offload(skb) && + !ixgbe_ipsec_tx(tx_ring, first, &ipsec_tx)) + goto out_drop; +#endif + tso = ixgbe_tso(tx_ring, first, &hdr_len, &ipsec_tx); + if (tso < 0) + goto out_drop; + else if (!tso) + ixgbe_tx_csum(tx_ring, first, &ipsec_tx); + + /* add the ATR filter if ATR is on */ + if (test_bit(__IXGBE_TX_FDIR_INIT_DONE, &tx_ring->state)) + ixgbe_atr(tx_ring, first); + +#ifdef IXGBE_FCOE +xmit_fcoe: +#endif /* IXGBE_FCOE */ + if (ixgbe_tx_map(tx_ring, first, hdr_len)) + goto cleanup_tx_timestamp; + + return NETDEV_TX_OK; + +out_drop: + dev_kfree_skb_any(first->skb); + first->skb = NULL; +cleanup_tx_timestamp: + if (unlikely(tx_flags & IXGBE_TX_FLAGS_TSTAMP)) { + dev_kfree_skb_any(adapter->ptp_tx_skb); + adapter->ptp_tx_skb = NULL; + cancel_work_sync(&adapter->ptp_tx_work); + clear_bit_unlock(__IXGBE_PTP_TX_IN_PROGRESS, &adapter->state); + } + + return NETDEV_TX_OK; +} + +static netdev_tx_t __ixgbe_xmit_frame(struct sk_buff *skb, + struct net_device *netdev, + struct ixgbe_ring *ring) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_ring *tx_ring; + + /* + * The minimum packet size for olinfo paylen is 17 so pad the skb + * in order to meet this minimum size requirement. + */ + if (skb_put_padto(skb, 17)) + return NETDEV_TX_OK; + + tx_ring = ring ? ring : adapter->tx_ring[skb_get_queue_mapping(skb)]; + if (unlikely(test_bit(__IXGBE_TX_DISABLED, &tx_ring->state))) + return NETDEV_TX_BUSY; + + return ixgbe_xmit_frame_ring(skb, adapter, tx_ring); +} + +static netdev_tx_t ixgbe_xmit_frame(struct sk_buff *skb, + struct net_device *netdev) +{ + return __ixgbe_xmit_frame(skb, netdev, NULL); +} + +/** + * ixgbe_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 ixgbe_set_mac(struct net_device *netdev, void *p) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + struct sockaddr *addr = p; + + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + + memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); + memcpy(hw->mac.addr, addr->sa_data, netdev->addr_len); + + ixgbe_mac_set_default_filter(adapter); + + return 0; +} + +static int +ixgbe_mdio_read(struct net_device *netdev, int prtad, int devad, u16 addr) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + u16 value; + int rc; + + if (adapter->mii_bus) { + int regnum = addr; + + if (devad != MDIO_DEVAD_NONE) + regnum |= (devad << 16) | MII_ADDR_C45; + + return mdiobus_read(adapter->mii_bus, prtad, regnum); + } + + if (prtad != hw->phy.mdio.prtad) + return -EINVAL; + rc = hw->phy.ops.read_reg(hw, addr, devad, &value); + if (!rc) + rc = value; + return rc; +} + +static int ixgbe_mdio_write(struct net_device *netdev, int prtad, int devad, + u16 addr, u16 value) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + + if (adapter->mii_bus) { + int regnum = addr; + + if (devad != MDIO_DEVAD_NONE) + regnum |= (devad << 16) | MII_ADDR_C45; + + return mdiobus_write(adapter->mii_bus, prtad, regnum, value); + } + + if (prtad != hw->phy.mdio.prtad) + return -EINVAL; + return hw->phy.ops.write_reg(hw, addr, devad, value); +} + +static int ixgbe_ioctl(struct net_device *netdev, struct ifreq *req, int cmd) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + switch (cmd) { + case SIOCSHWTSTAMP: + return ixgbe_ptp_set_ts_config(adapter, req); + case SIOCGHWTSTAMP: + return ixgbe_ptp_get_ts_config(adapter, req); + case SIOCGMIIPHY: + if (!adapter->hw.phy.ops.read_reg) + return -EOPNOTSUPP; + fallthrough; + default: + return mdio_mii_ioctl(&adapter->hw.phy.mdio, if_mii(req), cmd); + } +} + +/** + * ixgbe_add_sanmac_netdev - Add the SAN MAC address to the corresponding + * netdev->dev_addrs + * @dev: network interface device structure + * + * Returns non-zero on failure + **/ +static int ixgbe_add_sanmac_netdev(struct net_device *dev) +{ + int err = 0; + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_hw *hw = &adapter->hw; + + if (is_valid_ether_addr(hw->mac.san_addr)) { + rtnl_lock(); + err = dev_addr_add(dev, hw->mac.san_addr, NETDEV_HW_ADDR_T_SAN); + rtnl_unlock(); + + /* update SAN MAC vmdq pool selection */ + hw->mac.ops.set_vmdq_san_mac(hw, VMDQ_P(0)); + } + return err; +} + +/** + * ixgbe_del_sanmac_netdev - Removes the SAN MAC address to the corresponding + * netdev->dev_addrs + * @dev: network interface device structure + * + * Returns non-zero on failure + **/ +static int ixgbe_del_sanmac_netdev(struct net_device *dev) +{ + int err = 0; + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_mac_info *mac = &adapter->hw.mac; + + if (is_valid_ether_addr(mac->san_addr)) { + rtnl_lock(); + err = dev_addr_del(dev, mac->san_addr, NETDEV_HW_ADDR_T_SAN); + rtnl_unlock(); + } + return err; +} + +static void ixgbe_get_ring_stats64(struct rtnl_link_stats64 *stats, + struct ixgbe_ring *ring) +{ + u64 bytes, packets; + unsigned int start; + + if (ring) { + do { + start = u64_stats_fetch_begin_irq(&ring->syncp); + packets = ring->stats.packets; + bytes = ring->stats.bytes; + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + stats->tx_packets += packets; + stats->tx_bytes += bytes; + } +} + +static void ixgbe_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + int i; + + rcu_read_lock(); + for (i = 0; i < adapter->num_rx_queues; i++) { + struct ixgbe_ring *ring = READ_ONCE(adapter->rx_ring[i]); + u64 bytes, packets; + unsigned int start; + + if (ring) { + do { + start = u64_stats_fetch_begin_irq(&ring->syncp); + packets = ring->stats.packets; + bytes = ring->stats.bytes; + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + stats->rx_packets += packets; + stats->rx_bytes += bytes; + } + } + + for (i = 0; i < adapter->num_tx_queues; i++) { + struct ixgbe_ring *ring = READ_ONCE(adapter->tx_ring[i]); + + ixgbe_get_ring_stats64(stats, ring); + } + for (i = 0; i < adapter->num_xdp_queues; i++) { + struct ixgbe_ring *ring = READ_ONCE(adapter->xdp_ring[i]); + + ixgbe_get_ring_stats64(stats, ring); + } + rcu_read_unlock(); + + /* following stats updated by ixgbe_watchdog_task() */ + stats->multicast = netdev->stats.multicast; + stats->rx_errors = netdev->stats.rx_errors; + stats->rx_length_errors = netdev->stats.rx_length_errors; + stats->rx_crc_errors = netdev->stats.rx_crc_errors; + stats->rx_missed_errors = netdev->stats.rx_missed_errors; +} + +#ifdef CONFIG_IXGBE_DCB +/** + * ixgbe_validate_rtr - verify 802.1Qp to Rx packet buffer mapping is valid. + * @adapter: pointer to ixgbe_adapter + * @tc: number of traffic classes currently enabled + * + * Configure a valid 802.1Qp to Rx packet buffer mapping ie confirm + * 802.1Q priority maps to a packet buffer that exists. + */ +static void ixgbe_validate_rtr(struct ixgbe_adapter *adapter, u8 tc) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 reg, rsave; + int i; + + /* 82598 have a static priority to TC mapping that can not + * be changed so no validation is needed. + */ + if (hw->mac.type == ixgbe_mac_82598EB) + return; + + reg = IXGBE_READ_REG(hw, IXGBE_RTRUP2TC); + rsave = reg; + + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + u8 up2tc = reg >> (i * IXGBE_RTRUP2TC_UP_SHIFT); + + /* If up2tc is out of bounds default to zero */ + if (up2tc > tc) + reg &= ~(0x7 << IXGBE_RTRUP2TC_UP_SHIFT); + } + + if (reg != rsave) + IXGBE_WRITE_REG(hw, IXGBE_RTRUP2TC, reg); + + return; +} + +/** + * ixgbe_set_prio_tc_map - Configure netdev prio tc map + * @adapter: Pointer to adapter struct + * + * Populate the netdev user priority to tc map + */ +static void ixgbe_set_prio_tc_map(struct ixgbe_adapter *adapter) +{ + struct net_device *dev = adapter->netdev; + struct ixgbe_dcb_config *dcb_cfg = &adapter->dcb_cfg; + struct ieee_ets *ets = adapter->ixgbe_ieee_ets; + u8 prio; + + for (prio = 0; prio < MAX_USER_PRIORITY; prio++) { + u8 tc = 0; + + if (adapter->dcbx_cap & DCB_CAP_DCBX_VER_CEE) + tc = ixgbe_dcb_get_tc_from_up(dcb_cfg, 0, prio); + else if (ets) + tc = ets->prio_tc[prio]; + + netdev_set_prio_tc_map(dev, prio, tc); + } +} + +#endif /* CONFIG_IXGBE_DCB */ +static int ixgbe_reassign_macvlan_pool(struct net_device *vdev, + struct netdev_nested_priv *priv) +{ + struct ixgbe_adapter *adapter = (struct ixgbe_adapter *)priv->data; + struct ixgbe_fwd_adapter *accel; + int pool; + + /* we only care about macvlans... */ + if (!netif_is_macvlan(vdev)) + return 0; + + /* that have hardware offload enabled... */ + accel = macvlan_accel_priv(vdev); + if (!accel) + return 0; + + /* If we can relocate to a different bit do so */ + pool = find_first_zero_bit(adapter->fwd_bitmask, adapter->num_rx_pools); + if (pool < adapter->num_rx_pools) { + set_bit(pool, adapter->fwd_bitmask); + accel->pool = pool; + return 0; + } + + /* if we cannot find a free pool then disable the offload */ + netdev_err(vdev, "L2FW offload disabled due to lack of queue resources\n"); + macvlan_release_l2fw_offload(vdev); + + /* unbind the queues and drop the subordinate channel config */ + netdev_unbind_sb_channel(adapter->netdev, vdev); + netdev_set_sb_channel(vdev, 0); + + kfree(accel); + + return 0; +} + +static void ixgbe_defrag_macvlan_pools(struct net_device *dev) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct netdev_nested_priv priv = { + .data = (void *)adapter, + }; + + /* flush any stale bits out of the fwd bitmask */ + bitmap_clear(adapter->fwd_bitmask, 1, 63); + + /* walk through upper devices reassigning pools */ + netdev_walk_all_upper_dev_rcu(dev, ixgbe_reassign_macvlan_pool, + &priv); +} + +/** + * ixgbe_setup_tc - configure net_device for multiple traffic classes + * + * @dev: net device to configure + * @tc: number of traffic classes to enable + */ +int ixgbe_setup_tc(struct net_device *dev, u8 tc) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_hw *hw = &adapter->hw; + + /* Hardware supports up to 8 traffic classes */ + if (tc > adapter->dcb_cfg.num_tcs.pg_tcs) + return -EINVAL; + + if (hw->mac.type == ixgbe_mac_82598EB && tc && tc < MAX_TRAFFIC_CLASS) + return -EINVAL; + + /* Hardware has to reinitialize queues and interrupts to + * match packet buffer alignment. Unfortunately, the + * hardware is not flexible enough to do this dynamically. + */ + if (netif_running(dev)) + ixgbe_close(dev); + else + ixgbe_reset(adapter); + + ixgbe_clear_interrupt_scheme(adapter); + +#ifdef CONFIG_IXGBE_DCB + if (tc) { + if (adapter->xdp_prog) { + e_warn(probe, "DCB is not supported with XDP\n"); + + ixgbe_init_interrupt_scheme(adapter); + if (netif_running(dev)) + ixgbe_open(dev); + return -EINVAL; + } + + netdev_set_num_tc(dev, tc); + ixgbe_set_prio_tc_map(adapter); + + adapter->hw_tcs = tc; + adapter->flags |= IXGBE_FLAG_DCB_ENABLED; + + if (adapter->hw.mac.type == ixgbe_mac_82598EB) { + adapter->last_lfc_mode = adapter->hw.fc.requested_mode; + adapter->hw.fc.requested_mode = ixgbe_fc_none; + } + } else { + netdev_reset_tc(dev); + + if (adapter->hw.mac.type == ixgbe_mac_82598EB) + adapter->hw.fc.requested_mode = adapter->last_lfc_mode; + + adapter->flags &= ~IXGBE_FLAG_DCB_ENABLED; + adapter->hw_tcs = tc; + + adapter->temp_dcb_cfg.pfc_mode_enable = false; + adapter->dcb_cfg.pfc_mode_enable = false; + } + + ixgbe_validate_rtr(adapter, tc); + +#endif /* CONFIG_IXGBE_DCB */ + ixgbe_init_interrupt_scheme(adapter); + + ixgbe_defrag_macvlan_pools(dev); + + if (netif_running(dev)) + return ixgbe_open(dev); + + return 0; +} + +static int ixgbe_delete_clsu32(struct ixgbe_adapter *adapter, + struct tc_cls_u32_offload *cls) +{ + u32 hdl = cls->knode.handle; + u32 uhtid = TC_U32_USERHTID(cls->knode.handle); + u32 loc = cls->knode.handle & 0xfffff; + int err = 0, i, j; + struct ixgbe_jump_table *jump = NULL; + + if (loc > IXGBE_MAX_HW_ENTRIES) + return -EINVAL; + + if ((uhtid != 0x800) && (uhtid >= IXGBE_MAX_LINK_HANDLE)) + return -EINVAL; + + /* Clear this filter in the link data it is associated with */ + if (uhtid != 0x800) { + jump = adapter->jump_tables[uhtid]; + if (!jump) + return -EINVAL; + if (!test_bit(loc - 1, jump->child_loc_map)) + return -EINVAL; + clear_bit(loc - 1, jump->child_loc_map); + } + + /* Check if the filter being deleted is a link */ + for (i = 1; i < IXGBE_MAX_LINK_HANDLE; i++) { + jump = adapter->jump_tables[i]; + if (jump && jump->link_hdl == hdl) { + /* Delete filters in the hardware in the child hash + * table associated with this link + */ + for (j = 0; j < IXGBE_MAX_HW_ENTRIES; j++) { + if (!test_bit(j, jump->child_loc_map)) + continue; + spin_lock(&adapter->fdir_perfect_lock); + err = ixgbe_update_ethtool_fdir_entry(adapter, + NULL, + j + 1); + spin_unlock(&adapter->fdir_perfect_lock); + clear_bit(j, jump->child_loc_map); + } + /* Remove resources for this link */ + kfree(jump->input); + kfree(jump->mask); + kfree(jump); + adapter->jump_tables[i] = NULL; + return err; + } + } + + spin_lock(&adapter->fdir_perfect_lock); + err = ixgbe_update_ethtool_fdir_entry(adapter, NULL, loc); + spin_unlock(&adapter->fdir_perfect_lock); + return err; +} + +static int ixgbe_configure_clsu32_add_hnode(struct ixgbe_adapter *adapter, + struct tc_cls_u32_offload *cls) +{ + u32 uhtid = TC_U32_USERHTID(cls->hnode.handle); + + if (uhtid >= IXGBE_MAX_LINK_HANDLE) + return -EINVAL; + + /* This ixgbe devices do not support hash tables at the moment + * so abort when given hash tables. + */ + if (cls->hnode.divisor > 0) + return -EINVAL; + + set_bit(uhtid - 1, &adapter->tables); + return 0; +} + +static int ixgbe_configure_clsu32_del_hnode(struct ixgbe_adapter *adapter, + struct tc_cls_u32_offload *cls) +{ + u32 uhtid = TC_U32_USERHTID(cls->hnode.handle); + + if (uhtid >= IXGBE_MAX_LINK_HANDLE) + return -EINVAL; + + clear_bit(uhtid - 1, &adapter->tables); + return 0; +} + +#ifdef CONFIG_NET_CLS_ACT +struct upper_walk_data { + struct ixgbe_adapter *adapter; + u64 action; + int ifindex; + u8 queue; +}; + +static int get_macvlan_queue(struct net_device *upper, + struct netdev_nested_priv *priv) +{ + if (netif_is_macvlan(upper)) { + struct ixgbe_fwd_adapter *vadapter = macvlan_accel_priv(upper); + struct ixgbe_adapter *adapter; + struct upper_walk_data *data; + int ifindex; + + data = (struct upper_walk_data *)priv->data; + ifindex = data->ifindex; + adapter = data->adapter; + if (vadapter && upper->ifindex == ifindex) { + data->queue = adapter->rx_ring[vadapter->rx_base_queue]->reg_idx; + data->action = data->queue; + return 1; + } + } + + return 0; +} + +static int handle_redirect_action(struct ixgbe_adapter *adapter, int ifindex, + u8 *queue, u64 *action) +{ + struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; + unsigned int num_vfs = adapter->num_vfs, vf; + struct netdev_nested_priv priv; + struct upper_walk_data data; + struct net_device *upper; + + /* redirect to a SRIOV VF */ + for (vf = 0; vf < num_vfs; ++vf) { + upper = pci_get_drvdata(adapter->vfinfo[vf].vfdev); + if (upper->ifindex == ifindex) { + *queue = vf * __ALIGN_MASK(1, ~vmdq->mask); + *action = vf + 1; + *action <<= ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF; + return 0; + } + } + + /* redirect to a offloaded macvlan netdev */ + data.adapter = adapter; + data.ifindex = ifindex; + data.action = 0; + data.queue = 0; + priv.data = (void *)&data; + if (netdev_walk_all_upper_dev_rcu(adapter->netdev, + get_macvlan_queue, &priv)) { + *action = data.action; + *queue = data.queue; + + return 0; + } + + return -EINVAL; +} + +static int parse_tc_actions(struct ixgbe_adapter *adapter, + struct tcf_exts *exts, u64 *action, u8 *queue) +{ + const struct tc_action *a; + int i; + + if (!tcf_exts_has_actions(exts)) + return -EINVAL; + + tcf_exts_for_each_action(i, a, exts) { + /* Drop action */ + if (is_tcf_gact_shot(a)) { + *action = IXGBE_FDIR_DROP_QUEUE; + *queue = IXGBE_FDIR_DROP_QUEUE; + return 0; + } + + /* Redirect to a VF or a offloaded macvlan */ + if (is_tcf_mirred_egress_redirect(a)) { + struct net_device *dev = tcf_mirred_dev(a); + + if (!dev) + return -EINVAL; + return handle_redirect_action(adapter, dev->ifindex, + queue, action); + } + + return -EINVAL; + } + + return -EINVAL; +} +#else +static int parse_tc_actions(struct ixgbe_adapter *adapter, + struct tcf_exts *exts, u64 *action, u8 *queue) +{ + return -EINVAL; +} +#endif /* CONFIG_NET_CLS_ACT */ + +static int ixgbe_clsu32_build_input(struct ixgbe_fdir_filter *input, + union ixgbe_atr_input *mask, + struct tc_cls_u32_offload *cls, + struct ixgbe_mat_field *field_ptr, + struct ixgbe_nexthdr *nexthdr) +{ + int i, j, off; + __be32 val, m; + bool found_entry = false, found_jump_field = false; + + for (i = 0; i < cls->knode.sel->nkeys; i++) { + off = cls->knode.sel->keys[i].off; + val = cls->knode.sel->keys[i].val; + m = cls->knode.sel->keys[i].mask; + + for (j = 0; field_ptr[j].val; j++) { + if (field_ptr[j].off == off) { + field_ptr[j].val(input, mask, (__force u32)val, + (__force u32)m); + input->filter.formatted.flow_type |= + field_ptr[j].type; + found_entry = true; + break; + } + } + if (nexthdr) { + if (nexthdr->off == cls->knode.sel->keys[i].off && + nexthdr->val == + (__force u32)cls->knode.sel->keys[i].val && + nexthdr->mask == + (__force u32)cls->knode.sel->keys[i].mask) + found_jump_field = true; + else + continue; + } + } + + if (nexthdr && !found_jump_field) + return -EINVAL; + + if (!found_entry) + return 0; + + mask->formatted.flow_type = IXGBE_ATR_L4TYPE_IPV6_MASK | + IXGBE_ATR_L4TYPE_MASK; + + if (input->filter.formatted.flow_type == IXGBE_ATR_FLOW_TYPE_IPV4) + mask->formatted.flow_type &= IXGBE_ATR_L4TYPE_IPV6_MASK; + + return 0; +} + +static int ixgbe_configure_clsu32(struct ixgbe_adapter *adapter, + struct tc_cls_u32_offload *cls) +{ + __be16 protocol = cls->common.protocol; + u32 loc = cls->knode.handle & 0xfffff; + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_mat_field *field_ptr; + struct ixgbe_fdir_filter *input = NULL; + union ixgbe_atr_input *mask = NULL; + struct ixgbe_jump_table *jump = NULL; + int i, err = -EINVAL; + u8 queue; + u32 uhtid, link_uhtid; + + uhtid = TC_U32_USERHTID(cls->knode.handle); + link_uhtid = TC_U32_USERHTID(cls->knode.link_handle); + + /* At the moment cls_u32 jumps to network layer and skips past + * L2 headers. The canonical method to match L2 frames is to use + * negative values. However this is error prone at best but really + * just broken because there is no way to "know" what sort of hdr + * is in front of the network layer. Fix cls_u32 to support L2 + * headers when needed. + */ + if (protocol != htons(ETH_P_IP)) + return err; + + if (loc >= ((1024 << adapter->fdir_pballoc) - 2)) { + e_err(drv, "Location out of range\n"); + return err; + } + + /* cls u32 is a graph starting at root node 0x800. The driver tracks + * links and also the fields used to advance the parser across each + * link (e.g. nexthdr/eat parameters from 'tc'). This way we can map + * the u32 graph onto the hardware parse graph denoted in ixgbe_model.h + * To add support for new nodes update ixgbe_model.h parse structures + * this function _should_ be generic try not to hardcode values here. + */ + if (uhtid == 0x800) { + field_ptr = (adapter->jump_tables[0])->mat; + } else { + if (uhtid >= IXGBE_MAX_LINK_HANDLE) + return err; + if (!adapter->jump_tables[uhtid]) + return err; + field_ptr = (adapter->jump_tables[uhtid])->mat; + } + + if (!field_ptr) + return err; + + /* At this point we know the field_ptr is valid and need to either + * build cls_u32 link or attach filter. Because adding a link to + * a handle that does not exist is invalid and the same for adding + * rules to handles that don't exist. + */ + + if (link_uhtid) { + struct ixgbe_nexthdr *nexthdr = ixgbe_ipv4_jumps; + + if (link_uhtid >= IXGBE_MAX_LINK_HANDLE) + return err; + + if (!test_bit(link_uhtid - 1, &adapter->tables)) + return err; + + /* Multiple filters as links to the same hash table are not + * supported. To add a new filter with the same next header + * but different match/jump conditions, create a new hash table + * and link to it. + */ + if (adapter->jump_tables[link_uhtid] && + (adapter->jump_tables[link_uhtid])->link_hdl) { + e_err(drv, "Link filter exists for link: %x\n", + link_uhtid); + return err; + } + + for (i = 0; nexthdr[i].jump; i++) { + if (nexthdr[i].o != cls->knode.sel->offoff || + nexthdr[i].s != cls->knode.sel->offshift || + nexthdr[i].m != + (__force u32)cls->knode.sel->offmask) + return err; + + jump = kzalloc(sizeof(*jump), GFP_KERNEL); + if (!jump) + return -ENOMEM; + input = kzalloc(sizeof(*input), GFP_KERNEL); + if (!input) { + err = -ENOMEM; + goto free_jump; + } + mask = kzalloc(sizeof(*mask), GFP_KERNEL); + if (!mask) { + err = -ENOMEM; + goto free_input; + } + jump->input = input; + jump->mask = mask; + jump->link_hdl = cls->knode.handle; + + err = ixgbe_clsu32_build_input(input, mask, cls, + field_ptr, &nexthdr[i]); + if (!err) { + jump->mat = nexthdr[i].jump; + adapter->jump_tables[link_uhtid] = jump; + break; + } else { + kfree(mask); + kfree(input); + kfree(jump); + } + } + return 0; + } + + input = kzalloc(sizeof(*input), GFP_KERNEL); + if (!input) + return -ENOMEM; + mask = kzalloc(sizeof(*mask), GFP_KERNEL); + if (!mask) { + err = -ENOMEM; + goto free_input; + } + + if ((uhtid != 0x800) && (adapter->jump_tables[uhtid])) { + if ((adapter->jump_tables[uhtid])->input) + memcpy(input, (adapter->jump_tables[uhtid])->input, + sizeof(*input)); + if ((adapter->jump_tables[uhtid])->mask) + memcpy(mask, (adapter->jump_tables[uhtid])->mask, + sizeof(*mask)); + + /* Lookup in all child hash tables if this location is already + * filled with a filter + */ + for (i = 1; i < IXGBE_MAX_LINK_HANDLE; i++) { + struct ixgbe_jump_table *link = adapter->jump_tables[i]; + + if (link && (test_bit(loc - 1, link->child_loc_map))) { + e_err(drv, "Filter exists in location: %x\n", + loc); + err = -EINVAL; + goto err_out; + } + } + } + err = ixgbe_clsu32_build_input(input, mask, cls, field_ptr, NULL); + if (err) + goto err_out; + + err = parse_tc_actions(adapter, cls->knode.exts, &input->action, + &queue); + if (err < 0) + goto err_out; + + input->sw_idx = loc; + + spin_lock(&adapter->fdir_perfect_lock); + + if (hlist_empty(&adapter->fdir_filter_list)) { + memcpy(&adapter->fdir_mask, mask, sizeof(*mask)); + err = ixgbe_fdir_set_input_mask_82599(hw, mask); + if (err) + goto err_out_w_lock; + } else if (memcmp(&adapter->fdir_mask, mask, sizeof(*mask))) { + err = -EINVAL; + goto err_out_w_lock; + } + + ixgbe_atr_compute_perfect_hash_82599(&input->filter, mask); + err = ixgbe_fdir_write_perfect_filter_82599(hw, &input->filter, + input->sw_idx, queue); + if (err) + goto err_out_w_lock; + + ixgbe_update_ethtool_fdir_entry(adapter, input, input->sw_idx); + spin_unlock(&adapter->fdir_perfect_lock); + + if ((uhtid != 0x800) && (adapter->jump_tables[uhtid])) + set_bit(loc - 1, (adapter->jump_tables[uhtid])->child_loc_map); + + kfree(mask); + return err; +err_out_w_lock: + spin_unlock(&adapter->fdir_perfect_lock); +err_out: + kfree(mask); +free_input: + kfree(input); +free_jump: + kfree(jump); + return err; +} + +static int ixgbe_setup_tc_cls_u32(struct ixgbe_adapter *adapter, + struct tc_cls_u32_offload *cls_u32) +{ + switch (cls_u32->command) { + case TC_CLSU32_NEW_KNODE: + case TC_CLSU32_REPLACE_KNODE: + return ixgbe_configure_clsu32(adapter, cls_u32); + case TC_CLSU32_DELETE_KNODE: + return ixgbe_delete_clsu32(adapter, cls_u32); + case TC_CLSU32_NEW_HNODE: + case TC_CLSU32_REPLACE_HNODE: + return ixgbe_configure_clsu32_add_hnode(adapter, cls_u32); + case TC_CLSU32_DELETE_HNODE: + return ixgbe_configure_clsu32_del_hnode(adapter, cls_u32); + default: + return -EOPNOTSUPP; + } +} + +static int ixgbe_setup_tc_block_cb(enum tc_setup_type type, void *type_data, + void *cb_priv) +{ + struct ixgbe_adapter *adapter = cb_priv; + + if (!tc_cls_can_offload_and_chain0(adapter->netdev, type_data)) + return -EOPNOTSUPP; + + switch (type) { + case TC_SETUP_CLSU32: + return ixgbe_setup_tc_cls_u32(adapter, type_data); + default: + return -EOPNOTSUPP; + } +} + +static int ixgbe_setup_tc_mqprio(struct net_device *dev, + struct tc_mqprio_qopt *mqprio) +{ + mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS; + return ixgbe_setup_tc(dev, mqprio->num_tc); +} + +static LIST_HEAD(ixgbe_block_cb_list); + +static int __ixgbe_setup_tc(struct net_device *dev, enum tc_setup_type type, + void *type_data) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + + switch (type) { + case TC_SETUP_BLOCK: + return flow_block_cb_setup_simple(type_data, + &ixgbe_block_cb_list, + ixgbe_setup_tc_block_cb, + adapter, adapter, true); + case TC_SETUP_QDISC_MQPRIO: + return ixgbe_setup_tc_mqprio(dev, type_data); + default: + return -EOPNOTSUPP; + } +} + +#ifdef CONFIG_PCI_IOV +void ixgbe_sriov_reinit(struct ixgbe_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + + rtnl_lock(); + ixgbe_setup_tc(netdev, adapter->hw_tcs); + rtnl_unlock(); +} + +#endif +void ixgbe_do_reset(struct net_device *netdev) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + if (netif_running(netdev)) + ixgbe_reinit_locked(adapter); + else + ixgbe_reset(adapter); +} + +static netdev_features_t ixgbe_fix_features(struct net_device *netdev, + netdev_features_t features) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + /* If Rx checksum is disabled, then RSC/LRO should also be disabled */ + if (!(features & NETIF_F_RXCSUM)) + features &= ~NETIF_F_LRO; + + /* Turn off LRO if not RSC capable */ + if (!(adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE)) + features &= ~NETIF_F_LRO; + + if (adapter->xdp_prog && (features & NETIF_F_LRO)) { + e_dev_err("LRO is not supported with XDP\n"); + features &= ~NETIF_F_LRO; + } + + return features; +} + +static void ixgbe_reset_l2fw_offload(struct ixgbe_adapter *adapter) +{ + int rss = min_t(int, ixgbe_max_rss_indices(adapter), + num_online_cpus()); + + /* go back to full RSS if we're not running SR-IOV */ + if (!adapter->ring_feature[RING_F_VMDQ].offset) + adapter->flags &= ~(IXGBE_FLAG_VMDQ_ENABLED | + IXGBE_FLAG_SRIOV_ENABLED); + + adapter->ring_feature[RING_F_RSS].limit = rss; + adapter->ring_feature[RING_F_VMDQ].limit = 1; + + ixgbe_setup_tc(adapter->netdev, adapter->hw_tcs); +} + +static int ixgbe_set_features(struct net_device *netdev, + netdev_features_t features) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + netdev_features_t changed = netdev->features ^ features; + bool need_reset = false; + + /* Make sure RSC matches LRO, reset if change */ + if (!(features & NETIF_F_LRO)) { + if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) + need_reset = true; + adapter->flags2 &= ~IXGBE_FLAG2_RSC_ENABLED; + } else if ((adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE) && + !(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)) { + if (adapter->rx_itr_setting == 1 || + adapter->rx_itr_setting > IXGBE_MIN_RSC_ITR) { + adapter->flags2 |= IXGBE_FLAG2_RSC_ENABLED; + need_reset = true; + } else if ((changed ^ features) & NETIF_F_LRO) { + e_info(probe, "rx-usecs set too low, " + "disabling RSC\n"); + } + } + + /* + * Check if Flow Director n-tuple support or hw_tc support was + * enabled or disabled. If the state changed, we need to reset. + */ + if ((features & NETIF_F_NTUPLE) || (features & NETIF_F_HW_TC)) { + /* turn off ATR, enable perfect filters and reset */ + if (!(adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE)) + need_reset = true; + + adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; + adapter->flags |= IXGBE_FLAG_FDIR_PERFECT_CAPABLE; + } else { + /* turn off perfect filters, enable ATR and reset */ + if (adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE) + need_reset = true; + + adapter->flags &= ~IXGBE_FLAG_FDIR_PERFECT_CAPABLE; + + /* We cannot enable ATR if SR-IOV is enabled */ + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED || + /* We cannot enable ATR if we have 2 or more tcs */ + (adapter->hw_tcs > 1) || + /* We cannot enable ATR if RSS is disabled */ + (adapter->ring_feature[RING_F_RSS].limit <= 1) || + /* A sample rate of 0 indicates ATR disabled */ + (!adapter->atr_sample_rate)) + ; /* do nothing not supported */ + else /* otherwise supported and set the flag */ + adapter->flags |= IXGBE_FLAG_FDIR_HASH_CAPABLE; + } + + if (changed & NETIF_F_RXALL) + need_reset = true; + + netdev->features = features; + + if ((changed & NETIF_F_HW_L2FW_DOFFLOAD) && adapter->num_rx_pools > 1) + ixgbe_reset_l2fw_offload(adapter); + else if (need_reset) + ixgbe_do_reset(netdev); + else if (changed & (NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_FILTER)) + ixgbe_set_rx_mode(netdev); + + return 1; +} + +static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, u16 vid, + u16 flags, + struct netlink_ext_ack *extack) +{ + /* guarantee we can provide a unique filter for the unicast address */ + if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) { + struct ixgbe_adapter *adapter = netdev_priv(dev); + u16 pool = VMDQ_P(0); + + if (netdev_uc_count(dev) >= ixgbe_available_rars(adapter, pool)) + return -ENOMEM; + } + + return ndo_dflt_fdb_add(ndm, tb, dev, addr, vid, flags); +} + +/** + * ixgbe_configure_bridge_mode - set various bridge modes + * @adapter: the private structure + * @mode: requested bridge mode + * + * Configure some settings require for various bridge modes. + **/ +static int ixgbe_configure_bridge_mode(struct ixgbe_adapter *adapter, + __u16 mode) +{ + struct ixgbe_hw *hw = &adapter->hw; + unsigned int p, num_pools; + u32 vmdctl; + + switch (mode) { + case BRIDGE_MODE_VEPA: + /* disable Tx loopback, rely on switch hairpin mode */ + IXGBE_WRITE_REG(&adapter->hw, IXGBE_PFDTXGSWC, 0); + + /* must enable Rx switching replication to allow multicast + * packet reception on all VFs, and to enable source address + * pruning. + */ + vmdctl = IXGBE_READ_REG(hw, IXGBE_VMD_CTL); + vmdctl |= IXGBE_VT_CTL_REPLEN; + IXGBE_WRITE_REG(hw, IXGBE_VMD_CTL, vmdctl); + + /* enable Rx source address pruning. Note, this requires + * replication to be enabled or else it does nothing. + */ + num_pools = adapter->num_vfs + adapter->num_rx_pools; + for (p = 0; p < num_pools; p++) { + if (hw->mac.ops.set_source_address_pruning) + hw->mac.ops.set_source_address_pruning(hw, + true, + p); + } + break; + case BRIDGE_MODE_VEB: + /* enable Tx loopback for internal VF/PF communication */ + IXGBE_WRITE_REG(&adapter->hw, IXGBE_PFDTXGSWC, + IXGBE_PFDTXGSWC_VT_LBEN); + + /* disable Rx switching replication unless we have SR-IOV + * virtual functions + */ + vmdctl = IXGBE_READ_REG(hw, IXGBE_VMD_CTL); + if (!adapter->num_vfs) + vmdctl &= ~IXGBE_VT_CTL_REPLEN; + IXGBE_WRITE_REG(hw, IXGBE_VMD_CTL, vmdctl); + + /* disable Rx source address pruning, since we don't expect to + * be receiving external loopback of our transmitted frames. + */ + num_pools = adapter->num_vfs + adapter->num_rx_pools; + for (p = 0; p < num_pools; p++) { + if (hw->mac.ops.set_source_address_pruning) + hw->mac.ops.set_source_address_pruning(hw, + false, + p); + } + break; + default: + return -EINVAL; + } + + adapter->bridge_mode = mode; + + e_info(drv, "enabling bridge mode: %s\n", + mode == BRIDGE_MODE_VEPA ? "VEPA" : "VEB"); + + return 0; +} + +static int ixgbe_ndo_bridge_setlink(struct net_device *dev, + struct nlmsghdr *nlh, u16 flags, + struct netlink_ext_ack *extack) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct nlattr *attr, *br_spec; + int rem; + + if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) + return -EOPNOTSUPP; + + br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + if (!br_spec) + return -EINVAL; + + nla_for_each_nested(attr, br_spec, rem) { + int status; + __u16 mode; + + if (nla_type(attr) != IFLA_BRIDGE_MODE) + continue; + + if (nla_len(attr) < sizeof(mode)) + return -EINVAL; + + mode = nla_get_u16(attr); + status = ixgbe_configure_bridge_mode(adapter, mode); + if (status) + return status; + + break; + } + + return 0; +} + +static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, + struct net_device *dev, + u32 filter_mask, int nlflags) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + + if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) + return 0; + + return ndo_dflt_bridge_getlink(skb, pid, seq, dev, + adapter->bridge_mode, 0, 0, nlflags, + filter_mask, NULL); +} + +static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev) +{ + struct ixgbe_adapter *adapter = netdev_priv(pdev); + struct ixgbe_fwd_adapter *accel; + int tcs = adapter->hw_tcs ? : 1; + int pool, err; + + if (adapter->xdp_prog) { + e_warn(probe, "L2FW offload is not supported with XDP\n"); + return ERR_PTR(-EINVAL); + } + + /* The hardware supported by ixgbe only filters on the destination MAC + * address. In order to avoid issues we only support offloading modes + * where the hardware can actually provide the functionality. + */ + if (!macvlan_supports_dest_filter(vdev)) + return ERR_PTR(-EMEDIUMTYPE); + + /* We need to lock down the macvlan to be a single queue device so that + * we can reuse the tc_to_txq field in the macvlan netdev to represent + * the queue mapping to our netdev. + */ + if (netif_is_multiqueue(vdev)) + return ERR_PTR(-ERANGE); + + pool = find_first_zero_bit(adapter->fwd_bitmask, adapter->num_rx_pools); + if (pool == adapter->num_rx_pools) { + u16 used_pools = adapter->num_vfs + adapter->num_rx_pools; + u16 reserved_pools; + + if (((adapter->flags & IXGBE_FLAG_DCB_ENABLED) && + adapter->num_rx_pools >= (MAX_TX_QUEUES / tcs)) || + adapter->num_rx_pools > IXGBE_MAX_MACVLANS) + return ERR_PTR(-EBUSY); + + /* Hardware has a limited number of available pools. Each VF, + * and the PF require a pool. Check to ensure we don't + * attempt to use more then the available number of pools. + */ + if (used_pools >= IXGBE_MAX_VF_FUNCTIONS) + return ERR_PTR(-EBUSY); + + /* Enable VMDq flag so device will be set in VM mode */ + adapter->flags |= IXGBE_FLAG_VMDQ_ENABLED | + IXGBE_FLAG_SRIOV_ENABLED; + + /* Try to reserve as many queues per pool as possible, + * we start with the configurations that support 4 queues + * per pools, followed by 2, and then by just 1 per pool. + */ + if (used_pools < 32 && adapter->num_rx_pools < 16) + reserved_pools = min_t(u16, + 32 - used_pools, + 16 - adapter->num_rx_pools); + else if (adapter->num_rx_pools < 32) + reserved_pools = min_t(u16, + 64 - used_pools, + 32 - adapter->num_rx_pools); + else + reserved_pools = 64 - used_pools; + + + if (!reserved_pools) + return ERR_PTR(-EBUSY); + + adapter->ring_feature[RING_F_VMDQ].limit += reserved_pools; + + /* Force reinit of ring allocation with VMDQ enabled */ + err = ixgbe_setup_tc(pdev, adapter->hw_tcs); + if (err) + return ERR_PTR(err); + + if (pool >= adapter->num_rx_pools) + return ERR_PTR(-ENOMEM); + } + + accel = kzalloc(sizeof(*accel), GFP_KERNEL); + if (!accel) + return ERR_PTR(-ENOMEM); + + set_bit(pool, adapter->fwd_bitmask); + netdev_set_sb_channel(vdev, pool); + accel->pool = pool; + accel->netdev = vdev; + + if (!netif_running(pdev)) + return accel; + + err = ixgbe_fwd_ring_up(adapter, accel); + if (err) + return ERR_PTR(err); + + return accel; +} + +static void ixgbe_fwd_del(struct net_device *pdev, void *priv) +{ + struct ixgbe_fwd_adapter *accel = priv; + struct ixgbe_adapter *adapter = netdev_priv(pdev); + unsigned int rxbase = accel->rx_base_queue; + unsigned int i; + + /* delete unicast filter associated with offloaded interface */ + ixgbe_del_mac_filter(adapter, accel->netdev->dev_addr, + VMDQ_P(accel->pool)); + + /* Allow remaining Rx packets to get flushed out of the + * Rx FIFO before we drop the netdev for the ring. + */ + usleep_range(10000, 20000); + + for (i = 0; i < adapter->num_rx_queues_per_pool; i++) { + struct ixgbe_ring *ring = adapter->rx_ring[rxbase + i]; + struct ixgbe_q_vector *qv = ring->q_vector; + + /* Make sure we aren't processing any packets and clear + * netdev to shut down the ring. + */ + if (netif_running(adapter->netdev)) + napi_synchronize(&qv->napi); + ring->netdev = NULL; + } + + /* unbind the queues and drop the subordinate channel config */ + netdev_unbind_sb_channel(pdev, accel->netdev); + netdev_set_sb_channel(accel->netdev, 0); + + clear_bit(accel->pool, adapter->fwd_bitmask); + kfree(accel); +} + +#define IXGBE_MAX_MAC_HDR_LEN 127 +#define IXGBE_MAX_NETWORK_HDR_LEN 511 + +static netdev_features_t +ixgbe_features_check(struct sk_buff *skb, struct net_device *dev, + netdev_features_t features) +{ + unsigned int network_hdr_len, mac_hdr_len; + + /* Make certain the headers can be described by a context descriptor */ + mac_hdr_len = skb_network_header(skb) - skb->data; + if (unlikely(mac_hdr_len > IXGBE_MAX_MAC_HDR_LEN)) + return features & ~(NETIF_F_HW_CSUM | + NETIF_F_SCTP_CRC | + NETIF_F_GSO_UDP_L4 | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_TSO | + NETIF_F_TSO6); + + network_hdr_len = skb_checksum_start(skb) - skb_network_header(skb); + if (unlikely(network_hdr_len > IXGBE_MAX_NETWORK_HDR_LEN)) + return features & ~(NETIF_F_HW_CSUM | + NETIF_F_SCTP_CRC | + NETIF_F_GSO_UDP_L4 | + NETIF_F_TSO | + NETIF_F_TSO6); + + /* We can only support IPV4 TSO in tunnels if we can mangle the + * inner IP ID field, so strip TSO if MANGLEID is not supported. + * IPsec offoad sets skb->encapsulation but still can handle + * the TSO, so it's the exception. + */ + if (skb->encapsulation && !(features & NETIF_F_TSO_MANGLEID)) { +#ifdef CONFIG_IXGBE_IPSEC + if (!secpath_exists(skb)) +#endif + features &= ~NETIF_F_TSO; + } + + return features; +} + +static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) +{ + int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct bpf_prog *old_prog; + bool need_reset; + int num_queues; + + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) + return -EINVAL; + + if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) + return -EINVAL; + + /* verify ixgbe ring attributes are sufficient for XDP */ + for (i = 0; i < adapter->num_rx_queues; i++) { + struct ixgbe_ring *ring = adapter->rx_ring[i]; + + if (ring_is_rsc_enabled(ring)) + return -EINVAL; + + if (frame_size > ixgbe_rx_bufsz(ring)) + return -EINVAL; + } + + if (nr_cpu_ids > MAX_XDP_QUEUES) + return -ENOMEM; + + old_prog = xchg(&adapter->xdp_prog, prog); + need_reset = (!!prog != !!old_prog); + + /* If transitioning XDP modes reconfigure rings */ + if (need_reset) { + int err; + + if (!prog) + /* Wait until ndo_xsk_wakeup completes. */ + synchronize_rcu(); + err = ixgbe_setup_tc(dev, adapter->hw_tcs); + + if (err) { + rcu_assign_pointer(adapter->xdp_prog, old_prog); + return -EINVAL; + } + } else { + for (i = 0; i < adapter->num_rx_queues; i++) + (void)xchg(&adapter->rx_ring[i]->xdp_prog, + adapter->xdp_prog); + } + + if (old_prog) + bpf_prog_put(old_prog); + + /* Kick start the NAPI context if there is an AF_XDP socket open + * on that queue id. This so that receiving will start. + */ + if (need_reset && prog) { + num_queues = min_t(int, adapter->num_rx_queues, + adapter->num_xdp_queues); + for (i = 0; i < num_queues; i++) + if (adapter->xdp_ring[i]->xsk_pool) + (void)ixgbe_xsk_wakeup(adapter->netdev, i, + XDP_WAKEUP_RX); + } + + return 0; +} + +static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + + switch (xdp->command) { + case XDP_SETUP_PROG: + return ixgbe_xdp_setup(dev, xdp->prog); + case XDP_SETUP_XSK_POOL: + return ixgbe_xsk_pool_setup(adapter, xdp->xsk.pool, + xdp->xsk.queue_id); + + default: + return -EINVAL; + } +} + +void ixgbe_xdp_ring_update_tail(struct ixgbe_ring *ring) +{ + /* Force memory writes to complete before letting h/w know there + * are new descriptors to fetch. + */ + wmb(); + writel(ring->next_to_use, ring->tail); +} + +static int ixgbe_xdp_xmit(struct net_device *dev, int n, + struct xdp_frame **frames, u32 flags) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_ring *ring; + int drops = 0; + int i; + + if (unlikely(test_bit(__IXGBE_DOWN, &adapter->state))) + return -ENETDOWN; + + if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) + return -EINVAL; + + /* During program transitions its possible adapter->xdp_prog is assigned + * but ring has not been configured yet. In this case simply abort xmit. + */ + ring = adapter->xdp_prog ? adapter->xdp_ring[smp_processor_id()] : NULL; + if (unlikely(!ring)) + return -ENXIO; + + if (unlikely(test_bit(__IXGBE_TX_DISABLED, &ring->state))) + return -ENXIO; + + for (i = 0; i < n; i++) { + struct xdp_frame *xdpf = frames[i]; + int err; + + err = ixgbe_xmit_xdp_ring(adapter, xdpf); + if (err != IXGBE_XDP_TX) { + xdp_return_frame_rx_napi(xdpf); + drops++; + } + } + + if (unlikely(flags & XDP_XMIT_FLUSH)) + ixgbe_xdp_ring_update_tail(ring); + + return n - drops; +} + +static const struct net_device_ops ixgbe_netdev_ops = { + .ndo_open = ixgbe_open, + .ndo_stop = ixgbe_close, + .ndo_start_xmit = ixgbe_xmit_frame, + .ndo_set_rx_mode = ixgbe_set_rx_mode, + .ndo_validate_addr = eth_validate_addr, + .ndo_set_mac_address = ixgbe_set_mac, + .ndo_change_mtu = ixgbe_change_mtu, + .ndo_tx_timeout = ixgbe_tx_timeout, + .ndo_set_tx_maxrate = ixgbe_tx_maxrate, + .ndo_vlan_rx_add_vid = ixgbe_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = ixgbe_vlan_rx_kill_vid, + .ndo_do_ioctl = ixgbe_ioctl, + .ndo_set_vf_mac = ixgbe_ndo_set_vf_mac, + .ndo_set_vf_vlan = ixgbe_ndo_set_vf_vlan, + .ndo_set_vf_rate = ixgbe_ndo_set_vf_bw, + .ndo_set_vf_spoofchk = ixgbe_ndo_set_vf_spoofchk, + .ndo_set_vf_rss_query_en = ixgbe_ndo_set_vf_rss_query_en, + .ndo_set_vf_trust = ixgbe_ndo_set_vf_trust, + .ndo_get_vf_config = ixgbe_ndo_get_vf_config, + .ndo_get_stats64 = ixgbe_get_stats64, + .ndo_setup_tc = __ixgbe_setup_tc, +#ifdef IXGBE_FCOE + .ndo_select_queue = ixgbe_select_queue, + .ndo_fcoe_ddp_setup = ixgbe_fcoe_ddp_get, + .ndo_fcoe_ddp_target = ixgbe_fcoe_ddp_target, + .ndo_fcoe_ddp_done = ixgbe_fcoe_ddp_put, + .ndo_fcoe_enable = ixgbe_fcoe_enable, + .ndo_fcoe_disable = ixgbe_fcoe_disable, + .ndo_fcoe_get_wwn = ixgbe_fcoe_get_wwn, + .ndo_fcoe_get_hbainfo = ixgbe_fcoe_get_hbainfo, +#endif /* IXGBE_FCOE */ + .ndo_set_features = ixgbe_set_features, + .ndo_fix_features = ixgbe_fix_features, + .ndo_fdb_add = ixgbe_ndo_fdb_add, + .ndo_bridge_setlink = ixgbe_ndo_bridge_setlink, + .ndo_bridge_getlink = ixgbe_ndo_bridge_getlink, + .ndo_dfwd_add_station = ixgbe_fwd_add, + .ndo_dfwd_del_station = ixgbe_fwd_del, + .ndo_udp_tunnel_add = udp_tunnel_nic_add_port, + .ndo_udp_tunnel_del = udp_tunnel_nic_del_port, + .ndo_features_check = ixgbe_features_check, + .ndo_bpf = ixgbe_xdp, + .ndo_xdp_xmit = ixgbe_xdp_xmit, + .ndo_xsk_wakeup = ixgbe_xsk_wakeup, +}; + +static void ixgbe_disable_txr_hw(struct ixgbe_adapter *adapter, + struct ixgbe_ring *tx_ring) +{ + unsigned long wait_delay, delay_interval; + struct ixgbe_hw *hw = &adapter->hw; + u8 reg_idx = tx_ring->reg_idx; + int wait_loop; + u32 txdctl; + + IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH); + + /* delay mechanism from ixgbe_disable_tx */ + delay_interval = ixgbe_get_completion_timeout(adapter) / 100; + + wait_loop = IXGBE_MAX_RX_DESC_POLL; + wait_delay = delay_interval; + + while (wait_loop--) { + usleep_range(wait_delay, wait_delay + 10); + wait_delay += delay_interval * 2; + txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx)); + + if (!(txdctl & IXGBE_TXDCTL_ENABLE)) + return; + } + + e_err(drv, "TXDCTL.ENABLE not cleared within the polling period\n"); +} + +static void ixgbe_disable_txr(struct ixgbe_adapter *adapter, + struct ixgbe_ring *tx_ring) +{ + set_bit(__IXGBE_TX_DISABLED, &tx_ring->state); + ixgbe_disable_txr_hw(adapter, tx_ring); +} + +static void ixgbe_disable_rxr_hw(struct ixgbe_adapter *adapter, + struct ixgbe_ring *rx_ring) +{ + unsigned long wait_delay, delay_interval; + struct ixgbe_hw *hw = &adapter->hw; + u8 reg_idx = rx_ring->reg_idx; + int wait_loop; + u32 rxdctl; + + rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx)); + rxdctl &= ~IXGBE_RXDCTL_ENABLE; + rxdctl |= IXGBE_RXDCTL_SWFLSH; + + /* write value back with RXDCTL.ENABLE bit cleared */ + IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl); + + /* RXDCTL.EN may not change on 82598 if link is down, so skip it */ + if (hw->mac.type == ixgbe_mac_82598EB && + !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP)) + return; + + /* delay mechanism from ixgbe_disable_rx */ + delay_interval = ixgbe_get_completion_timeout(adapter) / 100; + + wait_loop = IXGBE_MAX_RX_DESC_POLL; + wait_delay = delay_interval; + + while (wait_loop--) { + usleep_range(wait_delay, wait_delay + 10); + wait_delay += delay_interval * 2; + rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx)); + + if (!(rxdctl & IXGBE_RXDCTL_ENABLE)) + return; + } + + e_err(drv, "RXDCTL.ENABLE not cleared within the polling period\n"); +} + +static void ixgbe_reset_txr_stats(struct ixgbe_ring *tx_ring) +{ + memset(&tx_ring->stats, 0, sizeof(tx_ring->stats)); + memset(&tx_ring->tx_stats, 0, sizeof(tx_ring->tx_stats)); +} + +static void ixgbe_reset_rxr_stats(struct ixgbe_ring *rx_ring) +{ + memset(&rx_ring->stats, 0, sizeof(rx_ring->stats)); + memset(&rx_ring->rx_stats, 0, sizeof(rx_ring->rx_stats)); +} + +/** + * ixgbe_txrx_ring_disable - Disable Rx/Tx/XDP Tx rings + * @adapter: adapter structure + * @ring: ring index + * + * This function disables a certain Rx/Tx/XDP Tx ring. The function + * assumes that the netdev is running. + **/ +void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring) +{ + struct ixgbe_ring *rx_ring, *tx_ring, *xdp_ring; + + rx_ring = adapter->rx_ring[ring]; + tx_ring = adapter->tx_ring[ring]; + xdp_ring = adapter->xdp_ring[ring]; + + ixgbe_disable_txr(adapter, tx_ring); + if (xdp_ring) + ixgbe_disable_txr(adapter, xdp_ring); + ixgbe_disable_rxr_hw(adapter, rx_ring); + + if (xdp_ring) + synchronize_rcu(); + + /* Rx/Tx/XDP Tx share the same napi context. */ + napi_disable(&rx_ring->q_vector->napi); + + ixgbe_clean_tx_ring(tx_ring); + if (xdp_ring) + ixgbe_clean_tx_ring(xdp_ring); + ixgbe_clean_rx_ring(rx_ring); + + ixgbe_reset_txr_stats(tx_ring); + if (xdp_ring) + ixgbe_reset_txr_stats(xdp_ring); + ixgbe_reset_rxr_stats(rx_ring); +} + +/** + * ixgbe_txrx_ring_enable - Enable Rx/Tx/XDP Tx rings + * @adapter: adapter structure + * @ring: ring index + * + * This function enables a certain Rx/Tx/XDP Tx ring. The function + * assumes that the netdev is running. + **/ +void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring) +{ + struct ixgbe_ring *rx_ring, *tx_ring, *xdp_ring; + + rx_ring = adapter->rx_ring[ring]; + tx_ring = adapter->tx_ring[ring]; + xdp_ring = adapter->xdp_ring[ring]; + + /* Rx/Tx/XDP Tx share the same napi context. */ + napi_enable(&rx_ring->q_vector->napi); + + ixgbe_configure_tx_ring(adapter, tx_ring); + if (xdp_ring) + ixgbe_configure_tx_ring(adapter, xdp_ring); + ixgbe_configure_rx_ring(adapter, rx_ring); + + clear_bit(__IXGBE_TX_DISABLED, &tx_ring->state); + if (xdp_ring) + clear_bit(__IXGBE_TX_DISABLED, &xdp_ring->state); +} + +/** + * ixgbe_enumerate_functions - Get the number of ports this device has + * @adapter: adapter structure + * + * This function enumerates the phsyical functions co-located on a single slot, + * in order to determine how many ports a device has. This is most useful in + * determining the required GT/s of PCIe bandwidth necessary for optimal + * performance. + **/ +static inline int ixgbe_enumerate_functions(struct ixgbe_adapter *adapter) +{ + struct pci_dev *entry, *pdev = adapter->pdev; + int physfns = 0; + + /* Some cards can not use the generic count PCIe functions method, + * because they are behind a parent switch, so we hardcode these with + * the correct number of functions. + */ + if (ixgbe_pcie_from_parent(&adapter->hw)) + physfns = 4; + + list_for_each_entry(entry, &adapter->pdev->bus->devices, bus_list) { + /* don't count virtual functions */ + if (entry->is_virtfn) + continue; + + /* When the devices on the bus don't all match our device ID, + * we can't reliably determine the correct number of + * functions. This can occur if a function has been direct + * attached to a virtual machine using VT-d, for example. In + * this case, simply return -1 to indicate this. + */ + if ((entry->vendor != pdev->vendor) || + (entry->device != pdev->device)) + return -1; + + physfns++; + } + + return physfns; +} + +/** + * ixgbe_wol_supported - Check whether device supports WoL + * @adapter: the adapter private structure + * @device_id: the device ID + * @subdevice_id: the subsystem device ID + * + * This function is used by probe and ethtool to determine + * which devices have WoL support + * + **/ +bool ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id, + u16 subdevice_id) +{ + struct ixgbe_hw *hw = &adapter->hw; + u16 wol_cap = adapter->eeprom_cap & IXGBE_DEVICE_CAPS_WOL_MASK; + + /* WOL not supported on 82598 */ + if (hw->mac.type == ixgbe_mac_82598EB) + return false; + + /* check eeprom to see if WOL is enabled for X540 and newer */ + if (hw->mac.type >= ixgbe_mac_X540) { + if ((wol_cap == IXGBE_DEVICE_CAPS_WOL_PORT0_1) || + ((wol_cap == IXGBE_DEVICE_CAPS_WOL_PORT0) && + (hw->bus.func == 0))) + return true; + } + + /* WOL is determined based on device IDs for 82599 MACs */ + switch (device_id) { + case IXGBE_DEV_ID_82599_SFP: + /* Only these subdevices could supports WOL */ + switch (subdevice_id) { + case IXGBE_SUBDEV_ID_82599_560FLR: + case IXGBE_SUBDEV_ID_82599_LOM_SNAP6: + case IXGBE_SUBDEV_ID_82599_SFP_WOL0: + case IXGBE_SUBDEV_ID_82599_SFP_2OCP: + /* only support first port */ + if (hw->bus.func != 0) + break; + fallthrough; + case IXGBE_SUBDEV_ID_82599_SP_560FLR: + case IXGBE_SUBDEV_ID_82599_SFP: + case IXGBE_SUBDEV_ID_82599_RNDC: + case IXGBE_SUBDEV_ID_82599_ECNA_DP: + case IXGBE_SUBDEV_ID_82599_SFP_1OCP: + case IXGBE_SUBDEV_ID_82599_SFP_LOM_OEM1: + case IXGBE_SUBDEV_ID_82599_SFP_LOM_OEM2: + return true; + } + break; + case IXGBE_DEV_ID_82599EN_SFP: + /* Only these subdevices support WOL */ + switch (subdevice_id) { + case IXGBE_SUBDEV_ID_82599EN_SFP_OCP1: + return true; + } + break; + case IXGBE_DEV_ID_82599_COMBO_BACKPLANE: + /* All except this subdevice support WOL */ + if (subdevice_id != IXGBE_SUBDEV_ID_82599_KX4_KR_MEZZ) + return true; + break; + case IXGBE_DEV_ID_82599_KX4: + return true; + default: + break; + } + + return false; +} + +/** + * ixgbe_set_fw_version - Set FW version + * @adapter: the adapter private structure + * + * This function is used by probe and ethtool to determine the FW version to + * format to display. The FW version is taken from the EEPROM/NVM. + */ +static void ixgbe_set_fw_version(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_nvm_version nvm_ver; + + ixgbe_get_oem_prod_version(hw, &nvm_ver); + if (nvm_ver.oem_valid) { + snprintf(adapter->eeprom_id, sizeof(adapter->eeprom_id), + "%x.%x.%x", nvm_ver.oem_major, nvm_ver.oem_minor, + nvm_ver.oem_release); + return; + } + + ixgbe_get_etk_id(hw, &nvm_ver); + ixgbe_get_orom_version(hw, &nvm_ver); + + if (nvm_ver.or_valid) { + snprintf(adapter->eeprom_id, sizeof(adapter->eeprom_id), + "0x%08x, %d.%d.%d", nvm_ver.etk_id, nvm_ver.or_major, + nvm_ver.or_build, nvm_ver.or_patch); + return; + } + + /* Set ETrack ID format */ + snprintf(adapter->eeprom_id, sizeof(adapter->eeprom_id), + "0x%08x", nvm_ver.etk_id); +} + +/** + * ixgbe_probe - Device Initialization Routine + * @pdev: PCI device information struct + * @ent: entry in ixgbe_pci_tbl + * + * Returns 0 on success, negative on failure + * + * ixgbe_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 ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) +{ + struct net_device *netdev; + struct ixgbe_adapter *adapter = NULL; + struct ixgbe_hw *hw; + const struct ixgbe_info *ii = ixgbe_info_tbl[ent->driver_data]; + int i, err, pci_using_dac, expected_gts; + unsigned int indices = MAX_TX_QUEUES; + u8 part_str[IXGBE_PBANUM_LENGTH]; + bool disable_dev = false; +#ifdef IXGBE_FCOE + u16 device_caps; +#endif + u32 eec; + + /* Catch broken hardware that put the wrong VF device ID in + * the PCIe SR-IOV capability. + */ + if (pdev->is_virtfn) { + WARN(1, KERN_ERR "%s (%hx:%hx) should not be a VF!\n", + pci_name(pdev), pdev->vendor, pdev->device); + return -EINVAL; + } + + err = pci_enable_device_mem(pdev); + if (err) + return err; + + if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) { + pci_using_dac = 1; + } else { + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) { + dev_err(&pdev->dev, + "No usable DMA configuration, aborting\n"); + goto err_dma; + } + pci_using_dac = 0; + } + + err = pci_request_mem_regions(pdev, ixgbe_driver_name); + if (err) { + dev_err(&pdev->dev, + "pci_request_selected_regions failed 0x%x\n", err); + goto err_pci_reg; + } + + pci_enable_pcie_error_reporting(pdev); + + pci_set_master(pdev); + pci_save_state(pdev); + + if (ii->mac == ixgbe_mac_82598EB) { +#ifdef CONFIG_IXGBE_DCB + /* 8 TC w/ 4 queues per TC */ + indices = 4 * MAX_TRAFFIC_CLASS; +#else + indices = IXGBE_MAX_RSS_INDICES; +#endif + } + + netdev = alloc_etherdev_mq(sizeof(struct ixgbe_adapter), indices); + if (!netdev) { + err = -ENOMEM; + goto err_alloc_etherdev; + } + + SET_NETDEV_DEV(netdev, &pdev->dev); + + adapter = netdev_priv(netdev); + + adapter->netdev = netdev; + adapter->pdev = pdev; + hw = &adapter->hw; + hw->back = adapter; + adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE); + + hw->hw_addr = ioremap(pci_resource_start(pdev, 0), + pci_resource_len(pdev, 0)); + adapter->io_addr = hw->hw_addr; + if (!hw->hw_addr) { + err = -EIO; + goto err_ioremap; + } + + netdev->netdev_ops = &ixgbe_netdev_ops; + ixgbe_set_ethtool_ops(netdev); + netdev->watchdog_timeo = 5 * HZ; + strlcpy(netdev->name, pci_name(pdev), sizeof(netdev->name)); + + /* Setup hw api */ + hw->mac.ops = *ii->mac_ops; + hw->mac.type = ii->mac; + hw->mvals = ii->mvals; + if (ii->link_ops) + hw->link.ops = *ii->link_ops; + + /* EEPROM */ + hw->eeprom.ops = *ii->eeprom_ops; + eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw)); + if (ixgbe_removed(hw->hw_addr)) { + err = -EIO; + goto err_ioremap; + } + /* If EEPROM is valid (bit 8 = 1), use default otherwise use bit bang */ + if (!(eec & BIT(8))) + hw->eeprom.ops.read = &ixgbe_read_eeprom_bit_bang_generic; + + /* PHY */ + hw->phy.ops = *ii->phy_ops; + hw->phy.sfp_type = ixgbe_sfp_type_unknown; + /* ixgbe_identify_phy_generic will set prtad and mmds properly */ + hw->phy.mdio.prtad = MDIO_PRTAD_NONE; + hw->phy.mdio.mmds = 0; + hw->phy.mdio.mode_support = MDIO_SUPPORTS_C45 | MDIO_EMULATE_C22; + hw->phy.mdio.dev = netdev; + hw->phy.mdio.mdio_read = ixgbe_mdio_read; + hw->phy.mdio.mdio_write = ixgbe_mdio_write; + + /* setup the private structure */ + err = ixgbe_sw_init(adapter, ii); + if (err) + goto err_sw_init; + + switch (adapter->hw.mac.type) { + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + netdev->udp_tunnel_nic_info = &ixgbe_udp_tunnels_x550; + break; + case ixgbe_mac_x550em_a: + netdev->udp_tunnel_nic_info = &ixgbe_udp_tunnels_x550em_a; + break; + default: + break; + } + + /* Make sure the SWFW semaphore is in a valid state */ + if (hw->mac.ops.init_swfw_sync) + hw->mac.ops.init_swfw_sync(hw); + + /* Make it possible the adapter to be woken up via WOL */ + switch (adapter->hw.mac.type) { + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + IXGBE_WRITE_REG(&adapter->hw, IXGBE_WUS, ~0); + break; + default: + break; + } + + /* + * If there is a fan on this device and it has failed log the + * failure. + */ + if (adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE) { + u32 esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + if (esdp & IXGBE_ESDP_SDP1) + e_crit(probe, "Fan has stopped, replace the adapter\n"); + } + + if (allow_unsupported_sfp) + hw->allow_unsupported_sfp = allow_unsupported_sfp; + + /* reset_hw fills in the perm_addr as well */ + hw->phy.reset_if_overtemp = true; + err = hw->mac.ops.reset_hw(hw); + hw->phy.reset_if_overtemp = false; + ixgbe_set_eee_capable(adapter); + if (err == IXGBE_ERR_SFP_NOT_PRESENT) { + err = 0; + } else if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) { + e_dev_err("failed to load because an unsupported SFP+ or QSFP module type was detected.\n"); + e_dev_err("Reload the driver after installing a supported module.\n"); + goto err_sw_init; + } else if (err) { + e_dev_err("HW Init failed: %d\n", err); + goto err_sw_init; + } + +#ifdef CONFIG_PCI_IOV + /* SR-IOV not supported on the 82598 */ + if (adapter->hw.mac.type == ixgbe_mac_82598EB) + goto skip_sriov; + /* Mailbox */ + ixgbe_init_mbx_params_pf(hw); + hw->mbx.ops = ii->mbx_ops; + pci_sriov_set_totalvfs(pdev, IXGBE_MAX_VFS_DRV_LIMIT); + ixgbe_enable_sriov(adapter, max_vfs); +skip_sriov: + +#endif + netdev->features = NETIF_F_SG | + NETIF_F_TSO | + NETIF_F_TSO6 | + NETIF_F_RXHASH | + NETIF_F_RXCSUM | + NETIF_F_HW_CSUM; + +#define IXGBE_GSO_PARTIAL_FEATURES (NETIF_F_GSO_GRE | \ + NETIF_F_GSO_GRE_CSUM | \ + NETIF_F_GSO_IPXIP4 | \ + NETIF_F_GSO_IPXIP6 | \ + NETIF_F_GSO_UDP_TUNNEL | \ + NETIF_F_GSO_UDP_TUNNEL_CSUM) + + netdev->gso_partial_features = IXGBE_GSO_PARTIAL_FEATURES; + netdev->features |= NETIF_F_GSO_PARTIAL | + IXGBE_GSO_PARTIAL_FEATURES; + + if (hw->mac.type >= ixgbe_mac_82599EB) + netdev->features |= NETIF_F_SCTP_CRC | NETIF_F_GSO_UDP_L4; + +#ifdef CONFIG_IXGBE_IPSEC +#define IXGBE_ESP_FEATURES (NETIF_F_HW_ESP | \ + NETIF_F_HW_ESP_TX_CSUM | \ + NETIF_F_GSO_ESP) + + if (adapter->ipsec) + netdev->features |= IXGBE_ESP_FEATURES; +#endif + /* copy netdev features into list of user selectable features */ + netdev->hw_features |= netdev->features | + NETIF_F_HW_VLAN_CTAG_FILTER | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_RXALL | + NETIF_F_HW_L2FW_DOFFLOAD; + + if (hw->mac.type >= ixgbe_mac_82599EB) + netdev->hw_features |= NETIF_F_NTUPLE | + NETIF_F_HW_TC; + + if (pci_using_dac) + netdev->features |= NETIF_F_HIGHDMA; + + netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID; + netdev->hw_enc_features |= netdev->vlan_features; + netdev->mpls_features |= NETIF_F_SG | + NETIF_F_TSO | + NETIF_F_TSO6 | + NETIF_F_HW_CSUM; + netdev->mpls_features |= IXGBE_GSO_PARTIAL_FEATURES; + + /* set this bit last since it cannot be part of vlan_features */ + netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_TX; + + netdev->priv_flags |= IFF_UNICAST_FLT; + netdev->priv_flags |= IFF_SUPP_NOFCS; + + /* MTU range: 68 - 9710 */ + netdev->min_mtu = ETH_MIN_MTU; + netdev->max_mtu = IXGBE_MAX_JUMBO_FRAME_SIZE - (ETH_HLEN + ETH_FCS_LEN); + +#ifdef CONFIG_IXGBE_DCB + if (adapter->flags & IXGBE_FLAG_DCB_CAPABLE) + netdev->dcbnl_ops = &ixgbe_dcbnl_ops; +#endif + +#ifdef IXGBE_FCOE + if (adapter->flags & IXGBE_FLAG_FCOE_CAPABLE) { + unsigned int fcoe_l; + + if (hw->mac.ops.get_device_caps) { + hw->mac.ops.get_device_caps(hw, &device_caps); + if (device_caps & IXGBE_DEVICE_CAPS_FCOE_OFFLOADS) + adapter->flags &= ~IXGBE_FLAG_FCOE_CAPABLE; + } + + + fcoe_l = min_t(int, IXGBE_FCRETA_SIZE, num_online_cpus()); + adapter->ring_feature[RING_F_FCOE].limit = fcoe_l; + + netdev->features |= NETIF_F_FSO | + NETIF_F_FCOE_CRC; + + netdev->vlan_features |= NETIF_F_FSO | + NETIF_F_FCOE_CRC | + NETIF_F_FCOE_MTU; + } +#endif /* IXGBE_FCOE */ + if (adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE) + netdev->hw_features |= NETIF_F_LRO; + if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) + netdev->features |= NETIF_F_LRO; + + if (ixgbe_check_fw_error(adapter)) { + err = -EIO; + goto err_sw_init; + } + + /* make sure the EEPROM is good */ + if (hw->eeprom.ops.validate_checksum(hw, NULL) < 0) { + e_dev_err("The EEPROM Checksum Is Not Valid\n"); + err = -EIO; + goto err_sw_init; + } + + eth_platform_get_mac_address(&adapter->pdev->dev, + adapter->hw.mac.perm_addr); + + memcpy(netdev->dev_addr, hw->mac.perm_addr, netdev->addr_len); + + if (!is_valid_ether_addr(netdev->dev_addr)) { + e_dev_err("invalid MAC address\n"); + err = -EIO; + goto err_sw_init; + } + + /* Set hw->mac.addr to permanent MAC address */ + ether_addr_copy(hw->mac.addr, hw->mac.perm_addr); + ixgbe_mac_set_default_filter(adapter); + + timer_setup(&adapter->service_timer, ixgbe_service_timer, 0); + + if (ixgbe_removed(hw->hw_addr)) { + err = -EIO; + goto err_sw_init; + } + INIT_WORK(&adapter->service_task, ixgbe_service_task); + set_bit(__IXGBE_SERVICE_INITED, &adapter->state); + clear_bit(__IXGBE_SERVICE_SCHED, &adapter->state); + + err = ixgbe_init_interrupt_scheme(adapter); + if (err) + goto err_sw_init; + + for (i = 0; i < adapter->num_rx_queues; i++) + u64_stats_init(&adapter->rx_ring[i]->syncp); + for (i = 0; i < adapter->num_tx_queues; i++) + u64_stats_init(&adapter->tx_ring[i]->syncp); + for (i = 0; i < adapter->num_xdp_queues; i++) + u64_stats_init(&adapter->xdp_ring[i]->syncp); + + /* WOL not supported for all devices */ + adapter->wol = 0; + hw->eeprom.ops.read(hw, 0x2c, &adapter->eeprom_cap); + hw->wol_enabled = ixgbe_wol_supported(adapter, pdev->device, + pdev->subsystem_device); + if (hw->wol_enabled) + adapter->wol = IXGBE_WUFC_MAG; + + device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol); + + /* save off EEPROM version number */ + ixgbe_set_fw_version(adapter); + + /* pick up the PCI bus settings for reporting later */ + if (ixgbe_pcie_from_parent(hw)) + ixgbe_get_parent_bus_info(adapter); + else + hw->mac.ops.get_bus_info(hw); + + /* calculate the expected PCIe bandwidth required for optimal + * performance. Note that some older parts will never have enough + * bandwidth due to being older generation PCIe parts. We clamp these + * parts to ensure no warning is displayed if it can't be fixed. + */ + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + expected_gts = min(ixgbe_enumerate_functions(adapter) * 10, 16); + break; + default: + expected_gts = ixgbe_enumerate_functions(adapter) * 10; + break; + } + + /* don't check link if we failed to enumerate functions */ + if (expected_gts > 0) + ixgbe_check_minimum_link(adapter, expected_gts); + + err = ixgbe_read_pba_string_generic(hw, part_str, sizeof(part_str)); + if (err) + strlcpy(part_str, "Unknown", sizeof(part_str)); + if (ixgbe_is_sfp(hw) && hw->phy.sfp_type != ixgbe_sfp_type_not_present) + e_dev_info("MAC: %d, PHY: %d, SFP+: %d, PBA No: %s\n", + hw->mac.type, hw->phy.type, hw->phy.sfp_type, + part_str); + else + e_dev_info("MAC: %d, PHY: %d, PBA No: %s\n", + hw->mac.type, hw->phy.type, part_str); + + e_dev_info("%pM\n", netdev->dev_addr); + + /* reset the hardware with the new settings */ + err = hw->mac.ops.start_hw(hw); + if (err == IXGBE_ERR_EEPROM_VERSION) { + /* We are running on a pre-production device, log a warning */ + e_dev_warn("This device is a pre-production adapter/LOM. " + "Please be aware there may be issues associated " + "with your hardware. If you are experiencing " + "problems please contact your Intel or hardware " + "representative who provided you with this " + "hardware.\n"); + } + strcpy(netdev->name, "eth%d"); + pci_set_drvdata(pdev, adapter); + err = register_netdev(netdev); + if (err) + goto err_register; + + + /* power down the optics for 82599 SFP+ fiber */ + if (hw->mac.ops.disable_tx_laser) + hw->mac.ops.disable_tx_laser(hw); + + /* carrier off reporting is important to ethtool even BEFORE open */ + netif_carrier_off(netdev); + +#ifdef CONFIG_IXGBE_DCA + if (dca_add_requester(&pdev->dev) == 0) { + adapter->flags |= IXGBE_FLAG_DCA_ENABLED; + ixgbe_setup_dca(adapter); + } +#endif + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { + e_info(probe, "IOV is enabled with %d VFs\n", adapter->num_vfs); + for (i = 0; i < adapter->num_vfs; i++) + ixgbe_vf_configuration(pdev, (i | 0x10000000)); + } + + /* firmware requires driver version to be 0xFFFFFFFF + * since os does not support feature + */ + if (hw->mac.ops.set_fw_drv_ver) + hw->mac.ops.set_fw_drv_ver(hw, 0xFF, 0xFF, 0xFF, 0xFF, + sizeof(UTS_RELEASE) - 1, + UTS_RELEASE); + + /* add san mac addr to netdev */ + ixgbe_add_sanmac_netdev(netdev); + + e_dev_info("%s\n", ixgbe_default_device_descr); + +#ifdef CONFIG_IXGBE_HWMON + if (ixgbe_sysfs_init(adapter)) + e_err(probe, "failed to allocate sysfs resources\n"); +#endif /* CONFIG_IXGBE_HWMON */ + + ixgbe_dbg_adapter_init(adapter); + + /* setup link for SFP devices with MNG FW, else wait for IXGBE_UP */ + if (ixgbe_mng_enabled(hw) && ixgbe_is_sfp(hw) && hw->mac.ops.setup_link) + hw->mac.ops.setup_link(hw, + IXGBE_LINK_SPEED_10GB_FULL | IXGBE_LINK_SPEED_1GB_FULL, + true); + + err = ixgbe_mii_bus_init(hw); + if (err) + goto err_netdev; + + return 0; + +err_netdev: + unregister_netdev(netdev); +err_register: + ixgbe_release_hw_control(adapter); + ixgbe_clear_interrupt_scheme(adapter); +err_sw_init: + ixgbe_disable_sriov(adapter); + adapter->flags2 &= ~IXGBE_FLAG2_SEARCH_FOR_SFP; + iounmap(adapter->io_addr); + kfree(adapter->jump_tables[0]); + kfree(adapter->mac_table); + kfree(adapter->rss_key); + bitmap_free(adapter->af_xdp_zc_qps); +err_ioremap: + disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state); + free_netdev(netdev); +err_alloc_etherdev: + pci_disable_pcie_error_reporting(pdev); + pci_release_mem_regions(pdev); +err_pci_reg: +err_dma: + if (!adapter || disable_dev) + pci_disable_device(pdev); + return err; +} + +/** + * ixgbe_remove - Device Removal Routine + * @pdev: PCI device information struct + * + * ixgbe_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 ixgbe_remove(struct pci_dev *pdev) +{ + struct ixgbe_adapter *adapter = pci_get_drvdata(pdev); + struct net_device *netdev; + bool disable_dev; + int i; + + /* if !adapter then we already cleaned up in probe */ + if (!adapter) + return; + + netdev = adapter->netdev; + ixgbe_dbg_adapter_exit(adapter); + + set_bit(__IXGBE_REMOVING, &adapter->state); + cancel_work_sync(&adapter->service_task); + + if (adapter->mii_bus) + mdiobus_unregister(adapter->mii_bus); + +#ifdef CONFIG_IXGBE_DCA + if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) { + adapter->flags &= ~IXGBE_FLAG_DCA_ENABLED; + dca_remove_requester(&pdev->dev); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL, + IXGBE_DCA_CTRL_DCA_DISABLE); + } + +#endif +#ifdef CONFIG_IXGBE_HWMON + ixgbe_sysfs_exit(adapter); +#endif /* CONFIG_IXGBE_HWMON */ + + /* remove the added san mac */ + ixgbe_del_sanmac_netdev(netdev); + +#ifdef CONFIG_PCI_IOV + ixgbe_disable_sriov(adapter); +#endif + if (netdev->reg_state == NETREG_REGISTERED) + unregister_netdev(netdev); + + ixgbe_stop_ipsec_offload(adapter); + ixgbe_clear_interrupt_scheme(adapter); + + ixgbe_release_hw_control(adapter); + +#ifdef CONFIG_DCB + kfree(adapter->ixgbe_ieee_pfc); + kfree(adapter->ixgbe_ieee_ets); + +#endif + iounmap(adapter->io_addr); + pci_release_mem_regions(pdev); + + e_dev_info("complete\n"); + + for (i = 0; i < IXGBE_MAX_LINK_HANDLE; i++) { + if (adapter->jump_tables[i]) { + kfree(adapter->jump_tables[i]->input); + kfree(adapter->jump_tables[i]->mask); + } + kfree(adapter->jump_tables[i]); + } + + kfree(adapter->mac_table); + kfree(adapter->rss_key); + bitmap_free(adapter->af_xdp_zc_qps); + disable_dev = !test_and_set_bit(__IXGBE_DISABLED, &adapter->state); + free_netdev(netdev); + + pci_disable_pcie_error_reporting(pdev); + + if (disable_dev) + pci_disable_device(pdev); +} + +/** + * ixgbe_io_error_detected - called when PCI error is detected + * @pdev: Pointer to PCI device + * @state: The current pci connection state + * + * This function is called after a PCI bus error affecting + * this device has been detected. + */ +static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev, + pci_channel_state_t state) +{ + struct ixgbe_adapter *adapter = pci_get_drvdata(pdev); + struct net_device *netdev = adapter->netdev; + +#ifdef CONFIG_PCI_IOV + struct ixgbe_hw *hw = &adapter->hw; + struct pci_dev *bdev, *vfdev; + u32 dw0, dw1, dw2, dw3; + int vf, pos; + u16 req_id, pf_func; + + if (adapter->hw.mac.type == ixgbe_mac_82598EB || + adapter->num_vfs == 0) + goto skip_bad_vf_detection; + + bdev = pdev->bus->self; + while (bdev && (pci_pcie_type(bdev) != PCI_EXP_TYPE_ROOT_PORT)) + bdev = bdev->bus->self; + + if (!bdev) + goto skip_bad_vf_detection; + + pos = pci_find_ext_capability(bdev, PCI_EXT_CAP_ID_ERR); + if (!pos) + goto skip_bad_vf_detection; + + dw0 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG); + dw1 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG + 4); + dw2 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG + 8); + dw3 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG + 12); + if (ixgbe_removed(hw->hw_addr)) + goto skip_bad_vf_detection; + + req_id = dw1 >> 16; + /* On the 82599 if bit 7 of the requestor ID is set then it's a VF */ + if (!(req_id & 0x0080)) + goto skip_bad_vf_detection; + + pf_func = req_id & 0x01; + if ((pf_func & 1) == (pdev->devfn & 1)) { + unsigned int device_id; + + vf = (req_id & 0x7F) >> 1; + e_dev_err("VF %d has caused a PCIe error\n", vf); + e_dev_err("TLP: dw0: %8.8x\tdw1: %8.8x\tdw2: " + "%8.8x\tdw3: %8.8x\n", + dw0, dw1, dw2, dw3); + switch (adapter->hw.mac.type) { + case ixgbe_mac_82599EB: + device_id = IXGBE_82599_VF_DEVICE_ID; + break; + case ixgbe_mac_X540: + device_id = IXGBE_X540_VF_DEVICE_ID; + break; + case ixgbe_mac_X550: + device_id = IXGBE_DEV_ID_X550_VF; + break; + case ixgbe_mac_X550EM_x: + device_id = IXGBE_DEV_ID_X550EM_X_VF; + break; + case ixgbe_mac_x550em_a: + device_id = IXGBE_DEV_ID_X550EM_A_VF; + break; + default: + device_id = 0; + break; + } + + /* Find the pci device of the offending VF */ + vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, device_id, NULL); + while (vfdev) { + if (vfdev->devfn == (req_id & 0xFF)) + break; + vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, + device_id, vfdev); + } + /* + * There's a slim chance the VF could have been hot plugged, + * so if it is no longer present we don't need to issue the + * VFLR. Just clean up the AER in that case. + */ + if (vfdev) { + pcie_flr(vfdev); + /* Free device reference count */ + pci_dev_put(vfdev); + } + } + + /* + * Even though the error may have occurred on the other port + * we still need to increment the vf error reference count for + * both ports because the I/O resume function will be called + * for both of them. + */ + adapter->vferr_refcount++; + + return PCI_ERS_RESULT_RECOVERED; + +skip_bad_vf_detection: +#endif /* CONFIG_PCI_IOV */ + if (!test_bit(__IXGBE_SERVICE_INITED, &adapter->state)) + return PCI_ERS_RESULT_DISCONNECT; + + if (!netif_device_present(netdev)) + return PCI_ERS_RESULT_DISCONNECT; + + rtnl_lock(); + netif_device_detach(netdev); + + if (netif_running(netdev)) + ixgbe_close_suspend(adapter); + + if (state == pci_channel_io_perm_failure) { + rtnl_unlock(); + return PCI_ERS_RESULT_DISCONNECT; + } + + if (!test_and_set_bit(__IXGBE_DISABLED, &adapter->state)) + pci_disable_device(pdev); + rtnl_unlock(); + + /* Request a slot reset. */ + return PCI_ERS_RESULT_NEED_RESET; +} + +/** + * ixgbe_io_slot_reset - called after the pci bus has been reset. + * @pdev: Pointer to PCI device + * + * Restart the card from scratch, as if from a cold-boot. + */ +static pci_ers_result_t ixgbe_io_slot_reset(struct pci_dev *pdev) +{ + struct ixgbe_adapter *adapter = pci_get_drvdata(pdev); + pci_ers_result_t result; + + if (pci_enable_device_mem(pdev)) { + e_err(probe, "Cannot re-enable PCI device after reset.\n"); + result = PCI_ERS_RESULT_DISCONNECT; + } else { + smp_mb__before_atomic(); + clear_bit(__IXGBE_DISABLED, &adapter->state); + adapter->hw.hw_addr = adapter->io_addr; + pci_set_master(pdev); + pci_restore_state(pdev); + pci_save_state(pdev); + + pci_wake_from_d3(pdev, false); + + ixgbe_reset(adapter); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_WUS, ~0); + result = PCI_ERS_RESULT_RECOVERED; + } + + return result; +} + +/** + * ixgbe_io_resume - called when traffic can start flowing again. + * @pdev: Pointer to PCI device + * + * This callback is called when the error recovery driver tells us that + * its OK to resume normal operation. + */ +static void ixgbe_io_resume(struct pci_dev *pdev) +{ + struct ixgbe_adapter *adapter = pci_get_drvdata(pdev); + struct net_device *netdev = adapter->netdev; + +#ifdef CONFIG_PCI_IOV + if (adapter->vferr_refcount) { + e_info(drv, "Resuming after VF err\n"); + adapter->vferr_refcount--; + return; + } + +#endif + rtnl_lock(); + if (netif_running(netdev)) + ixgbe_open(netdev); + + netif_device_attach(netdev); + rtnl_unlock(); +} + +static const struct pci_error_handlers ixgbe_err_handler = { + .error_detected = ixgbe_io_error_detected, + .slot_reset = ixgbe_io_slot_reset, + .resume = ixgbe_io_resume, +}; + +static SIMPLE_DEV_PM_OPS(ixgbe_pm_ops, ixgbe_suspend, ixgbe_resume); + +static struct pci_driver ixgbe_driver = { + .name = ixgbe_driver_name, + .id_table = ixgbe_pci_tbl, + .probe = ixgbe_probe, + .remove = ixgbe_remove, + .driver.pm = &ixgbe_pm_ops, + .shutdown = ixgbe_shutdown, + .sriov_configure = ixgbe_pci_sriov_configure, + .err_handler = &ixgbe_err_handler +}; + +/** + * ixgbe_init_module - Driver Registration Routine + * + * ixgbe_init_module is the first routine called when the driver is + * loaded. All it does is register with the PCI subsystem. + **/ +static int __init ixgbe_init_module(void) +{ + int ret; + pr_info("%s\n", ixgbe_driver_string); + pr_info("%s\n", ixgbe_copyright); + + ixgbe_wq = create_singlethread_workqueue(ixgbe_driver_name); + if (!ixgbe_wq) { + pr_err("%s: Failed to create workqueue\n", ixgbe_driver_name); + return -ENOMEM; + } + + ixgbe_dbg_init(); + + ret = pci_register_driver(&ixgbe_driver); + if (ret) { + destroy_workqueue(ixgbe_wq); + ixgbe_dbg_exit(); + return ret; + } + +#ifdef CONFIG_IXGBE_DCA + dca_register_notify(&dca_notifier); +#endif + + return 0; +} + +module_init(ixgbe_init_module); + +/** + * ixgbe_exit_module - Driver Exit Cleanup Routine + * + * ixgbe_exit_module is called just before the driver is removed + * from memory. + **/ +static void __exit ixgbe_exit_module(void) +{ +#ifdef CONFIG_IXGBE_DCA + dca_unregister_notify(&dca_notifier); +#endif + pci_unregister_driver(&ixgbe_driver); + + ixgbe_dbg_exit(); + if (ixgbe_wq) { + destroy_workqueue(ixgbe_wq); + ixgbe_wq = NULL; + } +} + +#ifdef CONFIG_IXGBE_DCA +static int ixgbe_notify_dca(struct notifier_block *nb, unsigned long event, + void *p) +{ + int ret_val; + + ret_val = driver_for_each_device(&ixgbe_driver.driver, NULL, &event, + __ixgbe_notify_dca); + + return ret_val ? NOTIFY_BAD : NOTIFY_DONE; +} + +#endif /* CONFIG_IXGBE_DCA */ + +module_exit(ixgbe_exit_module); + +/* ixgbe_main.c */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c new file mode 100644 index 000000000..5679293e5 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c @@ -0,0 +1,435 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#include <linux/pci.h> +#include <linux/delay.h> +#include "ixgbe.h" +#include "ixgbe_mbx.h" + +/** + * ixgbe_read_mbx - Reads a message from the mailbox + * @hw: pointer to the HW structure + * @msg: The message buffer + * @size: Length of buffer + * @mbx_id: id of mailbox to read + * + * returns SUCCESS if it successfully read message from buffer + **/ +s32 ixgbe_read_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size, u16 mbx_id) +{ + struct ixgbe_mbx_info *mbx = &hw->mbx; + + /* limit read to size of mailbox */ + if (size > mbx->size) + size = mbx->size; + + if (!mbx->ops) + return IXGBE_ERR_MBX; + + return mbx->ops->read(hw, msg, size, mbx_id); +} + +/** + * ixgbe_write_mbx - Write a message to the mailbox + * @hw: pointer to the HW structure + * @msg: The message buffer + * @size: Length of buffer + * @mbx_id: id of mailbox to write + * + * returns SUCCESS if it successfully copied message into the buffer + **/ +s32 ixgbe_write_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size, u16 mbx_id) +{ + struct ixgbe_mbx_info *mbx = &hw->mbx; + + if (size > mbx->size) + return IXGBE_ERR_MBX; + + if (!mbx->ops) + return IXGBE_ERR_MBX; + + return mbx->ops->write(hw, msg, size, mbx_id); +} + +/** + * ixgbe_check_for_msg - checks to see if someone sent us mail + * @hw: pointer to the HW structure + * @mbx_id: id of mailbox to check + * + * returns SUCCESS if the Status bit was found or else ERR_MBX + **/ +s32 ixgbe_check_for_msg(struct ixgbe_hw *hw, u16 mbx_id) +{ + struct ixgbe_mbx_info *mbx = &hw->mbx; + + if (!mbx->ops) + return IXGBE_ERR_MBX; + + return mbx->ops->check_for_msg(hw, mbx_id); +} + +/** + * ixgbe_check_for_ack - checks to see if someone sent us ACK + * @hw: pointer to the HW structure + * @mbx_id: id of mailbox to check + * + * returns SUCCESS if the Status bit was found or else ERR_MBX + **/ +s32 ixgbe_check_for_ack(struct ixgbe_hw *hw, u16 mbx_id) +{ + struct ixgbe_mbx_info *mbx = &hw->mbx; + + if (!mbx->ops) + return IXGBE_ERR_MBX; + + return mbx->ops->check_for_ack(hw, mbx_id); +} + +/** + * ixgbe_check_for_rst - checks to see if other side has reset + * @hw: pointer to the HW structure + * @mbx_id: id of mailbox to check + * + * returns SUCCESS if the Status bit was found or else ERR_MBX + **/ +s32 ixgbe_check_for_rst(struct ixgbe_hw *hw, u16 mbx_id) +{ + struct ixgbe_mbx_info *mbx = &hw->mbx; + + if (!mbx->ops) + return IXGBE_ERR_MBX; + + return mbx->ops->check_for_rst(hw, mbx_id); +} + +/** + * ixgbe_poll_for_msg - Wait for message notification + * @hw: pointer to the HW structure + * @mbx_id: id of mailbox to write + * + * returns SUCCESS if it successfully received a message notification + **/ +static s32 ixgbe_poll_for_msg(struct ixgbe_hw *hw, u16 mbx_id) +{ + struct ixgbe_mbx_info *mbx = &hw->mbx; + int countdown = mbx->timeout; + + if (!countdown || !mbx->ops) + return IXGBE_ERR_MBX; + + while (mbx->ops->check_for_msg(hw, mbx_id)) { + countdown--; + if (!countdown) + return IXGBE_ERR_MBX; + udelay(mbx->usec_delay); + } + + return 0; +} + +/** + * ixgbe_poll_for_ack - Wait for message acknowledgement + * @hw: pointer to the HW structure + * @mbx_id: id of mailbox to write + * + * returns SUCCESS if it successfully received a message acknowledgement + **/ +static s32 ixgbe_poll_for_ack(struct ixgbe_hw *hw, u16 mbx_id) +{ + struct ixgbe_mbx_info *mbx = &hw->mbx; + int countdown = mbx->timeout; + + if (!countdown || !mbx->ops) + return IXGBE_ERR_MBX; + + while (mbx->ops->check_for_ack(hw, mbx_id)) { + countdown--; + if (!countdown) + return IXGBE_ERR_MBX; + udelay(mbx->usec_delay); + } + + return 0; +} + +/** + * ixgbe_read_posted_mbx - Wait for message notification and receive message + * @hw: pointer to the HW structure + * @msg: The message buffer + * @size: Length of buffer + * @mbx_id: id of mailbox to write + * + * returns SUCCESS if it successfully received a message notification and + * copied it into the receive buffer. + **/ +static s32 ixgbe_read_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size, + u16 mbx_id) +{ + struct ixgbe_mbx_info *mbx = &hw->mbx; + s32 ret_val; + + if (!mbx->ops) + return IXGBE_ERR_MBX; + + ret_val = ixgbe_poll_for_msg(hw, mbx_id); + if (ret_val) + return ret_val; + + /* if ack received read message */ + return mbx->ops->read(hw, msg, size, mbx_id); +} + +/** + * ixgbe_write_posted_mbx - Write a message to the mailbox, wait for ack + * @hw: pointer to the HW structure + * @msg: The message buffer + * @size: Length of buffer + * @mbx_id: id of mailbox to write + * + * returns SUCCESS if it successfully copied message into the buffer and + * received an ack to that message within delay * timeout period + **/ +static s32 ixgbe_write_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size, + u16 mbx_id) +{ + struct ixgbe_mbx_info *mbx = &hw->mbx; + s32 ret_val; + + /* exit if either we can't write or there isn't a defined timeout */ + if (!mbx->ops || !mbx->timeout) + return IXGBE_ERR_MBX; + + /* send msg */ + ret_val = mbx->ops->write(hw, msg, size, mbx_id); + if (ret_val) + return ret_val; + + /* if msg sent wait until we receive an ack */ + return ixgbe_poll_for_ack(hw, mbx_id); +} + +static s32 ixgbe_check_for_bit_pf(struct ixgbe_hw *hw, u32 mask, s32 index) +{ + u32 mbvficr = IXGBE_READ_REG(hw, IXGBE_MBVFICR(index)); + + if (mbvficr & mask) { + IXGBE_WRITE_REG(hw, IXGBE_MBVFICR(index), mask); + return 0; + } + + return IXGBE_ERR_MBX; +} + +/** + * ixgbe_check_for_msg_pf - checks to see if the VF has sent mail + * @hw: pointer to the HW structure + * @vf_number: the VF index + * + * returns SUCCESS if the VF has set the Status bit or else ERR_MBX + **/ +static s32 ixgbe_check_for_msg_pf(struct ixgbe_hw *hw, u16 vf_number) +{ + s32 index = IXGBE_MBVFICR_INDEX(vf_number); + u32 vf_bit = vf_number % 16; + + if (!ixgbe_check_for_bit_pf(hw, IXGBE_MBVFICR_VFREQ_VF1 << vf_bit, + index)) { + hw->mbx.stats.reqs++; + return 0; + } + + return IXGBE_ERR_MBX; +} + +/** + * ixgbe_check_for_ack_pf - checks to see if the VF has ACKed + * @hw: pointer to the HW structure + * @vf_number: the VF index + * + * returns SUCCESS if the VF has set the Status bit or else ERR_MBX + **/ +static s32 ixgbe_check_for_ack_pf(struct ixgbe_hw *hw, u16 vf_number) +{ + s32 index = IXGBE_MBVFICR_INDEX(vf_number); + u32 vf_bit = vf_number % 16; + + if (!ixgbe_check_for_bit_pf(hw, IXGBE_MBVFICR_VFACK_VF1 << vf_bit, + index)) { + hw->mbx.stats.acks++; + return 0; + } + + return IXGBE_ERR_MBX; +} + +/** + * ixgbe_check_for_rst_pf - checks to see if the VF has reset + * @hw: pointer to the HW structure + * @vf_number: the VF index + * + * returns SUCCESS if the VF has set the Status bit or else ERR_MBX + **/ +static s32 ixgbe_check_for_rst_pf(struct ixgbe_hw *hw, u16 vf_number) +{ + u32 reg_offset = (vf_number < 32) ? 0 : 1; + u32 vf_shift = vf_number % 32; + u32 vflre = 0; + + switch (hw->mac.type) { + case ixgbe_mac_82599EB: + vflre = IXGBE_READ_REG(hw, IXGBE_VFLRE(reg_offset)); + break; + case ixgbe_mac_X540: + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + vflre = IXGBE_READ_REG(hw, IXGBE_VFLREC(reg_offset)); + break; + default: + break; + } + + if (vflre & BIT(vf_shift)) { + IXGBE_WRITE_REG(hw, IXGBE_VFLREC(reg_offset), BIT(vf_shift)); + hw->mbx.stats.rsts++; + return 0; + } + + return IXGBE_ERR_MBX; +} + +/** + * ixgbe_obtain_mbx_lock_pf - obtain mailbox lock + * @hw: pointer to the HW structure + * @vf_number: the VF index + * + * return SUCCESS if we obtained the mailbox lock + **/ +static s32 ixgbe_obtain_mbx_lock_pf(struct ixgbe_hw *hw, u16 vf_number) +{ + u32 p2v_mailbox; + + /* Take ownership of the buffer */ + IXGBE_WRITE_REG(hw, IXGBE_PFMAILBOX(vf_number), IXGBE_PFMAILBOX_PFU); + + /* reserve mailbox for vf use */ + p2v_mailbox = IXGBE_READ_REG(hw, IXGBE_PFMAILBOX(vf_number)); + if (p2v_mailbox & IXGBE_PFMAILBOX_PFU) + return 0; + + return IXGBE_ERR_MBX; +} + +/** + * ixgbe_write_mbx_pf - Places a message in the mailbox + * @hw: pointer to the HW structure + * @msg: The message buffer + * @size: Length of buffer + * @vf_number: the VF index + * + * returns SUCCESS if it successfully copied message into the buffer + **/ +static s32 ixgbe_write_mbx_pf(struct ixgbe_hw *hw, u32 *msg, u16 size, + u16 vf_number) +{ + s32 ret_val; + u16 i; + + /* lock the mailbox to prevent pf/vf race condition */ + ret_val = ixgbe_obtain_mbx_lock_pf(hw, vf_number); + if (ret_val) + return ret_val; + + /* flush msg and acks as we are overwriting the message buffer */ + ixgbe_check_for_msg_pf(hw, vf_number); + ixgbe_check_for_ack_pf(hw, vf_number); + + /* copy the caller specified message to the mailbox memory buffer */ + for (i = 0; i < size; i++) + IXGBE_WRITE_REG_ARRAY(hw, IXGBE_PFMBMEM(vf_number), i, msg[i]); + + /* Interrupt VF to tell it a message has been sent and release buffer*/ + IXGBE_WRITE_REG(hw, IXGBE_PFMAILBOX(vf_number), IXGBE_PFMAILBOX_STS); + + /* update stats */ + hw->mbx.stats.msgs_tx++; + + return 0; +} + +/** + * ixgbe_read_mbx_pf - Read a message from the mailbox + * @hw: pointer to the HW structure + * @msg: The message buffer + * @size: Length of buffer + * @vf_number: the VF index + * + * This function copies a message from the mailbox buffer to the caller's + * memory buffer. The presumption is that the caller knows that there was + * a message due to a VF request so no polling for message is needed. + **/ +static s32 ixgbe_read_mbx_pf(struct ixgbe_hw *hw, u32 *msg, u16 size, + u16 vf_number) +{ + s32 ret_val; + u16 i; + + /* lock the mailbox to prevent pf/vf race condition */ + ret_val = ixgbe_obtain_mbx_lock_pf(hw, vf_number); + if (ret_val) + return ret_val; + + /* copy the message to the mailbox memory buffer */ + for (i = 0; i < size; i++) + msg[i] = IXGBE_READ_REG_ARRAY(hw, IXGBE_PFMBMEM(vf_number), i); + + /* Acknowledge the message and release buffer */ + IXGBE_WRITE_REG(hw, IXGBE_PFMAILBOX(vf_number), IXGBE_PFMAILBOX_ACK); + + /* update stats */ + hw->mbx.stats.msgs_rx++; + + return 0; +} + +#ifdef CONFIG_PCI_IOV +/** + * ixgbe_init_mbx_params_pf - set initial values for pf mailbox + * @hw: pointer to the HW structure + * + * Initializes the hw->mbx struct to correct values for pf mailbox + */ +void ixgbe_init_mbx_params_pf(struct ixgbe_hw *hw) +{ + struct ixgbe_mbx_info *mbx = &hw->mbx; + + if (hw->mac.type != ixgbe_mac_82599EB && + hw->mac.type != ixgbe_mac_X550 && + hw->mac.type != ixgbe_mac_X550EM_x && + hw->mac.type != ixgbe_mac_x550em_a && + hw->mac.type != ixgbe_mac_X540) + return; + + mbx->timeout = 0; + mbx->usec_delay = 0; + + mbx->stats.msgs_tx = 0; + mbx->stats.msgs_rx = 0; + mbx->stats.reqs = 0; + mbx->stats.acks = 0; + mbx->stats.rsts = 0; + + mbx->size = IXGBE_VFMAILBOX_SIZE; +} +#endif /* CONFIG_PCI_IOV */ + +const struct ixgbe_mbx_operations mbx_ops_generic = { + .read = ixgbe_read_mbx_pf, + .write = ixgbe_write_mbx_pf, + .read_posted = ixgbe_read_posted_mbx, + .write_posted = ixgbe_write_posted_mbx, + .check_for_msg = ixgbe_check_for_msg_pf, + .check_for_ack = ixgbe_check_for_ack_pf, + .check_for_rst = ixgbe_check_for_rst_pf, +}; + diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h new file mode 100644 index 000000000..a148534d7 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h @@ -0,0 +1,109 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#ifndef _IXGBE_MBX_H_ +#define _IXGBE_MBX_H_ + +#include "ixgbe_type.h" + +#define IXGBE_VFMAILBOX_SIZE 16 /* 16 32 bit words - 64 bytes */ +#define IXGBE_ERR_MBX -100 + +#define IXGBE_VFMAILBOX 0x002FC +#define IXGBE_VFMBMEM 0x00200 + +#define IXGBE_PFMAILBOX_STS 0x00000001 /* Initiate message send to VF */ +#define IXGBE_PFMAILBOX_ACK 0x00000002 /* Ack message recv'd from VF */ +#define IXGBE_PFMAILBOX_VFU 0x00000004 /* VF owns the mailbox buffer */ +#define IXGBE_PFMAILBOX_PFU 0x00000008 /* PF owns the mailbox buffer */ +#define IXGBE_PFMAILBOX_RVFU 0x00000010 /* Reset VFU - used when VF stuck */ + +#define IXGBE_MBVFICR_VFREQ_MASK 0x0000FFFF /* bits for VF messages */ +#define IXGBE_MBVFICR_VFREQ_VF1 0x00000001 /* bit for VF 1 message */ +#define IXGBE_MBVFICR_VFACK_MASK 0xFFFF0000 /* bits for VF acks */ +#define IXGBE_MBVFICR_VFACK_VF1 0x00010000 /* bit for VF 1 ack */ + + +/* If it's a IXGBE_VF_* msg then it originates in the VF and is sent to the + * PF. The reverse is true if it is IXGBE_PF_*. + * Message ACK's are the value or'd with 0xF0000000 + */ +#define IXGBE_VT_MSGTYPE_ACK 0x80000000 /* Messages below or'd with + * this are the ACK */ +#define IXGBE_VT_MSGTYPE_NACK 0x40000000 /* Messages below or'd with + * this are the NACK */ +#define IXGBE_VT_MSGTYPE_CTS 0x20000000 /* Indicates that VF is still + clear to send requests */ +#define IXGBE_VT_MSGINFO_SHIFT 16 +/* bits 23:16 are used for exra info for certain messages */ +#define IXGBE_VT_MSGINFO_MASK (0xFF << IXGBE_VT_MSGINFO_SHIFT) + +/* definitions to support mailbox API version negotiation */ + +/* + * Each element denotes a version of the API; existing numbers may not + * change; any additions must go at the end + */ +enum ixgbe_pfvf_api_rev { + ixgbe_mbox_api_10, /* API version 1.0, linux/freebsd VF driver */ + ixgbe_mbox_api_20, /* API version 2.0, solaris Phase1 VF driver */ + ixgbe_mbox_api_11, /* API version 1.1, linux/freebsd VF driver */ + ixgbe_mbox_api_12, /* API version 1.2, linux/freebsd VF driver */ + ixgbe_mbox_api_13, /* API version 1.3, linux/freebsd VF driver */ + ixgbe_mbox_api_14, /* API version 1.4, linux/freebsd VF driver */ + /* This value should always be last */ + ixgbe_mbox_api_unknown, /* indicates that API version is not known */ +}; + +/* mailbox API, legacy requests */ +#define IXGBE_VF_RESET 0x01 /* VF requests reset */ +#define IXGBE_VF_SET_MAC_ADDR 0x02 /* VF requests PF to set MAC addr */ +#define IXGBE_VF_SET_MULTICAST 0x03 /* VF requests PF to set MC addr */ +#define IXGBE_VF_SET_VLAN 0x04 /* VF requests PF to set VLAN */ + +/* mailbox API, version 1.0 VF requests */ +#define IXGBE_VF_SET_LPE 0x05 /* VF requests PF to set VMOLR.LPE */ +#define IXGBE_VF_SET_MACVLAN 0x06 /* VF requests PF for unicast filter */ +#define IXGBE_VF_API_NEGOTIATE 0x08 /* negotiate API version */ + +/* mailbox API, version 1.1 VF requests */ +#define IXGBE_VF_GET_QUEUES 0x09 /* get queue configuration */ + +/* GET_QUEUES return data indices within the mailbox */ +#define IXGBE_VF_TX_QUEUES 1 /* number of Tx queues supported */ +#define IXGBE_VF_RX_QUEUES 2 /* number of Rx queues supported */ +#define IXGBE_VF_TRANS_VLAN 3 /* Indication of port vlan */ +#define IXGBE_VF_DEF_QUEUE 4 /* Default queue offset */ + +/* mailbox API, version 1.2 VF requests */ +#define IXGBE_VF_GET_RETA 0x0a /* VF request for RETA */ +#define IXGBE_VF_GET_RSS_KEY 0x0b /* get RSS key */ + +#define IXGBE_VF_UPDATE_XCAST_MODE 0x0c + +/* mailbox API, version 1.4 VF requests */ +#define IXGBE_VF_IPSEC_ADD 0x0d +#define IXGBE_VF_IPSEC_DEL 0x0e + +/* length of permanent address message returned from PF */ +#define IXGBE_VF_PERMADDR_MSG_LEN 4 +/* word in permanent address message with the current multicast type */ +#define IXGBE_VF_MC_TYPE_WORD 3 + +#define IXGBE_PF_CONTROL_MSG 0x0100 /* PF control message */ + +#define IXGBE_VF_MBX_INIT_TIMEOUT 2000 /* number of retries on mailbox */ +#define IXGBE_VF_MBX_INIT_DELAY 500 /* microseconds between retries */ + +s32 ixgbe_read_mbx(struct ixgbe_hw *, u32 *, u16, u16); +s32 ixgbe_write_mbx(struct ixgbe_hw *, u32 *, u16, u16); +s32 ixgbe_check_for_msg(struct ixgbe_hw *, u16); +s32 ixgbe_check_for_ack(struct ixgbe_hw *, u16); +s32 ixgbe_check_for_rst(struct ixgbe_hw *, u16); +#ifdef CONFIG_PCI_IOV +void ixgbe_init_mbx_params_pf(struct ixgbe_hw *); +#endif /* CONFIG_PCI_IOV */ + +extern const struct ixgbe_mbx_operations mbx_ops_generic; + +#endif /* _IXGBE_MBX_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_model.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_model.h new file mode 100644 index 000000000..1e6cf220f --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_model.h @@ -0,0 +1,98 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#ifndef _IXGBE_MODEL_H_ +#define _IXGBE_MODEL_H_ + +#include "ixgbe.h" +#include "ixgbe_type.h" + +struct ixgbe_mat_field { + unsigned int off; + int (*val)(struct ixgbe_fdir_filter *input, + union ixgbe_atr_input *mask, + u32 val, u32 m); + unsigned int type; +}; + +struct ixgbe_jump_table { + struct ixgbe_mat_field *mat; + struct ixgbe_fdir_filter *input; + union ixgbe_atr_input *mask; + u32 link_hdl; + unsigned long child_loc_map[32]; +}; + +#define IXGBE_MAX_HW_ENTRIES 2045 + +static inline int ixgbe_mat_prgm_sip(struct ixgbe_fdir_filter *input, + union ixgbe_atr_input *mask, + u32 val, u32 m) +{ + input->filter.formatted.src_ip[0] = (__force __be32)val; + mask->formatted.src_ip[0] = (__force __be32)m; + return 0; +} + +static inline int ixgbe_mat_prgm_dip(struct ixgbe_fdir_filter *input, + union ixgbe_atr_input *mask, + u32 val, u32 m) +{ + input->filter.formatted.dst_ip[0] = (__force __be32)val; + mask->formatted.dst_ip[0] = (__force __be32)m; + return 0; +} + +static struct ixgbe_mat_field ixgbe_ipv4_fields[] = { + { .off = 12, .val = ixgbe_mat_prgm_sip, + .type = IXGBE_ATR_FLOW_TYPE_IPV4}, + { .off = 16, .val = ixgbe_mat_prgm_dip, + .type = IXGBE_ATR_FLOW_TYPE_IPV4}, + { .val = NULL } /* terminal node */ +}; + +static inline int ixgbe_mat_prgm_ports(struct ixgbe_fdir_filter *input, + union ixgbe_atr_input *mask, + u32 val, u32 m) +{ + input->filter.formatted.src_port = (__force __be16)(val & 0xffff); + mask->formatted.src_port = (__force __be16)(m & 0xffff); + input->filter.formatted.dst_port = (__force __be16)(val >> 16); + mask->formatted.dst_port = (__force __be16)(m >> 16); + + return 0; +}; + +static struct ixgbe_mat_field ixgbe_tcp_fields[] = { + {.off = 0, .val = ixgbe_mat_prgm_ports, + .type = IXGBE_ATR_FLOW_TYPE_TCPV4}, + { .val = NULL } /* terminal node */ +}; + +static struct ixgbe_mat_field ixgbe_udp_fields[] = { + {.off = 0, .val = ixgbe_mat_prgm_ports, + .type = IXGBE_ATR_FLOW_TYPE_UDPV4}, + { .val = NULL } /* terminal node */ +}; + +struct ixgbe_nexthdr { + /* offset, shift, and mask of position to next header */ + unsigned int o; + u32 s; + u32 m; + /* match criteria to make this jump*/ + unsigned int off; + u32 val; + u32 mask; + /* location of jump to make */ + struct ixgbe_mat_field *jump; +}; + +static struct ixgbe_nexthdr ixgbe_ipv4_jumps[] = { + { .o = 0, .s = 6, .m = 0xf, + .off = 8, .val = 0x600, .mask = 0xff00, .jump = ixgbe_tcp_fields}, + { .o = 0, .s = 6, .m = 0xf, + .off = 8, .val = 0x1100, .mask = 0xff00, .jump = ixgbe_udp_fields}, + { .jump = NULL } /* terminal node */ +}; +#endif /* _IXGBE_MODEL_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c new file mode 100644 index 000000000..b0413904b --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -0,0 +1,2668 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#include <linux/pci.h> +#include <linux/delay.h> +#include <linux/iopoll.h> +#include <linux/sched.h> + +#include "ixgbe.h" +#include "ixgbe_phy.h" + +static void ixgbe_i2c_start(struct ixgbe_hw *hw); +static void ixgbe_i2c_stop(struct ixgbe_hw *hw); +static s32 ixgbe_clock_in_i2c_byte(struct ixgbe_hw *hw, u8 *data); +static s32 ixgbe_clock_out_i2c_byte(struct ixgbe_hw *hw, u8 data); +static s32 ixgbe_get_i2c_ack(struct ixgbe_hw *hw); +static s32 ixgbe_clock_in_i2c_bit(struct ixgbe_hw *hw, bool *data); +static s32 ixgbe_clock_out_i2c_bit(struct ixgbe_hw *hw, bool data); +static void ixgbe_raise_i2c_clk(struct ixgbe_hw *hw, u32 *i2cctl); +static void ixgbe_lower_i2c_clk(struct ixgbe_hw *hw, u32 *i2cctl); +static s32 ixgbe_set_i2c_data(struct ixgbe_hw *hw, u32 *i2cctl, bool data); +static bool ixgbe_get_i2c_data(struct ixgbe_hw *hw, u32 *i2cctl); +static void ixgbe_i2c_bus_clear(struct ixgbe_hw *hw); +static enum ixgbe_phy_type ixgbe_get_phy_type_from_id(u32 phy_id); +static s32 ixgbe_get_phy_id(struct ixgbe_hw *hw); +static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw); + +/** + * ixgbe_out_i2c_byte_ack - Send I2C byte with ack + * @hw: pointer to the hardware structure + * @byte: byte to send + * + * Returns an error code on error. + **/ +static s32 ixgbe_out_i2c_byte_ack(struct ixgbe_hw *hw, u8 byte) +{ + s32 status; + + status = ixgbe_clock_out_i2c_byte(hw, byte); + if (status) + return status; + return ixgbe_get_i2c_ack(hw); +} + +/** + * ixgbe_in_i2c_byte_ack - Receive an I2C byte and send ack + * @hw: pointer to the hardware structure + * @byte: pointer to a u8 to receive the byte + * + * Returns an error code on error. + **/ +static s32 ixgbe_in_i2c_byte_ack(struct ixgbe_hw *hw, u8 *byte) +{ + s32 status; + + status = ixgbe_clock_in_i2c_byte(hw, byte); + if (status) + return status; + /* ACK */ + return ixgbe_clock_out_i2c_bit(hw, false); +} + +/** + * ixgbe_ones_comp_byte_add - Perform one's complement addition + * @add1: addend 1 + * @add2: addend 2 + * + * Returns one's complement 8-bit sum. + **/ +static u8 ixgbe_ones_comp_byte_add(u8 add1, u8 add2) +{ + u16 sum = add1 + add2; + + sum = (sum & 0xFF) + (sum >> 8); + return sum & 0xFF; +} + +/** + * ixgbe_read_i2c_combined_generic_int - Perform I2C read combined operation + * @hw: pointer to the hardware structure + * @addr: I2C bus address to read from + * @reg: I2C device register to read from + * @val: pointer to location to receive read value + * @lock: true if to take and release semaphore + * + * Returns an error code on error. + */ +s32 ixgbe_read_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr, + u16 reg, u16 *val, bool lock) +{ + u32 swfw_mask = hw->phy.phy_semaphore_mask; + int max_retry = 3; + int retry = 0; + u8 csum_byte; + u8 high_bits; + u8 low_bits; + u8 reg_high; + u8 csum; + + reg_high = ((reg >> 7) & 0xFE) | 1; /* Indicate read combined */ + csum = ixgbe_ones_comp_byte_add(reg_high, reg & 0xFF); + csum = ~csum; + do { + if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) + return IXGBE_ERR_SWFW_SYNC; + ixgbe_i2c_start(hw); + /* Device Address and write indication */ + if (ixgbe_out_i2c_byte_ack(hw, addr)) + goto fail; + /* Write bits 14:8 */ + if (ixgbe_out_i2c_byte_ack(hw, reg_high)) + goto fail; + /* Write bits 7:0 */ + if (ixgbe_out_i2c_byte_ack(hw, reg & 0xFF)) + goto fail; + /* Write csum */ + if (ixgbe_out_i2c_byte_ack(hw, csum)) + goto fail; + /* Re-start condition */ + ixgbe_i2c_start(hw); + /* Device Address and read indication */ + if (ixgbe_out_i2c_byte_ack(hw, addr | 1)) + goto fail; + /* Get upper bits */ + if (ixgbe_in_i2c_byte_ack(hw, &high_bits)) + goto fail; + /* Get low bits */ + if (ixgbe_in_i2c_byte_ack(hw, &low_bits)) + goto fail; + /* Get csum */ + if (ixgbe_clock_in_i2c_byte(hw, &csum_byte)) + goto fail; + /* NACK */ + if (ixgbe_clock_out_i2c_bit(hw, false)) + goto fail; + ixgbe_i2c_stop(hw); + if (lock) + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + *val = (high_bits << 8) | low_bits; + return 0; + +fail: + ixgbe_i2c_bus_clear(hw); + if (lock) + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + retry++; + if (retry < max_retry) + hw_dbg(hw, "I2C byte read combined error - Retry.\n"); + else + hw_dbg(hw, "I2C byte read combined error.\n"); + } while (retry < max_retry); + + return IXGBE_ERR_I2C; +} + +/** + * ixgbe_write_i2c_combined_generic_int - Perform I2C write combined operation + * @hw: pointer to the hardware structure + * @addr: I2C bus address to write to + * @reg: I2C device register to write to + * @val: value to write + * @lock: true if to take and release semaphore + * + * Returns an error code on error. + */ +s32 ixgbe_write_i2c_combined_generic_int(struct ixgbe_hw *hw, u8 addr, + u16 reg, u16 val, bool lock) +{ + u32 swfw_mask = hw->phy.phy_semaphore_mask; + int max_retry = 1; + int retry = 0; + u8 reg_high; + u8 csum; + + reg_high = (reg >> 7) & 0xFE; /* Indicate write combined */ + csum = ixgbe_ones_comp_byte_add(reg_high, reg & 0xFF); + csum = ixgbe_ones_comp_byte_add(csum, val >> 8); + csum = ixgbe_ones_comp_byte_add(csum, val & 0xFF); + csum = ~csum; + do { + if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) + return IXGBE_ERR_SWFW_SYNC; + ixgbe_i2c_start(hw); + /* Device Address and write indication */ + if (ixgbe_out_i2c_byte_ack(hw, addr)) + goto fail; + /* Write bits 14:8 */ + if (ixgbe_out_i2c_byte_ack(hw, reg_high)) + goto fail; + /* Write bits 7:0 */ + if (ixgbe_out_i2c_byte_ack(hw, reg & 0xFF)) + goto fail; + /* Write data 15:8 */ + if (ixgbe_out_i2c_byte_ack(hw, val >> 8)) + goto fail; + /* Write data 7:0 */ + if (ixgbe_out_i2c_byte_ack(hw, val & 0xFF)) + goto fail; + /* Write csum */ + if (ixgbe_out_i2c_byte_ack(hw, csum)) + goto fail; + ixgbe_i2c_stop(hw); + if (lock) + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + return 0; + +fail: + ixgbe_i2c_bus_clear(hw); + if (lock) + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + retry++; + if (retry < max_retry) + hw_dbg(hw, "I2C byte write combined error - Retry.\n"); + else + hw_dbg(hw, "I2C byte write combined error.\n"); + } while (retry < max_retry); + + return IXGBE_ERR_I2C; +} + +/** + * ixgbe_probe_phy - Probe a single address for a PHY + * @hw: pointer to hardware structure + * @phy_addr: PHY address to probe + * + * Returns true if PHY found + **/ +static bool ixgbe_probe_phy(struct ixgbe_hw *hw, u16 phy_addr) +{ + u16 ext_ability = 0; + + hw->phy.mdio.prtad = phy_addr; + if (mdio45_probe(&hw->phy.mdio, phy_addr) != 0) + return false; + + if (ixgbe_get_phy_id(hw)) + return false; + + hw->phy.type = ixgbe_get_phy_type_from_id(hw->phy.id); + + if (hw->phy.type == ixgbe_phy_unknown) { + hw->phy.ops.read_reg(hw, + MDIO_PMA_EXTABLE, + MDIO_MMD_PMAPMD, + &ext_ability); + if (ext_ability & + (MDIO_PMA_EXTABLE_10GBT | + MDIO_PMA_EXTABLE_1000BT)) + hw->phy.type = ixgbe_phy_cu_unknown; + else + hw->phy.type = ixgbe_phy_generic; + } + + return true; +} + +/** + * ixgbe_identify_phy_generic - Get physical layer module + * @hw: pointer to hardware structure + * + * Determines the physical layer module found on the current adapter. + **/ +s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw) +{ + u32 phy_addr; + u32 status = IXGBE_ERR_PHY_ADDR_INVALID; + + if (!hw->phy.phy_semaphore_mask) { + if (hw->bus.lan_id) + hw->phy.phy_semaphore_mask = IXGBE_GSSR_PHY1_SM; + else + hw->phy.phy_semaphore_mask = IXGBE_GSSR_PHY0_SM; + } + + if (hw->phy.type != ixgbe_phy_unknown) + return 0; + + if (hw->phy.nw_mng_if_sel) { + phy_addr = (hw->phy.nw_mng_if_sel & + IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD) >> + IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD_SHIFT; + if (ixgbe_probe_phy(hw, phy_addr)) + return 0; + else + return IXGBE_ERR_PHY_ADDR_INVALID; + } + + for (phy_addr = 0; phy_addr < IXGBE_MAX_PHY_ADDR; phy_addr++) { + if (ixgbe_probe_phy(hw, phy_addr)) { + status = 0; + break; + } + } + + /* Certain media types do not have a phy so an address will not + * be found and the code will take this path. Caller has to + * decide if it is an error or not. + */ + if (status) + hw->phy.mdio.prtad = MDIO_PRTAD_NONE; + + return status; +} + +/** + * ixgbe_check_reset_blocked - check status of MNG FW veto bit + * @hw: pointer to the hardware structure + * + * This function checks the MMNGC.MNG_VETO bit to see if there are + * any constraints on link from manageability. For MAC's that don't + * have this bit just return false since the link can not be blocked + * via this method. + **/ +bool ixgbe_check_reset_blocked(struct ixgbe_hw *hw) +{ + u32 mmngc; + + /* If we don't have this bit, it can't be blocking */ + if (hw->mac.type == ixgbe_mac_82598EB) + return false; + + mmngc = IXGBE_READ_REG(hw, IXGBE_MMNGC); + if (mmngc & IXGBE_MMNGC_MNG_VETO) { + hw_dbg(hw, "MNG_VETO bit detected.\n"); + return true; + } + + return false; +} + +/** + * ixgbe_get_phy_id - Get the phy type + * @hw: pointer to hardware structure + * + **/ +static s32 ixgbe_get_phy_id(struct ixgbe_hw *hw) +{ + s32 status; + u16 phy_id_high = 0; + u16 phy_id_low = 0; + + status = hw->phy.ops.read_reg(hw, MDIO_DEVID1, MDIO_MMD_PMAPMD, + &phy_id_high); + + if (!status) { + hw->phy.id = (u32)(phy_id_high << 16); + status = hw->phy.ops.read_reg(hw, MDIO_DEVID2, MDIO_MMD_PMAPMD, + &phy_id_low); + hw->phy.id |= (u32)(phy_id_low & IXGBE_PHY_REVISION_MASK); + hw->phy.revision = (u32)(phy_id_low & ~IXGBE_PHY_REVISION_MASK); + } + return status; +} + +/** + * ixgbe_get_phy_type_from_id - Get the phy type + * @phy_id: hardware phy id + * + **/ +static enum ixgbe_phy_type ixgbe_get_phy_type_from_id(u32 phy_id) +{ + enum ixgbe_phy_type phy_type; + + switch (phy_id) { + case TN1010_PHY_ID: + phy_type = ixgbe_phy_tn; + break; + case X550_PHY_ID2: + case X550_PHY_ID3: + case X540_PHY_ID: + phy_type = ixgbe_phy_aq; + break; + case QT2022_PHY_ID: + phy_type = ixgbe_phy_qt; + break; + case ATH_PHY_ID: + phy_type = ixgbe_phy_nl; + break; + case X557_PHY_ID: + case X557_PHY_ID2: + phy_type = ixgbe_phy_x550em_ext_t; + break; + default: + phy_type = ixgbe_phy_unknown; + break; + } + + return phy_type; +} + +/** + * ixgbe_reset_phy_generic - Performs a PHY reset + * @hw: pointer to hardware structure + **/ +s32 ixgbe_reset_phy_generic(struct ixgbe_hw *hw) +{ + u32 i; + u16 ctrl = 0; + s32 status = 0; + + if (hw->phy.type == ixgbe_phy_unknown) + status = ixgbe_identify_phy_generic(hw); + + if (status != 0 || hw->phy.type == ixgbe_phy_none) + return status; + + /* Don't reset PHY if it's shut down due to overtemp. */ + if (!hw->phy.reset_if_overtemp && + (IXGBE_ERR_OVERTEMP == hw->phy.ops.check_overtemp(hw))) + return 0; + + /* Blocked by MNG FW so bail */ + if (ixgbe_check_reset_blocked(hw)) + return 0; + + /* + * Perform soft PHY reset to the PHY_XS. + * This will cause a soft reset to the PHY + */ + hw->phy.ops.write_reg(hw, MDIO_CTRL1, + MDIO_MMD_PHYXS, + MDIO_CTRL1_RESET); + + /* + * Poll for reset bit to self-clear indicating reset is complete. + * Some PHYs could take up to 3 seconds to complete and need about + * 1.7 usec delay after the reset is complete. + */ + for (i = 0; i < 30; i++) { + msleep(100); + if (hw->phy.type == ixgbe_phy_x550em_ext_t) { + status = hw->phy.ops.read_reg(hw, + IXGBE_MDIO_TX_VENDOR_ALARMS_3, + MDIO_MMD_PMAPMD, &ctrl); + if (status) + return status; + + if (ctrl & IXGBE_MDIO_TX_VENDOR_ALARMS_3_RST_MASK) { + udelay(2); + break; + } + } else { + status = hw->phy.ops.read_reg(hw, MDIO_CTRL1, + MDIO_MMD_PHYXS, &ctrl); + if (status) + return status; + + if (!(ctrl & MDIO_CTRL1_RESET)) { + udelay(2); + break; + } + } + } + + if (ctrl & MDIO_CTRL1_RESET) { + hw_dbg(hw, "PHY reset polling failed to complete.\n"); + return IXGBE_ERR_RESET_FAILED; + } + + return 0; +} + +/** + * ixgbe_read_phy_mdi - Reads a value from a specified PHY register without + * the SWFW lock + * @hw: pointer to hardware structure + * @reg_addr: 32 bit address of PHY register to read + * @device_type: 5 bit device type + * @phy_data: Pointer to read data from PHY register + **/ +s32 ixgbe_read_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, u32 device_type, + u16 *phy_data) +{ + u32 i, data, command; + + /* Setup and write the address cycle command */ + command = ((reg_addr << IXGBE_MSCA_NP_ADDR_SHIFT) | + (device_type << IXGBE_MSCA_DEV_TYPE_SHIFT) | + (hw->phy.mdio.prtad << IXGBE_MSCA_PHY_ADDR_SHIFT) | + (IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND)); + + IXGBE_WRITE_REG(hw, IXGBE_MSCA, command); + + /* Check every 10 usec to see if the address cycle completed. + * The MDI Command bit will clear when the operation is + * complete + */ + for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) { + udelay(10); + + command = IXGBE_READ_REG(hw, IXGBE_MSCA); + if ((command & IXGBE_MSCA_MDI_COMMAND) == 0) + break; + } + + + if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { + hw_dbg(hw, "PHY address command did not complete.