diff options
Diffstat (limited to 'drivers/net/ethernet/intel/ixgbe')
29 files changed, 11641 insertions, 5501 deletions
diff --git a/drivers/net/ethernet/intel/ixgbe/Makefile b/drivers/net/ethernet/intel/ixgbe/Makefile index 7a16177a12a..be2989e6000 100644 --- a/drivers/net/ethernet/intel/ixgbe/Makefile +++ b/drivers/net/ethernet/intel/ixgbe/Makefile @@ -1,7 +1,7 @@ ################################################################################ # # Intel 10 Gigabit PCI Express Linux driver -# Copyright(c) 1999 - 2012 Intel Corporation. +# Copyright(c) 1999 - 2013 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, @@ -34,9 +34,11 @@ obj-$(CONFIG_IXGBE) += ixgbe.o ixgbe-objs := ixgbe_main.o ixgbe_common.o ixgbe_ethtool.o \ ixgbe_82599.o ixgbe_82598.o ixgbe_phy.o ixgbe_sriov.o \ - ixgbe_mbx.o ixgbe_x540.o + ixgbe_mbx.o ixgbe_x540.o ixgbe_lib.o ixgbe_ptp.o ixgbe-$(CONFIG_IXGBE_DCB) += ixgbe_dcb.o ixgbe_dcb_82598.o \ ixgbe_dcb_82599.o ixgbe_dcb_nl.o +ixgbe-$(CONFIG_IXGBE_HWMON) += ixgbe_sysfs.o +ixgbe-$(CONFIG_DEBUG_FS) += ixgbe_debugfs.o ixgbe-$(CONFIG_FCOE:m=y) += ixgbe_fcoe.o diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index e6aeb64105a..ac9f2148cdc 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2013 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, @@ -20,6 +20,7 @@ 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 @@ -35,6 +36,11 @@ #include <linux/cpumask.h> #include <linux/aer.h> #include <linux/if_vlan.h> +#include <linux/jiffies.h> + +#include <linux/clocksource.h> +#include <linux/net_tstamp.h> +#include <linux/ptp_clock_kernel.h> #include "ixgbe_type.h" #include "ixgbe_common.h" @@ -47,6 +53,11 @@ #include <linux/dca.h> #endif +#include <net/busy_poll.h> + +#ifdef CONFIG_NET_RX_BUSY_POLL +#define BP_EXTENDED_STATS +#endif /* common prefix used by pr_<> macros */ #undef pr_fmt #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -57,7 +68,11 @@ #define IXGBE_MAX_TXD 4096 #define IXGBE_MIN_TXD 64 +#if (PAGE_SIZE < 8192) #define IXGBE_DEFAULT_RXD 512 +#else +#define IXGBE_DEFAULT_RXD 128 +#endif #define IXGBE_MAX_RXD 4096 #define IXGBE_MIN_RXD 64 @@ -71,51 +86,53 @@ #define IXGBE_MAX_FCPAUSE 0xFFFF /* Supported Rx Buffer Sizes */ -#define IXGBE_RXBUFFER_512 512 /* Used for packet split */ -#define IXGBE_RXBUFFER_2K 2048 -#define IXGBE_RXBUFFER_3K 3072 -#define IXGBE_RXBUFFER_4K 4096 -#define IXGBE_RXBUFFER_7K 7168 -#define IXGBE_RXBUFFER_8K 8192 -#define IXGBE_RXBUFFER_15K 15360 +#define IXGBE_RXBUFFER_256 256 /* Used for skb receive header */ +#define IXGBE_RXBUFFER_2K 2048 +#define IXGBE_RXBUFFER_3K 3072 +#define IXGBE_RXBUFFER_4K 4096 #define IXGBE_MAX_RXBUFFER 16384 /* largest size for a single descriptor */ /* - * 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 + * NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we + * reserve 64 more, and skb_shared_info adds an additional 320 bytes more, + * this adds up to 448 bytes of extra data. + * + * Since netdev_alloc_skb now allocates a page fragment we