diff options
Diffstat (limited to 'drivers/net/ethernet/intel/ixgbe')
25 files changed, 28510 insertions, 0 deletions
diff --git a/drivers/net/ethernet/intel/ixgbe/Makefile b/drivers/net/ethernet/intel/ixgbe/Makefile new file mode 100644 index 000000000000..7d7387fbdecd --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/Makefile @@ -0,0 +1,42 @@ +################################################################################ +# +# Intel 10 Gigabit PCI Express Linux driver +# Copyright(c) 1999 - 2010 Intel Corporation. +# +# This program is free software; you can redistribute it and/or modify it +# under the terms and conditions of the GNU General Public License, +# version 2, as published by the Free Software Foundation. +# +# This program is distributed in the hope it will be useful, but WITHOUT +# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or +# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for +# more details. +# +# You should have received a copy of the GNU General Public License along with +# this program; if not, write to the Free Software Foundation, Inc., +# 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. +# +# The full GNU General Public License is included in this distribution in +# the file called "COPYING". +# +# Contact Information: +# Linux NICS <linux.nics@intel.com> +# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> +# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 +# +################################################################################ + +# +# Makefile for the Intel(R) 10GbE PCI Express ethernet driver +# + +obj-$(CONFIG_IXGBE) += ixgbe.o + +ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \ + ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \ + ixgbe_mbx.o ixgbe_x540.o + +ixgbe-$(CONFIG_IXGBE_DCB) += ixgbe_dcb.o ixgbe_dcb_82598.o \ + ixgbe_dcb_82599.o ixgbe_dcb_nl.o + +ixgbe-$(CONFIG_FCOE:m=y) += ixgbe_fcoe.o diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h new file mode 100644 index 000000000000..e04a8e49e6dc --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -0,0 +1,617 @@ +/******************************************************************************* + + Intel 10 Gigabit PCI Express Linux driver + Copyright(c) 1999 - 2011 Intel Corporation. + + This program is free software; you can redistribute it and/or modify it + under the terms and conditions of the GNU General Public License, + version 2, as published by the Free Software Foundation. + + This program is distributed in the hope it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + more details. + + You should have received a copy of the GNU General Public License along with + this program; if not, write to the Free Software Foundation, Inc., + 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + + The full GNU General Public License is included in this distribution in + the file called "COPYING". + + Contact Information: + e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + +*******************************************************************************/ + +#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 "ixgbe_type.h" +#include "ixgbe_common.h" +#include "ixgbe_dcb.h" +#if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) +#define IXGBE_FCOE +#include "ixgbe_fcoe.h" +#endif /* CONFIG_FCOE or CONFIG_FCOE_MODULE */ +#ifdef CONFIG_IXGBE_DCA +#include <linux/dca.h> +#endif + +/* 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_MAX_TXD 4096 +#define IXGBE_MIN_TXD 64 + +#define IXGBE_DEFAULT_RXD 512 +#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_512 512 /* Used for packet split */ +#define IXGBE_RXBUFFER_2048 2048 +#define IXGBE_RXBUFFER_4096 4096 +#define IXGBE_RXBUFFER_8192 8192 +#define IXGBE_MAX_RXBUFFER 16384 /* largest size for a single descriptor */ + +/* + * NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN mans we + * reserve 2 more, and skb_shared_info adds an additional 384 bytes more, + * this adds up to 512 bytes of extra data meaning the smallest allocation + * we could have is 1K. + * i.e. RXBUFFER_512 --> size-1024 slab + */ +#define IXGBE_RX_HDR_SIZE IXGBE_RXBUFFER_512 + +#define MAXIMUM_ETHERNET_VLAN_SIZE (ETH_FRAME_LEN + ETH_FCS_LEN + VLAN_HLEN) + +/* 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_TX_FLAGS_CSUM (u32)(1) +#define IXGBE_TX_FLAGS_VLAN (u32)(1 << 1) +#define IXGBE_TX_FLAGS_TSO (u32)(1 << 2) +#define IXGBE_TX_FLAGS_IPV4 (u32)(1 << 3) +#define IXGBE_TX_FLAGS_FCOE (u32)(1 << 4) +#define IXGBE_TX_FLAGS_FSO (u32)(1 << 5) +#define IXGBE_TX_FLAGS_VLAN_MASK 0xffff0000 +#define IXGBE_TX_FLAGS_VLAN_PRIO_MASK 0x0000e000 +#define IXGBE_TX_FLAGS_VLAN_SHIFT 16 + +#define IXGBE_MAX_RSC_INT_RATE 162760 + +#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->num_vfs) + +struct vf_data_storage { + unsigned char vf_mac_addresses[ETH_ALEN]; + u16 vf_mc_hashes[IXGBE_MAX_VF_MC_ENTRIES]; + u16 num_vf_mc_hashes; + u16 default_vf_vlan_id; + u16 vlans_enabled; + bool clear_to_send; + bool pf_set_mac; + u16 pf_vlan; /* When set, guest VLAN config not allowed. */ + u16 pf_qos; + u16 tx_rate; +}; + +struct vf_macvlans { + struct list_head l; + int vf; + int rar_entry; + bool free; + bool is_macvlan; + u8 vf_macvlan[ETH_ALEN]; +}; + +#define IXGBE_MAX_TXD_PWR 14 +#define IXGBE_MAX_DATA_PER_TXD (1 << 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 * TXD_USE_COUNT(PAGE_SIZE)) + 4) + +/* wrapper around a pointer to a socket buffer, + * so a DMA handle can be stored along with the buffer */ +struct ixgbe_tx_buffer { + struct sk_buff *skb; + dma_addr_t dma; + unsigned long time_stamp; + u16 length; + u16 next_to_watch; + unsigned int bytecount; + u16 gso_segs; + u8 mapped_as_page; +}; + +struct ixgbe_rx_buffer { + struct sk_buff *skb; + dma_addr_t dma; + struct page *page; + dma_addr_t page_dma; + unsigned int page_offset; +}; + +struct ixgbe_queue_stats { + u64 packets; + u64 bytes; +}; + +struct ixgbe_tx_queue_stats { + u64 restart_queue; + u64 tx_busy; + u64 completed; + u64 tx_done_old; +}; + +struct ixgbe_rx_queue_stats { + u64 rsc_count; + u64 rsc_flush; + u64 non_eop_descs; + u64 alloc_rx_page_failed; + u64 alloc_rx_buff_failed; +}; + +enum ixbge_ring_state_t { + __IXGBE_TX_FDIR_INIT_DONE, + __IXGBE_TX_DETECT_HANG, + __IXGBE_HANG_CHECK_ARMED, + __IXGBE_RX_PS_ENABLED, + __IXGBE_RX_RSC_ENABLED, +}; + +#define ring_is_ps_enabled(ring) \ + test_bit(__IXGBE_RX_PS_ENABLED, &(ring)->state) +#define set_ring_ps_enabled(ring) \ + set_bit(__IXGBE_RX_PS_ENABLED, &(ring)->state) +#define clear_ring_ps_enabled(ring) \ + clear_bit(__IXGBE_RX_PS_ENABLED, &(ring)->state) +#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) +struct ixgbe_ring { + void *desc; /* descriptor ring memory */ + struct device *dev; /* device for DMA mapping */ + struct net_device *netdev; /* netdev ring belongs to */ + union { + struct ixgbe_tx_buffer *tx_buffer_info; + struct ixgbe_rx_buffer *rx_buffer_info; + }; + unsigned long state; + u8 __iomem *tail; + + u16 count; /* amount of descriptors */ + u16 rx_buf_len; + + 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 + */ + u8 atr_sample_rate; + u8 atr_count; + + u16 next_to_use; + u16 next_to_clean; + + 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; + }; + int numa_node; + unsigned int size; /* length in bytes */ + dma_addr_t dma; /* phys. address of descriptor ring */ + struct rcu_head rcu; + struct ixgbe_q_vector *q_vector; /* back-pointer to host q_vector */ +} ____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_VMDQ_INDICES 64 +#define IXGBE_MAX_FDIR_INDICES 64 +#ifdef IXGBE_FCOE +#define IXGBE_MAX_FCOE_INDICES 8 +#define MAX_RX_QUEUES (IXGBE_MAX_FDIR_INDICES + IXGBE_MAX_FCOE_INDICES) +#define MAX_TX_QUEUES (IXGBE_MAX_FDIR_INDICES + IXGBE_MAX_FCOE_INDICES) +#else +#define MAX_RX_QUEUES IXGBE_MAX_FDIR_INDICES +#define MAX_TX_QUEUES IXGBE_MAX_FDIR_INDICES +#endif /* IXGBE_FCOE */ +struct ixgbe_ring_feature { + int indices; + int mask; +} ____cacheline_internodealigned_in_smp; + +struct ixgbe_ring_container { +#if MAX_RX_QUEUES > MAX_TX_QUEUES + DECLARE_BITMAP(idx, MAX_RX_QUEUES); +#else + DECLARE_BITMAP(idx, MAX_TX_QUEUES); +#endif + 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 */ +}; + +#define MAX_RX_PACKET_BUFFERS ((adapter->flags & IXGBE_FLAG_DCB_ENABLED) \ + ? 8 : 1) +#define MAX_TX_PACKET_BUFFERS MAX_RX_PACKET_BUFFERS + +/* MAX_MSIX_Q_VECTORS of these are allocated, + * but we only use one per queue-specific vector. + */ +struct ixgbe_q_vector { + struct ixgbe_adapter *adapter; + unsigned int 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 */ +#ifdef CONFIG_IXGBE_DCA + int cpu; /* CPU for DCA */ +#endif + struct napi_struct napi; + struct ixgbe_ring_container rx, tx; + u32 eitr; + cpumask_var_t affinity_mask; + char name[IFNAMSIZ + 9]; +}; + +/* 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 + +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_ADV(R, i) \ + (&(((union ixgbe_adv_rx_desc *)((R)->desc))[i])) +#define IXGBE_TX_DESC_ADV(R, i) \ + (&(((union ixgbe_adv_tx_desc *)((R)->desc))[i])) +#define IXGBE_TX_CTXTDESC_ADV(R, i) \ + (&(((struct ixgbe_adv_tx_context_desc *)((R)->desc))[i])) + +#define IXGBE_MAX_JUMBO_FRAME_SIZE 16128 +#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_MSIX_Q_VECTORS_82599 64 +#define MAX_MSIX_VECTORS_82598 18 +#define MAX_MSIX_Q_VECTORS_82598 16 + +#define MAX_MSIX_Q_VECTORS MAX_MSIX_Q_VECTORS_82599 +#define MAX_MSIX_COUNT MAX_MSIX_VECTORS_82599 + +#define MIN_MSIX_Q_VECTORS 2 +#define MIN_MSIX_COUNT (MIN_MSIX_Q_VECTORS + NON_Q_VECTORS) + +/* board specific private data structure */ +struct ixgbe_adapter { + unsigned long state; + + /* Some features need tri-state capability, + * thus the additional *_CAPABLE flags. + */ + u32 flags; +#define IXGBE_FLAG_RX_CSUM_ENABLED (u32)(1) +#define IXGBE_FLAG_MSI_CAPABLE (u32)(1 << 1) +#define IXGBE_FLAG_MSI_ENABLED (u32)(1 << 2) +#define IXGBE_FLAG_MSIX_CAPABLE (u32)(1 << 3) +#define IXGBE_FLAG_MSIX_ENABLED (u32)(1 << 4) +#define IXGBE_FLAG_RX_1BUF_CAPABLE (u32)(1 << 6) +#define IXGBE_FLAG_RX_PS_CAPABLE (u32)(1 << 7) +#define IXGBE_FLAG_RX_PS_ENABLED (u32)(1 << 8) +#define IXGBE_FLAG_IN_NETPOLL (u32)(1 << 9) +#define IXGBE_FLAG_DCA_ENABLED (u32)(1 << 10) +#define IXGBE_FLAG_DCA_CAPABLE (u32)(1 << 11) +#define IXGBE_FLAG_IMIR_ENABLED (u32)(1 << 12) +#define IXGBE_FLAG_MQ_CAPABLE (u32)(1 << 13) +#define IXGBE_FLAG_DCB_ENABLED (u32)(1 << 14) +#define IXGBE_FLAG_RSS_ENABLED (u32)(1 << 16) +#define IXGBE_FLAG_RSS_CAPABLE (u32)(1 << 17) +#define IXGBE_FLAG_VMDQ_CAPABLE (u32)(1 << 18) +#define IXGBE_FLAG_VMDQ_ENABLED (u32)(1 << 19) +#define IXGBE_FLAG_FAN_FAIL_CAPABLE (u32)(1 << 20) +#define IXGBE_FLAG_NEED_LINK_UPDATE (u32)(1 << 22) +#define IXGBE_FLAG_NEED_LINK_CONFIG (u32)(1 << 23) +#define IXGBE_FLAG_FDIR_HASH_CAPABLE (u32)(1 << 24) +#define IXGBE_FLAG_FDIR_PERFECT_CAPABLE (u32)(1 << 25) +#define IXGBE_FLAG_FCOE_CAPABLE (u32)(1 << 26) +#define IXGBE_FLAG_FCOE_ENABLED (u32)(1 << 27) +#define IXGBE_FLAG_SRIOV_CAPABLE (u32)(1 << 28) +#define IXGBE_FLAG_SRIOV_ENABLED (u32)(1 << 29) + + u32 flags2; +#define IXGBE_FLAG2_RSC_CAPABLE (u32)(1) +#define IXGBE_FLAG2_RSC_ENABLED (u32)(1 << 1) +#define IXGBE_FLAG2_TEMP_SENSOR_CAPABLE (u32)(1 << 2) +#define IXGBE_FLAG2_TEMP_SENSOR_EVENT (u32)(1 << 3) +#define IXGBE_FLAG2_SEARCH_FOR_SFP (u32)(1 << 4) +#define IXGBE_FLAG2_SFP_NEEDS_RESET (u32)(1 << 5) +#define IXGBE_FLAG2_RESET_REQUESTED (u32)(1 << 6) +#define IXGBE_FLAG2_FDIR_REQUIRES_REINIT (u32)(1 << 7) + + unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + u16 bd_number; + struct ixgbe_q_vector *q_vector[MAX_MSIX_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 dcb_set_bitmap; + u8 dcbx_cap; + enum ixgbe_fc_mode last_lfc_mode; + + /* Interrupt Throttle Rate */ + u32 rx_itr_setting; + u32 tx_itr_setting; + u16 eitr_low; + u16 eitr_high; + + /* Work limits */ + u16 tx_work_limit; + + /* TX */ + struct ixgbe_ring *tx_ring[MAX_TX_QUEUES] ____cacheline_aligned_in_smp; + int num_tx_queues; + u32 tx_timeout_count; + bool detect_tx_hung; + + u64 restart_queue; + u64 lsc_int; + + /* RX */ + struct ixgbe_ring *rx_ring[MAX_RX_QUEUES] ____cacheline_aligned_in_smp; + int num_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 non_eop_descs; + int num_msix_vectors; + int max_msix_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 alloc_rx_page_failed; + u32 alloc_rx_buff_failed; + +/* default to trying for four seconds */ +#define IXGBE_TRY_LINK_TIMEOUT (4 * HZ) + + /* OS defined structs */ + struct net_device *netdev; + struct pci_dev *pdev; + + 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; + + /* Interrupt Throttle Rate */ + u32 rx_eitr_param; + u32 tx_eitr_param; + + u64 tx_busy; + unsigned int tx_ring_count; + unsigned int rx_ring_count; + + u32 link_speed; + bool link_up; + unsigned long link_check_timeout; + + struct work_struct service_task; + struct timer_list service_timer; + u32 fdir_pballoc; + u32 atr_sample_rate; + unsigned long fdir_overflow; /* number of times ATR was backed off */ + spinlock_t fdir_perfect_lock; +#ifdef IXGBE_FCOE + struct ixgbe_fcoe fcoe; +#endif /* IXGBE_FCOE */ + u64 rsc_total_count; + u64 rsc_total_flush; + u32 wol; + u16 eeprom_version; + + int node; + u32 led_reg; + u32 interrupt_event; + char lsc_int_name[IFNAMSIZ + 9]; + + /* 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; + bool antispoofing_enabled; + + struct hlist_head fdir_filter_list; + union ixgbe_atr_input fdir_mask; + int fdir_filter_count; +}; + +struct ixgbe_fdir_filter { + struct hlist_node fdir_node; + union ixgbe_atr_input filter; + u16 sw_idx; + u16 action; +}; + +enum ixbge_state_t { + __IXGBE_TESTING, + __IXGBE_RESETTING, + __IXGBE_DOWN, + __IXGBE_SERVICE_SCHED, + __IXGBE_IN_SFP_INIT, +}; + +struct ixgbe_rsc_cb { + dma_addr_t dma; + u16 skb_cnt; + bool delay_unmap; +}; +#define IXGBE_RSC_CB(skb) ((struct ixgbe_rsc_cb *)(skb)->cb) + +enum ixgbe_boards { + board_82598, + board_82599, + board_X540, +}; + +extern struct ixgbe_info ixgbe_82598_info; +extern struct ixgbe_info ixgbe_82599_info; +extern struct ixgbe_info ixgbe_X540_info; +#ifdef CONFIG_IXGBE_DCB +extern const struct dcbnl_rtnl_ops dcbnl_ops; +extern int ixgbe_copy_dcb_cfg(struct ixgbe_dcb_config *src_dcb_cfg, + struct ixgbe_dcb_config *dst_dcb_cfg, + int tc_max); +#endif + +extern char ixgbe_driver_name[]; +extern const char ixgbe_driver_version[]; + +extern int ixgbe_up(struct ixgbe_adapter *adapter); +extern void ixgbe_down(struct ixgbe_adapter *adapter); +extern void ixgbe_reinit_locked(struct ixgbe_adapter *adapter); +extern void ixgbe_reset(struct ixgbe_adapter *adapter); +extern void ixgbe_set_ethtool_ops(struct net_device *netdev); +extern int ixgbe_setup_rx_resources(struct ixgbe_ring *); +extern int ixgbe_setup_tx_resources(struct ixgbe_ring *); +extern void ixgbe_free_rx_resources(struct ixgbe_ring *); +extern void ixgbe_free_tx_resources(struct ixgbe_ring *); +extern void ixgbe_configure_rx_ring(struct ixgbe_adapter *,struct ixgbe_ring *); +extern void ixgbe_configure_tx_ring(struct ixgbe_adapter *,struct ixgbe_ring *); +extern void ixgbe_disable_rx_queue(struct ixgbe_adapter *adapter, + struct ixgbe_ring *); +extern void ixgbe_update_stats(struct ixgbe_adapter *adapter); +extern int ixgbe_init_interrupt_scheme(struct ixgbe_adapter *adapter); +extern void ixgbe_clear_interrupt_scheme(struct ixgbe_adapter *adapter); +extern netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *, + struct ixgbe_adapter *, + struct ixgbe_ring *); +extern void ixgbe_unmap_and_free_tx_resource(struct ixgbe_ring *, + struct ixgbe_tx_buffer *); +extern void ixgbe_alloc_rx_buffers(struct ixgbe_ring *, u16); +extern void ixgbe_write_eitr(struct ixgbe_q_vector *); +extern int ethtool_ioctl(struct ifreq *ifr); +extern s32 ixgbe_reinit_fdir_tables_82599(struct ixgbe_hw *hw); +extern s32 ixgbe_init_fdir_signature_82599(struct ixgbe_hw *hw, u32 fdirctrl); +extern s32 ixgbe_init_fdir_perfect_82599(struct ixgbe_hw *hw, u32 fdirctrl); +extern 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); +extern s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, + union ixgbe_atr_input *input_mask); +extern s32 ixgbe_fdir_write_perfect_filter_82599(struct ixgbe_hw *hw, + union ixgbe_atr_input *input, + u16 soft_id, u8 queue); +extern s32 ixgbe_fdir_erase_perfect_filter_82599(struct ixgbe_hw *hw, + union ixgbe_atr_input *input, + u16 soft_id); +extern void ixgbe_atr_compute_perfect_hash_82599(union ixgbe_atr_input *input, + union ixgbe_atr_input *mask); +extern void ixgbe_set_rx_mode(struct net_device *netdev); +extern int ixgbe_setup_tc(struct net_device *dev, u8 tc); +extern void ixgbe_tx_ctxtdesc(struct ixgbe_ring *, u32, u32, u32, u32); +extern void ixgbe_do_reset(struct net_device *netdev); +#ifdef IXGBE_FCOE +extern void ixgbe_configure_fcoe(struct ixgbe_adapter *adapter); +extern int ixgbe_fso(struct ixgbe_ring *tx_ring, struct sk_buff *skb, + u32 tx_flags, u8 *hdr_len); +extern void ixgbe_cleanup_fcoe(struct ixgbe_adapter *adapter); +extern int ixgbe_fcoe_ddp(struct ixgbe_adapter *adapter, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb, + u32 staterr); +extern int ixgbe_fcoe_ddp_get(struct net_device *netdev, u16 xid, + struct scatterlist *sgl, unsigned int sgc); +extern int ixgbe_fcoe_ddp_target(struct net_device *netdev, u16 xid, + struct scatterlist *sgl, unsigned int sgc); +extern int ixgbe_fcoe_ddp_put(struct net_device *netdev, u16 xid); +extern int ixgbe_fcoe_enable(struct net_device *netdev); +extern int ixgbe_fcoe_disable(struct net_device *netdev); +#ifdef CONFIG_IXGBE_DCB +extern u8 ixgbe_fcoe_getapp(struct ixgbe_adapter *adapter); +extern u8 ixgbe_fcoe_setapp(struct ixgbe_adapter *adapter, u8 up); +#endif /* CONFIG_IXGBE_DCB */ +extern int ixgbe_fcoe_get_wwn(struct net_device *netdev, u64 *wwn, int type); +#endif /* IXGBE_FCOE */ + +#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 000000000000..0d4e38264492 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c @@ -0,0 +1,1353 @@ +/******************************************************************************* + + Intel 10 Gigabit PCI Express Linux driver + Copyright(c) 1999 - 2011 Intel Corporation. + + This program is free software; you can redistribute it and/or modify it + under the terms and conditions of the GNU General Public License, + version 2, as published by the Free Software Foundation. + + This program is distributed in the hope it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + more details. + + You should have received a copy of the GNU General Public License along with + this program; if not, write to the Free Software Foundation, Inc., + 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + + The full GNU General Public License is included in this distribution in + the file called "COPYING". + + Contact Information: + e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + +*******************************************************************************/ + +#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, + 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) +{ + struct ixgbe_adapter *adapter = hw->back; + u32 gcr = IXGBE_READ_REG(hw, IXGBE_GCR); + u16 pcie_devctl2; + + /* 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 + */ + pci_read_config_word(adapter->pdev, + IXGBE_PCI_DEVICE_CONTROL2, &pcie_devctl2); + pcie_devctl2 |= IXGBE_PCI_DEVICE_CONTROL2_16ms; + pci_write_config_word(adapter->pdev, + IXGBE_PCI_DEVICE_CONTROL2, pcie_devctl2); +out: + /* disable completion timeout resend */ + gcr &= ~IXGBE_GCR_CMPL_TMOUT_RESEND; + IXGBE_WRITE_REG(hw, IXGBE_GCR, gcr); +} + +/** + * ixgbe_get_pcie_msix_count_82598 - 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. + **/ +static u16 ixgbe_get_pcie_msix_count_82598(struct ixgbe_hw *hw) +{ + struct ixgbe_adapter *adapter = hw->back; + u16 msix_count; + pci_read_config_word(adapter->pdev, IXGBE_PCIE_MSIX_82598_CAPS, + &msix_count); + msix_count &= IXGBE_PCIE_MSIX_TBL_SZ_MASK; + + /* MSI-X count is zero-based in HW, so increment to give proper value */ + msix_count++; + + return msix_count; +} + +/** + */ +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->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_82598(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 = 0; + 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; + phy->ops.get_firmware_version = + &ixgbe_get_phy_firmware_version_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 != 0) + goto out; + else if (hw->phy.sfp_type == ixgbe_sfp_type_unknown) { + ret_val = IXGBE_ERR_SFP_NOT_SUPPORTED; + goto out; + } + + /* Check to see if SFP+ module is supported */ + ret_val = ixgbe_get_sfp_init_sequence_offsets(hw, + &list_offset, + &data_offset); + if (ret_val != 0) { + ret_val = IXGBE_ERR_SFP_NOT_SUPPORTED; + goto out; + } + break; + default: + break; + } + +out: + return ret_val; +} + +/** + * 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 Then set pcie completion timeout + * + **/ +static s32 ixgbe_start_hw_82598(struct ixgbe_hw *hw) +{ + u32 regval; + u32 i; + s32 ret_val = 0; + + ret_val = ixgbe_start_hw_generic(hw); + + /* Disable relaxed ordering */ + for (i = 0; ((i < hw->mac.max_tx_queues) && + (i < IXGBE_DCA_MAX_QUEUES_82598)); i++) { + regval = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL(i)); + regval &= ~IXGBE_DCA_TXCTRL_TX_WB_RO_EN; + IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL(i), regval); + } + + for (i = 0; ((i < hw->mac.max_rx_queues) && + (i < IXGBE_DCA_MAX_QUEUES_82598)); i++) { + regval = IXGBE_READ_REG(hw, IXGBE_DCA_RXCTRL(i)); + regval &= ~(IXGBE_DCA_RXCTRL_DESC_WRO_EN | + IXGBE_DCA_RXCTRL_DESC_HSRO_EN); + IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(i), regval); + } + + hw->mac.rx_pb_size = IXGBE_82598_RX_PB_SIZE; + + /* set the completion timeout for interface */ + if (ret_val == 0) + ixgbe_set_pcie_completion_timeout(hw); + + return ret_val; +} + +/** + * 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) +{ + s32 status = 0; + 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: + status = IXGBE_ERR_LINK_SETUP; + break; + } + + return status; +} + +/** + * 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) +{ + enum ixgbe_media_type media_type; + + /* Detect if there is a copper PHY attached. */ + switch (hw->phy.type) { + case ixgbe_phy_cu_unknown: + case ixgbe_phy_tn: + case ixgbe_phy_aq: + media_type = ixgbe_media_type_copper; + goto out; + 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 */ + media_type = ixgbe_media_type_backplane; + break; + 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: + media_type = ixgbe_media_type_fiber; + break; + case IXGBE_DEV_ID_82598EB_CX4: + case IXGBE_DEV_ID_82598_CX4_DUAL_PORT: + media_type = ixgbe_media_type_cx4; + break; + case IXGBE_DEV_ID_82598AT: + case IXGBE_DEV_ID_82598AT2: + media_type = ixgbe_media_type_copper; + break; + default: + media_type = ixgbe_media_type_unknown; + break; + } +out: + return media_type; +} + +/** + * ixgbe_fc_enable_82598 - Enable flow control + * @hw: pointer to hardware structure + * @packetbuf_num: packet buffer number (0-7) + * + * Enable flow control according to the current settings. + **/ +static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw, s32 packetbuf_num) +{ + s32 ret_val = 0; + u32 fctrl_reg; + u32 rmcs_reg; + u32 reg; + u32 rx_pba_size; + u32 link_speed = 0; + bool link_up; + +#ifdef CONFIG_DCB + if (hw->fc.requested_mode == ixgbe_fc_pfc) + goto out; + +#endif /* CONFIG_DCB */ + /* + * 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 */ + ret_val = ixgbe_fc_autoneg(hw); + if (ret_val == IXGBE_ERR_FLOW_CONTROL) + goto out; + + /* 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. +#ifdef CONFIG_DCB + * 4: Priority Flow Control is enabled. +#endif + * 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; +#ifdef CONFIG_DCB + case ixgbe_fc_pfc: + goto out; + break; +#endif /* CONFIG_DCB */ + default: + hw_dbg(hw, "Flow control param set incorrectly\n"); + ret_val = IXGBE_ERR_CONFIG; + goto out; + break; + } + + /* 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. */ + if (hw->fc.current_mode & ixgbe_fc_tx_pause) { + rx_pba_size = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(packetbuf_num)); + rx_pba_size >>= IXGBE_RXPBSIZE_SHIFT; + + reg = (rx_pba_size - hw->fc.low_water) << 6; + if (hw->fc.send_xon) + reg |= IXGBE_FCRTL_XONE; + + IXGBE_WRITE_REG(hw, IXGBE_FCRTL(packetbuf_num), reg); + + reg = (rx_pba_size - hw->fc.high_water) << 6; + reg |= IXGBE_FCRTH_FCEN; + + IXGBE_WRITE_REG(hw, IXGBE_FCRTH(packetbuf_num), reg); + } + + /* Configure pause time (2 TCs per register) */ + reg = IXGBE_READ_REG(hw, IXGBE_FCTTV(packetbuf_num / 2)); + if ((packetbuf_num & 1) == 0) + reg = (reg & 0xFFFF0000) | hw->fc.pause_time; + else + reg = (reg & 0x0000FFFF) | (hw->fc.pause_time << 16); + IXGBE_WRITE_REG(hw, IXGBE_FCTTV(packetbuf_num / 2), reg); + + IXGBE_WRITE_REG(hw, IXGBE_FCRTV, (hw->fc.pause_time >> 1)); + +out: + return ret_val; +} + +/** + * ixgbe_start_mac_link_82598 - Configures MAC link settings + * @hw: pointer to hardware structure + * + * 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 == false) + goto out; + } + + 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 == true) && + (ixgbe_validate_link_ready(hw) != 0)) + *link_up = false; + + /* if link is down, zero out the current_mode */ + if (*link_up == false) { + hw->fc.current_mode = ixgbe_fc_none; + hw->fc.fc_was_autonegged = false; + } +out: + return 0; +} + +/** + * ixgbe_setup_mac_link_82598 - Set MAC link speed + * @hw: pointer to hardware structure + * @speed: new link speed + * @autoneg: true if auto-negotiation enabled + * @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, + bool autoneg_wait_to_complete) +{ + s32 status = 0; + 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) + status = 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); + } + + if (status == 0) { + /* + * 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 + */ + status = ixgbe_start_mac_link_82598(hw, + autoneg_wait_to_complete); + } + + return status; +} + + +/** + * ixgbe_setup_copper_link_82598 - Set the PHY autoneg advertised field + * @hw: pointer to hardware structure + * @speed: new link speed + * @autoneg: true if autonegotiation enabled + * @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, + bool autoneg_wait_to_complete) +{ + s32 status; + + /* Setup the PHY according to input speed */ + status = hw->phy.ops.setup_link_speed(hw, speed, autoneg, + 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 = 0; + 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 */ + hw->mac.ops.stop_adapter(hw); + + /* + * 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) + goto reset_hw_out; + else if (phy_status == IXGBE_ERR_SFP_NOT_PRESENT) + goto no_phy_reset; + + hw->phy.ops.reset(hw); + } + +no_phy_reset: + /* + * Prevent the PCI-E bus from from hanging by disabling PCI-E master + * access and verify no pending requests before reset + */ + ixgbe_disable_pcie_master(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_WRITE_REG(hw, IXGBE_CTRL, (ctrl | IXGBE_CTRL_RST)); + IXGBE_WRITE_FLUSH(hw); + + /* Poll for reset bit to self-clear indicating reset is complete */ + for (i = 0; i < 10; i++) { + udelay(1); + ctrl = IXGBE_READ_REG(hw, IXGBE_CTRL); + if (!(ctrl & IXGBE_CTRL_RST)) + break; + } + if (ctrl & IXGBE_CTRL_RST) { + status = IXGBE_ERR_RESET_FAILED; + hw_dbg(hw, "Reset polling failed to complete.\n"); + } + + /* + * 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. We use 1usec since that is + * what is needed for ixgbe_disable_pcie_master(). The second reset + * then clears out any effects of those events. + */ + if (hw->mac.flags & IXGBE_FLAGS_DOUBLE_RESET_REQUIRED) { + hw->mac.flags &= ~IXGBE_FLAGS_DOUBLE_RESET_REQUIRED; + udelay(1); + goto mac_reset_top; + } + + msleep(50); + + gheccr = IXGBE_READ_REG(hw, IXGBE_GHECCR); + gheccr &= ~((1 << 21) | (1 << 18) | (1 << 9) | (1 << 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); + +reset_hw_out: + 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 + * + * 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) +{ + 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 |= (1 << bitindex); + else + /* Turn off this VLAN id */ + bits &= ~(1 << 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_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) +{ + s32 status = 0; + u16 sfp_addr = 0; + u16 sfp_data = 0; + u16 sfp_stat = 0; + u32 i; + + 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 = (IXGBE_I2C_EEPROM_DEV_ADDR << 8) + byte_offset; + sfp_addr = (sfp_addr | IXGBE_I2C_EEPROM_READ_MASK); + hw->phy.ops.write_reg(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(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(hw, IXGBE_MDIO_PMA_PMD_SDA_SCL_DATA, + MDIO_MMD_PMAPMD, &sfp_data); + + *eeprom_data = (u8)(sfp_data >> 8); + } else { + status = IXGBE_ERR_PHY; + goto out; + } + +out: + return status; +} + +/** + * ixgbe_get_supported_physical_layer_82598 - Returns physical layer type + * @hw: pointer to hardware structure + * + * Determines physical layer capabilities of the current configuration. + **/ +static u32 ixgbe_get_supported_physical_layer_82598(struct ixgbe_hw *hw) +{ + u32 physical_layer = IXGBE_PHYSICAL_LAYER_UNKNOWN; + u32 autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC); + u32 pma_pmd_10g = autoc & IXGBE_AUTOC_10G_PMA_PMD_MASK; + u32 pma_pmd_1g = autoc & IXGBE_AUTOC_1G_PMA_PMD_MASK; + u16 ext_ability = 0; + + hw->phy.ops.identify(hw); + + /* Copper PHY must be checked before AUTOC LMS to determine correct + * physical layer because 10GBase-T PHYs use LMS = KX4/KX */ + switch (hw->phy.type) { + case ixgbe_phy_tn: + case ixgbe_phy_aq: + case ixgbe_phy_cu_unknown: + hw->phy.ops.read_reg(hw, MDIO_PMA_EXTABLE, + MDIO_MMD_PMAPMD, &ext_ability); + if (ext_ability & MDIO_PMA_EXTABLE_10GBT) + physical_layer |= IXGBE_PHYSICAL_LAYER_10GBASE_T; + if (ext_ability & MDIO_PMA_EXTABLE_1000BT) + physical_layer |= IXGBE_PHYSICAL_LAYER_1000BASE_T; + if (ext_ability & MDIO_PMA_EXTABLE_100BTX) + physical_layer |= IXGBE_PHYSICAL_LAYER_100BASE_TX; + goto out; + default: + break; + } + + switch (autoc & IXGBE_AUTOC_LMS_MASK) { + case IXGBE_AUTOC_LMS_1G_AN: + case IXGBE_AUTOC_LMS_1G_LINK_NO_AN: + if (pma_pmd_1g == IXGBE_AUTOC_1G_KX) + physical_layer = IXGBE_PHYSICAL_LAYER_1000BASE_KX; + else + physical_layer = IXGBE_PHYSICAL_LAYER_1000BASE_BX; + break; + case IXGBE_AUTOC_LMS_10G_LINK_NO_AN: + if (pma_pmd_10g == IXGBE_AUTOC_10G_CX4) + physical_layer = IXGBE_PHYSICAL_LAYER_10GBASE_CX4; + else if (pma_pmd_10g == IXGBE_AUTOC_10G_KX4) + physical_layer = IXGBE_PHYSICAL_LAYER_10GBASE_KX4; + else /* XAUI */ + physical_layer = IXGBE_PHYSICAL_LAYER_UNKNOWN; + break; + case IXGBE_AUTOC_LMS_KX4_AN: + case IXGBE_AUTOC_LMS_KX4_AN_1G_AN: + if (autoc & IXGBE_AUTOC_KX_SUPP) + physical_layer |= IXGBE_PHYSICAL_LAYER_1000BASE_KX; + if (autoc & IXGBE_AUTOC_KX4_SUPP) + physical_layer |= IXGBE_PHYSICAL_LAYER_10GBASE_KX4; + break; + default: + break; + } + + if (hw->phy.type == ixgbe_phy_nl) { + hw->phy.ops.identify_sfp(hw); + + switch (hw->phy.sfp_type) { + case ixgbe_sfp_type_da_cu: + physical_layer = IXGBE_PHYSICAL_LAYER_SFP_PLUS_CU; + break; + case ixgbe_sfp_type_sr: + physical_layer = IXGBE_PHYSICAL_LAYER_10GBASE_SR; + break; + case ixgbe_sfp_type_lr: + physical_layer = IXGBE_PHYSICAL_LAYER_10GBASE_LR; + break; + default: + physical_layer = IXGBE_PHYSICAL_LAYER_UNKNOWN; + break; + } + } + + switch (hw->device_id) { + case IXGBE_DEV_ID_82598_DA_DUAL_PORT: + physical_layer = IXGBE_PHYSICAL_LAYER_SFP_PLUS_CU; + break; + case IXGBE_DEV_ID_82598AF_DUAL_PORT: + case IXGBE_DEV_ID_82598AF_SINGLE_PORT: + case IXGBE_DEV_ID_82598_SR_DUAL_PORT_EM: + physical_layer = IXGBE_PHYSICAL_LAYER_10GBASE_SR; + break; + case IXGBE_DEV_ID_82598EB_XF_LR: + physical_layer = IXGBE_PHYSICAL_LAYER_10GBASE_LR; + break; + default: + break; + } + +out: + return physical_layer; +} + +/** + * 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 - Configure packet buffers + * @hw: pointer to hardware structure + * @dcb_config: pointer to ixgbe_dcb_config structure + * + * Configure packet buffers. + */ +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; + /* Fall Through */ + 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); + + return; +} + +static 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, + .get_supported_physical_layer = &ixgbe_get_supported_physical_layer_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, + .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, + .set_fw_drv_ver = NULL, + .acquire_swfw_sync = &ixgbe_acquire_swfw_sync, + .release_swfw_sync = &ixgbe_release_swfw_sync, +}; + +static struct ixgbe_eeprom_operations eeprom_ops_82598 = { + .init_params = &ixgbe_init_eeprom_params_generic, + .read = &ixgbe_read_eerd_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 struct ixgbe_phy_operations phy_ops_82598 = { + .identify = &ixgbe_identify_phy_generic, + .identify_sfp = &ixgbe_identify_sfp_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, + .setup_link = &ixgbe_setup_phy_link_generic, + .setup_link_speed = &ixgbe_setup_phy_link_speed_generic, + .read_i2c_eeprom = &ixgbe_read_i2c_eeprom_82598, + .check_overtemp = &ixgbe_tn_check_overtemp, +}; + +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, +}; + 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 000000000000..34f30ec79c2e --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -0,0 +1,2263 @@ +/******************************************************************************* + + Intel 10 Gigabit PCI Express Linux driver + Copyright(c) 1999 - 2011 Intel Corporation. + + This program is free software; you can redistribute it and/or modify it + under the terms and conditions of the GNU General Public License, + version 2, as published by the Free Software Foundation. + + This program is distributed in the hope it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + more details. + + You should have received a copy of the GNU General Public License along with + this program; if not, write to the Free Software Foundation, Inc., + 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + + The full GNU General Public License is included in this distribution in + the file called "COPYING". + + Contact Information: + e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + +*******************************************************************************/ + +#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 s32 ixgbe_setup_mac_link_multispeed_fiber(struct ixgbe_hw *hw, + ixgbe_link_speed speed, + bool autoneg, + bool autoneg_wait_to_complete); +static s32 ixgbe_setup_mac_link_smartspeed(struct ixgbe_hw *hw, + ixgbe_link_speed speed, + bool autoneg, + bool autoneg_wait_to_complete); +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, + bool autoneg_wait_to_complete); +static s32 ixgbe_setup_copper_link_82599(struct ixgbe_hw *hw, + ixgbe_link_speed speed, + bool autoneg, + bool autoneg_wait_to_complete); +static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw); +static bool ixgbe_verify_lesm_fw_enabled_82599(struct ixgbe_hw *hw); + +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 */ + if (mac->ops.get_media_type(hw) == ixgbe_media_type_fiber) { + 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; + } 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 = 0; + u32 reg_anlp1 = 0; + u32 i = 0; + 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 != 0) + goto setup_sfp_out; + + /* 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 != 0) { + ret_val = IXGBE_ERR_SWFW_SYNC; + goto setup_sfp_out; + } + + hw->eeprom.ops.read(hw, ++data_offset, &data_value); + while (data_value != 0xffff) { + IXGBE_WRITE_REG(hw, IXGBE_CORECTL, data_value); + IXGBE_WRITE_FLUSH(hw); + hw->eeprom.ops.read(hw, ++data_offset, &data_value); + } + + /* 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); + + /* Now restart DSP by setting Restart_AN and clearing LMS */ + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, ((IXGBE_READ_REG(hw, + IXGBE_AUTOC) & ~IXGBE_AUTOC_LMS_MASK) | + IXGBE_AUTOC_AN_RESTART)); + + /* Wait for AN to leave state 0 */ + for (i = 0; i < 10; i++) { + usleep_range(4000, 8000); + reg_anlp1 = IXGBE_READ_REG(hw, IXGBE_ANLP1); + if (reg_anlp1 & IXGBE_ANLP1_AN_STATE_MASK) + break; + } + if (!