\n"); + return IXGBE_ERR_PHY; + } + + /* Address cycle complete, setup and write the read + * command + */ + command = ((reg_addr << IXGBE_MSCA_NP_ADDR_SHIFT) | + (device_type << IXGBE_MSCA_DEV_TYPE_SHIFT) | + (hw->phy.mdio.prtad << IXGBE_MSCA_PHY_ADDR_SHIFT) | + (IXGBE_MSCA_READ | IXGBE_MSCA_MDI_COMMAND)); + + IXGBE_WRITE_REG(hw, IXGBE_MSCA, command); + + /* Check every 10 usec to see if the address cycle + * completed. The MDI Command bit will clear when the + * operation is complete + */ + for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) { + udelay(10); + + command = IXGBE_READ_REG(hw, IXGBE_MSCA); + if ((command & IXGBE_MSCA_MDI_COMMAND) == 0) + break; + } + + if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { + hw_dbg(hw, "PHY read command didn't complete\n"); + return IXGBE_ERR_PHY; + } + + /* Read operation is complete. Get the data + * from MSRWD + */ + data = IXGBE_READ_REG(hw, IXGBE_MSRWD); + data >>= IXGBE_MSRWD_READ_DATA_SHIFT; + *phy_data = (u16)(data); + + return 0; +} + +/** + * ixgbe_read_phy_reg_generic - Reads a value from a specified PHY register + * using the SWFW lock - this function is needed in most cases + * @hw: pointer to hardware structure + * @reg_addr: 32 bit address of PHY register to read + * @device_type: 5 bit device type + * @phy_data: Pointer to read data from PHY register + **/ +s32 ixgbe_read_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u16 *phy_data) +{ + s32 status; + u32 gssr = hw->phy.phy_semaphore_mask; + + if (hw->mac.ops.acquire_swfw_sync(hw, gssr) == 0) { + status = ixgbe_read_phy_reg_mdi(hw, reg_addr, device_type, + phy_data); + hw->mac.ops.release_swfw_sync(hw, gssr); + } else { + return IXGBE_ERR_SWFW_SYNC; + } + + return status; +} + +/** + * ixgbe_write_phy_reg_mdi - Writes a value to specified PHY register + * without SWFW lock + * @hw: pointer to hardware structure + * @reg_addr: 32 bit PHY register to write + * @device_type: 5 bit device type + * @phy_data: Data to write to the PHY register + **/ +s32 ixgbe_write_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u16 phy_data) +{ + u32 i, command; + + /* Put the data in the MDI single read and write data register*/ + IXGBE_WRITE_REG(hw, IXGBE_MSRWD, (u32)phy_data); + + /* Setup and write the address cycle command */ + command = ((reg_addr << IXGBE_MSCA_NP_ADDR_SHIFT) | + (device_type << IXGBE_MSCA_DEV_TYPE_SHIFT) | + (hw->phy.mdio.prtad << IXGBE_MSCA_PHY_ADDR_SHIFT) | + (IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND)); + + IXGBE_WRITE_REG(hw, IXGBE_MSCA, command); + + /* + * Check every 10 usec to see if the address cycle completed. + * The MDI Command bit will clear when the operation is + * complete + */ + for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) { + udelay(10); + + command = IXGBE_READ_REG(hw, IXGBE_MSCA); + if ((command & IXGBE_MSCA_MDI_COMMAND) == 0) + break; + } + + if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { + hw_dbg(hw, "PHY address cmd didn't complete\n"); + return IXGBE_ERR_PHY; + } + + /* + * Address cycle complete, setup and write the write + * command + */ + command = ((reg_addr << IXGBE_MSCA_NP_ADDR_SHIFT) | + (device_type << IXGBE_MSCA_DEV_TYPE_SHIFT) | + (hw->phy.mdio.prtad << IXGBE_MSCA_PHY_ADDR_SHIFT) | + (IXGBE_MSCA_WRITE | IXGBE_MSCA_MDI_COMMAND)); + + IXGBE_WRITE_REG(hw, IXGBE_MSCA, command); + + /* Check every 10 usec to see if the address cycle + * completed. The MDI Command bit will clear when the + * operation is complete + */ + for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) { + udelay(10); + + command = IXGBE_READ_REG(hw, IXGBE_MSCA); + if ((command & IXGBE_MSCA_MDI_COMMAND) == 0) + break; + } + + if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { + hw_dbg(hw, "PHY write cmd didn't complete\n"); + return IXGBE_ERR_PHY; + } + + return 0; +} + +/** + * ixgbe_write_phy_reg_generic - Writes a value to specified PHY register + * using SWFW lock- this function is needed in most cases + * @hw: pointer to hardware structure + * @reg_addr: 32 bit PHY register to write + * @device_type: 5 bit device type + * @phy_data: Data to write to the PHY register + **/ +s32 ixgbe_write_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u16 phy_data) +{ + s32 status; + u32 gssr = hw->phy.phy_semaphore_mask; + + if (hw->mac.ops.acquire_swfw_sync(hw, gssr) == 0) { + status = ixgbe_write_phy_reg_mdi(hw, reg_addr, device_type, + phy_data); + hw->mac.ops.release_swfw_sync(hw, gssr); + } else { + return IXGBE_ERR_SWFW_SYNC; + } + + return status; +} + +#define IXGBE_HW_READ_REG(addr) IXGBE_READ_REG(hw, addr) + +/** + * ixgbe_msca_cmd - Write the command register and poll for completion/timeout + * @hw: pointer to hardware structure + * @cmd: command register value to write + **/ +static s32 ixgbe_msca_cmd(struct ixgbe_hw *hw, u32 cmd) +{ + IXGBE_WRITE_REG(hw, IXGBE_MSCA, cmd); + + return readx_poll_timeout(IXGBE_HW_READ_REG, IXGBE_MSCA, cmd, + !(cmd & IXGBE_MSCA_MDI_COMMAND), 10, + 10 * IXGBE_MDIO_COMMAND_TIMEOUT); +} + +/** + * ixgbe_mii_bus_read_generic - Read a clause 22/45 register with gssr flags + * @hw: pointer to hardware structure + * @addr: address + * @regnum: register number + * @gssr: semaphore flags to acquire + **/ +static s32 ixgbe_mii_bus_read_generic(struct ixgbe_hw *hw, int addr, + int regnum, u32 gssr) +{ + u32 hwaddr, cmd; + s32 data; + + if (hw->mac.ops.acquire_swfw_sync(hw, gssr)) + return -EBUSY; + + hwaddr = addr << IXGBE_MSCA_PHY_ADDR_SHIFT; + if (regnum & MII_ADDR_C45) { + hwaddr |= regnum & GENMASK(21, 0); + cmd = hwaddr | IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND; + } else { + hwaddr |= (regnum & GENMASK(5, 0)) << IXGBE_MSCA_DEV_TYPE_SHIFT; + cmd = hwaddr | IXGBE_MSCA_OLD_PROTOCOL | + IXGBE_MSCA_READ_AUTOINC | IXGBE_MSCA_MDI_COMMAND; + } + + data = ixgbe_msca_cmd(hw, cmd); + if (data < 0) + goto mii_bus_read_done; + + /* For a clause 45 access the address cycle just completed, we still + * need to do the read command, otherwise just get the data + */ + if (!(regnum & MII_ADDR_C45)) + goto do_mii_bus_read; + + cmd = hwaddr | IXGBE_MSCA_READ | IXGBE_MSCA_MDI_COMMAND; + data = ixgbe_msca_cmd(hw, cmd); + if (data < 0) + goto mii_bus_read_done; + +do_mii_bus_read: + data = IXGBE_READ_REG(hw, IXGBE_MSRWD); + data = (data >> IXGBE_MSRWD_READ_DATA_SHIFT) & GENMASK(16, 0); + +mii_bus_read_done: + hw->mac.ops.release_swfw_sync(hw, gssr); + return data; +} + +/** + * ixgbe_mii_bus_write_generic - Write a clause 22/45 register with gssr flags + * @hw: pointer to hardware structure + * @addr: address + * @regnum: register number + * @val: value to write + * @gssr: semaphore flags to acquire + **/ +static s32 ixgbe_mii_bus_write_generic(struct ixgbe_hw *hw, int addr, + int regnum, u16 val, u32 gssr) +{ + u32 hwaddr, cmd; + s32 err; + + if (hw->mac.ops.acquire_swfw_sync(hw, gssr)) + return -EBUSY; + + IXGBE_WRITE_REG(hw, IXGBE_MSRWD, (u32)val); + + hwaddr = addr << IXGBE_MSCA_PHY_ADDR_SHIFT; + if (regnum & MII_ADDR_C45) { + hwaddr |= regnum & GENMASK(21, 0); + cmd = hwaddr | IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND; + } else { + hwaddr |= (regnum & GENMASK(5, 0)) << IXGBE_MSCA_DEV_TYPE_SHIFT; + cmd = hwaddr | IXGBE_MSCA_OLD_PROTOCOL | IXGBE_MSCA_WRITE | + IXGBE_MSCA_MDI_COMMAND; + } + + /* For clause 45 this is an address cycle, for clause 22 this is the + * entire transaction + */ + err = ixgbe_msca_cmd(hw, cmd); + if (err < 0 || !(regnum & MII_ADDR_C45)) + goto mii_bus_write_done; + + cmd = hwaddr | IXGBE_MSCA_WRITE | IXGBE_MSCA_MDI_COMMAND; + err = ixgbe_msca_cmd(hw, cmd); + +mii_bus_write_done: + hw->mac.ops.release_swfw_sync(hw, gssr); + return err; +} + +/** + * ixgbe_mii_bus_read - Read a clause 22/45 register + * @bus: pointer to mii_bus structure which points to our driver private + * @addr: address + * @regnum: register number + **/ +static s32 ixgbe_mii_bus_read(struct mii_bus *bus, int addr, int regnum) +{ + struct ixgbe_adapter *adapter = bus->priv; + struct ixgbe_hw *hw = &adapter->hw; + u32 gssr = hw->phy.phy_semaphore_mask; + + return ixgbe_mii_bus_read_generic(hw, addr, regnum, gssr); +} + +/** + * ixgbe_mii_bus_write - Write a clause 22/45 register + * @bus: pointer to mii_bus structure which points to our driver private + * @addr: address + * @regnum: register number + * @val: value to write + **/ +static s32 ixgbe_mii_bus_write(struct mii_bus *bus, int addr, int regnum, + u16 val) +{ + struct ixgbe_adapter *adapter = bus->priv; + struct ixgbe_hw *hw = &adapter->hw; + u32 gssr = hw->phy.phy_semaphore_mask; + + return ixgbe_mii_bus_write_generic(hw, addr, regnum, val, gssr); +} + +/** + * ixgbe_x550em_a_mii_bus_read - Read a clause 22/45 register on x550em_a + * @bus: pointer to mii_bus structure which points to our driver private + * @addr: address + * @regnum: register number + **/ +static s32 ixgbe_x550em_a_mii_bus_read(struct mii_bus *bus, int addr, + int regnum) +{ + struct ixgbe_adapter *adapter = bus->priv; + struct ixgbe_hw *hw = &adapter->hw; + u32 gssr = hw->phy.phy_semaphore_mask; + + gssr |= IXGBE_GSSR_TOKEN_SM | IXGBE_GSSR_PHY0_SM; + return ixgbe_mii_bus_read_generic(hw, addr, regnum, gssr); +} + +/** + * ixgbe_x550em_a_mii_bus_write - Write a clause 22/45 register on x550em_a + * @bus: pointer to mii_bus structure which points to our driver private + * @addr: address + * @regnum: register number + * @val: value to write + **/ +static s32 ixgbe_x550em_a_mii_bus_write(struct mii_bus *bus, int addr, + int regnum, u16 val) +{ + struct ixgbe_adapter *adapter = bus->priv; + struct ixgbe_hw *hw = &adapter->hw; + u32 gssr = hw->phy.phy_semaphore_mask; + + gssr |= IXGBE_GSSR_TOKEN_SM | IXGBE_GSSR_PHY0_SM; + return ixgbe_mii_bus_write_generic(hw, addr, regnum, val, gssr); +} + +/** + * ixgbe_get_first_secondary_devfn - get first device downstream of root port + * @devfn: PCI_DEVFN of root port on domain 0, bus 0 + * + * Returns pci_dev pointer to PCI_DEVFN(0, 0) on subordinate side of root + * on domain 0, bus 0, devfn = 'devfn' + **/ +static struct pci_dev *ixgbe_get_first_secondary_devfn(unsigned int devfn) +{ + struct pci_dev *rp_pdev; + int bus; + + rp_pdev = pci_get_domain_bus_and_slot(0, 0, devfn); + if (rp_pdev && rp_pdev->subordinate) { + bus = rp_pdev->subordinate->number; + pci_dev_put(rp_pdev); + return pci_get_domain_bus_and_slot(0, bus, 0); + } + + pci_dev_put(rp_pdev); + return NULL; +} + +/** + * ixgbe_x550em_a_has_mii - is this the first ixgbe x550em_a PCI function? + * @hw: pointer to hardware structure + * + * Returns true if hw points to lowest numbered PCI B:D.F x550_em_a device in + * the SoC. There are up to 4 MACs sharing a single MDIO bus on the x550em_a, + * but we only want to register one MDIO bus. + **/ +static bool ixgbe_x550em_a_has_mii(struct ixgbe_hw *hw) +{ + struct ixgbe_adapter *adapter = hw->back; + struct pci_dev *pdev = adapter->pdev; + struct pci_dev *func0_pdev; + bool has_mii = false; + + /* For the C3000 family of SoCs (x550em_a) the internal ixgbe devices + * are always downstream of root ports @ 0000:00:16.0 & 0000:00:17.0 + * It's not valid for function 0 to be disabled and function 1 is up, + * so the lowest numbered ixgbe dev will be device 0 function 0 on one + * of those two root ports + */ + func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x16, 0)); + if (func0_pdev) { + if (func0_pdev == pdev) + has_mii = true; + goto out; + } + func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x17, 0)); + if (func0_pdev == pdev) + has_mii = true; + +out: + pci_dev_put(func0_pdev); + return has_mii; +} + +/** + * ixgbe_mii_bus_init - mii_bus structure setup + * @hw: pointer to hardware structure + * + * Returns 0 on success, negative on failure + * + * ixgbe_mii_bus_init initializes a mii_bus structure in adapter + **/ +s32 ixgbe_mii_bus_init(struct ixgbe_hw *hw) +{ + s32 (*write)(struct mii_bus *bus, int addr, int regnum, u16 val); + s32 (*read)(struct mii_bus *bus, int addr, int regnum); + struct ixgbe_adapter *adapter = hw->back; + struct pci_dev *pdev = adapter->pdev; + struct device *dev = &adapter->netdev->dev; + struct mii_bus *bus; + + switch (hw->device_id) { + /* C3000 SoCs */ + case IXGBE_DEV_ID_X550EM_A_KR: + case IXGBE_DEV_ID_X550EM_A_KR_L: + case IXGBE_DEV_ID_X550EM_A_SFP_N: + case IXGBE_DEV_ID_X550EM_A_SGMII: + case IXGBE_DEV_ID_X550EM_A_SGMII_L: + case IXGBE_DEV_ID_X550EM_A_10G_T: + case IXGBE_DEV_ID_X550EM_A_SFP: + case IXGBE_DEV_ID_X550EM_A_1G_T: + case IXGBE_DEV_ID_X550EM_A_1G_T_L: + if (!ixgbe_x550em_a_has_mii(hw)) + return 0; + read = &ixgbe_x550em_a_mii_bus_read; + write = &ixgbe_x550em_a_mii_bus_write; + break; + default: + read = &ixgbe_mii_bus_read; + write = &ixgbe_mii_bus_write; + break; + } + + bus = devm_mdiobus_alloc(dev); + if (!bus) + return -ENOMEM; + + bus->read = read; + bus->write = write; + + /* Use the position of the device in the PCI hierarchy as the id */ + snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mdio-%s", ixgbe_driver_name, + pci_name(pdev)); + + bus->name = "ixgbe-mdio"; + bus->priv = adapter; + bus->parent = dev; + bus->phy_mask = GENMASK(31, 0); + + /* Support clause 22/45 natively. ixgbe_probe() sets MDIO_EMULATE_C22 + * unfortunately that causes some clause 22 frames to be sent with + * clause 45 addressing. We don't want that. + */ + hw->phy.mdio.mode_support = MDIO_SUPPORTS_C45 | MDIO_SUPPORTS_C22; + + adapter->mii_bus = bus; + return mdiobus_register(bus); +} + +/** + * ixgbe_setup_phy_link_generic - Set and restart autoneg + * @hw: pointer to hardware structure + * + * Restart autonegotiation and PHY and waits for completion. + **/ +s32 ixgbe_setup_phy_link_generic(struct ixgbe_hw *hw) +{ + s32 status = 0; + u16 autoneg_reg = IXGBE_MII_AUTONEG_REG; + bool autoneg = false; + ixgbe_link_speed speed; + + ixgbe_get_copper_link_capabilities_generic(hw, &speed, &autoneg); + + /* Set or unset auto-negotiation 10G advertisement */ + hw->phy.ops.read_reg(hw, MDIO_AN_10GBT_CTRL, MDIO_MMD_AN, &autoneg_reg); + + autoneg_reg &= ~MDIO_AN_10GBT_CTRL_ADV10G; + if ((hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL) && + (speed & IXGBE_LINK_SPEED_10GB_FULL)) + autoneg_reg |= MDIO_AN_10GBT_CTRL_ADV10G; + + hw->phy.ops.write_reg(hw, MDIO_AN_10GBT_CTRL, MDIO_MMD_AN, autoneg_reg); + + hw->phy.ops.read_reg(hw, IXGBE_MII_AUTONEG_VENDOR_PROVISION_1_REG, + MDIO_MMD_AN, &autoneg_reg); + + if (hw->mac.type == ixgbe_mac_X550) { + /* Set or unset auto-negotiation 5G advertisement */ + autoneg_reg &= ~IXGBE_MII_5GBASE_T_ADVERTISE; + if ((hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_5GB_FULL) && + (speed & IXGBE_LINK_SPEED_5GB_FULL)) + autoneg_reg |= IXGBE_MII_5GBASE_T_ADVERTISE; + + /* Set or unset auto-negotiation 2.5G advertisement */ + autoneg_reg &= ~IXGBE_MII_2_5GBASE_T_ADVERTISE; + if ((hw->phy.autoneg_advertised & + IXGBE_LINK_SPEED_2_5GB_FULL) && + (speed & IXGBE_LINK_SPEED_2_5GB_FULL)) + autoneg_reg |= IXGBE_MII_2_5GBASE_T_ADVERTISE; + } + + /* Set or unset auto-negotiation 1G advertisement */ + autoneg_reg &= ~IXGBE_MII_1GBASE_T_ADVERTISE; + if ((hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL) && + (speed & IXGBE_LINK_SPEED_1GB_FULL)) + autoneg_reg |= IXGBE_MII_1GBASE_T_ADVERTISE; + + hw->phy.ops.write_reg(hw, IXGBE_MII_AUTONEG_VENDOR_PROVISION_1_REG, + MDIO_MMD_AN, autoneg_reg); + + /* Set or unset auto-negotiation 100M advertisement */ + hw->phy.ops.read_reg(hw, MDIO_AN_ADVERTISE, MDIO_MMD_AN, &autoneg_reg); + + autoneg_reg &= ~(ADVERTISE_100FULL | ADVERTISE_100HALF); + if ((hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_100_FULL) && + (speed & IXGBE_LINK_SPEED_100_FULL)) + autoneg_reg |= ADVERTISE_100FULL; + + hw->phy.ops.write_reg(hw, MDIO_AN_ADVERTISE, MDIO_MMD_AN, autoneg_reg); + + /* Blocked by MNG FW so don't reset PHY */ + if (ixgbe_check_reset_blocked(hw)) + return 0; + + /* Restart PHY autonegotiation and wait for completion */ + hw->phy.ops.read_reg(hw, MDIO_CTRL1, + MDIO_MMD_AN, &autoneg_reg); + + autoneg_reg |= MDIO_AN_CTRL1_RESTART; + + hw->phy.ops.write_reg(hw, MDIO_CTRL1, + MDIO_MMD_AN, autoneg_reg); + + return status; +} + +/** + * ixgbe_setup_phy_link_speed_generic - Sets the auto advertised capabilities + * @hw: pointer to hardware structure + * @speed: new link speed + * @autoneg_wait_to_complete: unused + **/ +s32 ixgbe_setup_phy_link_speed_generic(struct ixgbe_hw *hw, + ixgbe_link_speed speed, + bool autoneg_wait_to_complete) +{ + /* Clear autoneg_advertised and set new values based on input link + * speed. + */ + hw->phy.autoneg_advertised = 0; + + if (speed & IXGBE_LINK_SPEED_10GB_FULL) + hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_10GB_FULL; + + if (speed & IXGBE_LINK_SPEED_5GB_FULL) + hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_5GB_FULL; + + if (speed & IXGBE_LINK_SPEED_2_5GB_FULL) + hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_2_5GB_FULL; + + if (speed & IXGBE_LINK_SPEED_1GB_FULL) + hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_1GB_FULL; + + if (speed & IXGBE_LINK_SPEED_100_FULL) + hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_100_FULL; + + if (speed & IXGBE_LINK_SPEED_10_FULL) + hw->phy.autoneg_advertised |= IXGBE_LINK_SPEED_10_FULL; + + /* Setup link based on the new speed settings */ + if (hw->phy.ops.setup_link) + hw->phy.ops.setup_link(hw); + + return 0; +} + +/** + * ixgbe_get_copper_speeds_supported - Get copper link speed from phy + * @hw: pointer to hardware structure + * + * Determines the supported link capabilities by reading the PHY auto + * negotiation register. + */ +static s32 ixgbe_get_copper_speeds_supported(struct ixgbe_hw *hw) +{ + u16 speed_ability; + s32 status; + + status = hw->phy.ops.read_reg(hw, MDIO_SPEED, MDIO_MMD_PMAPMD, + &speed_ability); + if (status) + return status; + + if (speed_ability & MDIO_SPEED_10G) + hw->phy.speeds_supported |= IXGBE_LINK_SPEED_10GB_FULL; + if (speed_ability & MDIO_PMA_SPEED_1000) + hw->phy.speeds_supported |= IXGBE_LINK_SPEED_1GB_FULL; + if (speed_ability & MDIO_PMA_SPEED_100) + hw->phy.speeds_supported |= IXGBE_LINK_SPEED_100_FULL; + + switch (hw->mac.type) { + case ixgbe_mac_X550: + hw->phy.speeds_supported |= IXGBE_LINK_SPEED_2_5GB_FULL; + hw->phy.speeds_supported |= IXGBE_LINK_SPEED_5GB_FULL; + break; + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + hw->phy.speeds_supported &= ~IXGBE_LINK_SPEED_100_FULL; + break; + default: + break; + } + + return 0; +} + +/** + * ixgbe_get_copper_link_capabilities_generic - Determines link capabilities + * @hw: pointer to hardware structure + * @speed: pointer to link speed + * @autoneg: boolean auto-negotiation value + */ +s32 ixgbe_get_copper_link_capabilities_generic(struct ixgbe_hw *hw, + ixgbe_link_speed *speed, + bool *autoneg) +{ + s32 status = 0; + + *autoneg = true; + if (!hw->phy.speeds_supported) + status = ixgbe_get_copper_speeds_supported(hw); + + *speed = hw->phy.speeds_supported; + return status; +} + +/** + * ixgbe_check_phy_link_tnx - Determine link and speed status + * @hw: pointer to hardware structure + * @speed: link speed + * @link_up: status of link + * + * Reads the VS1 register to determine if link is up and the current speed for + * the PHY. + **/ +s32 ixgbe_check_phy_link_tnx(struct ixgbe_hw *hw, ixgbe_link_speed *speed, + bool *link_up) +{ + s32 status; + u32 time_out; + u32 max_time_out = 10; + u16 phy_link = 0; + u16 phy_speed = 0; + u16 phy_data = 0; + + /* Initialize speed and link to default case */ + *link_up = false; + *speed = IXGBE_LINK_SPEED_10GB_FULL; + + /* + * Check current speed and link status of the PHY register. + * This is a vendor specific register and may have to + * be changed for other copper PHYs. + */ + for (time_out = 0; time_out < max_time_out; time_out++) { + udelay(10); + status = hw->phy.ops.read_reg(hw, + MDIO_STAT1, + MDIO_MMD_VEND1, + &phy_data); + phy_link = phy_data & + IXGBE_MDIO_VENDOR_SPECIFIC_1_LINK_STATUS; + phy_speed = phy_data & + IXGBE_MDIO_VENDOR_SPECIFIC_1_SPEED_STATUS; + if (phy_link == IXGBE_MDIO_VENDOR_SPECIFIC_1_LINK_STATUS) { + *link_up = true; + if (phy_speed == + IXGBE_MDIO_VENDOR_SPECIFIC_1_SPEED_STATUS) + *speed = IXGBE_LINK_SPEED_1GB_FULL; + break; + } + } + + return status; +} + +/** + * ixgbe_setup_phy_link_tnx - Set and restart autoneg + * @hw: pointer to hardware structure + * + * Restart autonegotiation and PHY and waits for completion. + * This function always returns success, this is nessary since + * it is called via a function pointer that could call other + * functions that could return an error. + **/ +s32 ixgbe_setup_phy_link_tnx(struct ixgbe_hw *hw) +{ + u16 autoneg_reg = IXGBE_MII_AUTONEG_REG; + bool autoneg = false; + ixgbe_link_speed speed; + + ixgbe_get_copper_link_capabilities_generic(hw, &speed, &autoneg); + + if (speed & IXGBE_LINK_SPEED_10GB_FULL) { + /* Set or unset auto-negotiation 10G advertisement */ + hw->phy.ops.read_reg(hw, MDIO_AN_10GBT_CTRL, + MDIO_MMD_AN, + &autoneg_reg); + + autoneg_reg &= ~MDIO_AN_10GBT_CTRL_ADV10G; + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_10GB_FULL) + autoneg_reg |= MDIO_AN_10GBT_CTRL_ADV10G; + + hw->phy.ops.write_reg(hw, MDIO_AN_10GBT_CTRL, + MDIO_MMD_AN, + autoneg_reg); + } + + if (speed & IXGBE_LINK_SPEED_1GB_FULL) { + /* Set or unset auto-negotiation 1G advertisement */ + hw->phy.ops.read_reg(hw, IXGBE_MII_AUTONEG_XNP_TX_REG, + MDIO_MMD_AN, + &autoneg_reg); + + autoneg_reg &= ~IXGBE_MII_1GBASE_T_ADVERTISE_XNP_TX; + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL) + autoneg_reg |= IXGBE_MII_1GBASE_T_ADVERTISE_XNP_TX; + + hw->phy.ops.write_reg(hw, IXGBE_MII_AUTONEG_XNP_TX_REG, + MDIO_MMD_AN, + autoneg_reg); + } + + if (speed & IXGBE_LINK_SPEED_100_FULL) { + /* Set or unset auto-negotiation 100M advertisement */ + hw->phy.ops.read_reg(hw, MDIO_AN_ADVERTISE, + MDIO_MMD_AN, + &autoneg_reg); + + autoneg_reg &= ~(ADVERTISE_100FULL | + ADVERTISE_100HALF); + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_100_FULL) + autoneg_reg |= ADVERTISE_100FULL; + + hw->phy.ops.write_reg(hw, MDIO_AN_ADVERTISE, + MDIO_MMD_AN, + autoneg_reg); + } + + /* Blocked by MNG FW so don't reset PHY */ + if (ixgbe_check_reset_blocked(hw)) + return 0; + + /* Restart PHY autonegotiation and wait for completion */ + hw->phy.ops.read_reg(hw, MDIO_CTRL1, + MDIO_MMD_AN, &autoneg_reg); + + autoneg_reg |= MDIO_AN_CTRL1_RESTART; + + hw->phy.ops.write_reg(hw, MDIO_CTRL1, + MDIO_MMD_AN, autoneg_reg); + return 0; +} + +/** + * ixgbe_reset_phy_nl - Performs a PHY reset + * @hw: pointer to hardware structure + **/ +s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw) +{ + u16 phy_offset, control, eword, edata, block_crc; + bool end_data = false; + u16 list_offset, data_offset; + u16 phy_data = 0; + s32 ret_val; + u32 i; + + /* Blocked by MNG FW so bail */ + if (ixgbe_check_reset_blocked(hw)) + return 0; + + hw->phy.ops.read_reg(hw, MDIO_CTRL1, MDIO_MMD_PHYXS, &phy_data); + + /* reset the PHY and poll for completion */ + hw->phy.ops.write_reg(hw, MDIO_CTRL1, MDIO_MMD_PHYXS, + (phy_data | MDIO_CTRL1_RESET)); + + for (i = 0; i < 100; i++) { + hw->phy.ops.read_reg(hw, MDIO_CTRL1, MDIO_MMD_PHYXS, + &phy_data); + if ((phy_data & MDIO_CTRL1_RESET) == 0) + break; + usleep_range(10000, 20000); + } + + if ((phy_data & MDIO_CTRL1_RESET) != 0) { + hw_dbg(hw, "PHY reset did not complete.\n"); + return IXGBE_ERR_PHY; + } + + /* Get init offsets */ + ret_val = ixgbe_get_sfp_init_sequence_offsets(hw, &list_offset, + &data_offset); + if (ret_val) + return ret_val; + + ret_val = hw->eeprom.ops.read(hw, data_offset, &block_crc); + data_offset++; + while (!end_data) { + /* + * Read control word from PHY init contents offset + */ + ret_val = hw->eeprom.ops.read(hw, data_offset, &eword); + if (ret_val) + goto err_eeprom; + control = (eword & IXGBE_CONTROL_MASK_NL) >> + IXGBE_CONTROL_SHIFT_NL; + edata = eword & IXGBE_DATA_MASK_NL; + switch (control) { + case IXGBE_DELAY_NL: + data_offset++; + hw_dbg(hw, "DELAY: %d MS\n", edata); + usleep_range(edata * 1000, edata * 2000); + break; + case IXGBE_DATA_NL: + hw_dbg(hw, "DATA:\n"); + data_offset++; + ret_val = hw->eeprom.ops.read(hw, data_offset++, + &phy_offset); + if (ret_val) + goto err_eeprom; + for (i = 0; i < edata; i++) { + ret_val = hw->eeprom.ops.read(hw, data_offset, + &eword); + if (ret_val) + goto err_eeprom; + hw->phy.ops.write_reg(hw, phy_offset, + MDIO_MMD_PMAPMD, eword); + hw_dbg(hw, "Wrote %4.4x to %4.4x\n", eword, + phy_offset); + data_offset++; + phy_offset++; + } + break; + case IXGBE_CONTROL_NL: + data_offset++; + hw_dbg(hw, "CONTROL:\n"); + if (edata == IXGBE_CONTROL_EOL_NL) { + hw_dbg(hw, "EOL\n"); + end_data = true; + } else if (edata == IXGBE_CONTROL_SOL_NL) { + hw_dbg(hw, "SOL\n"); + } else { + hw_dbg(hw, "Bad control value\n"); + return IXGBE_ERR_PHY; + } + break; + default: + hw_dbg(hw, "Bad control type\n"); + return IXGBE_ERR_PHY; + } + } + + return ret_val; + +err_eeprom: + hw_err(hw, "eeprom read at offset %d failed\n", data_offset); + return IXGBE_ERR_PHY; +} + +/** + * ixgbe_identify_module_generic - Identifies module type + * @hw: pointer to hardware structure + * + * Determines HW type and calls appropriate function. + **/ +s32 ixgbe_identify_module_generic(struct ixgbe_hw *hw) +{ + switch (hw->mac.ops.get_media_type(hw)) { + case ixgbe_media_type_fiber: + return ixgbe_identify_sfp_module_generic(hw); + case ixgbe_media_type_fiber_qsfp: + return ixgbe_identify_qsfp_module_generic(hw); + default: + hw->phy.sfp_type = ixgbe_sfp_type_not_present; + return IXGBE_ERR_SFP_NOT_PRESENT; + } + + return IXGBE_ERR_SFP_NOT_PRESENT; +} + +/** + * ixgbe_identify_sfp_module_generic - Identifies SFP modules + * @hw: pointer to hardware structure + * + * Searches for and identifies the SFP module and assigns appropriate PHY type. + **/ +s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) +{ + struct ixgbe_adapter *adapter = hw->back; + s32 status; + u32 vendor_oui = 0; + enum ixgbe_sfp_type stored_sfp_type = hw->phy.sfp_type; + u8 identifier = 0; + u8 comp_codes_1g = 0; + u8 comp_codes_10g = 0; + u8 oui_bytes[3] = {0, 0, 0}; + u8 cable_tech = 0; + u8 cable_spec = 0; + u16 enforce_sfp = 0; + + if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_fiber) { + hw->phy.sfp_type = ixgbe_sfp_type_not_present; + return IXGBE_ERR_SFP_NOT_PRESENT; + } + + /* LAN ID is needed for sfp_type determination */ + hw->mac.ops.set_lan_id(hw); + + status = hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_IDENTIFIER, + &identifier); + + if (status) + goto err_read_i2c_eeprom; + + if (identifier != IXGBE_SFF_IDENTIFIER_SFP) { + hw->phy.type = ixgbe_phy_sfp_unsupported; + return IXGBE_ERR_SFP_NOT_SUPPORTED; + } + status = hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_1GBE_COMP_CODES, + &comp_codes_1g); + + if (status) + goto err_read_i2c_eeprom; + + status = hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_10GBE_COMP_CODES, + &comp_codes_10g); + + if (status) + goto err_read_i2c_eeprom; + status = hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_CABLE_TECHNOLOGY, + &cable_tech); + + if (status) + goto err_read_i2c_eeprom; + + /* ID Module + * ========= + * 0 SFP_DA_CU + * 1 SFP_SR + * 2 SFP_LR + * 3 SFP_DA_CORE0 - 82599-specific + * 4 SFP_DA_CORE1 - 82599-specific + * 5 SFP_SR/LR_CORE0 - 82599-specific + * 6 SFP_SR/LR_CORE1 - 82599-specific + * 7 SFP_act_lmt_DA_CORE0 - 82599-specific + * 8 SFP_act_lmt_DA_CORE1 - 82599-specific + * 9 SFP_1g_cu_CORE0 - 82599-specific + * 10 SFP_1g_cu_CORE1 - 82599-specific + * 11 SFP_1g_sx_CORE0 - 82599-specific + * 12 SFP_1g_sx_CORE1 - 82599-specific + */ + if (hw->mac.type == ixgbe_mac_82598EB) { + if (cable_tech & IXGBE_SFF_DA_PASSIVE_CABLE) + hw->phy.sfp_type = ixgbe_sfp_type_da_cu; + else if (comp_codes_10g & IXGBE_SFF_10GBASESR_CAPABLE) + hw->phy.sfp_type = ixgbe_sfp_type_sr; + else if (comp_codes_10g & IXGBE_SFF_10GBASELR_CAPABLE) + hw->phy.sfp_type = ixgbe_sfp_type_lr; + else + hw->phy.sfp_type = ixgbe_sfp_type_unknown; + } else { + if (cable_tech & IXGBE_SFF_DA_PASSIVE_CABLE) { + if (hw->bus.lan_id == 0) + hw->phy.sfp_type = + ixgbe_sfp_type_da_cu_core0; + else + hw->phy.sfp_type = + ixgbe_sfp_type_da_cu_core1; + } else if (cable_tech & IXGBE_SFF_DA_ACTIVE_CABLE) { + hw->phy.ops.read_i2c_eeprom( + hw, IXGBE_SFF_CABLE_SPEC_COMP, + &cable_spec); + if (cable_spec & + IXGBE_SFF_DA_SPEC_ACTIVE_LIMITING) { + if (hw->bus.lan_id == 0) + hw->phy.sfp_type = + ixgbe_sfp_type_da_act_lmt_core0; + else + hw->phy.sfp_type = + ixgbe_sfp_type_da_act_lmt_core1; + } else { + hw->phy.sfp_type = + ixgbe_sfp_type_unknown; + } + } else if (comp_codes_10g & + (IXGBE_SFF_10GBASESR_CAPABLE | + IXGBE_SFF_10GBASELR_CAPABLE)) { + if (hw->bus.lan_id == 0) + hw->phy.sfp_type = + ixgbe_sfp_type_srlr_core0; + else + hw->phy.sfp_type = + ixgbe_sfp_type_srlr_core1; + } else if (comp_codes_1g & IXGBE_SFF_1GBASET_CAPABLE) { + if (hw->bus.lan_id == 0) + hw->phy.sfp_type = + ixgbe_sfp_type_1g_cu_core0; + else + hw->phy.sfp_type = + ixgbe_sfp_type_1g_cu_core1; + } else if (comp_codes_1g & IXGBE_SFF_1GBASESX_CAPABLE) { + if (hw->bus.lan_id == 0) + hw->phy.sfp_type = + ixgbe_sfp_type_1g_sx_core0; + else + hw->phy.sfp_type = + ixgbe_sfp_type_1g_sx_core1; + } else if (comp_codes_1g & IXGBE_SFF_1GBASELX_CAPABLE) { + if (hw->bus.lan_id == 0) + hw->phy.sfp_type = + ixgbe_sfp_type_1g_lx_core0; + else + hw->phy.sfp_type = + ixgbe_sfp_type_1g_lx_core1; + } else { + hw->phy.sfp_type = ixgbe_sfp_type_unknown; + } + } + + if (hw->phy.sfp_type != stored_sfp_type) + hw->phy.sfp_setup_needed = true; + + /* Determine if the SFP+ PHY is dual speed or not. */ + hw->phy.multispeed_fiber = false; + if (((comp_codes_1g & IXGBE_SFF_1GBASESX_CAPABLE) && + (comp_codes_10g & IXGBE_SFF_10GBASESR_CAPABLE)) || + ((comp_codes_1g & IXGBE_SFF_1GBASELX_CAPABLE) && + (comp_codes_10g & IXGBE_SFF_10GBASELR_CAPABLE))) + hw->phy.multispeed_fiber = true; + + /* Determine PHY vendor */ + if (hw->phy.type != ixgbe_phy_nl) { + hw->phy.id = identifier; + status = hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_VENDOR_OUI_BYTE0, + &oui_bytes[0]); + + if (status != 0) + goto err_read_i2c_eeprom; + + status = hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_VENDOR_OUI_BYTE1, + &oui_bytes[1]); + + if (status != 0) + goto err_read_i2c_eeprom; + + status = hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_VENDOR_OUI_BYTE2, + &oui_bytes[2]); + + if (status != 0) + goto err_read_i2c_eeprom; + + vendor_oui = + ((oui_bytes[0] << IXGBE_SFF_VENDOR_OUI_BYTE0_SHIFT) | + (oui_bytes[1] << IXGBE_SFF_VENDOR_OUI_BYTE1_SHIFT) | + (oui_bytes[2] << IXGBE_SFF_VENDOR_OUI_BYTE2_SHIFT)); + + switch (vendor_oui) { + case IXGBE_SFF_VENDOR_OUI_TYCO: + if (cable_tech & IXGBE_SFF_DA_PASSIVE_CABLE) + hw->phy.type = + ixgbe_phy_sfp_passive_tyco; + break; + case IXGBE_SFF_VENDOR_OUI_FTL: + if (cable_tech & IXGBE_SFF_DA_ACTIVE_CABLE) + hw->phy.type = ixgbe_phy_sfp_ftl_active; + else + hw->phy.type = ixgbe_phy_sfp_ftl; + break; + case IXGBE_SFF_VENDOR_OUI_AVAGO: + hw->phy.type = ixgbe_phy_sfp_avago; + break; + case IXGBE_SFF_VENDOR_OUI_INTEL: + hw->phy.type = ixgbe_phy_sfp_intel; + break; + default: + if (cable_tech & IXGBE_SFF_DA_PASSIVE_CABLE) + hw->phy.type = + ixgbe_phy_sfp_passive_unknown; + else if (cable_tech & IXGBE_SFF_DA_ACTIVE_CABLE) + hw->phy.type = + ixgbe_phy_sfp_active_unknown; + else + hw->phy.type = ixgbe_phy_sfp_unknown; + break; + } + } + + /* Allow any DA cable vendor */ + if (cable_tech & (IXGBE_SFF_DA_PASSIVE_CABLE | + IXGBE_SFF_DA_ACTIVE_CABLE)) + return 0; + + /* Verify supported 1G SFP modules */ + if (comp_codes_10g == 0 && + !(hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core1 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core1 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1)) { + hw->phy.type = ixgbe_phy_sfp_unsupported; + return IXGBE_ERR_SFP_NOT_SUPPORTED; + } + + /* Anything else 82598-based is supported */ + if (hw->mac.type == ixgbe_mac_82598EB) + return 0; + + hw->mac.ops.get_device_caps(hw, &enforce_sfp); + if (!(enforce_sfp & IXGBE_DEVICE_CAPS_ALLOW_ANY_SFP) && + !(hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core1 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core1 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1)) { + /* Make sure we're a supported PHY type */ + if (hw->phy.type == ixgbe_phy_sfp_intel) + return 0; + if (hw->allow_unsupported_sfp) { + e_warn(drv, "WARNING: Intel (R) Network Connections are quality tested using Intel (R) Ethernet Optics. Using untested modules is not supported and may cause unstable operation or damage to the module or the adapter. Intel Corporation is not responsible for any harm caused by using untested modules.\n"); + return 0; + } + hw_dbg(hw, "SFP+ module not supported\n"); + hw->phy.type = ixgbe_phy_sfp_unsupported; + return IXGBE_ERR_SFP_NOT_SUPPORTED; + } + return 0; + +err_read_i2c_eeprom: + hw->phy.sfp_type = ixgbe_sfp_type_not_present; + if (hw->phy.type != ixgbe_phy_nl) { + hw->phy.id = 0; + hw->phy.type = ixgbe_phy_unknown; + } + return IXGBE_ERR_SFP_NOT_PRESENT; +} + +/** + * ixgbe_identify_qsfp_module_generic - Identifies QSFP modules + * @hw: pointer to hardware structure + * + * Searches for and identifies the QSFP module and assigns appropriate PHY type + **/ +static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw) +{ + struct ixgbe_adapter *adapter = hw->back; + s32 status; + u32 vendor_oui = 0; + enum ixgbe_sfp_type stored_sfp_type = hw->phy.sfp_type; + u8 identifier = 0; + u8 comp_codes_1g = 0; + u8 comp_codes_10g = 0; + u8 oui_bytes[3] = {0, 0, 0}; + u16 enforce_sfp = 0; + u8 connector = 0; + u8 cable_length = 0; + u8 device_tech = 0; + bool active_cable = false; + + if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_fiber_qsfp) { + hw->phy.sfp_type = ixgbe_sfp_type_not_present; + return IXGBE_ERR_SFP_NOT_PRESENT; + } + + /* LAN ID is needed for sfp_type determination */ + hw->mac.ops.set_lan_id(hw); + + status = hw->phy.ops.read_i2c_eeprom(hw, IXGBE_SFF_IDENTIFIER, + &identifier); + + if (status != 0) + goto err_read_i2c_eeprom; + + if (identifier != IXGBE_SFF_IDENTIFIER_QSFP_PLUS) { + hw->phy.type = ixgbe_phy_sfp_unsupported; + return IXGBE_ERR_SFP_NOT_SUPPORTED; + } + + hw->phy.id = identifier; + + status = hw->phy.ops.read_i2c_eeprom(hw, IXGBE_SFF_QSFP_10GBE_COMP, + &comp_codes_10g); + + if (status != 0) + goto err_read_i2c_eeprom; + + status = hw->phy.ops.read_i2c_eeprom(hw, IXGBE_SFF_QSFP_1GBE_COMP, + &comp_codes_1g); + + if (status != 0) + goto err_read_i2c_eeprom; + + if (comp_codes_10g & IXGBE_SFF_QSFP_DA_PASSIVE_CABLE) { + hw->phy.type = ixgbe_phy_qsfp_passive_unknown; + if (hw->bus.lan_id == 0) + hw->phy.sfp_type = ixgbe_sfp_type_da_cu_core0; + else + hw->phy.sfp_type = ixgbe_sfp_type_da_cu_core1; + } else if (comp_codes_10g & (IXGBE_SFF_10GBASESR_CAPABLE | + IXGBE_SFF_10GBASELR_CAPABLE)) { + if (hw->bus.lan_id == 0) + hw->phy.sfp_type = ixgbe_sfp_type_srlr_core0; + else + hw->phy.sfp_type = ixgbe_sfp_type_srlr_core1; + } else { + if (comp_codes_10g & IXGBE_SFF_QSFP_DA_ACTIVE_CABLE) + active_cable = true; + + if (!active_cable) { + /* check for active DA cables that pre-date + * SFF-8436 v3.6 + */ + hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_QSFP_CONNECTOR, + &connector); + + hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_QSFP_CABLE_LENGTH, + &cable_length); + + hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_QSFP_DEVICE_TECH, + &device_tech); + + if ((connector == + IXGBE_SFF_QSFP_CONNECTOR_NOT_SEPARABLE) && + (cable_length > 0) && + ((device_tech >> 4) == + IXGBE_SFF_QSFP_TRANSMITER_850NM_VCSEL)) + active_cable = true; + } + + if (active_cable) { + hw->phy.type = ixgbe_phy_qsfp_active_unknown; + if (hw->bus.lan_id == 0) + hw->phy.sfp_type = + ixgbe_sfp_type_da_act_lmt_core0; + else + hw->phy.sfp_type = + ixgbe_sfp_type_da_act_lmt_core1; + } else { + /* unsupported module type */ + hw->phy.type = ixgbe_phy_sfp_unsupported; + return IXGBE_ERR_SFP_NOT_SUPPORTED; + } + } + + if (hw->phy.sfp_type != stored_sfp_type) + hw->phy.sfp_setup_needed = true; + + /* Determine if the QSFP+ PHY is dual speed or not. */ + hw->phy.multispeed_fiber = false; + if (((comp_codes_1g & IXGBE_SFF_1GBASESX_CAPABLE) && + (comp_codes_10g & IXGBE_SFF_10GBASESR_CAPABLE)) || + ((comp_codes_1g & IXGBE_SFF_1GBASELX_CAPABLE) && + (comp_codes_10g & IXGBE_SFF_10GBASELR_CAPABLE))) + hw->phy.multispeed_fiber = true; + + /* Determine PHY vendor for optical modules */ + if (comp_codes_10g & (IXGBE_SFF_10GBASESR_CAPABLE | + IXGBE_SFF_10GBASELR_CAPABLE)) { + status = hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_QSFP_VENDOR_OUI_BYTE0, + &oui_bytes[0]); + + if (status != 0) + goto err_read_i2c_eeprom; + + status = hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_QSFP_VENDOR_OUI_BYTE1, + &oui_bytes[1]); + + if (status != 0) + goto err_read_i2c_eeprom; + + status = hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_QSFP_VENDOR_OUI_BYTE2, + &oui_bytes[2]); + + if (status != 0) + goto err_read_i2c_eeprom; + + vendor_oui = + ((oui_bytes[0] << IXGBE_SFF_VENDOR_OUI_BYTE0_SHIFT) | + (oui_bytes[1] << IXGBE_SFF_VENDOR_OUI_BYTE1_SHIFT) | + (oui_bytes[2] << IXGBE_SFF_VENDOR_OUI_BYTE2_SHIFT)); + + if (vendor_oui == IXGBE_SFF_VENDOR_OUI_INTEL) + hw->phy.type = ixgbe_phy_qsfp_intel; + else + hw->phy.type = ixgbe_phy_qsfp_unknown; + + hw->mac.ops.get_device_caps(hw, &enforce_sfp); + if (!(enforce_sfp & IXGBE_DEVICE_CAPS_ALLOW_ANY_SFP)) { + /* Make sure we're a supported PHY type */ + if (hw->phy.type == ixgbe_phy_qsfp_intel) + return 0; + if (hw->allow_unsupported_sfp) { + e_warn(drv, "WARNING: Intel (R) Network Connections are quality tested using Intel (R) Ethernet Optics. Using untested modules is not supported and may cause unstable operation or damage to the module or the adapter. Intel Corporation is not responsible for any harm caused by using untested modules.\n"); + return 0; + } + hw_dbg(hw, "QSFP module not supported\n"); + hw->phy.type = ixgbe_phy_sfp_unsupported; + return IXGBE_ERR_SFP_NOT_SUPPORTED; + } + return 0; + } + return 0; + +err_read_i2c_eeprom: + hw->phy.sfp_type = ixgbe_sfp_type_not_present; + hw->phy.id = 0; + hw->phy.type = ixgbe_phy_unknown; + + return IXGBE_ERR_SFP_NOT_PRESENT; +} + +/** + * ixgbe_get_sfp_init_sequence_offsets - Provides offset of PHY init sequence + * @hw: pointer to hardware structure + * @list_offset: offset to the SFP ID list + * @data_offset: offset to the SFP data block + * + * Checks the MAC's EEPROM to see if it supports a given SFP+ module type, if + * so it returns the offsets to the phy init sequence block. + **/ +s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, + u16 *list_offset, + u16 *data_offset) +{ + u16 sfp_id; + u16 sfp_type = hw->phy.sfp_type; + + if (hw->phy.sfp_type == ixgbe_sfp_type_unknown) + return IXGBE_ERR_SFP_NOT_SUPPORTED; + + if (hw->phy.sfp_type == ixgbe_sfp_type_not_present) + return IXGBE_ERR_SFP_NOT_PRESENT; + + if ((hw->device_id == IXGBE_DEV_ID_82598_SR_DUAL_PORT_EM) && + (hw->phy.sfp_type == ixgbe_sfp_type_da_cu)) + return IXGBE_ERR_SFP_NOT_SUPPORTED; + + /* + * Limiting active cables and 1G Phys must be initialized as + * SR modules + */ + if (sfp_type == ixgbe_sfp_type_da_act_lmt_core0 || + sfp_type == ixgbe_sfp_type_1g_lx_core0 || + sfp_type == ixgbe_sfp_type_1g_cu_core0 || + sfp_type == ixgbe_sfp_type_1g_sx_core0) + sfp_type = ixgbe_sfp_type_srlr_core0; + else if (sfp_type == ixgbe_sfp_type_da_act_lmt_core1 || + sfp_type == ixgbe_sfp_type_1g_lx_core1 || + sfp_type == ixgbe_sfp_type_1g_cu_core1 || + sfp_type == ixgbe_sfp_type_1g_sx_core1) + sfp_type = ixgbe_sfp_type_srlr_core1; + + /* Read offset to PHY init contents */ + if (hw->eeprom.ops.read(hw, IXGBE_PHY_INIT_OFFSET_NL, list_offset)) { + hw_err(hw, "eeprom read at %d failed\n", + IXGBE_PHY_INIT_OFFSET_NL); + return IXGBE_ERR_SFP_NO_INIT_SEQ_PRESENT; + } + + if ((!*list_offset) || (*list_offset == 0xFFFF)) + return IXGBE_ERR_SFP_NO_INIT_SEQ_PRESENT; + + /* Shift offset to first ID word */ + (*list_offset)++; + + /* + * Find the matching SFP ID in the EEPROM + * and program the init sequence + */ + if (hw->eeprom.ops.read(hw, *list_offset, &sfp_id)) + goto err_phy; + + while (sfp_id != IXGBE_PHY_INIT_END_NL) { + if (sfp_id == sfp_type) { + (*list_offset)++; + if (hw->eeprom.ops.read(hw, *list_offset, data_offset)) + goto err_phy; + if ((!*data_offset) || (*data_offset == 0xFFFF)) { + hw_dbg(hw, "SFP+ module not supported\n"); + return IXGBE_ERR_SFP_NOT_SUPPORTED; + } else { + break; + } + } else { + (*list_offset) += 2; + if (hw->eeprom.ops.read(hw, *list_offset, &sfp_id)) + goto err_phy; + } + } + + if (sfp_id == IXGBE_PHY_INIT_END_NL) { + hw_dbg(hw, "No matching SFP+ module found\n"); + return IXGBE_ERR_SFP_NOT_SUPPORTED; + } + + return 0; + +err_phy: + hw_err(hw, "eeprom read at offset %d failed\n", *list_offset); + return IXGBE_ERR_PHY; +} + +/** + * ixgbe_read_i2c_eeprom_generic - Reads 8 bit EEPROM word over I2C interface + * @hw: pointer to hardware structure + * @byte_offset: EEPROM byte offset to read + * @eeprom_data: value read + * + * Performs byte read operation to SFP module's EEPROM over I2C interface. + **/ +s32 ixgbe_read_i2c_eeprom_generic(struct ixgbe_hw *hw, u8 byte_offset, + u8 *eeprom_data) +{ + return hw->phy.ops.read_i2c_byte(hw, byte_offset, + IXGBE_I2C_EEPROM_DEV_ADDR, + eeprom_data); +} + +/** + * ixgbe_read_i2c_sff8472_generic - Reads 8 bit word over I2C interface + * @hw: pointer to hardware structure + * @byte_offset: byte offset at address 0xA2 + * @sff8472_data: value read + * + * Performs byte read operation to SFP module's SFF-8472 data over I2C + **/ +s32 ixgbe_read_i2c_sff8472_generic(struct ixgbe_hw *hw, u8 byte_offset, + u8 *sff8472_data) +{ + return hw->phy.ops.read_i2c_byte(hw, byte_offset, + IXGBE_I2C_EEPROM_DEV_ADDR2, + sff8472_data); +} + +/** + * ixgbe_write_i2c_eeprom_generic - Writes 8 bit EEPROM word over I2C interface + * @hw: pointer to hardware structure + * @byte_offset: EEPROM byte offset to write + * @eeprom_data: value to write + * + * Performs byte write operation to SFP module's EEPROM over I2C interface. + **/ +s32 ixgbe_write_i2c_eeprom_generic(struct ixgbe_hw *hw, u8 byte_offset, + u8 eeprom_data) +{ + return hw->phy.ops.write_i2c_byte(hw, byte_offset, + IXGBE_I2C_EEPROM_DEV_ADDR, + eeprom_data); +} + +/** + * ixgbe_is_sfp_probe - Returns true if SFP is being detected + * @hw: pointer to hardware structure + * @offset: eeprom offset to be read + * @addr: I2C address to be read + */ +static bool ixgbe_is_sfp_probe(struct ixgbe_hw *hw, u8 offset, u8 addr) +{ + if (addr == IXGBE_I2C_EEPROM_DEV_ADDR && + offset == IXGBE_SFF_IDENTIFIER && + hw->phy.sfp_type == ixgbe_sfp_type_not_present) + return true; + return false; +} + +/** + * ixgbe_read_i2c_byte_generic_int - Reads 8 bit word over I2C + * @hw: pointer to hardware structure + * @byte_offset: byte offset to read + * @dev_addr: device address + * @data: value read + * @lock: true if to take and release semaphore + * + * Performs byte read operation to SFP module's EEPROM over I2C interface at + * a specified device address. + */ +static s32 ixgbe_read_i2c_byte_generic_int(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 *data, bool lock) +{ + s32 status; + u32 max_retry = 10; + u32 retry = 0; + u32 swfw_mask = hw->phy.phy_semaphore_mask; + bool nack = true; + + if (hw->mac.type >= ixgbe_mac_X550) + max_retry = 3; + if (ixgbe_is_sfp_probe(hw, byte_offset, dev_addr)) + max_retry = IXGBE_SFP_DETECT_RETRIES; + + *data = 0; + + do { + if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) + return IXGBE_ERR_SWFW_SYNC; + + ixgbe_i2c_start(hw); + + /* Device Address and write indication */ + status = ixgbe_clock_out_i2c_byte(hw, dev_addr); + if (status != 0) + goto fail; + + status = ixgbe_get_i2c_ack(hw); + if (status != 0) + goto fail; + + status = ixgbe_clock_out_i2c_byte(hw, byte_offset); + if (status != 0) + goto fail; + + status = ixgbe_get_i2c_ack(hw); + if (status != 0) + goto fail; + + ixgbe_i2c_start(hw); + + /* Device Address and read indication */ + status = ixgbe_clock_out_i2c_byte(hw, (dev_addr | 0x1)); + if (status != 0) + goto fail; + + status = ixgbe_get_i2c_ack(hw); + if (status != 0) + goto fail; + + status = ixgbe_clock_in_i2c_byte(hw, data); + if (status != 0) + goto fail; + + status = ixgbe_clock_out_i2c_bit(hw, nack); + if (status != 0) + goto fail; + + ixgbe_i2c_stop(hw); + if (lock) + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + return 0; + +fail: + ixgbe_i2c_bus_clear(hw); + if (lock) { + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + msleep(100); + } + retry++; + if (retry < max_retry) + hw_dbg(hw, "I2C byte read error - Retrying.\n"); + else + hw_dbg(hw, "I2C byte read error.\n"); + + } while (retry < max_retry); + + return status; +} + +/** + * ixgbe_read_i2c_byte_generic - Reads 8 bit word over I2C + * @hw: pointer to hardware structure + * @byte_offset: byte offset to read + * @dev_addr: device address + * @data: value read + * + * Performs byte read operation to SFP module's EEPROM over I2C interface at + * a specified device address. + */ +s32 ixgbe_read_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 *data) +{ + return ixgbe_read_i2c_byte_generic_int(hw, byte_offset, dev_addr, + data, true); +} + +/** + * ixgbe_read_i2c_byte_generic_unlocked - Reads 8 bit word over I2C + * @hw: pointer to hardware structure + * @byte_offset: byte offset to read + * @dev_addr: device address + * @data: value read + * + * Performs byte read operation to SFP module's EEPROM over I2C interface at + * a specified device address. + */ +s32 ixgbe_read_i2c_byte_generic_unlocked(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 *data) +{ + return ixgbe_read_i2c_byte_generic_int(hw, byte_offset, dev_addr, + data, false); +} + +/** + * ixgbe_write_i2c_byte_generic_int - Writes 8 bit word over I2C + * @hw: pointer to hardware structure + * @byte_offset: byte offset to write + * @dev_addr: device address + * @data: value to write + * @lock: true if to take and release semaphore + * + * Performs byte write operation to SFP module's EEPROM over I2C interface at + * a specified device address. + */ +static s32 ixgbe_write_i2c_byte_generic_int(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 data, bool lock) +{ + s32 status; + u32 max_retry = 1; + u32 retry = 0; + u32 swfw_mask = hw->phy.phy_semaphore_mask; + + if (lock && hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)) + return IXGBE_ERR_SWFW_SYNC; + + do { + ixgbe_i2c_start(hw); + + status = ixgbe_clock_out_i2c_byte(hw, dev_addr); + if (status != 0) + goto fail; + + status = ixgbe_get_i2c_ack(hw); + if (status != 0) + goto fail; + + status = ixgbe_clock_out_i2c_byte(hw, byte_offset); + if (status != 0) + goto fail; + + status = ixgbe_get_i2c_ack(hw); + if (status != 0) + goto fail; + + status = ixgbe_clock_out_i2c_byte(hw, data); + if (status != 0) + goto fail; + + status = ixgbe_get_i2c_ack(hw); + if (status != 0) + goto fail; + + ixgbe_i2c_stop(hw); + if (lock) + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + return 0; + +fail: + ixgbe_i2c_bus_clear(hw); + retry++; + if (retry < max_retry) + hw_dbg(hw, "I2C byte write error - Retrying.\n"); + else + hw_dbg(hw, "I2C byte write error.\n"); + } while (retry < max_retry); + + if (lock) + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + + return status; +} + +/** + * ixgbe_write_i2c_byte_generic - Writes 8 bit word over I2C + * @hw: pointer to hardware structure + * @byte_offset: byte offset to write + * @dev_addr: device address + * @data: value to write + * + * Performs byte write operation to SFP module's EEPROM over I2C interface at + * a specified device address. + */ +s32 ixgbe_write_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 data) +{ + return ixgbe_write_i2c_byte_generic_int(hw, byte_offset, dev_addr, + data, true); +} + +/** + * ixgbe_write_i2c_byte_generic_unlocked - Writes 8 bit word over I2C + * @hw: pointer to hardware structure + * @byte_offset: byte offset to write + * @dev_addr: device address + * @data: value to write + * + * Performs byte write operation to SFP module's EEPROM over I2C interface at + * a specified device address. + */ +s32 ixgbe_write_i2c_byte_generic_unlocked(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 data) +{ + return ixgbe_write_i2c_byte_generic_int(hw, byte_offset, dev_addr, + data, false); +} + +/** + * ixgbe_i2c_start - Sets I2C start condition + * @hw: pointer to hardware structure + * + * Sets I2C start condition (High -> Low on SDA while SCL is High) + * Set bit-bang mode on X550 hardware. + **/ +static void ixgbe_i2c_start(struct ixgbe_hw *hw) +{ + u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw)); + + i2cctl |= IXGBE_I2C_BB_EN(hw); + + /* Start condition must begin with data and clock high */ + ixgbe_set_i2c_data(hw, &i2cctl, 1); + ixgbe_raise_i2c_clk(hw, &i2cctl); + + /* Setup time for start condition (4.7us) */ + udelay(IXGBE_I2C_T_SU_STA); + + ixgbe_set_i2c_data(hw, &i2cctl, 0); + + /* Hold time for start condition (4us) */ + udelay(IXGBE_I2C_T_HD_STA); + + ixgbe_lower_i2c_clk(hw, &i2cctl); + + /* Minimum low period of clock is 4.7 us */ + udelay(IXGBE_I2C_T_LOW); + +} + +/** + * ixgbe_i2c_stop - Sets I2C stop condition + * @hw: pointer to hardware structure + * + * Sets I2C stop condition (Low -> High on SDA while SCL is High) + * Disables bit-bang mode and negates data output enable on X550 + * hardware. + **/ +static void ixgbe_i2c_stop(struct ixgbe_hw *hw) +{ + u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw)); + u32 data_oe_bit = IXGBE_I2C_DATA_OE_N_EN(hw); + u32 clk_oe_bit = IXGBE_I2C_CLK_OE_N_EN(hw); + u32 bb_en_bit = IXGBE_I2C_BB_EN(hw); + + /* Stop condition must begin with data low and clock high */ + ixgbe_set_i2c_data(hw, &i2cctl, 0); + ixgbe_raise_i2c_clk(hw, &i2cctl); + + /* Setup time for stop condition (4us) */ + udelay(IXGBE_I2C_T_SU_STO); + + ixgbe_set_i2c_data(hw, &i2cctl, 1); + + /* bus free time between stop and start (4.7us)*/ + udelay(IXGBE_I2C_T_BUF); + + if (bb_en_bit || data_oe_bit || clk_oe_bit) { + i2cctl &= ~bb_en_bit; + i2cctl |= data_oe_bit | clk_oe_bit; + IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), i2cctl); + IXGBE_WRITE_FLUSH(hw); + } +} + +/** + * ixgbe_clock_in_i2c_byte - Clocks in one byte via I2C + * @hw: pointer to hardware structure + * @data: data byte to clock in + * + * Clocks in one byte data via I2C data/clock + **/ +static s32 ixgbe_clock_in_i2c_byte(struct ixgbe_hw *hw, u8 *data) +{ + s32 i; + bool bit = false; + + *data = 0; + for (i = 7; i >= 0; i--) { + ixgbe_clock_in_i2c_bit(hw, &bit); + *data |= bit << i; + } + + return 0; +} + +/** + * ixgbe_clock_out_i2c_byte - Clocks out one byte via I2C + * @hw: pointer to hardware structure + * @data: data byte clocked out + * + * Clocks out one byte data via I2C data/clock + **/ +static s32 ixgbe_clock_out_i2c_byte(struct ixgbe_hw *hw, u8 data) +{ + s32 status; + s32 i; + u32 i2cctl; + bool bit = false; + + for (i = 7; i >= 0; i--) { + bit = (data >> i) & 0x1; + status = ixgbe_clock_out_i2c_bit(hw, bit); + + if (status != 0) + break; + } + + /* Release SDA line (set high) */ + i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw)); + i2cctl |= IXGBE_I2C_DATA_OUT(hw); + i2cctl |= IXGBE_I2C_DATA_OE_N_EN(hw); + IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), i2cctl); + IXGBE_WRITE_FLUSH(hw); + + return status; +} + +/** + * ixgbe_get_i2c_ack - Polls for I2C ACK + * @hw: pointer to hardware structure + * + * Clocks in/out one bit via I2C data/clock + **/ +static s32 ixgbe_get_i2c_ack(struct ixgbe_hw *hw) +{ + u32 data_oe_bit = IXGBE_I2C_DATA_OE_N_EN(hw); + s32 status = 0; + u32 i = 0; + u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw)); + u32 timeout = 10; + bool ack = true; + + if (data_oe_bit) { + i2cctl |= IXGBE_I2C_DATA_OUT(hw); + i2cctl |= data_oe_bit; + IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), i2cctl); + IXGBE_WRITE_FLUSH(hw); + } + ixgbe_raise_i2c_clk(hw, &i2cctl); + + /* Minimum high period of clock is 4us */ + udelay(IXGBE_I2C_T_HIGH); + + /* Poll for ACK. Note that ACK in I2C spec is + * transition from 1 to 0 */ + for (i = 0; i < timeout; i++) { + i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw)); + ack = ixgbe_get_i2c_data(hw, &i2cctl); + + udelay(1); + if (ack == 0) + break; + } + + if (ack == 1) { + hw_dbg(hw, "I2C ack was not received.\n"); + status = IXGBE_ERR_I2C; + } + + ixgbe_lower_i2c_clk(hw, &i2cctl); + + /* Minimum low period of clock is 4.7 us */ + udelay(IXGBE_I2C_T_LOW); + + return status; +} + +/** + * ixgbe_clock_in_i2c_bit - Clocks in one bit via I2C data/clock + * @hw: pointer to hardware structure + * @data: read data value + * + * Clocks in one bit via I2C data/clock + **/ +static s32 ixgbe_clock_in_i2c_bit(struct ixgbe_hw *hw, bool *data) +{ + u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw)); + u32 data_oe_bit = IXGBE_I2C_DATA_OE_N_EN(hw); + + if (data_oe_bit) { + i2cctl |= IXGBE_I2C_DATA_OUT(hw); + i2cctl |= data_oe_bit; + IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), i2cctl); + IXGBE_WRITE_FLUSH(hw); + } + ixgbe_raise_i2c_clk(hw, &i2cctl); + + /* Minimum high period of clock is 4us */ + udelay(IXGBE_I2C_T_HIGH); + + i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw)); + *data = ixgbe_get_i2c_data(hw, &i2cctl); + + ixgbe_lower_i2c_clk(hw, &i2cctl); + + /* Minimum low period of clock is 4.7 us */ + udelay(IXGBE_I2C_T_LOW); + + return 0; +} + +/** + * ixgbe_clock_out_i2c_bit - Clocks in/out one bit via I2C data/clock + * @hw: pointer to hardware structure + * @data: data value to write + * + * Clocks out one bit via I2C data/clock + **/ +static s32 ixgbe_clock_out_i2c_bit(struct ixgbe_hw *hw, bool data) +{ + s32 status; + u32 i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw)); + + status = ixgbe_set_i2c_data(hw, &i2cctl, data); + if (status == 0) { + ixgbe_raise_i2c_clk(hw, &i2cctl); + + /* Minimum high period of clock is 4us */ + udelay(IXGBE_I2C_T_HIGH); + + ixgbe_lower_i2c_clk(hw, &i2cctl); + + /* Minimum low period of clock is 4.7 us. + * This also takes care of the data hold time. + */ + udelay(IXGBE_I2C_T_LOW); + } else { + hw_dbg(hw, "I2C data was not set to %X\n", data); + return IXGBE_ERR_I2C; + } + + return 0; +} +/** + * ixgbe_raise_i2c_clk - Raises the I2C SCL clock + * @hw: pointer to hardware structure + * @i2cctl: Current value of I2CCTL register + * + * Raises the I2C clock line '0'->'1' + * Negates the I2C clock output enable on X550 hardware. + **/ +static void ixgbe_raise_i2c_clk(struct ixgbe_hw *hw, u32 *i2cctl) +{ + u32 clk_oe_bit = IXGBE_I2C_CLK_OE_N_EN(hw); + u32 i = 0; + u32 timeout = IXGBE_I2C_CLOCK_STRETCHING_TIMEOUT; + u32 i2cctl_r = 0; + + if (clk_oe_bit) { + *i2cctl |= clk_oe_bit; + IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), *i2cctl); + } + + for (i = 0; i < timeout; i++) { + *i2cctl |= IXGBE_I2C_CLK_OUT(hw); + IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), *i2cctl); + IXGBE_WRITE_FLUSH(hw); + /* SCL rise time (1000ns) */ + udelay(IXGBE_I2C_T_RISE); + + i2cctl_r = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw)); + if (i2cctl_r & IXGBE_I2C_CLK_IN(hw)) + break; + } +} + +/** + * ixgbe_lower_i2c_clk - Lowers the I2C SCL clock + * @hw: pointer to hardware structure + * @i2cctl: Current value of I2CCTL register + * + * Lowers the I2C clock line '1'->'0' + * Asserts the I2C clock output enable on X550 hardware. + **/ +static void ixgbe_lower_i2c_clk(struct ixgbe_hw *hw, u32 *i2cctl) +{ + + *i2cctl &= ~IXGBE_I2C_CLK_OUT(hw); + *i2cctl &= ~IXGBE_I2C_CLK_OE_N_EN(hw); + + IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), *i2cctl); + IXGBE_WRITE_FLUSH(hw); + + /* SCL fall time (300ns) */ + udelay(IXGBE_I2C_T_FALL); +} + +/** + * ixgbe_set_i2c_data - Sets the I2C data bit + * @hw: pointer to hardware structure + * @i2cctl: Current value of I2CCTL register + * @data: I2C data value (0 or 1) to set + * + * Sets the I2C data bit + * Asserts the I2C data output enable on X550 hardware. + **/ +static s32 ixgbe_set_i2c_data(struct ixgbe_hw *hw, u32 *i2cctl, bool data) +{ + u32 data_oe_bit = IXGBE_I2C_DATA_OE_N_EN(hw); + + if (data) + *i2cctl |= IXGBE_I2C_DATA_OUT(hw); + else + *i2cctl &= ~IXGBE_I2C_DATA_OUT(hw); + *i2cctl &= ~data_oe_bit; + + IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), *i2cctl); + IXGBE_WRITE_FLUSH(hw); + + /* Data rise/fall (1000ns/300ns) and set-up time (250ns) */ + udelay(IXGBE_I2C_T_RISE + IXGBE_I2C_T_FALL + IXGBE_I2C_T_SU_DATA); + + if (!data) /* Can't verify data in this case */ + return 0; + if (data_oe_bit) { + *i2cctl |= data_oe_bit; + IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), *i2cctl); + IXGBE_WRITE_FLUSH(hw); + } + + /* Verify data was set correctly */ + *i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw)); + if (data != ixgbe_get_i2c_data(hw, i2cctl)) { + hw_dbg(hw, "Error - I2C data was not set to %X.\n", data); + return IXGBE_ERR_I2C; + } + + return 0; +} + +/** + * ixgbe_get_i2c_data - Reads the I2C SDA data bit + * @hw: pointer to hardware structure + * @i2cctl: Current value of I2CCTL register + * + * Returns the I2C data bit value + * Negates the I2C data output enable on X550 hardware. + **/ +static bool ixgbe_get_i2c_data(struct ixgbe_hw *hw, u32 *i2cctl) +{ + u32 data_oe_bit = IXGBE_I2C_DATA_OE_N_EN(hw); + + if (data_oe_bit) { + *i2cctl |= data_oe_bit; + IXGBE_WRITE_REG(hw, IXGBE_I2CCTL(hw), *i2cctl); + IXGBE_WRITE_FLUSH(hw); + udelay(IXGBE_I2C_T_FALL); + } + + if (*i2cctl & IXGBE_I2C_DATA_IN(hw)) + return true; + return false; +} + +/** + * ixgbe_i2c_bus_clear - Clears the I2C bus + * @hw: pointer to hardware structure + * + * Clears the I2C bus by sending nine clock pulses. + * Used when data line is stuck low. + **/ +static void ixgbe_i2c_bus_clear(struct ixgbe_hw *hw) +{ + u32 i2cctl; + u32 i; + + ixgbe_i2c_start(hw); + i2cctl = IXGBE_READ_REG(hw, IXGBE_I2CCTL(hw)); + + ixgbe_set_i2c_data(hw, &i2cctl, 1); + + for (i = 0; i < 9; i++) { + ixgbe_raise_i2c_clk(hw, &i2cctl); + + /* Min high period of clock is 4us */ + udelay(IXGBE_I2C_T_HIGH); + + ixgbe_lower_i2c_clk(hw, &i2cctl); + + /* Min low period of clock is 4.7us*/ + udelay(IXGBE_I2C_T_LOW); + } + + ixgbe_i2c_start(hw); + + /* Put the i2c bus back to default state */ + ixgbe_i2c_stop(hw); +} + +/** + * ixgbe_tn_check_overtemp - Checks if an overtemp occurred. + * @hw: pointer to hardware structure + * + * Checks if the LASI temp alarm status was triggered due to overtemp + **/ +s32 ixgbe_tn_check_overtemp(struct ixgbe_hw *hw) +{ + u16 phy_data = 0; + + if (hw->device_id != IXGBE_DEV_ID_82599_T3_LOM) + return 0; + + /* Check that the LASI temp alarm status was triggered */ + hw->phy.ops.read_reg(hw, IXGBE_TN_LASI_STATUS_REG, + MDIO_MMD_PMAPMD, &phy_data); + + if (!(phy_data & IXGBE_TN_LASI_STATUS_TEMP_ALARM)) + return 0; + + return IXGBE_ERR_OVERTEMP; +} + +/** ixgbe_set_copper_phy_power - Control power for copper phy + * @hw: pointer to hardware structure + * @on: true for on, false for off + **/ +s32 ixgbe_set_copper_phy_power(struct ixgbe_hw *hw, bool on) +{ + u32 status; + u16 reg; + + /* Bail if we don't have copper phy */ + if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_copper) + return 0; + + if (!on && ixgbe_mng_present(hw)) + return 0; + + status = hw->phy.ops.read_reg(hw, MDIO_CTRL1, MDIO_MMD_VEND1, ®); + if (status) + return status; + + if (on) { + reg &= ~IXGBE_MDIO_PHY_SET_LOW_POWER_MODE; + } else { + if (ixgbe_check_reset_blocked(hw)) + return 0; + reg |= IXGBE_MDIO_PHY_SET_LOW_POWER_MODE; + } + + status = hw->phy.ops.write_reg(hw, MDIO_CTRL1, MDIO_MMD_VEND1, reg); + return status; +} diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h new file mode 100644 index 000000000..6544c4539 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h @@ -0,0 +1,177 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#ifndef _IXGBE_PHY_H_ +#define _IXGBE_PHY_H_ + +#include "ixgbe_type.h" +#define IXGBE_I2C_EEPROM_DEV_ADDR 0xA0 +#define IXGBE_I2C_EEPROM_DEV_ADDR2 0xA2 + +/* EEPROM byte offsets */ +#define IXGBE_SFF_IDENTIFIER 0x0 +#define IXGBE_SFF_IDENTIFIER_SFP 0x3 +#define IXGBE_SFF_VENDOR_OUI_BYTE0 0x25 +#define IXGBE_SFF_VENDOR_OUI_BYTE1 0x26 +#define IXGBE_SFF_VENDOR_OUI_BYTE2 0x27 +#define IXGBE_SFF_1GBE_COMP_CODES 0x6 +#define IXGBE_SFF_10GBE_COMP_CODES 0x3 +#define IXGBE_SFF_CABLE_TECHNOLOGY 0x8 +#define IXGBE_SFF_CABLE_SPEC_COMP 0x3C +#define IXGBE_SFF_SFF_8472_SWAP 0x5C +#define IXGBE_SFF_SFF_8472_COMP 0x5E +#define IXGBE_SFF_SFF_8472_OSCB 0x6E +#define IXGBE_SFF_SFF_8472_ESCB 0x76 +#define IXGBE_SFF_IDENTIFIER_QSFP_PLUS 0xD +#define IXGBE_SFF_QSFP_VENDOR_OUI_BYTE0 0xA5 +#define IXGBE_SFF_QSFP_VENDOR_OUI_BYTE1 0xA6 +#define IXGBE_SFF_QSFP_VENDOR_OUI_BYTE2 0xA7 +#define IXGBE_SFF_QSFP_CONNECTOR 0x82 +#define IXGBE_SFF_QSFP_10GBE_COMP 0x83 +#define IXGBE_SFF_QSFP_1GBE_COMP 0x86 +#define IXGBE_SFF_QSFP_CABLE_LENGTH 0x92 +#define IXGBE_SFF_QSFP_DEVICE_TECH 0x93 + +/* Bitmasks */ +#define IXGBE_SFF_DA_PASSIVE_CABLE 0x4 +#define IXGBE_SFF_DA_ACTIVE_CABLE 0x8 +#define IXGBE_SFF_DA_SPEC_ACTIVE_LIMITING 0x4 +#define IXGBE_SFF_1GBASESX_CAPABLE 0x1 +#define IXGBE_SFF_1GBASELX_CAPABLE 0x2 +#define IXGBE_SFF_1GBASET_CAPABLE 0x8 +#define IXGBE_SFF_10GBASESR_CAPABLE 0x10 +#define IXGBE_SFF_10GBASELR_CAPABLE 0x20 +#define IXGBE_SFF_SOFT_RS_SELECT_MASK 0x8 +#define IXGBE_SFF_SOFT_RS_SELECT_10G 0x8 +#define IXGBE_SFF_SOFT_RS_SELECT_1G 0x0 +#define IXGBE_SFF_ADDRESSING_MODE 0x4 +#define IXGBE_SFF_DDM_IMPLEMENTED 0x40 +#define IXGBE_SFF_QSFP_DA_ACTIVE_CABLE 0x1 +#define IXGBE_SFF_QSFP_DA_PASSIVE_CABLE 0x8 +#define IXGBE_SFF_QSFP_CONNECTOR_NOT_SEPARABLE 0x23 +#define IXGBE_SFF_QSFP_TRANSMITER_850NM_VCSEL 0x0 +#define IXGBE_I2C_EEPROM_READ_MASK 0x100 +#define IXGBE_I2C_EEPROM_STATUS_MASK 0x3 +#define IXGBE_I2C_EEPROM_STATUS_NO_OPERATION 0x0 +#define IXGBE_I2C_EEPROM_STATUS_PASS 0x1 +#define IXGBE_I2C_EEPROM_STATUS_FAIL 0x2 +#define IXGBE_I2C_EEPROM_STATUS_IN_PROGRESS 0x3 +#define IXGBE_CS4227 0xBE /* CS4227 address */ +#define IXGBE_CS4227_GLOBAL_ID_LSB 0 +#define IXGBE_CS4227_GLOBAL_ID_MSB 1 +#define IXGBE_CS4227_SCRATCH 2 +#define IXGBE_CS4227_EFUSE_PDF_SKU 0x19F +#define IXGBE_CS4223_SKU_ID 0x0010 /* Quad port */ +#define IXGBE_CS4227_SKU_ID 0x0014 /* Dual port */ +#define IXGBE_CS4227_RESET_PENDING 0x1357 +#define IXGBE_CS4227_RESET_COMPLETE 0x5AA5 +#define IXGBE_CS4227_RETRIES 15 +#define IXGBE_CS4227_EFUSE_STATUS 0x0181 +#define IXGBE_CS4227_LINE_SPARE22_MSB 0x12AD /* Reg to set speed */ +#define IXGBE_CS4227_LINE_SPARE24_LSB 0x12B0 /* Reg to set EDC */ +#define IXGBE_CS4227_HOST_SPARE22_MSB 0x1AAD /* Reg to set speed */ +#define IXGBE_CS4227_HOST_SPARE24_LSB 0x1AB0 /* Reg to program EDC */ +#define IXGBE_CS4227_EEPROM_STATUS 0x5001 +#define IXGBE_CS4227_EEPROM_LOAD_OK 0x0001 +#define IXGBE_CS4227_SPEED_1G 0x8000 +#define IXGBE_CS4227_SPEED_10G 0 +#define IXGBE_CS4227_EDC_MODE_CX1 0x0002 +#define IXGBE_CS4227_EDC_MODE_SR 0x0004 +#define IXGBE_CS4227_EDC_MODE_DIAG 0x0008 +#define IXGBE_CS4227_RESET_HOLD 500 /* microseconds */ +#define IXGBE_CS4227_RESET_DELAY 500 /* milliseconds */ +#define IXGBE_CS4227_CHECK_DELAY 30 /* milliseconds */ +#define IXGBE_PE 0xE0 /* Port expander addr */ +#define IXGBE_PE_OUTPUT 1 /* Output reg offset */ +#define IXGBE_PE_CONFIG 3 /* Config reg offset */ +#define IXGBE_PE_BIT1 BIT(1) + +/* Flow control defines */ +#define IXGBE_TAF_SYM_PAUSE 0x400 +#define IXGBE_TAF_ASM_PAUSE 0x800 + +/* Bit-shift macros */ +#define IXGBE_SFF_VENDOR_OUI_BYTE0_SHIFT 24 +#define IXGBE_SFF_VENDOR_OUI_BYTE1_SHIFT 16 +#define IXGBE_SFF_VENDOR_OUI_BYTE2_SHIFT 8 + +/* Vendor OUIs: format of OUI is 0x[byte0][byte1][byte2][00] */ +#define IXGBE_SFF_VENDOR_OUI_TYCO 0x00407600 +#define IXGBE_SFF_VENDOR_OUI_FTL 0x00906500 +#define IXGBE_SFF_VENDOR_OUI_AVAGO 0x00176A00 +#define IXGBE_SFF_VENDOR_OUI_INTEL 0x001B2100 + +/* I2C SDA and SCL timing parameters for standard mode */ +#define IXGBE_I2C_T_HD_STA 4 +#define IXGBE_I2C_T_LOW 5 +#define IXGBE_I2C_T_HIGH 4 +#define IXGBE_I2C_T_SU_STA 5 +#define IXGBE_I2C_T_HD_DATA 5 +#define IXGBE_I2C_T_SU_DATA 1 +#define IXGBE_I2C_T_RISE 1 +#define IXGBE_I2C_T_FALL 1 +#define IXGBE_I2C_T_SU_STO 4 +#define IXGBE_I2C_T_BUF 5 + +#define IXGBE_SFP_DETECT_RETRIES 2 + +#define IXGBE_TN_LASI_STATUS_REG 0x9005 +#define IXGBE_TN_LASI_STATUS_TEMP_ALARM 0x0008 + +/* SFP+ SFF-8472 Compliance code */ +#define IXGBE_SFF_SFF_8472_UNSUP 0x00 + +s32 ixgbe_mii_bus_init(struct ixgbe_hw *hw); + +s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw); +s32 ixgbe_reset_phy_generic(struct ixgbe_hw *hw); +s32 ixgbe_read_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u16 *phy_data); +s32 ixgbe_write_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u16 phy_data); +s32 ixgbe_read_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u16 *phy_data); +s32 ixgbe_write_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u16 phy_data); +s32 ixgbe_setup_phy_link_generic(struct ixgbe_hw *hw); +s32 ixgbe_setup_phy_link_speed_generic(struct ixgbe_hw *hw, + ixgbe_link_speed speed, + bool autoneg_wait_to_complete); +s32 ixgbe_get_copper_link_capabilities_generic(struct ixgbe_hw *hw, + ixgbe_link_speed *speed, + bool *autoneg); +bool ixgbe_check_reset_blocked(struct ixgbe_hw *hw); + +/* PHY specific */ +s32 ixgbe_check_phy_link_tnx(struct ixgbe_hw *hw, + ixgbe_link_speed *speed, + bool *link_up); +s32 ixgbe_setup_phy_link_tnx(struct ixgbe_hw *hw); + +s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw); +s32 ixgbe_set_copper_phy_power(struct ixgbe_hw *hw, bool on); +s32 ixgbe_identify_module_generic(struct ixgbe_hw *hw); +s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw); +s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, + u16 *list_offset, + u16 *data_offset); +s32 ixgbe_tn_check_overtemp(struct ixgbe_hw *hw); +s32 ixgbe_read_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 *data); +s32 ixgbe_read_i2c_byte_generic_unlocked(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 *data); +s32 ixgbe_write_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 data); +s32 ixgbe_write_i2c_byte_generic_unlocked(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 data); +s32 ixgbe_read_i2c_eeprom_generic(struct ixgbe_hw *hw, u8 byte_offset, + u8 *eeprom_data); +s32 ixgbe_read_i2c_sff8472_generic(struct ixgbe_hw *hw, u8 byte_offset, + u8 *sff8472_data); +s32 ixgbe_write_i2c_eeprom_generic(struct ixgbe_hw *hw, u8 byte_offset, + u8 eeprom_data); +s32 ixgbe_read_i2c_combined_generic_int(struct ixgbe_hw *, u8 addr, u16 reg, + u16 *val, bool lock); +s32 ixgbe_write_i2c_combined_generic_int(struct ixgbe_hw *, u8 addr, u16 reg, + u16 val, bool lock); +#endif /* _IXGBE_PHY_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c new file mode 100644 index 000000000..3eb2c0536 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -0,0 +1,1536 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#include "ixgbe.h" +#include <linux/ptp_classify.h> +#include <linux/clocksource.h> + +/* + * The 82599 and the X540 do not have true 64bit nanosecond scale + * counter registers. Instead, SYSTIME is defined by a fixed point + * system which allows the user to define the scale counter increment + * value at every level change of the oscillator driving the SYSTIME + * value. For both devices the TIMINCA:IV field defines this + * increment. On the X540 device, 31 bits are provided. However on the + * 82599 only provides 24 bits. The time unit is determined by the + * clock frequency of the oscillator in combination with the TIMINCA + * register. When these devices link at 10Gb the oscillator has a + * period of 6.4ns. In order to convert the scale counter into + * nanoseconds the cyclecounter and timecounter structures are + * used. The SYSTIME registers need to be converted to ns values by use + * of only a right shift (division by power of 2). The following math + * determines the largest incvalue that will fit into the available + * bits in the TIMINCA register. + * + * PeriodWidth: Number of bits to store the clock period + * MaxWidth: The maximum width value of the TIMINCA register + * Period: The clock period for the oscillator + * round(): discard the fractional portion of the calculation + * + * Period * [ 2 ^ ( MaxWidth - PeriodWidth ) ] + * + * For the X540, MaxWidth is 31 bits, and the base period is 6.4 ns + * For the 82599, MaxWidth is 24 bits, and the base period is 6.4 ns + * + * The period also changes based on the link speed: + * At 10Gb link or no link, the period remains the same. + * At 1Gb link, the period is multiplied by 10. (64ns) + * At 100Mb link, the period is multiplied by 100. (640ns) + * + * The calculated value allows us to right shift the SYSTIME register + * value in order to quickly convert it into a nanosecond clock, + * while allowing for the maximum possible adjustment value. + * + * These diagrams are only for the 10Gb link period + * + * SYSTIMEH SYSTIMEL + * +--------------+ +--------------+ + * X540 | 32 | | 1 | 3 | 28 | + * *--------------+ +--------------+ + * \________ 36 bits ______/ fract + * + * +--------------+ +--------------+ + * 82599 | 32 | | 8 | 3 | 21 | + * *--------------+ +--------------+ + * \________ 43 bits ______/ fract + * + * The 36 bit X540 SYSTIME overflows every + * 2^36 * 10^-9 / 60 = 1.14 minutes or 69 seconds + * + * The 43 bit 82599 SYSTIME overflows every + * 2^43 * 10^-9 / 3600 = 2.4 hours + */ +#define IXGBE_INCVAL_10GB 0x66666666 +#define IXGBE_INCVAL_1GB 0x40000000 +#define IXGBE_INCVAL_100 0x50000000 + +#define IXGBE_INCVAL_SHIFT_10GB 28 +#define IXGBE_INCVAL_SHIFT_1GB 24 +#define IXGBE_INCVAL_SHIFT_100 21 + +#define IXGBE_INCVAL_SHIFT_82599 7 +#define IXGBE_INCPER_SHIFT_82599 24 + +#define IXGBE_OVERFLOW_PERIOD (HZ * 30) +#define IXGBE_PTP_TX_TIMEOUT (HZ) + +/* We use our own definitions instead of NSEC_PER_SEC because we want to mark + * the value as a ULL to force precision when bit shifting. + */ +#define NS_PER_SEC 1000000000ULL +#define NS_PER_HALF_SEC 500000000ULL + +/* In contrast, the X550 controller has two registers, SYSTIMEH and SYSTIMEL + * which contain measurements of seconds and nanoseconds respectively. This + * matches the standard linux representation of time in the kernel. In addition, + * the X550 also has a SYSTIMER register which represents residue, or + * subnanosecond overflow adjustments. To control clock adjustment, the TIMINCA + * register is used, but it is unlike the X540 and 82599 devices. TIMINCA + * represents units of 2^-32 nanoseconds, and uses 31 bits for this, with the + * high bit representing whether the adjustent is positive or negative. Every + * clock cycle, the X550 will add 12.5 ns + TIMINCA which can result in a range + * of 12 to 13 nanoseconds adjustment. Unlike the 82599 and X540 devices, the + * X550's clock for purposes of SYSTIME generation is constant and not dependent + * on the link speed. + * + * SYSTIMEH SYSTIMEL SYSTIMER + * +--------------+ +--------------+ +-------------+ + * X550 | 32 | | 32 | | 32 | + * *--------------+ +--------------+ +-------------+ + * \____seconds___/ \_nanoseconds_/ \__2^-32 ns__/ + * + * This results in a full 96 bits to represent the clock, with 32 bits for + * seconds, 32 bits for nanoseconds (largest value is 0d999999999 or just under + * 1 second) and an additional 32 bits to measure sub nanosecond adjustments for + * underflow of adjustments. + * + * The 32 bits of seconds for the X550 overflows every + * 2^32 / ( 365.25 * 24 * 60 * 60 ) = ~136 years. + * + * In order to adjust the clock frequency for the X550, the TIMINCA register is + * provided. This register represents a + or minus nearly 0.5 ns adjustment to + * the base frequency. It is measured in 2^-32 ns units, with the high bit being + * the sign bit. This register enables software to calculate frequency + * adjustments and apply them directly to the clock rate. + * + * The math for converting ppb into TIMINCA values is fairly straightforward. + * TIMINCA value = ( Base_Frequency * ppb ) / 1000000000ULL + * + * This assumes that ppb is never high enough to create a value bigger than + * TIMINCA's 31 bits can store. This is ensured by the stack. Calculating this + * value is also simple. + * Max ppb = ( Max Adjustment / Base Frequency ) / 1000000000ULL + * + * For the X550, the Max adjustment is +/- 0.5 ns, and the base frequency is + * 12.5 nanoseconds. This means that the Max ppb is 39999999 + * Note: We subtract one in order to ensure no overflow, because the TIMINCA + * register can only hold slightly under 0.5 nanoseconds. + * + * Because TIMINCA is measured in 2^-32 ns units, we have to convert 12.5 ns + * into 2^-32 units, which is + * + * 12.5 * 2^32 = C80000000 + * + * Some revisions of hardware have a faster base frequency than the registers + * were defined for. To fix this, we use a timecounter structure with the + * proper mult and shift to convert the cycles into nanoseconds of time. + */ +#define IXGBE_X550_BASE_PERIOD 0xC80000000ULL +#define INCVALUE_MASK 0x7FFFFFFF +#define ISGN 0x80000000 +#define MAX_TIMADJ 0x7FFFFFFF + +/** + * ixgbe_ptp_setup_sdp_X540 + * @adapter: private adapter structure + * + * this function enables or disables the clock out feature on SDP0 for + * the X540 device. It will create a 1 second periodic output that can + * be used as the PPS (via an interrupt). + * + * It calculates when the system time will be on an exact second, and then + * aligns the start of the PPS signal to that value. + * + * This works by using the cycle counter shift and mult values in reverse, and + * assumes that the values we're shifting will not overflow. + */ +static void ixgbe_ptp_setup_sdp_X540(struct ixgbe_adapter *adapter) +{ + struct cyclecounter *cc = &adapter->hw_cc; + struct ixgbe_hw *hw = &adapter->hw; + u32 esdp, tsauxc, clktiml, clktimh, trgttiml, trgttimh, rem; + u64 ns = 0, clock_edge = 0, clock_period; + unsigned long flags; + + /* disable the pin first */ + IXGBE_WRITE_REG(hw, IXGBE_TSAUXC, 0x0); + IXGBE_WRITE_FLUSH(hw); + + if (!(adapter->flags2 & IXGBE_FLAG2_PTP_PPS_ENABLED)) + return; + + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + + /* enable the SDP0 pin as output, and connected to the + * native function for Timesync (ClockOut) + */ + esdp |= IXGBE_ESDP_SDP0_DIR | + IXGBE_ESDP_SDP0_NATIVE; + + /* enable the Clock Out feature on SDP0, and allow + * interrupts to occur when the pin changes + */ + tsauxc = (IXGBE_TSAUXC_EN_CLK | + IXGBE_TSAUXC_SYNCLK | + IXGBE_TSAUXC_SDP0_INT); + + /* Determine the clock time period to use. This assumes that the + * cycle counter shift is small enough to avoid overflow. + */ + clock_period = div_u64((NS_PER_HALF_SEC << cc->shift), cc->mult); + clktiml = (u32)(clock_period); + clktimh = (u32)(clock_period >> 32); + + /* Read the current clock time, and save the cycle counter value */ + spin_lock_irqsave(&adapter->tmreg_lock, flags); + ns = timecounter_read(&adapter->hw_tc); + clock_edge = adapter->hw_tc.cycle_last; + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + + /* Figure out how many seconds to add in order to round up */ + div_u64_rem(ns, NS_PER_SEC, &rem); + + /* Figure out how many nanoseconds to add to round the clock edge up + * to the next full second + */ + rem = (NS_PER_SEC - rem); + + /* Adjust the clock edge to align with the next full second. */ + clock_edge += div_u64(((u64)rem << cc->shift), cc->mult); + trgttiml = (u32)clock_edge; + trgttimh = (u32)(clock_edge >> 32); + + IXGBE_WRITE_REG(hw, IXGBE_CLKTIML, clktiml); + IXGBE_WRITE_REG(hw, IXGBE_CLKTIMH, clktimh); + IXGBE_WRITE_REG(hw, IXGBE_TRGTTIML0, trgttiml); + IXGBE_WRITE_REG(hw, IXGBE_TRGTTIMH0, trgttimh); + + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp); + IXGBE_WRITE_REG(hw, IXGBE_TSAUXC, tsauxc); + + IXGBE_WRITE_FLUSH(hw); +} + +/** + * ixgbe_ptp_setup_sdp_X550 + * @adapter: private adapter structure + * + * Enable or disable a clock output signal on SDP 0 for X550 hardware. + * + * Use the target time feature to align the output signal on the next full + * second. + * + * This works by using the cycle counter shift and mult values in reverse, and + * assumes that the values we're shifting will not overflow. + */ +static void ixgbe_ptp_setup_sdp_X550(struct ixgbe_adapter *adapter) +{ + u32 esdp, tsauxc, freqout, trgttiml, trgttimh, rem, tssdp; + struct cyclecounter *cc = &adapter->hw_cc; + struct ixgbe_hw *hw = &adapter->hw; + u64 ns = 0, clock_edge = 0; + struct timespec64 ts; + unsigned long flags; + + /* disable the pin first */ + IXGBE_WRITE_REG(hw, IXGBE_TSAUXC, 0x0); + IXGBE_WRITE_FLUSH(hw); + + if (!(adapter->flags2 & IXGBE_FLAG2_PTP_PPS_ENABLED)) + return; + + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + + /* enable the SDP0 pin as output, and connected to the + * native function for Timesync (ClockOut) + */ + esdp |= IXGBE_ESDP_SDP0_DIR | + IXGBE_ESDP_SDP0_NATIVE; + + /* enable the Clock Out feature on SDP0, and use Target Time 0 to + * enable generation of interrupts on the clock change. + */ +#define IXGBE_TSAUXC_DIS_TS_CLEAR 0x40000000 + tsauxc = (IXGBE_TSAUXC_EN_CLK | IXGBE_TSAUXC_ST0 | + IXGBE_TSAUXC_EN_TT0 | IXGBE_TSAUXC_SDP0_INT | + IXGBE_TSAUXC_DIS_TS_CLEAR); + + tssdp = (IXGBE_TSSDP_TS_SDP0_EN | + IXGBE_TSSDP_TS_SDP0_CLK0); + + /* Determine the clock time period to use. This assumes that the + * cycle counter shift is small enough to avoid overflowing a 32bit + * value. + */ + freqout = div_u64(NS_PER_HALF_SEC << cc->shift, cc->mult); + + /* Read the current clock time, and save the cycle counter value */ + spin_lock_irqsave(&adapter->tmreg_lock, flags); + ns = timecounter_read(&adapter->hw_tc); + clock_edge = adapter->hw_tc.cycle_last; + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + + /* Figure out how far past the next second we are */ + div_u64_rem(ns, NS_PER_SEC, &rem); + + /* Figure out how many nanoseconds to add to round the clock edge up + * to the next full second + */ + rem = (NS_PER_SEC - rem); + + /* Adjust the clock edge to align with the next full second. */ + clock_edge += div_u64(((u64)rem << cc->shift), cc->mult); + + /* X550 hardware stores the time in 32bits of 'billions of cycles' and + * 32bits of 'cycles'. There's no guarantee that cycles represents + * nanoseconds. However, we can use the math from a timespec64 to + * convert into the hardware representation. + * + * See ixgbe_ptp_read_X550() for more details. + */ + ts = ns_to_timespec64(clock_edge); + trgttiml = (u32)ts.tv_nsec; + trgttimh = (u32)ts.tv_sec; + + IXGBE_WRITE_REG(hw, IXGBE_FREQOUT0, freqout); + IXGBE_WRITE_REG(hw, IXGBE_TRGTTIML0, trgttiml); + IXGBE_WRITE_REG(hw, IXGBE_TRGTTIMH0, trgttimh); + + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp); + IXGBE_WRITE_REG(hw, IXGBE_TSSDP, tssdp); + IXGBE_WRITE_REG(hw, IXGBE_TSAUXC, tsauxc); + + IXGBE_WRITE_FLUSH(hw); +} + +/** + * ixgbe_ptp_read_X550 - read cycle counter value + * @cc: cyclecounter structure + * + * This function reads SYSTIME registers. It is called by the cyclecounter + * structure to convert from internal representation into nanoseconds. We need + * this for X550 since some skews do not have expected clock frequency and + * result of SYSTIME is 32bits of "billions of cycles" and 32 bits of + * "cycles", rather than seconds and nanoseconds. + */ +static u64 ixgbe_ptp_read_X550(const struct cyclecounter *cc) +{ + struct ixgbe_adapter *adapter = + container_of(cc, struct ixgbe_adapter, hw_cc); + struct ixgbe_hw *hw = &adapter->hw; + struct timespec64 ts; + + /* storage is 32 bits of 'billions of cycles' and 32 bits of 'cycles'. + * Some revisions of hardware run at a higher frequency and so the + * cycles are not guaranteed to be nanoseconds. The timespec64 created + * here is used for its math/conversions but does not necessarily + * represent nominal time. + * + * It should be noted that this cyclecounter will overflow at a + * non-bitmask field since we have to convert our billions of cycles + * into an actual cycles count. This results in some possible weird + * situations at high cycle counter stamps. However given that 32 bits + * of "seconds" is ~138 years this isn't a problem. Even at the + * increased frequency of some revisions, this is still ~103 years. + * Since the SYSTIME values start at 0 and we never write them, it is + * highly unlikely for the cyclecounter to overflow in practice. + */ + IXGBE_READ_REG(hw, IXGBE_SYSTIMR); + ts.tv_nsec = IXGBE_READ_REG(hw, IXGBE_SYSTIML); + ts.tv_sec = IXGBE_READ_REG(hw, IXGBE_SYSTIMH); + + return (u64)timespec64_to_ns(&ts); +} + +/** + * ixgbe_ptp_read_82599 - read raw cycle counter (to be used by time counter) + * @cc: the cyclecounter structure + * + * this function reads the cyclecounter registers and is called by the + * cyclecounter structure used to construct a ns counter from the + * arbitrary fixed point registers + */ +static u64 ixgbe_ptp_read_82599(const struct cyclecounter *cc) +{ + struct ixgbe_adapter *adapter = + container_of(cc, struct ixgbe_adapter, hw_cc); + struct ixgbe_hw *hw = &adapter->hw; + u64 stamp = 0; + + stamp |= (u64)IXGBE_READ_REG(hw, IXGBE_SYSTIML); + stamp |= (u64)IXGBE_READ_REG(hw, IXGBE_SYSTIMH) << 32; + + return stamp; +} + +/** + * ixgbe_ptp_convert_to_hwtstamp - convert register value to hw timestamp + * @adapter: private adapter structure + * @hwtstamp: stack timestamp structure + * @timestamp: unsigned 64bit system time value + * + * We need to convert the adapter's RX/TXSTMP registers into a hwtstamp value + * which can be used by the stack's ptp functions. + * + * The lock is used to protect consistency of the cyclecounter and the SYSTIME + * registers. However, it does not need to protect against the Rx or Tx + * timestamp registers, as there can't be a new timestamp until the old one is + * unlatched by reading. + * + * In addition to the timestamp in hardware, some controllers need a software + * overflow cyclecounter, and this function takes this into account as well. + **/ +static void ixgbe_ptp_convert_to_hwtstamp(struct ixgbe_adapter *adapter, + struct skb_shared_hwtstamps *hwtstamp, + u64 timestamp) +{ + unsigned long flags; + struct timespec64 systime; + u64 ns; + + memset(hwtstamp, 0, sizeof(*hwtstamp)); + + switch (adapter->hw.mac.type) { + /* X550 and later hardware supposedly represent time using a seconds + * and nanoseconds counter, instead of raw 64bits nanoseconds. We need + * to convert the timestamp into cycles before it can be fed to the + * cyclecounter. We need an actual cyclecounter because some revisions + * of hardware run at a higher frequency and thus the counter does + * not represent seconds/nanoseconds. Instead it can be thought of as + * cycles and billions of cycles. + */ + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + /* Upper 32 bits represent billions of cycles, lower 32 bits + * represent cycles. However, we use timespec64_to_ns for the + * correct math even though the units haven't been corrected + * yet. + */ + systime.tv_sec = timestamp >> 32; + systime.tv_nsec = timestamp & 0xFFFFFFFF; + + timestamp = timespec64_to_ns(&systime); + break; + default: + break; + } + + spin_lock_irqsave(&adapter->tmreg_lock, flags); + ns = timecounter_cyc2time(&adapter->hw_tc, timestamp); + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + + hwtstamp->hwtstamp = ns_to_ktime(ns); +} + +/** + * ixgbe_ptp_adjfreq_82599 + * @ptp: the ptp clock structure + * @ppb: parts per billion adjustment from base + * + * adjust the frequency of the ptp cycle counter by the + * indicated ppb from the base frequency. + */ +static int ixgbe_ptp_adjfreq_82599(struct ptp_clock_info *ptp, s32 ppb) +{ + struct ixgbe_adapter *adapter = + container_of(ptp, struct ixgbe_adapter, ptp_caps); + struct ixgbe_hw *hw = &adapter->hw; + u64 freq, incval; + u32 diff; + int neg_adj = 0; + + if (ppb < 0) { + neg_adj = 1; + ppb = -ppb; + } + + smp_mb(); + incval = READ_ONCE(adapter->base_incval); + + freq = incval; + freq *= ppb; + diff = div_u64(freq, 1000000000ULL); + + incval = neg_adj ? (incval - diff) : (incval + diff); + + switch (hw->mac.type) { + case ixgbe_mac_X540: + if (incval > 0xFFFFFFFFULL) + e_dev_warn("PTP ppb adjusted SYSTIME rate overflowed!\n"); + IXGBE_WRITE_REG(hw, IXGBE_TIMINCA, (u32)incval); + break; + case ixgbe_mac_82599EB: + if (incval > 0x00FFFFFFULL) + e_dev_warn("PTP ppb adjusted SYSTIME rate overflowed!\n"); + IXGBE_WRITE_REG(hw, IXGBE_TIMINCA, + BIT(IXGBE_INCPER_SHIFT_82599) | + ((u32)incval & 0x00FFFFFFUL)); + break; + default: + break; + } + + return 0; +} + +/** + * ixgbe_ptp_adjfreq_X550 + * @ptp: the ptp clock structure + * @ppb: parts per billion adjustment from base + * + * adjust the frequency of the SYSTIME registers by the indicated ppb from base + * frequency + */ +static int ixgbe_ptp_adjfreq_X550(struct ptp_clock_info *ptp, s32 ppb) +{ + struct ixgbe_adapter *adapter = + container_of(ptp, struct ixgbe_adapter, ptp_caps); + struct ixgbe_hw *hw = &adapter->hw; + int neg_adj = 0; + u64 rate = IXGBE_X550_BASE_PERIOD; + u32 inca; + + if (ppb < 0) { + neg_adj = 1; + ppb = -ppb; + } + rate *= ppb; + rate = div_u64(rate, 1000000000ULL); + + /* warn if rate is too large */ + if (rate >= INCVALUE_MASK) + e_dev_warn("PTP ppb adjusted SYSTIME rate overflowed!\n"); + + inca = rate & INCVALUE_MASK; + if (neg_adj) + inca |= ISGN; + + IXGBE_WRITE_REG(hw, IXGBE_TIMINCA, inca); + + return 0; +} + +/** + * ixgbe_ptp_adjtime + * @ptp: the ptp clock structure + * @delta: offset to adjust the cycle counter by + * + * adjust the timer by resetting the timecounter structure. + */ +static int ixgbe_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct ixgbe_adapter *adapter = + container_of(ptp, struct ixgbe_adapter, ptp_caps); + unsigned long flags; + + spin_lock_irqsave(&adapter->tmreg_lock, flags); + timecounter_adjtime(&adapter->hw_tc, delta); + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + + if (adapter->ptp_setup_sdp) + adapter->ptp_setup_sdp(adapter); + + return 0; +} + +/** + * ixgbe_ptp_gettimex + * @ptp: the ptp clock structure + * @ts: timespec to hold the PHC timestamp + * @sts: structure to hold the system time before and after reading the PHC + * + * read the timecounter and return the correct value on ns, + * after converting it into a struct timespec. + */ +static int ixgbe_ptp_gettimex(struct ptp_clock_info *ptp, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + struct ixgbe_adapter *adapter = + container_of(ptp, struct ixgbe_adapter, ptp_caps); + struct ixgbe_hw *hw = &adapter->hw; + unsigned long flags; + u64 ns, stamp; + + spin_lock_irqsave(&adapter->tmreg_lock, flags); + + switch (adapter->hw.mac.type) { + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + /* Upper 32 bits represent billions of cycles, lower 32 bits + * represent cycles. However, we use timespec64_to_ns for the + * correct math even though the units haven't been corrected + * yet. + */ + ptp_read_system_prets(sts); + IXGBE_READ_REG(hw, IXGBE_SYSTIMR); + ptp_read_system_postts(sts); + ts->tv_nsec = IXGBE_READ_REG(hw, IXGBE_SYSTIML); + ts->tv_sec = IXGBE_READ_REG(hw, IXGBE_SYSTIMH); + stamp = timespec64_to_ns(ts); + break; + default: + ptp_read_system_prets(sts); + stamp = IXGBE_READ_REG(hw, IXGBE_SYSTIML); + ptp_read_system_postts(sts); + stamp |= (u64)IXGBE_READ_REG(hw, IXGBE_SYSTIMH) << 32; + break; + } + + ns = timecounter_cyc2time(&adapter->hw_tc, stamp); + + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + + *ts = ns_to_timespec64(ns); + + return 0; +} + +/** + * ixgbe_ptp_settime + * @ptp: the ptp clock structure + * @ts: the timespec containing the new time for the cycle counter + * + * reset the timecounter to use a new base value instead of the kernel + * wall timer value. + */ +static int ixgbe_ptp_settime(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct ixgbe_adapter *adapter = + container_of(ptp, struct ixgbe_adapter, ptp_caps); + unsigned long flags; + u64 ns = timespec64_to_ns(ts); + + /* reset the timecounter */ + spin_lock_irqsave(&adapter->tmreg_lock, flags); + timecounter_init(&adapter->hw_tc, &adapter->hw_cc, ns); + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + + if (adapter->ptp_setup_sdp) + adapter->ptp_setup_sdp(adapter); + return 0; +} + +/** + * ixgbe_ptp_feature_enable + * @ptp: the ptp clock structure + * @rq: the requested feature to change + * @on: whether to enable or disable the feature + * + * enable (or disable) ancillary features of the phc subsystem. + * our driver only supports the PPS feature on the X540 + */ +static int ixgbe_ptp_feature_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on) +{ + struct ixgbe_adapter *adapter = + container_of(ptp, struct ixgbe_adapter, ptp_caps); + + /** + * When PPS is enabled, unmask the interrupt for the ClockOut + * feature, so that the interrupt handler can send the PPS + * event when the clock SDP triggers. Clear mask when PPS is + * disabled + */ + if (rq->type != PTP_CLK_REQ_PPS || !adapter->ptp_setup_sdp) + return -ENOTSUPP; + + if (on) + adapter->flags2 |= IXGBE_FLAG2_PTP_PPS_ENABLED; + else + adapter->flags2 &= ~IXGBE_FLAG2_PTP_PPS_ENABLED; + + adapter->ptp_setup_sdp(adapter); + return 0; +} + +/** + * ixgbe_ptp_check_pps_event + * @adapter: the private adapter structure + * + * This function is called by the interrupt routine when checking for + * interrupts. It will check and handle a pps event. + */ +void ixgbe_ptp_check_pps_event(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct ptp_clock_event event; + + event.type = PTP_CLOCK_PPS; + + /* this check is necessary in case the interrupt was enabled via some + * alternative means (ex. debug_fs). Better to check here than + * everywhere that calls this function. + */ + if (!adapter->ptp_clock) + return; + + switch (hw->mac.type) { + case ixgbe_mac_X540: + ptp_clock_event(adapter->ptp_clock, &event); + break; + default: + break; + } +} + +/** + * ixgbe_ptp_overflow_check - watchdog task to detect SYSTIME overflow + * @adapter: private adapter struct + * + * this watchdog task periodically reads the timecounter + * in order to prevent missing when the system time registers wrap + * around. This needs to be run approximately twice a minute. + */ +void ixgbe_ptp_overflow_check(struct ixgbe_adapter *adapter) +{ + bool timeout = time_is_before_jiffies(adapter->last_overflow_check + + IXGBE_OVERFLOW_PERIOD); + unsigned long flags; + + if (timeout) { + /* Update the timecounter */ + spin_lock_irqsave(&adapter->tmreg_lock, flags); + timecounter_read(&adapter->hw_tc); + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + + adapter->last_overflow_check = jiffies; + } +} + +/** + * ixgbe_ptp_rx_hang - detect error case when Rx timestamp registers latched + * @adapter: private network adapter structure + * + * this watchdog task is scheduled to detect error case where hardware has + * dropped an Rx packet that was timestamped when the ring is full. The + * particular error is rare but leaves the device in a state unable to timestamp + * any future packets. + */ +void ixgbe_ptp_rx_hang(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 tsyncrxctl = IXGBE_READ_REG(hw, IXGBE_TSYNCRXCTL); + struct ixgbe_ring *rx_ring; + unsigned long rx_event; + int n; + + /* if we don't have a valid timestamp in the registers, just update the + * timeout counter and exit + */ + if (!(tsyncrxctl & IXGBE_TSYNCRXCTL_VALID)) { + adapter->last_rx_ptp_check = jiffies; + return; + } + + /* determine the most recent watchdog or rx_timestamp event */ + rx_event = adapter->last_rx_ptp_check; + for (n = 0; n < adapter->num_rx_queues; n++) { + rx_ring = adapter->rx_ring[n]; + if (time_after(rx_ring->last_rx_timestamp, rx_event)) + rx_event = rx_ring->last_rx_timestamp; + } + + /* only need to read the high RXSTMP register to clear the lock */ + if (time_is_before_jiffies(rx_event + 5 * HZ)) { + IXGBE_READ_REG(hw, IXGBE_RXSTMPH); + adapter->last_rx_ptp_check = jiffies; + + adapter->rx_hwtstamp_cleared++; + e_warn(drv, "clearing RX Timestamp hang\n"); + } +} + +/** + * ixgbe_ptp_clear_tx_timestamp - utility function to clear Tx timestamp state + * @adapter: the private adapter structure + * + * This function should be called whenever the state related to a Tx timestamp + * needs to be cleared. This helps ensure that all related bits are reset for + * the next Tx timestamp event. + */ +static void ixgbe_ptp_clear_tx_timestamp(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + + IXGBE_READ_REG(hw, IXGBE_TXSTMPH); + if (adapter->ptp_tx_skb) { + dev_kfree_skb_any(adapter->ptp_tx_skb); + adapter->ptp_tx_skb = NULL; + } + clear_bit_unlock(__IXGBE_PTP_TX_IN_PROGRESS, &adapter->state); +} + +/** + * ixgbe_ptp_tx_hang - detect error case where Tx timestamp never finishes + * @adapter: private network adapter structure + */ +void ixgbe_ptp_tx_hang(struct ixgbe_adapter *adapter) +{ + bool timeout = time_is_before_jiffies(adapter->ptp_tx_start + + IXGBE_PTP_TX_TIMEOUT); + + if (!adapter->ptp_tx_skb) + return; + + if (!test_bit(__IXGBE_PTP_TX_IN_PROGRESS, &adapter->state)) + return; + + /* If we haven't received a timestamp within the timeout, it is + * reasonable to assume that it will never occur, so we can unlock the + * timestamp bit when this occurs. + */ + if (timeout) { + cancel_work_sync(&adapter->ptp_tx_work); + ixgbe_ptp_clear_tx_timestamp(adapter); + adapter->tx_hwtstamp_timeouts++; + e_warn(drv, "clearing Tx timestamp hang\n"); + } +} + +/** + * ixgbe_ptp_tx_hwtstamp - utility function which checks for TX time stamp + * @adapter: the private adapter struct + * + * if the timestamp is valid, we convert it into the timecounter ns + * value, then store that result into the shhwtstamps structure which + * is passed up the network stack + */ +static void ixgbe_ptp_tx_hwtstamp(struct ixgbe_adapter *adapter) +{ + struct sk_buff *skb = adapter->ptp_tx_skb; + struct ixgbe_hw *hw = &adapter->hw; + struct skb_shared_hwtstamps shhwtstamps; + u64 regval = 0; + + regval |= (u64)IXGBE_READ_REG(hw, IXGBE_TXSTMPL); + regval |= (u64)IXGBE_READ_REG(hw, IXGBE_TXSTMPH) << 32; + ixgbe_ptp_convert_to_hwtstamp(adapter, &shhwtstamps, regval); + + /* Handle cleanup of the ptp_tx_skb ourselves, and unlock the state + * bit prior to notifying the stack via skb_tstamp_tx(). This prevents + * well behaved applications from attempting to timestamp again prior + * to the lock bit being clear. + */ + adapter->ptp_tx_skb = NULL; + clear_bit_unlock(__IXGBE_PTP_TX_IN_PROGRESS, &adapter->state); + + /* Notify the stack and then free the skb after we've unlocked */ + skb_tstamp_tx(skb, &shhwtstamps); + dev_kfree_skb_any(skb); +} + +/** + * ixgbe_ptp_tx_hwtstamp_work + * @work: pointer to the work struct + * + * This work item polls TSYNCTXCTL valid bit to determine when a Tx hardware + * timestamp has been taken for the current skb. It is necessary, because the + * descriptor's "done" bit does not correlate with the timestamp event. + */ +static void ixgbe_ptp_tx_hwtstamp_work(struct work_struct *work) +{ + struct ixgbe_adapter *adapter = container_of(work, struct ixgbe_adapter, + ptp_tx_work); + struct ixgbe_hw *hw = &adapter->hw; + bool timeout = time_is_before_jiffies(adapter->ptp_tx_start + + IXGBE_PTP_TX_TIMEOUT); + u32 tsynctxctl; + + /* we have to have a valid skb to poll for a timestamp */ + if (!adapter->ptp_tx_skb) { + ixgbe_ptp_clear_tx_timestamp(adapter); + return; + } + + /* stop polling once we have a valid timestamp */ + tsynctxctl = IXGBE_READ_REG(hw, IXGBE_TSYNCTXCTL); + if (tsynctxctl & IXGBE_TSYNCTXCTL_VALID) { + ixgbe_ptp_tx_hwtstamp(adapter); + return; + } + + if (timeout) { + ixgbe_ptp_clear_tx_timestamp(adapter); + adapter->tx_hwtstamp_timeouts++; + e_warn(drv, "clearing Tx Timestamp hang\n"); + } else { + /* reschedule to keep checking if it's not available yet */ + schedule_work(&adapter->ptp_tx_work); + } +} + +/** + * ixgbe_ptp_rx_pktstamp - utility function to get RX time stamp from buffer + * @q_vector: structure containing interrupt and ring information + * @skb: the packet + * + * This function will be called by the Rx routine of the timestamp for this + * packet is stored in the buffer. The value is stored in little endian format + * starting at the end of the packet data. + */ +void ixgbe_ptp_rx_pktstamp(struct ixgbe_q_vector *q_vector, + struct sk_buff *skb) +{ + __le64 regval; + + /* copy the bits out of the skb, and then trim the skb length */ + skb_copy_bits(skb, skb->len - IXGBE_TS_HDR_LEN, ®val, + IXGBE_TS_HDR_LEN); + __pskb_trim(skb, skb->len - IXGBE_TS_HDR_LEN); + + /* The timestamp is recorded in little endian format, and is stored at + * the end of the packet. + * + * DWORD: N N + 1 N + 2 + * Field: End of Packet SYSTIMH SYSTIML + */ + ixgbe_ptp_convert_to_hwtstamp(q_vector->adapter, skb_hwtstamps(skb), + le64_to_cpu(regval)); +} + +/** + * ixgbe_ptp_rx_rgtstamp - utility function which checks for RX time stamp + * @q_vector: structure containing interrupt and ring information + * @skb: particular skb to send timestamp with + * + * if the timestamp is valid, we convert it into the timecounter ns + * value, then store that result into the shhwtstamps structure which + * is passed up the network stack + */ +void ixgbe_ptp_rx_rgtstamp(struct ixgbe_q_vector *q_vector, + struct sk_buff *skb) +{ + struct ixgbe_adapter *adapter; + struct ixgbe_hw *hw; + u64 regval = 0; + u32 tsyncrxctl; + + /* we cannot process timestamps on a ring without a q_vector */ + if (!q_vector || !q_vector->adapter) + return; + + adapter = q_vector->adapter; + hw = &adapter->hw; + + /* Read the tsyncrxctl register afterwards in order to prevent taking an + * I/O hit on every packet. + */ + + tsyncrxctl = IXGBE_READ_REG(hw, IXGBE_TSYNCRXCTL); + if (!(tsyncrxctl & IXGBE_TSYNCRXCTL_VALID)) + return; + + regval |= (u64)IXGBE_READ_REG(hw, IXGBE_RXSTMPL); + regval |= (u64)IXGBE_READ_REG(hw, IXGBE_RXSTMPH) << 32; + + ixgbe_ptp_convert_to_hwtstamp(adapter, skb_hwtstamps(skb), regval); +} + +/** + * ixgbe_ptp_get_ts_config - get current hardware timestamping configuration + * @adapter: pointer to adapter structure + * @ifr: ioctl data + * + * This function returns the current timestamping settings. Rather than + * attempt to deconstruct registers to fill in the values, simply keep a copy + * of the old settings around, and return a copy when requested. + */ +int ixgbe_ptp_get_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr) +{ + struct hwtstamp_config *config = &adapter->tstamp_config; + + return copy_to_user(ifr->ifr_data, config, + sizeof(*config)) ? -EFAULT : 0; +} + +/** + * ixgbe_ptp_set_timestamp_mode - setup the hardware for the requested mode + * @adapter: the private ixgbe adapter structure + * @config: the hwtstamp configuration requested + * + * Outgoing time stamping can be enabled and disabled. Play nice and + * disable it when requested, although it shouldn't cause any overhead + * when no packet needs it. At most one packet in the queue may be + * marked for time stamping, otherwise it would be impossible to tell + * for sure to which packet the hardware time stamp belongs. + * + * Incoming time stamping has to be configured via the hardware + * filters. Not all combinations are supported, in particular event + * type has to be specified. Matching the kind of event packet is + * not supported, with the exception of "all V2 events regardless of + * level 2 or 4". + * + * Since hardware always timestamps Path delay packets when timestamping V2 + * packets, regardless of the type specified in the register, only use V2 + * Event mode. This more accurately tells the user what the hardware is going + * to do anyways. + * + * Note: this may modify the hwtstamp configuration towards a more general + * mode, if required to support the specifically requested mode. + */ +static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, + struct hwtstamp_config *config) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 tsync_tx_ctl = IXGBE_TSYNCTXCTL_ENABLED; + u32 tsync_rx_ctl = IXGBE_TSYNCRXCTL_ENABLED; + u32 tsync_rx_mtrl = PTP_EV_PORT << 16; + u32 aflags = adapter->flags; + bool is_l2 = false; + u32 regval; + + /* reserved for future extensions */ + if (config->flags) + return -EINVAL; + + switch (config->tx_type) { + case HWTSTAMP_TX_OFF: + tsync_tx_ctl = 0; + case HWTSTAMP_TX_ON: + break; + default: + return -ERANGE; + } + + switch (config->rx_filter) { + case HWTSTAMP_FILTER_NONE: + tsync_rx_ctl = 0; + tsync_rx_mtrl = 0; + aflags &= ~(IXGBE_FLAG_RX_HWTSTAMP_ENABLED | + IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); + break; + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L4_V1; + tsync_rx_mtrl |= IXGBE_RXMTRL_V1_SYNC_MSG; + aflags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED | + IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); + break; + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L4_V1; + tsync_rx_mtrl |= IXGBE_RXMTRL_V1_DELAY_REQ_MSG; + aflags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED | + IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); + break; + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_EVENT_V2; + is_l2 = true; + config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + aflags |= (IXGBE_FLAG_RX_HWTSTAMP_ENABLED | + IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); + break; + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_NTP_ALL: + case HWTSTAMP_FILTER_ALL: + /* The X550 controller is capable of timestamping all packets, + * which allows it to accept any filter. + */ + if (hw->mac.type >= ixgbe_mac_X550) { + tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_ALL; + config->rx_filter = HWTSTAMP_FILTER_ALL; + aflags |= IXGBE_FLAG_RX_HWTSTAMP_ENABLED; + break; + } + fallthrough; + default: + /* + * register RXMTRL must be set in order to do V1 packets, + * therefore it is not possible to time stamp both V1 Sync and + * Delay_Req messages and hardware does not support + * timestamping all packets => return error + */ + config->rx_filter = HWTSTAMP_FILTER_NONE; + return -ERANGE; + } + + if (hw->mac.type == ixgbe_mac_82598EB) { + adapter->flags &= ~(IXGBE_FLAG_RX_HWTSTAMP_ENABLED | + IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER); + if (tsync_rx_ctl | tsync_tx_ctl) + return -ERANGE; + return 0; + } + + /* Per-packet timestamping only works if the filter is set to all + * packets. Since this is desired, always timestamp all packets as long + * as any Rx filter was configured. + */ + switch (hw->mac.type) { + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + /* enable timestamping all packets only if at least some + * packets were requested. Otherwise, play nice and disable + * timestamping + */ + if (config->rx_filter == HWTSTAMP_FILTER_NONE) + break; + + tsync_rx_ctl = IXGBE_TSYNCRXCTL_ENABLED | + IXGBE_TSYNCRXCTL_TYPE_ALL | + IXGBE_TSYNCRXCTL_TSIP_UT_EN; + config->rx_filter = HWTSTAMP_FILTER_ALL; + aflags |= IXGBE_FLAG_RX_HWTSTAMP_ENABLED; + aflags &= ~IXGBE_FLAG_RX_HWTSTAMP_IN_REGISTER; + is_l2 = true; + break; + default: + break; + } + + /* define ethertype filter for timestamping L2 packets */ + if (is_l2) + IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_1588), + (IXGBE_ETQF_FILTER_EN | /* enable filter */ + IXGBE_ETQF_1588 | /* enable timestamping */ + ETH_P_1588)); /* 1588 eth protocol type */ + else + IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_1588), 0); + + /* enable/disable TX */ + regval = IXGBE_READ_REG(hw, IXGBE_TSYNCTXCTL); + regval &= ~IXGBE_TSYNCTXCTL_ENABLED; + regval |= tsync_tx_ctl; + IXGBE_WRITE_REG(hw, IXGBE_TSYNCTXCTL, regval); + + /* enable/disable RX */ + regval = IXGBE_READ_REG(hw, IXGBE_TSYNCRXCTL); + regval &= ~(IXGBE_TSYNCRXCTL_ENABLED | IXGBE_TSYNCRXCTL_TYPE_MASK); + regval |= tsync_rx_ctl; + IXGBE_WRITE_REG(hw, IXGBE_TSYNCRXCTL, regval); + + /* define which PTP packets are time stamped */ + IXGBE_WRITE_REG(hw, IXGBE_RXMTRL, tsync_rx_mtrl); + + IXGBE_WRITE_FLUSH(hw); + + /* configure adapter flags only when HW is actually configured */ + adapter->flags = aflags; + + /* clear TX/RX time stamp registers, just to be sure */ + ixgbe_ptp_clear_tx_timestamp(adapter); + IXGBE_READ_REG(hw, IXGBE_RXSTMPH); + + return 0; +} + +/** + * ixgbe_ptp_set_ts_config - user entry point for timestamp mode + * @adapter: pointer to adapter struct + * @ifr: ioctl data + * + * Set hardware to requested mode. If unsupported, return an error with no + * changes. Otherwise, store the mode for future reference. + */ +int ixgbe_ptp_set_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr) +{ + struct hwtstamp_config config; + int err; + + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) + return -EFAULT; + + err = ixgbe_ptp_set_timestamp_mode(adapter, &config); + if (err) + return err; + + /* save these settings for future reference */ + memcpy(&adapter->tstamp_config, &config, + sizeof(adapter->tstamp_config)); + + return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? + -EFAULT : 0; +} + +static void ixgbe_ptp_link_speed_adjust(struct ixgbe_adapter *adapter, + u32 *shift, u32 *incval) +{ + /** + * Scale the NIC cycle counter by a large factor so that + * relatively small corrections to the frequency can be added + * or subtracted. The drawbacks of a large factor include + * (a) the clock register overflows more quickly, (b) the cycle + * counter structure must be able to convert the systime value + * to nanoseconds using only a multiplier and a right-shift, + * and (c) the value must fit within the timinca register space + * => math based on internal DMA clock rate and available bits + * + * Note that when there is no link, internal DMA clock is same as when + * link speed is 10Gb. Set the registers correctly even when link is + * down to preserve the clock setting + */ + switch (adapter->link_speed) { + case IXGBE_LINK_SPEED_100_FULL: + *shift = IXGBE_INCVAL_SHIFT_100; + *incval = IXGBE_INCVAL_100; + break; + case IXGBE_LINK_SPEED_1GB_FULL: + *shift = IXGBE_INCVAL_SHIFT_1GB; + *incval = IXGBE_INCVAL_1GB; + break; + case IXGBE_LINK_SPEED_10GB_FULL: + default: + *shift = IXGBE_INCVAL_SHIFT_10GB; + *incval = IXGBE_INCVAL_10GB; + break; + } +} + +/** + * ixgbe_ptp_start_cyclecounter - create the cycle counter from hw + * @adapter: pointer to the adapter structure + * + * This function should be called to set the proper values for the TIMINCA + * register and tell the cyclecounter structure what the tick rate of SYSTIME + * is. It does not directly modify SYSTIME registers or the timecounter + * structure. It should be called whenever a new TIMINCA value is necessary, + * such as during initialization or when the link speed changes. + */ +void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct cyclecounter cc; + unsigned long flags; + u32 incval = 0; + u32 fuse0 = 0; + + /* For some of the boards below this mask is technically incorrect. + * The timestamp mask overflows at approximately 61bits. However the + * particular hardware does not overflow on an even bitmask value. + * Instead, it overflows due to conversion of upper 32bits billions of + * cycles. Timecounters are not really intended for this purpose so + * they do not properly function if the overflow point isn't 2^N-1. + * However, the actual SYSTIME values in question take ~138 years to + * overflow. In practice this means they won't actually overflow. A + * proper fix to this problem would require modification of the + * timecounter delta calculations. + */ + cc.mask = CLOCKSOURCE_MASK(64); + cc.mult = 1; + cc.shift = 0; + + switch (hw->mac.type) { + case ixgbe_mac_X550EM_x: + /* SYSTIME assumes X550EM_x board frequency is 300Mhz, and is + * designed to represent seconds and nanoseconds when this is + * the case. However, some revisions of hardware have a 400Mhz + * clock and we have to compensate for this frequency + * variation using corrected mult and shift values. + */ + fuse0 = IXGBE_READ_REG(hw, IXGBE_FUSES0_GROUP(0)); + if (!(fuse0 & IXGBE_FUSES0_300MHZ)) { + cc.mult = 3; + cc.shift = 2; + } + fallthrough; + case ixgbe_mac_x550em_a: + case ixgbe_mac_X550: + cc.read = ixgbe_ptp_read_X550; + break; + case ixgbe_mac_X540: + cc.read = ixgbe_ptp_read_82599; + + ixgbe_ptp_link_speed_adjust(adapter, &cc.shift, &incval); + IXGBE_WRITE_REG(hw, IXGBE_TIMINCA, incval); + break; + case ixgbe_mac_82599EB: + cc.read = ixgbe_ptp_read_82599; + + ixgbe_ptp_link_speed_adjust(adapter, &cc.shift, &incval); + incval >>= IXGBE_INCVAL_SHIFT_82599; + cc.shift -= IXGBE_INCVAL_SHIFT_82599; + IXGBE_WRITE_REG(hw, IXGBE_TIMINCA, + BIT(IXGBE_INCPER_SHIFT_82599) | incval); + break; + default: + /* other devices aren't supported */ + return; + } + + /* update the base incval used to calculate frequency adjustment */ + WRITE_ONCE(adapter->base_incval, incval); + smp_mb(); + + /* need lock to prevent incorrect read while modifying cyclecounter */ + spin_lock_irqsave(&adapter->tmreg_lock, flags); + memcpy(&adapter->hw_cc, &cc, sizeof(adapter->hw_cc)); + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); +} + +/** + * ixgbe_ptp_init_systime - Initialize SYSTIME registers + * @adapter: the ixgbe private board structure + * + * Initialize and start the SYSTIME registers. + */ +static void ixgbe_ptp_init_systime(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 tsauxc; + + switch (hw->mac.type) { + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + case ixgbe_mac_X550: + tsauxc = IXGBE_READ_REG(hw, IXGBE_TSAUXC); + + /* Reset SYSTIME registers to 0 */ + IXGBE_WRITE_REG(hw, IXGBE_SYSTIMR, 0); + IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0); + IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0); + + /* Reset interrupt settings */ + IXGBE_WRITE_REG(hw, IXGBE_TSIM, IXGBE_TSIM_TXTS); + IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_TIMESYNC); + + /* Activate the SYSTIME counter */ + IXGBE_WRITE_REG(hw, IXGBE_TSAUXC, + tsauxc & ~IXGBE_TSAUXC_DISABLE_SYSTIME); + break; + case ixgbe_mac_X540: + case ixgbe_mac_82599EB: + /* Reset SYSTIME registers to 0 */ + IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0); + IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0); + break; + default: + /* Other devices aren't supported */ + return; + }; + + IXGBE_WRITE_FLUSH(hw); +} + +/** + * ixgbe_ptp_reset + * @adapter: the ixgbe private board structure + * + * When the MAC resets, all the hardware bits for timesync are reset. This + * function is used to re-enable the device for PTP based on current settings. + * We do lose the current clock time, so just reset the cyclecounter to the + * system real clock time. + * + * This function will maintain hwtstamp_config settings, and resets the SDP + * output if it was enabled. + */ +void ixgbe_ptp_reset(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + unsigned long flags; + + /* reset the hardware timestamping mode */ + ixgbe_ptp_set_timestamp_mode(adapter, &adapter->tstamp_config); + + /* 82598 does not support PTP */ + if (hw->mac.type == ixgbe_mac_82598EB) + return; + + ixgbe_ptp_start_cyclecounter(adapter); + + ixgbe_ptp_init_systime(adapter); + + spin_lock_irqsave(&adapter->tmreg_lock, flags); + timecounter_init(&adapter->hw_tc, &adapter->hw_cc, + ktime_to_ns(ktime_get_real())); + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + + adapter->last_overflow_check = jiffies; + + /* Now that the shift has been calculated and the systime + * registers reset, (re-)enable the Clock out feature + */ + if (adapter->ptp_setup_sdp) + adapter->ptp_setup_sdp(adapter); +} + +/** + * ixgbe_ptp_create_clock + * @adapter: the ixgbe private adapter structure + * + * This function performs setup of the user entry point function table and + * initializes the PTP clock device, which is used to access the clock-like + * features of the PTP core. It will be called by ixgbe_ptp_init, and may + * reuse a previously initialized clock (such as during a suspend/resume + * cycle). + */ +static long ixgbe_ptp_create_clock(struct ixgbe_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + long err; + + /* do nothing if we already have a clock device */ + if (!IS_ERR_OR_NULL(adapter->ptp_clock)) + return 0; + + switch (adapter->hw.mac.type) { + case ixgbe_mac_X540: + snprintf(adapter->ptp_caps.name, + sizeof(adapter->ptp_caps.name), + "%s", netdev->name); + adapter->ptp_caps.owner = THIS_MODULE; + adapter->ptp_caps.max_adj = 250000000; + adapter->ptp_caps.n_alarm = 0; + adapter->ptp_caps.n_ext_ts = 0; + adapter->ptp_caps.n_per_out = 0; + adapter->ptp_caps.pps = 1; + adapter->ptp_caps.adjfreq = ixgbe_ptp_adjfreq_82599; + adapter->ptp_caps.adjtime = ixgbe_ptp_adjtime; + adapter->ptp_caps.gettimex64 = ixgbe_ptp_gettimex; + adapter->ptp_caps.settime64 = ixgbe_ptp_settime; + adapter->ptp_caps.enable = ixgbe_ptp_feature_enable; + adapter->ptp_setup_sdp = ixgbe_ptp_setup_sdp_X540; + break; + case ixgbe_mac_82599EB: + snprintf(adapter->ptp_caps.name, + sizeof(adapter->ptp_caps.name), + "%s", netdev->name); + adapter->ptp_caps.owner = THIS_MODULE; + adapter->ptp_caps.max_adj = 250000000; + adapter->ptp_caps.n_alarm = 0; + adapter->ptp_caps.n_ext_ts = 0; + adapter->ptp_caps.n_per_out = 0; + adapter->ptp_caps.pps = 0; + adapter->ptp_caps.adjfreq = ixgbe_ptp_adjfreq_82599; + adapter->ptp_caps.adjtime = ixgbe_ptp_adjtime; + adapter->ptp_caps.gettimex64 = ixgbe_ptp_gettimex; + adapter->ptp_caps.settime64 = ixgbe_ptp_settime; + adapter->ptp_caps.enable = ixgbe_ptp_feature_enable; + break; + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + snprintf(adapter->ptp_caps.name, 16, "%s", netdev->name); + adapter->ptp_caps.owner = THIS_MODULE; + adapter->ptp_caps.max_adj = 30000000; + adapter->ptp_caps.n_alarm = 0; + adapter->ptp_caps.n_ext_ts = 0; + adapter->ptp_caps.n_per_out = 0; + adapter->ptp_caps.pps = 1; + adapter->ptp_caps.adjfreq = ixgbe_ptp_adjfreq_X550; + adapter->ptp_caps.adjtime = ixgbe_ptp_adjtime; + adapter->ptp_caps.gettimex64 = ixgbe_ptp_gettimex; + adapter->ptp_caps.settime64 = ixgbe_ptp_settime; + adapter->ptp_caps.enable = ixgbe_ptp_feature_enable; + adapter->ptp_setup_sdp = ixgbe_ptp_setup_sdp_X550; + break; + default: + adapter->ptp_clock = NULL; + adapter->ptp_setup_sdp = NULL; + return -EOPNOTSUPP; + } + + adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps, + &adapter->pdev->dev); + if (IS_ERR(adapter->ptp_clock)) { + err = PTR_ERR(adapter->ptp_clock); + adapter->ptp_clock = NULL; + e_dev_err("ptp_clock_register failed\n"); + return err; + } else if (adapter->ptp_clock) + e_dev_info("registered PHC device on %s\n", netdev->name); + + /* set default timestamp mode to disabled here. We do this in + * create_clock instead of init, because we don't want to override the + * previous settings during a resume cycle. + */ + adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; + adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF; + + return 0; +} + +/** + * ixgbe_ptp_init + * @adapter: the ixgbe private adapter structure + * + * This function performs the required steps for enabling PTP + * support. If PTP support has already been loaded it simply calls the + * cyclecounter init routine and exits. + */ +void ixgbe_ptp_init(struct ixgbe_adapter *adapter) +{ + /* initialize the spin lock first since we can't control when a user + * will call the entry functions once we have initialized the clock + * device + */ + spin_lock_init(&adapter->tmreg_lock); + + /* obtain a PTP device, or re-use an existing device */ + if (ixgbe_ptp_create_clock(adapter)) + return; + + /* we have a clock so we can initialize work now */ + INIT_WORK(&adapter->ptp_tx_work, ixgbe_ptp_tx_hwtstamp_work); + + /* reset the PTP related hardware bits */ + ixgbe_ptp_reset(adapter); + + /* enter the IXGBE_PTP_RUNNING state */ + set_bit(__IXGBE_PTP_RUNNING, &adapter->state); + + return; +} + +/** + * ixgbe_ptp_suspend - stop PTP work items + * @adapter: pointer to adapter struct + * + * this function suspends PTP activity, and prevents more PTP work from being + * generated, but does not destroy the PTP clock device. + */ +void ixgbe_ptp_suspend(struct ixgbe_adapter *adapter) +{ + /* Leave the IXGBE_PTP_RUNNING state. */ + if (!test_and_clear_bit(__IXGBE_PTP_RUNNING, &adapter->state)) + return; + + adapter->flags2 &= ~IXGBE_FLAG2_PTP_PPS_ENABLED; + if (adapter->ptp_setup_sdp) + adapter->ptp_setup_sdp(adapter); + + /* ensure that we cancel any pending PTP Tx work item in progress */ + cancel_work_sync(&adapter->ptp_tx_work); + ixgbe_ptp_clear_tx_timestamp(adapter); +} + +/** + * ixgbe_ptp_stop - close the PTP device + * @adapter: pointer to adapter struct + * + * completely destroy the PTP device, should only be called when the device is + * being fully closed. + */ +void ixgbe_ptp_stop(struct ixgbe_adapter *adapter) +{ + /* first, suspend PTP activity */ + ixgbe_ptp_suspend(adapter); + + /* disable the PTP clock device */ + if (adapter->ptp_clock) { + ptp_clock_unregister(adapter->ptp_clock); + adapter->ptp_clock = NULL; + e_dev_info("removed PHC on %s\n", + adapter->netdev->name); + } +} diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c new file mode 100644 index 000000000..5eba08669 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -0,0 +1,1724 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#include <linux/types.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/netdevice.h> +#include <linux/vmalloc.h> +#include <linux/string.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/tcp.h> +#include <linux/ipv6.h> +#include <linux/if_bridge.h> +#ifdef NETIF_F_HW_VLAN_CTAG_TX +#include <linux/if_vlan.h> +#endif + +#include "ixgbe.h" +#include "ixgbe_type.h" +#include "ixgbe_sriov.h" + +#ifdef CONFIG_PCI_IOV +static inline void ixgbe_alloc_vf_macvlans(struct ixgbe_adapter *adapter, + unsigned int num_vfs) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct vf_macvlans *mv_list; + int num_vf_macvlans, i; + + /* Initialize list of VF macvlans */ + INIT_LIST_HEAD(&adapter->vf_mvs.l); + + num_vf_macvlans = hw->mac.num_rar_entries - + (IXGBE_MAX_PF_MACVLANS + 1 + num_vfs); + if (!num_vf_macvlans) + return; + + mv_list = kcalloc(num_vf_macvlans, sizeof(struct vf_macvlans), + GFP_KERNEL); + if (mv_list) { + for (i = 0; i < num_vf_macvlans; i++) { + mv_list[i].vf = -1; + mv_list[i].free = true; + list_add(&mv_list[i].l, &adapter->vf_mvs.l); + } + adapter->mv_list = mv_list; + } +} + +static int __ixgbe_enable_sriov(struct ixgbe_adapter *adapter, + unsigned int num_vfs) +{ + struct ixgbe_hw *hw = &adapter->hw; + int i; + + if (adapter->xdp_prog) { + e_warn(probe, "SRIOV is not supported with XDP\n"); + return -EINVAL; + } + + /* Enable VMDq flag so device will be set in VM mode */ + adapter->flags |= IXGBE_FLAG_SRIOV_ENABLED | + IXGBE_FLAG_VMDQ_ENABLED; + + /* Allocate memory for per VF control structures */ + adapter->vfinfo = kcalloc(num_vfs, sizeof(struct vf_data_storage), + GFP_KERNEL); + if (!adapter->vfinfo) + return -ENOMEM; + + adapter->num_vfs = num_vfs; + + ixgbe_alloc_vf_macvlans(adapter, num_vfs); + adapter->ring_feature[RING_F_VMDQ].offset = num_vfs; + + /* Initialize default switching mode VEB */ + IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, IXGBE_PFDTXGSWC_VT_LBEN); + adapter->bridge_mode = BRIDGE_MODE_VEB; + + /* limit trafffic classes based on VFs enabled */ + if ((adapter->hw.mac.type == ixgbe_mac_82599EB) && (num_vfs < 16)) { + adapter->dcb_cfg.num_tcs.pg_tcs = MAX_TRAFFIC_CLASS; + adapter->dcb_cfg.num_tcs.pfc_tcs = MAX_TRAFFIC_CLASS; + } else if (num_vfs < 32) { + adapter->dcb_cfg.num_tcs.pg_tcs = 4; + adapter->dcb_cfg.num_tcs.pfc_tcs = 4; + } else { + adapter->dcb_cfg.num_tcs.pg_tcs = 1; + adapter->dcb_cfg.num_tcs.pfc_tcs = 1; + } + + /* Disable RSC when in SR-IOV mode */ + adapter->flags2 &= ~(IXGBE_FLAG2_RSC_CAPABLE | + IXGBE_FLAG2_RSC_ENABLED); + + for (i = 0; i < num_vfs; i++) { + /* enable spoof checking for all VFs */ + adapter->vfinfo[i].spoofchk_enabled = true; + + /* We support VF RSS querying only for 82599 and x540 + * devices at the moment. These devices share RSS + * indirection table and RSS hash key with PF therefore + * we want to disable the querying by default. + */ + adapter->vfinfo[i].rss_query_enabled = false; + + /* Untrust all VFs */ + adapter->vfinfo[i].trusted = false; + + /* set the default xcast mode */ + adapter->vfinfo[i].xcast_mode = IXGBEVF_XCAST_MODE_NONE; + } + + e_info(probe, "SR-IOV enabled with %d VFs\n", num_vfs); + return 0; +} + +/** + * ixgbe_get_vfs - Find and take references to all vf devices + * @adapter: Pointer to adapter struct + */ +static void ixgbe_get_vfs(struct ixgbe_adapter *adapter) +{ + struct pci_dev *pdev = adapter->pdev; + u16 vendor = pdev->vendor; + struct pci_dev *vfdev; + int vf = 0; + u16 vf_id; + int pos; + + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_SRIOV); + if (!pos) + return; + pci_read_config_word(pdev, pos + PCI_SRIOV_VF_DID, &vf_id); + + vfdev = pci_get_device(vendor, vf_id, NULL); + for (; vfdev; vfdev = pci_get_device(vendor, vf_id, vfdev)) { + if (!vfdev->is_virtfn) + continue; + if (vfdev->physfn != pdev) + continue; + if (vf >= adapter->num_vfs) + continue; + pci_dev_get(vfdev); + adapter->vfinfo[vf].vfdev = vfdev; + ++vf; + } +} + +/* Note this function is called when the user wants to enable SR-IOV + * VFs using the now deprecated module parameter + */ +void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, unsigned int max_vfs) +{ + int pre_existing_vfs = 0; + unsigned int num_vfs; + + pre_existing_vfs = pci_num_vf(adapter->pdev); + if (!pre_existing_vfs && !max_vfs) + return; + + /* If there are pre-existing VFs then we have to force + * use of that many - over ride any module parameter value. + * This may result from the user unloading the PF driver + * while VFs were assigned to guest VMs or because the VFs + * have been created via the new PCI SR-IOV sysfs interface. + */ + if (pre_existing_vfs) { + num_vfs = pre_existing_vfs; + dev_warn(&adapter->pdev->dev, + "Virtual Functions already enabled for this device - Please reload all VF drivers to avoid spoofed packet errors\n"); + } else { + int err; + /* + * The 82599 supports up to 64 VFs per physical function + * but this implementation limits allocation to 63 so that + * basic networking resources are still available to the + * physical function. If the user requests greater than + * 63 VFs then it is an error - reset to default of zero. + */ + num_vfs = min_t(unsigned int, max_vfs, IXGBE_MAX_VFS_DRV_LIMIT); + + err = pci_enable_sriov(adapter->pdev, num_vfs); + if (err) { + e_err(probe, "Failed to enable PCI sriov: %d\n", err); + return; + } + } + + if (!__ixgbe_enable_sriov(adapter, num_vfs)) { + ixgbe_get_vfs(adapter); + return; + } + + /* If we have gotten to this point then there is no memory available + * to manage the VF devices - print message and bail. + */ + e_err(probe, "Unable to allocate memory for VF Data Storage - " + "SRIOV disabled\n"); + ixgbe_disable_sriov(adapter); +} + +#endif /* #ifdef CONFIG_PCI_IOV */ +int ixgbe_disable_sriov(struct ixgbe_adapter *adapter) +{ + unsigned int num_vfs = adapter->num_vfs, vf; + unsigned long flags; + int rss; + + spin_lock_irqsave(&adapter->vfs_lock, flags); + /* set num VFs to 0 to prevent access to vfinfo */ + adapter->num_vfs = 0; + spin_unlock_irqrestore(&adapter->vfs_lock, flags); + + /* put the reference to all of the vf devices */ + for (vf = 0; vf < num_vfs; ++vf) { + struct pci_dev *vfdev = adapter->vfinfo[vf].vfdev; + + if (!vfdev) + continue; + adapter->vfinfo[vf].vfdev = NULL; + pci_dev_put(vfdev); + } + + /* free VF control structures */ + kfree(adapter->vfinfo); + adapter->vfinfo = NULL; + + /* free macvlan list */ + kfree(adapter->mv_list); + adapter->mv_list = NULL; + + /* if SR-IOV is already disabled then there is nothing to do */ + if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) + return 0; + +#ifdef CONFIG_PCI_IOV + /* + * If our VFs are assigned we cannot shut down SR-IOV + * without causing issues, so just leave the hardware + * available but disabled + */ + if (pci_vfs_assigned(adapter->pdev)) { + e_dev_warn("Unloading driver while VFs are assigned - VFs will not be deallocated\n"); + return -EPERM; + } + /* disable iov and allow time for transactions to clear */ + pci_disable_sriov(adapter->pdev); +#endif + + /* Disable VMDq flag so device will be set in VM mode */ + if (bitmap_weight(adapter->fwd_bitmask, adapter->num_rx_pools) == 1) { + adapter->flags &= ~IXGBE_FLAG_VMDQ_ENABLED; + adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED; + rss = min_t(int, ixgbe_max_rss_indices(adapter), + num_online_cpus()); + } else { + rss = min_t(int, IXGBE_MAX_L2A_QUEUES, num_online_cpus()); + } + + adapter->ring_feature[RING_F_VMDQ].offset = 0; + adapter->ring_feature[RING_F_RSS].limit = rss; + + /* take a breather then clean up driver data */ + msleep(100); + return 0; +} + +static int ixgbe_pci_sriov_enable(struct pci_dev *dev, int num_vfs) +{ +#ifdef CONFIG_PCI_IOV + struct ixgbe_adapter *adapter = pci_get_drvdata(dev); + int pre_existing_vfs = pci_num_vf(dev); + int err = 0, num_rx_pools, i, limit; + u8 num_tc; + + if (pre_existing_vfs && pre_existing_vfs != num_vfs) + err = ixgbe_disable_sriov(adapter); + else if (pre_existing_vfs && pre_existing_vfs == num_vfs) + return num_vfs; + + if (err) + return err; + + /* While the SR-IOV capability structure reports total VFs to be 64, + * we limit the actual number allocated as below based on two factors. + * Num_TCs MAX_VFs + * 1 63 + * <=4 31 + * >4 15 + * First, we reserve some transmit/receive resources for the PF. + * Second, VMDQ also uses the same pools that SR-IOV does. We need to + * account for this, so that we don't accidentally allocate more VFs + * than we have available pools. The PCI bus driver already checks for + * other values out of range. + */ + num_tc = adapter->hw_tcs; + num_rx_pools = bitmap_weight(adapter->fwd_bitmask, + adapter->num_rx_pools); + limit = (num_tc > 4) ? IXGBE_MAX_VFS_8TC : + (num_tc > 1) ? IXGBE_MAX_VFS_4TC : IXGBE_MAX_VFS_1TC; + + if (num_vfs > (limit - num_rx_pools)) { + e_dev_err("Currently configured with %d TCs, and %d offloaded macvlans. Creating more than %d VFs is not allowed\n", + num_tc, num_rx_pools - 1, limit - num_rx_pools); + return -EPERM; + } + + err = __ixgbe_enable_sriov(adapter, num_vfs); + if (err) + return err; + + for (i = 0; i < num_vfs; i++) + ixgbe_vf_configuration(dev, (i | 0x10000000)); + + /* reset before enabling SRIOV to avoid mailbox issues */ + ixgbe_sriov_reinit(adapter); + + err = pci_enable_sriov(dev, num_vfs); + if (err) { + e_dev_warn("Failed to enable PCI sriov: %d\n", err); + return err; + } + ixgbe_get_vfs(adapter); + + return num_vfs; +#else + return 0; +#endif +} + +static int ixgbe_pci_sriov_disable(struct pci_dev *dev) +{ + struct ixgbe_adapter *adapter = pci_get_drvdata(dev); + int err; +#ifdef CONFIG_PCI_IOV + u32 current_flags = adapter->flags; + int prev_num_vf = pci_num_vf(dev); +#endif + + err = ixgbe_disable_sriov(adapter); + + /* Only reinit if no error and state changed */ +#ifdef CONFIG_PCI_IOV + if (!err && (current_flags != adapter->flags || + prev_num_vf != pci_num_vf(dev))) + ixgbe_sriov_reinit(adapter); +#endif + + return err; +} + +int ixgbe_pci_sriov_configure(struct pci_dev *dev, int num_vfs) +{ + if (num_vfs == 0) + return ixgbe_pci_sriov_disable(dev); + else + return ixgbe_pci_sriov_enable(dev, num_vfs); +} + +static int ixgbe_set_vf_multicasts(struct ixgbe_adapter *adapter, + u32 *msgbuf, u32 vf) +{ + int entries = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) + >> IXGBE_VT_MSGINFO_SHIFT; + u16 *hash_list = (u16 *)&msgbuf[1]; + struct vf_data_storage *vfinfo = &adapter->vfinfo[vf]; + struct ixgbe_hw *hw = &adapter->hw; + int i; + u32 vector_bit; + u32 vector_reg; + u32 mta_reg; + u32 vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(vf)); + + /* only so many hash values supported */ + entries = min(entries, IXGBE_MAX_VF_MC_ENTRIES); + + /* + * salt away the number of multi cast addresses assigned + * to this VF for later use to restore when the PF multi cast + * list changes + */ + vfinfo->num_vf_mc_hashes = entries; + + /* + * VFs are limited to using the MTA hash table for their multicast + * addresses + */ + for (i = 0; i < entries; i++) { + vfinfo->vf_mc_hashes[i] = hash_list[i]; + } + + for (i = 0; i < vfinfo->num_vf_mc_hashes; i++) { + vector_reg = (vfinfo->vf_mc_hashes[i] >> 5) & 0x7F; + vector_bit = vfinfo->vf_mc_hashes[i] & 0x1F; + mta_reg = IXGBE_READ_REG(hw, IXGBE_MTA(vector_reg)); + mta_reg |= BIT(vector_bit); + IXGBE_WRITE_REG(hw, IXGBE_MTA(vector_reg), mta_reg); + } + vmolr |= IXGBE_VMOLR_ROMPE; + IXGBE_WRITE_REG(hw, IXGBE_VMOLR(vf), vmolr); + + return 0; +} + +#ifdef CONFIG_PCI_IOV +void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct vf_data_storage *vfinfo; + int i, j; + u32 vector_bit; + u32 vector_reg; + u32 mta_reg; + + for (i = 0; i < adapter->num_vfs; i++) { + u32 vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(i)); + vfinfo = &adapter->vfinfo[i]; + for (j = 0; j < vfinfo->num_vf_mc_hashes; j++) { + hw->addr_ctrl.mta_in_use++; + vector_reg = (vfinfo->vf_mc_hashes[j] >> 5) & 0x7F; + vector_bit = vfinfo->vf_mc_hashes[j] & 0x1F; + mta_reg = IXGBE_READ_REG(hw, IXGBE_MTA(vector_reg)); + mta_reg |= BIT(vector_bit); + IXGBE_WRITE_REG(hw, IXGBE_MTA(vector_reg), mta_reg); + } + + if (vfinfo->num_vf_mc_hashes) + vmolr |= IXGBE_VMOLR_ROMPE; + else + vmolr &= ~IXGBE_VMOLR_ROMPE; + IXGBE_WRITE_REG(hw, IXGBE_VMOLR(i), vmolr); + } + + /* Restore any VF macvlans */ + ixgbe_full_sync_mac_table(adapter); +} +#endif + +static int ixgbe_set_vf_vlan(struct ixgbe_adapter *adapter, int add, int vid, + u32 vf) +{ + struct ixgbe_hw *hw = &adapter->hw; + int err; + + /* If VLAN overlaps with one the PF is currently monitoring make + * sure that we are able to allocate a VLVF entry. This may be + * redundant but it guarantees PF will maintain visibility to + * the VLAN. + */ + if (add && test_bit(vid, adapter->active_vlans)) { + err = hw->mac.ops.set_vfta(hw, vid, VMDQ_P(0), true, false); + if (err) + return err; + } + + err = hw->mac.ops.set_vfta(hw, vid, vf, !!add, false); + + if (add && !err) + return err; + + /* If we failed to add the VF VLAN or we are removing the VF VLAN + * we may need to drop the PF pool bit in order to allow us to free + * up the VLVF resources. + */ + if (test_bit(vid, adapter->active_vlans) || + (adapter->flags2 & IXGBE_FLAG2_VLAN_PROMISC)) + ixgbe_update_pf_promisc_vlvf(adapter, vid); + + return err; +} + +static int ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 max_frame, u32 vf) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 max_frs; + + if (max_frame < ETH_MIN_MTU || max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE) { + e_err(drv, "VF max_frame %d out of range\n", max_frame); + return -EINVAL; + } + + /* + * For 82599EB we have to keep all PFs and VFs operating with + * the same max_frame value in order to avoid sending an oversize + * frame to a VF. In order to guarantee this is handled correctly + * for all cases we have several special exceptions to take into + * account before we can enable the VF for receive + */ + if (adapter->hw.mac.type == ixgbe_mac_82599EB) { + struct net_device *dev = adapter->netdev; + int pf_max_frame = dev->mtu + ETH_HLEN; + u32 reg_offset, vf_shift, vfre; + s32 err = 0; + +#ifdef CONFIG_FCOE + if (dev->features & NETIF_F_FCOE_MTU) + pf_max_frame = max_t(int, pf_max_frame, + IXGBE_FCOE_JUMBO_FRAME_SIZE); + +#endif /* CONFIG_FCOE */ + switch (adapter->vfinfo[vf].vf_api) { + case ixgbe_mbox_api_11: + case ixgbe_mbox_api_12: + case ixgbe_mbox_api_13: + case ixgbe_mbox_api_14: + /* Version 1.1 supports jumbo frames on VFs if PF has + * jumbo frames enabled which means legacy VFs are + * disabled + */ + if (pf_max_frame > ETH_FRAME_LEN) + break; + fallthrough; + default: + /* If the PF or VF are running w/ jumbo frames enabled + * we need to shut down the VF Rx path as we cannot + * support jumbo frames on legacy VFs + */ + if ((pf_max_frame > ETH_FRAME_LEN) || + (max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN))) + err = -EINVAL; + break; + } + + /* determine VF receive enable location */ + vf_shift = vf % 32; + reg_offset = vf / 32; + + /* enable or disable receive depending on error */ + vfre = IXGBE_READ_REG(hw, IXGBE_VFRE(reg_offset)); + if (err) + vfre &= ~BIT(vf_shift); + else + vfre |= BIT(vf_shift); + IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset), vfre); + + if (err) { + e_err(drv, "VF max_frame %d out of range\n", max_frame); + return err; + } + } + + /* pull current max frame size from hardware */ + max_frs = IXGBE_READ_REG(hw, IXGBE_MAXFRS); + max_frs &= IXGBE_MHADD_MFS_MASK; + max_frs >>= IXGBE_MHADD_MFS_SHIFT; + + if (max_frs < max_frame) { + max_frs = max_frame << IXGBE_MHADD_MFS_SHIFT; + IXGBE_WRITE_REG(hw, IXGBE_MAXFRS, max_frs); + } + + e_info(hw, "VF requests change max MTU to %d\n", max_frame); + + return 0; +} + +static void ixgbe_set_vmolr(struct ixgbe_hw *hw, u32 vf, bool aupe) +{ + u32 vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(vf)); + vmolr |= IXGBE_VMOLR_BAM; + if (aupe) + vmolr |= IXGBE_VMOLR_AUPE; + else + vmolr &= ~IXGBE_VMOLR_AUPE; + IXGBE_WRITE_REG(hw, IXGBE_VMOLR(vf), vmolr); +} + +static void ixgbe_clear_vmvir(struct ixgbe_adapter *adapter, u32 vf) +{ + struct ixgbe_hw *hw = &adapter->hw; + + IXGBE_WRITE_REG(hw, IXGBE_VMVIR(vf), 0); +} + +static void ixgbe_clear_vf_vlans(struct ixgbe_adapter *adapter, u32 vf) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 vlvfb_mask, pool_mask, i; + + /* create mask for VF and other pools */ + pool_mask = ~BIT(VMDQ_P(0) % 32); + vlvfb_mask = BIT(vf % 32); + + /* post increment loop, covers VLVF_ENTRIES - 1 to 0 */ + for (i = IXGBE_VLVF_ENTRIES; i--;) { + u32 bits[2], vlvfb, vid, vfta, vlvf; + u32 word = i * 2 + vf / 32; + u32 mask; + + vlvfb = IXGBE_READ_REG(hw, IXGBE_VLVFB(word)); + + /* if our bit isn't set we can skip it */ + if (!(vlvfb & vlvfb_mask)) + continue; + + /* clear our bit from vlvfb */ + vlvfb ^= vlvfb_mask; + + /* create 64b mask to chedk to see if we should clear VLVF */ + bits[word % 2] = vlvfb; + bits[~word % 2] = IXGBE_READ_REG(hw, IXGBE_VLVFB(word ^ 1)); + + /* if other pools are present, just remove ourselves */ + if (bits[(VMDQ_P(0) / 32) ^ 1] || + (bits[VMDQ_P(0) / 32] & pool_mask)) + goto update_vlvfb; + + /* if PF is present, leave VFTA */ + if (bits[0] || bits[1]) + goto update_vlvf; + + /* if we cannot determine VLAN just remove ourselves */ + vlvf = IXGBE_READ_REG(hw, IXGBE_VLVF(i)); + if (!vlvf) + goto update_vlvfb; + + vid = vlvf & VLAN_VID_MASK; + mask = BIT(vid % 32); + + /* clear bit from VFTA */ + vfta = IXGBE_READ_REG(hw, IXGBE_VFTA(vid / 32)); + if (vfta & mask) + IXGBE_WRITE_REG(hw, IXGBE_VFTA(vid / 32), vfta ^ mask); +update_vlvf: + /* clear POOL selection enable */ + IXGBE_WRITE_REG(hw, IXGBE_VLVF(i), 0); + + if (!(adapter->flags2 & IXGBE_FLAG2_VLAN_PROMISC)) + vlvfb = 0; +update_vlvfb: + /* clear pool bits */ + IXGBE_WRITE_REG(hw, IXGBE_VLVFB(word), vlvfb); + } +} + +static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter, + int vf, int index, unsigned char *mac_addr) +{ + struct vf_macvlans *entry; + struct list_head *pos; + int retval = 0; + + if (index <= 1) { + list_for_each(pos, &adapter->vf_mvs.l) { + entry = list_entry(pos, struct vf_macvlans, l); + if (entry->vf == vf) { + entry->vf = -1; + entry->free = true; + entry->is_macvlan = false; + ixgbe_del_mac_filter(adapter, + entry->vf_macvlan, vf); + } + } + } + + /* + * If index was zero then we were asked to clear the uc list + * for the VF. We're done. + */ + if (!index) + return 0; + + entry = NULL; + + list_for_each(pos, &adapter->vf_mvs.l) { + entry = list_entry(pos, struct vf_macvlans, l); + if (entry->free) + break; + } + + /* + * If we traversed the entire list and didn't find a free entry + * then we're out of space on the RAR table. Also entry may + * be NULL because the original memory allocation for the list + * failed, which is not fatal but does mean we can't support + * VF requests for MACVLAN because we couldn't allocate + * memory for the list management required. + */ + if (!entry || !entry->free) + return -ENOSPC; + + retval = ixgbe_add_mac_filter(adapter, mac_addr, vf); + if (retval < 0) + return retval; + + entry->free = false; + entry->is_macvlan = true; + entry->vf = vf; + memcpy(entry->vf_macvlan, mac_addr, ETH_ALEN); + + return 0; +} + +static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; + struct vf_data_storage *vfinfo = &adapter->vfinfo[vf]; + u32 q_per_pool = __ALIGN_MASK(1, ~vmdq->mask); + u8 num_tcs = adapter->hw_tcs; + u32 reg_val; + u32 queue; + + /* remove VLAN filters beloning to this VF */ + ixgbe_clear_vf_vlans(adapter, vf); + + /* add back PF assigned VLAN or VLAN 0 */ + ixgbe_set_vf_vlan(adapter, true, vfinfo->pf_vlan, vf); + + /* reset offloads to defaults */ + ixgbe_set_vmolr(hw, vf, !vfinfo->pf_vlan); + + /* set outgoing tags for VFs */ + if (!vfinfo->pf_vlan && !vfinfo->pf_qos && !num_tcs) { + ixgbe_clear_vmvir(adapter, vf); + } else { + if (vfinfo->pf_qos || !num_tcs) + ixgbe_set_vmvir(adapter, vfinfo->pf_vlan, + vfinfo->pf_qos, vf); + else + ixgbe_set_vmvir(adapter, vfinfo->pf_vlan, + adapter->default_up, vf); + + if (vfinfo->spoofchk_enabled) { + hw->mac.ops.set_vlan_anti_spoofing(hw, true, vf); + hw->mac.ops.set_mac_anti_spoofing(hw, true, vf); + } + } + + /* reset multicast table array for vf */ + adapter->vfinfo[vf].num_vf_mc_hashes = 0; + + /* clear any ipsec table info */ + ixgbe_ipsec_vf_clear(adapter, vf); + + /* Flush and reset the mta with the new values */ + ixgbe_set_rx_mode(adapter->netdev); + + ixgbe_del_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf); + ixgbe_set_vf_macvlan(adapter, vf, 0, NULL); + + /* reset VF api back to unknown */ + adapter->vfinfo[vf].vf_api = ixgbe_mbox_api_10; + + /* Restart each queue for given VF */ + for (queue = 0; queue < q_per_pool; queue++) { + unsigned int reg_idx = (vf * q_per_pool) + queue; + + reg_val = IXGBE_READ_REG(hw, IXGBE_PVFTXDCTL(reg_idx)); + + /* Re-enabling only configured queues */ + if (reg_val) { + reg_val |= IXGBE_TXDCTL_ENABLE; + IXGBE_WRITE_REG(hw, IXGBE_PVFTXDCTL(reg_idx), reg_val); + reg_val &= ~IXGBE_TXDCTL_ENABLE; + IXGBE_WRITE_REG(hw, IXGBE_PVFTXDCTL(reg_idx), reg_val); + } + } + + IXGBE_WRITE_FLUSH(hw); +} + +static void ixgbe_vf_clear_mbx(struct ixgbe_adapter *adapter, u32 vf) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 word; + + /* Clear VF's mailbox memory */ + for (word = 0; word < IXGBE_VFMAILBOX_SIZE; word++) + IXGBE_WRITE_REG_ARRAY(hw, IXGBE_PFMBMEM(vf), word, 0); + + IXGBE_WRITE_FLUSH(hw); +} + +static int ixgbe_set_vf_mac(struct ixgbe_adapter *adapter, + int vf, unsigned char *mac_addr) +{ + s32 retval; + + ixgbe_del_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf); + retval = ixgbe_add_mac_filter(adapter, mac_addr, vf); + if (retval >= 0) + memcpy(adapter->vfinfo[vf].vf_mac_addresses, mac_addr, + ETH_ALEN); + else + eth_zero_addr(adapter->vfinfo[vf].vf_mac_addresses); + + return retval; +} + +int ixgbe_vf_configuration(struct pci_dev *pdev, unsigned int event_mask) +{ + struct ixgbe_adapter *adapter = pci_get_drvdata(pdev); + unsigned int vfn = (event_mask & 0x3f); + + bool enable = ((event_mask & 0x10000000U) != 0); + + if (enable) + eth_zero_addr(adapter->vfinfo[vfn].vf_mac_addresses); + + return 0; +} + +static inline void ixgbe_write_qde(struct ixgbe_adapter *adapter, u32 vf, + u32 qde) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; + u32 q_per_pool = __ALIGN_MASK(1, ~vmdq->mask); + int i; + + for (i = vf * q_per_pool; i < ((vf + 1) * q_per_pool); i++) { + u32 reg; + + /* flush previous write */ + IXGBE_WRITE_FLUSH(hw); + + /* indicate to hardware that we want to set drop enable */ + reg = IXGBE_QDE_WRITE | qde; + reg |= i << IXGBE_QDE_IDX_SHIFT; + IXGBE_WRITE_REG(hw, IXGBE_QDE, reg); + } +} + +static int ixgbe_vf_reset_msg(struct ixgbe_adapter *adapter, u32 vf) +{ + struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; + struct ixgbe_hw *hw = &adapter->hw; + unsigned char *vf_mac = adapter->vfinfo[vf].vf_mac_addresses; + u32 reg, reg_offset, vf_shift; + u32 msgbuf[4] = {0, 0, 0, 0}; + u8 *addr = (u8 *)(&msgbuf[1]); + u32 q_per_pool = __ALIGN_MASK(1, ~vmdq->mask); + int i; + + e_info(probe, "VF Reset msg received from vf %d\n", vf); + + /* reset the filters for the device */ + ixgbe_vf_reset_event(adapter, vf); + + ixgbe_vf_clear_mbx(adapter, vf); + + /* set vf mac address */ + if (!is_zero_ether_addr(vf_mac)) + ixgbe_set_vf_mac(adapter, vf, vf_mac); + + vf_shift = vf % 32; + reg_offset = vf / 32; + + /* enable transmit for vf */ + reg = IXGBE_READ_REG(hw, IXGBE_VFTE(reg_offset)); + reg |= BIT(vf_shift); + IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset), reg); + + /* force drop enable for all VF Rx queues */ + reg = IXGBE_QDE_ENABLE; + if (adapter->vfinfo[vf].pf_vlan) + reg |= IXGBE_QDE_HIDE_VLAN; + + ixgbe_write_qde(adapter, vf, reg); + + /* enable receive for vf */ + reg = IXGBE_READ_REG(hw, IXGBE_VFRE(reg_offset)); + reg |= BIT(vf_shift); + /* + * The 82599 cannot support a mix of jumbo and non-jumbo PF/VFs. + * For more info take a look at ixgbe_set_vf_lpe + */ + if (adapter->hw.mac.type == ixgbe_mac_82599EB) { + struct net_device *dev = adapter->netdev; + int pf_max_frame = dev->mtu + ETH_HLEN; + +#ifdef CONFIG_FCOE + if (dev->features & NETIF_F_FCOE_MTU) + pf_max_frame = max_t(int, pf_max_frame, + IXGBE_FCOE_JUMBO_FRAME_SIZE); + +#endif /* CONFIG_FCOE */ + if (pf_max_frame > ETH_FRAME_LEN) + reg &= ~BIT(vf_shift); + } + IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset), reg); + + /* enable VF mailbox for further messages */ + adapter->vfinfo[vf].clear_to_send = true; + + /* Enable counting of spoofed packets in the SSVPC register */ + reg = IXGBE_READ_REG(hw, IXGBE_VMECM(reg_offset)); + reg |= BIT(vf_shift); + IXGBE_WRITE_REG(hw, IXGBE_VMECM(reg_offset), reg); + + /* + * Reset the VFs TDWBAL and TDWBAH registers + * which are not cleared by an FLR + */ + for (i = 0; i < q_per_pool; i++) { + IXGBE_WRITE_REG(hw, IXGBE_PVFTDWBAHn(q_per_pool, vf, i), 0); + IXGBE_WRITE_REG(hw, IXGBE_PVFTDWBALn(q_per_pool, vf, i), 0); + } + + /* reply to reset with ack and vf mac address */ + msgbuf[0] = IXGBE_VF_RESET; + if (!is_zero_ether_addr(vf_mac) && adapter->vfinfo[vf].pf_set_mac) { + msgbuf[0] |= IXGBE_VT_MSGTYPE_ACK; + memcpy(addr, vf_mac, ETH_ALEN); + } else { + msgbuf[0] |= IXGBE_VT_MSGTYPE_NACK; + } + + /* + * Piggyback the multicast filter type so VF can compute the + * correct vectors + */ + msgbuf[3] = hw->mac.mc_filter_type; + ixgbe_write_mbx(hw, msgbuf, IXGBE_VF_PERMADDR_MSG_LEN, vf); + + return 0; +} + +static int ixgbe_set_vf_mac_addr(struct ixgbe_adapter *adapter, + u32 *msgbuf, u32 vf) +{ + u8 *new_mac = ((u8 *)(&msgbuf[1])); + + if (!is_valid_ether_addr(new_mac)) { + e_warn(drv, "VF %d attempted to set invalid mac\n", vf); + return -1; + } + + if (adapter->vfinfo[vf].pf_set_mac && !adapter->vfinfo[vf].trusted && + !ether_addr_equal(adapter->vfinfo[vf].vf_mac_addresses, new_mac)) { + e_warn(drv, + "VF %d attempted to override administratively set MAC address\n" + "Reload the VF driver to resume operations\n", + vf); + return -1; + } + + return ixgbe_set_vf_mac(adapter, vf, new_mac) < 0; +} + +static int ixgbe_set_vf_vlan_msg(struct ixgbe_adapter *adapter, + u32 *msgbuf, u32 vf) +{ + u32 add = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) >> IXGBE_VT_MSGINFO_SHIFT; + u32 vid = (msgbuf[1] & IXGBE_VLVF_VLANID_MASK); + u8 tcs = adapter->hw_tcs; + + if (adapter->vfinfo[vf].pf_vlan || tcs) { + e_warn(drv, + "VF %d attempted to override administratively set VLAN configuration\n" + "Reload the VF driver to resume operations\n", + vf); + return -1; + } + + /* VLAN 0 is a special case, don't allow it to be removed */ + if (!vid && !add) + return 0; + + return ixgbe_set_vf_vlan(adapter, add, vid, vf); +} + +static int ixgbe_set_vf_macvlan_msg(struct ixgbe_adapter *adapter, + u32 *msgbuf, u32 vf) +{ + u8 *new_mac = ((u8 *)(&msgbuf[1])); + int index = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) >> + IXGBE_VT_MSGINFO_SHIFT; + int err; + + if (adapter->vfinfo[vf].pf_set_mac && !adapter->vfinfo[vf].trusted && + index > 0) { + e_warn(drv, + "VF %d requested MACVLAN filter but is administratively denied\n", + vf); + return -1; + } + + /* An non-zero index indicates the VF is setting a filter */ + if (index) { + if (!is_valid_ether_addr(new_mac)) { + e_warn(drv, "VF %d attempted to set invalid mac\n", vf); + return -1; + } + + /* + * If the VF is allowed to set MAC filters then turn off + * anti-spoofing to avoid false positives. + */ + if (adapter->vfinfo[vf].spoofchk_enabled) { + struct ixgbe_hw *hw = &adapter->hw; + + hw->mac.ops.set_mac_anti_spoofing(hw, false, vf); + hw->mac.ops.set_vlan_anti_spoofing(hw, false, vf); + } + } + + err = ixgbe_set_vf_macvlan(adapter, vf, index, new_mac); + if (err == -ENOSPC) + e_warn(drv, + "VF %d has requested a MACVLAN filter but there is no space for it\n", + vf); + + return err < 0; +} + +static int ixgbe_negotiate_vf_api(struct ixgbe_adapter *adapter, + u32 *msgbuf, u32 vf) +{ + int api = msgbuf[1]; + + switch (api) { + case ixgbe_mbox_api_10: + case ixgbe_mbox_api_11: + case ixgbe_mbox_api_12: + case ixgbe_mbox_api_13: + case ixgbe_mbox_api_14: + adapter->vfinfo[vf].vf_api = api; + return 0; + default: + break; + } + + e_info(drv, "VF %d requested invalid api version %u\n", vf, api); + + return -1; +} + +static int ixgbe_get_vf_queues(struct ixgbe_adapter *adapter, + u32 *msgbuf, u32 vf) +{ + struct net_device *dev = adapter->netdev; + struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; + unsigned int default_tc = 0; + u8 num_tcs = adapter->hw_tcs; + + /* verify the PF is supporting the correct APIs */ + switch (adapter->vfinfo[vf].vf_api) { + case ixgbe_mbox_api_20: + case ixgbe_mbox_api_11: + case ixgbe_mbox_api_12: + case ixgbe_mbox_api_13: + case ixgbe_mbox_api_14: + break; + default: + return -1; + } + + /* only allow 1 Tx queue for bandwidth limiting */ + msgbuf[IXGBE_VF_TX_QUEUES] = __ALIGN_MASK(1, ~vmdq->mask); + msgbuf[IXGBE_VF_RX_QUEUES] = __ALIGN_MASK(1, ~vmdq->mask); + + /* if TCs > 1 determine which TC belongs to default user priority */ + if (num_tcs > 1) + default_tc = netdev_get_prio_tc_map(dev, adapter->default_up); + + /* notify VF of need for VLAN tag stripping, and correct queue */ + if (num_tcs) + msgbuf[IXGBE_VF_TRANS_VLAN] = num_tcs; + else if (adapter->vfinfo[vf].pf_vlan || adapter->vfinfo[vf].pf_qos) + msgbuf[IXGBE_VF_TRANS_VLAN] = 1; + else + msgbuf[IXGBE_VF_TRANS_VLAN] = 0; + + /* notify VF of default queue */ + msgbuf[IXGBE_VF_DEF_QUEUE] = default_tc; + + return 0; +} + +static int ixgbe_get_vf_reta(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) +{ + u32 i, j; + u32 *out_buf = &msgbuf[1]; + const u8 *reta = adapter->rss_indir_tbl; + u32 reta_size = ixgbe_rss_indir_tbl_entries(adapter); + + /* Check if operation is permitted */ + if (!adapter->vfinfo[vf].rss_query_enabled) + return -EPERM; + + /* verify the PF is supporting the correct API */ + switch (adapter->vfinfo[vf].vf_api) { + case ixgbe_mbox_api_14: + case ixgbe_mbox_api_13: + case ixgbe_mbox_api_12: + break; + default: + return -EOPNOTSUPP; + } + + /* This mailbox command is supported (required) only for 82599 and x540 + * VFs which support up to 4 RSS queues. Therefore we will compress the + * RETA by saving only 2 bits from each entry. This way we will be able + * to transfer the whole RETA in a single mailbox operation. + */ + for (i = 0; i < reta_size / 16; i++) { + out_buf[i] = 0; + for (j = 0; j < 16; j++) + out_buf[i] |= (u32)(reta[16 * i + j] & 0x3) << (2 * j); + } + + return 0; +} + +static int ixgbe_get_vf_rss_key(struct ixgbe_adapter *adapter, + u32 *msgbuf, u32 vf) +{ + u32 *rss_key = &msgbuf[1]; + + /* Check if the operation is permitted */ + if (!adapter->vfinfo[vf].rss_query_enabled) + return -EPERM; + + /* verify the PF is supporting the correct API */ + switch (adapter->vfinfo[vf].vf_api) { + case ixgbe_mbox_api_14: + case ixgbe_mbox_api_13: + case ixgbe_mbox_api_12: + break; + default: + return -EOPNOTSUPP; + } + + memcpy(rss_key, adapter->rss_key, IXGBE_RSS_KEY_SIZE); + + return 0; +} + +static int ixgbe_update_vf_xcast_mode(struct ixgbe_adapter *adapter, + u32 *msgbuf, u32 vf) +{ + struct ixgbe_hw *hw = &adapter->hw; + int xcast_mode = msgbuf[1]; + u32 vmolr, fctrl, disable, enable; + + /* verify the PF is supporting the correct APIs */ + switch (adapter->vfinfo[vf].vf_api) { + case ixgbe_mbox_api_12: + /* promisc introduced in 1.3 version */ + if (xcast_mode == IXGBEVF_XCAST_MODE_PROMISC) + return -EOPNOTSUPP; + fallthrough; + case ixgbe_mbox_api_13: + case ixgbe_mbox_api_14: + break; + default: + return -EOPNOTSUPP; + } + + if (xcast_mode > IXGBEVF_XCAST_MODE_MULTI && + !adapter->vfinfo[vf].trusted) { + xcast_mode = IXGBEVF_XCAST_MODE_MULTI; + } + + if (adapter->vfinfo[vf].xcast_mode == xcast_mode) + goto out; + + switch (xcast_mode) { + case IXGBEVF_XCAST_MODE_NONE: + disable = IXGBE_VMOLR_ROMPE | + IXGBE_VMOLR_MPE | IXGBE_VMOLR_UPE | IXGBE_VMOLR_VPE; + enable = IXGBE_VMOLR_BAM; + break; + case IXGBEVF_XCAST_MODE_MULTI: + disable = IXGBE_VMOLR_MPE | IXGBE_VMOLR_UPE | IXGBE_VMOLR_VPE; + enable = IXGBE_VMOLR_BAM | IXGBE_VMOLR_ROMPE; + break; + case IXGBEVF_XCAST_MODE_ALLMULTI: + disable = IXGBE_VMOLR_UPE | IXGBE_VMOLR_VPE; + enable = IXGBE_VMOLR_BAM | IXGBE_VMOLR_ROMPE | IXGBE_VMOLR_MPE; + break; + case IXGBEVF_XCAST_MODE_PROMISC: + if (hw->mac.type <= ixgbe_mac_82599EB) + return -EOPNOTSUPP; + + fctrl = IXGBE_READ_REG(hw, IXGBE_FCTRL); + if (!(fctrl & IXGBE_FCTRL_UPE)) { + /* VF promisc requires PF in promisc */ + e_warn(drv, + "Enabling VF promisc requires PF in promisc\n"); + return -EPERM; + } + + disable = IXGBE_VMOLR_VPE; + enable = IXGBE_VMOLR_BAM | IXGBE_VMOLR_ROMPE | + IXGBE_VMOLR_MPE | IXGBE_VMOLR_UPE; + break; + default: + return -EOPNOTSUPP; + } + + vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(vf)); + vmolr &= ~disable; + vmolr |= enable; + IXGBE_WRITE_REG(hw, IXGBE_VMOLR(vf), vmolr); + + adapter->vfinfo[vf].xcast_mode = xcast_mode; + +out: + msgbuf[1] = xcast_mode; + + return 0; +} + +static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) +{ + u32 mbx_size = IXGBE_VFMAILBOX_SIZE; + u32 msgbuf[IXGBE_VFMAILBOX_SIZE]; + struct ixgbe_hw *hw = &adapter->hw; + s32 retval; + + retval = ixgbe_read_mbx(hw, msgbuf, mbx_size, vf); + + if (retval) { + pr_err("Error receiving message from VF\n"); + return retval; + } + + /* this is a message we already processed, do nothing */ + if (msgbuf[0] & (IXGBE_VT_MSGTYPE_ACK | IXGBE_VT_MSGTYPE_NACK)) + return 0; + + /* flush the ack before we write any messages back */ + IXGBE_WRITE_FLUSH(hw); + + if (msgbuf[0] == IXGBE_VF_RESET) + return ixgbe_vf_reset_msg(adapter, vf); + + /* + * until the vf completes a virtual function reset it should not be + * allowed to start any configuration. + */ + if (!adapter->vfinfo[vf].clear_to_send) { + msgbuf[0] |= IXGBE_VT_MSGTYPE_NACK; + ixgbe_write_mbx(hw, msgbuf, 1, vf); + return 0; + } + + switch ((msgbuf[0] & 0xFFFF)) { + case IXGBE_VF_SET_MAC_ADDR: + retval = ixgbe_set_vf_mac_addr(adapter, msgbuf, vf); + break; + case IXGBE_VF_SET_MULTICAST: + retval = ixgbe_set_vf_multicasts(adapter, msgbuf, vf); + break; + case IXGBE_VF_SET_VLAN: + retval = ixgbe_set_vf_vlan_msg(adapter, msgbuf, vf); + break; + case IXGBE_VF_SET_LPE: + retval = ixgbe_set_vf_lpe(adapter, msgbuf[1], vf); + break; + case IXGBE_VF_SET_MACVLAN: + retval = ixgbe_set_vf_macvlan_msg(adapter, msgbuf, vf); + break; + case IXGBE_VF_API_NEGOTIATE: + retval = ixgbe_negotiate_vf_api(adapter, msgbuf, vf); + break; + case IXGBE_VF_GET_QUEUES: + retval = ixgbe_get_vf_queues(adapter, msgbuf, vf); + break; + case IXGBE_VF_GET_RETA: + retval = ixgbe_get_vf_reta(adapter, msgbuf, vf); + break; + case IXGBE_VF_GET_RSS_KEY: + retval = ixgbe_get_vf_rss_key(adapter, msgbuf, vf); + break; + case IXGBE_VF_UPDATE_XCAST_MODE: + retval = ixgbe_update_vf_xcast_mode(adapter, msgbuf, vf); + break; + case IXGBE_VF_IPSEC_ADD: + retval = ixgbe_ipsec_vf_add_sa(adapter, msgbuf, vf); + break; + case IXGBE_VF_IPSEC_DEL: + retval = ixgbe_ipsec_vf_del_sa(adapter, msgbuf, vf); + break; + default: + e_err(drv, "Unhandled Msg %8.8x\n", msgbuf[0]); + retval = IXGBE_ERR_MBX; + break; + } + + /* notify the VF of the results of what it sent us */ + if (retval) + msgbuf[0] |= IXGBE_VT_MSGTYPE_NACK; + else + msgbuf[0] |= IXGBE_VT_MSGTYPE_ACK; + + msgbuf[0] |= IXGBE_VT_MSGTYPE_CTS; + + ixgbe_write_mbx(hw, msgbuf, mbx_size, vf); + + return retval; +} + +static void ixgbe_rcv_ack_from_vf(struct ixgbe_adapter *adapter, u32 vf) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 msg = IXGBE_VT_MSGTYPE_NACK; + + /* if device isn't clear to send it shouldn't be reading either */ + if (!adapter->vfinfo[vf].clear_to_send) + ixgbe_write_mbx(hw, &msg, 1, vf); +} + +void ixgbe_msg_task(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + unsigned long flags; + u32 vf; + + spin_lock_irqsave(&adapter->vfs_lock, flags); + for (vf = 0; vf < adapter->num_vfs; vf++) { + /* process any reset requests */ + if (!ixgbe_check_for_rst(hw, vf)) + ixgbe_vf_reset_event(adapter, vf); + + /* process any messages pending */ + if (!ixgbe_check_for_msg(hw, vf)) + ixgbe_rcv_msg_from_vf(adapter, vf); + + /* process any acks */ + if (!ixgbe_check_for_ack(hw, vf)) + ixgbe_rcv_ack_from_vf(adapter, vf); + } + spin_unlock_irqrestore(&adapter->vfs_lock, flags); +} + +void ixgbe_disable_tx_rx(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + + /* disable transmit and receive for all vfs */ + IXGBE_WRITE_REG(hw, IXGBE_VFTE(0), 0); + IXGBE_WRITE_REG(hw, IXGBE_VFTE(1), 0); + + IXGBE_WRITE_REG(hw, IXGBE_VFRE(0), 0); + IXGBE_WRITE_REG(hw, IXGBE_VFRE(1), 0); +} + +static inline void ixgbe_ping_vf(struct ixgbe_adapter *adapter, int vf) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 ping; + + ping = IXGBE_PF_CONTROL_MSG; + if (adapter->vfinfo[vf].clear_to_send) + ping |= IXGBE_VT_MSGTYPE_CTS; + ixgbe_write_mbx(hw, &ping, 1, vf); +} + +void ixgbe_ping_all_vfs(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 ping; + int i; + + for (i = 0 ; i < adapter->num_vfs; i++) { + ping = IXGBE_PF_CONTROL_MSG; + if (adapter->vfinfo[i].clear_to_send) + ping |= IXGBE_VT_MSGTYPE_CTS; + ixgbe_write_mbx(hw, &ping, 1, i); + } +} + +int ixgbe_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + s32 retval; + + if (vf >= adapter->num_vfs) + return -EINVAL; + + if (is_valid_ether_addr(mac)) { + dev_info(&adapter->pdev->dev, "setting MAC %pM on VF %d\n", + mac, vf); + dev_info(&adapter->pdev->dev, "Reload the VF driver to make this change effective."); + + retval = ixgbe_set_vf_mac(adapter, vf, mac); + if (retval >= 0) { + adapter->vfinfo[vf].pf_set_mac = true; + + if (test_bit(__IXGBE_DOWN, &adapter->state)) { + dev_warn(&adapter->pdev->dev, "The VF MAC address has been set, but the PF device is not up.\n"); + dev_warn(&adapter->pdev->dev, "Bring the PF device up before attempting to use the VF device.\n"); + } + } else { + dev_warn(&adapter->pdev->dev, "The VF MAC address was NOT set due to invalid or duplicate MAC address.\n"); + } + } else if (is_zero_ether_addr(mac)) { + unsigned char *vf_mac_addr = + adapter->vfinfo[vf].vf_mac_addresses; + + /* nothing to do */ + if (is_zero_ether_addr(vf_mac_addr)) + return 0; + + dev_info(&adapter->pdev->dev, "removing MAC on VF %d\n", vf); + + retval = ixgbe_del_mac_filter(adapter, vf_mac_addr, vf); + if (retval >= 0) { + adapter->vfinfo[vf].pf_set_mac = false; + memcpy(vf_mac_addr, mac, ETH_ALEN); + } else { + dev_warn(&adapter->pdev->dev, "Could NOT remove the VF MAC address.\n"); + } + } else { + retval = -EINVAL; + } + + return retval; +} + +static int ixgbe_enable_port_vlan(struct ixgbe_adapter *adapter, int vf, + u16 vlan, u8 qos) +{ + struct ixgbe_hw *hw = &adapter->hw; + int err; + + err = ixgbe_set_vf_vlan(adapter, true, vlan, vf); + if (err) + goto out; + + /* Revoke tagless access via VLAN 0 */ + ixgbe_set_vf_vlan(adapter, false, 0, vf); + + ixgbe_set_vmvir(adapter, vlan, qos, vf); + ixgbe_set_vmolr(hw, vf, false); + + /* enable hide vlan on X550 */ + if (hw->mac.type >= ixgbe_mac_X550) + ixgbe_write_qde(adapter, vf, IXGBE_QDE_ENABLE | + IXGBE_QDE_HIDE_VLAN); + + adapter->vfinfo[vf].pf_vlan = vlan; + adapter->vfinfo[vf].pf_qos = qos; + dev_info(&adapter->pdev->dev, + "Setting VLAN %d, QOS 0x%x on VF %d\n", vlan, qos, vf); + if (test_bit(__IXGBE_DOWN, &adapter->state)) { + dev_warn(&adapter->pdev->dev, + "The VF VLAN has been set, but the PF device is not up.\n"); + dev_warn(&adapter->pdev->dev, + "Bring the PF device up before attempting to use the VF device.\n"); + } + +out: + return err; +} + +static int ixgbe_disable_port_vlan(struct ixgbe_adapter *adapter, int vf) +{ + struct ixgbe_hw *hw = &adapter->hw; + int err; + + err = ixgbe_set_vf_vlan(adapter, false, + adapter->vfinfo[vf].pf_vlan, vf); + /* Restore tagless access via VLAN 0 */ + ixgbe_set_vf_vlan(adapter, true, 0, vf); + ixgbe_clear_vmvir(adapter, vf); + ixgbe_set_vmolr(hw, vf, true); + + /* disable hide VLAN on X550 */ + if (hw->mac.type >= ixgbe_mac_X550) + ixgbe_write_qde(adapter, vf, IXGBE_QDE_ENABLE); + + adapter->vfinfo[vf].pf_vlan = 0; + adapter->vfinfo[vf].pf_qos = 0; + + return err; +} + +int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, + u8 qos, __be16 vlan_proto) +{ + int err = 0; + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + if ((vf >= adapter->num_vfs) || (vlan > 4095) || (qos > 7)) + return -EINVAL; + if (vlan_proto != htons(ETH_P_8021Q)) + return -EPROTONOSUPPORT; + if (vlan || qos) { + /* Check if there is already a port VLAN set, if so + * we have to delete the old one first before we + * can set the new one. The usage model had + * previously assumed the user would delete the + * old port VLAN before setting a new one but this + * is not necessarily the case. + */ + if (adapter->vfinfo[vf].pf_vlan) + err = ixgbe_disable_port_vlan(adapter, vf); + if (err) + goto out; + err = ixgbe_enable_port_vlan(adapter, vf, vlan, qos); + } else { + err = ixgbe_disable_port_vlan(adapter, vf); + } + +out: + return err; +} + +int ixgbe_link_mbps(struct ixgbe_adapter *adapter) +{ + switch (adapter->link_speed) { + case IXGBE_LINK_SPEED_100_FULL: + return 100; + case IXGBE_LINK_SPEED_1GB_FULL: + return 1000; + case IXGBE_LINK_SPEED_10GB_FULL: + return 10000; + default: + return 0; + } +} + +static void ixgbe_set_vf_rate_limit(struct ixgbe_adapter *adapter, int vf) +{ + struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; + struct ixgbe_hw *hw = &adapter->hw; + u32 bcnrc_val = 0; + u16 queue, queues_per_pool; + u16 tx_rate = adapter->vfinfo[vf].tx_rate; + + if (tx_rate) { + /* start with base link speed value */ + bcnrc_val = adapter->vf_rate_link_speed; + + /* Calculate the rate factor values to set */ + bcnrc_val <<= IXGBE_RTTBCNRC_RF_INT_SHIFT; + bcnrc_val /= tx_rate; + + /* clear everything but the rate factor */ + bcnrc_val &= IXGBE_RTTBCNRC_RF_INT_MASK | + IXGBE_RTTBCNRC_RF_DEC_MASK; + + /* enable the rate scheduler */ + bcnrc_val |= IXGBE_RTTBCNRC_RS_ENA; + } + + /* + * Set global transmit compensation time to the MMW_SIZE in RTTBCNRM + * register. Typically MMW_SIZE=0x014 if 9728-byte jumbo is supported + * and 0x004 otherwise. + */ + switch (hw->mac.type) { + case ixgbe_mac_82599EB: + IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRM, 0x4); + break; + case ixgbe_mac_X540: + IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRM, 0x14); + break; + default: + break; + } + + /* determine how many queues per pool based on VMDq mask */ + queues_per_pool = __ALIGN_MASK(1, ~vmdq->mask); + + /* write value for all Tx queues belonging to VF */ + for (queue = 0; queue < queues_per_pool; queue++) { + unsigned int reg_idx = (vf * queues_per_pool) + queue; + + IXGBE_WRITE_REG(hw, IXGBE_RTTDQSEL, reg_idx); + IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRC, bcnrc_val); + } +} + +void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter) +{ + int i; + + /* VF Tx rate limit was not set */ + if (!adapter->vf_rate_link_speed) + return; + + if (ixgbe_link_mbps(adapter) != adapter->vf_rate_link_speed) { + adapter->vf_rate_link_speed = 0; + dev_info(&adapter->pdev->dev, + "Link speed has been changed. VF Transmit rate is disabled\n"); + } + + for (i = 0; i < adapter->num_vfs; i++) { + if (!adapter->vf_rate_link_speed) + adapter->vfinfo[i].tx_rate = 0; + + ixgbe_set_vf_rate_limit(adapter, i); + } +} + +int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int min_tx_rate, + int max_tx_rate) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + int link_speed; + + /* verify VF is active */ + if (vf >= adapter->num_vfs) + return -EINVAL; + + /* verify link is up */ + if (!adapter->link_up) + return -EINVAL; + + /* verify we are linked at 10Gbps */ + link_speed = ixgbe_link_mbps(adapter); + if (link_speed != 10000) + return -EINVAL; + + if (min_tx_rate) + return -EINVAL; + + /* rate limit cannot be less than 10Mbs or greater than link speed */ + if (max_tx_rate && ((max_tx_rate <= 10) || (max_tx_rate > link_speed))) + return -EINVAL; + + /* store values */ + adapter->vf_rate_link_speed = link_speed; + adapter->vfinfo[vf].tx_rate = max_tx_rate; + + /* update hardware configuration */ + ixgbe_set_vf_rate_limit(adapter, vf); + + return 0; +} + +int ixgbe_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + + if (vf >= adapter->num_vfs) + return -EINVAL; + + adapter->vfinfo[vf].spoofchk_enabled = setting; + + /* configure MAC spoofing */ + hw->mac.ops.set_mac_anti_spoofing(hw, setting, vf); + + /* configure VLAN spoofing */ + hw->mac.ops.set_vlan_anti_spoofing(hw, setting, vf); + + /* Ensure LLDP and FC is set for Ethertype Antispoofing if we will be + * calling set_ethertype_anti_spoofing for each VF in loop below + */ + if (hw->mac.ops.set_ethertype_anti_spoofing) { + IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_LLDP), + (IXGBE_ETQF_FILTER_EN | + IXGBE_ETQF_TX_ANTISPOOF | + ETH_P_LLDP)); + + IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_FC), + (IXGBE_ETQF_FILTER_EN | + IXGBE_ETQF_TX_ANTISPOOF | + ETH_P_PAUSE)); + + hw->mac.ops.set_ethertype_anti_spoofing(hw, setting, vf); + } + + return 0; +} + +int ixgbe_ndo_set_vf_rss_query_en(struct net_device *netdev, int vf, + bool setting) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + /* This operation is currently supported only for 82599 and x540 + * devices. + */ + if (adapter->hw.mac.type < ixgbe_mac_82599EB || + adapter->hw.mac.type >= ixgbe_mac_X550) + return -EOPNOTSUPP; + + if (vf >= adapter->num_vfs) + return -EINVAL; + + adapter->vfinfo[vf].rss_query_enabled = setting; + + return 0; +} + +int ixgbe_ndo_set_vf_trust(struct net_device *netdev, int vf, bool setting) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + if (vf >= adapter->num_vfs) + return -EINVAL; + + /* nothing to do */ + if (adapter->vfinfo[vf].trusted == setting) + return 0; + + adapter->vfinfo[vf].trusted = setting; + + /* reset VF to reconfigure features */ + adapter->vfinfo[vf].clear_to_send = false; + ixgbe_ping_vf(adapter, vf); + + e_info(drv, "VF %u is %strusted\n", vf, setting ? "" : "not "); + + return 0; +} + +int ixgbe_ndo_get_vf_config(struct net_device *netdev, + int vf, struct ifla_vf_info *ivi) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + if (vf >= adapter->num_vfs) + return -EINVAL; + ivi->vf = vf; + memcpy(&ivi->mac, adapter->vfinfo[vf].vf_mac_addresses, ETH_ALEN); + ivi->max_tx_rate = adapter->vfinfo[vf].tx_rate; + ivi->min_tx_rate = 0; + ivi->vlan = adapter->vfinfo[vf].pf_vlan; + ivi->qos = adapter->vfinfo[vf].pf_qos; + ivi->spoofchk = adapter->vfinfo[vf].spoofchk_enabled; + ivi->rss_query_en = adapter->vfinfo[vf].rss_query_enabled; + ivi->trusted = adapter->vfinfo[vf].trusted; + return 0; +} diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h new file mode 100644 index 000000000..3ec21923c --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h @@ -0,0 +1,51 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#ifndef _IXGBE_SRIOV_H_ +#define _IXGBE_SRIOV_H_ + +/* ixgbe driver limit the max number of VFs could be enabled to + * 63 (IXGBE_MAX_VF_FUNCTIONS - 1) + */ +#define IXGBE_MAX_VFS_DRV_LIMIT (IXGBE_MAX_VF_FUNCTIONS - 1) +#define IXGBE_MAX_VFS_1TC IXGBE_MAX_VF_FUNCTIONS +#define IXGBE_MAX_VFS_4TC 32 +#define IXGBE_MAX_VFS_8TC 16 + +#ifdef CONFIG_PCI_IOV +void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter); +#endif +void ixgbe_msg_task(struct ixgbe_adapter *adapter); +int ixgbe_vf_configuration(struct pci_dev *pdev, unsigned int event_mask); +void ixgbe_disable_tx_rx(struct ixgbe_adapter *adapter); +void ixgbe_ping_all_vfs(struct ixgbe_adapter *adapter); +int ixgbe_ndo_set_vf_mac(struct net_device *netdev, int queue, u8 *mac); +int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int queue, u16 vlan, + u8 qos, __be16 vlan_proto); +int ixgbe_link_mbps(struct ixgbe_adapter *adapter); +int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int min_tx_rate, + int max_tx_rate); +int ixgbe_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting); +int ixgbe_ndo_set_vf_rss_query_en(struct net_device *netdev, int vf, + bool setting); +int ixgbe_ndo_set_vf_trust(struct net_device *netdev, int vf, bool setting); +int ixgbe_ndo_get_vf_config(struct net_device *netdev, + int vf, struct ifla_vf_info *ivi); +void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter); +int ixgbe_disable_sriov(struct ixgbe_adapter *adapter); +#ifdef CONFIG_PCI_IOV +void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, unsigned int max_vfs); +#endif +int ixgbe_pci_sriov_configure(struct pci_dev *dev, int num_vfs); + +static inline void ixgbe_set_vmvir(struct ixgbe_adapter *adapter, + u16 vid, u16 qos, u32 vf) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 vmvir = vid | (qos << VLAN_PRIO_SHIFT) | IXGBE_VMVIR_VLANA_DEFAULT; + + IXGBE_WRITE_REG(hw, IXGBE_VMVIR(vf), vmvir); +} + +#endif /* _IXGBE_SRIOV_H_ */ + diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c new file mode 100644 index 000000000..204844288 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c @@ -0,0 +1,205 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#include "ixgbe.h" +#include "ixgbe_common.h" +#include "ixgbe_type.h" + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/sysfs.h> +#include <linux/kobject.h> +#include <linux/device.h> +#include <linux/netdevice.h> +#include <linux/hwmon.h> + +/* hwmon callback functions */ +static ssize_t ixgbe_hwmon_show_location(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct hwmon_attr *ixgbe_attr = container_of(attr, struct hwmon_attr, + dev_attr); + return sprintf(buf, "loc%u\n", + ixgbe_attr->sensor->location); +} + +static ssize_t ixgbe_hwmon_show_temp(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct hwmon_attr *ixgbe_attr = container_of(attr, struct hwmon_attr, + dev_attr); + unsigned int value; + + /* reset the temp field */ + ixgbe_attr->hw->mac.ops.get_thermal_sensor_data(ixgbe_attr->hw); + + value = ixgbe_attr->sensor->temp; + + /* display millidegree */ + value *= 1000; + + return sprintf(buf, "%u\n", value); +} + +static ssize_t ixgbe_hwmon_show_cautionthresh(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct hwmon_attr *ixgbe_attr = container_of(attr, struct hwmon_attr, + dev_attr); + unsigned int value = ixgbe_attr->sensor->caution_thresh; + + /* display millidegree */ + value *= 1000; + + return sprintf(buf, "%u\n", value); +} + +static ssize_t ixgbe_hwmon_show_maxopthresh(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct hwmon_attr *ixgbe_attr = container_of(attr, struct hwmon_attr, + dev_attr); + unsigned int value = ixgbe_attr->sensor->max_op_thresh; + + /* display millidegree */ + value *= 1000; + + return sprintf(buf, "%u\n", value); +} + +/** + * ixgbe_add_hwmon_attr - Create hwmon attr table for a hwmon sysfs file. + * @adapter: pointer to the adapter structure + * @offset: offset in the eeprom sensor data table + * @type: type of sensor data to display + * + * For each file we want in hwmon's sysfs interface we need a device_attribute + * This is included in our hwmon_attr struct that contains the references to + * the data structures we need to get the data to display. + */ +static int ixgbe_add_hwmon_attr(struct ixgbe_adapter *adapter, + unsigned int offset, int type) { + int rc; + unsigned int n_attr; + struct hwmon_attr *ixgbe_attr; + + n_attr = adapter->ixgbe_hwmon_buff->n_hwmon; + ixgbe_attr = &adapter->ixgbe_hwmon_buff->hwmon_list[n_attr]; + + switch (type) { + case IXGBE_HWMON_TYPE_LOC: + ixgbe_attr->dev_attr.show = ixgbe_hwmon_show_location; + snprintf(ixgbe_attr->name, sizeof(ixgbe_attr->name), + "temp%u_label", offset + 1); + break; + case IXGBE_HWMON_TYPE_TEMP: + ixgbe_attr->dev_attr.show = ixgbe_hwmon_show_temp; + snprintf(ixgbe_attr->name, sizeof(ixgbe_attr->name), + "temp%u_input", offset + 1); + break; + case IXGBE_HWMON_TYPE_CAUTION: + ixgbe_attr->dev_attr.show = ixgbe_hwmon_show_cautionthresh; + snprintf(ixgbe_attr->name, sizeof(ixgbe_attr->name), + "temp%u_max", offset + 1); + break; + case IXGBE_HWMON_TYPE_MAX: + ixgbe_attr->dev_attr.show = ixgbe_hwmon_show_maxopthresh; + snprintf(ixgbe_attr->name, sizeof(ixgbe_attr->name), + "temp%u_crit", offset + 1); + break; + default: + rc = -EPERM; + return rc; + } + + /* These always the same regardless of type */ + ixgbe_attr->sensor = + &adapter->hw.mac.thermal_sensor_data.sensor[offset]; + ixgbe_attr->hw = &adapter->hw; + ixgbe_attr->dev_attr.store = NULL; + ixgbe_attr->dev_attr.attr.mode = 0444; + ixgbe_attr->dev_attr.attr.name = ixgbe_attr->name; + sysfs_attr_init(&ixgbe_attr->dev_attr.attr); + + adapter->ixgbe_hwmon_buff->attrs[n_attr] = &ixgbe_attr->dev_attr.attr; + + ++adapter->ixgbe_hwmon_buff->n_hwmon; + + return 0; +} + +static void ixgbe_sysfs_del_adapter(struct ixgbe_adapter *adapter) +{ +} + +/* called from ixgbe_main.c */ +void ixgbe_sysfs_exit(struct ixgbe_adapter *adapter) +{ + ixgbe_sysfs_del_adapter(adapter); +} + +/* called from ixgbe_main.c */ +int ixgbe_sysfs_init(struct ixgbe_adapter *adapter) +{ + struct hwmon_buff *ixgbe_hwmon; + struct device *hwmon_dev; + unsigned int i; + int rc = 0; + + /* If this method isn't defined we don't support thermals */ + if (adapter->hw.mac.ops.init_thermal_sensor_thresh == NULL) { + goto exit; + } + + /* Don't create thermal hwmon interface if no sensors present */ + if (adapter->hw.mac.ops.init_thermal_sensor_thresh(&adapter->hw)) + goto exit; + + ixgbe_hwmon = devm_kzalloc(&adapter->pdev->dev, sizeof(*ixgbe_hwmon), + GFP_KERNEL); + if (ixgbe_hwmon == NULL) { + rc = -ENOMEM; + goto exit; + } + adapter->ixgbe_hwmon_buff = ixgbe_hwmon; + + for (i = 0; i < IXGBE_MAX_SENSORS; i++) { + /* + * Only create hwmon sysfs entries for sensors that have + * meaningful data for. + */ + if (adapter->hw.mac.thermal_sensor_data.sensor[i].location == 0) + continue; + + /* Bail if any hwmon attr struct fails to initialize */ + rc = ixgbe_add_hwmon_attr(adapter, i, IXGBE_HWMON_TYPE_CAUTION); + if (rc) + goto exit; + rc = ixgbe_add_hwmon_attr(adapter, i, IXGBE_HWMON_TYPE_LOC); + if (rc) + goto exit; + rc = ixgbe_add_hwmon_attr(adapter, i, IXGBE_HWMON_TYPE_TEMP); + if (rc) + goto exit; + rc = ixgbe_add_hwmon_attr(adapter, i, IXGBE_HWMON_TYPE_MAX); + if (rc) + goto exit; + } + + ixgbe_hwmon->groups[0] = &ixgbe_hwmon->group; + ixgbe_hwmon->group.attrs = ixgbe_hwmon->attrs; + + hwmon_dev = devm_hwmon_device_register_with_groups(&adapter->pdev->dev, + "ixgbe", + ixgbe_hwmon, + ixgbe_hwmon->groups); + if (IS_ERR(hwmon_dev)) + rc = PTR_ERR(hwmon_dev); +exit: + return rc; +} + diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h new file mode 100644 index 000000000..2aeec7802 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h @@ -0,0 +1,49 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2018 Intel Corporation. */ + +#ifndef _IXGBE_TXRX_COMMON_H_ +#define _IXGBE_TXRX_COMMON_H_ + +#define IXGBE_XDP_PASS 0 +#define IXGBE_XDP_CONSUMED BIT(0) +#define IXGBE_XDP_TX BIT(1) +#define IXGBE_XDP_REDIR BIT(2) + +#define IXGBE_TXD_CMD (IXGBE_TXD_CMD_EOP | \ + IXGBE_TXD_CMD_RS) + +int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, + struct xdp_frame *xdpf); +bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb); +void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb); +void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector, + struct sk_buff *skb); +void ixgbe_xdp_ring_update_tail(struct ixgbe_ring *ring); +void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter, u64 qmask); + +void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring); +void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring); + +struct xsk_buff_pool *ixgbe_xsk_pool(struct ixgbe_adapter *adapter, + struct ixgbe_ring *ring); +int ixgbe_xsk_pool_setup(struct ixgbe_adapter *adapter, + struct xsk_buff_pool *pool, + u16 qid); + +void ixgbe_zca_free(struct zero_copy_allocator *alloc, unsigned long handle); + +bool ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 cleaned_count); +int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, + struct ixgbe_ring *rx_ring, + const int budget); +void ixgbe_xsk_clean_rx_ring(struct ixgbe_ring *rx_ring); +bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector, + struct ixgbe_ring *tx_ring, int napi_budget); +int ixgbe_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags); +void ixgbe_xsk_clean_tx_ring(struct ixgbe_ring *tx_ring); + +#endif /* #define _IXGBE_TXRX_COMMON_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h new file mode 100644 index 000000000..2be1c4c72 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -0,0 +1,3809 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#ifndef _IXGBE_TYPE_H_ +#define _IXGBE_TYPE_H_ + +#include <linux/types.h> +#include <linux/mdio.h> +#include <linux/netdevice.h> + +/* Device IDs */ +#define IXGBE_DEV_ID_82598 0x10B6 +#define IXGBE_DEV_ID_82598_BX 0x1508 +#define IXGBE_DEV_ID_82598AF_DUAL_PORT 0x10C6 +#define IXGBE_DEV_ID_82598AF_SINGLE_PORT 0x10C7 +#define IXGBE_DEV_ID_82598EB_SFP_LOM 0x10DB +#define IXGBE_DEV_ID_82598AT 0x10C8 +#define IXGBE_DEV_ID_82598AT2 0x150B +#define IXGBE_DEV_ID_82598EB_CX4 0x10DD +#define IXGBE_DEV_ID_82598_CX4_DUAL_PORT 0x10EC +#define IXGBE_DEV_ID_82598_DA_DUAL_PORT 0x10F1 +#define IXGBE_DEV_ID_82598_SR_DUAL_PORT_EM 0x10E1 +#define IXGBE_DEV_ID_82598EB_XF_LR 0x10F4 +#define IXGBE_DEV_ID_82599_KX4 0x10F7 +#define IXGBE_DEV_ID_82599_KX4_MEZZ 0x1514 +#define IXGBE_DEV_ID_82599_KR 0x1517 +#define IXGBE_DEV_ID_82599_T3_LOM 0x151C +#define IXGBE_DEV_ID_82599_CX4 0x10F9 +#define IXGBE_DEV_ID_82599_SFP 0x10FB +#define IXGBE_DEV_ID_82599_BACKPLANE_FCOE 0x152a +#define IXGBE_DEV_ID_82599_SFP_FCOE 0x1529 +#define IXGBE_SUBDEV_ID_82599_SFP 0x11A9 +#define IXGBE_SUBDEV_ID_82599_SFP_WOL0 0x1071 +#define IXGBE_SUBDEV_ID_82599_RNDC 0x1F72 +#define IXGBE_SUBDEV_ID_82599_560FLR 0x17D0 +#define IXGBE_SUBDEV_ID_82599_SP_560FLR 0x211B +#define IXGBE_SUBDEV_ID_82599_LOM_SNAP6 0x2159 +#define IXGBE_SUBDEV_ID_82599_SFP_1OCP 0x000D +#define IXGBE_SUBDEV_ID_82599_SFP_2OCP 0x0008 +#define IXGBE_SUBDEV_ID_82599_SFP_LOM_OEM1 0x8976 +#define IXGBE_SUBDEV_ID_82599_SFP_LOM_OEM2 0x06EE +#define IXGBE_SUBDEV_ID_82599_ECNA_DP 0x0470 +#define IXGBE_DEV_ID_82599_SFP_EM 0x1507 +#define IXGBE_DEV_ID_82599_SFP_SF2 0x154D +#define IXGBE_DEV_ID_82599EN_SFP 0x1557 +#define IXGBE_SUBDEV_ID_82599EN_SFP_OCP1 0x0001 +#define IXGBE_DEV_ID_82599_XAUI_LOM 0x10FC +#define IXGBE_DEV_ID_82599_COMBO_BACKPLANE 0x10F8 +#define IXGBE_SUBDEV_ID_82599_KX4_KR_MEZZ 0x000C +#define IXGBE_DEV_ID_82599_LS 0x154F +#define IXGBE_DEV_ID_X540T 0x1528 +#define IXGBE_DEV_ID_82599_SFP_SF_QP 0x154A +#define IXGBE_DEV_ID_82599_QSFP_SF_QP 0x1558 +#define IXGBE_DEV_ID_X540T1 0x1560 + +#define IXGBE_DEV_ID_X550T 0x1563 +#define IXGBE_DEV_ID_X550T1 0x15D1 +#define IXGBE_DEV_ID_X550EM_X_KX4 0x15AA +#define IXGBE_DEV_ID_X550EM_X_KR 0x15AB +#define IXGBE_DEV_ID_X550EM_X_SFP 0x15AC +#define IXGBE_DEV_ID_X550EM_X_10G_T 0x15AD +#define IXGBE_DEV_ID_X550EM_X_1G_T 0x15AE +#define IXGBE_DEV_ID_X550EM_X_XFI 0x15B0 +#define IXGBE_DEV_ID_X550EM_A_KR 0x15C2 +#define IXGBE_DEV_ID_X550EM_A_KR_L 0x15C3 +#define IXGBE_DEV_ID_X550EM_A_SFP_N 0x15C4 +#define IXGBE_DEV_ID_X550EM_A_SGMII 0x15C6 +#define IXGBE_DEV_ID_X550EM_A_SGMII_L 0x15C7 +#define IXGBE_DEV_ID_X550EM_A_10G_T 0x15C8 +#define IXGBE_DEV_ID_X550EM_A_SFP 0x15CE +#define IXGBE_DEV_ID_X550EM_A_1G_T 0x15E4 +#define IXGBE_DEV_ID_X550EM_A_1G_T_L 0x15E5 + +/* VF Device IDs */ +#define IXGBE_DEV_ID_82599_VF 0x10ED +#define IXGBE_DEV_ID_X540_VF 0x1515 +#define IXGBE_DEV_ID_X550_VF 0x1565 +#define IXGBE_DEV_ID_X550EM_X_VF 0x15A8 +#define IXGBE_DEV_ID_X550EM_A_VF 0x15C5 + +#define IXGBE_CAT(r, m) IXGBE_##r##_##m + +#define IXGBE_BY_MAC(_hw, r) ((_hw)->mvals[IXGBE_CAT(r, IDX)]) + +/* General Registers */ +#define IXGBE_CTRL 0x00000 +#define IXGBE_STATUS 0x00008 +#define IXGBE_CTRL_EXT 0x00018 +#define IXGBE_ESDP 0x00020 +#define IXGBE_EODSDP 0x00028 + +#define IXGBE_I2CCTL_8259X 0x00028 +#define IXGBE_I2CCTL_X540 IXGBE_I2CCTL_8259X +#define IXGBE_I2CCTL_X550 0x15F5C +#define IXGBE_I2CCTL_X550EM_x IXGBE_I2CCTL_X550 +#define IXGBE_I2CCTL_X550EM_a IXGBE_I2CCTL_X550 +#define IXGBE_I2CCTL(_hw) IXGBE_BY_MAC((_hw), I2CCTL) + +#define IXGBE_LEDCTL 0x00200 +#define IXGBE_FRTIMER 0x00048 +#define IXGBE_TCPTIMER 0x0004C +#define IXGBE_CORESPARE 0x00600 +#define IXGBE_EXVET 0x05078 + +/* NVM Registers */ +#define IXGBE_EEC_8259X 0x10010 +#define IXGBE_EEC_X540 IXGBE_EEC_8259X +#define IXGBE_EEC_X550 IXGBE_EEC_8259X +#define IXGBE_EEC_X550EM_x IXGBE_EEC_8259X +#define IXGBE_EEC_X550EM_a 0x15FF8 +#define IXGBE_EEC(_hw) IXGBE_BY_MAC((_hw), EEC) +#define IXGBE_EERD 0x10014 +#define IXGBE_EEWR 0x10018 +#define IXGBE_FLA_8259X 0x1001C +#define IXGBE_FLA_X540 IXGBE_FLA_8259X +#define IXGBE_FLA_X550 IXGBE_FLA_8259X +#define IXGBE_FLA_X550EM_x IXGBE_FLA_8259X +#define IXGBE_FLA_X550EM_a 0x15F68 +#define IXGBE_FLA(_hw) IXGBE_BY_MAC((_hw), FLA) +#define IXGBE_EEMNGCTL 0x10110 +#define IXGBE_EEMNGDATA 0x10114 +#define IXGBE_FLMNGCTL 0x10118 +#define IXGBE_FLMNGDATA 0x1011C +#define IXGBE_FLMNGCNT 0x10120 +#define IXGBE_FLOP 0x1013C +#define IXGBE_GRC_8259X 0x10200 +#define IXGBE_GRC_X540 IXGBE_GRC_8259X +#define IXGBE_GRC_X550 IXGBE_GRC_8259X +#define IXGBE_GRC_X550EM_x IXGBE_GRC_8259X +#define IXGBE_GRC_X550EM_a 0x15F64 +#define IXGBE_GRC(_hw) IXGBE_BY_MAC((_hw), GRC) + +/* General Receive Control */ +#define IXGBE_GRC_MNG 0x00000001 /* Manageability Enable */ +#define IXGBE_GRC_APME 0x00000002 /* APM enabled in EEPROM */ + +#define IXGBE_VPDDIAG0 0x10204 +#define IXGBE_VPDDIAG1 0x10208 + +/* I2CCTL Bit Masks */ +#define IXGBE_I2C_CLK_IN_8259X 0x00000001 +#define IXGBE_I2C_CLK_IN_X540 IXGBE_I2C_CLK_IN_8259X +#define IXGBE_I2C_CLK_IN_X550 0x00004000 +#define IXGBE_I2C_CLK_IN_X550EM_x IXGBE_I2C_CLK_IN_X550 +#define IXGBE_I2C_CLK_IN_X550EM_a IXGBE_I2C_CLK_IN_X550 +#define IXGBE_I2C_CLK_IN(_hw) IXGBE_BY_MAC((_hw), I2C_CLK_IN) + +#define IXGBE_I2C_CLK_OUT_8259X 0x00000002 +#define IXGBE_I2C_CLK_OUT_X540 IXGBE_I2C_CLK_OUT_8259X +#define IXGBE_I2C_CLK_OUT_X550 0x00000200 +#define IXGBE_I2C_CLK_OUT_X550EM_x IXGBE_I2C_CLK_OUT_X550 +#define IXGBE_I2C_CLK_OUT_X550EM_a IXGBE_I2C_CLK_OUT_X550 +#define IXGBE_I2C_CLK_OUT(_hw) IXGBE_BY_MAC((_hw), I2C_CLK_OUT) + +#define IXGBE_I2C_DATA_IN_8259X 0x00000004 +#define IXGBE_I2C_DATA_IN_X540 IXGBE_I2C_DATA_IN_8259X +#define IXGBE_I2C_DATA_IN_X550 0x00001000 +#define IXGBE_I2C_DATA_IN_X550EM_x IXGBE_I2C_DATA_IN_X550 +#define IXGBE_I2C_DATA_IN_X550EM_a IXGBE_I2C_DATA_IN_X550 +#define IXGBE_I2C_DATA_IN(_hw) IXGBE_BY_MAC((_hw), I2C_DATA_IN) + +#define IXGBE_I2C_DATA_OUT_8259X 0x00000008 +#define IXGBE_I2C_DATA_OUT_X540 IXGBE_I2C_DATA_OUT_8259X +#define IXGBE_I2C_DATA_OUT_X550 0x00000400 +#define IXGBE_I2C_DATA_OUT_X550EM_x IXGBE_I2C_DATA_OUT_X550 +#define IXGBE_I2C_DATA_OUT_X550EM_a IXGBE_I2C_DATA_OUT_X550 +#define IXGBE_I2C_DATA_OUT(_hw) IXGBE_BY_MAC((_hw), I2C_DATA_OUT) + +#define IXGBE_I2C_DATA_OE_N_EN_8259X 0 +#define IXGBE_I2C_DATA_OE_N_EN_X540 IXGBE_I2C_DATA_OE_N_EN_8259X +#define IXGBE_I2C_DATA_OE_N_EN_X550 0x00000800 +#define IXGBE_I2C_DATA_OE_N_EN_X550EM_x IXGBE_I2C_DATA_OE_N_EN_X550 +#define IXGBE_I2C_DATA_OE_N_EN_X550EM_a IXGBE_I2C_DATA_OE_N_EN_X550 +#define IXGBE_I2C_DATA_OE_N_EN(_hw) IXGBE_BY_MAC((_hw), I2C_DATA_OE_N_EN) + +#define IXGBE_I2C_BB_EN_8259X 0 +#define IXGBE_I2C_BB_EN_X540 IXGBE_I2C_BB_EN_8259X +#define IXGBE_I2C_BB_EN_X550 0x00000100 +#define IXGBE_I2C_BB_EN_X550EM_x IXGBE_I2C_BB_EN_X550 +#define IXGBE_I2C_BB_EN_X550EM_a IXGBE_I2C_BB_EN_X550 +#define IXGBE_I2C_BB_EN(_hw) IXGBE_BY_MAC((_hw), I2C_BB_EN) + +#define IXGBE_I2C_CLK_OE_N_EN_8259X 0 +#define IXGBE_I2C_CLK_OE_N_EN_X540 IXGBE_I2C_CLK_OE_N_EN_8259X +#define IXGBE_I2C_CLK_OE_N_EN_X550 0x00002000 +#define IXGBE_I2C_CLK_OE_N_EN_X550EM_x IXGBE_I2C_CLK_OE_N_EN_X550 +#define IXGBE_I2C_CLK_OE_N_EN_X550EM_a IXGBE_I2C_CLK_OE_N_EN_X550 +#define IXGBE_I2C_CLK_OE_N_EN(_hw) IXGBE_BY_MAC((_hw), I2C_CLK_OE_N_EN) + +#define IXGBE_I2C_CLOCK_STRETCHING_TIMEOUT 500 + +#define IXGBE_I2C_THERMAL_SENSOR_ADDR 0xF8 +#define IXGBE_EMC_INTERNAL_DATA 0x00 +#define IXGBE_EMC_INTERNAL_THERM_LIMIT 0x20 +#define IXGBE_EMC_DIODE1_DATA 0x01 +#define IXGBE_EMC_DIODE1_THERM_LIMIT 0x19 +#define IXGBE_EMC_DIODE2_DATA 0x23 +#define IXGBE_EMC_DIODE2_THERM_LIMIT 0x1A + +#define IXGBE_MAX_SENSORS 3 + +struct ixgbe_thermal_diode_data { + u8 location; + u8 temp; + u8 caution_thresh; + u8 max_op_thresh; +}; + +struct ixgbe_thermal_sensor_data { + struct ixgbe_thermal_diode_data sensor[IXGBE_MAX_SENSORS]; +}; + +#define NVM_OROM_OFFSET 0x17 +#define NVM_OROM_BLK_LOW 0x83 +#define NVM_OROM_BLK_HI 0x84 +#define NVM_OROM_PATCH_MASK 0xFF +#define NVM_OROM_SHIFT 8 + +#define NVM_VER_MASK 0x00FF /* version mask */ +#define NVM_VER_SHIFT 8 /* version bit shift */ +#define NVM_OEM_PROD_VER_PTR 0x1B /* OEM Product version block pointer */ +#define NVM_OEM_PROD_VER_CAP_OFF 0x1 /* OEM Product version format offset */ +#define NVM_OEM_PROD_VER_OFF_L 0x2 /* OEM Product version offset low */ +#define NVM_OEM_PROD_VER_OFF_H 0x3 /* OEM Product version offset high */ +#define NVM_OEM_PROD_VER_CAP_MASK 0xF /* OEM Product version cap mask */ +#define NVM_OEM_PROD_VER_MOD_LEN 0x3 /* OEM Product version module length */ +#define NVM_ETK_OFF_LOW 0x2D /* version low order word */ +#define NVM_ETK_OFF_HI 0x2E /* version high order word */ +#define NVM_ETK_SHIFT 16 /* high version word shift */ +#define NVM_VER_INVALID 0xFFFF +#define NVM_ETK_VALID 0x8000 +#define NVM_INVALID_PTR 0xFFFF +#define NVM_VER_SIZE 32 /* version sting size */ + +struct ixgbe_nvm_version { + u32 etk_id; + u8 nvm_major; + u16 nvm_minor; + u8 nvm_id; + + bool oem_valid; + u8 oem_major; + u8 oem_minor; + u16 oem_release; + + bool or_valid; + u8 or_major; + u16 or_build; + u8 or_patch; +}; + +/* Interrupt Registers */ +#define IXGBE_EICR 0x00800 +#define IXGBE_EICS 0x00808 +#define IXGBE_EIMS 0x00880 +#define IXGBE_EIMC 0x00888 +#define IXGBE_EIAC 0x00810 +#define IXGBE_EIAM 0x00890 +#define IXGBE_EICS_EX(_i) (0x00A90 + (_i) * 4) +#define IXGBE_EIMS_EX(_i) (0x00AA0 + (_i) * 4) +#define IXGBE_EIMC_EX(_i) (0x00AB0 + (_i) * 4) +#define IXGBE_EIAM_EX(_i) (0x00AD0 + (_i) * 4) +/* + * 82598 EITR is 16 bits but set the limits based on the max + * supported by all ixgbe hardware. 82599 EITR is only 12 bits, + * with the lower 3 always zero. + */ +#define IXGBE_MAX_INT_RATE 488281 +#define IXGBE_MIN_INT_RATE 956 +#define IXGBE_MAX_EITR 0x00000FF8 +#define IXGBE_MIN_EITR 8 +#define IXGBE_EITR(_i) (((_i) <= 23) ? (0x00820 + ((_i) * 4)) : \ + (0x012300 + (((_i) - 24) * 4))) +#define IXGBE_EITR_ITR_INT_MASK 0x00000FF8 +#define IXGBE_EITR_LLI_MOD 0x00008000 +#define IXGBE_EITR_CNT_WDIS 0x80000000 +#define IXGBE_IVAR(_i) (0x00900 + ((_i) * 4)) /* 24 at 0x900-0x960 */ +#define IXGBE_IVAR_MISC 0x00A00 /* misc MSI-X interrupt causes */ +#define IXGBE_EITRSEL 0x00894 +#define IXGBE_MSIXT 0x00000 /* MSI-X Table. 0x0000 - 0x01C */ +#define IXGBE_MSIXPBA 0x02000 /* MSI-X Pending bit array */ +#define IXGBE_PBACL(_i) (((_i) == 0) ? (0x11068) : (0x110C0 + ((_i) * 4))) +#define IXGBE_GPIE 0x00898 + +/* Flow Control Registers */ +#define IXGBE_FCADBUL 0x03210 +#define IXGBE_FCADBUH 0x03214 +#define IXGBE_FCAMACL 0x04328 +#define IXGBE_FCAMACH 0x0432C +#define IXGBE_FCRTH_82599(_i) (0x03260 + ((_i) * 4)) /* 8 of these (0-7) */ +#define IXGBE_FCRTL_82599(_i) (0x03220 + ((_i) * 4)) /* 8 of these (0-7) */ +#define IXGBE_PFCTOP 0x03008 +#define IXGBE_FCTTV(_i) (0x03200 + ((_i) * 4)) /* 4 of these (0-3) */ +#define IXGBE_FCRTL(_i) (0x03220 + ((_i) * 8)) /* 8 of these (0-7) */ +#define IXGBE_FCRTH(_i) (0x03260 + ((_i) * 8)) /* 8 of these (0-7) */ +#define IXGBE_FCRTV 0x032A0 +#define IXGBE_FCCFG 0x03D00 +#define IXGBE_TFCS 0x0CE00 + +/* Receive DMA Registers */ +#define IXGBE_RDBAL(_i) (((_i) < 64) ? (0x01000 + ((_i) * 0x40)) : \ + (0x0D000 + (((_i) - 64) * 0x40))) +#define IXGBE_RDBAH(_i) (((_i) < 64) ? (0x01004 + ((_i) * 0x40)) : \ + (0x0D004 + (((_i) - 64) * 0x40))) +#define IXGBE_RDLEN(_i) (((_i) < 64) ? (0x01008 + ((_i) * 0x40)) : \ + (0x0D008 + (((_i) - 64) * 0x40))) +#define IXGBE_RDH(_i) (((_i) < 64) ? (0x01010 + ((_i) * 0x40)) : \ + (0x0D010 + (((_i) - 64) * 0x40))) +#define IXGBE_RDT(_i) (((_i) < 64) ? (0x01018 + ((_i) * 0x40)) : \ + (0x0D018 + (((_i) - 64) * 0x40))) +#define IXGBE_RXDCTL(_i) (((_i) < 64) ? (0x01028 + ((_i) * 0x40)) : \ + (0x0D028 + (((_i) - 64) * 0x40))) +#define IXGBE_RSCCTL(_i) (((_i) < 64) ? (0x0102C + ((_i) * 0x40)) : \ + (0x0D02C + (((_i) - 64) * 0x40))) +#define IXGBE_RSCDBU 0x03028 +#define IXGBE_RDDCC 0x02F20 +#define IXGBE_RXMEMWRAP 0x03190 +#define IXGBE_STARCTRL 0x03024 +/* + * Split and Replication Receive Control Registers + * 00-15 : 0x02100 + n*4 + * 16-64 : 0x01014 + n*0x40 + * 64-127: 0x0D014 + (n-64)*0x40 + */ +#define IXGBE_SRRCTL(_i) (((_i) <= 15) ? (0x02100 + ((_i) * 4)) : \ + (((_i) < 64) ? (0x01014 + ((_i) * 0x40)) : \ + (0x0D014 + (((_i) - 64) * 0x40)))) +/* + * Rx DCA Control Register: + * 00-15 : 0x02200 + n*4 + * 16-64 : 0x0100C + n*0x40 + * 64-127: 0x0D00C + (n-64)*0x40 + */ +#define IXGBE_DCA_RXCTRL(_i) (((_i) <= 15) ? (0x02200 + ((_i) * 4)) : \ + (((_i) < 64) ? (0x0100C + ((_i) * 0x40)) : \ + (0x0D00C + (((_i) - 64) * 0x40)))) +#define IXGBE_RDRXCTL 0x02F00 +#define IXGBE_RXPBSIZE(_i) (0x03C00 + ((_i) * 4)) + /* 8 of these 0x03C00 - 0x03C1C */ +#define IXGBE_RXCTRL 0x03000 +#define IXGBE_DROPEN 0x03D04 +#define IXGBE_RXPBSIZE_SHIFT 10 + +/* Receive Registers */ +#define IXGBE_RXCSUM 0x05000 +#define IXGBE_RFCTL 0x05008 +#define IXGBE_DRECCCTL 0x02F08 +#define IXGBE_DRECCCTL_DISABLE 0 +/* Multicast Table Array - 128 entries */ +#define IXGBE_MTA(_i) (0x05200 + ((_i) * 4)) +#define IXGBE_RAL(_i) (((_i) <= 15) ? (0x05400 + ((_i) * 8)) : \ + (0x0A200 + ((_i) * 8))) +#define IXGBE_RAH(_i) (((_i) <= 15) ? (0x05404 + ((_i) * 8)) : \ + (0x0A204 + ((_i) * 8))) +#define IXGBE_MPSAR_LO(_i) (0x0A600 + ((_i) * 8)) +#define IXGBE_MPSAR_HI(_i) (0x0A604 + ((_i) * 8)) +/* Packet split receive type */ +#define IXGBE_PSRTYPE(_i) (((_i) <= 15) ? (0x05480 + ((_i) * 4)) : \ + (0x0EA00 + ((_i) * 4))) +/* array of 4096 1-bit vlan filters */ +#define IXGBE_VFTA(_i) (0x0A000 + ((_i) * 4)) +/*array of 4096 4-bit vlan vmdq indices */ +#define IXGBE_VFTAVIND(_j, _i) (0x0A200 + ((_j) * 0x200) + ((_i) * 4)) +#define IXGBE_FCTRL 0x05080 +#define IXGBE_VLNCTRL 0x05088 +#define IXGBE_MCSTCTRL 0x05090 +#define IXGBE_MRQC 0x05818 +#define IXGBE_SAQF(_i) (0x0E000 + ((_i) * 4)) /* Source Address Queue Filter */ +#define IXGBE_DAQF(_i) (0x0E200 + ((_i) * 4)) /* Dest. Address Queue Filter */ +#define IXGBE_SDPQF(_i) (0x0E400 + ((_i) * 4)) /* Src Dest. Addr Queue Filter */ +#define IXGBE_FTQF(_i) (0x0E600 + ((_i) * 4)) /* Five Tuple Queue Filter */ +#define IXGBE_ETQF(_i) (0x05128 + ((_i) * 4)) /* EType Queue Filter */ +#define IXGBE_ETQS(_i) (0x0EC00 + ((_i) * 4)) /* EType Queue Select */ +#define IXGBE_SYNQF 0x0EC30 /* SYN Packet Queue Filter */ +#define IXGBE_RQTC 0x0EC70 +#define IXGBE_MTQC 0x08120 +#define IXGBE_VLVF(_i) (0x0F100 + ((_i) * 4)) /* 64 of these (0-63) */ +#define IXGBE_VLVFB(_i) (0x0F200 + ((_i) * 4)) /* 128 of these (0-127) */ +#define IXGBE_VMVIR(_i) (0x08000 + ((_i) * 4)) /* 64 of these (0-63) */ +#define IXGBE_PFFLPL 0x050B0 +#define IXGBE_PFFLPH 0x050B4 +#define IXGBE_VT_CTL 0x051B0 +#define IXGBE_PFMAILBOX(_i) (0x04B00 + (4 * (_i))) /* 64 total */ +#define IXGBE_PFMBMEM(_i) (0x13000 + (64 * (_i))) /* 64 Mailboxes, 16 DW each */ +#define IXGBE_PFMBICR(_i) (0x00710 + (4 * (_i))) /* 4 total */ +#define IXGBE_PFMBIMR(_i) (0x00720 + (4 * (_i))) /* 4 total */ +#define IXGBE_VFRE(_i) (0x051E0 + ((_i) * 4)) +#define IXGBE_VFTE(_i) (0x08110 + ((_i) * 4)) +#define IXGBE_VMECM(_i) (0x08790 + ((_i) * 4)) +#define IXGBE_QDE 0x2F04 +#define IXGBE_VMTXSW(_i) (0x05180 + ((_i) * 4)) /* 2 total */ +#define IXGBE_VMOLR(_i) (0x0F000 + ((_i) * 4)) /* 64 total */ +#define IXGBE_UTA(_i) (0x0F400 + ((_i) * 4)) +#define IXGBE_MRCTL(_i) (0x0F600 + ((_i) * 4)) +#define IXGBE_VMRVLAN(_i) (0x0F610 + ((_i) * 4)) +#define IXGBE_VMRVM(_i) (0x0F630 + ((_i) * 4)) +#define IXGBE_WQBR_RX(_i) (0x2FB0 + ((_i) * 4)) /* 4 total */ +#define IXGBE_WQBR_TX(_i) (0x8130 + ((_i) * 4)) /* 4 total */ +#define IXGBE_L34T_IMIR(_i) (0x0E800 + ((_i) * 4)) /*128 of these (0-127)*/ +#define IXGBE_RXFECCERR0 0x051B8 +#define IXGBE_LLITHRESH 0x0EC90 +#define IXGBE_IMIR(_i) (0x05A80 + ((_i) * 4)) /* 8 of these (0-7) */ +#define IXGBE_IMIREXT(_i) (0x05AA0 + ((_i) * 4)) /* 8 of these (0-7) */ +#define IXGBE_IMIRVP 0x05AC0 +#define IXGBE_VMD_CTL 0x0581C +#define IXGBE_RETA(_i) (0x05C00 + ((_i) * 4)) /* 32 of these (0-31) */ +#define IXGBE_ERETA(_i) (0x0EE80 + ((_i) * 4)) /* 96 of these (0-95) */ +#define IXGBE_RSSRK(_i) (0x05C80 + ((_i) * 4)) /* 10 of these (0-9) */ + +/* Registers for setting up RSS on X550 with SRIOV + * _p - pool number (0..63) + * _i - index (0..10 for PFVFRSSRK, 0..15 for PFVFRETA) + */ +#define IXGBE_PFVFMRQC(_p) (0x03400 + ((_p) * 4)) +#define IXGBE_PFVFRSSRK(_i, _p) (0x018000 + ((_i) * 4) + ((_p) * 0x40)) +#define IXGBE_PFVFRETA(_i, _p) (0x019000 + ((_i) * 4) + ((_p) * 0x40)) + +/* Flow Director registers */ +#define IXGBE_FDIRCTRL 0x0EE00 +#define IXGBE_FDIRHKEY 0x0EE68 +#define IXGBE_FDIRSKEY 0x0EE6C +#define IXGBE_FDIRDIP4M 0x0EE3C +#define IXGBE_FDIRSIP4M 0x0EE40 +#define IXGBE_FDIRTCPM 0x0EE44 +#define IXGBE_FDIRUDPM 0x0EE48 +#define IXGBE_FDIRSCTPM 0x0EE78 +#define IXGBE_FDIRIP6M 0x0EE74 +#define IXGBE_FDIRM 0x0EE70 + +/* Flow Director Stats registers */ +#define IXGBE_FDIRFREE 0x0EE38 +#define IXGBE_FDIRLEN 0x0EE4C +#define IXGBE_FDIRUSTAT 0x0EE50 +#define IXGBE_FDIRFSTAT 0x0EE54 +#define IXGBE_FDIRMATCH 0x0EE58 +#define IXGBE_FDIRMISS 0x0EE5C + +/* Flow Director Programming registers */ +#define IXGBE_FDIRSIPv6(_i) (0x0EE0C + ((_i) * 4)) /* 3 of these (0-2) */ +#define IXGBE_FDIRIPSA 0x0EE18 +#define IXGBE_FDIRIPDA 0x0EE1C +#define IXGBE_FDIRPORT 0x0EE20 +#define IXGBE_FDIRVLAN 0x0EE24 +#define IXGBE_FDIRHASH 0x0EE28 +#define IXGBE_FDIRCMD 0x0EE2C + +/* Transmit DMA registers */ +#define IXGBE_TDBAL(_i) (0x06000 + ((_i) * 0x40)) /* 32 of these (0-31)*/ +#define IXGBE_TDBAH(_i) (0x06004 + ((_i) * 0x40)) +#define IXGBE_TDLEN(_i) (0x06008 + ((_i) * 0x40)) +#define IXGBE_TDH(_i) (0x06010 + ((_i) * 0x40)) +#define IXGBE_TDT(_i) (0x06018 + ((_i) * 0x40)) +#define IXGBE_TXDCTL(_i) (0x06028 + ((_i) * 0x40)) +#define IXGBE_TDWBAL(_i) (0x06038 + ((_i) * 0x40)) +#define IXGBE_TDWBAH(_i) (0x0603C + ((_i) * 0x40)) +#define IXGBE_DTXCTL 0x07E00 + +#define IXGBE_DMATXCTL 0x04A80 +#define IXGBE_PFVFSPOOF(_i) (0x08200 + ((_i) * 4)) /* 8 of these 0 - 7 */ +#define IXGBE_PFDTXGSWC 0x08220 +#define IXGBE_DTXMXSZRQ 0x08100 +#define IXGBE_DTXTCPFLGL 0x04A88 +#define IXGBE_DTXTCPFLGH 0x04A8C +#define IXGBE_LBDRPEN 0x0CA00 +#define IXGBE_TXPBTHRESH(_i) (0x04950 + ((_i) * 4)) /* 8 of these 0 - 7 */ + +#define IXGBE_DMATXCTL_TE 0x1 /* Transmit Enable */ +#define IXGBE_DMATXCTL_NS 0x2 /* No Snoop LSO hdr buffer */ +#define IXGBE_DMATXCTL_GDV 0x8 /* Global Double VLAN */ +#define IXGBE_DMATXCTL_MDP_EN 0x20 /* Bit 5 */ +#define IXGBE_DMATXCTL_MBINTEN 0x40 /* Bit 6 */ +#define IXGBE_DMATXCTL_VT_SHIFT 16 /* VLAN EtherType */ + +#define IXGBE_PFDTXGSWC_VT_LBEN 0x1 /* Local L2 VT switch enable */ + +/* Anti-spoofing defines */ +#define IXGBE_SPOOF_MACAS_MASK 0xFF +#define IXGBE_SPOOF_VLANAS_MASK 0xFF00 +#define IXGBE_SPOOF_VLANAS_SHIFT 8 +#define IXGBE_SPOOF_ETHERTYPEAS 0xFF000000 +#define IXGBE_SPOOF_ETHERTYPEAS_SHIFT 16 +#define IXGBE_PFVFSPOOF_REG_COUNT 8 + +#define IXGBE_DCA_TXCTRL(_i) (0x07200 + ((_i) * 4)) /* 16 of these (0-15) */ +/* Tx DCA Control register : 128 of these (0-127) */ +#define IXGBE_DCA_TXCTRL_82599(_i) (0x0600C + ((_i) * 0x40)) +#define IXGBE_TIPG 0x0CB00 +#define IXGBE_TXPBSIZE(_i) (0x0CC00 + ((_i) * 4)) /* 8 of these */ +#define IXGBE_MNGTXMAP 0x0CD10 +#define IXGBE_TIPG_FIBER_DEFAULT 3 +#define IXGBE_TXPBSIZE_SHIFT 10 + +/* Wake up registers */ +#define IXGBE_WUC 0x05800 +#define IXGBE_WUFC 0x05808 +#define IXGBE_WUS 0x05810 +#define IXGBE_IPAV 0x05838 +#define IXGBE_IP4AT 0x05840 /* IPv4 table 0x5840-0x5858 */ +#define IXGBE_IP6AT 0x05880 /* IPv6 table 0x5880-0x588F */ + +#define IXGBE_WUPL 0x05900 +#define IXGBE_WUPM 0x05A00 /* wake up pkt memory 0x5A00-0x5A7C */ +#define IXGBE_VXLANCTRL 0x0000507C /* Rx filter VXLAN UDPPORT Register */ +#define IXGBE_FHFT(_n) (0x09000 + ((_n) * 0x100)) /* Flex host filter table */ +#define IXGBE_FHFT_EXT(_n) (0x09800 + ((_n) * 0x100)) /* Ext Flexible Host + * Filter Table */ + +/* masks for accessing VXLAN and GENEVE UDP ports */ +#define IXGBE_VXLANCTRL_VXLAN_UDPPORT_MASK 0x0000ffff /* VXLAN port */ +#define IXGBE_VXLANCTRL_GENEVE_UDPPORT_MASK 0xffff0000 /* GENEVE port */ +#define IXGBE_VXLANCTRL_ALL_UDPPORT_MASK 0xffffffff /* GENEVE/VXLAN */ + +#define IXGBE_VXLANCTRL_GENEVE_UDPPORT_SHIFT 16 + +#define IXGBE_FLEXIBLE_FILTER_COUNT_MAX 4 +#define IXGBE_EXT_FLEXIBLE_FILTER_COUNT_MAX 2 + +/* Each Flexible Filter is at most 128 (0x80) bytes in length */ +#define IXGBE_FLEXIBLE_FILTER_SIZE_MAX 128 +#define IXGBE_FHFT_LENGTH_OFFSET 0xFC /* Length byte in FHFT */ +#define IXGBE_FHFT_LENGTH_MASK 0x0FF /* Length in lower byte */ + +/* Definitions for power management and wakeup registers */ +/* Wake Up Control */ +#define IXGBE_WUC_PME_EN 0x00000002 /* PME Enable */ +#define IXGBE_WUC_PME_STATUS 0x00000004 /* PME Status */ +#define IXGBE_WUC_WKEN 0x00000010 /* Enable PE_WAKE_N pin assertion */ + +/* Wake Up Filter Control */ +#define IXGBE_WUFC_LNKC 0x00000001 /* Link Status Change Wakeup Enable */ +#define IXGBE_WUFC_MAG 0x00000002 /* Magic Packet Wakeup Enable */ +#define IXGBE_WUFC_EX 0x00000004 /* Directed Exact Wakeup Enable */ +#define IXGBE_WUFC_MC 0x00000008 /* Directed Multicast Wakeup Enable */ +#define IXGBE_WUFC_BC 0x00000010 /* Broadcast Wakeup Enable */ +#define IXGBE_WUFC_ARP 0x00000020 /* ARP Request Packet Wakeup Enable */ +#define IXGBE_WUFC_IPV4 0x00000040 /* Directed IPv4 Packet Wakeup Enable */ +#define IXGBE_WUFC_IPV6 0x00000080 /* Directed IPv6 Packet Wakeup Enable */ +#define IXGBE_WUFC_MNG 0x00000100 /* Directed Mgmt Packet Wakeup Enable */ + +#define IXGBE_WUFC_IGNORE_TCO 0x00008000 /* Ignore WakeOn TCO packets */ +#define IXGBE_WUFC_FLX0 0x00010000 /* Flexible Filter 0 Enable */ +#define IXGBE_WUFC_FLX1 0x00020000 /* Flexible Filter 1 Enable */ +#define IXGBE_WUFC_FLX2 0x00040000 /* Flexible Filter 2 Enable */ +#define IXGBE_WUFC_FLX3 0x00080000 /* Flexible Filter 3 Enable */ +#define IXGBE_WUFC_FLX4 0x00100000 /* Flexible Filter 4 Enable */ +#define IXGBE_WUFC_FLX5 0x00200000 /* Flexible Filter 5 Enable */ +#define IXGBE_WUFC_FLX_FILTERS 0x000F0000 /* Mask for 4 flex filters */ +#define IXGBE_WUFC_EXT_FLX_FILTERS 0x00300000 /* Mask for Ext. flex filters */ +#define IXGBE_WUFC_ALL_FILTERS 0x003F00FF /* Mask for all wakeup filters */ +#define IXGBE_WUFC_FLX_OFFSET 16 /* Offset to the Flexible Filters bits */ + +/* Wake Up Status */ +#define IXGBE_WUS_LNKC IXGBE_WUFC_LNKC +#define IXGBE_WUS_MAG IXGBE_WUFC_MAG +#define IXGBE_WUS_EX IXGBE_WUFC_EX +#define IXGBE_WUS_MC IXGBE_WUFC_MC +#define IXGBE_WUS_BC IXGBE_WUFC_BC +#define IXGBE_WUS_ARP IXGBE_WUFC_ARP +#define IXGBE_WUS_IPV4 IXGBE_WUFC_IPV4 +#define IXGBE_WUS_IPV6 IXGBE_WUFC_IPV6 +#define IXGBE_WUS_MNG IXGBE_WUFC_MNG +#define IXGBE_WUS_FLX0 IXGBE_WUFC_FLX0 +#define IXGBE_WUS_FLX1 IXGBE_WUFC_FLX1 +#define IXGBE_WUS_FLX2 IXGBE_WUFC_FLX2 +#define IXGBE_WUS_FLX3 IXGBE_WUFC_FLX3 +#define IXGBE_WUS_FLX4 IXGBE_WUFC_FLX4 +#define IXGBE_WUS_FLX5 IXGBE_WUFC_FLX5 +#define IXGBE_WUS_FLX_FILTERS IXGBE_WUFC_FLX_FILTERS + +/* Wake Up Packet Length */ +#define IXGBE_WUPL_LENGTH_MASK 0xFFFF + +/* DCB registers */ +#define MAX_TRAFFIC_CLASS 8 +#define X540_TRAFFIC_CLASS 4 +#define DEF_TRAFFIC_CLASS 1 +#define IXGBE_RMCS 0x03D00 +#define IXGBE_DPMCS 0x07F40 +#define IXGBE_PDPMCS 0x0CD00 +#define IXGBE_RUPPBMR 0x050A0 +#define IXGBE_RT2CR(_i) (0x03C20 + ((_i) * 4)) /* 8 of these (0-7) */ +#define IXGBE_RT2SR(_i) (0x03C40 + ((_i) * 4)) /* 8 of these (0-7) */ +#define IXGBE_TDTQ2TCCR(_i) (0x0602C + ((_i) * 0x40)) /* 8 of these (0-7) */ +#define IXGBE_TDTQ2TCSR(_i) (0x0622C + ((_i) * 0x40)) /* 8 of these (0-7) */ +#define IXGBE_TDPT2TCCR(_i) (0x0CD20 + ((_i) * 4)) /* 8 of these (0-7) */ +#define IXGBE_TDPT2TCSR(_i) (0x0CD40 + ((_i) * 4)) /* 8 of these (0-7) */ + +/* Security Control Registers */ +#define IXGBE_SECTXCTRL 0x08800 +#define IXGBE_SECTXSTAT 0x08804 +#define IXGBE_SECTXBUFFAF 0x08808 +#define IXGBE_SECTXMINIFG 0x08810 +#define IXGBE_SECRXCTRL 0x08D00 +#define IXGBE_SECRXSTAT 0x08D04 + +/* Security Bit Fields and Masks */ +#define IXGBE_SECTXCTRL_SECTX_DIS 0x00000001 +#define IXGBE_SECTXCTRL_TX_DIS 0x00000002 +#define IXGBE_SECTXCTRL_STORE_FORWARD 0x00000004 + +#define IXGBE_SECTXSTAT_SECTX_RDY 0x00000001 +#define IXGBE_SECTXSTAT_SECTX_OFF_DIS 0x00000002 +#define IXGBE_SECTXSTAT_ECC_TXERR 0x00000004 + +#define IXGBE_SECRXCTRL_SECRX_DIS 0x00000001 +#define IXGBE_SECRXCTRL_RX_DIS 0x00000002 + +#define IXGBE_SECRXSTAT_SECRX_RDY 0x00000001 +#define IXGBE_SECRXSTAT_SECRX_OFF_DIS 0x00000002 +#define IXGBE_SECRXSTAT_ECC_RXERR 0x00000004 + +/* LinkSec (MacSec) Registers */ +#define IXGBE_LSECTXCAP 0x08A00 +#define IXGBE_LSECRXCAP 0x08F00 +#define IXGBE_LSECTXCTRL 0x08A04 +#define IXGBE_LSECTXSCL 0x08A08 /* SCI Low */ +#define IXGBE_LSECTXSCH 0x08A0C /* SCI High */ +#define IXGBE_LSECTXSA 0x08A10 +#define IXGBE_LSECTXPN0 0x08A14 +#define IXGBE_LSECTXPN1 0x08A18 +#define IXGBE_LSECTXKEY0(_n) (0x08A1C + (4 * (_n))) /* 4 of these (0-3) */ +#define IXGBE_LSECTXKEY1(_n) (0x08A2C + (4 * (_n))) /* 4 of these (0-3) */ +#define IXGBE_LSECRXCTRL 0x08F04 +#define IXGBE_LSECRXSCL 0x08F08 +#define IXGBE_LSECRXSCH 0x08F0C +#define IXGBE_LSECRXSA(_i) (0x08F10 + (4 * (_i))) /* 2 of these (0-1) */ +#define IXGBE_LSECRXPN(_i) (0x08F18 + (4 * (_i))) /* 2 of these (0-1) */ +#define IXGBE_LSECRXKEY(_n, _m) (0x08F20 + ((0x10 * (_n)) + (4 * (_m)))) +#define IXGBE_LSECTXUT 0x08A3C /* OutPktsUntagged */ +#define IXGBE_LSECTXPKTE 0x08A40 /* OutPktsEncrypted */ +#define IXGBE_LSECTXPKTP 0x08A44 /* OutPktsProtected */ +#define IXGBE_LSECTXOCTE 0x08A48 /* OutOctetsEncrypted */ +#define IXGBE_LSECTXOCTP 0x08A4C /* OutOctetsProtected */ +#define IXGBE_LSECRXUT 0x08F40 /* InPktsUntagged/InPktsNoTag */ +#define IXGBE_LSECRXOCTD 0x08F44 /* InOctetsDecrypted */ +#define IXGBE_LSECRXOCTV 0x08F48 /* InOctetsValidated */ +#define IXGBE_LSECRXBAD 0x08F4C /* InPktsBadTag */ +#define IXGBE_LSECRXNOSCI 0x08F50 /* InPktsNoSci */ +#define IXGBE_LSECRXUNSCI 0x08F54 /* InPktsUnknownSci */ +#define IXGBE_LSECRXUNCH 0x08F58 /* InPktsUnchecked */ +#define IXGBE_LSECRXDELAY 0x08F5C /* InPktsDelayed */ +#define IXGBE_LSECRXLATE 0x08F60 /* InPktsLate */ +#define IXGBE_LSECRXOK(_n) (0x08F64 + (0x04 * (_n))) /* InPktsOk */ +#define IXGBE_LSECRXINV(_n) (0x08F6C + (0x04 * (_n))) /* InPktsInvalid */ +#define IXGBE_LSECRXNV(_n) (0x08F74 + (0x04 * (_n))) /* InPktsNotValid */ +#define IXGBE_LSECRXUNSA 0x08F7C /* InPktsUnusedSa */ +#define IXGBE_LSECRXNUSA 0x08F80 /* InPktsNotUsingSa */ + +/* LinkSec (MacSec) Bit Fields and Masks */ +#define IXGBE_LSECTXCAP_SUM_MASK 0x00FF0000 +#define IXGBE_LSECTXCAP_SUM_SHIFT 16 +#define IXGBE_LSECRXCAP_SUM_MASK 0x00FF0000 +#define IXGBE_LSECRXCAP_SUM_SHIFT 16 + +#define IXGBE_LSECTXCTRL_EN_MASK 0x00000003 +#define IXGBE_LSECTXCTRL_DISABLE 0x0 +#define IXGBE_LSECTXCTRL_AUTH 0x1 +#define IXGBE_LSECTXCTRL_AUTH_ENCRYPT 0x2 +#define IXGBE_LSECTXCTRL_AISCI 0x00000020 +#define IXGBE_LSECTXCTRL_PNTHRSH_MASK 0xFFFFFF00 +#define IXGBE_LSECTXCTRL_RSV_MASK 0x000000D8 + +#define IXGBE_LSECRXCTRL_EN_MASK 0x0000000C +#define IXGBE_LSECRXCTRL_EN_SHIFT 2 +#define IXGBE_LSECRXCTRL_DISABLE 0x0 +#define IXGBE_LSECRXCTRL_CHECK 0x1 +#define IXGBE_LSECRXCTRL_STRICT 0x2 +#define IXGBE_LSECRXCTRL_DROP 0x3 +#define IXGBE_LSECRXCTRL_PLSH 0x00000040 +#define IXGBE_LSECRXCTRL_RP 0x00000080 +#define IXGBE_LSECRXCTRL_RSV_MASK 0xFFFFFF33 + +/* IpSec Registers */ +#define IXGBE_IPSTXIDX 0x08900 +#define IXGBE_IPSTXSALT 0x08904 +#define IXGBE_IPSTXKEY(_i) (0x08908 + (4 * (_i))) /* 4 of these (0-3) */ +#define IXGBE_IPSRXIDX 0x08E00 +#define IXGBE_IPSRXIPADDR(_i) (0x08E04 + (4 * (_i))) /* 4 of these (0-3) */ +#define IXGBE_IPSRXSPI 0x08E14 +#define IXGBE_IPSRXIPIDX 0x08E18 +#define IXGBE_IPSRXKEY(_i) (0x08E1C + (4 * (_i))) /* 4 of these (0-3) */ +#define IXGBE_IPSRXSALT 0x08E2C +#define IXGBE_IPSRXMOD 0x08E30 + +#define IXGBE_SECTXCTRL_STORE_FORWARD_ENABLE 0x4 + +/* DCB registers */ +#define IXGBE_RTRPCS 0x02430 +#define IXGBE_RTTDCS 0x04900 +#define IXGBE_RTTDCS_ARBDIS 0x00000040 /* DCB arbiter disable */ +#define IXGBE_RTTPCS 0x0CD00 +#define IXGBE_RTRUP2TC 0x03020 +#define IXGBE_RTTUP2TC 0x0C800 +#define IXGBE_RTRPT4C(_i) (0x02140 + ((_i) * 4)) /* 8 of these (0-7) */ +#define IXGBE_TXLLQ(_i) (0x082E0 + ((_i) * 4)) /* 4 of these (0-3) */ +#define IXGBE_RTRPT4S(_i) (0x02160 + ((_i) * 4)) /* 8 of these (0-7) */ +#define IXGBE_RTTDT2C(_i) (0x04910 + ((_i) * 4)) /* 8 of these (0-7) */ +#define IXGBE_RTTDT2S(_i) (0x04930 + ((_i) * 4)) /* 8 of these (0-7) */ +#define IXGBE_RTTPT2C(_i) (0x0CD20 + ((_i) * 4)) /* 8 of these (0-7) */ +#define IXGBE_RTTPT2S(_i) (0x0CD40 + ((_i) * 4)) /* 8 of these (0-7) */ +#define IXGBE_RTTDQSEL 0x04904 +#define IXGBE_RTTDT1C 0x04908 +#define IXGBE_RTTDT1S 0x0490C +#define IXGBE_RTTQCNCR 0x08B00 +#define IXGBE_RTTQCNTG 0x04A90 +#define IXGBE_RTTBCNRD 0x0498C +#define IXGBE_RTTQCNRR 0x0498C +#define IXGBE_RTTDTECC 0x04990 +#define IXGBE_RTTDTECC_NO_BCN 0x00000100 +#define IXGBE_RTTBCNRC 0x04984 +#define IXGBE_RTTBCNRC_RS_ENA 0x80000000 +#define IXGBE_RTTBCNRC_RF_DEC_MASK 0x00003FFF +#define IXGBE_RTTBCNRC_RF_INT_SHIFT 14 +#define IXGBE_RTTBCNRC_RF_INT_MASK \ + (IXGBE_RTTBCNRC_RF_DEC_MASK << IXGBE_RTTBCNRC_RF_INT_SHIFT) +#define IXGBE_RTTBCNRM 0x04980 +#define IXGBE_RTTQCNRM 0x04980 + +/* FCoE Direct DMA Context */ +#define IXGBE_FCDDC(_i, _j) (0x20000 + ((_i) * 0x4) + ((_j) * 0x10)) +/* FCoE DMA Context Registers */ +#define IXGBE_FCPTRL 0x02410 /* FC User Desc. PTR Low */ +#define IXGBE_FCPTRH 0x02414 /* FC USer Desc. PTR High */ +#define IXGBE_FCBUFF 0x02418 /* FC Buffer Control */ +#define IXGBE_FCDMARW 0x02420 /* FC Receive DMA RW */ +#define IXGBE_FCINVST0 0x03FC0 /* FC Invalid DMA Context Status Reg 0 */ +#define IXGBE_FCINVST(_i) (IXGBE_FCINVST0 + ((_i) * 4)) +#define IXGBE_FCBUFF_VALID BIT(0) /* DMA Context Valid */ +#define IXGBE_FCBUFF_BUFFSIZE (3u << 3) /* User Buffer Size */ +#define IXGBE_FCBUFF_WRCONTX BIT(7) /* 0: Initiator, 1: Target */ +#define IXGBE_FCBUFF_BUFFCNT 0x0000ff00 /* Number of User Buffers */ +#define IXGBE_FCBUFF_OFFSET 0xffff0000 /* User Buffer Offset */ +#define IXGBE_FCBUFF_BUFFSIZE_SHIFT 3 +#define IXGBE_FCBUFF_BUFFCNT_SHIFT 8 +#define IXGBE_FCBUFF_OFFSET_SHIFT 16 +#define IXGBE_FCDMARW_WE BIT(14) /* Write enable */ +#define IXGBE_FCDMARW_RE BIT(15) /* Read enable */ +#define IXGBE_FCDMARW_FCOESEL 0x000001ff /* FC X_ID: 11 bits */ +#define IXGBE_FCDMARW_LASTSIZE 0xffff0000 /* Last User Buffer Size */ +#define IXGBE_FCDMARW_LASTSIZE_SHIFT 16 + +/* FCoE SOF/EOF */ +#define IXGBE_TEOFF 0x04A94 /* Tx FC EOF */ +#define IXGBE_TSOFF 0x04A98 /* Tx FC SOF */ +#define IXGBE_REOFF 0x05158 /* Rx FC EOF */ +#define IXGBE_RSOFF 0x051F8 /* Rx FC SOF */ +/* FCoE Direct Filter Context */ +#define IXGBE_FCDFC(_i, _j) (0x28000 + ((_i) * 0x4) + ((_j) * 0x10)) +#define IXGBE_FCDFCD(_i) (0x30000 + ((_i) * 0x4)) +/* FCoE Filter Context Registers */ +#define IXGBE_FCFLT 0x05108 /* FC FLT Context */ +#define IXGBE_FCFLTRW 0x05110 /* FC Filter RW Control */ +#define IXGBE_FCPARAM 0x051d8 /* FC Offset Parameter */ +#define IXGBE_FCFLT_VALID BIT(0) /* Filter Context Valid */ +#define IXGBE_FCFLT_FIRST BIT(1) /* Filter First */ +#define IXGBE_FCFLT_SEQID 0x00ff0000 /* Sequence ID */ +#define IXGBE_FCFLT_SEQCNT 0xff000000 /* Sequence Count */ +#define IXGBE_FCFLTRW_RVALDT BIT(13) /* Fast Re-Validation */ +#define IXGBE_FCFLTRW_WE BIT(14) /* Write Enable */ +#define IXGBE_FCFLTRW_RE BIT(15) /* Read Enable */ +/* FCoE Receive Control */ +#define IXGBE_FCRXCTRL 0x05100 /* FC Receive Control */ +#define IXGBE_FCRXCTRL_FCOELLI BIT(0) /* Low latency interrupt */ +#define IXGBE_FCRXCTRL_SAVBAD BIT(1) /* Save Bad Frames */ +#define IXGBE_FCRXCTRL_FRSTRDH BIT(2) /* EN 1st Read Header */ +#define IXGBE_FCRXCTRL_LASTSEQH BIT(3) /* EN Last Header in Seq */ +#define IXGBE_FCRXCTRL_ALLH BIT(4) /* EN All Headers */ +#define IXGBE_FCRXCTRL_FRSTSEQH BIT(5) /* EN 1st Seq. Header */ +#define IXGBE_FCRXCTRL_ICRC BIT(6) /* Ignore Bad FC CRC */ +#define IXGBE_FCRXCTRL_FCCRCBO BIT(7) /* FC CRC Byte Ordering */ +#define IXGBE_FCRXCTRL_FCOEVER 0x00000f00 /* FCoE Version: 4 bits */ +#define IXGBE_FCRXCTRL_FCOEVER_SHIFT 8 +/* FCoE Redirection */ +#define IXGBE_FCRECTL 0x0ED00 /* FC Redirection Control */ +#define IXGBE_FCRETA0 0x0ED10 /* FC Redirection Table 0 */ +#define IXGBE_FCRETA(_i) (IXGBE_FCRETA0 + ((_i) * 4)) /* FCoE Redir */ +#define IXGBE_FCRECTL_ENA 0x1 /* FCoE Redir Table Enable */ +#define IXGBE_FCRETA_SIZE 8 /* Max entries in FCRETA */ +#define IXGBE_FCRETA_ENTRY_MASK 0x0000007f /* 7 bits for the queue index */ +#define IXGBE_FCRETA_SIZE_X550 32 /* Max entries in FCRETA */ +/* Higher 7 bits for the queue index */ +#define IXGBE_FCRETA_ENTRY_HIGH_MASK 0x007F0000 +#define IXGBE_FCRETA_ENTRY_HIGH_SHIFT 16 + +/* Stats registers */ +#define IXGBE_CRCERRS 0x04000 +#define IXGBE_ILLERRC 0x04004 +#define IXGBE_ERRBC 0x04008 +#define IXGBE_MSPDC 0x04010 +#define IXGBE_MPC(_i) (0x03FA0 + ((_i) * 4)) /* 8 of these 3FA0-3FBC*/ +#define IXGBE_MLFC 0x04034 +#define IXGBE_MRFC 0x04038 +#define IXGBE_RLEC 0x04040 +#define IXGBE_LXONTXC 0x03F60 +#define IXGBE_LXONRXC 0x0CF60 +#define IXGBE_LXOFFTXC 0x03F68 +#define IXGBE_LXOFFRXC 0x0CF68 +#define IXGBE_LXONRXCNT 0x041A4 +#define IXGBE_LXOFFRXCNT 0x041A8 +#define IXGBE_PXONRXCNT(_i) (0x04140 + ((_i) * 4)) /* 8 of these */ +#define IXGBE_PXOFFRXCNT(_i) (0x04160 + ((_i) * 4)) /* 8 of these */ +#define IXGBE_PXON2OFFCNT(_i) (0x03240 + ((_i) * 4)) /* 8 of these */ +#define IXGBE_PXONTXC(_i) (0x03F00 + ((_i) * 4)) /* 8 of these 3F00-3F1C*/ +#define IXGBE_PXONRXC(_i) (0x0CF00 + ((_i) * 4)) /* 8 of these CF00-CF1C*/ +#define IXGBE_PXOFFTXC(_i) (0x03F20 + ((_i) * 4)) /* 8 of these 3F20-3F3C*/ +#define IXGBE_PXOFFRXC(_i) (0x0CF20 + ((_i) * 4)) /* 8 of these CF20-CF3C*/ +#define IXGBE_PRC64 0x0405C +#define IXGBE_PRC127 0x04060 +#define IXGBE_PRC255 0x04064 +#define IXGBE_PRC511 0x04068 +#define IXGBE_PRC1023 0x0406C +#define IXGBE_PRC1522 0x04070 +#define IXGBE_GPRC 0x04074 +#define IXGBE_BPRC 0x04078 +#define IXGBE_MPRC 0x0407C +#define IXGBE_GPTC 0x04080 +#define IXGBE_GORCL 0x04088 +#define IXGBE_GORCH 0x0408C +#define IXGBE_GOTCL 0x04090 +#define IXGBE_GOTCH 0x04094 +#define IXGBE_RNBC(_i) (0x03FC0 + ((_i) * 4)) /* 8 of these 3FC0-3FDC*/ +#define IXGBE_RUC 0x040A4 +#define IXGBE_RFC 0x040A8 +#define IXGBE_ROC 0x040AC +#define IXGBE_RJC 0x040B0 +#define IXGBE_MNGPRC 0x040B4 +#define IXGBE_MNGPDC 0x040B8 +#define IXGBE_MNGPTC 0x0CF90 +#define IXGBE_TORL 0x040C0 +#define IXGBE_TORH 0x040C4 +#define IXGBE_TPR 0x040D0 +#define IXGBE_TPT 0x040D4 +#define IXGBE_PTC64 0x040D8 +#define IXGBE_PTC127 0x040DC +#define IXGBE_PTC255 0x040E0 +#define IXGBE_PTC511 0x040E4 +#define IXGBE_PTC1023 0x040E8 +#define IXGBE_PTC1522 0x040EC +#define IXGBE_MPTC 0x040F0 +#define IXGBE_BPTC 0x040F4 +#define IXGBE_XEC 0x04120 +#define IXGBE_SSVPC 0x08780 + +#define IXGBE_RQSMR(_i) (0x02300 + ((_i) * 4)) +#define IXGBE_TQSMR(_i) (((_i) <= 7) ? (0x07300 + ((_i) * 4)) : \ + (0x08600 + ((_i) * 4))) +#define IXGBE_TQSM(_i) (0x08600 + ((_i) * 4)) + +#define IXGBE_QPRC(_i) (0x01030 + ((_i) * 0x40)) /* 16 of these */ +#define IXGBE_QPTC(_i) (0x06030 + ((_i) * 0x40)) /* 16 of these */ +#define IXGBE_QBRC(_i) (0x01034 + ((_i) * 0x40)) /* 16 of these */ +#define IXGBE_QBTC(_i) (0x06034 + ((_i) * 0x40)) /* 16 of these */ +#define IXGBE_QBRC_L(_i) (0x01034 + ((_i) * 0x40)) /* 16 of these */ +#define IXGBE_QBRC_H(_i) (0x01038 + ((_i) * 0x40)) /* 16 of these */ +#define IXGBE_QPRDC(_i) (0x01430 + ((_i) * 0x40)) /* 16 of these */ +#define IXGBE_QBTC_L(_i) (0x08700 + ((_i) * 0x8)) /* 16 of these */ +#define IXGBE_QBTC_H(_i) (0x08704 + ((_i) * 0x8)) /* 16 of these */ +#define IXGBE_FCCRC 0x05118 /* Count of Good Eth CRC w/ Bad FC CRC */ +#define IXGBE_FCOERPDC 0x0241C /* FCoE Rx Packets Dropped Count */ +#define IXGBE_FCLAST 0x02424 /* FCoE Last Error Count */ +#define IXGBE_FCOEPRC 0x02428 /* Number of FCoE Packets Received */ +#define IXGBE_FCOEDWRC 0x0242C /* Number of FCoE DWords Received */ +#define IXGBE_FCOEPTC 0x08784 /* Number of FCoE Packets Transmitted */ +#define IXGBE_FCOEDWTC 0x08788 /* Number of FCoE DWords Transmitted */ +#define IXGBE_O2BGPTC 0x041C4 +#define IXGBE_O2BSPC 0x087B0 +#define IXGBE_B2OSPC 0x041C0 +#define IXGBE_B2OGPRC 0x02F90 +#define IXGBE_PCRC8ECL 0x0E810 +#define IXGBE_PCRC8ECH 0x0E811 +#define IXGBE_PCRC8ECH_MASK 0x1F +#define IXGBE_LDPCECL 0x0E820 +#define IXGBE_LDPCECH 0x0E821 + +/* MII clause 22/28 definitions */ +#define IXGBE_MDIO_PHY_LOW_POWER_MODE 0x0800 + +#define IXGBE_MDIO_XENPAK_LASI_STATUS 0x9005 /* XENPAK LASI Status register */ +#define IXGBE_XENPAK_LASI_LINK_STATUS_ALARM 0x1 /* Link Status Alarm change */ + +#define IXGBE_MDIO_AUTO_NEG_LINK_STATUS 0x4 /* Indicates if link is up */ + +#define IXGBE_MDIO_AUTO_NEG_VENDOR_STATUS_MASK 0x7 /* Speed/Duplex Mask */ +#define IXGBE_MDIO_AUTO_NEG_VEN_STAT_SPEED_MASK 0x6 /* Speed Mask */ +#define IXGBE_MDIO_AUTO_NEG_VENDOR_STATUS_10M_HALF 0x0 /* 10Mb/s Half Duplex */ +#define IXGBE_MDIO_AUTO_NEG_VENDOR_STATUS_10M_FULL 0x1 /* 10Mb/s Full Duplex */ +#define IXGBE_MDIO_AUTO_NEG_VENDOR_STATUS_100M_HALF 0x2 /* 100Mb/s H Duplex */ +#define IXGBE_MDIO_AUTO_NEG_VENDOR_STATUS_100M_FULL 0x3 /* 100Mb/s F Duplex */ +#define IXGBE_MDIO_AUTO_NEG_VENDOR_STATUS_1GB_HALF 0x4 /* 1Gb/s Half Duplex */ +#define IXGBE_MDIO_AUTO_NEG_VENDOR_STATUS_1GB_FULL 0x5 /* 1Gb/s Full Duplex */ +#define IXGBE_MDIO_AUTO_NEG_VENDOR_STATUS_10GB_HALF 0x6 /* 10Gb/s Half Duplex */ +#define IXGBE_MDIO_AUTO_NEG_VENDOR_STATUS_10GB_FULL 0x7 /* 10Gb/s Full Duplex */ +#define IXGBE_MDIO_AUTO_NEG_VENDOR_STATUS_1GB 0x4 /* 1Gb/s */ +#define IXGBE_MDIO_AUTO_NEG_VENDOR_STATUS_10GB 0x6 /* 10Gb/s */ + +#define IXGBE_MII_AUTONEG_VENDOR_PROVISION_1_REG 0xC400 /* 1G Provisioning 1 */ +#define IXGBE_MII_AUTONEG_XNP_TX_REG 0x17 /* 1G XNP Transmit */ +#define IXGBE_MII_1GBASE_T_ADVERTISE_XNP_TX 0x4000 /* full duplex, bit:14*/ +#define IXGBE_MII_1GBASE_T_ADVERTISE 0x8000 /* full duplex, bit:15*/ +#define IXGBE_MII_2_5GBASE_T_ADVERTISE 0x0400 +#define IXGBE_MII_5GBASE_T_ADVERTISE 0x0800 +#define IXGBE_MII_RESTART 0x200 +#define IXGBE_MII_AUTONEG_LINK_UP 0x04 +#define IXGBE_MII_AUTONEG_REG 0x0 + +/* Management */ +#define IXGBE_MAVTV(_i) (0x05010 + ((_i) * 4)) /* 8 of these (0-7) */ +#define IXGBE_MFUTP(_i) (0x05030 + ((_i) * 4)) /* 8 of these (0-7) */ +#define IXGBE_MANC 0x05820 +#define IXGBE_MFVAL 0x05824 +#define IXGBE_MANC2H 0x05860 +#define IXGBE_MDEF(_i) (0x05890 + ((_i) * 4)) /* 8 of these (0-7) */ +#define IXGBE_MIPAF 0x058B0 +#define IXGBE_MMAL(_i) (0x05910 + ((_i) * 8)) /* 4 of these (0-3) */ +#define IXGBE_MMAH(_i) (0x05914 + ((_i) * 8)) /* 4 of these (0-3) */ +#define IXGBE_FTFT 0x09400 /* 0x9400-0x97FC */ +#define IXGBE_METF(_i) (0x05190 + ((_i) * 4)) /* 4 of these (0-3) */ +#define IXGBE_MDEF_EXT(_i) (0x05160 + ((_i) * 4)) /* 8 of these (0-7) */ +#define IXGBE_LSWFW 0x15014 + +/* Management