(reg_anlp1 & IXGBE_ANLP1_AN_STATE_MASK)) { + hw_dbg(hw, "sfp module setup not complete\n"); + ret_val = IXGBE_ERR_SFP_SETUP_NOT_COMPLETE; + goto setup_sfp_out; + } + + /* Restart DSP by setting Restart_AN and return to SFI mode */ + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, (IXGBE_READ_REG(hw, + IXGBE_AUTOC) | IXGBE_AUTOC_LMS_10G_SERIAL | + IXGBE_AUTOC_AN_RESTART)); + } + +setup_sfp_out: + 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->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 = 0; + + /* 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; + phy->ops.get_firmware_version = + &ixgbe_get_phy_firmware_version_tnx; + break; + case ixgbe_phy_aq: + phy->ops.get_firmware_version = + &ixgbe_get_phy_firmware_version_generic; + break; + default: + break; + } + + return ret_val; +} + +/** + * ixgbe_get_link_capabilities_82599 - Determines link capabilities + * @hw: pointer to hardware structure + * @speed: pointer to link speed + * @negotiation: 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 *negotiation) +{ + s32 status = 0; + 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) { + *speed = IXGBE_LINK_SPEED_1GB_FULL; + *negotiation = true; + goto out; + } + + /* + * 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; + *negotiation = false; + break; + + case IXGBE_AUTOC_LMS_10G_LINK_NO_AN: + *speed = IXGBE_LINK_SPEED_10GB_FULL; + *negotiation = false; + break; + + case IXGBE_AUTOC_LMS_1G_AN: + *speed = IXGBE_LINK_SPEED_1GB_FULL; + *negotiation = true; + break; + + case IXGBE_AUTOC_LMS_10G_SERIAL: + *speed = IXGBE_LINK_SPEED_10GB_FULL; + *negotiation = 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; + *negotiation = 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; + *negotiation = true; + break; + + case IXGBE_AUTOC_LMS_SGMII_1G_100M: + *speed = IXGBE_LINK_SPEED_1GB_FULL | IXGBE_LINK_SPEED_100_FULL; + *negotiation = false; + break; + + default: + status = IXGBE_ERR_LINK_SETUP; + goto out; + break; + } + + if (hw->phy.multispeed_fiber) { + *speed |= IXGBE_LINK_SPEED_10GB_FULL | + IXGBE_LINK_SPEED_1GB_FULL; + *negotiation = true; + } + +out: + return status; +} + +/** + * 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) +{ + enum ixgbe_media_type media_type; + + /* Detect if there is a copper PHY attached. */ + switch (hw->phy.type) { + case ixgbe_phy_cu_unknown: + case ixgbe_phy_tn: + case ixgbe_phy_aq: + media_type = ixgbe_media_type_copper; + goto out; + 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 */ + media_type = ixgbe_media_type_backplane; + break; + 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: + media_type = ixgbe_media_type_fiber; + break; + case IXGBE_DEV_ID_82599_CX4: + media_type = ixgbe_media_type_cx4; + break; + case IXGBE_DEV_ID_82599_T3_LOM: + media_type = ixgbe_media_type_copper; + break; + case IXGBE_DEV_ID_82599_LS: + media_type = ixgbe_media_type_fiber_lco; + break; + default: + media_type = ixgbe_media_type_unknown; + break; + } +out: + return media_type; +} + +/** + * 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; + + /* 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_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); + + /* 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) +{ + 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_setup_mac_link_multispeed_fiber - Set MAC link speed + * @hw: pointer to hardware structure + * @speed: new link speed + * @autoneg: true if autonegotiation enabled + * @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_multispeed_fiber(struct ixgbe_hw *hw, + ixgbe_link_speed speed, + bool autoneg, + bool autoneg_wait_to_complete) +{ + s32 status = 0; + ixgbe_link_speed link_speed = IXGBE_LINK_SPEED_UNKNOWN; + ixgbe_link_speed highest_link_speed = IXGBE_LINK_SPEED_UNKNOWN; + u32 speedcnt = 0; + u32 esdp_reg = IXGBE_READ_REG(hw, IXGBE_ESDP); + u32 i = 0; + bool link_up = false; + bool negotiation; + + /* Mask off requested but non-supported speeds */ + status = hw->mac.ops.get_link_capabilities(hw, &link_speed, + &negotiation); + if (status != 0) + 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; + + /* If we already have link at this speed, just jump out */ + status = hw->mac.ops.check_link(hw, &link_speed, &link_up, + false); + if (status != 0) + return status; + + if ((link_speed == IXGBE_LINK_SPEED_10GB_FULL) && link_up) + goto out; + + /* Set the module link speed */ + esdp_reg |= (IXGBE_ESDP_SDP5_DIR | IXGBE_ESDP_SDP5); + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp_reg); + IXGBE_WRITE_FLUSH(hw); + + /* Allow module to change analog characteristics (1G->10G) */ + msleep(40); + + status = ixgbe_setup_mac_link_82599(hw, + IXGBE_LINK_SPEED_10GB_FULL, + autoneg, + autoneg_wait_to_complete); + if (status != 0) + return status; + + /* Flap the tx laser if it has not already been done */ + 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 != 0) + 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; + + /* If we already have link at this speed, just jump out */ + status = hw->mac.ops.check_link(hw, &link_speed, &link_up, + false); + if (status != 0) + return status; + + if ((link_speed == IXGBE_LINK_SPEED_1GB_FULL) && link_up) + goto out; + + /* Set the module link speed */ + esdp_reg &= ~IXGBE_ESDP_SDP5; + esdp_reg |= IXGBE_ESDP_SDP5_DIR; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp_reg); + IXGBE_WRITE_FLUSH(hw); + + /* Allow module to change analog characteristics (10G->1G) */ + msleep(40); + + status = ixgbe_setup_mac_link_82599(hw, + IXGBE_LINK_SPEED_1GB_FULL, + autoneg, + autoneg_wait_to_complete); + if (status != 0) + return status; + + /* Flap the tx laser if it has not already been done */ + 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 != 0) + 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, + 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_setup_mac_link_smartspeed - Set MAC link speed using SmartSpeed + * @hw: pointer to hardware structure + * @speed: new link speed + * @autoneg: true if autonegotiation enabled + * @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, + 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, + 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, + 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, + 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: true if autonegotiation enabled + * @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, + bool autoneg_wait_to_complete) +{ + s32 status = 0; + u32 autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC); + u32 autoc2 = IXGBE_READ_REG(hw, IXGBE_AUTOC2); + u32 start_autoc = autoc; + u32 orig_autoc = 0; + u32 link_mode = autoc & IXGBE_AUTOC_LMS_MASK; + u32 pma_pmd_1g = autoc & IXGBE_AUTOC_1G_PMA_PMD_MASK; + u32 pma_pmd_10g_serial = autoc2 & IXGBE_AUTOC2_10G_SERIAL_PMA_PMD_MASK; + u32 links_reg; + u32 i; + ixgbe_link_speed link_capabilities = IXGBE_LINK_SPEED_UNKNOWN; + + /* Check to see if speed passed in is supported. */ + hw->mac.ops.get_link_capabilities(hw, &link_capabilities, &autoneg); + if (status != 0) + goto out; + + speed &= link_capabilities; + + if (speed == IXGBE_LINK_SPEED_UNKNOWN) { + status = IXGBE_ERR_LINK_SETUP; + goto out; + } + + /* 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; + + 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 != start_autoc) { + /* Restart link */ + autoc |= IXGBE_AUTOC_AN_RESTART; + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc); + + /* 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); + } + +out: + return status; +} + +/** + * ixgbe_setup_copper_link_82599 - Set the PHY autoneg advertised field + * @hw: pointer to hardware structure + * @speed: new link speed + * @autoneg: true if autonegotiation enabled + * @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, + bool autoneg_wait_to_complete) +{ + s32 status; + + /* Setup the PHY according to input speed */ + status = hw->phy.ops.setup_link_speed(hw, speed, autoneg, + 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) +{ + s32 status = 0; + u32 ctrl; + u32 i; + u32 autoc; + u32 autoc2; + + /* Call adapter stop to disable tx/rx and clear interrupts */ + hw->mac.ops.stop_adapter(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) + goto reset_hw_out; + + /* 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) + goto reset_hw_out; + + /* Reset PHY */ + if (hw->phy.reset_disable == false && hw->phy.ops.reset != NULL) + hw->phy.ops.reset(hw); + + /* + * Prevent the PCI-E bus from from hanging by disabling PCI-E master + * access and verify no pending requests before reset + */ + ixgbe_disable_pcie_master(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_WRITE_REG(hw, IXGBE_CTRL, (ctrl | IXGBE_CTRL_RST)); + IXGBE_WRITE_FLUSH(hw); + + /* Poll for reset bit to self-clear indicating reset is complete */ + for (i = 0; i < 10; i++) { + udelay(1); + ctrl = IXGBE_READ_REG(hw, IXGBE_CTRL); + if (!(ctrl & IXGBE_CTRL_RST)) + break; + } + if (ctrl & IXGBE_CTRL_RST) { + status = IXGBE_ERR_RESET_FAILED; + hw_dbg(hw, "Reset polling failed to complete.\n"); + } + + /* + * 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. We use 1usec since that is + * what is needed for ixgbe_disable_pcie_master(). The second reset + * then clears out any effects of those events. + */ + if (hw->mac.flags & IXGBE_FLAGS_DOUBLE_RESET_REQUIRED) { + hw->mac.flags &= ~IXGBE_FLAGS_DOUBLE_RESET_REQUIRED; + udelay(1); + goto mac_reset_top; + } + + msleep(50); + + /* + * 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); + 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 (autoc != hw->mac.orig_autoc) + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, (hw->mac.orig_autoc | + IXGBE_AUTOC_AN_RESTART)); + + 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 = 128; + 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 (ixgbe_validate_mac_addr(hw->mac.san_addr) == 0) { + hw->mac.ops.set_rar(hw, hw->mac.num_rar_entries - 1, + hw->mac.san_addr, 0, IXGBE_RAH_AV); + + /* 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); + +reset_hw_out: + return status; +} + +/** + * 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); + fdirctrl &= ~IXGBE_FDIRCTRL_INIT_DONE; + + /* + * Before starting reinitialization process, + * FDIRCMD.CMD must be zero. + */ + for (i = 0; i < IXGBE_FDIRCMD_CMD_POLL; i++) { + if (!(IXGBE_READ_REG(hw, IXGBE_FDIRCMD) & + IXGBE_FDIRCMD_CMD_MASK)) + break; + udelay(10); + } + if (i >= IXGBE_FDIRCMD_CMD_POLL) { + hw_dbg(hw, "Flow Director previous command isn't complete, " + "aborting table re-initialization.\n"); + return IXGBE_ERR_FDIR_REINIT_FAILED; + } + + 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; + udelay(10); + } + 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_set_fdir_rxpba_82599 - Initialize Flow Director Rx packet buffer + * @hw: pointer to hardware structure + * @pballoc: which mode to allocate filters with + **/ +static s32 ixgbe_set_fdir_rxpba_82599(struct ixgbe_hw *hw, const u32 pballoc) +{ + u32 fdir_pbsize = hw->mac.rx_pb_size << IXGBE_RXPBSIZE_SHIFT; + u32 current_rxpbsize = 0; + int i; + + /* reserve space for Flow Director filters */ + switch (pballoc) { + case IXGBE_FDIR_PBALLOC_256K: + fdir_pbsize -= 256 << IXGBE_RXPBSIZE_SHIFT; + break; + case IXGBE_FDIR_PBALLOC_128K: + fdir_pbsize -= 128 << IXGBE_RXPBSIZE_SHIFT; + break; + case IXGBE_FDIR_PBALLOC_64K: + fdir_pbsize -= 64 << IXGBE_RXPBSIZE_SHIFT; + break; + case IXGBE_FDIR_PBALLOC_NONE: + default: + return IXGBE_ERR_PARAM; + } + + /* determine current RX packet buffer size */ + for (i = 0; i < 8; i++) + current_rxpbsize += IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(i)); + + /* if there is already room for the filters do nothing */ + if (current_rxpbsize <= fdir_pbsize) + return 0; + + if (current_rxpbsize > hw->mac.rx_pb_size) { + /* + * if rxpbsize is greater than max then HW max the Rx buffer + * sizes are unconfigured or misconfigured since HW default is + * to give the full buffer to each traffic class resulting in + * the total size being buffer size 8x actual size + * + * This assumes no DCB since the RXPBSIZE registers appear to + * be unconfigured. + */ + IXGBE_WRITE_REG(hw, IXGBE_RXPBSIZE(0), fdir_pbsize); + for (i = 1; i < 8; i++) + IXGBE_WRITE_REG(hw, IXGBE_RXPBSIZE(i), 0); + } else { + /* + * Since the Rx packet buffer appears to have already been + * configured we need to shrink each packet buffer by enough + * to make room for the filters. As such we take each rxpbsize + * value and multiply it by a fraction representing the size + * needed over the size we currently have. + * + * We need to reduce fdir_pbsize and current_rxpbsize to + * 1/1024 of their original values in order to avoid + * overflowing the u32 being used to store rxpbsize. + */ + fdir_pbsize >>= IXGBE_RXPBSIZE_SHIFT; + current_rxpbsize >>= IXGBE_RXPBSIZE_SHIFT; + for (i = 0; i < 8; i++) { + u32 rxpbsize = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(i)); + rxpbsize *= fdir_pbsize; + rxpbsize /= current_rxpbsize; + IXGBE_WRITE_REG(hw, IXGBE_RXPBSIZE(i), rxpbsize); + } + } + + 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) +{ + s32 err; + + /* Before enabling Flow Director, verify the Rx Packet Buffer size */ + err = ixgbe_set_fdir_rxpba_82599(hw, fdirctrl); + if (err) + return err; + + /* + * 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) +{ + s32 err; + + /* Before enabling Flow Director, verify the Rx Packet Buffer size */ + err = ixgbe_set_fdir_rxpba_82599(hw, fdirctrl); + if (err) + return err; + + /* + * Continue setup of fdirctrl register bits: + * Turn perfect match filtering on + * Report hash in RSS field of Rx wb descriptor + * 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_FDIRCTRL_REPORT_STATUS | + (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 & (0x01 << n)) \ + common_hash ^= lo_hash_dword >> n; \ + else if (IXGBE_ATR_BUCKET_HASH_KEY & (0x01 << n)) \ + bucket_hash ^= lo_hash_dword >> n; \ + else if (IXGBE_ATR_SIGNATURE_HASH_KEY & (0x01 << n)) \ + sig_hash ^= lo_hash_dword << (16 - n); \ + if (IXGBE_ATR_COMMON_HASH_KEY & (0x01 << (n + 16))) \ + common_hash ^= hi_hash_dword >> n; \ + else if (IXGBE_ATR_BUCKET_HASH_KEY & (0x01 << (n + 16))) \ + bucket_hash ^= hi_hash_dword >> n; \ + else if (IXGBE_ATR_SIGNATURE_HASH_KEY & (0x01 << (n + 16))) \ + sig_hash ^= hi_hash_dword << (16 - n); \ +} while (0); + +/** + * ixgbe_atr_compute_sig_hash_82599 - Compute the signature hash + * @stream: input bitstream to compute the hash on + * + * This function is almost identical to the function above but contains + * several optomizations 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 + **/ +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; + u32 fdircmd; + + /* + * Get the flow_type in order to program FDIRCMD properly + * lowest 2 bits are FDIRCMD.L4TYPE, third lowest bit is FDIRCMD.IPV6 + */ + switch (input.formatted.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 |= input.formatted.flow_type << IXGBE_FDIRCMD_FLOW_TYPE_SHIFT; + fdircmd |= (u32)queue << IXGBE_FDIRCMD_RX_QUEUE_SHIFT; + + /* + * 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 & (0x01 << n)) \ + bucket_hash ^= lo_hash_dword >> n; \ + if (IXGBE_ATR_BUCKET_HASH_KEY & (0x01 << (n + 16))) \ + bucket_hash ^= hi_hash_dword >> n; \ +} while (0); + +/** + * ixgbe_atr_compute_perfect_hash_82599 - Compute the perfect filter hash + * @atr_input: input bitstream to compute the hash on + * @input_mask: mask for the input bitstream + * + * This function serves two main purposes. First it applys 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; + + /* Apply masks to input data */ + input->dword_stream[0] &= input_mask->dword_stream[0]; + input->dword_stream[1] &= input_mask->dword_stream[1]; + input->dword_stream[2] &= input_mask->dword_stream[2]; + input->dword_stream[3] &= input_mask->dword_stream[3]; + input->dword_stream[4] &= input_mask->dword_stream[4]; + input->dword_stream[5] &= input_mask->dword_stream[5]; + input->dword_stream[6] &= input_mask->dword_stream[6]; + input->dword_stream[7] &= input_mask->dword_stream[7]; + input->dword_stream[8] &= input_mask->dword_stream[8]; + input->dword_stream[9] &= input_mask->dword_stream[9]; + input->dword_stream[10] &= input_mask->dword_stream[10]; + + /* 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 */ + hi_hash_dword = ntohl(input->dword_stream[1] ^ + input->dword_stream[2] ^ + input->dword_stream[3] ^ + input->dword_stream[4] ^ + input->dword_stream[5] ^ + input->dword_stream[6] ^ + input->dword_stream[7] ^ + input->dword_stream[8] ^ + input->dword_stream[9] ^ + input->dword_stream[10]); + + /* 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 */ + IXGBE_COMPUTE_BKT_HASH_ITERATION(1); + IXGBE_COMPUTE_BKT_HASH_ITERATION(2); + IXGBE_COMPUTE_BKT_HASH_ITERATION(3); + IXGBE_COMPUTE_BKT_HASH_ITERATION(4); + IXGBE_COMPUTE_BKT_HASH_ITERATION(5); + IXGBE_COMPUTE_BKT_HASH_ITERATION(6); + IXGBE_COMPUTE_BKT_HASH_ITERATION(7); + IXGBE_COMPUTE_BKT_HASH_ITERATION(8); + IXGBE_COMPUTE_BKT_HASH_ITERATION(9); + IXGBE_COMPUTE_BKT_HASH_ITERATION(10); + IXGBE_COMPUTE_BKT_HASH_ITERATION(11); + IXGBE_COMPUTE_BKT_HASH_ITERATION(12); + IXGBE_COMPUTE_BKT_HASH_ITERATION(13); + IXGBE_COMPUTE_BKT_HASH_ITERATION(14); + IXGBE_COMPUTE_BKT_HASH_ITERATION(15); + + /* + * Limit hash to 13 bits since max bucket count is 8K. + * Store result at the end of the input stream. + */ + input->formatted.bkt_hash = 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, fall through to mask VLAN priority */ + fdirm |= IXGBE_FDIRM_VLANID; + case 0x0FFF: + /* mask VLAN priority */ + fdirm |= IXGBE_FDIRM_VLANP; + break; + case 0xE000: + /* mask VLAN ID only, fall through */ + fdirm |= IXGBE_FDIRM_VLANID; + case 0xEFFF: + /* no VLAN fields masked */ + break; + default: + hw_dbg(hw, " Error on VLAN mask\n"); + return IXGBE_ERR_CONFIG; + } + + switch (input_mask->formatted.flex_bytes & 0xFFFF) { + case 0x0000: + /* Mask Flex Bytes, fall through */ + fdirm |= IXGBE_FDIRM_FLEX; + 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); + + /* 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; + + /* 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(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 = 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); + + 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 = 0; + u32 retry_count; + s32 err = 0; + + /* configure FDIRHASH register */ + fdirhash = 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); + + for (retry_count = 10; retry_count; retry_count--) { + /* allow 10us for query to process */ + udelay(10); + /* verify query completed successfully */ + fdircmd = IXGBE_READ_REG(hw, IXGBE_FDIRCMD); + if (!(fdircmd & IXGBE_FDIRCMD_CMD_MASK)) + break; + } + + if (!retry_count) + err = IXGBE_ERR_FDIR_REINIT_FAILED; + + /* 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 err; +} + +/** + * 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 != 0) + goto out; + + ret_val = ixgbe_start_hw_gen2(hw); + if (ret_val != 0) + goto out; + + /* We need to run link autotry after the driver loads */ + hw->mac.autotry_restart = true; + hw->mac.rx_pb_size = IXGBE_82599_RX_PB_SIZE; + + if (ret_val == 0) + ret_val = ixgbe_verify_fw_version_82599(hw); +out: + return ret_val; +} + +/** + * 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 = IXGBE_ERR_PHY_ADDR_INVALID; + + /* Detect PHY if not unknown - returns success if already detected. */ + status = ixgbe_identify_phy_generic(hw); + if (status != 0) { + /* 82599 10GBASE-T requires an external PHY */ + if (hw->mac.ops.get_media_type(hw) == ixgbe_media_type_copper) + goto out; + else + status = ixgbe_identify_sfp_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) + status = IXGBE_ERR_SFP_NOT_SUPPORTED; + +out: + return status; +} + +/** + * ixgbe_get_supported_physical_layer_82599 - Returns physical layer type + * @hw: pointer to hardware structure + * + * Determines physical layer capabilities of the current configuration. + **/ +static u32 ixgbe_get_supported_physical_layer_82599(struct ixgbe_hw *hw) +{ + u32 physical_layer = IXGBE_PHYSICAL_LAYER_UNKNOWN; + u32 autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC); + u32 autoc2 = IXGBE_READ_REG(hw, IXGBE_AUTOC2); + u32 pma_pmd_10g_serial = autoc2 & IXGBE_AUTOC2_10G_SERIAL_PMA_PMD_MASK; + u32 pma_pmd_10g_parallel = autoc & IXGBE_AUTOC_10G_PMA_PMD_MASK; + u32 pma_pmd_1g = autoc & IXGBE_AUTOC_1G_PMA_PMD_MASK; + u16 ext_ability = 0; + u8 comp_codes_10g = 0; + u8 comp_codes_1g = 0; + + hw->phy.ops.identify(hw); + + switch (hw->phy.type) { + case ixgbe_phy_tn: + case ixgbe_phy_aq: + case ixgbe_phy_cu_unknown: + hw->phy.ops.read_reg(hw, MDIO_PMA_EXTABLE, MDIO_MMD_PMAPMD, + &ext_ability); + if (ext_ability & MDIO_PMA_EXTABLE_10GBT) + physical_layer |= IXGBE_PHYSICAL_LAYER_10GBASE_T; + if (ext_ability & MDIO_PMA_EXTABLE_1000BT) + physical_layer |= IXGBE_PHYSICAL_LAYER_1000BASE_T; + if (ext_ability & MDIO_PMA_EXTABLE_100BTX) + physical_layer |= IXGBE_PHYSICAL_LAYER_100BASE_TX; + goto out; + default: + break; + } + + switch (autoc & IXGBE_AUTOC_LMS_MASK) { + case IXGBE_AUTOC_LMS_1G_AN: + case IXGBE_AUTOC_LMS_1G_LINK_NO_AN: + if (pma_pmd_1g == IXGBE_AUTOC_1G_KX_BX) { + physical_layer = IXGBE_PHYSICAL_LAYER_1000BASE_KX | + IXGBE_PHYSICAL_LAYER_1000BASE_BX; + goto out; + } else + /* SFI mode so read SFP module */ + goto sfp_check; + break; + case IXGBE_AUTOC_LMS_10G_LINK_NO_AN: + if (pma_pmd_10g_parallel == IXGBE_AUTOC_10G_CX4) + physical_layer = IXGBE_PHYSICAL_LAYER_10GBASE_CX4; + else if (pma_pmd_10g_parallel == IXGBE_AUTOC_10G_KX4) + physical_layer = IXGBE_PHYSICAL_LAYER_10GBASE_KX4; + else if (pma_pmd_10g_parallel == IXGBE_AUTOC_10G_XAUI) + physical_layer = IXGBE_PHYSICAL_LAYER_10GBASE_XAUI; + goto out; + break; + case IXGBE_AUTOC_LMS_10G_SERIAL: + if (pma_pmd_10g_serial == IXGBE_AUTOC2_10G_KR) { + physical_layer = IXGBE_PHYSICAL_LAYER_10GBASE_KR; + goto out; + } else if (pma_pmd_10g_serial == IXGBE_AUTOC2_10G_SFI) + goto sfp_check; + break; + case IXGBE_AUTOC_LMS_KX4_KX_KR: + case IXGBE_AUTOC_LMS_KX4_KX_KR_1G_AN: + if (autoc & IXGBE_AUTOC_KX_SUPP) + physical_layer |= IXGBE_PHYSICAL_LAYER_1000BASE_KX; + if (autoc & IXGBE_AUTOC_KX4_SUPP) + physical_layer |= IXGBE_PHYSICAL_LAYER_10GBASE_KX4; + if (autoc & IXGBE_AUTOC_KR_SUPP) + physical_layer |= IXGBE_PHYSICAL_LAYER_10GBASE_KR; + goto out; + break; + default: + goto out; + break; + } + +sfp_check: + /* SFP check must be done last since DA modules are sometimes used to + * test KR mode - we need to id KR mode correctly before SFP module. + * Call identify_sfp because the pluggable module may have changed */ + hw->phy.ops.identify_sfp(hw); + if (hw->phy.sfp_type == ixgbe_sfp_type_not_present) + goto out; + + switch (hw->phy.type) { + case ixgbe_phy_sfp_passive_tyco: + case ixgbe_phy_sfp_passive_unknown: + physical_layer = IXGBE_PHYSICAL_LAYER_SFP_PLUS_CU; + break; + case ixgbe_phy_sfp_ftl_active: + case ixgbe_phy_sfp_active_unknown: + physical_layer = IXGBE_PHYSICAL_LAYER_SFP_ACTIVE_DA; + break; + case ixgbe_phy_sfp_avago: + case ixgbe_phy_sfp_ftl: + case ixgbe_phy_sfp_intel: + case ixgbe_phy_sfp_unknown: + hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_1GBE_COMP_CODES, &comp_codes_1g); + hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_10GBE_COMP_CODES, &comp_codes_10g); + if (comp_codes_10g & IXGBE_SFF_10GBASESR_CAPABLE) + physical_layer = IXGBE_PHYSICAL_LAYER_10GBASE_SR; + else if (comp_codes_10g & IXGBE_SFF_10GBASELR_CAPABLE) + physical_layer = IXGBE_PHYSICAL_LAYER_10GBASE_LR; + else if (comp_codes_1g & IXGBE_SFF_1GBASET_CAPABLE) + physical_layer = IXGBE_PHYSICAL_LAYER_1000BASE_T; + break; + default: + break; + } + +out: + return physical_layer; +} + +/** + * 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) +{ +#define IXGBE_MAX_SECRX_POLL 30 + int i; + int secrxreg; + + /* + * 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. + */ + 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(10); + } + + /* 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"); + + IXGBE_WRITE_REG(hw, IXGBE_RXCTRL, regval); + 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_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 fw_version = 0; + + /* firmware check is only necessary for SFI devices */ + if (hw->phy.media_type != ixgbe_media_type_fiber) { + status = 0; + goto fw_version_out; + } + + /* get the offset to the Firmware Module block */ + hw->eeprom.ops.read(hw, IXGBE_FW_PTR, &fw_offset); + + if ((fw_offset == 0) || (fw_offset == 0xFFFF)) + goto fw_version_out; + + /* get the offset to the Pass Through Patch Configuration block */ + hw->eeprom.ops.read(hw, (fw_offset + + IXGBE_FW_PASSTHROUGH_PATCH_CONFIG_PTR), + &fw_ptp_cfg_offset); + + if ((fw_ptp_cfg_offset == 0) || (fw_ptp_cfg_offset == 0xFFFF)) + goto fw_version_out; + + /* get the firmware version */ + hw->eeprom.ops.read(hw, (fw_ptp_cfg_offset + + IXGBE_FW_PATCH_VERSION_4), + &fw_version); + + if (fw_version > 0x5) + status = 0; + +fw_version_out: + return status; +} + +/** + * 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) +{ + bool lesm_enabled = false; + 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 != 0) || + (fw_offset == 0) || (fw_offset == 0xFFFF)) + goto out; + + /* 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 != 0) || + (fw_lesm_param_offset == 0) || (fw_lesm_param_offset == 0xFFFF)) + goto out; + + /* 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 == 0) && + (fw_lesm_state & IXGBE_FW_LESM_STATE_ENABLED)) + lesm_enabled = true; + +out: + return lesm_enabled; +} + +/** + * 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; + s32 ret_val = IXGBE_ERR_CONFIG; + + /* + * 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)) + ret_val = ixgbe_read_eerd_buffer_generic(hw, offset, words, + data); + else + ret_val = ixgbe_read_eeprom_buffer_bit_bang_generic(hw, offset, + words, + data); + + return ret_val; +} + +/** + * 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; + s32 ret_val = IXGBE_ERR_CONFIG; + + /* + * 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)) + ret_val = ixgbe_read_eerd_generic(hw, offset, data); + else + ret_val = ixgbe_read_eeprom_bit_bang_generic(hw, offset, data); + + return ret_val; +} + +static 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, + .get_supported_physical_layer = &ixgbe_get_supported_physical_layer_82599, + .enable_rx_dma = &ixgbe_enable_rx_dma_82599, + .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, + .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, + .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, + .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_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, + +}; + +static 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 struct ixgbe_phy_operations phy_ops_82599 = { + .identify = &ixgbe_identify_phy_82599, + .identify_sfp = &ixgbe_identify_sfp_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_eeprom = &ixgbe_read_i2c_eeprom_generic, + .write_i2c_eeprom = &ixgbe_write_i2c_eeprom_generic, + .check_overtemp = &ixgbe_tn_check_overtemp, +}; + +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, +}; 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 000000000000..fc1375f26fe5 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -0,0 +1,3510 @@ +/******************************************************************************* + + Intel 10 Gigabit PCI Express Linux driver + Copyright(c) 1999 - 2011 Intel Corporation. + + This program is free software; you can redistribute it and/or modify it + under the terms and conditions of the GNU General Public License, + version 2, as published by the Free Software Foundation. + + This program is distributed in the hope it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + more details. + + You should have received a copy of the GNU General Public License along with + this program; if not, write to the Free Software Foundation, Inc., + 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + + The full GNU General Public License is included in this distribution in + the file called "COPYING". + + Contact Information: + e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + +*******************************************************************************/ + +#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_fc_autoneg_fiber(struct ixgbe_hw *hw); +static s32 ixgbe_fc_autoneg_backplane(struct ixgbe_hw *hw); +static s32 ixgbe_fc_autoneg_copper(struct ixgbe_hw *hw); +static s32 ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw); +static 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); +static s32 ixgbe_setup_fc(struct ixgbe_hw *hw, s32 packetbuf_num); +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); + +/** + * 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) +{ + u32 ctrl_ext; + + /* 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 */ + ixgbe_setup_fc(hw, 0); + + /* 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; + u32 regval; + + /* 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); + + /* Disable relaxed ordering */ + for (i = 0; i < hw->mac.max_tx_queues; i++) { + regval = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL_82599(i)); + regval &= ~IXGBE_DCA_TXCTRL_TX_WB_RO_EN; + IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL_82599(i), regval); + } + + for (i = 0; i < hw->mac.max_rx_queues; i++) { + regval = IXGBE_READ_REG(hw, IXGBE_DCA_RXCTRL(i)); + regval &= ~(IXGBE_DCA_RXCTRL_DESC_WRO_EN | + IXGBE_DCA_RXCTRL_DESC_HSRO_EN); + IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(i), regval); + } + + 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); + } + + 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); + 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_X540) { + if (hw->phy.id == 0) + hw->phy.ops.identify(hw); + hw->phy.ops.read_reg(hw, 0x3, IXGBE_PCRC8ECL, &i); + hw->phy.ops.read_reg(hw, 0x3, IXGBE_PCRC8ECH, &i); + hw->phy.ops.read_reg(hw, 0x3, IXGBE_LDPCECL, &i); + hw->phy.ops.read_reg(hw, 0x3, IXGBE_LDPCECH, &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; +} + +/** + * 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) +{ + struct ixgbe_adapter *adapter = hw->back; + struct ixgbe_mac_info *mac = &hw->mac; + u16 link_status; + + hw->bus.type = ixgbe_bus_type_pci_express; + + /* Get the negotiated link width and speed from PCI config space */ + pci_read_config_word(adapter->pdev, IXGBE_PCI_LINK_STATUS, + &link_status); + + switch (link_status & IXGBE_PCI_LINK_WIDTH) { + case IXGBE_PCI_LINK_WIDTH_1: + hw->bus.width = ixgbe_bus_width_pcie_x1; + break; + case IXGBE_PCI_LINK_WIDTH_2: + hw->bus.width = ixgbe_bus_width_pcie_x2; + break; + case IXGBE_PCI_LINK_WIDTH_4: + hw->bus.width = ixgbe_bus_width_pcie_x4; + break; + case IXGBE_PCI_LINK_WIDTH_8: + hw->bus.width = ixgbe_bus_width_pcie_x8; + break; + default: + hw->bus.width = ixgbe_bus_width_unknown; + break; + } + + switch (link_status & IXGBE_PCI_LINK_SPEED) { + case IXGBE_PCI_LINK_SPEED_2500: + hw->bus.speed = ixgbe_bus_speed_2500; + break; + case IXGBE_PCI_LINK_SPEED_5000: + hw->bus.speed = ixgbe_bus_speed_5000; + break; + default: + hw->bus.speed = ixgbe_bus_speed_unknown; + break; + } + + 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; + 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); + if (reg & IXGBE_FACTPS_LFS) + bus->func ^= 0x1; +} + +/** + * 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 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 */ + reg_val = IXGBE_READ_REG(hw, IXGBE_RXCTRL); + reg_val &= ~(IXGBE_RXCTRL_RXEN); + IXGBE_WRITE_REG(hw, IXGBE_RXCTRL, reg_val); + IXGBE_WRITE_FLUSH(hw); + usleep_range(2000, 4000); + + /* Clear interrupt mask to stop from interrupts being generated */ + IXGBE_WRITE_REG(hw, IXGBE_EIMC, IXGBE_IRQ_CLEAR_MASK); + + /* Clear any pending interrupts */ + IXGBE_READ_REG(hw, IXGBE_EICR); + + /* 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_TXDCTL(i)); + if (reg_val & IXGBE_TXDCTL_ENABLE) { + reg_val &= ~IXGBE_TXDCTL_ENABLE; + IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(i), reg_val); + } + } + + /* + * Prevent the PCI-E bus from from hanging by disabling PCI-E master + * access and verify no pending requests + */ + ixgbe_disable_pcie_master(hw); + + 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); + + /* 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); + + /* 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); + 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 = 1 << (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 = 0; + u16 i, count; + + hw->eeprom.ops.init_params(hw); + + if (words == 0) { + status = IXGBE_ERR_INVALID_ARGUMENT; + goto out; + } + + if (offset + words > hw->eeprom.word_size) { + status = IXGBE_ERR_EEPROM; + goto out; + } + + /* + * 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; + } + +out: + 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 == 0) { + if (ixgbe_ready_eeprom(hw) != 0) { + ixgbe_release_eeprom(hw); + status = IXGBE_ERR_EEPROM; + } + } + + if (status == 0) { + 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 status; +} + +/** + * 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) +{ + s32 status; + + hw->eeprom.ops.init_params(hw); + + if (offset >= hw->eeprom.word_size) { + status = IXGBE_ERR_EEPROM; + goto out; + } + + status = ixgbe_write_eeprom_buffer_bit_bang(hw, offset, 1, &data); + +out: + return status; +} + +/** + * 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 = 0; + u16 i, count; + + hw->eeprom.ops.init_params(hw); + + if (words == 0) { + status = IXGBE_ERR_INVALID_ARGUMENT; + goto out; + } + + if (offset + words > hw->eeprom.word_size) { + status = IXGBE_ERR_EEPROM; + goto out; + } + + /* + * 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 != 0) + break; + } + +out: + return status; +} + +/** + * 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 == 0) { + if (ixgbe_ready_eeprom(hw) != 0) { + ixgbe_release_eeprom(hw); + status = IXGBE_ERR_EEPROM; + } + } + + if (status == 0) { + 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 status; +} + +/** + * 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) +{ + s32 status; + + hw->eeprom.ops.init_params(hw); + + if (offset >= hw->eeprom.word_size) { + status = IXGBE_ERR_EEPROM; + goto out; + } + + status = ixgbe_read_eeprom_buffer_bit_bang(hw, offset, 1, data); + +out: + return status; +} + +/** + * 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 = 0; + u32 i; + + hw->eeprom.ops.init_params(hw); + + if (words == 0) { + status = IXGBE_ERR_INVALID_ARGUMENT; + goto out; + } + + if (offset >= hw->eeprom.word_size) { + status = IXGBE_ERR_EEPROM; + goto out; + } + + 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"); + goto out; + } + } +out: + return status; +} + +/** + * 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 = 0; + 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 != 0) + goto out; + + status = ixgbe_read_eeprom_buffer_bit_bang(hw, offset, 1, data); + if (status != 0) + goto out; + + /* + * 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.", + hw->eeprom.word_page_size); +out: + return status; +} + +/** + * 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 = 0; + u16 i; + + hw->eeprom.ops.init_params(hw); + + if (words == 0) { + status = IXGBE_ERR_INVALID_ARGUMENT; + goto out; + } + + if (offset >= hw->eeprom.word_size) { + status = IXGBE_ERR_EEPROM; + goto out; + } + + 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 != 0) { + hw_dbg(hw, "Eeprom write EEWR timed out\n"); + goto out; + } + + IXGBE_WRITE_REG(hw, IXGBE_EEWR, eewr); + + status = ixgbe_poll_eerd_eewr_done(hw, IXGBE_NVM_POLL_WRITE); + if (status != 0) { + hw_dbg(hw, "Eeprom write EEWR timed out\n"); + goto out; + } + } + +out: + return status; +} + +/** + * 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; + s32 status = IXGBE_ERR_EEPROM; + + 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) { + status = 0; + break; + } + udelay(5); + } + return status; +} + +/** + * 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) +{ + s32 status = 0; + u32 eec; + u32 i; + + if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_EEP_SM) != 0) + status = IXGBE_ERR_SWFW_SYNC; + + if (status == 0) { + eec = IXGBE_READ_REG(hw, IXGBE_EEC); + + /* Request EEPROM Access */ + eec |= IXGBE_EEC_REQ; + IXGBE_WRITE_REG(hw, IXGBE_EEC, eec); + + for (i = 0; i < IXGBE_EEPROM_GRANT_ATTEMPTS; i++) { + eec = IXGBE_READ_REG(hw, IXGBE_EEC); + 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, eec); + hw_dbg(hw, "Could not acquire EEPROM grant\n"); + + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_EEP_SM); + status = IXGBE_ERR_EEPROM; + } + + /* Setup EEPROM for Read/Write */ + if (status == 0) { + /* Clear CS and SK */ + eec &= ~(IXGBE_EEC_CS | IXGBE_EEC_SK); + IXGBE_WRITE_REG(hw, IXGBE_EEC, eec); + IXGBE_WRITE_FLUSH(hw); + udelay(1); + } + } + return status; +} + +/** + * 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) +{ + s32 status = IXGBE_ERR_EEPROM; + 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); + if (!