Bit Fields and Masks */ +#define IXGBE_MANC_RCV_TCO_EN 0x00020000 /* Rcv TCO packet enable */ + +/* Firmware Semaphore Register */ +#define IXGBE_FWSM_MODE_MASK 0xE +#define IXGBE_FWSM_FW_MODE_PT 0x4 +#define IXGBE_FWSM_FW_NVM_RECOVERY_MODE BIT(5) +#define IXGBE_FWSM_EXT_ERR_IND_MASK 0x01F80000 +#define IXGBE_FWSM_FW_VAL_BIT BIT(15) + +/* ARC Subsystem registers */ +#define IXGBE_HICR 0x15F00 +#define IXGBE_FWSTS 0x15F0C +#define IXGBE_HSMC0R 0x15F04 +#define IXGBE_HSMC1R 0x15F08 +#define IXGBE_SWSR 0x15F10 +#define IXGBE_HFDR 0x15FE8 +#define IXGBE_FLEX_MNG 0x15800 /* 0x15800 - 0x15EFC */ + +#define IXGBE_HICR_EN 0x01 /* Enable bit - RO */ +/* Driver sets this bit when done to put command in RAM */ +#define IXGBE_HICR_C 0x02 +#define IXGBE_HICR_SV 0x04 /* Status Validity */ +#define IXGBE_HICR_FW_RESET_ENABLE 0x40 +#define IXGBE_HICR_FW_RESET 0x80 + +/* PCI-E registers */ +#define IXGBE_GCR 0x11000 +#define IXGBE_GTV 0x11004 +#define IXGBE_FUNCTAG 0x11008 +#define IXGBE_GLT 0x1100C +#define IXGBE_GSCL_1 0x11010 +#define IXGBE_GSCL_2 0x11014 +#define IXGBE_GSCL_3 0x11018 +#define IXGBE_GSCL_4 0x1101C +#define IXGBE_GSCN_0 0x11020 +#define IXGBE_GSCN_1 0x11024 +#define IXGBE_GSCN_2 0x11028 +#define IXGBE_GSCN_3 0x1102C +#define IXGBE_FACTPS_8259X 0x10150 +#define IXGBE_FACTPS_X540 IXGBE_FACTPS_8259X +#define IXGBE_FACTPS_X550 IXGBE_FACTPS_8259X +#define IXGBE_FACTPS_X550EM_x IXGBE_FACTPS_8259X +#define IXGBE_FACTPS_X550EM_a 0x15FEC +#define IXGBE_FACTPS(_hw) IXGBE_BY_MAC((_hw), FACTPS) + +#define IXGBE_PCIEANACTL 0x11040 +#define IXGBE_SWSM_8259X 0x10140 +#define IXGBE_SWSM_X540 IXGBE_SWSM_8259X +#define IXGBE_SWSM_X550 IXGBE_SWSM_8259X +#define IXGBE_SWSM_X550EM_x IXGBE_SWSM_8259X +#define IXGBE_SWSM_X550EM_a 0x15F70 +#define IXGBE_SWSM(_hw) IXGBE_BY_MAC((_hw), SWSM) +#define IXGBE_FWSM_8259X 0x10148 +#define IXGBE_FWSM_X540 IXGBE_FWSM_8259X +#define IXGBE_FWSM_X550 IXGBE_FWSM_8259X +#define IXGBE_FWSM_X550EM_x IXGBE_FWSM_8259X +#define IXGBE_FWSM_X550EM_a 0x15F74 +#define IXGBE_FWSM(_hw) IXGBE_BY_MAC((_hw), FWSM) +#define IXGBE_GSSR 0x10160 +#define IXGBE_MREVID 0x11064 +#define IXGBE_DCA_ID 0x11070 +#define IXGBE_DCA_CTRL 0x11074 +#define IXGBE_SWFW_SYNC_8259X IXGBE_GSSR +#define IXGBE_SWFW_SYNC_X540 IXGBE_SWFW_SYNC_8259X +#define IXGBE_SWFW_SYNC_X550 IXGBE_SWFW_SYNC_8259X +#define IXGBE_SWFW_SYNC_X550EM_x IXGBE_SWFW_SYNC_8259X +#define IXGBE_SWFW_SYNC_X550EM_a 0x15F78 +#define IXGBE_SWFW_SYNC(_hw) IXGBE_BY_MAC((_hw), SWFW_SYNC) + +/* PCIe registers 82599-specific */ +#define IXGBE_GCR_EXT 0x11050 +#define IXGBE_GSCL_5_82599 0x11030 +#define IXGBE_GSCL_6_82599 0x11034 +#define IXGBE_GSCL_7_82599 0x11038 +#define IXGBE_GSCL_8_82599 0x1103C +#define IXGBE_PHYADR_82599 0x11040 +#define IXGBE_PHYDAT_82599 0x11044 +#define IXGBE_PHYCTL_82599 0x11048 +#define IXGBE_PBACLR_82599 0x11068 + +#define IXGBE_CIAA_8259X 0x11088 +#define IXGBE_CIAA_X540 IXGBE_CIAA_8259X +#define IXGBE_CIAA_X550 0x11508 +#define IXGBE_CIAA_X550EM_x IXGBE_CIAA_X550 +#define IXGBE_CIAA_X550EM_a IXGBE_CIAA_X550 +#define IXGBE_CIAA(_hw) IXGBE_BY_MAC((_hw), CIAA) + +#define IXGBE_CIAD_8259X 0x1108C +#define IXGBE_CIAD_X540 IXGBE_CIAD_8259X +#define IXGBE_CIAD_X550 0x11510 +#define IXGBE_CIAD_X550EM_x IXGBE_CIAD_X550 +#define IXGBE_CIAD_X550EM_a IXGBE_CIAD_X550 +#define IXGBE_CIAD(_hw) IXGBE_BY_MAC((_hw), CIAD) + +#define IXGBE_PICAUSE 0x110B0 +#define IXGBE_PIENA 0x110B8 +#define IXGBE_CDQ_MBR_82599 0x110B4 +#define IXGBE_PCIESPARE 0x110BC +#define IXGBE_MISC_REG_82599 0x110F0 +#define IXGBE_ECC_CTRL_0_82599 0x11100 +#define IXGBE_ECC_CTRL_1_82599 0x11104 +#define IXGBE_ECC_STATUS_82599 0x110E0 +#define IXGBE_BAR_CTRL_82599 0x110F4 + +/* PCI Express Control */ +#define IXGBE_GCR_CMPL_TMOUT_MASK 0x0000F000 +#define IXGBE_GCR_CMPL_TMOUT_10ms 0x00001000 +#define IXGBE_GCR_CMPL_TMOUT_RESEND 0x00010000 +#define IXGBE_GCR_CAP_VER2 0x00040000 + +#define IXGBE_GCR_EXT_MSIX_EN 0x80000000 +#define IXGBE_GCR_EXT_BUFFERS_CLEAR 0x40000000 +#define IXGBE_GCR_EXT_VT_MODE_16 0x00000001 +#define IXGBE_GCR_EXT_VT_MODE_32 0x00000002 +#define IXGBE_GCR_EXT_VT_MODE_64 0x00000003 +#define IXGBE_GCR_EXT_SRIOV (IXGBE_GCR_EXT_MSIX_EN | \ + IXGBE_GCR_EXT_VT_MODE_64) + +/* Time Sync Registers */ +#define IXGBE_TSYNCRXCTL 0x05188 /* Rx Time Sync Control register - RW */ +#define IXGBE_TSYNCTXCTL 0x08C00 /* Tx Time Sync Control register - RW */ +#define IXGBE_RXSTMPL 0x051E8 /* Rx timestamp Low - RO */ +#define IXGBE_RXSTMPH 0x051A4 /* Rx timestamp High - RO */ +#define IXGBE_RXSATRL 0x051A0 /* Rx timestamp attribute low - RO */ +#define IXGBE_RXSATRH 0x051A8 /* Rx timestamp attribute high - RO */ +#define IXGBE_RXMTRL 0x05120 /* RX message type register low - RW */ +#define IXGBE_TXSTMPL 0x08C04 /* Tx timestamp value Low - RO */ +#define IXGBE_TXSTMPH 0x08C08 /* Tx timestamp value High - RO */ +#define IXGBE_SYSTIML 0x08C0C /* System time register Low - RO */ +#define IXGBE_SYSTIMH 0x08C10 /* System time register High - RO */ +#define IXGBE_SYSTIMR 0x08C58 /* System time register Residue - RO */ +#define IXGBE_TIMINCA 0x08C14 /* Increment attributes register - RW */ +#define IXGBE_TIMADJL 0x08C18 /* Time Adjustment Offset register Low - RW */ +#define IXGBE_TIMADJH 0x08C1C /* Time Adjustment Offset register High - RW */ +#define IXGBE_TSAUXC 0x08C20 /* TimeSync Auxiliary Control register - RW */ +#define IXGBE_TRGTTIML0 0x08C24 /* Target Time Register 0 Low - RW */ +#define IXGBE_TRGTTIMH0 0x08C28 /* Target Time Register 0 High - RW */ +#define IXGBE_TRGTTIML1 0x08C2C /* Target Time Register 1 Low - RW */ +#define IXGBE_TRGTTIMH1 0x08C30 /* Target Time Register 1 High - RW */ +#define IXGBE_CLKTIML 0x08C34 /* Clock Out Time Register Low - RW */ +#define IXGBE_CLKTIMH 0x08C38 /* Clock Out Time Register High - RW */ +#define IXGBE_FREQOUT0 0x08C34 /* Frequency Out 0 Control register - RW */ +#define IXGBE_FREQOUT1 0x08C38 /* Frequency Out 1 Control register - RW */ +#define IXGBE_AUXSTMPL0 0x08C3C /* Auxiliary Time Stamp 0 register Low - RO */ +#define IXGBE_AUXSTMPH0 0x08C40 /* Auxiliary Time Stamp 0 register High - RO */ +#define IXGBE_AUXSTMPL1 0x08C44 /* Auxiliary Time Stamp 1 register Low - RO */ +#define IXGBE_AUXSTMPH1 0x08C48 /* Auxiliary Time Stamp 1 register High - RO */ +#define IXGBE_TSIM 0x08C68 /* TimeSync Interrupt Mask Register - RW */ +#define IXGBE_TSSDP 0x0003C /* TimeSync SDP Configuration Register - RW */ + +/* Diagnostic Registers */ +#define IXGBE_RDSTATCTL 0x02C20 +#define IXGBE_RDSTAT(_i) (0x02C00 + ((_i) * 4)) /* 0x02C00-0x02C1C */ +#define IXGBE_RDHMPN 0x02F08 +#define IXGBE_RIC_DW(_i) (0x02F10 + ((_i) * 4)) +#define IXGBE_RDPROBE 0x02F20 +#define IXGBE_RDMAM 0x02F30 +#define IXGBE_RDMAD 0x02F34 +#define IXGBE_TDSTATCTL 0x07C20 +#define IXGBE_TDSTAT(_i) (0x07C00 + ((_i) * 4)) /* 0x07C00 - 0x07C1C */ +#define IXGBE_TDHMPN 0x07F08 +#define IXGBE_TDHMPN2 0x082FC +#define IXGBE_TXDESCIC 0x082CC +#define IXGBE_TIC_DW(_i) (0x07F10 + ((_i) * 4)) +#define IXGBE_TIC_DW2(_i) (0x082B0 + ((_i) * 4)) +#define IXGBE_TDPROBE 0x07F20 +#define IXGBE_TXBUFCTRL 0x0C600 +#define IXGBE_TXBUFDATA(_i) (0x0C610 + ((_i) * 4)) /* 4 of these (0-3) */ +#define IXGBE_RXBUFCTRL 0x03600 +#define IXGBE_RXBUFDATA(_i) (0x03610 + ((_i) * 4)) /* 4 of these (0-3) */ +#define IXGBE_PCIE_DIAG(_i) (0x11090 + ((_i) * 4)) /* 8 of these */ +#define IXGBE_RFVAL 0x050A4 +#define IXGBE_MDFTC1 0x042B8 +#define IXGBE_MDFTC2 0x042C0 +#define IXGBE_MDFTFIFO1 0x042C4 +#define IXGBE_MDFTFIFO2 0x042C8 +#define IXGBE_MDFTS 0x042CC +#define IXGBE_RXDATAWRPTR(_i) (0x03700 + ((_i) * 4)) /* 8 of these 3700-370C*/ +#define IXGBE_RXDESCWRPTR(_i) (0x03710 + ((_i) * 4)) /* 8 of these 3710-371C*/ +#define IXGBE_RXDATARDPTR(_i) (0x03720 + ((_i) * 4)) /* 8 of these 3720-372C*/ +#define IXGBE_RXDESCRDPTR(_i) (0x03730 + ((_i) * 4)) /* 8 of these 3730-373C*/ +#define IXGBE_TXDATAWRPTR(_i) (0x0C700 + ((_i) * 4)) /* 8 of these C700-C70C*/ +#define IXGBE_TXDESCWRPTR(_i) (0x0C710 + ((_i) * 4)) /* 8 of these C710-C71C*/ +#define IXGBE_TXDATARDPTR(_i) (0x0C720 + ((_i) * 4)) /* 8 of these C720-C72C*/ +#define IXGBE_TXDESCRDPTR(_i) (0x0C730 + ((_i) * 4)) /* 8 of these C730-C73C*/ +#define IXGBE_PCIEECCCTL 0x1106C +#define IXGBE_RXWRPTR(_i) (0x03100 + ((_i) * 4)) /* 8 of these 3100-310C*/ +#define IXGBE_RXUSED(_i) (0x03120 + ((_i) * 4)) /* 8 of these 3120-312C*/ +#define IXGBE_RXRDPTR(_i) (0x03140 + ((_i) * 4)) /* 8 of these 3140-314C*/ +#define IXGBE_RXRDWRPTR(_i) (0x03160 + ((_i) * 4)) /* 8 of these 3160-310C*/ +#define IXGBE_TXWRPTR(_i) (0x0C100 + ((_i) * 4)) /* 8 of these C100-C10C*/ +#define IXGBE_TXUSED(_i) (0x0C120 + ((_i) * 4)) /* 8 of these C120-C12C*/ +#define IXGBE_TXRDPTR(_i) (0x0C140 + ((_i) * 4)) /* 8 of these C140-C14C*/ +#define IXGBE_TXRDWRPTR(_i) (0x0C160 + ((_i) * 4)) /* 8 of these C160-C10C*/ +#define IXGBE_PCIEECCCTL0 0x11100 +#define IXGBE_PCIEECCCTL1 0x11104 +#define IXGBE_RXDBUECC 0x03F70 +#define IXGBE_TXDBUECC 0x0CF70 +#define IXGBE_RXDBUEST 0x03F74 +#define IXGBE_TXDBUEST 0x0CF74 +#define IXGBE_PBTXECC 0x0C300 +#define IXGBE_PBRXECC 0x03300 +#define IXGBE_GHECCR 0x110B0 + +/* MAC Registers */ +#define IXGBE_PCS1GCFIG 0x04200 +#define IXGBE_PCS1GLCTL 0x04208 +#define IXGBE_PCS1GLSTA 0x0420C +#define IXGBE_PCS1GDBG0 0x04210 +#define IXGBE_PCS1GDBG1 0x04214 +#define IXGBE_PCS1GANA 0x04218 +#define IXGBE_PCS1GANLP 0x0421C +#define IXGBE_PCS1GANNP 0x04220 +#define IXGBE_PCS1GANLPNP 0x04224 +#define IXGBE_HLREG0 0x04240 +#define IXGBE_HLREG1 0x04244 +#define IXGBE_PAP 0x04248 +#define IXGBE_MACA 0x0424C +#define IXGBE_APAE 0x04250 +#define IXGBE_ARD 0x04254 +#define IXGBE_AIS 0x04258 +#define IXGBE_MSCA 0x0425C +#define IXGBE_MSRWD 0x04260 +#define IXGBE_MLADD 0x04264 +#define IXGBE_MHADD 0x04268 +#define IXGBE_MAXFRS 0x04268 +#define IXGBE_TREG 0x0426C +#define IXGBE_PCSS1 0x04288 +#define IXGBE_PCSS2 0x0428C +#define IXGBE_XPCSS 0x04290 +#define IXGBE_MFLCN 0x04294 +#define IXGBE_SERDESC 0x04298 +#define IXGBE_MAC_SGMII_BUSY 0x04298 +#define IXGBE_MACS 0x0429C +#define IXGBE_AUTOC 0x042A0 +#define IXGBE_LINKS 0x042A4 +#define IXGBE_LINKS2 0x04324 +#define IXGBE_AUTOC2 0x042A8 +#define IXGBE_AUTOC3 0x042AC +#define IXGBE_ANLP1 0x042B0 +#define IXGBE_ANLP2 0x042B4 +#define IXGBE_MACC 0x04330 +#define IXGBE_ATLASCTL 0x04800 +#define IXGBE_MMNGC 0x042D0 +#define IXGBE_ANLPNP1 0x042D4 +#define IXGBE_ANLPNP2 0x042D8 +#define IXGBE_KRPCSFC 0x042E0 +#define IXGBE_KRPCSS 0x042E4 +#define IXGBE_FECS1 0x042E8 +#define IXGBE_FECS2 0x042EC +#define IXGBE_SMADARCTL 0x14F10 +#define IXGBE_MPVC 0x04318 +#define IXGBE_SGMIIC 0x04314 + +/* Statistics Registers */ +#define IXGBE_RXNFGPC 0x041B0 +#define IXGBE_RXNFGBCL 0x041B4 +#define IXGBE_RXNFGBCH 0x041B8 +#define IXGBE_RXDGPC 0x02F50 +#define IXGBE_RXDGBCL 0x02F54 +#define IXGBE_RXDGBCH 0x02F58 +#define IXGBE_RXDDGPC 0x02F5C +#define IXGBE_RXDDGBCL 0x02F60 +#define IXGBE_RXDDGBCH 0x02F64 +#define IXGBE_RXLPBKGPC 0x02F68 +#define IXGBE_RXLPBKGBCL 0x02F6C +#define IXGBE_RXLPBKGBCH 0x02F70 +#define IXGBE_RXDLPBKGPC 0x02F74 +#define IXGBE_RXDLPBKGBCL 0x02F78 +#define IXGBE_RXDLPBKGBCH 0x02F7C +#define IXGBE_TXDGPC 0x087A0 +#define IXGBE_TXDGBCL 0x087A4 +#define IXGBE_TXDGBCH 0x087A8 + +#define IXGBE_RXDSTATCTRL 0x02F40 + +/* Copper Pond 2 link timeout */ +#define IXGBE_VALIDATE_LINK_READY_TIMEOUT 50 + +/* Omer CORECTL */ +#define IXGBE_CORECTL 0x014F00 +/* BARCTRL */ +#define IXGBE_BARCTRL 0x110F4 +#define IXGBE_BARCTRL_FLSIZE 0x0700 +#define IXGBE_BARCTRL_FLSIZE_SHIFT 8 +#define IXGBE_BARCTRL_CSRSIZE 0x2000 + +/* RSCCTL Bit Masks */ +#define IXGBE_RSCCTL_RSCEN 0x01 +#define IXGBE_RSCCTL_MAXDESC_1 0x00 +#define IXGBE_RSCCTL_MAXDESC_4 0x04 +#define IXGBE_RSCCTL_MAXDESC_8 0x08 +#define IXGBE_RSCCTL_MAXDESC_16 0x0C + +/* RSCDBU Bit Masks */ +#define IXGBE_RSCDBU_RSCSMALDIS_MASK 0x0000007F +#define IXGBE_RSCDBU_RSCACKDIS 0x00000080 + +/* RDRXCTL Bit Masks */ +#define IXGBE_RDRXCTL_RDMTS_1_2 0x00000000 /* Rx Desc Min Threshold Size */ +#define IXGBE_RDRXCTL_CRCSTRIP 0x00000002 /* CRC Strip */ +#define IXGBE_RDRXCTL_PSP 0x00000004 /* Pad small packet */ +#define IXGBE_RDRXCTL_MVMEN 0x00000020 +#define IXGBE_RDRXCTL_DMAIDONE 0x00000008 /* DMA init cycle done */ +#define IXGBE_RDRXCTL_AGGDIS 0x00010000 /* Aggregation disable */ +#define IXGBE_RDRXCTL_RSCFRSTSIZE 0x003E0000 /* RSC First packet size */ +#define IXGBE_RDRXCTL_RSCLLIDIS 0x00800000 /* Disable RSC compl on LLI */ +#define IXGBE_RDRXCTL_RSCACKC 0x02000000 /* must set 1 when RSC enabled */ +#define IXGBE_RDRXCTL_FCOE_WRFIX 0x04000000 /* must set 1 when RSC enabled */ +#define IXGBE_RDRXCTL_MBINTEN 0x10000000 +#define IXGBE_RDRXCTL_MDP_EN 0x20000000 + +/* RQTC Bit Masks and Shifts */ +#define IXGBE_RQTC_SHIFT_TC(_i) ((_i) * 4) +#define IXGBE_RQTC_TC0_MASK (0x7 << 0) +#define IXGBE_RQTC_TC1_MASK (0x7 << 4) +#define IXGBE_RQTC_TC2_MASK (0x7 << 8) +#define IXGBE_RQTC_TC3_MASK (0x7 << 12) +#define IXGBE_RQTC_TC4_MASK (0x7 << 16) +#define IXGBE_RQTC_TC5_MASK (0x7 << 20) +#define IXGBE_RQTC_TC6_MASK (0x7 << 24) +#define IXGBE_RQTC_TC7_MASK (0x7 << 28) + +/* PSRTYPE.RQPL Bit masks and shift */ +#define IXGBE_PSRTYPE_RQPL_MASK 0x7 +#define IXGBE_PSRTYPE_RQPL_SHIFT 29 + +/* CTRL Bit Masks */ +#define IXGBE_CTRL_GIO_DIS 0x00000004 /* Global IO Master Disable bit */ +#define IXGBE_CTRL_LNK_RST 0x00000008 /* Link Reset. Resets everything. */ +#define IXGBE_CTRL_RST 0x04000000 /* Reset (SW) */ +#define IXGBE_CTRL_RST_MASK (IXGBE_CTRL_LNK_RST | IXGBE_CTRL_RST) + +/* FACTPS */ +#define IXGBE_FACTPS_MNGCG 0x20000000 /* Manageblility Clock Gated */ +#define IXGBE_FACTPS_LFS 0x40000000 /* LAN Function Select */ + +/* MHADD Bit Masks */ +#define IXGBE_MHADD_MFS_MASK 0xFFFF0000 +#define IXGBE_MHADD_MFS_SHIFT 16 + +/* Extended Device Control */ +#define IXGBE_CTRL_EXT_PFRSTD 0x00004000 /* Physical Function Reset Done */ +#define IXGBE_CTRL_EXT_NS_DIS 0x00010000 /* No Snoop disable */ +#define IXGBE_CTRL_EXT_RO_DIS 0x00020000 /* Relaxed Ordering disable */ +#define IXGBE_CTRL_EXT_DRV_LOAD 0x10000000 /* Driver loaded bit for FW */ + +/* Direct Cache Access (DCA) definitions */ +#define IXGBE_DCA_CTRL_DCA_ENABLE 0x00000000 /* DCA Enable */ +#define IXGBE_DCA_CTRL_DCA_DISABLE 0x00000001 /* DCA Disable */ + +#define IXGBE_DCA_CTRL_DCA_MODE_CB1 0x00 /* DCA Mode CB1 */ +#define IXGBE_DCA_CTRL_DCA_MODE_CB2 0x02 /* DCA Mode CB2 */ + +#define IXGBE_DCA_RXCTRL_CPUID_MASK 0x0000001F /* Rx CPUID Mask */ +#define IXGBE_DCA_RXCTRL_CPUID_MASK_82599 0xFF000000 /* Rx CPUID Mask */ +#define IXGBE_DCA_RXCTRL_CPUID_SHIFT_82599 24 /* Rx CPUID Shift */ +#define IXGBE_DCA_RXCTRL_DESC_DCA_EN BIT(5) /* DCA Rx Desc enable */ +#define IXGBE_DCA_RXCTRL_HEAD_DCA_EN BIT(6) /* DCA Rx Desc header enable */ +#define IXGBE_DCA_RXCTRL_DATA_DCA_EN BIT(7) /* DCA Rx Desc payload enable */ +#define IXGBE_DCA_RXCTRL_DESC_RRO_EN BIT(9) /* DCA Rx rd Desc Relax Order */ +#define IXGBE_DCA_RXCTRL_DATA_WRO_EN BIT(13) /* Rx wr data Relax Order */ +#define IXGBE_DCA_RXCTRL_HEAD_WRO_EN BIT(15) /* Rx wr header RO */ + +#define IXGBE_DCA_TXCTRL_CPUID_MASK 0x0000001F /* Tx CPUID Mask */ +#define IXGBE_DCA_TXCTRL_CPUID_MASK_82599 0xFF000000 /* Tx CPUID Mask */ +#define IXGBE_DCA_TXCTRL_CPUID_SHIFT_82599 24 /* Tx CPUID Shift */ +#define IXGBE_DCA_TXCTRL_DESC_DCA_EN BIT(5) /* DCA Tx Desc enable */ +#define IXGBE_DCA_TXCTRL_DESC_RRO_EN BIT(9) /* Tx rd Desc Relax Order */ +#define IXGBE_DCA_TXCTRL_DESC_WRO_EN BIT(11) /* Tx Desc writeback RO bit */ +#define IXGBE_DCA_TXCTRL_DATA_RRO_EN BIT(13) /* Tx rd data Relax Order */ +#define IXGBE_DCA_MAX_QUEUES_82598 16 /* DCA regs only on 16 queues */ + +/* MSCA Bit Masks */ +#define IXGBE_MSCA_NP_ADDR_MASK 0x0000FFFF /* MDI Address (new protocol) */ +#define IXGBE_MSCA_NP_ADDR_SHIFT 0 +#define IXGBE_MSCA_DEV_TYPE_MASK 0x001F0000 /* Device Type (new protocol) */ +#define IXGBE_MSCA_DEV_TYPE_SHIFT 16 /* Register Address (old protocol */ +#define IXGBE_MSCA_PHY_ADDR_MASK 0x03E00000 /* PHY Address mask */ +#define IXGBE_MSCA_PHY_ADDR_SHIFT 21 /* PHY Address shift*/ +#define IXGBE_MSCA_OP_CODE_MASK 0x0C000000 /* OP CODE mask */ +#define IXGBE_MSCA_OP_CODE_SHIFT 26 /* OP CODE shift */ +#define IXGBE_MSCA_ADDR_CYCLE 0x00000000 /* OP CODE 00 (addr cycle) */ +#define IXGBE_MSCA_WRITE 0x04000000 /* OP CODE 01 (write) */ +#define IXGBE_MSCA_READ 0x0C000000 /* OP CODE 11 (read) */ +#define IXGBE_MSCA_READ_AUTOINC 0x08000000 /* OP CODE 10 (read, auto inc)*/ +#define IXGBE_MSCA_ST_CODE_MASK 0x30000000 /* ST Code mask */ +#define IXGBE_MSCA_ST_CODE_SHIFT 28 /* ST Code shift */ +#define IXGBE_MSCA_NEW_PROTOCOL 0x00000000 /* ST CODE 00 (new protocol) */ +#define IXGBE_MSCA_OLD_PROTOCOL 0x10000000 /* ST CODE 01 (old protocol) */ +#define IXGBE_MSCA_MDI_COMMAND 0x40000000 /* Initiate MDI command */ +#define IXGBE_MSCA_MDI_IN_PROG_EN 0x80000000 /* MDI in progress enable */ + +/* MSRWD bit masks */ +#define IXGBE_MSRWD_WRITE_DATA_MASK 0x0000FFFF +#define IXGBE_MSRWD_WRITE_DATA_SHIFT 0 +#define IXGBE_MSRWD_READ_DATA_MASK 0xFFFF0000 +#define IXGBE_MSRWD_READ_DATA_SHIFT 16 + +/* Atlas registers */ +#define IXGBE_ATLAS_PDN_LPBK 0x24 +#define IXGBE_ATLAS_PDN_10G 0xB +#define IXGBE_ATLAS_PDN_1G 0xC +#define IXGBE_ATLAS_PDN_AN 0xD + +/* Atlas bit masks */ +#define IXGBE_ATLASCTL_WRITE_CMD 0x00010000 +#define IXGBE_ATLAS_PDN_TX_REG_EN 0x10 +#define IXGBE_ATLAS_PDN_TX_10G_QL_ALL 0xF0 +#define IXGBE_ATLAS_PDN_TX_1G_QL_ALL 0xF0 +#define IXGBE_ATLAS_PDN_TX_AN_QL_ALL 0xF0 + +/* Omer bit masks */ +#define IXGBE_CORECTL_WRITE_CMD 0x00010000 + +/* MDIO definitions */ + +#define IXGBE_MDIO_ZERO_DEV_TYPE 0x0 +#define IXGBE_MDIO_PCS_DEV_TYPE 0x3 +#define IXGBE_TWINAX_DEV 1 + +#define IXGBE_MDIO_COMMAND_TIMEOUT 100 /* PHY Timeout for 1 GB mode */ + +#define IXGBE_MDIO_VENDOR_SPECIFIC_1_LINK_STATUS 0x0008 /* 1 = Link Up */ +#define IXGBE_MDIO_VENDOR_SPECIFIC_1_SPEED_STATUS 0x0010 /* 0 - 10G, 1 - 1G */ +#define IXGBE_MDIO_VENDOR_SPECIFIC_1_10G_SPEED 0x0018 +#define IXGBE_MDIO_VENDOR_SPECIFIC_1_1G_SPEED 0x0010 + +#define IXGBE_MDIO_AUTO_NEG_VENDOR_STAT 0xC800 /* AUTO_NEG Vendor Status Reg */ +#define IXGBE_MDIO_AUTO_NEG_VENDOR_TX_ALARM 0xCC00 /* AUTO_NEG Vendor TX Reg */ +#define IXGBE_MDIO_AUTO_NEG_VENDOR_TX_ALARM2 0xCC01 /* AUTO_NEG Vendor Tx Reg */ +#define IXGBE_MDIO_AUTO_NEG_VEN_LSC 0x1 /* AUTO_NEG Vendor Tx LSC */ +#define IXGBE_MDIO_AUTO_NEG_EEE_ADVT 0x3C /* AUTO_NEG EEE Advt Reg */ + +#define IXGBE_MDIO_PHY_SET_LOW_POWER_MODE 0x0800 /* Set low power mode */ +#define IXGBE_AUTO_NEG_LP_STATUS 0xE820 /* AUTO NEG Rx LP Status Reg */ +#define IXGBE_AUTO_NEG_LP_1000BASE_CAP 0x8000 /* AUTO NEG Rx LP 1000BaseT */ +#define IXGBE_MDIO_TX_VENDOR_ALARMS_3 0xCC02 /* Vendor Alarms 3 Reg */ +#define IXGBE_MDIO_TX_VENDOR_ALARMS_3_RST_MASK 0x3 /* PHY Reset Complete Mask */ +#define IXGBE_MDIO_GLOBAL_RES_PR_10 0xC479 /* Global Resv Provisioning 10 Reg */ +#define IXGBE_MDIO_POWER_UP_STALL 0x8000 /* Power Up Stall */ +#define IXGBE_MDIO_GLOBAL_INT_CHIP_STD_MASK 0xFF00 /* int std mask */ +#define IXGBE_MDIO_GLOBAL_CHIP_STD_INT_FLAG 0xFC00 /* chip std int flag */ +#define IXGBE_MDIO_GLOBAL_INT_CHIP_VEN_MASK 0xFF01 /* int chip-wide mask */ +#define IXGBE_MDIO_GLOBAL_INT_CHIP_VEN_FLAG 0xFC01 /* int chip-wide mask */ +#define IXGBE_MDIO_GLOBAL_ALARM_1 0xCC00 /* Global alarm 1 */ +#define IXGBE_MDIO_GLOBAL_ALM_1_DEV_FAULT 0x0010 /* device fault */ +#define IXGBE_MDIO_GLOBAL_ALM_1_HI_TMP_FAIL 0x4000 /* high temp failure */ +#define IXGBE_MDIO_GLOBAL_FAULT_MSG 0xC850 /* global fault msg */ +#define IXGBE_MDIO_GLOBAL_FAULT_MSG_HI_TMP 0x8007 /* high temp failure */ +#define IXGBE_MDIO_GLOBAL_INT_MASK 0xD400 /* Global int mask */ +/* autoneg vendor alarm int enable */ +#define IXGBE_MDIO_GLOBAL_AN_VEN_ALM_INT_EN 0x1000 +#define IXGBE_MDIO_GLOBAL_ALARM_1_INT 0x4 /* int in Global alarm 1 */ +#define IXGBE_MDIO_GLOBAL_VEN_ALM_INT_EN 0x1 /* vendor alarm int enable */ +#define IXGBE_MDIO_GLOBAL_STD_ALM2_INT 0x200 /* vendor alarm2 int mask */ +#define IXGBE_MDIO_GLOBAL_INT_HI_TEMP_EN 0x4000 /* int high temp enable */ +#define IXGBE_MDIO_GLOBAL_INT_DEV_FAULT_EN 0x0010 /*int dev fault enable */ + +#define IXGBE_MDIO_PMA_PMD_SDA_SCL_ADDR 0xC30A /* PHY_XS SDA/SCL Addr Reg */ +#define IXGBE_MDIO_PMA_PMD_SDA_SCL_DATA 0xC30B /* PHY_XS SDA/SCL Data Reg */ +#define IXGBE_MDIO_PMA_PMD_SDA_SCL_STAT 0xC30C /* PHY_XS SDA/SCL Stat Reg */ +#define IXGBE_MDIO_PMA_TX_VEN_LASI_INT_MASK 0xD401 /* PHY TX Vendor LASI */ +#define IXGBE_MDIO_PMA_TX_VEN_LASI_INT_EN 0x1 /* PHY TX Vendor LASI enable */ +#define IXGBE_MDIO_PMD_STD_TX_DISABLE_CNTR 0x9 /* Standard Tx Dis Reg */ +#define IXGBE_MDIO_PMD_GLOBAL_TX_DISABLE 0x0001 /* PMD Global Tx Dis */ + +/* MII clause 22/28 definitions */ +#define IXGBE_MII_AUTONEG_VENDOR_PROVISION_1_REG 0xC400 /* 1G Provisioning 1 */ +#define IXGBE_MII_AUTONEG_XNP_TX_REG 0x17 /* 1G XNP Transmit */ +#define IXGBE_MII_1GBASE_T_ADVERTISE_XNP_TX 0x4000 /* full duplex, bit:14*/ +#define IXGBE_MII_1GBASE_T_ADVERTISE 0x8000 /* full duplex, bit:15*/ +#define IXGBE_MII_AUTONEG_REG 0x0 + +#define IXGBE_PHY_REVISION_MASK 0xFFFFFFF0 +#define IXGBE_MAX_PHY_ADDR 32 + +/* PHY IDs*/ +#define TN1010_PHY_ID 0x00A19410 +#define TNX_FW_REV 0xB +#define X540_PHY_ID 0x01540200 +#define X550_PHY_ID2 0x01540223 +#define X550_PHY_ID3 0x01540221 +#define X557_PHY_ID 0x01540240 +#define X557_PHY_ID2 0x01540250 +#define QT2022_PHY_ID 0x0043A400 +#define ATH_PHY_ID 0x03429050 +#define AQ_FW_REV 0x20 + +/* Special PHY Init Routine */ +#define IXGBE_PHY_INIT_OFFSET_NL 0x002B +#define IXGBE_PHY_INIT_END_NL 0xFFFF +#define IXGBE_CONTROL_MASK_NL 0xF000 +#define IXGBE_DATA_MASK_NL 0x0FFF +#define IXGBE_CONTROL_SHIFT_NL 12 +#define IXGBE_DELAY_NL 0 +#define IXGBE_DATA_NL 1 +#define IXGBE_CONTROL_NL 0x000F +#define IXGBE_CONTROL_EOL_NL 0x0FFF +#define IXGBE_CONTROL_SOL_NL 0x0000 + +/* General purpose Interrupt Enable */ +#define IXGBE_SDP0_GPIEN_8259X 0x00000001 /* SDP0 */ +#define IXGBE_SDP1_GPIEN_8259X 0x00000002 /* SDP1 */ +#define IXGBE_SDP2_GPIEN_8259X 0x00000004 /* SDP2 */ +#define IXGBE_SDP0_GPIEN_X540 0x00000002 /* SDP0 on X540 and X550 */ +#define IXGBE_SDP1_GPIEN_X540 0x00000004 /* SDP1 on X540 and X550 */ +#define IXGBE_SDP2_GPIEN_X540 0x00000008 /* SDP2 on X540 and X550 */ +#define IXGBE_SDP0_GPIEN_X550 IXGBE_SDP0_GPIEN_X540 +#define IXGBE_SDP1_GPIEN_X550 IXGBE_SDP1_GPIEN_X540 +#define IXGBE_SDP2_GPIEN_X550 IXGBE_SDP2_GPIEN_X540 +#define IXGBE_SDP0_GPIEN_X550EM_x IXGBE_SDP0_GPIEN_X540 +#define IXGBE_SDP1_GPIEN_X550EM_x IXGBE_SDP1_GPIEN_X540 +#define IXGBE_SDP2_GPIEN_X550EM_x IXGBE_SDP2_GPIEN_X540 +#define IXGBE_SDP0_GPIEN_X550EM_a IXGBE_SDP0_GPIEN_X540 +#define IXGBE_SDP1_GPIEN_X550EM_a IXGBE_SDP1_GPIEN_X540 +#define IXGBE_SDP2_GPIEN_X550EM_a IXGBE_SDP2_GPIEN_X540 +#define IXGBE_SDP0_GPIEN(_hw) IXGBE_BY_MAC((_hw), SDP0_GPIEN) +#define IXGBE_SDP1_GPIEN(_hw) IXGBE_BY_MAC((_hw), SDP1_GPIEN) +#define IXGBE_SDP2_GPIEN(_hw) IXGBE_BY_MAC((_hw), SDP2_GPIEN) + +#define IXGBE_GPIE_MSIX_MODE 0x00000010 /* MSI-X mode */ +#define IXGBE_GPIE_OCD 0x00000020 /* Other Clear Disable */ +#define IXGBE_GPIE_EIMEN 0x00000040 /* Immediate Interrupt Enable */ +#define IXGBE_GPIE_EIAME 0x40000000 +#define IXGBE_GPIE_PBA_SUPPORT 0x80000000 +#define IXGBE_GPIE_RSC_DELAY_SHIFT 11 +#define IXGBE_GPIE_VTMODE_MASK 0x0000C000 /* VT Mode Mask */ +#define IXGBE_GPIE_VTMODE_16 0x00004000 /* 16 VFs 8 queues per VF */ +#define IXGBE_GPIE_VTMODE_32 0x00008000 /* 32 VFs 4 queues per VF */ +#define IXGBE_GPIE_VTMODE_64 0x0000C000 /* 64 VFs 2 queues per VF */ + +/* Packet Buffer Initialization */ +#define IXGBE_TXPBSIZE_20KB 0x00005000 /* 20KB Packet Buffer */ +#define IXGBE_TXPBSIZE_40KB 0x0000A000 /* 40KB Packet Buffer */ +#define IXGBE_RXPBSIZE_48KB 0x0000C000 /* 48KB Packet Buffer */ +#define IXGBE_RXPBSIZE_64KB 0x00010000 /* 64KB Packet Buffer */ +#define IXGBE_RXPBSIZE_80KB 0x00014000 /* 80KB Packet Buffer */ +#define IXGBE_RXPBSIZE_128KB 0x00020000 /* 128KB Packet Buffer */ +#define IXGBE_RXPBSIZE_MAX 0x00080000 /* 512KB Packet Buffer*/ +#define IXGBE_TXPBSIZE_MAX 0x00028000 /* 160KB Packet Buffer*/ + +#define IXGBE_TXPKT_SIZE_MAX 0xA /* Max Tx Packet size */ +#define IXGBE_MAX_PB 8 + +/* Packet buffer allocation strategies */ +enum { + PBA_STRATEGY_EQUAL = 0, /* Distribute PB space equally */ +#define PBA_STRATEGY_EQUAL PBA_STRATEGY_EQUAL + PBA_STRATEGY_WEIGHTED = 1, /* Weight front half of TCs */ +#define PBA_STRATEGY_WEIGHTED PBA_STRATEGY_WEIGHTED +}; + +/* Transmit Flow Control status */ +#define IXGBE_TFCS_TXOFF 0x00000001 +#define IXGBE_TFCS_TXOFF0 0x00000100 +#define IXGBE_TFCS_TXOFF1 0x00000200 +#define IXGBE_TFCS_TXOFF2 0x00000400 +#define IXGBE_TFCS_TXOFF3 0x00000800 +#define IXGBE_TFCS_TXOFF4 0x00001000 +#define IXGBE_TFCS_TXOFF5 0x00002000 +#define IXGBE_TFCS_TXOFF6 0x00004000 +#define IXGBE_TFCS_TXOFF7 0x00008000 + +/* TCP Timer */ +#define IXGBE_TCPTIMER_KS 0x00000100 +#define IXGBE_TCPTIMER_COUNT_ENABLE 0x00000200 +#define IXGBE_TCPTIMER_COUNT_FINISH 0x00000400 +#define IXGBE_TCPTIMER_LOOP 0x00000800 +#define IXGBE_TCPTIMER_DURATION_MASK 0x000000FF + +/* HLREG0 Bit Masks */ +#define IXGBE_HLREG0_TXCRCEN 0x00000001 /* bit 0 */ +#define IXGBE_HLREG0_RXCRCSTRP 0x00000002 /* bit 1 */ +#define IXGBE_HLREG0_JUMBOEN 0x00000004 /* bit 2 */ +#define IXGBE_HLREG0_TXPADEN 0x00000400 /* bit 10 */ +#define IXGBE_HLREG0_TXPAUSEEN 0x00001000 /* bit 12 */ +#define IXGBE_HLREG0_RXPAUSEEN 0x00004000 /* bit 14 */ +#define IXGBE_HLREG0_LPBK 0x00008000 /* bit 15 */ +#define IXGBE_HLREG0_MDCSPD 0x00010000 /* bit 16 */ +#define IXGBE_HLREG0_CONTMDC 0x00020000 /* bit 17 */ +#define IXGBE_HLREG0_CTRLFLTR 0x00040000 /* bit 18 */ +#define IXGBE_HLREG0_PREPEND 0x00F00000 /* bits 20-23 */ +#define IXGBE_HLREG0_PRIPAUSEEN 0x01000000 /* bit 24 */ +#define IXGBE_HLREG0_RXPAUSERECDA 0x06000000 /* bits 25-26 */ +#define IXGBE_HLREG0_RXLNGTHERREN 0x08000000 /* bit 27 */ +#define IXGBE_HLREG0_RXPADSTRIPEN 0x10000000 /* bit 28 */ + +/* VMD_CTL bitmasks */ +#define IXGBE_VMD_CTL_VMDQ_EN 0x00000001 +#define IXGBE_VMD_CTL_VMDQ_FILTER 0x00000002 + +/* VT_CTL bitmasks */ +#define IXGBE_VT_CTL_DIS_DEFPL 0x20000000 /* disable default pool */ +#define IXGBE_VT_CTL_REPLEN 0x40000000 /* replication enabled */ +#define IXGBE_VT_CTL_VT_ENABLE 0x00000001 /* Enable VT Mode */ +#define IXGBE_VT_CTL_POOL_SHIFT 7 +#define IXGBE_VT_CTL_POOL_MASK (0x3F << IXGBE_VT_CTL_POOL_SHIFT) + +/* VMOLR bitmasks */ +#define IXGBE_VMOLR_UPE 0x00400000 /* unicast promiscuous */ +#define IXGBE_VMOLR_VPE 0x00800000 /* VLAN promiscuous */ +#define IXGBE_VMOLR_AUPE 0x01000000 /* accept untagged packets */ +#define IXGBE_VMOLR_ROMPE 0x02000000 /* accept packets in MTA tbl */ +#define IXGBE_VMOLR_ROPE 0x04000000 /* accept packets in UC tbl */ +#define IXGBE_VMOLR_BAM 0x08000000 /* accept broadcast packets */ +#define IXGBE_VMOLR_MPE 0x10000000 /* multicast promiscuous */ + +/* VFRE bitmask */ +#define IXGBE_VFRE_ENABLE_ALL 0xFFFFFFFF + +#define IXGBE_VF_INIT_TIMEOUT 200 /* Number of retries to clear RSTI */ + +/* RDHMPN and TDHMPN bitmasks */ +#define IXGBE_RDHMPN_RDICADDR 0x007FF800 +#define IXGBE_RDHMPN_RDICRDREQ 0x00800000 +#define IXGBE_RDHMPN_RDICADDR_SHIFT 11 +#define IXGBE_TDHMPN_TDICADDR 0x003FF800 +#define IXGBE_TDHMPN_TDICRDREQ 0x00800000 +#define IXGBE_TDHMPN_TDICADDR_SHIFT 11 + +#define IXGBE_RDMAM_MEM_SEL_SHIFT 13 +#define IXGBE_RDMAM_DWORD_SHIFT 9 +#define IXGBE_RDMAM_DESC_COMP_FIFO 1 +#define IXGBE_RDMAM_DFC_CMD_FIFO 2 +#define IXGBE_RDMAM_TCN_STATUS_RAM 4 +#define IXGBE_RDMAM_WB_COLL_FIFO 5 +#define IXGBE_RDMAM_QSC_CNT_RAM 6 +#define IXGBE_RDMAM_QSC_QUEUE_CNT 8 +#define IXGBE_RDMAM_QSC_QUEUE_RAM 0xA +#define IXGBE_RDMAM_DESC_COM_FIFO_RANGE 135 +#define IXGBE_RDMAM_DESC_COM_FIFO_COUNT 4 +#define IXGBE_RDMAM_DFC_CMD_FIFO_RANGE 48 +#define IXGBE_RDMAM_DFC_CMD_FIFO_COUNT 7 +#define IXGBE_RDMAM_TCN_STATUS_RAM_RANGE 256 +#define IXGBE_RDMAM_TCN_STATUS_RAM_COUNT 9 +#define IXGBE_RDMAM_WB_COLL_FIFO_RANGE 8 +#define IXGBE_RDMAM_WB_COLL_FIFO_COUNT 4 +#define IXGBE_RDMAM_QSC_CNT_RAM_RANGE 64 +#define IXGBE_RDMAM_QSC_CNT_RAM_COUNT 4 +#define IXGBE_RDMAM_QSC_QUEUE_CNT_RANGE 32 +#define IXGBE_RDMAM_QSC_QUEUE_CNT_COUNT 4 +#define IXGBE_RDMAM_QSC_QUEUE_RAM_RANGE 128 +#define IXGBE_RDMAM_QSC_QUEUE_RAM_COUNT 8 + +#define IXGBE_TXDESCIC_READY 0x80000000 + +/* Receive Checksum Control */ +#define IXGBE_RXCSUM_IPPCSE 0x00001000 /* IP payload checksum enable */ +#define IXGBE_RXCSUM_PCSD 0x00002000 /* packet checksum disabled */ + +/* FCRTL Bit Masks */ +#define IXGBE_FCRTL_XONE 0x80000000 /* XON enable */ +#define IXGBE_FCRTH_FCEN 0x80000000 /* Packet buffer fc enable */ + +/* PAP bit masks*/ +#define IXGBE_PAP_TXPAUSECNT_MASK 0x0000FFFF /* Pause counter mask */ + +/* RMCS Bit Masks */ +#define IXGBE_RMCS_RRM 0x00000002 /* Receive Recycle Mode enable */ +/* Receive Arbitration Control: 0 Round Robin, 1 DFP */ +#define IXGBE_RMCS_RAC 0x00000004 +#define IXGBE_RMCS_DFP IXGBE_RMCS_RAC /* Deficit Fixed Priority ena */ +#define IXGBE_RMCS_TFCE_802_3X 0x00000008 /* Tx Priority FC ena */ +#define IXGBE_RMCS_TFCE_PRIORITY 0x00000010 /* Tx Priority FC ena */ +#define IXGBE_RMCS_ARBDIS 0x00000040 /* Arbitration disable bit */ + +/* FCCFG Bit Masks */ +#define IXGBE_FCCFG_TFCE_802_3X 0x00000008 /* Tx link FC enable */ +#define IXGBE_FCCFG_TFCE_PRIORITY 0x00000010 /* Tx priority FC enable */ + +/* Interrupt register bitmasks */ + +/* Extended Interrupt Cause Read */ +#define IXGBE_EICR_RTX_QUEUE 0x0000FFFF /* RTx Queue Interrupt */ +#define IXGBE_EICR_FLOW_DIR 0x00010000 /* FDir Exception */ +#define IXGBE_EICR_RX_MISS 0x00020000 /* Packet Buffer Overrun */ +#define IXGBE_EICR_PCI 0x00040000 /* PCI Exception */ +#define IXGBE_EICR_MAILBOX 0x00080000 /* VF to PF Mailbox Interrupt */ +#define IXGBE_EICR_LSC 0x00100000 /* Link Status Change */ +#define IXGBE_EICR_LINKSEC 0x00200000 /* PN Threshold */ +#define IXGBE_EICR_MNG 0x00400000 /* Manageability Event Interrupt */ +#define IXGBE_EICR_TS 0x00800000 /* Thermal Sensor Event */ +#define IXGBE_EICR_TIMESYNC 0x01000000 /* Timesync Event */ +#define IXGBE_EICR_GPI_SDP0_8259X 0x01000000 /* Gen Purpose INT on SDP0 */ +#define IXGBE_EICR_GPI_SDP1_8259X 0x02000000 /* Gen Purpose INT on SDP1 */ +#define IXGBE_EICR_GPI_SDP2_8259X 0x04000000 /* Gen Purpose INT on SDP2 */ +#define IXGBE_EICR_GPI_SDP0_X540 0x02000000 +#define IXGBE_EICR_GPI_SDP1_X540 0x04000000 +#define IXGBE_EICR_GPI_SDP2_X540 0x08000000 +#define IXGBE_EICR_GPI_SDP0_X550 IXGBE_EICR_GPI_SDP0_X540 +#define IXGBE_EICR_GPI_SDP1_X550 IXGBE_EICR_GPI_SDP1_X540 +#define IXGBE_EICR_GPI_SDP2_X550 IXGBE_EICR_GPI_SDP2_X540 +#define IXGBE_EICR_GPI_SDP0_X550EM_x IXGBE_EICR_GPI_SDP0_X540 +#define IXGBE_EICR_GPI_SDP1_X550EM_x IXGBE_EICR_GPI_SDP1_X540 +#define IXGBE_EICR_GPI_SDP2_X550EM_x IXGBE_EICR_GPI_SDP2_X540 +#define IXGBE_EICR_GPI_SDP0_X550EM_a IXGBE_EICR_GPI_SDP0_X540 +#define IXGBE_EICR_GPI_SDP1_X550EM_a IXGBE_EICR_GPI_SDP1_X540 +#define IXGBE_EICR_GPI_SDP2_X550EM_a IXGBE_EICR_GPI_SDP2_X540 +#define IXGBE_EICR_GPI_SDP0(_hw) IXGBE_BY_MAC((_hw), EICR_GPI_SDP0) +#define IXGBE_EICR_GPI_SDP1(_hw) IXGBE_BY_MAC((_hw), EICR_GPI_SDP1) +#define IXGBE_EICR_GPI_SDP2(_hw) IXGBE_BY_MAC((_hw), EICR_GPI_SDP2) + +#define IXGBE_EICR_ECC 0x10000000 /* ECC Error */ +#define IXGBE_EICR_PBUR 0x10000000 /* Packet Buffer Handler Error */ +#define IXGBE_EICR_DHER 0x20000000 /* Descriptor Handler Error */ +#define IXGBE_EICR_TCP_TIMER 0x40000000 /* TCP Timer */ +#define IXGBE_EICR_OTHER 0x80000000 /* Interrupt Cause Active */ + +/* Extended Interrupt Cause Set */ +#define IXGBE_EICS_RTX_QUEUE IXGBE_EICR_RTX_QUEUE /* RTx Queue Interrupt */ +#define IXGBE_EICS_FLOW_DIR IXGBE_EICR_FLOW_DIR /* FDir Exception */ +#define IXGBE_EICS_RX_MISS IXGBE_EICR_RX_MISS /* Pkt Buffer Overrun */ +#define IXGBE_EICS_PCI IXGBE_EICR_PCI /* PCI Exception */ +#define IXGBE_EICS_MAILBOX IXGBE_EICR_MAILBOX /* VF to PF Mailbox Int */ +#define IXGBE_EICS_LSC IXGBE_EICR_LSC /* Link Status Change */ +#define IXGBE_EICS_MNG IXGBE_EICR_MNG /* MNG Event Interrupt */ +#define IXGBE_EICS_TIMESYNC IXGBE_EICR_TIMESYNC /* Timesync Event */ +#define IXGBE_EICS_GPI_SDP0(_hw) IXGBE_EICR_GPI_SDP0(_hw) +#define IXGBE_EICS_GPI_SDP1(_hw) IXGBE_EICR_GPI_SDP1(_hw) +#define IXGBE_EICS_GPI_SDP2(_hw) IXGBE_EICR_GPI_SDP2(_hw) +#define IXGBE_EICS_ECC IXGBE_EICR_ECC /* ECC Error */ +#define IXGBE_EICS_PBUR IXGBE_EICR_PBUR /* Pkt Buf Handler Err */ +#define IXGBE_EICS_DHER IXGBE_EICR_DHER /* Desc Handler Error */ +#define IXGBE_EICS_TCP_TIMER IXGBE_EICR_TCP_TIMER /* TCP Timer */ +#define IXGBE_EICS_OTHER IXGBE_EICR_OTHER /* INT Cause Active */ + +/* Extended Interrupt Mask Set */ +#define IXGBE_EIMS_RTX_QUEUE IXGBE_EICR_RTX_QUEUE /* RTx Queue Interrupt */ +#define IXGBE_EIMS_FLOW_DIR IXGBE_EICR_FLOW_DIR /* FDir Exception */ +#define IXGBE_EIMS_RX_MISS IXGBE_EICR_RX_MISS /* Packet Buffer Overrun */ +#define IXGBE_EIMS_PCI IXGBE_EICR_PCI /* PCI Exception */ +#define IXGBE_EIMS_MAILBOX IXGBE_EICR_MAILBOX /* VF to PF Mailbox Int */ +#define IXGBE_EIMS_LSC IXGBE_EICR_LSC /* Link Status Change */ +#define IXGBE_EIMS_MNG IXGBE_EICR_MNG /* MNG Event Interrupt */ +#define IXGBE_EIMS_TS IXGBE_EICR_TS /* Thermel Sensor Event */ +#define IXGBE_EIMS_TIMESYNC IXGBE_EICR_TIMESYNC /* Timesync Event */ +#define IXGBE_EIMS_GPI_SDP0(_hw) IXGBE_EICR_GPI_SDP0(_hw) +#define IXGBE_EIMS_GPI_SDP1(_hw) IXGBE_EICR_GPI_SDP1(_hw) +#define IXGBE_EIMS_GPI_SDP2(_hw) IXGBE_EICR_GPI_SDP2(_hw) +#define IXGBE_EIMS_ECC IXGBE_EICR_ECC /* ECC Error */ +#define IXGBE_EIMS_PBUR IXGBE_EICR_PBUR /* Pkt Buf Handler Err */ +#define IXGBE_EIMS_DHER IXGBE_EICR_DHER /* Descr Handler Error */ +#define IXGBE_EIMS_TCP_TIMER IXGBE_EICR_TCP_TIMER /* TCP Timer */ +#define IXGBE_EIMS_OTHER IXGBE_EICR_OTHER /* INT Cause Active */ + +/* Extended Interrupt Mask Clear */ +#define IXGBE_EIMC_RTX_QUEUE IXGBE_EICR_RTX_QUEUE /* RTx Queue Interrupt */ +#define IXGBE_EIMC_FLOW_DIR IXGBE_EICR_FLOW_DIR /* FDir Exception */ +#define IXGBE_EIMC_RX_MISS IXGBE_EICR_RX_MISS /* Packet Buffer Overrun */ +#define IXGBE_EIMC_PCI IXGBE_EICR_PCI /* PCI Exception */ +#define IXGBE_EIMC_MAILBOX IXGBE_EICR_MAILBOX /* VF to PF Mailbox Int */ +#define IXGBE_EIMC_LSC IXGBE_EICR_LSC /* Link Status Change */ +#define IXGBE_EIMC_MNG IXGBE_EICR_MNG /* MNG Event Interrupt */ +#define IXGBE_EIMC_TIMESYNC IXGBE_EICR_TIMESYNC /* Timesync Event */ +#define IXGBE_EIMC_GPI_SDP0(_hw) IXGBE_EICR_GPI_SDP0(_hw) +#define IXGBE_EIMC_GPI_SDP1(_hw) IXGBE_EICR_GPI_SDP1(_hw) +#define IXGBE_EIMC_GPI_SDP2(_hw) IXGBE_EICR_GPI_SDP2(_hw) +#define IXGBE_EIMC_ECC IXGBE_EICR_ECC /* ECC Error */ +#define IXGBE_EIMC_PBUR IXGBE_EICR_PBUR /* Pkt Buf Handler Err */ +#define IXGBE_EIMC_DHER IXGBE_EICR_DHER /* Desc Handler Err */ +#define IXGBE_EIMC_TCP_TIMER IXGBE_EICR_TCP_TIMER /* TCP Timer */ +#define IXGBE_EIMC_OTHER IXGBE_EICR_OTHER /* INT Cause Active */ + +#define IXGBE_EIMS_ENABLE_MASK ( \ + IXGBE_EIMS_RTX_QUEUE | \ + IXGBE_EIMS_LSC | \ + IXGBE_EIMS_TCP_TIMER | \ + IXGBE_EIMS_OTHER) + +/* Immediate Interrupt Rx (A.K.A. Low Latency Interrupt) */ +#define IXGBE_IMIR_PORT_IM_EN 0x00010000 /* TCP port enable */ +#define IXGBE_IMIR_PORT_BP 0x00020000 /* TCP port check bypass */ +#define IXGBE_IMIREXT_SIZE_BP 0x00001000 /* Packet size bypass */ +#define IXGBE_IMIREXT_CTRL_URG 0x00002000 /* Check URG bit in header */ +#define IXGBE_IMIREXT_CTRL_ACK 0x00004000 /* Check ACK bit in header */ +#define IXGBE_IMIREXT_CTRL_PSH 0x00008000 /* Check PSH bit in header */ +#define IXGBE_IMIREXT_CTRL_RST 0x00010000 /* Check RST bit in header */ +#define IXGBE_IMIREXT_CTRL_SYN 0x00020000 /* Check SYN bit in header */ +#define IXGBE_IMIREXT_CTRL_FIN 0x00040000 /* Check FIN bit in header */ +#define IXGBE_IMIREXT_CTRL_BP 0x00080000 /* Bypass check of control bits */ +#define IXGBE_IMIR_SIZE_BP_82599 0x00001000 /* Packet size bypass */ +#define IXGBE_IMIR_CTRL_URG_82599 0x00002000 /* Check URG bit in header */ +#define IXGBE_IMIR_CTRL_ACK_82599 0x00004000 /* Check ACK bit in header */ +#define IXGBE_IMIR_CTRL_PSH_82599 0x00008000 /* Check PSH bit in header */ +#define IXGBE_IMIR_CTRL_RST_82599 0x00010000 /* Check RST bit in header */ +#define IXGBE_IMIR_CTRL_SYN_82599 0x00020000 /* Check SYN bit in header */ +#define IXGBE_IMIR_CTRL_FIN_82599 0x00040000 /* Check FIN bit in header */ +#define IXGBE_IMIR_CTRL_BP_82599 0x00080000 /* Bypass check of control bits */ +#define IXGBE_IMIR_LLI_EN_82599 0x00100000 /* Enables low latency Int */ +#define IXGBE_IMIR_RX_QUEUE_MASK_82599 0x0000007F /* Rx Queue Mask */ +#define IXGBE_IMIR_RX_QUEUE_SHIFT_82599 21 /* Rx Queue Shift */ +#define IXGBE_IMIRVP_PRIORITY_MASK 0x00000007 /* VLAN priority mask */ +#define IXGBE_IMIRVP_PRIORITY_EN 0x00000008 /* VLAN priority enable */ + +#define IXGBE_MAX_FTQF_FILTERS 128 +#define IXGBE_FTQF_PROTOCOL_MASK 0x00000003 +#define IXGBE_FTQF_PROTOCOL_TCP 0x00000000 +#define IXGBE_FTQF_PROTOCOL_UDP 0x00000001 +#define IXGBE_FTQF_PROTOCOL_SCTP 2 +#define IXGBE_FTQF_PRIORITY_MASK 0x00000007 +#define IXGBE_FTQF_PRIORITY_SHIFT 2 +#define IXGBE_FTQF_POOL_MASK 0x0000003F +#define IXGBE_FTQF_POOL_SHIFT 8 +#define IXGBE_FTQF_5TUPLE_MASK_MASK 0x0000001F +#define IXGBE_FTQF_5TUPLE_MASK_SHIFT 25 +#define IXGBE_FTQF_SOURCE_ADDR_MASK 0x1E +#define IXGBE_FTQF_DEST_ADDR_MASK 0x1D +#define IXGBE_FTQF_SOURCE_PORT_MASK 0x1B +#define IXGBE_FTQF_DEST_PORT_MASK 0x17 +#define IXGBE_FTQF_PROTOCOL_COMP_MASK 0x0F +#define IXGBE_FTQF_POOL_MASK_EN 0x40000000 +#define IXGBE_FTQF_QUEUE_ENABLE 0x80000000 + +/* Interrupt clear mask */ +#define IXGBE_IRQ_CLEAR_MASK 0xFFFFFFFF + +/* Interrupt Vector Allocation Registers */ +#define IXGBE_IVAR_REG_NUM 25 +#define IXGBE_IVAR_REG_NUM_82599 64 +#define IXGBE_IVAR_TXRX_ENTRY 96 +#define IXGBE_IVAR_RX_ENTRY 64 +#define IXGBE_IVAR_RX_QUEUE(_i) (0 + (_i)) +#define IXGBE_IVAR_TX_QUEUE(_i) (64 + (_i)) +#define IXGBE_IVAR_TX_ENTRY 32 + +#define IXGBE_IVAR_TCP_TIMER_INDEX 96 /* 0 based index */ +#define IXGBE_IVAR_OTHER_CAUSES_INDEX 97 /* 0 based index */ + +#define IXGBE_MSIX_VECTOR(_i) (0 + (_i)) + +#define IXGBE_IVAR_ALLOC_VAL 0x80 /* Interrupt Allocation valid */ + +/* ETYPE Queue Filter/Select Bit Masks */ +#define IXGBE_MAX_ETQF_FILTERS 8 +#define IXGBE_ETQF_FCOE 0x08000000 /* bit 27 */ +#define IXGBE_ETQF_BCN 0x10000000 /* bit 28 */ +#define IXGBE_ETQF_TX_ANTISPOOF 0x20000000 /* bit 29 */ +#define IXGBE_ETQF_1588 0x40000000 /* bit 30 */ +#define IXGBE_ETQF_FILTER_EN 0x80000000 /* bit 31 */ +#define IXGBE_ETQF_POOL_ENABLE BIT(26) /* bit 26 */ +#define IXGBE_ETQF_POOL_SHIFT 20 + +#define IXGBE_ETQS_RX_QUEUE 0x007F0000 /* bits 22:16 */ +#define IXGBE_ETQS_RX_QUEUE_SHIFT 16 +#define IXGBE_ETQS_LLI 0x20000000 /* bit 29 */ +#define IXGBE_ETQS_QUEUE_EN 0x80000000 /* bit 31 */ + +/* + * ETQF filter list: one static filter per filter consumer. This is + * to avoid filter collisions later. Add new filters + * here!! + * + * Current filters: + * EAPOL 802.1x (0x888e): Filter 0 + * FCoE (0x8906): Filter 2 + * 1588 (0x88f7): Filter 3 + * FIP (0x8914): Filter 4 + * LLDP (0x88CC): Filter 5 + * LACP (0x8809): Filter 6 + * FC (0x8808): Filter 7 + */ +#define IXGBE_ETQF_FILTER_EAPOL 0 +#define IXGBE_ETQF_FILTER_FCOE 2 +#define IXGBE_ETQF_FILTER_1588 3 +#define IXGBE_ETQF_FILTER_FIP 4 +#define IXGBE_ETQF_FILTER_LLDP 5 +#define IXGBE_ETQF_FILTER_LACP 6 +#define IXGBE_ETQF_FILTER_FC 7 + +/* VLAN Control Bit Masks */ +#define IXGBE_VLNCTRL_VET 0x0000FFFF /* bits 0-15 */ +#define IXGBE_VLNCTRL_CFI 0x10000000 /* bit 28 */ +#define IXGBE_VLNCTRL_CFIEN 0x20000000 /* bit 29 */ +#define IXGBE_VLNCTRL_VFE 0x40000000 /* bit 30 */ +#define IXGBE_VLNCTRL_VME 0x80000000 /* bit 31 */ + +/* VLAN pool filtering masks */ +#define IXGBE_VLVF_VIEN 0x80000000 /* filter is valid */ +#define IXGBE_VLVF_ENTRIES 64 +#define IXGBE_VLVF_VLANID_MASK 0x00000FFF + +/* Per VF Port VLAN insertion rules */ +#define IXGBE_VMVIR_VLANA_DEFAULT 0x40000000 /* Always use default VLAN */ +#define IXGBE_VMVIR_VLANA_NEVER 0x80000000 /* Never insert VLAN tag */ + +#define IXGBE_ETHERNET_IEEE_VLAN_TYPE 0x8100 /* 802.1q protocol */ + +/* STATUS Bit Masks */ +#define IXGBE_STATUS_LAN_ID 0x0000000C /* LAN ID */ +#define IXGBE_STATUS_LAN_ID_SHIFT 2 /* LAN ID Shift*/ +#define IXGBE_STATUS_GIO 0x00080000 /* GIO Master Enable Status */ + +#define IXGBE_STATUS_LAN_ID_0 0x00000000 /* LAN ID 0 */ +#define IXGBE_STATUS_LAN_ID_1 0x00000004 /* LAN ID 1 */ + +/* ESDP Bit Masks */ +#define IXGBE_ESDP_SDP0 0x00000001 /* SDP0 Data Value */ +#define IXGBE_ESDP_SDP1 0x00000002 /* SDP1 Data Value */ +#define IXGBE_ESDP_SDP2 0x00000004 /* SDP2 Data Value */ +#define IXGBE_ESDP_SDP3 0x00000008 /* SDP3 Data Value */ +#define IXGBE_ESDP_SDP4 0x00000010 /* SDP4 Data Value */ +#define IXGBE_ESDP_SDP5 0x00000020 /* SDP5 Data Value */ +#define IXGBE_ESDP_SDP6 0x00000040 /* SDP6 Data Value */ +#define IXGBE_ESDP_SDP0_DIR 0x00000100 /* SDP0 IO direction */ +#define IXGBE_ESDP_SDP1_DIR 0x00000200 /* SDP1 IO direction */ +#define IXGBE_ESDP_SDP4_DIR 0x00000004 /* SDP4 IO direction */ +#define IXGBE_ESDP_SDP5_DIR 0x00002000 /* SDP5 IO direction */ +#define IXGBE_ESDP_SDP0_NATIVE 0x00010000 /* SDP0 Native Function */ +#define IXGBE_ESDP_SDP1_NATIVE 0x00020000 /* SDP1 IO mode */ + +/* LEDCTL Bit Masks */ +#define IXGBE_LED_IVRT_BASE 0x00000040 +#define IXGBE_LED_BLINK_BASE 0x00000080 +#define IXGBE_LED_MODE_MASK_BASE 0x0000000F +#define IXGBE_LED_OFFSET(_base, _i) (_base << (8 * (_i))) +#define IXGBE_LED_MODE_SHIFT(_i) (8 * (_i)) +#define IXGBE_LED_IVRT(_i) IXGBE_LED_OFFSET(IXGBE_LED_IVRT_BASE, _i) +#define IXGBE_LED_BLINK(_i) IXGBE_LED_OFFSET(IXGBE_LED_BLINK_BASE, _i) +#define IXGBE_LED_MODE_MASK(_i) IXGBE_LED_OFFSET(IXGBE_LED_MODE_MASK_BASE, _i) +#define IXGBE_X557_LED_MANUAL_SET_MASK BIT(8) +#define IXGBE_X557_MAX_LED_INDEX 3 +#define IXGBE_X557_LED_PROVISIONING 0xC430 + +/* LED modes */ +#define IXGBE_LED_LINK_UP 0x0 +#define IXGBE_LED_LINK_10G 0x1 +#define IXGBE_LED_MAC 0x2 +#define IXGBE_LED_FILTER 0x3 +#define IXGBE_LED_LINK_ACTIVE 0x4 +#define IXGBE_LED_LINK_1G 0x5 +#define IXGBE_LED_ON 0xE +#define IXGBE_LED_OFF 0xF + +/* AUTOC Bit Masks */ +#define IXGBE_AUTOC_KX4_KX_SUPP_MASK 0xC0000000 +#define IXGBE_AUTOC_KX4_SUPP 0x80000000 +#define IXGBE_AUTOC_KX_SUPP 0x40000000 +#define IXGBE_AUTOC_PAUSE 0x30000000 +#define IXGBE_AUTOC_ASM_PAUSE 0x20000000 +#define IXGBE_AUTOC_SYM_PAUSE 0x10000000 +#define IXGBE_AUTOC_RF 0x08000000 +#define IXGBE_AUTOC_PD_TMR 0x06000000 +#define IXGBE_AUTOC_AN_RX_LOOSE 0x01000000 +#define IXGBE_AUTOC_AN_RX_DRIFT 0x00800000 +#define IXGBE_AUTOC_AN_RX_ALIGN 0x007C0000 +#define IXGBE_AUTOC_FECA 0x00040000 +#define IXGBE_AUTOC_FECR 0x00020000 +#define IXGBE_AUTOC_KR_SUPP 0x00010000 +#define IXGBE_AUTOC_AN_RESTART 0x00001000 +#define IXGBE_AUTOC_FLU 0x00000001 +#define IXGBE_AUTOC_LMS_SHIFT 13 +#define IXGBE_AUTOC_LMS_10G_SERIAL (0x3 << IXGBE_AUTOC_LMS_SHIFT) +#define IXGBE_AUTOC_LMS_KX4_KX_KR (0x4 << IXGBE_AUTOC_LMS_SHIFT) +#define IXGBE_AUTOC_LMS_SGMII_1G_100M (0x5 << IXGBE_AUTOC_LMS_SHIFT) +#define IXGBE_AUTOC_LMS_KX4_KX_KR_1G_AN (0x6 << IXGBE_AUTOC_LMS_SHIFT) +#define IXGBE_AUTOC_LMS_KX4_KX_KR_SGMII (0x7 << IXGBE_AUTOC_LMS_SHIFT) +#define IXGBE_AUTOC_LMS_MASK (0x7 << IXGBE_AUTOC_LMS_SHIFT) +#define IXGBE_AUTOC_LMS_1G_LINK_NO_AN (0x0 << IXGBE_AUTOC_LMS_SHIFT) +#define IXGBE_AUTOC_LMS_10G_LINK_NO_AN (0x1 << IXGBE_AUTOC_LMS_SHIFT) +#define IXGBE_AUTOC_LMS_1G_AN (0x2 << IXGBE_AUTOC_LMS_SHIFT) +#define IXGBE_AUTOC_LMS_KX4_AN (0x4 << IXGBE_AUTOC_LMS_SHIFT) +#define IXGBE_AUTOC_LMS_KX4_AN_1G_AN (0x6 << IXGBE_AUTOC_LMS_SHIFT) +#define IXGBE_AUTOC_LMS_ATTACH_TYPE (0x7 << IXGBE_AUTOC_10G_PMA_PMD_SHIFT) + +#define IXGBE_AUTOC_1G_PMA_PMD_MASK 0x00000200 +#define IXGBE_AUTOC_1G_PMA_PMD_SHIFT 9 +#define IXGBE_AUTOC_10G_PMA_PMD_MASK 0x00000180 +#define IXGBE_AUTOC_10G_PMA_PMD_SHIFT 7 +#define IXGBE_AUTOC_10G_XAUI (0u << IXGBE_AUTOC_10G_PMA_PMD_SHIFT) +#define IXGBE_AUTOC_10G_KX4 (1u << IXGBE_AUTOC_10G_PMA_PMD_SHIFT) +#define IXGBE_AUTOC_10G_CX4 (2u << IXGBE_AUTOC_10G_PMA_PMD_SHIFT) +#define IXGBE_AUTOC_1G_BX (0u << IXGBE_AUTOC_1G_PMA_PMD_SHIFT) +#define IXGBE_AUTOC_1G_KX (1u << IXGBE_AUTOC_1G_PMA_PMD_SHIFT) +#define IXGBE_AUTOC_1G_SFI (0u << IXGBE_AUTOC_1G_PMA_PMD_SHIFT) +#define IXGBE_AUTOC_1G_KX_BX (1u << IXGBE_AUTOC_1G_PMA_PMD_SHIFT) + +#define IXGBE_AUTOC2_UPPER_MASK 0xFFFF0000 +#define IXGBE_AUTOC2_10G_SERIAL_PMA_PMD_MASK 0x00030000 +#define IXGBE_AUTOC2_10G_SERIAL_PMA_PMD_SHIFT 16 +#define IXGBE_AUTOC2_10G_KR (0u << IXGBE_AUTOC2_10G_SERIAL_PMA_PMD_SHIFT) +#define IXGBE_AUTOC2_10G_XFI (1u << IXGBE_AUTOC2_10G_SERIAL_PMA_PMD_SHIFT) +#define IXGBE_AUTOC2_10G_SFI (2u << IXGBE_AUTOC2_10G_SERIAL_PMA_PMD_SHIFT) +#define IXGBE_AUTOC2_LINK_DISABLE_ON_D3_MASK 0x50000000 +#define IXGBE_AUTOC2_LINK_DISABLE_MASK 0x70000000 + +#define IXGBE_MACC_FLU 0x00000001 +#define IXGBE_MACC_FSV_10G 0x00030000 +#define IXGBE_MACC_FS 0x00040000 +#define IXGBE_MAC_RX2TX_LPBK 0x00000002 + +/* Veto Bit definition */ +#define IXGBE_MMNGC_MNG_VETO 0x00000001 + +/* LINKS Bit Masks */ +#define IXGBE_LINKS_KX_AN_COMP 0x80000000 +#define IXGBE_LINKS_UP 0x40000000 +#define IXGBE_LINKS_SPEED 0x20000000 +#define IXGBE_LINKS_MODE 0x18000000 +#define IXGBE_LINKS_RX_MODE 0x06000000 +#define IXGBE_LINKS_TX_MODE 0x01800000 +#define IXGBE_LINKS_XGXS_EN 0x00400000 +#define IXGBE_LINKS_SGMII_EN 0x02000000 +#define IXGBE_LINKS_PCS_1G_EN 0x00200000 +#define IXGBE_LINKS_1G_AN_EN 0x00100000 +#define IXGBE_LINKS_KX_AN_IDLE 0x00080000 +#define IXGBE_LINKS_1G_SYNC 0x00040000 +#define IXGBE_LINKS_10G_ALIGN 0x00020000 +#define IXGBE_LINKS_10G_LANE_SYNC 0x00017000 +#define IXGBE_LINKS_TL_FAULT 0x00001000 +#define IXGBE_LINKS_SIGNAL 0x00000F00 + +#define IXGBE_LINKS_SPEED_NON_STD 0x08000000 +#define IXGBE_LINKS_SPEED_82599 0x30000000 +#define IXGBE_LINKS_SPEED_10G_82599 0x30000000 +#define IXGBE_LINKS_SPEED_1G_82599 0x20000000 +#define IXGBE_LINKS_SPEED_100_82599 0x10000000 +#define IXGBE_LINKS_SPEED_10_X550EM_A 0 +#define IXGBE_LINK_UP_TIME 90 /* 9.0 Seconds */ +#define IXGBE_AUTO_NEG_TIME 45 /* 4.5 Seconds */ + +#define IXGBE_LINKS2_AN_SUPPORTED 0x00000040 + +/* PCS1GLSTA Bit Masks */ +#define IXGBE_PCS1GLSTA_LINK_OK 1 +#define IXGBE_PCS1GLSTA_SYNK_OK 0x10 +#define IXGBE_PCS1GLSTA_AN_COMPLETE 0x10000 +#define IXGBE_PCS1GLSTA_AN_PAGE_RX 0x20000 +#define IXGBE_PCS1GLSTA_AN_TIMED_OUT 0x40000 +#define IXGBE_PCS1GLSTA_AN_REMOTE_FAULT 0x80000 +#define IXGBE_PCS1GLSTA_AN_ERROR_RWS 0x100000 + +#define IXGBE_PCS1GANA_SYM_PAUSE 0x80 +#define IXGBE_PCS1GANA_ASM_PAUSE 0x100 + +/* PCS1GLCTL Bit Masks */ +#define IXGBE_PCS1GLCTL_AN_1G_TIMEOUT_EN 0x00040000 /* PCS 1G autoneg to en */ +#define IXGBE_PCS1GLCTL_FLV_LINK_UP 1 +#define IXGBE_PCS1GLCTL_FORCE_LINK 0x20 +#define IXGBE_PCS1GLCTL_LOW_LINK_LATCH 0x40 +#define IXGBE_PCS1GLCTL_AN_ENABLE 0x10000 +#define IXGBE_PCS1GLCTL_AN_RESTART 0x20000 + +/* ANLP1 Bit Masks */ +#define IXGBE_ANLP1_PAUSE 0x0C00 +#define IXGBE_ANLP1_SYM_PAUSE 0x0400 +#define IXGBE_ANLP1_ASM_PAUSE 0x0800 +#define IXGBE_ANLP1_AN_STATE_MASK 0x000f0000 + +/* SW Semaphore Register bitmasks */ +#define IXGBE_SWSM_SMBI 0x00000001 /* Driver Semaphore bit */ +#define IXGBE_SWSM_SWESMBI 0x00000002 /* FW Semaphore bit */ +#define IXGBE_SWSM_WMNG 0x00000004 /* Wake MNG Clock */ +#define IXGBE_SWFW_REGSMP 0x80000000 /* Register Semaphore bit 31 */ + +/* SW_FW_SYNC/GSSR definitions */ +#define IXGBE_GSSR_EEP_SM 0x0001 +#define IXGBE_GSSR_PHY0_SM 0x0002 +#define IXGBE_GSSR_PHY1_SM 0x0004 +#define IXGBE_GSSR_MAC_CSR_SM 0x0008 +#define IXGBE_GSSR_FLASH_SM 0x0010 +#define IXGBE_GSSR_NVM_UPDATE_SM 0x0200 +#define IXGBE_GSSR_SW_MNG_SM 0x0400 +#define IXGBE_GSSR_TOKEN_SM 0x40000000 /* SW bit for shared access */ +#define IXGBE_GSSR_SHARED_I2C_SM 0x1806 /* Wait for both phys & I2Cs */ +#define IXGBE_GSSR_I2C_MASK 0x1800 +#define IXGBE_GSSR_NVM_PHY_MASK 0xF + +/* FW Status register bitmask */ +#define IXGBE_FWSTS_FWRI 0x00000200 /* Firmware Reset Indication */ + +/* EEC Register */ +#define IXGBE_EEC_SK 0x00000001 /* EEPROM Clock */ +#define IXGBE_EEC_CS 0x00000002 /* EEPROM Chip Select */ +#define IXGBE_EEC_DI 0x00000004 /* EEPROM Data In */ +#define IXGBE_EEC_DO 0x00000008 /* EEPROM Data Out */ +#define IXGBE_EEC_FWE_MASK 0x00000030 /* FLASH Write Enable */ +#define IXGBE_EEC_FWE_DIS 0x00000010 /* Disable FLASH writes */ +#define IXGBE_EEC_FWE_EN 0x00000020 /* Enable FLASH writes */ +#define IXGBE_EEC_FWE_SHIFT 4 +#define IXGBE_EEC_REQ 0x00000040 /* EEPROM Access Request */ +#define IXGBE_EEC_GNT 0x00000080 /* EEPROM Access Grant */ +#define IXGBE_EEC_PRES 0x00000100 /* EEPROM Present */ +#define IXGBE_EEC_ARD 0x00000200 /* EEPROM Auto Read Done */ +#define IXGBE_EEC_FLUP 0x00800000 /* Flash update command */ +#define IXGBE_EEC_SEC1VAL 0x02000000 /* Sector 1 Valid */ +#define IXGBE_EEC_FLUDONE 0x04000000 /* Flash update done */ +/* EEPROM Addressing bits based on type (0-small, 1-large) */ +#define IXGBE_EEC_ADDR_SIZE 0x00000400 +#define IXGBE_EEC_SIZE 0x00007800 /* EEPROM Size */ +#define IXGBE_EERD_MAX_ADDR 0x00003FFF /* EERD alows 14 bits for addr. */ + +#define IXGBE_EEC_SIZE_SHIFT 11 +#define IXGBE_EEPROM_WORD_SIZE_SHIFT 6 +#define IXGBE_EEPROM_OPCODE_BITS 8 + +/* Part Number String Length */ +#define IXGBE_PBANUM_LENGTH 11 + +/* Checksum and EEPROM pointers */ +#define IXGBE_PBANUM_PTR_GUARD 0xFAFA +#define IXGBE_EEPROM_CHECKSUM 0x3F +#define IXGBE_EEPROM_SUM 0xBABA +#define IXGBE_EEPROM_CTRL_4 0x45 +#define IXGBE_EE_CTRL_4_INST_ID 0x10 +#define IXGBE_EE_CTRL_4_INST_ID_SHIFT 4 +#define IXGBE_PCIE_ANALOG_PTR 0x03 +#define IXGBE_ATLAS0_CONFIG_PTR 0x04 +#define IXGBE_PHY_PTR 0x04 +#define IXGBE_ATLAS1_CONFIG_PTR 0x05 +#define IXGBE_OPTION_ROM_PTR 0x05 +#define IXGBE_PCIE_GENERAL_PTR 0x06 +#define IXGBE_PCIE_CONFIG0_PTR 0x07 +#define IXGBE_PCIE_CONFIG1_PTR 0x08 +#define IXGBE_CORE0_PTR 0x09 +#define IXGBE_CORE1_PTR 0x0A +#define IXGBE_MAC0_PTR 0x0B +#define IXGBE_MAC1_PTR 0x0C +#define IXGBE_CSR0_CONFIG_PTR 0x0D +#define IXGBE_CSR1_CONFIG_PTR 0x0E +#define IXGBE_PCIE_ANALOG_PTR_X550 0x02 +#define IXGBE_SHADOW_RAM_SIZE_X550 0x4000 +#define IXGBE_IXGBE_PCIE_GENERAL_SIZE 0x24 +#define IXGBE_PCIE_CONFIG_SIZE 0x08 +#define IXGBE_EEPROM_LAST_WORD 0x41 +#define IXGBE_FW_PTR 0x0F +#define IXGBE_PBANUM0_PTR 0x15 +#define IXGBE_PBANUM1_PTR 0x16 +#define IXGBE_FREE_SPACE_PTR 0X3E + +/* External Thermal Sensor Config */ +#define IXGBE_ETS_CFG 0x26 +#define IXGBE_ETS_LTHRES_DELTA_MASK 0x07C0 +#define IXGBE_ETS_LTHRES_DELTA_SHIFT 6 +#define IXGBE_ETS_TYPE_MASK 0x0038 +#define IXGBE_ETS_TYPE_SHIFT 3 +#define IXGBE_ETS_TYPE_EMC 0x000 +#define IXGBE_ETS_TYPE_EMC_SHIFTED 0x000 +#define IXGBE_ETS_NUM_SENSORS_MASK 0x0007 +#define IXGBE_ETS_DATA_LOC_MASK 0x3C00 +#define IXGBE_ETS_DATA_LOC_SHIFT 10 +#define IXGBE_ETS_DATA_INDEX_MASK 0x0300 +#define IXGBE_ETS_DATA_INDEX_SHIFT 8 +#define IXGBE_ETS_DATA_HTHRESH_MASK 0x00FF + +#define IXGBE_SAN_MAC_ADDR_PTR 0x28 +#define IXGBE_DEVICE_CAPS 0x2C +#define IXGBE_SERIAL_NUMBER_MAC_ADDR 0x11 +#define IXGBE_PCIE_MSIX_82599_CAPS 0x72 +#define IXGBE_MAX_MSIX_VECTORS_82599 0x40 +#define IXGBE_PCIE_MSIX_82598_CAPS 0x62 +#define IXGBE_MAX_MSIX_VECTORS_82598 0x13 + +/* MSI-X capability fields masks */ +#define IXGBE_PCIE_MSIX_TBL_SZ_MASK 0x7FF + +/* Legacy EEPROM word offsets */ +#define IXGBE_ISCSI_BOOT_CAPS 0x0033 +#define IXGBE_ISCSI_SETUP_PORT_0 0x0030 +#define IXGBE_ISCSI_SETUP_PORT_1 0x0034 + +/* EEPROM Commands - SPI */ +#define IXGBE_EEPROM_MAX_RETRY_SPI 5000 /* Max wait 5ms for RDY signal */ +#define IXGBE_EEPROM_STATUS_RDY_SPI 0x01 +#define IXGBE_EEPROM_READ_OPCODE_SPI 0x03 /* EEPROM read opcode */ +#define IXGBE_EEPROM_WRITE_OPCODE_SPI 0x02 /* EEPROM write opcode */ +#define IXGBE_EEPROM_A8_OPCODE_SPI 0x08 /* opcode bit-3 = addr bit-8 */ +#define IXGBE_EEPROM_WREN_OPCODE_SPI 0x06 /* EEPROM set Write Ena latch */ +/* EEPROM reset Write Enable latch */ +#define IXGBE_EEPROM_WRDI_OPCODE_SPI 0x04 +#define IXGBE_EEPROM_RDSR_OPCODE_SPI 0x05 /* EEPROM read Status reg */ +#define IXGBE_EEPROM_WRSR_OPCODE_SPI 0x01 /* EEPROM write Status reg */ +#define IXGBE_EEPROM_ERASE4K_OPCODE_SPI 0x20 /* EEPROM ERASE 4KB */ +#define IXGBE_EEPROM_ERASE64K_OPCODE_SPI 0xD8 /* EEPROM ERASE 64KB */ +#define IXGBE_EEPROM_ERASE256_OPCODE_SPI 0xDB /* EEPROM ERASE 256B */ + +/* EEPROM Read Register */ +#define IXGBE_EEPROM_RW_REG_DATA 16 /* data offset in EEPROM read reg */ +#define IXGBE_EEPROM_RW_REG_DONE 2 /* Offset to READ done bit */ +#define IXGBE_EEPROM_RW_REG_START 1 /* First bit to start operation */ +#define IXGBE_EEPROM_RW_ADDR_SHIFT 2 /* Shift to the address bits */ +#define IXGBE_NVM_POLL_WRITE 1 /* Flag for polling for write complete */ +#define IXGBE_NVM_POLL_READ 0 /* Flag for polling for read complete */ + +#define NVM_INIT_CTRL_3 0x38 +#define NVM_INIT_CTRL_3_LPLU 0x8 +#define NVM_INIT_CTRL_3_D10GMP_PORT0 0x40 +#define NVM_INIT_CTRL_3_D10GMP_PORT1 0x100 + +#define IXGBE_EEPROM_PAGE_SIZE_MAX 128 +#define IXGBE_EEPROM_RD_BUFFER_MAX_COUNT 512 /* EEPROM words # read in burst */ +#define IXGBE_EEPROM_WR_BUFFER_MAX_COUNT 256 /* EEPROM words # wr in burst */ + +#define IXGBE_EEPROM_CTRL_2 1 /* EEPROM CTRL word 2 */ +#define IXGBE_EEPROM_CCD_BIT 2 /* EEPROM Core Clock Disable bit */ + +#ifndef IXGBE_EEPROM_GRANT_ATTEMPTS +#define IXGBE_EEPROM_GRANT_ATTEMPTS 1000 /* EEPROM # attempts to gain grant */ +#endif + +#ifndef IXGBE_EERD_EEWR_ATTEMPTS +/* Number of 5 microseconds we wait for EERD read and + * EERW write to complete */ +#define IXGBE_EERD_EEWR_ATTEMPTS 100000 +#endif + +#ifndef IXGBE_FLUDONE_ATTEMPTS +/* # attempts we wait for flush update to complete */ +#define IXGBE_FLUDONE_ATTEMPTS 20000 +#endif + +#define IXGBE_PCIE_CTRL2 0x5 /* PCIe Control 2 Offset */ +#define IXGBE_PCIE_CTRL2_DUMMY_ENABLE 0x8 /* Dummy Function Enable */ +#define IXGBE_PCIE_CTRL2_LAN_DISABLE 0x2 /* LAN PCI Disable */ +#define IXGBE_PCIE_CTRL2_DISABLE_SELECT 0x1 /* LAN Disable Select */ + +#define IXGBE_SAN_MAC_ADDR_PORT0_OFFSET 0x0 +#define IXGBE_SAN_MAC_ADDR_PORT1_OFFSET 0x3 +#define IXGBE_DEVICE_CAPS_ALLOW_ANY_SFP 0x1 +#define IXGBE_DEVICE_CAPS_FCOE_OFFLOADS 0x2 +#define IXGBE_DEVICE_CAPS_NO_CROSSTALK_WR BIT(7) +#define IXGBE_FW_LESM_PARAMETERS_PTR 0x2 +#define IXGBE_FW_LESM_STATE_1 0x1 +#define IXGBE_FW_LESM_STATE_ENABLED 0x8000 /* LESM Enable bit */ +#define IXGBE_FW_PASSTHROUGH_PATCH_CONFIG_PTR 0x4 +#define IXGBE_FW_PATCH_VERSION_4 0x7 +#define IXGBE_FCOE_IBA_CAPS_BLK_PTR 0x33 /* iSCSI/FCOE block */ +#define IXGBE_FCOE_IBA_CAPS_FCOE 0x20 /* FCOE flags */ +#define IXGBE_ISCSI_FCOE_BLK_PTR 0x17 /* iSCSI/FCOE block */ +#define IXGBE_ISCSI_FCOE_FLAGS_OFFSET 0x0 /* FCOE flags */ +#define IXGBE_ISCSI_FCOE_FLAGS_ENABLE 0x1 /* FCOE flags enable bit */ +#define IXGBE_ALT_SAN_MAC_ADDR_BLK_PTR 0x27 /* Alt. SAN MAC block */ +#define IXGBE_ALT_SAN_MAC_ADDR_CAPS_OFFSET 0x0 /* Alt. SAN MAC capability */ +#define IXGBE_ALT_SAN_MAC_ADDR_PORT0_OFFSET 0x1 /* Alt. SAN MAC 0 offset */ +#define IXGBE_ALT_SAN_MAC_ADDR_PORT1_OFFSET 0x4 /* Alt. SAN MAC 1 offset */ +#define IXGBE_ALT_SAN_MAC_ADDR_WWNN_OFFSET 0x7 /* Alt. WWNN prefix offset */ +#define IXGBE_ALT_SAN_MAC_ADDR_WWPN_OFFSET 0x8 /* Alt. WWPN prefix offset */ +#define IXGBE_ALT_SAN_MAC_ADDR_CAPS_SANMAC 0x0 /* Alt. SAN MAC exists */ +#define IXGBE_ALT_SAN_MAC_ADDR_CAPS_ALTWWN 0x1 /* Alt. WWN base exists */ + +#define IXGBE_DEVICE_CAPS_WOL_PORT0_1 0x4 /* WoL supported on ports 0 & 1 */ +#define IXGBE_DEVICE_CAPS_WOL_PORT0 0x8 /* WoL supported on port 0 */ +#define IXGBE_DEVICE_CAPS_WOL_MASK 0xC /* Mask for WoL capabilities */ + +/* PCI Bus Info */ +#define IXGBE_PCI_DEVICE_STATUS 0xAA +#define IXGBE_PCI_DEVICE_STATUS_TRANSACTION_PENDING 0x0020 +#define IXGBE_PCI_LINK_STATUS 0xB2 +#define IXGBE_PCI_DEVICE_CONTROL2 0xC8 +#define IXGBE_PCI_LINK_WIDTH 0x3F0 +#define IXGBE_PCI_LINK_WIDTH_1 0x10 +#define IXGBE_PCI_LINK_WIDTH_2 0x20 +#define IXGBE_PCI_LINK_WIDTH_4 0x40 +#define IXGBE_PCI_LINK_WIDTH_8 0x80 +#define IXGBE_PCI_LINK_SPEED 0xF +#define IXGBE_PCI_LINK_SPEED_2500 0x1 +#define IXGBE_PCI_LINK_SPEED_5000 0x2 +#define IXGBE_PCI_LINK_SPEED_8000 0x3 +#define IXGBE_PCI_HEADER_TYPE_REGISTER 0x0E +#define IXGBE_PCI_HEADER_TYPE_MULTIFUNC 0x80 +#define IXGBE_PCI_DEVICE_CONTROL2_16ms 0x0005 + +#define IXGBE_PCIDEVCTRL2_TIMEO_MASK 0xf +#define IXGBE_PCIDEVCTRL2_16_32ms_def 0x0 +#define IXGBE_PCIDEVCTRL2_50_100us 0x1 +#define IXGBE_PCIDEVCTRL2_1_2ms 0x2 +#define IXGBE_PCIDEVCTRL2_16_32ms 0x5 +#define IXGBE_PCIDEVCTRL2_65_130ms 0x6 +#define IXGBE_PCIDEVCTRL2_260_520ms 0x9 +#define IXGBE_PCIDEVCTRL2_1_2s 0xa +#define IXGBE_PCIDEVCTRL2_4_8s 0xd +#define IXGBE_PCIDEVCTRL2_17_34s 0xe + +/* Number of 100 microseconds we wait for PCI Express master disable */ +#define IXGBE_PCI_MASTER_DISABLE_TIMEOUT 800 + +/* RAH */ +#define IXGBE_RAH_VIND_MASK 0x003C0000 +#define IXGBE_RAH_VIND_SHIFT 18 +#define IXGBE_RAH_AV 0x80000000 +#define IXGBE_CLEAR_VMDQ_ALL 0xFFFFFFFF + +/* Header split receive */ +#define IXGBE_RFCTL_ISCSI_DIS 0x00000001 +#define IXGBE_RFCTL_ISCSI_DWC_MASK 0x0000003E +#define IXGBE_RFCTL_ISCSI_DWC_SHIFT 1 +#define IXGBE_RFCTL_RSC_DIS 0x00000020 +#define IXGBE_RFCTL_NFSW_DIS 0x00000040 +#define IXGBE_RFCTL_NFSR_DIS 0x00000080 +#define IXGBE_RFCTL_NFS_VER_MASK 0x00000300 +#define IXGBE_RFCTL_NFS_VER_SHIFT 8 +#define IXGBE_RFCTL_NFS_VER_2 0 +#define IXGBE_RFCTL_NFS_VER_3 1 +#define IXGBE_RFCTL_NFS_VER_4 2 +#define IXGBE_RFCTL_IPV6_DIS 0x00000400 +#define IXGBE_RFCTL_IPV6_XSUM_DIS 0x00000800 +#define IXGBE_RFCTL_IPFRSP_DIS 0x00004000 +#define IXGBE_RFCTL_IPV6_EX_DIS 0x00010000 +#define IXGBE_RFCTL_NEW_IPV6_EXT_DIS 0x00020000 + +/* Transmit Config masks */ +#define IXGBE_TXDCTL_ENABLE 0x02000000 /* Enable specific Tx Queue */ +#define IXGBE_TXDCTL_SWFLSH 0x04000000 /* Tx Desc. write-back flushing */ +#define IXGBE_TXDCTL_WTHRESH_SHIFT 16 /* shift to WTHRESH bits */ +/* Enable short packet padding to 64 bytes */ +#define IXGBE_TX_PAD_ENABLE 0x00000400 +#define IXGBE_JUMBO_FRAME_ENABLE 0x00000004 /* Allow jumbo frames */ +/* This allows for 16K packets + 4k for vlan */ +#define IXGBE_MAX_FRAME_SZ 0x40040000 + +#define IXGBE_TDWBAL_HEAD_WB_ENABLE 0x1 /* Tx head write-back enable */ +#define IXGBE_TDWBAL_SEQNUM_WB_ENABLE 0x2 /* Tx seq# write-back enable */ + +/* Receive Config masks */ +#define IXGBE_RXCTRL_RXEN 0x00000001 /* Enable Receiver */ +#define IXGBE_RXCTRL_DMBYPS 0x00000002 /* Descriptor Monitor Bypass */ +#define IXGBE_RXDCTL_ENABLE 0x02000000 /* Enable specific Rx Queue */ +#define IXGBE_RXDCTL_SWFLSH 0x04000000 /* Rx Desc. write-back flushing */ +#define IXGBE_RXDCTL_RLPMLMASK 0x00003FFF /* Only supported on the X540 */ +#define IXGBE_RXDCTL_RLPML_EN 0x00008000 +#define IXGBE_RXDCTL_VME 0x40000000 /* VLAN mode enable */ + +#define IXGBE_TSAUXC_EN_CLK 0x00000004 +#define IXGBE_TSAUXC_SYNCLK 0x00000008 +#define IXGBE_TSAUXC_SDP0_INT 0x00000040 +#define IXGBE_TSAUXC_EN_TT0 0x00000001 +#define IXGBE_TSAUXC_EN_TT1 0x00000002 +#define IXGBE_TSAUXC_ST0 0x00000010 +#define IXGBE_TSAUXC_DISABLE_SYSTIME 0x80000000 + +#define IXGBE_TSSDP_TS_SDP0_SEL_MASK 0x000000C0 +#define IXGBE_TSSDP_TS_SDP0_CLK0 0x00000080 +#define IXGBE_TSSDP_TS_SDP0_EN 0x00000100 + +#define IXGBE_TSYNCTXCTL_VALID 0x00000001 /* Tx timestamp valid */ +#define IXGBE_TSYNCTXCTL_ENABLED 0x00000010 /* Tx timestamping enabled */ + +#define IXGBE_TSYNCRXCTL_VALID 0x00000001 /* Rx timestamp valid */ +#define IXGBE_TSYNCRXCTL_TYPE_MASK 0x0000000E /* Rx type mask */ +#define IXGBE_TSYNCRXCTL_TYPE_L2_V2 0x00 +#define IXGBE_TSYNCRXCTL_TYPE_L4_V1 0x02 +#define IXGBE_TSYNCRXCTL_TYPE_L2_L4_V2 0x04 +#define IXGBE_TSYNCRXCTL_TYPE_ALL 0x08 +#define IXGBE_TSYNCRXCTL_TYPE_EVENT_V2 0x0A +#define IXGBE_TSYNCRXCTL_ENABLED 0x00000010 /* Rx Timestamping enabled */ +#define IXGBE_TSYNCRXCTL_TSIP_UT_EN 0x00800000 /* Rx Timestamp in Packet */ + +#define IXGBE_TSIM_TXTS 0x00000002 + +#define IXGBE_RXMTRL_V1_CTRLT_MASK 0x000000FF +#define IXGBE_RXMTRL_V1_SYNC_MSG 0x00 +#define IXGBE_RXMTRL_V1_DELAY_REQ_MSG 0x01 +#define IXGBE_RXMTRL_V1_FOLLOWUP_MSG 0x02 +#define IXGBE_RXMTRL_V1_DELAY_RESP_MSG 0x03 +#define IXGBE_RXMTRL_V1_MGMT_MSG 0x04 + +#define IXGBE_RXMTRL_V2_MSGID_MASK 0x0000FF00 +#define IXGBE_RXMTRL_V2_SYNC_MSG 0x0000 +#define IXGBE_RXMTRL_V2_DELAY_REQ_MSG 0x0100 +#define IXGBE_RXMTRL_V2_PDELAY_REQ_MSG 0x0200 +#define IXGBE_RXMTRL_V2_PDELAY_RESP_MSG 0x0300 +#define IXGBE_RXMTRL_V2_FOLLOWUP_MSG 0x0800 +#define IXGBE_RXMTRL_V2_DELAY_RESP_MSG 0x0900 +#define IXGBE_RXMTRL_V2_PDELAY_FOLLOWUP_MSG 0x0A00 +#define IXGBE_RXMTRL_V2_ANNOUNCE_MSG 0x0B00 +#define IXGBE_RXMTRL_V2_SIGNALING_MSG 0x0C00 +#define IXGBE_RXMTRL_V2_MGMT_MSG 0x0D00 + +#define IXGBE_FCTRL_SBP 0x00000002 /* Store Bad Packet */ +#define IXGBE_FCTRL_MPE 0x00000100 /* Multicast Promiscuous Ena*/ +#define IXGBE_FCTRL_UPE 0x00000200 /* Unicast Promiscuous Ena */ +#define IXGBE_FCTRL_BAM 0x00000400 /* Broadcast Accept Mode */ +#define IXGBE_FCTRL_PMCF 0x00001000 /* Pass MAC Control Frames */ +#define IXGBE_FCTRL_DPF 0x00002000 /* Discard Pause Frame */ +/* Receive Priority Flow Control Enable */ +#define IXGBE_FCTRL_RPFCE 0x00004000 +#define IXGBE_FCTRL_RFCE 0x00008000 /* Receive Flow Control Ena */ +#define IXGBE_MFLCN_PMCF 0x00000001 /* Pass MAC Control Frames */ +#define IXGBE_MFLCN_DPF 0x00000002 /* Discard Pause Frame */ +#define IXGBE_MFLCN_RPFCE 0x00000004 /* Receive Priority FC Enable */ +#define IXGBE_MFLCN_RFCE 0x00000008 /* Receive FC Enable */ +#define IXGBE_MFLCN_RPFCE_MASK 0x00000FF4 /* Receive FC Mask */ + +#define IXGBE_MFLCN_RPFCE_SHIFT 4 + +/* Multiple Receive Queue Control */ +#define IXGBE_MRQC_RSSEN 0x00000001 /* RSS Enable */ +#define IXGBE_MRQC_MRQE_MASK 0xF /* Bits 3:0 */ +#define IXGBE_MRQC_RT8TCEN 0x00000002 /* 8 TC no RSS */ +#define IXGBE_MRQC_RT4TCEN 0x00000003 /* 4 TC no RSS */ +#define IXGBE_MRQC_RTRSS8TCEN 0x00000004 /* 8 TC w/ RSS */ +#define IXGBE_MRQC_RTRSS4TCEN 0x00000005 /* 4 TC w/ RSS */ +#define IXGBE_MRQC_VMDQEN 0x00000008 /* VMDq2 64 pools no RSS */ +#define IXGBE_MRQC_VMDQRSS32EN 0x0000000A /* VMDq2 32 pools w/ RSS */ +#define IXGBE_MRQC_VMDQRSS64EN 0x0000000B /* VMDq2 64 pools w/ RSS */ +#define IXGBE_MRQC_VMDQRT8TCEN 0x0000000C /* VMDq2/RT 16 pool 8 TC */ +#define IXGBE_MRQC_VMDQRT4TCEN 0x0000000D /* VMDq2/RT 32 pool 4 TC */ +#define IXGBE_MRQC_RSS_FIELD_MASK 0xFFFF0000 +#define IXGBE_MRQC_RSS_FIELD_IPV4_TCP 0x00010000 +#define IXGBE_MRQC_RSS_FIELD_IPV4 0x00020000 +#define IXGBE_MRQC_RSS_FIELD_IPV6_EX_TCP 0x00040000 +#define IXGBE_MRQC_RSS_FIELD_IPV6_EX 0x00080000 +#define IXGBE_MRQC_RSS_FIELD_IPV6 0x00100000 +#define IXGBE_MRQC_RSS_FIELD_IPV6_TCP 0x00200000 +#define IXGBE_MRQC_RSS_FIELD_IPV4_UDP 0x00400000 +#define IXGBE_MRQC_RSS_FIELD_IPV6_UDP 0x00800000 +#define IXGBE_MRQC_RSS_FIELD_IPV6_EX_UDP 0x01000000 +#define IXGBE_MRQC_MULTIPLE_RSS 0x00002000 +#define IXGBE_MRQC_L3L4TXSWEN 0x00008000 + +#define IXGBE_FWSM_TS_ENABLED 0x1 + +/* Queue Drop Enable */ +#define IXGBE_QDE_ENABLE 0x00000001 +#define IXGBE_QDE_HIDE_VLAN 0x00000002 +#define IXGBE_QDE_IDX_MASK 0x00007F00 +#define IXGBE_QDE_IDX_SHIFT 8 +#define IXGBE_QDE_WRITE 0x00010000 + +#define IXGBE_TXD_POPTS_IXSM 0x01 /* Insert IP checksum */ +#define IXGBE_TXD_POPTS_TXSM 0x02 /* Insert TCP/UDP checksum */ +#define IXGBE_TXD_CMD_EOP 0x01000000 /* End of Packet */ +#define IXGBE_TXD_CMD_IFCS 0x02000000 /* Insert FCS (Ethernet CRC) */ +#define IXGBE_TXD_CMD_IC 0x04000000 /* Insert Checksum */ +#define IXGBE_TXD_CMD_RS 0x08000000 /* Report Status */ +#define IXGBE_TXD_CMD_DEXT 0x20000000 /* Descriptor extension (0 = legacy) */ +#define IXGBE_TXD_CMD_VLE 0x40000000 /* Add VLAN tag */ +#define IXGBE_TXD_STAT_DD 0x00000001 /* Descriptor Done */ + +/* Multiple Transmit Queue Command Register */ +#define IXGBE_MTQC_RT_ENA 0x1 /* DCB Enable */ +#define IXGBE_MTQC_VT_ENA 0x2 /* VMDQ2 Enable */ +#define IXGBE_MTQC_64Q_1PB 0x0 /* 64 queues 1 pack buffer */ +#define IXGBE_MTQC_32VF 0x8 /* 4 TX Queues per pool w/32VF's */ +#define IXGBE_MTQC_64VF 0x4 /* 2 TX Queues per pool w/64VF's */ +#define IXGBE_MTQC_8TC_8TQ 0xC /* 8 TC if RT_ENA or 8 TQ if VT_ENA */ +#define IXGBE_MTQC_4TC_4TQ 0x8 /* 4 TC if RT_ENA or 4 TQ if VT_ENA */ + +/* Receive Descriptor bit definitions */ +#define IXGBE_RXD_STAT_DD 0x01 /* Descriptor Done */ +#define IXGBE_RXD_STAT_EOP 0x02 /* End of Packet */ +#define IXGBE_RXD_STAT_FLM 0x04 /* FDir Match */ +#define IXGBE_RXD_STAT_VP 0x08 /* IEEE VLAN Packet */ +#define IXGBE_RXDADV_NEXTP_MASK 0x000FFFF0 /* Next Descriptor Index */ +#define IXGBE_RXDADV_NEXTP_SHIFT 0x00000004 +#define IXGBE_RXD_STAT_UDPCS 0x10 /* UDP xsum calculated */ +#define IXGBE_RXD_STAT_L4CS 0x20 /* L4 xsum calculated */ +#define IXGBE_RXD_STAT_IPCS 0x40 /* IP xsum calculated */ +#define IXGBE_RXD_STAT_PIF 0x80 /* passed in-exact filter */ +#define IXGBE_RXD_STAT_CRCV 0x100 /* Speculative CRC Valid */ +#define IXGBE_RXD_STAT_OUTERIPCS 0x100 /* Cloud IP xsum calculated */ +#define IXGBE_RXD_STAT_VEXT 0x200 /* 1st VLAN found */ +#define IXGBE_RXD_STAT_UDPV 0x400 /* Valid UDP checksum */ +#define IXGBE_RXD_STAT_DYNINT 0x800 /* Pkt caused INT via DYNINT */ +#define IXGBE_RXD_STAT_LLINT 0x800 /* Pkt caused Low Latency Interrupt */ +#define IXGBE_RXD_STAT_TSIP 0x08000 /* Time Stamp in packet buffer */ +#define IXGBE_RXD_STAT_TS 0x10000 /* Time Stamp */ +#define IXGBE_RXD_STAT_SECP 0x20000 /* Security Processing */ +#define IXGBE_RXD_STAT_LB 0x40000 /* Loopback Status */ +#define IXGBE_RXD_STAT_ACK 0x8000 /* ACK Packet indication */ +#define IXGBE_RXD_ERR_CE 0x01 /* CRC Error */ +#define IXGBE_RXD_ERR_LE 0x02 /* Length Error */ +#define IXGBE_RXD_ERR_PE 0x08 /* Packet Error */ +#define IXGBE_RXD_ERR_OSE 0x10 /* Oversize Error */ +#define IXGBE_RXD_ERR_USE 0x20 /* Undersize Error */ +#define IXGBE_RXD_ERR_TCPE 0x40 /* TCP/UDP Checksum Error */ +#define IXGBE_RXD_ERR_IPE 0x80 /* IP Checksum Error */ +#define IXGBE_RXDADV_ERR_MASK 0xfff00000 /* RDESC.ERRORS mask */ +#define IXGBE_RXDADV_ERR_SHIFT 20 /* RDESC.ERRORS shift */ +#define IXGBE_RXDADV_ERR_OUTERIPER 0x04000000 /* CRC IP Header error */ +#define IXGBE_RXDADV_ERR_FCEOFE 0x80000000 /* FCoEFe/IPE */ +#define IXGBE_RXDADV_ERR_FCERR 0x00700000 /* FCERR/FDIRERR */ +#define IXGBE_RXDADV_ERR_FDIR_LEN 0x00100000 /* FDIR Length error */ +#define IXGBE_RXDADV_ERR_FDIR_DROP 0x00200000 /* FDIR Drop error */ +#define IXGBE_RXDADV_ERR_FDIR_COLL 0x00400000 /* FDIR Collision error */ +#define IXGBE_RXDADV_ERR_HBO 0x00800000 /*Header Buffer Overflow */ +#define IXGBE_RXDADV_ERR_CE 0x01000000 /* CRC Error */ +#define IXGBE_RXDADV_ERR_LE 0x02000000 /* Length Error */ +#define IXGBE_RXDADV_ERR_PE 0x08000000 /* Packet Error */ +#define IXGBE_RXDADV_ERR_OSE 0x10000000 /* Oversize Error */ +#define IXGBE_RXDADV_ERR_IPSEC_INV_PROTOCOL 0x08000000 /* overlap ERR_PE */ +#define IXGBE_RXDADV_ERR_IPSEC_INV_LENGTH 0x10000000 /* overlap ERR_OSE */ +#define IXGBE_RXDADV_ERR_IPSEC_AUTH_FAILED 0x18000000 +#define IXGBE_RXDADV_ERR_USE 0x20000000 /* Undersize Error */ +#define IXGBE_RXDADV_ERR_TCPE 0x40000000 /* TCP/UDP Checksum Error */ +#define IXGBE_RXDADV_ERR_IPE 0x80000000 /* IP Checksum Error */ +#define IXGBE_RXD_VLAN_ID_MASK 0x0FFF /* VLAN ID is in lower 12 bits */ +#define IXGBE_RXD_PRI_MASK 0xE000 /* Priority is in upper 3 bits */ +#define IXGBE_RXD_PRI_SHIFT 13 +#define IXGBE_RXD_CFI_MASK 0x1000 /* CFI is bit 12 */ +#define IXGBE_RXD_CFI_SHIFT 12 + +#define IXGBE_RXDADV_STAT_DD IXGBE_RXD_STAT_DD /* Done */ +#define IXGBE_RXDADV_STAT_EOP IXGBE_RXD_STAT_EOP /* End of Packet */ +#define IXGBE_RXDADV_STAT_FLM IXGBE_RXD_STAT_FLM /* FDir Match */ +#define IXGBE_RXDADV_STAT_VP IXGBE_RXD_STAT_VP /* IEEE VLAN Pkt */ +#define IXGBE_RXDADV_STAT_MASK 0x000fffff /* Stat/NEXTP: bit 0-19 */ +#define IXGBE_RXDADV_STAT_FCEOFS 0x00000040 /* FCoE EOF/SOF Stat */ +#define IXGBE_RXDADV_STAT_FCSTAT 0x00000030 /* FCoE Pkt Stat */ +#define IXGBE_RXDADV_STAT_FCSTAT_NOMTCH 0x00000000 /* 00: No Ctxt Match */ +#define IXGBE_RXDADV_STAT_FCSTAT_NODDP 0x00000010 /* 01: Ctxt w/o DDP */ +#define IXGBE_RXDADV_STAT_FCSTAT_FCPRSP 0x00000020 /* 10: Recv. FCP_RSP */ +#define IXGBE_RXDADV_STAT_FCSTAT_DDP 0x00000030 /* 11: Ctxt w/ DDP */ +#define IXGBE_RXDADV_STAT_TS 0x00010000 /* IEEE 1588 Time Stamp */ +#define IXGBE_RXDADV_STAT_SECP 0x00020000 /* IPsec/MACsec pkt found */ + +/* PSRTYPE bit definitions */ +#define IXGBE_PSRTYPE_TCPHDR 0x00000010 +#define IXGBE_PSRTYPE_UDPHDR 0x00000020 +#define IXGBE_PSRTYPE_IPV4HDR 0x00000100 +#define IXGBE_PSRTYPE_IPV6HDR 0x00000200 +#define IXGBE_PSRTYPE_L2HDR 0x00001000 + +/* SRRCTL bit definitions */ +#define IXGBE_SRRCTL_BSIZEPKT_SHIFT 10 /* so many KBs */ +#define IXGBE_SRRCTL_RDMTS_SHIFT 22 +#define IXGBE_SRRCTL_RDMTS_MASK 0x01C00000 +#define IXGBE_SRRCTL_DROP_EN 0x10000000 +#define IXGBE_SRRCTL_BSIZEPKT_MASK 0x0000007F +#define IXGBE_SRRCTL_BSIZEHDR_MASK 0x00003F00 +#define IXGBE_SRRCTL_DESCTYPE_LEGACY 0x00000000 +#define IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF 0x02000000 +#define IXGBE_SRRCTL_DESCTYPE_HDR_SPLIT 0x04000000 +#define IXGBE_SRRCTL_DESCTYPE_HDR_REPLICATION_LARGE_PKT 0x08000000 +#define IXGBE_SRRCTL_DESCTYPE_HDR_SPLIT_ALWAYS 0x0A000000 +#define IXGBE_SRRCTL_DESCTYPE_MASK 0x0E000000 + +#define IXGBE_RXDPS_HDRSTAT_HDRSP 0x00008000 +#define IXGBE_RXDPS_HDRSTAT_HDRLEN_MASK 0x000003FF + +#define IXGBE_RXDADV_RSSTYPE_MASK 0x0000000F +#define IXGBE_RXDADV_PKTTYPE_MASK 0x0000FFF0 +#define IXGBE_RXDADV_PKTTYPE_MASK_EX 0x0001FFF0 +#define IXGBE_RXDADV_HDRBUFLEN_MASK 0x00007FE0 +#define IXGBE_RXDADV_RSCCNT_MASK 0x001E0000 +#define IXGBE_RXDADV_RSCCNT_SHIFT 17 +#define IXGBE_RXDADV_HDRBUFLEN_SHIFT 5 +#define IXGBE_RXDADV_SPLITHEADER_EN 0x00001000 +#define IXGBE_RXDADV_SPH 0x8000 + +/* RSS Hash results */ +#define IXGBE_RXDADV_RSSTYPE_NONE 0x00000000 +#define IXGBE_RXDADV_RSSTYPE_IPV4_TCP 0x00000001 +#define IXGBE_RXDADV_RSSTYPE_IPV4 0x00000002 +#define IXGBE_RXDADV_RSSTYPE_IPV6_TCP 0x00000003 +#define IXGBE_RXDADV_RSSTYPE_IPV6_EX 0x00000004 +#define IXGBE_RXDADV_RSSTYPE_IPV6 0x00000005 +#define IXGBE_RXDADV_RSSTYPE_IPV6_TCP_EX 0x00000006 +#define IXGBE_RXDADV_RSSTYPE_IPV4_UDP 0x00000007 +#define IXGBE_RXDADV_RSSTYPE_IPV6_UDP 0x00000008 +#define IXGBE_RXDADV_RSSTYPE_IPV6_UDP_EX 0x00000009 + +/* RSS Packet Types as indicated in the receive descriptor. */ +#define IXGBE_RXDADV_PKTTYPE_NONE 0x00000000 +#define IXGBE_RXDADV_PKTTYPE_IPV4 0x00000010 /* IPv4 hdr present */ +#define IXGBE_RXDADV_PKTTYPE_IPV4_EX 0x00000020 /* IPv4 hdr + extensions */ +#define IXGBE_RXDADV_PKTTYPE_IPV6 0x00000040 /* IPv6 hdr present */ +#define IXGBE_RXDADV_PKTTYPE_IPV6_EX 0x00000080 /* IPv6 hdr + extensions */ +#define IXGBE_RXDADV_PKTTYPE_TCP 0x00000100 /* TCP hdr present */ +#define IXGBE_RXDADV_PKTTYPE_UDP 0x00000200 /* UDP hdr present */ +#define IXGBE_RXDADV_PKTTYPE_SCTP 0x00000400 /* SCTP hdr present */ +#define IXGBE_RXDADV_PKTTYPE_NFS 0x00000800 /* NFS hdr present */ +#define IXGBE_RXDADV_PKTTYPE_VXLAN 0x00000800 /* VXLAN hdr present */ +#define IXGBE_RXDADV_PKTTYPE_TUNNEL 0x00010000 /* Tunnel type */ +#define IXGBE_RXDADV_PKTTYPE_IPSEC_ESP 0x00001000 /* IPSec ESP */ +#define IXGBE_RXDADV_PKTTYPE_IPSEC_AH 0x00002000 /* IPSec AH */ +#define IXGBE_RXDADV_PKTTYPE_LINKSEC 0x00004000 /* LinkSec Encap */ +#define IXGBE_RXDADV_PKTTYPE_ETQF 0x00008000 /* PKTTYPE is ETQF index */ +#define IXGBE_RXDADV_PKTTYPE_ETQF_MASK 0x00000070 /* ETQF has 8 indices */ +#define IXGBE_RXDADV_PKTTYPE_ETQF_SHIFT 4 /* Right-shift 4 bits */ + +/* Masks to determine if packets should be dropped due to frame errors */ +#define IXGBE_RXD_ERR_FRAME_ERR_MASK ( \ + IXGBE_RXD_ERR_CE | \ + IXGBE_RXD_ERR_LE | \ + IXGBE_RXD_ERR_PE | \ + IXGBE_RXD_ERR_OSE | \ + IXGBE_RXD_ERR_USE) + +#define IXGBE_RXDADV_ERR_FRAME_ERR_MASK ( \ + IXGBE_RXDADV_ERR_CE | \ + IXGBE_RXDADV_ERR_LE | \ + IXGBE_RXDADV_ERR_PE | \ + IXGBE_RXDADV_ERR_OSE | \ + IXGBE_RXDADV_ERR_IPSEC_INV_PROTOCOL | \ + IXGBE_RXDADV_ERR_IPSEC_INV_LENGTH | \ + IXGBE_RXDADV_ERR_USE) + +/* Multicast bit mask */ +#define IXGBE_MCSTCTRL_MFE 0x4 + +/* Number of Transmit and Receive Descriptors must be a multiple of 8 */ +#define IXGBE_REQ_TX_DESCRIPTOR_MULTIPLE 8 +#define IXGBE_REQ_RX_DESCRIPTOR_MULTIPLE 8 +#define IXGBE_REQ_TX_BUFFER_GRANULARITY 1024 + +/* Vlan-specific macros */ +#define IXGBE_RX_DESC_SPECIAL_VLAN_MASK 0x0FFF /* VLAN ID in lower 12 bits */ +#define IXGBE_RX_DESC_SPECIAL_PRI_MASK 0xE000 /* Priority in upper 3 bits */ +#define IXGBE_RX_DESC_SPECIAL_PRI_SHIFT 0x000D /* Priority in upper 3 of 16 */ +#define IXGBE_TX_DESC_SPECIAL_PRI_SHIFT IXGBE_RX_DESC_SPECIAL_PRI_SHIFT + +/* SR-IOV specific macros */ +#define IXGBE_MBVFICR_INDEX(vf_number) (vf_number >> 4) +#define IXGBE_MBVFICR(_i) (0x00710 + ((_i) * 4)) +#define IXGBE_VFLRE(_i) ((((_i) & 1) ? 0x001C0 : 0x00600)) +#define IXGBE_VFLREC(_i) (0x00700 + ((_i) * 4)) +/* Translated register #defines */ +#define IXGBE_PVFTDH(P) (0x06010 + (0x40 * (P))) +#define IXGBE_PVFTDT(P) (0x06018 + (0x40 * (P))) +#define IXGBE_PVFTXDCTL(P) (0x06028 + (0x40 * (P))) +#define IXGBE_PVFTDWBAL(P) (0x06038 + (0x40 * (P))) +#define IXGBE_PVFTDWBAH(P) (0x0603C + (0x40 * (P))) + +#define IXGBE_PVFTDWBALn(q_per_pool, vf_number, vf_q_index) \ + (IXGBE_PVFTDWBAL((q_per_pool)*(vf_number) + (vf_q_index))) +#define IXGBE_PVFTDWBAHn(q_per_pool, vf_number, vf_q_index) \ + (IXGBE_PVFTDWBAH((q_per_pool)*(vf_number) + (vf_q_index))) + +#define IXGBE_PVFTDHN(q_per_pool, vf_number, vf_q_index) \ + (IXGBE_PVFTDH((q_per_pool)*(vf_number) + (vf_q_index))) +#define IXGBE_PVFTDTN(q_per_pool, vf_number, vf_q_index) \ + (IXGBE_PVFTDT((q_per_pool)*(vf_number) + (vf_q_index))) + +enum ixgbe_fdir_pballoc_type { + IXGBE_FDIR_PBALLOC_NONE = 0, + IXGBE_FDIR_PBALLOC_64K = 1, + IXGBE_FDIR_PBALLOC_128K = 2, + IXGBE_FDIR_PBALLOC_256K = 3, +}; +#define IXGBE_FDIR_PBALLOC_SIZE_SHIFT 16 + +/* Flow Director register values */ +#define IXGBE_FDIRCTRL_PBALLOC_64K 0x00000001 +#define IXGBE_FDIRCTRL_PBALLOC_128K 0x00000002 +#define IXGBE_FDIRCTRL_PBALLOC_256K 0x00000003 +#define IXGBE_FDIRCTRL_INIT_DONE 0x00000008 +#define IXGBE_FDIRCTRL_PERFECT_MATCH 0x00000010 +#define IXGBE_FDIRCTRL_REPORT_STATUS 0x00000020 +#define IXGBE_FDIRCTRL_REPORT_STATUS_ALWAYS 0x00000080 +#define IXGBE_FDIRCTRL_DROP_Q_SHIFT 8 +#define IXGBE_FDIRCTRL_FLEX_SHIFT 16 +#define IXGBE_FDIRCTRL_DROP_NO_MATCH 0x00008000 +#define IXGBE_FDIRCTRL_FILTERMODE_SHIFT 21 +#define IXGBE_FDIRCTRL_FILTERMODE_MACVLAN 0x0001 /* bit 23:21, 001b */ +#define IXGBE_FDIRCTRL_FILTERMODE_CLOUD 0x0002 /* bit 23:21, 010b */ +#define IXGBE_FDIRCTRL_SEARCHLIM 0x00800000 +#define IXGBE_FDIRCTRL_MAX_LENGTH_SHIFT 24 +#define IXGBE_FDIRCTRL_FULL_THRESH_MASK 0xF0000000 +#define IXGBE_FDIRCTRL_FULL_THRESH_SHIFT 28 + +#define IXGBE_FDIRTCPM_DPORTM_SHIFT 16 +#define IXGBE_FDIRUDPM_DPORTM_SHIFT 16 +#define IXGBE_FDIRIP6M_DIPM_SHIFT 16 +#define IXGBE_FDIRM_VLANID 0x00000001 +#define IXGBE_FDIRM_VLANP 0x00000002 +#define IXGBE_FDIRM_POOL 0x00000004 +#define IXGBE_FDIRM_L4P 0x00000008 +#define IXGBE_FDIRM_FLEX 0x00000010 +#define IXGBE_FDIRM_DIPv6 0x00000020 + +#define IXGBE_FDIRFREE_FREE_MASK 0xFFFF +#define IXGBE_FDIRFREE_FREE_SHIFT 0 +#define IXGBE_FDIRFREE_COLL_MASK 0x7FFF0000 +#define IXGBE_FDIRFREE_COLL_SHIFT 16 +#define IXGBE_FDIRLEN_MAXLEN_MASK 0x3F +#define IXGBE_FDIRLEN_MAXLEN_SHIFT 0 +#define IXGBE_FDIRLEN_MAXHASH_MASK 0x7FFF0000 +#define IXGBE_FDIRLEN_MAXHASH_SHIFT 16 +#define IXGBE_FDIRUSTAT_ADD_MASK 0xFFFF +#define IXGBE_FDIRUSTAT_ADD_SHIFT 0 +#define IXGBE_FDIRUSTAT_REMOVE_MASK 0xFFFF0000 +#define IXGBE_FDIRUSTAT_REMOVE_SHIFT 16 +#define IXGBE_FDIRFSTAT_FADD_MASK 0x00FF +#define IXGBE_FDIRFSTAT_FADD_SHIFT 0 +#define IXGBE_FDIRFSTAT_FREMOVE_MASK 0xFF00 +#define IXGBE_FDIRFSTAT_FREMOVE_SHIFT 8 +#define IXGBE_FDIRPORT_DESTINATION_SHIFT 16 +#define IXGBE_FDIRVLAN_FLEX_SHIFT 16 +#define IXGBE_FDIRHASH_BUCKET_VALID_SHIFT 15 +#define IXGBE_FDIRHASH_SIG_SW_INDEX_SHIFT 16 + +#define IXGBE_FDIRCMD_CMD_MASK 0x00000003 +#define IXGBE_FDIRCMD_CMD_ADD_FLOW 0x00000001 +#define IXGBE_FDIRCMD_CMD_REMOVE_FLOW 0x00000002 +#define IXGBE_FDIRCMD_CMD_QUERY_REM_FILT 0x00000003 +#define IXGBE_FDIRCMD_FILTER_VALID 0x00000004 +#define IXGBE_FDIRCMD_FILTER_UPDATE 0x00000008 +#define IXGBE_FDIRCMD_IPv6DMATCH 0x00000010 +#define IXGBE_FDIRCMD_L4TYPE_UDP 0x00000020 +#define IXGBE_FDIRCMD_L4TYPE_TCP 0x00000040 +#define IXGBE_FDIRCMD_L4TYPE_SCTP 0x00000060 +#define IXGBE_FDIRCMD_IPV6 0x00000080 +#define IXGBE_FDIRCMD_CLEARHT 0x00000100 +#define IXGBE_FDIRCMD_DROP 0x00000200 +#define IXGBE_FDIRCMD_INT 0x00000400 +#define IXGBE_FDIRCMD_LAST 0x00000800 +#define IXGBE_FDIRCMD_COLLISION 0x00001000 +#define IXGBE_FDIRCMD_QUEUE_EN 0x00008000 +#define IXGBE_FDIRCMD_FLOW_TYPE_SHIFT 5 +#define IXGBE_FDIRCMD_RX_QUEUE_SHIFT 16 +#define IXGBE_FDIRCMD_RX_TUNNEL_FILTER_SHIFT 23 +#define IXGBE_FDIRCMD_VT_POOL_SHIFT 24 +#define IXGBE_FDIR_INIT_DONE_POLL 10 +#define IXGBE_FDIRCMD_CMD_POLL 10 +#define IXGBE_FDIRCMD_TUNNEL_FILTER 0x00800000 + +#define IXGBE_FDIR_DROP_QUEUE 127 + +/* Manageablility Host Interface defines */ +#define IXGBE_HI_MAX_BLOCK_BYTE_LENGTH 1792 /* Num of bytes in range */ +#define IXGBE_HI_MAX_BLOCK_DWORD_LENGTH 448 /* Num of dwords in range */ +#define IXGBE_HI_COMMAND_TIMEOUT 500 /* Process HI command limit */ +#define IXGBE_HI_FLASH_ERASE_TIMEOUT 1000 /* Process Erase command limit */ +#define IXGBE_HI_FLASH_UPDATE_TIMEOUT 5000 /* Process Update command limit */ +#define IXGBE_HI_FLASH_APPLY_TIMEOUT 0 /* Process Apply command limit */ + +/* CEM Support */ +#define FW_CEM_HDR_LEN 0x4 +#define FW_CEM_CMD_DRIVER_INFO 0xDD +#define FW_CEM_CMD_DRIVER_INFO_LEN 0x5 +#define FW_CEM_CMD_RESERVED 0x0 +#define FW_CEM_UNUSED_VER 0x0 +#define FW_CEM_MAX_RETRIES 3 +#define FW_CEM_RESP_STATUS_SUCCESS 0x1 +#define FW_CEM_DRIVER_VERSION_SIZE 39 /* +9 would send 48 bytes to fw */ +#define FW_READ_SHADOW_RAM_CMD 0x31 +#define FW_READ_SHADOW_RAM_LEN 0x6 +#define FW_WRITE_SHADOW_RAM_CMD 0x33 +#define FW_WRITE_SHADOW_RAM_LEN 0xA /* 8 plus 1 WORD to write */ +#define FW_SHADOW_RAM_DUMP_CMD 0x36 +#define FW_SHADOW_RAM_DUMP_LEN 0 +#define FW_DEFAULT_CHECKSUM 0xFF /* checksum always 0xFF */ +#define FW_NVM_DATA_OFFSET 3 +#define FW_MAX_READ_BUFFER_SIZE 1024 +#define FW_DISABLE_RXEN_CMD 0xDE +#define FW_DISABLE_RXEN_LEN 0x1 +#define FW_PHY_MGMT_REQ_CMD 0x20 +#define FW_PHY_TOKEN_REQ_CMD 0x0A +#define FW_PHY_TOKEN_REQ_LEN 2 +#define FW_PHY_TOKEN_REQ 0 +#define FW_PHY_TOKEN_REL 1 +#define FW_PHY_TOKEN_OK 1 +#define FW_PHY_TOKEN_RETRY 0x80 +#define FW_PHY_TOKEN_DELAY 5 /* milliseconds */ +#define FW_PHY_TOKEN_WAIT 5 /* seconds */ +#define FW_PHY_TOKEN_RETRIES ((FW_PHY_TOKEN_WAIT * 1000) / FW_PHY_TOKEN_DELAY) +#define FW_INT_PHY_REQ_CMD 0xB +#define FW_INT_PHY_REQ_LEN 10 +#define FW_INT_PHY_REQ_READ 0 +#define FW_INT_PHY_REQ_WRITE 1 +#define FW_PHY_ACT_REQ_CMD 5 +#define FW_PHY_ACT_DATA_COUNT 4 +#define FW_PHY_ACT_REQ_LEN (4 + 4 * FW_PHY_ACT_DATA_COUNT) +#define FW_PHY_ACT_INIT_PHY 1 +#define FW_PHY_ACT_SETUP_LINK 2 +#define FW_PHY_ACT_LINK_SPEED_10 BIT(0) +#define FW_PHY_ACT_LINK_SPEED_100 BIT(1) +#define FW_PHY_ACT_LINK_SPEED_1G BIT(2) +#define FW_PHY_ACT_LINK_SPEED_2_5G BIT(3) +#define FW_PHY_ACT_LINK_SPEED_5G BIT(4) +#define FW_PHY_ACT_LINK_SPEED_10G BIT(5) +#define FW_PHY_ACT_LINK_SPEED_20G BIT(6) +#define FW_PHY_ACT_LINK_SPEED_25G BIT(7) +#define FW_PHY_ACT_LINK_SPEED_40G BIT(8) +#define FW_PHY_ACT_LINK_SPEED_50G BIT(9) +#define FW_PHY_ACT_LINK_SPEED_100G BIT(10) +#define FW_PHY_ACT_SETUP_LINK_PAUSE_SHIFT 16 +#define FW_PHY_ACT_SETUP_LINK_PAUSE_MASK (3 << \ + HW_PHY_ACT_SETUP_LINK_PAUSE_SHIFT) +#define FW_PHY_ACT_SETUP_LINK_PAUSE_NONE 0u +#define FW_PHY_ACT_SETUP_LINK_PAUSE_TX 1u +#define FW_PHY_ACT_SETUP_LINK_PAUSE_RX 2u +#define FW_PHY_ACT_SETUP_LINK_PAUSE_RXTX 3u +#define FW_PHY_ACT_SETUP_LINK_LP BIT(18) +#define FW_PHY_ACT_SETUP_LINK_HP BIT(19) +#define FW_PHY_ACT_SETUP_LINK_EEE BIT(20) +#define FW_PHY_ACT_SETUP_LINK_AN BIT(22) +#define FW_PHY_ACT_SETUP_LINK_RSP_DOWN BIT(0) +#define FW_PHY_ACT_GET_LINK_INFO 3 +#define FW_PHY_ACT_GET_LINK_INFO_EEE BIT(19) +#define FW_PHY_ACT_GET_LINK_INFO_FC_TX BIT(20) +#define FW_PHY_ACT_GET_LINK_INFO_FC_RX BIT(21) +#define FW_PHY_ACT_GET_LINK_INFO_POWER BIT(22) +#define FW_PHY_ACT_GET_LINK_INFO_AN_COMPLETE BIT(24) +#define FW_PHY_ACT_GET_LINK_INFO_TEMP BIT(25) +#define FW_PHY_ACT_GET_LINK_INFO_LP_FC_TX BIT(28) +#define FW_PHY_ACT_GET_LINK_INFO_LP_FC_RX BIT(29) +#define FW_PHY_ACT_FORCE_LINK_DOWN 4 +#define FW_PHY_ACT_FORCE_LINK_DOWN_OFF BIT(0) +#define FW_PHY_ACT_PHY_SW_RESET 5 +#define FW_PHY_ACT_PHY_HW_RESET 6 +#define FW_PHY_ACT_GET_PHY_INFO 7 +#define FW_PHY_ACT_UD_2 0x1002 +#define FW_PHY_ACT_UD_2_10G_KR_EEE BIT(6) +#define FW_PHY_ACT_UD_2_10G_KX4_EEE BIT(5) +#define FW_PHY_ACT_UD_2_1G_KX_EEE BIT(4) +#define FW_PHY_ACT_UD_2_10G_T_EEE BIT(3) +#define FW_PHY_ACT_UD_2_1G_T_EEE BIT(2) +#define FW_PHY_ACT_UD_2_100M_TX_EEE BIT(1) +#define FW_PHY_ACT_RETRIES 50 +#define FW_PHY_INFO_SPEED_MASK 0xFFFu +#define FW_PHY_INFO_ID_HI_MASK 0xFFFF0000u +#define FW_PHY_INFO_ID_LO_MASK 0x0000FFFFu + +/* Host Interface Command Structures */ +struct ixgbe_hic_hdr { + u8 cmd; + u8 buf_len; + union { + u8 cmd_resv; + u8 ret_status; + } cmd_or_resp; + u8 checksum; +}; + +struct ixgbe_hic_hdr2_req { + u8 cmd; + u8 buf_lenh; + u8 buf_lenl; + u8 checksum; +}; + +struct ixgbe_hic_hdr2_rsp { + u8 cmd; + u8 buf_lenl; + u8 buf_lenh_status; /* 7-5: high bits of buf_len, 4-0: status */ + u8 checksum; +}; + +union ixgbe_hic_hdr2 { + struct ixgbe_hic_hdr2_req req; + struct ixgbe_hic_hdr2_rsp rsp; +}; + +struct ixgbe_hic_drv_info { + struct ixgbe_hic_hdr hdr; + u8 port_num; + u8 ver_sub; + u8 ver_build; + u8 ver_min; + u8 ver_maj; + u8 pad; /* end spacing to ensure length is mult. of dword */ + u16 pad2; /* end spacing to ensure length is mult. of dword2 */ +}; + +struct ixgbe_hic_drv_info2 { + struct ixgbe_hic_hdr hdr; + u8 port_num; + u8 ver_sub; + u8 ver_build; + u8 ver_min; + u8 ver_maj; + char driver_string[FW_CEM_DRIVER_VERSION_SIZE]; +}; + +/* These need to be dword aligned */ +struct ixgbe_hic_read_shadow_ram { + union ixgbe_hic_hdr2 hdr; + u32 address; + u16 length; + u16 pad2; + u16 data; + u16 pad3; +}; + +struct ixgbe_hic_write_shadow_ram { + union ixgbe_hic_hdr2 hdr; + __be32 address; + __be16 length; + u16 pad2; + u16 data; + u16 pad3; +}; + +struct ixgbe_hic_disable_rxen { + struct ixgbe_hic_hdr hdr; + u8 port_number; + u8 pad2; + u16 pad3; +}; + +struct ixgbe_hic_phy_token_req { + struct ixgbe_hic_hdr hdr; + u8 port_number; + u8 command_type; + u16 pad; +}; + +struct ixgbe_hic_internal_phy_req { + struct ixgbe_hic_hdr hdr; + u8 port_number; + u8 command_type; + __be16 address; + u16 rsv1; + __be32 write_data; + u16 pad; +} __packed; + +struct ixgbe_hic_internal_phy_resp { + struct ixgbe_hic_hdr hdr; + __be32 read_data; +}; + +struct ixgbe_hic_phy_activity_req { + struct ixgbe_hic_hdr hdr; + u8 port_number; + u8 pad; + __le16 activity_id; + __be32 data[FW_PHY_ACT_DATA_COUNT]; +}; + +struct ixgbe_hic_phy_activity_resp { + struct ixgbe_hic_hdr hdr; + __be32 data[FW_PHY_ACT_DATA_COUNT]; +}; + +/* Transmit Descriptor - Advanced */ +union ixgbe_adv_tx_desc { + struct { + __le64 buffer_addr; /* Address of descriptor's data buf */ + __le32 cmd_type_len; + __le32 olinfo_status; + } read; + struct { + __le64 rsvd; /* Reserved */ + __le32 nxtseq_seed; + __le32 status; + } wb; +}; + +/* Receive Descriptor - Advanced */ +union ixgbe_adv_rx_desc { + struct { + __le64 pkt_addr; /* Packet buffer address */ + __le64 hdr_addr; /* Header buffer address */ + } read; + struct { + struct { + union { + __le32 data; + struct { + __le16 pkt_info; /* RSS, Pkt type */ + __le16 hdr_info; /* Splithdr, hdrlen */ + } hs_rss; + } lo_dword; + union { + __le32 rss; /* RSS Hash */ + struct { + __le16 ip_id; /* IP id */ + __le16 csum; /* Packet Checksum */ + } csum_ip; + } hi_dword; + } lower; + struct { + __le32 status_error; /* ext status/error */ + __le16 length; /* Packet length */ + __le16 vlan; /* VLAN tag */ + } upper; + } wb; /* writeback */ +}; + +/* Context descriptors */ +struct ixgbe_adv_tx_context_desc { + __le32 vlan_macip_lens; + __le32 fceof_saidx; + __le32 type_tucmd_mlhl; + __le32 mss_l4len_idx; +}; + +/* Adv Transmit Descriptor Config Masks */ +#define IXGBE_ADVTXD_DTALEN_MASK 0x0000FFFF /* Data buf length(bytes) */ +#define IXGBE_ADVTXD_MAC_LINKSEC 0x00040000 /* Insert LinkSec */ +#define IXGBE_ADVTXD_MAC_TSTAMP 0x00080000 /* IEEE 1588 Time Stamp */ +#define IXGBE_ADVTXD_IPSEC_SA_INDEX_MASK 0x000003FF /* IPSec SA index */ +#define IXGBE_ADVTXD_IPSEC_ESP_LEN_MASK 0x000001FF /* IPSec ESP length */ +#define IXGBE_ADVTXD_DTYP_MASK 0x00F00000 /* DTYP mask */ +#define IXGBE_ADVTXD_DTYP_CTXT 0x00200000 /* Advanced Context Desc */ +#define IXGBE_ADVTXD_DTYP_DATA 0x00300000 /* Advanced Data Descriptor */ +#define IXGBE_ADVTXD_DCMD_EOP IXGBE_TXD_CMD_EOP /* End of Packet */ +#define IXGBE_ADVTXD_DCMD_IFCS IXGBE_TXD_CMD_IFCS /* Insert FCS */ +#define IXGBE_ADVTXD_DCMD_RS IXGBE_TXD_CMD_RS /* Report Status */ +#define IXGBE_ADVTXD_DCMD_DDTYP_ISCSI 0x10000000 /* DDP hdr type or iSCSI */ +#define IXGBE_ADVTXD_DCMD_DEXT IXGBE_TXD_CMD_DEXT /* Desc ext (1=Adv) */ +#define IXGBE_ADVTXD_DCMD_VLE IXGBE_TXD_CMD_VLE /* VLAN pkt enable */ +#define IXGBE_ADVTXD_DCMD_TSE 0x80000000 /* TCP Seg enable */ +#define IXGBE_ADVTXD_STAT_DD IXGBE_TXD_STAT_DD /* Descriptor Done */ +#define IXGBE_ADVTXD_STAT_SN_CRC 0x00000002 /* NXTSEQ/SEED pres in WB */ +#define IXGBE_ADVTXD_STAT_RSV 0x0000000C /* STA Reserved */ +#define IXGBE_ADVTXD_IDX_SHIFT 4 /* Adv desc Index shift */ +#define IXGBE_ADVTXD_CC 0x00000080 /* Check Context */ +#define IXGBE_ADVTXD_POPTS_SHIFT 8 /* Adv desc POPTS shift */ +#define IXGBE_ADVTXD_POPTS_IXSM (IXGBE_TXD_POPTS_IXSM << \ + IXGBE_ADVTXD_POPTS_SHIFT) +#define IXGBE_ADVTXD_POPTS_TXSM (IXGBE_TXD_POPTS_TXSM << \ + IXGBE_ADVTXD_POPTS_SHIFT) +#define IXGBE_ADVTXD_POPTS_IPSEC 0x00000400 /* IPSec offload request */ +#define IXGBE_ADVTXD_POPTS_ISCO_1ST 0x00000000 /* 1st TSO of iSCSI PDU */ +#define IXGBE_ADVTXD_POPTS_ISCO_MDL 0x00000800 /* Middle TSO of iSCSI PDU */ +#define IXGBE_ADVTXD_POPTS_ISCO_LAST 0x00001000 /* Last TSO of iSCSI PDU */ +#define IXGBE_ADVTXD_POPTS_ISCO_FULL 0x00001800 /* 1st&Last TSO-full iSCSI PDU */ +#define IXGBE_ADVTXD_POPTS_RSV 0x00002000 /* POPTS Reserved */ +#define IXGBE_ADVTXD_PAYLEN_SHIFT 14 /* Adv desc PAYLEN shift */ +#define IXGBE_ADVTXD_MACLEN_SHIFT 9 /* Adv ctxt desc mac len shift */ +#define IXGBE_ADVTXD_VLAN_SHIFT 16 /* Adv ctxt vlan tag shift */ +#define IXGBE_ADVTXD_TUCMD_IPV4 0x00000400 /* IP Packet Type: 1=IPv4 */ +#define IXGBE_ADVTXD_TUCMD_IPV6 0x00000000 /* IP Packet Type: 0=IPv6 */ +#define IXGBE_ADVTXD_TUCMD_L4T_UDP 0x00000000 /* L4 Packet TYPE of UDP */ +#define IXGBE_ADVTXD_TUCMD_L4T_TCP 0x00000800 /* L4 Packet TYPE of TCP */ +#define IXGBE_ADVTXD_TUCMD_L4T_SCTP 0x00001000 /* L4 Packet TYPE of SCTP */ +#define IXGBE_ADVTXD_TUCMD_L4T_RSV 0x00001800 /* RSV L4 Packet TYPE */ +#define IXGBE_ADVTXD_TUCMD_MKRREQ 0x00002000 /*Req requires Markers and CRC*/ +#define IXGBE_ADVTXD_TUCMD_IPSEC_TYPE_ESP 0x00002000 /* IPSec Type ESP */ +#define IXGBE_ADVTXD_TUCMD_IPSEC_ENCRYPT_EN 0x00004000/* ESP Encrypt Enable */ +#define IXGBE_ADVTXT_TUCMD_FCOE 0x00008000 /* FCoE Frame Type */ +#define IXGBE_ADVTXD_FCOEF_SOF (BIT(2) << 10) /* FC SOF index */ +#define IXGBE_ADVTXD_FCOEF_PARINC (BIT(3) << 10) /* Rel_Off in F_CTL */ +#define IXGBE_ADVTXD_FCOEF_ORIE (BIT(4) << 10) /* Orientation: End */ +#define IXGBE_ADVTXD_FCOEF_ORIS (BIT(5) << 10) /* Orientation: Start */ +#define IXGBE_ADVTXD_FCOEF_EOF_N (0u << 10) /* 00: EOFn */ +#define IXGBE_ADVTXD_FCOEF_EOF_T (1u << 10) /* 01: EOFt */ +#define IXGBE_ADVTXD_FCOEF_EOF_NI (2u << 10) /* 10: EOFni */ +#define IXGBE_ADVTXD_FCOEF_EOF_A (3u << 10) /* 11: EOFa */ +#define IXGBE_ADVTXD_FCOEF_EOF_MASK (3u << 10) /* FC EOF index */ +#define IXGBE_ADVTXD_L4LEN_SHIFT 8 /* Adv ctxt L4LEN shift */ +#define IXGBE_ADVTXD_MSS_SHIFT 16 /* Adv ctxt MSS shift */ + +/* Autonegotiation advertised speeds */ +typedef u32 ixgbe_autoneg_advertised; +/* Link speed */ +typedef u32 ixgbe_link_speed; +#define IXGBE_LINK_SPEED_UNKNOWN 0 +#define IXGBE_LINK_SPEED_10_FULL 0x0002 +#define IXGBE_LINK_SPEED_100_FULL 0x0008 +#define IXGBE_LINK_SPEED_1GB_FULL 0x0020 +#define IXGBE_LINK_SPEED_2_5GB_FULL 0x0400 +#define IXGBE_LINK_SPEED_5GB_FULL 0x0800 +#define IXGBE_LINK_SPEED_10GB_FULL 0x0080 +#define IXGBE_LINK_SPEED_82598_AUTONEG (IXGBE_LINK_SPEED_1GB_FULL | \ + IXGBE_LINK_SPEED_10GB_FULL) +#define IXGBE_LINK_SPEED_82599_AUTONEG (IXGBE_LINK_SPEED_100_FULL | \ + IXGBE_LINK_SPEED_1GB_FULL | \ + IXGBE_LINK_SPEED_10GB_FULL) + +/* Flow Control Data Sheet defined values + * Calculation and defines taken from 802.1bb Annex O + */ + +/* BitTimes (BT) conversion */ +#define IXGBE_BT2KB(BT) ((BT + (8 * 1024 - 1)) / (8 * 1024)) +#define IXGBE_B2BT(BT) (BT * 8) + +/* Calculate Delay to respond to PFC */ +#define IXGBE_PFC_D 672 + +/* Calculate Cable Delay */ +#define IXGBE_CABLE_DC 5556 /* Delay Copper */ +#define IXGBE_CABLE_DO 5000 /* Delay Optical */ + +/* Calculate Interface Delay X540 */ +#define IXGBE_PHY_DC 25600 /* Delay 10G BASET */ +#define IXGBE_MAC_DC 8192 /* Delay Copper XAUI interface */ +#define IXGBE_XAUI_DC (2 * 2048) /* Delay Copper Phy */ + +#define IXGBE_ID_X540 (IXGBE_MAC_DC + IXGBE_XAUI_DC + IXGBE_PHY_DC) + +/* Calculate Interface Delay 82598, 82599 */ +#define IXGBE_PHY_D 12800 +#define IXGBE_MAC_D 4096 +#define IXGBE_XAUI_D (2 * 1024) + +#define IXGBE_ID (IXGBE_MAC_D + IXGBE_XAUI_D + IXGBE_PHY_D) + +/* Calculate Delay incurred from higher layer */ +#define IXGBE_HD 6144 + +/* Calculate PCI Bus delay for low thresholds */ +#define IXGBE_PCI_DELAY 10000 + +/* Calculate X540 delay value in bit times */ +#define IXGBE_DV_X540(_max_frame_link, _max_frame_tc) \ + ((36 * \ + (IXGBE_B2BT(_max_frame_link) + \ + IXGBE_PFC_D + \ + (2 * IXGBE_CABLE_DC) + \ + (2 * IXGBE_ID_X540) + \ + IXGBE_HD) / 25 + 1) + \ + 2 * IXGBE_B2BT(_max_frame_tc)) + +/* Calculate 82599, 82598 delay value in bit times */ +#define IXGBE_DV(_max_frame_link, _max_frame_tc) \ + ((36 * \ + (IXGBE_B2BT(_max_frame_link) + \ + IXGBE_PFC_D + \ + (2 * IXGBE_CABLE_DC) + \ + (2 * IXGBE_ID) + \ + IXGBE_HD) / 25 + 1) + \ + 2 * IXGBE_B2BT(_max_frame_tc)) + +/* Calculate low threshold delay values */ +#define IXGBE_LOW_DV_X540(_max_frame_tc) \ + (2 * IXGBE_B2BT(_max_frame_tc) + \ + (36 * IXGBE_PCI_DELAY / 25) + 1) +#define IXGBE_LOW_DV(_max_frame_tc) \ + (2 * IXGBE_LOW_DV_X540(_max_frame_tc)) + +/* Software ATR hash keys */ +#define IXGBE_ATR_BUCKET_HASH_KEY 0x3DAD14E2 +#define IXGBE_ATR_SIGNATURE_HASH_KEY 0x174D3614 + +/* Software ATR input stream values and masks */ +#define IXGBE_ATR_HASH_MASK 0x7fff +#define IXGBE_ATR_L4TYPE_MASK 0x3 +#define IXGBE_ATR_L4TYPE_UDP 0x1 +#define IXGBE_ATR_L4TYPE_TCP 0x2 +#define IXGBE_ATR_L4TYPE_SCTP 0x3 +#define IXGBE_ATR_L4TYPE_IPV6_MASK 0x4 +#define IXGBE_ATR_L4TYPE_TUNNEL_MASK 0x10 +enum ixgbe_atr_flow_type { + IXGBE_ATR_FLOW_TYPE_IPV4 = 0x0, + IXGBE_ATR_FLOW_TYPE_UDPV4 = 0x1, + IXGBE_ATR_FLOW_TYPE_TCPV4 = 0x2, + IXGBE_ATR_FLOW_TYPE_SCTPV4 = 0x3, + IXGBE_ATR_FLOW_TYPE_IPV6 = 0x4, + IXGBE_ATR_FLOW_TYPE_UDPV6 = 0x5, + IXGBE_ATR_FLOW_TYPE_TCPV6 = 0x6, + IXGBE_ATR_FLOW_TYPE_SCTPV6 = 0x7, +}; + +/* Flow Director ATR input struct. */ +union ixgbe_atr_input { + /* + * Byte layout in order, all values with MSB first: + * + * vm_pool - 1 byte + * flow_type - 1 byte + * vlan_id - 2 bytes + * src_ip - 16 bytes + * dst_ip - 16 bytes + * src_port - 2 bytes + * dst_port - 2 bytes + * flex_bytes - 2 bytes + * bkt_hash - 2 bytes + */ + struct { + u8 vm_pool; + u8 flow_type; + __be16 vlan_id; + __be32 dst_ip[4]; + __be32 src_ip[4]; + __be16 src_port; + __be16 dst_port; + __be16 flex_bytes; + __be16 bkt_hash; + } formatted; + __be32 dword_stream[11]; +}; + +/* Flow Director compressed ATR hash input struct */ +union ixgbe_atr_hash_dword { + struct { + u8 vm_pool; + u8 flow_type; + __be16 vlan_id; + } formatted; + __be32 ip; + struct { + __be16 src; + __be16 dst; + } port; + __be16 flex_bytes; + __be32 dword; +}; + +#define IXGBE_MVALS_INIT(m) \ + IXGBE_CAT(EEC, m), \ + IXGBE_CAT(FLA, m), \ + IXGBE_CAT(GRC, m), \ + IXGBE_CAT(FACTPS, m), \ + IXGBE_CAT(SWSM, m), \ + IXGBE_CAT(SWFW_SYNC, m), \ + IXGBE_CAT(FWSM, m), \ + IXGBE_CAT(SDP0_GPIEN, m), \ + IXGBE_CAT(SDP1_GPIEN, m), \ + IXGBE_CAT(SDP2_GPIEN, m), \ + IXGBE_CAT(EICR_GPI_SDP0, m), \ + IXGBE_CAT(EICR_GPI_SDP1, m), \ + IXGBE_CAT(EICR_GPI_SDP2, m), \ + IXGBE_CAT(CIAA, m), \ + IXGBE_CAT(CIAD, m), \ + IXGBE_CAT(I2C_CLK_IN, m), \ + IXGBE_CAT(I2C_CLK_OUT, m), \ + IXGBE_CAT(I2C_DATA_IN, m), \ + IXGBE_CAT(I2C_DATA_OUT, m), \ + IXGBE_CAT(I2C_DATA_OE_N_EN, m), \ + IXGBE_CAT(I2C_BB_EN, m), \ + IXGBE_CAT(I2C_CLK_OE_N_EN, m), \ + IXGBE_CAT(I2CCTL, m) + +enum ixgbe_mvals { + IXGBE_MVALS_INIT(IDX), + IXGBE_MVALS_IDX_LIMIT +}; + +enum ixgbe_eeprom_type { + ixgbe_eeprom_uninitialized = 0, + ixgbe_eeprom_spi, + ixgbe_flash, + ixgbe_eeprom_none /* No NVM support */ +}; + +enum ixgbe_mac_type { + ixgbe_mac_unknown = 0, + ixgbe_mac_82598EB, + ixgbe_mac_82599EB, + ixgbe_mac_X540, + ixgbe_mac_X550, + ixgbe_mac_X550EM_x, + ixgbe_mac_x550em_a, + ixgbe_num_macs +}; + +enum ixgbe_phy_type { + ixgbe_phy_unknown = 0, + ixgbe_phy_none, + ixgbe_phy_tn, + ixgbe_phy_aq, + ixgbe_phy_x550em_kr, + ixgbe_phy_x550em_kx4, + ixgbe_phy_x550em_xfi, + ixgbe_phy_x550em_ext_t, + ixgbe_phy_ext_1g_t, + ixgbe_phy_cu_unknown, + ixgbe_phy_qt, + ixgbe_phy_xaui, + ixgbe_phy_nl, + ixgbe_phy_sfp_passive_tyco, + ixgbe_phy_sfp_passive_unknown, + ixgbe_phy_sfp_active_unknown, + ixgbe_phy_sfp_avago, + ixgbe_phy_sfp_ftl, + ixgbe_phy_sfp_ftl_active, + ixgbe_phy_sfp_unknown, + ixgbe_phy_sfp_intel, + ixgbe_phy_qsfp_passive_unknown, + ixgbe_phy_qsfp_active_unknown, + ixgbe_phy_qsfp_intel, + ixgbe_phy_qsfp_unknown, + ixgbe_phy_sfp_unsupported, + ixgbe_phy_sgmii, + ixgbe_phy_fw, + ixgbe_phy_generic +}; + +/* + * SFP+ module type IDs: + * + * ID Module Type + * ============= + * 0 SFP_DA_CU + * 1 SFP_SR + * 2 SFP_LR + * 3 SFP_DA_CU_CORE0 - 82599-specific + * 4 SFP_DA_CU_CORE1 - 82599-specific + * 5 SFP_SR/LR_CORE0 - 82599-specific + * 6 SFP_SR/LR_CORE1 - 82599-specific + */ +enum ixgbe_sfp_type { + ixgbe_sfp_type_da_cu = 0, + ixgbe_sfp_type_sr = 1, + ixgbe_sfp_type_lr = 2, + ixgbe_sfp_type_da_cu_core0 = 3, + ixgbe_sfp_type_da_cu_core1 = 4, + ixgbe_sfp_type_srlr_core0 = 5, + ixgbe_sfp_type_srlr_core1 = 6, + ixgbe_sfp_type_da_act_lmt_core0 = 7, + ixgbe_sfp_type_da_act_lmt_core1 = 8, + ixgbe_sfp_type_1g_cu_core0 = 9, + ixgbe_sfp_type_1g_cu_core1 = 10, + ixgbe_sfp_type_1g_sx_core0 = 11, + ixgbe_sfp_type_1g_sx_core1 = 12, + ixgbe_sfp_type_1g_lx_core0 = 13, + ixgbe_sfp_type_1g_lx_core1 = 14, + ixgbe_sfp_type_not_present = 0xFFFE, + ixgbe_sfp_type_unknown = 0xFFFF +}; + +enum ixgbe_media_type { + ixgbe_media_type_unknown = 0, + ixgbe_media_type_fiber, + ixgbe_media_type_fiber_qsfp, + ixgbe_media_type_fiber_lco, + ixgbe_media_type_copper, + ixgbe_media_type_backplane, + ixgbe_media_type_cx4, + ixgbe_media_type_virtual +}; + +/* Flow Control Settings */ +enum ixgbe_fc_mode { + ixgbe_fc_none = 0, + ixgbe_fc_rx_pause, + ixgbe_fc_tx_pause, + ixgbe_fc_full, + ixgbe_fc_default +}; + +/* Smart Speed Settings */ +#define IXGBE_SMARTSPEED_MAX_RETRIES 3 +enum ixgbe_smart_speed { + ixgbe_smart_speed_auto = 0, + ixgbe_smart_speed_on, + ixgbe_smart_speed_off +}; + +/* PCI bus types */ +enum ixgbe_bus_type { + ixgbe_bus_type_unknown = 0, + ixgbe_bus_type_pci_express, + ixgbe_bus_type_internal, + ixgbe_bus_type_reserved +}; + +/* PCI bus speeds */ +enum ixgbe_bus_speed { + ixgbe_bus_speed_unknown = 0, + ixgbe_bus_speed_33 = 33, + ixgbe_bus_speed_66 = 66, + ixgbe_bus_speed_100 = 100, + ixgbe_bus_speed_120 = 120, + ixgbe_bus_speed_133 = 133, + ixgbe_bus_speed_2500 = 2500, + ixgbe_bus_speed_5000 = 5000, + ixgbe_bus_speed_8000 = 8000, + ixgbe_bus_speed_reserved +}; + +/* PCI bus widths */ +enum ixgbe_bus_width { + ixgbe_bus_width_unknown = 0, + ixgbe_bus_width_pcie_x1 = 1, + ixgbe_bus_width_pcie_x2 = 2, + ixgbe_bus_width_pcie_x4 = 4, + ixgbe_bus_width_pcie_x8 = 8, + ixgbe_bus_width_32 = 32, + ixgbe_bus_width_64 = 64, + ixgbe_bus_width_reserved +}; + +struct ixgbe_addr_filter_info { + u32 num_mc_addrs; + u32 rar_used_count; + u32 mta_in_use; + u32 overflow_promisc; + bool uc_set_promisc; + bool user_set_promisc; +}; + +/* Bus parameters */ +struct ixgbe_bus_info { + enum ixgbe_bus_speed speed; + enum ixgbe_bus_width width; + enum ixgbe_bus_type type; + + u8 func; + u8 lan_id; + u8 instance_id; +}; + +/* Flow control parameters */ +struct ixgbe_fc_info { + u32 high_water[MAX_TRAFFIC_CLASS]; /* Flow Control High-water */ + u32 low_water[MAX_TRAFFIC_CLASS]; /* Flow Control Low-water */ + u16 pause_time; /* Flow Control Pause timer */ + bool send_xon; /* Flow control send XON */ + bool strict_ieee; /* Strict IEEE mode */ + bool disable_fc_autoneg; /* Do not autonegotiate FC */ + bool fc_was_autonegged; /* Is current_mode the result of autonegging? */ + enum ixgbe_fc_mode current_mode; /* FC mode in effect */ + enum ixgbe_fc_mode requested_mode; /* FC mode requested by caller */ +}; + +/* Statistics counters collected by the MAC */ +struct ixgbe_hw_stats { + u64 crcerrs; + u64 illerrc; + u64 errbc; + u64 mspdc; + u64 mpctotal; + u64 mpc[8]; + u64 mlfc; + u64 mrfc; + u64 rlec; + u64 lxontxc; + u64 lxonrxc; + u64 lxofftxc; + u64 lxoffrxc; + u64 pxontxc[8]; + u64 pxonrxc[8]; + u64 pxofftxc[8]; + u64 pxoffrxc[8]; + u64 prc64; + u64 prc127; + u64 prc255; + u64 prc511; + u64 prc1023; + u64 prc1522; + u64 gprc; + u64 bprc; + u64 mprc; + u64 gptc; + u64 gorc; + u64 gotc; + u64 rnbc[8]; + u64 ruc; + u64 rfc; + u64 roc; + u64 rjc; + u64 mngprc; + u64 mngpdc; + u64 mngptc; + u64 tor; + u64 tpr; + u64 tpt; + u64 ptc64; + u64 ptc127; + u64 ptc255; + u64 ptc511; + u64 ptc1023; + u64 ptc1522; + u64 mptc; + u64 bptc; + u64 xec; + u64 rqsmr[16]; + u64 tqsmr[8]; + u64 qprc[16]; + u64 qptc[16]; + u64 qbrc[16]; + u64 qbtc[16]; + u64 qprdc[16]; + u64 pxon2offc[8]; + u64 fdirustat_add; + u64 fdirustat_remove; + u64 fdirfstat_fadd; + u64 fdirfstat_fremove; + u64 fdirmatch; + u64 fdirmiss; + u64 fccrc; + u64 fcoerpdc; + u64 fcoeprc; + u64 fcoeptc; + u64 fcoedwrc; + u64 fcoedwtc; + u64 fcoe_noddp; + u64 fcoe_noddp_ext_buff; + u64 b2ospc; + u64 b2ogprc; + u64 o2bgptc; + u64 o2bspc; +}; + +/* forward declaration */ +struct ixgbe_hw; + +/* iterator type for walking multicast address lists */ +typedef u8* (*ixgbe_mc_addr_itr) (struct ixgbe_hw *hw, u8 **mc_addr_ptr, + u32 *vmdq); + +/* Function pointer table */ +struct ixgbe_eeprom_operations { + s32 (*init_params)(struct ixgbe_hw *); + s32 (*read)(struct ixgbe_hw *, u16, u16 *); + s32 (*read_buffer)(struct ixgbe_hw *, u16, u16, u16 *); + s32 (*write)(struct ixgbe_hw *, u16, u16); + s32 (*write_buffer)(struct ixgbe_hw *, u16, u16, u16 *); + s32 (*validate_checksum)(struct ixgbe_hw *, u16 *); + s32 (*update_checksum)(struct ixgbe_hw *); + s32 (*calc_checksum)(struct ixgbe_hw *); +}; + +struct ixgbe_mac_operations { + s32 (*init_hw)(struct ixgbe_hw *); + s32 (*reset_hw)(struct ixgbe_hw *); + s32 (*start_hw)(struct ixgbe_hw *); + s32 (*clear_hw_cntrs)(struct ixgbe_hw *); + enum ixgbe_media_type (*get_media_type)(struct ixgbe_hw *); + s32 (*get_mac_addr)(struct ixgbe_hw *, u8 *); + s32 (*get_san_mac_addr)(struct ixgbe_hw *, u8 *); + s32 (*get_device_caps)(struct ixgbe_hw *, u16 *); + s32 (*get_wwn_prefix)(struct ixgbe_hw *, u16 *, u16 *); + s32 (*stop_adapter)(struct ixgbe_hw *); + s32 (*get_bus_info)(struct ixgbe_hw *); + void (*set_lan_id)(struct ixgbe_hw *); + s32 (*read_analog_reg8)(struct ixgbe_hw*, u32, u8*); + s32 (*write_analog_reg8)(struct ixgbe_hw*, u32, u8); + s32 (*setup_sfp)(struct ixgbe_hw *); + s32 (*disable_rx_buff)(struct ixgbe_hw *); + s32 (*enable_rx_buff)(struct ixgbe_hw *); + s32 (*enable_rx_dma)(struct ixgbe_hw *, u32); + s32 (*acquire_swfw_sync)(struct ixgbe_hw *, u32); + void (*release_swfw_sync)(struct ixgbe_hw *, u32); + void (*init_swfw_sync)(struct ixgbe_hw *); + s32 (*prot_autoc_read)(struct ixgbe_hw *, bool *, u32 *); + s32 (*prot_autoc_write)(struct ixgbe_hw *, u32, bool); + + /* Link */ + void (*disable_tx_laser)(struct ixgbe_hw *); + void (*enable_tx_laser)(struct ixgbe_hw *); + void (*flap_tx_laser)(struct ixgbe_hw *); + void (*stop_link_on_d3)(struct ixgbe_hw *); + s32 (*setup_link)(struct ixgbe_hw *, ixgbe_link_speed, bool); + s32 (*setup_mac_link)(struct ixgbe_hw *, ixgbe_link_speed, bool); + s32 (*check_link)(struct ixgbe_hw *, ixgbe_link_speed *, bool *, bool); + s32 (*get_link_capabilities)(struct ixgbe_hw *, ixgbe_link_speed *, + bool *); + void (*set_rate_select_speed)(struct ixgbe_hw *, ixgbe_link_speed); + + /* Packet Buffer Manipulation */ + void (*set_rxpba)(struct ixgbe_hw *, int, u32, int); + + /* LED */ + s32 (*led_on)(struct ixgbe_hw *, u32); + s32 (*led_off)(struct ixgbe_hw *, u32); + s32 (*blink_led_start)(struct ixgbe_hw *, u32); + s32 (*blink_led_stop)(struct ixgbe_hw *, u32); + s32 (*init_led_link_act)(struct ixgbe_hw *); + + /* RAR, Multicast, VLAN */ + s32 (*set_rar)(struct ixgbe_hw *, u32, u8 *, u32, u32); + s32 (*clear_rar)(struct ixgbe_hw *, u32); + s32 (*set_vmdq)(struct ixgbe_hw *, u32, u32); + s32 (*set_vmdq_san_mac)(struct ixgbe_hw *, u32); + s32 (*clear_vmdq)(struct ixgbe_hw *, u32, u32); + s32 (*init_rx_addrs)(struct ixgbe_hw *); + s32 (*update_mc_addr_list)(struct ixgbe_hw *, struct net_device *); + s32 (*enable_mc)(struct ixgbe_hw *); + s32 (*disable_mc)(struct ixgbe_hw *); + s32 (*clear_vfta)(struct ixgbe_hw *); + s32 (*set_vfta)(struct ixgbe_hw *, u32, u32, bool, bool); + s32 (*init_uta_tables)(struct ixgbe_hw *); + void (*set_mac_anti_spoofing)(struct ixgbe_hw *, bool, int); + void (*set_vlan_anti_spoofing)(struct ixgbe_hw *, bool, int); + + /* Flow Control */ + s32 (*fc_enable)(struct ixgbe_hw *); + s32 (*setup_fc)(struct ixgbe_hw *); + void (*fc_autoneg)(struct ixgbe_hw *); + + /* Manageability interface */ + s32 (*set_fw_drv_ver)(struct ixgbe_hw *, u8, u8, u8, u8, u16, + const char *); + s32 (*get_thermal_sensor_data)(struct ixgbe_hw *); + s32 (*init_thermal_sensor_thresh)(struct ixgbe_hw *hw); + bool (*fw_recovery_mode)(struct ixgbe_hw *hw); + void (*disable_rx)(struct ixgbe_hw *hw); + void (*enable_rx)(struct ixgbe_hw *hw); + void (*set_source_address_pruning)(struct ixgbe_hw *, bool, + unsigned int); + void (*set_ethertype_anti_spoofing)(struct ixgbe_hw *, bool, int); + + /* DMA Coalescing */ + s32 (*dmac_config)(struct ixgbe_hw *hw); + s32 (*dmac_update_tcs)(struct ixgbe_hw *hw); + s32 (*dmac_config_tcs)(struct ixgbe_hw *hw); + s32 (*read_iosf_sb_reg)(struct ixgbe_hw *, u32, u32, u32 *); + s32 (*write_iosf_sb_reg)(struct ixgbe_hw *, u32, u32, u32); +}; + +struct ixgbe_phy_operations { + s32 (*identify)(struct ixgbe_hw *); + s32 (*identify_sfp)(struct ixgbe_hw *); + s32 (*init)(struct ixgbe_hw *); + s32 (*reset)(struct ixgbe_hw *); + s32 (*read_reg)(struct ixgbe_hw *, u32, u32, u16 *); + s32 (*write_reg)(struct ixgbe_hw *, u32, u32, u16); + s32 (*read_reg_mdi)(struct ixgbe_hw *, u32, u32, u16 *); + s32 (*write_reg_mdi)(struct ixgbe_hw *, u32, u32, u16); + s32 (*setup_link)(struct ixgbe_hw *); + s32 (*setup_internal_link)(struct ixgbe_hw *); + s32 (*setup_link_speed)(struct ixgbe_hw *, ixgbe_link_speed, bool); + s32 (*check_link)(struct ixgbe_hw *, ixgbe_link_speed *, bool *); + s32 (*read_i2c_byte)(struct ixgbe_hw *, u8, u8, u8 *); + s32 (*write_i2c_byte)(struct ixgbe_hw *, u8, u8, u8); + s32 (*read_i2c_sff8472)(struct ixgbe_hw *, u8 , u8 *); + s32 (*read_i2c_eeprom)(struct ixgbe_hw *, u8 , u8 *); + s32 (*write_i2c_eeprom)(struct ixgbe_hw *, u8, u8); + s32 (*check_overtemp)(struct ixgbe_hw *); + s32 (*set_phy_power)(struct ixgbe_hw *, bool on); + s32 (*enter_lplu)(struct ixgbe_hw *); + s32 (*handle_lasi)(struct ixgbe_hw *hw); + s32 (*read_i2c_byte_unlocked)(struct ixgbe_hw *, u8 offset, u8 addr, + u8 *value); + s32 (*write_i2c_byte_unlocked)(struct ixgbe_hw *, u8 offset, u8 addr, + u8 value); +}; + +struct ixgbe_link_operations { + s32 (*read_link)(struct ixgbe_hw *, u8 addr, u16 reg, u16 *val); + s32 (*read_link_unlocked)(struct ixgbe_hw *, u8 addr, u16 reg, + u16 *val); + s32 (*write_link)(struct ixgbe_hw *, u8 addr, u16 reg, u16 val); + s32 (*write_link_unlocked)(struct ixgbe_hw *, u8 addr, u16 reg, + u16 val); +}; + +struct ixgbe_link_info { + struct ixgbe_link_operations ops; + u8 addr; +}; + +struct ixgbe_eeprom_info { + struct ixgbe_eeprom_operations ops; + enum ixgbe_eeprom_type type; + u32 semaphore_delay; + u16 word_size; + u16 address_bits; + u16 word_page_size; + u16 ctrl_word_3; +}; + +#define IXGBE_FLAGS_DOUBLE_RESET_REQUIRED 0x01 +struct ixgbe_mac_info { + struct ixgbe_mac_operations ops; + enum ixgbe_mac_type type; + u8 addr[ETH_ALEN]; + u8 perm_addr[ETH_ALEN]; + u8 san_addr[ETH_ALEN]; + /* prefix for World Wide Node Name (WWNN) */ + u16 wwnn_prefix; + /* prefix for World Wide Port Name (WWPN) */ + u16 wwpn_prefix; + u16 max_msix_vectors; +#define IXGBE_MAX_MTA 128 + u32 mta_shadow[IXGBE_MAX_MTA]; + s32 mc_filter_type; + u32 mcft_size; + u32 vft_size; + u32 num_rar_entries; + u32 rar_highwater; + u32 rx_pb_size; + u32 max_tx_queues; + u32 max_rx_queues; + u32 orig_autoc; + u32 orig_autoc2; + bool orig_link_settings_stored; + bool autotry_restart; + u8 flags; + u8 san_mac_rar_index; + struct ixgbe_thermal_sensor_data thermal_sensor_data; + bool set_lben; + u8 led_link_act; +}; + +struct ixgbe_phy_info { + struct ixgbe_phy_operations ops; + struct mdio_if_info mdio; + enum ixgbe_phy_type type; + u32 id; + enum ixgbe_sfp_type sfp_type; + bool sfp_setup_needed; + u32 revision; + enum ixgbe_media_type media_type; + u32 phy_semaphore_mask; + bool reset_disable; + ixgbe_autoneg_advertised autoneg_advertised; + ixgbe_link_speed speeds_supported; + ixgbe_link_speed eee_speeds_supported; + ixgbe_link_speed eee_speeds_advertised; + enum ixgbe_smart_speed smart_speed; + bool smart_speed_active; + bool multispeed_fiber; + bool reset_if_overtemp; + bool qsfp_shared_i2c_bus; + u32 nw_mng_if_sel; +}; + +#include "ixgbe_mbx.h" + +struct ixgbe_mbx_operations { + s32 (*init_params)(struct ixgbe_hw *hw); + s32 (*read)(struct ixgbe_hw *, u32 *, u16, u16); + s32 (*write)(struct ixgbe_hw *, u32 *, u16, u16); + s32 (*read_posted)(struct ixgbe_hw *, u32 *, u16, u16); + s32 (*write_posted)(struct ixgbe_hw *, u32 *, u16, u16); + s32 (*check_for_msg)(struct ixgbe_hw *, u16); + s32 (*check_for_ack)(struct ixgbe_hw *, u16); + s32 (*check_for_rst)(struct ixgbe_hw *, u16); +}; + +struct ixgbe_mbx_stats { + u32 msgs_tx; + u32 msgs_rx; + + u32 acks; + u32 reqs; + u32 rsts; +}; + +struct ixgbe_mbx_info { + const struct ixgbe_mbx_operations *ops; + struct ixgbe_mbx_stats stats; + u32 timeout; + u32 usec_delay; + u32 v2p_mailbox; + u16 size; +}; + +struct ixgbe_hw { + u8 __iomem *hw_addr; + void *back; + struct ixgbe_mac_info mac; + struct ixgbe_addr_filter_info addr_ctrl; + struct ixgbe_fc_info fc; + struct ixgbe_phy_info phy; + struct ixgbe_link_info link; + struct ixgbe_eeprom_info eeprom; + struct ixgbe_bus_info bus; + struct ixgbe_mbx_info mbx; + const u32 *mvals; + u16 device_id; + u16 vendor_id; + u16 subsystem_device_id; + u16 subsystem_vendor_id; + u8 revision_id; + bool adapter_stopped; + bool force_full_reset; + bool allow_unsupported_sfp; + bool wol_enabled; + bool need_crosstalk_fix; +}; + +struct ixgbe_info { + enum ixgbe_mac_type mac; + s32 (*get_invariants)(struct ixgbe_hw *); + const struct ixgbe_mac_operations *mac_ops; + const struct ixgbe_eeprom_operations *eeprom_ops; + const struct ixgbe_phy_operations *phy_ops; + const struct ixgbe_mbx_operations *mbx_ops; + const struct ixgbe_link_operations *link_ops; + const u32 *mvals; +}; + + +/* Error Codes */ +#define IXGBE_ERR_EEPROM -1 +#define IXGBE_ERR_EEPROM_CHECKSUM -2 +#define IXGBE_ERR_PHY -3 +#define IXGBE_ERR_CONFIG -4 +#define IXGBE_ERR_PARAM -5 +#define IXGBE_ERR_MAC_TYPE -6 +#define IXGBE_ERR_UNKNOWN_PHY -7 +#define IXGBE_ERR_LINK_SETUP -8 +#define IXGBE_ERR_ADAPTER_STOPPED -9 +#define IXGBE_ERR_INVALID_MAC_ADDR -10 +#define IXGBE_ERR_DEVICE_NOT_SUPPORTED -11 +#define IXGBE_ERR_MASTER_REQUESTS_PENDING -12 +#define IXGBE_ERR_INVALID_LINK_SETTINGS -13 +#define IXGBE_ERR_AUTONEG_NOT_COMPLETE -14 +#define IXGBE_ERR_RESET_FAILED -15 +#define IXGBE_ERR_SWFW_SYNC -16 +#define IXGBE_ERR_PHY_ADDR_INVALID -17 +#define IXGBE_ERR_I2C -18 +#define IXGBE_ERR_SFP_NOT_SUPPORTED -19 +#define IXGBE_ERR_SFP_NOT_PRESENT -20 +#define IXGBE_ERR_SFP_NO_INIT_SEQ_PRESENT -21 +#define IXGBE_ERR_NO_SAN_ADDR_PTR -22 +#define IXGBE_ERR_FDIR_REINIT_FAILED -23 +#define IXGBE_ERR_EEPROM_VERSION -24 +#define IXGBE_ERR_NO_SPACE -25 +#define IXGBE_ERR_OVERTEMP -26 +#define IXGBE_ERR_FC_NOT_NEGOTIATED -27 +#define IXGBE_ERR_FC_NOT_SUPPORTED -28 +#define IXGBE_ERR_SFP_SETUP_NOT_COMPLETE -30 +#define IXGBE_ERR_PBA_SECTION -31 +#define IXGBE_ERR_INVALID_ARGUMENT -32 +#define IXGBE_ERR_HOST_INTERFACE_COMMAND -33 +#define IXGBE_ERR_FDIR_CMD_INCOMPLETE -38 +#define IXGBE_ERR_FW_RESP_INVALID -39 +#define IXGBE_ERR_TOKEN_RETRY -40 +#define IXGBE_NOT_IMPLEMENTED 0x7FFFFFFF + +#define IXGBE_FUSES0_GROUP(_i) (0x11158 + ((_i) * 4)) +#define IXGBE_FUSES0_300MHZ BIT(5) +#define IXGBE_FUSES0_REV_MASK (3u << 6) + +#define IXGBE_KRM_PORT_CAR_GEN_CTRL(P) ((P) ? 