(swsm & IXGBE_SWSM_SMBI)) { + status = 0; + break; + } + udelay(50); + } + + 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); + + udelay(50); + /* + * 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); + if (!(swsm & IXGBE_SWSM_SMBI)) + status = 0; + } + + /* Now get the semaphore between SW/FW through the SWESMBI bit */ + if (status == 0) { + for (i = 0; i < timeout; i++) { + swsm = IXGBE_READ_REG(hw, IXGBE_SWSM); + + /* Set the SW EEPROM semaphore bit to request access */ + swsm |= IXGBE_SWSM_SWESMBI; + IXGBE_WRITE_REG(hw, IXGBE_SWSM, swsm); + + /* + * If we set the bit successfully then we got the + * semaphore. + */ + swsm = IXGBE_READ_REG(hw, IXGBE_SWSM); + if (swsm & IXGBE_SWSM_SWESMBI) + break; + + udelay(50); + } + + /* + * 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); + status = IXGBE_ERR_EEPROM; + } + } else { + hw_dbg(hw, "Software semaphore SMBI between device drivers " + "not granted.\n"); + } + + return status; +} + +/** + * 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); + + /* 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, 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) +{ + s32 status = 0; + 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"); + status = IXGBE_ERR_EEPROM; + } + + return status; +} + +/** + * 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); + + /* Toggle CS to flush commands */ + eec |= IXGBE_EEC_CS; + IXGBE_WRITE_REG(hw, IXGBE_EEC, eec); + IXGBE_WRITE_FLUSH(hw); + udelay(1); + eec &= ~IXGBE_EEC_CS; + IXGBE_WRITE_REG(hw, IXGBE_EEC, 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); + + /* + * 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 = 0x01 << (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, 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, eec); + IXGBE_WRITE_FLUSH(hw); +} + +/** + * ixgbe_shift_in_eeprom_bits - Shift data bits in from the EEPROM + * @hw: pointer to hardware structure + **/ +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); + + 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); + + 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, *eec); + IXGBE_WRITE_FLUSH(hw); + udelay(1); +} + +/** + * ixgbe_lower_eeprom_clk - Lowers the EEPROM's clock input. + * @hw: pointer to hardware structure + * @eecd: EECD'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, *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); + + eec |= IXGBE_EEC_CS; /* Pull CS high */ + eec &= ~IXGBE_EEC_SK; /* Lower SCK */ + + IXGBE_WRITE_REG(hw, IXGBE_EEC, eec); + IXGBE_WRITE_FLUSH(hw); + + udelay(1); + + /* Stop requesting EEPROM access */ + eec &= ~IXGBE_EEC_REQ; + IXGBE_WRITE_REG(hw, IXGBE_EEC, 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 + **/ +u16 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) != 0) { + 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++) { + hw->eeprom.ops.read(hw, i, &pointer); + + /* Make sure the pointer seems valid */ + if (pointer != 0xFFFF && pointer != 0) { + hw->eeprom.ops.read(hw, pointer, &length); + + if (length != 0xFFFF && length != 0) { + for (j = pointer+1; j <= pointer+length; j++) { + hw->eeprom.ops.read(hw, j, &word); + checksum += word; + } + } + } + } + + checksum = (u16)IXGBE_EEPROM_SUM - checksum; + + return 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 == 0) { + checksum = hw->eeprom.ops.calc_checksum(hw); + + hw->eeprom.ops.read(hw, IXGBE_EEPROM_CHECKSUM, &read_checksum); + + /* + * 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; + } else { + hw_dbg(hw, "EEPROM read failed\n"); + } + + 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 == 0) { + checksum = hw->eeprom.ops.calc_checksum(hw); + status = hw->eeprom.ops.write(hw, IXGBE_EEPROM_CHECKSUM, + checksum); + } else { + hw_dbg(hw, "EEPROM read failed\n"); + } + + return status; +} + +/** + * ixgbe_validate_mac_addr - Validate MAC address + * @mac_addr: pointer to MAC address. + * + * Tests a MAC address to ensure it is a valid Individual Address + **/ +s32 ixgbe_validate_mac_addr(u8 *mac_addr) +{ + s32 status = 0; + + /* Make sure it is not a multicast address */ + if (IXGBE_IS_MULTICAST(mac_addr)) + status = IXGBE_ERR_INVALID_MAC_ADDR; + /* Not a broadcast address */ + else if (IXGBE_IS_BROADCAST(mac_addr)) + status = IXGBE_ERR_INVALID_MAC_ADDR; + /* Reject the zero address */ + else if (mac_addr[0] == 0 && mac_addr[1] == 0 && mac_addr[2] == 0 && + mac_addr[3] == 0 && mac_addr[4] == 0 && mac_addr[5] == 0) + status = IXGBE_ERR_INVALID_MAC_ADDR; + + 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; + + IXGBE_WRITE_REG(hw, IXGBE_RAL(index), rar_low); + 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); + + IXGBE_WRITE_REG(hw, IXGBE_RAL(index), 0); + IXGBE_WRITE_REG(hw, IXGBE_RAH(index), rar_high); + + /* 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 (ixgbe_validate_mac_addr(hw->mac.addr) == + IXGBE_ERR_INVALID_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 + * @hash_value: Multicast address hash value + * + * 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] |= (1 << 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 + * @packetbuf_num: packet buffer number (0-7) + * + * Enable flow control according to the current settings. + **/ +s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw, s32 packetbuf_num) +{ + s32 ret_val = 0; + u32 mflcn_reg, fccfg_reg; + u32 reg; + u32 rx_pba_size; + u32 fcrtl, fcrth; + +#ifdef CONFIG_DCB + if (hw->fc.requested_mode == ixgbe_fc_pfc) + goto out; + +#endif /* CONFIG_DCB */ + /* Negotiate the fc mode to use */ + ret_val = ixgbe_fc_autoneg(hw); + if (ret_val == IXGBE_ERR_FLOW_CONTROL) + goto out; + + /* Disable any previous flow control settings */ + mflcn_reg = IXGBE_READ_REG(hw, IXGBE_MFLCN); + mflcn_reg &= ~(IXGBE_MFLCN_RFCE | IXGBE_MFLCN_RPFCE); + + 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. +#ifdef CONFIG_DCB + * 4: Priority Flow Control is enabled. +#endif + * 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; +#ifdef CONFIG_DCB + case ixgbe_fc_pfc: + goto out; + break; +#endif /* CONFIG_DCB */ + default: + hw_dbg(hw, "Flow control param set incorrectly\n"); + ret_val = IXGBE_ERR_CONFIG; + goto out; + break; + } + + /* 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); + + rx_pba_size = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(packetbuf_num)); + rx_pba_size >>= IXGBE_RXPBSIZE_SHIFT; + + fcrth = (rx_pba_size - hw->fc.high_water) << 10; + fcrtl = (rx_pba_size - hw->fc.low_water) << 10; + + if (hw->fc.current_mode & ixgbe_fc_tx_pause) { + fcrth |= IXGBE_FCRTH_FCEN; + if (hw->fc.send_xon) + fcrtl |= IXGBE_FCRTL_XONE; + } + + IXGBE_WRITE_REG(hw, IXGBE_FCRTH_82599(packetbuf_num), fcrth); + IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(packetbuf_num), fcrtl); + + /* Configure pause time (2 TCs per register) */ + reg = IXGBE_READ_REG(hw, IXGBE_FCTTV(packetbuf_num / 2)); + if ((packetbuf_num & 1) == 0) + reg = (reg & 0xFFFF0000) | hw->fc.pause_time; + else + reg = (reg & 0x0000FFFF) | (hw->fc.pause_time << 16); + IXGBE_WRITE_REG(hw, IXGBE_FCTTV(packetbuf_num / 2), reg); + + IXGBE_WRITE_REG(hw, IXGBE_FCRTV, (hw->fc.pause_time >> 1)); + +out: + return ret_val; +} + +/** + * 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. + **/ +s32 ixgbe_fc_autoneg(struct ixgbe_hw *hw) +{ + s32 ret_val = IXGBE_ERR_FC_NOT_NEGOTIATED; + ixgbe_link_speed speed; + bool link_up; + + if (hw->fc.disable_fc_autoneg) + goto out; + + /* + * 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. + */ + hw->mac.ops.check_link(hw, &speed, &link_up, false); + if (!link_up) { + ret_val = IXGBE_ERR_FLOW_CONTROL; + 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) == 0) + 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; + } + return ret_val; +} + +/** + * 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)) { + ret_val = IXGBE_ERR_FC_NOT_NEGOTIATED; + goto out; + } + + 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); + +out: + 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) { + hw->fc.fc_was_autonegged = false; + hw->fc.current_mode = hw->fc.requested_mode; + ret_val = IXGBE_ERR_FC_NOT_NEGOTIATED; + goto out; + } + + if (hw->mac.type == ixgbe_mac_82599EB) { + links2 = IXGBE_READ_REG(hw, IXGBE_LINKS2); + if ((links2 & IXGBE_LINKS2_AN_SUPPORTED) == 0) { + hw->fc.fc_was_autonegged = false; + hw->fc.current_mode = hw->fc.requested_mode; + ret_val = IXGBE_ERR_FC_NOT_NEGOTIATED; + goto out; + } + } + /* + * 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); + +out: + 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_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 + **/ +static 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_setup_fc - Set up flow control + * @hw: pointer to hardware structure + * + * Called at init time to set up flow control. + **/ +static s32 ixgbe_setup_fc(struct ixgbe_hw *hw, s32 packetbuf_num) +{ + s32 ret_val = 0; + u32 reg = 0, reg_bp = 0; + u16 reg_cu = 0; + +#ifdef CONFIG_DCB + if (hw->fc.requested_mode == ixgbe_fc_pfc) { + hw->fc.current_mode = hw->fc.requested_mode; + goto out; + } + +#endif /* CONFIG_DCB */ + /* Validate the packetbuf configuration */ + if (packetbuf_num < 0 || packetbuf_num > 7) { + hw_dbg(hw, "Invalid packet buffer number [%d], expected range " + "is 0-7\n", packetbuf_num); + ret_val = IXGBE_ERR_INVALID_LINK_SETTINGS; + goto out; + } + + /* + * Validate the water mark configuration. Zero water marks are invalid + * because it causes the controller to just blast out fc packets. + */ + if (!hw->fc.low_water || !hw->fc.high_water || !hw->fc.pause_time) { + hw_dbg(hw, "Invalid water mark configuration\n"); + ret_val = IXGBE_ERR_INVALID_LINK_SETTINGS; + goto out; + } + + /* + * 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"); + ret_val = IXGBE_ERR_INVALID_LINK_SETTINGS; + goto out; + } + + /* + * 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_fiber: + case ixgbe_media_type_backplane: + reg = IXGBE_READ_REG(hw, IXGBE_PCS1GANA); + reg_bp = IXGBE_READ_REG(hw, IXGBE_AUTOC); + break; + + case ixgbe_media_type_copper: + hw->phy.ops.read_reg(hw, MDIO_AN_ADVERTISE, + MDIO_MMD_AN, ®_cu); + break; + + default: + ; + } + + /* + * 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. +#ifdef CONFIG_DCB + * 4: Priority Flow Control is enabled. +#endif + * 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_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. + */ + 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_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; +#ifdef CONFIG_DCB + case ixgbe_fc_pfc: + goto out; + break; +#endif /* CONFIG_DCB */ + default: + hw_dbg(hw, "Flow control param set incorrectly\n"); + ret_val = IXGBE_ERR_CONFIG; + goto out; + break; + } + + 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) { + reg_bp |= IXGBE_AUTOC_AN_RESTART; + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, reg_bp); + } else if ((hw->phy.media_type == ixgbe_media_type_copper) && + (ixgbe_device_supports_autoneg_fc(hw) == 0)) { + 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); +out: + return ret_val; +} + +/** + * 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. + **/ +s32 ixgbe_disable_pcie_master(struct ixgbe_hw *hw) +{ + struct ixgbe_adapter *adapter = hw->back; + u32 i; + u32 reg_val; + u32 number_of_queues; + s32 status = 0; + u16 dev_status = 0; + + /* Just jump out if bus mastering is already disabled */ + if (!(IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_GIO)) + goto out; + + /* Disable the receive unit by stopping 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_RXDCTL(i)); + if (reg_val & IXGBE_RXDCTL_ENABLE) { + reg_val &= ~IXGBE_RXDCTL_ENABLE; + IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(i), reg_val); + } + } + + reg_val = IXGBE_READ_REG(hw, IXGBE_CTRL); + reg_val |= IXGBE_CTRL_GIO_DIS; + IXGBE_WRITE_REG(hw, IXGBE_CTRL, reg_val); + + for (i = 0; i < IXGBE_PCI_MASTER_DISABLE_TIMEOUT; i++) { + if (!(IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_GIO)) + goto check_device_status; + udelay(100); + } + + hw_dbg(hw, "GIO Master Disable bit didn't clear - requesting resets\n"); + status = IXGBE_ERR_MASTER_REQUESTS_PENDING; + + /* + * Before proceeding, make sure that the PCIe block does not have + * transactions pending. + */ +check_device_status: + for (i = 0; i < IXGBE_PCI_MASTER_DISABLE_TIMEOUT; i++) { + pci_read_config_word(adapter->pdev, IXGBE_PCI_DEVICE_STATUS, + &dev_status); + if (!(dev_status & IXGBE_PCI_DEVICE_STATUS_TRANSACTION_PENDING)) + break; + udelay(100); + } + + if (i == IXGBE_PCI_MASTER_DISABLE_TIMEOUT) + hw_dbg(hw, "PCIe transaction pending bit also did not clear.\n"); + else + goto out; + + /* + * 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 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->mac.flags |= IXGBE_FLAGS_DOUBLE_RESET_REQUIRED; + +out: + return status; +} + + +/** + * 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, u16 mask) +{ + u32 gssr; + u32 swmask = mask; + u32 fwmask = mask << 5; + s32 timeout = 200; + + while (timeout) { + /* + * SW EEPROM semaphore bit is used for access to all + * SW_FW_SYNC/GSSR bits (not just EEPROM) + */ + if (ixgbe_get_eeprom_semaphore(hw)) + return IXGBE_ERR_SWFW_SYNC; + + gssr = IXGBE_READ_REG(hw, IXGBE_GSSR); + if (!(gssr & (fwmask | swmask))) + break; + + /* + * Firmware currently using resource (fwmask) or other software + * thread currently using resource (swmask) + */ + ixgbe_release_eeprom_semaphore(hw); + usleep_range(5000, 10000); + timeout--; + } + + if (!timeout) { + hw_dbg(hw, "Driver can't access resource, SW_FW_SYNC timeout.\n"); + return IXGBE_ERR_SWFW_SYNC; + } + + gssr |= swmask; + IXGBE_WRITE_REG(hw, IXGBE_GSSR, gssr); + + ixgbe_release_eeprom_semaphore(hw); + return 0; +} + +/** + * 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, u16 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); +} + +/** + * 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) +{ + IXGBE_WRITE_REG(hw, IXGBE_RXCTRL, regval); + + 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 = 0; + u32 autoc_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC); + u32 led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); + + /* + * 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) { + autoc_reg |= IXGBE_AUTOC_AN_RESTART; + autoc_reg |= IXGBE_AUTOC_FLU; + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc_reg); + 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 = IXGBE_READ_REG(hw, IXGBE_AUTOC); + u32 led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); + + autoc_reg &= ~IXGBE_AUTOC_FLU; + autoc_reg |= IXGBE_AUTOC_AN_RESTART; + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc_reg); + + 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) +{ + /* + * First read the EEPROM pointer to see if the MAC addresses are + * available. + */ + hw->eeprom.ops.read(hw, IXGBE_SAN_MAC_ADDR_PTR, san_mac_offset); + + return 0; +} + +/** + * 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; + + /* + * 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. + */ + ixgbe_get_san_mac_addr_offset(hw, &san_mac_offset); + + if ((san_mac_offset == 0) || (san_mac_offset == 0xFFFF)) { + /* + * No addresses available in this EEPROM. It's not an + * error though, so just wipe the local address and return. + */ + for (i = 0; i < 6; i++) + san_mac_addr[i] = 0xFF; + + goto san_mac_addr_out; + } + + /* 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++) { + hw->eeprom.ops.read(hw, san_mac_offset, &san_mac_data); + san_mac_addr[i * 2] = (u8)(san_mac_data); + san_mac_addr[i * 2 + 1] = (u8)(san_mac_data >> 8); + san_mac_offset++; + } + +san_mac_addr_out: + return 0; +} + +/** + * 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. + **/ +u32 ixgbe_get_pcie_msix_count_generic(struct ixgbe_hw *hw) +{ + struct ixgbe_adapter *adapter = hw->back; + u16 msix_count; + pci_read_config_word(adapter->pdev, IXGBE_PCIE_MSIX_82599_CAPS, + &msix_count); + msix_count &= IXGBE_PCIE_MSIX_TBL_SZ_MASK; + + /* MSI-X count is zero-based in HW, so increment to give proper value */ + 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 (!mpsar_lo && !mpsar_hi) + goto done; + + 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 &= ~(1 << vmdq); + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_LO(rar), mpsar_lo); + } else { + mpsar_hi &= ~(1 << (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) + hw->mac.ops.clear_rar(hw, rar); +done: + 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 |= 1 << vmdq; + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_LO(rar), mpsar); + } else { + mpsar = IXGBE_READ_REG(hw, IXGBE_MPSAR_HI(rar)); + mpsar |= 1 << (vmdq - 32); + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_HI(rar), mpsar); + } + 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 + * + * return the VLVF index where this VLAN id should be placed + * + **/ +static s32 ixgbe_find_vlvf_slot(struct ixgbe_hw *hw, u32 vlan) +{ + u32 bits = 0; + u32 first_empty_slot = 0; + s32 regindex; + + /* short cut the special case */ + if (vlan == 0) + return 0; + + /* + * Search for the vlan id in the VLVF entries. Save off the first empty + * slot found along the way + */ + for (regindex = 1; regindex < IXGBE_VLVF_ENTRIES; regindex++) { + bits = IXGBE_READ_REG(hw, IXGBE_VLVF(regindex)); + if (!bits && !(first_empty_slot)) + first_empty_slot = regindex; + else if ((bits & 0x0FFF) == vlan) + break; + } + + /* + * If regindex is less than IXGBE_VLVF_ENTRIES, then we found the vlan + * in the VLVF. Else use the first empty VLVF register for this + * vlan id. + */ + if (regindex >= IXGBE_VLVF_ENTRIES) { + if (first_empty_slot) + regindex = first_empty_slot; + else { + hw_dbg(hw, "No space in VLVF.\n"); + regindex = IXGBE_ERR_NO_SPACE; + } + } + + return regindex; +} + +/** + * 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 + * + * 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) +{ + s32 regindex; + u32 bitindex; + u32 vfta; + u32 bits; + u32 vt; + u32 targetbit; + bool vfta_changed = false; + + if (vlan > 4095) + 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 + */ + regindex = (vlan >> 5) & 0x7F; + bitindex = vlan & 0x1F; + targetbit = (1 << bitindex); + vfta = IXGBE_READ_REG(hw, IXGBE_VFTA(regindex)); + + if (vlan_on) { + if (!(vfta & targetbit)) { + vfta |= targetbit; + vfta_changed = true; + } + } else { + if ((vfta & targetbit)) { + vfta &= ~targetbit; + vfta_changed = true; + } + } + + /* 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 + */ + vt = IXGBE_READ_REG(hw, IXGBE_VT_CTL); + if (vt & IXGBE_VT_CTL_VT_ENABLE) { + s32 vlvf_index; + + vlvf_index = ixgbe_find_vlvf_slot(hw, vlan); + if (vlvf_index < 0) + return vlvf_index; + + if (vlan_on) { + /* set the pool bit */ + if (vind < 32) { + bits = IXGBE_READ_REG(hw, + IXGBE_VLVFB(vlvf_index*2)); + bits |= (1 << vind); + IXGBE_WRITE_REG(hw, + IXGBE_VLVFB(vlvf_index*2), + bits); + } else { + bits = IXGBE_READ_REG(hw, + IXGBE_VLVFB((vlvf_index*2)+1)); + bits |= (1 << (vind-32)); + IXGBE_WRITE_REG(hw, + IXGBE_VLVFB((vlvf_index*2)+1), + bits); + } + } else { + /* clear the pool bit */ + if (vind < 32) { + bits = IXGBE_READ_REG(hw, + IXGBE_VLVFB(vlvf_index*2)); + bits &= ~(1 << vind); + IXGBE_WRITE_REG(hw, + IXGBE_VLVFB(vlvf_index*2), + bits); + bits |= IXGBE_READ_REG(hw, + IXGBE_VLVFB((vlvf_index*2)+1)); + } else { + bits = IXGBE_READ_REG(hw, + IXGBE_VLVFB((vlvf_index*2)+1)); + bits &= ~(1 << (vind-32)); + IXGBE_WRITE_REG(hw, + IXGBE_VLVFB((vlvf_index*2)+1), + bits); + bits |= IXGBE_READ_REG(hw, + IXGBE_VLVFB(vlvf_index*2)); + } + } + + /* + * 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. + */ + if (bits) { + IXGBE_WRITE_REG(hw, IXGBE_VLVF(vlvf_index), + (IXGBE_VLVF_VIEN | vlan)); + if (!vlan_on) { + /* someone wants to clear the vfta entry + * but some pools/VFs are still using it. + * Ignore it. */ + vfta_changed = false; + } + } + else + IXGBE_WRITE_REG(hw, IXGBE_VLVF(vlvf_index), 0); + } + + if (vfta_changed) + IXGBE_WRITE_REG(hw, IXGBE_VFTA(regindex), 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_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; + + /* 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; + } + + if ((links_reg & IXGBE_LINKS_SPEED_82599) == + IXGBE_LINKS_SPEED_10G_82599) + *speed = IXGBE_LINK_SPEED_10GB_FULL; + else if ((links_reg & IXGBE_LINKS_SPEED_82599) == + IXGBE_LINKS_SPEED_1G_82599) + *speed = IXGBE_LINK_SPEED_1GB_FULL; + else if ((links_reg & IXGBE_LINKS_SPEED_82599) == + IXGBE_LINKS_SPEED_100_82599) + *speed = IXGBE_LINK_SPEED_100_FULL; + else + *speed = IXGBE_LINK_SPEED_UNKNOWN; + + /* if link is down, zero out the current_mode */ + if (*link_up == false) { + hw->fc.current_mode = ixgbe_fc_none; + hw->fc.fc_was_autonegged = false; + } + + 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 */ + hw->eeprom.ops.read(hw, IXGBE_ALT_SAN_MAC_ADDR_BLK_PTR, + &alt_san_mac_blk_offset); + + if ((alt_san_mac_blk_offset == 0) || + (alt_san_mac_blk_offset == 0xFFFF)) + goto wwn_prefix_out; + + /* check capability in alternative san mac address block */ + offset = alt_san_mac_blk_offset + IXGBE_ALT_SAN_MAC_ADDR_CAPS_OFFSET; + hw->eeprom.ops.read(hw, offset, &caps); + if (!(caps & IXGBE_ALT_SAN_MAC_ADDR_CAPS_ALTWWN)) + goto wwn_prefix_out; + + /* get the corresponding prefix for WWNN/WWPN */ + offset = alt_san_mac_blk_offset + IXGBE_ALT_SAN_MAC_ADDR_WWNN_OFFSET; + hw->eeprom.ops.read(hw, offset, wwnn_prefix); + + offset = alt_san_mac_blk_offset + IXGBE_ALT_SAN_MAC_ADDR_WWPN_OFFSET; + hw->eeprom.ops.read(hw, offset, wwpn_prefix); + +wwn_prefix_out: + return 0; +} + +/** + * 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. + **/ +static s32 ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw) +{ + + switch (hw->device_id) { + case IXGBE_DEV_ID_X540T: + return 0; + case IXGBE_DEV_ID_82599_T3_LOM: + return 0; + default: + return IXGBE_ERR_FC_NOT_SUPPORTED; + } +} + +/** + * ixgbe_set_mac_anti_spoofing - Enable/Disable MAC anti-spoofing + * @hw: pointer to hardware structure + * @enable: enable or disable switch for anti-spoofing + * @pf: Physical Function pool - do not enable anti-spoofing for the PF + * + **/ +void ixgbe_set_mac_anti_spoofing(struct ixgbe_hw *hw, bool enable, int pf) +{ + int j; + int pf_target_reg = pf >> 3; + int pf_target_shift = pf % 8; + u32 pfvfspoof = 0; + + if (hw->mac.type == ixgbe_mac_82598EB) + return; + + if (enable) + pfvfspoof = IXGBE_SPOOF_MACAS_MASK; + + /* + * PFVFSPOOF register array is size 8 with 8 bits assigned to + * MAC anti-spoof enables in each register array element. + */ + for (j = 0; j < IXGBE_PFVFSPOOF_REG_COUNT; j++) + IXGBE_WRITE_REG(hw, IXGBE_PFVFSPOOF(j), pfvfspoof); + + /* If not enabling anti-spoofing then done */ + if (!enable) + return; + + /* + * The PF should be allowed to spoof so that it can support + * emulation mode NICs. Reset the bit assigned to the PF + */ + pfvfspoof = IXGBE_READ_REG(hw, IXGBE_PFVFSPOOF(pf_target_reg)); + pfvfspoof ^= (1 << pf_target_shift); + IXGBE_WRITE_REG(hw, IXGBE_PFVFSPOOF(pf_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 + * @pf: 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 |= (1 << vf_target_shift); + else + pfvfspoof &= ~(1 << 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); + /* Fall through to 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. + **/ +static 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_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 + * @lenght: lenght of buffer, must be multiple of 4 bytes + * + * Communicates with the manageability block. On success return 0 + * else return IXGBE_ERR_HOST_INTERFACE_COMMAND. + **/ +static s32 ixgbe_host_interface_command(struct ixgbe_hw *hw, u8 *buffer, + u32 length) +{ + u32 hicr, i; + u32 hdr_size = sizeof(struct ixgbe_hic_hdr); + u8 buf_len, dword_len; + + s32 ret_val = 0; + + if (length == 0 || length & 0x3 || + length > IXGBE_HI_MAX_BLOCK_BYTE_LENGTH) { + hw_dbg(hw, "Buffer length failure.\n"); + ret_val = IXGBE_ERR_HOST_INTERFACE_COMMAND; + goto out; + } + + /* Check that the host interface is enabled. */ + hicr = IXGBE_READ_REG(hw, IXGBE_HICR); + if ((hicr & IXGBE_HICR_EN) == 0) { + hw_dbg(hw, "IXGBE_HOST_EN bit disabled.\n"); + ret_val = IXGBE_ERR_HOST_INTERFACE_COMMAND; + goto out; + } + + /* Calculate length in DWORDs */ + 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, *((u32 *)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 < IXGBE_HI_COMMAND_TIMEOUT; i++) { + hicr = IXGBE_READ_REG(hw, IXGBE_HICR); + if (!(hicr & IXGBE_HICR_C)) + break; + usleep_range(1000, 2000); + } + + /* Check command successful completion. */ + if (i == IXGBE_HI_COMMAND_TIMEOUT || + (!(IXGBE_READ_REG(hw, IXGBE_HICR) & IXGBE_HICR_SV))) { + hw_dbg(hw, "Command has failed with no status valid.\n"); + ret_val = IXGBE_ERR_HOST_INTERFACE_COMMAND; + goto out; + } + + /* Calculate length in DWORDs */ + dword_len = hdr_size >> 2; + + /* first pull in the header so we know the buffer length */ + for (i = 0; i < dword_len; i++) + *((u32 *)buffer + i) = + IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, i); + + /* If there is any thing in data position pull it in */ + buf_len = ((struct ixgbe_hic_hdr *)buffer)->buf_len; + if (buf_len == 0) + goto out; + + if (length < (buf_len + hdr_size)) { + hw_dbg(hw, "Buffer not large enough for reply message.\n"); + ret_val = IXGBE_ERR_HOST_INTERFACE_COMMAND; + goto out; + } + + /* Calculate length in DWORDs, add one for odd lengths */ + dword_len = (buf_len + 1) >> 2; + + /* Pull in the rest of the buffer (i is where we left off)*/ + for (; i < buf_len; i++) + *((u32 *)buffer + i) = + IXGBE_READ_REG_ARRAY(hw, IXGBE_FLEX_MNG, i); + +out: + return ret_val; +} + +/** + * 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 + * + * 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) +{ + struct ixgbe_hic_drv_info fw_cmd; + int i; + s32 ret_val = 0; + + if (hw->mac.ops.acquire_swfw_sync(hw, IXGBE_GSSR_SW_MNG_SM) != 0) { + ret_val = IXGBE_ERR_SWFW_SYNC; + goto out; + } + + 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 = (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; + fw_cmd.hdr.checksum = ixgbe_calculate_checksum((u8 *)&fw_cmd, + (FW_CEM_HDR_LEN + fw_cmd.hdr.buf_len)); + fw_cmd.pad = 0; + fw_cmd.pad2 = 0; + + for (i = 0; i <= FW_CEM_MAX_RETRIES; i++) { + ret_val = ixgbe_host_interface_command(hw, (u8 *)&fw_cmd, + sizeof(fw_cmd)); + 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; + } + + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_SW_MNG_SM); +out: + return ret_val; +} 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 000000000000..f24fd64a4c46 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h @@ -0,0 +1,145 @@ +/******************************************************************************* + + Intel 10 Gigabit PCI Express Linux driver + Copyright(c) 1999 - 2011 Intel Corporation. + + This program is free software; you can redistribute it and/or modify it + under the terms and conditions of the GNU General Public License, + version 2, as published by the Free Software Foundation. + + This program is distributed in the hope it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + more details. + + You should have received a copy of the GNU General Public License along with + this program; if not, write to the Free Software Foundation, Inc., + 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + + The full GNU General Public License is included in this distribution in + the file called "COPYING". + + Contact Information: + e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + +*******************************************************************************/ + +#ifndef _IXGBE_COMMON_H_ +#define _IXGBE_COMMON_H_ + +#include "ixgbe_type.h" +#include "ixgbe.h" + +u32 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); +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_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); +u16 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_enable_rx_dma_generic(struct ixgbe_hw *hw, u32 regval); +s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw, s32 packtetbuf_num); +s32 ixgbe_fc_autoneg(struct ixgbe_hw *hw); + +s32 ixgbe_validate_mac_addr(u8 *mac_addr); +s32 ixgbe_acquire_swfw_sync(struct ixgbe_hw *hw, u16 mask); +void ixgbe_release_swfw_sync(struct ixgbe_hw *hw, u16 mask); +s32 ixgbe_disable_pcie_master(struct ixgbe_hw *hw); +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_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); +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 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 pf); +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); + +void ixgbe_set_rxpba_generic(struct ixgbe_hw *hw, int num_pb, + u32 headroom, int strategy); + +#define IXGBE_WRITE_REG(a, reg, value) writel((value), ((a)->hw_addr + (reg))) + +#ifndef writeq +#define writeq(val, addr) writel((u32) (val), addr); \ + writel((u32) (val >> 32), (addr + 4)); +#endif + +#define IXGBE_WRITE_REG64(a, reg, value) writeq((value), ((a)->hw_addr + (reg))) + +#define IXGBE_READ_REG(a, reg) readl((a)->hw_addr + (reg)) + +#define IXGBE_WRITE_REG_ARRAY(a, reg, offset, value) (\ + writel((value), ((a)->hw_addr + (reg) + ((offset) << 2)))) + +#define IXGBE_READ_REG_ARRAY(a, reg, offset) (\ + readl((a)->hw_addr + (reg) + ((offset) << 2))) + +#define IXGBE_WRITE_FLUSH(a) IXGBE_READ_REG(a, IXGBE_STATUS) + +#define hw_dbg(hw, format, arg...) \ + netdev_dbg(((struct ixgbe_adapter *)(hw->back))->netdev, 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 000000000000..9d88c31487bc --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.c @@ -0,0 +1,320 @@ +/******************************************************************************* + + Intel 10 Gigabit PCI Express Linux driver + Copyright(c) 1999 - 2011 Intel Corporation. + + This program is free software; you can redistribute it and/or modify it + under the terms and conditions of the GNU General Public License, + version 2, as published by the Free Software Foundation. + + This program is distributed in the hope it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + more details. + + You should have received a copy of the GNU General Public License along with + this program; if not, write to the Free Software Foundation, Inc., + 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + + The full GNU General Public License is included in this distribution in + the file called "COPYING". + + Contact Information: + Linux NICS <linux.nics@intel.com> + e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + +*******************************************************************************/ + + +#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. + */ +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 + * @ixgbe_dcb_config: Struct containing DCB settings. + * @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; + s32 ret_val = 0; + /* 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 == NULL) { + ret_val = DCB_ERR_CONFIG; + goto out; + } + + 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); + 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 && (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; + } + +out: + return ret_val; +} + +void ixgbe_dcb_unpack_pfc(struct ixgbe_dcb_config *cfg, u8 *pfc_en) +{ + int i; + + *pfc_en = 0; + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) + *pfc_en |= (cfg->tc_config[i].dcb_pfc & 0xF) << i; +} + +void ixgbe_dcb_unpack_refill(struct ixgbe_dcb_config *cfg, int direction, + u16 *refill) +{ + struct tc_bw_alloc *p; + int i; + + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + p = &cfg->tc_config[i].path[direction]; + refill[i] = p->data_credits_refill; + } +} + +void ixgbe_dcb_unpack_max(struct ixgbe_dcb_config *cfg, u16 *max) +{ + int i; + + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) + max[i] = cfg->tc_config[i].desc_credits_max; +} + +void ixgbe_dcb_unpack_bwgid(struct ixgbe_dcb_config *cfg, int direction, + u8 *bwgid) +{ + struct tc_bw_alloc *p; + int i; + + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + p = &cfg->tc_config[i].path[direction]; + bwgid[i] = p->bwg_id; + } +} + +void ixgbe_dcb_unpack_prio(struct ixgbe_dcb_config *cfg, int direction, + u8 *ptype) +{ + struct tc_bw_alloc *p; + int i; + + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + p = &cfg->tc_config[i].path[direction]; + ptype[i] = p->prio_type; + } +} + +/** + * 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) +{ + s32 ret = 0; + u8 pfc_en; + u8 ptype[MAX_TRAFFIC_CLASS]; + u8 bwgid[MAX_TRAFFIC_CLASS]; + u16 refill[MAX_TRAFFIC_CLASS]; + u16 max[MAX_TRAFFIC_CLASS]; + /* CEE does not define a priority to tc mapping so map 1:1 */ + u8 prio_tc[MAX_TRAFFIC_CLASS] = {0, 1, 2, 3, 4, 5, 6, 7}; + + /* 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); + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + ret = ixgbe_dcb_hw_config_82598(hw, pfc_en, refill, max, + bwgid, ptype); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + ret = ixgbe_dcb_hw_config_82599(hw, pfc_en, refill, max, + bwgid, ptype, prio_tc); + break; + default: + break; + } + return ret; +} + +/* Helper routines to abstract HW specifics from DCB netlink ops */ +s32 ixgbe_dcb_hw_pfc_config(struct ixgbe_hw *hw, u8 pfc_en) +{ + int ret = -EINVAL; + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + ret = ixgbe_dcb_config_pfc_82598(hw, pfc_en); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + ret = ixgbe_dcb_config_pfc_82599(hw, pfc_en); + break; + default: + break; + } + return ret; +} + +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: + 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; +} 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 000000000000..e85826ae0320 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h @@ -0,0 +1,167 @@ +/******************************************************************************* + + Intel 10 Gigabit PCI Express Linux driver + Copyright(c) 1999 - 2011 Intel Corporation. + + This program is free software; you can redistribute it and/or modify it + under the terms and conditions of the GNU General Public License, + version 2, as published by the Free Software Foundation. + + This program is distributed in the hope it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + more details. + + You should have received a copy of the GNU General Public License along with + this program; if not, write to the Free Software Foundation, Inc., + 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + + The full GNU General Public License is included in this distribution in + the file called "COPYING". + + Contact Information: + Linux NICS <linux.nics@intel.com> + e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + +*******************************************************************************/ + +#ifndef _DCB_CONFIG_H_ +#define _DCB_CONFIG_H_ + +#include "ixgbe_type.h" + +/* DCB data structures */ + +#define IXGBE_MAX_PACKET_BUFFERS 8 +#define MAX_USER_PRIORITY 8 +#define MAX_TRAFFIC_CLASS 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 *); + +/* DCB credits calculation */ +s32 ixgbe_ieee_credits(__u8 *bw, __u16 *refill, __u16 *max, int max_frame); +s32 ixgbe_dcb_calculate_tc_credits(struct ixgbe_hw *, + struct ixgbe_dcb_config *, int, u8); + +/* DCB hw initialization */ +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); +s32 ixgbe_dcb_hw_config(struct ixgbe_hw *, struct ixgbe_dcb_config *); + +/* 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 000000000000..2288c3cac010 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c @@ -0,0 +1,297 @@ +/******************************************************************************* + + Intel 10 Gigabit PCI Express Linux driver + Copyright(c) 1999 - 2011 Intel Corporation. + + This program is free software; you can redistribute it and/or modify it + under the terms and conditions of the GNU General Public License, + version 2, as published by the Free Software Foundation. + + This program is distributed in the hope it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + more details. + + You should have received a copy of the GNU General Public License along with + this program; if not, write to the Free Software Foundation, Inc., + 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + + The full GNU General Public License is included in this distribution in + the file called "COPYING". + + Contact Information: + Linux NICS <linux.nics@intel.com> + e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + +*******************************************************************************/ + +#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 + * @dcb_config: pointer to ixgbe_dcb_config structure + * + * 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 + * @dcb_config: pointer to ixgbe_dcb_config structure + * + * 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; + /* Enable DFP and Recycle mode */ + reg |= (IXGBE_DPMCS_TDPAC | IXGBE_DPMCS_TRM); + 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 + * @dcb_config: pointer to ixgbe_dcb_config structure + * + * 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 + * @dcb_config: pointer to ixgbe_dcb_config structure + * + * Configure Priority Flow Control for each traffic class. + */ +s32 ixgbe_dcb_config_pfc_82598(struct ixgbe_hw *hw, u8 pfc_en) +{ + u32 reg, rx_pba_size; + u8 i; + + if (pfc_en) { + /* Enable Transmit Priority Flow Control */ + reg = IXGBE_READ_REG(hw, IXGBE_RMCS); + reg &= ~IXGBE_RMCS_TFCE_802_3X; + /* correct the reporting of our flow control status */ + 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_RFCE; + reg |= IXGBE_FCTRL_RPFCE; + IXGBE_WRITE_REG(hw, IXGBE_FCTRL, reg); + + /* Configure pause time */ + for (i = 0; i < (MAX_TRAFFIC_CLASS >> 1); i++) + IXGBE_WRITE_REG(hw, IXGBE_FCTTV(i), 0x68006800); + + /* Configure flow control refresh threshold value */ + IXGBE_WRITE_REG(hw, IXGBE_FCRTV, 0x3400); + } + + /* + * Configure flow control thresholds and enable priority flow control + * for each traffic class. + */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + int enabled = pfc_en & (1 << i); + rx_pba_size = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(i)); + rx_pba_size >>= IXGBE_RXPBSIZE_SHIFT; + reg = (rx_pba_size - hw->fc.low_water) << 10; + + if (enabled == pfc_enabled_tx || + enabled == pfc_enabled_full) + reg |= IXGBE_FCRTL_XONE; + + IXGBE_WRITE_REG(hw, IXGBE_FCRTL(i), reg); + + reg = (rx_pba_size - hw->fc.high_water) << 10; + if (enabled == pfc_enabled_tx || + enabled == pfc_enabled_full) + reg |= IXGBE_FCRTH_FCEN; + + IXGBE_WRITE_REG(hw, IXGBE_FCRTH(i), reg); + } + + 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 + * @dcb_config: pointer to ixgbe_dcb_config structure + * + * 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 000000000000..2f318935561a --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.h @@ -0,0 +1,97 @@ +/******************************************************************************* + + Intel 10 Gigabit PCI Express Linux driver + Copyright(c) 1999 - 2011 Intel Corporation. + + This program is free software; you can redistribute it and/or modify it + under the terms and conditions of the GNU General Public License, + version 2, as published by the Free Software Foundation. + + This program is distributed in the hope it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + more details. + + You should have received a copy of the GNU General Public License along with + this program; if not, write to the Free Software Foundation, Inc., + 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + + The full GNU General Public License is included in this distribution in + the file called "COPYING". + + Contact Information: + Linux NICS <linux.nics@intel.com> + e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + +*******************************************************************************/ + +#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 000000000000..ade98200288c --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c @@ -0,0 +1,346 @@ +/******************************************************************************* + + Intel 10 Gigabit PCI Express Linux driver + Copyright(c) 1999 - 2011 Intel Corporation. + + This program is free software; you can redistribute it and/or modify it + under the terms and conditions of the GNU General Public License, + version 2, as published by the Free Software Foundation. + + This program is distributed in the hope it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + more details. + + You should have received a copy of the GNU General Public License along with + this program; if not, write to the Free Software Foundation, Inc., + 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + + The full GNU General Public License is included in this distribution in + the file called "COPYING". + + Contact Information: + e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + +*******************************************************************************/ + +#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 + * + * 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, 1 to 1 */ + reg = 0; + for (i = 0; i < MAX_TRAFFIC_CLASS; 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 + * + * 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, 1 to 1 */ + reg = 0; + for (i = 0; i < MAX_TRAFFIC_CLASS; 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 + * + * Configure Priority Flow Control (PFC) for each traffic class. + */ +s32 ixgbe_dcb_config_pfc_82599(struct ixgbe_hw *hw, u8 pfc_en) +{ + u32 i, reg, rx_pba_size; + + /* Configure PFC Tx thresholds per TC */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + int enabled = pfc_en & (1 << i); + rx_pba_size = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(i)); + rx_pba_size >>= IXGBE_RXPBSIZE_SHIFT; + + reg = (rx_pba_size - hw->fc.low_water) << 10; + + if (enabled) + reg |= IXGBE_FCRTL_XONE; + IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(i), reg); + + reg = (rx_pba_size - hw->fc.high_water) << 10; + if (enabled) + reg |= IXGBE_FCRTH_FCEN; + IXGBE_WRITE_REG(hw, IXGBE_FCRTH_82599(i), reg); + } + + if (pfc_en) { + /* Configure pause time (2 TCs per register) */ + reg = hw->fc.pause_time | (hw->fc.pause_time << 16); + 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); + + + reg = IXGBE_FCCFG_TFCE_PRIORITY; + IXGBE_WRITE_REG(hw, IXGBE_FCCFG, reg); + /* + * Enable Receive PFC + * 82599 will always honor XOFF frames we receive when + * we are in PFC mode however X540 only honors enabled + * traffic classes. + */ + reg = IXGBE_READ_REG(hw, IXGBE_MFLCN); + reg &= ~IXGBE_MFLCN_RFCE; + reg |= IXGBE_MFLCN_RPFCE | IXGBE_MFLCN_DPF; + + if (hw->mac.type == ixgbe_mac_X540) + reg |= pfc_en << IXGBE_MFLCN_RPFCE_SHIFT; + + IXGBE_WRITE_REG(hw, IXGBE_MFLCN, reg); + + } else { + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) + hw->mac.ops.fc_enable(hw, i); + } + + 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 + * @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 + * @pfc_en: enabled pfc bitmask + * + * 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); + 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 000000000000..08d1749862a3 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.h @@ -0,0 +1,123 @@ +/******************************************************************************* + + Intel 10 Gigabit PCI Express Linux driver + Copyright(c) 1999 - 2011 Intel Corporation. + + This program is free software; you can redistribute it and/or modify it + under the terms and conditions of the GNU General Public License, + version 2, as published by the Free Software Foundation. + + This program is distributed in the hope it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + more details. + + You should have received a copy of the GNU General Public License along with + this program; if not, write to the Free Software Foundation, Inc., + 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + + The full GNU General Public License is included in this distribution in + the file called "COPYING". + + Contact Information: + e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + +*******************************************************************************/ + +#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 +/* 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); + +/* 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 000000000000..0ace6ce1d0b4 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c @@ -0,0 +1,816 @@ +/******************************************************************************* + + Intel 10 Gigabit PCI Express Linux driver + Copyright(c) 1999 - 2011 Intel Corporation. + + This program is free software; you can redistribute it and/or modify it + under the terms and conditions of the GNU General Public License, + version 2, as published by the Free Software Foundation. + + This program is distributed in the hope it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + more details. + + You should have received a copy of the GNU General Public License along with + this program; if not, write to the Free Software Foundation, Inc., + 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + + The full GNU General Public License is included in this distribution in + the file called "COPYING". + + Contact Information: + Linux NICS <linux.nics@intel.com> + e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + +*******************************************************************************/ + +#include "ixgbe.h" +#include <linux/dcbnl.h> +#include "ixgbe_dcb_82598.h" +#include "ixgbe_dcb_82599.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 */ + +int ixgbe_copy_dcb_cfg(struct ixgbe_dcb_config *src_dcb_cfg, + struct ixgbe_dcb_config *dst_dcb_cfg, int tc_max) +{ + struct tc_configuration *src_tc_cfg = NULL; + struct tc_configuration *dst_tc_cfg = NULL; + int i; + + if (!src_dcb_cfg || !dst_dcb_cfg) + return -EINVAL; + + for (i = DCB_PG_ATTR_TC_0; i < tc_max + DCB_PG_ATTR_TC_0; i++) { + src_tc_cfg = &src_dcb_cfg->tc_config[i - DCB_PG_ATTR_TC_0]; + dst_tc_cfg = &dst_dcb_cfg->tc_config[i - DCB_PG_ATTR_TC_0]; + + dst_tc_cfg->path[DCB_TX_CONFIG].prio_type = + src_tc_cfg->path[DCB_TX_CONFIG].prio_type; + + dst_tc_cfg->path[DCB_TX_CONFIG].bwg_id = + src_tc_cfg->path[DCB_TX_CONFIG].bwg_id; + + dst_tc_cfg->path[DCB_TX_CONFIG].bwg_percent = + src_tc_cfg->path[DCB_TX_CONFIG].bwg_percent; + + dst_tc_cfg->path[DCB_TX_CONFIG].up_to_tc_bitmap = + src_tc_cfg->path[DCB_TX_CONFIG].up_to_tc_bitmap; + + dst_tc_cfg->path[DCB_RX_CONFIG].prio_type = + src_tc_cfg->path[DCB_RX_CONFIG].prio_type; + + dst_tc_cfg->path[DCB_RX_CONFIG].bwg_id = + src_tc_cfg->path[DCB_RX_CONFIG].bwg_id; + + dst_tc_cfg->path[DCB_RX_CONFIG].bwg_percent = + src_tc_cfg->path[DCB_RX_CONFIG].bwg_percent; + + dst_tc_cfg->path[DCB_RX_CONFIG].up_to_tc_bitmap = + src_tc_cfg->path[DCB_RX_CONFIG].up_to_tc_bitmap; + } + + for (i = DCB_PG_ATTR_BW_ID_0; i < DCB_PG_ATTR_BW_ID_MAX; i++) { + dst_dcb_cfg->bw_percentage[DCB_TX_CONFIG] + [i-DCB_PG_ATTR_BW_ID_0] = src_dcb_cfg->bw_percentage + [DCB_TX_CONFIG][i-DCB_PG_ATTR_BW_ID_0]; + dst_dcb_cfg->bw_percentage[DCB_RX_CONFIG] + [i-DCB_PG_ATTR_BW_ID_0] = src_dcb_cfg->bw_percentage + [DCB_RX_CONFIG][i-DCB_PG_ATTR_BW_ID_0]; + } + + for (i = DCB_PFC_UP_ATTR_0; i < DCB_PFC_UP_ATTR_MAX; i++) { + dst_dcb_cfg->tc_config[i - DCB_PFC_UP_ATTR_0].dcb_pfc = + src_dcb_cfg->tc_config[i - DCB_PFC_UP_ATTR_0].dcb_pfc; + } + + dst_dcb_cfg->pfc_mode_enable = src_dcb_cfg->pfc_mode_enable; + + return 0; +} + +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) +{ + u8 err = 0; + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + /* verify there is something to do, if not then exit */ + if (!!state != !(adapter->flags & IXGBE_FLAG_DCB_ENABLED)) + return err; + + if (state > 0) { + /* Turn on DCB */ + if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) { + e_err(drv, "Enable failed, needs MSI-X\n"); + err = 1; + goto out; + } + + adapter->flags |= IXGBE_FLAG_DCB_ENABLED; + + switch (adapter->hw.mac.type) { + case ixgbe_mac_82598EB: + adapter->last_lfc_mode = adapter->hw.fc.current_mode; + adapter->hw.fc.requested_mode = ixgbe_fc_none; + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; + break; + default: + break; + } + + ixgbe_setup_tc(netdev, MAX_TRAFFIC_CLASS); + } else { + /* Turn off DCB */ + adapter->hw.fc.requested_mode = adapter->last_lfc_mode; + adapter->temp_dcb_cfg.pfc_mode_enable = false; + adapter->dcb_cfg.pfc_mode_enable = false; + adapter->flags &= ~IXGBE_FLAG_DCB_ENABLED; + switch (adapter->hw.mac.type) { + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + if (!(adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE)) + adapter->flags |= IXGBE_FLAG_FDIR_HASH_CAPABLE; + break; + default: + break; + } + ixgbe_setup_tc(netdev, 0); + } + +out: + return err; +} + +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: + 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; + + if ((adapter->temp_dcb_cfg.tc_config[tc].path[0].prio_type != + adapter->dcb_cfg.tc_config[tc].path[0].prio_type) || + (adapter->temp_dcb_cfg.tc_config[tc].path[0].bwg_id != + adapter->dcb_cfg.tc_config[tc].path[0].bwg_id) || + (adapter->temp_dcb_cfg.tc_config[tc].path[0].bwg_percent != + adapter->dcb_cfg.tc_config[tc].path[0].bwg_percent) || + (adapter->temp_dcb_cfg.tc_config[tc].path[0].up_to_tc_bitmap != + adapter->dcb_cfg.tc_config[tc].path[0].up_to_tc_bitmap)) + adapter->dcb_set_bitmap |= BIT_PG_TX; +} + +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; + + if (adapter->temp_dcb_cfg.bw_percentage[0][bwg_id] != + adapter->dcb_cfg.bw_percentage[0][bwg_id]) + adapter->dcb_set_bitmap |= BIT_PG_TX; +} + +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; + + if ((adapter->temp_dcb_cfg.tc_config[tc].path[1].prio_type != + adapter->dcb_cfg.tc_config[tc].path[1].prio_type) || + (adapter->temp_dcb_cfg.tc_config[tc].path[1].bwg_id != + adapter->dcb_cfg.tc_config[tc].path[1].bwg_id) || + (adapter->temp_dcb_cfg.tc_config[tc].path[1].bwg_percent != + adapter->dcb_cfg.tc_config[tc].path[1].bwg_percent) || + (adapter->temp_dcb_cfg.tc_config[tc].path[1].up_to_tc_bitmap != + adapter->dcb_cfg.tc_config[tc].path[1].up_to_tc_bitmap)) + adapter->dcb_set_bitmap |= BIT_PG_RX; +} + +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; + + if (adapter->temp_dcb_cfg.bw_percentage[1][bwg_id] != + adapter->dcb_cfg.bw_percentage[1][bwg_id]) + adapter->dcb_set_bitmap |= BIT_PG_RX; +} + +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->dcb_set_bitmap |= BIT_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 u8 ixgbe_dcbnl_set_all(struct net_device *netdev) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + int ret; +#ifdef IXGBE_FCOE + struct dcb_app app = { + .selector = DCB_APP_IDTYPE_ETHTYPE, + .protocol = ETH_P_FCOE, + }; + u8 up = dcb_getapp(netdev, &app); +#endif + + ret = ixgbe_copy_dcb_cfg(&adapter->temp_dcb_cfg, &adapter->dcb_cfg, + MAX_TRAFFIC_CLASS); + if (ret) + return DCB_NO_HW_CHG; + +#ifdef IXGBE_FCOE + if (up && (up != (1 << adapter->fcoe.up))) + adapter->dcb_set_bitmap |= BIT_APP_UPCHG; + + /* + * Only take down the adapter if an app change occurred. FCoE + * may shuffle tx rings in this case and this can not be done + * without a reset currently. + */ + if (adapter->dcb_set_bitmap & BIT_APP_UPCHG) { + while (test_and_set_bit(__IXGBE_RESETTING, &adapter->state)) + usleep_range(1000, 2000); + + adapter->fcoe.up = ffs(up) - 1; + + if (netif_running(netdev)) + netdev->netdev_ops->ndo_stop(netdev); + ixgbe_clear_interrupt_scheme(adapter); + } +#endif + + if (adapter->dcb_cfg.pfc_mode_enable) { + switch (adapter->hw.mac.type) { + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + if (adapter->hw.fc.current_mode != ixgbe_fc_pfc) + adapter->last_lfc_mode = + adapter->hw.fc.current_mode; + break; + default: + break; + } + adapter->hw.fc.requested_mode = ixgbe_fc_pfc; + } else { + switch (adapter->hw.mac.type) { + case ixgbe_mac_82598EB: + adapter->hw.fc.requested_mode = ixgbe_fc_none; + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + adapter->hw.fc.requested_mode = adapter->last_lfc_mode; + break; + default: + break; + } + } + +#ifdef IXGBE_FCOE + if (adapter->dcb_set_bitmap & BIT_APP_UPCHG) { + ixgbe_init_interrupt_scheme(adapter); + if (netif_running(netdev)) + netdev->netdev_ops->ndo_open(netdev); + ret = DCB_HW_CHG_RST; + } +#endif + + if (adapter->dcb_set_bitmap & BIT_PFC) { + u8 pfc_en; + ixgbe_dcb_unpack_pfc(&adapter->dcb_cfg, &pfc_en); + ixgbe_dcb_hw_pfc_config(&adapter->hw, pfc_en); + ret = DCB_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_TRAFFIC_CLASS] = {0, 1, 2, 3, 4, 5, 6, 7}; + int max_frame = adapter->netdev->mtu + ETH_HLEN + ETH_FCS_LEN; + +#ifdef CONFIG_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(&adapter->hw, &adapter->dcb_cfg, + max_frame, DCB_TX_CONFIG); + ixgbe_dcb_calculate_tc_credits(&adapter->hw, &adapter->dcb_cfg, + max_frame, DCB_RX_CONFIG); + + ixgbe_dcb_unpack_refill(&adapter->dcb_cfg, + DCB_TX_CONFIG, refill); + ixgbe_dcb_unpack_max(&adapter->dcb_cfg, max); + ixgbe_dcb_unpack_bwgid(&adapter->dcb_cfg, + DCB_TX_CONFIG, bwg_id); + ixgbe_dcb_unpack_prio(&adapter->dcb_cfg, + DCB_TX_CONFIG, prio_type); + + ixgbe_dcb_hw_ets_config(&adapter->hw, refill, max, + bwg_id, prio_type, prio_tc); + } + + if (adapter->dcb_cfg.pfc_mode_enable) + adapter->hw.fc.current_mode = ixgbe_fc_pfc; + + if (adapter->dcb_set_bitmap & BIT_APP_UPCHG) + clear_bit(__IXGBE_RESETTING, &adapter->state); + 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 u8 ixgbe_dcbnl_getnumtcs(struct net_device *netdev, int tcid, u8 *num) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + u8 rval = 0; + + if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) { + switch (tcid) { + case DCB_NUMTCS_ATTR_PG: + *num = MAX_TRAFFIC_CLASS; + break; + case DCB_NUMTCS_ATTR_PFC: + *num = MAX_TRAFFIC_CLASS; + break; + default: + rval = -EINVAL; + break; + } + } else { + rval = -EINVAL; + } + + return rval; +} + +static u8 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; + if (adapter->temp_dcb_cfg.pfc_mode_enable != + adapter->dcb_cfg.pfc_mode_enable) + adapter->dcb_set_bitmap |= BIT_PFC; +} + +/** + * 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 0 as the invalid user priority bitmap to indicate an + * error. + */ +static u8 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 0; + + 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; + + /* No IEEE PFC settings available */ + if (!my_ets) + return -EINVAL; + + ets->ets_cap = MAX_TRAFFIC_CLASS; + 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); + __u16 refill[IEEE_8021QAZ_MAX_TCS], max[IEEE_8021QAZ_MAX_TCS]; + __u8 prio_type[IEEE_8021QAZ_MAX_TCS]; + int max_frame = dev->mtu + ETH_HLEN + ETH_FCS_LEN; + int i, err; + __u64 *p = (__u64 *) ets->prio_tc; + /* 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}; + + 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; + } + + memcpy(adapter->ixgbe_ieee_ets, ets, sizeof(*adapter->ixgbe_ieee_ets)); + + /* 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; + } + } + + if (*p) + ixgbe_dcbnl_set_state(dev, 1); + else + ixgbe_dcbnl_set_state(dev, 0); + + ixgbe_ieee_credits(ets->tc_tx_bw, refill, max, max_frame); + err = ixgbe_dcb_hw_ets_config(&adapter->hw, refill, max, + bwg_id, prio_type, ets->prio_tc); + return err; +} + +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; + + /* No IEEE PFC settings available */ + if (!my_pfc) + return -EINVAL; + + pfc->pfc_cap = MAX_TRAFFIC_CLASS; + 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); + 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; + } + + memcpy(adapter->ixgbe_ieee_pfc, pfc, sizeof(*adapter->ixgbe_ieee_pfc)); + err = ixgbe_dcb_hw_pfc_config(&adapter->hw, pfc->pfc_en); + return err; +} + +#ifdef IXGBE_FCOE +static void ixgbe_dcbnl_devreset(struct net_device *dev) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + + 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); +} +#endif + +static int ixgbe_dcbnl_ieee_setapp(struct net_device *dev, + struct dcb_app *app) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + int err = -EINVAL; + + if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) + return err; + + err = dcb_ieee_setapp(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 & (1 << adapter->fcoe.up)) + return err; + + adapter->fcoe.up = app->priority; + ixgbe_dcbnl_devreset(dev); + } +#endif + 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 & (1 << adapter->fcoe.up)) + return err; + + adapter->fcoe.up = app_mask ? + ffs(app_mask) - 1 : IXGBE_FCOE_DEFTC; + ixgbe_dcbnl_devreset(dev); + } +#endif + 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}; + + /* 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) { + adapter->dcb_set_bitmap |= (BIT_PFC & BIT_PG_TX & BIT_PG_RX); + 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); + ixgbe_dcbnl_set_state(dev, 0); + } + + return 0; +} + +const struct dcbnl_rtnl_ops 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_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c new file mode 100644 index 000000000000..82d4244c6e10 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -0,0 +1,2592 @@ +/******************************************************************************* + + Intel 10 Gigabit PCI Express Linux driver + Copyright(c) 1999 - 2011 Intel Corporation. + + This program is free software; you can redistribute it and/or modify it + under the terms and conditions of the GNU General Public License, + version 2, as published by the Free Software Foundation. + + This program is distributed in the hope it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + more details. + + You should have received a copy of the GNU General Public License along with + this program; if not, write to the Free Software Foundation, Inc., + 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + + The full GNU General Public License is included in this distribution in + the file called "COPYING". + + Contact Information: + e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + +*******************************************************************************/ + +/* 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/uaccess.h> + +#include "ixgbe.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 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_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_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)}, +#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)}, + {"tx_fcoe_packets", IXGBE_STAT(stats.fcoeptc)}, + {"tx_fcoe_dwords", IXGBE_STAT(stats.fcoedwtc)}, +#endif /* IXGBE_FCOE */ +}; + +#define IXGBE_QUEUE_STATS_LEN \ + ((((struct ixgbe_adapter *)netdev_priv(netdev))->num_tx_queues + \ + ((struct ixgbe_adapter *)netdev_priv(netdev))->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 ( \ + (((struct ixgbe_adapter *)netdev_priv(netdev))->flags & \ + IXGBE_FLAG_DCB_ENABLED) ? \ + (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) : 0) +#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 int ixgbe_get_settings(struct net_device *netdev, + struct ethtool_cmd *ecmd) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + u32 link_speed = 0; + bool link_up; + + ecmd->supported = SUPPORTED_10000baseT_Full; + ecmd->autoneg = AUTONEG_ENABLE; + ecmd->transceiver = XCVR_EXTERNAL; + if ((hw->phy.media_type == ixgbe_media_type_copper) || + (hw->phy.multispeed_fiber)) { + ecmd->supported |= (SUPPORTED_1000baseT_Full | + SUPPORTED_Autoneg); + + switch (hw->mac.type) { + case ixgbe_mac_X540: + ecmd->supported |= SUPPORTED_100baseT_Full; + break; + default: + break; + } + + ecmd->advertising = ADVERTISED_Autoneg; + if (hw->phy.autoneg_advertised) { + if (hw->phy.autoneg_advertised & + IXGBE_LINK_SPEED_100_FULL) + ecmd->advertising |= ADVERTISED_100baseT_Full; + if (hw->phy.autoneg_advertised & + IXGBE_LINK_SPEED_10GB_FULL) + ecmd->advertising |= ADVERTISED_10000baseT_Full; + if (hw->phy.autoneg_advertised & + IXGBE_LINK_SPEED_1GB_FULL) + ecmd->advertising |= ADVERTISED_1000baseT_Full; + } else { + /* + * Default advertised modes in case + * phy.autoneg_advertised isn't set. + */ + ecmd->advertising |= (ADVERTISED_10000baseT_Full | + ADVERTISED_1000baseT_Full); + if (hw->mac.type == ixgbe_mac_X540) + ecmd->advertising |= ADVERTISED_100baseT_Full; + } + + if (hw->phy.media_type == ixgbe_media_type_copper) { + ecmd->supported |= SUPPORTED_TP; + ecmd->advertising |= ADVERTISED_TP; + ecmd->port = PORT_TP; + } else { + ecmd->supported |= SUPPORTED_FIBRE; + ecmd->advertising |= ADVERTISED_FIBRE; + ecmd->port = PORT_FIBRE; + } + } else if (hw->phy.media_type == ixgbe_media_type_backplane) { + /* Set as FIBRE until SERDES defined in kernel */ + if (hw->device_id == IXGBE_DEV_ID_82598_BX) { + ecmd->supported = (SUPPORTED_1000baseT_Full | + SUPPORTED_FIBRE); + ecmd->advertising = (ADVERTISED_1000baseT_Full | + ADVERTISED_FIBRE); + ecmd->port = PORT_FIBRE; + ecmd->autoneg = AUTONEG_DISABLE; + } else if ((hw->device_id == IXGBE_DEV_ID_82599_COMBO_BACKPLANE) || + (hw->device_id == IXGBE_DEV_ID_82599_KX4_MEZZ)) { + ecmd->supported |= (SUPPORTED_1000baseT_Full | + SUPPORTED_Autoneg | + SUPPORTED_FIBRE); + ecmd->advertising = (ADVERTISED_10000baseT_Full | + ADVERTISED_1000baseT_Full | + ADVERTISED_Autoneg | + ADVERTISED_FIBRE); + ecmd->port = PORT_FIBRE; + } else { + ecmd->supported |= (SUPPORTED_1000baseT_Full | + SUPPORTED_FIBRE); + ecmd->advertising = (ADVERTISED_10000baseT_Full | + ADVERTISED_1000baseT_Full | + ADVERTISED_FIBRE); + ecmd->port = PORT_FIBRE; + } + } else { + ecmd->supported |= SUPPORTED_FIBRE; + ecmd->advertising = (ADVERTISED_10000baseT_Full | + ADVERTISED_FIBRE); + ecmd->port = PORT_FIBRE; + ecmd->autoneg = AUTONEG_DISABLE; + } + + /* Get PHY type */ + switch (adapter->hw.phy.type) { + case ixgbe_phy_tn: + case ixgbe_phy_aq: + case ixgbe_phy_cu_unknown: + /* Copper 10G-BASET */ + ecmd->port = PORT_TP; + break; + case ixgbe_phy_qt: + ecmd->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: + switch (adapter->hw.phy.sfp_type) { + /* SFP+ devices, further checking needed */ + case ixgbe_sfp_type_da_cu: + case ixgbe_sfp_type_da_cu_core0: + case ixgbe_sfp_type_da_cu_core1: + ecmd->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: + ecmd->port = PORT_FIBRE; + break; + case ixgbe_sfp_type_not_present: + ecmd->port = PORT_NONE; + break; + case ixgbe_sfp_type_1g_cu_core0: + case ixgbe_sfp_type_1g_cu_core1: + ecmd->port = PORT_TP; + ecmd->supported = SUPPORTED_TP; + ecmd->advertising = (ADVERTISED_1000baseT_Full | + ADVERTISED_TP); + break; + case ixgbe_sfp_type_unknown: + default: + ecmd->port = PORT_OTHER; + break; + } + break; + case ixgbe_phy_xaui: + ecmd->port = PORT_NONE; + break; + case ixgbe_phy_unknown: + case ixgbe_phy_generic: + case ixgbe_phy_sfp_unsupported: + default: + ecmd->port = PORT_OTHER; + break; + } + + hw->mac.ops.check_link(hw, &link_speed, &link_up, false); + if (link_up) { + switch (link_speed) { + case IXGBE_LINK_SPEED_10GB_FULL: + ethtool_cmd_speed_set(ecmd, SPEED_10000); + break; + case IXGBE_LINK_SPEED_1GB_FULL: + ethtool_cmd_speed_set(ecmd, SPEED_1000); + break; + case IXGBE_LINK_SPEED_100_FULL: + ethtool_cmd_speed_set(ecmd, SPEED_100); + break; + default: + break; + } + ecmd->duplex = DUPLEX_FULL; + } else { + ethtool_cmd_speed_set(ecmd, -1); + ecmd->duplex = -1; + } + + return 0; +} + +static int ixgbe_set_settings(struct net_device *netdev, + struct ethtool_cmd *ecmd) +{ + 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)) { + /* 10000/copper and 1000/copper must autoneg + * this function does not support any duplex forcing, but can + * limit the advertising of the adapter to only 10000 or 1000 */ + if (ecmd->autoneg == AUTONEG_DISABLE) + return -EINVAL; + + old = hw->phy.autoneg_advertised; + advertised = 0; + if (ecmd->advertising & ADVERTISED_10000baseT_Full) + advertised |= IXGBE_LINK_SPEED_10GB_FULL; + + if (ecmd->advertising & ADVERTISED_1000baseT_Full) + advertised |= IXGBE_LINK_SPEED_1GB_FULL; + + if (ecmd->advertising & ADVERTISED_100baseT_Full) + advertised |= IXGBE_LINK_SPEED_100_FULL; + + if (old == advertised) + return err; + /* this sets the link speed and restarts auto-neg */ + hw->mac.autotry_restart = true; + err = hw->mac.ops.setup_link(hw, advertised, true, true); + if (err) { + e_info(probe, "setup link failed with code %d\n", err); + hw->mac.ops.setup_link(hw, old, true, true); + } + } else { + /* in this case we currently only support 10Gb/FULL */ + u32 speed = ethtool_cmd_speed(ecmd); + if ((ecmd->autoneg == AUTONEG_ENABLE) || + (ecmd->advertising != ADVERTISED_10000baseT_Full) || + (speed + ecmd->duplex != SPEED_10000 + DUPLEX_FULL)) + return -EINVAL; + } + + return err; +} + +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; + + /* + * Flow Control Autoneg isn't on if + * - we didn't ask for it OR + * - it failed, we know this by tx & rx being off + */ + if (hw->fc.disable_fc_autoneg || + (hw->fc.current_mode == ixgbe_fc_none)) + pause->autoneg = 0; + else + pause->autoneg = 1; + + 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; +#ifdef CONFIG_DCB + } else if (hw->fc.current_mode == ixgbe_fc_pfc) { + pause->rx_pause = 0; + pause->tx_pause = 0; +#endif + } +} + +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; + +#ifdef CONFIG_DCB + if (adapter->dcb_cfg.pfc_mode_enable || + ((hw->mac.type == ixgbe_mac_82598EB) && + (adapter->flags & IXGBE_FLAG_DCB_ENABLED))) + return -EINVAL; + +#endif + fc = hw->fc; + + if (pause->autoneg != AUTONEG_ENABLE) + fc.disable_fc_autoneg = true; + else + fc.disable_fc_autoneg = false; + + 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 if (!pause->rx_pause && !pause->tx_pause) + fc.requested_mode = ixgbe_fc_none; + else + return -EINVAL; + +#ifdef CONFIG_DCB + adapter->last_lfc_mode = fc.requested_mode; +#endif + + /* 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 1128 + 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 = (1 << 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); + regs_buff[9] = IXGBE_READ_REG(hw, IXGBE_EERD); + regs_buff[10] = IXGBE_READ_REG(hw, IXGBE_FLA); + 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); + + /* 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); + regs_buff[31] = IXGBE_READ_REG(hw, IXGBE_FCTTV(0)); + regs_buff[32] = IXGBE_READ_REG(hw, IXGBE_FCTTV(1)); + regs_buff[33] = IXGBE_READ_REG(hw, IXGBE_FCTTV(2)); + regs_buff[34] = IXGBE_READ_REG(hw, IXGBE_FCTTV(3)); + 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: + 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); + regs_buff[830] = IXGBE_READ_REG(hw, IXGBE_DPMCS); + regs_buff[831] = IXGBE_READ_REG(hw, IXGBE_PDPMCS); + 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)); + for (i = 0; i < 8; i++) + regs_buff[865 + i] = IXGBE_READ_REG(hw, IXGBE_TDPT2TCCR(i)); + for (i = 0; i < 8; i++) + regs_buff[873 + i] = IXGBE_READ_REG(hw, IXGBE_TDPT2TCSR(i)); + + /* 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] = IXGBE_GET_STAT(adapter, gorc); + regs_buff[944] = IXGBE_GET_STAT(adapter, gotc); + 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] = IXGBE_GET_STAT(adapter, tor); + 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); + regs_buff[1102] = IXGBE_READ_REG(hw, IXGBE_TXBUFDATA0); + regs_buff[1103] = IXGBE_READ_REG(hw, IXGBE_TXBUFDATA1); + regs_buff[1104] = IXGBE_READ_REG(hw, IXGBE_TXBUFDATA2); + regs_buff[1105] = IXGBE_READ_REG(hw, IXGBE_TXBUFDATA3); + regs_buff[1106] = IXGBE_READ_REG(hw, IXGBE_RXBUFCTRL); + regs_buff[1107] = IXGBE_READ_REG(hw, IXGBE_RXBUFDATA0); + regs_buff[1108] = IXGBE_READ_REG(hw, IXGBE_RXBUFDATA1); + regs_buff[1109] = IXGBE_READ_REG(hw, IXGBE_RXBUFDATA2); + regs_buff[1110] = IXGBE_READ_REG(hw, IXGBE_RXBUFDATA3); + 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); +} + +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(sizeof(u16) * eeprom_len, 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 void ixgbe_get_drvinfo(struct net_device *netdev, + struct ethtool_drvinfo *drvinfo) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + char firmware_version[32]; + + strncpy(drvinfo->driver, ixgbe_driver_name, + sizeof(drvinfo->driver) - 1); + strncpy(drvinfo->version, ixgbe_driver_version, + sizeof(drvinfo->version) - 1); + + snprintf(firmware_version, sizeof(firmware_version), "%d.