0x8010 : 0x4010) +#define IXGBE_KRM_LINK_S1(P) ((P) ? 0x8200 : 0x4200) +#define IXGBE_KRM_LINK_CTRL_1(P) ((P) ? 0x820C : 0x420C) +#define IXGBE_KRM_AN_CNTL_1(P) ((P) ? 0x822C : 0x422C) +#define IXGBE_KRM_AN_CNTL_8(P) ((P) ? 0x8248 : 0x4248) +#define IXGBE_KRM_SGMII_CTRL(P) ((P) ? 0x82A0 : 0x42A0) +#define IXGBE_KRM_LP_BASE_PAGE_HIGH(P) ((P) ? 0x836C : 0x436C) +#define IXGBE_KRM_DSP_TXFFE_STATE_4(P) ((P) ? 0x8634 : 0x4634) +#define IXGBE_KRM_DSP_TXFFE_STATE_5(P) ((P) ? 0x8638 : 0x4638) +#define IXGBE_KRM_RX_TRN_LINKUP_CTRL(P) ((P) ? 0x8B00 : 0x4B00) +#define IXGBE_KRM_PMD_DFX_BURNIN(P) ((P) ? 0x8E00 : 0x4E00) +#define IXGBE_KRM_PMD_FLX_MASK_ST20(P) ((P) ? 0x9054 : 0x5054) +#define IXGBE_KRM_TX_COEFF_CTRL_1(P) ((P) ? 0x9520 : 0x5520) +#define IXGBE_KRM_RX_ANA_CTL(P) ((P) ? 0x9A00 : 0x5A00) + +#define IXGBE_KRM_PMD_FLX_MASK_ST20_SFI_10G_DA ~(0x3 << 20) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_SFI_10G_SR BIT(20) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_SFI_10G_LR (0x2 << 20) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_SGMII_EN BIT(25) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_AN37_EN BIT(26) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_AN_EN BIT(27) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_10M ~(0x7 << 28) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_100M BIT(28) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_1G (0x2 << 28) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_10G (0x3 << 28) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_AN (0x4 << 28) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_2_5G (0x7 << 28) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_MASK (0x7 << 28) +#define IXGBE_KRM_PMD_FLX_MASK_ST20_FW_AN_RESTART BIT(31) + +#define IXGBE_KRM_PORT_CAR_GEN_CTRL_NELB_32B BIT(9) +#define IXGBE_KRM_PORT_CAR_GEN_CTRL_NELB_KRPCS BIT(11) + +#define IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_MASK (7u << 8) +#define IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_1G (2u << 8) +#define IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_10G (4u << 8) +#define IXGBE_KRM_LINK_CTRL_1_TETH_AN_SGMII_EN BIT(12) +#define IXGBE_KRM_LINK_CTRL_1_TETH_AN_CLAUSE_37_EN BIT(13) +#define IXGBE_KRM_LINK_CTRL_1_TETH_AN_FEC_REQ BIT(14) +#define IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_FEC BIT(15) +#define IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_KX BIT(16) +#define IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_KR BIT(18) +#define IXGBE_KRM_LINK_CTRL_1_TETH_EEE_CAP_KX BIT(24) +#define IXGBE_KRM_LINK_CTRL_1_TETH_EEE_CAP_KR BIT(26) +#define IXGBE_KRM_LINK_S1_MAC_AN_COMPLETE BIT(28) +#define IXGBE_KRM_LINK_CTRL_1_TETH_AN_ENABLE BIT(29) +#define IXGBE_KRM_LINK_CTRL_1_TETH_AN_RESTART BIT(31) + +#define IXGBE_KRM_AN_CNTL_1_SYM_PAUSE BIT(28) +#define IXGBE_KRM_AN_CNTL_1_ASM_PAUSE BIT(29) + +#define IXGBE_KRM_AN_CNTL_8_LINEAR BIT(0) +#define IXGBE_KRM_AN_CNTL_8_LIMITING BIT(1) + +#define IXGBE_KRM_LP_BASE_PAGE_HIGH_SYM_PAUSE BIT(10) +#define IXGBE_KRM_LP_BASE_PAGE_HIGH_ASM_PAUSE BIT(11) +#define IXGBE_KRM_SGMII_CTRL_MAC_TAR_FORCE_100_D BIT(12) +#define IXGBE_KRM_SGMII_CTRL_MAC_TAR_FORCE_10_D BIT(19) + +#define IXGBE_KRM_DSP_TXFFE_STATE_C0_EN BIT(6) +#define IXGBE_KRM_DSP_TXFFE_STATE_CP1_CN1_EN BIT(15) +#define IXGBE_KRM_DSP_TXFFE_STATE_CO_ADAPT_EN BIT(16) + +#define IXGBE_KRM_RX_TRN_LINKUP_CTRL_CONV_WO_PROTOCOL BIT(4) +#define IXGBE_KRM_RX_TRN_LINKUP_CTRL_PROTOCOL_BYPASS BIT(2) + +#define IXGBE_KRM_PMD_DFX_BURNIN_TX_RX_KR_LB_MASK (3u << 16) + +#define IXGBE_KRM_TX_COEFF_CTRL_1_CMINUS1_OVRRD_EN BIT(1) +#define IXGBE_KRM_TX_COEFF_CTRL_1_CPLUS1_OVRRD_EN BIT(2) +#define IXGBE_KRM_TX_COEFF_CTRL_1_CZERO_EN BIT(3) +#define IXGBE_KRM_TX_COEFF_CTRL_1_OVRRD_EN BIT(31) + +#define IXGBE_SB_IOSF_INDIRECT_CTRL 0x00011144 +#define IXGBE_SB_IOSF_INDIRECT_DATA 0x00011148 + +#define IXGBE_SB_IOSF_CTRL_ADDR_SHIFT 0 +#define IXGBE_SB_IOSF_CTRL_ADDR_MASK 0xFF +#define IXGBE_SB_IOSF_CTRL_RESP_STAT_SHIFT 18 +#define IXGBE_SB_IOSF_CTRL_RESP_STAT_MASK \ + (0x3 << IXGBE_SB_IOSF_CTRL_RESP_STAT_SHIFT) +#define IXGBE_SB_IOSF_CTRL_CMPL_ERR_SHIFT 20 +#define IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK \ + (0xFF << IXGBE_SB_IOSF_CTRL_CMPL_ERR_SHIFT) +#define IXGBE_SB_IOSF_CTRL_TARGET_SELECT_SHIFT 28 +#define IXGBE_SB_IOSF_CTRL_TARGET_SELECT_MASK 0x7 +#define IXGBE_SB_IOSF_CTRL_BUSY_SHIFT 31 +#define IXGBE_SB_IOSF_CTRL_BUSY BIT(IXGBE_SB_IOSF_CTRL_BUSY_SHIFT) +#define IXGBE_SB_IOSF_TARGET_KR_PHY 0 + +#define IXGBE_NW_MNG_IF_SEL 0x00011178 +#define IXGBE_NW_MNG_IF_SEL_MDIO_ACT BIT(1) +#define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_10M BIT(17) +#define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_100M BIT(18) +#define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_1G BIT(19) +#define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_2_5G BIT(20) +#define IXGBE_NW_MNG_IF_SEL_PHY_SPEED_10G BIT(21) +#define IXGBE_NW_MNG_IF_SEL_SGMII_ENABLE BIT(25) +#define IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE BIT(24) /* X552 only */ +#define IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD_SHIFT 3 +#define IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD \ + (0x1F << IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD_SHIFT) +#endif /* _IXGBE_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c new file mode 100644 index 000000000..4b93ba149 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c @@ -0,0 +1,922 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#include <linux/pci.h> +#include <linux/delay.h> +#include <linux/sched.h> + +#include "ixgbe.h" +#include "ixgbe_phy.h" +#include "ixgbe_x540.h" + +#define IXGBE_X540_MAX_TX_QUEUES 128 +#define IXGBE_X540_MAX_RX_QUEUES 128 +#define IXGBE_X540_RAR_ENTRIES 128 +#define IXGBE_X540_MC_TBL_SIZE 128 +#define IXGBE_X540_VFT_TBL_SIZE 128 +#define IXGBE_X540_RX_PB_SIZE 384 + +static s32 ixgbe_update_flash_X540(struct ixgbe_hw *hw); +static s32 ixgbe_poll_flash_update_done_X540(struct ixgbe_hw *hw); +static s32 ixgbe_get_swfw_sync_semaphore(struct ixgbe_hw *hw); +static void ixgbe_release_swfw_sync_semaphore(struct ixgbe_hw *hw); + +enum ixgbe_media_type ixgbe_get_media_type_X540(struct ixgbe_hw *hw) +{ + return ixgbe_media_type_copper; +} + +s32 ixgbe_get_invariants_X540(struct ixgbe_hw *hw) +{ + struct ixgbe_mac_info *mac = &hw->mac; + struct ixgbe_phy_info *phy = &hw->phy; + + /* set_phy_power was set by default to NULL */ + phy->ops.set_phy_power = ixgbe_set_copper_phy_power; + + mac->mcft_size = IXGBE_X540_MC_TBL_SIZE; + mac->vft_size = IXGBE_X540_VFT_TBL_SIZE; + mac->num_rar_entries = IXGBE_X540_RAR_ENTRIES; + mac->rx_pb_size = IXGBE_X540_RX_PB_SIZE; + mac->max_rx_queues = IXGBE_X540_MAX_RX_QUEUES; + mac->max_tx_queues = IXGBE_X540_MAX_TX_QUEUES; + mac->max_msix_vectors = ixgbe_get_pcie_msix_count_generic(hw); + + return 0; +} + +/** + * ixgbe_setup_mac_link_X540 - Set the auto advertised capabilitires + * @hw: pointer to hardware structure + * @speed: new link speed + * @autoneg_wait_to_complete: true when waiting for completion is needed + **/ +s32 ixgbe_setup_mac_link_X540(struct ixgbe_hw *hw, ixgbe_link_speed speed, + bool autoneg_wait_to_complete) +{ + return hw->phy.ops.setup_link_speed(hw, speed, + autoneg_wait_to_complete); +} + +/** + * ixgbe_reset_hw_X540 - Perform hardware reset + * @hw: pointer to hardware structure + * + * Resets the hardware by resetting the transmit and receive units, masks + * and clears all interrupts, perform a PHY reset, and perform a link (MAC) + * reset. + **/ +s32 ixgbe_reset_hw_X540(struct ixgbe_hw *hw) +{ + s32 status; + u32 ctrl, i; + u32 swfw_mask = hw->phy.phy_semaphore_mask; + + /* Call adapter stop to disable tx/rx and clear interrupts */ + status = hw->mac.ops.stop_adapter(hw); + if (status) + return status; + + /* flush pending Tx transactions */ + ixgbe_clear_tx_pending(hw); + +mac_reset_top: + status = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask); + if (status) { + hw_dbg(hw, "semaphore failed with %d", status); + return IXGBE_ERR_SWFW_SYNC; + } + + ctrl = IXGBE_CTRL_RST; + ctrl |= IXGBE_READ_REG(hw, IXGBE_CTRL); + IXGBE_WRITE_REG(hw, IXGBE_CTRL, ctrl); + IXGBE_WRITE_FLUSH(hw); + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + usleep_range(1000, 1200); + + /* Poll for reset bit to self-clear indicating reset is complete */ + for (i = 0; i < 10; i++) { + ctrl = IXGBE_READ_REG(hw, IXGBE_CTRL); + if (!(ctrl & IXGBE_CTRL_RST_MASK)) + break; + udelay(1); + } + + if (ctrl & IXGBE_CTRL_RST_MASK) { + status = IXGBE_ERR_RESET_FAILED; + hw_dbg(hw, "Reset polling failed to complete.\n"); + } + msleep(100); + + /* + * Double resets are required for recovery from certain error + * conditions. Between resets, it is necessary to stall to allow time + * for any pending HW events to complete. + */ + if (hw->mac.flags & IXGBE_FLAGS_DOUBLE_RESET_REQUIRED) { + hw->mac.flags &= ~IXGBE_FLAGS_DOUBLE_RESET_REQUIRED; + goto mac_reset_top; + } + + /* Set the Rx packet buffer size. */ + IXGBE_WRITE_REG(hw, IXGBE_RXPBSIZE(0), 384 << IXGBE_RXPBSIZE_SHIFT); + + /* Store the permanent mac address */ + hw->mac.ops.get_mac_addr(hw, hw->mac.perm_addr); + + /* + * Store MAC address from RAR0, clear receive address registers, and + * clear the multicast table. Also reset num_rar_entries to 128, + * since we modify this value when programming the SAN MAC address. + */ + hw->mac.num_rar_entries = IXGBE_X540_MAX_TX_QUEUES; + hw->mac.ops.init_rx_addrs(hw); + + /* Store the permanent SAN mac address */ + hw->mac.ops.get_san_mac_addr(hw, hw->mac.san_addr); + + /* Add the SAN MAC address to the RAR only if it's a valid address */ + if (is_valid_ether_addr(hw->mac.san_addr)) { + /* Save the SAN MAC RAR index */ + hw->mac.san_mac_rar_index = hw->mac.num_rar_entries - 1; + + hw->mac.ops.set_rar(hw, hw->mac.san_mac_rar_index, + hw->mac.san_addr, 0, IXGBE_RAH_AV); + + /* clear VMDq pool/queue selection for this RAR */ + hw->mac.ops.clear_vmdq(hw, hw->mac.san_mac_rar_index, + IXGBE_CLEAR_VMDQ_ALL); + + /* Reserve the last RAR for the SAN MAC address */ + hw->mac.num_rar_entries--; + } + + /* Store the alternative WWNN/WWPN prefix */ + hw->mac.ops.get_wwn_prefix(hw, &hw->mac.wwnn_prefix, + &hw->mac.wwpn_prefix); + + return status; +} + +/** + * ixgbe_start_hw_X540 - Prepare hardware for Tx/Rx + * @hw: pointer to hardware structure + * + * Starts the hardware using the generic start_hw function + * and the generation start_hw function. + * Then performs revision-specific operations, if any. + **/ +s32 ixgbe_start_hw_X540(struct ixgbe_hw *hw) +{ + s32 ret_val; + + ret_val = ixgbe_start_hw_generic(hw); + if (ret_val) + return ret_val; + + return ixgbe_start_hw_gen2(hw); +} + +/** + * ixgbe_init_eeprom_params_X540 - Initialize EEPROM params + * @hw: pointer to hardware structure + * + * Initializes the EEPROM parameters ixgbe_eeprom_info within the + * ixgbe_hw struct in order to set up EEPROM access. + **/ +s32 ixgbe_init_eeprom_params_X540(struct ixgbe_hw *hw) +{ + struct ixgbe_eeprom_info *eeprom = &hw->eeprom; + u32 eec; + u16 eeprom_size; + + if (eeprom->type == ixgbe_eeprom_uninitialized) { + eeprom->semaphore_delay = 10; + eeprom->type = ixgbe_flash; + + eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw)); + eeprom_size = (u16)((eec & IXGBE_EEC_SIZE) >> + IXGBE_EEC_SIZE_SHIFT); + eeprom->word_size = BIT(eeprom_size + + IXGBE_EEPROM_WORD_SIZE_SHIFT); + + hw_dbg(hw, "Eeprom params: type = %d, size = %d\n", + eeprom->type, eeprom->word_size); + } + + return 0; +} + +/** + * ixgbe_read_eerd_X540- Read EEPROM word using EERD + * @hw: pointer to hardware structure + * @offset: offset of word in the EEPROM to read + * @data: word read from the EEPROM + * + * Reads a 16 bit word from the EEPROM using the EERD register. + **/ +static s32 ixgbe_read_eerd_X540(struct ixgbe_hw *hw, u16 offset, u16 *data) +{ + s32 status; + + if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) + return IXGBE_ERR_SWFW_SYNC; + + status = ixgbe_read_eerd_generic(hw, offset, data); + + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM); + return status; +} + +/** + * ixgbe_read_eerd_buffer_X540 - Read EEPROM word(s) using EERD + * @hw: pointer to hardware structure + * @offset: offset of word in the EEPROM to read + * @words: number of words + * @data: word(s) read from the EEPROM + * + * Reads a 16 bit word(s) from the EEPROM using the EERD register. + **/ +static s32 ixgbe_read_eerd_buffer_X540(struct ixgbe_hw *hw, + u16 offset, u16 words, u16 *data) +{ + s32 status; + + if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) + return IXGBE_ERR_SWFW_SYNC; + + status = ixgbe_read_eerd_buffer_generic(hw, offset, words, data); + + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM); + return status; +} + +/** + * ixgbe_write_eewr_X540 - Write EEPROM word using EEWR + * @hw: pointer to hardware structure + * @offset: offset of word in the EEPROM to write + * @data: word write to the EEPROM + * + * Write a 16 bit word to the EEPROM using the EEWR register. + **/ +static s32 ixgbe_write_eewr_X540(struct ixgbe_hw *hw, u16 offset, u16 data) +{ + s32 status; + + if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) + return IXGBE_ERR_SWFW_SYNC; + + status = ixgbe_write_eewr_generic(hw, offset, data); + + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM); + return status; +} + +/** + * ixgbe_write_eewr_buffer_X540 - Write EEPROM word(s) using EEWR + * @hw: pointer to hardware structure + * @offset: offset of word in the EEPROM to write + * @words: number of words + * @data: word(s) write to the EEPROM + * + * Write a 16 bit word(s) to the EEPROM using the EEWR register. + **/ +static s32 ixgbe_write_eewr_buffer_X540(struct ixgbe_hw *hw, + u16 offset, u16 words, u16 *data) +{ + s32 status; + + if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) + return IXGBE_ERR_SWFW_SYNC; + + status = ixgbe_write_eewr_buffer_generic(hw, offset, words, data); + + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM); + return status; +} + +/** + * ixgbe_calc_eeprom_checksum_X540 - Calculates and returns the checksum + * + * This function does not use synchronization for EERD and EEWR. It can + * be used internally by function which utilize ixgbe_acquire_swfw_sync_X540. + * + * @hw: pointer to hardware structure + **/ +static s32 ixgbe_calc_eeprom_checksum_X540(struct ixgbe_hw *hw) +{ + u16 i; + u16 j; + u16 checksum = 0; + u16 length = 0; + u16 pointer = 0; + u16 word = 0; + u16 checksum_last_word = IXGBE_EEPROM_CHECKSUM; + u16 ptr_start = IXGBE_PCIE_ANALOG_PTR; + + /* + * Do not use hw->eeprom.ops.read because we do not want to take + * the synchronization semaphores here. Instead use + * ixgbe_read_eerd_generic + */ + + /* Include 0x0-0x3F in the checksum */ + for (i = 0; i < checksum_last_word; i++) { + if (ixgbe_read_eerd_generic(hw, i, &word)) { + hw_dbg(hw, "EEPROM read failed\n"); + return IXGBE_ERR_EEPROM; + } + checksum += word; + } + + /* + * Include all data from pointers 0x3, 0x6-0xE. This excludes the + * FW, PHY module, and PCIe Expansion/Option ROM pointers. + */ + for (i = ptr_start; i < IXGBE_FW_PTR; i++) { + if (i == IXGBE_PHY_PTR || i == IXGBE_OPTION_ROM_PTR) + continue; + + if (ixgbe_read_eerd_generic(hw, i, &pointer)) { + hw_dbg(hw, "EEPROM read failed\n"); + break; + } + + /* Skip pointer section if the pointer is invalid. */ + if (pointer == 0xFFFF || pointer == 0 || + pointer >= hw->eeprom.word_size) + continue; + + if (ixgbe_read_eerd_generic(hw, pointer, &length)) { + hw_dbg(hw, "EEPROM read failed\n"); + return IXGBE_ERR_EEPROM; + } + + /* Skip pointer section if length is invalid. */ + if (length == 0xFFFF || length == 0 || + (pointer + length) >= hw->eeprom.word_size) + continue; + + for (j = pointer + 1; j <= pointer + length; j++) { + if (ixgbe_read_eerd_generic(hw, j, &word)) { + hw_dbg(hw, "EEPROM read failed\n"); + return IXGBE_ERR_EEPROM; + } + checksum += word; + } + } + + checksum = (u16)IXGBE_EEPROM_SUM - checksum; + + return (s32)checksum; +} + +/** + * ixgbe_validate_eeprom_checksum_X540 - Validate EEPROM checksum + * @hw: pointer to hardware structure + * @checksum_val: calculated checksum + * + * Performs checksum calculation and validates the EEPROM checksum. If the + * caller does not need checksum_val, the value can be NULL. + **/ +static s32 ixgbe_validate_eeprom_checksum_X540(struct ixgbe_hw *hw, + u16 *checksum_val) +{ + s32 status; + u16 checksum; + u16 read_checksum = 0; + + /* Read the first word from the EEPROM. If this times out or fails, do + * not continue or we could be in for a very long wait while every + * EEPROM read fails + */ + status = hw->eeprom.ops.read(hw, 0, &checksum); + if (status) { + hw_dbg(hw, "EEPROM read failed\n"); + return status; + } + + if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) + return IXGBE_ERR_SWFW_SYNC; + + status = hw->eeprom.ops.calc_checksum(hw); + if (status < 0) + goto out; + + checksum = (u16)(status & 0xffff); + + /* Do not use hw->eeprom.ops.read because we do not want to take + * the synchronization semaphores twice here. + */ + status = ixgbe_read_eerd_generic(hw, IXGBE_EEPROM_CHECKSUM, + &read_checksum); + if (status) + goto out; + + /* Verify read checksum from EEPROM is the same as + * calculated checksum + */ + if (read_checksum != checksum) { + hw_dbg(hw, "Invalid EEPROM checksum"); + status = IXGBE_ERR_EEPROM_CHECKSUM; + } + + /* If the user cares, return the calculated checksum */ + if (checksum_val) + *checksum_val = checksum; + +out: + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM); + + return status; +} + +/** + * ixgbe_update_eeprom_checksum_X540 - Updates the EEPROM checksum and flash + * @hw: pointer to hardware structure + * + * After writing EEPROM to shadow RAM using EEWR register, software calculates + * checksum and updates the EEPROM and instructs the hardware to update + * the flash. + **/ +static s32 ixgbe_update_eeprom_checksum_X540(struct ixgbe_hw *hw) +{ + s32 status; + u16 checksum; + + /* Read the first word from the EEPROM. If this times out or fails, do + * not continue or we could be in for a very long wait while every + * EEPROM read fails + */ + status = hw->eeprom.ops.read(hw, 0, &checksum); + if (status) { + hw_dbg(hw, "EEPROM read failed\n"); + return status; + } + + if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM)) + return IXGBE_ERR_SWFW_SYNC; + + status = hw->eeprom.ops.calc_checksum(hw); + if (status < 0) + goto out; + + checksum = (u16)(status & 0xffff); + + /* Do not use hw->eeprom.ops.write because we do not want to + * take the synchronization semaphores twice here. + */ + status = ixgbe_write_eewr_generic(hw, IXGBE_EEPROM_CHECKSUM, checksum); + if (status) + goto out; + + status = ixgbe_update_flash_X540(hw); + +out: + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM); + return status; +} + +/** + * ixgbe_update_flash_X540 - Instruct HW to copy EEPROM to Flash device + * @hw: pointer to hardware structure + * + * Set FLUP (bit 23) of the EEC register to instruct Hardware to copy + * EEPROM from shadow RAM to the flash device. + **/ +static s32 ixgbe_update_flash_X540(struct ixgbe_hw *hw) +{ + u32 flup; + s32 status; + + status = ixgbe_poll_flash_update_done_X540(hw); + if (status == IXGBE_ERR_EEPROM) { + hw_dbg(hw, "Flash update time out\n"); + return status; + } + + flup = IXGBE_READ_REG(hw, IXGBE_EEC(hw)) | IXGBE_EEC_FLUP; + IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), flup); + + status = ixgbe_poll_flash_update_done_X540(hw); + if (status == 0) + hw_dbg(hw, "Flash update complete\n"); + else + hw_dbg(hw, "Flash update time out\n"); + + if (hw->revision_id == 0) { + flup = IXGBE_READ_REG(hw, IXGBE_EEC(hw)); + + if (flup & IXGBE_EEC_SEC1VAL) { + flup |= IXGBE_EEC_FLUP; + IXGBE_WRITE_REG(hw, IXGBE_EEC(hw), flup); + } + + status = ixgbe_poll_flash_update_done_X540(hw); + if (status == 0) + hw_dbg(hw, "Flash update complete\n"); + else + hw_dbg(hw, "Flash update time out\n"); + } + + return status; +} + +/** + * ixgbe_poll_flash_update_done_X540 - Poll flash update status + * @hw: pointer to hardware structure + * + * Polls the FLUDONE (bit 26) of the EEC Register to determine when the + * flash update is done. + **/ +static s32 ixgbe_poll_flash_update_done_X540(struct ixgbe_hw *hw) +{ + u32 i; + u32 reg; + + for (i = 0; i < IXGBE_FLUDONE_ATTEMPTS; i++) { + reg = IXGBE_READ_REG(hw, IXGBE_EEC(hw)); + if (reg & IXGBE_EEC_FLUDONE) + return 0; + udelay(5); + } + return IXGBE_ERR_EEPROM; +} + +/** + * ixgbe_acquire_swfw_sync_X540 - Acquire SWFW semaphore + * @hw: pointer to hardware structure + * @mask: Mask to specify which semaphore to acquire + * + * Acquires the SWFW semaphore thought the SW_FW_SYNC register for + * the specified function (CSR, PHY0, PHY1, NVM, Flash) + **/ +s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask) +{ + u32 swmask = mask & IXGBE_GSSR_NVM_PHY_MASK; + u32 swi2c_mask = mask & IXGBE_GSSR_I2C_MASK; + u32 fwmask = swmask << 5; + u32 timeout = 200; + u32 hwmask = 0; + u32 swfw_sync; + u32 i; + + if (swmask & IXGBE_GSSR_EEP_SM) + hwmask = IXGBE_GSSR_FLASH_SM; + + /* SW only mask does not have FW bit pair */ + if (mask & IXGBE_GSSR_SW_MNG_SM) + swmask |= IXGBE_GSSR_SW_MNG_SM; + + swmask |= swi2c_mask; + fwmask |= swi2c_mask << 2; + for (i = 0; i < timeout; i++) { + /* SW NVM semaphore bit is used for access to all + * SW_FW_SYNC bits (not just NVM) + */ + if (ixgbe_get_swfw_sync_semaphore(hw)) + return IXGBE_ERR_SWFW_SYNC; + + swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC(hw)); + if (!(swfw_sync & (fwmask | swmask | hwmask))) { + swfw_sync |= swmask; + IXGBE_WRITE_REG(hw, IXGBE_SWFW_SYNC(hw), swfw_sync); + ixgbe_release_swfw_sync_semaphore(hw); + usleep_range(5000, 6000); + return 0; + } + /* Firmware currently using resource (fwmask), hardware + * currently using resource (hwmask), or other software + * thread currently using resource (swmask) + */ + ixgbe_release_swfw_sync_semaphore(hw); + usleep_range(5000, 10000); + } + + /* If the resource is not released by the FW/HW the SW can assume that + * the FW/HW malfunctions. In that case the SW should set the SW bit(s) + * of the requested resource(s) while ignoring the corresponding FW/HW + * bits in the SW_FW_SYNC register. + */ + if (ixgbe_get_swfw_sync_semaphore(hw)) + return IXGBE_ERR_SWFW_SYNC; + swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC(hw)); + if (swfw_sync & (fwmask | hwmask)) { + swfw_sync |= swmask; + IXGBE_WRITE_REG(hw, IXGBE_SWFW_SYNC(hw), swfw_sync); + ixgbe_release_swfw_sync_semaphore(hw); + usleep_range(5000, 6000); + return 0; + } + /* If the resource is not released by other SW the SW can assume that + * the other SW malfunctions. In that case the SW should clear all SW + * flags that it does not own and then repeat the whole process once + * again. + */ + if (swfw_sync & swmask) { + u32 rmask = IXGBE_GSSR_EEP_SM | IXGBE_GSSR_PHY0_SM | + IXGBE_GSSR_PHY1_SM | IXGBE_GSSR_MAC_CSR_SM | + IXGBE_GSSR_SW_MNG_SM; + + if (swi2c_mask) + rmask |= IXGBE_GSSR_I2C_MASK; + ixgbe_release_swfw_sync_X540(hw, rmask); + ixgbe_release_swfw_sync_semaphore(hw); + return IXGBE_ERR_SWFW_SYNC; + } + ixgbe_release_swfw_sync_semaphore(hw); + + return IXGBE_ERR_SWFW_SYNC; +} + +/** + * ixgbe_release_swfw_sync_X540 - Release SWFW semaphore + * @hw: pointer to hardware structure + * @mask: Mask to specify which semaphore to release + * + * Releases the SWFW semaphore through the SW_FW_SYNC register + * for the specified function (CSR, PHY0, PHY1, EVM, Flash) + **/ +void ixgbe_release_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask) +{ + u32 swmask = mask & (IXGBE_GSSR_NVM_PHY_MASK | IXGBE_GSSR_SW_MNG_SM); + u32 swfw_sync; + + if (mask & IXGBE_GSSR_I2C_MASK) + swmask |= mask & IXGBE_GSSR_I2C_MASK; + ixgbe_get_swfw_sync_semaphore(hw); + + swfw_sync = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC(hw)); + swfw_sync &= ~swmask; + IXGBE_WRITE_REG(hw, IXGBE_SWFW_SYNC(hw), swfw_sync); + + ixgbe_release_swfw_sync_semaphore(hw); + usleep_range(5000, 6000); +} + +/** + * ixgbe_get_swfw_sync_semaphore - Get hardware semaphore + * @hw: pointer to hardware structure + * + * Sets the hardware semaphores so SW/FW can gain control of shared resources + */ +static s32 ixgbe_get_swfw_sync_semaphore(struct ixgbe_hw *hw) +{ + u32 timeout = 2000; + u32 i; + u32 swsm; + + /* Get SMBI software semaphore between device drivers first */ + for (i = 0; i < timeout; i++) { + /* If the SMBI bit is 0 when we read it, then the bit will be + * set and we have the semaphore + */ + swsm = IXGBE_READ_REG(hw, IXGBE_SWSM(hw)); + if (!(swsm & IXGBE_SWSM_SMBI)) + break; + usleep_range(50, 100); + } + + if (i == timeout) { + hw_dbg(hw, + "Software semaphore SMBI between device drivers not granted.\n"); + return IXGBE_ERR_EEPROM; + } + + /* Now get the semaphore between SW/FW through the REGSMP bit */ + for (i = 0; i < timeout; i++) { + swsm = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC(hw)); + if (!(swsm & IXGBE_SWFW_REGSMP)) + return 0; + + usleep_range(50, 100); + } + + /* Release semaphores and return error if SW NVM semaphore + * was not granted because we do not have access to the EEPROM + */ + hw_dbg(hw, "REGSMP Software NVM semaphore not granted\n"); + ixgbe_release_swfw_sync_semaphore(hw); + return IXGBE_ERR_EEPROM; +} + +/** + * ixgbe_release_nvm_semaphore - Release hardware semaphore + * @hw: pointer to hardware structure + * + * This function clears hardware semaphore bits. + **/ +static void ixgbe_release_swfw_sync_semaphore(struct ixgbe_hw *hw) +{ + u32 swsm; + + /* Release both semaphores by writing 0 to the bits REGSMP and SMBI */ + + swsm = IXGBE_READ_REG(hw, IXGBE_SWFW_SYNC(hw)); + swsm &= ~IXGBE_SWFW_REGSMP; + IXGBE_WRITE_REG(hw, IXGBE_SWFW_SYNC(hw), swsm); + + swsm = IXGBE_READ_REG(hw, IXGBE_SWSM(hw)); + swsm &= ~IXGBE_SWSM_SMBI; + IXGBE_WRITE_REG(hw, IXGBE_SWSM(hw), swsm); + + IXGBE_WRITE_FLUSH(hw); +} + +/** + * ixgbe_init_swfw_sync_X540 - Release hardware semaphore + * @hw: pointer to hardware structure + * + * This function reset hardware semaphore bits for a semaphore that may + * have be left locked due to a catastrophic failure. + **/ +void ixgbe_init_swfw_sync_X540(struct ixgbe_hw *hw) +{ + u32 rmask; + + /* First try to grab the semaphore but we don't need to bother + * looking to see whether we got the lock or not since we do + * the same thing regardless of whether we got the lock or not. + * We got the lock - we release it. + * We timeout trying to get the lock - we force its release. + */ + ixgbe_get_swfw_sync_semaphore(hw); + ixgbe_release_swfw_sync_semaphore(hw); + + /* Acquire and release all software resources. */ + rmask = IXGBE_GSSR_EEP_SM | IXGBE_GSSR_PHY0_SM | + IXGBE_GSSR_PHY1_SM | IXGBE_GSSR_MAC_CSR_SM | + IXGBE_GSSR_SW_MNG_SM | IXGBE_GSSR_I2C_MASK; + + ixgbe_acquire_swfw_sync_X540(hw, rmask); + ixgbe_release_swfw_sync_X540(hw, rmask); +} + +/** + * ixgbe_blink_led_start_X540 - Blink LED based on index. + * @hw: pointer to hardware structure + * @index: led number to blink + * + * Devices that implement the version 2 interface: + * X540 + **/ +s32 ixgbe_blink_led_start_X540(struct ixgbe_hw *hw, u32 index) +{ + u32 macc_reg; + u32 ledctl_reg; + ixgbe_link_speed speed; + bool link_up; + + if (index > 3) + return IXGBE_ERR_PARAM; + + /* Link should be up in order for the blink bit in the LED control + * register to work. Force link and speed in the MAC if link is down. + * This will be reversed when we stop the blinking. + */ + hw->mac.ops.check_link(hw, &speed, &link_up, false); + if (!link_up) { + macc_reg = IXGBE_READ_REG(hw, IXGBE_MACC); + macc_reg |= IXGBE_MACC_FLU | IXGBE_MACC_FSV_10G | IXGBE_MACC_FS; + IXGBE_WRITE_REG(hw, IXGBE_MACC, macc_reg); + } + /* Set the LED to LINK_UP + BLINK. */ + ledctl_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); + ledctl_reg &= ~IXGBE_LED_MODE_MASK(index); + ledctl_reg |= IXGBE_LED_BLINK(index); + IXGBE_WRITE_REG(hw, IXGBE_LEDCTL, ledctl_reg); + IXGBE_WRITE_FLUSH(hw); + + return 0; +} + +/** + * ixgbe_blink_led_stop_X540 - Stop blinking LED based on index. + * @hw: pointer to hardware structure + * @index: led number to stop blinking + * + * Devices that implement the version 2 interface: + * X540 + **/ +s32 ixgbe_blink_led_stop_X540(struct ixgbe_hw *hw, u32 index) +{ + u32 macc_reg; + u32 ledctl_reg; + + if (index > 3) + return IXGBE_ERR_PARAM; + + /* Restore the LED to its default value. */ + ledctl_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); + ledctl_reg &= ~IXGBE_LED_MODE_MASK(index); + ledctl_reg |= IXGBE_LED_LINK_ACTIVE << IXGBE_LED_MODE_SHIFT(index); + ledctl_reg &= ~IXGBE_LED_BLINK(index); + IXGBE_WRITE_REG(hw, IXGBE_LEDCTL, ledctl_reg); + + /* Unforce link and speed in the MAC. */ + macc_reg = IXGBE_READ_REG(hw, IXGBE_MACC); + macc_reg &= ~(IXGBE_MACC_FLU | IXGBE_MACC_FSV_10G | IXGBE_MACC_FS); + IXGBE_WRITE_REG(hw, IXGBE_MACC, macc_reg); + IXGBE_WRITE_FLUSH(hw); + + return 0; +} +static const struct ixgbe_mac_operations mac_ops_X540 = { + .init_hw = &ixgbe_init_hw_generic, + .reset_hw = &ixgbe_reset_hw_X540, + .start_hw = &ixgbe_start_hw_X540, + .clear_hw_cntrs = &ixgbe_clear_hw_cntrs_generic, + .get_media_type = &ixgbe_get_media_type_X540, + .enable_rx_dma = &ixgbe_enable_rx_dma_generic, + .get_mac_addr = &ixgbe_get_mac_addr_generic, + .get_san_mac_addr = &ixgbe_get_san_mac_addr_generic, + .get_device_caps = &ixgbe_get_device_caps_generic, + .get_wwn_prefix = &ixgbe_get_wwn_prefix_generic, + .stop_adapter = &ixgbe_stop_adapter_generic, + .get_bus_info = &ixgbe_get_bus_info_generic, + .set_lan_id = &ixgbe_set_lan_id_multi_port_pcie, + .read_analog_reg8 = NULL, + .write_analog_reg8 = NULL, + .setup_link = &ixgbe_setup_mac_link_X540, + .set_rxpba = &ixgbe_set_rxpba_generic, + .check_link = &ixgbe_check_mac_link_generic, + .get_link_capabilities = &ixgbe_get_copper_link_capabilities_generic, + .led_on = &ixgbe_led_on_generic, + .led_off = &ixgbe_led_off_generic, + .init_led_link_act = ixgbe_init_led_link_act_generic, + .blink_led_start = &ixgbe_blink_led_start_X540, + .blink_led_stop = &ixgbe_blink_led_stop_X540, + .set_rar = &ixgbe_set_rar_generic, + .clear_rar = &ixgbe_clear_rar_generic, + .set_vmdq = &ixgbe_set_vmdq_generic, + .set_vmdq_san_mac = &ixgbe_set_vmdq_san_mac_generic, + .clear_vmdq = &ixgbe_clear_vmdq_generic, + .init_rx_addrs = &ixgbe_init_rx_addrs_generic, + .update_mc_addr_list = &ixgbe_update_mc_addr_list_generic, + .enable_mc = &ixgbe_enable_mc_generic, + .disable_mc = &ixgbe_disable_mc_generic, + .clear_vfta = &ixgbe_clear_vfta_generic, + .set_vfta = &ixgbe_set_vfta_generic, + .fc_enable = &ixgbe_fc_enable_generic, + .setup_fc = ixgbe_setup_fc_generic, + .fc_autoneg = ixgbe_fc_autoneg, + .set_fw_drv_ver = &ixgbe_set_fw_drv_ver_generic, + .init_uta_tables = &ixgbe_init_uta_tables_generic, + .setup_sfp = NULL, + .set_mac_anti_spoofing = &ixgbe_set_mac_anti_spoofing, + .set_vlan_anti_spoofing = &ixgbe_set_vlan_anti_spoofing, + .acquire_swfw_sync = &ixgbe_acquire_swfw_sync_X540, + .release_swfw_sync = &ixgbe_release_swfw_sync_X540, + .init_swfw_sync = &ixgbe_init_swfw_sync_X540, + .disable_rx_buff = &ixgbe_disable_rx_buff_generic, + .enable_rx_buff = &ixgbe_enable_rx_buff_generic, + .get_thermal_sensor_data = NULL, + .init_thermal_sensor_thresh = NULL, + .prot_autoc_read = &prot_autoc_read_generic, + .prot_autoc_write = &prot_autoc_write_generic, + .enable_rx = &ixgbe_enable_rx_generic, + .disable_rx = &ixgbe_disable_rx_generic, +}; + +static const struct ixgbe_eeprom_operations eeprom_ops_X540 = { + .init_params = &ixgbe_init_eeprom_params_X540, + .read = &ixgbe_read_eerd_X540, + .read_buffer = &ixgbe_read_eerd_buffer_X540, + .write = &ixgbe_write_eewr_X540, + .write_buffer = &ixgbe_write_eewr_buffer_X540, + .calc_checksum = &ixgbe_calc_eeprom_checksum_X540, + .validate_checksum = &ixgbe_validate_eeprom_checksum_X540, + .update_checksum = &ixgbe_update_eeprom_checksum_X540, +}; + +static const struct ixgbe_phy_operations phy_ops_X540 = { + .identify = &ixgbe_identify_phy_generic, + .identify_sfp = &ixgbe_identify_sfp_module_generic, + .init = NULL, + .reset = NULL, + .read_reg = &ixgbe_read_phy_reg_generic, + .write_reg = &ixgbe_write_phy_reg_generic, + .setup_link = &ixgbe_setup_phy_link_generic, + .setup_link_speed = &ixgbe_setup_phy_link_speed_generic, + .read_i2c_byte = &ixgbe_read_i2c_byte_generic, + .write_i2c_byte = &ixgbe_write_i2c_byte_generic, + .read_i2c_sff8472 = &ixgbe_read_i2c_sff8472_generic, + .read_i2c_eeprom = &ixgbe_read_i2c_eeprom_generic, + .write_i2c_eeprom = &ixgbe_write_i2c_eeprom_generic, + .check_overtemp = &ixgbe_tn_check_overtemp, + .set_phy_power = &ixgbe_set_copper_phy_power, +}; + +static const u32 ixgbe_mvals_X540[IXGBE_MVALS_IDX_LIMIT] = { + IXGBE_MVALS_INIT(X540) +}; + +const struct ixgbe_info ixgbe_X540_info = { + .mac = ixgbe_mac_X540, + .get_invariants = &ixgbe_get_invariants_X540, + .mac_ops = &mac_ops_X540, + .eeprom_ops = &eeprom_ops_X540, + .phy_ops = &phy_ops_X540, + .mbx_ops = &mbx_ops_generic, + .mvals = ixgbe_mvals_X540, +}; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h new file mode 100644 index 000000000..e246c0d2a --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#include "ixgbe_type.h" + +s32 ixgbe_get_invariants_X540(struct ixgbe_hw *hw); +s32 ixgbe_setup_mac_link_X540(struct ixgbe_hw *hw, ixgbe_link_speed speed, + bool autoneg_wait_to_complete); +s32 ixgbe_reset_hw_X540(struct ixgbe_hw *hw); +s32 ixgbe_start_hw_X540(struct ixgbe_hw *hw); +enum ixgbe_media_type ixgbe_get_media_type_X540(struct ixgbe_hw *hw); +s32 ixgbe_setup_mac_link_X540(struct ixgbe_hw *hw, ixgbe_link_speed speed, + bool autoneg_wait_to_complete); +s32 ixgbe_blink_led_start_X540(struct ixgbe_hw *hw, u32 index); +s32 ixgbe_blink_led_stop_X540(struct ixgbe_hw *hw, u32 index); +s32 ixgbe_acquire_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask); +void ixgbe_release_swfw_sync_X540(struct ixgbe_hw *hw, u32 mask); +void ixgbe_init_swfw_sync_X540(struct ixgbe_hw *hw); +s32 ixgbe_init_eeprom_params_X540(struct ixgbe_hw *hw); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c new file mode 100644 index 000000000..37f2bc6de --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -0,0 +1,4100 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#include "ixgbe_x540.h" +#include "ixgbe_type.h" +#include "ixgbe_common.h" +#include "ixgbe_phy.h" + +static s32 ixgbe_setup_kr_speed_x550em(struct ixgbe_hw *, ixgbe_link_speed); +static s32 ixgbe_setup_fc_x550em(struct ixgbe_hw *); +static void ixgbe_fc_autoneg_fiber_x550em_a(struct ixgbe_hw *); +static void ixgbe_fc_autoneg_backplane_x550em_a(struct ixgbe_hw *); +static s32 ixgbe_setup_fc_backplane_x550em_a(struct ixgbe_hw *); + +static s32 ixgbe_get_invariants_X550_x(struct ixgbe_hw *hw) +{ + struct ixgbe_mac_info *mac = &hw->mac; + struct ixgbe_phy_info *phy = &hw->phy; + struct ixgbe_link_info *link = &hw->link; + + /* Start with X540 invariants, since so simular */ + ixgbe_get_invariants_X540(hw); + + if (mac->ops.get_media_type(hw) != ixgbe_media_type_copper) + phy->ops.set_phy_power = NULL; + + link->addr = IXGBE_CS4227; + + return 0; +} + +static s32 ixgbe_get_invariants_X550_x_fw(struct ixgbe_hw *hw) +{ + struct ixgbe_phy_info *phy = &hw->phy; + + /* Start with X540 invariants, since so similar */ + ixgbe_get_invariants_X540(hw); + + phy->ops.set_phy_power = NULL; + + return 0; +} + +static s32 ixgbe_get_invariants_X550_a(struct ixgbe_hw *hw) +{ + struct ixgbe_mac_info *mac = &hw->mac; + struct ixgbe_phy_info *phy = &hw->phy; + + /* Start with X540 invariants, since so simular */ + ixgbe_get_invariants_X540(hw); + + if (mac->ops.get_media_type(hw) != ixgbe_media_type_copper) + phy->ops.set_phy_power = NULL; + + return 0; +} + +static s32 ixgbe_get_invariants_X550_a_fw(struct ixgbe_hw *hw) +{ + struct ixgbe_phy_info *phy = &hw->phy; + + /* Start with X540 invariants, since so similar */ + ixgbe_get_invariants_X540(hw); + + phy->ops.set_phy_power = NULL; + + return 0; +} + +/** ixgbe_setup_mux_ctl - Setup ESDP register for I2C mux control + * @hw: pointer to hardware structure + **/ +static void ixgbe_setup_mux_ctl(struct ixgbe_hw *hw) +{ + u32 esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + + if (hw->bus.lan_id) { + esdp &= ~(IXGBE_ESDP_SDP1_NATIVE | IXGBE_ESDP_SDP1); + esdp |= IXGBE_ESDP_SDP1_DIR; + } + esdp &= ~(IXGBE_ESDP_SDP0_NATIVE | IXGBE_ESDP_SDP0_DIR); + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp); + IXGBE_WRITE_FLUSH(hw); +} + +/** + * ixgbe_read_cs4227 - Read CS4227 register + * @hw: pointer to hardware structure + * @reg: register number to write + * @value: pointer to receive value read + * + * Returns status code + */ +static s32 ixgbe_read_cs4227(struct ixgbe_hw *hw, u16 reg, u16 *value) +{ + return hw->link.ops.read_link_unlocked(hw, hw->link.addr, reg, value); +} + +/** + * ixgbe_write_cs4227 - Write CS4227 register + * @hw: pointer to hardware structure + * @reg: register number to write + * @value: value to write to register + * + * Returns status code + */ +static s32 ixgbe_write_cs4227(struct ixgbe_hw *hw, u16 reg, u16 value) +{ + return hw->link.ops.write_link_unlocked(hw, hw->link.addr, reg, value); +} + +/** + * ixgbe_read_pe - Read register from port expander + * @hw: pointer to hardware structure + * @reg: register number to read + * @value: pointer to receive read value + * + * Returns status code + */ +static s32 ixgbe_read_pe(struct ixgbe_hw *hw, u8 reg, u8 *value) +{ + s32 status; + + status = ixgbe_read_i2c_byte_generic_unlocked(hw, reg, IXGBE_PE, value); + if (status) + hw_err(hw, "port expander access failed with %d\n", status); + return status; +} + +/** + * ixgbe_write_pe - Write register to port expander + * @hw: pointer to hardware structure + * @reg: register number to write + * @value: value to write + * + * Returns status code + */ +static s32 ixgbe_write_pe(struct ixgbe_hw *hw, u8 reg, u8 value) +{ + s32 status; + + status = ixgbe_write_i2c_byte_generic_unlocked(hw, reg, IXGBE_PE, + value); + if (status) + hw_err(hw, "port expander access failed with %d\n", status); + return status; +} + +/** + * ixgbe_reset_cs4227 - Reset CS4227 using port expander + * @hw: pointer to hardware structure + * + * This function assumes that the caller has acquired the proper semaphore. + * Returns error code + */ +static s32 ixgbe_reset_cs4227(struct ixgbe_hw *hw) +{ + s32 status; + u32 retry; + u16 value; + u8 reg; + + /* Trigger hard reset. */ + status = ixgbe_read_pe(hw, IXGBE_PE_OUTPUT, ®); + if (status) + return status; + reg |= IXGBE_PE_BIT1; + status = ixgbe_write_pe(hw, IXGBE_PE_OUTPUT, reg); + if (status) + return status; + + status = ixgbe_read_pe(hw, IXGBE_PE_CONFIG, ®); + if (status) + return status; + reg &= ~IXGBE_PE_BIT1; + status = ixgbe_write_pe(hw, IXGBE_PE_CONFIG, reg); + if (status) + return status; + + status = ixgbe_read_pe(hw, IXGBE_PE_OUTPUT, ®); + if (status) + return status; + reg &= ~IXGBE_PE_BIT1; + status = ixgbe_write_pe(hw, IXGBE_PE_OUTPUT, reg); + if (status) + return status; + + usleep_range(IXGBE_CS4227_RESET_HOLD, IXGBE_CS4227_RESET_HOLD + 100); + + status = ixgbe_read_pe(hw, IXGBE_PE_OUTPUT, ®); + if (status) + return status; + reg |= IXGBE_PE_BIT1; + status = ixgbe_write_pe(hw, IXGBE_PE_OUTPUT, reg); + if (status) + return status; + + /* Wait for the reset to complete. */ + msleep(IXGBE_CS4227_RESET_DELAY); + for (retry = 0; retry < IXGBE_CS4227_RETRIES; retry++) { + status = ixgbe_read_cs4227(hw, IXGBE_CS4227_EFUSE_STATUS, + &value); + if (!status && value == IXGBE_CS4227_EEPROM_LOAD_OK) + break; + msleep(IXGBE_CS4227_CHECK_DELAY); + } + if (retry == IXGBE_CS4227_RETRIES) { + hw_err(hw, "CS4227 reset did not complete\n"); + return IXGBE_ERR_PHY; + } + + status = ixgbe_read_cs4227(hw, IXGBE_CS4227_EEPROM_STATUS, &value); + if (status || !(value & IXGBE_CS4227_EEPROM_LOAD_OK)) { + hw_err(hw, "CS4227 EEPROM did not load successfully\n"); + return IXGBE_ERR_PHY; + } + + return 0; +} + +/** + * ixgbe_check_cs4227 - Check CS4227 and reset as needed + * @hw: pointer to hardware structure + */ +static void ixgbe_check_cs4227(struct ixgbe_hw *hw) +{ + u32 swfw_mask = hw->phy.phy_semaphore_mask; + s32 status; + u16 value; + u8 retry; + + for (retry = 0; retry < IXGBE_CS4227_RETRIES; retry++) { + status = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask); + if (status) { + hw_err(hw, "semaphore failed with %d\n", status); + msleep(IXGBE_CS4227_CHECK_DELAY); + continue; + } + + /* Get status of reset flow. */ + status = ixgbe_read_cs4227(hw, IXGBE_CS4227_SCRATCH, &value); + if (!status && value == IXGBE_CS4227_RESET_COMPLETE) + goto out; + + if (status || value != IXGBE_CS4227_RESET_PENDING) + break; + + /* Reset is pending. Wait and check again. */ + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + msleep(IXGBE_CS4227_CHECK_DELAY); + } + /* If still pending, assume other instance failed. */ + if (retry == IXGBE_CS4227_RETRIES) { + status = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask); + if (status) { + hw_err(hw, "semaphore failed with %d\n", status); + return; + } + } + + /* Reset the CS4227. */ + status = ixgbe_reset_cs4227(hw); + if (status) { + hw_err(hw, "CS4227 reset failed: %d", status); + goto out; + } + + /* Reset takes so long, temporarily release semaphore in case the + * other driver instance is waiting for the reset indication. + */ + ixgbe_write_cs4227(hw, IXGBE_CS4227_SCRATCH, + IXGBE_CS4227_RESET_PENDING); + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + usleep_range(10000, 12000); + status = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask); + if (status) { + hw_err(hw, "semaphore failed with %d", status); + return; + } + + /* Record completion for next time. */ + status = ixgbe_write_cs4227(hw, IXGBE_CS4227_SCRATCH, + IXGBE_CS4227_RESET_COMPLETE); + +out: + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + msleep(hw->eeprom.semaphore_delay); +} + +/** ixgbe_identify_phy_x550em - Get PHY type based on device id + * @hw: pointer to hardware structure + * + * Returns error code + */ +static s32 ixgbe_identify_phy_x550em(struct ixgbe_hw *hw) +{ + switch (hw->device_id) { + case IXGBE_DEV_ID_X550EM_A_SFP: + if (hw->bus.lan_id) + hw->phy.phy_semaphore_mask = IXGBE_GSSR_PHY1_SM; + else + hw->phy.phy_semaphore_mask = IXGBE_GSSR_PHY0_SM; + return ixgbe_identify_module_generic(hw); + case IXGBE_DEV_ID_X550EM_X_SFP: + /* set up for CS4227 usage */ + hw->phy.phy_semaphore_mask = IXGBE_GSSR_SHARED_I2C_SM; + ixgbe_setup_mux_ctl(hw); + ixgbe_check_cs4227(hw); + fallthrough; + case IXGBE_DEV_ID_X550EM_A_SFP_N: + return ixgbe_identify_module_generic(hw); + case IXGBE_DEV_ID_X550EM_X_KX4: + hw->phy.type = ixgbe_phy_x550em_kx4; + break; + case IXGBE_DEV_ID_X550EM_X_XFI: + hw->phy.type = ixgbe_phy_x550em_xfi; + break; + case IXGBE_DEV_ID_X550EM_X_KR: + case IXGBE_DEV_ID_X550EM_A_KR: + case IXGBE_DEV_ID_X550EM_A_KR_L: + hw->phy.type = ixgbe_phy_x550em_kr; + break; + case IXGBE_DEV_ID_X550EM_A_10G_T: + if (hw->bus.lan_id) + hw->phy.phy_semaphore_mask = IXGBE_GSSR_PHY1_SM; + else + hw->phy.phy_semaphore_mask = IXGBE_GSSR_PHY0_SM; + fallthrough; + case IXGBE_DEV_ID_X550EM_X_10G_T: + return ixgbe_identify_phy_generic(hw); + case IXGBE_DEV_ID_X550EM_X_1G_T: + hw->phy.type = ixgbe_phy_ext_1g_t; + break; + case IXGBE_DEV_ID_X550EM_A_1G_T: + case IXGBE_DEV_ID_X550EM_A_1G_T_L: + hw->phy.type = ixgbe_phy_fw; + hw->phy.ops.read_reg = NULL; + hw->phy.ops.write_reg = NULL; + if (hw->bus.lan_id) + hw->phy.phy_semaphore_mask |= IXGBE_GSSR_PHY1_SM; + else + hw->phy.phy_semaphore_mask |= IXGBE_GSSR_PHY0_SM; + break; + default: + break; + } + return 0; +} + +static s32 ixgbe_read_phy_reg_x550em(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u16 *phy_data) +{ + return IXGBE_NOT_IMPLEMENTED; +} + +static s32 ixgbe_write_phy_reg_x550em(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u16 phy_data) +{ + return IXGBE_NOT_IMPLEMENTED; +} + +/** + * ixgbe_read_i2c_combined_generic - Perform I2C read combined operation + * @hw: pointer to the hardware structure + * @addr: I2C bus address to read from + * @reg: I2C device register to read from + * @val: pointer to location to receive read value + * + * Returns an error code on error. + **/ +static s32 ixgbe_read_i2c_combined_generic(struct ixgbe_hw *hw, u8 addr, + u16 reg, u16 *val) +{ + return ixgbe_read_i2c_combined_generic_int(hw, addr, reg, val, true); +} + +/** + * ixgbe_read_i2c_combined_generic_unlocked - Do I2C read combined operation + * @hw: pointer to the hardware structure + * @addr: I2C bus address to read from + * @reg: I2C device register to read from + * @val: pointer to location to receive read value + * + * Returns an error code on error. + **/ +static s32 +ixgbe_read_i2c_combined_generic_unlocked(struct ixgbe_hw *hw, u8 addr, + u16 reg, u16 *val) +{ + return ixgbe_read_i2c_combined_generic_int(hw, addr, reg, val, false); +} + +/** + * ixgbe_write_i2c_combined_generic - Perform I2C write combined operation + * @hw: pointer to the hardware structure + * @addr: I2C bus address to write to + * @reg: I2C device register to write to + * @val: value to write + * + * Returns an error code on error. + **/ +static s32 ixgbe_write_i2c_combined_generic(struct ixgbe_hw *hw, + u8 addr, u16 reg, u16 val) +{ + return ixgbe_write_i2c_combined_generic_int(hw, addr, reg, val, true); +} + +/** + * ixgbe_write_i2c_combined_generic_unlocked - Do I2C write combined operation + * @hw: pointer to the hardware structure + * @addr: I2C bus address to write to + * @reg: I2C device register to write to + * @val: value to write + * + * Returns an error code on error. + **/ +static s32 +ixgbe_write_i2c_combined_generic_unlocked(struct ixgbe_hw *hw, + u8 addr, u16 reg, u16 val) +{ + return ixgbe_write_i2c_combined_generic_int(hw, addr, reg, val, false); +} + +/** + * ixgbe_fw_phy_activity - Perform an activity on a PHY + * @hw: pointer to hardware structure + * @activity: activity to perform + * @data: Pointer to 4 32-bit words of data + */ +s32 ixgbe_fw_phy_activity(struct ixgbe_hw *hw, u16 activity, + u32 (*data)[FW_PHY_ACT_DATA_COUNT]) +{ + union { + struct ixgbe_hic_phy_activity_req cmd; + struct ixgbe_hic_phy_activity_resp rsp; + } hic; + u16 retries = FW_PHY_ACT_RETRIES; + s32 rc; + u32 i; + + do { + memset(&hic, 0, sizeof(hic)); + hic.cmd.hdr.cmd = FW_PHY_ACT_REQ_CMD; + hic.cmd.hdr.buf_len = FW_PHY_ACT_REQ_LEN; + hic.cmd.hdr.checksum = FW_DEFAULT_CHECKSUM; + hic.cmd.port_number = hw->bus.lan_id; + hic.cmd.activity_id = cpu_to_le16(activity); + for (i = 0; i < ARRAY_SIZE(hic.cmd.data); ++i) + hic.cmd.data[i] = cpu_to_be32((*data)[i]); + + rc = ixgbe_host_interface_command(hw, &hic.cmd, sizeof(hic.cmd), + IXGBE_HI_COMMAND_TIMEOUT, + true); + if (rc) + return rc; + if (hic.rsp.hdr.cmd_or_resp.ret_status == + FW_CEM_RESP_STATUS_SUCCESS) { + for (i = 0; i < FW_PHY_ACT_DATA_COUNT; ++i) + (*data)[i] = be32_to_cpu(hic.rsp.data[i]); + return 0; + } + usleep_range(20, 30); + --retries; + } while (retries > 0); + + return IXGBE_ERR_HOST_INTERFACE_COMMAND; +} + +static const struct { + u16 fw_speed; + ixgbe_link_speed phy_speed; +} ixgbe_fw_map[] = { + { FW_PHY_ACT_LINK_SPEED_10, IXGBE_LINK_SPEED_10_FULL }, + { FW_PHY_ACT_LINK_SPEED_100, IXGBE_LINK_SPEED_100_FULL }, + { FW_PHY_ACT_LINK_SPEED_1G, IXGBE_LINK_SPEED_1GB_FULL }, + { FW_PHY_ACT_LINK_SPEED_2_5G, IXGBE_LINK_SPEED_2_5GB_FULL }, + { FW_PHY_ACT_LINK_SPEED_5G, IXGBE_LINK_SPEED_5GB_FULL }, + { FW_PHY_ACT_LINK_SPEED_10G, IXGBE_LINK_SPEED_10GB_FULL }, +}; + +/** + * ixgbe_get_phy_id_fw - Get the phy ID via firmware command + * @hw: pointer to hardware structure + * + * Returns error code + */ +static s32 ixgbe_get_phy_id_fw(struct ixgbe_hw *hw) +{ + u32 info[FW_PHY_ACT_DATA_COUNT] = { 0 }; + u16 phy_speeds; + u16 phy_id_lo; + s32 rc; + u16 i; + + if (hw->phy.id) + return 0; + + rc = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_GET_PHY_INFO, &info); + if (rc) + return rc; + + hw->phy.speeds_supported = 0; + phy_speeds = info[0] & FW_PHY_INFO_SPEED_MASK; + for (i = 0; i < ARRAY_SIZE(ixgbe_fw_map); ++i) { + if (phy_speeds & ixgbe_fw_map[i].fw_speed) + hw->phy.speeds_supported |= ixgbe_fw_map[i].phy_speed; + } + + hw->phy.id = info[0] & FW_PHY_INFO_ID_HI_MASK; + phy_id_lo = info[1] & FW_PHY_INFO_ID_LO_MASK; + hw->phy.id |= phy_id_lo & IXGBE_PHY_REVISION_MASK; + hw->phy.revision = phy_id_lo & ~IXGBE_PHY_REVISION_MASK; + if (!hw->phy.id || hw->phy.id == IXGBE_PHY_REVISION_MASK) + return IXGBE_ERR_PHY_ADDR_INVALID; + + hw->phy.autoneg_advertised = hw->phy.speeds_supported; + hw->phy.eee_speeds_supported = IXGBE_LINK_SPEED_100_FULL | + IXGBE_LINK_SPEED_1GB_FULL; + hw->phy.eee_speeds_advertised = hw->phy.eee_speeds_supported; + return 0; +} + +/** + * ixgbe_identify_phy_fw - Get PHY type based on firmware command + * @hw: pointer to hardware structure + * + * Returns error code + */ +static s32 ixgbe_identify_phy_fw(struct ixgbe_hw *hw) +{ + if (hw->bus.lan_id) + hw->phy.phy_semaphore_mask = IXGBE_GSSR_PHY1_SM; + else + hw->phy.phy_semaphore_mask = IXGBE_GSSR_PHY0_SM; + + hw->phy.type = ixgbe_phy_fw; + hw->phy.ops.read_reg = NULL; + hw->phy.ops.write_reg = NULL; + return ixgbe_get_phy_id_fw(hw); +} + +/** + * ixgbe_shutdown_fw_phy - Shutdown a firmware-controlled PHY + * @hw: pointer to hardware structure + * + * Returns error code + */ +static s32 ixgbe_shutdown_fw_phy(struct ixgbe_hw *hw) +{ + u32 setup[FW_PHY_ACT_DATA_COUNT] = { 0 }; + + setup[0] = FW_PHY_ACT_FORCE_LINK_DOWN_OFF; + return ixgbe_fw_phy_activity(hw, FW_PHY_ACT_FORCE_LINK_DOWN, &setup); +} + +/** + * ixgbe_setup_fw_link - Setup firmware-controlled PHYs + * @hw: pointer to hardware structure + */ +static s32 ixgbe_setup_fw_link(struct ixgbe_hw *hw) +{ + u32 setup[FW_PHY_ACT_DATA_COUNT] = { 0 }; + s32 rc; + u16 i; + + if (hw->phy.reset_disable || ixgbe_check_reset_blocked(hw)) + return 0; + + if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) { + hw_err(hw, "rx_pause not valid in strict IEEE mode\n"); + return IXGBE_ERR_INVALID_LINK_SETTINGS; + } + + switch (hw->fc.requested_mode) { + case ixgbe_fc_full: + setup[0] |= FW_PHY_ACT_SETUP_LINK_PAUSE_RXTX << + FW_PHY_ACT_SETUP_LINK_PAUSE_SHIFT; + break; + case ixgbe_fc_rx_pause: + setup[0] |= FW_PHY_ACT_SETUP_LINK_PAUSE_RX << + FW_PHY_ACT_SETUP_LINK_PAUSE_SHIFT; + break; + case ixgbe_fc_tx_pause: + setup[0] |= FW_PHY_ACT_SETUP_LINK_PAUSE_TX << + FW_PHY_ACT_SETUP_LINK_PAUSE_SHIFT; + break; + default: + break; + } + + for (i = 0; i < ARRAY_SIZE(ixgbe_fw_map); ++i) { + if (hw->phy.autoneg_advertised & ixgbe_fw_map[i].phy_speed) + setup[0] |= ixgbe_fw_map[i].fw_speed; + } + setup[0] |= FW_PHY_ACT_SETUP_LINK_HP | FW_PHY_ACT_SETUP_LINK_AN; + + if (hw->phy.eee_speeds_advertised) + setup[0] |= FW_PHY_ACT_SETUP_LINK_EEE; + + rc = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_SETUP_LINK, &setup); + if (rc) + return rc; + if (setup[0] == FW_PHY_ACT_SETUP_LINK_RSP_DOWN) + return IXGBE_ERR_OVERTEMP; + return 0; +} + +/** + * ixgbe_fc_autoneg_fw - Set up flow control for FW-controlled PHYs + * @hw: pointer to hardware structure + * + * Called at init time to set up flow control. + */ +static s32 ixgbe_fc_autoneg_fw(struct ixgbe_hw *hw) +{ + if (hw->fc.requested_mode == ixgbe_fc_default) + hw->fc.requested_mode = ixgbe_fc_full; + + return ixgbe_setup_fw_link(hw); +} + +/** ixgbe_init_eeprom_params_X550 - Initialize EEPROM params + * @hw: pointer to hardware structure + * + * Initializes the EEPROM parameters ixgbe_eeprom_info within the + * ixgbe_hw struct in order to set up EEPROM access. + **/ +static s32 ixgbe_init_eeprom_params_X550(struct ixgbe_hw *hw) +{ + struct ixgbe_eeprom_info *eeprom = &hw->eeprom; + u32 eec; + u16 eeprom_size; + + if (eeprom->type == ixgbe_eeprom_uninitialized) { + eeprom->semaphore_delay = 10; + eeprom->type = ixgbe_flash; + + eec = IXGBE_READ_REG(hw, IXGBE_EEC(hw)); + eeprom_size = (u16)((eec & IXGBE_EEC_SIZE) >> + IXGBE_EEC_SIZE_SHIFT); + eeprom->word_size = BIT(eeprom_size + + IXGBE_EEPROM_WORD_SIZE_SHIFT); + + hw_dbg(hw, "Eeprom params: type = %d, size = %d\n", + eeprom->type, eeprom->word_size); + } + + return 0; +} + +/** + * ixgbe_iosf_wait - Wait for IOSF command completion + * @hw: pointer to hardware structure + * @ctrl: pointer to location to receive final IOSF control value + * + * Return: failing status on timeout + * + * Note: ctrl can be NULL if the IOSF control register value is not needed + */ +static s32 ixgbe_iosf_wait(struct ixgbe_hw *hw, u32 *ctrl) +{ + u32 i, command; + + /* Check every 10 usec to see if the address cycle completed. + * The SB IOSF BUSY bit will clear when the operation is + * complete. + */ + for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) { + command = IXGBE_READ_REG(hw, IXGBE_SB_IOSF_INDIRECT_CTRL); + if (!(command & IXGBE_SB_IOSF_CTRL_BUSY)) + break; + udelay(10); + } + if (ctrl) + *ctrl = command; + if (i == IXGBE_MDIO_COMMAND_TIMEOUT) { + hw_dbg(hw, "IOSF wait timed out\n"); + return IXGBE_ERR_PHY; + } + + return 0; +} + +/** ixgbe_read_iosf_sb_reg_x550 - Writes a value to specified register of the + * IOSF device + * @hw: pointer to hardware structure + * @reg_addr: 32 bit PHY register to write + * @device_type: 3 bit device type + * @phy_data: Pointer to read data from the register + **/ +static s32 ixgbe_read_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u32 *data) +{ + u32 gssr = IXGBE_GSSR_PHY1_SM | IXGBE_GSSR_PHY0_SM; + u32 command, error; + s32 ret; + + ret = hw->mac.ops.acquire_swfw_sync(hw, gssr); + if (ret) + return ret; + + ret = ixgbe_iosf_wait(hw, NULL); + if (ret) + goto out; + + command = ((reg_addr << IXGBE_SB_IOSF_CTRL_ADDR_SHIFT) | + (device_type << IXGBE_SB_IOSF_CTRL_TARGET_SELECT_SHIFT)); + + /* Write IOSF control register */ + IXGBE_WRITE_REG(hw, IXGBE_SB_IOSF_INDIRECT_CTRL, command); + + ret = ixgbe_iosf_wait(hw, &command); + + if ((command & IXGBE_SB_IOSF_CTRL_RESP_STAT_MASK) != 0) { + error = (command & IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK) >> + IXGBE_SB_IOSF_CTRL_CMPL_ERR_SHIFT; + hw_dbg(hw, "Failed to read, error %x\n", error); + return IXGBE_ERR_PHY; + } + + if (!ret) + *data = IXGBE_READ_REG(hw, IXGBE_SB_IOSF_INDIRECT_DATA); + +out: + hw->mac.ops.release_swfw_sync(hw, gssr); + return ret; +} + +/** + * ixgbe_get_phy_token - Get the token for shared PHY access + * @hw: Pointer to hardware structure + */ +static s32 ixgbe_get_phy_token(struct ixgbe_hw *hw) +{ + struct ixgbe_hic_phy_token_req token_cmd; + s32 status; + + token_cmd.hdr.cmd = FW_PHY_TOKEN_REQ_CMD; + token_cmd.hdr.buf_len = FW_PHY_TOKEN_REQ_LEN; + token_cmd.hdr.cmd_or_resp.cmd_resv = 0; + token_cmd.hdr.checksum = FW_DEFAULT_CHECKSUM; + token_cmd.port_number = hw->bus.lan_id; + token_cmd.command_type = FW_PHY_TOKEN_REQ; + token_cmd.pad = 0; + status = ixgbe_host_interface_command(hw, &token_cmd, sizeof(token_cmd), + IXGBE_HI_COMMAND_TIMEOUT, + true); + if (status) + return status; + if (token_cmd.hdr.cmd_or_resp.ret_status == FW_PHY_TOKEN_OK) + return 0; + if (token_cmd.hdr.cmd_or_resp.ret_status != FW_PHY_TOKEN_RETRY) + return IXGBE_ERR_FW_RESP_INVALID; + + return IXGBE_ERR_TOKEN_RETRY; +} + +/** + * ixgbe_put_phy_token - Put the token for shared PHY access + * @hw: Pointer to hardware structure + */ +static s32 ixgbe_put_phy_token(struct ixgbe_hw *hw) +{ + struct ixgbe_hic_phy_token_req token_cmd; + s32 status; + + token_cmd.hdr.cmd = FW_PHY_TOKEN_REQ_CMD; + token_cmd.hdr.buf_len = FW_PHY_TOKEN_REQ_LEN; + token_cmd.hdr.cmd_or_resp.cmd_resv = 0; + token_cmd.hdr.checksum = FW_DEFAULT_CHECKSUM; + token_cmd.port_number = hw->bus.lan_id; + token_cmd.command_type = FW_PHY_TOKEN_REL; + token_cmd.pad = 0; + status = ixgbe_host_interface_command(hw, &token_cmd, sizeof(token_cmd), + IXGBE_HI_COMMAND_TIMEOUT, + true); + if (status) + return status; + if (token_cmd.hdr.cmd_or_resp.ret_status == FW_PHY_TOKEN_OK) + return 0; + return IXGBE_ERR_FW_RESP_INVALID; +} + +/** + * ixgbe_write_iosf_sb_reg_x550a - Write to IOSF PHY register + * @hw: pointer to hardware structure + * @reg_addr: 32 bit PHY register to write + * @device_type: 3 bit device type + * @data: Data to write to the register + **/ +static s32 ixgbe_write_iosf_sb_reg_x550a(struct ixgbe_hw *hw, u32 reg_addr, + __always_unused u32 device_type, + u32 data) +{ + struct ixgbe_hic_internal_phy_req write_cmd; + + memset(&write_cmd, 0, sizeof(write_cmd)); + write_cmd.hdr.cmd = FW_INT_PHY_REQ_CMD; + write_cmd.hdr.buf_len = FW_INT_PHY_REQ_LEN; + write_cmd.hdr.checksum = FW_DEFAULT_CHECKSUM; + write_cmd.port_number = hw->bus.lan_id; + write_cmd.command_type = FW_INT_PHY_REQ_WRITE; + write_cmd.address = cpu_to_be16(reg_addr); + write_cmd.write_data = cpu_to_be32(data); + + return ixgbe_host_interface_command(hw, &write_cmd, sizeof(write_cmd), + IXGBE_HI_COMMAND_TIMEOUT, false); +} + +/** + * ixgbe_read_iosf_sb_reg_x550a - Read from IOSF PHY register + * @hw: pointer to hardware structure + * @reg_addr: 32 bit PHY register to write + * @device_type: 3 bit device type + * @data: Pointer to read data from the register + **/ +static s32 ixgbe_read_iosf_sb_reg_x550a(struct ixgbe_hw *hw, u32 reg_addr, + __always_unused u32 device_type, + u32 *data) +{ + union { + struct ixgbe_hic_internal_phy_req cmd; + struct ixgbe_hic_internal_phy_resp rsp; + } hic; + s32 status; + + memset(&hic, 0, sizeof(hic)); + hic.cmd.hdr.cmd = FW_INT_PHY_REQ_CMD; + hic.cmd.hdr.buf_len = FW_INT_PHY_REQ_LEN; + hic.cmd.hdr.checksum = FW_DEFAULT_CHECKSUM; + hic.cmd.port_number = hw->bus.lan_id; + hic.cmd.command_type = FW_INT_PHY_REQ_READ; + hic.cmd.address = cpu_to_be16(reg_addr); + + status = ixgbe_host_interface_command(hw, &hic.cmd, sizeof(hic.cmd), + IXGBE_HI_COMMAND_TIMEOUT, true); + + /* Extract the register value from the response. */ + *data = be32_to_cpu(hic.rsp.read_data); + + return status; +} + +/** ixgbe_read_ee_hostif_buffer_X550- Read EEPROM word(s) using hostif + * @hw: pointer to hardware structure + * @offset: offset of word in the EEPROM to read + * @words: number of words + * @data: word(s) read from the EEPROM + * + * Reads a 16 bit word(s) from the EEPROM using the hostif. + **/ +static s32 ixgbe_read_ee_hostif_buffer_X550(struct ixgbe_hw *hw, + u16 offset, u16 words, u16 *data) +{ + const u32 mask = IXGBE_GSSR_SW_MNG_SM | IXGBE_GSSR_EEP_SM; + struct ixgbe_hic_read_shadow_ram buffer; + u32 current_word = 0; + u16 words_to_read; + s32 status; + u32 i; + + /* Take semaphore for the entire operation. */ + status = hw->mac.ops.acquire_swfw_sync(hw, mask); + if (status) { + hw_dbg(hw, "EEPROM read buffer - semaphore failed\n"); + return status; + } + + while (words) { + if (words > FW_MAX_READ_BUFFER_SIZE / 2) + words_to_read = FW_MAX_READ_BUFFER_SIZE / 2; + else + words_to_read = words; + + buffer.hdr.req.cmd = FW_READ_SHADOW_RAM_CMD; + buffer.hdr.req.buf_lenh = 0; + buffer.hdr.req.buf_lenl = FW_READ_SHADOW_RAM_LEN; + buffer.hdr.req.checksum = FW_DEFAULT_CHECKSUM; + + /* convert offset from words to bytes */ + buffer.address = (__force u32)cpu_to_be32((offset + + current_word) * 2); + buffer.length = (__force u16)cpu_to_be16(words_to_read * 2); + buffer.pad2 = 0; + buffer.pad3 = 0; + + status = ixgbe_hic_unlocked(hw, (u32 *)&buffer, sizeof(buffer), + IXGBE_HI_COMMAND_TIMEOUT); + if (status) { + hw_dbg(hw, "Host interface command failed\n"); + goto out; + } + + for (i = 0; i < words_to_read; i++) { + u32 reg = IXGBE_FLEX_MNG + (FW_NVM_DATA_OFFSET << 2) + + 2 * i; + u32 value = IXGBE_READ_REG(hw, reg); + + data[current_word] = (u16)(value & 0xffff); + current_word++; + i++; + if (i < words_to_read) { + value >>= 16; + data[current_word] = (u16)(value & 0xffff); + current_word++; + } + } + words -= words_to_read; + } + +out: + hw->mac.ops.release_swfw_sync(hw, mask); + return status; +} + +/** ixgbe_checksum_ptr_x550 - Checksum one pointer region + * @hw: pointer to hardware structure + * @ptr: pointer offset in eeprom + * @size: size of section pointed by ptr, if 0 first word will be used as size + * @csum: address of checksum to update + * + * Returns error status for any failure + **/ +static s32 ixgbe_checksum_ptr_x550(struct ixgbe_hw *hw, u16 ptr, + u16 size, u16 *csum, u16 *buffer, + u32 buffer_size) +{ + u16 buf[256]; + s32 status; + u16 length, bufsz, i, start; + u16 *local_buffer; + + bufsz = ARRAY_SIZE(buf); + + /* Read a chunk at the pointer location */ + if (!buffer) { + status = ixgbe_read_ee_hostif_buffer_X550(hw, ptr, bufsz, buf); + if (status) { + hw_dbg(hw, "Failed to read EEPROM image\n"); + return status; + } + local_buffer = buf; + } else { + if (buffer_size < ptr) + return IXGBE_ERR_PARAM; + local_buffer = &buffer[ptr]; + } + + if (size) { + start = 0; + length = size; + } else { + start = 1; + length = local_buffer[0]; + + /* Skip pointer section if length is invalid. */ + if (length == 0xFFFF || length == 0 || + (ptr + length) >= hw->eeprom.word_size) + return 0; + } + + if (buffer && ((u32)start + (u32)length > buffer_size)) + return IXGBE_ERR_PARAM; + + for (i = start; length; i++, length--) { + if (i == bufsz && !buffer) { + ptr += bufsz; + i = 0; + if (length < bufsz) + bufsz = length; + + /* Read a chunk at the pointer location */ + status = ixgbe_read_ee_hostif_buffer_X550(hw, ptr, + bufsz, buf); + if (status) { + hw_dbg(hw, "Failed to read EEPROM image\n"); + return status; + } + } + *csum += local_buffer[i]; + } + return 0; +} + +/** ixgbe_calc_checksum_X550 - Calculates and returns the checksum + * @hw: pointer to hardware structure + * @buffer: pointer to buffer containing calculated checksum + * @buffer_size: size of buffer + * + * Returns a negative error code on error, or the 16-bit checksum + **/ +static s32 ixgbe_calc_checksum_X550(struct ixgbe_hw *hw, u16 *buffer, + u32 buffer_size) +{ + u16 eeprom_ptrs[IXGBE_EEPROM_LAST_WORD + 1]; + u16 *local_buffer; + s32 status; + u16 checksum = 0; + u16 pointer, i, size; + + hw->eeprom.ops.init_params(hw); + + if (!buffer) { + /* Read pointer area */ + status = ixgbe_read_ee_hostif_buffer_X550(hw, 0, + IXGBE_EEPROM_LAST_WORD + 1, + eeprom_ptrs); + if (status) { + hw_dbg(hw, "Failed to read EEPROM image\n"); + return status; + } + local_buffer = eeprom_ptrs; + } else { + if (buffer_size < IXGBE_EEPROM_LAST_WORD) + return IXGBE_ERR_PARAM; + local_buffer = buffer; + } + + /* For X550 hardware include 0x0-0x41 in the checksum, skip the + * checksum word itself + */ + for (i = 0; i <= IXGBE_EEPROM_LAST_WORD; i++) + if (i != IXGBE_EEPROM_CHECKSUM) + checksum += local_buffer[i]; + + /* Include all data from pointers 0x3, 0x6-0xE. This excludes the + * FW, PHY module, and PCIe Expansion/Option ROM pointers. + */ + for (i = IXGBE_PCIE_ANALOG_PTR_X550; i < IXGBE_FW_PTR; i++) { + if (i == IXGBE_PHY_PTR || i == IXGBE_OPTION_ROM_PTR) + continue; + + pointer = local_buffer[i]; + + /* Skip pointer section if the pointer is invalid. */ + if (pointer == 0xFFFF || pointer == 0 || + pointer >= hw->eeprom.word_size) + continue; + + switch (i) { + case IXGBE_PCIE_GENERAL_PTR: + size = IXGBE_IXGBE_PCIE_GENERAL_SIZE; + break; + case IXGBE_PCIE_CONFIG0_PTR: + case IXGBE_PCIE_CONFIG1_PTR: + size = IXGBE_PCIE_CONFIG_SIZE; + break; + default: + size = 0; + break; + } + + status = ixgbe_checksum_ptr_x550(hw, pointer, size, &checksum, + buffer, buffer_size); + if (status) + return status; + } + + checksum = (u16)IXGBE_EEPROM_SUM - checksum; + + return (s32)checksum; +} + +/** ixgbe_calc_eeprom_checksum_X550 - Calculates and returns the checksum + * @hw: pointer to hardware structure + * + * Returns a negative error code on error, or the 16-bit checksum + **/ +static s32 ixgbe_calc_eeprom_checksum_X550(struct ixgbe_hw *hw) +{ + return ixgbe_calc_checksum_X550(hw, NULL, 0); +} + +/** ixgbe_read_ee_hostif_X550 - Read EEPROM word using a host interface command + * @hw: pointer to hardware structure + * @offset: offset of word in the EEPROM to read + * @data: word read from the EEPROM + * + * Reads a 16 bit word from the EEPROM using the hostif. + **/ +static s32 ixgbe_read_ee_hostif_X550(struct ixgbe_hw *hw, u16 offset, u16 *data) +{ + const u32 mask = IXGBE_GSSR_SW_MNG_SM | IXGBE_GSSR_EEP_SM; + struct ixgbe_hic_read_shadow_ram buffer; + s32 status; + + buffer.hdr.req.cmd = FW_READ_SHADOW_RAM_CMD; + buffer.hdr.req.buf_lenh = 0; + buffer.hdr.req.buf_lenl = FW_READ_SHADOW_RAM_LEN; + buffer.hdr.req.checksum = FW_DEFAULT_CHECKSUM; + + /* convert offset from words to bytes */ + buffer.address = (__force u32)cpu_to_be32(offset * 2); + /* one word */ + buffer.length = (__force u16)cpu_to_be16(sizeof(u16)); + + status = hw->mac.ops.acquire_swfw_sync(hw, mask); + if (status) + return status; + + status = ixgbe_hic_unlocked(hw, (u32 *)&buffer, sizeof(buffer), + IXGBE_HI_COMMAND_TIMEOUT); + if (!status) { + *data = (u16)IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, + FW_NVM_DATA_OFFSET); + } + + hw->mac.ops.release_swfw_sync(hw, mask); + return status; +} + +/** ixgbe_validate_eeprom_checksum_X550 - Validate EEPROM checksum + * @hw: pointer to hardware structure + * @checksum_val: calculated checksum + * + * Performs checksum calculation and validates the EEPROM checksum. If the + * caller does not need checksum_val, the value can be NULL. + **/ +static s32 ixgbe_validate_eeprom_checksum_X550(struct ixgbe_hw *hw, + u16 *checksum_val) +{ + s32 status; + u16 checksum; + u16 read_checksum = 0; + + /* Read the first word from the EEPROM. If this times out or fails, do + * not continue or we could be in for a very long wait while every + * EEPROM read fails + */ + status = hw->eeprom.ops.read(hw, 0, &checksum); + if (status) { + hw_dbg(hw, "EEPROM read failed\n"); + return status; + } + + status = hw->eeprom.ops.calc_checksum(hw); + if (status < 0) + return status; + + checksum = (u16)(status & 0xffff); + + status = ixgbe_read_ee_hostif_X550(hw, IXGBE_EEPROM_CHECKSUM, + &read_checksum); + if (status) + return status; + + /* Verify read checksum from EEPROM is the same as + * calculated checksum + */ + if (read_checksum != checksum) { + status = IXGBE_ERR_EEPROM_CHECKSUM; + hw_dbg(hw, "Invalid EEPROM checksum"); + } + + /* If the user cares, return the calculated checksum */ + if (checksum_val) + *checksum_val = checksum; + + return status; +} + +/** ixgbe_write_ee_hostif_X550 - Write EEPROM word using hostif + * @hw: pointer to hardware structure + * @offset: offset of word in the EEPROM to write + * @data: word write to the EEPROM + * + * Write a 16 bit word to the EEPROM using the hostif. + **/ +static s32 ixgbe_write_ee_hostif_data_X550(struct ixgbe_hw *hw, u16 offset, + u16 data) +{ + s32 status; + struct ixgbe_hic_write_shadow_ram buffer; + + buffer.hdr.req.cmd = FW_WRITE_SHADOW_RAM_CMD; + buffer.hdr.req.buf_lenh = 0; + buffer.hdr.req.buf_lenl = FW_WRITE_SHADOW_RAM_LEN; + buffer.hdr.req.checksum = FW_DEFAULT_CHECKSUM; + + /* one word */ + buffer.length = cpu_to_be16(sizeof(u16)); + buffer.data = data; + buffer.address = cpu_to_be32(offset * 2); + + status = ixgbe_host_interface_command(hw, &buffer, sizeof(buffer), + IXGBE_HI_COMMAND_TIMEOUT, false); + return status; +} + +/** ixgbe_write_ee_hostif_X550 - Write EEPROM word using hostif + * @hw: pointer to hardware structure + * @offset: offset of word in the EEPROM to write + * @data: word write to the EEPROM + * + * Write a 16 bit word to the EEPROM using the hostif. + **/ +static s32 ixgbe_write_ee_hostif_X550(struct ixgbe_hw *hw, u16 offset, u16 data) +{ + s32 status = 0; + + if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM) == 0) { + status = ixgbe_write_ee_hostif_data_X550(hw, offset, data); + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM); + } else { + hw_dbg(hw, "write ee hostif failed to get semaphore"); + status = IXGBE_ERR_SWFW_SYNC; + } + + return status; +} + +/** ixgbe_update_flash_X550 - Instruct HW to copy EEPROM to Flash device + * @hw: pointer to hardware structure + * + * Issue a shadow RAM dump to FW to copy EEPROM from shadow RAM to the flash. + **/ +static s32 ixgbe_update_flash_X550(struct ixgbe_hw *hw) +{ + s32 status = 0; + union ixgbe_hic_hdr2 buffer; + + buffer.req.cmd = FW_SHADOW_RAM_DUMP_CMD; + buffer.req.buf_lenh = 0; + buffer.req.buf_lenl = FW_SHADOW_RAM_DUMP_LEN; + buffer.req.checksum = FW_DEFAULT_CHECKSUM; + + status = ixgbe_host_interface_command(hw, &buffer, sizeof(buffer), + IXGBE_HI_COMMAND_TIMEOUT, false); + return status; +} + +/** + * ixgbe_get_bus_info_X550em - Set PCI bus info + * @hw: pointer to hardware structure + * + * Sets bus link width and speed to unknown because X550em is + * not a PCI device. + **/ +static s32 ixgbe_get_bus_info_X550em(struct ixgbe_hw *hw) +{ + hw->bus.type = ixgbe_bus_type_internal; + hw->bus.width = ixgbe_bus_width_unknown; + hw->bus.speed = ixgbe_bus_speed_unknown; + + hw->mac.ops.set_lan_id(hw); + + return 0; +} + +/** + * ixgbe_fw_recovery_mode - Check FW NVM recovery mode + * @hw: pointer t hardware structure + * + * Returns true if in FW NVM recovery mode. + */ +static bool ixgbe_fw_recovery_mode_X550(struct ixgbe_hw *hw) +{ + u32 fwsm; + + fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM(hw)); + return !!(fwsm & IXGBE_FWSM_FW_NVM_RECOVERY_MODE); +} + +/** ixgbe_disable_rx_x550 - Disable RX unit + * + * Enables the Rx DMA unit for x550 + **/ +static void ixgbe_disable_rx_x550(struct ixgbe_hw *hw) +{ + u32 rxctrl, pfdtxgswc; + s32 status; + struct ixgbe_hic_disable_rxen fw_cmd; + + rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL); + if (rxctrl & IXGBE_RXCTRL_RXEN) { + pfdtxgswc = IXGBE_READ_REG(hw, IXGBE_PFDTXGSWC); + if (pfdtxgswc & IXGBE_PFDTXGSWC_VT_LBEN) { + pfdtxgswc &= ~IXGBE_PFDTXGSWC_VT_LBEN; + IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, pfdtxgswc); + hw->mac.set_lben = true; + } else { + hw->mac.set_lben = false; + } + + fw_cmd.hdr.cmd = FW_DISABLE_RXEN_CMD; + fw_cmd.hdr.buf_len = FW_DISABLE_RXEN_LEN; + fw_cmd.hdr.checksum = FW_DEFAULT_CHECKSUM; + fw_cmd.port_number = hw->bus.lan_id; + + status = ixgbe_host_interface_command(hw, &fw_cmd, + sizeof(struct ixgbe_hic_disable_rxen), + IXGBE_HI_COMMAND_TIMEOUT, true); + + /* If we fail - disable RX using register write */ + if (status) { + rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL); + if (rxctrl & IXGBE_RXCTRL_RXEN) { + rxctrl &= ~IXGBE_RXCTRL_RXEN; + IXGBE_WRITE_REG(hw, IXGBE_RXCTRL, rxctrl); + } + } + } +} + +/** ixgbe_update_eeprom_checksum_X550 - Updates the EEPROM checksum and flash + * @hw: pointer to hardware structure + * + * After writing EEPROM to shadow RAM using EEWR register, software calculates + * checksum and updates the EEPROM and instructs the hardware to update + * the flash. + **/ +static s32 ixgbe_update_eeprom_checksum_X550(struct ixgbe_hw *hw) +{ + s32 status; + u16 checksum = 0; + + /* Read the first word from the EEPROM. If this times out or fails, do + * not continue or we could be in for a very long wait while every + * EEPROM read fails + */ + status = ixgbe_read_ee_hostif_X550(hw, 0, &checksum); + if (status) { + hw_dbg(hw, "EEPROM read failed\n"); + return status; + } + + status = ixgbe_calc_eeprom_checksum_X550(hw); + if (status < 0) + return status; + + checksum = (u16)(status & 0xffff); + + status = ixgbe_write_ee_hostif_X550(hw, IXGBE_EEPROM_CHECKSUM, + checksum); + if (status) + return status; + + status = ixgbe_update_flash_X550(hw); + + return status; +} + +/** ixgbe_write_ee_hostif_buffer_X550 - Write EEPROM word(s) using hostif + * @hw: pointer to hardware structure + * @offset: offset of word in the EEPROM to write + * @words: number of words + * @data: word(s) write to the EEPROM + * + * + * Write a 16 bit word(s) to the EEPROM using the hostif. + **/ +static s32 ixgbe_write_ee_hostif_buffer_X550(struct ixgbe_hw *hw, + u16 offset, u16 words, + u16 *data) +{ + s32 status = 0; + u32 i = 0; + + /* Take semaphore for the entire operation. */ + status = hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM); + if (status) { + hw_dbg(hw, "EEPROM write buffer - semaphore failed\n"); + return status; + } + + for (i = 0; i < words; i++) { + status = ixgbe_write_ee_hostif_data_X550(hw, offset + i, + data[i]); + if (status) { + hw_dbg(hw, "Eeprom buffered write failed\n"); + break; + } + } + + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM); + + return status; +} + +/** ixgbe_write_iosf_sb_reg_x550 - Writes a value to specified register of the + * IOSF device + * + * @hw: pointer to hardware structure + * @reg_addr: 32 bit PHY register to write + * @device_type: 3 bit device type + * @data: Data to write to the register + **/ +static s32 ixgbe_write_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u32 data) +{ + u32 gssr = IXGBE_GSSR_PHY1_SM | IXGBE_GSSR_PHY0_SM; + u32 command, error; + s32 ret; + + ret = hw->mac.ops.acquire_swfw_sync(hw, gssr); + if (ret) + return ret; + + ret = ixgbe_iosf_wait(hw, NULL); + if (ret) + goto out; + + command = ((reg_addr << IXGBE_SB_IOSF_CTRL_ADDR_SHIFT) | + (device_type << IXGBE_SB_IOSF_CTRL_TARGET_SELECT_SHIFT)); + + /* Write IOSF control register */ + IXGBE_WRITE_REG(hw, IXGBE_SB_IOSF_INDIRECT_CTRL, command); + + /* Write IOSF data register */ + IXGBE_WRITE_REG(hw, IXGBE_SB_IOSF_INDIRECT_DATA, data); + + ret = ixgbe_iosf_wait(hw, &command); + + if ((command & IXGBE_SB_IOSF_CTRL_RESP_STAT_MASK) != 0) { + error = (command & IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK) >> + IXGBE_SB_IOSF_CTRL_CMPL_ERR_SHIFT; + hw_dbg(hw, "Failed to write, error %x\n", error); + return IXGBE_ERR_PHY; + } + +out: + hw->mac.ops.release_swfw_sync(hw, gssr); + return ret; +} + +/** + * ixgbe_setup_ixfi_x550em_x - MAC specific iXFI configuration + * @hw: pointer to hardware structure + * + * iXfI configuration needed for ixgbe_mac_X550EM_x devices. + **/ +static s32 ixgbe_setup_ixfi_x550em_x(struct ixgbe_hw *hw) +{ + s32 status; + u32 reg_val; + + /* Disable training protocol FSM. */ + status = ixgbe_read_iosf_sb_reg_x550(hw, + IXGBE_KRM_RX_TRN_LINKUP_CTRL(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); + if (status) + return status; + + reg_val |= IXGBE_KRM_RX_TRN_LINKUP_CTRL_CONV_WO_PROTOCOL; + status = ixgbe_write_iosf_sb_reg_x550(hw, + IXGBE_KRM_RX_TRN_LINKUP_CTRL(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); + if (status) + return status; + + /* Disable Flex from training TXFFE. */ + status = ixgbe_read_iosf_sb_reg_x550(hw, + IXGBE_KRM_DSP_TXFFE_STATE_4(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); + if (status) + return status; + + reg_val &= ~IXGBE_KRM_DSP_TXFFE_STATE_C0_EN; + reg_val &= ~IXGBE_KRM_DSP_TXFFE_STATE_CP1_CN1_EN; + reg_val &= ~IXGBE_KRM_DSP_TXFFE_STATE_CO_ADAPT_EN; + status = ixgbe_write_iosf_sb_reg_x550(hw, + IXGBE_KRM_DSP_TXFFE_STATE_4(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); + if (status) + return status; + + status = ixgbe_read_iosf_sb_reg_x550(hw, + IXGBE_KRM_DSP_TXFFE_STATE_5(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); + if (status) + return status; + + reg_val &= ~IXGBE_KRM_DSP_TXFFE_STATE_C0_EN; + reg_val &= ~IXGBE_KRM_DSP_TXFFE_STATE_CP1_CN1_EN; + reg_val &= ~IXGBE_KRM_DSP_TXFFE_STATE_CO_ADAPT_EN; + status = ixgbe_write_iosf_sb_reg_x550(hw, + IXGBE_KRM_DSP_TXFFE_STATE_5(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); + if (status) + return status; + + /* Enable override for coefficients. */ + status = ixgbe_read_iosf_sb_reg_x550(hw, + IXGBE_KRM_TX_COEFF_CTRL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); + if (status) + return status; + + reg_val |= IXGBE_KRM_TX_COEFF_CTRL_1_OVRRD_EN; + reg_val |= IXGBE_KRM_TX_COEFF_CTRL_1_CZERO_EN; + reg_val |= IXGBE_KRM_TX_COEFF_CTRL_1_CPLUS1_OVRRD_EN; + reg_val |= IXGBE_KRM_TX_COEFF_CTRL_1_CMINUS1_OVRRD_EN; + status = ixgbe_write_iosf_sb_reg_x550(hw, + IXGBE_KRM_TX_COEFF_CTRL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); + return status; +} + +/** + * ixgbe_restart_an_internal_phy_x550em - restart autonegotiation for the + * internal PHY + * @hw: pointer to hardware structure + **/ +static s32 ixgbe_restart_an_internal_phy_x550em(struct ixgbe_hw *hw) +{ + s32 status; + u32 link_ctrl; + + /* Restart auto-negotiation. */ + status = hw->mac.ops.read_iosf_sb_reg(hw, + IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &link_ctrl); + + if (status) { + hw_dbg(hw, "Auto-negotiation did not complete\n"); + return status; + } + + link_ctrl |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_RESTART; + status = hw->mac.ops.write_iosf_sb_reg(hw, + IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, link_ctrl); + + if (hw->mac.type == ixgbe_mac_x550em_a) { + u32 flx_mask_st20; + + /* Indicate to FW that AN restart has been asserted */ + status = hw->mac.ops.read_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &flx_mask_st20); + + if (status) { + hw_dbg(hw, "Auto-negotiation did not complete\n"); + return status; + } + + flx_mask_st20 |= IXGBE_KRM_PMD_FLX_MASK_ST20_FW_AN_RESTART; + status = hw->mac.ops.write_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, flx_mask_st20); + } + + return status; +} + +/** ixgbe_setup_ixfi_x550em - Configure the KR PHY for iXFI mode. + * @hw: pointer to hardware structure + * @speed: the link speed to force + * + * Configures the integrated KR PHY to use iXFI mode. Used to connect an + * internal and external PHY at a specific speed, without autonegotiation. + **/ +static s32 ixgbe_setup_ixfi_x550em(struct ixgbe_hw *hw, ixgbe_link_speed *speed) +{ + struct ixgbe_mac_info *mac = &hw->mac; + s32 status; + u32 reg_val; + + /* iXFI is only supported with X552 */ + if (mac->type != ixgbe_mac_X550EM_x) + return IXGBE_ERR_LINK_SETUP; + + /* Disable AN and force speed to 10G Serial. */ + status = ixgbe_read_iosf_sb_reg_x550(hw, + IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); + if (status) + return status; + + reg_val &= ~IXGBE_KRM_LINK_CTRL_1_TETH_AN_ENABLE; + reg_val &= ~IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_MASK; + + /* Select forced link speed for internal PHY. */ + switch (*speed) { + case IXGBE_LINK_SPEED_10GB_FULL: + reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_10G; + break; + case IXGBE_LINK_SPEED_1GB_FULL: + reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_1G; + break; + default: + /* Other link speeds are not supported by internal KR PHY. */ + return IXGBE_ERR_LINK_SETUP; + } + + status = ixgbe_write_iosf_sb_reg_x550(hw, + IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); + if (status) + return status; + + /* Additional configuration needed for x550em_x */ + if (hw->mac.type == ixgbe_mac_X550EM_x) { + status = ixgbe_setup_ixfi_x550em_x(hw); + if (status) + return status; + } + + /* Toggle port SW reset by AN reset. */ + status = ixgbe_restart_an_internal_phy_x550em(hw); + + return status; +} + +/** + * ixgbe_supported_sfp_modules_X550em - Check if SFP module type is supported + * @hw: pointer to hardware structure + * @linear: true if SFP module is linear + */ +static s32 ixgbe_supported_sfp_modules_X550em(struct ixgbe_hw *hw, bool *linear) +{ + switch (hw->phy.sfp_type) { + case ixgbe_sfp_type_not_present: + return IXGBE_ERR_SFP_NOT_PRESENT; + case ixgbe_sfp_type_da_cu_core0: + case ixgbe_sfp_type_da_cu_core1: + *linear = true; + break; + case ixgbe_sfp_type_srlr_core0: + case ixgbe_sfp_type_srlr_core1: + case ixgbe_sfp_type_da_act_lmt_core0: + case ixgbe_sfp_type_da_act_lmt_core1: + case ixgbe_sfp_type_1g_sx_core0: + case ixgbe_sfp_type_1g_sx_core1: + case ixgbe_sfp_type_1g_lx_core0: + case ixgbe_sfp_type_1g_lx_core1: + *linear = false; + break; + case ixgbe_sfp_type_unknown: + case ixgbe_sfp_type_1g_cu_core0: + case ixgbe_sfp_type_1g_cu_core1: + default: + return IXGBE_ERR_SFP_NOT_SUPPORTED; + } + + return 0; +} + +/** + * ixgbe_setup_mac_link_sfp_x550em - Configure the KR PHY for SFP. + * @hw: pointer to hardware structure + * @speed: the link speed to force + * @autoneg_wait_to_complete: unused + * + * Configures the extern PHY and the integrated KR PHY for SFP support. + */ +static s32 +ixgbe_setup_mac_link_sfp_x550em(struct ixgbe_hw *hw, + ixgbe_link_speed speed, + __always_unused bool autoneg_wait_to_complete) +{ + s32 status; + u16 reg_slice, reg_val; + bool setup_linear = false; + + /* Check if SFP module is supported and linear */ + status = ixgbe_supported_sfp_modules_X550em(hw, &setup_linear); + + /* If no SFP module present, then return success. Return success since + * there is no reason to configure CS4227 and SFP not present error is + * not accepted in the setup MAC link flow. + */ + if (status == IXGBE_ERR_SFP_NOT_PRESENT) + return 0; + + if (status) + return status; + + /* Configure internal PHY for KR/KX. */ + ixgbe_setup_kr_speed_x550em(hw, speed); + + /* Configure CS4227 LINE side to proper mode. */ + reg_slice = IXGBE_CS4227_LINE_SPARE24_LSB + (hw->bus.lan_id << 12); + if (setup_linear) + reg_val = (IXGBE_CS4227_EDC_MODE_CX1 << 1) | 0x1; + else + reg_val = (IXGBE_CS4227_EDC_MODE_SR << 1) | 0x1; + + status = hw->link.ops.write_link(hw, hw->link.addr, reg_slice, + reg_val); + + return status; +} + +/** + * ixgbe_setup_sfi_x550a - Configure the internal PHY for native SFI mode + * @hw: pointer to hardware structure + * @speed: the link speed to force + * + * Configures the integrated PHY for native SFI mode. Used to connect the + * internal PHY directly to an SFP cage, without autonegotiation. + **/ +static s32 ixgbe_setup_sfi_x550a(struct ixgbe_hw *hw, ixgbe_link_speed *speed) +{ + struct ixgbe_mac_info *mac = &hw->mac; + s32 status; + u32 reg_val; + + /* Disable all AN and force speed to 10G Serial. */ + status = mac->ops.read_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); + if (status) + return status; + + reg_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_AN_EN; + reg_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_AN37_EN; + reg_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_SGMII_EN; + reg_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_MASK; + + /* Select forced link speed for internal PHY. */ + switch (*speed) { + case IXGBE_LINK_SPEED_10GB_FULL: + reg_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_10G; + break; + case IXGBE_LINK_SPEED_1GB_FULL: + reg_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_1G; + break; + default: + /* Other link speeds are not supported by internal PHY. */ + return IXGBE_ERR_LINK_SETUP; + } + + status = mac->ops.write_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); + + /* Toggle port SW reset by AN reset. */ + status = ixgbe_restart_an_internal_phy_x550em(hw); + + return status; +} + +/** + * ixgbe_setup_mac_link_sfp_n - Setup internal PHY for native SFP + * @hw: pointer to hardware structure + * @speed: link speed + * @autoneg_wait_to_complete: unused + * + * Configure the the integrated PHY for native SFP support. + */ +static s32 +ixgbe_setup_mac_link_sfp_n(struct ixgbe_hw *hw, ixgbe_link_speed speed, + __always_unused bool autoneg_wait_to_complete) +{ + bool setup_linear = false; + u32 reg_phy_int; + s32 ret_val; + + /* Check if SFP module is supported and linear */ + ret_val = ixgbe_supported_sfp_modules_X550em(hw, &setup_linear); + + /* If no SFP module present, then return success. Return success since + * SFP not present error is not excepted in the setup MAC link flow. + */ + if (ret_val == IXGBE_ERR_SFP_NOT_PRESENT) + return 0; + + if (ret_val) + return ret_val; + + /* Configure internal PHY for native SFI based on module type */ + ret_val = hw->mac.ops.read_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, ®_phy_int); + if (ret_val) + return ret_val; + + reg_phy_int &= IXGBE_KRM_PMD_FLX_MASK_ST20_SFI_10G_DA; + if (!setup_linear) + reg_phy_int |= IXGBE_KRM_PMD_FLX_MASK_ST20_SFI_10G_SR; + + ret_val = hw->mac.ops.write_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, reg_phy_int); + if (ret_val) + return ret_val; + + /* Setup SFI internal link. */ + return ixgbe_setup_sfi_x550a(hw, &speed); +} + +/** + * ixgbe_setup_mac_link_sfp_x550a - Setup internal PHY for SFP + * @hw: pointer to hardware structure + * @speed: link speed + * @autoneg_wait_to_complete: unused + * + * Configure the the integrated PHY for SFP support. + */ +static s32 +ixgbe_setup_mac_link_sfp_x550a(struct ixgbe_hw *hw, ixgbe_link_speed speed, + __always_unused bool autoneg_wait_to_complete) +{ + u32 reg_slice, slice_offset; + bool setup_linear = false; + u16 reg_phy_ext; + s32 ret_val; + + /* Check if SFP module is supported and linear */ + ret_val = ixgbe_supported_sfp_modules_X550em(hw, &setup_linear); + + /* If no SFP module present, then return success. Return success since + * SFP not present error is not excepted in the setup MAC link flow. + */ + if (ret_val == IXGBE_ERR_SFP_NOT_PRESENT) + return 0; + + if (ret_val) + return ret_val; + + /* Configure internal PHY for KR/KX. */ + ixgbe_setup_kr_speed_x550em(hw, speed); + + if (hw->phy.mdio.prtad == MDIO_PRTAD_NONE) + return IXGBE_ERR_PHY_ADDR_INVALID; + + /* Get external PHY SKU id */ + ret_val = hw->phy.ops.read_reg(hw, IXGBE_CS4227_EFUSE_PDF_SKU, + IXGBE_MDIO_ZERO_DEV_TYPE, ®_phy_ext); + if (ret_val) + return ret_val; + + /* When configuring quad port CS4223, the MAC instance is part + * of the slice offset. + */ + if (reg_phy_ext == IXGBE_CS4223_SKU_ID) + slice_offset = (hw->bus.lan_id + + (hw->bus.instance_id << 1)) << 12; + else + slice_offset = hw->bus.lan_id << 12; + + /* Configure CS4227/CS4223 LINE side to proper mode. */ + reg_slice = IXGBE_CS4227_LINE_SPARE24_LSB + slice_offset; + + ret_val = hw->phy.ops.read_reg(hw, reg_slice, + IXGBE_MDIO_ZERO_DEV_TYPE, ®_phy_ext); + if (ret_val) + return ret_val; + + reg_phy_ext &= ~((IXGBE_CS4227_EDC_MODE_CX1 << 1) | + (IXGBE_CS4227_EDC_MODE_SR << 1)); + + if (setup_linear) + reg_phy_ext |= (IXGBE_CS4227_EDC_MODE_CX1 << 1) | 1; + else + reg_phy_ext |= (IXGBE_CS4227_EDC_MODE_SR << 1) | 1; + + ret_val = hw->phy.ops.write_reg(hw, reg_slice, + IXGBE_MDIO_ZERO_DEV_TYPE, reg_phy_ext); + if (ret_val) + return ret_val; + + /* Flush previous write with a read */ + return hw->phy.ops.read_reg(hw, reg_slice, + IXGBE_MDIO_ZERO_DEV_TYPE, ®_phy_ext); +} + +/** + * ixgbe_setup_mac_link_t_X550em - Sets the auto advertised link speed + * @hw: pointer to hardware structure + * @speed: new link speed + * @autoneg_wait: true when waiting for completion is needed + * + * Setup internal/external PHY link speed based on link speed, then set + * external PHY auto advertised link speed. + * + * Returns error status for any failure + **/ +static s32 ixgbe_setup_mac_link_t_X550em(struct ixgbe_hw *hw, + ixgbe_link_speed speed, + bool autoneg_wait) +{ + s32 status; + ixgbe_link_speed force_speed; + + /* Setup internal/external PHY link speed to iXFI (10G), unless + * only 1G is auto advertised then setup KX link. + */ + if (speed & IXGBE_LINK_SPEED_10GB_FULL) + force_speed = IXGBE_LINK_SPEED_10GB_FULL; + else + force_speed = IXGBE_LINK_SPEED_1GB_FULL; + + /* If X552 and internal link mode is XFI, then setup XFI internal link. + */ + if (hw->mac.type == ixgbe_mac_X550EM_x && + !(hw->phy.nw_mng_if_sel & IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE)) { + status = ixgbe_setup_ixfi_x550em(hw, &force_speed); + + if (status) + return status; + } + + return hw->phy.ops.setup_link_speed(hw, speed, autoneg_wait); +} + +/** ixgbe_check_link_t_X550em - Determine link and speed status + * @hw: pointer to hardware structure + * @speed: pointer to link speed + * @link_up: true when link is up + * @link_up_wait_to_complete: bool used to wait for link up or not + * + * Check that both the MAC and X557 external PHY have link. + **/ +static s32 ixgbe_check_link_t_X550em(struct ixgbe_hw *hw, + ixgbe_link_speed *speed, + bool *link_up, + bool link_up_wait_to_complete) +{ + u32 status; + u16 i, autoneg_status; + + if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_copper) + return IXGBE_ERR_CONFIG; + + status = ixgbe_check_mac_link_generic(hw, speed, link_up, + link_up_wait_to_complete); + + /* If check link fails or MAC link is not up, then return */ + if (status || !(*link_up)) + return status; + + /* MAC link is up, so check external PHY link. + * Link status is latching low, and can only be used to detect link + * drop, and not the current status of the link without performing + * back-to-back reads. + */ + for (i = 0; i < 2; i++) { + status = hw->phy.ops.read_reg(hw, MDIO_STAT1, MDIO_MMD_AN, + &autoneg_status); + + if (status) + return status; + } + + /* If external PHY link is not up, then indicate link not up */ + if (!(autoneg_status & IXGBE_MDIO_AUTO_NEG_LINK_STATUS)) + *link_up = false; + + return 0; +} + +/** + * ixgbe_setup_sgmii - Set up link for sgmii + * @hw: pointer to hardware structure + * @speed: unused + * @autoneg_wait_to_complete: unused + */ +static s32 +ixgbe_setup_sgmii(struct ixgbe_hw *hw, __always_unused ixgbe_link_speed speed, + __always_unused bool autoneg_wait_to_complete) +{ + struct ixgbe_mac_info *mac = &hw->mac; + u32 lval, sval, flx_val; + s32 rc; + + rc = mac->ops.read_iosf_sb_reg(hw, + IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &lval); + if (rc) + return rc; + + lval &= ~IXGBE_KRM_LINK_CTRL_1_TETH_AN_ENABLE; + lval &= ~IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_MASK; + lval |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_SGMII_EN; + lval |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_CLAUSE_37_EN; + lval |= IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_1G; + rc = mac->ops.write_iosf_sb_reg(hw, + IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, lval); + if (rc) + return rc; + + rc = mac->ops.read_iosf_sb_reg(hw, + IXGBE_KRM_SGMII_CTRL(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &sval); + if (rc) + return rc; + + sval |= IXGBE_KRM_SGMII_CTRL_MAC_TAR_FORCE_10_D; + sval |= IXGBE_KRM_SGMII_CTRL_MAC_TAR_FORCE_100_D; + rc = mac->ops.write_iosf_sb_reg(hw, + IXGBE_KRM_SGMII_CTRL(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, sval); + if (rc) + return rc; + + rc = mac->ops.read_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &flx_val); + if (rc) + return rc; + + rc = mac->ops.read_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &flx_val); + if (rc) + return rc; + + flx_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_MASK; + flx_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_1G; + flx_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_AN_EN; + flx_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_SGMII_EN; + flx_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_AN37_EN; + + rc = mac->ops.write_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, flx_val); + if (rc) + return rc; + + rc = ixgbe_restart_an_internal_phy_x550em(hw); + return rc; +} + +/** + * ixgbe_setup_sgmii_fw - Set up link for sgmii with firmware-controlled PHYs + * @hw: pointer to hardware structure + * @speed: the link speed to force + * @autoneg_wait: true when waiting for completion is needed + */ +static s32 ixgbe_setup_sgmii_fw(struct ixgbe_hw *hw, ixgbe_link_speed speed, + bool autoneg_wait) +{ + struct ixgbe_mac_info *mac = &hw->mac; + u32 lval, sval, flx_val; + s32 rc; + + rc = mac->ops.read_iosf_sb_reg(hw, + IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &lval); + if (rc) + return rc; + + lval &= ~IXGBE_KRM_LINK_CTRL_1_TETH_AN_ENABLE; + lval &= ~IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_MASK; + lval |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_SGMII_EN; + lval |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_CLAUSE_37_EN; + lval &= ~IXGBE_KRM_LINK_CTRL_1_TETH_FORCE_SPEED_1G; + rc = mac->ops.write_iosf_sb_reg(hw, + IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, lval); + if (rc) + return rc; + + rc = mac->ops.read_iosf_sb_reg(hw, + IXGBE_KRM_SGMII_CTRL(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &sval); + if (rc) + return rc; + + sval &= ~IXGBE_KRM_SGMII_CTRL_MAC_TAR_FORCE_10_D; + sval &= ~IXGBE_KRM_SGMII_CTRL_MAC_TAR_FORCE_100_D; + rc = mac->ops.write_iosf_sb_reg(hw, + IXGBE_KRM_SGMII_CTRL(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, sval); + if (rc) + return rc; + + rc = mac->ops.write_iosf_sb_reg(hw, + IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, lval); + if (rc) + return rc; + + rc = mac->ops.read_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &flx_val); + if (rc) + return rc; + + flx_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_MASK; + flx_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_AN; + flx_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_AN_EN; + flx_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_SGMII_EN; + flx_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_AN37_EN; + + rc = mac->ops.write_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, flx_val); + if (rc) + return rc; + + ixgbe_restart_an_internal_phy_x550em(hw); + + return hw->phy.ops.setup_link_speed(hw, speed, autoneg_wait); +} + +/** + * ixgbe_fc_autoneg_sgmii_x550em_a - Enable flow control IEEE clause 37 + * @hw: pointer to hardware structure + * + * Enable flow control according to IEEE clause 37. + */ +static void ixgbe_fc_autoneg_sgmii_x550em_a(struct ixgbe_hw *hw) +{ + s32 status = IXGBE_ERR_FC_NOT_NEGOTIATED; + u32 info[FW_PHY_ACT_DATA_COUNT] = { 0 }; + ixgbe_link_speed speed; + bool link_up; + + /* AN should have completed when the cable was plugged in. + * Look for reasons to bail out. Bail out if: + * - FC autoneg is disabled, or if + * - link is not up. + */ + if (hw->fc.disable_fc_autoneg) + goto out; + + hw->mac.ops.check_link(hw, &speed, &link_up, false); + if (!link_up) + goto out; + + /* Check if auto-negotiation has completed */ + status = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_GET_LINK_INFO, &info); + if (status || !(info[0] & FW_PHY_ACT_GET_LINK_INFO_AN_COMPLETE)) { + status = IXGBE_ERR_FC_NOT_NEGOTIATED; + goto out; + } + + /* Negotiate the flow control */ + status = ixgbe_negotiate_fc(hw, info[0], info[0], + FW_PHY_ACT_GET_LINK_INFO_FC_RX, + FW_PHY_ACT_GET_LINK_INFO_FC_TX, + FW_PHY_ACT_GET_LINK_INFO_LP_FC_RX, + FW_PHY_ACT_GET_LINK_INFO_LP_FC_TX); + +out: + if (!status) { + hw->fc.fc_was_autonegged = true; + } else { + hw->fc.fc_was_autonegged = false; + hw->fc.current_mode = hw->fc.requested_mode; + } +} + +/** ixgbe_init_mac_link_ops_X550em_a - Init mac link function pointers + * @hw: pointer to hardware structure + **/ +static void ixgbe_init_mac_link_ops_X550em_a(struct ixgbe_hw *hw) +{ + struct ixgbe_mac_info *mac = &hw->mac; + + switch (mac->ops.get_media_type(hw)) { + case ixgbe_media_type_fiber: + mac->ops.setup_fc = NULL; + mac->ops.fc_autoneg = ixgbe_fc_autoneg_fiber_x550em_a; + break; + case ixgbe_media_type_copper: + if (hw->device_id != IXGBE_DEV_ID_X550EM_A_1G_T && + hw->device_id != IXGBE_DEV_ID_X550EM_A_1G_T_L) { + mac->ops.setup_link = ixgbe_setup_mac_link_t_X550em; + break; + } + mac->ops.fc_autoneg = ixgbe_fc_autoneg_sgmii_x550em_a; + mac->ops.setup_fc = ixgbe_fc_autoneg_fw; + mac->ops.setup_link = ixgbe_setup_sgmii_fw; + mac->ops.check_link = ixgbe_check_mac_link_generic; + break; + case ixgbe_media_type_backplane: + mac->ops.fc_autoneg = ixgbe_fc_autoneg_backplane_x550em_a; + mac->ops.setup_fc = ixgbe_setup_fc_backplane_x550em_a; + break; + default: + break; + } +} + +/** ixgbe_init_mac_link_ops_X550em - init mac link function pointers + * @hw: pointer to hardware structure + **/ +static void ixgbe_init_mac_link_ops_X550em(struct ixgbe_hw *hw) +{ + struct ixgbe_mac_info *mac = &hw->mac; + + mac->ops.setup_fc = ixgbe_setup_fc_x550em; + + switch (mac->ops.get_media_type(hw)) { + case ixgbe_media_type_fiber: + /* CS4227 does not support autoneg, so disable the laser control + * functions for SFP+ fiber + */ + mac->ops.disable_tx_laser = NULL; + mac->ops.enable_tx_laser = NULL; + mac->ops.flap_tx_laser = NULL; + mac->ops.setup_link = ixgbe_setup_mac_link_multispeed_fiber; + switch (hw->device_id) { + case IXGBE_DEV_ID_X550EM_A_SFP_N: + mac->ops.setup_mac_link = ixgbe_setup_mac_link_sfp_n; + break; + case IXGBE_DEV_ID_X550EM_A_SFP: + mac->ops.setup_mac_link = + ixgbe_setup_mac_link_sfp_x550a; + break; + default: + mac->ops.setup_mac_link = + ixgbe_setup_mac_link_sfp_x550em; + break; + } + mac->ops.set_rate_select_speed = + ixgbe_set_soft_rate_select_speed; + break; + case ixgbe_media_type_copper: + if (hw->device_id == IXGBE_DEV_ID_X550EM_X_1G_T) + break; + mac->ops.setup_link = ixgbe_setup_mac_link_t_X550em; + mac->ops.setup_fc = ixgbe_setup_fc_generic; + mac->ops.check_link = ixgbe_check_link_t_X550em; + break; + case ixgbe_media_type_backplane: + if (hw->device_id == IXGBE_DEV_ID_X550EM_A_SGMII || + hw->device_id == IXGBE_DEV_ID_X550EM_A_SGMII_L) + mac->ops.setup_link = ixgbe_setup_sgmii; + break; + default: + break; + } + + /* Additional modification for X550em_a devices */ + if (hw->mac.type == ixgbe_mac_x550em_a) + ixgbe_init_mac_link_ops_X550em_a(hw); +} + +/** ixgbe_setup_sfp_modules_X550em - Setup SFP module + * @hw: pointer to hardware structure + */ +static s32 ixgbe_setup_sfp_modules_X550em(struct ixgbe_hw *hw) +{ + s32 status; + bool linear; + + /* Check if SFP module is supported */ + status = ixgbe_supported_sfp_modules_X550em(hw, &linear); + if (status) + return status; + + ixgbe_init_mac_link_ops_X550em(hw); + hw->phy.ops.reset = NULL; + + return 0; +} + +/** ixgbe_get_link_capabilities_x550em - Determines link capabilities + * @hw: pointer to hardware structure + * @speed: pointer to link speed + * @autoneg: true when autoneg or autotry is enabled + **/ +static s32 ixgbe_get_link_capabilities_X550em(struct ixgbe_hw *hw, + ixgbe_link_speed *speed, + bool *autoneg) +{ + if (hw->phy.type == ixgbe_phy_fw) { + *autoneg = true; + *speed = hw->phy.speeds_supported; + return 0; + } + + /* SFP */ + if (hw->phy.media_type == ixgbe_media_type_fiber) { + /* CS4227 SFP must not enable auto-negotiation */ + *autoneg = false; + + if (hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core1) { + *speed = IXGBE_LINK_SPEED_1GB_FULL; + return 0; + } + + /* Link capabilities are based on SFP */ + if (hw->phy.multispeed_fiber) + *speed = IXGBE_LINK_SPEED_10GB_FULL | + IXGBE_LINK_SPEED_1GB_FULL; + else + *speed = IXGBE_LINK_SPEED_10GB_FULL; + } else { + switch (hw->phy.type) { + case ixgbe_phy_x550em_kx4: + *speed = IXGBE_LINK_SPEED_1GB_FULL | + IXGBE_LINK_SPEED_2_5GB_FULL | + IXGBE_LINK_SPEED_10GB_FULL; + break; + case ixgbe_phy_x550em_xfi: + *speed = IXGBE_LINK_SPEED_1GB_FULL | + IXGBE_LINK_SPEED_10GB_FULL; + break; + case ixgbe_phy_ext_1g_t: + case ixgbe_phy_sgmii: + *speed = IXGBE_LINK_SPEED_1GB_FULL; + break; + case ixgbe_phy_x550em_kr: + if (hw->mac.type == ixgbe_mac_x550em_a) { + /* check different backplane modes */ + if (hw->phy.nw_mng_if_sel & + IXGBE_NW_MNG_IF_SEL_PHY_SPEED_2_5G) { + *speed = IXGBE_LINK_SPEED_2_5GB_FULL; + break; + } else if (hw->device_id == + IXGBE_DEV_ID_X550EM_A_KR_L) { + *speed = IXGBE_LINK_SPEED_1GB_FULL; + break; + } + } + fallthrough; + default: + *speed = IXGBE_LINK_SPEED_10GB_FULL | + IXGBE_LINK_SPEED_1GB_FULL; + break; + } + *autoneg = true; + } + return 0; +} + +/** + * ixgbe_get_lasi_ext_t_x550em - Determime external Base T PHY interrupt cause + * @hw: pointer to hardware structure + * @lsc: pointer to boolean flag which indicates whether external Base T + * PHY interrupt is lsc + * + * Determime if external Base T PHY interrupt cause is high temperature + * failure alarm or link status change. + * + * Return IXGBE_ERR_OVERTEMP if interrupt is high temperature + * failure alarm, else return PHY access status. + **/ +static s32 ixgbe_get_lasi_ext_t_x550em(struct ixgbe_hw *hw, bool *lsc) +{ + u32 status; + u16 reg; + + *lsc = false; + + /* Vendor alarm triggered */ + status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_CHIP_STD_INT_FLAG, + MDIO_MMD_VEND1, + ®); + + if (status || !(reg & IXGBE_MDIO_GLOBAL_VEN_ALM_INT_EN)) + return status; + + /* Vendor Auto-Neg alarm triggered or Global alarm 1 triggered */ + status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_INT_CHIP_VEN_FLAG, + MDIO_MMD_VEND1, + ®); + + if (status || !(reg & (IXGBE_MDIO_GLOBAL_AN_VEN_ALM_INT_EN | + IXGBE_MDIO_GLOBAL_ALARM_1_INT))) + return status; + + /* Global alarm triggered */ + status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_ALARM_1, + MDIO_MMD_VEND1, + ®); + + if (status) + return status; + + /* If high temperature failure, then return over temp error and exit */ + if (reg & IXGBE_MDIO_GLOBAL_ALM_1_HI_TMP_FAIL) { + /* power down the PHY in case the PHY FW didn't already */ + ixgbe_set_copper_phy_power(hw, false); + return IXGBE_ERR_OVERTEMP; + } + if (reg & IXGBE_MDIO_GLOBAL_ALM_1_DEV_FAULT) { + /* device fault alarm triggered */ + status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_FAULT_MSG, + MDIO_MMD_VEND1, + ®); + if (status) + return status; + + /* if device fault was due to high temp alarm handle and exit */ + if (reg == IXGBE_MDIO_GLOBAL_FAULT_MSG_HI_TMP) { + /* power down the PHY in case the PHY FW didn't */ + ixgbe_set_copper_phy_power(hw, false); + return IXGBE_ERR_OVERTEMP; + } + } + + /* Vendor alarm 2 triggered */ + status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_CHIP_STD_INT_FLAG, + MDIO_MMD_AN, ®); + + if (status || !