%d-%d", + (adapter->eeprom_version & 0xF000) >> 12, + (adapter->eeprom_version & 0x0FF0) >> 4, + adapter->eeprom_version & 0x000F); + + strncpy(drvinfo->fw_version, firmware_version, + sizeof(drvinfo->fw_version)); + strncpy(drvinfo->bus_info, pci_name(adapter->pdev), + sizeof(drvinfo->bus_info)); + drvinfo->n_stats = IXGBE_STATS_LEN; + drvinfo->testinfo_len = IXGBE_TEST_LEN; + drvinfo->regdump_len = ixgbe_get_regs_len(netdev); +} + +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_mini_max_pending = 0; + ring->rx_jumbo_max_pending = 0; + ring->rx_pending = rx_ring->count; + ring->tx_pending = tx_ring->count; + ring->rx_mini_pending = 0; + ring->rx_jumbo_pending = 0; +} + +static int ixgbe_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_ring *temp_tx_ring, *temp_rx_ring; + int i, err = 0; + u32 new_rx_count, new_tx_count; + bool need_update = false; + + if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) + return -EINVAL; + + new_rx_count = max(ring->rx_pending, (u32)IXGBE_MIN_RXD); + new_rx_count = min(new_rx_count, (u32)IXGBE_MAX_RXD); + new_rx_count = ALIGN(new_rx_count, IXGBE_REQ_RX_DESCRIPTOR_MULTIPLE); + + new_tx_count = max(ring->tx_pending, (u32)IXGBE_MIN_TXD); + new_tx_count = min(new_tx_count, (u32)IXGBE_MAX_TXD); + new_tx_count = ALIGN(new_tx_count, IXGBE_REQ_TX_DESCRIPTOR_MULTIPLE); + + if ((new_tx_count == adapter->tx_ring[0]->count) && + (new_rx_count == adapter->rx_ring[0]->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_rx_queues; i++) + adapter->rx_ring[i]->count = new_rx_count; + adapter->tx_ring_count = new_tx_count; + adapter->rx_ring_count = new_rx_count; + goto clear_reset; + } + + temp_tx_ring = vmalloc(adapter->num_tx_queues * sizeof(struct ixgbe_ring)); + if (!temp_tx_ring) { + err = -ENOMEM; + goto clear_reset; + } + + if (new_tx_count != adapter->tx_ring_count) { + for (i = 0; i < adapter->num_tx_queues; i++) { + memcpy(&temp_tx_ring[i], adapter->tx_ring[i], + sizeof(struct ixgbe_ring)); + temp_tx_ring[i].count = new_tx_count; + err = ixgbe_setup_tx_resources(&temp_tx_ring[i]); + if (err) { + while (i) { + i--; + ixgbe_free_tx_resources(&temp_tx_ring[i]); + } + goto clear_reset; + } + } + need_update = true; + } + + temp_rx_ring = vmalloc(adapter->num_rx_queues * sizeof(struct ixgbe_ring)); + if (!temp_rx_ring) { + err = -ENOMEM; + goto err_setup; + } + + if (new_rx_count != adapter->rx_ring_count) { + for (i = 0; i < adapter->num_rx_queues; i++) { + memcpy(&temp_rx_ring[i], adapter->rx_ring[i], + sizeof(struct ixgbe_ring)); + temp_rx_ring[i].count = new_rx_count; + err = ixgbe_setup_rx_resources(&temp_rx_ring[i]); + if (err) { + while (i) { + i--; + ixgbe_free_rx_resources(&temp_rx_ring[i]); + } + goto err_setup; + } + } + need_update = true; + } + + /* if rings need to be updated, here's the place to do it in one shot */ + if (need_update) { + ixgbe_down(adapter); + + /* tx */ + if (new_tx_count != adapter->tx_ring_count) { + for (i = 0; i < adapter->num_tx_queues; i++) { + ixgbe_free_tx_resources(adapter->tx_ring[i]); + memcpy(adapter->tx_ring[i], &temp_tx_ring[i], + sizeof(struct ixgbe_ring)); + } + adapter->tx_ring_count = new_tx_count; + } + + /* rx */ + if (new_rx_count != adapter->rx_ring_count) { + for (i = 0; i < adapter->num_rx_queues; i++) { + ixgbe_free_rx_resources(adapter->rx_ring[i]); + memcpy(adapter->rx_ring[i], &temp_rx_ring[i], + sizeof(struct ixgbe_ring)); + } + adapter->rx_ring_count = new_rx_count; + } + ixgbe_up(adapter); + } + + vfree(temp_rx_ring); +err_setup: + vfree(temp_tx_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; + 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; + } + + data[i] = (ixgbe_gstrings_stats[i].sizeof_stat == + sizeof(u64)) ? *(u64 *)p : *(u32 *)p; + } + for (j = 0; j < adapter->num_tx_queues; j++) { + ring = adapter->tx_ring[j]; + do { + start = u64_stats_fetch_begin_bh(&ring->syncp); + data[i] = ring->stats.packets; + data[i+1] = ring->stats.bytes; + } while (u64_stats_fetch_retry_bh(&ring->syncp, start)); + i += 2; + } + for (j = 0; j < adapter->num_rx_queues; j++) { + ring = adapter->rx_ring[j]; + do { + start = u64_stats_fetch_begin_bh(&ring->syncp); + data[i] = ring->stats.packets; + data[i+1] = ring->stats.bytes; + } while (u64_stats_fetch_retry_bh(&ring->syncp, start)); + i += 2; + } + if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) { + for (j = 0; j < MAX_TX_PACKET_BUFFERS; j++) { + data[i++] = adapter->stats.pxontxc[j]; + data[i++] = adapter->stats.pxofftxc[j]; + } + for (j = 0; j < MAX_RX_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) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + char *p = (char *)data; + int i; + + switch (stringset) { + case ETH_SS_TEST: + memcpy(data, *ixgbe_gstrings_test, + IXGBE_TEST_LEN * 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 < 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_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; + } + if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) { + for (i = 0; i < MAX_TX_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 < MAX_RX_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; + } +} + +static int ixgbe_link_test(struct ixgbe_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) + 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 }, + { 0, 0, 0, 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 }, + { 0, 0, 0, 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}; + + for (pat = 0; pat < ARRAY_SIZE(test_pattern); pat++) { + before = readl(adapter->hw.hw_addr + reg); + writel((test_pattern[pat] & write), + (adapter->hw.hw_addr + reg)); + val = readl(adapter->hw.hw_addr + 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; + writel(before, adapter->hw.hw_addr + reg); + return 1; + } + writel(before, adapter->hw.hw_addr + reg); + } + return 0; +} + +static bool reg_set_and_check(struct ixgbe_adapter *adapter, u64 *data, int reg, + u32 mask, u32 write) +{ + u32 val, before; + before = readl(adapter->hw.hw_addr + reg); + writel((write & mask), (adapter->hw.hw_addr + reg)); + val = readl(adapter->hw.hw_addr + 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; + writel(before, (adapter->hw.hw_addr + reg)); + return 1; + } + writel(before, (adapter->hw.hw_addr + reg)); + return 0; +} + +#define REG_PATTERN_TEST(reg, mask, write) \ + do { \ + if (reg_pattern_test(adapter, data, reg, mask, write)) \ + return 1; \ + } while (0) \ + + +#define REG_SET_AND_CHECK(reg, mask, write) \ + do { \ + if (reg_set_and_check(adapter, data, reg, mask, write)) \ + return 1; \ + } while (0) \ + +static int ixgbe_reg_test(struct ixgbe_adapter *adapter, u64 *data) +{ + const struct ixgbe_reg_test *test; + u32 value, before, after; + u32 i, toggle; + + switch (adapter->hw.mac.type) { + case ixgbe_mac_82598EB: + toggle = 0x7FFFF3FF; + test = reg_test_82598; + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + toggle = 0x7FFFF30F; + test = reg_test_82599; + break; + default: + *data = 1; + return 1; + break; + } + + /* + * 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++) { + switch (test->test_type) { + case PATTERN_TEST: + REG_PATTERN_TEST(test->reg + (i * 0x40), + test->mask, + test->write); + break; + case SET_READ_TEST: + REG_SET_AND_CHECK(test->reg + (i * 0x40), + test->mask, + test->write); + break; + case WRITE_NO_TEST: + writel(test->write, + (adapter->hw.hw_addr + test->reg) + + (i * 0x40)); + break; + case TABLE32_TEST: + REG_PATTERN_TEST(test->reg + (i * 4), + test->mask, + test->write); + break; + case TABLE64_TEST_LO: + REG_PATTERN_TEST(test->reg + (i * 8), + test->mask, + test->write); + break; + case TABLE64_TEST_HI: + REG_PATTERN_TEST((test->reg + 4) + (i * 8), + test->mask, + test->write); + break; + } + } + 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 = 1 << 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) +{ + 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 reg_ctl; + + /* shut down the DMA engines now so they can be reinitialized later */ + + /* first Rx */ + reg_ctl = IXGBE_READ_REG(hw, IXGBE_RXCTRL); + reg_ctl &= ~IXGBE_RXCTRL_RXEN; + IXGBE_WRITE_REG(hw, IXGBE_RXCTRL, reg_ctl); + ixgbe_disable_rx_queue(adapter, rx_ring); + + /* now Tx */ + reg_ctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(tx_ring->reg_idx)); + reg_ctl &= ~IXGBE_TXDCTL_ENABLE; + IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(tx_ring->reg_idx), reg_ctl); + + switch (hw->mac.type) { + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + reg_ctl = IXGBE_READ_REG(hw, IXGBE_DMATXCTL); + reg_ctl &= ~IXGBE_DMATXCTL_TE; + IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL, reg_ctl); + break; + default: + break; + } + + 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; + 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; + tx_ring->numa_node = adapter->node; + + err = ixgbe_setup_tx_resources(tx_ring); + if (err) + return 1; + + switch (adapter->hw.mac.type) { + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + 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; + rx_ring->rx_buf_len = IXGBE_RXBUFFER_2048; + rx_ring->numa_node = adapter->node; + + err = ixgbe_setup_rx_resources(rx_ring); + if (err) { + ret_val = 4; + goto err_nomem; + } + + rctl = IXGBE_READ_REG(&adapter->hw, IXGBE_RXCTRL); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_RXCTRL, rctl & ~IXGBE_RXCTRL_RXEN); + + ixgbe_configure_rx_ring(adapter, rx_ring); + + rctl |= IXGBE_RXCTRL_RXEN | IXGBE_RXCTRL_DMBYPS; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_RXCTRL, rctl); + + 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; + + /* X540 needs to set the MACC.FLU bit to force link up */ + if (adapter->hw.mac.type == ixgbe_mac_X540) { + reg_data = IXGBE_READ_REG(&adapter->hw, IXGBE_MACC); + reg_data |= IXGBE_MACC_FLU; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_MACC, reg_data); + } + + /* right now we only support MAC loopback in the driver */ + reg_data = IXGBE_READ_REG(&adapter->hw, IXGBE_HLREG0); + /* Setup MAC loopback */ + reg_data |= IXGBE_HLREG0_LPBK; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_HLREG0, reg_data); + + reg_data = IXGBE_READ_REG(&adapter->hw, IXGBE_FCTRL); + reg_data |= IXGBE_FCTRL_BAM | IXGBE_FCTRL_SBP | IXGBE_FCTRL_MPE; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_FCTRL, reg_data); + + reg_data = IXGBE_READ_REG(&adapter->hw, IXGBE_AUTOC); + reg_data &= ~IXGBE_AUTOC_LMS_MASK; + reg_data |= IXGBE_AUTOC_LMS_10G_LINK_NO_AN | IXGBE_AUTOC_FLU; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_AUTOC, reg_data); + IXGBE_WRITE_FLUSH(&adapter->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 / 2], 0xAA, frame_size / 2 - 1); + memset(&skb->data[frame_size / 2 + 10], 0xBE, 1); + memset(&skb->data[frame_size / 2 + 12], 0xAF, 1); +} + +static int ixgbe_check_lbtest_frame(struct sk_buff *skb, + unsigned int frame_size) +{ + frame_size &= ~1; + if (*(skb->data + 3) == 0xFF) { + if ((*(skb->data + frame_size / 2 + 10) == 0xBE) && + (*(skb->data + frame_size / 2 + 12) == 0xAF)) { + return 0; + } + } + return 13; +} + +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; + struct ixgbe_rx_buffer *rx_buffer_info; + struct ixgbe_tx_buffer *tx_buffer_info; + const int bufsz = rx_ring->rx_buf_len; + u32 staterr; + 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_ADV(rx_ring, rx_ntc); + staterr = le32_to_cpu(rx_desc->wb.upper.status_error); + + while (staterr & IXGBE_RXD_STAT_DD) { + /* check Rx buffer */ + rx_buffer_info = &rx_ring->rx_buffer_info[rx_ntc]; + + /* unmap Rx buffer, will be remapped by alloc_rx_buffers */ + dma_unmap_single(rx_ring->dev, + rx_buffer_info->dma, + bufsz, + DMA_FROM_DEVICE); + rx_buffer_info->dma = 0; + + /* verify contents of skb */ + if (!ixgbe_check_lbtest_frame(rx_buffer_info->skb, size)) + count++; + + /* unmap buffer on Tx side */ + tx_buffer_info = &tx_ring->tx_buffer_info[tx_ntc]; + ixgbe_unmap_and_free_tx_resource(tx_ring, tx_buffer_info); + + /* increment Rx/Tx next to clean counters */ + rx_ntc++; + if (rx_ntc == rx_ring->count) + rx_ntc = 0; + tx_ntc++; + if (tx_ntc == tx_ring->count) + tx_ntc = 0; + + /* fetch next descriptor */ + rx_desc = IXGBE_RX_DESC_ADV(rx_ring, rx_ntc); + staterr = le32_to_cpu(rx_desc->wb.upper.status_error); + } + + /* 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; + + /* 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); + + 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); + + set_bit(__IXGBE_TESTING, &adapter->state); + if (eth_test->flags == ETH_TEST_FL_OFFLINE) { + /* 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 (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, "%s", + "offline diagnostic is not " + "supported when VFs are " + "present\n"); + data[0] = 1; + data[1] = 1; + data[2] = 1; + data[3] = 1; + eth_test->flags |= ETH_TEST_FL_FAILED; + clear_bit(__IXGBE_TESTING, + &adapter->state); + goto skip_ol_tests; + } + } + } + + if (if_running) + /* indicate we're in test mode */ + dev_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_bit(__IXGBE_TESTING, &adapter->state); + if (if_running) + dev_open(netdev); + } else { + e_info(hw, "online testing starting\n"); + /* Online tests */ + if (ixgbe_link_test(adapter, &data[4])) + eth_test->flags |= ETH_TEST_FL_FAILED; + + /* Online 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); + } +skip_ol_tests: + msleep_interruptible(4 * 1000); +} + +static int ixgbe_wol_exclusion(struct ixgbe_adapter *adapter, + struct ethtool_wolinfo *wol) +{ + struct ixgbe_hw *hw = &adapter->hw; + int retval = 1; + + /* WOL not supported except for the following */ + switch(hw->device_id) { + case IXGBE_DEV_ID_82599_SFP: + /* Only this subdevice supports WOL */ + if (hw->subsystem_device_id != IXGBE_SUBDEV_ID_82599_SFP) { + wol->supported = 0; + break; + } + retval = 0; + break; + case IXGBE_DEV_ID_82599_COMBO_BACKPLANE: + /* All except this subdevice support WOL */ + if (hw->subsystem_device_id == + IXGBE_SUBDEV_ID_82599_KX4_KR_MEZZ) { + wol->supported = 0; + break; + } + retval = 0; + break; + case IXGBE_DEV_ID_82599_KX4: + retval = 0; + break; + default: + 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)) + 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; + + 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, IXGBE_LED_ON); + break; + + case ETHTOOL_ID_OFF: + hw->mac.ops.led_off(hw, IXGBE_LED_ON); + 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); + + ec->tx_max_coalesced_frames_irq = adapter->tx_work_limit; + + /* only valid if in constant ITR mode */ + switch (adapter->rx_itr_setting) { + case 0: + /* throttling disabled */ + ec->rx_coalesce_usecs = 0; + break; + case 1: + /* dynamic ITR mode */ + ec->rx_coalesce_usecs = 1; + break; + default: + /* fixed interrupt rate mode */ + ec->rx_coalesce_usecs = 1000000/adapter->rx_eitr_param; + break; + } + + /* 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 */ + switch (adapter->tx_itr_setting) { + case 0: + /* throttling disabled */ + ec->tx_coalesce_usecs = 0; + break; + case 1: + /* dynamic ITR mode */ + ec->tx_coalesce_usecs = 1; + break; + default: + ec->tx_coalesce_usecs = 1000000/adapter->tx_eitr_param; + break; + } + + 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 ethtool_coalesce *ec) +{ + struct net_device *netdev = adapter->netdev; + + if (!(adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE)) + return false; + + /* if interrupt rate is too high then disable RSC */ + if (ec->rx_coalesce_usecs != 1 && + ec->rx_coalesce_usecs <= 1000000/IXGBE_MAX_RSC_INT_RATE) { + if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) { + e_info(probe, "rx-usecs set too low, " + "disabling RSC\n"); + adapter->flags2 &= ~IXGBE_FLAG2_RSC_ENABLED; + return true; + } + } else { + /* check the feature flag value and enable RSC if necessary */ + if ((netdev->features & NETIF_F_LRO) && + !(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)) { + e_info(probe, "rx-usecs set to %d, " + "re-enabling RSC\n", + ec->rx_coalesce_usecs); + adapter->flags2 |= IXGBE_FLAG2_RSC_ENABLED; + 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; + bool need_reset = false; + + /* 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->tx_max_coalesced_frames_irq) + adapter->tx_work_limit = ec->tx_max_coalesced_frames_irq; + + if (ec->rx_coalesce_usecs > 1) { + /* check the limits */ + if ((1000000/ec->rx_coalesce_usecs > IXGBE_MAX_INT_RATE) || + (1000000/ec->rx_coalesce_usecs < IXGBE_MIN_INT_RATE)) + return -EINVAL; + + /* check the old value and enable RSC if necessary */ + need_reset = ixgbe_update_rsc(adapter, ec); + + /* store the value in ints/second */ + adapter->rx_eitr_param = 1000000/ec->rx_coalesce_usecs; + + /* static value of interrupt rate */ + adapter->rx_itr_setting = adapter->rx_eitr_param; + /* clear the lower bit as its used for dynamic state */ + adapter->rx_itr_setting &= ~1; + } else if (ec->rx_coalesce_usecs == 1) { + /* check the old value and enable RSC if necessary */ + need_reset = ixgbe_update_rsc(adapter, ec); + + /* 1 means dynamic mode */ + adapter->rx_eitr_param = 20000; + adapter->rx_itr_setting = 1; + } else { + /* check the old value and enable RSC if necessary */ + need_reset = ixgbe_update_rsc(adapter, ec); + /* + * any other value means disable eitr, which is best + * served by setting the interrupt rate very high + */ + adapter->rx_eitr_param = IXGBE_MAX_INT_RATE; + adapter->rx_itr_setting = 0; + } + + if (ec->tx_coalesce_usecs > 1) { + /* + * don't have to worry about max_int as above because + * tx vectors don't do hardware RSC (an rx function) + */ + /* check the limits */ + if ((1000000/ec->tx_coalesce_usecs > IXGBE_MAX_INT_RATE) || + (1000000/ec->tx_coalesce_usecs < IXGBE_MIN_INT_RATE)) + return -EINVAL; + + /* store the value in ints/second */ + adapter->tx_eitr_param = 1000000/ec->tx_coalesce_usecs; + + /* static value of interrupt rate */ + adapter->tx_itr_setting = adapter->tx_eitr_param; + + /* clear the lower bit as its used for dynamic state */ + adapter->tx_itr_setting &= ~1; + } else if (ec->tx_coalesce_usecs == 1) { + /* 1 means dynamic mode */ + adapter->tx_eitr_param = 10000; + adapter->tx_itr_setting = 1; + } else { + adapter->tx_eitr_param = IXGBE_MAX_INT_RATE; + adapter->tx_itr_setting = 0; + } + + /* MSI/MSIx Interrupt Mode */ + if (adapter->flags & + (IXGBE_FLAG_MSIX_ENABLED | IXGBE_FLAG_MSI_ENABLED)) { + int 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->eitr = adapter->tx_eitr_param; + else + /* rx only or mixed */ + q_vector->eitr = adapter->rx_eitr_param; + q_vector->tx.work_limit = adapter->tx_work_limit; + ixgbe_write_eitr(q_vector); + } + /* Legacy Interrupt Mode */ + } else { + q_vector = adapter->q_vector[0]; + q_vector->eitr = adapter->rx_eitr_param; + q_vector->tx.work_limit = adapter->tx_work_limit; + 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 *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, node, 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 *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, node, node2, + &adapter->fdir_filter_list, fdir_node) { + if (cnt == cmd->rule_cnt) + return -EMSGSIZE; + rule_locs[cnt] = rule->sw_idx; + cnt++; + } + + return 0; +} + +static int ixgbe_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, + void *rule_locs) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + int ret = -EOPNOTSUPP; + + switch (cmd->cmd) { + case ETHTOOL_GRXRINGS: + cmd->data = adapter->num_rx_queues; + 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, + (u32 *)rule_locs); + break; + default: + break; + } + + return ret; +} + +static 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 *node, *node2, *parent; + struct ixgbe_fdir_filter *rule; + int err = -EINVAL; + + parent = NULL; + rule = NULL; + + hlist_for_each_entry_safe(rule, node, node2, + &adapter->fdir_filter_list, fdir_node) { + /* hash found, or no matching entry */ + if (rule->sw_idx >= sw_idx) + break; + parent = node; + } + + /* 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_after(parent, &input->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; + } + 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; + int err; + + if (!(adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE)) + return -EOPNOTSUPP; + + /* + * Don't allow programming if the action is a queue greater than + * the number of online Rx queues. + */ + if ((fsp->ring_cookie != RX_CLS_FLOW_DISC) && + (fsp->ring_cookie >= adapter->num_rx_queues)) + return -EINVAL; + + /* 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, + (input->action == IXGBE_FDIR_DROP_QUEUE) ? + IXGBE_FDIR_DROP_QUEUE : + adapter->rx_ring[input->action]->reg_idx); + 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; +} + +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; + default: + break; + } + + return ret; +} + +static const struct ethtool_ops ixgbe_ethtool_ops = { + .get_settings = ixgbe_get_settings, + .set_settings = ixgbe_set_settings, + .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, + .get_ringparam = ixgbe_get_ringparam, + .set_ringparam = ixgbe_set_ringparam, + .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, +}; + +void ixgbe_set_ethtool_ops(struct net_device *netdev) +{ + SET_ETHTOOL_OPS(netdev, &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 000000000000..824edae77865 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c @@ -0,0 +1,836 @@ +/******************************************************************************* + + Intel 10 Gigabit PCI Express Linux driver + Copyright(c) 1999 - 2011 Intel Corporation. + + This program is free software; you can redistribute it and/or modify it + under the terms and conditions of the GNU General Public License, + version 2, as published by the Free Software Foundation. + + This program is distributed in the hope it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + more details. + + You should have received a copy of the GNU General Public License along with + this program; if not, write to the Free Software Foundation, Inc., + 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + + The full GNU General Public License is included in this distribution in + the file called "COPYING". + + Contact Information: + e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + +*******************************************************************************/ + +#include "ixgbe.h" +#include <linux/if_ether.h> +#include <linux/gfp.h> +#include <linux/if_vlan.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 = 0; + struct ixgbe_fcoe *fcoe; + struct ixgbe_adapter *adapter; + struct ixgbe_fcoe_ddp *ddp; + u32 fcbuff; + + if (!netdev) + goto out_ddp_put; + + if (xid >= IXGBE_FCOE_DDP_MAX) + goto out_ddp_put; + + adapter = netdev_priv(netdev); + fcoe = &adapter->fcoe; + ddp = &fcoe->ddp[xid]; + if (!ddp->udl) + goto out_ddp_put; + + len = ddp->len; + /* if there an error, force to invalidate ddp context */ + if (ddp->err) { + spin_lock_bh(&fcoe->lock); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_FCFLT, 0); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_FCFLTRW, + (xid | IXGBE_FCFLTRW_WE)); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_FCBUFF, 0); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_FCDMARW, + (xid | IXGBE_FCDMARW_WE)); + + /* guaranteed to be invalidated after 100us */ + IXGBE_WRITE_REG(&adapter->hw, IXGBE_FCDMARW, + (xid | IXGBE_FCDMARW_RE)); + fcbuff = IXGBE_READ_REG(&adapter->hw, IXGBE_FCBUFF); + spin_unlock_bh(&fcoe->lock); + if (fcbuff & IXGBE_FCBUFF_VALID) + udelay(100); + } + if (ddp->sgl) + pci_unmap_sg(adapter->pdev, ddp->sgl, ddp->sgc, + DMA_FROM_DEVICE); + if (ddp->pool) { + pci_pool_free(ddp->pool, ddp->udl, ddp->udp); + ddp->pool = NULL; + } + + ixgbe_fcoe_clear_ddp(ddp); + +out_ddp_put: + 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 + * + * 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 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; + struct pci_pool *pool; + + if (!netdev || !sgl) + return 0; + + adapter = netdev_priv(netdev); + if (xid >= IXGBE_FCOE_DDP_MAX) { + 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; + if (!fcoe->pool) { + e_warn(drv, "xid=0x%x no ddp pool for fcoe\n", xid); + return 0; + } + + 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); + + /* setup dma from scsi command sgl */ + dmacount = pci_map_sg(adapter->pdev, sgl, sgc, DMA_FROM_DEVICE); + if (dmacount == 0) { + e_err(drv, "xid 0x%x DMA map error\n", xid); + return 0; + } + + /* alloc the udl from per cpu ddp pool */ + pool = *per_cpu_ptr(fcoe->pool, get_cpu()); + ddp->udl = pci_pool_alloc(pool, GFP_ATOMIC, &ddp->udp); + if (!ddp->udl) { + e_err(drv, "failed allocated ddp context\n"); + goto out_noddp_unmap; + } + 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) { + e_err(drv, "xid=%x:%d,%d,%d:addr=%llx " + "not enough descriptors\n", + xid, i, j, dmacount, (u64)addr); + 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) { + e_err(drv, "xid=%x:%d,%d,%d:addr=%llx " + "not enough user buffers. We need an extra " + "buffer because lastsize is bufflen.\n", + xid, i, j, dmacount, (u64)addr); + 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; + spin_lock_bh(&fcoe->lock); + + /* 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); + } + + 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: + pci_pool_free(pool, ddp->udl, ddp->udp); + ixgbe_fcoe_clear_ddp(ddp); + +out_noddp_unmap: + pci_unmap_sg(adapter->pdev, sgl, sgc, DMA_FROM_DEVICE); + 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, + u32 staterr) +{ + u16 xid; + u32 fctl; + u32 fceofe, fcerr, fcstat; + int rc = -EINVAL; + struct ixgbe_fcoe *fcoe; + struct ixgbe_fcoe_ddp *ddp; + struct fc_frame_header *fh; + struct fcoe_crc_eof *crc; + + fcerr = (staterr & IXGBE_RXDADV_ERR_FCERR); + fceofe = (staterr & IXGBE_RXDADV_ERR_FCEOFE); + if (fcerr == IXGBE_FCERR_BADCRC) + skb_checksum_none_assert(skb); + 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); + + if (xid >= IXGBE_FCOE_DDP_MAX) + goto ddp_out; + + fcoe = &adapter->fcoe; + ddp = &fcoe->ddp[xid]; + if (!ddp->udl) + goto ddp_out; + + if (fcerr | fceofe) + goto ddp_out; + + fcstat = (staterr & IXGBE_RXDADV_STAT_FCSTAT); + if (fcstat) { + /* update length of DDPed data */ + ddp->len = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss); + /* unmap the sg list when FCP_RSP is received */ + if (fcstat == IXGBE_RXDADV_STAT_FCSTAT_FCPRSP) { + pci_unmap_sg(adapter->pdev, ddp->sgl, + ddp->sgc, DMA_FROM_DEVICE); + ddp->err = (fcerr | fceofe); + ddp->sgl = NULL; + ddp->sgc = 0; + } + /* return 0 to bypass going to ULD for DDPed data */ + if (fcstat == IXGBE_RXDADV_STAT_FCSTAT_DDP) + rc = 0; + else if (ddp->len) + rc = ddp->len; + } + /* 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)) { + crc = (struct fcoe_crc_eof *)skb_put(skb, sizeof(*crc)); + crc->fcoe_eof = FC_EOF_T; + } +ddp_out: + return rc; +} + +/** + * ixgbe_fso - ixgbe FCoE Sequence Offload (FSO) + * @adapter: ixgbe adapter + * @tx_ring: tx desc ring + * @skb: associated skb + * @tx_flags: tx flags + * @hdr_len: hdr_len to be returned + * + * This sets up large send offload for FCoE + * + * Returns : 0 indicates no FSO, > 0 for FSO, < 0 for error + */ +int ixgbe_fso(struct ixgbe_ring *tx_ring, struct sk_buff *skb, + u32 tx_flags, u8 *hdr_len) +{ + struct fc_frame_header *fh; + u32 vlan_macip_lens; + u32 fcoe_sof_eof = 0; + u32 mss_l4len_idx; + 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)); + + /* mss_l4len_id: use 1 for FSO as TSO, no need for L4LEN */ + mss_l4len_idx = skb_shinfo(skb)->gso_size << IXGBE_ADVTXD_MSS_SHIFT; + mss_l4len_idx |= 1 << IXGBE_ADVTXD_IDX_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 |= tx_flags & IXGBE_TX_FLAGS_VLAN_MASK; + + /* write context desc */ + ixgbe_tx_ctxtdesc(tx_ring, vlan_macip_lens, fcoe_sof_eof, + IXGBE_ADVTXT_TUCMD_FCOE, mss_l4len_idx); + + return skb_is_gso(skb); +} + +static void ixgbe_fcoe_ddp_pools_free(struct ixgbe_fcoe *fcoe) +{ + unsigned int cpu; + struct pci_pool **pool; + + for_each_possible_cpu(cpu) { + pool = per_cpu_ptr(fcoe->pool, cpu); + if (*pool) + pci_pool_destroy(*pool); + } + free_percpu(fcoe->pool); + fcoe->pool = NULL; +} + +static void ixgbe_fcoe_ddp_pools_alloc(struct ixgbe_adapter *adapter) +{ + struct ixgbe_fcoe *fcoe = &adapter->fcoe; + unsigned int cpu; + struct pci_pool **pool; + char pool_name[32]; + + fcoe->pool = alloc_percpu(struct pci_pool *); + if (!fcoe->pool) + return; + + /* allocate pci pool for each cpu */ + for_each_possible_cpu(cpu) { + snprintf(pool_name, 32, "ixgbe_fcoe_ddp_%d", cpu); + pool = per_cpu_ptr(fcoe->pool, cpu); + *pool = pci_pool_create(pool_name, + adapter->pdev, IXGBE_FCPTR_MAX, + IXGBE_FCPTR_ALIGN, PAGE_SIZE); + if (!*pool) { + e_err(drv, "failed to alloc DDP pool on cpu:%d\n", cpu); + ixgbe_fcoe_ddp_pools_free(fcoe); + return; + } + } +} + +/** + * 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) +{ + int i, fcoe_q, fcoe_i; + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_fcoe *fcoe = &adapter->fcoe; + struct ixgbe_ring_feature *f = &adapter->ring_feature[RING_F_FCOE]; + + if (!fcoe->pool) { + spin_lock_init(&fcoe->lock); + + ixgbe_fcoe_ddp_pools_alloc(adapter); + if (!fcoe->pool) { + e_err(drv, "failed to alloc percpu fcoe DDP pools\n"); + return; + } + + /* Extra buffer to be shared by all DDPs for HW work around */ + fcoe->extra_ddp_buffer = kmalloc(IXGBE_FCBUFF_MIN, GFP_ATOMIC); + if (fcoe->extra_ddp_buffer == NULL) { + e_err(drv, "failed to allocated extra DDP buffer\n"); + goto out_ddp_pools; + } + + fcoe->extra_ddp_buffer_dma = + dma_map_single(&adapter->pdev->dev, + fcoe->extra_ddp_buffer, + IXGBE_FCBUFF_MIN, + DMA_FROM_DEVICE); + if (dma_mapping_error(&adapter->pdev->dev, + fcoe->extra_ddp_buffer_dma)) { + e_err(drv, "failed to map extra DDP buffer\n"); + goto out_extra_ddp_buffer; + } + } + + /* Enable L2 eth type filter for FCoE */ + IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_FCOE), + (ETH_P_FCOE | IXGBE_ETQF_FCOE | IXGBE_ETQF_FILTER_EN)); + /* Enable L2 eth type filter for FIP */ + IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_FIP), + (ETH_P_FIP | IXGBE_ETQF_FILTER_EN)); + if (adapter->ring_feature[RING_F_FCOE].indices) { + /* Use multiple rx queues for FCoE by redirection table */ + for (i = 0; i < IXGBE_FCRETA_SIZE; i++) { + fcoe_i = f->mask + i % f->indices; + fcoe_i &= IXGBE_FCRETA_ENTRY_MASK; + fcoe_q = adapter->rx_ring[fcoe_i]->reg_idx; + IXGBE_WRITE_REG(hw, IXGBE_FCRETA(i), fcoe_q); + } + IXGBE_WRITE_REG(hw, IXGBE_FCRECTL, IXGBE_FCRECTL_ENA); + IXGBE_WRITE_REG(hw, IXGBE_ETQS(IXGBE_ETQF_FILTER_FCOE), 0); + } else { + /* Use single rx queue for FCoE */ + fcoe_i = f->mask; + fcoe_q = adapter->rx_ring[fcoe_i]->reg_idx; + IXGBE_WRITE_REG(hw, IXGBE_FCRECTL, 0); + IXGBE_WRITE_REG(hw, IXGBE_ETQS(IXGBE_ETQF_FILTER_FCOE), + IXGBE_ETQS_QUEUE_EN | + (fcoe_q << IXGBE_ETQS_RX_QUEUE_SHIFT)); + } + /* send FIP frames to the first FCoE queue */ + fcoe_i = f->mask; + fcoe_q = adapter->rx_ring[fcoe_i]->reg_idx; + IXGBE_WRITE_REG(hw, IXGBE_ETQS(IXGBE_ETQF_FILTER_FIP), + IXGBE_ETQS_QUEUE_EN | + (fcoe_q << IXGBE_ETQS_RX_QUEUE_SHIFT)); + + IXGBE_WRITE_REG(hw, IXGBE_FCRXCTRL, + IXGBE_FCRXCTRL_FCOELLI | + IXGBE_FCRXCTRL_FCCRCBO | + (FC_FCOE_VER << IXGBE_FCRXCTRL_FCOEVER_SHIFT)); + return; + +out_extra_ddp_buffer: + kfree(fcoe->extra_ddp_buffer); +out_ddp_pools: + ixgbe_fcoe_ddp_pools_free(fcoe); +} + +/** + * ixgbe_cleanup_fcoe - release all fcoe ddp context resources + * @adapter : ixgbe adapter + * + * Cleans up outstanding ddp context resources + * + * Returns : none + */ +void ixgbe_cleanup_fcoe(struct ixgbe_adapter *adapter) +{ + int i; + struct ixgbe_fcoe *fcoe = &adapter->fcoe; + + if (!fcoe->pool) + return; + + for (i = 0; i < IXGBE_FCOE_DDP_MAX; i++) + ixgbe_fcoe_ddp_put(adapter->netdev, i); + dma_unmap_single(&adapter->pdev->dev, + fcoe->extra_ddp_buffer_dma, + IXGBE_FCBUFF_MIN, + DMA_FROM_DEVICE); + kfree(fcoe->extra_ddp_buffer); + ixgbe_fcoe_ddp_pools_free(fcoe); +} + +/** + * 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) +{ + int rc = -EINVAL; + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_fcoe *fcoe = &adapter->fcoe; + + + if (!(adapter->flags & IXGBE_FLAG_FCOE_CAPABLE)) + goto out_enable; + + atomic_inc(&fcoe->refcnt); + if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) + goto out_enable; + + e_info(drv, "Enabling FCoE offload features.\n"); + if (netif_running(netdev)) + netdev->netdev_ops->ndo_stop(netdev); + + ixgbe_clear_interrupt_scheme(adapter); + + adapter->flags |= IXGBE_FLAG_FCOE_ENABLED; + adapter->ring_feature[RING_F_FCOE].indices = IXGBE_FCRETA_SIZE; + netdev->features |= NETIF_F_FCOE_CRC; + netdev->features |= NETIF_F_FSO; + netdev->features |= NETIF_F_FCOE_MTU; + netdev->fcoe_ddp_xid = IXGBE_FCOE_DDP_MAX - 1; + + ixgbe_init_interrupt_scheme(adapter); + netdev_features_change(netdev); + + if (netif_running(netdev)) + netdev->netdev_ops->ndo_open(netdev); + rc = 0; + +out_enable: + return rc; +} + +/** + * 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) +{ + int rc = -EINVAL; + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_fcoe *fcoe = &adapter->fcoe; + + if (!(adapter->flags & IXGBE_FLAG_FCOE_CAPABLE)) + goto out_disable; + + if (!(adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) + goto out_disable; + + if (!atomic_dec_and_test(&fcoe->refcnt)) + goto out_disable; + + e_info(drv, "Disabling FCoE offload features.\n"); + netdev->features &= ~NETIF_F_FCOE_CRC; + netdev->features &= ~NETIF_F_FSO; + netdev->features &= ~NETIF_F_FCOE_MTU; + netdev->fcoe_ddp_xid = 0; + netdev_features_change(netdev); + + if (netif_running(netdev)) + netdev->netdev_ops->ndo_stop(netdev); + + ixgbe_clear_interrupt_scheme(adapter); + adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED; + adapter->ring_feature[RING_F_FCOE].indices = 0; + ixgbe_cleanup_fcoe(adapter); + ixgbe_init_interrupt_scheme(adapter); + + if (netif_running(netdev)) + netdev->netdev_ops->ndo_open(netdev); + rc = 0; + +out_disable: + return rc; +} + +/** + * 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) +{ + int rc = -EINVAL; + 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]); + rc = 0; + } + return rc; +} 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 000000000000..99de145e290d --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h @@ -0,0 +1,81 @@ +/******************************************************************************* + + Intel 10 Gigabit PCI Express Linux driver + Copyright(c) 1999 - 2011 Intel Corporation. + + This program is free software; you can redistribute it and/or modify it + under the terms and conditions of the GNU General Public License, + version 2, as published by the Free Software Foundation. + + This program is distributed in the hope it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + more details. + + You should have received a copy of the GNU General Public License along with + this program; if not, write to the Free Software Foundation, Inc., + 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + + The full GNU General Public License is included in this distribution in + the file called "COPYING". + + Contact Information: + e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + +*******************************************************************************/ + +#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 */ + +/* 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 pci_pool *pool; +}; + +struct ixgbe_fcoe { + struct pci_pool **pool; + atomic_t refcnt; + spinlock_t lock; + struct ixgbe_fcoe_ddp ddp[IXGBE_FCOE_DDP_MAX]; + unsigned char *extra_ddp_buffer; + dma_addr_t extra_ddp_buffer_dma; + unsigned long mode; +#ifdef CONFIG_IXGBE_DCB + u8 up; +#endif +}; + +#endif /* _IXGBE_FCOE_H */ 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 000000000000..e86297b32733 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -0,0 +1,7934 @@ +/******************************************************************************* + + Intel 10 Gigabit PCI Express Linux driver + Copyright(c) 1999 - 2011 Intel Corporation. + + This program is free software; you can redistribute it and/or modify it + under the terms and conditions of the GNU General Public License, + version 2, as published by the Free Software Foundation. + + This program is distributed in the hope it will be useful, but WITHOUT + ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + more details. + + You should have received a copy of the GNU General Public License along with + this program; if not, write to the Free Software Foundation, Inc., + 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + + The full GNU General Public License is included in this distribution in + the file called "COPYING". + + Contact Information: + e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> + Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + +*******************************************************************************/ + +#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/ethtool.h> +#include <linux/if_vlan.h> +#include <linux/prefetch.h> +#include <scsi/fc/fc_fcoe.h> + +#include "ixgbe.h" +#include "ixgbe_common.h" +#include "ixgbe_dcb_82599.h" +#include "ixgbe_sriov.h" + +char ixgbe_driver_name[] = "ixgbe"; +static const char ixgbe_driver_string[] = + "Intel(R) 10 Gigabit PCI Express Network Driver"; +#define MAJ 3 +#define MIN 4 +#define BUILD 8 +#define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \ + __stringify(BUILD) "-k" +const char ixgbe_driver_version[] = DRV_VERSION; +static const char ixgbe_copyright[] = + "Copyright (c) 1999-2011 Intel Corporation."; + +static const struct ixgbe_info *ixgbe_info_tbl[] = { + [board_82598] = &ixgbe_82598_info, + [board_82599] = &ixgbe_82599_info, + [board_X540] = &ixgbe_X540_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 DEFINE_PCI_DEVICE_TABLE(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 }, + + /* 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"); +#endif /* CONFIG_PCI_IOV */ + +MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); +MODULE_DESCRIPTION("Intel(R) 10 Gigabit PCI Express Network Driver"); +MODULE_LICENSE("GPL"); +MODULE_VERSION(DRV_VERSION); + +#define DEFAULT_DEBUG_LEVEL_SHIFT 3 + +static inline void ixgbe_disable_sriov(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 gcr; + u32 gpie; + u32 vmdctl; + +#ifdef CONFIG_PCI_IOV + /* disable iov and allow time for transactions to clear */ + pci_disable_sriov(adapter->pdev); +#endif + + /* turn off device IOV mode */ + gcr = IXGBE_READ_REG(hw, IXGBE_GCR_EXT); + gcr &= ~(IXGBE_GCR_EXT_SRIOV); + IXGBE_WRITE_REG(hw, IXGBE_GCR_EXT, gcr); + gpie = IXGBE_READ_REG(hw, IXGBE_GPIE); + gpie &= ~IXGBE_GPIE_VTMODE_MASK; + IXGBE_WRITE_REG(hw, IXGBE_GPIE, gpie); + + /* set default pool back to 0 */ + vmdctl = IXGBE_READ_REG(hw, IXGBE_VT_CTL); + vmdctl &= ~IXGBE_VT_CTL_POOL_MASK; + IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, vmdctl); + IXGBE_WRITE_FLUSH(hw); + + /* take a breather then clean up driver data */ + msleep(100); + + kfree(adapter->vfinfo); + adapter->vfinfo = NULL; + + adapter->num_vfs = 0; + adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED; +} + +static void ixgbe_service_event_schedule(struct ixgbe_adapter *adapter) +{ + if (!test_bit(__IXGBE_DOWN, &adapter->state) && + !test_and_set_bit(__IXGBE_SERVICE_SCHED, &adapter->state)) + schedule_work(&adapter->service_task); +} + +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 watchog */ + smp_mb__before_clear_bit(); + 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 */ + {} +}; + + +/* + * ixgbe_regdump - register printout routine + */ +static void ixgbe_regdump(struct ixgbe_hw *hw, struct ixgbe_reg_info *reginfo) +{ + int i = 0, j = 0; + 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; + } + + for (i = 0; i < 8; i++) { + snprintf(rname, 16, "%s[%d-%d]", reginfo->name, i*8, i*8+7); + pr_err("%-15s", rname); + for (j = 0; j < 8; j++) + pr_cont(" %08x", regs[i*8+j]); + pr_cont("\n"); + } + +} + +/* + * 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 *tx_ring; + struct ixgbe_tx_buffer *tx_buffer_info; + 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; + u32 staterr; + 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 last_rx\n"); + pr_info("%-15s %016lX %016lX %016lX\n", + netdev->name, + netdev->state, + netdev->trans_start, + netdev->last_rx); + } + + /* 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)) + goto exit; + + dev_info(&adapter->pdev->dev, "TX Rings Summary\n"); + pr_info("Queue [NTU] [NTC] [bi(ntc)->dma ] leng ntw timestamp\n"); + for (n = 0; n < adapter->num_tx_queues; n++) { + tx_ring = adapter->tx_ring[n]; + tx_buffer_info = + &tx_ring->tx_buffer_info[tx_ring->next_to_clean]; + pr_info(" %5d %5X %5X %016llX %04X %3X %016llX\n", + n, tx_ring->next_to_use, tx_ring->next_to_clean, + (u64)tx_buffer_info->dma, + tx_buffer_info->length, + tx_buffer_info->next_to_watch, + (u64)tx_buffer_info->time_stamp); + } + + /* 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 + * + * Advanced Transmit Descriptor + * +--------------------------------------------------------------+ + * 0 | Buffer Address [63:0] | + * +--------------------------------------------------------------+ + * 8 | PAYLEN | PORTS | IDX | STA | DCMD |DTYP | RSV | DTALEN | + * +--------------------------------------------------------------+ + * 63 46 45 40 39 36 35 32 31 24 23 20 19 0 + */ + + for (n = 0; n < adapter->num_tx_queues; n++) { + tx_ring = adapter->tx_ring[n]; + pr_info("------------------------------------\n"); + pr_info("TX QUEUE INDEX = %d\n", tx_ring->queue_index); + pr_info("------------------------------------\n"); + pr_info("T [desc] [address 63:0 ] " + "[PlPOIdStDDt Ln] [bi->dma ] " + "leng ntw timestamp bi->skb\n"); + + for (i = 0; tx_ring->desc && (i < tx_ring->count); i++) { + tx_desc = IXGBE_TX_DESC_ADV(tx_ring, i); + tx_buffer_info = &tx_ring->tx_buffer_info[i]; + u0 = (struct my_u0 *)tx_desc; + pr_info("T [0x%03X] %016llX %016llX %016llX" + " %04X %3X %016llX %p", i, + le64_to_cpu(u0->a), + le64_to_cpu(u0->b), + (u64)tx_buffer_info->dma, + tx_buffer_info->length, + tx_buffer_info->next_to_watch, + (u64)tx_buffer_info->time_stamp, + tx_buffer_info->skb); + if (i == tx_ring->next_to_use && + i == tx_ring->next_to_clean) + pr_cont(" NTC/U\n"); + else if (i == tx_ring->next_to_use) + pr_cont(" NTU\n"); + else if (i == tx_ring->next_to_clean) + pr_cont(" NTC\n"); + else + pr_cont("\n"); + + if (netif_msg_pktdata(adapter) && + tx_buffer_info->dma != 0) + print_hex_dump(KERN_INFO, "", + DUMP_PREFIX_ADDRESS, 16, 1, + phys_to_virt(tx_buffer_info->dma), + tx_buffer_info->length, 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)) + goto exit; + + dev_info(&adapter->pdev->dev, "RX Rings Dump\n"); + + /* Advanced Receive Descriptor (Read) Format + * 63 1 0 + * +-----------------------------------------------------+ + * 0 | Packet Buffer Address [63:1] |A0/NSE| + * +----------------------------------------------+------+ + * 8 | Header Buffer Address [63:1] | DD | + * +-----------------------------------------------------+ + * + * + * Advanced Receive Descriptor (Write-Back) Format + * + * 63 48 47 32 31 30 21 20 16 15 4 3 0 + * +------------------------------------------------------+ + * 0 | Packet IP |SPH| HDR_LEN | RSV|Packet| RSS | + * | Checksum Ident | | | | Type | Type | + * +------------------------------------------------------+ + * 8 | VLAN Tag | Length | Extended Error | Extended Status | + * +------------------------------------------------------+ + * 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("R [desc] [ PktBuf A0] " + "[ HeadBuf DD] [bi->dma ] [bi->skb] " + "<-- Adv Rx Read format\n"); + pr_info("RWB[desc] [PcsmIpSHl PtRs] " + "[vl er S cks ln] ---------------- [bi->skb] " + "<-- Adv Rx Write-Back format\n"); + + for (i = 0; i < rx_ring->count; i++) { + rx_buffer_info = &rx_ring->rx_buffer_info[i]; + rx_desc = IXGBE_RX_DESC_ADV(rx_ring, i); + u0 = (struct my_u0 *)rx_desc; + staterr = le32_to_cpu(rx_desc->wb.upper.status_error); + if (staterr & IXGBE_RXD_STAT_DD) { + /* Descriptor Done */ + pr_info("RWB[0x%03X] %016llX " + "%016llX ---------------- %p", i, + le64_to_cpu(u0->a), + le64_to_cpu(u0->b), + rx_buffer_info->skb); + } else { + pr_info("R [0x%03X] %016llX " + "%016llX %016llX %p", i, + le64_to_cpu(u0->a), + le64_to_cpu(u0->b), + (u64)rx_buffer_info->dma, + rx_buffer_info->skb); + + if (netif_msg_pktdata(adapter)) { + print_hex_dump(KERN_INFO, "", + DUMP_PREFIX_ADDRESS, 16, 1, + phys_to_virt(rx_buffer_info->dma), + rx_ring->rx_buf_len, true); + + if (rx_ring->rx_buf_len + < IXGBE_RXBUFFER_2048) + print_hex_dump(KERN_INFO, "", + DUMP_PREFIX_ADDRESS, 16, 1, + phys_to_virt( + rx_buffer_info->page_dma + + rx_buffer_info->page_offset + ), + PAGE_SIZE/2, true); + } + } + + if (i == rx_ring->next_to_use) + pr_cont(" NTU\n"); + else if (i == rx_ring->next_to_clean) + pr_cont(" NTC\n"); + else + pr_cont("\n"); + + } + } + +exit: + return; +} + +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: + 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; + } +} + +static inline 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: + 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; + } +} + +void ixgbe_unmap_and_free_tx_resource(struct ixgbe_ring *tx_ring, + struct ixgbe_tx_buffer *tx_buffer_info) +{ + if (tx_buffer_info->dma) { + if (tx_buffer_info->mapped_as_page) + dma_unmap_page(tx_ring->dev, + tx_buffer_info->dma, + tx_buffer_info->length, + DMA_TO_DEVICE); + else + dma_unmap_single(tx_ring->dev, + tx_buffer_info->dma, + tx_buffer_info->length, + DMA_TO_DEVICE); + tx_buffer_info->dma = 0; + } + if (tx_buffer_info->skb) { + dev_kfree_skb_any(tx_buffer_info->skb); + tx_buffer_info->skb = NULL; + } + tx_buffer_info->time_stamp = 0; + /* tx_buffer_info must be completely set up in the transmit path */ +} + +static void ixgbe_update_xoff_received(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_hw_stats *hwstats = &adapter->stats; + u32 data = 0; + u32 xoff[8] = {0}; + int i; + + if ((hw->fc.current_mode == ixgbe_fc_full) || + (hw->fc.current_mode == ixgbe_fc_rx_pause)) { + 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); + return; + } else if (!(adapter->dcb_cfg.pfc_mode_enable)) + return; + + /* update stats for each tc, only valid with PFC enabled */ + for (i = 0; i < MAX_TX_PACKET_BUFFERS; i++) { + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + xoff[i] = IXGBE_READ_REG(hw, IXGBE_PXOFFRXC(i)); + break; + default: + xoff[i] = IXGBE_READ_REG(hw, IXGBE_PXOFFRXCNT(i)); + } + hwstats->pxoffrxc[i] += xoff[i]; + } + + /* 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]; + u8 tc = tx_ring->dcb_tc; + + if (xoff[tc]) + clear_bit(__IXGBE_HANG_CHECK_ARMED, &tx_ring->state); + } +} + +static u64 ixgbe_get_tx_completed(struct ixgbe_ring *ring) +{ + return ring->tx_stats.completed; +} + +static u64 ixgbe_get_tx_pending(struct ixgbe_ring *ring) +{ + struct ixgbe_adapter *adapter = netdev_priv(ring->netdev); + struct ixgbe_hw *hw = &adapter->hw; + + u32 head = IXGBE_READ_REG(hw, IXGBE_TDH(ring->reg_idx)); + u32 tail = IXGBE_READ_REG(hw, IXGBE_TDT(ring->reg_idx)); + + if (head != tail) + return (head < tail) ? + tail - head : (tail + ring->count - head); + + return 0; +} + +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); + bool ret = false; + + 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 */ + ret = test_and_set_bit(__IXGBE_HANG_CHECK_ARMED, + &tx_ring->state); + } else { + /* 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 ret; +} + +/** + * 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)) { + adapter->flags2 |= IXGBE_FLAG2_RESET_REQUESTED; + ixgbe_service_event_schedule(adapter); + } +} + +/** + * ixgbe_clean_tx_irq - Reclaim resources after transmit completes + * @q_vector: structure containing interrupt and ring information + * @tx_ring: tx ring to clean + **/ +static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, + struct ixgbe_ring *tx_ring) +{ + struct ixgbe_adapter *adapter = q_vector->adapter; + union ixgbe_adv_tx_desc *tx_desc, *eop_desc; + struct ixgbe_tx_buffer *tx_buffer_info; + unsigned int total_bytes = 0, total_packets = 0; + u16 i, eop, count = 0; + + i = tx_ring->next_to_clean; + eop = tx_ring->tx_buffer_info[i].next_to_watch; + eop_desc = IXGBE_TX_DESC_ADV(tx_ring, eop); + + while ((eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)) && + (count < q_vector->tx.work_limit)) { + bool cleaned = false; + rmb(); /* read buffer_info after eop_desc */ + for ( ; !cleaned; count++) { + tx_desc = IXGBE_TX_DESC_ADV(tx_ring, i); + tx_buffer_info = &tx_ring->tx_buffer_info[i]; + + tx_desc->wb.status = 0; + cleaned = (i == eop); + + i++; + if (i == tx_ring->count) + i = 0; + + if (cleaned && tx_buffer_info->skb) { + total_bytes += tx_buffer_info->bytecount; + total_packets += tx_buffer_info->gso_segs; + } + + ixgbe_unmap_and_free_tx_resource(tx_ring, + tx_buffer_info); + } + + tx_ring->tx_stats.completed++; + eop = tx_ring->tx_buffer_info[i].next_to_watch; + eop_desc = IXGBE_TX_DESC_ADV(tx_ring, eop); + } + + tx_ring->next_to_clean = i; + tx_ring->stats.bytes += total_bytes; + tx_ring->stats.packets += total_packets; + u64_stats_update_begin(&tx_ring->syncp); + q_vector->tx.total_bytes += total_bytes; + q_vector->tx.total_packets += total_packets; + u64_stats_update_end(&tx_ring->syncp); + + 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; + tx_desc = IXGBE_TX_DESC_ADV(tx_ring, eop); + e_err(drv, "Detected Tx Unit Hang\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", + 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, eop, + tx_ring->tx_buffer_info[eop].time_stamp, jiffies); + + 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; + } + +#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2) + if (unlikely(count && 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 count < q_vector->tx.work_limit; +} + +#ifdef CONFIG_IXGBE_DCA +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; + u8 reg_idx = rx_ring->reg_idx; + + rxctrl = IXGBE_READ_REG(hw, IXGBE_DCA_RXCTRL(reg_idx)); + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + rxctrl &= ~IXGBE_DCA_RXCTRL_CPUID_MASK; + rxctrl |= dca3_get_tag(&adapter->pdev->dev, cpu); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + rxctrl &= ~IXGBE_DCA_RXCTRL_CPUID_MASK_82599; + rxctrl |= (dca3_get_tag(&adapter->pdev->dev, cpu) << + IXGBE_DCA_RXCTRL_CPUID_SHIFT_82599); + break; + default: + break; + } + rxctrl |= IXGBE_DCA_RXCTRL_DESC_DCA_EN; + rxctrl |= IXGBE_DCA_RXCTRL_HEAD_DCA_EN; + rxctrl &= ~(IXGBE_DCA_RXCTRL_DESC_RRO_EN); + IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(reg_idx), rxctrl); +} + +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; + u8 reg_idx = tx_ring->reg_idx; + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + txctrl = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL(reg_idx)); + txctrl &= ~IXGBE_DCA_TXCTRL_CPUID_MASK; + txctrl |= dca3_get_tag(&adapter->pdev->dev, cpu); + txctrl |= IXGBE_DCA_TXCTRL_DESC_DCA_EN; + IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL(reg_idx), txctrl); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + txctrl = IXGBE_READ_REG(hw, IXGBE_DCA_TXCTRL_82599(reg_idx)); + txctrl &= ~IXGBE_DCA_TXCTRL_CPUID_MASK_82599; + txctrl |= (dca3_get_tag(&adapter->pdev->dev, cpu) << + IXGBE_DCA_TXCTRL_CPUID_SHIFT_82599); + txctrl |= IXGBE_DCA_TXCTRL_DESC_DCA_EN; + IXGBE_WRITE_REG(hw, IXGBE_DCA_TXCTRL_82599(reg_idx), txctrl); + break; + default: + break; + } +} + +static void ixgbe_update_dca(struct ixgbe_q_vector *q_vector) +{ + struct ixgbe_adapter *adapter = q_vector->adapter; + int cpu = get_cpu(); + long r_idx; + int i; + + if (q_vector->cpu == cpu) + goto out_no_update; + + r_idx = find_first_bit(q_vector->tx.idx, adapter->num_tx_queues); + for (i = 0; i < q_vector->tx.count; i++) { + ixgbe_update_tx_dca(adapter, adapter->tx_ring[r_idx], cpu); + r_idx = find_next_bit(q_vector->tx.idx, adapter->num_tx_queues, + r_idx + 1); + } + + r_idx = find_first_bit(q_vector->rx.idx, adapter->num_rx_queues); + for (i = 0; i < q_vector->rx.count; i++) { + ixgbe_update_rx_dca(adapter, adapter->rx_ring[r_idx], cpu); + r_idx = find_next_bit(q_vector->rx.idx, adapter->num_rx_queues, + r_idx + 1); + } + + q_vector->cpu = cpu; +out_no_update: + put_cpu(); +} + +static void ixgbe_setup_dca(struct ixgbe_adapter *adapter) +{ + int num_q_vectors; + int i; + + if (!(adapter->flags & IXGBE_FLAG_DCA_ENABLED)) + return; + + /* always use CB2 mode, difference is masked in the CB driver */ + IXGBE_WRITE_REG(&adapter->hw, IXGBE_DCA_CTRL, 2); + + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) + num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + else + num_q_vectors = 1; + + for (i = 0; i < 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_setup_dca(adapter); + break; + } + /* Fall Through since 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, 1); + } + break; + } + + return 0; +} +#endif /* CONFIG_IXGBE_DCA */ + +static inline void ixgbe_rx_hash(union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + skb->rxhash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss); +} + +/** + * ixgbe_rx_is_fcoe - check the rx desc for incoming pkt type + * @adapter: address of board private structure + * @rx_desc: advanced rx descriptor + * + * Returns : true if it is FCoE pkt + */ +static inline bool ixgbe_rx_is_fcoe(struct ixgbe_adapter *adapter, + union ixgbe_adv_rx_desc *rx_desc) +{ + __le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info; + + return (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) && + ((pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_ETQF_MASK)) == + (cpu_to_le16(IXGBE_ETQF_FILTER_FCOE << + IXGBE_RXDADV_PKTTYPE_ETQF_SHIFT))); +} + +/** + * ixgbe_receive_skb - Send a completed packet up the stack + * @adapter: board private structure + * @skb: packet to send up + * @status: hardware indication of status of receive + * @rx_ring: rx descriptor ring (for a specific queue) to setup + * @rx_desc: rx descriptor + **/ +static void ixgbe_receive_skb(struct ixgbe_q_vector *q_vector, + struct sk_buff *skb, u8 status, + struct ixgbe_ring *ring, + union ixgbe_adv_rx_desc *rx_desc) +{ + struct ixgbe_adapter *adapter = q_vector->adapter; + struct napi_struct *napi = &q_vector->napi; + bool is_vlan = (status & IXGBE_RXD_STAT_VP); + u16 tag = le16_to_cpu(rx_desc->wb.upper.vlan); + + if (is_vlan && (tag & VLAN_VID_MASK)) + __vlan_hwaccel_put_tag(skb, tag); + + if (!(adapter->flags & IXGBE_FLAG_IN_NETPOLL)) + napi_gro_receive(napi, skb); + else + netif_rx(skb); +} + +/** + * ixgbe_rx_checksum - indicate in skb if hw indicated a good cksum + * @adapter: address of board private structure + * @status_err: hardware indication of status of receive + * @skb: skb currently being received and modified + * @status_err: status error value of last descriptor in packet + **/ +static inline void ixgbe_rx_checksum(struct ixgbe_adapter *adapter, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb, + u32 status_err) +{ + skb->ip_summed = CHECKSUM_NONE; + + /* Rx csum disabled */ + if (!(adapter->flags & IXGBE_FLAG_RX_CSUM_ENABLED)) + return; + + /* if IP and error */ + if ((status_err & IXGBE_RXD_STAT_IPCS) && + (status_err & IXGBE_RXDADV_ERR_IPE)) { + adapter->hw_csum_rx_error++; + return; + } + + if (!(status_err & IXGBE_RXD_STAT_L4CS)) + return; + + if (status_err & IXGBE_RXDADV_ERR_TCPE) { + u16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info; + + /* + * 82599 errata, UDP frames with a 0 checksum can be marked as + * checksum errors. + */ + if ((pkt_info & IXGBE_RXDADV_PKTTYPE_UDP) && + (adapter->hw.mac.type == ixgbe_mac_82599EB)) + return; + + adapter->hw_csum_rx_error++; + return; + } + + /* It must be a TCP or UDP packet with a valid checksum */ + skb->ip_summed = CHECKSUM_UNNECESSARY; +} + +static inline void ixgbe_release_rx_desc(struct ixgbe_ring *rx_ring, u32 val) +{ + /* + * 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(val, rx_ring->tail); +} + +/** + * ixgbe_alloc_rx_buffers - Replace used receive buffers; packet split + * @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; + struct sk_buff *skb; + u16 i = rx_ring->next_to_use; + + /* do nothing if no valid netdev defined */ + if (!rx_ring->netdev) + return; + + while (cleaned_count--) { + rx_desc = IXGBE_RX_DESC_ADV(rx_ring, i); + bi = &rx_ring->rx_buffer_info[i]; + skb = bi->skb; + + if (!skb) { + skb = netdev_alloc_skb_ip_align(rx_ring->netdev, + rx_ring->rx_buf_len); + if (!skb) { + rx_ring->rx_stats.alloc_rx_buff_failed++; + goto no_buffers; + } + /* initialize queue mapping */ + skb_record_rx_queue(skb, rx_ring->queue_index); + bi->skb = skb; + } + + if (!bi->dma) { + bi->dma = dma_map_single(rx_ring->dev, + skb->data, + rx_ring->rx_buf_len, + DMA_FROM_DEVICE); + if (dma_mapping_error(rx_ring->dev, bi->dma)) { + rx_ring->rx_stats.alloc_rx_buff_failed++; + bi->dma = 0; + goto no_buffers; + } + } + + if (ring_is_ps_enabled(rx_ring)) { + if (!bi->page) { + bi->page = netdev_alloc_page(rx_ring->netdev); + if (!bi->page) { + rx_ring->rx_stats.alloc_rx_page_failed++; + goto no_buffers; + } + } + + if (!bi->page_dma) { + /* use a half page if we're re-using */ + bi->page_offset ^= PAGE_SIZE / 2; + bi->page_dma = dma_map_page(rx_ring->dev, + bi->page, + bi->page_offset, + PAGE_SIZE / 2, + DMA_FROM_DEVICE); + if (dma_mapping_error(rx_ring->dev, + bi->page_dma)) { + rx_ring->rx_stats.alloc_rx_page_failed++; + bi->page_dma = 0; + goto no_buffers; + } + } + + /* 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->page_dma); + rx_desc->read.hdr_addr = cpu_to_le64(bi->dma); + } else { + rx_desc->read.pkt_addr = cpu_to_le64(bi->dma); + rx_desc->read.hdr_addr = 0; + } + + i++; + if (i == rx_ring->count) + i = 0; + } + +no_buffers: + if (rx_ring->next_to_use != i) { + rx_ring->next_to_use = i; + ixgbe_release_rx_desc(rx_ring, i); + } +} + +static inline u16 ixgbe_get_hlen(union ixgbe_adv_rx_desc *rx_desc) +{ + /* HW will not DMA in data larger than the given buffer, even if it + * parses the (NFS, of course) header to be larger. In that case, it + * fills the header buffer and spills the rest into the page. + */ + u16 hdr_info = le16_to_cpu(rx_desc->wb.lower.lo_dword.hs_rss.hdr_info); + u16 hlen = (hdr_info & IXGBE_RXDADV_HDRBUFLEN_MASK) >> + IXGBE_RXDADV_HDRBUFLEN_SHIFT; + if (hlen > IXGBE_RX_HDR_SIZE) + hlen = IXGBE_RX_HDR_SIZE; + return hlen; +} + +/** + * ixgbe_transform_rsc_queue - change rsc queue into a full packet + * @skb: pointer to the last skb in the rsc queue + * + * This function changes a queue full of hw rsc buffers into a completed + * packet. It uses the ->prev pointers to find the first packet and then + * turns it into the frag list owner. + **/ +static inline struct sk_buff *ixgbe_transform_rsc_queue(struct sk_buff *skb) +{ + unsigned int frag_list_size = 0; + unsigned int skb_cnt = 1; + + while (skb->prev) { + struct sk_buff *prev = skb->prev; + frag_list_size += skb->len; + skb->prev = NULL; + skb = prev; + skb_cnt++; + } + + skb_shinfo(skb)->frag_list = skb->next; + skb->next = NULL; + skb->len += frag_list_size; + skb->data_len += frag_list_size; + skb->truesize += frag_list_size; + IXGBE_RSC_CB(skb)->skb_cnt = skb_cnt; + + return skb; +} + +static inline bool ixgbe_get_rsc_state(union ixgbe_adv_rx_desc *rx_desc) +{ + return !!(le32_to_cpu(rx_desc->wb.lower.lo_dword.data) & + IXGBE_RXDADV_RSCCNT_MASK); +} + +static void ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, + struct ixgbe_ring *rx_ring, + int *work_done, int work_to_do) +{ + struct ixgbe_adapter *adapter = q_vector->adapter; + union ixgbe_adv_rx_desc *rx_desc, *next_rxd; + struct ixgbe_rx_buffer *rx_buffer_info, *next_buffer; + struct sk_buff *skb; + unsigned int total_rx_bytes = 0, total_rx_packets = 0; + const int current_node = numa_node_id(); +#ifdef IXGBE_FCOE + int ddp_bytes = 0; +#endif /* IXGBE_FCOE */ + u32 staterr; + u16 i; + u16 cleaned_count = 0; + bool pkt_is_rsc = false; + + i = rx_ring->next_to_clean; + rx_desc = IXGBE_RX_DESC_ADV(rx_ring, i); + staterr = le32_to_cpu(rx_desc->wb.upper.status_error); + + while (staterr & IXGBE_RXD_STAT_DD) { + u32 upper_len = 0; + + rmb(); /* read descriptor and rx_buffer_info after status DD */ + + rx_buffer_info = &rx_ring->rx_buffer_info[i]; + + skb = rx_buffer_info->skb; + rx_buffer_info->skb = NULL; + prefetch(skb->data); + + if (ring_is_rsc_enabled(rx_ring)) + pkt_is_rsc = ixgbe_get_rsc_state(rx_desc); + + /* if this is a skb from previous receive DMA will be 0 */ + if (rx_buffer_info->dma) { + u16 hlen; + if (pkt_is_rsc && + !(staterr & IXGBE_RXD_STAT_EOP) && + !skb->prev) { + /* + * When HWRSC is enabled, 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 + */ + IXGBE_RSC_CB(skb)->delay_unmap = true; + IXGBE_RSC_CB(skb)->dma = rx_buffer_info->dma; + } else { + dma_unmap_single(rx_ring->dev, + rx_buffer_info->dma, + rx_ring->rx_buf_len, + DMA_FROM_DEVICE); + } + rx_buffer_info->dma = 0; + + if (ring_is_ps_enabled(rx_ring)) { + hlen = ixgbe_get_hlen(rx_desc); + upper_len = le16_to_cpu(rx_desc->wb.upper.length); + } else { + hlen = le16_to_cpu(rx_desc->wb.upper.length); + } + + skb_put(skb, hlen); + } else { + /* assume packet split since header is unmapped */ + upper_len = le16_to_cpu(rx_desc->wb.upper.length); + } + + if (upper_len) { + dma_unmap_page(rx_ring->dev, + rx_buffer_info->page_dma, + PAGE_SIZE / 2, + DMA_FROM_DEVICE); + rx_buffer_info->page_dma = 0; + skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags, + rx_buffer_info->page, + rx_buffer_info->page_offset, + upper_len); + + if ((page_count(rx_buffer_info->page) == 1) && + (page_to_nid(rx_buffer_info->page) == current_node)) + get_page(rx_buffer_info->page); + else + rx_buffer_info->page = NULL; + + skb->len += upper_len; + skb->data_len += upper_len; + skb->truesize += upper_len; + } + + i++; + if (i == rx_ring->count) + i = 0; + + next_rxd = IXGBE_RX_DESC_ADV(rx_ring, i); + prefetch(next_rxd); + cleaned_count++; + + if (pkt_is_rsc) { + u32 nextp = (staterr & IXGBE_RXDADV_NEXTP_MASK) >> + IXGBE_RXDADV_NEXTP_SHIFT; + next_buffer = &rx_ring->rx_buffer_info[nextp]; + } else { + next_buffer = &rx_ring->rx_buffer_info[i]; + } + + if (!(staterr & IXGBE_RXD_STAT_EOP)) { + if (ring_is_ps_enabled(rx_ring)) { + rx_buffer_info->skb = next_buffer->skb; + rx_buffer_info->dma = next_buffer->dma; + next_buffer->skb = skb; + next_buffer->dma = 0; + } else { + skb->next = next_buffer->skb; + skb->next->prev = skb; + } + rx_ring->rx_stats.non_eop_descs++; + goto next_desc; + } + + if (skb->prev) { + skb = ixgbe_transform_rsc_queue(skb); + /* if we got here without RSC the packet is invalid */ + if (!pkt_is_rsc) { + __pskb_trim(skb, 0); + rx_buffer_info->skb = skb; + goto next_desc; + } + } + + if (ring_is_rsc_enabled(rx_ring)) { + if (IXGBE_RSC_CB(skb)->delay_unmap) { + dma_unmap_single(rx_ring->dev, + IXGBE_RSC_CB(skb)->dma, + rx_ring->rx_buf_len, + DMA_FROM_DEVICE); + IXGBE_RSC_CB(skb)->dma = 0; + IXGBE_RSC_CB(skb)->delay_unmap = false; + } + } + if (pkt_is_rsc) { + if (ring_is_ps_enabled(rx_ring)) + rx_ring->rx_stats.rsc_count += + skb_shinfo(skb)->nr_frags; + else + rx_ring->rx_stats.rsc_count += + IXGBE_RSC_CB(skb)->skb_cnt; + rx_ring->rx_stats.rsc_flush++; + } + + /* ERR_MASK will only have valid bits if EOP set */ + if (unlikely(staterr & IXGBE_RXDADV_ERR_FRAME_ERR_MASK)) { + dev_kfree_skb_any(skb); + goto next_desc; + } + + ixgbe_rx_checksum(adapter, rx_desc, skb, staterr); + if (adapter->netdev->features & NETIF_F_RXHASH) + ixgbe_rx_hash(rx_desc, skb); + + /* probably a little skewed due to removing CRC */ + total_rx_bytes += skb->len; + total_rx_packets++; + + skb->protocol = eth_type_trans(skb, rx_ring->netdev); +#ifdef IXGBE_FCOE + /* if ddp, not passing to ULD unless for FCP_RSP or error */ + if (ixgbe_rx_is_fcoe(adapter, rx_desc)) { + ddp_bytes = ixgbe_fcoe_ddp(adapter, rx_desc, skb, + staterr); + if (!ddp_bytes) + goto next_desc; + } +#endif /* IXGBE_FCOE */ + ixgbe_receive_skb(q_vector, skb, staterr, rx_ring, rx_desc); + +next_desc: + rx_desc->wb.upper.status_error = 0; + + (*work_done)++; + if (*work_done >= work_to_do) + break; + + /* 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; + } + + /* use prefetched values */ + rx_desc = next_rxd; + staterr = le32_to_cpu(rx_desc->wb.upper.status_error); + } + + rx_ring->next_to_clean = i; + cleaned_count = ixgbe_desc_unused(rx_ring); + + if (cleaned_count) + ixgbe_alloc_rx_buffers(rx_ring, cleaned_count); + +#ifdef IXGBE_FCOE + /* include DDPed FCoE data */ + if (ddp_bytes > 0) { + unsigned int 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); + } +#endif /* IXGBE_FCOE */ + + 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; +} + +static int ixgbe_clean_rxonly(struct napi_struct *, int); +/** + * 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 i, q_vectors, v_idx, r_idx; + u32 mask; + + q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + + /* + * Populate the IVAR table and set the ITR values to the + * corresponding register. + */ + for (v_idx = 0; v_idx < q_vectors; v_idx++) { + q_vector = adapter->q_vector[v_idx]; + /* XXX for_each_set_bit(...) */ + r_idx = find_first_bit(q_vector->rx.idx, + adapter->num_rx_queues); + + for (i = 0; i < q_vector->rx.count; i++) { + u8 reg_idx = adapter->rx_ring[r_idx]->reg_idx; + ixgbe_set_ivar(adapter, 0, reg_idx, v_idx); + r_idx = find_next_bit(q_vector->rx.idx, + adapter->num_rx_queues, + r_idx + 1); + } + r_idx = find_first_bit(q_vector->tx.idx, + adapter->num_tx_queues); + + for (i = 0; i < q_vector->tx.count; i++) { + u8 reg_idx = adapter->tx_ring[r_idx]->reg_idx; + ixgbe_set_ivar(adapter, 1, reg_idx, v_idx); + r_idx = find_next_bit(q_vector->tx.idx, + adapter->num_tx_queues, + r_idx + 1); + } + + if (q_vector->tx.count && !q_vector->rx.count) + /* tx only */ + q_vector->eitr = adapter->tx_eitr_param; + else if (q_vector->rx.count) + /* rx or mixed */ + q_vector->eitr = adapter->rx_eitr_param; + + ixgbe_write_eitr(q_vector); + /* If ATR is enabled, set interrupt affinity */ + if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) { + /* + * Allocate the affinity_hint cpumask, assign the mask + * for this vector, and set our affinity_hint for + * this irq. + */ + if (!alloc_cpumask_var(&q_vector->affinity_mask, + GFP_KERNEL)) + return; + cpumask_set_cpu(v_idx, q_vector->affinity_mask); + irq_set_affinity_hint(adapter->msix_entries[v_idx].vector, + q_vector->affinity_mask); + } + } + + 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: + 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; + if (adapter->num_vfs) + mask &= ~(IXGBE_EIMS_OTHER | + IXGBE_EIMS_MAILBOX | + IXGBE_EIMS_LSC); + else + mask &= ~(IXGBE_EIMS_OTHER | IXGBE_EIMS_LSC); + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIAC, mask); +} + +enum latency_range { + lowest_latency = 0, + low_latency = 1, + bulk_latency = 2, + latency_invalid = 255 +}; + +/** + * 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. + * this functionality is controlled by the InterruptThrottleRate module + * parameter (see ixgbe_param.c) + **/ +static void ixgbe_update_itr(struct ixgbe_q_vector *q_vector, + struct ixgbe_ring_container *ring_container) +{ + u64 bytes_perint; + struct ixgbe_adapter *adapter = q_vector->adapter; + int bytes = ring_container->total_bytes; + int packets = ring_container->total_packets; + u32 timepassed_us; + u8 itr_setting = ring_container->itr; + + if (packets == 0) + return; + + /* simple throttlerate management + * 0-20MB/s lowest (100000 ints/s) + * 20-100MB/s low (20000 ints/s) + * 100-1249MB/s bulk (8000 ints/s) + */ + /* what was last interrupt timeslice? */ + timepassed_us = 1000000/q_vector->eitr; + bytes_perint = bytes / timepassed_us; /* bytes/usec */ + + switch (itr_setting) { + case lowest_latency: + if (bytes_perint > adapter->eitr_low) + itr_setting = low_latency; + break; + case low_latency: + if (bytes_perint > adapter->eitr_high) + itr_setting = bulk_latency; + else if (bytes_perint <= adapter->eitr_low) + itr_setting = lowest_latency; + break; + case bulk_latency: + if (bytes_perint <= adapter->eitr_high) + 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; +} + +/** + * 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 = EITR_INTS_PER_SEC_TO_REG(q_vector->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: + /* + * 82599 and X540 can support a value of zero, so allow it for + * max interrupt rate, but there is an errata where it can + * not be zero with RSC + */ + if (itr_reg == 8 && + !