(reg & IXGBE_MDIO_GLOBAL_STD_ALM2_INT)) + return status; + + /* link connect/disconnect event occurred */ + status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_VENDOR_TX_ALARM2, + MDIO_MMD_AN, ®); + + if (status) + return status; + + /* Indicate LSC */ + if (reg & IXGBE_MDIO_AUTO_NEG_VEN_LSC) + *lsc = true; + + return 0; +} + +/** + * ixgbe_enable_lasi_ext_t_x550em - Enable external Base T PHY interrupts + * @hw: pointer to hardware structure + * + * Enable link status change and temperature failure alarm for the external + * Base T PHY + * + * Returns PHY access status + **/ +static s32 ixgbe_enable_lasi_ext_t_x550em(struct ixgbe_hw *hw) +{ + u32 status; + u16 reg; + bool lsc; + + /* Clear interrupt flags */ + status = ixgbe_get_lasi_ext_t_x550em(hw, &lsc); + + /* Enable link status change alarm */ + + /* Enable the LASI interrupts on X552 devices to receive notifications + * of the link configurations of the external PHY and correspondingly + * support the configuration of the internal iXFI link, since iXFI does + * not support auto-negotiation. This is not required for X553 devices + * having KR support, which performs auto-negotiations and which is used + * as the internal link to the external PHY. Hence adding a check here + * to avoid enabling LASI interrupts for X553 devices. + */ + if (hw->mac.type != ixgbe_mac_x550em_a) { + status = hw->phy.ops.read_reg(hw, + IXGBE_MDIO_PMA_TX_VEN_LASI_INT_MASK, + MDIO_MMD_AN, ®); + if (status) + return status; + + reg |= IXGBE_MDIO_PMA_TX_VEN_LASI_INT_EN; + + status = hw->phy.ops.write_reg(hw, + IXGBE_MDIO_PMA_TX_VEN_LASI_INT_MASK, + MDIO_MMD_AN, reg); + if (status) + return status; + } + + /* Enable high temperature failure and global fault alarms */ + status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_INT_MASK, + MDIO_MMD_VEND1, + ®); + if (status) + return status; + + reg |= (IXGBE_MDIO_GLOBAL_INT_HI_TEMP_EN | + IXGBE_MDIO_GLOBAL_INT_DEV_FAULT_EN); + + status = hw->phy.ops.write_reg(hw, IXGBE_MDIO_GLOBAL_INT_MASK, + MDIO_MMD_VEND1, + reg); + if (status) + return status; + + /* Enable vendor Auto-Neg alarm and Global Interrupt Mask 1 alarm */ + status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_INT_CHIP_VEN_MASK, + MDIO_MMD_VEND1, + ®); + if (status) + return status; + + reg |= (IXGBE_MDIO_GLOBAL_AN_VEN_ALM_INT_EN | + IXGBE_MDIO_GLOBAL_ALARM_1_INT); + + status = hw->phy.ops.write_reg(hw, IXGBE_MDIO_GLOBAL_INT_CHIP_VEN_MASK, + MDIO_MMD_VEND1, + reg); + if (status) + return status; + + /* Enable chip-wide vendor alarm */ + status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_GLOBAL_INT_CHIP_STD_MASK, + MDIO_MMD_VEND1, + ®); + if (status) + return status; + + reg |= IXGBE_MDIO_GLOBAL_VEN_ALM_INT_EN; + + status = hw->phy.ops.write_reg(hw, IXGBE_MDIO_GLOBAL_INT_CHIP_STD_MASK, + MDIO_MMD_VEND1, + reg); + + return status; +} + +/** + * ixgbe_handle_lasi_ext_t_x550em - Handle external Base T PHY interrupt + * @hw: pointer to hardware structure + * + * Handle external Base T PHY interrupt. If high temperature + * failure alarm then return error, else if link status change + * then setup internal/external PHY link + * + * Return IXGBE_ERR_OVERTEMP if interrupt is high temperature + * failure alarm, else return PHY access status. + **/ +static s32 ixgbe_handle_lasi_ext_t_x550em(struct ixgbe_hw *hw) +{ + struct ixgbe_phy_info *phy = &hw->phy; + bool lsc; + u32 status; + + status = ixgbe_get_lasi_ext_t_x550em(hw, &lsc); + if (status) + return status; + + if (lsc && phy->ops.setup_internal_link) + return phy->ops.setup_internal_link(hw); + + return 0; +} + +/** + * ixgbe_setup_kr_speed_x550em - Configure the KR PHY for link speed. + * @hw: pointer to hardware structure + * @speed: link speed + * + * Configures the integrated KR PHY. + **/ +static s32 ixgbe_setup_kr_speed_x550em(struct ixgbe_hw *hw, + ixgbe_link_speed speed) +{ + s32 status; + u32 reg_val; + + status = hw->mac.ops.read_iosf_sb_reg(hw, + IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); + if (status) + return status; + + reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_ENABLE; + reg_val &= ~(IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_KR | + IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_KX); + + /* Advertise 10G support. */ + if (speed & IXGBE_LINK_SPEED_10GB_FULL) + reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_KR; + + /* Advertise 1G support. */ + if (speed & IXGBE_LINK_SPEED_1GB_FULL) + reg_val |= IXGBE_KRM_LINK_CTRL_1_TETH_AN_CAP_KX; + + status = hw->mac.ops.write_iosf_sb_reg(hw, + IXGBE_KRM_LINK_CTRL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); + + if (hw->mac.type == ixgbe_mac_x550em_a) { + /* Set lane mode to KR auto negotiation */ + status = hw->mac.ops.read_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, ®_val); + + if (status) + return status; + + reg_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_MASK; + reg_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_SPEED_AN; + reg_val |= IXGBE_KRM_PMD_FLX_MASK_ST20_AN_EN; + reg_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_AN37_EN; + reg_val &= ~IXGBE_KRM_PMD_FLX_MASK_ST20_SGMII_EN; + + status = hw->mac.ops.write_iosf_sb_reg(hw, + IXGBE_KRM_PMD_FLX_MASK_ST20(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, reg_val); + } + + return ixgbe_restart_an_internal_phy_x550em(hw); +} + +/** + * ixgbe_setup_kr_x550em - Configure the KR PHY + * @hw: pointer to hardware structure + **/ +static s32 ixgbe_setup_kr_x550em(struct ixgbe_hw *hw) +{ + /* leave link alone for 2.5G */ + if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_2_5GB_FULL) + return 0; + + if (ixgbe_check_reset_blocked(hw)) + return 0; + + return ixgbe_setup_kr_speed_x550em(hw, hw->phy.autoneg_advertised); +} + +/** ixgbe_ext_phy_t_x550em_get_link - Get ext phy link status + * @hw: address of hardware structure + * @link_up: address of boolean to indicate link status + * + * Returns error code if unable to get link status. + **/ +static s32 ixgbe_ext_phy_t_x550em_get_link(struct ixgbe_hw *hw, bool *link_up) +{ + u32 ret; + u16 autoneg_status; + + *link_up = false; + + /* read this twice back to back to indicate current status */ + ret = hw->phy.ops.read_reg(hw, MDIO_STAT1, MDIO_MMD_AN, + &autoneg_status); + if (ret) + return ret; + + ret = hw->phy.ops.read_reg(hw, MDIO_STAT1, MDIO_MMD_AN, + &autoneg_status); + if (ret) + return ret; + + *link_up = !!(autoneg_status & IXGBE_MDIO_AUTO_NEG_LINK_STATUS); + + return 0; +} + +/** ixgbe_setup_internal_phy_t_x550em - Configure KR PHY to X557 link + * @hw: point to hardware structure + * + * Configures the link between the integrated KR PHY and the external X557 PHY + * The driver will call this function when it gets a link status change + * interrupt from the X557 PHY. This function configures the link speed + * between the PHYs to match the link speed of the BASE-T link. + * + * A return of a non-zero value indicates an error, and the base driver should + * not report link up. + **/ +static s32 ixgbe_setup_internal_phy_t_x550em(struct ixgbe_hw *hw) +{ + ixgbe_link_speed force_speed; + bool link_up; + u32 status; + u16 speed; + + if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_copper) + return IXGBE_ERR_CONFIG; + + if (!(hw->mac.type == ixgbe_mac_X550EM_x && + !(hw->phy.nw_mng_if_sel & IXGBE_NW_MNG_IF_SEL_INT_PHY_MODE))) { + speed = IXGBE_LINK_SPEED_10GB_FULL | + IXGBE_LINK_SPEED_1GB_FULL; + return ixgbe_setup_kr_speed_x550em(hw, speed); + } + + /* If link is not up, then there is no setup necessary so return */ + status = ixgbe_ext_phy_t_x550em_get_link(hw, &link_up); + if (status) + return status; + + if (!link_up) + return 0; + + status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_VENDOR_STAT, + MDIO_MMD_AN, + &speed); + if (status) + return status; + + /* If link is not still up, then no setup is necessary so return */ + status = ixgbe_ext_phy_t_x550em_get_link(hw, &link_up); + if (status) + return status; + + if (!link_up) + return 0; + + /* clear everything but the speed and duplex bits */ + speed &= IXGBE_MDIO_AUTO_NEG_VENDOR_STATUS_MASK; + + switch (speed) { + case IXGBE_MDIO_AUTO_NEG_VENDOR_STATUS_10GB_FULL: + force_speed = IXGBE_LINK_SPEED_10GB_FULL; + break; + case IXGBE_MDIO_AUTO_NEG_VENDOR_STATUS_1GB_FULL: + force_speed = IXGBE_LINK_SPEED_1GB_FULL; + break; + default: + /* Internal PHY does not support anything else */ + return IXGBE_ERR_INVALID_LINK_SETTINGS; + } + + return ixgbe_setup_ixfi_x550em(hw, &force_speed); +} + +/** ixgbe_reset_phy_t_X550em - Performs X557 PHY reset and enables LASI + * @hw: pointer to hardware structure + **/ +static s32 ixgbe_reset_phy_t_X550em(struct ixgbe_hw *hw) +{ + s32 status; + + status = ixgbe_reset_phy_generic(hw); + + if (status) + return status; + + /* Configure Link Status Alarm and Temperature Threshold interrupts */ + return ixgbe_enable_lasi_ext_t_x550em(hw); +} + +/** + * ixgbe_led_on_t_x550em - Turns on the software controllable LEDs. + * @hw: pointer to hardware structure + * @led_idx: led number to turn on + **/ +static s32 ixgbe_led_on_t_x550em(struct ixgbe_hw *hw, u32 led_idx) +{ + u16 phy_data; + + if (led_idx >= IXGBE_X557_MAX_LED_INDEX) + return IXGBE_ERR_PARAM; + + /* To turn on the LED, set mode to ON. */ + hw->phy.ops.read_reg(hw, IXGBE_X557_LED_PROVISIONING + led_idx, + MDIO_MMD_VEND1, &phy_data); + phy_data |= IXGBE_X557_LED_MANUAL_SET_MASK; + hw->phy.ops.write_reg(hw, IXGBE_X557_LED_PROVISIONING + led_idx, + MDIO_MMD_VEND1, phy_data); + + return 0; +} + +/** + * ixgbe_led_off_t_x550em - Turns off the software controllable LEDs. + * @hw: pointer to hardware structure + * @led_idx: led number to turn off + **/ +static s32 ixgbe_led_off_t_x550em(struct ixgbe_hw *hw, u32 led_idx) +{ + u16 phy_data; + + if (led_idx >= IXGBE_X557_MAX_LED_INDEX) + return IXGBE_ERR_PARAM; + + /* To turn on the LED, set mode to ON. */ + hw->phy.ops.read_reg(hw, IXGBE_X557_LED_PROVISIONING + led_idx, + MDIO_MMD_VEND1, &phy_data); + phy_data &= ~IXGBE_X557_LED_MANUAL_SET_MASK; + hw->phy.ops.write_reg(hw, IXGBE_X557_LED_PROVISIONING + led_idx, + MDIO_MMD_VEND1, phy_data); + + return 0; +} + +/** + * ixgbe_set_fw_drv_ver_x550 - Sends driver version to firmware + * @hw: pointer to the HW structure + * @maj: driver version major number + * @min: driver version minor number + * @build: driver version build number + * @sub: driver version sub build number + * @len: length of driver_ver string + * @driver_ver: driver string + * + * Sends driver version number to firmware through the manageability + * block. On success return 0 + * else returns IXGBE_ERR_SWFW_SYNC when encountering an error acquiring + * semaphore or IXGBE_ERR_HOST_INTERFACE_COMMAND when command fails. + **/ +static s32 ixgbe_set_fw_drv_ver_x550(struct ixgbe_hw *hw, u8 maj, u8 min, + u8 build, u8 sub, u16 len, + const char *driver_ver) +{ + struct ixgbe_hic_drv_info2 fw_cmd; + s32 ret_val; + int i; + + if (!len || !driver_ver || (len > sizeof(fw_cmd.driver_string))) + return IXGBE_ERR_INVALID_ARGUMENT; + + fw_cmd.hdr.cmd = FW_CEM_CMD_DRIVER_INFO; + fw_cmd.hdr.buf_len = FW_CEM_CMD_DRIVER_INFO_LEN + len; + fw_cmd.hdr.cmd_or_resp.cmd_resv = FW_CEM_CMD_RESERVED; + fw_cmd.port_num = (u8)hw->bus.func; + fw_cmd.ver_maj = maj; + fw_cmd.ver_min = min; + fw_cmd.ver_build = build; + fw_cmd.ver_sub = sub; + fw_cmd.hdr.checksum = 0; + memcpy(fw_cmd.driver_string, driver_ver, len); + fw_cmd.hdr.checksum = ixgbe_calculate_checksum((u8 *)&fw_cmd, + (FW_CEM_HDR_LEN + fw_cmd.hdr.buf_len)); + + for (i = 0; i <= FW_CEM_MAX_RETRIES; i++) { + ret_val = ixgbe_host_interface_command(hw, (u32 *)&fw_cmd, + sizeof(fw_cmd), + IXGBE_HI_COMMAND_TIMEOUT, + true); + if (ret_val) + continue; + + if (fw_cmd.hdr.cmd_or_resp.ret_status != + FW_CEM_RESP_STATUS_SUCCESS) + return IXGBE_ERR_HOST_INTERFACE_COMMAND; + return 0; + } + + return ret_val; +} + +/** ixgbe_get_lcd_x550em - Determine lowest common denominator + * @hw: pointer to hardware structure + * @lcd_speed: pointer to lowest common link speed + * + * Determine lowest common link speed with link partner. + **/ +static s32 ixgbe_get_lcd_t_x550em(struct ixgbe_hw *hw, + ixgbe_link_speed *lcd_speed) +{ + u16 an_lp_status; + s32 status; + u16 word = hw->eeprom.ctrl_word_3; + + *lcd_speed = IXGBE_LINK_SPEED_UNKNOWN; + + status = hw->phy.ops.read_reg(hw, IXGBE_AUTO_NEG_LP_STATUS, + MDIO_MMD_AN, + &an_lp_status); + if (status) + return status; + + /* If link partner advertised 1G, return 1G */ + if (an_lp_status & IXGBE_AUTO_NEG_LP_1000BASE_CAP) { + *lcd_speed = IXGBE_LINK_SPEED_1GB_FULL; + return status; + } + + /* If 10G disabled for LPLU via NVM D10GMP, then return no valid LCD */ + if ((hw->bus.lan_id && (word & NVM_INIT_CTRL_3_D10GMP_PORT1)) || + (word & NVM_INIT_CTRL_3_D10GMP_PORT0)) + return status; + + /* Link partner not capable of lower speeds, return 10G */ + *lcd_speed = IXGBE_LINK_SPEED_10GB_FULL; + return status; +} + +/** + * ixgbe_setup_fc_x550em - Set up flow control + * @hw: pointer to hardware structure + */ +static s32 ixgbe_setup_fc_x550em(struct ixgbe_hw *hw) +{ + bool pause, asm_dir; + u32 reg_val; + s32 rc = 0; + + /* Validate the requested mode */ + if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) { + hw_err(hw, "ixgbe_fc_rx_pause not valid in strict IEEE mode\n"); + return IXGBE_ERR_INVALID_LINK_SETTINGS; + } + + /* 10gig parts do not have a word in the EEPROM to determine the + * default flow control setting, so we explicitly set it to full. + */ + if (hw->fc.requested_mode == ixgbe_fc_default) + hw->fc.requested_mode = ixgbe_fc_full; + + /* Determine PAUSE and ASM_DIR bits. */ + switch (hw->fc.requested_mode) { + case ixgbe_fc_none: + pause = false; + asm_dir = false; + break; + case ixgbe_fc_tx_pause: + pause = false; + asm_dir = true; + break; + case ixgbe_fc_rx_pause: + /* Rx Flow control is enabled and Tx Flow control is + * disabled by software override. Since there really + * isn't a way to advertise that we are capable of RX + * Pause ONLY, we will advertise that we support both + * symmetric and asymmetric Rx PAUSE, as such we fall + * through to the fc_full statement. Later, we will + * disable the adapter's ability to send PAUSE frames. + */ + fallthrough; + case ixgbe_fc_full: + pause = true; + asm_dir = true; + break; + default: + hw_err(hw, "Flow control param set incorrectly\n"); + return IXGBE_ERR_CONFIG; + } + + switch (hw->device_id) { + case IXGBE_DEV_ID_X550EM_X_KR: + case IXGBE_DEV_ID_X550EM_A_KR: + case IXGBE_DEV_ID_X550EM_A_KR_L: + rc = hw->mac.ops.read_iosf_sb_reg(hw, + IXGBE_KRM_AN_CNTL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, + ®_val); + if (rc) + return rc; + + reg_val &= ~(IXGBE_KRM_AN_CNTL_1_SYM_PAUSE | + IXGBE_KRM_AN_CNTL_1_ASM_PAUSE); + if (pause) + reg_val |= IXGBE_KRM_AN_CNTL_1_SYM_PAUSE; + if (asm_dir) + reg_val |= IXGBE_KRM_AN_CNTL_1_ASM_PAUSE; + rc = hw->mac.ops.write_iosf_sb_reg(hw, + IXGBE_KRM_AN_CNTL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, + reg_val); + + /* This device does not fully support AN. */ + hw->fc.disable_fc_autoneg = true; + break; + case IXGBE_DEV_ID_X550EM_X_XFI: + hw->fc.disable_fc_autoneg = true; + break; + default: + break; + } + return rc; +} + +/** + * ixgbe_fc_autoneg_backplane_x550em_a - Enable flow control IEEE clause 37 + * @hw: pointer to hardware structure + **/ +static void ixgbe_fc_autoneg_backplane_x550em_a(struct ixgbe_hw *hw) +{ + u32 link_s1, lp_an_page_low, an_cntl_1; + s32 status = IXGBE_ERR_FC_NOT_NEGOTIATED; + ixgbe_link_speed speed; + bool link_up; + + /* AN should have completed when the cable was plugged in. + * Look for reasons to bail out. Bail out if: + * - FC autoneg is disabled, or if + * - link is not up. + */ + if (hw->fc.disable_fc_autoneg) { + hw_err(hw, "Flow control autoneg is disabled"); + goto out; + } + + hw->mac.ops.check_link(hw, &speed, &link_up, false); + if (!link_up) { + hw_err(hw, "The link is down"); + goto out; + } + + /* Check at auto-negotiation has completed */ + status = hw->mac.ops.read_iosf_sb_reg(hw, + IXGBE_KRM_LINK_S1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &link_s1); + + if (status || (link_s1 & IXGBE_KRM_LINK_S1_MAC_AN_COMPLETE) == 0) { + hw_dbg(hw, "Auto-Negotiation did not complete\n"); + status = IXGBE_ERR_FC_NOT_NEGOTIATED; + goto out; + } + + /* Read the 10g AN autoc and LP ability registers and resolve + * local flow control settings accordingly + */ + status = hw->mac.ops.read_iosf_sb_reg(hw, + IXGBE_KRM_AN_CNTL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &an_cntl_1); + + if (status) { + hw_dbg(hw, "Auto-Negotiation did not complete\n"); + goto out; + } + + status = hw->mac.ops.read_iosf_sb_reg(hw, + IXGBE_KRM_LP_BASE_PAGE_HIGH(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &lp_an_page_low); + + if (status) { + hw_dbg(hw, "Auto-Negotiation did not complete\n"); + goto out; + } + + status = ixgbe_negotiate_fc(hw, an_cntl_1, lp_an_page_low, + IXGBE_KRM_AN_CNTL_1_SYM_PAUSE, + IXGBE_KRM_AN_CNTL_1_ASM_PAUSE, + IXGBE_KRM_LP_BASE_PAGE_HIGH_SYM_PAUSE, + IXGBE_KRM_LP_BASE_PAGE_HIGH_ASM_PAUSE); + +out: + if (!status) { + hw->fc.fc_was_autonegged = true; + } else { + hw->fc.fc_was_autonegged = false; + hw->fc.current_mode = hw->fc.requested_mode; + } +} + +/** + * ixgbe_fc_autoneg_fiber_x550em_a - passthrough FC settings + * @hw: pointer to hardware structure + **/ +static void ixgbe_fc_autoneg_fiber_x550em_a(struct ixgbe_hw *hw) +{ + hw->fc.fc_was_autonegged = false; + hw->fc.current_mode = hw->fc.requested_mode; +} + +/** ixgbe_enter_lplu_x550em - Transition to low power states + * @hw: pointer to hardware structure + * + * Configures Low Power Link Up on transition to low power states + * (from D0 to non-D0). Link is required to enter LPLU so avoid resetting + * the X557 PHY immediately prior to entering LPLU. + **/ +static s32 ixgbe_enter_lplu_t_x550em(struct ixgbe_hw *hw) +{ + u16 an_10g_cntl_reg, autoneg_reg, speed; + s32 status; + ixgbe_link_speed lcd_speed; + u32 save_autoneg; + bool link_up; + + /* If blocked by MNG FW, then don't restart AN */ + if (ixgbe_check_reset_blocked(hw)) + return 0; + + status = ixgbe_ext_phy_t_x550em_get_link(hw, &link_up); + if (status) + return status; + + status = hw->eeprom.ops.read(hw, NVM_INIT_CTRL_3, + &hw->eeprom.ctrl_word_3); + if (status) + return status; + + /* If link is down, LPLU disabled in NVM, WoL disabled, or + * manageability disabled, then force link down by entering + * low power mode. + */ + if (!link_up || !(hw->eeprom.ctrl_word_3 & NVM_INIT_CTRL_3_LPLU) || + !(hw->wol_enabled || ixgbe_mng_present(hw))) + return ixgbe_set_copper_phy_power(hw, false); + + /* Determine LCD */ + status = ixgbe_get_lcd_t_x550em(hw, &lcd_speed); + if (status) + return status; + + /* If no valid LCD link speed, then force link down and exit. */ + if (lcd_speed == IXGBE_LINK_SPEED_UNKNOWN) + return ixgbe_set_copper_phy_power(hw, false); + + status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_VENDOR_STAT, + MDIO_MMD_AN, + &speed); + if (status) + return status; + + /* If no link now, speed is invalid so take link down */ + status = ixgbe_ext_phy_t_x550em_get_link(hw, &link_up); + if (status) + return ixgbe_set_copper_phy_power(hw, false); + + /* clear everything but the speed bits */ + speed &= IXGBE_MDIO_AUTO_NEG_VEN_STAT_SPEED_MASK; + + /* If current speed is already LCD, then exit. */ + if (((speed == IXGBE_MDIO_AUTO_NEG_VENDOR_STATUS_1GB) && + (lcd_speed == IXGBE_LINK_SPEED_1GB_FULL)) || + ((speed == IXGBE_MDIO_AUTO_NEG_VENDOR_STATUS_10GB) && + (lcd_speed == IXGBE_LINK_SPEED_10GB_FULL))) + return status; + + /* Clear AN completed indication */ + status = hw->phy.ops.read_reg(hw, IXGBE_MDIO_AUTO_NEG_VENDOR_TX_ALARM, + MDIO_MMD_AN, + &autoneg_reg); + if (status) + return status; + + status = hw->phy.ops.read_reg(hw, MDIO_AN_10GBT_CTRL, + MDIO_MMD_AN, + &an_10g_cntl_reg); + if (status) + return status; + + status = hw->phy.ops.read_reg(hw, + IXGBE_MII_AUTONEG_VENDOR_PROVISION_1_REG, + MDIO_MMD_AN, + &autoneg_reg); + if (status) + return status; + + save_autoneg = hw->phy.autoneg_advertised; + + /* Setup link at least common link speed */ + status = hw->mac.ops.setup_link(hw, lcd_speed, false); + + /* restore autoneg from before setting lplu speed */ + hw->phy.autoneg_advertised = save_autoneg; + + return status; +} + +/** + * ixgbe_reset_phy_fw - Reset firmware-controlled PHYs + * @hw: pointer to hardware structure + */ +static s32 ixgbe_reset_phy_fw(struct ixgbe_hw *hw) +{ + u32 store[FW_PHY_ACT_DATA_COUNT] = { 0 }; + s32 rc; + + if (hw->phy.reset_disable || ixgbe_check_reset_blocked(hw)) + return 0; + + rc = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_PHY_SW_RESET, &store); + if (rc) + return rc; + memset(store, 0, sizeof(store)); + + rc = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_INIT_PHY, &store); + if (rc) + return rc; + + return ixgbe_setup_fw_link(hw); +} + +/** + * ixgbe_check_overtemp_fw - Check firmware-controlled PHYs for overtemp + * @hw: pointer to hardware structure + */ +static s32 ixgbe_check_overtemp_fw(struct ixgbe_hw *hw) +{ + u32 store[FW_PHY_ACT_DATA_COUNT] = { 0 }; + s32 rc; + + rc = ixgbe_fw_phy_activity(hw, FW_PHY_ACT_GET_LINK_INFO, &store); + if (rc) + return rc; + + if (store[0] & FW_PHY_ACT_GET_LINK_INFO_TEMP) { + ixgbe_shutdown_fw_phy(hw); + return IXGBE_ERR_OVERTEMP; + } + return 0; +} + +/** + * ixgbe_read_mng_if_sel_x550em - Read NW_MNG_IF_SEL register + * @hw: pointer to hardware structure + * + * Read NW_MNG_IF_SEL register and save field values. + */ +static void ixgbe_read_mng_if_sel_x550em(struct ixgbe_hw *hw) +{ + /* Save NW management interface connected on board. This is used + * to determine internal PHY mode. + */ + hw->phy.nw_mng_if_sel = IXGBE_READ_REG(hw, IXGBE_NW_MNG_IF_SEL); + + /* If X552 (X550EM_a) and MDIO is connected to external PHY, then set + * PHY address. This register field was has only been used for X552. + */ + if (hw->mac.type == ixgbe_mac_x550em_a && + hw->phy.nw_mng_if_sel & IXGBE_NW_MNG_IF_SEL_MDIO_ACT) { + hw->phy.mdio.prtad = (hw->phy.nw_mng_if_sel & + IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD) >> + IXGBE_NW_MNG_IF_SEL_MDIO_PHY_ADD_SHIFT; + } +} + +/** ixgbe_init_phy_ops_X550em - PHY/SFP specific init + * @hw: pointer to hardware structure + * + * Initialize any function pointers that were not able to be + * set during init_shared_code because the PHY/SFP type was + * not known. Perform the SFP init if necessary. + **/ +static s32 ixgbe_init_phy_ops_X550em(struct ixgbe_hw *hw) +{ + struct ixgbe_phy_info *phy = &hw->phy; + s32 ret_val; + + hw->mac.ops.set_lan_id(hw); + + ixgbe_read_mng_if_sel_x550em(hw); + + if (hw->mac.ops.get_media_type(hw) == ixgbe_media_type_fiber) { + phy->phy_semaphore_mask = IXGBE_GSSR_SHARED_I2C_SM; + ixgbe_setup_mux_ctl(hw); + } + + /* Identify the PHY or SFP module */ + ret_val = phy->ops.identify(hw); + if (ret_val == IXGBE_ERR_SFP_NOT_SUPPORTED || + ret_val == IXGBE_ERR_PHY_ADDR_INVALID) + return ret_val; + + /* Setup function pointers based on detected hardware */ + ixgbe_init_mac_link_ops_X550em(hw); + if (phy->sfp_type != ixgbe_sfp_type_unknown) + phy->ops.reset = NULL; + + /* Set functions pointers based on phy type */ + switch (hw->phy.type) { + case ixgbe_phy_x550em_kx4: + phy->ops.setup_link = NULL; + phy->ops.read_reg = ixgbe_read_phy_reg_x550em; + phy->ops.write_reg = ixgbe_write_phy_reg_x550em; + break; + case ixgbe_phy_x550em_kr: + phy->ops.setup_link = ixgbe_setup_kr_x550em; + phy->ops.read_reg = ixgbe_read_phy_reg_x550em; + phy->ops.write_reg = ixgbe_write_phy_reg_x550em; + break; + case ixgbe_phy_x550em_xfi: + /* link is managed by HW */ + phy->ops.setup_link = NULL; + phy->ops.read_reg = ixgbe_read_phy_reg_x550em; + phy->ops.write_reg = ixgbe_write_phy_reg_x550em; + break; + case ixgbe_phy_x550em_ext_t: + /* Save NW management interface connected on board. This is used + * to determine internal PHY mode + */ + phy->nw_mng_if_sel = IXGBE_READ_REG(hw, IXGBE_NW_MNG_IF_SEL); + + /* If internal link mode is XFI, then setup iXFI internal link, + * else setup KR now. + */ + phy->ops.setup_internal_link = + ixgbe_setup_internal_phy_t_x550em; + + /* setup SW LPLU only for first revision */ + if (hw->mac.type == ixgbe_mac_X550EM_x && + !(IXGBE_READ_REG(hw, IXGBE_FUSES0_GROUP(0)) & + IXGBE_FUSES0_REV_MASK)) + phy->ops.enter_lplu = ixgbe_enter_lplu_t_x550em; + + phy->ops.handle_lasi = ixgbe_handle_lasi_ext_t_x550em; + phy->ops.reset = ixgbe_reset_phy_t_X550em; + break; + case ixgbe_phy_sgmii: + phy->ops.setup_link = NULL; + break; + case ixgbe_phy_fw: + phy->ops.setup_link = ixgbe_setup_fw_link; + phy->ops.reset = ixgbe_reset_phy_fw; + break; + case ixgbe_phy_ext_1g_t: + phy->ops.setup_link = NULL; + phy->ops.read_reg = NULL; + phy->ops.write_reg = NULL; + phy->ops.reset = NULL; + break; + default: + break; + } + + return ret_val; +} + +/** ixgbe_get_media_type_X550em - Get media type + * @hw: pointer to hardware structure + * + * Returns the media type (fiber, copper, backplane) + * + */ +static enum ixgbe_media_type ixgbe_get_media_type_X550em(struct ixgbe_hw *hw) +{ + enum ixgbe_media_type media_type; + + /* Detect if there is a copper PHY attached. */ + switch (hw->device_id) { + case IXGBE_DEV_ID_X550EM_A_SGMII: + case IXGBE_DEV_ID_X550EM_A_SGMII_L: + hw->phy.type = ixgbe_phy_sgmii; + fallthrough; + case IXGBE_DEV_ID_X550EM_X_KR: + case IXGBE_DEV_ID_X550EM_X_KX4: + case IXGBE_DEV_ID_X550EM_X_XFI: + case IXGBE_DEV_ID_X550EM_A_KR: + case IXGBE_DEV_ID_X550EM_A_KR_L: + media_type = ixgbe_media_type_backplane; + break; + case IXGBE_DEV_ID_X550EM_X_SFP: + case IXGBE_DEV_ID_X550EM_A_SFP: + case IXGBE_DEV_ID_X550EM_A_SFP_N: + media_type = ixgbe_media_type_fiber; + break; + case IXGBE_DEV_ID_X550EM_X_1G_T: + case IXGBE_DEV_ID_X550EM_X_10G_T: + case IXGBE_DEV_ID_X550EM_A_10G_T: + case IXGBE_DEV_ID_X550EM_A_1G_T: + case IXGBE_DEV_ID_X550EM_A_1G_T_L: + media_type = ixgbe_media_type_copper; + break; + default: + media_type = ixgbe_media_type_unknown; + break; + } + return media_type; +} + +/** ixgbe_init_ext_t_x550em - Start (unstall) the external Base T PHY. + ** @hw: pointer to hardware structure + **/ +static s32 ixgbe_init_ext_t_x550em(struct ixgbe_hw *hw) +{ + s32 status; + u16 reg; + + status = hw->phy.ops.read_reg(hw, + IXGBE_MDIO_TX_VENDOR_ALARMS_3, + MDIO_MMD_PMAPMD, + ®); + if (status) + return status; + + /* If PHY FW reset completed bit is set then this is the first + * SW instance after a power on so the PHY FW must be un-stalled. + */ + if (reg & IXGBE_MDIO_TX_VENDOR_ALARMS_3_RST_MASK) { + status = hw->phy.ops.read_reg(hw, + IXGBE_MDIO_GLOBAL_RES_PR_10, + MDIO_MMD_VEND1, + ®); + if (status) + return status; + + reg &= ~IXGBE_MDIO_POWER_UP_STALL; + + status = hw->phy.ops.write_reg(hw, + IXGBE_MDIO_GLOBAL_RES_PR_10, + MDIO_MMD_VEND1, + reg); + if (status) + return status; + } + + return status; +} + +/** + * ixgbe_set_mdio_speed - Set MDIO clock speed + * @hw: pointer to hardware structure + */ +static void ixgbe_set_mdio_speed(struct ixgbe_hw *hw) +{ + u32 hlreg0; + + switch (hw->device_id) { + case IXGBE_DEV_ID_X550EM_X_10G_T: + case IXGBE_DEV_ID_X550EM_A_SGMII: + case IXGBE_DEV_ID_X550EM_A_SGMII_L: + case IXGBE_DEV_ID_X550EM_A_10G_T: + case IXGBE_DEV_ID_X550EM_A_SFP: + /* Config MDIO clock speed before the first MDIO PHY access */ + hlreg0 = IXGBE_READ_REG(hw, IXGBE_HLREG0); + hlreg0 &= ~IXGBE_HLREG0_MDCSPD; + IXGBE_WRITE_REG(hw, IXGBE_HLREG0, hlreg0); + break; + case IXGBE_DEV_ID_X550EM_A_1G_T: + case IXGBE_DEV_ID_X550EM_A_1G_T_L: + /* Select fast MDIO clock speed for these devices */ + hlreg0 = IXGBE_READ_REG(hw, IXGBE_HLREG0); + hlreg0 |= IXGBE_HLREG0_MDCSPD; + IXGBE_WRITE_REG(hw, IXGBE_HLREG0, hlreg0); + break; + default: + break; + } +} + +/** ixgbe_reset_hw_X550em - Perform hardware reset + ** @hw: pointer to hardware structure + ** + ** Resets the hardware by resetting the transmit and receive units, masks + ** and clears all interrupts, perform a PHY reset, and perform a link (MAC) + ** reset. + **/ +static s32 ixgbe_reset_hw_X550em(struct ixgbe_hw *hw) +{ + ixgbe_link_speed link_speed; + s32 status; + u32 ctrl = 0; + u32 i; + bool link_up = false; + u32 swfw_mask = hw->phy.phy_semaphore_mask; + + /* Call adapter stop to disable Tx/Rx and clear interrupts */ + status = hw->mac.ops.stop_adapter(hw); + if (status) + return status; + + /* flush pending Tx transactions */ + ixgbe_clear_tx_pending(hw); + + /* set MDIO speed before talking to the PHY in case it's the 1st time */ + ixgbe_set_mdio_speed(hw); + + /* PHY ops must be identified and initialized prior to reset */ + status = hw->phy.ops.init(hw); + if (status == IXGBE_ERR_SFP_NOT_SUPPORTED || + status == IXGBE_ERR_PHY_ADDR_INVALID) + return status; + + /* start the external PHY */ + if (hw->phy.type == ixgbe_phy_x550em_ext_t) { + status = ixgbe_init_ext_t_x550em(hw); + if (status) + return status; + } + + /* Setup SFP module if there is one present. */ + if (hw->phy.sfp_setup_needed) { + status = hw->mac.ops.setup_sfp(hw); + hw->phy.sfp_setup_needed = false; + } + + if (status == IXGBE_ERR_SFP_NOT_SUPPORTED) + return status; + + /* Reset PHY */ + if (!hw->phy.reset_disable && hw->phy.ops.reset) + hw->phy.ops.reset(hw); + +mac_reset_top: + /* Issue global reset to the MAC. Needs to be SW reset if link is up. + * If link reset is used when link is up, it might reset the PHY when + * mng is using it. If link is down or the flag to force full link + * reset is set, then perform link reset. + */ + ctrl = IXGBE_CTRL_LNK_RST; + + if (!hw->force_full_reset) { + hw->mac.ops.check_link(hw, &link_speed, &link_up, false); + if (link_up) + ctrl = IXGBE_CTRL_RST; + } + + status = hw->mac.ops.acquire_swfw_sync(hw, swfw_mask); + if (status) { + hw_dbg(hw, "semaphore failed with %d", status); + return IXGBE_ERR_SWFW_SYNC; + } + + ctrl |= IXGBE_READ_REG(hw, IXGBE_CTRL); + IXGBE_WRITE_REG(hw, IXGBE_CTRL, ctrl); + IXGBE_WRITE_FLUSH(hw); + hw->mac.ops.release_swfw_sync(hw, swfw_mask); + usleep_range(1000, 1200); + + /* Poll for reset bit to self-clear meaning reset is complete */ + for (i = 0; i < 10; i++) { + ctrl = IXGBE_READ_REG(hw, IXGBE_CTRL); + if (!(ctrl & IXGBE_CTRL_RST_MASK)) + break; + udelay(1); + } + + if (ctrl & IXGBE_CTRL_RST_MASK) { + status = IXGBE_ERR_RESET_FAILED; + hw_dbg(hw, "Reset polling failed to complete.\n"); + } + + msleep(50); + + /* Double resets are required for recovery from certain error + * clear the multicast table. Also reset num_rar_entries to 128, + * since we modify this value when programming the SAN MAC address. + */ + if (hw->mac.flags & IXGBE_FLAGS_DOUBLE_RESET_REQUIRED) { + hw->mac.flags &= ~IXGBE_FLAGS_DOUBLE_RESET_REQUIRED; + goto mac_reset_top; + } + + /* Store the permanent mac address */ + hw->mac.ops.get_mac_addr(hw, hw->mac.perm_addr); + + /* Store MAC address from RAR0, clear receive address registers, and + * clear the multicast table. Also reset num_rar_entries to 128, + * since we modify this value when programming the SAN MAC address. + */ + hw->mac.num_rar_entries = 128; + hw->mac.ops.init_rx_addrs(hw); + + ixgbe_set_mdio_speed(hw); + + if (hw->device_id == IXGBE_DEV_ID_X550EM_X_SFP) + ixgbe_setup_mux_ctl(hw); + + return status; +} + +/** ixgbe_set_ethertype_anti_spoofing_X550 - Enable/Disable Ethertype + * anti-spoofing + * @hw: pointer to hardware structure + * @enable: enable or disable switch for Ethertype anti-spoofing + * @vf: Virtual Function pool - VF Pool to set for Ethertype anti-spoofing + **/ +static void ixgbe_set_ethertype_anti_spoofing_X550(struct ixgbe_hw *hw, + bool enable, int vf) +{ + int vf_target_reg = vf >> 3; + int vf_target_shift = vf % 8 + IXGBE_SPOOF_ETHERTYPEAS_SHIFT; + u32 pfvfspoof; + + pfvfspoof = IXGBE_READ_REG(hw, IXGBE_PFVFSPOOF(vf_target_reg)); + if (enable) + pfvfspoof |= BIT(vf_target_shift); + else + pfvfspoof &= ~BIT(vf_target_shift); + + IXGBE_WRITE_REG(hw, IXGBE_PFVFSPOOF(vf_target_reg), pfvfspoof); +} + +/** ixgbe_set_source_address_pruning_X550 - Enable/Disbale src address pruning + * @hw: pointer to hardware structure + * @enable: enable or disable source address pruning + * @pool: Rx pool to set source address pruning for + **/ +static void ixgbe_set_source_address_pruning_X550(struct ixgbe_hw *hw, + bool enable, + unsigned int pool) +{ + u64 pfflp; + + /* max rx pool is 63 */ + if (pool > 63) + return; + + pfflp = (u64)IXGBE_READ_REG(hw, IXGBE_PFFLPL); + pfflp |= (u64)IXGBE_READ_REG(hw, IXGBE_PFFLPH) << 32; + + if (enable) + pfflp |= (1ULL << pool); + else + pfflp &= ~(1ULL << pool); + + IXGBE_WRITE_REG(hw, IXGBE_PFFLPL, (u32)pfflp); + IXGBE_WRITE_REG(hw, IXGBE_PFFLPH, (u32)(pfflp >> 32)); +} + +/** + * ixgbe_setup_fc_backplane_x550em_a - Set up flow control + * @hw: pointer to hardware structure + * + * Called at init time to set up flow control. + **/ +static s32 ixgbe_setup_fc_backplane_x550em_a(struct ixgbe_hw *hw) +{ + s32 status = 0; + u32 an_cntl = 0; + + /* Validate the requested mode */ + if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) { + hw_err(hw, "ixgbe_fc_rx_pause not valid in strict IEEE mode\n"); + return IXGBE_ERR_INVALID_LINK_SETTINGS; + } + + if (hw->fc.requested_mode == ixgbe_fc_default) + hw->fc.requested_mode = ixgbe_fc_full; + + /* Set up the 1G and 10G flow control advertisement registers so the + * HW will be able to do FC autoneg once the cable is plugged in. If + * we link at 10G, the 1G advertisement is harmless and vice versa. + */ + status = hw->mac.ops.read_iosf_sb_reg(hw, + IXGBE_KRM_AN_CNTL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, &an_cntl); + + if (status) { + hw_dbg(hw, "Auto-Negotiation did not complete\n"); + return status; + } + + /* The possible values of fc.requested_mode 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.requested_mode) { + case ixgbe_fc_none: + /* Flow control completely disabled by software override. */ + an_cntl &= ~(IXGBE_KRM_AN_CNTL_1_SYM_PAUSE | + IXGBE_KRM_AN_CNTL_1_ASM_PAUSE); + break; + case ixgbe_fc_tx_pause: + /* Tx Flow control is enabled, and Rx Flow control is + * disabled by software override. + */ + an_cntl |= IXGBE_KRM_AN_CNTL_1_ASM_PAUSE; + an_cntl &= ~IXGBE_KRM_AN_CNTL_1_SYM_PAUSE; + break; + case ixgbe_fc_rx_pause: + /* Rx Flow control is enabled and Tx Flow control is + * disabled by software override. Since there really + * isn't a way to advertise that we are capable of RX + * Pause ONLY, we will advertise that we support both + * symmetric and asymmetric Rx PAUSE, as such we fall + * through to the fc_full statement. Later, we will + * disable the adapter's ability to send PAUSE frames. + */ + case ixgbe_fc_full: + /* Flow control (both Rx and Tx) is enabled by SW override. */ + an_cntl |= IXGBE_KRM_AN_CNTL_1_SYM_PAUSE | + IXGBE_KRM_AN_CNTL_1_ASM_PAUSE; + break; + default: + hw_err(hw, "Flow control param set incorrectly\n"); + return IXGBE_ERR_CONFIG; + } + + status = hw->mac.ops.write_iosf_sb_reg(hw, + IXGBE_KRM_AN_CNTL_1(hw->bus.lan_id), + IXGBE_SB_IOSF_TARGET_KR_PHY, an_cntl); + + /* Restart auto-negotiation. */ + status = ixgbe_restart_an_internal_phy_x550em(hw); + + return status; +} + +/** + * ixgbe_set_mux - Set mux for port 1 access with CS4227 + * @hw: pointer to hardware structure + * @state: set mux if 1, clear if 0 + */ +static void ixgbe_set_mux(struct ixgbe_hw *hw, u8 state) +{ + u32 esdp; + + if (!hw->bus.lan_id) + return; + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + if (state) + esdp |= IXGBE_ESDP_SDP1; + else + esdp &= ~IXGBE_ESDP_SDP1; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp); + IXGBE_WRITE_FLUSH(hw); +} + +/** + * ixgbe_acquire_swfw_sync_X550em - Acquire SWFW semaphore + * @hw: pointer to hardware structure + * @mask: Mask to specify which semaphore to acquire + * + * Acquires the SWFW semaphore and sets the I2C MUX + */ +static s32 ixgbe_acquire_swfw_sync_X550em(struct ixgbe_hw *hw, u32 mask) +{ + s32 status; + + status = ixgbe_acquire_swfw_sync_X540(hw, mask); + if (status) + return status; + + if (mask & IXGBE_GSSR_I2C_MASK) + ixgbe_set_mux(hw, 1); + + return 0; +} + +/** + * ixgbe_release_swfw_sync_X550em - Release SWFW semaphore + * @hw: pointer to hardware structure + * @mask: Mask to specify which semaphore to release + * + * Releases the SWFW semaphore and sets the I2C MUX + */ +static void ixgbe_release_swfw_sync_X550em(struct ixgbe_hw *hw, u32 mask) +{ + if (mask & IXGBE_GSSR_I2C_MASK) + ixgbe_set_mux(hw, 0); + + ixgbe_release_swfw_sync_X540(hw, mask); +} + +/** + * ixgbe_acquire_swfw_sync_x550em_a - Acquire SWFW semaphore + * @hw: pointer to hardware structure + * @mask: Mask to specify which semaphore to acquire + * + * Acquires the SWFW semaphore and get the shared PHY token as needed + */ +static s32 ixgbe_acquire_swfw_sync_x550em_a(struct ixgbe_hw *hw, u32 mask) +{ + u32 hmask = mask & ~IXGBE_GSSR_TOKEN_SM; + int retries = FW_PHY_TOKEN_RETRIES; + s32 status; + + while (--retries) { + status = 0; + if (hmask) + status = ixgbe_acquire_swfw_sync_X540(hw, hmask); + if (status) + return status; + if (!(mask & IXGBE_GSSR_TOKEN_SM)) + return 0; + + status = ixgbe_get_phy_token(hw); + if (!status) + return 0; + if (hmask) + ixgbe_release_swfw_sync_X540(hw, hmask); + if (status != IXGBE_ERR_TOKEN_RETRY) + return status; + msleep(FW_PHY_TOKEN_DELAY); + } + + return status; +} + +/** + * ixgbe_release_swfw_sync_x550em_a - Release SWFW semaphore + * @hw: pointer to hardware structure + * @mask: Mask to specify which semaphore to release + * + * Release the SWFW semaphore and puts the shared PHY token as needed + */ +static void ixgbe_release_swfw_sync_x550em_a(struct ixgbe_hw *hw, u32 mask) +{ + u32 hmask = mask & ~IXGBE_GSSR_TOKEN_SM; + + if (mask & IXGBE_GSSR_TOKEN_SM) + ixgbe_put_phy_token(hw); + + if (hmask) + ixgbe_release_swfw_sync_X540(hw, hmask); +} + +/** + * ixgbe_read_phy_reg_x550a - Reads specified PHY register + * @hw: pointer to hardware structure + * @reg_addr: 32 bit address of PHY register to read + * @device_type: 5 bit device type + * @phy_data: Pointer to read data from PHY register + * + * Reads a value from a specified PHY register using the SWFW lock and PHY + * Token. The PHY Token is needed since the MDIO is shared between to MAC + * instances. + */ +static s32 ixgbe_read_phy_reg_x550a(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u16 *phy_data) +{ + u32 mask = hw->phy.phy_semaphore_mask | IXGBE_GSSR_TOKEN_SM; + s32 status; + + if (hw->mac.ops.acquire_swfw_sync(hw, mask)) + return IXGBE_ERR_SWFW_SYNC; + + status = hw->phy.ops.read_reg_mdi(hw, reg_addr, device_type, phy_data); + + hw->mac.ops.release_swfw_sync(hw, mask); + + return status; +} + +/** + * ixgbe_write_phy_reg_x550a - Writes specified PHY register + * @hw: pointer to hardware structure + * @reg_addr: 32 bit PHY register to write + * @device_type: 5 bit device type + * @phy_data: Data to write to the PHY register + * + * Writes a value to specified PHY register using the SWFW lock and PHY Token. + * The PHY Token is needed since the MDIO is shared between to MAC instances. + */ +static s32 ixgbe_write_phy_reg_x550a(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u16 phy_data) +{ + u32 mask = hw->phy.phy_semaphore_mask | IXGBE_GSSR_TOKEN_SM; + s32 status; + + if (hw->mac.ops.acquire_swfw_sync(hw, mask)) + return IXGBE_ERR_SWFW_SYNC; + + status = ixgbe_write_phy_reg_mdi(hw, reg_addr, device_type, phy_data); + hw->mac.ops.release_swfw_sync(hw, mask); + + return status; +} + +#define X550_COMMON_MAC \ + .init_hw = &ixgbe_init_hw_generic, \ + .start_hw = &ixgbe_start_hw_X540, \ + .clear_hw_cntrs = &ixgbe_clear_hw_cntrs_generic, \ + .enable_rx_dma = &ixgbe_enable_rx_dma_generic, \ + .get_mac_addr = &ixgbe_get_mac_addr_generic, \ + .get_device_caps = &ixgbe_get_device_caps_generic, \ + .stop_adapter = &ixgbe_stop_adapter_generic, \ + .set_lan_id = &ixgbe_set_lan_id_multi_port_pcie, \ + .read_analog_reg8 = NULL, \ + .write_analog_reg8 = NULL, \ + .set_rxpba = &ixgbe_set_rxpba_generic, \ + .check_link = &ixgbe_check_mac_link_generic, \ + .blink_led_start = &ixgbe_blink_led_start_X540, \ + .blink_led_stop = &ixgbe_blink_led_stop_X540, \ + .set_rar = &ixgbe_set_rar_generic, \ + .clear_rar = &ixgbe_clear_rar_generic, \ + .set_vmdq = &ixgbe_set_vmdq_generic, \ + .set_vmdq_san_mac = &ixgbe_set_vmdq_san_mac_generic, \ + .clear_vmdq = &ixgbe_clear_vmdq_generic, \ + .init_rx_addrs = &ixgbe_init_rx_addrs_generic, \ + .update_mc_addr_list = &ixgbe_update_mc_addr_list_generic, \ + .enable_mc = &ixgbe_enable_mc_generic, \ + .disable_mc = &ixgbe_disable_mc_generic, \ + .clear_vfta = &ixgbe_clear_vfta_generic, \ + .set_vfta = &ixgbe_set_vfta_generic, \ + .fc_enable = &ixgbe_fc_enable_generic, \ + .set_fw_drv_ver = &ixgbe_set_fw_drv_ver_x550, \ + .init_uta_tables = &ixgbe_init_uta_tables_generic, \ + .set_mac_anti_spoofing = &ixgbe_set_mac_anti_spoofing, \ + .set_vlan_anti_spoofing = &ixgbe_set_vlan_anti_spoofing, \ + .set_source_address_pruning = \ + &ixgbe_set_source_address_pruning_X550, \ + .set_ethertype_anti_spoofing = \ + &ixgbe_set_ethertype_anti_spoofing_X550, \ + .disable_rx_buff = &ixgbe_disable_rx_buff_generic, \ + .enable_rx_buff = &ixgbe_enable_rx_buff_generic, \ + .get_thermal_sensor_data = NULL, \ + .init_thermal_sensor_thresh = NULL, \ + .fw_recovery_mode = &ixgbe_fw_recovery_mode_X550, \ + .enable_rx = &ixgbe_enable_rx_generic, \ + .disable_rx = &ixgbe_disable_rx_x550, \ + +static const struct ixgbe_mac_operations mac_ops_X550 = { + X550_COMMON_MAC + .led_on = ixgbe_led_on_generic, + .led_off = ixgbe_led_off_generic, + .init_led_link_act = ixgbe_init_led_link_act_generic, + .reset_hw = &ixgbe_reset_hw_X540, + .get_media_type = &ixgbe_get_media_type_X540, + .get_san_mac_addr = &ixgbe_get_san_mac_addr_generic, + .get_wwn_prefix = &ixgbe_get_wwn_prefix_generic, + .setup_link = &ixgbe_setup_mac_link_X540, + .get_link_capabilities = &ixgbe_get_copper_link_capabilities_generic, + .get_bus_info = &ixgbe_get_bus_info_generic, + .setup_sfp = NULL, + .acquire_swfw_sync = &ixgbe_acquire_swfw_sync_X540, + .release_swfw_sync = &ixgbe_release_swfw_sync_X540, + .init_swfw_sync = &ixgbe_init_swfw_sync_X540, + .prot_autoc_read = prot_autoc_read_generic, + .prot_autoc_write = prot_autoc_write_generic, + .setup_fc = ixgbe_setup_fc_generic, + .fc_autoneg = ixgbe_fc_autoneg, +}; + +static const struct ixgbe_mac_operations mac_ops_X550EM_x = { + X550_COMMON_MAC + .led_on = ixgbe_led_on_t_x550em, + .led_off = ixgbe_led_off_t_x550em, + .init_led_link_act = ixgbe_init_led_link_act_generic, + .reset_hw = &ixgbe_reset_hw_X550em, + .get_media_type = &ixgbe_get_media_type_X550em, + .get_san_mac_addr = NULL, + .get_wwn_prefix = NULL, + .setup_link = &ixgbe_setup_mac_link_X540, + .get_link_capabilities = &ixgbe_get_link_capabilities_X550em, + .get_bus_info = &ixgbe_get_bus_info_X550em, + .setup_sfp = ixgbe_setup_sfp_modules_X550em, + .acquire_swfw_sync = &ixgbe_acquire_swfw_sync_X550em, + .release_swfw_sync = &ixgbe_release_swfw_sync_X550em, + .init_swfw_sync = &ixgbe_init_swfw_sync_X540, + .setup_fc = NULL, /* defined later */ + .fc_autoneg = ixgbe_fc_autoneg, + .read_iosf_sb_reg = ixgbe_read_iosf_sb_reg_x550, + .write_iosf_sb_reg = ixgbe_write_iosf_sb_reg_x550, +}; + +static const struct ixgbe_mac_operations mac_ops_X550EM_x_fw = { + X550_COMMON_MAC + .led_on = NULL, + .led_off = NULL, + .init_led_link_act = NULL, + .reset_hw = &ixgbe_reset_hw_X550em, + .get_media_type = &ixgbe_get_media_type_X550em, + .get_san_mac_addr = NULL, + .get_wwn_prefix = NULL, + .setup_link = &ixgbe_setup_mac_link_X540, + .get_link_capabilities = &ixgbe_get_link_capabilities_X550em, + .get_bus_info = &ixgbe_get_bus_info_X550em, + .setup_sfp = ixgbe_setup_sfp_modules_X550em, + .acquire_swfw_sync = &ixgbe_acquire_swfw_sync_X550em, + .release_swfw_sync = &ixgbe_release_swfw_sync_X550em, + .init_swfw_sync = &ixgbe_init_swfw_sync_X540, + .setup_fc = NULL, + .fc_autoneg = ixgbe_fc_autoneg, + .read_iosf_sb_reg = ixgbe_read_iosf_sb_reg_x550, + .write_iosf_sb_reg = ixgbe_write_iosf_sb_reg_x550, +}; + +static const struct ixgbe_mac_operations mac_ops_x550em_a = { + X550_COMMON_MAC + .led_on = ixgbe_led_on_t_x550em, + .led_off = ixgbe_led_off_t_x550em, + .init_led_link_act = ixgbe_init_led_link_act_generic, + .reset_hw = ixgbe_reset_hw_X550em, + .get_media_type = ixgbe_get_media_type_X550em, + .get_san_mac_addr = NULL, + .get_wwn_prefix = NULL, + .setup_link = &ixgbe_setup_mac_link_X540, + .get_link_capabilities = ixgbe_get_link_capabilities_X550em, + .get_bus_info = ixgbe_get_bus_info_X550em, + .setup_sfp = ixgbe_setup_sfp_modules_X550em, + .acquire_swfw_sync = ixgbe_acquire_swfw_sync_x550em_a, + .release_swfw_sync = ixgbe_release_swfw_sync_x550em_a, + .setup_fc = ixgbe_setup_fc_x550em, + .fc_autoneg = ixgbe_fc_autoneg, + .read_iosf_sb_reg = ixgbe_read_iosf_sb_reg_x550a, + .write_iosf_sb_reg = ixgbe_write_iosf_sb_reg_x550a, +}; + +static const struct ixgbe_mac_operations mac_ops_x550em_a_fw = { + X550_COMMON_MAC + .led_on = ixgbe_led_on_generic, + .led_off = ixgbe_led_off_generic, + .init_led_link_act = ixgbe_init_led_link_act_generic, + .reset_hw = ixgbe_reset_hw_X550em, + .get_media_type = ixgbe_get_media_type_X550em, + .get_san_mac_addr = NULL, + .get_wwn_prefix = NULL, + .setup_link = NULL, /* defined later */ + .get_link_capabilities = ixgbe_get_link_capabilities_X550em, + .get_bus_info = ixgbe_get_bus_info_X550em, + .setup_sfp = ixgbe_setup_sfp_modules_X550em, + .acquire_swfw_sync = ixgbe_acquire_swfw_sync_x550em_a, + .release_swfw_sync = ixgbe_release_swfw_sync_x550em_a, + .setup_fc = ixgbe_setup_fc_x550em, + .fc_autoneg = ixgbe_fc_autoneg, + .read_iosf_sb_reg = ixgbe_read_iosf_sb_reg_x550a, + .write_iosf_sb_reg = ixgbe_write_iosf_sb_reg_x550a, +}; + +#define X550_COMMON_EEP \ + .read = &ixgbe_read_ee_hostif_X550, \ + .read_buffer = &ixgbe_read_ee_hostif_buffer_X550, \ + .write = &ixgbe_write_ee_hostif_X550, \ + .write_buffer = &ixgbe_write_ee_hostif_buffer_X550, \ + .validate_checksum = &ixgbe_validate_eeprom_checksum_X550, \ + .update_checksum = &ixgbe_update_eeprom_checksum_X550, \ + .calc_checksum = &ixgbe_calc_eeprom_checksum_X550, \ + +static const struct ixgbe_eeprom_operations eeprom_ops_X550 = { + X550_COMMON_EEP + .init_params = &ixgbe_init_eeprom_params_X550, +}; + +static const struct ixgbe_eeprom_operations eeprom_ops_X550EM_x = { + X550_COMMON_EEP + .init_params = &ixgbe_init_eeprom_params_X540, +}; + +#define X550_COMMON_PHY \ + .identify_sfp = &ixgbe_identify_module_generic, \ + .reset = NULL, \ + .setup_link_speed = &ixgbe_setup_phy_link_speed_generic, \ + .read_i2c_byte = &ixgbe_read_i2c_byte_generic, \ + .write_i2c_byte = &ixgbe_write_i2c_byte_generic, \ + .read_i2c_sff8472 = &ixgbe_read_i2c_sff8472_generic, \ + .read_i2c_eeprom = &ixgbe_read_i2c_eeprom_generic, \ + .write_i2c_eeprom = &ixgbe_write_i2c_eeprom_generic, \ + .setup_link = &ixgbe_setup_phy_link_generic, \ + .set_phy_power = NULL, + +static const struct ixgbe_phy_operations phy_ops_X550 = { + X550_COMMON_PHY + .check_overtemp = &ixgbe_tn_check_overtemp, + .init = NULL, + .identify = &ixgbe_identify_phy_generic, + .read_reg = &ixgbe_read_phy_reg_generic, + .write_reg = &ixgbe_write_phy_reg_generic, +}; + +static const struct ixgbe_phy_operations phy_ops_X550EM_x = { + X550_COMMON_PHY + .check_overtemp = &ixgbe_tn_check_overtemp, + .init = &ixgbe_init_phy_ops_X550em, + .identify = &ixgbe_identify_phy_x550em, + .read_reg = &ixgbe_read_phy_reg_generic, + .write_reg = &ixgbe_write_phy_reg_generic, +}; + +static const struct ixgbe_phy_operations phy_ops_x550em_x_fw = { + X550_COMMON_PHY + .check_overtemp = NULL, + .init = ixgbe_init_phy_ops_X550em, + .identify = ixgbe_identify_phy_x550em, + .read_reg = NULL, + .write_reg = NULL, + .read_reg_mdi = NULL, + .write_reg_mdi = NULL, +}; + +static const struct ixgbe_phy_operations phy_ops_x550em_a = { + X550_COMMON_PHY + .check_overtemp = &ixgbe_tn_check_overtemp, + .init = &ixgbe_init_phy_ops_X550em, + .identify = &ixgbe_identify_phy_x550em, + .read_reg = &ixgbe_read_phy_reg_x550a, + .write_reg = &ixgbe_write_phy_reg_x550a, + .read_reg_mdi = &ixgbe_read_phy_reg_mdi, + .write_reg_mdi = &ixgbe_write_phy_reg_mdi, +}; + +static const struct ixgbe_phy_operations phy_ops_x550em_a_fw = { + X550_COMMON_PHY + .check_overtemp = ixgbe_check_overtemp_fw, + .init = ixgbe_init_phy_ops_X550em, + .identify = ixgbe_identify_phy_fw, + .read_reg = NULL, + .write_reg = NULL, + .read_reg_mdi = NULL, + .write_reg_mdi = NULL, +}; + +static const struct ixgbe_link_operations link_ops_x550em_x = { + .read_link = &ixgbe_read_i2c_combined_generic, + .read_link_unlocked = &ixgbe_read_i2c_combined_generic_unlocked, + .write_link = &ixgbe_write_i2c_combined_generic, + .write_link_unlocked = &ixgbe_write_i2c_combined_generic_unlocked, +}; + +static const u32 ixgbe_mvals_X550[IXGBE_MVALS_IDX_LIMIT] = { + IXGBE_MVALS_INIT(X550) +}; + +static const u32 ixgbe_mvals_X550EM_x[IXGBE_MVALS_IDX_LIMIT] = { + IXGBE_MVALS_INIT(X550EM_x) +}; + +static const u32 ixgbe_mvals_x550em_a[IXGBE_MVALS_IDX_LIMIT] = { + IXGBE_MVALS_INIT(X550EM_a) +}; + +const struct ixgbe_info ixgbe_X550_info = { + .mac = ixgbe_mac_X550, + .get_invariants = &ixgbe_get_invariants_X540, + .mac_ops = &mac_ops_X550, + .eeprom_ops = &eeprom_ops_X550, + .phy_ops = &phy_ops_X550, + .mbx_ops = &mbx_ops_generic, + .mvals = ixgbe_mvals_X550, +}; + +const struct ixgbe_info ixgbe_X550EM_x_info = { + .mac = ixgbe_mac_X550EM_x, + .get_invariants = &ixgbe_get_invariants_X550_x, + .mac_ops = &mac_ops_X550EM_x, + .eeprom_ops = &eeprom_ops_X550EM_x, + .phy_ops = &phy_ops_X550EM_x, + .mbx_ops = &mbx_ops_generic, + .mvals = ixgbe_mvals_X550EM_x, + .link_ops = &link_ops_x550em_x, +}; + +const struct ixgbe_info ixgbe_x550em_x_fw_info = { + .mac = ixgbe_mac_X550EM_x, + .get_invariants = ixgbe_get_invariants_X550_x_fw, + .mac_ops = &mac_ops_X550EM_x_fw, + .eeprom_ops = &eeprom_ops_X550EM_x, + .phy_ops = &phy_ops_x550em_x_fw, + .mbx_ops = &mbx_ops_generic, + .mvals = ixgbe_mvals_X550EM_x, +}; + +const struct ixgbe_info ixgbe_x550em_a_info = { + .mac = ixgbe_mac_x550em_a, + .get_invariants = &ixgbe_get_invariants_X550_a, + .mac_ops = &mac_ops_x550em_a, + .eeprom_ops = &eeprom_ops_X550EM_x, + .phy_ops = &phy_ops_x550em_a, + .mbx_ops = &mbx_ops_generic, + .mvals = ixgbe_mvals_x550em_a, +}; + +const struct ixgbe_info ixgbe_x550em_a_fw_info = { + .mac = ixgbe_mac_x550em_a, + .get_invariants = ixgbe_get_invariants_X550_a_fw, + .mac_ops = &mac_ops_x550em_a_fw, + .eeprom_ops = &eeprom_ops_X550EM_x, + .phy_ops = &phy_ops_x550em_a_fw, + .mbx_ops = &mbx_ops_generic, + .mvals = ixgbe_mvals_x550em_a, +}; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c new file mode 100644 index 000000000..ca1a428b2 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -0,0 +1,561 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2018 Intel Corporation. */ + +#include <linux/bpf_trace.h> +#include <net/xdp_sock_drv.h> +#include <net/xdp.h> + +#include "ixgbe.h" +#include "ixgbe_txrx_common.h" + +struct xsk_buff_pool *ixgbe_xsk_pool(struct ixgbe_adapter *adapter, + struct ixgbe_ring *ring) +{ + bool xdp_on = READ_ONCE(adapter->xdp_prog); + int qid = ring->ring_idx; + + if (!xdp_on || !test_bit(qid, adapter->af_xdp_zc_qps)) + return NULL; + + return xsk_get_pool_from_qid(adapter->netdev, qid); +} + +static int ixgbe_xsk_pool_enable(struct ixgbe_adapter *adapter, + struct xsk_buff_pool *pool, + u16 qid) +{ + struct net_device *netdev = adapter->netdev; + bool if_running; + int err; + + if (qid >= adapter->num_rx_queues) + return -EINVAL; + + if (qid >= netdev->real_num_rx_queues || + qid >= netdev->real_num_tx_queues) + return -EINVAL; + + err = xsk_pool_dma_map(pool, &adapter->pdev->dev, IXGBE_RX_DMA_ATTR); + if (err) + return err; + + if_running = netif_running(adapter->netdev) && + ixgbe_enabled_xdp_adapter(adapter); + + if (if_running) + ixgbe_txrx_ring_disable(adapter, qid); + + set_bit(qid, adapter->af_xdp_zc_qps); + + if (if_running) { + ixgbe_txrx_ring_enable(adapter, qid); + + /* Kick start the NAPI context so that receiving will start */ + err = ixgbe_xsk_wakeup(adapter->netdev, qid, XDP_WAKEUP_RX); + if (err) { + clear_bit(qid, adapter->af_xdp_zc_qps); + xsk_pool_dma_unmap(pool, IXGBE_RX_DMA_ATTR); + return err; + } + } + + return 0; +} + +static int ixgbe_xsk_pool_disable(struct ixgbe_adapter *adapter, u16 qid) +{ + struct xsk_buff_pool *pool; + bool if_running; + + pool = xsk_get_pool_from_qid(adapter->netdev, qid); + if (!pool) + return -EINVAL; + + if_running = netif_running(adapter->netdev) && + ixgbe_enabled_xdp_adapter(adapter); + + if (if_running) + ixgbe_txrx_ring_disable(adapter, qid); + + clear_bit(qid, adapter->af_xdp_zc_qps); + xsk_pool_dma_unmap(pool, IXGBE_RX_DMA_ATTR); + + if (if_running) + ixgbe_txrx_ring_enable(adapter, qid); + + return 0; +} + +int ixgbe_xsk_pool_setup(struct ixgbe_adapter *adapter, + struct xsk_buff_pool *pool, + u16 qid) +{ + return pool ? ixgbe_xsk_pool_enable(adapter, pool, qid) : + ixgbe_xsk_pool_disable(adapter, qid); +} + +static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter, + struct ixgbe_ring *rx_ring, + struct xdp_buff *xdp) +{ + int err, result = IXGBE_XDP_PASS; + struct bpf_prog *xdp_prog; + struct xdp_frame *xdpf; + u32 act; + + rcu_read_lock(); + xdp_prog = READ_ONCE(rx_ring->xdp_prog); + act = bpf_prog_run_xdp(xdp_prog, xdp); + + if (likely(act == XDP_REDIRECT)) { + err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); + if (err) + goto out_failure; + rcu_read_unlock(); + return IXGBE_XDP_REDIR; + } + + switch (act) { + case XDP_PASS: + break; + case XDP_TX: + xdpf = xdp_convert_buff_to_frame(xdp); + if (unlikely(!xdpf)) + goto out_failure; + result = ixgbe_xmit_xdp_ring(adapter, xdpf); + if (result == IXGBE_XDP_CONSUMED) + goto out_failure; + break; + default: + bpf_warn_invalid_xdp_action(act); + fallthrough; + case XDP_ABORTED: +out_failure: + trace_xdp_exception(rx_ring->netdev, xdp_prog, act); + fallthrough; /* handle aborts by dropping packet */ + case XDP_DROP: + result = IXGBE_XDP_CONSUMED; + break; + } + rcu_read_unlock(); + return result; +} + +bool ixgbe_alloc_rx_buffers_zc(struct ixgbe_ring *rx_ring, u16 count) +{ + union ixgbe_adv_rx_desc *rx_desc; + struct ixgbe_rx_buffer *bi; + u16 i = rx_ring->next_to_use; + dma_addr_t dma; + bool ok = true; + + /* nothing to do */ + if (!count) + return true; + + rx_desc = IXGBE_RX_DESC(rx_ring, i); + bi = &rx_ring->rx_buffer_info[i]; + i -= rx_ring->count; + + do { + bi->xdp = xsk_buff_alloc(rx_ring->xsk_pool); + if (!bi->xdp) { + ok = false; + break; + } + + dma = xsk_buff_xdp_get_dma(bi->xdp); + + /* Refresh the desc even if buffer_addrs didn't change + * because each write-back erases this info. + */ + rx_desc->read.pkt_addr = cpu_to_le64(dma); + + rx_desc++; + bi++; + i++; + if (unlikely(!i)) { + rx_desc = IXGBE_RX_DESC(rx_ring, 0); + bi = rx_ring->rx_buffer_info; + i -= rx_ring->count; + } + + /* clear the length for the next_to_use descriptor */ + rx_desc->wb.upper.length = 0; + + count--; + } while (count); + + i += rx_ring->count; + + if (rx_ring->next_to_use != i) { + rx_ring->next_to_use = i; + + /* 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(); + writel(i, rx_ring->tail); + } + + return ok; +} + +static struct sk_buff *ixgbe_construct_skb_zc(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *bi) +{ + unsigned int metasize = bi->xdp->data - bi->xdp->data_meta; + unsigned int datasize = bi->xdp->data_end - bi->xdp->data; + struct sk_buff *skb; + + /* allocate a skb to store the frags */ + skb = __napi_alloc_skb(&rx_ring->q_vector->napi, + bi->xdp->data_end - bi->xdp->data_hard_start, + GFP_ATOMIC | __GFP_NOWARN); + if (unlikely(!skb)) + return NULL; + + skb_reserve(skb, bi->xdp->data - bi->xdp->data_hard_start); + memcpy(__skb_put(skb, datasize), bi->xdp->data, datasize); + if (metasize) + skb_metadata_set(skb, metasize); + + xsk_buff_free(bi->xdp); + bi->xdp = NULL; + return skb; +} + +static void ixgbe_inc_ntc(struct ixgbe_ring *rx_ring) +{ + u32 ntc = rx_ring->next_to_clean + 1; + + ntc = (ntc < rx_ring->count) ? ntc : 0; + rx_ring->next_to_clean = ntc; + prefetch(IXGBE_RX_DESC(rx_ring, ntc)); +} + +int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, + struct ixgbe_ring *rx_ring, + const int budget) +{ + unsigned int total_rx_bytes = 0, total_rx_packets = 0; + struct ixgbe_adapter *adapter = q_vector->adapter; + u16 cleaned_count = ixgbe_desc_unused(rx_ring); + unsigned int xdp_res, xdp_xmit = 0; + bool failure = false; + struct sk_buff *skb; + + while (likely(total_rx_packets < budget)) { + union ixgbe_adv_rx_desc *rx_desc; + struct ixgbe_rx_buffer *bi; + unsigned int size; + + /* return some buffers to hardware, one at a time is too slow */ + if (cleaned_count >= IXGBE_RX_BUFFER_WRITE) { + failure = failure || + !ixgbe_alloc_rx_buffers_zc(rx_ring, + cleaned_count); + cleaned_count = 0; + } + + rx_desc = IXGBE_RX_DESC(rx_ring, rx_ring->next_to_clean); + size = le16_to_cpu(rx_desc->wb.upper.length); + if (!size) + break; + + /* This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc until we know the + * descriptor has been written back + */ + dma_rmb(); + + bi = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + + if (unlikely(!ixgbe_test_staterr(rx_desc, + IXGBE_RXD_STAT_EOP))) { + struct ixgbe_rx_buffer *next_bi; + + xsk_buff_free(bi->xdp); + bi->xdp = NULL; + ixgbe_inc_ntc(rx_ring); + next_bi = + &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + next_bi->discard = true; + continue; + } + + if (unlikely(bi->discard)) { + xsk_buff_free(bi->xdp); + bi->xdp = NULL; + bi->discard = false; + ixgbe_inc_ntc(rx_ring); + continue; + } + + bi->xdp->data_end = bi->xdp->data + size; + xsk_buff_dma_sync_for_cpu(bi->xdp, rx_ring->xsk_pool); + xdp_res = ixgbe_run_xdp_zc(adapter, rx_ring, bi->xdp); + + if (xdp_res) { + if (xdp_res & (IXGBE_XDP_TX | IXGBE_XDP_REDIR)) + xdp_xmit |= xdp_res; + else + xsk_buff_free(bi->xdp); + + bi->xdp = NULL; + total_rx_packets++; + total_rx_bytes += size; + + cleaned_count++; + ixgbe_inc_ntc(rx_ring); + continue; + } + + /* XDP_PASS path */ + skb = ixgbe_construct_skb_zc(rx_ring, bi); + if (!skb) { + rx_ring->rx_stats.alloc_rx_buff_failed++; + break; + } + + cleaned_count++; + ixgbe_inc_ntc(rx_ring); + + if (eth_skb_pad(skb)) + continue; + + total_rx_bytes += skb->len; + total_rx_packets++; + + ixgbe_process_skb_fields(rx_ring, rx_desc, skb); + ixgbe_rx_skb(q_vector, skb); + } + + if (xdp_xmit & IXGBE_XDP_REDIR) + xdp_do_flush_map(); + + if (xdp_xmit & IXGBE_XDP_TX) { + struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()]; + + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. + */ + wmb(); + writel(ring->next_to_use, ring->tail); + } + + u64_stats_update_begin(&rx_ring->syncp); + rx_ring->stats.packets += total_rx_packets; + rx_ring->stats.bytes += total_rx_bytes; + u64_stats_update_end(&rx_ring->syncp); + q_vector->rx.total_packets += total_rx_packets; + q_vector->rx.total_bytes += total_rx_bytes; + + if (xsk_uses_need_wakeup(rx_ring->xsk_pool)) { + if (failure || rx_ring->next_to_clean == rx_ring->next_to_use) + xsk_set_rx_need_wakeup(rx_ring->xsk_pool); + else + xsk_clear_rx_need_wakeup(rx_ring->xsk_pool); + + return (int)total_rx_packets; + } + return failure ? budget : (int)total_rx_packets; +} + +void ixgbe_xsk_clean_rx_ring(struct ixgbe_ring *rx_ring) +{ + struct ixgbe_rx_buffer *bi; + u16 i; + + for (i = 0; i < rx_ring->count; i++) { + bi = &rx_ring->rx_buffer_info[i]; + + if (!bi->xdp) + continue; + + xsk_buff_free(bi->xdp); + bi->xdp = NULL; + } +} + +static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) +{ + struct xsk_buff_pool *pool = xdp_ring->xsk_pool; + union ixgbe_adv_tx_desc *tx_desc = NULL; + struct ixgbe_tx_buffer *tx_bi; + bool work_done = true; + struct xdp_desc desc; + dma_addr_t dma; + u32 cmd_type; + + while (budget-- > 0) { + if (unlikely(!ixgbe_desc_unused(xdp_ring))) { + work_done = false; + break; + } + + if (!netif_carrier_ok(xdp_ring->netdev)) + break; + + if (!xsk_tx_peek_desc(pool, &desc)) + break; + + dma = xsk_buff_raw_get_dma(pool, desc.addr); + xsk_buff_raw_dma_sync_for_device(pool, dma, desc.len); + + tx_bi = &xdp_ring->tx_buffer_info[xdp_ring->next_to_use]; + tx_bi->bytecount = desc.len; + tx_bi->xdpf = NULL; + tx_bi->gso_segs = 1; + + tx_desc = IXGBE_TX_DESC(xdp_ring, xdp_ring->next_to_use); + tx_desc->read.buffer_addr = cpu_to_le64(dma); + + /* put descriptor type bits */ + cmd_type = IXGBE_ADVTXD_DTYP_DATA | + IXGBE_ADVTXD_DCMD_DEXT | + IXGBE_ADVTXD_DCMD_IFCS; + cmd_type |= desc.len | IXGBE_TXD_CMD; + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); + tx_desc->read.olinfo_status = + cpu_to_le32(desc.len << IXGBE_ADVTXD_PAYLEN_SHIFT); + + xdp_ring->next_to_use++; + if (xdp_ring->next_to_use == xdp_ring->count) + xdp_ring->next_to_use = 0; + } + + if (tx_desc) { + ixgbe_xdp_ring_update_tail(xdp_ring); + xsk_tx_release(pool); + } + + return !!budget && work_done; +} + +static void ixgbe_clean_xdp_tx_buffer(struct ixgbe_ring *tx_ring, + struct ixgbe_tx_buffer *tx_bi) +{ + xdp_return_frame(tx_bi->xdpf); + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_bi, dma), + dma_unmap_len(tx_bi, len), DMA_TO_DEVICE); + dma_unmap_len_set(tx_bi, len, 0); +} + +bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector, + struct ixgbe_ring *tx_ring, int napi_budget) +{ + u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use; + unsigned int total_packets = 0, total_bytes = 0; + struct xsk_buff_pool *pool = tx_ring->xsk_pool; + union ixgbe_adv_tx_desc *tx_desc; + struct ixgbe_tx_buffer *tx_bi; + u32 xsk_frames = 0; + + tx_bi = &tx_ring->tx_buffer_info[ntc]; + tx_desc = IXGBE_TX_DESC(tx_ring, ntc); + + while (ntc != ntu) { + if (!(tx_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD))) + break; + + total_bytes += tx_bi->bytecount; + total_packets += tx_bi->gso_segs; + + if (tx_bi->xdpf) + ixgbe_clean_xdp_tx_buffer(tx_ring, tx_bi); + else + xsk_frames++; + + tx_bi->xdpf = NULL; + + tx_bi++; + tx_desc++; + ntc++; + if (unlikely(ntc == tx_ring->count)) { + ntc = 0; + tx_bi = tx_ring->tx_buffer_info; + tx_desc = IXGBE_TX_DESC(tx_ring, 0); + } + + /* issue prefetch for next Tx descriptor */ + prefetch(tx_desc); + } + + tx_ring->next_to_clean = ntc; + + u64_stats_update_begin(&tx_ring->syncp); + tx_ring->stats.bytes += total_bytes; + tx_ring->stats.packets += total_packets; + u64_stats_update_end(&tx_ring->syncp); + q_vector->tx.total_bytes += total_bytes; + q_vector->tx.total_packets += total_packets; + + if (xsk_frames) + xsk_tx_completed(pool, xsk_frames); + + if (xsk_uses_need_wakeup(pool)) + xsk_set_tx_need_wakeup(pool); + + return ixgbe_xmit_zc(tx_ring, q_vector->tx.work_limit); +} + +int ixgbe_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_ring *ring; + + if (test_bit(__IXGBE_DOWN, &adapter->state)) + return -ENETDOWN; + + if (!READ_ONCE(adapter->xdp_prog)) + return -ENXIO; + + if (qid >= adapter->num_xdp_queues) + return -ENXIO; + + ring = adapter->xdp_ring[qid]; + + if (test_bit(__IXGBE_TX_DISABLED, &ring->state)) + return -ENETDOWN; + + if (!ring->xsk_pool) + return -ENXIO; + + if (!napi_if_scheduled_mark_missed(&ring->q_vector->napi)) { + u64 eics = BIT_ULL(ring->q_vector->v_idx); + + ixgbe_irq_rearm_queues(adapter, eics); + } + + return 0; +} + +void ixgbe_xsk_clean_tx_ring(struct ixgbe_ring *tx_ring) +{ + u16 ntc = tx_ring->next_to_clean, ntu = tx_ring->next_to_use; + struct xsk_buff_pool *pool = tx_ring->xsk_pool; + struct ixgbe_tx_buffer *tx_bi; + u32 xsk_frames = 0; + + while (ntc != ntu) { + tx_bi = &tx_ring->tx_buffer_info[ntc]; + + if (tx_bi->xdpf) + ixgbe_clean_xdp_tx_buffer(tx_ring, tx_bi); + else + xsk_frames++; + + tx_bi->xdpf = NULL; + + ntc++; + if (ntc == tx_ring->count) + ntc = 0; + } + + if (xsk_frames) + xsk_tx_completed(pool, xsk_frames); +} diff --git a/drivers/net/ethernet/intel/ixgbevf/Makefile b/drivers/net/ethernet/intel/ixgbevf/Makefile new file mode 100644 index 000000000..186a4bb24 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbevf/Makefile @@ -0,0 +1,14 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright(c) 1999 - 2018 Intel Corporation. +# +# Makefile for the Intel(R) 82599 VF ethernet driver +# + +obj-$(CONFIG_IXGBEVF) += ixgbevf.o + +ixgbevf-objs := vf.o \ + mbx.o \ + ethtool.o \ + ixgbevf_main.o +ixgbevf-$(CONFIG_IXGBEVF_IPSEC) += ipsec.o + diff --git a/drivers/net/ethernet/intel/ixgbevf/defines.h b/drivers/net/ethernet/intel/ixgbevf/defines.h new file mode 100644 index 000000000..6bace746e --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbevf/defines.h @@ -0,0 +1,302 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#ifndef _IXGBEVF_DEFINES_H_ +#define _IXGBEVF_DEFINES_H_ + +/* Device IDs */ +#define IXGBE_DEV_ID_82599_VF 0x10ED +#define IXGBE_DEV_ID_X540_VF 0x1515 +#define IXGBE_DEV_ID_X550_VF 0x1565 +#define IXGBE_DEV_ID_X550EM_X_VF 0x15A8 +#define IXGBE_DEV_ID_X550EM_A_VF 0x15C5 + +#define IXGBE_DEV_ID_82599_VF_HV 0x152E +#define IXGBE_DEV_ID_X540_VF_HV 0x1530 +#define IXGBE_DEV_ID_X550_VF_HV 0x1564 +#define IXGBE_DEV_ID_X550EM_X_VF_HV 0x15A9 + +#define IXGBE_VF_IRQ_CLEAR_MASK 7 +#define IXGBE_VF_MAX_TX_QUEUES 8 +#define IXGBE_VF_MAX_RX_QUEUES 8 + +/* DCB define */ +#define IXGBE_VF_MAX_TRAFFIC_CLASS 8 + +/* Link speed */ +typedef u32 ixgbe_link_speed; +#define IXGBE_LINK_SPEED_1GB_FULL 0x0020 +#define IXGBE_LINK_SPEED_10GB_FULL 0x0080 +#define IXGBE_LINK_SPEED_100_FULL 0x0008 + +#define IXGBE_CTRL_RST 0x04000000 /* Reset (SW) */ +#define IXGBE_RXDCTL_ENABLE 0x02000000 /* Enable specific Rx Queue */ +#define IXGBE_TXDCTL_ENABLE 0x02000000 /* Enable specific Tx Queue */ +#define IXGBE_LINKS_UP 0x40000000 +#define IXGBE_LINKS_SPEED_82599 0x30000000 +#define IXGBE_LINKS_SPEED_10G_82599 0x30000000 +#define IXGBE_LINKS_SPEED_1G_82599 0x20000000 +#define IXGBE_LINKS_SPEED_100_82599 0x10000000 + +/* Number of Transmit and Receive Descriptors must be a multiple of 8 */ +#define IXGBE_REQ_TX_DESCRIPTOR_MULTIPLE 8 +#define IXGBE_REQ_RX_DESCRIPTOR_MULTIPLE 8 +#define IXGBE_REQ_TX_BUFFER_GRANULARITY 1024 + +/* Interrupt Vector Allocation Registers */ +#define IXGBE_IVAR_ALLOC_VAL 0x80 /* Interrupt Allocation valid */ + +#define IXGBE_VF_INIT_TIMEOUT 200 /* Number of retries to clear RSTI */ + +/* Receive Config masks */ +#define IXGBE_RXCTRL_RXEN 0x00000001 /* Enable Receiver */ +#define IXGBE_RXCTRL_DMBYPS 0x00000002 /* Descriptor Monitor Bypass */ +#define IXGBE_RXDCTL_ENABLE 0x02000000 /* Enable specific Rx Queue */ +#define IXGBE_RXDCTL_VME 0x40000000 /* VLAN mode enable */ +#define IXGBE_RXDCTL_RLPMLMASK 0x00003FFF /* Only supported on the X540 */ +#define IXGBE_RXDCTL_RLPML_EN 0x00008000 + +/* DCA Control */ +#define IXGBE_DCA_TXCTRL_TX_WB_RO_EN BIT(11) /* Tx Desc writeback RO bit */ + +/* PSRTYPE bit definitions */ +#define IXGBE_PSRTYPE_TCPHDR 0x00000010 +#define IXGBE_PSRTYPE_UDPHDR 0x00000020 +#define IXGBE_PSRTYPE_IPV4HDR 0x00000100 +#define IXGBE_PSRTYPE_IPV6HDR 0x00000200 +#define IXGBE_PSRTYPE_L2HDR 0x00001000 + +/* SRRCTL bit definitions */ +#define IXGBE_SRRCTL_BSIZEPKT_SHIFT 10 /* so many KBs */ +#define IXGBE_SRRCTL_RDMTS_SHIFT 22 +#define IXGBE_SRRCTL_RDMTS_MASK 0x01C00000 +#define IXGBE_SRRCTL_DROP_EN 0x10000000 +#define IXGBE_SRRCTL_BSIZEPKT_MASK 0x0000007F +#define IXGBE_SRRCTL_BSIZEHDR_MASK 0x00003F00 +#define IXGBE_SRRCTL_DESCTYPE_LEGACY 0x00000000 +#define IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF 0x02000000 +#define IXGBE_SRRCTL_DESCTYPE_HDR_SPLIT 0x04000000 +#define IXGBE_SRRCTL_DESCTYPE_HDR_REPLICATION_LARGE_PKT 0x08000000 +#define IXGBE_SRRCTL_DESCTYPE_HDR_SPLIT_ALWAYS 0x0A000000 +#define IXGBE_SRRCTL_DESCTYPE_MASK 0x0E000000 + +/* Receive Descriptor bit definitions */ +#define IXGBE_RXD_STAT_DD 0x01 /* Descriptor Done */ +#define IXGBE_RXD_STAT_EOP 0x02 /* End of Packet */ +#define IXGBE_RXD_STAT_FLM 0x04 /* FDir Match */ +#define IXGBE_RXD_STAT_VP 0x08 /* IEEE VLAN Packet */ +#define IXGBE_RXDADV_NEXTP_MASK 0x000FFFF0 /* Next Descriptor Index */ +#define IXGBE_RXDADV_NEXTP_SHIFT 0x00000004 +#define IXGBE_RXD_STAT_UDPCS 0x10 /* UDP xsum calculated */ +#define IXGBE_RXD_STAT_L4CS 0x20 /* L4 xsum calculated */ +#define IXGBE_RXD_STAT_IPCS 0x40 /* IP xsum calculated */ +#define IXGBE_RXD_STAT_PIF 0x80 /* passed in-exact filter */ +#define IXGBE_RXD_STAT_CRCV 0x100 /* Speculative CRC Valid */ +#define IXGBE_RXD_STAT_VEXT 0x200 /* 1st VLAN found */ +#define IXGBE_RXD_STAT_UDPV 0x400 /* Valid UDP checksum */ +#define IXGBE_RXD_STAT_DYNINT 0x800 /* Pkt caused INT via DYNINT */ +#define IXGBE_RXD_STAT_TS 0x10000 /* Time Stamp */ +#define IXGBE_RXD_STAT_SECP 0x20000 /* Security Processing */ +#define IXGBE_RXD_STAT_LB 0x40000 /* Loopback Status */ +#define IXGBE_RXD_STAT_ACK 0x8000 /* ACK Packet indication */ +#define IXGBE_RXD_ERR_CE 0x01 /* CRC Error */ +#define IXGBE_RXD_ERR_LE 0x02 /* Length Error */ +#define IXGBE_RXD_ERR_PE 0x08 /* Packet Error */ +#define IXGBE_RXD_ERR_OSE 0x10 /* Oversize Error */ +#define IXGBE_RXD_ERR_USE 0x20 /* Undersize Error */ +#define IXGBE_RXD_ERR_TCPE 0x40 /* TCP/UDP Checksum Error */ +#define IXGBE_RXD_ERR_IPE 0x80 /* IP Checksum Error */ +#define IXGBE_RXDADV_ERR_MASK 0xFFF00000 /* RDESC.ERRORS mask */ +#define IXGBE_RXDADV_ERR_SHIFT 20 /* RDESC.ERRORS shift */ +#define IXGBE_RXDADV_ERR_HBO 0x00800000 /*Header Buffer Overflow */ +#define IXGBE_RXDADV_ERR_CE 0x01000000 /* CRC Error */ +#define IXGBE_RXDADV_ERR_LE 0x02000000 /* Length Error */ +#define IXGBE_RXDADV_ERR_PE 0x08000000 /* Packet Error */ +#define IXGBE_RXDADV_ERR_OSE 0x10000000 /* Oversize Error */ +#define IXGBE_RXDADV_ERR_USE 0x20000000 /* Undersize Error */ +#define IXGBE_RXDADV_ERR_TCPE 0x40000000 /* TCP/UDP Checksum Error */ +#define IXGBE_RXDADV_ERR_IPE 0x80000000 /* IP Checksum Error */ +#define IXGBE_RXD_VLAN_ID_MASK 0x0FFF /* VLAN ID is in lower 12 bits */ +#define IXGBE_RXD_PRI_MASK 0xE000 /* Priority is in upper 3 bits */ +#define IXGBE_RXD_PRI_SHIFT 13 +#define IXGBE_RXD_CFI_MASK 0x1000 /* CFI is bit 12 */ +#define IXGBE_RXD_CFI_SHIFT 12 + +#define IXGBE_RXDADV_STAT_DD IXGBE_RXD_STAT_DD /* Done */ +#define IXGBE_RXDADV_STAT_EOP IXGBE_RXD_STAT_EOP /* End of Packet */ +#define IXGBE_RXDADV_STAT_FLM IXGBE_RXD_STAT_FLM /* FDir Match */ +#define IXGBE_RXDADV_STAT_VP IXGBE_RXD_STAT_VP /* IEEE VLAN Pkt */ +#define IXGBE_RXDADV_STAT_MASK 0x000FFFFF /* Stat/NEXTP: bit 0-19 */ +#define IXGBE_RXDADV_STAT_FCEOFS 0x00000040 /* FCoE EOF/SOF Stat */ +#define IXGBE_RXDADV_STAT_FCSTAT 0x00000030 /* FCoE Pkt Stat */ +#define IXGBE_RXDADV_STAT_FCSTAT_NOMTCH 0x00000000 /* 00: No Ctxt Match */ +#define IXGBE_RXDADV_STAT_FCSTAT_NODDP 0x00000010 /* 01: Ctxt w/o DDP */ +#define IXGBE_RXDADV_STAT_FCSTAT_FCPRSP 0x00000020 /* 10: Recv. FCP_RSP */ +#define IXGBE_RXDADV_STAT_FCSTAT_DDP 0x00000030 /* 11: Ctxt w/ DDP */ +#define IXGBE_RXDADV_STAT_SECP 0x00020000 /* IPsec/MACsec pkt found */ + +#define IXGBE_RXDADV_RSSTYPE_MASK 0x0000000F +#define IXGBE_RXDADV_PKTTYPE_MASK 0x0000FFF0 +#define IXGBE_RXDADV_PKTTYPE_IPV4 0x00000010 /* IPv4 hdr present */ +#define IXGBE_RXDADV_PKTTYPE_IPV6 0x00000040 /* IPv6 hdr present */ +#define IXGBE_RXDADV_PKTTYPE_IPSEC_ESP 0x00001000 /* IPSec ESP */ +#define IXGBE_RXDADV_PKTTYPE_IPSEC_AH 0x00002000 /* IPSec AH */ +#define IXGBE_RXDADV_PKTTYPE_MASK_EX 0x0001FFF0 +#define IXGBE_RXDADV_HDRBUFLEN_MASK 0x00007FE0 +#define IXGBE_RXDADV_RSCCNT_MASK 0x001E0000 +#define IXGBE_RXDADV_RSCCNT_SHIFT 17 +#define IXGBE_RXDADV_HDRBUFLEN_SHIFT 5 +#define IXGBE_RXDADV_SPLITHEADER_EN 0x00001000 +#define IXGBE_RXDADV_SPH 0x8000 + +/* RSS Hash results */ +#define IXGBE_RXDADV_RSSTYPE_NONE 0x00000000 +#define IXGBE_RXDADV_RSSTYPE_IPV4_TCP 0x00000001 +#define IXGBE_RXDADV_RSSTYPE_IPV4 0x00000002 +#define IXGBE_RXDADV_RSSTYPE_IPV6_TCP 0x00000003 +#define IXGBE_RXDADV_RSSTYPE_IPV6_EX 0x00000004 +#define IXGBE_RXDADV_RSSTYPE_IPV6 0x00000005 +#define IXGBE_RXDADV_RSSTYPE_IPV6_TCP_EX 0x00000006 +#define IXGBE_RXDADV_RSSTYPE_IPV4_UDP 0x00000007 +#define IXGBE_RXDADV_RSSTYPE_IPV6_UDP 0x00000008 +#define IXGBE_RXDADV_RSSTYPE_IPV6_UDP_EX 0x00000009 + +#define IXGBE_RXD_ERR_FRAME_ERR_MASK ( \ + IXGBE_RXD_ERR_CE | \ + IXGBE_RXD_ERR_LE | \ + IXGBE_RXD_ERR_PE | \ + IXGBE_RXD_ERR_OSE | \ + IXGBE_RXD_ERR_USE) + +#define IXGBE_RXDADV_ERR_FRAME_ERR_MASK ( \ + IXGBE_RXDADV_ERR_CE | \ + IXGBE_RXDADV_ERR_LE | \ + IXGBE_RXDADV_ERR_PE | \ + IXGBE_RXDADV_ERR_OSE | \ + IXGBE_RXDADV_ERR_USE) + +#define IXGBE_TXD_POPTS_IXSM 0x01 /* Insert IP checksum */ +#define IXGBE_TXD_POPTS_TXSM 0x02 /* Insert TCP/UDP checksum */ +#define IXGBE_TXD_CMD_EOP 0x01000000 /* End of Packet */ +#define IXGBE_TXD_CMD_IFCS 0x02000000 /* Insert FCS (Ethernet CRC) */ +#define IXGBE_TXD_CMD_IC 0x04000000 /* Insert Checksum */ +#define IXGBE_TXD_CMD_RS 0x08000000 /* Report Status */ +#define IXGBE_TXD_CMD_DEXT 0x20000000 /* Descriptor ext (0 = legacy) */ +#define IXGBE_TXD_CMD_VLE 0x40000000 /* Add VLAN tag */ +#define IXGBE_TXD_STAT_DD 0x00000001 /* Descriptor Done */ +#define IXGBE_TXD_CMD (IXGBE_TXD_CMD_EOP | IXGBE_TXD_CMD_RS) + +/* Transmit Descriptor - Advanced */ +union ixgbe_adv_tx_desc { + struct { + __le64 buffer_addr; /* Address of descriptor's data buf */ + __le32 cmd_type_len; + __le32 olinfo_status; + } read; + struct { + __le64 rsvd; /* Reserved */ + __le32 nxtseq_seed; + __le32 status; + } wb; +}; + +/* Receive Descriptor - Advanced */ +union ixgbe_adv_rx_desc { + struct { + __le64 pkt_addr; /* Packet buffer address */ + __le64 hdr_addr; /* Header buffer address */ + } read; + struct { + struct { + union { + __le32 data; + struct { + __le16 pkt_info; /* RSS, Pkt type */ + __le16 hdr_info; /* Splithdr, hdrlen */ + } hs_rss; + } lo_dword; + union { + __le32 rss; /* RSS Hash */ + struct { + __le16 ip_id; /* IP id */ + __le16 csum; /* Packet Checksum */ + } csum_ip; + } hi_dword; + } lower; + struct { + __le32 status_error; /* ext status/error */ + __le16 length; /* Packet length */ + __le16 vlan; /* VLAN tag */ + } upper; + } wb; /* writeback */ +}; + +/* Context descriptors */ +struct ixgbe_adv_tx_context_desc { + __le32 vlan_macip_lens; + __le32 fceof_saidx; + __le32 type_tucmd_mlhl; + __le32 mss_l4len_idx; +}; + +/* Adv Transmit Descriptor Config Masks */ +#define IXGBE_ADVTXD_DTYP_MASK 0x00F00000 /* DTYP mask */ +#define IXGBE_ADVTXD_DTYP_CTXT 0x00200000 /* Advanced Context Desc */ +#define IXGBE_ADVTXD_DTYP_DATA 0x00300000 /* Advanced Data Descriptor */ +#define IXGBE_ADVTXD_DCMD_EOP IXGBE_TXD_CMD_EOP /* End of Packet */ +#define IXGBE_ADVTXD_DCMD_IFCS IXGBE_TXD_CMD_IFCS /* Insert FCS */ +#define IXGBE_ADVTXD_DCMD_RS IXGBE_TXD_CMD_RS /* Report Status */ +#define IXGBE_ADVTXD_DCMD_DEXT IXGBE_TXD_CMD_DEXT /* Desc ext (1=Adv) */ +#define IXGBE_ADVTXD_DCMD_VLE IXGBE_TXD_CMD_VLE /* VLAN pkt enable */ +#define IXGBE_ADVTXD_DCMD_TSE 0x80000000 /* TCP Seg enable */ +#define IXGBE_ADVTXD_STAT_DD IXGBE_TXD_STAT_DD /* Descriptor Done */ +#define IXGBE_ADVTXD_TUCMD_IPV4 0x00000400 /* IP Packet Type: 1=IPv4 */ +#define IXGBE_ADVTXD_TUCMD_IPV6 0x00000000 /* IP Packet Type: 0=IPv6 */ +#define IXGBE_ADVTXD_TUCMD_L4T_UDP 0x00000000 /* L4 Packet TYPE of UDP */ +#define IXGBE_ADVTXD_TUCMD_L4T_TCP 0x00000800 /* L4 Packet TYPE of TCP */ +#define IXGBE_ADVTXD_TUCMD_L4T_SCTP 0x00001000 /* L4 Packet TYPE of SCTP */ +#define IXGBE_ADVTXD_TUCMD_IPSEC_TYPE_ESP 0x00002000 /* IPSec Type ESP */ +#define IXGBE_ADVTXD_TUCMD_IPSEC_ENCRYPT_EN 0x00004000 /* ESP Encrypt Enable */ +#define IXGBE_ADVTXD_IDX_SHIFT 4 /* Adv desc Index shift */ +#define IXGBE_ADVTXD_CC 0x00000080 /* Check Context */ +#define IXGBE_ADVTXD_POPTS_SHIFT 8 /* Adv desc POPTS shift */ +#define IXGBE_ADVTXD_POPTS_IPSEC 0x00000400 /* IPSec offload request */ +#define IXGBE_ADVTXD_POPTS_IXSM (IXGBE_TXD_POPTS_IXSM << \ + IXGBE_ADVTXD_POPTS_SHIFT) +#define IXGBE_ADVTXD_POPTS_TXSM (IXGBE_TXD_POPTS_TXSM << \ + IXGBE_ADVTXD_POPTS_SHIFT) +#define IXGBE_ADVTXD_PAYLEN_SHIFT 14 /* Adv desc PAYLEN shift */ +#define IXGBE_ADVTXD_MACLEN_SHIFT 9 /* Adv ctxt desc mac len shift */ +#define IXGBE_ADVTXD_VLAN_SHIFT 16 /* Adv ctxt vlan tag shift */ +#define IXGBE_ADVTXD_L4LEN_SHIFT 8 /* Adv ctxt L4LEN shift */ +#define IXGBE_ADVTXD_MSS_SHIFT 16 /* Adv ctxt MSS shift */ + +/* Interrupt register bitmasks */ + +#define IXGBE_EITR_CNT_WDIS 0x80000000 +#define IXGBE_MAX_EITR 0x00000FF8 +#define IXGBE_MIN_EITR 8 + +/* Error Codes */ +#define IXGBE_ERR_INVALID_MAC_ADDR -1 +#define IXGBE_ERR_RESET_FAILED -2 +#define IXGBE_ERR_INVALID_ARGUMENT -3 + +/* Transmit Config masks */ +#define IXGBE_TXDCTL_ENABLE 0x02000000 /* Ena specific Tx Queue */ +#define IXGBE_TXDCTL_SWFLSH 0x04000000 /* Tx Desc. wr-bk flushing */ +#define IXGBE_TXDCTL_WTHRESH_SHIFT 16 /* shift to WTHRESH bits */ + +#define IXGBE_DCA_RXCTRL_DESC_DCA_EN BIT(5) /* Rx Desc enable */ +#define IXGBE_DCA_RXCTRL_HEAD_DCA_EN BIT(6) /* Rx Desc header ena */ +#define IXGBE_DCA_RXCTRL_DATA_DCA_EN BIT(7) /* Rx Desc payload ena */ +#define IXGBE_DCA_RXCTRL_DESC_RRO_EN BIT(9) /* Rx rd Desc Relax Order */ +#define IXGBE_DCA_RXCTRL_DATA_WRO_EN BIT(13) /* Rx wr data Relax Order */ +#define IXGBE_DCA_RXCTRL_HEAD_WRO_EN BIT(15) /* Rx wr header RO */ + +#define IXGBE_DCA_TXCTRL_DESC_DCA_EN BIT(5) /* DCA Tx Desc enable */ +#define IXGBE_DCA_TXCTRL_DESC_RRO_EN BIT(9) /* Tx rd Desc Relax Order */ +#define IXGBE_DCA_TXCTRL_DESC_WRO_EN BIT(11) /* Tx Desc writeback RO bit */ +#define IXGBE_DCA_TXCTRL_DATA_RRO_EN BIT(13) /* Tx rd data Relax Order */ + +#endif /* _IXGBEVF_DEFINES_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c new file mode 100644 index 000000000..e49fb1cd9 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c @@ -0,0 +1,997 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +/* ethtool support for ixgbevf */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/types.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/pci.h> +#include <linux/netdevice.h> +#include <linux/ethtool.h> +#include <linux/vmalloc.h> +#include <linux/if_vlan.h> +#include <linux/uaccess.h> + +#include "ixgbevf.h" + +#define IXGBE_ALL_RAR_ENTRIES 16 + +enum {NETDEV_STATS, IXGBEVF_STATS}; + +struct ixgbe_stats { + char stat_string[ETH_GSTRING_LEN]; + int type; + int sizeof_stat; + int stat_offset; +}; + +#define IXGBEVF_STAT(_name, _stat) { \ + .stat_string = _name, \ + .type = IXGBEVF_STATS, \ + .sizeof_stat = sizeof_field(struct ixgbevf_adapter, _stat), \ + .stat_offset = offsetof(struct ixgbevf_adapter, _stat) \ +} + +#define IXGBEVF_NETDEV_STAT(_net_stat) { \ + .stat_string = #_net_stat, \ + .type = NETDEV_STATS, \ + .sizeof_stat = sizeof_field(struct net_device_stats, _net_stat), \ + .stat_offset = offsetof(struct net_device_stats, _net_stat) \ +} + +static struct ixgbe_stats ixgbevf_gstrings_stats[] = { + IXGBEVF_NETDEV_STAT(rx_packets), + IXGBEVF_NETDEV_STAT(tx_packets), + IXGBEVF_NETDEV_STAT(rx_bytes), + IXGBEVF_NETDEV_STAT(tx_bytes), + IXGBEVF_STAT("tx_busy", tx_busy), + IXGBEVF_STAT("tx_restart_queue", restart_queue), + IXGBEVF_STAT("tx_timeout_count", tx_timeout_count), + IXGBEVF_NETDEV_STAT(multicast), + IXGBEVF_STAT("rx_csum_offload_errors", hw_csum_rx_error), + IXGBEVF_STAT("alloc_rx_page", alloc_rx_page), + IXGBEVF_STAT("alloc_rx_page_failed", alloc_rx_page_failed), + IXGBEVF_STAT("alloc_rx_buff_failed", alloc_rx_buff_failed), + IXGBEVF_STAT("tx_ipsec", tx_ipsec), + IXGBEVF_STAT("rx_ipsec", rx_ipsec), +}; + +#define IXGBEVF_QUEUE_STATS_LEN ( \ + (((struct ixgbevf_adapter *)netdev_priv(netdev))->num_tx_queues + \ + ((struct ixgbevf_adapter *)netdev_priv(netdev))->num_xdp_queues + \ + ((struct ixgbevf_adapter *)netdev_priv(netdev))->num_rx_queues) * \ + (sizeof(struct ixgbevf_stats) / sizeof(u64))) +#define IXGBEVF_GLOBAL_STATS_LEN ARRAY_SIZE(ixgbevf_gstrings_stats) + +#define IXGBEVF_STATS_LEN (IXGBEVF_GLOBAL_STATS_LEN + IXGBEVF_QUEUE_STATS_LEN) +static const char ixgbe_gstrings_test[][ETH_GSTRING_LEN] = { + "Register test (offline)", + "Link test (on/offline)" +}; + +#define IXGBEVF_TEST_LEN (sizeof(ixgbe_gstrings_test) / ETH_GSTRING_LEN) + +static const char ixgbevf_priv_flags_strings[][ETH_GSTRING_LEN] = { +#define IXGBEVF_PRIV_FLAGS_LEGACY_RX BIT(0) + "legacy-rx", +}; + +#define IXGBEVF_PRIV_FLAGS_STR_LEN ARRAY_SIZE(ixgbevf_priv_flags_strings) + +static int ixgbevf_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *cmd) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + + ethtool_link_ksettings_zero_link_mode(cmd, supported); + ethtool_link_ksettings_add_link_mode(cmd, supported, 10000baseT_Full); + cmd->base.autoneg = AUTONEG_DISABLE; + cmd->base.port = -1; + + if (adapter->link_up) { + __u32 speed = SPEED_10000; + + switch (adapter->link_speed) { + case IXGBE_LINK_SPEED_10GB_FULL: + speed = SPEED_10000; + break; + case IXGBE_LINK_SPEED_1GB_FULL: + speed = SPEED_1000; + break; + case IXGBE_LINK_SPEED_100_FULL: + speed = SPEED_100; + break; + } + + cmd->base.speed = speed; + cmd->base.duplex = DUPLEX_FULL; + } else { + cmd->base.speed = SPEED_UNKNOWN; + cmd->base.duplex = DUPLEX_UNKNOWN; + } + + return 0; +} + +static u32 ixgbevf_get_msglevel(struct net_device *netdev) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + + return adapter->msg_enable; +} + +static void ixgbevf_set_msglevel(struct net_device *netdev, u32 data) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + + adapter->msg_enable = data; +} + +#define IXGBE_GET_STAT(_A_, _R_) (_A_->stats._R_) + +static int ixgbevf_get_regs_len(struct net_device *netdev) +{ +#define IXGBE_REGS_LEN 45 + return IXGBE_REGS_LEN * sizeof(u32); +} + +static void ixgbevf_get_regs(struct net_device *netdev, + struct ethtool_regs *regs, + void *p) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + u32 *regs_buff = p; + u32 regs_len = ixgbevf_get_regs_len(netdev); + u8 i; + + memset(p, 0, regs_len); + + /* generate a number suitable for ethtool's register version */ + regs->version = (1u << 24) | (hw->revision_id << 16) | hw->device_id; + + /* General Registers */ + regs_buff[0] = IXGBE_READ_REG(hw, IXGBE_VFCTRL); + regs_buff[1] = IXGBE_READ_REG(hw, IXGBE_VFSTATUS); + regs_buff[2] = IXGBE_READ_REG(hw, IXGBE_VFLINKS); + regs_buff[3] = IXGBE_READ_REG(hw, IXGBE_VFRXMEMWRAP); + regs_buff[4] = IXGBE_READ_REG(hw, IXGBE_VFFRTIMER); + + /* Interrupt */ + /* don't read EICR because it can clear interrupt causes, instead + * read EICS which is a shadow but doesn't clear EICR + */ + regs_buff[5] = IXGBE_READ_REG(hw, IXGBE_VTEICS); + regs_buff[6] = IXGBE_READ_REG(hw, IXGBE_VTEICS); + regs_buff[7] = IXGBE_READ_REG(hw, IXGBE_VTEIMS); + regs_buff[8] = IXGBE_READ_REG(hw, IXGBE_VTEIMC); + regs_buff[9] = IXGBE_READ_REG(hw, IXGBE_VTEIAC); + regs_buff[10] = IXGBE_READ_REG(hw, IXGBE_VTEIAM); + regs_buff[11] = IXGBE_READ_REG(hw, IXGBE_VTEITR(0)); + regs_buff[12] = IXGBE_READ_REG(hw, IXGBE_VTIVAR(0)); + regs_buff[13] = IXGBE_READ_REG(hw, IXGBE_VTIVAR_MISC); + + /* Receive DMA */ + for (i = 0; i < 2; i++) + regs_buff[14 + i] = IXGBE_READ_REG(hw, IXGBE_VFRDBAL(i)); + for (i = 0; i < 2; i++) + regs_buff[16 + i] = IXGBE_READ_REG(hw, IXGBE_VFRDBAH(i)); + for (i = 0; i < 2; i++) + regs_buff[18 + i] = IXGBE_READ_REG(hw, IXGBE_VFRDLEN(i)); + for (i = 0; i < 2; i++) + regs_buff[20 + i] = IXGBE_READ_REG(hw, IXGBE_VFRDH(i)); + for (i = 0; i < 2; i++) + regs_buff[22 + i] = IXGBE_READ_REG(hw, IXGBE_VFRDT(i)); + for (i = 0; i < 2; i++) + regs_buff[24 + i] = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(i)); + for (i = 0; i < 2; i++) + regs_buff[26 + i] = IXGBE_READ_REG(hw, IXGBE_VFSRRCTL(i)); + + /* Receive */ + regs_buff[28] = IXGBE_READ_REG(hw, IXGBE_VFPSRTYPE); + + /* Transmit */ + for (i = 0; i < 2; i++) + regs_buff[29 + i] = IXGBE_READ_REG(hw, IXGBE_VFTDBAL(i)); + for (i = 0; i < 2; i++) + regs_buff[31 + i] = IXGBE_READ_REG(hw, IXGBE_VFTDBAH(i)); + for (i = 0; i < 2; i++) + regs_buff[33 + i] = IXGBE_READ_REG(hw, IXGBE_VFTDLEN(i)); + for (i = 0; i < 2; i++) + regs_buff[35 + i] = IXGBE_READ_REG(hw, IXGBE_VFTDH(i)); + for (i = 0; i < 2; i++) + regs_buff[37 + i] = IXGBE_READ_REG(hw, IXGBE_VFTDT(i)); + for (i = 0; i < 2; i++) + regs_buff[39 + i] = IXGBE_READ_REG(hw, IXGBE_VFTXDCTL(i)); + for (i = 0; i < 2; i++) + regs_buff[41 + i] = IXGBE_READ_REG(hw, IXGBE_VFTDWBAL(i)); + for (i = 0; i < 2; i++) + regs_buff[43 + i] = IXGBE_READ_REG(hw, IXGBE_VFTDWBAH(i)); +} + +static void ixgbevf_get_drvinfo(struct net_device *netdev, + struct ethtool_drvinfo *drvinfo) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + + strlcpy(drvinfo->driver, ixgbevf_driver_name, sizeof(drvinfo->driver)); + strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), + sizeof(drvinfo->bus_info)); + + drvinfo->n_priv_flags = IXGBEVF_PRIV_FLAGS_STR_LEN; +} + +static void ixgbevf_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + + ring->rx_max_pending = IXGBEVF_MAX_RXD; + ring->tx_max_pending = IXGBEVF_MAX_TXD; + ring->rx_pending = adapter->rx_ring_count; + ring->tx_pending = adapter->tx_ring_count; +} + +static int ixgbevf_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + struct ixgbevf_ring *tx_ring = NULL, *rx_ring = NULL; + u32 new_rx_count, new_tx_count; + int i, j, err = 0; + + if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) + return -EINVAL; + + new_tx_count = max_t(u32, ring->tx_pending, IXGBEVF_MIN_TXD); + new_tx_count = min_t(u32, new_tx_count, IXGBEVF_MAX_TXD); + new_tx_count = ALIGN(new_tx_count, IXGBE_REQ_TX_DESCRIPTOR_MULTIPLE); + + new_rx_count = max_t(u32, ring->rx_pending, IXGBEVF_MIN_RXD); + new_rx_count = min_t(u32, new_rx_count, IXGBEVF_MAX_RXD); + new_rx_count = ALIGN(new_rx_count, IXGBE_REQ_RX_DESCRIPTOR_MULTIPLE); + + /* if nothing to do return success */ + if ((new_tx_count == adapter->tx_ring_count) && + (new_rx_count == adapter->rx_ring_count)) + return 0; + + while (test_and_set_bit(__IXGBEVF_RESETTING, &adapter->state)) + usleep_range(1000, 2000); + + if (!netif_running(adapter->netdev)) { + for (i = 0; i < adapter->num_tx_queues; i++) + adapter->tx_ring[i]->count = new_tx_count; + for (i = 0; i < adapter->num_xdp_queues; i++) + adapter->xdp_ring[i]->count = new_tx_count; + for (i = 0; i < adapter->num_rx_queues; i++) + adapter->rx_ring[i]->count = new_rx_count; + adapter->tx_ring_count = new_tx_count; + adapter->xdp_ring_count = new_tx_count; + adapter->rx_ring_count = new_rx_count; + goto clear_reset; + } + + if (new_tx_count != adapter->tx_ring_count) { + tx_ring = vmalloc(array_size(sizeof(*tx_ring), + adapter->num_tx_queues + + adapter->num_xdp_queues)); + if (!tx_ring) { + err = -ENOMEM; + goto clear_reset; + } + + for (i = 0; i < adapter->num_tx_queues; i++) { + /* clone ring and setup updated count */ + tx_ring[i] = *adapter->tx_ring[i]; + tx_ring[i].count = new_tx_count; + err = ixgbevf_setup_tx_resources(&tx_ring[i]); + if (err) { + while (i) { + i--; + ixgbevf_free_tx_resources(&tx_ring[i]); + } + + vfree(tx_ring); + tx_ring = NULL; + + goto clear_reset; + } + } + + for (j = 0; j < adapter->num_xdp_queues; i++, j++) { + /* clone ring and setup updated count */ + tx_ring[i] = *adapter->xdp_ring[j]; + tx_ring[i].count = new_tx_count; + err = ixgbevf_setup_tx_resources(&tx_ring[i]); + if (err) { + while (i) { + i--; + ixgbevf_free_tx_resources(&tx_ring[i]); + } + + vfree(tx_ring); + tx_ring = NULL; + + goto clear_reset; + } + } + } + + if (new_rx_count != adapter->rx_ring_count) { + rx_ring = vmalloc(array_size(sizeof(*rx_ring), + adapter->num_rx_queues)); + if (!rx_ring) { + err = -ENOMEM; + goto clear_reset; + } + + for (i = 0; i < adapter->num_rx_queues; i++) { + /* clone ring and setup updated count */ + rx_ring[i] = *adapter->rx_ring[i]; + + /* Clear copied XDP RX-queue info */ + memset(&rx_ring[i].xdp_rxq, 0, + sizeof(rx_ring[i].xdp_rxq)); + + rx_ring[i].count = new_rx_count; + err = ixgbevf_setup_rx_resources(adapter, &rx_ring[i]); + if (err) { + while (i) { + i--; + ixgbevf_free_rx_resources(&rx_ring[i]); + } + + vfree(rx_ring); + rx_ring = NULL; + + goto clear_reset; + } + } + } + + /* bring interface down to prepare for update */ + ixgbevf_down(adapter); + + /* Tx */ + if (tx_ring) { + for (i = 0; i < adapter->num_tx_queues; i++) { + ixgbevf_free_tx_resources(adapter->tx_ring[i]); + *adapter->tx_ring[i] = tx_ring[i]; + } + adapter->tx_ring_count = new_tx_count; + + for (j = 0; j < adapter->num_xdp_queues; i++, j++) { + ixgbevf_free_tx_resources(adapter->xdp_ring[j]); + *adapter->xdp_ring[j] = tx_ring[i]; + } + adapter->xdp_ring_count = new_tx_count; + + vfree(tx_ring); + tx_ring = NULL; + } + + /* Rx */ + if (rx_ring) { + for (i = 0; i < adapter->num_rx_queues; i++) { + ixgbevf_free_rx_resources(adapter->rx_ring[i]); + *adapter->rx_ring[i] = rx_ring[i]; + } + adapter->rx_ring_count = new_rx_count; + + vfree(rx_ring); + rx_ring = NULL; + } + + /* restore interface using new values */ + ixgbevf_up(adapter); + +clear_reset: + /* free Tx resources if Rx error is encountered */ + if (tx_ring) { + for (i = 0; + i < adapter->num_tx_queues + adapter->num_xdp_queues; i++) + ixgbevf_free_tx_resources(&tx_ring[i]); + vfree(tx_ring); + } + + clear_bit(__IXGBEVF_RESETTING, &adapter->state); + return err; +} + +static int ixgbevf_get_sset_count(struct net_device *netdev, int stringset) +{ + switch (stringset) { + case ETH_SS_TEST: + return IXGBEVF_TEST_LEN; + case ETH_SS_STATS: + return IXGBEVF_STATS_LEN; + case ETH_SS_PRIV_FLAGS: + return IXGBEVF_PRIV_FLAGS_STR_LEN; + default: + return -EINVAL; + } +} + +static void ixgbevf_get_ethtool_stats(struct net_device *netdev, + struct ethtool_stats *stats, u64 *data) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + struct rtnl_link_stats64 temp; + const struct rtnl_link_stats64 *net_stats; + unsigned int start; + struct ixgbevf_ring *ring; + int i, j; + char *p; + + ixgbevf_update_stats(adapter); + net_stats = dev_get_stats(netdev, &temp); + for (i = 0; i < IXGBEVF_GLOBAL_STATS_LEN; i++) { + switch (ixgbevf_gstrings_stats[i].type) { + case NETDEV_STATS: + p = (char *)net_stats + + ixgbevf_gstrings_stats[i].stat_offset; + break; + case IXGBEVF_STATS: + p = (char *)adapter + + ixgbevf_gstrings_stats[i].stat_offset; + break; + default: + data[i] = 0; + continue; + } + + data[i] = (ixgbevf_gstrings_stats[i].sizeof_stat == + sizeof(u64)) ? *(u64 *)p : *(u32 *)p; + } + + /* populate Tx queue data */ + for (j = 0; j < adapter->num_tx_queues; j++) { + ring = adapter->tx_ring[j]; + if (!ring) { + data[i++] = 0; + data[i++] = 0; + continue; + } + + do { + start = u64_stats_fetch_begin_irq(&ring->syncp); + data[i] = ring->stats.packets; + data[i + 1] = ring->stats.bytes; + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + i += 2; + } + + /* populate XDP queue data */ + for (j = 0; j < adapter->num_xdp_queues; j++) { + ring = adapter->xdp_ring[j]; + if (!ring) { + data[i++] = 0; + data[i++] = 0; + continue; + } + + do { + start = u64_stats_fetch_begin_irq(&ring->syncp); + data[i] = ring->stats.packets; + data[i + 1] = ring->stats.bytes; + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + i += 2; + } + + /* populate Rx queue data */ + for (j = 0; j < adapter->num_rx_queues; j++) { + ring = adapter->rx_ring[j]; + if (!ring) { + data[i++] = 0; + data[i++] = 0; + continue; + } + + do { + start = u64_stats_fetch_begin_irq(&ring->syncp); + data[i] = ring->stats.packets; + data[i + 1] = ring->stats.bytes; + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + i += 2; + } +} + +static void ixgbevf_get_strings(struct net_device *netdev, u32 stringset, + u8 *data) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + char *p = (char *)data; + int i; + + switch (stringset) { + case ETH_SS_TEST: + memcpy(data, *ixgbe_gstrings_test, + IXGBEVF_TEST_LEN * ETH_GSTRING_LEN); + break; + case ETH_SS_STATS: + for (i = 0; i < IXGBEVF_GLOBAL_STATS_LEN; i++) { + memcpy(p, ixgbevf_gstrings_stats[i].stat_string, + ETH_GSTRING_LEN); + p += ETH_GSTRING_LEN; + } + + for (i = 0; i < adapter->num_tx_queues; i++) { + sprintf(p, "tx_queue_%u_packets", i); + p += ETH_GSTRING_LEN; + sprintf(p, "tx_queue_%u_bytes", i); + p += ETH_GSTRING_LEN; + } + for (i = 0; i < adapter->num_xdp_queues; i++) { + sprintf(p, "xdp_queue_%u_packets", i); + p += ETH_GSTRING_LEN; + sprintf(p, "xdp_queue_%u_bytes", i); + p += ETH_GSTRING_LEN; + } + for (i = 0; i < adapter->num_rx_queues; i++) { + sprintf(p, "rx_queue_%u_packets", i); + p += ETH_GSTRING_LEN; + sprintf(p, "rx_queue_%u_bytes", i); + p += ETH_GSTRING_LEN; + } + break; + case ETH_SS_PRIV_FLAGS: + memcpy(data, ixgbevf_priv_flags_strings, + IXGBEVF_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN); + break; + } +} + +static int ixgbevf_link_test(struct ixgbevf_adapter *adapter, u64 *data) +{ + struct ixgbe_hw *hw = &adapter->hw; + bool link_up; + u32 link_speed = 0; + *data = 0; + + hw->mac.ops.check_link(hw, &link_speed, &link_up, true); + if (!link_up) + *data = 1; + + return *data; +} + +/* ethtool register test data */ +struct ixgbevf_reg_test { + u16 reg; + u8 array_len; + u8 test_type; + u32 mask; + u32 write; +}; + +/* In the hardware, registers are laid out either singly, in arrays + * spaced 0x40 bytes apart, or in contiguous tables. We assume + * most tests take place on arrays or single registers (handled + * as a single-element array) and special-case the tables. + * Table tests are always pattern tests. + * + * We also make provision for some required setup steps by specifying + * registers to be written without any read-back testing. + */ + +#define PATTERN_TEST 1 +#define SET_READ_TEST 2 +#define WRITE_NO_TEST 3 +#define TABLE32_TEST 4 +#define TABLE64_TEST_LO 5 +#define TABLE64_TEST_HI 6 + +/* default VF register test */ +static const struct ixgbevf_reg_test reg_test_vf[] = { + { IXGBE_VFRDBAL(0), 2, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFF80 }, + { IXGBE_VFRDBAH(0), 2, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { IXGBE_VFRDLEN(0), 2, PATTERN_TEST, 0x000FFF80, 0x000FFFFF }, + { IXGBE_VFRXDCTL(0), 2, WRITE_NO_TEST, 0, IXGBE_RXDCTL_ENABLE }, + { IXGBE_VFRDT(0), 2, PATTERN_TEST, 0x0000FFFF, 0x0000FFFF }, + { IXGBE_VFRXDCTL(0), 2, WRITE_NO_TEST, 0, 0 }, + { IXGBE_VFTDBAL(0), 2, PATTERN_TEST, 0xFFFFFF80, 0xFFFFFFFF }, + { IXGBE_VFTDBAH(0), 2, PATTERN_TEST, 0xFFFFFFFF, 0xFFFFFFFF }, + { IXGBE_VFTDLEN(0), 2, PATTERN_TEST, 0x000FFF80, 0x000FFF80 }, + { .reg = 0 } +}; + +static const u32 register_test_patterns[] = { + 0x5A5A5A5A, 0xA5A5A5A5, 0x00000000, 0xFFFFFFFF +}; + +static bool reg_pattern_test(struct ixgbevf_adapter *adapter, u64 *data, + int reg, u32 mask, u32 write) +{ + u32 pat, val, before; + + if (IXGBE_REMOVED(adapter->hw.hw_addr)) { + *data = 1; + return true; + } + for (pat = 0; pat < ARRAY_SIZE(register_test_patterns); pat++) { + before = ixgbevf_read_reg(&adapter->hw, reg); + ixgbe_write_reg(&adapter->hw, reg, + register_test_patterns[pat] & write); + val = ixgbevf_read_reg(&adapter->hw, reg); + if (val != (register_test_patterns[pat] & write & mask)) { + hw_dbg(&adapter->hw, + "pattern test reg %04X failed: got 0x%08X expected 0x%08X\n", + reg, val, + register_test_patterns[pat] & write & mask); + *data = reg; + ixgbe_write_reg(&adapter->hw, reg, before); + return true; + } + ixgbe_write_reg(&adapter->hw, reg, before); + } + return false; +} + +static bool reg_set_and_check(struct ixgbevf_adapter *adapter, u64 *data, + int reg, u32 mask, u32 write) +{ + u32 val, before; + + if (IXGBE_REMOVED(adapter->hw.hw_addr)) { + *data = 1; + return true; + } + before = ixgbevf_read_reg(&adapter->hw, reg); + ixgbe_write_reg(&adapter->hw, reg, write & mask); + val = ixgbevf_read_reg(&adapter->hw, reg); + if ((write & mask) != (val & mask)) { + pr_err("set/check reg %04X test failed: got 0x%08X expected 0x%08X\n", + reg, (val & mask), write & mask); + *data = reg; + ixgbe_write_reg(&adapter->hw, reg, before); + return true; + } + ixgbe_write_reg(&adapter->hw, reg, before); + return false; +} + +static int ixgbevf_reg_test(struct ixgbevf_adapter *adapter, u64 *data) +{ + const struct ixgbevf_reg_test *test; + u32 i; + + if (IXGBE_REMOVED(adapter->hw.hw_addr)) { + dev_err(&adapter->pdev->dev, + "Adapter removed - register test blocked\n"); + *data = 1; + return 1; + } + test = reg_test_vf; + + /* Perform the register test, looping through the test table + * until we either fail or reach the null entry. + */ + while (test->reg) { + for (i = 0; i < test->array_len; i++) { + bool b = false; + + switch (test->test_type) { + case PATTERN_TEST: + b = reg_pattern_test(adapter, data, + test->reg + (i * 0x40), + test->mask, + test->write); + break; + case SET_READ_TEST: + b = reg_set_and_check(adapter, data, + test->reg + (i * 0x40), + test->mask, + test->write); + break; + case WRITE_NO_TEST: + ixgbe_write_reg(&adapter->hw, + test->reg + (i * 0x40), + test->write); + break; + case TABLE32_TEST: + b = reg_pattern_test(adapter, data, + test->reg + (i * 4), + test->mask, + test->write); + break; + case TABLE64_TEST_LO: + b = reg_pattern_test(adapter, data, + test->reg + (i * 8), + test->mask, + test->write); + break; + case TABLE64_TEST_HI: + b = reg_pattern_test(adapter, data, + test->reg + 4 + (i * 8), + test->mask, + test->write); + break; + } + if (b) + return 1; + } + test++; + } + + *data = 0; + return *data; +} + +static void ixgbevf_diag_test(struct net_device *netdev, + struct ethtool_test *eth_test, u64 *data) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + bool if_running = netif_running(netdev); + + if (IXGBE_REMOVED(adapter->hw.hw_addr)) { + dev_err(&adapter->pdev->dev, + "Adapter removed - test blocked\n"); + data[0] = 1; + data[1] = 1; + eth_test->flags |= ETH_TEST_FL_FAILED; + return; + } + set_bit(__IXGBEVF_TESTING, &adapter->state); + if (eth_test->flags == ETH_TEST_FL_OFFLINE) { + /* Offline tests */ + + hw_dbg(&adapter->hw, "offline testing starting\n"); + + /* Link test performed before hardware reset so autoneg doesn't + * interfere with test result + */ + if (ixgbevf_link_test(adapter, &data[1])) + eth_test->flags |= ETH_TEST_FL_FAILED; + + if (if_running) + /* indicate we're in test mode */ + ixgbevf_close(netdev); + else + ixgbevf_reset(adapter); + + hw_dbg(&adapter->hw, "register testing starting\n"); + if (ixgbevf_reg_test(adapter, &data[0])) + eth_test->flags |= ETH_TEST_FL_FAILED; + + ixgbevf_reset(adapter); + + clear_bit(__IXGBEVF_TESTING, &adapter->state); + if (if_running) + ixgbevf_open(netdev); + } else { + hw_dbg(&adapter->hw, "online testing starting\n"); + /* Online tests */ + if (ixgbevf_link_test(adapter, &data[1])) + eth_test->flags |= ETH_TEST_FL_FAILED; + + /* Online tests aren't run; pass by default */ + data[0] = 0; + + clear_bit(__IXGBEVF_TESTING, &adapter->state); + } + msleep_interruptible(4 * 1000); +} + +static int ixgbevf_nway_reset(struct net_device *netdev) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + + if (netif_running(netdev)) + ixgbevf_reinit_locked(adapter); + + return 0; +} + +static int ixgbevf_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + + /* only valid if in constant ITR mode */ + if (adapter->rx_itr_setting <= 1) + ec->rx_coalesce_usecs = adapter->rx_itr_setting; + else + ec->rx_coalesce_usecs = adapter->rx_itr_setting >> 2; + + /* if in mixed Tx/Rx queues per vector mode, report only Rx settings */ + if (adapter->q_vector[0]->tx.count && adapter->q_vector[0]->rx.count) + return 0; + + /* only valid if in constant ITR mode */ + if (adapter->tx_itr_setting <= 1) + ec->tx_coalesce_usecs = adapter->tx_itr_setting; + else + ec->tx_coalesce_usecs = adapter->tx_itr_setting >> 2; + + return 0; +} + +static int ixgbevf_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *ec) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + struct ixgbevf_q_vector *q_vector; + int num_vectors, i; + u16 tx_itr_param, rx_itr_param; + + /* don't accept Tx specific changes if we've got mixed RxTx vectors */ + if (adapter->q_vector[0]->tx.count && + adapter->q_vector[0]->rx.count && ec->tx_coalesce_usecs) + return -EINVAL; + + if ((ec->rx_coalesce_usecs > (IXGBE_MAX_EITR >> 2)) || + (ec->tx_coalesce_usecs > (IXGBE_MAX_EITR >> 2))) + return -EINVAL; + + if (ec->rx_coalesce_usecs > 1) + adapter->rx_itr_setting = ec->rx_coalesce_usecs << 2; + else + adapter->rx_itr_setting = ec->rx_coalesce_usecs; + + if (adapter->rx_itr_setting == 1) + rx_itr_param = IXGBE_20K_ITR; + else + rx_itr_param = adapter->rx_itr_setting; + + if (ec->tx_coalesce_usecs > 1) + adapter->tx_itr_setting = ec->tx_coalesce_usecs << 2; + else + adapter->tx_itr_setting = ec->tx_coalesce_usecs; + + if (adapter->tx_itr_setting == 1) + tx_itr_param = IXGBE_12K_ITR; + else + tx_itr_param = adapter->tx_itr_setting; + + num_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + + for (i = 0; i < num_vectors; i++) { + q_vector = adapter->q_vector[i]; + if (q_vector->tx.count && !q_vector->rx.count) + /* Tx only */ + q_vector->itr = tx_itr_param; + else + /* Rx only or mixed */ + q_vector->itr = rx_itr_param; + ixgbevf_write_eitr(q_vector); + } + + return 0; +} + +static int ixgbevf_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, + u32 *rules __always_unused) +{ + struct ixgbevf_adapter *adapter = netdev_priv(dev); + + switch (info->cmd) { + case ETHTOOL_GRXRINGS: + info->data = adapter->num_rx_queues; + return 0; + default: + hw_dbg(&adapter->hw, "Command parameters not supported\n"); + return -EOPNOTSUPP; + } +} + +static u32 ixgbevf_get_rxfh_indir_size(struct net_device *netdev) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + + if (adapter->hw.mac.type >= ixgbe_mac_X550_vf) + return IXGBEVF_X550_VFRETA_SIZE; + + return IXGBEVF_82599_RETA_SIZE; +} + +static u32 ixgbevf_get_rxfh_key_size(struct net_device *netdev) +{ + return IXGBEVF_RSS_HASH_KEY_SIZE; +} + +static int ixgbevf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, + u8 *hfunc) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + int err = 0; + + if (hfunc) + *hfunc = ETH_RSS_HASH_TOP; + + if (adapter->hw.mac.type >= ixgbe_mac_X550_vf) { + if (key) + memcpy(key, adapter->rss_key, + ixgbevf_get_rxfh_key_size(netdev)); + + if (indir) { + int i; + + for (i = 0; i < IXGBEVF_X550_VFRETA_SIZE; i++) + indir[i] = adapter->rss_indir_tbl[i]; + } + } else { + /* If neither indirection table nor hash key was requested + * - just return a success avoiding taking any locks. + */ + if (!indir && !key) + return 0; + + spin_lock_bh(&adapter->mbx_lock); + if (indir) + err = ixgbevf_get_reta_locked(&adapter->hw, indir, + adapter->num_rx_queues); + + if (!err && key) + err = ixgbevf_get_rss_key_locked(&adapter->hw, key); + + spin_unlock_bh(&adapter->mbx_lock); + } + + return err; +} + +static u32 ixgbevf_get_priv_flags(struct net_device *netdev) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + u32 priv_flags = 0; + + if (adapter->flags & IXGBEVF_FLAGS_LEGACY_RX) + priv_flags |= IXGBEVF_PRIV_FLAGS_LEGACY_RX; + + return priv_flags; +} + +static int ixgbevf_set_priv_flags(struct net_device *netdev, u32 priv_flags) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + unsigned int flags = adapter->flags; + + flags &= ~IXGBEVF_FLAGS_LEGACY_RX; + if (priv_flags & IXGBEVF_PRIV_FLAGS_LEGACY_RX) + flags |= IXGBEVF_FLAGS_LEGACY_RX; + + if (flags != adapter->flags) { + adapter->flags = flags; + + /* reset interface to repopulate queues */ + if (netif_running(netdev)) + ixgbevf_reinit_locked(adapter); + } + + return 0; +} + +static const struct ethtool_ops ixgbevf_ethtool_ops = { + .supported_coalesce_params = ETHTOOL_COALESCE_USECS, + .get_drvinfo = ixgbevf_get_drvinfo, + .get_regs_len = ixgbevf_get_regs_len, + .get_regs = ixgbevf_get_regs, + .nway_reset = ixgbevf_nway_reset, + .get_link = ethtool_op_get_link, + .get_ringparam = ixgbevf_get_ringparam, + .set_ringparam = ixgbevf_set_ringparam, + .get_msglevel = ixgbevf_get_msglevel, + .set_msglevel = ixgbevf_set_msglevel, + .self_test = ixgbevf_diag_test, + .get_sset_count = ixgbevf_get_sset_count, + .get_strings = ixgbevf_get_strings, + .get_ethtool_stats = ixgbevf_get_ethtool_stats, + .get_coalesce = ixgbevf_get_coalesce, + .set_coalesce = ixgbevf_set_coalesce, + .get_rxnfc = ixgbevf_get_rxnfc, + .get_rxfh_indir_size = ixgbevf_get_rxfh_indir_size, + .get_rxfh_key_size = ixgbevf_get_rxfh_key_size, + .get_rxfh = ixgbevf_get_rxfh, + .get_link_ksettings = ixgbevf_get_link_ksettings, + .get_priv_flags = ixgbevf_get_priv_flags, + .set_priv_flags = ixgbevf_set_priv_flags, +}; + +void ixgbevf_set_ethtool_ops(struct net_device *netdev) +{ + netdev->ethtool_ops = &ixgbevf_ethtool_ops; +} diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.c b/drivers/net/ethernet/intel/ixgbevf/ipsec.c new file mode 100644 index 000000000..e3e4676af --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.c @@ -0,0 +1,684 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2018 Oracle and/or its affiliates. All rights reserved. */ + +#include "ixgbevf.h" +#include <net/xfrm.h> +#include <crypto/aead.h> + +#define IXGBE_IPSEC_KEY_BITS 160 +static const char aes_gcm_name[] = "rfc4106(gcm(aes))"; + +/** + * ixgbevf_ipsec_set_pf_sa - ask the PF to set up an SA + * @adapter: board private structure + * @xs: xfrm info to be sent to the PF + * + * Returns: positive offload handle from the PF, or negative error code + **/ +static int ixgbevf_ipsec_set_pf_sa(struct ixgbevf_adapter *adapter, + struct xfrm_state *xs) +{ + u32 msgbuf[IXGBE_VFMAILBOX_SIZE] = { 0 }; + struct ixgbe_hw *hw = &adapter->hw; + struct sa_mbx_msg *sam; + int ret; + + /* send the important bits to the PF */ + sam = (struct sa_mbx_msg *)(&msgbuf[1]); + sam->flags = xs->xso.flags; + sam->spi = xs->id.spi; + sam->proto = xs->id.proto; + sam->family = xs->props.family; + + if (xs->props.family == AF_INET6) + memcpy(sam->addr, &xs->id.daddr.a6, sizeof(xs->id.daddr.a6)); + else + memcpy(sam->addr, &xs->id.daddr.a4, sizeof(xs->id.daddr.a4)); + memcpy(sam->key, xs->aead->alg_key, sizeof(sam->key)); + + msgbuf[0] = IXGBE_VF_IPSEC_ADD; + + spin_lock_bh(&adapter->mbx_lock); + + ret = hw->mbx.ops.write_posted(hw, msgbuf, IXGBE_VFMAILBOX_SIZE); + if (ret) + goto out; + + ret = hw->mbx.ops.read_posted(hw, msgbuf, 2); + if (ret) + goto out; + + ret = (int)msgbuf[1]; + if (msgbuf[0] & IXGBE_VT_MSGTYPE_NACK && ret >= 0) + ret = -1; + +out: + spin_unlock_bh(&adapter->mbx_lock); + + return ret; +} + +/** + * ixgbevf_ipsec_del_pf_sa - ask the PF to delete an SA + * @adapter: board private structure + * @pfsa: sa index returned from PF when created, -1 for all + * + * Returns: 0 on success, or negative error code + **/ +static int ixgbevf_ipsec_del_pf_sa(struct ixgbevf_adapter *adapter, int pfsa) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 msgbuf[2]; + int err; + + memset(msgbuf, 0, sizeof(msgbuf)); + msgbuf[0] = IXGBE_VF_IPSEC_DEL; + msgbuf[1] = (u32)pfsa; + + spin_lock_bh(&adapter->mbx_lock); + + err = hw->mbx.ops.write_posted(hw, msgbuf, 2); + if (err) + goto out; + + err = hw->mbx.ops.read_posted(hw, msgbuf, 2); + if (err) + goto out; + +out: + spin_unlock_bh(&adapter->mbx_lock); + return err; +} + +/** + * ixgbevf_ipsec_restore - restore the IPsec HW settings after a reset + * @adapter: board private structure + * + * Reload the HW tables from the SW tables after they've been bashed + * by a chip reset. While we're here, make sure any stale VF data is + * removed, since we go through reset when num_vfs changes. + **/ +void ixgbevf_ipsec_restore(struct ixgbevf_adapter *adapter) +{ + struct ixgbevf_ipsec *ipsec = adapter->ipsec; + struct net_device *netdev = adapter->netdev; + int i; + + if (!