(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)) + itr_reg = 0; + + /* + * 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 = q_vector->eitr; + u8 current_itr; + + ixgbe_update_itr(q_vector, &q_vector->tx); + ixgbe_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 = 100000; + break; + case low_latency: + new_itr = 20000; /* aka hwitr = ~200 */ + break; + case bulk_latency: + new_itr = 8000; + break; + default: + break; + } + + if (new_itr != q_vector->eitr) { + /* do an exponential smoothing */ + new_itr = ((q_vector->eitr * 9) + new_itr)/10; + + /* save the algorithm value here */ + q_vector->eitr = new_itr; + + ixgbe_write_eitr(q_vector); + } +} + +/** + * ixgbe_check_overtemp_subtask - check for over tempurature + * @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; + + if (test_bit(__IXGBE_DOWN, &adapter->state)) + return; + + if (!(adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE) && + !(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) && + !(eicr & IXGBE_EICR_LSC)) + return; + + if (!(eicr & IXGBE_EICR_LSC) && hw->mac.ops.check_link) { + u32 autoneg; + bool link_up = false; + + hw->mac.ops.check_link(hw, &autoneg, &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; + default: + if (!(eicr & IXGBE_EICR_GPI_SDP0)) + return; + break; + } + e_crit(drv, + "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\n"); + + 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)) { + 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); + } +} + +static void ixgbe_check_sfp_event(struct ixgbe_adapter *adapter, u32 eicr) +{ + struct ixgbe_hw *hw = &adapter->hw; + + if (eicr & IXGBE_EICR_GPI_SDP2) { + /* Clear the interrupt */ + IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP2); + if (!test_bit(__IXGBE_DOWN, &adapter->state)) { + adapter->flags2 |= IXGBE_FLAG2_SFP_NEEDS_RESET; + ixgbe_service_event_schedule(adapter); + } + } + + if (eicr & IXGBE_EICR_GPI_SDP1) { + /* Clear the interrupt */ + IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_GPI_SDP1); + 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 irqreturn_t ixgbe_msix_lsc(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); + 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: + /* 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); + eicr &= ~IXGBE_EICR_FLOW_DIR; + adapter->flags2 |= IXGBE_FLAG2_FDIR_REQUIRES_REINIT; + ixgbe_service_event_schedule(adapter); + } + } + ixgbe_check_sfp_event(adapter, eicr); + if ((adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE) && + ((eicr & IXGBE_EICR_GPI_SDP0) || (eicr & IXGBE_EICR_LSC))) { + if (!test_bit(__IXGBE_DOWN, &adapter->state)) { + adapter->interrupt_event = eicr; + adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_EVENT; + ixgbe_service_event_schedule(adapter); + } + } + break; + default: + break; + } + + ixgbe_check_fan_failure(adapter, eicr); + + /* re-enable the original interrupt state, no lsc, no queues */ + if (!test_bit(__IXGBE_DOWN, &adapter->state)) + IXGBE_WRITE_REG(hw, IXGBE_EIMS, eicr & + ~(IXGBE_EIMS_LSC | IXGBE_EIMS_RTX_QUEUE)); + + return IRQ_HANDLED; +} + +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: + 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 */ +} + +static inline void ixgbe_irq_disable_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_EIMC, mask); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + mask = (qmask & 0xFFFFFFFF); + if (mask) + IXGBE_WRITE_REG(hw, IXGBE_EIMC_EX(0), mask); + mask = (qmask >> 32); + if (mask) + IXGBE_WRITE_REG(hw, IXGBE_EIMC_EX(1), mask); + break; + default: + break; + } + /* skip the flush */ +} + +static irqreturn_t ixgbe_msix_clean_tx(int irq, void *data) +{ + struct ixgbe_q_vector *q_vector = data; + struct ixgbe_adapter *adapter = q_vector->adapter; + struct ixgbe_ring *tx_ring; + int i, r_idx; + + if (!q_vector->tx.count) + return IRQ_HANDLED; + + r_idx = find_first_bit(q_vector->tx.idx, adapter->num_tx_queues); + for (i = 0; i < q_vector->tx.count; i++) { + tx_ring = adapter->tx_ring[r_idx]; + r_idx = find_next_bit(q_vector->tx.idx, adapter->num_tx_queues, + r_idx + 1); + } + + /* EIAM disabled interrupts (on this vector) for us */ + napi_schedule(&q_vector->napi); + + return IRQ_HANDLED; +} + +/** + * ixgbe_msix_clean_rx - single unshared vector rx clean (all queues) + * @irq: unused + * @data: pointer to our q_vector struct for this interrupt vector + **/ +static irqreturn_t ixgbe_msix_clean_rx(int irq, void *data) +{ + struct ixgbe_q_vector *q_vector = data; + struct ixgbe_adapter *adapter = q_vector->adapter; + struct ixgbe_ring *rx_ring; + int r_idx; + int i; + +#ifdef CONFIG_IXGBE_DCA + if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) + ixgbe_update_dca(q_vector); +#endif + + r_idx = find_first_bit(q_vector->rx.idx, adapter->num_rx_queues); + for (i = 0; i < q_vector->rx.count; i++) { + rx_ring = adapter->rx_ring[r_idx]; + r_idx = find_next_bit(q_vector->rx.idx, adapter->num_rx_queues, + r_idx + 1); + } + + if (!q_vector->rx.count) + return IRQ_HANDLED; + + /* EIAM disabled interrupts (on this vector) for us */ + napi_schedule(&q_vector->napi); + + return IRQ_HANDLED; +} + +static irqreturn_t ixgbe_msix_clean_many(int irq, void *data) +{ + struct ixgbe_q_vector *q_vector = data; + struct ixgbe_adapter *adapter = q_vector->adapter; + struct ixgbe_ring *ring; + int r_idx; + int i; + + if (!q_vector->tx.count && !q_vector->rx.count) + return IRQ_HANDLED; + + r_idx = find_first_bit(q_vector->tx.idx, adapter->num_tx_queues); + for (i = 0; i < q_vector->tx.count; i++) { + ring = adapter->tx_ring[r_idx]; + r_idx = find_next_bit(q_vector->tx.idx, adapter->num_tx_queues, + r_idx + 1); + } + + r_idx = find_first_bit(q_vector->rx.idx, adapter->num_rx_queues); + for (i = 0; i < q_vector->rx.count; i++) { + ring = adapter->rx_ring[r_idx]; + r_idx = find_next_bit(q_vector->rx.idx, adapter->num_rx_queues, + r_idx + 1); + } + + /* EIAM disabled interrupts (on this vector) for us */ + napi_schedule(&q_vector->napi); + + return IRQ_HANDLED; +} + +/** + * ixgbe_clean_rxonly - msix (aka one shot) rx clean routine + * @napi: napi struct with our devices info in it + * @budget: amount of work driver is allowed to do this pass, in packets + * + * This function is optimized for cleaning one queue only on a single + * q_vector!!! + **/ +static int ixgbe_clean_rxonly(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 *rx_ring = NULL; + int work_done = 0; + long r_idx; + +#ifdef CONFIG_IXGBE_DCA + if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) + ixgbe_update_dca(q_vector); +#endif + + r_idx = find_first_bit(q_vector->rx.idx, adapter->num_rx_queues); + rx_ring = adapter->rx_ring[r_idx]; + + ixgbe_clean_rx_irq(q_vector, rx_ring, &work_done, budget); + + /* If all Rx work done, exit the polling mode */ + if (work_done < budget) { + napi_complete(napi); + if (adapter->rx_itr_setting & 1) + ixgbe_set_itr(q_vector); + if (!test_bit(__IXGBE_DOWN, &adapter->state)) + ixgbe_irq_enable_queues(adapter, + ((u64)1 << q_vector->v_idx)); + } + + return work_done; +} + +/** + * ixgbe_clean_rxtx_many - msix (aka one shot) rx clean routine + * @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 rx queue associated with a + * q_vector. + **/ +static int ixgbe_clean_rxtx_many(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 = NULL; + int work_done = 0, i; + long r_idx; + bool tx_clean_complete = true; + +#ifdef CONFIG_IXGBE_DCA + if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) + ixgbe_update_dca(q_vector); +#endif + + r_idx = find_first_bit(q_vector->tx.idx, adapter->num_tx_queues); + for (i = 0; i < q_vector->tx.count; i++) { + ring = adapter->tx_ring[r_idx]; + tx_clean_complete &= ixgbe_clean_tx_irq(q_vector, ring); + r_idx = find_next_bit(q_vector->tx.idx, adapter->num_tx_queues, + r_idx + 1); + } + + /* attempt to distribute budget to each queue fairly, but don't allow + * the budget to go below 1 because we'll exit polling */ + budget /= (q_vector->rx.count ?: 1); + budget = max(budget, 1); + r_idx = find_first_bit(q_vector->rx.idx, adapter->num_rx_queues); + for (i = 0; i < q_vector->rx.count; i++) { + ring = adapter->rx_ring[r_idx]; + ixgbe_clean_rx_irq(q_vector, ring, &work_done, budget); + r_idx = find_next_bit(q_vector->rx.idx, adapter->num_rx_queues, + r_idx + 1); + } + + r_idx = find_first_bit(q_vector->rx.idx, adapter->num_rx_queues); + ring = adapter->rx_ring[r_idx]; + /* If all Rx work done, exit the polling mode */ + if (work_done < budget) { + napi_complete(napi); + if (adapter->rx_itr_setting & 1) + ixgbe_set_itr(q_vector); + if (!test_bit(__IXGBE_DOWN, &adapter->state)) + ixgbe_irq_enable_queues(adapter, + ((u64)1 << q_vector->v_idx)); + return 0; + } + + return work_done; +} + +/** + * ixgbe_clean_txonly - msix (aka one shot) tx clean routine + * @napi: napi struct with our devices info in it + * @budget: amount of work driver is allowed to do this pass, in packets + * + * This function is optimized for cleaning one queue only on a single + * q_vector!!! + **/ +static int ixgbe_clean_txonly(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 *tx_ring = NULL; + int work_done = 0; + long r_idx; + +#ifdef CONFIG_IXGBE_DCA + if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) + ixgbe_update_dca(q_vector); +#endif + + r_idx = find_first_bit(q_vector->tx.idx, adapter->num_tx_queues); + tx_ring = adapter->tx_ring[r_idx]; + + if (!ixgbe_clean_tx_irq(q_vector, tx_ring)) + work_done = budget; + + /* If all Tx work done, exit the polling mode */ + if (work_done < budget) { + napi_complete(napi); + if (adapter->tx_itr_setting & 1) + ixgbe_set_itr(q_vector); + if (!test_bit(__IXGBE_DOWN, &adapter->state)) + ixgbe_irq_enable_queues(adapter, + ((u64)1 << q_vector->v_idx)); + } + + return work_done; +} + +static inline void map_vector_to_rxq(struct ixgbe_adapter *a, int v_idx, + int r_idx) +{ + struct ixgbe_q_vector *q_vector = a->q_vector[v_idx]; + struct ixgbe_ring *rx_ring = a->rx_ring[r_idx]; + + set_bit(r_idx, q_vector->rx.idx); + q_vector->rx.count++; + rx_ring->q_vector = q_vector; +} + +static inline void map_vector_to_txq(struct ixgbe_adapter *a, int v_idx, + int t_idx) +{ + struct ixgbe_q_vector *q_vector = a->q_vector[v_idx]; + struct ixgbe_ring *tx_ring = a->tx_ring[t_idx]; + + set_bit(t_idx, q_vector->tx.idx); + q_vector->tx.count++; + tx_ring->q_vector = q_vector; + q_vector->tx.work_limit = a->tx_work_limit; +} + +/** + * ixgbe_map_rings_to_vectors - Maps descriptor rings to vectors + * @adapter: board private structure to initialize + * + * This function maps descriptor rings to the queue-specific vectors + * we were allotted through the MSI-X enabling code. Ideally, we'd have + * one vector per ring/queue, but on a constrained vector budget, we + * group the rings as "efficiently" as possible. You would add new + * mapping configurations in here. + **/ +static int ixgbe_map_rings_to_vectors(struct ixgbe_adapter *adapter) +{ + int q_vectors; + int v_start = 0; + int rxr_idx = 0, txr_idx = 0; + int rxr_remaining = adapter->num_rx_queues; + int txr_remaining = adapter->num_tx_queues; + int i, j; + int rqpv, tqpv; + int err = 0; + + /* No mapping required if MSI-X is disabled. */ + if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) + goto out; + + q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + + /* + * The ideal configuration... + * We have enough vectors to map one per queue. + */ + if (q_vectors == adapter->num_rx_queues + adapter->num_tx_queues) { + for (; rxr_idx < rxr_remaining; v_start++, rxr_idx++) + map_vector_to_rxq(adapter, v_start, rxr_idx); + + for (; txr_idx < txr_remaining; v_start++, txr_idx++) + map_vector_to_txq(adapter, v_start, txr_idx); + + goto out; + } + + /* + * If we don't have enough vectors for a 1-to-1 + * mapping, we'll have to group them so there are + * multiple queues per vector. + */ + /* Re-adjusting *qpv takes care of the remainder. */ + for (i = v_start; i < q_vectors; i++) { + rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - i); + for (j = 0; j < rqpv; j++) { + map_vector_to_rxq(adapter, i, rxr_idx); + rxr_idx++; + rxr_remaining--; + } + tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - i); + for (j = 0; j < tqpv; j++) { + map_vector_to_txq(adapter, i, txr_idx); + txr_idx++; + txr_remaining--; + } + } +out: + return err; +} + +/** + * 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; + irqreturn_t (*handler)(int, void *); + int i, vector, q_vectors, err; + int ri = 0, ti = 0; + + /* Decrement for Other and TCP Timer vectors */ + q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + + err = ixgbe_map_rings_to_vectors(adapter); + if (err) + return err; + +#define SET_HANDLER(_v) (((_v)->rx.count && (_v)->tx.count) \ + ? &ixgbe_msix_clean_many : \ + (_v)->rx.count ? &ixgbe_msix_clean_rx : \ + (_v)->tx.count ? &ixgbe_msix_clean_tx : \ + NULL) + for (vector = 0; vector < q_vectors; vector++) { + struct ixgbe_q_vector *q_vector = adapter->q_vector[vector]; + handler = SET_HANDLER(q_vector); + + if (handler == &ixgbe_msix_clean_rx) { + snprintf(q_vector->name, sizeof(q_vector->name) - 1, + "%s-%s-%d", netdev->name, "rx", ri++); + } else if (handler == &ixgbe_msix_clean_tx) { + snprintf(q_vector->name, sizeof(q_vector->name) - 1, + "%s-%s-%d", netdev->name, "tx", ti++); + } else if (handler == &ixgbe_msix_clean_many) { + snprintf(q_vector->name, sizeof(q_vector->name) - 1, + "%s-%s-%d", netdev->name, "TxRx", ri++); + ti++; + } else { + /* skip this unused q_vector */ + continue; + } + err = request_irq(adapter->msix_entries[vector].vector, + handler, 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; + } + } + + sprintf(adapter->lsc_int_name, "%s:lsc", netdev->name); + err = request_irq(adapter->msix_entries[vector].vector, + ixgbe_msix_lsc, 0, adapter->lsc_int_name, adapter); + if (err) { + e_err(probe, "request_irq for msix_lsc failed: %d\n", err); + goto free_queue_irqs; + } + + return 0; + +free_queue_irqs: + for (i = vector - 1; i >= 0; i--) + free_irq(adapter->msix_entries[--vector].vector, + adapter->q_vector[i]); + adapter->flags &= ~IXGBE_FLAG_MSIX_ENABLED; + pci_disable_msix(adapter->pdev); + kfree(adapter->msix_entries); + adapter->msix_entries = NULL; + return err; +} + +/** + * ixgbe_irq_enable - Enable default interrupt generation settings + * @adapter: board private structure + **/ +static inline void ixgbe_irq_enable(struct ixgbe_adapter *adapter, bool queues, + bool flush) +{ + u32 mask; + + mask = (IXGBE_EIMS_ENABLE_MASK & ~IXGBE_EIMS_RTX_QUEUE); + if (adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE) + mask |= IXGBE_EIMS_GPI_SDP0; + if (adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE) + mask |= IXGBE_EIMS_GPI_SDP1; + switch (adapter->hw.mac.type) { + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + mask |= IXGBE_EIMS_ECC; + mask |= IXGBE_EIMS_GPI_SDP1; + mask |= IXGBE_EIMS_GPI_SDP2; + if (adapter->num_vfs) + mask |= IXGBE_EIMS_MAILBOX; + break; + default: + break; + } + if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) + 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); + + if (adapter->num_vfs > 32) { + u32 eitrsel = (1 << (adapter->num_vfs - 32)) - 1; + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EITRSEL, eitrsel); + } +} + +/** + * 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 on 82598. Mask the interrupts + * 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 explict 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); + if ((adapter->flags2 & IXGBE_FLAG2_TEMP_SENSOR_CAPABLE) && + ((eicr & IXGBE_EICR_GPI_SDP0) || (eicr & IXGBE_EICR_LSC))) { + if (!test_bit(__IXGBE_DOWN, &adapter->state)) { + adapter->interrupt_event = eicr; + adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_EVENT; + ixgbe_service_event_schedule(adapter); + } + } + break; + default: + break; + } + + ixgbe_check_fan_failure(adapter, eicr); + + if (napi_schedule_prep(&(q_vector->napi))) { + /* would disable interrupts here but EIAM disabled it */ + __napi_schedule(&(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; +} + +static inline void ixgbe_reset_q_vectors(struct ixgbe_adapter *adapter) +{ + int i, q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + + for (i = 0; i < q_vectors; i++) { + struct ixgbe_q_vector *q_vector = adapter->q_vector[i]; + bitmap_zero(q_vector->rx.idx, MAX_RX_QUEUES); + bitmap_zero(q_vector->tx.idx, MAX_TX_QUEUES); + q_vector->rx.count = 0; + q_vector->tx.count = 0; + } +} + +/** + * 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) +{ + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) { + int i, q_vectors; + + 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.count && + !adapter->q_vector[i]->tx.count) + continue; + + free_irq(adapter->msix_entries[i].vector, + adapter->q_vector[i]); + } + + ixgbe_reset_q_vectors(adapter); + } else { + free_irq(adapter->pdev->irq, 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: + 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); + if (adapter->num_vfs > 32) + IXGBE_WRITE_REG(&adapter->hw, IXGBE_EITRSEL, 0); + break; + default: + break; + } + IXGBE_WRITE_FLUSH(&adapter->hw); + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) { + int i; + for (i = 0; i < adapter->num_msix_vectors; i++) + synchronize_irq(adapter->msix_entries[i].vector); + } else { + synchronize_irq(adapter->pdev->irq); + } +} + +/** + * ixgbe_configure_msi_and_legacy - Initialize PIN (INTA...) and MSI interrupts + * + **/ +static void ixgbe_configure_msi_and_legacy(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + + IXGBE_WRITE_REG(hw, IXGBE_EITR(0), + EITR_INTS_PER_SEC_TO_REG(adapter->rx_eitr_param)); + + ixgbe_set_ivar(adapter, 0, 0, 0); + ixgbe_set_ivar(adapter, 1, 0, 0); + + map_vector_to_rxq(adapter, 0, 0); + map_vector_to_txq(adapter, 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; + u8 reg_idx = ring->reg_idx; + + /* disable queue to avoid issues while updating state */ + txdctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx)); + IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), + txdctl & ~IXGBE_TXDCTL_ENABLE); + 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 = hw->hw_addr + IXGBE_TDT(reg_idx); + + /* configure fetching thresholds */ + if (adapter->rx_itr_setting == 0) { + /* cannot set wthresh when itr==0 */ + txdctl &= ~0x007F0000; + } else { + /* enable WTHRESH=8 descriptors, to encourage burst writeback */ + txdctl |= (8 << 16); + } + if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) { + /* PThresh workaround for Tx hang with DFP enabled. */ + txdctl |= 32; + } + + /* reinitialize flowdirector state */ + if ((adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) && + adapter->atr_sample_rate) { + 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; + } + + clear_bit(__IXGBE_HANG_CHECK_ARMED, &ring->state); + + /* enable queue */ + txdctl |= IXGBE_TXDCTL_ENABLE; + 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) + e_err(drv, "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; + u32 reg; + u8 tcs = netdev_get_num_tc(adapter->netdev); + + 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 */ + switch (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { + case (IXGBE_FLAG_SRIOV_ENABLED): + IXGBE_WRITE_REG(hw, IXGBE_MTQC, + (IXGBE_MTQC_VT_ENA | IXGBE_MTQC_64VF)); + break; + default: + if (!tcs) + reg = IXGBE_MTQC_64Q_1PB; + else if (tcs <= 4) + reg = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ; + else + reg = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_8TC_8TQ; + + IXGBE_WRITE_REG(hw, IXGBE_MTQC, reg); + + /* Enable Security TX Buffer IFG for multiple pb */ + if (tcs) { + reg = IXGBE_READ_REG(hw, IXGBE_SECTXMINIFG); + reg |= IXGBE_SECTX_DCB; + IXGBE_WRITE_REG(hw, IXGBE_SECTXMINIFG, reg); + } + break; + } + + /* 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]); +} + +#define IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT 2 + +static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter, + struct ixgbe_ring *rx_ring) +{ + u32 srrctl; + u8 reg_idx = rx_ring->reg_idx; + + switch (adapter->hw.mac.type) { + case ixgbe_mac_82598EB: { + struct ixgbe_ring_feature *feature = adapter->ring_feature; + const int mask = feature[RING_F_RSS].mask; + reg_idx = reg_idx & mask; + } + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + default: + break; + } + + srrctl = IXGBE_READ_REG(&adapter->hw, IXGBE_SRRCTL(reg_idx)); + + srrctl &= ~IXGBE_SRRCTL_BSIZEHDR_MASK; + srrctl &= ~IXGBE_SRRCTL_BSIZEPKT_MASK; + if (adapter->num_vfs) + srrctl |= IXGBE_SRRCTL_DROP_EN; + + srrctl |= (IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT) & + IXGBE_SRRCTL_BSIZEHDR_MASK; + + if (ring_is_ps_enabled(rx_ring)) { +#if (PAGE_SIZE / 2) > IXGBE_MAX_RXBUFFER + srrctl |= IXGBE_MAX_RXBUFFER >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; +#else + srrctl |= (PAGE_SIZE / 2) >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; +#endif + srrctl |= IXGBE_SRRCTL_DESCTYPE_HDR_SPLIT_ALWAYS; + } else { + srrctl |= ALIGN(rx_ring->rx_buf_len, 1024) >> + IXGBE_SRRCTL_BSIZEPKT_SHIFT; + srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF; + } + + IXGBE_WRITE_REG(&adapter->hw, IXGBE_SRRCTL(reg_idx), srrctl); +} + +static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + static const u32 seed[10] = { 0xE291D73D, 0x1805EC6C, 0x2A94B30D, + 0xA54F2BEC, 0xEA49AF7C, 0xE214AD3D, 0xB855AABE, + 0x6A3E67EA, 0x14364D17, 0x3BED200D}; + u32 mrqc = 0, reta = 0; + u32 rxcsum; + int i, j; + u8 tcs = netdev_get_num_tc(adapter->netdev); + int maxq = adapter->ring_feature[RING_F_RSS].indices; + + if (tcs) + maxq = min(maxq, adapter->num_tx_queues / tcs); + + /* Fill out hash function seeds */ + for (i = 0; i < 10; i++) + IXGBE_WRITE_REG(hw, IXGBE_RSSRK(i), seed[i]); + + /* Fill out redirection table */ + for (i = 0, j = 0; i < 128; i++, j++) { + if (j == maxq) + j = 0; + /* reta = 4-byte sliding window of + * 0x00..(indices-1)(indices-1)00..etc. */ + reta = (reta << 8) | (j * 0x11); + if ((i & 3) == 3) + IXGBE_WRITE_REG(hw, IXGBE_RETA(i >> 2), reta); + } + + /* 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 && + (adapter->flags & IXGBE_FLAG_RSS_ENABLED)) { + mrqc = IXGBE_MRQC_RSSEN; + } else { + int mask = adapter->flags & (IXGBE_FLAG_RSS_ENABLED + | IXGBE_FLAG_SRIOV_ENABLED); + + switch (mask) { + case (IXGBE_FLAG_RSS_ENABLED): + if (!tcs) + mrqc = IXGBE_MRQC_RSSEN; + else if (tcs <= 4) + mrqc = IXGBE_MRQC_RTRSS4TCEN; + else + mrqc = IXGBE_MRQC_RTRSS8TCEN; + break; + case (IXGBE_FLAG_SRIOV_ENABLED): + mrqc = IXGBE_MRQC_VMDQEN; + break; + default: + break; + } + } + + /* 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; + + IXGBE_WRITE_REG(hw, IXGBE_MRQC, mrqc); +} + +/** + * ixgbe_configure_rscctl - enable RSC for the indicated ring + * @adapter: address of board private structure + * @index: index of ring to set + **/ +static void ixgbe_configure_rscctl(struct ixgbe_adapter *adapter, + struct ixgbe_ring *ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 rscctrl; + int rx_buf_len; + u8 reg_idx = ring->reg_idx; + + if (!ring_is_rsc_enabled(ring)) + return; + + rx_buf_len = ring->rx_buf_len; + 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 65535 + */ + if (ring_is_ps_enabled(ring)) { +#if (MAX_SKB_FRAGS > 16) + rscctrl |= IXGBE_RSCCTL_MAXDESC_16; +#elif (MAX_SKB_FRAGS > 8) + rscctrl |= IXGBE_RSCCTL_MAXDESC_8; +#elif (MAX_SKB_FRAGS > 4) + rscctrl |= IXGBE_RSCCTL_MAXDESC_4; +#else + rscctrl |= IXGBE_RSCCTL_MAXDESC_1; +#endif + } else { + if (rx_buf_len < IXGBE_RXBUFFER_4096) + rscctrl |= IXGBE_RSCCTL_MAXDESC_16; + else if (rx_buf_len < IXGBE_RXBUFFER_8192) + rscctrl |= IXGBE_RSCCTL_MAXDESC_8; + else + rscctrl |= IXGBE_RSCCTL_MAXDESC_4; + } + IXGBE_WRITE_REG(hw, IXGBE_RSCCTL(reg_idx), rscctrl); +} + +/** + * ixgbe_set_uta - Set unicast filter table address + * @adapter: board private structure + * + * The unicast table address is a register array of 32-bit registers. + * The table is meant to be used in a way similar to how the MTA is used + * however due to certain limitations in the hardware it is necessary to + * set all the hash bits to 1 and use the VMOLR ROPE bit as a promiscuous + * enable bit to allow vlan tag stripping when promiscuous mode is enabled + **/ +static void ixgbe_set_uta(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int i; + + /* The UTA table only exists on 82599 hardware and newer */ + if (hw->mac.type < ixgbe_mac_82599EB) + return; + + /* we only need to do this if VMDq is enabled */ + if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) + return; + + for (i = 0; i < 128; i++) + IXGBE_WRITE_REG(hw, IXGBE_UTA(i), ~0); +} + +#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; + + /* 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_disable_rx_queue(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; + + 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); + + if (hw->mac.type == ixgbe_mac_82598EB && + !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP)) + return; + + /* the hardware may take up to 100us to really disable the rx queue */ + do { + udelay(10); + 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 cleared 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; + 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_RXDCTL(reg_idx)); + ixgbe_disable_rx_queue(adapter, ring); + + 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)); + IXGBE_WRITE_REG(hw, IXGBE_RDH(reg_idx), 0); + IXGBE_WRITE_REG(hw, IXGBE_RDT(reg_idx), 0); + ring->tail = hw->hw_addr + IXGBE_RDT(reg_idx); + + ixgbe_configure_srrctl(adapter, ring); + ixgbe_configure_rscctl(adapter, ring); + + /* If operating in IOV mode set RLPML for X540 */ + if ((adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) && + hw->mac.type == ixgbe_mac_X540) { + rxdctl &= ~IXGBE_RXDCTL_RLPMLMASK; + rxdctl |= ((ring->netdev->mtu + ETH_HLEN + + ETH_FCS_LEN + VLAN_HLEN) | IXGBE_RXDCTL_RLPML_EN); + } + + 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; + } + + /* enable receive descriptor ring */ + rxdctl |= IXGBE_RXDCTL_ENABLE; + IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl); + + ixgbe_rx_desc_queue_enable(adapter, ring); + 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 p; + + /* 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 (adapter->flags & IXGBE_FLAG_RSS_ENABLED) + psrtype |= (adapter->num_rx_queues_per_pool << 29); + + for (p = 0; p < adapter->num_rx_pools; p++) + IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(adapter->num_vfs + p), + psrtype); +} + +static void ixgbe_configure_virtualization(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 gcr_ext; + u32 vt_reg_bits; + u32 reg_offset, vf_shift; + u32 vmdctl; + + if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) + return; + + vmdctl = IXGBE_READ_REG(hw, IXGBE_VT_CTL); + vt_reg_bits = IXGBE_VMD_CTL_VMDQ_EN | IXGBE_VT_CTL_REPLEN; + vt_reg_bits |= (adapter->num_vfs << IXGBE_VT_CTL_POOL_SHIFT); + IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, vmdctl | vt_reg_bits); + + vf_shift = adapter->num_vfs % 32; + reg_offset = (adapter->num_vfs > 32) ? 1 : 0; + + /* Enable only the PF's pool for Tx/Rx */ + IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset), (1 << vf_shift)); + IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset ^ 1), 0); + IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset), (1 << vf_shift)); + IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset ^ 1), 0); + 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, adapter->num_vfs); + + /* + * Set up VF register offsets for selected VT Mode, + * i.e. 32 or 64 VFs for SR-IOV + */ + gcr_ext = IXGBE_READ_REG(hw, IXGBE_GCR_EXT); + gcr_ext |= IXGBE_GCR_EXT_MSIX_EN; + gcr_ext |= IXGBE_GCR_EXT_VT_MODE_64; + IXGBE_WRITE_REG(hw, IXGBE_GCR_EXT, gcr_ext); + + /* enable Tx loopback for VF/PF communication */ + IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, IXGBE_PFDTXGSWC_VT_LBEN); + /* Enable MAC Anti-Spoofing */ + hw->mac.ops.set_mac_anti_spoofing(hw, + (adapter->antispoofing_enabled = + (adapter->num_vfs != 0)), + adapter->num_vfs); +} + +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; + int rx_buf_len; + struct ixgbe_ring *rx_ring; + int i; + u32 mhadd, hlreg0; + + /* Decide whether to use packet split mode or not */ + /* On by default */ + adapter->flags |= IXGBE_FLAG_RX_PS_ENABLED; + + /* Do not use packet split if we're in SR-IOV Mode */ + if (adapter->num_vfs) + adapter->flags &= ~IXGBE_FLAG_RX_PS_ENABLED; + + /* Disable packet split due to 82599 erratum #45 */ + if (hw->mac.type == ixgbe_mac_82599EB) + adapter->flags &= ~IXGBE_FLAG_RX_PS_ENABLED; + + /* Set the RX buffer length according to the mode */ + if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) { + rx_buf_len = IXGBE_RX_HDR_SIZE; + } else { + if (!(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) && + (netdev->mtu <= ETH_DATA_LEN)) + rx_buf_len = MAXIMUM_ETHERNET_VLAN_SIZE; + else + rx_buf_len = ALIGN(max_frame + VLAN_HLEN, 1024); + } + +#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 */ + 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]; + rx_ring->rx_buf_len = rx_buf_len; + + if (adapter->flags & IXGBE_FLAG_RX_PS_ENABLED) + set_ring_ps_enabled(rx_ring); + else + clear_ring_ps_enabled(rx_ring); + + if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) + set_ring_rsc_enabled(rx_ring); + else + clear_ring_rsc_enabled(rx_ring); + +#ifdef IXGBE_FCOE + if (netdev->features & NETIF_F_FCOE_MTU) { + struct ixgbe_ring_feature *f; + f = &adapter->ring_feature[RING_F_FCOE]; + if ((i >= f->mask) && (i < f->mask + f->indices)) { + clear_ring_ps_enabled(rx_ring); + if (rx_buf_len < IXGBE_FCOE_JUMBO_FRAME_SIZE) + rx_ring->rx_buf_len = + IXGBE_FCOE_JUMBO_FRAME_SIZE; + } else if (!ring_is_rsc_enabled(rx_ring) && + !ring_is_ps_enabled(rx_ring)) { + rx_ring->rx_buf_len = + IXGBE_FCOE_JUMBO_FRAME_SIZE; + } + } +#endif /* IXGBE_FCOE */ + } +} + +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_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; + + /* disable receives while setting up the descriptors */ + rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL); + IXGBE_WRITE_REG(hw, IXGBE_RXCTRL, rxctrl & ~IXGBE_RXCTRL_RXEN); + + ixgbe_setup_psrtype(adapter); + ixgbe_setup_rdrxctl(adapter); + + /* Program registers for the distribution of queues */ + ixgbe_setup_mrqc(adapter); + + ixgbe_set_uta(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]); + + /* 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 void ixgbe_vlan_rx_add_vid(struct net_device *netdev, u16 vid) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + int pool_ndx = adapter->num_vfs; + + /* add VID to filter table */ + hw->mac.ops.set_vfta(&adapter->hw, vid, pool_ndx, true); + set_bit(vid, adapter->active_vlans); +} + +static void ixgbe_vlan_rx_kill_vid(struct net_device *netdev, u16 vid) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + int pool_ndx = adapter->num_vfs; + + /* remove VID from filter table */ + hw->mac.ops.set_vfta(&adapter->hw, vid, pool_ndx, false); + clear_bit(vid, adapter->active_vlans); +} + +/** + * ixgbe_vlan_filter_disable - helper to disable hw vlan filtering + * @adapter: driver data + */ +static void ixgbe_vlan_filter_disable(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 vlnctrl; + + vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); + vlnctrl &= ~(IXGBE_VLNCTRL_VFE | IXGBE_VLNCTRL_CFIEN); + IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); +} + +/** + * ixgbe_vlan_filter_enable - helper to enable hw vlan filtering + * @adapter: driver data + */ +static void ixgbe_vlan_filter_enable(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 vlnctrl; + + vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); + vlnctrl |= IXGBE_VLNCTRL_VFE; + vlnctrl &= ~IXGBE_VLNCTRL_CFIEN; + IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); +} + +/** + * 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: + for (i = 0; i < adapter->num_rx_queues; i++) { + j = adapter->rx_ring[i]->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: + for (i = 0; i < adapter->num_rx_queues; i++) { + j = adapter->rx_ring[i]->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_restore_vlan(struct ixgbe_adapter *adapter) +{ + u16 vid; + + ixgbe_vlan_rx_add_vid(adapter->netdev, 0); + + for_each_set_bit(vid, adapter->active_vlans, VLAN_N_VID) + ixgbe_vlan_rx_add_vid(adapter->netdev, vid); +} + +/** + * ixgbe_write_uc_addr_list - write unicast addresses to RAR table + * @netdev: network interface device structure + * + * Writes unicast address list to the RAR table. + * Returns: -ENOMEM on failure/insufficient address space + * 0 on no addresses written + * X on writing X addresses to the RAR table + **/ +static int ixgbe_write_uc_addr_list(struct net_device *netdev) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + unsigned int vfn = adapter->num_vfs; + unsigned int rar_entries = IXGBE_MAX_PF_MACVLANS; + int count = 0; + + /* return ENOMEM indicating insufficient memory for addresses */ + if (netdev_uc_count(netdev) > rar_entries) + return -ENOMEM; + + if (!netdev_uc_empty(netdev) && rar_entries) { + struct netdev_hw_addr *ha; + /* return error if we do not support writing to RAR table */ + if (!hw->mac.ops.set_rar) + return -ENOMEM; + + netdev_for_each_uc_addr(ha, netdev) { + if (!rar_entries) + break; + hw->mac.ops.set_rar(hw, rar_entries--, ha->addr, + vfn, IXGBE_RAH_AV); + count++; + } + } + /* write the addresses in reverse order to avoid write combining */ + for (; rar_entries > 0 ; rar_entries--) + hw->mac.ops.clear_rar(hw, rar_entries); + + return count; +} + +/** + * 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; + 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_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_ROPE | IXGBE_VMOLR_MPE); + /* don't hardware filter vlans in promisc mode */ + ixgbe_vlan_filter_disable(adapter); + } else { + if (netdev->flags & IFF_ALLMULTI) { + fctrl |= IXGBE_FCTRL_MPE; + vmolr |= IXGBE_VMOLR_MPE; + } else { + /* + * 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 + */ + hw->mac.ops.update_mc_addr_list(hw, netdev); + vmolr |= IXGBE_VMOLR_ROMPE; + } + ixgbe_vlan_filter_enable(adapter); + 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 + */ + count = ixgbe_write_uc_addr_list(netdev); + if (count < 0) { + fctrl |= IXGBE_FCTRL_UPE; + vmolr |= IXGBE_VMOLR_ROPE; + } + } + + if (adapter->num_vfs) { + ixgbe_restore_vf_multicasts(adapter); + vmolr |= IXGBE_READ_REG(hw, IXGBE_VMOLR(adapter->num_vfs)) & + ~(IXGBE_VMOLR_MPE | IXGBE_VMOLR_ROMPE | + IXGBE_VMOLR_ROPE); + IXGBE_WRITE_REG(hw, IXGBE_VMOLR(adapter->num_vfs), vmolr); + } + + IXGBE_WRITE_REG(hw, IXGBE_FCTRL, fctrl); + + if (netdev->features & NETIF_F_HW_VLAN_RX) + ixgbe_vlan_strip_enable(adapter); + else + ixgbe_vlan_strip_disable(adapter); +} + +static void ixgbe_napi_enable_all(struct ixgbe_adapter *adapter) +{ + int q_idx; + struct ixgbe_q_vector *q_vector; + int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + + /* legacy and MSI only use one vector */ + if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) + q_vectors = 1; + + for (q_idx = 0; q_idx < q_vectors; q_idx++) { + struct napi_struct *napi; + q_vector = adapter->q_vector[q_idx]; + napi = &q_vector->napi; + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) { + if (!q_vector->rx.count || !q_vector->tx.count) { + if (q_vector->tx.count == 1) + napi->poll = &ixgbe_clean_txonly; + else if (q_vector->rx.count == 1) + napi->poll = &ixgbe_clean_rxonly; + } + } + + napi_enable(napi); + } +} + +static void ixgbe_napi_disable_all(struct ixgbe_adapter *adapter) +{ + int q_idx; + struct ixgbe_q_vector *q_vector; + int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + + /* legacy and MSI only use one vector */ + if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) + q_vectors = 1; + + for (q_idx = 0; q_idx < q_vectors; q_idx++) { + q_vector = adapter->q_vector[q_idx]; + napi_disable(&q_vector->napi); + } +} + +#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); + + + /* Enable VLAN tag insert/strip */ + adapter->netdev->features |= NETIF_F_HW_VLAN_RX; + + hw->mac.ops.set_vfta(&adapter->hw, 0, 0, true); + + /* reconfigure the hardware */ + if (adapter->dcbx_cap & DCB_CAP_DCBX_VER_CEE) { +#ifdef CONFIG_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, &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 { + struct net_device *dev = adapter->netdev; + + if (adapter->ixgbe_ieee_ets) + dev->dcbnl_ops->ieee_setets(dev, + adapter->ixgbe_ieee_ets); + if (adapter->ixgbe_ieee_pfc) + dev->dcbnl_ops->ieee_setpfc(dev, + adapter->ixgbe_ieee_pfc); + } + + /* Enable RSS Hash per TC */ + if (hw->mac.type != ixgbe_mac_82598EB) { + int i; + u32 reg = 0; + + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + u8 msb = 0; + u8 cnt = adapter->netdev->tc_to_txq[i].count; + + while (cnt >>= 1) + msb++; + + reg |= msb << IXGBE_RQTC_SHIFT_TC(i); + } + IXGBE_WRITE_REG(hw, IXGBE_RQTC, reg); + } +} + +#endif + +static void ixgbe_configure_pb(struct ixgbe_adapter *adapter) +{ + int hdrm = 0; + int num_tc = netdev_get_num_tc(adapter->netdev); + struct ixgbe_hw *hw = &adapter->hw; + + if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE || + adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE) + hdrm = 64 << adapter->fdir_pballoc; + + hw->mac.ops.set_rxpba(&adapter->hw, num_tc, hdrm, PBA_STRATEGY_EQUAL); +} + +static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct hlist_node *node, *node2; + struct ixgbe_fdir_filter *filter; + + 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, node, node2, + &adapter->fdir_filter_list, fdir_node) { + ixgbe_fdir_write_perfect_filter_82599(hw, + &filter->filter, + filter->sw_idx, + (filter->action == IXGBE_FDIR_DROP_QUEUE) ? + IXGBE_FDIR_DROP_QUEUE : + adapter->rx_ring[filter->action]->reg_idx); + } + + spin_unlock(&adapter->fdir_perfect_lock); +} + +static void ixgbe_configure(struct ixgbe_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct ixgbe_hw *hw = &adapter->hw; + int i; + + ixgbe_configure_pb(adapter); +#ifdef CONFIG_IXGBE_DCB + ixgbe_configure_dcb(adapter); +#endif + + ixgbe_set_rx_mode(netdev); + ixgbe_restore_vlan(adapter); + +#ifdef IXGBE_FCOE + if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) + ixgbe_configure_fcoe(adapter); + +#endif /* IXGBE_FCOE */ + if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) { + for (i = 0; i < adapter->num_tx_queues; i++) + adapter->tx_ring[i]->atr_sample_rate = + adapter->atr_sample_rate; + ixgbe_init_fdir_signature_82599(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); + } + ixgbe_configure_virtualization(adapter); + + ixgbe_configure_tx(adapter); + ixgbe_configure_rx(adapter); +} + +static inline bool ixgbe_is_sfp(struct ixgbe_hw *hw) +{ + switch (hw->phy.type) { + case ixgbe_phy_sfp_avago: + case ixgbe_phy_sfp_ftl: + case ixgbe_phy_sfp_intel: + case ixgbe_phy_sfp_unknown: + case ixgbe_phy_sfp_passive_tyco: + case ixgbe_phy_sfp_passive_unknown: + case ixgbe_phy_sfp_active_unknown: + case ixgbe_phy_sfp_ftl_active: + return true; + default: + return false; + } +} + +/** + * 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 scenerio 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; +} + +/** + * 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 autoneg; + bool negotiation, link_up = false; + u32 ret = IXGBE_ERR_LINK_SETUP; + + if (hw->mac.ops.check_link) + ret = hw->mac.ops.check_link(hw, &autoneg, &link_up, false); + + if (ret) + goto link_cfg_out; + + autoneg = hw->phy.autoneg_advertised; + if ((!autoneg) && (hw->mac.ops.get_link_capabilities)) + ret = hw->mac.ops.get_link_capabilities(hw, &autoneg, + &negotiation); + if (ret) + goto link_cfg_out; + + if (hw->mac.ops.setup_link) + ret = hw->mac.ops.setup_link(hw, autoneg, negotiation, link_up); +link_cfg_out: + 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: + 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; + gpie |= IXGBE_GPIE_VTMODE_64; + } + + /* Enable fan failure interrupt */ + if (adapter->flags & IXGBE_FLAG_FAN_FAIL_CAPABLE) + gpie |= IXGBE_SDP1_GPIEN; + + if (hw->mac.type == ixgbe_mac_82599EB) { + gpie |= IXGBE_SDP1_GPIEN; + gpie |= IXGBE_SDP2_GPIEN; + } + + IXGBE_WRITE_REG(hw, IXGBE_GPIE, gpie); +} + +static int 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 both mult-speed fiber and 82599 SFP+ fiber */ + if (hw->mac.ops.enable_tx_laser && + ((hw->phy.multispeed_fiber) || + ((hw->mac.ops.get_media_type(hw) == ixgbe_media_type_fiber) && + (hw->mac.type == ixgbe_mac_82599EB)))) + hw->mac.ops.enable_tx_laser(hw); + + 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"); + } + + /* enable transmits */ + netif_tx_start_all_queues(adapter->netdev); + + /* 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); + + return 0; +} + +void ixgbe_reinit_locked(struct ixgbe_adapter *adapter) +{ + WARN_ON(in_interrupt()); + /* put off any impending NetWatchDogTimeout */ + adapter->netdev->trans_start = jiffies; + + while (test_and_set_bit(__IXGBE_RESETTING, &adapter->state)) + usleep_range(1000, 2000); + 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); +} + +int ixgbe_up(struct ixgbe_adapter *adapter) +{ + /* hardware has been reset, we need to reload some things */ + ixgbe_configure(adapter); + + return ixgbe_up_complete(adapter); +} + +void ixgbe_reset(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int err; + + /* 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 issuesassociated 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); + + /* reprogram the RAR[0] in case user changed it. */ + hw->mac.ops.set_rar(hw, 0, hw->mac.addr, adapter->num_vfs, + IXGBE_RAH_AV); +} + +/** + * 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) +{ + struct device *dev = rx_ring->dev; + unsigned long size; + u16 i; + + /* ring already cleared, nothing to do */ + if (!rx_ring->rx_buffer_info) + return; + + /* Free all the Rx ring sk_buffs */ + for (i = 0; i < rx_ring->count; i++) { + struct ixgbe_rx_buffer *rx_buffer_info; + + rx_buffer_info = &rx_ring->rx_buffer_info[i]; + if (rx_buffer_info->dma) { + dma_unmap_single(rx_ring->dev, rx_buffer_info->dma, + rx_ring->rx_buf_len, + DMA_FROM_DEVICE); + rx_buffer_info->dma = 0; + } + if (rx_buffer_info->skb) { + struct sk_buff *skb = rx_buffer_info->skb; + rx_buffer_info->skb = NULL; + do { + struct sk_buff *this = skb; + if (IXGBE_RSC_CB(this)->delay_unmap) { + dma_unmap_single(dev, + IXGBE_RSC_CB(this)->dma, + rx_ring->rx_buf_len, + DMA_FROM_DEVICE); + IXGBE_RSC_CB(this)->dma = 0; + IXGBE_RSC_CB(skb)->delay_unmap = false; + } + skb = skb->prev; + dev_kfree_skb(this); + } while (skb); + } + if (!rx_buffer_info->page) + continue; + if (rx_buffer_info->page_dma) { + dma_unmap_page(dev, rx_buffer_info->page_dma, + PAGE_SIZE / 2, DMA_FROM_DEVICE); + rx_buffer_info->page_dma = 0; + } + put_page(rx_buffer_info->page); + rx_buffer_info->page = NULL; + rx_buffer_info->page_offset = 0; + } + + size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count; + memset(rx_ring->rx_buffer_info, 0, size); + + /* Zero out the descriptor ring */ + memset(rx_ring->desc, 0, rx_ring->size); + + rx_ring->next_to_clean = 0; + rx_ring->next_to_use = 0; +} + +/** + * ixgbe_clean_tx_ring - Free Tx Buffers + * @tx_ring: ring to be cleaned + **/ +static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring) +{ + struct ixgbe_tx_buffer *tx_buffer_info; + unsigned long size; + u16 i; + + /* ring already cleared, nothing to do */ + if (!tx_ring->tx_buffer_info) + return; + + /* Free all the Tx ring sk_buffs */ + for (i = 0; i < tx_ring->count; i++) { + tx_buffer_info = &tx_ring->tx_buffer_info[i]; + ixgbe_unmap_and_free_tx_resource(tx_ring, tx_buffer_info); + } + + size = sizeof(struct ixgbe_tx_buffer) * tx_ring->count; + memset(tx_ring->tx_buffer_info, 0, size); + + /* Zero out the descriptor ring */ + memset(tx_ring->desc, 0, tx_ring->size); + + tx_ring->next_to_use = 0; + tx_ring->next_to_clean = 0; +} + +/** + * 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]); +} + +static void ixgbe_fdir_filter_exit(struct ixgbe_adapter *adapter) +{ + struct hlist_node *node, *node2; + struct ixgbe_fdir_filter *filter; + + spin_lock(&adapter->fdir_perfect_lock); + + hlist_for_each_entry_safe(filter, node, 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; + u32 rxctrl; + int i; + int num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + + /* signal that we are down to the interrupt handler */ + set_bit(__IXGBE_DOWN, &adapter->state); + + /* disable receives */ + rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL); + IXGBE_WRITE_REG(hw, IXGBE_RXCTRL, rxctrl & ~IXGBE_RXCTRL_RXEN); + + /* disable all enabled rx queues */ + for (i = 0; i < adapter->num_rx_queues; i++) + /* this call also flushes the previous write */ + ixgbe_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); + + ixgbe_irq_disable(adapter); + + ixgbe_napi_disable_all(adapter); + + adapter->flags2 &= ~(IXGBE_FLAG2_FDIR_REQUIRES_REINIT | + IXGBE_FLAG2_RESET_REQUESTED); + adapter->flags &= ~IXGBE_FLAG_NEED_LINK_UPDATE; + + del_timer_sync(&adapter->service_timer); + + /* disable receive for all VFs and wait one second */ + if (adapter->num_vfs) { + /* 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); + + /* Mark all the VFs as inactive */ + for (i = 0 ; i < adapter->num_vfs; i++) + adapter->vfinfo[i].clear_to_send = 0; + } + + /* Cleanup the affinity_hint CPU mask memory and callback */ + for (i = 0; i < num_q_vectors; i++) { + struct ixgbe_q_vector *q_vector = adapter->q_vector[i]; + /* clear the affinity_mask in the IRQ descriptor */ + irq_set_affinity_hint(adapter->msix_entries[i]. vector, NULL); + /* release the CPU mask memory */ + free_cpumask_var(q_vector->affinity_mask); + } + + /* 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_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH); + } + + /* Disable the Tx DMA engine on 82599 and X540 */ + switch (hw->mac.type) { + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL, + (IXGBE_READ_REG(hw, IXGBE_DMATXCTL) & + ~IXGBE_DMATXCTL_TE)); + break; + default: + break; + } + + if (!pci_channel_offline(adapter->pdev)) + ixgbe_reset(adapter); + + /* power down the optics for multispeed fiber and 82599 SFP+ fiber */ + if (hw->mac.ops.disable_tx_laser && + ((hw->phy.multispeed_fiber) || + ((hw->mac.ops.get_media_type(hw) == ixgbe_media_type_fiber) && + (hw->mac.type == ixgbe_mac_82599EB)))) + hw->mac.ops.disable_tx_laser(hw); + + ixgbe_clean_all_tx_rings(adapter); + ixgbe_clean_all_rx_rings(adapter); + +#ifdef CONFIG_IXGBE_DCA + /* since we reset the hardware DCA settings were cleared */ + ixgbe_setup_dca(adapter); +#endif +} + +/** + * 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 + **/ +static 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; + int tx_clean_complete, work_done = 0; + +#ifdef CONFIG_IXGBE_DCA + if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) + ixgbe_update_dca(q_vector); +#endif + + tx_clean_complete = ixgbe_clean_tx_irq(q_vector, adapter->tx_ring[0]); + ixgbe_clean_rx_irq(q_vector, adapter->rx_ring[0], &work_done, budget); + + if (!tx_clean_complete) + work_done = budget; + + /* If budget not fully consumed, exit the polling mode */ + if (work_done < budget) { + napi_complete(napi); + if (adapter->rx_itr_setting & 1) + ixgbe_set_itr(q_vector); + if (!test_bit(__IXGBE_DOWN, &adapter->state)) + ixgbe_irq_enable_queues(adapter, IXGBE_EIMS_RTX_QUEUE); + } + return work_done; +} + +/** + * ixgbe_tx_timeout - Respond to a Tx Hang + * @netdev: network interface device structure + **/ +static void ixgbe_tx_timeout(struct net_device *netdev) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + + /* Do the reset outside of interrupt context */ + ixgbe_tx_timeout_reset(adapter); +} + +/** + * 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 inline bool ixgbe_set_rss_queues(struct ixgbe_adapter *adapter) +{ + bool ret = false; + struct ixgbe_ring_feature *f = &adapter->ring_feature[RING_F_RSS]; + + if (adapter->flags & IXGBE_FLAG_RSS_ENABLED) { + f->mask = 0xF; + adapter->num_rx_queues = f->indices; + adapter->num_tx_queues = f->indices; + ret = true; + } else { + ret = false; + } + + return ret; +} + +/** + * ixgbe_set_fdir_queues: Allocate queues for Flow Director + * @adapter: board private structure to initialize + * + * Flow Director is an advanced Rx filter, attempting to get Rx flows back + * to the original CPU that initiated the Tx session. This runs in addition + * to RSS, so if a packet doesn't match an FDIR filter, we can still spread the + * Rx load across CPUs using RSS. + * + **/ +static inline bool ixgbe_set_fdir_queues(struct ixgbe_adapter *adapter) +{ + bool ret = false; + struct ixgbe_ring_feature *f_fdir = &adapter->ring_feature[RING_F_FDIR]; + + f_fdir->indices = min((int)num_online_cpus(), f_fdir->indices); + f_fdir->mask = 0; + + /* Flow Director must have RSS enabled */ + if ((adapter->flags & IXGBE_FLAG_RSS_ENABLED) && + (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE)) { + adapter->num_tx_queues = f_fdir->indices; + adapter->num_rx_queues = f_fdir->indices; + ret = true; + } else { + adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; + } + return ret; +} + +#ifdef IXGBE_FCOE +/** + * ixgbe_set_fcoe_queues: Allocate queues for Fiber Channel over Ethernet (FCoE) + * @adapter: board private structure to initialize + * + * FCoE RX FCRETA can use up to 8 rx queues for up to 8 different exchanges. + * The ring feature mask is not used as a mask for FCoE, as it can take any 8 + * rx queues out of the max number of rx queues, instead, it is used as the + * index of the first rx queue used by FCoE. + * + **/ +static inline bool ixgbe_set_fcoe_queues(struct ixgbe_adapter *adapter) +{ + struct ixgbe_ring_feature *f = &adapter->ring_feature[RING_F_FCOE]; + + if (!(adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) + return false; + + f->indices = min((int)num_online_cpus(), f->indices); + + adapter->num_rx_queues = 1; + adapter->num_tx_queues = 1; + + if (adapter->flags & IXGBE_FLAG_RSS_ENABLED) { + e_info(probe, "FCoE enabled with RSS\n"); + if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) + ixgbe_set_fdir_queues(adapter); + else + ixgbe_set_rss_queues(adapter); + } + + /* adding FCoE rx rings to the end */ + f->mask = adapter->num_rx_queues; + adapter->num_rx_queues += f->indices; + adapter->num_tx_queues += f->indices; + + return true; +} +#endif /* IXGBE_FCOE */ + +/* Artificial max queue cap per traffic class in DCB mode */ +#define DCB_QUEUE_CAP 8 + +#ifdef CONFIG_IXGBE_DCB +static inline bool ixgbe_set_dcb_queues(struct ixgbe_adapter *adapter) +{ + int per_tc_q, q, i, offset = 0; + struct net_device *dev = adapter->netdev; + int tcs = netdev_get_num_tc(dev); + + if (!tcs) + return false; + + /* Map queue offset and counts onto allocated tx queues */ + per_tc_q = min(dev->num_tx_queues / tcs, (unsigned int)DCB_QUEUE_CAP); + q = min((int)num_online_cpus(), per_tc_q); + + for (i = 0; i < tcs; i++) { + netdev_set_prio_tc_map(dev, i, i); + netdev_set_tc_queue(dev, i, q, offset); + offset += q; + } + + adapter->num_tx_queues = q * tcs; + adapter->num_rx_queues = q * tcs; + +#ifdef IXGBE_FCOE + /* FCoE enabled queues require special configuration indexed + * by feature specific indices and mask. Here we map FCoE + * indices onto the DCB queue pairs allowing FCoE to own + * configuration later. + */ + if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) { + int tc; + struct ixgbe_ring_feature *f = + &adapter->ring_feature[RING_F_FCOE]; + + tc = netdev_get_prio_tc_map(dev, adapter->fcoe.up); + f->indices = dev->tc_to_txq[tc].count; + f->mask = dev->tc_to_txq[tc].offset; + } +#endif + + return true; +} +#endif + +/** + * ixgbe_set_sriov_queues: Allocate queues for IOV use + * @adapter: board private structure to initialize + * + * IOV doesn't actually use anything, so just NAK the + * request for now and let the other queue routines + * figure out what to do. + */ +static inline bool ixgbe_set_sriov_queues(struct ixgbe_adapter *adapter) +{ + return false; +} + +/* + * 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 int ixgbe_set_num_queues(struct ixgbe_adapter *adapter) +{ + /* Start with base case */ + adapter->num_rx_queues = 1; + adapter->num_tx_queues = 1; + adapter->num_rx_pools = adapter->num_rx_queues; + adapter->num_rx_queues_per_pool = 1; + + if (ixgbe_set_sriov_queues(adapter)) + goto done; + +#ifdef CONFIG_IXGBE_DCB + if (ixgbe_set_dcb_queues(adapter)) + goto done; + +#endif +#ifdef IXGBE_FCOE + if (ixgbe_set_fcoe_queues(adapter)) + goto done; + +#endif /* IXGBE_FCOE */ + if (ixgbe_set_fdir_queues(adapter)) + goto done; + + if (ixgbe_set_rss_queues(adapter)) + goto done; + + /* fallback to base case */ + adapter->num_rx_queues = 1; + adapter->num_tx_queues = 1; + +done: + /* Notify the stack of the (possibly) reduced queue counts. */ + netif_set_real_num_tx_queues(adapter->netdev, adapter->num_tx_queues); + return netif_set_real_num_rx_queues(adapter->netdev, + adapter->num_rx_queues); +} + +static void ixgbe_acquire_msix_vectors(struct ixgbe_adapter *adapter, + int vectors) +{ + int err, vector_threshold; + + /* We'll want at least 3 (vector_threshold): + * 1) TxQ[0] Cleanup + * 2) RxQ[0] Cleanup + * 3) Other (Link Status Change, etc.) + * 4) TCP Timer (optional) + */ + 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. + */ + while (vectors >= vector_threshold) { + err = pci_enable_msix(adapter->pdev, adapter->msix_entries, + vectors); + if (!err) /* Success in acquiring all requested vectors. */ + break; + else if (err < 0) + vectors = 0; /* Nasty failure, quit now */ + else /* err == number of vectors we should try again with */ + vectors = err; + } + + if (vectors < vector_threshold) { + /* Can't allocate enough MSI-X interrupts? Oh well. + * This just means we'll go with either a single MSI + * vector or fall back to legacy interrupts. + */ + netif_printk(adapter, hw, KERN_DEBUG, adapter->netdev, + "Unable to allocate MSI-X interrupts\n"); + adapter->flags &= ~IXGBE_FLAG_MSIX_ENABLED; + kfree(adapter->msix_entries); + adapter->msix_entries = NULL; + } else { + adapter->flags |= IXGBE_FLAG_MSIX_ENABLED; /* Woot! */ + /* + * 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 = min(vectors, + adapter->max_msix_q_vectors + NON_Q_VECTORS); + } +} + +/** + * 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 inline bool ixgbe_cache_ring_rss(struct ixgbe_adapter *adapter) +{ + int i; + + if (!(adapter->flags & IXGBE_FLAG_RSS_ENABLED)) + return false; + + for (i = 0; i < adapter->num_rx_queues; i++) + adapter->rx_ring[i]->reg_idx = i; + for (i = 0; i < adapter->num_tx_queues; i++) + adapter->tx_ring[i]->reg_idx = i; + + return true; +} + +#ifdef CONFIG_IXGBE_DCB + +/* 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 net_device *dev = adapter->netdev; + struct ixgbe_hw *hw = &adapter->hw; + u8 num_tcs = netdev_get_num_tc(dev); + + *tx = 0; + *rx = 0; + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + *tx = tc << 2; + *rx = tc << 3; + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + if (num_tcs == 8) { + if (tc < 3) { + *tx = tc << 5; + *rx = tc << 4; + } else if (tc < 5) { + *tx = ((tc + 2) << 4); + *rx = tc << 4; + } else if (tc < num_tcs) { + *tx = ((tc + 8) << 3); + *rx = tc << 4; + } + } else if (num_tcs == 4) { + *rx = tc << 5; + switch (tc) { + case 0: + *tx = 0; + break; + case 1: + *tx = 64; + break; + case 2: + *tx = 96; + break; + case 3: + *tx = 112; + break; + default: + break; + } + } + break; + 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 inline bool ixgbe_cache_ring_dcb(struct ixgbe_adapter *adapter) +{ + struct net_device *dev = adapter->netdev; + int i, j, k; + u8 num_tcs = netdev_get_num_tc(dev); + + if (!num_tcs) + return false; + + for (i = 0, k = 0; i < num_tcs; i++) { + unsigned int tx_s, rx_s; + u16 count = dev->tc_to_txq[i].count; + + ixgbe_get_first_reg_idx(adapter, i, &tx_s, &rx_s); + for (j = 0; j < count; j++, k++) { + adapter->tx_ring[k]->reg_idx = tx_s + j; + adapter->rx_ring[k]->reg_idx = rx_s + j; + adapter->tx_ring[k]->dcb_tc = i; + adapter->rx_ring[k]->dcb_tc = i; + } + } + + return true; +} +#endif + +/** + * ixgbe_cache_ring_fdir - Descriptor ring to register mapping for Flow Director + * @adapter: board private structure to initialize + * + * Cache the descriptor ring offsets for Flow Director to the assigned rings. + * + **/ +static inline bool ixgbe_cache_ring_fdir(struct ixgbe_adapter *adapter) +{ + int i; + bool ret = false; + + if ((adapter->flags & IXGBE_FLAG_RSS_ENABLED) && + (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE)) { + for (i = 0; i < adapter->num_rx_queues; i++) + adapter->rx_ring[i]->reg_idx = i; + for (i = 0; i < adapter->num_tx_queues; i++) + adapter->tx_ring[i]->reg_idx = i; + ret = true; + } + + return ret; +} + +#ifdef IXGBE_FCOE +/** + * ixgbe_cache_ring_fcoe - Descriptor ring to register mapping for the FCoE + * @adapter: board private structure to initialize + * + * Cache the descriptor ring offsets for FCoE mode to the assigned rings. + * + */ +static inline bool ixgbe_cache_ring_fcoe(struct ixgbe_adapter *adapter) +{ + struct ixgbe_ring_feature *f = &adapter->ring_feature[RING_F_FCOE]; + int i; + u8 fcoe_rx_i = 0, fcoe_tx_i = 0; + + if (!(adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) + return false; + + if (adapter->flags & IXGBE_FLAG_RSS_ENABLED) { + if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) + ixgbe_cache_ring_fdir(adapter); + else + ixgbe_cache_ring_rss(adapter); + + fcoe_rx_i = f->mask; + fcoe_tx_i = f->mask; + } + for (i = 0; i < f->indices; i++, fcoe_rx_i++, fcoe_tx_i++) { + adapter->rx_ring[f->mask + i]->reg_idx = fcoe_rx_i; + adapter->tx_ring[f->mask + i]->reg_idx = fcoe_tx_i; + } + return true; +} + +#endif /* IXGBE_FCOE */ +/** + * 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 inline bool ixgbe_cache_ring_sriov(struct ixgbe_adapter *adapter) +{ + adapter->rx_ring[0]->reg_idx = adapter->num_vfs * 2; + adapter->tx_ring[0]->reg_idx = adapter->num_vfs * 2; + if (adapter->num_vfs) + return true; + else + return false; +} + +/** + * 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; + + if (ixgbe_cache_ring_sriov(adapter)) + return; + +#ifdef CONFIG_IXGBE_DCB + if (ixgbe_cache_ring_dcb(adapter)) + return; +#endif + +#ifdef IXGBE_FCOE + if (ixgbe_cache_ring_fcoe(adapter)) + return; +#endif /* IXGBE_FCOE */ + + if (ixgbe_cache_ring_fdir(adapter)) + return; + + if (ixgbe_cache_ring_rss(adapter)) + return; +} + +/** + * ixgbe_alloc_queues - Allocate memory for all rings + * @adapter: board private structure to initialize + * + * We allocate one ring per queue at run-time since we don't know the + * number of queues at compile-time. The polling_netdev array is + * intended for Multiqueue, but should work fine with a single queue. + **/ +static int ixgbe_alloc_queues(struct ixgbe_adapter *adapter) +{ + int rx = 0, tx = 0, nid = adapter->node; + + if (nid < 0 || !node_online(nid)) + nid = first_online_node; + + for (; tx < adapter->num_tx_queues; tx++) { + struct ixgbe_ring *ring; + + ring = kzalloc_node(sizeof(*ring), GFP_KERNEL, nid); + if (!ring) + ring = kzalloc(sizeof(*ring), GFP_KERNEL); + if (!ring) + goto err_allocation; + ring->count = adapter->tx_ring_count; + ring->queue_index = tx; + ring->numa_node = nid; + ring->dev = &adapter->pdev->dev; + ring->netdev = adapter->netdev; + + adapter->tx_ring[tx] = ring; + } + + for (; rx < adapter->num_rx_queues; rx++) { + struct ixgbe_ring *ring; + + ring = kzalloc_node(sizeof(*ring), GFP_KERNEL, nid); + if (!ring) + ring = kzalloc(sizeof(*ring), GFP_KERNEL); + if (!ring) + goto err_allocation; + ring->count = adapter->rx_ring_count; + ring->queue_index = rx; + ring->numa_node = nid; + ring->dev = &adapter->pdev->dev; + ring->netdev = adapter->netdev; + + adapter->rx_ring[rx] = ring; + } + + ixgbe_cache_ring_register(adapter); + + return 0; + +err_allocation: + while (tx) + kfree(adapter->tx_ring[--tx]); + + while (rx) + kfree(adapter->rx_ring[--rx]); + return -ENOMEM; +} + +/** + * 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 int ixgbe_set_interrupt_capability(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int err = 0; + 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. + */ + v_budget = min(adapter->num_rx_queues + adapter->num_tx_queues, + (int)num_online_cpus()) + NON_Q_VECTORS; + + /* + * At the same time, hardware can only support a maximum of + * hw.mac->max_msix_vectors 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 it off in + * those rare cases where the cpu count also exceeds our vector limit. + */ + v_budget = min(v_budget, (int)hw->mac.max_msix_vectors); + + /* A failure in MSI-X entry allocation isn't fatal, but it does + * mean we disable MSI-X capabilities of the adapter. */ + adapter->msix_entries = kcalloc(v_budget, + sizeof(struct msix_entry), GFP_KERNEL); + if (adapter->msix_entries) { + for (vector = 0; vector < v_budget; vector++) + adapter->msix_entries[vector].entry = vector; + + ixgbe_acquire_msix_vectors(adapter, v_budget); + + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) + goto out; + } + + adapter->flags &= ~IXGBE_FLAG_DCB_ENABLED; + adapter->flags &= ~IXGBE_FLAG_RSS_ENABLED; + if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) { + e_err(probe, + "ATR is not supported while multiple " + "queues are disabled. Disabling Flow Director\n"); + } + adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; + adapter->atr_sample_rate = 0; + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) + ixgbe_disable_sriov(adapter); + + err = ixgbe_set_num_queues(adapter); + if (err) + return err; + + err = pci_enable_msi(adapter->pdev); + if (!err) { + adapter->flags |= IXGBE_FLAG_MSI_ENABLED; + } else { + netif_printk(adapter, hw, KERN_DEBUG, adapter->netdev, + "Unable to allocate MSI interrupt, " + "falling back to legacy. Error: %d\n", err); + /* reset err */ + err = 0; + } + +out: + return err; +} + +/** + * 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_idx, num_q_vectors; + struct ixgbe_q_vector *q_vector; + int (*poll)(struct napi_struct *, int); + + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) { + num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + poll = &ixgbe_clean_rxtx_many; + } else { + num_q_vectors = 1; + poll = &ixgbe_poll; + } + + for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { + q_vector = kzalloc_node(sizeof(struct ixgbe_q_vector), + GFP_KERNEL, adapter->node); + if (!q_vector) + q_vector = kzalloc(sizeof(struct ixgbe_q_vector), + GFP_KERNEL); + if (!q_vector) + goto err_out; + q_vector->adapter = adapter; + if (q_vector->tx.count && !q_vector->rx.count) + q_vector->eitr = adapter->tx_eitr_param; + else + q_vector->eitr = adapter->rx_eitr_param; + q_vector->v_idx = q_idx; + netif_napi_add(adapter->netdev, &q_vector->napi, (*poll), 64); + adapter->q_vector[q_idx] = q_vector; + } + + return 0; + +err_out: + while (q_idx) { + q_idx--; + q_vector = adapter->q_vector[q_idx]; + netif_napi_del(&q_vector->napi); + kfree(q_vector); + adapter->q_vector[q_idx] = NULL; + } + 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 q_idx, num_q_vectors; + + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) + num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; + else + num_q_vectors = 1; + + for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { + struct ixgbe_q_vector *q_vector = adapter->q_vector[q_idx]; + adapter->q_vector[q_idx] = NULL; + netif_napi_del(&q_vector->napi); + kfree(q_vector); + } +} + +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_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 */ + err = ixgbe_set_num_queues(adapter); + if (err) + return err; + + err = ixgbe_set_interrupt_capability(adapter); + if (err) { + e_dev_err("Unable to setup interrupt capabilities\n"); + goto err_set_interrupt; + } + + err = ixgbe_alloc_q_vectors(adapter); + if (err) { + e_dev_err("Unable to allocate memory for queue vectors\n"); + goto err_alloc_q_vectors; + } + + err = ixgbe_alloc_queues(adapter); + if (err) { + e_dev_err("Unable to allocate memory for queues\n"); + goto err_alloc_queues; + } + + e_dev_info("Multiqueue %s: Rx Queue count = %u, Tx Queue count = %u\n", + (adapter->num_rx_queues > 1) ? "Enabled" : "Disabled", + adapter->num_rx_queues, adapter->num_tx_queues); + + set_bit(__IXGBE_DOWN, &adapter->state); + + return 0; + +err_alloc_queues: + ixgbe_free_q_vectors(adapter); +err_alloc_q_vectors: + ixgbe_reset_interrupt_capability(adapter); +err_set_interrupt: + 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) +{ + int i; + + for (i = 0; i < adapter->num_tx_queues; i++) { + kfree(adapter->tx_ring[i]); + adapter->tx_ring[i] = NULL; + } + for (i = 0; i < adapter->num_rx_queues; i++) { + struct ixgbe_ring *ring = adapter->rx_ring[i]; + + /* ixgbe_get_stats64() might access this ring, we must wait + * a grace period before freeing it. + */ + kfree_rcu(ring, rcu); + adapter->rx_ring[i] = NULL; + } + + adapter->num_tx_queues = 0; + adapter->num_rx_queues = 0; + + ixgbe_free_q_vectors(adapter); + ixgbe_reset_interrupt_capability(adapter); +} + +/** + * ixgbe_sw_init - Initialize general software structures (struct ixgbe_adapter) + * @adapter: board private structure to initialize + * + * 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 __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct pci_dev *pdev = adapter->pdev; + struct net_device *dev = adapter->netdev; + unsigned int rss; +#ifdef CONFIG_IXGBE_DCB + int j; + struct tc_configuration *tc; +#endif + int max_frame = dev->mtu + ETH_HLEN + ETH_FCS_LEN; + + /* 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; + + /* Set capability flags */ + rss = min(IXGBE_MAX_RSS_INDICES, (int)num_online_cpus()); + adapter->ring_feature[RING_F_RSS].indices = rss; + adapter->flags |= IXGBE_FLAG_RSS_ENABLED; + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + if (hw->device_id == IXGBE_DEV_ID_82598AT) + adapter->flags |= IXGBE_FLAG_FAN_FAIL_CAPABLE; + adapter->max_msix_q_vectors = MAX_MSIX_Q_VECTORS_82598; + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + adapter->max_msix_q_vectors = MAX_MSIX_Q_VECTORS_82599; + adapter->flags2 |= IXGBE_FLAG2_RSC_CAPABLE; + adapter->flags2 |= IXGBE_FLAG2_RSC_ENABLED; + if (hw->device_id == IXGBE_DEV_ID_82599_T3_LOM) + adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE; + /* Flow Director hash filters enabled */ + adapter->flags |= IXGBE_FLAG_FDIR_HASH_CAPABLE; + adapter->atr_sample_rate = 20; + adapter->ring_feature[RING_F_FDIR].indices = + IXGBE_MAX_FDIR_INDICES; + adapter->fdir_pballoc = IXGBE_FDIR_PBALLOC_64K; +#ifdef IXGBE_FCOE + adapter->flags |= IXGBE_FLAG_FCOE_CAPABLE; + adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED; + adapter->ring_feature[RING_F_FCOE].indices = 0; +#ifdef CONFIG_IXGBE_DCB + /* Default traffic class to use for FCoE */ + adapter->fcoe.up = IXGBE_FCOE_DEFTC; +#endif +#endif /* IXGBE_FCOE */ + break; + default: + break; + } + + /* n-tuple support exists, always init our spinlock */ + spin_lock_init(&adapter->fdir_perfect_lock); + +#ifdef CONFIG_IXGBE_DCB + /* 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; + } + 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; + adapter->dcbx_cap = DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_CEE; + ixgbe_copy_dcb_cfg(&adapter->dcb_cfg, &adapter->temp_dcb_cfg, + MAX_TRAFFIC_CLASS); + +#endif + + /* default flow control settings */ + hw->fc.requested_mode = ixgbe_fc_full; + hw->fc.current_mode = ixgbe_fc_full; /* init for ethtool output */ +#ifdef CONFIG_DCB + adapter->last_lfc_mode = hw->fc.current_mode; +#endif + hw->fc.high_water = FC_HIGH_WATER(max_frame); + hw->fc.low_water = FC_LOW_WATER(max_frame); + hw->fc.pause_time = IXGBE_DEFAULT_FCPAUSE; + hw->fc.send_xon = true; + hw->fc.disable_fc_autoneg = false; + + /* enable itr by default in dynamic mode */ + adapter->rx_itr_setting = 1; + adapter->rx_eitr_param = 20000; + adapter->tx_itr_setting = 1; + adapter->tx_eitr_param = 10000; + + /* set defaults for eitr in MegaBytes */ + adapter->eitr_low = 10; + adapter->eitr_high = 20; + + /* set default ring sizes */ |