(adapter->netdev->features & NETIF_F_HW_ESP)) + return; + + /* reload the Rx and Tx keys */ + for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) { + struct rx_sa *r = &ipsec->rx_tbl[i]; + struct tx_sa *t = &ipsec->tx_tbl[i]; + int ret; + + if (r->used) { + ret = ixgbevf_ipsec_set_pf_sa(adapter, r->xs); + if (ret < 0) + netdev_err(netdev, "reload rx_tbl[%d] failed = %d\n", + i, ret); + } + + if (t->used) { + ret = ixgbevf_ipsec_set_pf_sa(adapter, t->xs); + if (ret < 0) + netdev_err(netdev, "reload tx_tbl[%d] failed = %d\n", + i, ret); + } + } +} + +/** + * ixgbevf_ipsec_find_empty_idx - find the first unused security parameter index + * @ipsec: pointer to IPsec struct + * @rxtable: true if we need to look in the Rx table + * + * Returns the first unused index in either the Rx or Tx SA table + **/ +static +int ixgbevf_ipsec_find_empty_idx(struct ixgbevf_ipsec *ipsec, bool rxtable) +{ + u32 i; + + if (rxtable) { + if (ipsec->num_rx_sa == IXGBE_IPSEC_MAX_SA_COUNT) + return -ENOSPC; + + /* search rx sa table */ + for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) { + if (!ipsec->rx_tbl[i].used) + return i; + } + } else { + if (ipsec->num_tx_sa == IXGBE_IPSEC_MAX_SA_COUNT) + return -ENOSPC; + + /* search tx sa table */ + for (i = 0; i < IXGBE_IPSEC_MAX_SA_COUNT; i++) { + if (!ipsec->tx_tbl[i].used) + return i; + } + } + + return -ENOSPC; +} + +/** + * ixgbevf_ipsec_find_rx_state - find the state that matches + * @ipsec: pointer to IPsec struct + * @daddr: inbound address to match + * @proto: protocol to match + * @spi: SPI to match + * @ip4: true if using an IPv4 address + * + * Returns a pointer to the matching SA state information + **/ +static +struct xfrm_state *ixgbevf_ipsec_find_rx_state(struct ixgbevf_ipsec *ipsec, + __be32 *daddr, u8 proto, + __be32 spi, bool ip4) +{ + struct xfrm_state *ret = NULL; + struct rx_sa *rsa; + + rcu_read_lock(); + hash_for_each_possible_rcu(ipsec->rx_sa_list, rsa, hlist, + (__force u32)spi) { + if (spi == rsa->xs->id.spi && + ((ip4 && *daddr == rsa->xs->id.daddr.a4) || + (!ip4 && !memcmp(daddr, &rsa->xs->id.daddr.a6, + sizeof(rsa->xs->id.daddr.a6)))) && + proto == rsa->xs->id.proto) { + ret = rsa->xs; + xfrm_state_hold(ret); + break; + } + } + rcu_read_unlock(); + return ret; +} + +/** + * ixgbevf_ipsec_parse_proto_keys - find the key and salt based on the protocol + * @xs: pointer to xfrm_state struct + * @mykey: pointer to key array to populate + * @mysalt: pointer to salt value to populate + * + * This copies the protocol keys and salt to our own data tables. The + * 82599 family only supports the one algorithm. + **/ +static int ixgbevf_ipsec_parse_proto_keys(struct xfrm_state *xs, + u32 *mykey, u32 *mysalt) +{ + struct net_device *dev = xs->xso.real_dev; + unsigned char *key_data; + char *alg_name = NULL; + int key_len; + + if (!xs->aead) { + netdev_err(dev, "Unsupported IPsec algorithm\n"); + return -EINVAL; + } + + if (xs->aead->alg_icv_len != IXGBE_IPSEC_AUTH_BITS) { + netdev_err(dev, "IPsec offload requires %d bit authentication\n", + IXGBE_IPSEC_AUTH_BITS); + return -EINVAL; + } + + key_data = &xs->aead->alg_key[0]; + key_len = xs->aead->alg_key_len; + alg_name = xs->aead->alg_name; + + if (strcmp(alg_name, aes_gcm_name)) { + netdev_err(dev, "Unsupported IPsec algorithm - please use %s\n", + aes_gcm_name); + return -EINVAL; + } + + /* The key bytes come down in a big endian array of bytes, so + * we don't need to do any byte swapping. + * 160 accounts for 16 byte key and 4 byte salt + */ + if (key_len > IXGBE_IPSEC_KEY_BITS) { + *mysalt = ((u32 *)key_data)[4]; + } else if (key_len == IXGBE_IPSEC_KEY_BITS) { + *mysalt = 0; + } else { + netdev_err(dev, "IPsec hw offload only supports keys up to 128 bits with a 32 bit salt\n"); + return -EINVAL; + } + memcpy(mykey, key_data, 16); + + return 0; +} + +/** + * ixgbevf_ipsec_add_sa - program device with a security association + * @xs: pointer to transformer state struct + **/ +static int ixgbevf_ipsec_add_sa(struct xfrm_state *xs) +{ + struct net_device *dev = xs->xso.real_dev; + struct ixgbevf_adapter *adapter; + struct ixgbevf_ipsec *ipsec; + u16 sa_idx; + int ret; + + adapter = netdev_priv(dev); + ipsec = adapter->ipsec; + + if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) { + netdev_err(dev, "Unsupported protocol 0x%04x for IPsec offload\n", + xs->id.proto); + return -EINVAL; + } + + if (xs->props.mode != XFRM_MODE_TRANSPORT) { + netdev_err(dev, "Unsupported mode for ipsec offload\n"); + return -EINVAL; + } + + if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) { + struct rx_sa rsa; + + if (xs->calg) { + netdev_err(dev, "Compression offload not supported\n"); + return -EINVAL; + } + + /* find the first unused index */ + ret = ixgbevf_ipsec_find_empty_idx(ipsec, true); + if (ret < 0) { + netdev_err(dev, "No space for SA in Rx table!\n"); + return ret; + } + sa_idx = (u16)ret; + + memset(&rsa, 0, sizeof(rsa)); + rsa.used = true; + rsa.xs = xs; + + if (rsa.xs->id.proto & IPPROTO_ESP) + rsa.decrypt = xs->ealg || xs->aead; + + /* get the key and salt */ + ret = ixgbevf_ipsec_parse_proto_keys(xs, rsa.key, &rsa.salt); + if (ret) { + netdev_err(dev, "Failed to get key data for Rx SA table\n"); + return ret; + } + + /* get ip for rx sa table */ + if (xs->props.family == AF_INET6) + memcpy(rsa.ipaddr, &xs->id.daddr.a6, 16); + else + memcpy(&rsa.ipaddr[3], &xs->id.daddr.a4, 4); + + rsa.mode = IXGBE_RXMOD_VALID; + if (rsa.xs->id.proto & IPPROTO_ESP) + rsa.mode |= IXGBE_RXMOD_PROTO_ESP; + if (rsa.decrypt) + rsa.mode |= IXGBE_RXMOD_DECRYPT; + if (rsa.xs->props.family == AF_INET6) + rsa.mode |= IXGBE_RXMOD_IPV6; + + ret = ixgbevf_ipsec_set_pf_sa(adapter, xs); + if (ret < 0) + return ret; + rsa.pfsa = ret; + + /* the preparations worked, so save the info */ + memcpy(&ipsec->rx_tbl[sa_idx], &rsa, sizeof(rsa)); + + xs->xso.offload_handle = sa_idx + IXGBE_IPSEC_BASE_RX_INDEX; + + ipsec->num_rx_sa++; + + /* hash the new entry for faster search in Rx path */ + hash_add_rcu(ipsec->rx_sa_list, &ipsec->rx_tbl[sa_idx].hlist, + (__force u32)rsa.xs->id.spi); + } else { + struct tx_sa tsa; + + /* find the first unused index */ + ret = ixgbevf_ipsec_find_empty_idx(ipsec, false); + if (ret < 0) { + netdev_err(dev, "No space for SA in Tx table\n"); + return ret; + } + sa_idx = (u16)ret; + + memset(&tsa, 0, sizeof(tsa)); + tsa.used = true; + tsa.xs = xs; + + if (xs->id.proto & IPPROTO_ESP) + tsa.encrypt = xs->ealg || xs->aead; + + ret = ixgbevf_ipsec_parse_proto_keys(xs, tsa.key, &tsa.salt); + if (ret) { + netdev_err(dev, "Failed to get key data for Tx SA table\n"); + memset(&tsa, 0, sizeof(tsa)); + return ret; + } + + ret = ixgbevf_ipsec_set_pf_sa(adapter, xs); + if (ret < 0) + return ret; + tsa.pfsa = ret; + + /* the preparations worked, so save the info */ + memcpy(&ipsec->tx_tbl[sa_idx], &tsa, sizeof(tsa)); + + xs->xso.offload_handle = sa_idx + IXGBE_IPSEC_BASE_TX_INDEX; + + ipsec->num_tx_sa++; + } + + return 0; +} + +/** + * ixgbevf_ipsec_del_sa - clear out this specific SA + * @xs: pointer to transformer state struct + **/ +static void ixgbevf_ipsec_del_sa(struct xfrm_state *xs) +{ + struct net_device *dev = xs->xso.real_dev; + struct ixgbevf_adapter *adapter; + struct ixgbevf_ipsec *ipsec; + u16 sa_idx; + + adapter = netdev_priv(dev); + ipsec = adapter->ipsec; + + if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) { + sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_RX_INDEX; + + if (!ipsec->rx_tbl[sa_idx].used) { + netdev_err(dev, "Invalid Rx SA selected sa_idx=%d offload_handle=%lu\n", + sa_idx, xs->xso.offload_handle); + return; + } + + ixgbevf_ipsec_del_pf_sa(adapter, ipsec->rx_tbl[sa_idx].pfsa); + hash_del_rcu(&ipsec->rx_tbl[sa_idx].hlist); + memset(&ipsec->rx_tbl[sa_idx], 0, sizeof(struct rx_sa)); + ipsec->num_rx_sa--; + } else { + sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_TX_INDEX; + + if (!ipsec->tx_tbl[sa_idx].used) { + netdev_err(dev, "Invalid Tx SA selected sa_idx=%d offload_handle=%lu\n", + sa_idx, xs->xso.offload_handle); + return; + } + + ixgbevf_ipsec_del_pf_sa(adapter, ipsec->tx_tbl[sa_idx].pfsa); + memset(&ipsec->tx_tbl[sa_idx], 0, sizeof(struct tx_sa)); + ipsec->num_tx_sa--; + } +} + +/** + * ixgbevf_ipsec_offload_ok - can this packet use the xfrm hw offload + * @skb: current data packet + * @xs: pointer to transformer state struct + **/ +static bool ixgbevf_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs) +{ + if (xs->props.family == AF_INET) { + /* Offload with IPv4 options is not supported yet */ + if (ip_hdr(skb)->ihl != 5) + return false; + } else { + /* Offload with IPv6 extension headers is not support yet */ + if (ipv6_ext_hdr(ipv6_hdr(skb)->nexthdr)) + return false; + } + + return true; +} + +static const struct xfrmdev_ops ixgbevf_xfrmdev_ops = { + .xdo_dev_state_add = ixgbevf_ipsec_add_sa, + .xdo_dev_state_delete = ixgbevf_ipsec_del_sa, + .xdo_dev_offload_ok = ixgbevf_ipsec_offload_ok, +}; + +/** + * ixgbevf_ipsec_tx - setup Tx flags for IPsec offload + * @tx_ring: outgoing context + * @first: current data packet + * @itd: ipsec Tx data for later use in building context descriptor + **/ +int ixgbevf_ipsec_tx(struct ixgbevf_ring *tx_ring, + struct ixgbevf_tx_buffer *first, + struct ixgbevf_ipsec_tx_data *itd) +{ + struct ixgbevf_adapter *adapter = netdev_priv(tx_ring->netdev); + struct ixgbevf_ipsec *ipsec = adapter->ipsec; + struct xfrm_state *xs; + struct sec_path *sp; + struct tx_sa *tsa; + u16 sa_idx; + + sp = skb_sec_path(first->skb); + if (unlikely(!sp->len)) { + netdev_err(tx_ring->netdev, "%s: no xfrm state len = %d\n", + __func__, sp->len); + return 0; + } + + xs = xfrm_input_state(first->skb); + if (unlikely(!xs)) { + netdev_err(tx_ring->netdev, "%s: no xfrm_input_state() xs = %p\n", + __func__, xs); + return 0; + } + + sa_idx = xs->xso.offload_handle - IXGBE_IPSEC_BASE_TX_INDEX; + if (unlikely(sa_idx >= IXGBE_IPSEC_MAX_SA_COUNT)) { + netdev_err(tx_ring->netdev, "%s: bad sa_idx=%d handle=%lu\n", + __func__, sa_idx, xs->xso.offload_handle); + return 0; + } + + tsa = &ipsec->tx_tbl[sa_idx]; + if (unlikely(!tsa->used)) { + netdev_err(tx_ring->netdev, "%s: unused sa_idx=%d\n", + __func__, sa_idx); + return 0; + } + + itd->pfsa = tsa->pfsa - IXGBE_IPSEC_BASE_TX_INDEX; + + first->tx_flags |= IXGBE_TX_FLAGS_IPSEC | IXGBE_TX_FLAGS_CSUM; + + if (xs->id.proto == IPPROTO_ESP) { + itd->flags |= IXGBE_ADVTXD_TUCMD_IPSEC_TYPE_ESP | + IXGBE_ADVTXD_TUCMD_L4T_TCP; + if (first->protocol == htons(ETH_P_IP)) + itd->flags |= IXGBE_ADVTXD_TUCMD_IPV4; + + /* The actual trailer length is authlen (16 bytes) plus + * 2 bytes for the proto and the padlen values, plus + * padlen bytes of padding. This ends up not the same + * as the static value found in xs->props.trailer_len (21). + * + * ... but if we're doing GSO, don't bother as the stack + * doesn't add a trailer for those. + */ + if (!skb_is_gso(first->skb)) { + /* The "correct" way to get the auth length would be + * to use + * authlen = crypto_aead_authsize(xs->data); + * but since we know we only have one size to worry + * about * we can let the compiler use the constant + * and save us a few CPU cycles. + */ + const int authlen = IXGBE_IPSEC_AUTH_BITS / 8; + struct sk_buff *skb = first->skb; + u8 padlen; + int ret; + + ret = skb_copy_bits(skb, skb->len - (authlen + 2), + &padlen, 1); + if (unlikely(ret)) + return 0; + itd->trailer_len = authlen + 2 + padlen; + } + } + if (tsa->encrypt) + itd->flags |= IXGBE_ADVTXD_TUCMD_IPSEC_ENCRYPT_EN; + + return 1; +} + +/** + * ixgbevf_ipsec_rx - decode IPsec bits from Rx descriptor + * @rx_ring: receiving ring + * @rx_desc: receive data descriptor + * @skb: current data packet + * + * Determine if there was an IPsec encapsulation noticed, and if so set up + * the resulting status for later in the receive stack. + **/ +void ixgbevf_ipsec_rx(struct ixgbevf_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + struct ixgbevf_adapter *adapter = netdev_priv(rx_ring->netdev); + __le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info; + __le16 ipsec_pkt_types = cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPSEC_AH | + IXGBE_RXDADV_PKTTYPE_IPSEC_ESP); + struct ixgbevf_ipsec *ipsec = adapter->ipsec; + struct xfrm_offload *xo = NULL; + struct xfrm_state *xs = NULL; + struct ipv6hdr *ip6 = NULL; + struct iphdr *ip4 = NULL; + struct sec_path *sp; + void *daddr; + __be32 spi; + u8 *c_hdr; + u8 proto; + + /* Find the IP and crypto headers in the data. + * We can assume no VLAN header in the way, b/c the + * hw won't recognize the IPsec packet and anyway the + * currently VLAN device doesn't support xfrm offload. + */ + if (pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPV4)) { + ip4 = (struct iphdr *)(skb->data + ETH_HLEN); + daddr = &ip4->daddr; + c_hdr = (u8 *)ip4 + ip4->ihl * 4; + } else if (pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPV6)) { + ip6 = (struct ipv6hdr *)(skb->data + ETH_HLEN); + daddr = &ip6->daddr; + c_hdr = (u8 *)ip6 + sizeof(struct ipv6hdr); + } else { + return; + } + + switch (pkt_info & ipsec_pkt_types) { + case cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPSEC_AH): + spi = ((struct ip_auth_hdr *)c_hdr)->spi; + proto = IPPROTO_AH; + break; + case cpu_to_le16(IXGBE_RXDADV_PKTTYPE_IPSEC_ESP): + spi = ((struct ip_esp_hdr *)c_hdr)->spi; + proto = IPPROTO_ESP; + break; + default: + return; + } + + xs = ixgbevf_ipsec_find_rx_state(ipsec, daddr, proto, spi, !!ip4); + if (unlikely(!xs)) + return; + + sp = secpath_set(skb); + if (unlikely(!sp)) + return; + + sp->xvec[sp->len++] = xs; + sp->olen++; + xo = xfrm_offload(skb); + xo->flags = CRYPTO_DONE; + xo->status = CRYPTO_SUCCESS; + + adapter->rx_ipsec++; +} + +/** + * ixgbevf_init_ipsec_offload - initialize registers for IPsec operation + * @adapter: board private structure + **/ +void ixgbevf_init_ipsec_offload(struct ixgbevf_adapter *adapter) +{ + struct ixgbevf_ipsec *ipsec; + size_t size; + + switch (adapter->hw.api_version) { + case ixgbe_mbox_api_14: + break; + default: + return; + } + + ipsec = kzalloc(sizeof(*ipsec), GFP_KERNEL); + if (!ipsec) + goto err1; + hash_init(ipsec->rx_sa_list); + + size = sizeof(struct rx_sa) * IXGBE_IPSEC_MAX_SA_COUNT; + ipsec->rx_tbl = kzalloc(size, GFP_KERNEL); + if (!ipsec->rx_tbl) + goto err2; + + size = sizeof(struct tx_sa) * IXGBE_IPSEC_MAX_SA_COUNT; + ipsec->tx_tbl = kzalloc(size, GFP_KERNEL); + if (!ipsec->tx_tbl) + goto err2; + + ipsec->num_rx_sa = 0; + ipsec->num_tx_sa = 0; + + adapter->ipsec = ipsec; + + adapter->netdev->xfrmdev_ops = &ixgbevf_xfrmdev_ops; + +#define IXGBEVF_ESP_FEATURES (NETIF_F_HW_ESP | \ + NETIF_F_HW_ESP_TX_CSUM | \ + NETIF_F_GSO_ESP) + + adapter->netdev->features |= IXGBEVF_ESP_FEATURES; + adapter->netdev->hw_enc_features |= IXGBEVF_ESP_FEATURES; + + return; + +err2: + kfree(ipsec->rx_tbl); + kfree(ipsec->tx_tbl); + kfree(ipsec); +err1: + netdev_err(adapter->netdev, "Unable to allocate memory for SA tables"); +} + +/** + * ixgbevf_stop_ipsec_offload - tear down the IPsec offload + * @adapter: board private structure + **/ +void ixgbevf_stop_ipsec_offload(struct ixgbevf_adapter *adapter) +{ + struct ixgbevf_ipsec *ipsec = adapter->ipsec; + + adapter->ipsec = NULL; + if (ipsec) { + kfree(ipsec->rx_tbl); + kfree(ipsec->tx_tbl); + kfree(ipsec); + } +} diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.h b/drivers/net/ethernet/intel/ixgbevf/ipsec.h new file mode 100644 index 000000000..374072504 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2018 Oracle and/or its affiliates. All rights reserved. */ + +#ifndef _IXGBEVF_IPSEC_H_ +#define _IXGBEVF_IPSEC_H_ + +#define IXGBE_IPSEC_MAX_SA_COUNT 1024 +#define IXGBE_IPSEC_BASE_RX_INDEX 0 +#define IXGBE_IPSEC_BASE_TX_INDEX IXGBE_IPSEC_MAX_SA_COUNT +#define IXGBE_IPSEC_AUTH_BITS 128 + +#define IXGBE_RXMOD_VALID 0x00000001 +#define IXGBE_RXMOD_PROTO_ESP 0x00000004 +#define IXGBE_RXMOD_DECRYPT 0x00000008 +#define IXGBE_RXMOD_IPV6 0x00000010 + +struct rx_sa { + struct hlist_node hlist; + struct xfrm_state *xs; + __be32 ipaddr[4]; + u32 key[4]; + u32 salt; + u32 mode; + u32 pfsa; + bool used; + bool decrypt; +}; + +struct rx_ip_sa { + __be32 ipaddr[4]; + u32 ref_cnt; + bool used; +}; + +struct tx_sa { + struct xfrm_state *xs; + u32 key[4]; + u32 salt; + u32 pfsa; + bool encrypt; + bool used; +}; + +struct ixgbevf_ipsec_tx_data { + u32 flags; + u16 trailer_len; + u16 pfsa; +}; + +struct ixgbevf_ipsec { + u16 num_rx_sa; + u16 num_tx_sa; + struct rx_sa *rx_tbl; + struct tx_sa *tx_tbl; + DECLARE_HASHTABLE(rx_sa_list, 10); +}; + +struct sa_mbx_msg { + __be32 spi; + u8 flags; + u8 proto; + u16 family; + __be32 addr[4]; + u32 key[5]; +}; +#endif /* _IXGBEVF_IPSEC_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h new file mode 100644 index 000000000..a0e325774 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h @@ -0,0 +1,494 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#ifndef _IXGBEVF_H_ +#define _IXGBEVF_H_ + +#include <linux/types.h> +#include <linux/bitops.h> +#include <linux/timer.h> +#include <linux/io.h> +#include <linux/netdevice.h> +#include <linux/if_vlan.h> +#include <linux/u64_stats_sync.h> +#include <net/xdp.h> + +#include "vf.h" +#include "ipsec.h" + +#define IXGBE_MAX_TXD_PWR 14 +#define IXGBE_MAX_DATA_PER_TXD BIT(IXGBE_MAX_TXD_PWR) + +/* Tx Descriptors needed, worst case */ +#define TXD_USE_COUNT(S) DIV_ROUND_UP((S), IXGBE_MAX_DATA_PER_TXD) +#define DESC_NEEDED (MAX_SKB_FRAGS + 4) + +/* wrapper around a pointer to a socket buffer, + * so a DMA handle can be stored along with the buffer + */ +struct ixgbevf_tx_buffer { + union ixgbe_adv_tx_desc *next_to_watch; + unsigned long time_stamp; + union { + struct sk_buff *skb; + /* XDP uses address ptr on irq_clean */ + void *data; + }; + unsigned int bytecount; + unsigned short gso_segs; + __be16 protocol; + DEFINE_DMA_UNMAP_ADDR(dma); + DEFINE_DMA_UNMAP_LEN(len); + u32 tx_flags; +}; + +struct ixgbevf_rx_buffer { + dma_addr_t dma; + struct page *page; +#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) + __u32 page_offset; +#else + __u16 page_offset; +#endif + __u16 pagecnt_bias; +}; + +struct ixgbevf_stats { + u64 packets; + u64 bytes; +}; + +struct ixgbevf_tx_queue_stats { + u64 restart_queue; + u64 tx_busy; + u64 tx_done_old; +}; + +struct ixgbevf_rx_queue_stats { + u64 alloc_rx_page_failed; + u64 alloc_rx_buff_failed; + u64 alloc_rx_page; + u64 csum_err; +}; + +enum ixgbevf_ring_state_t { + __IXGBEVF_RX_3K_BUFFER, + __IXGBEVF_RX_BUILD_SKB_ENABLED, + __IXGBEVF_TX_DETECT_HANG, + __IXGBEVF_HANG_CHECK_ARMED, + __IXGBEVF_TX_XDP_RING, + __IXGBEVF_TX_XDP_RING_PRIMED, +}; + +#define ring_is_xdp(ring) \ + test_bit(__IXGBEVF_TX_XDP_RING, &(ring)->state) +#define set_ring_xdp(ring) \ + set_bit(__IXGBEVF_TX_XDP_RING, &(ring)->state) +#define clear_ring_xdp(ring) \ + clear_bit(__IXGBEVF_TX_XDP_RING, &(ring)->state) + +struct ixgbevf_ring { + struct ixgbevf_ring *next; + struct ixgbevf_q_vector *q_vector; /* backpointer to q_vector */ + struct net_device *netdev; + struct bpf_prog *xdp_prog; + struct device *dev; + void *desc; /* descriptor ring memory */ + dma_addr_t dma; /* phys. address of descriptor ring */ + unsigned int size; /* length in bytes */ + u16 count; /* amount of descriptors */ + u16 next_to_use; + u16 next_to_clean; + u16 next_to_alloc; + + union { + struct ixgbevf_tx_buffer *tx_buffer_info; + struct ixgbevf_rx_buffer *rx_buffer_info; + }; + unsigned long state; + struct ixgbevf_stats stats; + struct u64_stats_sync syncp; + union { + struct ixgbevf_tx_queue_stats tx_stats; + struct ixgbevf_rx_queue_stats rx_stats; + }; + struct xdp_rxq_info xdp_rxq; + u64 hw_csum_rx_error; + u8 __iomem *tail; + struct sk_buff *skb; + + /* holds the special value that gets the hardware register offset + * associated with this ring, which is different for DCB and RSS modes + */ + u16 reg_idx; + int queue_index; /* needed for multiqueue queue management */ +} ____cacheline_internodealigned_in_smp; + +/* How many Rx Buffers do we bundle into one write to the hardware ? */ +#define IXGBEVF_RX_BUFFER_WRITE 16 /* Must be power of 2 */ + +#define MAX_RX_QUEUES IXGBE_VF_MAX_RX_QUEUES +#define MAX_TX_QUEUES IXGBE_VF_MAX_TX_QUEUES +#define MAX_XDP_QUEUES IXGBE_VF_MAX_TX_QUEUES +#define IXGBEVF_MAX_RSS_QUEUES 2 +#define IXGBEVF_82599_RETA_SIZE 128 /* 128 entries */ +#define IXGBEVF_X550_VFRETA_SIZE 64 /* 64 entries */ +#define IXGBEVF_RSS_HASH_KEY_SIZE 40 +#define IXGBEVF_VFRSSRK_REGS 10 /* 10 registers for RSS key */ + +#define IXGBEVF_DEFAULT_TXD 1024 +#define IXGBEVF_DEFAULT_RXD 512 +#define IXGBEVF_MAX_TXD 4096 +#define IXGBEVF_MIN_TXD 64 +#define IXGBEVF_MAX_RXD 4096 +#define IXGBEVF_MIN_RXD 64 + +/* Supported Rx Buffer Sizes */ +#define IXGBEVF_RXBUFFER_256 256 /* Used for packet split */ +#define IXGBEVF_RXBUFFER_2048 2048 +#define IXGBEVF_RXBUFFER_3072 3072 + +#define IXGBEVF_RX_HDR_SIZE IXGBEVF_RXBUFFER_256 + +#define MAXIMUM_ETHERNET_VLAN_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN) + +#define IXGBEVF_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) +#if (PAGE_SIZE < 8192) +#define IXGBEVF_MAX_FRAME_BUILD_SKB \ + (SKB_WITH_OVERHEAD(IXGBEVF_RXBUFFER_2048) - IXGBEVF_SKB_PAD) +#else +#define IXGBEVF_MAX_FRAME_BUILD_SKB IXGBEVF_RXBUFFER_2048 +#endif + +#define IXGBE_TX_FLAGS_CSUM BIT(0) +#define IXGBE_TX_FLAGS_VLAN BIT(1) +#define IXGBE_TX_FLAGS_TSO BIT(2) +#define IXGBE_TX_FLAGS_IPV4 BIT(3) +#define IXGBE_TX_FLAGS_IPSEC BIT(4) +#define IXGBE_TX_FLAGS_VLAN_MASK 0xffff0000 +#define IXGBE_TX_FLAGS_VLAN_PRIO_MASK 0x0000e000 +#define IXGBE_TX_FLAGS_VLAN_SHIFT 16 + +#define ring_uses_large_buffer(ring) \ + test_bit(__IXGBEVF_RX_3K_BUFFER, &(ring)->state) +#define set_ring_uses_large_buffer(ring) \ + set_bit(__IXGBEVF_RX_3K_BUFFER, &(ring)->state) +#define clear_ring_uses_large_buffer(ring) \ + clear_bit(__IXGBEVF_RX_3K_BUFFER, &(ring)->state) + +#define ring_uses_build_skb(ring) \ + test_bit(__IXGBEVF_RX_BUILD_SKB_ENABLED, &(ring)->state) +#define set_ring_build_skb_enabled(ring) \ + set_bit(__IXGBEVF_RX_BUILD_SKB_ENABLED, &(ring)->state) +#define clear_ring_build_skb_enabled(ring) \ + clear_bit(__IXGBEVF_RX_BUILD_SKB_ENABLED, &(ring)->state) + +static inline unsigned int ixgbevf_rx_bufsz(struct ixgbevf_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring_uses_large_buffer(ring)) + return IXGBEVF_RXBUFFER_3072; + + if (ring_uses_build_skb(ring)) + return IXGBEVF_MAX_FRAME_BUILD_SKB; +#endif + return IXGBEVF_RXBUFFER_2048; +} + +static inline unsigned int ixgbevf_rx_pg_order(struct ixgbevf_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring_uses_large_buffer(ring)) + return 1; +#endif + return 0; +} + +#define ixgbevf_rx_pg_size(_ring) (PAGE_SIZE << ixgbevf_rx_pg_order(_ring)) + +#define check_for_tx_hang(ring) \ + test_bit(__IXGBEVF_TX_DETECT_HANG, &(ring)->state) +#define set_check_for_tx_hang(ring) \ + set_bit(__IXGBEVF_TX_DETECT_HANG, &(ring)->state) +#define clear_check_for_tx_hang(ring) \ + clear_bit(__IXGBEVF_TX_DETECT_HANG, &(ring)->state) + +struct ixgbevf_ring_container { + struct ixgbevf_ring *ring; /* pointer to linked list of rings */ + unsigned int total_bytes; /* total bytes processed this int */ + unsigned int total_packets; /* total packets processed this int */ + u8 count; /* total number of rings in vector */ + u8 itr; /* current ITR setting for ring */ +}; + +/* iterator for handling rings in ring container */ +#define ixgbevf_for_each_ring(pos, head) \ + for (pos = (head).ring; pos != NULL; pos = pos->next) + +/* MAX_MSIX_Q_VECTORS of these are allocated, + * but we only use one per queue-specific vector. + */ +struct ixgbevf_q_vector { + struct ixgbevf_adapter *adapter; + /* index of q_vector within array, also used for finding the bit in + * EICR and friends that represents the vector for this ring + */ + u16 v_idx; + u16 itr; /* Interrupt throttle rate written to EITR */ + struct napi_struct napi; + struct ixgbevf_ring_container rx, tx; + struct rcu_head rcu; /* to avoid race with update stats on free */ + char name[IFNAMSIZ + 9]; + + /* for dynamic allocation of rings associated with this q_vector */ + struct ixgbevf_ring ring[0] ____cacheline_internodealigned_in_smp; +#ifdef CONFIG_NET_RX_BUSY_POLL + unsigned int state; +#define IXGBEVF_QV_STATE_IDLE 0 +#define IXGBEVF_QV_STATE_NAPI 1 /* NAPI owns this QV */ +#define IXGBEVF_QV_STATE_POLL 2 /* poll owns this QV */ +#define IXGBEVF_QV_STATE_DISABLED 4 /* QV is disabled */ +#define IXGBEVF_QV_OWNED (IXGBEVF_QV_STATE_NAPI | IXGBEVF_QV_STATE_POLL) +#define IXGBEVF_QV_LOCKED (IXGBEVF_QV_OWNED | IXGBEVF_QV_STATE_DISABLED) +#define IXGBEVF_QV_STATE_NAPI_YIELD 8 /* NAPI yielded this QV */ +#define IXGBEVF_QV_STATE_POLL_YIELD 16 /* poll yielded this QV */ +#define IXGBEVF_QV_YIELD (IXGBEVF_QV_STATE_NAPI_YIELD | \ + IXGBEVF_QV_STATE_POLL_YIELD) +#define IXGBEVF_QV_USER_PEND (IXGBEVF_QV_STATE_POLL | \ + IXGBEVF_QV_STATE_POLL_YIELD) + spinlock_t lock; +#endif /* CONFIG_NET_RX_BUSY_POLL */ +}; + +/* microsecond values for various ITR rates shifted by 2 to fit itr register + * with the first 3 bits reserved 0 + */ +#define IXGBE_MIN_RSC_ITR 24 +#define IXGBE_100K_ITR 40 +#define IXGBE_20K_ITR 200 +#define IXGBE_12K_ITR 336 + +/* Helper macros to switch between ints/sec and what the register uses. + * And yes, it's the same math going both ways. The lowest value + * supported by all of the ixgbe hardware is 8. + */ +#define EITR_INTS_PER_SEC_TO_REG(_eitr) \ + ((_eitr) ? (1000000000 / ((_eitr) * 256)) : 8) +#define EITR_REG_TO_INTS_PER_SEC EITR_INTS_PER_SEC_TO_REG + +/* ixgbevf_test_staterr - tests bits in Rx descriptor status and error fields */ +static inline __le32 ixgbevf_test_staterr(union ixgbe_adv_rx_desc *rx_desc, + const u32 stat_err_bits) +{ + return rx_desc->wb.upper.status_error & cpu_to_le32(stat_err_bits); +} + +static inline u16 ixgbevf_desc_unused(struct ixgbevf_ring *ring) +{ + u16 ntc = ring->next_to_clean; + u16 ntu = ring->next_to_use; + + return ((ntc > ntu) ? 0 : ring->count) + ntc - ntu - 1; +} + +static inline void ixgbevf_write_tail(struct ixgbevf_ring *ring, u32 value) +{ + writel(value, ring->tail); +} + +#define IXGBEVF_RX_DESC(R, i) \ + (&(((union ixgbe_adv_rx_desc *)((R)->desc))[i])) +#define IXGBEVF_TX_DESC(R, i) \ + (&(((union ixgbe_adv_tx_desc *)((R)->desc))[i])) +#define IXGBEVF_TX_CTXTDESC(R, i) \ + (&(((struct ixgbe_adv_tx_context_desc *)((R)->desc))[i])) + +#define IXGBE_MAX_JUMBO_FRAME_SIZE 9728 /* Maximum Supported Size 9.5KB */ + +#define OTHER_VECTOR 1 +#define NON_Q_VECTORS (OTHER_VECTOR) + +#define MAX_MSIX_Q_VECTORS 2 + +#define MIN_MSIX_Q_VECTORS 1 +#define MIN_MSIX_COUNT (MIN_MSIX_Q_VECTORS + NON_Q_VECTORS) + +#define IXGBEVF_RX_DMA_ATTR \ + (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) + +/* board specific private data structure */ +struct ixgbevf_adapter { + /* this field must be first, see ixgbevf_process_skb_fields */ + unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + + struct ixgbevf_q_vector *q_vector[MAX_MSIX_Q_VECTORS]; + + /* Interrupt Throttle Rate */ + u16 rx_itr_setting; + u16 tx_itr_setting; + + /* interrupt masks */ + u32 eims_enable_mask; + u32 eims_other; + + /* XDP */ + int num_xdp_queues; + struct ixgbevf_ring *xdp_ring[MAX_XDP_QUEUES]; + + /* TX */ + int num_tx_queues; + struct ixgbevf_ring *tx_ring[MAX_TX_QUEUES]; /* One per active queue */ + u64 restart_queue; + u32 tx_timeout_count; + u64 tx_ipsec; + + /* RX */ + int num_rx_queues; + struct ixgbevf_ring *rx_ring[MAX_TX_QUEUES]; /* One per active queue */ + u64 hw_csum_rx_error; + u64 hw_rx_no_dma_resources; + int num_msix_vectors; + u64 alloc_rx_page_failed; + u64 alloc_rx_buff_failed; + u64 alloc_rx_page; + u64 rx_ipsec; + + struct msix_entry *msix_entries; + + /* OS defined structs */ + struct net_device *netdev; + struct bpf_prog *xdp_prog; + struct pci_dev *pdev; + + /* structs defined in ixgbe_vf.h */ + struct ixgbe_hw hw; + u16 msg_enable; + /* Interrupt Throttle Rate */ + u32 eitr_param; + + struct ixgbevf_hw_stats stats; + + unsigned long state; + u64 tx_busy; + unsigned int tx_ring_count; + unsigned int xdp_ring_count; + unsigned int rx_ring_count; + + u8 __iomem *io_addr; /* Mainly for iounmap use */ + u32 link_speed; + bool link_up; + + struct timer_list service_timer; + struct work_struct service_task; + + spinlock_t mbx_lock; + unsigned long last_reset; + + u32 *rss_key; + u8 rss_indir_tbl[IXGBEVF_X550_VFRETA_SIZE]; + u32 flags; +#define IXGBEVF_FLAGS_LEGACY_RX BIT(1) + +#ifdef CONFIG_XFRM + struct ixgbevf_ipsec *ipsec; +#endif /* CONFIG_XFRM */ +}; + +enum ixbgevf_state_t { + __IXGBEVF_TESTING, + __IXGBEVF_RESETTING, + __IXGBEVF_DOWN, + __IXGBEVF_DISABLED, + __IXGBEVF_REMOVING, + __IXGBEVF_SERVICE_SCHED, + __IXGBEVF_SERVICE_INITED, + __IXGBEVF_RESET_REQUESTED, + __IXGBEVF_QUEUE_RESET_REQUESTED, +}; + +enum ixgbevf_boards { + board_82599_vf, + board_82599_vf_hv, + board_X540_vf, + board_X540_vf_hv, + board_X550_vf, + board_X550_vf_hv, + board_X550EM_x_vf, + board_X550EM_x_vf_hv, + board_x550em_a_vf, +}; + +enum ixgbevf_xcast_modes { + IXGBEVF_XCAST_MODE_NONE = 0, + IXGBEVF_XCAST_MODE_MULTI, + IXGBEVF_XCAST_MODE_ALLMULTI, + IXGBEVF_XCAST_MODE_PROMISC, +}; + +extern const struct ixgbevf_info ixgbevf_82599_vf_info; +extern const struct ixgbevf_info ixgbevf_X540_vf_info; +extern const struct ixgbevf_info ixgbevf_X550_vf_info; +extern const struct ixgbevf_info ixgbevf_X550EM_x_vf_info; +extern const struct ixgbe_mbx_operations ixgbevf_mbx_ops; +extern const struct ixgbevf_info ixgbevf_x550em_a_vf_info; + +extern const struct ixgbevf_info ixgbevf_82599_vf_hv_info; +extern const struct ixgbevf_info ixgbevf_X540_vf_hv_info; +extern const struct ixgbevf_info ixgbevf_X550_vf_hv_info; +extern const struct ixgbevf_info ixgbevf_X550EM_x_vf_hv_info; +extern const struct ixgbe_mbx_operations ixgbevf_hv_mbx_ops; + +/* needed by ethtool.c */ +extern const char ixgbevf_driver_name[]; + +int ixgbevf_open(struct net_device *netdev); +int ixgbevf_close(struct net_device *netdev); +void ixgbevf_up(struct ixgbevf_adapter *adapter); +void ixgbevf_down(struct ixgbevf_adapter *adapter); +void ixgbevf_reinit_locked(struct ixgbevf_adapter *adapter); +void ixgbevf_reset(struct ixgbevf_adapter *adapter); +void ixgbevf_set_ethtool_ops(struct net_device *netdev); +int ixgbevf_setup_rx_resources(struct ixgbevf_adapter *adapter, + struct ixgbevf_ring *rx_ring); +int ixgbevf_setup_tx_resources(struct ixgbevf_ring *); +void ixgbevf_free_rx_resources(struct ixgbevf_ring *); +void ixgbevf_free_tx_resources(struct ixgbevf_ring *); +void ixgbevf_update_stats(struct ixgbevf_adapter *adapter); +int ethtool_ioctl(struct ifreq *ifr); + +extern void ixgbevf_write_eitr(struct ixgbevf_q_vector *q_vector); + +#ifdef CONFIG_IXGBEVF_IPSEC +void ixgbevf_init_ipsec_offload(struct ixgbevf_adapter *adapter); +void ixgbevf_stop_ipsec_offload(struct ixgbevf_adapter *adapter); +void ixgbevf_ipsec_restore(struct ixgbevf_adapter *adapter); +void ixgbevf_ipsec_rx(struct ixgbevf_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb); +int ixgbevf_ipsec_tx(struct ixgbevf_ring *tx_ring, + struct ixgbevf_tx_buffer *first, + struct ixgbevf_ipsec_tx_data *itd); +#else +static inline void ixgbevf_init_ipsec_offload(struct ixgbevf_adapter *adapter) +{ } +static inline void ixgbevf_stop_ipsec_offload(struct ixgbevf_adapter *adapter) +{ } +static inline void ixgbevf_ipsec_restore(struct ixgbevf_adapter *adapter) { } +static inline void ixgbevf_ipsec_rx(struct ixgbevf_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) { } +static inline int ixgbevf_ipsec_tx(struct ixgbevf_ring *tx_ring, + struct ixgbevf_tx_buffer *first, + struct ixgbevf_ipsec_tx_data *itd) +{ return 0; } +#endif /* CONFIG_IXGBEVF_IPSEC */ + +void ixgbe_napi_add_all(struct ixgbevf_adapter *adapter); +void ixgbe_napi_del_all(struct ixgbevf_adapter *adapter); + +#define ixgbevf_hw_to_netdev(hw) \ + (((struct ixgbevf_adapter *)(hw)->back)->netdev) + +#define hw_dbg(hw, format, arg...) \ + netdev_dbg(ixgbevf_hw_to_netdev(hw), format, ## arg) +#endif /* _IXGBEVF_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c new file mode 100644 index 000000000..4510a8451 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -0,0 +1,4933 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +/****************************************************************************** + Copyright (c)2006 - 2007 Myricom, Inc. for some LRO specific code +******************************************************************************/ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/types.h> +#include <linux/bitops.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/netdevice.h> +#include <linux/vmalloc.h> +#include <linux/string.h> +#include <linux/in.h> +#include <linux/ip.h> +#include <linux/tcp.h> +#include <linux/sctp.h> +#include <linux/ipv6.h> +#include <linux/slab.h> +#include <net/checksum.h> +#include <net/ip6_checksum.h> +#include <linux/ethtool.h> +#include <linux/if.h> +#include <linux/if_vlan.h> +#include <linux/prefetch.h> +#include <net/mpls.h> +#include <linux/bpf.h> +#include <linux/bpf_trace.h> +#include <linux/atomic.h> +#include <net/xfrm.h> + +#include "ixgbevf.h" + +const char ixgbevf_driver_name[] = "ixgbevf"; +static const char ixgbevf_driver_string[] = + "Intel(R) 10 Gigabit PCI Express Virtual Function Network Driver"; + +static char ixgbevf_copyright[] = + "Copyright (c) 2009 - 2018 Intel Corporation."; + +static const struct ixgbevf_info *ixgbevf_info_tbl[] = { + [board_82599_vf] = &ixgbevf_82599_vf_info, + [board_82599_vf_hv] = &ixgbevf_82599_vf_hv_info, + [board_X540_vf] = &ixgbevf_X540_vf_info, + [board_X540_vf_hv] = &ixgbevf_X540_vf_hv_info, + [board_X550_vf] = &ixgbevf_X550_vf_info, + [board_X550_vf_hv] = &ixgbevf_X550_vf_hv_info, + [board_X550EM_x_vf] = &ixgbevf_X550EM_x_vf_info, + [board_X550EM_x_vf_hv] = &ixgbevf_X550EM_x_vf_hv_info, + [board_x550em_a_vf] = &ixgbevf_x550em_a_vf_info, +}; + +/* ixgbevf_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 ixgbevf_pci_tbl[] = { + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_VF), board_82599_vf }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_VF_HV), board_82599_vf_hv }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540_VF), board_X540_vf }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540_VF_HV), board_X540_vf_hv }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550_VF), board_X550_vf }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550_VF_HV), board_X550_vf_hv }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_VF), board_X550EM_x_vf }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_X_VF_HV), board_X550EM_x_vf_hv}, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X550EM_A_VF), board_x550em_a_vf }, + /* required last entry */ + {0, } +}; +MODULE_DEVICE_TABLE(pci, ixgbevf_pci_tbl); + +MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); +MODULE_DESCRIPTION("Intel(R) 10 Gigabit Virtual Function 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)"); + +static struct workqueue_struct *ixgbevf_wq; + +static void ixgbevf_service_event_schedule(struct ixgbevf_adapter *adapter) +{ + if (!test_bit(__IXGBEVF_DOWN, &adapter->state) && + !test_bit(__IXGBEVF_REMOVING, &adapter->state) && + !test_and_set_bit(__IXGBEVF_SERVICE_SCHED, &adapter->state)) + queue_work(ixgbevf_wq, &adapter->service_task); +} + +static void ixgbevf_service_event_complete(struct ixgbevf_adapter *adapter) +{ + BUG_ON(!test_bit(__IXGBEVF_SERVICE_SCHED, &adapter->state)); + + /* flush memory to make sure state is correct before next watchdog */ + smp_mb__before_atomic(); + clear_bit(__IXGBEVF_SERVICE_SCHED, &adapter->state); +} + +/* forward decls */ +static void ixgbevf_queue_reset_subtask(struct ixgbevf_adapter *adapter); +static void ixgbevf_set_itr(struct ixgbevf_q_vector *q_vector); +static void ixgbevf_free_all_rx_resources(struct ixgbevf_adapter *adapter); +static bool ixgbevf_can_reuse_rx_page(struct ixgbevf_rx_buffer *rx_buffer); +static void ixgbevf_reuse_rx_page(struct ixgbevf_ring *rx_ring, + struct ixgbevf_rx_buffer *old_buff); + +static void ixgbevf_remove_adapter(struct ixgbe_hw *hw) +{ + struct ixgbevf_adapter *adapter = hw->back; + + if (!hw->hw_addr) + return; + hw->hw_addr = NULL; + dev_err(&adapter->pdev->dev, "Adapter removed\n"); + if (test_bit(__IXGBEVF_SERVICE_INITED, &adapter->state)) + ixgbevf_service_event_schedule(adapter); +} + +static void ixgbevf_check_remove(struct ixgbe_hw *hw, u32 reg) +{ + u32 value; + + /* The following check not only optimizes a bit by not + * performing a read on the status register when the + * register just read was a status register read that + * returned IXGBE_FAILED_READ_REG. It also blocks any + * potential recursion. + */ + if (reg == IXGBE_VFSTATUS) { + ixgbevf_remove_adapter(hw); + return; + } + value = ixgbevf_read_reg(hw, IXGBE_VFSTATUS); + if (value == IXGBE_FAILED_READ_REG) + ixgbevf_remove_adapter(hw); +} + +u32 ixgbevf_read_reg(struct ixgbe_hw *hw, u32 reg) +{ + u8 __iomem *reg_addr = READ_ONCE(hw->hw_addr); + u32 value; + + if (IXGBE_REMOVED(reg_addr)) + return IXGBE_FAILED_READ_REG; + value = readl(reg_addr + reg); + if (unlikely(value == IXGBE_FAILED_READ_REG)) + ixgbevf_check_remove(hw, reg); + return value; +} + +/** + * ixgbevf_set_ivar - set IVAR registers - maps interrupt causes to vectors + * @adapter: pointer to adapter struct + * @direction: 0 for Rx, 1 for Tx, -1 for other causes + * @queue: queue to map the corresponding interrupt to + * @msix_vector: the vector to map to the corresponding queue + **/ +static void ixgbevf_set_ivar(struct ixgbevf_adapter *adapter, s8 direction, + u8 queue, u8 msix_vector) +{ + u32 ivar, index; + struct ixgbe_hw *hw = &adapter->hw; + + if (direction == -1) { + /* other causes */ + msix_vector |= IXGBE_IVAR_ALLOC_VAL; + ivar = IXGBE_READ_REG(hw, IXGBE_VTIVAR_MISC); + ivar &= ~0xFF; + ivar |= msix_vector; + IXGBE_WRITE_REG(hw, IXGBE_VTIVAR_MISC, ivar); + } else { + /* Tx or Rx causes */ + msix_vector |= IXGBE_IVAR_ALLOC_VAL; + index = ((16 * (queue & 1)) + (8 * direction)); + ivar = IXGBE_READ_REG(hw, IXGBE_VTIVAR(queue >> 1)); + ivar &= ~(0xFF << index); + ivar |= (msix_vector << index); + IXGBE_WRITE_REG(hw, IXGBE_VTIVAR(queue >> 1), ivar); + } +} + +static u64 ixgbevf_get_tx_completed(struct ixgbevf_ring *ring) +{ + return ring->stats.packets; +} + +static u32 ixgbevf_get_tx_pending(struct ixgbevf_ring *ring) +{ + struct ixgbevf_adapter *adapter = netdev_priv(ring->netdev); + struct ixgbe_hw *hw = &adapter->hw; + + u32 head = IXGBE_READ_REG(hw, IXGBE_VFTDH(ring->reg_idx)); + u32 tail = IXGBE_READ_REG(hw, IXGBE_VFTDT(ring->reg_idx)); + + if (head != tail) + return (head < tail) ? + tail - head : (tail + ring->count - head); + + return 0; +} + +static inline bool ixgbevf_check_tx_hang(struct ixgbevf_ring *tx_ring) +{ + u32 tx_done = ixgbevf_get_tx_completed(tx_ring); + u32 tx_done_old = tx_ring->tx_stats.tx_done_old; + u32 tx_pending = ixgbevf_get_tx_pending(tx_ring); + + clear_check_for_tx_hang(tx_ring); + + /* Check for a hung queue, but be thorough. This verifies + * that a transmit has been completed since the previous + * check AND there is at least one packet pending. The + * ARMED bit is set to indicate a potential hang. + */ + if ((tx_done_old == tx_done) && tx_pending) { + /* make sure it is true for two checks in a row */ + return test_and_set_bit(__IXGBEVF_HANG_CHECK_ARMED, + &tx_ring->state); + } + /* reset the countdown */ + clear_bit(__IXGBEVF_HANG_CHECK_ARMED, &tx_ring->state); + + /* update completed stats and continue */ + tx_ring->tx_stats.tx_done_old = tx_done; + + return false; +} + +static void ixgbevf_tx_timeout_reset(struct ixgbevf_adapter *adapter) +{ + /* Do the reset outside of interrupt context */ + if (!test_bit(__IXGBEVF_DOWN, &adapter->state)) { + set_bit(__IXGBEVF_RESET_REQUESTED, &adapter->state); + ixgbevf_service_event_schedule(adapter); + } +} + +/** + * ixgbevf_tx_timeout - Respond to a Tx Hang + * @netdev: network interface device structure + * @txqueue: transmit queue hanging (unused) + **/ +static void ixgbevf_tx_timeout(struct net_device *netdev, unsigned int __always_unused txqueue) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + + ixgbevf_tx_timeout_reset(adapter); +} + +/** + * ixgbevf_clean_tx_irq - Reclaim resources after transmit completes + * @q_vector: board private structure + * @tx_ring: tx ring to clean + * @napi_budget: Used to determine if we are in netpoll + **/ +static bool ixgbevf_clean_tx_irq(struct ixgbevf_q_vector *q_vector, + struct ixgbevf_ring *tx_ring, int napi_budget) +{ + struct ixgbevf_adapter *adapter = q_vector->adapter; + struct ixgbevf_tx_buffer *tx_buffer; + union ixgbe_adv_tx_desc *tx_desc; + unsigned int total_bytes = 0, total_packets = 0, total_ipsec = 0; + unsigned int budget = tx_ring->count / 2; + unsigned int i = tx_ring->next_to_clean; + + if (test_bit(__IXGBEVF_DOWN, &adapter->state)) + return true; + + tx_buffer = &tx_ring->tx_buffer_info[i]; + tx_desc = IXGBEVF_TX_DESC(tx_ring, i); + i -= tx_ring->count; + + do { + union ixgbe_adv_tx_desc *eop_desc = tx_buffer->next_to_watch; + + /* if next_to_watch is not set then there is no work pending */ + if (!eop_desc) + break; + + /* prevent any other reads prior to eop_desc */ + smp_rmb(); + + /* if DD is not set pending work has not been completed */ + if (!(eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD))) + break; + + /* clear next_to_watch to prevent false hangs */ + tx_buffer->next_to_watch = NULL; + + /* update the statistics for this packet */ + total_bytes += tx_buffer->bytecount; + total_packets += tx_buffer->gso_segs; + if (tx_buffer->tx_flags & IXGBE_TX_FLAGS_IPSEC) + total_ipsec++; + + /* free the skb */ + if (ring_is_xdp(tx_ring)) + page_frag_free(tx_buffer->data); + else + napi_consume_skb(tx_buffer->skb, napi_budget); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + + /* clear tx_buffer data */ + dma_unmap_len_set(tx_buffer, len, 0); + + /* unmap remaining buffers */ + while (tx_desc != eop_desc) { + tx_buffer++; + tx_desc++; + i++; + if (unlikely(!i)) { + i -= tx_ring->count; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = IXGBEVF_TX_DESC(tx_ring, 0); + } + + /* unmap any remaining paged data */ + if (dma_unmap_len(tx_buffer, len)) { + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + } + } + + /* move us one more past the eop_desc for start of next pkt */ + tx_buffer++; + tx_desc++; + i++; + if (unlikely(!i)) { + i -= tx_ring->count; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = IXGBEVF_TX_DESC(tx_ring, 0); + } + + /* issue prefetch for next Tx descriptor */ + prefetch(tx_desc); + + /* update budget accounting */ + budget--; + } while (likely(budget)); + + i += tx_ring->count; + tx_ring->next_to_clean = i; + u64_stats_update_begin(&tx_ring->syncp); + tx_ring->stats.bytes += total_bytes; + tx_ring->stats.packets += total_packets; + u64_stats_update_end(&tx_ring->syncp); + q_vector->tx.total_bytes += total_bytes; + q_vector->tx.total_packets += total_packets; + adapter->tx_ipsec += total_ipsec; + + if (check_for_tx_hang(tx_ring) && ixgbevf_check_tx_hang(tx_ring)) { + struct ixgbe_hw *hw = &adapter->hw; + union ixgbe_adv_tx_desc *eop_desc; + + eop_desc = tx_ring->tx_buffer_info[i].next_to_watch; + + pr_err("Detected Tx Unit Hang%s\n" + " Tx Queue <%d>\n" + " TDH, TDT <%x>, <%x>\n" + " next_to_use <%x>\n" + " next_to_clean <%x>\n" + "tx_buffer_info[next_to_clean]\n" + " next_to_watch <%p>\n" + " eop_desc->wb.status <%x>\n" + " time_stamp <%lx>\n" + " jiffies <%lx>\n", + ring_is_xdp(tx_ring) ? " XDP" : "", + tx_ring->queue_index, + IXGBE_READ_REG(hw, IXGBE_VFTDH(tx_ring->reg_idx)), + IXGBE_READ_REG(hw, IXGBE_VFTDT(tx_ring->reg_idx)), + tx_ring->next_to_use, i, + eop_desc, (eop_desc ? eop_desc->wb.status : 0), + tx_ring->tx_buffer_info[i].time_stamp, jiffies); + + if (!ring_is_xdp(tx_ring)) + netif_stop_subqueue(tx_ring->netdev, + tx_ring->queue_index); + + /* schedule immediate reset if we believe we hung */ + ixgbevf_tx_timeout_reset(adapter); + + return true; + } + + if (ring_is_xdp(tx_ring)) + return !!budget; + +#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2) + if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) && + (ixgbevf_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(__IXGBEVF_DOWN, &adapter->state)) { + netif_wake_subqueue(tx_ring->netdev, + tx_ring->queue_index); + ++tx_ring->tx_stats.restart_queue; + } + } + + return !!budget; +} + +/** + * ixgbevf_rx_skb - Helper function to determine proper Rx method + * @q_vector: structure containing interrupt and ring information + * @skb: packet to send up + **/ +static void ixgbevf_rx_skb(struct ixgbevf_q_vector *q_vector, + struct sk_buff *skb) +{ + napi_gro_receive(&q_vector->napi, skb); +} + +#define IXGBE_RSS_L4_TYPES_MASK \ + ((1ul << IXGBE_RXDADV_RSSTYPE_IPV4_TCP) | \ + (1ul << IXGBE_RXDADV_RSSTYPE_IPV4_UDP) | \ + (1ul << IXGBE_RXDADV_RSSTYPE_IPV6_TCP) | \ + (1ul << IXGBE_RXDADV_RSSTYPE_IPV6_UDP)) + +static inline void ixgbevf_rx_hash(struct ixgbevf_ring *ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + u16 rss_type; + + if (!(ring->netdev->features & NETIF_F_RXHASH)) + return; + + rss_type = le16_to_cpu(rx_desc->wb.lower.lo_dword.hs_rss.pkt_info) & + IXGBE_RXDADV_RSSTYPE_MASK; + + if (!rss_type) + return; + + skb_set_hash(skb, le32_to_cpu(rx_desc->wb.lower.hi_dword.rss), + (IXGBE_RSS_L4_TYPES_MASK & (1ul << rss_type)) ? + PKT_HASH_TYPE_L4 : PKT_HASH_TYPE_L3); +} + +/** + * ixgbevf_rx_checksum - indicate in skb if hw indicated a good cksum + * @ring: structure containig ring specific data + * @rx_desc: current Rx descriptor being processed + * @skb: skb currently being received and modified + **/ +static inline void ixgbevf_rx_checksum(struct ixgbevf_ring *ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + skb_checksum_none_assert(skb); + + /* Rx csum disabled */ + if (!(ring->netdev->features & NETIF_F_RXCSUM)) + return; + + /* if IP and error */ + if (ixgbevf_test_staterr(rx_desc, IXGBE_RXD_STAT_IPCS) && + ixgbevf_test_staterr(rx_desc, IXGBE_RXDADV_ERR_IPE)) { + ring->rx_stats.csum_err++; + return; + } + + if (!ixgbevf_test_staterr(rx_desc, IXGBE_RXD_STAT_L4CS)) + return; + + if (ixgbevf_test_staterr(rx_desc, IXGBE_RXDADV_ERR_TCPE)) { + ring->rx_stats.csum_err++; + return; + } + + /* It must be a TCP or UDP packet with a valid checksum */ + skb->ip_summed = CHECKSUM_UNNECESSARY; +} + +/** + * ixgbevf_process_skb_fields - Populate skb header fields from Rx descriptor + * @rx_ring: rx descriptor ring packet is being transacted on + * @rx_desc: pointer to the EOP Rx descriptor + * @skb: pointer to current skb being populated + * + * This function checks the ring, descriptor, and packet information in + * order to populate the checksum, VLAN, protocol, and other fields within + * the skb. + **/ +static void ixgbevf_process_skb_fields(struct ixgbevf_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + ixgbevf_rx_hash(rx_ring, rx_desc, skb); + ixgbevf_rx_checksum(rx_ring, rx_desc, skb); + + if (ixgbevf_test_staterr(rx_desc, IXGBE_RXD_STAT_VP)) { + u16 vid = le16_to_cpu(rx_desc->wb.upper.vlan); + unsigned long *active_vlans = netdev_priv(rx_ring->netdev); + + if (test_bit(vid & VLAN_VID_MASK, active_vlans)) + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid); + } + + if (ixgbevf_test_staterr(rx_desc, IXGBE_RXDADV_STAT_SECP)) + ixgbevf_ipsec_rx(rx_ring, rx_desc, skb); + + skb->protocol = eth_type_trans(skb, rx_ring->netdev); +} + +static +struct ixgbevf_rx_buffer *ixgbevf_get_rx_buffer(struct ixgbevf_ring *rx_ring, + const unsigned int size) +{ + struct ixgbevf_rx_buffer *rx_buffer; + + rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + prefetchw(rx_buffer->page); + + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + size, + DMA_FROM_DEVICE); + + rx_buffer->pagecnt_bias--; + + return rx_buffer; +} + +static void ixgbevf_put_rx_buffer(struct ixgbevf_ring *rx_ring, + struct ixgbevf_rx_buffer *rx_buffer, + struct sk_buff *skb) +{ + if (ixgbevf_can_reuse_rx_page(rx_buffer)) { + /* hand second half of page back to the ring */ + ixgbevf_reuse_rx_page(rx_ring, rx_buffer); + } else { + if (IS_ERR(skb)) + /* We are not reusing the buffer so unmap it and free + * any references we are holding to it + */ + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, + ixgbevf_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IXGBEVF_RX_DMA_ATTR); + __page_frag_cache_drain(rx_buffer->page, + rx_buffer->pagecnt_bias); + } + + /* clear contents of rx_buffer */ + rx_buffer->page = NULL; +} + +/** + * ixgbevf_is_non_eop - process handling of non-EOP buffers + * @rx_ring: Rx ring being processed + * @rx_desc: Rx descriptor for current buffer + * + * This function updates next to clean. If the buffer is an EOP buffer + * this function exits returning false, otherwise it will place the + * sk_buff in the next buffer to be chained and return true indicating + * that this is in fact a non-EOP buffer. + **/ +static bool ixgbevf_is_non_eop(struct ixgbevf_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc) +{ + u32 ntc = rx_ring->next_to_clean + 1; + + /* fetch, update, and store next to clean */ + ntc = (ntc < rx_ring->count) ? ntc : 0; + rx_ring->next_to_clean = ntc; + + prefetch(IXGBEVF_RX_DESC(rx_ring, ntc)); + + if (likely(ixgbevf_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))) + return false; + + return true; +} + +static inline unsigned int ixgbevf_rx_offset(struct ixgbevf_ring *rx_ring) +{ + return ring_uses_build_skb(rx_ring) ? IXGBEVF_SKB_PAD : 0; +} + +static bool ixgbevf_alloc_mapped_page(struct ixgbevf_ring *rx_ring, + struct ixgbevf_rx_buffer *bi) +{ + struct page *page = bi->page; + dma_addr_t dma; + + /* since we are recycling buffers we should seldom need to alloc */ + if (likely(page)) + return true; + + /* alloc new page for storage */ + page = dev_alloc_pages(ixgbevf_rx_pg_order(rx_ring)); + if (unlikely(!page)) { + rx_ring->rx_stats.alloc_rx_page_failed++; + return false; + } + + /* map page for use */ + dma = dma_map_page_attrs(rx_ring->dev, page, 0, + ixgbevf_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, IXGBEVF_RX_DMA_ATTR); + + /* if mapping failed free memory back to system since + * there isn't much point in holding memory we can't use + */ + if (dma_mapping_error(rx_ring->dev, dma)) { + __free_pages(page, ixgbevf_rx_pg_order(rx_ring)); + + rx_ring->rx_stats.alloc_rx_page_failed++; + return false; + } + + bi->dma = dma; + bi->page = page; + bi->page_offset = ixgbevf_rx_offset(rx_ring); + bi->pagecnt_bias = 1; + rx_ring->rx_stats.alloc_rx_page++; + + return true; +} + +/** + * ixgbevf_alloc_rx_buffers - Replace used receive buffers; packet split + * @rx_ring: rx descriptor ring (for a specific queue) to setup buffers on + * @cleaned_count: number of buffers to replace + **/ +static void ixgbevf_alloc_rx_buffers(struct ixgbevf_ring *rx_ring, + u16 cleaned_count) +{ + union ixgbe_adv_rx_desc *rx_desc; + struct ixgbevf_rx_buffer *bi; + unsigned int i = rx_ring->next_to_use; + + /* nothing to do or no valid netdev defined */ + if (!cleaned_count || !rx_ring->netdev) + return; + + rx_desc = IXGBEVF_RX_DESC(rx_ring, i); + bi = &rx_ring->rx_buffer_info[i]; + i -= rx_ring->count; + + do { + if (!ixgbevf_alloc_mapped_page(rx_ring, bi)) + break; + + /* sync the buffer for use by the device */ + dma_sync_single_range_for_device(rx_ring->dev, bi->dma, + bi->page_offset, + ixgbevf_rx_bufsz(rx_ring), + DMA_FROM_DEVICE); + + /* Refresh the desc even if pkt_addr didn't change + * because each write-back erases this info. + */ + rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset); + + rx_desc++; + bi++; + i++; + if (unlikely(!i)) { + rx_desc = IXGBEVF_RX_DESC(rx_ring, 0); + bi = rx_ring->rx_buffer_info; + i -= rx_ring->count; + } + + /* clear the length for the next_to_use descriptor */ + rx_desc->wb.upper.length = 0; + + cleaned_count--; + } while (cleaned_count); + + i += rx_ring->count; + + if (rx_ring->next_to_use != i) { + /* record the next descriptor to use */ + rx_ring->next_to_use = i; + + /* update next to alloc since we have filled the ring */ + rx_ring->next_to_alloc = i; + + /* 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(); + ixgbevf_write_tail(rx_ring, i); + } +} + +/** + * ixgbevf_cleanup_headers - Correct corrupted or empty headers + * @rx_ring: rx descriptor ring packet is being transacted on + * @rx_desc: pointer to the EOP Rx descriptor + * @skb: pointer to current skb being fixed + * + * Check for corrupted packet headers caused by senders on the local L2 + * embedded NIC switch not setting up their Tx Descriptors right. These + * should be very rare. + * + * Also address the case where we are pulling data in on pages only + * and as such no data is present in the skb header. + * + * In addition if skb is not at least 60 bytes we need to pad it so that + * it is large enough to qualify as a valid Ethernet frame. + * + * Returns true if an error was encountered and skb was freed. + **/ +static bool ixgbevf_cleanup_headers(struct ixgbevf_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + /* XDP packets use error pointer so abort at this point */ + if (IS_ERR(skb)) + return true; + + /* verify that the packet does not have any known errors */ + if (unlikely(ixgbevf_test_staterr(rx_desc, + IXGBE_RXDADV_ERR_FRAME_ERR_MASK))) { + struct net_device *netdev = rx_ring->netdev; + + if (!(netdev->features & NETIF_F_RXALL)) { + dev_kfree_skb_any(skb); + return true; + } + } + + /* if eth_skb_pad returns an error the skb was freed */ + if (eth_skb_pad(skb)) + return true; + + return false; +} + +/** + * ixgbevf_reuse_rx_page - page flip buffer and store it back on the ring + * @rx_ring: rx descriptor ring to store buffers on + * @old_buff: donor buffer to have page reused + * + * Synchronizes page for reuse by the adapter + **/ +static void ixgbevf_reuse_rx_page(struct ixgbevf_ring *rx_ring, + struct ixgbevf_rx_buffer *old_buff) +{ + struct ixgbevf_rx_buffer *new_buff; + u16 nta = rx_ring->next_to_alloc; + + new_buff = &rx_ring->rx_buffer_info[nta]; + + /* update, and store next to alloc */ + nta++; + rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; + + /* transfer page from old buffer to new buffer */ + new_buff->page = old_buff->page; + new_buff->dma = old_buff->dma; + new_buff->page_offset = old_buff->page_offset; + new_buff->pagecnt_bias = old_buff->pagecnt_bias; +} + +static inline bool ixgbevf_page_is_reserved(struct page *page) +{ + return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); +} + +static bool ixgbevf_can_reuse_rx_page(struct ixgbevf_rx_buffer *rx_buffer) +{ + unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; + struct page *page = rx_buffer->page; + + /* avoid re-using remote pages */ + if (unlikely(ixgbevf_page_is_reserved(page))) + return false; + +#if (PAGE_SIZE < 8192) + /* if we are only owner of page we can reuse it */ + if (unlikely((page_ref_count(page) - pagecnt_bias) > 1)) + return false; +#else +#define IXGBEVF_LAST_OFFSET \ + (SKB_WITH_OVERHEAD(PAGE_SIZE) - IXGBEVF_RXBUFFER_2048) + + if (rx_buffer->page_offset > IXGBEVF_LAST_OFFSET) + return false; + +#endif + + /* If we have drained the page fragment pool we need to update + * the pagecnt_bias and page count so that we fully restock the + * number of references the driver holds. + */ + if (unlikely(!pagecnt_bias)) { + page_ref_add(page, USHRT_MAX); + rx_buffer->pagecnt_bias = USHRT_MAX; + } + + return true; +} + +/** + * ixgbevf_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: size of buffer to be added + * + * This function will add the data contained in rx_buffer->page to the skb. + **/ +static void ixgbevf_add_rx_frag(struct ixgbevf_ring *rx_ring, + struct ixgbevf_rx_buffer *rx_buffer, + struct sk_buff *skb, + unsigned int size) +{ +#if (PAGE_SIZE < 8192) + unsigned int truesize = ixgbevf_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = ring_uses_build_skb(rx_ring) ? + SKB_DATA_ALIGN(IXGBEVF_SKB_PAD + size) : + SKB_DATA_ALIGN(size); +#endif + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, + rx_buffer->page_offset, size, truesize); +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif +} + +static +struct sk_buff *ixgbevf_construct_skb(struct ixgbevf_ring *rx_ring, + struct ixgbevf_rx_buffer *rx_buffer, + struct xdp_buff *xdp, + union ixgbe_adv_rx_desc *rx_desc) +{ + unsigned int size = xdp->data_end - xdp->data; +#if (PAGE_SIZE < 8192) + unsigned int truesize = ixgbevf_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(xdp->data_end - + xdp->data_hard_start); +#endif + unsigned int headlen; + struct sk_buff *skb; + + /* prefetch first cache line of first page */ + net_prefetch(xdp->data); + + /* Note, we get here by enabling legacy-rx via: + * + * ethtool --set-priv-flags <dev> legacy-rx on + * + * In this mode, we currently get 0 extra XDP headroom as + * opposed to having legacy-rx off, where we process XDP + * packets going to stack via ixgbevf_build_skb(). + * + * For ixgbevf_construct_skb() mode it means that the + * xdp->data_meta will always point to xdp->data, since + * the helper cannot expand the head. Should this ever + * changed in future for legacy-rx mode on, then lets also + * add xdp->data_meta handling here. + */ + + /* allocate a skb to store the frags */ + skb = napi_alloc_skb(&rx_ring->q_vector->napi, IXGBEVF_RX_HDR_SIZE); + if (unlikely(!skb)) + return NULL; + + /* Determine available headroom for copy */ + headlen = size; + if (headlen > IXGBEVF_RX_HDR_SIZE) + headlen = eth_get_headlen(skb->dev, xdp->data, + IXGBEVF_RX_HDR_SIZE); + + /* align pull length to size of long to optimize memcpy performance */ + memcpy(__skb_put(skb, headlen), xdp->data, + ALIGN(headlen, sizeof(long))); + + /* update all of the pointers */ + size -= headlen; + if (size) { + skb_add_rx_frag(skb, 0, rx_buffer->page, + (xdp->data + headlen) - + page_address(rx_buffer->page), + size, truesize); +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif + } else { + rx_buffer->pagecnt_bias++; + } + + return skb; +} + +static inline void ixgbevf_irq_enable_queues(struct ixgbevf_adapter *adapter, + u32 qmask) +{ + struct ixgbe_hw *hw = &adapter->hw; + + IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, qmask); +} + +static struct sk_buff *ixgbevf_build_skb(struct ixgbevf_ring *rx_ring, + struct ixgbevf_rx_buffer *rx_buffer, + struct xdp_buff *xdp, + union ixgbe_adv_rx_desc *rx_desc) +{ + unsigned int metasize = xdp->data - xdp->data_meta; +#if (PAGE_SIZE < 8192) + unsigned int truesize = ixgbevf_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 + * is unused, this points to xdp->data, otherwise, we likely + * have a consumer accessing first few bytes of meta data, + * and then actual data. + */ + net_prefetch(xdp->data_meta); + + /* build an skb around the page buffer */ + skb = build_skb(xdp->data_hard_start, truesize); + if (unlikely(!skb)) + return NULL; + + /* update pointers within the skb to store the data */ + skb_reserve(skb, xdp->data - xdp->data_hard_start); + __skb_put(skb, xdp->data_end - xdp->data); + if (metasize) + skb_metadata_set(skb, metasize); + + /* update buffer offset */ +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif + + return skb; +} + +#define IXGBEVF_XDP_PASS 0 +#define IXGBEVF_XDP_CONSUMED 1 +#define IXGBEVF_XDP_TX 2 + +static int ixgbevf_xmit_xdp_ring(struct ixgbevf_ring *ring, + struct xdp_buff *xdp) +{ + struct ixgbevf_tx_buffer *tx_buffer; + union ixgbe_adv_tx_desc *tx_desc; + u32 len, cmd_type; + dma_addr_t dma; + u16 i; + + len = xdp->data_end - xdp->data; + + if (unlikely(!ixgbevf_desc_unused(ring))) + return IXGBEVF_XDP_CONSUMED; + + dma = dma_map_single(ring->dev, xdp->data, len, DMA_TO_DEVICE); + if (dma_mapping_error(ring->dev, dma)) + return IXGBEVF_XDP_CONSUMED; + + /* record the location of the first descriptor for this packet */ + i = ring->next_to_use; + tx_buffer = &ring->tx_buffer_info[i]; + + dma_unmap_len_set(tx_buffer, len, len); + dma_unmap_addr_set(tx_buffer, dma, dma); + tx_buffer->data = xdp->data; + tx_buffer->bytecount = len; + tx_buffer->gso_segs = 1; + tx_buffer->protocol = 0; + + /* Populate minimal context descriptor that will provide for the + * fact that we are expected to process Ethernet frames. + */ + if (!test_bit(__IXGBEVF_TX_XDP_RING_PRIMED, &ring->state)) { + struct ixgbe_adv_tx_context_desc *context_desc; + + set_bit(__IXGBEVF_TX_XDP_RING_PRIMED, &ring->state); + + context_desc = IXGBEVF_TX_CTXTDESC(ring, 0); + context_desc->vlan_macip_lens = + cpu_to_le32(ETH_HLEN << IXGBE_ADVTXD_MACLEN_SHIFT); + context_desc->fceof_saidx = 0; + context_desc->type_tucmd_mlhl = + cpu_to_le32(IXGBE_TXD_CMD_DEXT | + IXGBE_ADVTXD_DTYP_CTXT); + context_desc->mss_l4len_idx = 0; + + i = 1; + } + + /* put descriptor type bits */ + cmd_type = IXGBE_ADVTXD_DTYP_DATA | + IXGBE_ADVTXD_DCMD_DEXT | + IXGBE_ADVTXD_DCMD_IFCS; + cmd_type |= len | IXGBE_TXD_CMD; + + tx_desc = IXGBEVF_TX_DESC(ring, i); + tx_desc->read.buffer_addr = cpu_to_le64(dma); + + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); + tx_desc->read.olinfo_status = + cpu_to_le32((len << IXGBE_ADVTXD_PAYLEN_SHIFT) | + IXGBE_ADVTXD_CC); + + /* Avoid any potential race with cleanup */ + smp_wmb(); + + /* set next_to_watch value indicating a packet is present */ + i++; + if (i == ring->count) + i = 0; + + tx_buffer->next_to_watch = tx_desc; + ring->next_to_use = i; + + return IXGBEVF_XDP_TX; +} + +static struct sk_buff *ixgbevf_run_xdp(struct ixgbevf_adapter *adapter, + struct ixgbevf_ring *rx_ring, + struct xdp_buff *xdp) +{ + int result = IXGBEVF_XDP_PASS; + struct ixgbevf_ring *xdp_ring; + struct bpf_prog *xdp_prog; + u32 act; + + rcu_read_lock(); + xdp_prog = READ_ONCE(rx_ring->xdp_prog); + + if (!xdp_prog) + goto xdp_out; + + act = bpf_prog_run_xdp(xdp_prog, xdp); + switch (act) { + case XDP_PASS: + break; + case XDP_TX: + xdp_ring = adapter->xdp_ring[rx_ring->queue_index]; + result = ixgbevf_xmit_xdp_ring(xdp_ring, xdp); + if (result == IXGBEVF_XDP_CONSUMED) + goto out_failure; + break; + default: + bpf_warn_invalid_xdp_action(act); + fallthrough; + case XDP_ABORTED: +out_failure: + trace_xdp_exception(rx_ring->netdev, xdp_prog, act); + fallthrough; /* handle aborts by dropping packet */ + case XDP_DROP: + result = IXGBEVF_XDP_CONSUMED; + break; + } +xdp_out: + rcu_read_unlock(); + return ERR_PTR(-result); +} + +static unsigned int ixgbevf_rx_frame_truesize(struct ixgbevf_ring *rx_ring, + unsigned int size) +{ + unsigned int truesize; + +#if (PAGE_SIZE < 8192) + truesize = ixgbevf_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */ +#else + truesize = ring_uses_build_skb(rx_ring) ? + SKB_DATA_ALIGN(IXGBEVF_SKB_PAD + size) + + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) : + SKB_DATA_ALIGN(size); +#endif + return truesize; +} + +static void ixgbevf_rx_buffer_flip(struct ixgbevf_ring *rx_ring, + struct ixgbevf_rx_buffer *rx_buffer, + unsigned int size) +{ + unsigned int truesize = ixgbevf_rx_frame_truesize(rx_ring, size); + +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif +} + +static int ixgbevf_clean_rx_irq(struct ixgbevf_q_vector *q_vector, + struct ixgbevf_ring *rx_ring, + int budget) +{ + unsigned int total_rx_bytes = 0, total_rx_packets = 0; + struct ixgbevf_adapter *adapter = q_vector->adapter; + u16 cleaned_count = ixgbevf_desc_unused(rx_ring); + struct sk_buff *skb = rx_ring->skb; + bool xdp_xmit = false; + struct xdp_buff xdp; + + xdp.rxq = &rx_ring->xdp_rxq; + + /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */ +#if (PAGE_SIZE < 8192) + xdp.frame_sz = ixgbevf_rx_frame_truesize(rx_ring, 0); +#endif + + while (likely(total_rx_packets < budget)) { + struct ixgbevf_rx_buffer *rx_buffer; + union ixgbe_adv_rx_desc *rx_desc; + unsigned int size; + + /* return some buffers to hardware, one at a time is too slow */ + if (cleaned_count >= IXGBEVF_RX_BUFFER_WRITE) { + ixgbevf_alloc_rx_buffers(rx_ring, cleaned_count); + cleaned_count = 0; + } + + rx_desc = IXGBEVF_RX_DESC(rx_ring, rx_ring->next_to_clean); + size = le16_to_cpu(rx_desc->wb.upper.length); + if (!size) + break; + + /* This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc until we know the + * RXD_STAT_DD bit is set + */ + rmb(); + + rx_buffer = ixgbevf_get_rx_buffer(rx_ring, size); + + /* retrieve a buffer from the ring */ + if (!skb) { + xdp.data = page_address(rx_buffer->page) + + rx_buffer->page_offset; + xdp.data_meta = xdp.data; + xdp.data_hard_start = xdp.data - + ixgbevf_rx_offset(rx_ring); + xdp.data_end = xdp.data + size; +#if (PAGE_SIZE > 4096) + /* At larger PAGE_SIZE, frame_sz depend on len size */ + xdp.frame_sz = ixgbevf_rx_frame_truesize(rx_ring, size); +#endif + skb = ixgbevf_run_xdp(adapter, rx_ring, &xdp); + } + + if (IS_ERR(skb)) { + if (PTR_ERR(skb) == -IXGBEVF_XDP_TX) { + xdp_xmit = true; + ixgbevf_rx_buffer_flip(rx_ring, rx_buffer, + size); + } else { + rx_buffer->pagecnt_bias++; + } + total_rx_packets++; + total_rx_bytes += size; + } else if (skb) { + ixgbevf_add_rx_frag(rx_ring, rx_buffer, skb, size); + } else if (ring_uses_build_skb(rx_ring)) { + skb = ixgbevf_build_skb(rx_ring, rx_buffer, + &xdp, rx_desc); + } else { + skb = ixgbevf_construct_skb(rx_ring, rx_buffer, + &xdp, rx_desc); + } + + /* exit if we failed to retrieve a buffer */ + if (!skb) { + rx_ring->rx_stats.alloc_rx_buff_failed++; + rx_buffer->pagecnt_bias++; + break; + } + + ixgbevf_put_rx_buffer(rx_ring, rx_buffer, skb); + cleaned_count++; + + /* fetch next buffer in frame if non-eop */ + if (ixgbevf_is_non_eop(rx_ring, rx_desc)) + continue; + + /* verify the packet layout is correct */ + if (ixgbevf_cleanup_headers(rx_ring, rx_desc, skb)) { + skb = NULL; + continue; + } + + /* probably a little skewed due to removing CRC */ + total_rx_bytes += skb->len; + + /* Workaround hardware that can't do proper VEPA multicast + * source pruning. + */ + if ((skb->pkt_type == PACKET_BROADCAST || + skb->pkt_type == PACKET_MULTICAST) && + ether_addr_equal(rx_ring->netdev->dev_addr, + eth_hdr(skb)->h_source)) { + dev_kfree_skb_irq(skb); + continue; + } + + /* populate checksum, VLAN, and protocol */ + ixgbevf_process_skb_fields(rx_ring, rx_desc, skb); + + ixgbevf_rx_skb(q_vector, skb); + + /* reset skb pointer */ + skb = NULL; + + /* update budget accounting */ + total_rx_packets++; + } + + /* place incomplete frames back on ring for completion */ + rx_ring->skb = skb; + + if (xdp_xmit) { + struct ixgbevf_ring *xdp_ring = + adapter->xdp_ring[rx_ring->queue_index]; + + /* Force memory writes to complete before letting h/w + * know there are new descriptors to fetch. + */ + wmb(); + ixgbevf_write_tail(xdp_ring, xdp_ring->next_to_use); + } + + u64_stats_update_begin(&rx_ring->syncp); + rx_ring->stats.packets += total_rx_packets; + rx_ring->stats.bytes += total_rx_bytes; + u64_stats_update_end(&rx_ring->syncp); + q_vector->rx.total_packets += total_rx_packets; + q_vector->rx.total_bytes += total_rx_bytes; + + return total_rx_packets; +} + +/** + * ixgbevf_poll - NAPI polling calback + * @napi: napi struct with our devices info in it + * @budget: amount of work driver is allowed to do this pass, in packets + * + * This function will clean more than one or more rings associated with a + * q_vector. + **/ +static int ixgbevf_poll(struct napi_struct *napi, int budget) +{ + struct ixgbevf_q_vector *q_vector = + container_of(napi, struct ixgbevf_q_vector, napi); + struct ixgbevf_adapter *adapter = q_vector->adapter; + struct ixgbevf_ring *ring; + int per_ring_budget, work_done = 0; + bool clean_complete = true; + + ixgbevf_for_each_ring(ring, q_vector->tx) { + if (!ixgbevf_clean_tx_irq(q_vector, ring, budget)) + clean_complete = false; + } + + if (budget <= 0) + return budget; + + /* attempt to distribute budget to each queue fairly, but don't allow + * the budget to go below 1 because we'll exit polling + */ + if (q_vector->rx.count > 1) + per_ring_budget = max(budget/q_vector->rx.count, 1); + else + per_ring_budget = budget; + + ixgbevf_for_each_ring(ring, q_vector->rx) { + int cleaned = ixgbevf_clean_rx_irq(q_vector, ring, + per_ring_budget); + work_done += cleaned; + if (cleaned >= per_ring_budget) + clean_complete = false; + } + + /* If all work not completed, return budget and keep polling */ + if (!clean_complete) + return budget; + + /* Exit the polling mode, but don't re-enable interrupts if stack might + * poll us due to busy-polling + */ + if (likely(napi_complete_done(napi, work_done))) { + if (adapter->rx_itr_setting == 1) + ixgbevf_set_itr(q_vector); + if (!test_bit(__IXGBEVF_DOWN, &adapter->state) && + !test_bit(__IXGBEVF_REMOVING, &adapter->state)) + ixgbevf_irq_enable_queues(adapter, + BIT(q_vector->v_idx)); + } + + return min(work_done, budget - 1); +} + +/** + * ixgbevf_write_eitr - write VTEITR register in hardware specific way + * @q_vector: structure containing interrupt and ring information + **/ +void ixgbevf_write_eitr(struct ixgbevf_q_vector *q_vector) +{ + struct ixgbevf_adapter *adapter = q_vector->adapter; + struct ixgbe_hw *hw = &adapter->hw; + int v_idx = q_vector->v_idx; + u32 itr_reg = q_vector->itr & IXGBE_MAX_EITR; + + /* set the WDIS bit to not clear the timer bits and cause an + * immediate assertion of the interrupt + */ + itr_reg |= IXGBE_EITR_CNT_WDIS; + + IXGBE_WRITE_REG(hw, IXGBE_VTEITR(v_idx), itr_reg); +} + +/** + * ixgbevf_configure_msix - Configure MSI-X hardware + * @adapter: board private structure + * + * ixgbevf_configure_msix sets up the hardware to properly generate MSI-X + * interrupts. + **/ +static void ixgbevf_configure_msix(struct ixgbevf_adapter *adapter) +{ + struct ixgbevf_q_vector *q_vector; + int q_vectors, v_idx; + + q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + adapter->eims_enable_mask = 0; + + /* Populate the IVAR table and set the ITR values to the + * corresponding register. + */ + for (v_idx = 0; v_idx < q_vectors; v_idx++) { + struct ixgbevf_ring *ring; + + q_vector = adapter->q_vector[v_idx]; + + ixgbevf_for_each_ring(ring, q_vector->rx) + ixgbevf_set_ivar(adapter, 0, ring->reg_idx, v_idx); + + ixgbevf_for_each_ring(ring, q_vector->tx) + ixgbevf_set_ivar(adapter, 1, ring->reg_idx, v_idx); + + if (q_vector->tx.ring && !q_vector->rx.ring) { + /* Tx only vector */ + if (adapter->tx_itr_setting == 1) + q_vector->itr = IXGBE_12K_ITR; + else + q_vector->itr = adapter->tx_itr_setting; + } else { + /* Rx or Rx/Tx vector */ + if (adapter->rx_itr_setting == 1) + q_vector->itr = IXGBE_20K_ITR; + else + q_vector->itr = adapter->rx_itr_setting; + } + + /* add q_vector eims value to global eims_enable_mask */ + adapter->eims_enable_mask |= BIT(v_idx); + + ixgbevf_write_eitr(q_vector); + } + + ixgbevf_set_ivar(adapter, -1, 1, v_idx); + /* setup eims_other and add value to global eims_enable_mask */ + adapter->eims_other = BIT(v_idx); + adapter->eims_enable_mask |= adapter->eims_other; +} + +enum latency_range { + lowest_latency = 0, + low_latency = 1, + bulk_latency = 2, + latency_invalid = 255 +}; + +/** + * ixgbevf_update_itr - update the dynamic ITR value based on statistics + * @q_vector: structure containing interrupt and ring information + * @ring_container: structure containing ring performance data + * + * Stores a new ITR value based on packets and byte + * counts during the last interrupt. The advantage of per interrupt + * computation is faster updates and more accurate ITR for the current + * traffic pattern. Constants in this function were computed + * based on theoretical maximum wire speed and thresholds were set based + * on testing data as well as attempting to minimize response time + * while increasing bulk throughput. + **/ +static void ixgbevf_update_itr(struct ixgbevf_q_vector *q_vector, + struct ixgbevf_ring_container *ring_container) +{ + int bytes = ring_container->total_bytes; + int packets = ring_container->total_packets; + u32 timepassed_us; + u64 bytes_perint; + u8 itr_setting = ring_container->itr; + + if (packets == 0) + return; + + /* simple throttle rate management + * 0-20MB/s lowest (100000 ints/s) + * 20-100MB/s low (20000 ints/s) + * 100-1249MB/s bulk (12000 ints/s) + */ + /* what was last interrupt timeslice? */ + timepassed_us = q_vector->itr >> 2; + if (timepassed_us == 0) + return; + + bytes_perint = bytes / timepassed_us; /* bytes/usec */ + + switch (itr_setting) { + case lowest_latency: + if (bytes_perint > 10) + itr_setting = low_latency; + break; + case low_latency: + if (bytes_perint > 20) + itr_setting = bulk_latency; + else if (bytes_perint <= 10) + itr_setting = lowest_latency; + break; + case bulk_latency: + if (bytes_perint <= 20) + itr_setting = low_latency; + break; + } + + /* clear work counters since we have the values we need */ + ring_container->total_bytes = 0; + ring_container->total_packets = 0; + + /* write updated itr to ring container */ + ring_container->itr = itr_setting; +} + +static void ixgbevf_set_itr(struct ixgbevf_q_vector *q_vector) +{ + u32 new_itr = q_vector->itr; + u8 current_itr; + + ixgbevf_update_itr(q_vector, &q_vector->tx); + ixgbevf_update_itr(q_vector, &q_vector->rx); + + current_itr = max(q_vector->rx.itr, q_vector->tx.itr); + + switch (current_itr) { + /* counts and packets in update_itr are dependent on these numbers */ + case lowest_latency: + new_itr = IXGBE_100K_ITR; + break; + case low_latency: + new_itr = IXGBE_20K_ITR; + break; + case bulk_latency: + new_itr = IXGBE_12K_ITR; + break; + default: + break; + } + + if (new_itr != q_vector->itr) { + /* do an exponential smoothing */ + new_itr = (10 * new_itr * q_vector->itr) / + ((9 * new_itr) + q_vector->itr); + + /* save the algorithm value here */ + q_vector->itr = new_itr; + + ixgbevf_write_eitr(q_vector); + } +} + +static irqreturn_t ixgbevf_msix_other(int irq, void *data) +{ + struct ixgbevf_adapter *adapter = data; + struct ixgbe_hw *hw = &adapter->hw; + + hw->mac.get_link_status = 1; + + ixgbevf_service_event_schedule(adapter); + + IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, adapter->eims_other); + + return IRQ_HANDLED; +} + +/** + * ixgbevf_msix_clean_rings - single unshared vector rx clean (all queues) + * @irq: unused + * @data: pointer to our q_vector struct for this interrupt vector + **/ +static irqreturn_t ixgbevf_msix_clean_rings(int irq, void *data) +{ + struct ixgbevf_q_vector *q_vector = data; + + /* EIAM disabled interrupts (on this vector) for us */ + if (q_vector->rx.ring || q_vector->tx.ring) + napi_schedule_irqoff(&q_vector->napi); + + return IRQ_HANDLED; +} + +/** + * ixgbevf_request_msix_irqs - Initialize MSI-X interrupts + * @adapter: board private structure + * + * ixgbevf_request_msix_irqs allocates MSI-X vectors and requests + * interrupts from the kernel. + **/ +static int ixgbevf_request_msix_irqs(struct ixgbevf_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + unsigned int ri = 0, ti = 0; + int vector, err; + + for (vector = 0; vector < q_vectors; vector++) { + struct ixgbevf_q_vector *q_vector = adapter->q_vector[vector]; + struct msix_entry *entry = &adapter->msix_entries[vector]; + + if (q_vector->tx.ring && q_vector->rx.ring) { + snprintf(q_vector->name, sizeof(q_vector->name), + "%s-TxRx-%u", netdev->name, ri++); + ti++; + } else if (q_vector->rx.ring) { + snprintf(q_vector->name, sizeof(q_vector->name), + "%s-rx-%u", netdev->name, ri++); + } else if (q_vector->tx.ring) { + snprintf(q_vector->name, sizeof(q_vector->name), + "%s-tx-%u", netdev->name, ti++); + } else { + /* skip this unused q_vector */ + continue; + } + err = request_irq(entry->vector, &ixgbevf_msix_clean_rings, 0, + q_vector->name, q_vector); + if (err) { + hw_dbg(&adapter->hw, + "request_irq failed for MSIX interrupt Error: %d\n", + err); + goto free_queue_irqs; + } + } + + err = request_irq(adapter->msix_entries[vector].vector, + &ixgbevf_msix_other, 0, netdev->name, adapter); + if (err) { + hw_dbg(&adapter->hw, "request_irq for msix_other failed: %d\n", + err); + goto free_queue_irqs; + } + + return 0; + +free_queue_irqs: + while (vector) { + vector--; + free_irq(adapter->msix_entries[vector].vector, + adapter->q_vector[vector]); + } + /* This failure is non-recoverable - it indicates the system is + * out of MSIX vector resources and the VF driver cannot run + * without them. Set the number of msix vectors to zero + * indicating that not enough can be allocated. The error + * will be returned to the user indicating device open failed. + * Any further attempts to force the driver to open will also + * fail. The only way to recover is to unload the driver and + * reload it again. If the system has recovered some MSIX + * vectors then it may succeed. + */ + adapter->num_msix_vectors = 0; + return err; +} + +/** + * ixgbevf_request_irq - initialize interrupts + * @adapter: board private structure + * + * Attempts to configure interrupts using the best available + * capabilities of the hardware and kernel. + **/ +static int ixgbevf_request_irq(struct ixgbevf_adapter *adapter) +{ + int err = ixgbevf_request_msix_irqs(adapter); + + if (err) + hw_dbg(&adapter->hw, "request_irq failed, Error %d\n", err); + + return err; +} + +static void ixgbevf_free_irq(struct ixgbevf_adapter *adapter) +{ + int i, q_vectors; + + if (!adapter->msix_entries) + return; + + q_vectors = adapter->num_msix_vectors; + i = q_vectors - 1; + + free_irq(adapter->msix_entries[i].vector, adapter); + i--; + + for (; i >= 0; i--) { + /* free only the irqs that were actually requested */ + if (!adapter->q_vector[i]->rx.ring && + !adapter->q_vector[i]->tx.ring) + continue; + + free_irq(adapter->msix_entries[i].vector, + adapter->q_vector[i]); + } +} + +/** + * ixgbevf_irq_disable - Mask off interrupt generation on the NIC + * @adapter: board private structure + **/ +static inline void ixgbevf_irq_disable(struct ixgbevf_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int i; + + IXGBE_WRITE_REG(hw, IXGBE_VTEIAM, 0); + IXGBE_WRITE_REG(hw, IXGBE_VTEIMC, ~0); + IXGBE_WRITE_REG(hw, IXGBE_VTEIAC, 0); + + IXGBE_WRITE_FLUSH(hw); + + for (i = 0; i < adapter->num_msix_vectors; i++) + synchronize_irq(adapter->msix_entries[i].vector); +} + +/** + * ixgbevf_irq_enable - Enable default interrupt generation settings + * @adapter: board private structure + **/ +static inline void ixgbevf_irq_enable(struct ixgbevf_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + + IXGBE_WRITE_REG(hw, IXGBE_VTEIAM, adapter->eims_enable_mask); + IXGBE_WRITE_REG(hw, IXGBE_VTEIAC, adapter->eims_enable_mask); + IXGBE_WRITE_REG(hw, IXGBE_VTEIMS, adapter->eims_enable_mask); +} + +/** + * ixgbevf_configure_tx_ring - Configure 82599 VF Tx ring after Reset + * @adapter: board private structure + * @ring: structure containing ring specific data + * + * Configure the Tx descriptor ring after a reset. + **/ +static void ixgbevf_configure_tx_ring(struct ixgbevf_adapter *adapter, + struct ixgbevf_ring *ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + u64 tdba = ring->dma; + int wait_loop = 10; + u32 txdctl = IXGBE_TXDCTL_ENABLE; + u8 reg_idx = ring->reg_idx; + + /* disable queue to avoid issues while updating state */ + IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH); + IXGBE_WRITE_FLUSH(hw); + + IXGBE_WRITE_REG(hw, IXGBE_VFTDBAL(reg_idx), tdba & DMA_BIT_MASK(32)); + IXGBE_WRITE_REG(hw, IXGBE_VFTDBAH(reg_idx), tdba >> 32); + IXGBE_WRITE_REG(hw, IXGBE_VFTDLEN(reg_idx), + ring->count * sizeof(union ixgbe_adv_tx_desc)); + + /* disable head writeback */ + IXGBE_WRITE_REG(hw, IXGBE_VFTDWBAH(reg_idx), 0); + IXGBE_WRITE_REG(hw, IXGBE_VFTDWBAL(reg_idx), 0); + + /* enable relaxed ordering */ + IXGBE_WRITE_REG(hw, IXGBE_VFDCA_TXCTRL(reg_idx), + (IXGBE_DCA_TXCTRL_DESC_RRO_EN | + IXGBE_DCA_TXCTRL_DATA_RRO_EN)); + + /* reset head and tail pointers */ + IXGBE_WRITE_REG(hw, IXGBE_VFTDH(reg_idx), 0); + IXGBE_WRITE_REG(hw, IXGBE_VFTDT(reg_idx), 0); + ring->tail = adapter->io_addr + IXGBE_VFTDT(reg_idx); + + /* reset ntu and ntc to place SW in sync with hardwdare */ + ring->next_to_clean = 0; + ring->next_to_use = 0; + + /* In order to avoid issues WTHRESH + PTHRESH should always be equal + * to or less than the number of on chip descriptors, which is + * currently 40. + */ + txdctl |= (8 << 16); /* WTHRESH = 8 */ + + /* Setting PTHRESH to 32 both improves performance */ + txdctl |= (1u << 8) | /* HTHRESH = 1 */ + 32; /* PTHRESH = 32 */ + + /* reinitialize tx_buffer_info */ + memset(ring->tx_buffer_info, 0, + sizeof(struct ixgbevf_tx_buffer) * ring->count); + + clear_bit(__IXGBEVF_HANG_CHECK_ARMED, &ring->state); + clear_bit(__IXGBEVF_TX_XDP_RING_PRIMED, &ring->state); + + IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(reg_idx), txdctl); + + /* poll to verify queue is enabled */ + do { + usleep_range(1000, 2000); + txdctl = IXGBE_READ_REG(hw, IXGBE_VFTXDCTL(reg_idx)); + } while (--wait_loop && !(txdctl & IXGBE_TXDCTL_ENABLE)); + if (!wait_loop) + hw_dbg(hw, "Could not enable Tx Queue %d\n", reg_idx); +} + +/** + * ixgbevf_configure_tx - Configure 82599 VF Transmit Unit after Reset + * @adapter: board private structure + * + * Configure the Tx unit of the MAC after a reset. + **/ +static void ixgbevf_configure_tx(struct ixgbevf_adapter *adapter) +{ + u32 i; + + /* Setup the HW Tx Head and Tail descriptor pointers */ + for (i = 0; i < adapter->num_tx_queues; i++) + ixgbevf_configure_tx_ring(adapter, adapter->tx_ring[i]); + for (i = 0; i < adapter->num_xdp_queues; i++) + ixgbevf_configure_tx_ring(adapter, adapter->xdp_ring[i]); +} + +#define IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT 2 + +static void ixgbevf_configure_srrctl(struct ixgbevf_adapter *adapter, + struct ixgbevf_ring *ring, int index) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 srrctl; + + srrctl = IXGBE_SRRCTL_DROP_EN; + + srrctl |= IXGBEVF_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT; + if (ring_uses_large_buffer(ring)) + srrctl |= IXGBEVF_RXBUFFER_3072 >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; + else + srrctl |= IXGBEVF_RXBUFFER_2048 >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; + srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF; + + IXGBE_WRITE_REG(hw, IXGBE_VFSRRCTL(index), srrctl); +} + +static void ixgbevf_setup_psrtype(struct ixgbevf_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + + /* PSRTYPE must be initialized in 82599 */ + u32 psrtype = IXGBE_PSRTYPE_TCPHDR | IXGBE_PSRTYPE_UDPHDR | + IXGBE_PSRTYPE_IPV4HDR | IXGBE_PSRTYPE_IPV6HDR | + IXGBE_PSRTYPE_L2HDR; + + if (adapter->num_rx_queues > 1) + psrtype |= BIT(29); + + IXGBE_WRITE_REG(hw, IXGBE_VFPSRTYPE, psrtype); +} + +#define IXGBEVF_MAX_RX_DESC_POLL 10 +static void ixgbevf_disable_rx_queue(struct ixgbevf_adapter *adapter, + struct ixgbevf_ring *ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + int wait_loop = IXGBEVF_MAX_RX_DESC_POLL; + u32 rxdctl; + u8 reg_idx = ring->reg_idx; + + if (IXGBE_REMOVED(hw->hw_addr)) + return; + rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(reg_idx)); + rxdctl &= ~IXGBE_RXDCTL_ENABLE; + + /* write value back with RXDCTL.ENABLE bit cleared */ + IXGBE_WRITE_REG(hw, IXGBE_VFRXDCTL(reg_idx), rxdctl); + + /* the hardware may take up to 100us to really disable the Rx queue */ + do { + udelay(10); + rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(reg_idx)); + } while (--wait_loop && (rxdctl & IXGBE_RXDCTL_ENABLE)); + + if (!wait_loop) + pr_err("RXDCTL.ENABLE queue %d not cleared while polling\n", + reg_idx); +} + +static void ixgbevf_rx_desc_queue_enable(struct ixgbevf_adapter *adapter, + struct ixgbevf_ring *ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + int wait_loop = IXGBEVF_MAX_RX_DESC_POLL; + u32 rxdctl; + u8 reg_idx = ring->reg_idx; + + if (IXGBE_REMOVED(hw->hw_addr)) + return; + do { + usleep_range(1000, 2000); + rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(reg_idx)); + } while (--wait_loop && !(rxdctl & IXGBE_RXDCTL_ENABLE)); + + if (!wait_loop) + pr_err("RXDCTL.ENABLE queue %d not set while polling\n", + reg_idx); +} + +/** + * ixgbevf_init_rss_key - Initialize adapter RSS key + * @adapter: device handle + * + * Allocates and initializes the RSS key if it is not allocated. + **/ +static inline int ixgbevf_init_rss_key(struct ixgbevf_adapter *adapter) +{ + u32 *rss_key; + + if (!adapter->rss_key) { + rss_key = kzalloc(IXGBEVF_RSS_HASH_KEY_SIZE, GFP_KERNEL); + if (unlikely(!rss_key)) + return -ENOMEM; + + netdev_rss_key_fill(rss_key, IXGBEVF_RSS_HASH_KEY_SIZE); + adapter->rss_key = rss_key; + } + + return 0; +} + +static void ixgbevf_setup_vfmrqc(struct ixgbevf_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 vfmrqc = 0, vfreta = 0; + u16 rss_i = adapter->num_rx_queues; + u8 i, j; + + /* Fill out hash function seeds */ + for (i = 0; i < IXGBEVF_VFRSSRK_REGS; i++) + IXGBE_WRITE_REG(hw, IXGBE_VFRSSRK(i), *(adapter->rss_key + i)); + + for (i = 0, j = 0; i < IXGBEVF_X550_VFRETA_SIZE; i++, j++) { + if (j == rss_i) + j = 0; + + adapter->rss_indir_tbl[i] = j; + + vfreta |= j << (i & 0x3) * 8; + if ((i & 3) == 3) { + IXGBE_WRITE_REG(hw, IXGBE_VFRETA(i >> 2), vfreta); + vfreta = 0; + } + } + + /* Perform hash on these packet types */ + vfmrqc |= IXGBE_VFMRQC_RSS_FIELD_IPV4 | + IXGBE_VFMRQC_RSS_FIELD_IPV4_TCP | + IXGBE_VFMRQC_RSS_FIELD_IPV6 | + IXGBE_VFMRQC_RSS_FIELD_IPV6_TCP; + + vfmrqc |= IXGBE_VFMRQC_RSSEN; + + IXGBE_WRITE_REG(hw, IXGBE_VFMRQC, vfmrqc); +} + +static void ixgbevf_configure_rx_ring(struct ixgbevf_adapter *adapter, + struct ixgbevf_ring *ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + union ixgbe_adv_rx_desc *rx_desc; + u64 rdba = ring->dma; + u32 rxdctl; + u8 reg_idx = ring->reg_idx; + + /* disable queue to avoid issues while updating state */ + rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(reg_idx)); + ixgbevf_disable_rx_queue(adapter, ring); + + IXGBE_WRITE_REG(hw, IXGBE_VFRDBAL(reg_idx), rdba & DMA_BIT_MASK(32)); + IXGBE_WRITE_REG(hw, IXGBE_VFRDBAH(reg_idx), rdba >> 32); + IXGBE_WRITE_REG(hw, IXGBE_VFRDLEN(reg_idx), + ring->count * sizeof(union ixgbe_adv_rx_desc)); + +#ifndef CONFIG_SPARC + /* enable relaxed ordering */ + IXGBE_WRITE_REG(hw, IXGBE_VFDCA_RXCTRL(reg_idx), + IXGBE_DCA_RXCTRL_DESC_RRO_EN); +#else + IXGBE_WRITE_REG(hw, IXGBE_VFDCA_RXCTRL(reg_idx), + IXGBE_DCA_RXCTRL_DESC_RRO_EN | + IXGBE_DCA_RXCTRL_DATA_WRO_EN); +#endif + + /* reset head and tail pointers */ + IXGBE_WRITE_REG(hw, IXGBE_VFRDH(reg_idx), 0); + IXGBE_WRITE_REG(hw, IXGBE_VFRDT(reg_idx), 0); + ring->tail = adapter->io_addr + IXGBE_VFRDT(reg_idx); + + /* initialize rx_buffer_info */ + memset(ring->rx_buffer_info, 0, + sizeof(struct ixgbevf_rx_buffer) * ring->count); + + /* initialize Rx descriptor 0 */ + rx_desc = IXGBEVF_RX_DESC(ring, 0); + rx_desc->wb.upper.length = 0; + + /* reset ntu and ntc to place SW in sync with hardwdare */ + ring->next_to_clean = 0; + ring->next_to_use = 0; + ring->next_to_alloc = 0; + + ixgbevf_configure_srrctl(adapter, ring, reg_idx); + + /* RXDCTL.RLPML does not work on 82599 */ + if (adapter->hw.mac.type != ixgbe_mac_82599_vf) { + rxdctl &= ~(IXGBE_RXDCTL_RLPMLMASK | + IXGBE_RXDCTL_RLPML_EN); + +#if (PAGE_SIZE < 8192) + /* Limit the maximum frame size so we don't overrun the skb */ + if (ring_uses_build_skb(ring) && + !ring_uses_large_buffer(ring)) + rxdctl |= IXGBEVF_MAX_FRAME_BUILD_SKB | + IXGBE_RXDCTL_RLPML_EN; +#endif + } + + rxdctl |= IXGBE_RXDCTL_ENABLE | IXGBE_RXDCTL_VME; + IXGBE_WRITE_REG(hw, IXGBE_VFRXDCTL(reg_idx), rxdctl); + + ixgbevf_rx_desc_queue_enable(adapter, ring); + ixgbevf_alloc_rx_buffers(ring, ixgbevf_desc_unused(ring)); +} + +static void ixgbevf_set_rx_buffer_len(struct ixgbevf_adapter *adapter, + struct ixgbevf_ring *rx_ring) +{ + struct net_device *netdev = adapter->netdev; + unsigned int max_frame = netdev->mtu + ETH_HLEN + ETH_FCS_LEN; + + /* set build_skb and buffer size flags */ + clear_ring_build_skb_enabled(rx_ring); + clear_ring_uses_large_buffer(rx_ring); + + if (adapter->flags & IXGBEVF_FLAGS_LEGACY_RX) + return; + + if (PAGE_SIZE < 8192) + if (max_frame > IXGBEVF_MAX_FRAME_BUILD_SKB) + set_ring_uses_large_buffer(rx_ring); + + /* 82599 can't rely on RXDCTL.RLPML to restrict the size of the frame */ + if (adapter->hw.mac.type == ixgbe_mac_82599_vf && !ring_uses_large_buffer(rx_ring)) + return; + + set_ring_build_skb_enabled(rx_ring); +} + +/** + * ixgbevf_configure_rx - Configure 82599 VF Receive Unit after Reset + * @adapter: board private structure + * + * Configure the Rx unit of the MAC after a reset. + **/ +static void ixgbevf_configure_rx(struct ixgbevf_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; + int i, ret; + + ixgbevf_setup_psrtype(adapter); + if (hw->mac.type >= ixgbe_mac_X550_vf) + ixgbevf_setup_vfmrqc(adapter); + + spin_lock_bh(&adapter->mbx_lock); + /* notify the PF of our intent to use this size of frame */ + ret = hw->mac.ops.set_rlpml(hw, netdev->mtu + ETH_HLEN + ETH_FCS_LEN); + spin_unlock_bh(&adapter->mbx_lock); + if (ret) + dev_err(&adapter->pdev->dev, + "Failed to set MTU at %d\n", netdev->mtu); + + /* Setup the HW Rx Head and Tail Descriptor Pointers and + * the Base and Length of the Rx Descriptor Ring + */ + for (i = 0; i < adapter->num_rx_queues; i++) { + struct ixgbevf_ring *rx_ring = adapter->rx_ring[i]; + + ixgbevf_set_rx_buffer_len(adapter, rx_ring); + ixgbevf_configure_rx_ring(adapter, rx_ring); + } +} + +static int ixgbevf_vlan_rx_add_vid(struct net_device *netdev, + __be16 proto, u16 vid) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + int err; + + spin_lock_bh(&adapter->mbx_lock); + + /* add VID to filter table */ + err = hw->mac.ops.set_vfta(hw, vid, 0, true); + + spin_unlock_bh(&adapter->mbx_lock); + + /* translate error return types so error makes sense */ + if (err == IXGBE_ERR_MBX) + return -EIO; + + if (err == IXGBE_ERR_INVALID_ARGUMENT) + return -EACCES; + + set_bit(vid, adapter->active_vlans); + + return err; +} + +static int ixgbevf_vlan_rx_kill_vid(struct net_device *netdev, + __be16 proto, u16 vid) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + int err; + + spin_lock_bh(&adapter->mbx_lock); + + /* remove VID from filter table */ + err = hw->mac.ops.set_vfta(hw, vid, 0, false); + + spin_unlock_bh(&adapter->mbx_lock); + + clear_bit(vid, adapter->active_vlans); + + return err; +} + +static void ixgbevf_restore_vlan(struct ixgbevf_adapter *adapter) +{ + u16 vid; + + for_each_set_bit(vid, adapter->active_vlans, VLAN_N_VID) + ixgbevf_vlan_rx_add_vid(adapter->netdev, + htons(ETH_P_8021Q), vid); +} + +static int ixgbevf_write_uc_addr_list(struct net_device *netdev) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + int count = 0; + + if (!netdev_uc_empty(netdev)) { + struct netdev_hw_addr *ha; + + netdev_for_each_uc_addr(ha, netdev) { + hw->mac.ops.set_uc_addr(hw, ++count, ha->addr); + udelay(200); + } + } else { + /* If the list is empty then send message to PF driver to + * clear all MAC VLANs on this VF. + */ + hw->mac.ops.set_uc_addr(hw, 0, NULL); + } + + return count; +} + +/** + * ixgbevf_set_rx_mode - Multicast and unicast set + * @netdev: network interface device structure + * + * The set_rx_method entry point is called whenever the multicast address + * list, unicast address list or the network interface flags are updated. + * This routine is responsible for configuring the hardware for proper + * multicast mode and configuring requested unicast filters. + **/ +static void ixgbevf_set_rx_mode(struct net_device *netdev) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + unsigned int flags = netdev->flags; + int xcast_mode; + + /* request the most inclusive mode we need */ + if (flags & IFF_PROMISC) + xcast_mode = IXGBEVF_XCAST_MODE_PROMISC; + else if (flags & IFF_ALLMULTI) + xcast_mode = IXGBEVF_XCAST_MODE_ALLMULTI; + else if (flags & (IFF_BROADCAST | IFF_MULTICAST)) + xcast_mode = IXGBEVF_XCAST_MODE_MULTI; + else + xcast_mode = IXGBEVF_XCAST_MODE_NONE; + + spin_lock_bh(&adapter->mbx_lock); + + hw->mac.ops.update_xcast_mode(hw, xcast_mode); + + /* reprogram multicast list */ + hw->mac.ops.update_mc_addr_list(hw, netdev); + + ixgbevf_write_uc_addr_list(netdev); + + spin_unlock_bh(&adapter->mbx_lock); +} + +static void ixgbevf_napi_enable_all(struct ixgbevf_adapter *adapter) +{ + int q_idx; + struct ixgbevf_q_vector *q_vector; + int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + + for (q_idx = 0; q_idx < q_vectors; q_idx++) { + q_vector = adapter->q_vector[q_idx]; + napi_enable(&q_vector->napi); + } +} + +static void ixgbevf_napi_disable_all(struct ixgbevf_adapter *adapter) +{ + int q_idx; + struct ixgbevf_q_vector *q_vector; + int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + + for (q_idx = 0; q_idx < q_vectors; q_idx++) { + q_vector = adapter->q_vector[q_idx]; + napi_disable(&q_vector->napi); + } +} + +static int ixgbevf_configure_dcb(struct ixgbevf_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + unsigned int def_q = 0; + unsigned int num_tcs = 0; + unsigned int num_rx_queues = adapter->num_rx_queues; + unsigned int num_tx_queues = adapter->num_tx_queues; + int err; + + spin_lock_bh(&adapter->mbx_lock); + + /* fetch queue configuration from the PF */ + err = ixgbevf_get_queues(hw, &num_tcs, &def_q); + + spin_unlock_bh(&adapter->mbx_lock); + + if (err) + return err; + + if (num_tcs > 1) { + /* we need only one Tx queue */ + num_tx_queues = 1; + + /* update default Tx ring register index */ + adapter->tx_ring[0]->reg_idx = def_q; + + /* we need as many queues as traffic classes */ + num_rx_queues = num_tcs; + } + + /* if we have a bad config abort request queue reset */ + if ((adapter->num_rx_queues != num_rx_queues) || + (adapter->num_tx_queues != num_tx_queues)) { + /* force mailbox timeout to prevent further messages */ + hw->mbx.timeout = 0; + + /* wait for watchdog to come around and bail us out */ + set_bit(__IXGBEVF_QUEUE_RESET_REQUESTED, &adapter->state); + } + + return 0; +} + +static void ixgbevf_configure(struct ixgbevf_adapter *adapter) +{ + ixgbevf_configure_dcb(adapter); + + ixgbevf_set_rx_mode(adapter->netdev); + + ixgbevf_restore_vlan(adapter); + ixgbevf_ipsec_restore(adapter); + + ixgbevf_configure_tx(adapter); + ixgbevf_configure_rx(adapter); +} + +static void ixgbevf_save_reset_stats(struct ixgbevf_adapter *adapter) +{ + /* Only save pre-reset stats if there are some */ + if (adapter->stats.vfgprc || adapter->stats.vfgptc) { + adapter->stats.saved_reset_vfgprc += adapter->stats.vfgprc - + adapter->stats.base_vfgprc; + adapter->stats.saved_reset_vfgptc += adapter->stats.vfgptc - + adapter->stats.base_vfgptc; + adapter->stats.saved_reset_vfgorc += adapter->stats.vfgorc - + adapter->stats.base_vfgorc; + adapter->stats.saved_reset_vfgotc += adapter->stats.vfgotc - + adapter->stats.base_vfgotc; + adapter->stats.saved_reset_vfmprc += adapter->stats.vfmprc - + adapter->stats.base_vfmprc; + } +} + +static void ixgbevf_init_last_counter_stats(struct ixgbevf_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + + adapter->stats.last_vfgprc = IXGBE_READ_REG(hw, IXGBE_VFGPRC); + adapter->stats.last_vfgorc = IXGBE_READ_REG(hw, IXGBE_VFGORC_LSB); + adapter->stats.last_vfgorc |= + (((u64)(IXGBE_READ_REG(hw, IXGBE_VFGORC_MSB))) << 32); + adapter->stats.last_vfgptc = IXGBE_READ_REG(hw, IXGBE_VFGPTC); + adapter->stats.last_vfgotc = IXGBE_READ_REG(hw, IXGBE_VFGOTC_LSB); + adapter->stats.last_vfgotc |= + (((u64)(IXGBE_READ_REG(hw, IXGBE_VFGOTC_MSB))) << 32); + adapter->stats.last_vfmprc = IXGBE_READ_REG(hw, IXGBE_VFMPRC); + + adapter->stats.base_vfgprc = adapter->stats.last_vfgprc; + adapter->stats.base_vfgorc = adapter->stats.last_vfgorc; + adapter->stats.base_vfgptc = adapter->stats.last_vfgptc; + adapter->stats.base_vfgotc = adapter->stats.last_vfgotc; + adapter->stats.base_vfmprc = adapter->stats.last_vfmprc; +} + +static void ixgbevf_negotiate_api(struct ixgbevf_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + static const int api[] = { + ixgbe_mbox_api_14, + ixgbe_mbox_api_13, + ixgbe_mbox_api_12, + ixgbe_mbox_api_11, + ixgbe_mbox_api_10, + ixgbe_mbox_api_unknown + }; + int err, idx = 0; + + spin_lock_bh(&adapter->mbx_lock); + + while (api[idx] != ixgbe_mbox_api_unknown) { + err = hw->mac.ops.negotiate_api_version(hw, api[idx]); + if (!err) + break; + idx++; + } + + spin_unlock_bh(&adapter->mbx_lock); +} + +static void ixgbevf_up_complete(struct ixgbevf_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct ixgbe_hw *hw = &adapter->hw; + + ixgbevf_configure_msix(adapter); + + spin_lock_bh(&adapter->mbx_lock); + + if (is_valid_ether_addr(hw->mac.addr)) + hw->mac.ops.set_rar(hw, 0, hw->mac.addr, 0); + else + hw->mac.ops.set_rar(hw, 0, hw->mac.perm_addr, 0); + + spin_unlock_bh(&adapter->mbx_lock); + + smp_mb__before_atomic(); + clear_bit(__IXGBEVF_DOWN, &adapter->state); + ixgbevf_napi_enable_all(adapter); + + /* clear any pending interrupts, may auto mask */ + IXGBE_READ_REG(hw, IXGBE_VTEICR); + ixgbevf_irq_enable(adapter); + + /* enable transmits */ + netif_tx_start_all_queues(netdev); + + ixgbevf_save_reset_stats(adapter); + ixgbevf_init_last_counter_stats(adapter); + + hw->mac.get_link_status = 1; + mod_timer(&adapter->service_timer, jiffies); +} + +void ixgbevf_up(struct ixgbevf_adapter *adapter) +{ + ixgbevf_configure(adapter); + + ixgbevf_up_complete(adapter); +} + +/** + * ixgbevf_clean_rx_ring - Free Rx Buffers per Queue + * @rx_ring: ring to free buffers from + **/ +static void ixgbevf_clean_rx_ring(struct ixgbevf_ring *rx_ring) +{ + u16 i = rx_ring->next_to_clean; + + /* Free Rx ring sk_buff */ + if (rx_ring->skb) { + dev_kfree_skb(rx_ring->skb); + rx_ring->skb = NULL; + } + + /* Free all the Rx ring pages */ + while (i != rx_ring->next_to_alloc) { + struct ixgbevf_rx_buffer *rx_buffer; + + rx_buffer = &rx_ring->rx_buffer_info[i]; + + /* Invalidate cache lines that may have been written to by + * device so that we avoid corrupting memory. + */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + ixgbevf_rx_bufsz(rx_ring), + DMA_FROM_DEVICE); + + /* free resources associated with mapping */ + dma_unmap_page_attrs(rx_ring->dev, + rx_buffer->dma, + ixgbevf_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IXGBEVF_RX_DMA_ATTR); + + __page_frag_cache_drain(rx_buffer->page, + rx_buffer->pagecnt_bias); + + i++; + if (i == rx_ring->count) + i = 0; + } + + rx_ring->next_to_alloc = 0; + rx_ring->next_to_clean = 0; + rx_ring->next_to_use = 0; +} + +/** + * ixgbevf_clean_tx_ring - Free Tx Buffers + * @tx_ring: ring to be cleaned + **/ +static void ixgbevf_clean_tx_ring(struct ixgbevf_ring *tx_ring) +{ + u16 i = tx_ring->next_to_clean; + struct ixgbevf_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i]; + + while (i != tx_ring->next_to_use) { + union ixgbe_adv_tx_desc *eop_desc, *tx_desc; + + /* Free all the Tx ring sk_buffs */ + if (ring_is_xdp(tx_ring)) + page_frag_free(tx_buffer->data); + else + dev_kfree_skb_any(tx_buffer->skb); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + + /* check for eop_desc to determine the end of the packet */ + eop_desc = tx_buffer->next_to_watch; + tx_desc = IXGBEVF_TX_DESC(tx_ring, i); + + /* unmap remaining buffers */ + while (tx_desc != eop_desc) { + tx_buffer++; + tx_desc++; + i++; + if (unlikely(i == tx_ring->count)) { + i = 0; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = IXGBEVF_TX_DESC(tx_ring, 0); + } + + /* unmap any remaining paged data */ + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + } + + /* move us one more past the eop_desc for start of next pkt */ + tx_buffer++; + i++; + if (unlikely(i == tx_ring->count)) { + i = 0; + tx_buffer = tx_ring->tx_buffer_info; + } + } + + /* reset next_to_use and next_to_clean */ + tx_ring->next_to_use = 0; + tx_ring->next_to_clean = 0; + +} + +/** + * ixgbevf_clean_all_rx_rings - Free Rx Buffers for all queues + * @adapter: board private structure + **/ +static void ixgbevf_clean_all_rx_rings(struct ixgbevf_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_rx_queues; i++) + ixgbevf_clean_rx_ring(adapter->rx_ring[i]); +} + +/** + * ixgbevf_clean_all_tx_rings - Free Tx Buffers for all queues + * @adapter: board private structure + **/ +static void ixgbevf_clean_all_tx_rings(struct ixgbevf_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) + ixgbevf_clean_tx_ring(adapter->tx_ring[i]); + for (i = 0; i < adapter->num_xdp_queues; i++) + ixgbevf_clean_tx_ring(adapter->xdp_ring[i]); +} + +void ixgbevf_down(struct ixgbevf_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct ixgbe_hw *hw = &adapter->hw; + int i; + + /* signal that we are down to the interrupt handler */ + if (test_and_set_bit(__IXGBEVF_DOWN, &adapter->state)) + return; /* do nothing if already down */ + + /* disable all enabled Rx queues */ + for (i = 0; i < adapter->num_rx_queues; i++) + ixgbevf_disable_rx_queue(adapter, adapter->rx_ring[i]); + + usleep_range(10000, 20000); + + netif_tx_stop_all_queues(netdev); + + /* call carrier off first to avoid false dev_watchdog timeouts */ + netif_carrier_off(netdev); + netif_tx_disable(netdev); + + ixgbevf_irq_disable(adapter); + + ixgbevf_napi_disable_all(adapter); + + del_timer_sync(&adapter->service_timer); + + /* disable transmits in the hardware now that interrupts are off */ + for (i = 0; i < adapter->num_tx_queues; i++) { + u8 reg_idx = adapter->tx_ring[i]->reg_idx; + + IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(reg_idx), + IXGBE_TXDCTL_SWFLSH); + } + + for (i = 0; i < adapter->num_xdp_queues; i++) { + u8 reg_idx = adapter->xdp_ring[i]->reg_idx; + + IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(reg_idx), + IXGBE_TXDCTL_SWFLSH); + } + + if (!pci_channel_offline(adapter->pdev)) + ixgbevf_reset(adapter); + + ixgbevf_clean_all_tx_rings(adapter); + ixgbevf_clean_all_rx_rings(adapter); +} + +void ixgbevf_reinit_locked(struct ixgbevf_adapter *adapter) +{ + while (test_and_set_bit(__IXGBEVF_RESETTING, &adapter->state)) + msleep(1); + + ixgbevf_down(adapter); + pci_set_master(adapter->pdev); + ixgbevf_up(adapter); + + clear_bit(__IXGBEVF_RESETTING, &adapter->state); +} + +void ixgbevf_reset(struct ixgbevf_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; + + if (hw->mac.ops.reset_hw(hw)) { + hw_dbg(hw, "PF still resetting\n"); + } else { + hw->mac.ops.init_hw(hw); + ixgbevf_negotiate_api(adapter); + } + + if (is_valid_ether_addr(adapter->hw.mac.addr)) { + ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr); + ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); + } + + adapter->last_reset = jiffies; +} + +static int ixgbevf_acquire_msix_vectors(struct ixgbevf_adapter *adapter, + int vectors) +{ + int vector_threshold; + + /* We'll want at least 2 (vector_threshold): + * 1) TxQ[0] + RxQ[0] handler + * 2) Other (Link Status Change, etc.) + */ + vector_threshold = MIN_MSIX_COUNT; + + /* The more we get, the more we will assign to Tx/Rx Cleanup + * for the separate queues...where Rx Cleanup >= Tx Cleanup. + * Right now, we simply care about how many we'll get; we'll + * set them up later while requesting irq's. + */ + vectors = pci_enable_msix_range(adapter->pdev, adapter->msix_entries, + vector_threshold, vectors); + + if (vectors < 0) { + dev_err(&adapter->pdev->dev, + "Unable to allocate MSI-X interrupts\n"); + kfree(adapter->msix_entries); + adapter->msix_entries = NULL; + return vectors; + } + + /* Adjust for only the vectors we'll use, which is minimum + * of max_msix_q_vectors + NON_Q_VECTORS, or the number of + * vectors we were allocated. + */ + adapter->num_msix_vectors = vectors; + + return 0; +} + +/** + * ixgbevf_set_num_queues - Allocate queues for device, feature dependent + * @adapter: board private structure to initialize + * + * This is the top level queue allocation routine. The order here is very + * important, starting with the "most" number of features turned on at once, + * and ending with the smallest set of features. This way large combinations + * can be allocated if they're turned on, and smaller combinations are the + * fall through conditions. + * + **/ +static void ixgbevf_set_num_queues(struct ixgbevf_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + unsigned int def_q = 0; + unsigned int num_tcs = 0; + int err; + + /* Start with base case */ + adapter->num_rx_queues = 1; + adapter->num_tx_queues = 1; + adapter->num_xdp_queues = 0; + + spin_lock_bh(&adapter->mbx_lock); + + /* fetch queue configuration from the PF */ + err = ixgbevf_get_queues(hw, &num_tcs, &def_q); + + spin_unlock_bh(&adapter->mbx_lock); + + if (err) + return; + + /* we need as many queues as traffic classes */ + if (num_tcs > 1) { + adapter->num_rx_queues = num_tcs; + } else { + u16 rss = min_t(u16, num_online_cpus(), IXGBEVF_MAX_RSS_QUEUES); + + switch (hw->api_version) { + case ixgbe_mbox_api_11: + case ixgbe_mbox_api_12: + case ixgbe_mbox_api_13: + case ixgbe_mbox_api_14: + if (adapter->xdp_prog && + hw->mac.max_tx_queues == rss) + rss = rss > 3 ? 2 : 1; + + adapter->num_rx_queues = rss; + adapter->num_tx_queues = rss; + adapter->num_xdp_queues = adapter->xdp_prog ? rss : 0; + default: + break; + } + } +} + +/** + * ixgbevf_set_interrupt_capability - set MSI-X or FAIL if not supported + * @adapter: board private structure to initialize + * + * Attempt to configure the interrupts using the best available + * capabilities of the hardware and the kernel. + **/ +static int ixgbevf_set_interrupt_capability(struct ixgbevf_adapter *adapter) +{ + int vector, v_budget; + + /* It's easy to be greedy for MSI-X vectors, but it really + * doesn't do us much good if we have a lot more vectors + * than CPU's. So let's be conservative and only ask for + * (roughly) the same number of vectors as there are CPU's. + * The default is to use pairs of vectors. + */ + v_budget = max(adapter->num_rx_queues, adapter->num_tx_queues); + v_budget = min_t(int, v_budget, num_online_cpus()); + v_budget += NON_Q_VECTORS; + + adapter->msix_entries = kcalloc(v_budget, + sizeof(struct msix_entry), GFP_KERNEL); + if (!adapter->msix_entries) + return -ENOMEM; + + for (vector = 0; vector < v_budget; vector++) + adapter->msix_entries[vector].entry = vector; + + /* A failure in MSI-X entry allocation isn't fatal, but the VF driver + * does not support any other modes, so we will simply fail here. Note + * that we clean up the msix_entries pointer else-where. + */ + return ixgbevf_acquire_msix_vectors(adapter, v_budget); +} + +static void ixgbevf_add_ring(struct ixgbevf_ring *ring, + struct ixgbevf_ring_container *head) +{ + ring->next = head->ring; + head->ring = ring; + head->count++; +} + +/** + * ixgbevf_alloc_q_vector - Allocate memory for a single interrupt vector + * @adapter: board private structure to initialize + * @v_idx: index of vector in adapter struct + * @txr_count: number of Tx rings for q vector + * @txr_idx: index of first Tx ring to assign + * @xdp_count: total number of XDP rings to allocate + * @xdp_idx: index of first XDP ring to allocate + * @rxr_count: number of Rx rings for q vector + * @rxr_idx: index of first Rx ring to assign + * + * We allocate one q_vector. If allocation fails we return -ENOMEM. + **/ +static int ixgbevf_alloc_q_vector(struct ixgbevf_adapter *adapter, int v_idx, + int txr_count, int txr_idx, + int xdp_count, int xdp_idx, + int rxr_count, int rxr_idx) +{ + struct ixgbevf_q_vector *q_vector; + int reg_idx = txr_idx + xdp_idx; + struct ixgbevf_ring *ring; + int ring_count, size; + + ring_count = txr_count + xdp_count + rxr_count; + size = sizeof(*q_vector) + (sizeof(*ring) * ring_count); + + /* allocate q_vector and rings */ + q_vector = kzalloc(size, GFP_KERNEL); + if (!q_vector) + return -ENOMEM; + + /* initialize NAPI */ + netif_napi_add(adapter->netdev, &q_vector->napi, ixgbevf_poll, 64); + + /* tie q_vector and adapter together */ + adapter->q_vector[v_idx] = q_vector; + q_vector->adapter = adapter; + q_vector->v_idx = v_idx; + + /* initialize pointer to rings */ + ring = q_vector->ring; + + while (txr_count) { + /* assign generic ring traits */ + ring->dev = &adapter->pdev->dev; + ring->netdev = adapter->netdev; + + /* configure backlink on ring */ + ring->q_vector = q_vector; + + /* update q_vector Tx values */ + ixgbevf_add_ring(ring, &q_vector->tx); + + /* apply Tx specific ring traits */ + ring->count = adapter->tx_ring_count; + ring->queue_index = txr_idx; + ring->reg_idx = reg_idx; + + /* assign ring to adapter */ + adapter->tx_ring[txr_idx] = ring; + + /* update count and index */ + txr_count--; + txr_idx++; + reg_idx++; + + /* push pointer to next ring */ + ring++; + } + + while (xdp_count) { + /* assign generic ring traits */ + ring->dev = &adapter->pdev->dev; + ring->netdev = adapter->netdev; + + /* configure backlink on ring */ + ring->q_vector = q_vector; + + /* update q_vector Tx values */ + ixgbevf_add_ring(ring, &q_vector->tx); + + /* apply Tx specific ring traits */ + ring->count = adapter->tx_ring_count; + ring->queue_index = xdp_idx; + ring->reg_idx = reg_idx; + set_ring_xdp(ring); + + /* assign ring to adapter */ + adapter->xdp_ring[xdp_idx] = ring; + + /* update count and index */ + xdp_count--; + xdp_idx++; + reg_idx++; + + /* push pointer to next ring */ + ring++; + } + + while (rxr_count) { + /* assign generic ring traits */ + ring->dev = &adapter->pdev->dev; + ring->netdev = adapter->netdev; + + /* configure backlink on ring */ + ring->q_vector = q_vector; + + /* update q_vector Rx values */ + ixgbevf_add_ring(ring, &q_vector->rx); + + /* apply Rx specific ring traits */ + ring->count = adapter->rx_ring_count; + ring->queue_index = rxr_idx; + ring->reg_idx = rxr_idx; + + /* assign ring to adapter */ + adapter->rx_ring[rxr_idx] = ring; + + /* update count and index */ + rxr_count--; + rxr_idx++; + + /* push pointer to next ring */ + ring++; + } + + return 0; +} + +/** + * ixgbevf_free_q_vector - Free memory allocated for specific interrupt vector + * @adapter: board private structure to initialize + * @v_idx: index of vector in adapter struct + * + * This function frees the memory allocated to the q_vector. In addition if + * NAPI is enabled it will delete any references to the NAPI struct prior + * to freeing the q_vector. + **/ +static void ixgbevf_free_q_vector(struct ixgbevf_adapter *adapter, int v_idx) +{ + struct ixgbevf_q_vector *q_vector = adapter->q_vector[v_idx]; + struct ixgbevf_ring *ring; + + ixgbevf_for_each_ring(ring, q_vector->tx) { + if (ring_is_xdp(ring)) + adapter->xdp_ring[ring->queue_index] = NULL; + else + adapter->tx_ring[ring->queue_index] = NULL; + } + + ixgbevf_for_each_ring(ring, q_vector->rx) + adapter->rx_ring[ring->queue_index] = NULL; + + adapter->q_vector[v_idx] = NULL; + netif_napi_del(&q_vector->napi); + + /* ixgbevf_get_stats() might access the rings on this vector, + * we must wait a grace period before freeing it. + */ + kfree_rcu(q_vector, rcu); +} + +/** + * ixgbevf_alloc_q_vectors - Allocate memory for interrupt vectors + * @adapter: board private structure to initialize + * + * We allocate one q_vector per queue interrupt. If allocation fails we + * return -ENOMEM. + **/ +static int ixgbevf_alloc_q_vectors(struct ixgbevf_adapter *adapter) +{ + int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + int rxr_remaining = adapter->num_rx_queues; + int txr_remaining = adapter->num_tx_queues; + int xdp_remaining = adapter->num_xdp_queues; + int rxr_idx = 0, txr_idx = 0, xdp_idx = 0, v_idx = 0; + int err; + + if (q_vectors >= (rxr_remaining + txr_remaining + xdp_remaining)) { + for (; rxr_remaining; v_idx++, q_vectors--) { + int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors); + + err = ixgbevf_alloc_q_vector(adapter, v_idx, + 0, 0, 0, 0, rqpv, rxr_idx); + if (err) + goto err_out; + + /* update counts and index */ + rxr_remaining -= rqpv; + rxr_idx += rqpv; + } + } + + for (; q_vectors; v_idx++, q_vectors--) { + int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors); + int tqpv = DIV_ROUND_UP(txr_remaining, q_vectors); + int xqpv = DIV_ROUND_UP(xdp_remaining, q_vectors); + + err = ixgbevf_alloc_q_vector(adapter, v_idx, + tqpv, txr_idx, + xqpv, xdp_idx, + rqpv, rxr_idx); + + if (err) + goto err_out; + + /* update counts and index */ + rxr_remaining -= rqpv; + rxr_idx += rqpv; + txr_remaining -= tqpv; + txr_idx += tqpv; + xdp_remaining -= xqpv; + xdp_idx += xqpv; + } + + return 0; + +err_out: + while (v_idx) { + v_idx--; + ixgbevf_free_q_vector(adapter, v_idx); + } + + return -ENOMEM; +} + +/** + * ixgbevf_free_q_vectors - Free memory allocated for interrupt vectors + * @adapter: board private structure to initialize + * + * This function frees the memory allocated to the q_vectors. In addition if + * NAPI is enabled it will delete any references to the NAPI struct prior + * to freeing the q_vector. + **/ +static void ixgbevf_free_q_vectors(struct ixgbevf_adapter *adapter) +{ + int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + + while (q_vectors) { + q_vectors--; + ixgbevf_free_q_vector(adapter, q_vectors); + } +} + +/** + * ixgbevf_reset_interrupt_capability - Reset MSIX setup + * @adapter: board private structure + * + **/ +static void ixgbevf_reset_interrupt_capability(struct ixgbevf_adapter *adapter) +{ + if (!adapter->msix_entries) + return; + + pci_disable_msix(adapter->pdev); + kfree(adapter->msix_entries); + adapter->msix_entries = NULL; +} + +/** + * ixgbevf_init_interrupt_scheme - Determine if MSIX is supported and init + * @adapter: board private structure to initialize + * + **/ +static int ixgbevf_init_interrupt_scheme(struct ixgbevf_adapter *adapter) +{ + int err; + + /* Number of supported queues */ + ixgbevf_set_num_queues(adapter); + + err = ixgbevf_set_interrupt_capability(adapter); + if (err) { + hw_dbg(&adapter->hw, + "Unable to setup interrupt capabilities\n"); + goto err_set_interrupt; + } + + err = ixgbevf_alloc_q_vectors(adapter); + if (err) { + hw_dbg(&adapter->hw, "Unable to allocate memory for queue vectors\n"); + goto err_alloc_q_vectors; + } + + hw_dbg(&adapter->hw, "Multiqueue %s: Rx Queue count = %u, Tx Queue count = %u XDP Queue count %u\n", + (adapter->num_rx_queues > 1) ? "Enabled" : "Disabled", + adapter->num_rx_queues, adapter->num_tx_queues, + adapter->num_xdp_queues); + + set_bit(__IXGBEVF_DOWN, &adapter->state); + + return 0; +err_alloc_q_vectors: + ixgbevf_reset_interrupt_capability(adapter); +err_set_interrupt: + return err; +} + +/** + * ixgbevf_clear_interrupt_scheme - Clear the current interrupt scheme settings + * @adapter: board private structure to clear interrupt scheme on + * + * We go through and clear interrupt specific resources and reset the structure + * to pre-load conditions + **/ +static void ixgbevf_clear_interrupt_scheme(struct ixgbevf_adapter *adapter) +{ + adapter->num_tx_queues = 0; + adapter->num_xdp_queues = 0; + adapter->num_rx_queues = 0; + + ixgbevf_free_q_vectors(adapter); + ixgbevf_reset_interrupt_capability(adapter); +} + +/** + * ixgbevf_sw_init - Initialize general software structures + * @adapter: board private structure to initialize + * + * ixgbevf_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 ixgbevf_sw_init(struct ixgbevf_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct pci_dev *pdev = adapter->pdev; + struct net_device *netdev = adapter->netdev; + int err; + + /* PCI config space info */ + hw->vendor_id = pdev->vendor; + hw->device_id = pdev->device; + hw->revision_id = pdev->revision; + hw->subsystem_vendor_id = pdev->subsystem_vendor; + hw->subsystem_device_id = pdev->subsystem_device; + + hw->mbx.ops.init_params(hw); + + if (hw->mac.type >= ixgbe_mac_X550_vf) { + err = ixgbevf_init_rss_key(adapter); + if (err) + goto out; + } + + /* assume legacy case in which PF would only give VF 2 queues */ + hw->mac.max_tx_queues = 2; + hw->mac.max_rx_queues = 2; + + /* lock to protect mailbox accesses */ + spin_lock_init(&adapter->mbx_lock); + + err = hw->mac.ops.reset_hw(hw); + if (err) { + dev_info(&pdev->dev, + "PF still in reset state. Is the PF interface up?\n"); + } else { + err = hw->mac.ops.init_hw(hw); + if (err) { + pr_err("init_shared_code failed: %d\n", err); + goto out; + } + ixgbevf_negotiate_api(adapter); + err = hw->mac.ops.get_mac_addr(hw, hw->mac.addr); + if (err) + dev_info(&pdev->dev, "Error reading MAC address\n"); + else if (is_zero_ether_addr(adapter->hw.mac.addr)) + dev_info(&pdev->dev, + "MAC address not assigned by administrator.\n"); + ether_addr_copy(netdev->dev_addr, hw->mac.addr); + } + + if (!is_valid_ether_addr(netdev->dev_addr)) { + dev_info(&pdev->dev, "Assigning random MAC address\n"); + eth_hw_addr_random(netdev); + ether_addr_copy(hw->mac.addr, netdev->dev_addr); + ether_addr_copy(hw->mac.perm_addr, netdev->dev_addr); + } + + /* Enable dynamic interrupt throttling rates */ + adapter->rx_itr_setting = 1; + adapter->tx_itr_setting = 1; + + /* set default ring sizes */ + adapter->tx_ring_count = IXGBEVF_DEFAULT_TXD; + adapter->rx_ring_count = IXGBEVF_DEFAULT_RXD; + + set_bit(__IXGBEVF_DOWN, &adapter->state); + return 0; + +out: + return err; +} + +#define UPDATE_VF_COUNTER_32bit(reg, last_counter, counter) \ + { \ + u32 current_counter = IXGBE_READ_REG(hw, reg); \ + if (current_counter < last_counter) \ + counter += 0x100000000LL; \ + last_counter = current_counter; \ + counter &= 0xFFFFFFFF00000000LL; \ + counter |= current_counter; \ + } + +#define UPDATE_VF_COUNTER_36bit(reg_lsb, reg_msb, last_counter, counter) \ + { \ + u64 current_counter_lsb = IXGBE_READ_REG(hw, reg_lsb); \ + u64 current_counter_msb = IXGBE_READ_REG(hw, reg_msb); \ + u64 current_counter = (current_counter_msb << 32) | \ + current_counter_lsb; \ + if (current_counter < last_counter) \ + counter += 0x1000000000LL; \ + last_counter = current_counter; \ + counter &= 0xFFFFFFF000000000LL; \ + counter |= current_counter; \ + } +/** + * ixgbevf_update_stats - Update the board statistics counters. + * @adapter: board private structure + **/ +void ixgbevf_update_stats(struct ixgbevf_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u64 alloc_rx_page_failed = 0, alloc_rx_buff_failed = 0; + u64 alloc_rx_page = 0, hw_csum_rx_error = 0; + int i; + + if (test_bit(__IXGBEVF_DOWN, &adapter->state) || + test_bit(__IXGBEVF_RESETTING, &adapter->state)) + return; + + UPDATE_VF_COUNTER_32bit(IXGBE_VFGPRC, adapter->stats.last_vfgprc, + adapter->stats.vfgprc); + UPDATE_VF_COUNTER_32bit(IXGBE_VFGPTC, adapter->stats.last_vfgptc, + adapter->stats.vfgptc); + UPDATE_VF_COUNTER_36bit(IXGBE_VFGORC_LSB, IXGBE_VFGORC_MSB, + adapter->stats.last_vfgorc, + adapter->stats.vfgorc); + UPDATE_VF_COUNTER_36bit(IXGBE_VFGOTC_LSB, IXGBE_VFGOTC_MSB, + adapter->stats.last_vfgotc, + adapter->stats.vfgotc); + UPDATE_VF_COUNTER_32bit(IXGBE_VFMPRC, adapter->stats.last_vfmprc, + adapter->stats.vfmprc); + + for (i = 0; i < adapter->num_rx_queues; i++) { + struct ixgbevf_ring *rx_ring = adapter->rx_ring[i]; + + hw_csum_rx_error += rx_ring->rx_stats.csum_err; + alloc_rx_page_failed += rx_ring->rx_stats.alloc_rx_page_failed; + alloc_rx_buff_failed += rx_ring->rx_stats.alloc_rx_buff_failed; + alloc_rx_page += rx_ring->rx_stats.alloc_rx_page; + } + + adapter->hw_csum_rx_error = hw_csum_rx_error; + adapter->alloc_rx_page_failed = alloc_rx_page_failed; + adapter->alloc_rx_buff_failed = alloc_rx_buff_failed; + adapter->alloc_rx_page = alloc_rx_page; +} + +/** + * ixgbevf_service_timer - Timer Call-back + * @t: pointer to timer_list struct + **/ +static void ixgbevf_service_timer(struct timer_list *t) +{ + struct ixgbevf_adapter *adapter = from_timer(adapter, t, + service_timer); + + /* Reset the timer */ + mod_timer(&adapter->service_timer, (HZ * 2) + jiffies); + + ixgbevf_service_event_schedule(adapter); +} + +static void ixgbevf_reset_subtask(struct ixgbevf_adapter *adapter) +{ + if (!test_and_clear_bit(__IXGBEVF_RESET_REQUESTED, &adapter->state)) + return; + + rtnl_lock(); + /* If we're already down or resetting, just bail */ + if (test_bit(__IXGBEVF_DOWN, &adapter->state) || + test_bit(__IXGBEVF_REMOVING, &adapter->state) || + test_bit(__IXGBEVF_RESETTING, &adapter->state)) { + rtnl_unlock(); + return; + } + + adapter->tx_timeout_count++; + + ixgbevf_reinit_locked(adapter); + rtnl_unlock(); +} + +/** + * ixgbevf_check_hang_subtask - check for hung queues and dropped interrupts + * @adapter: pointer to the device adapter structure + * + * This function serves two purposes. First it strobes the interrupt lines + * in order to make certain interrupts are occurring. Secondly it sets the + * bits needed to check for TX hangs. As a result we should immediately + * determine if a hang has occurred. + **/ +static void ixgbevf_check_hang_subtask(struct ixgbevf_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 eics = 0; + int i; + + /* If we're down or resetting, just bail */ + if (test_bit(__IXGBEVF_DOWN, &adapter->state) || + test_bit(__IXGBEVF_RESETTING, &adapter->state)) + return; + + /* Force detection of hung controller */ + if (netif_carrier_ok(adapter->netdev)) { + for (i = 0; i < adapter->num_tx_queues; i++) + set_check_for_tx_hang(adapter->tx_ring[i]); + for (i = 0; i < adapter->num_xdp_queues; i++) + set_check_for_tx_hang(adapter->xdp_ring[i]); + } + + /* get one bit for every active Tx/Rx interrupt vector */ + for (i = 0; i < adapter->num_msix_vectors - NON_Q_VECTORS; i++) { + struct ixgbevf_q_vector *qv = adapter->q_vector[i]; + + if (qv->rx.ring || qv->tx.ring) + eics |= BIT(i); + } + + /* Cause software interrupt to ensure rings are cleaned */ + IXGBE_WRITE_REG(hw, IXGBE_VTEICS, eics); +} + +/** + * ixgbevf_watchdog_update_link - update the link status + * @adapter: pointer to the device adapter structure + **/ +static void ixgbevf_watchdog_update_link(struct ixgbevf_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 link_speed = adapter->link_speed; + bool link_up = adapter->link_up; + s32 err; + + spin_lock_bh(&adapter->mbx_lock); + + err = hw->mac.ops.check_link(hw, &link_speed, &link_up, false); + + spin_unlock_bh(&adapter->mbx_lock); + + /* if check for link returns error we will need to reset */ + if (err && time_after(jiffies, adapter->last_reset + (10 * HZ))) { + set_bit(__IXGBEVF_RESET_REQUESTED, &adapter->state); + link_up = false; + } + + adapter->link_up = link_up; + adapter->link_speed = link_speed; +} + +/** + * ixgbevf_watchdog_link_is_up - update netif_carrier status and + * print link up message + * @adapter: pointer to the device adapter structure + **/ +static void ixgbevf_watchdog_link_is_up(struct ixgbevf_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + + /* only continue if link was previously down */ + if (netif_carrier_ok(netdev)) + return; + + dev_info(&adapter->pdev->dev, "NIC Link is Up %s\n", + (adapter->link_speed == IXGBE_LINK_SPEED_10GB_FULL) ? + "10 Gbps" : + (adapter->link_speed == IXGBE_LINK_SPEED_1GB_FULL) ? + "1 Gbps" : + (adapter->link_speed == IXGBE_LINK_SPEED_100_FULL) ? + "100 Mbps" : + "unknown speed"); + + netif_carrier_on(netdev); +} + +/** + * ixgbevf_watchdog_link_is_down - update netif_carrier status and + * print link down message + * @adapter: pointer to the adapter structure + **/ +static void ixgbevf_watchdog_link_is_down(struct ixgbevf_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + + adapter->link_speed = 0; + + /* only continue if link was up previously */ + if (!netif_carrier_ok(netdev)) + return; + + dev_info(&adapter->pdev->dev, "NIC Link is Down\n"); + + netif_carrier_off(netdev); +} + +/** + * ixgbevf_watchdog_subtask - worker thread to bring link up + * @adapter: board private structure + **/ +static void ixgbevf_watchdog_subtask(struct ixgbevf_adapter *adapter) +{ + /* if interface is down do nothing */ + if (test_bit(__IXGBEVF_DOWN, &adapter->state) || + test_bit(__IXGBEVF_RESETTING, &adapter->state)) + return; + + ixgbevf_watchdog_update_link(adapter); + + if (adapter->link_up) + ixgbevf_watchdog_link_is_up(adapter); + else + ixgbevf_watchdog_link_is_down(adapter); + + ixgbevf_update_stats(adapter); +} + +/** + * ixgbevf_service_task - manages and runs subtasks + * @work: pointer to work_struct containing our data + **/ +static void ixgbevf_service_task(struct work_struct *work) +{ + struct ixgbevf_adapter *adapter = container_of(work, + struct ixgbevf_adapter, + service_task); + struct ixgbe_hw *hw = &adapter->hw; + + if (IXGBE_REMOVED(hw->hw_addr)) { + if (!test_bit(__IXGBEVF_DOWN, &adapter->state)) { + rtnl_lock(); + ixgbevf_down(adapter); + rtnl_unlock(); + } + return; + } + + ixgbevf_queue_reset_subtask(adapter); + ixgbevf_reset_subtask(adapter); + ixgbevf_watchdog_subtask(adapter); + ixgbevf_check_hang_subtask(adapter); + + ixgbevf_service_event_complete(adapter); +} + +/** + * ixgbevf_free_tx_resources - Free Tx Resources per Queue + * @tx_ring: Tx descriptor ring for a specific queue + * + * Free all transmit software resources + **/ +void ixgbevf_free_tx_resources(struct ixgbevf_ring *tx_ring) +{ + ixgbevf_clean_tx_ring(tx_ring); + + vfree(tx_ring->tx_buffer_info); + tx_ring->tx_buffer_info = NULL; + + /* if not set, then don't free */ + if (!tx_ring->desc) + return; + + dma_free_coherent(tx_ring->dev, tx_ring->size, tx_ring->desc, + tx_ring->dma); + + tx_ring->desc = NULL; +} + +/** + * ixgbevf_free_all_tx_resources - Free Tx Resources for All Queues + * @adapter: board private structure + * + * Free all transmit software resources + **/ +static void ixgbevf_free_all_tx_resources(struct ixgbevf_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) + if (adapter->tx_ring[i]->desc) + ixgbevf_free_tx_resources(adapter->tx_ring[i]); + for (i = 0; i < adapter->num_xdp_queues; i++) + if (adapter->xdp_ring[i]->desc) + ixgbevf_free_tx_resources(adapter->xdp_ring[i]); +} + +/** + * ixgbevf_setup_tx_resources - allocate Tx resources (Descriptors) + * @tx_ring: Tx descriptor ring (for a specific queue) to setup + * + * Return 0 on success, negative on failure + **/ +int ixgbevf_setup_tx_resources(struct ixgbevf_ring *tx_ring) +{ + struct ixgbevf_adapter *adapter = netdev_priv(tx_ring->netdev); + int size; + + size = sizeof(struct ixgbevf_tx_buffer) * tx_ring->count; + tx_ring->tx_buffer_info = vmalloc(size); + if (!tx_ring->tx_buffer_info) + goto err; + + u64_stats_init(&tx_ring->syncp); + + /* round up to nearest 4K */ + tx_ring->size = tx_ring->count * sizeof(union ixgbe_adv_tx_desc); + tx_ring->size = ALIGN(tx_ring->size, 4096); + + tx_ring->desc = dma_alloc_coherent(tx_ring->dev, tx_ring->size, + &tx_ring->dma, GFP_KERNEL); + if (!tx_ring->desc) + goto err; + + return 0; + +err: + vfree(tx_ring->tx_buffer_info); + tx_ring->tx_buffer_info = NULL; + hw_dbg(&adapter->hw, "Unable to allocate memory for the transmit descriptor ring\n"); + return -ENOMEM; +} + +/** + * ixgbevf_setup_all_tx_resources - allocate all queues Tx resources + * @adapter: board private structure + * + * If this function returns with an error, then it's possible one or + * more of the rings is populated (while the rest are not). It is the + * callers duty to clean those orphaned rings. + * + * Return 0 on success, negative on failure + **/ +static int ixgbevf_setup_all_tx_resources(struct ixgbevf_adapter *adapter) +{ + int i, j = 0, err = 0; + + for (i = 0; i < adapter->num_tx_queues; i++) { + err = ixgbevf_setup_tx_resources(adapter->tx_ring[i]); + if (!err) + continue; + hw_dbg(&adapter->hw, "Allocation for Tx Queue %u failed\n", i); + goto err_setup_tx; + } + + for (j = 0; j < adapter->num_xdp_queues; j++) { + err = ixgbevf_setup_tx_resources(adapter->xdp_ring[j]); + if (!err) + continue; + hw_dbg(&adapter->hw, "Allocation for XDP Queue %u failed\n", j); + goto err_setup_tx; + } + + return 0; +err_setup_tx: + /* rewind the index freeing the rings as we go */ + while (j--) + ixgbevf_free_tx_resources(adapter->xdp_ring[j]); + while (i--) + ixgbevf_free_tx_resources(adapter->tx_ring[i]); + + return err; +} + +/** + * ixgbevf_setup_rx_resources - allocate Rx resources (Descriptors) + * @adapter: board private structure + * @rx_ring: Rx descriptor ring (for a specific queue) to setup + * + * Returns 0 on success, negative on failure + **/ +int ixgbevf_setup_rx_resources(struct ixgbevf_adapter *adapter, + struct ixgbevf_ring *rx_ring) +{ + int size; + + size = sizeof(struct ixgbevf_rx_buffer) * rx_ring->count; + rx_ring->rx_buffer_info = vmalloc(size); + if (!rx_ring->rx_buffer_info) + goto err; + + u64_stats_init(&rx_ring->syncp); + + /* Round up to nearest 4K */ + rx_ring->size = rx_ring->count * sizeof(union ixgbe_adv_rx_desc); + rx_ring->size = ALIGN(rx_ring->size, 4096); + + rx_ring->desc = dma_alloc_coherent(rx_ring->dev, rx_ring->size, + &rx_ring->dma, GFP_KERNEL); + + if (!rx_ring->desc) + goto err; + + /* XDP RX-queue info */ + if (xdp_rxq_info_reg(&rx_ring->xdp_rxq, adapter->netdev, + rx_ring->queue_index) < 0) + goto err; + + rx_ring->xdp_prog = adapter->xdp_prog; + + return 0; +err: + vfree(rx_ring->rx_buffer_info); + rx_ring->rx_buffer_info = NULL; + dev_err(rx_ring->dev, "Unable to allocate memory for the Rx descriptor ring\n"); + return -ENOMEM; +} + +/** + * ixgbevf_setup_all_rx_resources - allocate all queues Rx resources + * @adapter: board private structure + * + * If this function returns with an error, then it's possible one or + * more of the rings is populated (while the rest are not). It is the + * callers duty to clean those orphaned rings. + * + * Return 0 on success, negative on failure + **/ +static int ixgbevf_setup_all_rx_resources(struct ixgbevf_adapter *adapter) +{ + int i, err = 0; + + for (i = 0; i < adapter->num_rx_queues; i++) { + err = ixgbevf_setup_rx_resources(adapter, adapter->rx_ring[i]); + if (!err) + continue; + hw_dbg(&adapter->hw, "Allocation for Rx Queue %u failed\n", i); + goto err_setup_rx; + } + + return 0; +err_setup_rx: + /* rewind the index freeing the rings as we go */ + while (i--) + ixgbevf_free_rx_resources(adapter->rx_ring[i]); + return err; +} + +/** + * ixgbevf_free_rx_resources - Free Rx Resources + * @rx_ring: ring to clean the resources from + * + * Free all receive software resources + **/ +void ixgbevf_free_rx_resources(struct ixgbevf_ring *rx_ring) +{ + ixgbevf_clean_rx_ring(rx_ring); + + rx_ring->xdp_prog = NULL; + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); + vfree(rx_ring->rx_buffer_info); + rx_ring->rx_buffer_info = NULL; + + dma_free_coherent(rx_ring->dev, rx_ring->size, rx_ring->desc, + rx_ring->dma); + + rx_ring->desc = NULL; +} + +/** + * ixgbevf_free_all_rx_resources - Free Rx Resources for All Queues + * @adapter: board private structure + * + * Free all receive software resources + **/ +static void ixgbevf_free_all_rx_resources(struct ixgbevf_adapter *adapter) +{ + int i; + + for (i = 0; i < adapter->num_rx_queues; i++) + if (adapter->rx_ring[i]->desc) + ixgbevf_free_rx_resources(adapter->rx_ring[i]); +} + +/** + * ixgbevf_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. + **/ +int ixgbevf_open(struct net_device *netdev) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + int err; + + /* A previous failure to open the device because of a lack of + * available MSIX vector resources may have reset the number + * of msix vectors variable to zero. The only way to recover + * is to unload/reload the driver and hope that the system has + * been able to recover some MSIX vector resources. + */ + if (!adapter->num_msix_vectors) + return -ENOMEM; + + if (hw->adapter_stopped) { + ixgbevf_reset(adapter); + /* if adapter is still stopped then PF isn't up and + * the VF can't start. + */ + if (hw->adapter_stopped) { + err = IXGBE_ERR_MBX; + pr_err("Unable to start - perhaps the PF Driver isn't up yet\n"); + goto err_setup_reset; + } + } + + /* disallow open during test */ + if (test_bit(__IXGBEVF_TESTING, &adapter->state)) + return -EBUSY; + + netif_carrier_off(netdev); + + /* allocate transmit descriptors */ + err = ixgbevf_setup_all_tx_resources(adapter); + if (err) + goto err_setup_tx; + + /* allocate receive descriptors */ + err = ixgbevf_setup_all_rx_resources(adapter); + if (err) + goto err_setup_rx; + + ixgbevf_configure(adapter); + + err = ixgbevf_request_irq(adapter); + if (err) + goto err_req_irq; + + /* Notify the stack of the actual queue counts. */ + err = netif_set_real_num_tx_queues(netdev, adapter->num_tx_queues); + if (err) + goto err_set_queues; + + err = netif_set_real_num_rx_queues(netdev, adapter->num_rx_queues); + if (err) + goto err_set_queues; + + ixgbevf_up_complete(adapter); + + return 0; + +err_set_queues: + ixgbevf_free_irq(adapter); +err_req_irq: + ixgbevf_free_all_rx_resources(adapter); +err_setup_rx: + ixgbevf_free_all_tx_resources(adapter); +err_setup_tx: + ixgbevf_reset(adapter); +err_setup_reset: + + return err; +} + +/** + * ixgbevf_close_suspend - actions necessary to both suspend and close flows + * @adapter: the private adapter struct + * + * This function should contain the necessary work common to both suspending + * and closing of the device. + */ +static void ixgbevf_close_suspend(struct ixgbevf_adapter *adapter) +{ + ixgbevf_down(adapter); + ixgbevf_free_irq(adapter); + ixgbevf_free_all_tx_resources(adapter); + ixgbevf_free_all_rx_resources(adapter); +} + +/** + * ixgbevf_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. + **/ +int ixgbevf_close(struct net_device *netdev) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + + if (netif_device_present(netdev)) + ixgbevf_close_suspend(adapter); + + return 0; +} + +static void ixgbevf_queue_reset_subtask(struct ixgbevf_adapter *adapter) +{ + struct net_device *dev = adapter->netdev; + + if (!test_and_clear_bit(__IXGBEVF_QUEUE_RESET_REQUESTED, + &adapter->state)) + return; + + /* if interface is down do nothing */ + if (test_bit(__IXGBEVF_DOWN, &adapter->state) || + test_bit(__IXGBEVF_RESETTING, &adapter->state)) + return; + + /* Hardware has to reinitialize queues and interrupts to + * match packet buffer alignment. Unfortunately, the + * hardware is not flexible enough to do this dynamically. + */ + rtnl_lock(); + + if (netif_running(dev)) + ixgbevf_close(dev); + + ixgbevf_clear_interrupt_scheme(adapter); + ixgbevf_init_interrupt_scheme(adapter); + + if (netif_running(dev)) + ixgbevf_open(dev); + + rtnl_unlock(); +} + +static void ixgbevf_tx_ctxtdesc(struct ixgbevf_ring *tx_ring, + u32 vlan_macip_lens, u32 fceof_saidx, + u32 type_tucmd, u32 mss_l4len_idx) +{ + struct ixgbe_adv_tx_context_desc *context_desc; + u16 i = tx_ring->next_to_use; + + context_desc = IXGBEVF_TX_CTXTDESC(tx_ring, i); + + i++; + tx_ring->next_to_use = (i < tx_ring->count) ? i : 0; + + /* set bits to identify this as an advanced context descriptor */ + type_tucmd |= IXGBE_TXD_CMD_DEXT | IXGBE_ADVTXD_DTYP_CTXT; + + context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens); + context_desc->fceof_saidx = cpu_to_le32(fceof_saidx); + context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd); + context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx); +} + +static int ixgbevf_tso(struct ixgbevf_ring *tx_ring, + struct ixgbevf_tx_buffer *first, + u8 *hdr_len, + struct ixgbevf_ipsec_tx_data *itd) +{ + u32 vlan_macip_lens, type_tucmd, mss_l4len_idx; + struct sk_buff *skb = first->skb; + union { + struct iphdr *v4; + struct ipv6hdr *v6; + unsigned char *hdr; + } ip; + union { + struct tcphdr *tcp; + unsigned char *hdr; + } l4; + u32 paylen, l4_offset; + u32 fceof_saidx = 0; + int err; + + if (skb->ip_summed != CHECKSUM_PARTIAL) + return 0; + + if (!skb_is_gso(skb)) + return 0; + + err = skb_cow_head(skb, 0); + if (err < 0) + return err; + + if (eth_p_mpls(first->protocol)) + ip.hdr = skb_inner_network_header(skb); + else + ip.hdr = skb_network_header(skb); + l4.hdr = skb_checksum_start(skb); + + /* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */ + type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_TCP; + + /* initialize outer IP header fields */ + if (ip.v4->version == 4) { + unsigned char *csum_start = skb_checksum_start(skb); + unsigned char *trans_start = ip.hdr + (ip.v4->ihl * 4); + int len = csum_start - trans_start; + + /* IP header will have to cancel out any data that + * is not a part of the outer IP header, so set to + * a reverse csum if needed, else init check to 0. + */ + ip.v4->check = (skb_shinfo(skb)->gso_type & SKB_GSO_PARTIAL) ? + csum_fold(csum_partial(trans_start, + len, 0)) : 0; + type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4; + + ip.v4->tot_len = 0; + first->tx_flags |= IXGBE_TX_FLAGS_TSO | + IXGBE_TX_FLAGS_CSUM | + IXGBE_TX_FLAGS_IPV4; + } else { + ip.v6->payload_len = 0; + first->tx_flags |= IXGBE_TX_FLAGS_TSO | + IXGBE_TX_FLAGS_CSUM; + } + + /* determine offset of inner transport header */ + l4_offset = l4.hdr - skb->data; + + /* compute length of segmentation header */ + *hdr_len = (l4.tcp->doff * 4) + l4_offset; + + /* remove payload length from inner checksum */ + paylen = skb->len - l4_offset; + csum_replace_by_diff(&l4.tcp->check, htonl(paylen)); + + /* update gso size and bytecount with header size */ + first->gso_segs = skb_shinfo(skb)->gso_segs; + first->bytecount += (first->gso_segs - 1) * *hdr_len; + + /* mss_l4len_id: use 1 as index for TSO */ + mss_l4len_idx = (*hdr_len - l4_offset) << IXGBE_ADVTXD_L4LEN_SHIFT; + mss_l4len_idx |= skb_shinfo(skb)->gso_size << IXGBE_ADVTXD_MSS_SHIFT; + mss_l4len_idx |= (1u << IXGBE_ADVTXD_IDX_SHIFT); + + fceof_saidx |= itd->pfsa; + type_tucmd |= itd->flags | itd->trailer_len; + + /* vlan_macip_lens: HEADLEN, MACLEN, VLAN tag */ + vlan_macip_lens = l4.hdr - ip.hdr; + vlan_macip_lens |= (ip.hdr - skb->data) << IXGBE_ADVTXD_MACLEN_SHIFT; + vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK; + + ixgbevf_tx_ctxtdesc(tx_ring, vlan_macip_lens, fceof_saidx, type_tucmd, + mss_l4len_idx); + + return 1; +} + +static inline bool ixgbevf_ipv6_csum_is_sctp(struct sk_buff *skb) +{ + unsigned int offset = 0; + + ipv6_find_hdr(skb, &offset, IPPROTO_SCTP, NULL, NULL); + + return offset == skb_checksum_start_offset(skb); +} + +static void ixgbevf_tx_csum(struct ixgbevf_ring *tx_ring, + struct ixgbevf_tx_buffer *first, + struct ixgbevf_ipsec_tx_data *itd) +{ + struct sk_buff *skb = first->skb; + u32 vlan_macip_lens = 0; + u32 fceof_saidx = 0; + u32 type_tucmd = 0; + + if (skb->ip_summed != CHECKSUM_PARTIAL) + goto no_csum; + + switch (skb->csum_offset) { + case offsetof(struct tcphdr, check): + type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_TCP; + fallthrough; + case offsetof(struct udphdr, check): + break; + case offsetof(struct sctphdr, checksum): + /* validate that this is actually an SCTP request */ + if (((first->protocol == htons(ETH_P_IP)) && + (ip_hdr(skb)->protocol == IPPROTO_SCTP)) || + ((first->protocol == htons(ETH_P_IPV6)) && + ixgbevf_ipv6_csum_is_sctp(skb))) { + type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_SCTP; + break; + } + fallthrough; + default: + skb_checksum_help(skb); + goto no_csum; + } + + if (first->protocol == htons(ETH_P_IP)) + type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4; + + /* update TX checksum flag */ + first->tx_flags |= IXGBE_TX_FLAGS_CSUM; + vlan_macip_lens = skb_checksum_start_offset(skb) - + skb_network_offset(skb); +no_csum: + /* vlan_macip_lens: MACLEN, VLAN tag */ + vlan_macip_lens |= skb_network_offset(skb) << IXGBE_ADVTXD_MACLEN_SHIFT; + vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK; + + fceof_saidx |= itd->pfsa; + type_tucmd |= itd->flags | itd->trailer_len; + + ixgbevf_tx_ctxtdesc(tx_ring, vlan_macip_lens, + fceof_saidx, type_tucmd, 0); +} + +static __le32 ixgbevf_tx_cmd_type(u32 tx_flags) +{ + /* set type for advanced descriptor with frame checksum insertion */ + __le32 cmd_type = cpu_to_le32(IXGBE_ADVTXD_DTYP_DATA | + IXGBE_ADVTXD_DCMD_IFCS | + IXGBE_ADVTXD_DCMD_DEXT); + + /* set HW VLAN bit if VLAN is present */ + if (tx_flags & IXGBE_TX_FLAGS_VLAN) + cmd_type |= cpu_to_le32(IXGBE_ADVTXD_DCMD_VLE); + + /* set segmentation enable bits for TSO/FSO */ + if (tx_flags & IXGBE_TX_FLAGS_TSO) + cmd_type |= cpu_to_le32(IXGBE_ADVTXD_DCMD_TSE); + + return cmd_type; +} + +static void ixgbevf_tx_olinfo_status(union ixgbe_adv_tx_desc *tx_desc, + u32 tx_flags, unsigned int paylen) +{ + __le32 olinfo_status = cpu_to_le32(paylen << IXGBE_ADVTXD_PAYLEN_SHIFT); + + /* enable L4 checksum for TSO and TX checksum offload */ + if (tx_flags & IXGBE_TX_FLAGS_CSUM) + olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_POPTS_TXSM); + + /* enble IPv4 checksum for TSO */ + if (tx_flags & IXGBE_TX_FLAGS_IPV4) + olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_POPTS_IXSM); + + /* enable IPsec */ + if (tx_flags & IXGBE_TX_FLAGS_IPSEC) + olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_POPTS_IPSEC); + + /* use index 1 context for TSO/FSO/FCOE/IPSEC */ + if (tx_flags & (IXGBE_TX_FLAGS_TSO | IXGBE_TX_FLAGS_IPSEC)) + olinfo_status |= cpu_to_le32(1u << IXGBE_ADVTXD_IDX_SHIFT); + + /* Check Context must be set if Tx switch is enabled, which it + * always is for case where virtual functions are running + */ + olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_CC); + + tx_desc->read.olinfo_status = olinfo_status; +} + +static void ixgbevf_tx_map(struct ixgbevf_ring *tx_ring, + struct ixgbevf_tx_buffer *first, + const u8 hdr_len) +{ + struct sk_buff *skb = first->skb; + struct ixgbevf_tx_buffer *tx_buffer; + union ixgbe_adv_tx_desc *tx_desc; + skb_frag_t *frag; + dma_addr_t dma; + unsigned int data_len, size; + u32 tx_flags = first->tx_flags; + __le32 cmd_type = ixgbevf_tx_cmd_type(tx_flags); + u16 i = tx_ring->next_to_use; + + tx_desc = IXGBEVF_TX_DESC(tx_ring, i); + + ixgbevf_tx_olinfo_status(tx_desc, tx_flags, skb->len - hdr_len); + + size = skb_headlen(skb); + data_len = skb->data_len; + + dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE); + + tx_buffer = first; + + for (frag = &skb_shinfo(skb)->frags[0];; frag++) { + if (dma_mapping_error(tx_ring->dev, dma)) + goto dma_error; + + /* record length, and DMA address */ + dma_unmap_len_set(tx_buffer, len, size); + dma_unmap_addr_set(tx_buffer, dma, dma); + + tx_desc->read.buffer_addr = cpu_to_le64(dma); + + while (unlikely(size > IXGBE_MAX_DATA_PER_TXD)) { + tx_desc->read.cmd_type_len = + cmd_type | cpu_to_le32(IXGBE_MAX_DATA_PER_TXD); + + i++; + tx_desc++; + if (i == tx_ring->count) { + tx_desc = IXGBEVF_TX_DESC(tx_ring, 0); + i = 0; + } + tx_desc->read.olinfo_status = 0; + + dma += IXGBE_MAX_DATA_PER_TXD; + size -= IXGBE_MAX_DATA_PER_TXD; + + tx_desc->read.buffer_addr = cpu_to_le64(dma); + } + + if (likely(!data_len)) + break; + + tx_desc->read.cmd_type_len = cmd_type | cpu_to_le32(size); + + i++; + tx_desc++; + if (i == tx_ring->count) { + tx_desc = IXGBEVF_TX_DESC(tx_ring, 0); + i = 0; + } + tx_desc->read.olinfo_status = 0; + + size = skb_frag_size(frag); + data_len -= size; + + dma = skb_frag_dma_map(tx_ring->dev, frag, 0, size, + DMA_TO_DEVICE); + + tx_buffer = &tx_ring->tx_buffer_info[i]; + } + + /* write last descriptor with RS and EOP bits */ + cmd_type |= cpu_to_le32(size) | cpu_to_le32(IXGBE_TXD_CMD); + tx_desc->read.cmd_type_len = cmd_type; + + /* set the timestamp */ + first->time_stamp = jiffies; + + skb_tx_timestamp(skb); + + /* 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). + * + * We also need this memory barrier (wmb) to make certain all of the + * status bits have been updated before next_to_watch is written. + */ + wmb(); + + /* set next_to_watch value indicating a packet is present */ + first->next_to_watch = tx_desc; + + i++; + if (i == tx_ring->count) + i = 0; + + tx_ring->next_to_use = i; + + /* notify HW of packet */ + ixgbevf_write_tail(tx_ring, i); + + return; +dma_error: + dev_err(tx_ring->dev, "TX DMA map failed\n"); + tx_buffer = &tx_ring->tx_buffer_info[i]; + + /* clear dma mappings for failed tx_buffer_info map */ + while (tx_buffer != first) { + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + + if (i-- == 0) + i += tx_ring->count; + tx_buffer = &tx_ring->tx_buffer_info[i]; + } + + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + + dev_kfree_skb_any(tx_buffer->skb); + tx_buffer->skb = NULL; + + tx_ring->next_to_use = i; +} + +static int __ixgbevf_maybe_stop_tx(struct ixgbevf_ring *tx_ring, int 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(ixgbevf_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; +} + +static int ixgbevf_maybe_stop_tx(struct ixgbevf_ring *tx_ring, int size) +{ + if (likely(ixgbevf_desc_unused(tx_ring) >= size)) + return 0; + return __ixgbevf_maybe_stop_tx(tx_ring, size); +} + +static int ixgbevf_xmit_frame_ring(struct sk_buff *skb, + struct ixgbevf_ring *tx_ring) +{ + struct ixgbevf_tx_buffer *first; + int tso; + u32 tx_flags = 0; + u16 count = TXD_USE_COUNT(skb_headlen(skb)); + struct ixgbevf_ipsec_tx_data ipsec_tx = { 0 }; +#if PAGE_SIZE > IXGBE_MAX_DATA_PER_TXD + unsigned short f; +#endif + u8 hdr_len = 0; + u8 *dst_mac = skb_header_pointer(skb, 0, 0, NULL); + + if (!dst_mac || is_link_local_ether_addr(dst_mac)) { + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + + /* need: 1 descriptor per page * PAGE_SIZE/IXGBE_MAX_DATA_PER_TXD, + * + 1 desc for skb_headlen/IXGBE_MAX_DATA_PER_TXD, + * + 2 desc gap to keep tail from touching head, + * + 1 desc for context descriptor, + * otherwise try next time + */ +#if PAGE_SIZE > IXGBE_MAX_DATA_PER_TXD + for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; + + count += TXD_USE_COUNT(skb_frag_size(frag)); + } +#else + count += skb_shinfo(skb)->nr_frags; +#endif + if (ixgbevf_maybe_stop_tx(tx_ring, count + 3)) { + tx_ring->tx_stats.tx_busy++; + return NETDEV_TX_BUSY; + } + + /* record the location of the first descriptor for this packet */ + first = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + first->skb = skb; + first->bytecount = skb->len; + first->gso_segs = 1; + + if (skb_vlan_tag_present(skb)) { + tx_flags |= skb_vlan_tag_get(skb); + tx_flags <<= IXGBE_TX_FLAGS_VLAN_SHIFT; + tx_flags |= IXGBE_TX_FLAGS_VLAN; + } + + /* record initial flags and protocol */ + first->tx_flags = tx_flags; + first->protocol = vlan_get_protocol(skb); + +#ifdef CONFIG_IXGBEVF_IPSEC + if (xfrm_offload(skb) && !ixgbevf_ipsec_tx(tx_ring, first, &ipsec_tx)) + goto out_drop; +#endif + tso = ixgbevf_tso(tx_ring, first, &hdr_len, &ipsec_tx); + if (tso < 0) + goto out_drop; + else if (!tso) + ixgbevf_tx_csum(tx_ring, first, &ipsec_tx); + + ixgbevf_tx_map(tx_ring, first, hdr_len); + + ixgbevf_maybe_stop_tx(tx_ring, DESC_NEEDED); + + return NETDEV_TX_OK; + +out_drop: + dev_kfree_skb_any(first->skb); + first->skb = NULL; + + return NETDEV_TX_OK; +} + +static netdev_tx_t ixgbevf_xmit_frame(struct sk_buff *skb, struct net_device *netdev) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + struct ixgbevf_ring *tx_ring; + + if (skb->len <= 0) { + dev_kfree_skb_any(skb); + return NETDEV_TX_OK; + } + + /* The minimum packet size for olinfo paylen is 17 so pad the skb + * in order to meet this minimum size requirement. + */ + if (skb->len < 17) { + if (skb_padto(skb, 17)) + return NETDEV_TX_OK; + skb->len = 17; + } + + tx_ring = adapter->tx_ring[skb->queue_mapping]; + return ixgbevf_xmit_frame_ring(skb, tx_ring); +} + +/** + * ixgbevf_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 ixgbevf_set_mac(struct net_device *netdev, void *p) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + struct sockaddr *addr = p; + int err; + + if (!is_valid_ether_addr(addr->sa_data)) + return -EADDRNOTAVAIL; + + spin_lock_bh(&adapter->mbx_lock); + + err = hw->mac.ops.set_rar(hw, 0, addr->sa_data, 0); + + spin_unlock_bh(&adapter->mbx_lock); + + if (err) + return -EPERM; + + ether_addr_copy(hw->mac.addr, addr->sa_data); + ether_addr_copy(hw->mac.perm_addr, addr->sa_data); + ether_addr_copy(netdev->dev_addr, addr->sa_data); + + return 0; +} + +/** + * ixgbevf_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 ixgbevf_change_mtu(struct net_device *netdev, int new_mtu) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN; + int ret; + + /* prevent MTU being changed to a size unsupported by XDP */ + if (adapter->xdp_prog) { + dev_warn(&adapter->pdev->dev, "MTU cannot be changed while XDP program is loaded\n"); + return -EPERM; + } + + spin_lock_bh(&adapter->mbx_lock); + /* notify the PF of our intent to use this size of frame */ + ret = hw->mac.ops.set_rlpml(hw, max_frame); + spin_unlock_bh(&adapter->mbx_lock); + if (ret) + return -EINVAL; + + hw_dbg(hw, "changing MTU from %d to %d\n", + netdev->mtu, new_mtu); + + /* must set new MTU before calling down or up */ + netdev->mtu = new_mtu; + + if (netif_running(netdev)) + ixgbevf_reinit_locked(adapter); + + return 0; +} + +static int __maybe_unused ixgbevf_suspend(struct device *dev_d) +{ + struct net_device *netdev = dev_get_drvdata(dev_d); + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + + rtnl_lock(); + netif_device_detach(netdev); + + if (netif_running(netdev)) + ixgbevf_close_suspend(adapter); + + ixgbevf_clear_interrupt_scheme(adapter); + rtnl_unlock(); + + return 0; +} + +static int __maybe_unused ixgbevf_resume(struct device *dev_d) +{ + struct pci_dev *pdev = to_pci_dev(dev_d); + struct net_device *netdev = pci_get_drvdata(pdev); + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + u32 err; + + adapter->hw.hw_addr = adapter->io_addr; + smp_mb__before_atomic(); + clear_bit(__IXGBEVF_DISABLED, &adapter->state); + pci_set_master(pdev); + + ixgbevf_reset(adapter); + + rtnl_lock(); + err = ixgbevf_init_interrupt_scheme(adapter); + if (!err && netif_running(netdev)) + err = ixgbevf_open(netdev); + rtnl_unlock(); + if (err) + return err; + + netif_device_attach(netdev); + + return err; +} + +static void ixgbevf_shutdown(struct pci_dev *pdev) +{ + ixgbevf_suspend(&pdev->dev); +} + +static void ixgbevf_get_tx_ring_stats(struct rtnl_link_stats64 *stats, + const struct ixgbevf_ring *ring) +{ + u64 bytes, packets; + unsigned int start; + + if (ring) { + do { + start = u64_stats_fetch_begin_irq(&ring->syncp); + bytes = ring->stats.bytes; + packets = ring->stats.packets; + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + stats->tx_bytes += bytes; + stats->tx_packets += packets; + } +} + +static void ixgbevf_get_stats(struct net_device *netdev, + struct rtnl_link_stats64 *stats) +{ + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + unsigned int start; + u64 bytes, packets; + const struct ixgbevf_ring *ring; + int i; + + ixgbevf_update_stats(adapter); + + stats->multicast = adapter->stats.vfmprc - adapter->stats.base_vfmprc; + + rcu_read_lock(); + for (i = 0; i < adapter->num_rx_queues; i++) { + ring = adapter->rx_ring[i]; + do { + start = u64_stats_fetch_begin_irq(&ring->syncp); + bytes = ring->stats.bytes; + packets = ring->stats.packets; + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); + stats->rx_bytes += bytes; + stats->rx_packets += packets; + } + + for (i = 0; i < adapter->num_tx_queues; i++) { + ring = adapter->tx_ring[i]; + ixgbevf_get_tx_ring_stats(stats, ring); + } + + for (i = 0; i < adapter->num_xdp_queues; i++) { + ring = adapter->xdp_ring[i]; + ixgbevf_get_tx_ring_stats(stats, ring); + } + rcu_read_unlock(); +} + +#define IXGBEVF_MAX_MAC_HDR_LEN 127 +#define IXGBEVF_MAX_NETWORK_HDR_LEN 511 + +static netdev_features_t +ixgbevf_features_check(struct sk_buff *skb, struct net_device *dev, + netdev_features_t features) +{ + unsigned int network_hdr_len, mac_hdr_len; + + /* Make certain the headers can be described by a context descriptor */ + mac_hdr_len = skb_network_header(skb) - skb->data; + if (unlikely(mac_hdr_len > IXGBEVF_MAX_MAC_HDR_LEN)) + return features & ~(NETIF_F_HW_CSUM | + NETIF_F_SCTP_CRC | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_TSO | + NETIF_F_TSO6); + + network_hdr_len = skb_checksum_start(skb) - skb_network_header(skb); + if (unlikely(network_hdr_len > IXGBEVF_MAX_NETWORK_HDR_LEN)) + return features & ~(NETIF_F_HW_CSUM | + NETIF_F_SCTP_CRC | + NETIF_F_TSO | + NETIF_F_TSO6); + + /* We can only support IPV4 TSO in tunnels if we can mangle the + * inner IP ID field, so strip TSO if MANGLEID is not supported. + */ + if (skb->encapsulation && !(features & NETIF_F_TSO_MANGLEID)) + features &= ~NETIF_F_TSO; + + return features; +} + +static int ixgbevf_xdp_setup(struct net_device *dev, struct bpf_prog *prog) +{ + int i, frame_size = dev->mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN; + struct ixgbevf_adapter *adapter = netdev_priv(dev); + struct bpf_prog *old_prog; + + /* verify ixgbevf ring attributes are sufficient for XDP */ + for (i = 0; i < adapter->num_rx_queues; i++) { + struct ixgbevf_ring *ring = adapter->rx_ring[i]; + + if (frame_size > ixgbevf_rx_bufsz(ring)) + return -EINVAL; + } + + old_prog = xchg(&adapter->xdp_prog, prog); + + /* If transitioning XDP modes reconfigure rings */ + if (!!prog != !!old_prog) { + /* Hardware has to reinitialize queues and interrupts to + * match packet buffer alignment. Unfortunately, the + * hardware is not flexible enough to do this dynamically. + */ + if (netif_running(dev)) + ixgbevf_close(dev); + + ixgbevf_clear_interrupt_scheme(adapter); + ixgbevf_init_interrupt_scheme(adapter); + + if (netif_running(dev)) + ixgbevf_open(dev); + } else { + for (i = 0; i < adapter->num_rx_queues; i++) + xchg(&adapter->rx_ring[i]->xdp_prog, adapter->xdp_prog); + } + + if (old_prog) + bpf_prog_put(old_prog); + + return 0; +} + +static int ixgbevf_xdp(struct net_device *dev, struct netdev_bpf *xdp) +{ + switch (xdp->command) { + case XDP_SETUP_PROG: + return ixgbevf_xdp_setup(dev, xdp->prog); + default: + return -EINVAL; + } +} + +static const struct net_device_ops ixgbevf_netdev_ops = { + .ndo_open = ixgbevf_open, + .ndo_stop = ixgbevf_close, + .ndo_start_xmit = ixgbevf_xmit_frame, + .ndo_set_rx_mode = ixgbevf_set_rx_mode, + .ndo_get_stats64 = ixgbevf_get_stats, + .ndo_validate_addr = eth_validate_addr, + .ndo_set_mac_address = ixgbevf_set_mac, + .ndo_change_mtu = ixgbevf_change_mtu, + .ndo_tx_timeout = ixgbevf_tx_timeout, + .ndo_vlan_rx_add_vid = ixgbevf_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = ixgbevf_vlan_rx_kill_vid, + .ndo_features_check = ixgbevf_features_check, + .ndo_bpf = ixgbevf_xdp, +}; + +static void ixgbevf_assign_netdev_ops(struct net_device *dev) +{ + dev->netdev_ops = &ixgbevf_netdev_ops; + ixgbevf_set_ethtool_ops(dev); + dev->watchdog_timeo = 5 * HZ; +} + +/** + * ixgbevf_probe - Device Initialization Routine + * @pdev: PCI device information struct + * @ent: entry in ixgbevf_pci_tbl + * + * Returns 0 on success, negative on failure + * + * ixgbevf_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 ixgbevf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) +{ + struct net_device *netdev; + struct ixgbevf_adapter *adapter = NULL; + struct ixgbe_hw *hw = NULL; + const struct ixgbevf_info *ii = ixgbevf_info_tbl[ent->driver_data]; + int err, pci_using_dac; + bool disable_dev = false; + + err = pci_enable_device(pdev); + if (err) + return err; + + if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) { + pci_using_dac = 1; + } else { + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); + if (err) { + dev_err(&pdev->dev, "No usable DMA configuration, aborting\n"); + goto err_dma; + } + pci_using_dac = 0; + } + + err = pci_request_regions(pdev, ixgbevf_driver_name); + if (err) { + dev_err(&pdev->dev, "pci_request_regions failed 0x%x\n", err); + goto err_pci_reg; + } + + pci_set_master(pdev); + + netdev = alloc_etherdev_mq(sizeof(struct ixgbevf_adapter), + MAX_TX_QUEUES); + if (!netdev) { + err = -ENOMEM; + goto err_alloc_etherdev; + } + + SET_NETDEV_DEV(netdev, &pdev->dev); + + adapter = netdev_priv(netdev); + + adapter->netdev = netdev; + adapter->pdev = pdev; + hw = &adapter->hw; + hw->back = adapter; + adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE); + + /* call save state here in standalone driver because it relies on + * adapter struct to exist, and needs to call netdev_priv + */ + pci_save_state(pdev); + + hw->hw_addr = ioremap(pci_resource_start(pdev, 0), + pci_resource_len(pdev, 0)); + adapter->io_addr = hw->hw_addr; + if (!hw->hw_addr) { + err = -EIO; + goto err_ioremap; + } + + ixgbevf_assign_netdev_ops(netdev); + + /* Setup HW API */ + memcpy(&hw->mac.ops, ii->mac_ops, sizeof(hw->mac.ops)); + hw->mac.type = ii->mac; + + memcpy(&hw->mbx.ops, &ixgbevf_mbx_ops, + sizeof(struct ixgbe_mbx_operations)); + + /* setup the private structure */ + err = ixgbevf_sw_init(adapter); + if (err) + goto err_sw_init; + + /* The HW MAC address was set and/or determined in sw_init */ + if (!is_valid_ether_addr(netdev->dev_addr)) { + pr_err("invalid MAC address\n"); + err = -EIO; + goto err_sw_init; + } + + netdev->hw_features = NETIF_F_SG | + NETIF_F_TSO | + NETIF_F_TSO6 | + NETIF_F_RXCSUM | + NETIF_F_HW_CSUM | + NETIF_F_SCTP_CRC; + +#define IXGBEVF_GSO_PARTIAL_FEATURES (NETIF_F_GSO_GRE | \ + NETIF_F_GSO_GRE_CSUM | \ + NETIF_F_GSO_IPXIP4 | \ + NETIF_F_GSO_IPXIP6 | \ + NETIF_F_GSO_UDP_TUNNEL | \ + NETIF_F_GSO_UDP_TUNNEL_CSUM) + + netdev->gso_partial_features = IXGBEVF_GSO_PARTIAL_FEATURES; + netdev->hw_features |= NETIF_F_GSO_PARTIAL | + IXGBEVF_GSO_PARTIAL_FEATURES; + + netdev->features = netdev->hw_features; + + if (pci_using_dac) + netdev->features |= NETIF_F_HIGHDMA; + + netdev->vlan_features |= netdev->features | NETIF_F_TSO_MANGLEID; + netdev->mpls_features |= NETIF_F_SG | + NETIF_F_TSO | + NETIF_F_TSO6 | + NETIF_F_HW_CSUM; + netdev->mpls_features |= IXGBEVF_GSO_PARTIAL_FEATURES; + netdev->hw_enc_features |= netdev->vlan_features; + + /* set this bit last since it cannot be part of vlan_features */ + netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_TX; + + netdev->priv_flags |= IFF_UNICAST_FLT; + + /* MTU range: 68 - 1504 or 9710 */ + netdev->min_mtu = ETH_MIN_MTU; + switch (adapter->hw.api_version) { + case ixgbe_mbox_api_11: + case ixgbe_mbox_api_12: + case ixgbe_mbox_api_13: + case ixgbe_mbox_api_14: + netdev->max_mtu = IXGBE_MAX_JUMBO_FRAME_SIZE - + (ETH_HLEN + ETH_FCS_LEN); + break; + default: + if (adapter->hw.mac.type != ixgbe_mac_82599_vf) + netdev->max_mtu = IXGBE_MAX_JUMBO_FRAME_SIZE - + (ETH_HLEN + ETH_FCS_LEN); + else + netdev->max_mtu = ETH_DATA_LEN + ETH_FCS_LEN; + break; + } + + if (IXGBE_REMOVED(hw->hw_addr)) { + err = -EIO; + goto err_sw_init; + } + + timer_setup(&adapter->service_timer, ixgbevf_service_timer, 0); + + INIT_WORK(&adapter->service_task, ixgbevf_service_task); + set_bit(__IXGBEVF_SERVICE_INITED, &adapter->state); + clear_bit(__IXGBEVF_SERVICE_SCHED, &adapter->state); + + err = ixgbevf_init_interrupt_scheme(adapter); + if (err) + goto err_sw_init; + + strcpy(netdev->name, "eth%d"); + + err = register_netdev(netdev); + if (err) + goto err_register; + + pci_set_drvdata(pdev, netdev); + netif_carrier_off(netdev); + ixgbevf_init_ipsec_offload(adapter); + + ixgbevf_init_last_counter_stats(adapter); + + /* print the VF info */ + dev_info(&pdev->dev, "%pM\n", netdev->dev_addr); + dev_info(&pdev->dev, "MAC: %d\n", hw->mac.type); + + switch (hw->mac.type) { + case ixgbe_mac_X550_vf: + dev_info(&pdev->dev, "Intel(R) X550 Virtual Function\n"); + break; + case ixgbe_mac_X540_vf: + dev_info(&pdev->dev, "Intel(R) X540 Virtual Function\n"); + break; + case ixgbe_mac_82599_vf: + default: + dev_info(&pdev->dev, "Intel(R) 82599 Virtual Function\n"); + break; + } + + return 0; + +err_register: + ixgbevf_clear_interrupt_scheme(adapter); +err_sw_init: + ixgbevf_reset_interrupt_capability(adapter); + iounmap(adapter->io_addr); + kfree(adapter->rss_key); +err_ioremap: + disable_dev = !test_and_set_bit(__IXGBEVF_DISABLED, &adapter->state); + free_netdev(netdev); +err_alloc_etherdev: + pci_release_regions(pdev); +err_pci_reg: +err_dma: + if (!adapter || disable_dev) + pci_disable_device(pdev); + return err; +} + +/** + * ixgbevf_remove - Device Removal Routine + * @pdev: PCI device information struct + * + * ixgbevf_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 ixgbevf_remove(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct ixgbevf_adapter *adapter; + bool disable_dev; + + if (!netdev) + return; + + adapter = netdev_priv(netdev); + + set_bit(__IXGBEVF_REMOVING, &adapter->state); + cancel_work_sync(&adapter->service_task); + + if (netdev->reg_state == NETREG_REGISTERED) + unregister_netdev(netdev); + + ixgbevf_stop_ipsec_offload(adapter); + ixgbevf_clear_interrupt_scheme(adapter); + ixgbevf_reset_interrupt_capability(adapter); + + iounmap(adapter->io_addr); + pci_release_regions(pdev); + + hw_dbg(&adapter->hw, "Remove complete\n"); + + kfree(adapter->rss_key); + disable_dev = !test_and_set_bit(__IXGBEVF_DISABLED, &adapter->state); + free_netdev(netdev); + + if (disable_dev) + pci_disable_device(pdev); +} + +/** + * ixgbevf_io_error_detected - called when PCI error is detected + * @pdev: Pointer to PCI device + * @state: The current pci connection state + * + * This function is called after a PCI bus error affecting + * this device has been detected. + **/ +static pci_ers_result_t ixgbevf_io_error_detected(struct pci_dev *pdev, + pci_channel_state_t state) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + + if (!test_bit(__IXGBEVF_SERVICE_INITED, &adapter->state)) + return PCI_ERS_RESULT_DISCONNECT; + + rtnl_lock(); + netif_device_detach(netdev); + + if (netif_running(netdev)) + ixgbevf_close_suspend(adapter); + + if (state == pci_channel_io_perm_failure) { + rtnl_unlock(); + return PCI_ERS_RESULT_DISCONNECT; + } + + if (!test_and_set_bit(__IXGBEVF_DISABLED, &adapter->state)) + pci_disable_device(pdev); + rtnl_unlock(); + + /* Request a slot slot reset. */ + return PCI_ERS_RESULT_NEED_RESET; +} + +/** + * ixgbevf_io_slot_reset - called after the pci bus has been reset. + * @pdev: Pointer to PCI device + * + * Restart the card from scratch, as if from a cold-boot. Implementation + * resembles the first-half of the ixgbevf_resume routine. + **/ +static pci_ers_result_t ixgbevf_io_slot_reset(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + struct ixgbevf_adapter *adapter = netdev_priv(netdev); + + if (pci_enable_device_mem(pdev)) { + dev_err(&pdev->dev, + "Cannot re-enable PCI device after reset.\n"); + return PCI_ERS_RESULT_DISCONNECT; + } + + adapter->hw.hw_addr = adapter->io_addr; + smp_mb__before_atomic(); + clear_bit(__IXGBEVF_DISABLED, &adapter->state); + pci_set_master(pdev); + + ixgbevf_reset(adapter); + + return PCI_ERS_RESULT_RECOVERED; +} + +/** + * ixgbevf_io_resume - called when traffic can start flowing again. + * @pdev: Pointer to PCI device + * + * This callback is called when the error recovery driver tells us that + * its OK to resume normal operation. Implementation resembles the + * second-half of the ixgbevf_resume routine. + **/ +static void ixgbevf_io_resume(struct pci_dev *pdev) +{ + struct net_device *netdev = pci_get_drvdata(pdev); + + rtnl_lock(); + if (netif_running(netdev)) + ixgbevf_open(netdev); + + netif_device_attach(netdev); + rtnl_unlock(); +} + +/* PCI Error Recovery (ERS) */ +static const struct pci_error_handlers ixgbevf_err_handler = { + .error_detected = ixgbevf_io_error_detected, + .slot_reset = ixgbevf_io_slot_reset, + .resume = ixgbevf_io_resume, +}; + +static SIMPLE_DEV_PM_OPS(ixgbevf_pm_ops, ixgbevf_suspend, ixgbevf_resume); + +static struct pci_driver ixgbevf_driver = { + .name = ixgbevf_driver_name, + .id_table = ixgbevf_pci_tbl, + .probe = ixgbevf_probe, + .remove = ixgbevf_remove, + + /* Power Management Hooks */ + .driver.pm = &ixgbevf_pm_ops, + + .shutdown = ixgbevf_shutdown, + .err_handler = &ixgbevf_err_handler +}; + +/** + * ixgbevf_init_module - Driver Registration Routine + * + * ixgbevf_init_module is the first routine called when the driver is + * loaded. All it does is register with the PCI subsystem. + **/ +static int __init ixgbevf_init_module(void) +{ + int err; + + pr_info("%s\n", ixgbevf_driver_string); + pr_info("%s\n", ixgbevf_copyright); + ixgbevf_wq = create_singlethread_workqueue(ixgbevf_driver_name); + if (!ixgbevf_wq) { + pr_err("%s: Failed to create workqueue\n", ixgbevf_driver_name); + return -ENOMEM; + } + + err = pci_register_driver(&ixgbevf_driver); + if (err) { + destroy_workqueue(ixgbevf_wq); + return err; + } + + return 0; +} + +module_init(ixgbevf_init_module); + +/** + * ixgbevf_exit_module - Driver Exit Cleanup Routine + * + * ixgbevf_exit_module is called just before the driver is removed + * from memory. + **/ +static void __exit ixgbevf_exit_module(void) +{ + pci_unregister_driver(&ixgbevf_driver); + if (ixgbevf_wq) { + destroy_workqueue(ixgbevf_wq); + ixgbevf_wq = NULL; + } +} + +#ifdef DEBUG +/** + * ixgbevf_get_hw_dev_name - return device name string + * used by hardware layer to print debugging information + * @hw: pointer to private hardware struct + **/ +char *ixgbevf_get_hw_dev_name(struct ixgbe_hw *hw) +{ + struct ixgbevf_adapter *adapter = hw->back; + + return adapter->netdev->name; +} + +#endif +module_exit(ixgbevf_exit_module); + +/* ixgbevf_main.c */ diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.c b/drivers/net/ethernet/intel/ixgbevf/mbx.c new file mode 100644 index 000000000..6bc195326 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbevf/mbx.c @@ -0,0 +1,336 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#include "mbx.h" +#include "ixgbevf.h" + +/** + * ixgbevf_poll_for_msg - Wait for message notification + * @hw: pointer to the HW structure + * + * returns 0 if it successfully received a message notification + **/ +static s32 ixgbevf_poll_for_msg(struct ixgbe_hw *hw) +{ + struct ixgbe_mbx_info *mbx = &hw->mbx; + int countdown = mbx->timeout; + + while (countdown && mbx->ops.check_for_msg(hw)) { + countdown--; + udelay(mbx->udelay); + } + + /* if we failed, all future posted messages fail until reset */ + if (!countdown) + mbx->timeout = 0; + + return countdown ? 0 : IXGBE_ERR_MBX; +} + +/** + * ixgbevf_poll_for_ack - Wait for message acknowledgment + * @hw: pointer to the HW structure + * + * returns 0 if it successfully received a message acknowledgment + **/ +static s32 ixgbevf_poll_for_ack(struct ixgbe_hw *hw) +{ + struct ixgbe_mbx_info *mbx = &hw->mbx; + int countdown = mbx->timeout; + + while (countdown && mbx->ops.check_for_ack(hw)) { + countdown--; + udelay(mbx->udelay); + } + + /* if we failed, all future posted messages fail until reset */ + if (!countdown) + mbx->timeout = 0; + + return countdown ? 0 : IXGBE_ERR_MBX; +} + +/** + * ixgbevf_read_posted_mbx - Wait for message notification and receive message + * @hw: pointer to the HW structure + * @msg: The message buffer + * @size: Length of buffer + * + * returns 0 if it successfully received a message notification and + * copied it into the receive buffer. + **/ +static s32 ixgbevf_read_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size) +{ + struct ixgbe_mbx_info *mbx = &hw->mbx; + s32 ret_val = IXGBE_ERR_MBX; + + if (!mbx->ops.read) + goto out; + + ret_val = ixgbevf_poll_for_msg(hw); + + /* if ack received read message, otherwise we timed out */ + if (!ret_val) + ret_val = mbx->ops.read(hw, msg, size); +out: + return ret_val; +} + +/** + * ixgbevf_write_posted_mbx - Write a message to the mailbox, wait for ack + * @hw: pointer to the HW structure + * @msg: The message buffer + * @size: Length of buffer + * + * returns 0 if it successfully copied message into the buffer and + * received an ack to that message within delay * timeout period + **/ +static s32 ixgbevf_write_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size) +{ + struct ixgbe_mbx_info *mbx = &hw->mbx; + s32 ret_val = IXGBE_ERR_MBX; + + /* exit if either we can't write or there isn't a defined timeout */ + if (!mbx->ops.write || !mbx->timeout) + goto out; + + /* send msg */ + ret_val = mbx->ops.write(hw, msg, size); + + /* if msg sent wait until we receive an ack */ + if (!ret_val) + ret_val = ixgbevf_poll_for_ack(hw); +out: + return ret_val; +} + +/** + * ixgbevf_read_v2p_mailbox - read v2p mailbox + * @hw: pointer to the HW structure + * + * This function is used to read the v2p mailbox without losing the read to + * clear status bits. + **/ +static u32 ixgbevf_read_v2p_mailbox(struct ixgbe_hw *hw) +{ + u32 v2p_mailbox = IXGBE_READ_REG(hw, IXGBE_VFMAILBOX); + + v2p_mailbox |= hw->mbx.v2p_mailbox; + hw->mbx.v2p_mailbox |= v2p_mailbox & IXGBE_VFMAILBOX_R2C_BITS; + + return v2p_mailbox; +} + +/** + * ixgbevf_check_for_bit_vf - Determine if a status bit was set + * @hw: pointer to the HW structure + * @mask: bitmask for bits to be tested and cleared + * + * This function is used to check for the read to clear bits within + * the V2P mailbox. + **/ +static s32 ixgbevf_check_for_bit_vf(struct ixgbe_hw *hw, u32 mask) +{ + u32 v2p_mailbox = ixgbevf_read_v2p_mailbox(hw); + s32 ret_val = IXGBE_ERR_MBX; + + if (v2p_mailbox & mask) + ret_val = 0; + + hw->mbx.v2p_mailbox &= ~mask; + + return ret_val; +} + +/** + * ixgbevf_check_for_msg_vf - checks to see if the PF has sent mail + * @hw: pointer to the HW structure + * + * returns 0 if the PF has set the Status bit or else ERR_MBX + **/ +static s32 ixgbevf_check_for_msg_vf(struct ixgbe_hw *hw) +{ + s32 ret_val = IXGBE_ERR_MBX; + + if (!ixgbevf_check_for_bit_vf(hw, IXGBE_VFMAILBOX_PFSTS)) { + ret_val = 0; + hw->mbx.stats.reqs++; + } + + return ret_val; +} + +/** + * ixgbevf_check_for_ack_vf - checks to see if the PF has ACK'd + * @hw: pointer to the HW structure + * + * returns 0 if the PF has set the ACK bit or else ERR_MBX + **/ +static s32 ixgbevf_check_for_ack_vf(struct ixgbe_hw *hw) +{ + s32 ret_val = IXGBE_ERR_MBX; + + if (!ixgbevf_check_for_bit_vf(hw, IXGBE_VFMAILBOX_PFACK)) { + ret_val = 0; + hw->mbx.stats.acks++; + } + + return ret_val; +} + +/** + * ixgbevf_check_for_rst_vf - checks to see if the PF has reset + * @hw: pointer to the HW structure + * + * returns true if the PF has set the reset done bit or else false + **/ +static s32 ixgbevf_check_for_rst_vf(struct ixgbe_hw *hw) +{ + s32 ret_val = IXGBE_ERR_MBX; + + if (!ixgbevf_check_for_bit_vf(hw, (IXGBE_VFMAILBOX_RSTD | + IXGBE_VFMAILBOX_RSTI))) { + ret_val = 0; + hw->mbx.stats.rsts++; + } + + return ret_val; +} + +/** + * ixgbevf_obtain_mbx_lock_vf - obtain mailbox lock + * @hw: pointer to the HW structure + * + * return 0 if we obtained the mailbox lock + **/ +static s32 ixgbevf_obtain_mbx_lock_vf(struct ixgbe_hw *hw) +{ + s32 ret_val = IXGBE_ERR_MBX; + + /* Take ownership of the buffer */ + IXGBE_WRITE_REG(hw, IXGBE_VFMAILBOX, IXGBE_VFMAILBOX_VFU); + + /* reserve mailbox for VF use */ + if (ixgbevf_read_v2p_mailbox(hw) & IXGBE_VFMAILBOX_VFU) + ret_val = 0; + + return ret_val; +} + +/** + * ixgbevf_write_mbx_vf - Write a message to the mailbox + * @hw: pointer to the HW structure + * @msg: The message buffer + * @size: Length of buffer + * + * returns 0 if it successfully copied message into the buffer + **/ +static s32 ixgbevf_write_mbx_vf(struct ixgbe_hw *hw, u32 *msg, u16 size) +{ + s32 ret_val; + u16 i; + + /* lock the mailbox to prevent PF/VF race condition */ + ret_val = ixgbevf_obtain_mbx_lock_vf(hw); + if (ret_val) + goto out_no_write; + + /* flush msg and acks as we are overwriting the message buffer */ + ixgbevf_check_for_msg_vf(hw); + ixgbevf_check_for_ack_vf(hw); + + /* copy the caller specified message to the mailbox memory buffer */ + for (i = 0; i < size; i++) + IXGBE_WRITE_REG_ARRAY(hw, IXGBE_VFMBMEM, i, msg[i]); + + /* update stats */ + hw->mbx.stats.msgs_tx++; + + /* Drop VFU and interrupt the PF to tell it a message has been sent */ + IXGBE_WRITE_REG(hw, IXGBE_VFMAILBOX, IXGBE_VFMAILBOX_REQ); + +out_no_write: + return ret_val; +} + +/** + * ixgbevf_read_mbx_vf - Reads a message from the inbox intended for VF + * @hw: pointer to the HW structure + * @msg: The message buffer + * @size: Length of buffer + * + * returns 0 if it successfully read message from buffer + **/ +static s32 ixgbevf_read_mbx_vf(struct ixgbe_hw *hw, u32 *msg, u16 size) +{ + s32 ret_val = 0; + u16 i; + + /* lock the mailbox to prevent PF/VF race condition */ + ret_val = ixgbevf_obtain_mbx_lock_vf(hw); + if (ret_val) + goto out_no_read; + + /* copy the message from the mailbox memory buffer */ + for (i = 0; i < size; i++) + msg[i] = IXGBE_READ_REG_ARRAY(hw, IXGBE_VFMBMEM, i); + + /* Acknowledge receipt and release mailbox, then we're done */ + IXGBE_WRITE_REG(hw, IXGBE_VFMAILBOX, IXGBE_VFMAILBOX_ACK); + + /* update stats */ + hw->mbx.stats.msgs_rx++; + +out_no_read: + return ret_val; +} + +/** + * ixgbevf_init_mbx_params_vf - set initial values for VF mailbox + * @hw: pointer to the HW structure + * + * Initializes the hw->mbx struct to correct values for VF mailbox + */ +static s32 ixgbevf_init_mbx_params_vf(struct ixgbe_hw *hw) +{ + struct ixgbe_mbx_info *mbx = &hw->mbx; + + /* start mailbox as timed out and let the reset_hw call set the timeout + * value to begin communications + */ + mbx->timeout = 0; + mbx->udelay = IXGBE_VF_MBX_INIT_DELAY; + + mbx->size = IXGBE_VFMAILBOX_SIZE; + + mbx->stats.msgs_tx = 0; + mbx->stats.msgs_rx = 0; + mbx->stats.reqs = 0; + mbx->stats.acks = 0; + mbx->stats.rsts = 0; + + return 0; +} + +const struct ixgbe_mbx_operations ixgbevf_mbx_ops = { + .init_params = ixgbevf_init_mbx_params_vf, + .read = ixgbevf_read_mbx_vf, + .write = ixgbevf_write_mbx_vf, + .read_posted = ixgbevf_read_posted_mbx, + .write_posted = ixgbevf_write_posted_mbx, + .check_for_msg = ixgbevf_check_for_msg_vf, + .check_for_ack = ixgbevf_check_for_ack_vf, + .check_for_rst = ixgbevf_check_for_rst_vf, +}; + +/* Mailbox operations when running on Hyper-V. + * On Hyper-V, PF/VF communication is not through the + * hardware mailbox; this communication is through + * a software mediated path. + * Most mail box operations are noop while running on + * Hyper-V. + */ +const struct ixgbe_mbx_operations ixgbevf_hv_mbx_ops = { + .init_params = ixgbevf_init_mbx_params_vf, + .check_for_rst = ixgbevf_check_for_rst_vf, +}; diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.h b/drivers/net/ethernet/intel/ixgbevf/mbx.h new file mode 100644 index 000000000..853796c8e --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbevf/mbx.h @@ -0,0 +1,113 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#ifndef _IXGBE_MBX_H_ +#define _IXGBE_MBX_H_ + +#include "vf.h" + +#define IXGBE_VFMAILBOX_SIZE 16 /* 16 32 bit words - 64 bytes */ +#define IXGBE_ERR_MBX -100 + +#define IXGBE_VFMAILBOX 0x002FC +#define IXGBE_VFMBMEM 0x00200 + +/* Define mailbox register bits */ +#define IXGBE_VFMAILBOX_REQ 0x00000001 /* Request for PF Ready bit */ +#define IXGBE_VFMAILBOX_ACK 0x00000002 /* Ack PF message received */ +#define IXGBE_VFMAILBOX_VFU 0x00000004 /* VF owns the mailbox buffer */ +#define IXGBE_VFMAILBOX_PFU 0x00000008 /* PF owns the mailbox buffer */ +#define IXGBE_VFMAILBOX_PFSTS 0x00000010 /* PF wrote a message in the MB */ +#define IXGBE_VFMAILBOX_PFACK 0x00000020 /* PF ack the previous VF msg */ +#define IXGBE_VFMAILBOX_RSTI 0x00000040 /* PF has reset indication */ +#define IXGBE_VFMAILBOX_RSTD 0x00000080 /* PF has indicated reset done */ +#define IXGBE_VFMAILBOX_R2C_BITS 0x000000B0 /* All read to clear bits */ + +#define IXGBE_PFMAILBOX(x) (0x04B00 + (4 * (x))) +#define IXGBE_PFMBMEM(vfn) (0x13000 + (64 * (vfn))) + +#define IXGBE_PFMAILBOX_STS 0x00000001 /* Initiate message send to VF */ +#define IXGBE_PFMAILBOX_ACK 0x00000002 /* Ack message recv'd from VF */ +#define IXGBE_PFMAILBOX_VFU 0x00000004 /* VF owns the mailbox buffer */ +#define IXGBE_PFMAILBOX_PFU 0x00000008 /* PF owns the mailbox buffer */ +#define IXGBE_PFMAILBOX_RVFU 0x00000010 /* Reset VFU - used when VF stuck */ + +#define IXGBE_MBVFICR_VFREQ_MASK 0x0000FFFF /* bits for VF messages */ +#define IXGBE_MBVFICR_VFREQ_VF1 0x00000001 /* bit for VF 1 message */ +#define IXGBE_MBVFICR_VFACK_MASK 0xFFFF0000 /* bits for VF acks */ +#define IXGBE_MBVFICR_VFACK_VF1 0x00010000 /* bit for VF 1 ack */ + +/* If it's a IXGBE_VF_* msg then it originates in the VF and is sent to the + * PF. The reverse is true if it is IXGBE_PF_*. + * Message ACK's are the value or'd with 0xF0000000 + */ +/* Messages below or'd with this are the ACK */ +#define IXGBE_VT_MSGTYPE_ACK 0x80000000 +/* Messages below or'd with this are the NACK */ +#define IXGBE_VT_MSGTYPE_NACK 0x40000000 +/* Indicates that VF is still clear to send requests */ +#define IXGBE_VT_MSGTYPE_CTS 0x20000000 +#define IXGBE_VT_MSGINFO_SHIFT 16 +/* bits 23:16 are used for exra info for certain messages */ +#define IXGBE_VT_MSGINFO_MASK (0xFF << IXGBE_VT_MSGINFO_SHIFT) + +/* definitions to support mailbox API version negotiation */ + +/* each element denotes a version of the API; existing numbers may not + * change; any additions must go at the end + */ +enum ixgbe_pfvf_api_rev { + ixgbe_mbox_api_10, /* API version 1.0, linux/freebsd VF driver */ + ixgbe_mbox_api_20, /* API version 2.0, solaris Phase1 VF driver */ + ixgbe_mbox_api_11, /* API version 1.1, linux/freebsd VF driver */ + ixgbe_mbox_api_12, /* API version 1.2, linux/freebsd VF driver */ + ixgbe_mbox_api_13, /* API version 1.3, linux/freebsd VF driver */ + ixgbe_mbox_api_14, /* API version 1.4, linux/freebsd VF driver */ + /* This value should always be last */ + ixgbe_mbox_api_unknown, /* indicates that API version is not known */ +}; + +/* mailbox API, legacy requests */ +#define IXGBE_VF_RESET 0x01 /* VF requests reset */ +#define IXGBE_VF_SET_MAC_ADDR 0x02 /* VF requests PF to set MAC addr */ +#define IXGBE_VF_SET_MULTICAST 0x03 /* VF requests PF to set MC addr */ +#define IXGBE_VF_SET_VLAN 0x04 /* VF requests PF to set VLAN */ + +/* mailbox API, version 1.0 VF requests */ +#define IXGBE_VF_SET_LPE 0x05 /* VF requests PF to set VMOLR.LPE */ +#define IXGBE_VF_SET_MACVLAN 0x06 /* VF requests PF for unicast filter */ +#define IXGBE_VF_API_NEGOTIATE 0x08 /* negotiate API version */ + +/* mailbox API, version 1.1 VF requests */ +#define IXGBE_VF_GET_QUEUE 0x09 /* get queue configuration */ + +/* GET_QUEUES return data indices within the mailbox */ +#define IXGBE_VF_TX_QUEUES 1 /* number of Tx queues supported */ +#define IXGBE_VF_RX_QUEUES 2 /* number of Rx queues supported */ +#define IXGBE_VF_TRANS_VLAN 3 /* Indication of port VLAN */ +#define IXGBE_VF_DEF_QUEUE 4 /* Default queue offset */ + +/* mailbox API, version 1.2 VF requests */ +#define IXGBE_VF_GET_RETA 0x0a /* VF request for RETA */ +#define IXGBE_VF_GET_RSS_KEY 0x0b /* get RSS hash key */ + +#define IXGBE_VF_UPDATE_XCAST_MODE 0x0c + +/* mailbox API, version 1.4 VF requests */ +#define IXGBE_VF_IPSEC_ADD 0x0d +#define IXGBE_VF_IPSEC_DEL 0x0e + +/* length of permanent address message returned from PF */ +#define IXGBE_VF_PERMADDR_MSG_LEN 4 +/* word in permanent address message with the current multicast type */ +#define IXGBE_VF_MC_TYPE_WORD 3 + +#define IXGBE_PF_CONTROL_MSG 0x0100 /* PF control message */ + +#define IXGBE_VF_MBX_INIT_TIMEOUT 2000 /* number of retries on mailbox */ +#define IXGBE_VF_MBX_INIT_DELAY 500 /* microseconds between retries */ + +/* forward declaration of the HW struct */ +struct ixgbe_hw; + +#endif /* _IXGBE_MBX_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbevf/regs.h b/drivers/net/ethernet/intel/ixgbevf/regs.h new file mode 100644 index 000000000..68d16ae5b --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbevf/regs.h @@ -0,0 +1,61 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#ifndef _IXGBEVF_REGS_H_ +#define _IXGBEVF_REGS_H_ + +#define IXGBE_VFCTRL 0x00000 +#define IXGBE_VFSTATUS 0x00008 +#define IXGBE_VFLINKS 0x00010 +#define IXGBE_VFFRTIMER 0x00048 +#define IXGBE_VFRXMEMWRAP 0x03190 +#define IXGBE_VTEICR 0x00100 +#define IXGBE_VTEICS 0x00104 +#define IXGBE_VTEIMS 0x00108 +#define IXGBE_VTEIMC 0x0010C +#define IXGBE_VTEIAC 0x00110 +#define IXGBE_VTEIAM 0x00114 +#define IXGBE_VTEITR(x) (0x00820 + (4 * (x))) +#define IXGBE_VTIVAR(x) (0x00120 + (4 * (x))) +#define IXGBE_VTIVAR_MISC 0x00140 +#define IXGBE_VTRSCINT(x) (0x00180 + (4 * (x))) +#define IXGBE_VFRDBAL(x) (0x01000 + (0x40 * (x))) +#define IXGBE_VFRDBAH(x) (0x01004 + (0x40 * (x))) +#define IXGBE_VFRDLEN(x) (0x01008 + (0x40 * (x))) +#define IXGBE_VFRDH(x) (0x01010 + (0x40 * (x))) +#define IXGBE_VFRDT(x) (0x01018 + (0x40 * (x))) +#define IXGBE_VFRXDCTL(x) (0x01028 + (0x40 * (x))) +#define IXGBE_VFSRRCTL(x) (0x01014 + (0x40 * (x))) +#define IXGBE_VFRSCCTL(x) (0x0102C + (0x40 * (x))) +#define IXGBE_VFPSRTYPE 0x00300 +#define IXGBE_VFTDBAL(x) (0x02000 + (0x40 * (x))) +#define IXGBE_VFTDBAH(x) (0x02004 + (0x40 * (x))) +#define IXGBE_VFTDLEN(x) (0x02008 + (0x40 * (x))) +#define IXGBE_VFTDH(x) (0x02010 + (0x40 * (x))) +#define IXGBE_VFTDT(x) (0x02018 + (0x40 * (x))) +#define IXGBE_VFTXDCTL(x) (0x02028 + (0x40 * (x))) +#define IXGBE_VFTDWBAL(x) (0x02038 + (0x40 * (x))) +#define IXGBE_VFTDWBAH(x) (0x0203C + (0x40 * (x))) +#define IXGBE_VFDCA_RXCTRL(x) (0x0100C + (0x40 * (x))) +#define IXGBE_VFDCA_TXCTRL(x) (0x0200c + (0x40 * (x))) +#define IXGBE_VFGPRC 0x0101C +#define IXGBE_VFGPTC 0x0201C +#define IXGBE_VFGORC_LSB 0x01020 +#define IXGBE_VFGORC_MSB 0x01024 +#define IXGBE_VFGOTC_LSB 0x02020 +#define IXGBE_VFGOTC_MSB 0x02024 +#define IXGBE_VFMPRC 0x01034 +#define IXGBE_VFMRQC 0x3000 +#define IXGBE_VFRSSRK(x) (0x3100 + ((x) * 4)) +#define IXGBE_VFRETA(x) (0x3200 + ((x) * 4)) + +/* VFMRQC bits */ +#define IXGBE_VFMRQC_RSSEN 0x00000001 /* RSS Enable */ +#define IXGBE_VFMRQC_RSS_FIELD_IPV4_TCP 0x00010000 +#define IXGBE_VFMRQC_RSS_FIELD_IPV4 0x00020000 +#define IXGBE_VFMRQC_RSS_FIELD_IPV6 0x00100000 +#define IXGBE_VFMRQC_RSS_FIELD_IPV6_TCP 0x00200000 + +#define IXGBE_WRITE_FLUSH(a) (IXGBE_READ_REG(a, IXGBE_VFSTATUS)) + +#endif /* _IXGBEVF_REGS_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c new file mode 100644 index 000000000..bfe6dfcec --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbevf/vf.c @@ -0,0 +1,1018 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#include "vf.h" +#include "ixgbevf.h" + +/* On Hyper-V, to reset, we need to read from this offset + * from the PCI config space. This is the mechanism used on + * Hyper-V to support PF/VF communication. + */ +#define IXGBE_HV_RESET_OFFSET 0x201 + +static inline s32 ixgbevf_write_msg_read_ack(struct ixgbe_hw *hw, u32 *msg, + u32 *retmsg, u16 size) +{ + struct ixgbe_mbx_info *mbx = &hw->mbx; + s32 retval = mbx->ops.write_posted(hw, msg, size); + + if (retval) + return retval; + + return mbx->ops.read_posted(hw, retmsg, size); +} + +/** + * ixgbevf_start_hw_vf - Prepare hardware for Tx/Rx + * @hw: pointer to hardware structure + * + * Starts the hardware by filling the bus info structure and media type, clears + * all on chip counters, initializes receive address registers, multicast + * table, VLAN filter table, calls routine to set up link and flow control + * settings, and leaves transmit and receive units disabled and uninitialized + **/ +static s32 ixgbevf_start_hw_vf(struct ixgbe_hw *hw) +{ + /* Clear adapter stopped flag */ + hw->adapter_stopped = false; + + return 0; +} + +/** + * ixgbevf_init_hw_vf - virtual function hardware initialization + * @hw: pointer to hardware structure + * + * Initialize the hardware by resetting the hardware and then starting + * the hardware + **/ +static s32 ixgbevf_init_hw_vf(struct ixgbe_hw *hw) +{ + s32 status = hw->mac.ops.start_hw(hw); + + hw->mac.ops.get_mac_addr(hw, hw->mac.addr); + + return status; +} + +/** + * ixgbevf_reset_hw_vf - Performs hardware reset + * @hw: pointer to hardware structure + * + * Resets the hardware by resetting the transmit and receive units, masks and + * clears all interrupts. + **/ +static s32 ixgbevf_reset_hw_vf(struct ixgbe_hw *hw) +{ + struct ixgbe_mbx_info *mbx = &hw->mbx; + u32 timeout = IXGBE_VF_INIT_TIMEOUT; + s32 ret_val = IXGBE_ERR_INVALID_MAC_ADDR; + u32 msgbuf[IXGBE_VF_PERMADDR_MSG_LEN]; + u8 *addr = (u8 *)(&msgbuf[1]); + + /* Call adapter stop to disable tx/rx and clear interrupts */ + hw->mac.ops.stop_adapter(hw); + + /* reset the api version */ + hw->api_version = ixgbe_mbox_api_10; + + IXGBE_WRITE_REG(hw, IXGBE_VFCTRL, IXGBE_CTRL_RST); + IXGBE_WRITE_FLUSH(hw); + + /* we cannot reset while the RSTI / RSTD bits are asserted */ + while (!mbx->ops.check_for_rst(hw) && timeout) { + timeout--; + udelay(5); + } + + if (!timeout) + return IXGBE_ERR_RESET_FAILED; + + /* mailbox timeout can now become active */ + mbx->timeout = IXGBE_VF_MBX_INIT_TIMEOUT; + + msgbuf[0] = IXGBE_VF_RESET; + mbx->ops.write_posted(hw, msgbuf, 1); + + mdelay(10); + + /* set our "perm_addr" based on info provided by PF + * also set up the mc_filter_type which is piggy backed + * on the mac address in word 3 + */ + ret_val = mbx->ops.read_posted(hw, msgbuf, IXGBE_VF_PERMADDR_MSG_LEN); + if (ret_val) + return ret_val; + + /* New versions of the PF may NACK the reset return message + * to indicate that no MAC address has yet been assigned for + * the VF. + */ + if (msgbuf[0] != (IXGBE_VF_RESET | IXGBE_VT_MSGTYPE_ACK) && + msgbuf[0] != (IXGBE_VF_RESET | IXGBE_VT_MSGTYPE_NACK)) + return IXGBE_ERR_INVALID_MAC_ADDR; + + if (msgbuf[0] == (IXGBE_VF_RESET | IXGBE_VT_MSGTYPE_ACK)) + ether_addr_copy(hw->mac.perm_addr, addr); + + hw->mac.mc_filter_type = msgbuf[IXGBE_VF_MC_TYPE_WORD]; + + return 0; +} + +/** + * Hyper-V variant; the VF/PF communication is through the PCI + * config space. + * @hw: pointer to private hardware struct + */ +static s32 ixgbevf_hv_reset_hw_vf(struct ixgbe_hw *hw) +{ +#if IS_ENABLED(CONFIG_PCI_MMCONFIG) + struct ixgbevf_adapter *adapter = hw->back; + int i; + + for (i = 0; i < 6; i++) + pci_read_config_byte(adapter->pdev, + (i + IXGBE_HV_RESET_OFFSET), + &hw->mac.perm_addr[i]); + return 0; +#else + pr_err("PCI_MMCONFIG needs to be enabled for Hyper-V\n"); + return -EOPNOTSUPP; +#endif +} + +/** + * ixgbevf_stop_hw_vf - Generic stop Tx/Rx units + * @hw: pointer to hardware structure + * + * Sets the adapter_stopped flag within ixgbe_hw struct. Clears interrupts, + * disables transmit and receive units. The adapter_stopped flag is used by + * the shared code and drivers to determine if the adapter is in a stopped + * state and should not touch the hardware. + **/ +static s32 ixgbevf_stop_hw_vf(struct ixgbe_hw *hw) +{ + u32 number_of_queues; + u32 reg_val; + u16 i; + + /* Set the adapter_stopped flag so other driver functions stop touching + * the hardware + */ + hw->adapter_stopped = true; + + /* Disable the receive unit by stopped each queue */ + number_of_queues = hw->mac.max_rx_queues; + for (i = 0; i < number_of_queues; i++) { + reg_val = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(i)); + if (reg_val & IXGBE_RXDCTL_ENABLE) { + reg_val &= ~IXGBE_RXDCTL_ENABLE; + IXGBE_WRITE_REG(hw, IXGBE_VFRXDCTL(i), reg_val); + } + } + + IXGBE_WRITE_FLUSH(hw); + + /* Clear interrupt mask to stop from interrupts being generated */ + IXGBE_WRITE_REG(hw, IXGBE_VTEIMC, IXGBE_VF_IRQ_CLEAR_MASK); + + /* Clear any pending interrupts */ + IXGBE_READ_REG(hw, IXGBE_VTEICR); + + /* Disable the transmit unit. Each queue must be disabled. */ + number_of_queues = hw->mac.max_tx_queues; + for (i = 0; i < number_of_queues; i++) { + reg_val = IXGBE_READ_REG(hw, IXGBE_VFTXDCTL(i)); + if (reg_val & IXGBE_TXDCTL_ENABLE) { + reg_val &= ~IXGBE_TXDCTL_ENABLE; + IXGBE_WRITE_REG(hw, IXGBE_VFTXDCTL(i), reg_val); + } + } + + return 0; +} + +/** + * ixgbevf_mta_vector - Determines bit-vector in multicast table to set + * @hw: pointer to hardware structure + * @mc_addr: the multicast address + * + * Extracts the 12 bits, from a multicast address, to determine which + * bit-vector to set in the multicast table. The hardware uses 12 bits, from + * incoming Rx multicast addresses, to determine the bit-vector to check in + * the MTA. Which of the 4 combination, of 12-bits, the hardware uses is set + * by the MO field of the MCSTCTRL. The MO field is set during initialization + * to mc_filter_type. + **/ +static s32 ixgbevf_mta_vector(struct ixgbe_hw *hw, u8 *mc_addr) +{ + u32 vector = 0; + + switch (hw->mac.mc_filter_type) { + case 0: /* use bits [47:36] of the address */ + vector = ((mc_addr[4] >> 4) | (((u16)mc_addr[5]) << 4)); + break; + case 1: /* use bits [46:35] of the address */ + vector = ((mc_addr[4] >> 3) | (((u16)mc_addr[5]) << 5)); + break; + case 2: /* use bits [45:34] of the address */ + vector = ((mc_addr[4] >> 2) | (((u16)mc_addr[5]) << 6)); + break; + case 3: /* use bits [43:32] of the address */ + vector = ((mc_addr[4]) | (((u16)mc_addr[5]) << 8)); + break; + default: /* Invalid mc_filter_type */ + break; + } + + /* vector can only be 12-bits or boundary will be exceeded */ + vector &= 0xFFF; + return vector; +} + +/** + * ixgbevf_get_mac_addr_vf - Read device MAC address + * @hw: pointer to the HW structure + * @mac_addr: pointer to storage for retrieved MAC address + **/ +static s32 ixgbevf_get_mac_addr_vf(struct ixgbe_hw *hw, u8 *mac_addr) +{ + ether_addr_copy(mac_addr, hw->mac.perm_addr); + + return 0; +} + +static s32 ixgbevf_set_uc_addr_vf(struct ixgbe_hw *hw, u32 index, u8 *addr) +{ + u32 msgbuf[3], msgbuf_chk; + u8 *msg_addr = (u8 *)(&msgbuf[1]); + s32 ret_val; + + memset(msgbuf, 0, sizeof(msgbuf)); + /* If index is one then this is the start of a new list and needs + * indication to the PF so it can do it's own list management. + * If it is zero then that tells the PF to just clear all of + * this VF's macvlans and there is no new list. + */ + msgbuf[0] |= index << IXGBE_VT_MSGINFO_SHIFT; + msgbuf[0] |= IXGBE_VF_SET_MACVLAN; + msgbuf_chk = msgbuf[0]; + + if (addr) + ether_addr_copy(msg_addr, addr); + + ret_val = ixgbevf_write_msg_read_ack(hw, msgbuf, msgbuf, + ARRAY_SIZE(msgbuf)); + if (!ret_val) { + msgbuf[0] &= ~IXGBE_VT_MSGTYPE_CTS; + + if (msgbuf[0] == (msgbuf_chk | IXGBE_VT_MSGTYPE_NACK)) + return -ENOMEM; + } + + return ret_val; +} + +static s32 ixgbevf_hv_set_uc_addr_vf(struct ixgbe_hw *hw, u32 index, u8 *addr) +{ + return -EOPNOTSUPP; +} + +/** + * ixgbevf_get_reta_locked - get the RSS redirection table (RETA) contents. + * @hw: pointer to hardware structure + * @reta: buffer to fill with RETA contents. + * @num_rx_queues: Number of Rx queues configured for this port + * + * The "reta" buffer should be big enough to contain 32 registers. + * + * Returns: 0 on success. + * if API doesn't support this operation - (-EOPNOTSUPP). + */ +int ixgbevf_get_reta_locked(struct ixgbe_hw *hw, u32 *reta, int num_rx_queues) +{ + int err, i, j; + u32 msgbuf[IXGBE_VFMAILBOX_SIZE]; + u32 *hw_reta = &msgbuf[1]; + u32 mask = 0; + + /* We have to use a mailbox for 82599 and x540 devices only. + * For these devices RETA has 128 entries. + * Also these VFs support up to 4 RSS queues. Therefore PF will compress + * 16 RETA entries in each DWORD giving 2 bits to each entry. + */ + int dwords = IXGBEVF_82599_RETA_SIZE / 16; + + /* We support the RSS querying for 82599 and x540 devices only. + * Thus return an error if API doesn't support RETA querying or querying + * is not supported for this device type. + */ + switch (hw->api_version) { + case ixgbe_mbox_api_14: + case ixgbe_mbox_api_13: + case ixgbe_mbox_api_12: + if (hw->mac.type < ixgbe_mac_X550_vf) + break; + fallthrough; + default: + return -EOPNOTSUPP; + } + + msgbuf[0] = IXGBE_VF_GET_RETA; + + err = hw->mbx.ops.write_posted(hw, msgbuf, 1); + + if (err) + return err; + + err = hw->mbx.ops.read_posted(hw, msgbuf, dwords + 1); + + if (err) + return err; + + msgbuf[0] &= ~IXGBE_VT_MSGTYPE_CTS; + + /* If the operation has been refused by a PF return -EPERM */ + if (msgbuf[0] == (IXGBE_VF_GET_RETA | IXGBE_VT_MSGTYPE_NACK)) + return -EPERM; + + /* If we didn't get an ACK there must have been + * some sort of mailbox error so we should treat it + * as such. + */ + if (msgbuf[0] != (IXGBE_VF_GET_RETA | IXGBE_VT_MSGTYPE_ACK)) + return IXGBE_ERR_MBX; + + /* ixgbevf doesn't support more than 2 queues at the moment */ + if (num_rx_queues > 1) + mask = 0x1; + + for (i = 0; i < dwords; i++) + for (j = 0; j < 16; j++) + reta[i * 16 + j] = (hw_reta[i] >> (2 * j)) & mask; + + return 0; +} + +/** + * ixgbevf_get_rss_key_locked - get the RSS Random Key + * @hw: pointer to the HW structure + * @rss_key: buffer to fill with RSS Hash Key contents. + * + * The "rss_key" buffer should be big enough to contain 10 registers. + * + * Returns: 0 on success. + * if API doesn't support this operation - (-EOPNOTSUPP). + */ +int ixgbevf_get_rss_key_locked(struct ixgbe_hw *hw, u8 *rss_key) +{ + int err; + u32 msgbuf[IXGBE_VFMAILBOX_SIZE]; + + /* We currently support the RSS Random Key retrieval for 82599 and x540 + * devices only. + * + * Thus return an error if API doesn't support RSS Random Key retrieval + * or if the operation is not supported for this device type. + */ + switch (hw->api_version) { + case ixgbe_mbox_api_14: + case ixgbe_mbox_api_13: + case ixgbe_mbox_api_12: + if (hw->mac.type < ixgbe_mac_X550_vf) + break; + fallthrough; + default: + return -EOPNOTSUPP; + } + + msgbuf[0] = IXGBE_VF_GET_RSS_KEY; + err = hw->mbx.ops.write_posted(hw, msgbuf, 1); + + if (err) + return err; + + err = hw->mbx.ops.read_posted(hw, msgbuf, 11); + + if (err) + return err; + + msgbuf[0] &= ~IXGBE_VT_MSGTYPE_CTS; + + /* If the operation has been refused by a PF return -EPERM */ + if (msgbuf[0] == (IXGBE_VF_GET_RSS_KEY | IXGBE_VT_MSGTYPE_NACK)) + return -EPERM; + + /* If we didn't get an ACK there must have been + * some sort of mailbox error so we should treat it + * as such. + */ + if (msgbuf[0] != (IXGBE_VF_GET_RSS_KEY | IXGBE_VT_MSGTYPE_ACK)) + return IXGBE_ERR_MBX; + + memcpy(rss_key, msgbuf + 1, IXGBEVF_RSS_HASH_KEY_SIZE); + + return 0; +} + +/** + * ixgbevf_set_rar_vf - set device MAC address + * @hw: pointer to hardware structure + * @index: Receive address register to write + * @addr: Address to put into receive address register + * @vmdq: Unused in this implementation + **/ +static s32 ixgbevf_set_rar_vf(struct ixgbe_hw *hw, u32 index, u8 *addr, + u32 vmdq) +{ + u32 msgbuf[3]; + u8 *msg_addr = (u8 *)(&msgbuf[1]); + s32 ret_val; + + memset(msgbuf, 0, sizeof(msgbuf)); + msgbuf[0] = IXGBE_VF_SET_MAC_ADDR; + ether_addr_copy(msg_addr, addr); + + ret_val = ixgbevf_write_msg_read_ack(hw, msgbuf, msgbuf, + ARRAY_SIZE(msgbuf)); + msgbuf[0] &= ~IXGBE_VT_MSGTYPE_CTS; + + /* if nacked the address was rejected, use "perm_addr" */ + if (!ret_val && + (msgbuf[0] == (IXGBE_VF_SET_MAC_ADDR | IXGBE_VT_MSGTYPE_NACK))) { + ixgbevf_get_mac_addr_vf(hw, hw->mac.addr); + return IXGBE_ERR_MBX; + } + + return ret_val; +} + +/** + * ixgbevf_hv_set_rar_vf - set device MAC address Hyper-V variant + * @hw: pointer to hardware structure + * @index: Receive address register to write + * @addr: Address to put into receive address register + * @vmdq: Unused in this implementation + * + * We don't really allow setting the device MAC address. However, + * if the address being set is the permanent MAC address we will + * permit that. + **/ +static s32 ixgbevf_hv_set_rar_vf(struct ixgbe_hw *hw, u32 index, u8 *addr, + u32 vmdq) +{ + if (ether_addr_equal(addr, hw->mac.perm_addr)) + return 0; + + return -EOPNOTSUPP; +} + +/** + * ixgbevf_update_mc_addr_list_vf - Update Multicast addresses + * @hw: pointer to the HW structure + * @netdev: pointer to net device structure + * + * Updates the Multicast Table Array. + **/ +static s32 ixgbevf_update_mc_addr_list_vf(struct ixgbe_hw *hw, + struct net_device *netdev) +{ + struct netdev_hw_addr *ha; + u32 msgbuf[IXGBE_VFMAILBOX_SIZE]; + u16 *vector_list = (u16 *)&msgbuf[1]; + u32 cnt, i; + + /* Each entry in the list uses 1 16 bit word. We have 30 + * 16 bit words available in our HW msg buffer (minus 1 for the + * msg type). That's 30 hash values if we pack 'em right. If + * there are more than 30 MC addresses to add then punt the + * extras for now and then add code to handle more than 30 later. + * It would be unusual for a server to request that many multi-cast + * addresses except for in large enterprise network environments. + */ + + cnt = netdev_mc_count(netdev); + if (cnt > 30) + cnt = 30; + msgbuf[0] = IXGBE_VF_SET_MULTICAST; + msgbuf[0] |= cnt << IXGBE_VT_MSGINFO_SHIFT; + + i = 0; + netdev_for_each_mc_addr(ha, netdev) { + if (i == cnt) + break; + if (is_link_local_ether_addr(ha->addr)) + continue; + + vector_list[i++] = ixgbevf_mta_vector(hw, ha->addr); + } + + return ixgbevf_write_msg_read_ack(hw, msgbuf, msgbuf, + IXGBE_VFMAILBOX_SIZE); +} + +/** + * Hyper-V variant - just a stub. + * @hw: unused + * @netdev: unused + */ +static s32 ixgbevf_hv_update_mc_addr_list_vf(struct ixgbe_hw *hw, + struct net_device *netdev) +{ + return -EOPNOTSUPP; +} + +/** + * ixgbevf_update_xcast_mode - Update Multicast mode + * @hw: pointer to the HW structure + * @xcast_mode: new multicast mode + * + * Updates the Multicast Mode of VF. + **/ +static s32 ixgbevf_update_xcast_mode(struct ixgbe_hw *hw, int xcast_mode) +{ + u32 msgbuf[2]; + s32 err; + + switch (hw->api_version) { + case ixgbe_mbox_api_12: + /* promisc introduced in 1.3 version */ + if (xcast_mode == IXGBEVF_XCAST_MODE_PROMISC) + return -EOPNOTSUPP; + fallthrough; + case ixgbe_mbox_api_14: + case ixgbe_mbox_api_13: + break; + default: + return -EOPNOTSUPP; + } + + msgbuf[0] = IXGBE_VF_UPDATE_XCAST_MODE; + msgbuf[1] = xcast_mode; + + err = ixgbevf_write_msg_read_ack(hw, msgbuf, msgbuf, + ARRAY_SIZE(msgbuf)); + if (err) + return err; + + msgbuf[0] &= ~IXGBE_VT_MSGTYPE_CTS; + if (msgbuf[0] == (IXGBE_VF_UPDATE_XCAST_MODE | IXGBE_VT_MSGTYPE_NACK)) + return -EPERM; + + return 0; +} + +/** + * Hyper-V variant - just a stub. + * @hw: unused + * @xcast_mode: unused + */ +static s32 ixgbevf_hv_update_xcast_mode(struct ixgbe_hw *hw, int xcast_mode) +{ + return -EOPNOTSUPP; +} + +/** + * ixgbevf_set_vfta_vf - Set/Unset VLAN filter table address + * @hw: pointer to the HW structure + * @vlan: 12 bit VLAN ID + * @vind: unused by VF drivers + * @vlan_on: if true then set bit, else clear bit + **/ +static s32 ixgbevf_set_vfta_vf(struct ixgbe_hw *hw, u32 vlan, u32 vind, + bool vlan_on) +{ + u32 msgbuf[2]; + s32 err; + + msgbuf[0] = IXGBE_VF_SET_VLAN; + msgbuf[1] = vlan; + /* Setting the 8 bit field MSG INFO to TRUE indicates "add" */ + msgbuf[0] |= vlan_on << IXGBE_VT_MSGINFO_SHIFT; + + err = ixgbevf_write_msg_read_ack(hw, msgbuf, msgbuf, + ARRAY_SIZE(msgbuf)); + if (err) + goto mbx_err; + + /* remove extra bits from the message */ + msgbuf[0] &= ~IXGBE_VT_MSGTYPE_CTS; + msgbuf[0] &= ~(0xFF << IXGBE_VT_MSGINFO_SHIFT); + + if (msgbuf[0] != (IXGBE_VF_SET_VLAN | IXGBE_VT_MSGTYPE_ACK)) + err = IXGBE_ERR_INVALID_ARGUMENT; + +mbx_err: + return err; +} + +/** + * Hyper-V variant - just a stub. + * @hw: unused + * @vlan: unused + * @vind: unused + * @vlan_on: unused + */ +static s32 ixgbevf_hv_set_vfta_vf(struct ixgbe_hw *hw, u32 vlan, u32 vind, + bool vlan_on) +{ + return -EOPNOTSUPP; +} + +/** + * ixgbevf_setup_mac_link_vf - Setup MAC link settings + * @hw: pointer to hardware structure + * @speed: Unused in this implementation + * @autoneg: Unused in this implementation + * @autoneg_wait_to_complete: Unused in this implementation + * + * Do nothing and return success. VF drivers are not allowed to change + * global settings. Maintained for driver compatibility. + **/ +static s32 ixgbevf_setup_mac_link_vf(struct ixgbe_hw *hw, + ixgbe_link_speed speed, bool autoneg, + bool autoneg_wait_to_complete) +{ + return 0; +} + +/** + * ixgbevf_check_mac_link_vf - Get link/speed status + * @hw: pointer to hardware structure + * @speed: pointer to link speed + * @link_up: true is link is up, false otherwise + * @autoneg_wait_to_complete: unused + * + * Reads the links register to determine if link is up and the current speed + **/ +static s32 ixgbevf_check_mac_link_vf(struct ixgbe_hw *hw, + ixgbe_link_speed *speed, + bool *link_up, + bool autoneg_wait_to_complete) +{ + struct ixgbe_mbx_info *mbx = &hw->mbx; + struct ixgbe_mac_info *mac = &hw->mac; + s32 ret_val = 0; + u32 links_reg; + u32 in_msg = 0; + + /* If we were hit with a reset drop the link */ + if (!mbx->ops.check_for_rst(hw) || !mbx->timeout) + mac->get_link_status = true; + + if (!mac->get_link_status) + goto out; + + /* if link status is down no point in checking to see if pf is up */ + links_reg = IXGBE_READ_REG(hw, IXGBE_VFLINKS); + if (!(links_reg & IXGBE_LINKS_UP)) + goto out; + + /* for SFP+ modules and DA cables on 82599 it can take up to 500usecs + * before the link status is correct + */ + if (mac->type == ixgbe_mac_82599_vf) { + int i; + + for (i = 0; i < 5; i++) { + udelay(100); + links_reg = IXGBE_READ_REG(hw, IXGBE_VFLINKS); + + if (!(links_reg & IXGBE_LINKS_UP)) + goto out; + } + } + + switch (links_reg & IXGBE_LINKS_SPEED_82599) { + case IXGBE_LINKS_SPEED_10G_82599: + *speed = IXGBE_LINK_SPEED_10GB_FULL; + break; + case IXGBE_LINKS_SPEED_1G_82599: + *speed = IXGBE_LINK_SPEED_1GB_FULL; + break; + case IXGBE_LINKS_SPEED_100_82599: + *speed = IXGBE_LINK_SPEED_100_FULL; + break; + } + + /* if the read failed it could just be a mailbox collision, best wait + * until we are called again and don't report an error + */ + if (mbx->ops.read(hw, &in_msg, 1)) + goto out; + + if (!(in_msg & IXGBE_VT_MSGTYPE_CTS)) { + /* msg is not CTS and is NACK we must have lost CTS status */ + if (in_msg & IXGBE_VT_MSGTYPE_NACK) + ret_val = -1; + goto out; + } + + /* the pf is talking, if we timed out in the past we reinit */ + if (!mbx->timeout) { + ret_val = -1; + goto out; + } + + /* if we passed all the tests above then the link is up and we no + * longer need to check for link + */ + mac->get_link_status = false; + +out: + *link_up = !mac->get_link_status; + return ret_val; +} + +/** + * Hyper-V variant; there is no mailbox communication. + * @hw: pointer to private hardware struct + * @speed: pointer to link speed + * @link_up: true is link is up, false otherwise + * @autoneg_wait_to_complete: unused + */ +static s32 ixgbevf_hv_check_mac_link_vf(struct ixgbe_hw *hw, + ixgbe_link_speed *speed, + bool *link_up, + bool autoneg_wait_to_complete) +{ + struct ixgbe_mbx_info *mbx = &hw->mbx; + struct ixgbe_mac_info *mac = &hw->mac; + u32 links_reg; + + /* If we were hit with a reset drop the link */ + if (!mbx->ops.check_for_rst(hw) || !mbx->timeout) + mac->get_link_status = true; + + if (!mac->get_link_status) + goto out; + + /* if link status is down no point in checking to see if pf is up */ + links_reg = IXGBE_READ_REG(hw, IXGBE_VFLINKS); + if (!(links_reg & IXGBE_LINKS_UP)) + goto out; + + /* for SFP+ modules and DA cables on 82599 it can take up to 500usecs + * before the link status is correct + */ + if (mac->type == ixgbe_mac_82599_vf) { + int i; + + for (i = 0; i < 5; i++) { + udelay(100); + links_reg = IXGBE_READ_REG(hw, IXGBE_VFLINKS); + + if (!(links_reg & IXGBE_LINKS_UP)) + goto out; + } + } + + switch (links_reg & IXGBE_LINKS_SPEED_82599) { + case IXGBE_LINKS_SPEED_10G_82599: + *speed = IXGBE_LINK_SPEED_10GB_FULL; + break; + case IXGBE_LINKS_SPEED_1G_82599: + *speed = IXGBE_LINK_SPEED_1GB_FULL; + break; + case IXGBE_LINKS_SPEED_100_82599: + *speed = IXGBE_LINK_SPEED_100_FULL; + break; + } + + /* if we passed all the tests above then the link is up and we no + * longer need to check for link + */ + mac->get_link_status = false; + +out: + *link_up = !mac->get_link_status; + return 0; +} + +/** + * ixgbevf_set_rlpml_vf - Set the maximum receive packet length + * @hw: pointer to the HW structure + * @max_size: value to assign to max frame size + **/ +static s32 ixgbevf_set_rlpml_vf(struct ixgbe_hw *hw, u16 max_size) +{ + u32 msgbuf[2]; + s32 ret_val; + + msgbuf[0] = IXGBE_VF_SET_LPE; + msgbuf[1] = max_size; + + ret_val = ixgbevf_write_msg_read_ack(hw, msgbuf, msgbuf, + ARRAY_SIZE(msgbuf)); + if (ret_val) + return ret_val; + if ((msgbuf[0] & IXGBE_VF_SET_LPE) && + (msgbuf[0] & IXGBE_VT_MSGTYPE_NACK)) + return IXGBE_ERR_MBX; + + return 0; +} + +/** + * ixgbevf_hv_set_rlpml_vf - Set the maximum receive packet length + * @hw: pointer to the HW structure + * @max_size: value to assign to max frame size + * Hyper-V variant. + **/ +static s32 ixgbevf_hv_set_rlpml_vf(struct ixgbe_hw *hw, u16 max_size) +{ + u32 reg; + + /* If we are on Hyper-V, we implement this functionality + * differently. + */ + reg = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(0)); + /* CRC == 4 */ + reg |= ((max_size + 4) | IXGBE_RXDCTL_RLPML_EN); + IXGBE_WRITE_REG(hw, IXGBE_VFRXDCTL(0), reg); + + return 0; +} + +/** + * ixgbevf_negotiate_api_version_vf - Negotiate supported API version + * @hw: pointer to the HW structure + * @api: integer containing requested API version + **/ +static int ixgbevf_negotiate_api_version_vf(struct ixgbe_hw *hw, int api) +{ + int err; + u32 msg[3]; + + /* Negotiate the mailbox API version */ + msg[0] = IXGBE_VF_API_NEGOTIATE; + msg[1] = api; + msg[2] = 0; + + err = ixgbevf_write_msg_read_ack(hw, msg, msg, ARRAY_SIZE(msg)); + if (!err) { + msg[0] &= ~IXGBE_VT_MSGTYPE_CTS; + + /* Store value and return 0 on success */ + if (msg[0] == (IXGBE_VF_API_NEGOTIATE | IXGBE_VT_MSGTYPE_ACK)) { + hw->api_version = api; + return 0; + } + + err = IXGBE_ERR_INVALID_ARGUMENT; + } + + return err; +} + +/** + * ixgbevf_hv_negotiate_api_version_vf - Negotiate supported API version + * @hw: pointer to the HW structure + * @api: integer containing requested API version + * Hyper-V version - only ixgbe_mbox_api_10 supported. + **/ +static int ixgbevf_hv_negotiate_api_version_vf(struct ixgbe_hw *hw, int api) +{ + /* Hyper-V only supports api version ixgbe_mbox_api_10 */ + if (api != ixgbe_mbox_api_10) + return IXGBE_ERR_INVALID_ARGUMENT; + + return 0; +} + +int ixgbevf_get_queues(struct ixgbe_hw *hw, unsigned int *num_tcs, + unsigned int *default_tc) +{ + int err; + u32 msg[5]; + + /* do nothing if API doesn't support ixgbevf_get_queues */ + switch (hw->api_version) { + case ixgbe_mbox_api_11: + case ixgbe_mbox_api_12: + case ixgbe_mbox_api_13: + case ixgbe_mbox_api_14: + break; + default: + return 0; + } + + /* Fetch queue configuration from the PF */ + msg[0] = IXGBE_VF_GET_QUEUE; + msg[1] = msg[2] = msg[3] = msg[4] = 0; + + err = ixgbevf_write_msg_read_ack(hw, msg, msg, ARRAY_SIZE(msg)); + if (!err) { + msg[0] &= ~IXGBE_VT_MSGTYPE_CTS; + + /* if we we didn't get an ACK there must have been + * some sort of mailbox error so we should treat it + * as such + */ + if (msg[0] != (IXGBE_VF_GET_QUEUE | IXGBE_VT_MSGTYPE_ACK)) + return IXGBE_ERR_MBX; + + /* record and validate values from message */ + hw->mac.max_tx_queues = msg[IXGBE_VF_TX_QUEUES]; + if (hw->mac.max_tx_queues == 0 || + hw->mac.max_tx_queues > IXGBE_VF_MAX_TX_QUEUES) + hw->mac.max_tx_queues = IXGBE_VF_MAX_TX_QUEUES; + + hw->mac.max_rx_queues = msg[IXGBE_VF_RX_QUEUES]; + if (hw->mac.max_rx_queues == 0 || + hw->mac.max_rx_queues > IXGBE_VF_MAX_RX_QUEUES) + hw->mac.max_rx_queues = IXGBE_VF_MAX_RX_QUEUES; + + *num_tcs = msg[IXGBE_VF_TRANS_VLAN]; + /* in case of unknown state assume we cannot tag frames */ + if (*num_tcs > hw->mac.max_rx_queues) + *num_tcs = 1; + + *default_tc = msg[IXGBE_VF_DEF_QUEUE]; + /* default to queue 0 on out-of-bounds queue number */ + if (*default_tc >= hw->mac.max_tx_queues) + *default_tc = 0; + } + + return err; +} + +static const struct ixgbe_mac_operations ixgbevf_mac_ops = { + .init_hw = ixgbevf_init_hw_vf, + .reset_hw = ixgbevf_reset_hw_vf, + .start_hw = ixgbevf_start_hw_vf, + .get_mac_addr = ixgbevf_get_mac_addr_vf, + .stop_adapter = ixgbevf_stop_hw_vf, + .setup_link = ixgbevf_setup_mac_link_vf, + .check_link = ixgbevf_check_mac_link_vf, + .negotiate_api_version = ixgbevf_negotiate_api_version_vf, + .set_rar = ixgbevf_set_rar_vf, + .update_mc_addr_list = ixgbevf_update_mc_addr_list_vf, + .update_xcast_mode = ixgbevf_update_xcast_mode, + .set_uc_addr = ixgbevf_set_uc_addr_vf, + .set_vfta = ixgbevf_set_vfta_vf, + .set_rlpml = ixgbevf_set_rlpml_vf, +}; + +static const struct ixgbe_mac_operations ixgbevf_hv_mac_ops = { + .init_hw = ixgbevf_init_hw_vf, + .reset_hw = ixgbevf_hv_reset_hw_vf, + .start_hw = ixgbevf_start_hw_vf, + .get_mac_addr = ixgbevf_get_mac_addr_vf, + .stop_adapter = ixgbevf_stop_hw_vf, + .setup_link = ixgbevf_setup_mac_link_vf, + .check_link = ixgbevf_hv_check_mac_link_vf, + .negotiate_api_version = ixgbevf_hv_negotiate_api_version_vf, + .set_rar = ixgbevf_hv_set_rar_vf, + .update_mc_addr_list = ixgbevf_hv_update_mc_addr_list_vf, + .update_xcast_mode = ixgbevf_hv_update_xcast_mode, + .set_uc_addr = ixgbevf_hv_set_uc_addr_vf, + .set_vfta = ixgbevf_hv_set_vfta_vf, + .set_rlpml = ixgbevf_hv_set_rlpml_vf, +}; + +const struct ixgbevf_info ixgbevf_82599_vf_info = { + .mac = ixgbe_mac_82599_vf, + .mac_ops = &ixgbevf_mac_ops, +}; + +const struct ixgbevf_info ixgbevf_82599_vf_hv_info = { + .mac = ixgbe_mac_82599_vf, + .mac_ops = &ixgbevf_hv_mac_ops, +}; + +const struct ixgbevf_info ixgbevf_X540_vf_info = { + .mac = ixgbe_mac_X540_vf, + .mac_ops = &ixgbevf_mac_ops, +}; + +const struct ixgbevf_info ixgbevf_X540_vf_hv_info = { + .mac = ixgbe_mac_X540_vf, + .mac_ops = &ixgbevf_hv_mac_ops, +}; + +const struct ixgbevf_info ixgbevf_X550_vf_info = { + .mac = ixgbe_mac_X550_vf, + .mac_ops = &ixgbevf_mac_ops, +}; + +const struct ixgbevf_info ixgbevf_X550_vf_hv_info = { + .mac = ixgbe_mac_X550_vf, + .mac_ops = &ixgbevf_hv_mac_ops, +}; + +const struct ixgbevf_info ixgbevf_X550EM_x_vf_info = { + .mac = ixgbe_mac_X550EM_x_vf, + .mac_ops = &ixgbevf_mac_ops, +}; + +const struct ixgbevf_info ixgbevf_X550EM_x_vf_hv_info = { + .mac = ixgbe_mac_X550EM_x_vf, + .mac_ops = &ixgbevf_hv_mac_ops, +}; + +const struct ixgbevf_info ixgbevf_x550em_a_vf_info = { + .mac = ixgbe_mac_x550em_a_vf, + .mac_ops = &ixgbevf_mac_ops, +}; diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.h b/drivers/net/ethernet/intel/ixgbevf/vf.h new file mode 100644 index 000000000..d1e9e3066 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbevf/vf.h @@ -0,0 +1,194 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + +#ifndef __IXGBE_VF_H__ +#define __IXGBE_VF_H__ + +#include <linux/pci.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/if_ether.h> +#include <linux/netdevice.h> + +#include "defines.h" +#include "regs.h" +#include "mbx.h" + +struct ixgbe_hw; + +/* iterator type for walking multicast address lists */ +typedef u8* (*ixgbe_mc_addr_itr) (struct ixgbe_hw *hw, u8 **mc_addr_ptr, + u32 *vmdq); +struct ixgbe_mac_operations { + s32 (*init_hw)(struct ixgbe_hw *); + s32 (*reset_hw)(struct ixgbe_hw *); + s32 (*start_hw)(struct ixgbe_hw *); + s32 (*clear_hw_cntrs)(struct ixgbe_hw *); + enum ixgbe_media_type (*get_media_type)(struct ixgbe_hw *); + s32 (*get_mac_addr)(struct ixgbe_hw *, u8 *); + s32 (*stop_adapter)(struct ixgbe_hw *); + s32 (*get_bus_info)(struct ixgbe_hw *); + s32 (*negotiate_api_version)(struct ixgbe_hw *hw, int api); + + /* Link */ + s32 (*setup_link)(struct ixgbe_hw *, ixgbe_link_speed, bool, bool); + s32 (*check_link)(struct ixgbe_hw *, ixgbe_link_speed *, bool *, bool); + s32 (*get_link_capabilities)(struct ixgbe_hw *, ixgbe_link_speed *, + bool *); + + /* RAR, Multicast, VLAN */ + s32 (*set_rar)(struct ixgbe_hw *, u32, u8 *, u32); + s32 (*set_uc_addr)(struct ixgbe_hw *, u32, u8 *); + s32 (*init_rx_addrs)(struct ixgbe_hw *); + s32 (*update_mc_addr_list)(struct ixgbe_hw *, struct net_device *); + s32 (*update_xcast_mode)(struct ixgbe_hw *, int); + s32 (*enable_mc)(struct ixgbe_hw *); + s32 (*disable_mc)(struct ixgbe_hw *); + s32 (*clear_vfta)(struct ixgbe_hw *); + s32 (*set_vfta)(struct ixgbe_hw *, u32, u32, bool); + s32 (*set_rlpml)(struct ixgbe_hw *, u16); +}; + +enum ixgbe_mac_type { + ixgbe_mac_unknown = 0, + ixgbe_mac_82599_vf, + ixgbe_mac_X540_vf, + ixgbe_mac_X550_vf, + ixgbe_mac_X550EM_x_vf, + ixgbe_mac_x550em_a_vf, + ixgbe_num_macs +}; + +struct ixgbe_mac_info { + struct ixgbe_mac_operations ops; + u8 addr[6]; + u8 perm_addr[6]; + + enum ixgbe_mac_type type; + + s32 mc_filter_type; + + bool get_link_status; + u32 max_tx_queues; + u32 max_rx_queues; + u32 max_msix_vectors; +}; + +struct ixgbe_mbx_operations { + s32 (*init_params)(struct ixgbe_hw *hw); + s32 (*read)(struct ixgbe_hw *, u32 *, u16); + s32 (*write)(struct ixgbe_hw *, u32 *, u16); + s32 (*read_posted)(struct ixgbe_hw *, u32 *, u16); + s32 (*write_posted)(struct ixgbe_hw *, u32 *, u16); + s32 (*check_for_msg)(struct ixgbe_hw *); + s32 (*check_for_ack)(struct ixgbe_hw *); + s32 (*check_for_rst)(struct ixgbe_hw *); +}; + +struct ixgbe_mbx_stats { + u32 msgs_tx; + u32 msgs_rx; + + u32 acks; + u32 reqs; + u32 rsts; +}; + +struct ixgbe_mbx_info { + struct ixgbe_mbx_operations ops; + struct ixgbe_mbx_stats stats; + u32 timeout; + u32 udelay; + u32 v2p_mailbox; + u16 size; +}; + +struct ixgbe_hw { + void *back; + + u8 __iomem *hw_addr; + + struct ixgbe_mac_info mac; + struct ixgbe_mbx_info mbx; + + u16 device_id; + u16 subsystem_vendor_id; + u16 subsystem_device_id; + u16 vendor_id; + + u8 revision_id; + bool adapter_stopped; + + int api_version; +}; + +struct ixgbevf_hw_stats { + u64 base_vfgprc; + u64 base_vfgptc; + u64 base_vfgorc; + u64 base_vfgotc; + u64 base_vfmprc; + + u64 last_vfgprc; + u64 last_vfgptc; + u64 last_vfgorc; + u64 last_vfgotc; + u64 last_vfmprc; + + u64 vfgprc; + u64 vfgptc; + u64 vfgorc; + u64 vfgotc; + u64 vfmprc; + + u64 saved_reset_vfgprc; + u64 saved_reset_vfgptc; + u64 saved_reset_vfgorc; + u64 saved_reset_vfgotc; + u64 saved_reset_vfmprc; +}; + +struct ixgbevf_info { + enum ixgbe_mac_type mac; + const struct ixgbe_mac_operations *mac_ops; +}; + +#define IXGBE_FAILED_READ_REG 0xffffffffU + +#define IXGBE_REMOVED(a) unlikely(!(a)) + +static inline void ixgbe_write_reg(struct ixgbe_hw *hw, u32 reg, u32 value) +{ + u8 __iomem *reg_addr = READ_ONCE(hw->hw_addr); + + if (IXGBE_REMOVED(reg_addr)) + return; + writel(value, reg_addr + reg); +} + +#define IXGBE_WRITE_REG(h, r, v) ixgbe_write_reg(h, r, v) + +u32 ixgbevf_read_reg(struct ixgbe_hw *hw, u32 reg); +#define IXGBE_READ_REG(h, r) ixgbevf_read_reg(h, r) + +static inline void ixgbe_write_reg_array(struct ixgbe_hw *hw, u32 reg, + u32 offset, u32 value) +{ + ixgbe_write_reg(hw, reg + (offset << 2), value); +} + +#define IXGBE_WRITE_REG_ARRAY(h, r, o, v) ixgbe_write_reg_array(h, r, o, v) + +static inline u32 ixgbe_read_reg_array(struct ixgbe_hw *hw, u32 reg, + u32 offset) +{ + return ixgbevf_read_reg(hw, reg + (offset << 2)); +} + +#define IXGBE_READ_REG_ARRAY(h, r, o) ixgbe_read_reg_array(h, r, o) + +int ixgbevf_get_queues(struct ixgbe_hw *hw, unsigned int *num_tcs, + unsigned int *default_tc); +int ixgbevf_get_reta_locked(struct ixgbe_hw *hw, u32 *reta, int num_rx_queues); +int ixgbevf_get_rss_key_locked(struct ixgbe_hw *hw, u8 *rss_key); +#endif /* __IXGBE_VF_H__ */ |