can use a value + * of 256 and the resultant skb will have a truesize of 960 or less. */ -#define IXGBE_RX_HDR_SIZE IXGBE_RXBUFFER_512 - -#define MAXIMUM_ETHERNET_VLAN_SIZE (ETH_FRAME_LEN + ETH_FCS_LEN + VLAN_HLEN) +#define IXGBE_RX_HDR_SIZE IXGBE_RXBUFFER_256 /* How many Rx Buffers do we bundle into one write to the hardware ? */ #define IXGBE_RX_BUFFER_WRITE 16 /* Must be power of 2 */ -#define IXGBE_TX_FLAGS_CSUM (u32)(1) -#define IXGBE_TX_FLAGS_HW_VLAN (u32)(1 << 1) -#define IXGBE_TX_FLAGS_SW_VLAN (u32)(1 << 2) -#define IXGBE_TX_FLAGS_TSO (u32)(1 << 3) -#define IXGBE_TX_FLAGS_IPV4 (u32)(1 << 4) -#define IXGBE_TX_FLAGS_FCOE (u32)(1 << 5) -#define IXGBE_TX_FLAGS_FSO (u32)(1 << 6) -#define IXGBE_TX_FLAGS_TXSW (u32)(1 << 7) -#define IXGBE_TX_FLAGS_MAPPED_AS_PAGE (u32)(1 << 8) +enum ixgbe_tx_flags { + /* cmd_type flags */ + IXGBE_TX_FLAGS_HW_VLAN = 0x01, + IXGBE_TX_FLAGS_TSO = 0x02, + IXGBE_TX_FLAGS_TSTAMP = 0x04, + + /* olinfo flags */ + IXGBE_TX_FLAGS_CC = 0x08, + IXGBE_TX_FLAGS_IPV4 = 0x10, + IXGBE_TX_FLAGS_CSUM = 0x20, + + /* software defined flags */ + IXGBE_TX_FLAGS_SW_VLAN = 0x40, + IXGBE_TX_FLAGS_FCOE = 0x80, +}; + +/* VLAN info */ #define IXGBE_TX_FLAGS_VLAN_MASK 0xffff0000 #define IXGBE_TX_FLAGS_VLAN_PRIO_MASK 0xe0000000 #define IXGBE_TX_FLAGS_VLAN_PRIO_SHIFT 29 #define IXGBE_TX_FLAGS_VLAN_SHIFT 16 -#define IXGBE_MAX_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) +#define VMDQ_P(p) ((p) + adapter->ring_feature[RING_F_VMDQ].offset) #define IXGBE_82599_VF_DEVICE_ID 0x10ED #define IXGBE_X540_VF_DEVICE_ID 0x1515 @@ -132,13 +149,12 @@ struct vf_data_storage { u16 tx_rate; u16 vlan_count; u8 spoofchk_enabled; - struct pci_dev *vfdev; + unsigned int vf_api; }; struct vf_macvlans { struct list_head l; int vf; - int rar_entry; bool free; bool is_macvlan; u8 vf_macvlan[ETH_ALEN]; @@ -149,38 +165,42 @@ struct vf_macvlans { /* 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) +#define DESC_NEEDED (MAX_SKB_FRAGS + 4) /* wrapper around a pointer to a socket buffer, * so a DMA handle can be stored along with the buffer */ struct ixgbe_tx_buffer { union ixgbe_adv_tx_desc *next_to_watch; unsigned long time_stamp; - dma_addr_t dma; - u32 length; - u32 tx_flags; struct sk_buff *skb; - u32 bytecount; - u16 gso_segs; + unsigned int bytecount; + unsigned short gso_segs; + __be16 protocol; + DEFINE_DMA_UNMAP_ADDR(dma); + DEFINE_DMA_UNMAP_LEN(len); + u32 tx_flags; }; struct ixgbe_rx_buffer { 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; +#ifdef BP_EXTENDED_STATS + u64 yields; + u64 misses; + u64 cleaned; +#endif /* BP_EXTENDED_STATS */ }; struct ixgbe_tx_queue_stats { u64 restart_queue; u64 tx_busy; - u64 completed; u64 tx_done_old; }; @@ -190,22 +210,28 @@ struct ixgbe_rx_queue_stats { u64 non_eop_descs; u64 alloc_rx_page_failed; u64 alloc_rx_buff_failed; + u64 csum_err; }; -enum ixbge_ring_state_t { +enum ixgbe_ring_state_t { __IXGBE_TX_FDIR_INIT_DONE, + __IXGBE_TX_XPS_INIT_DONE, __IXGBE_TX_DETECT_HANG, __IXGBE_HANG_CHECK_ARMED, - __IXGBE_RX_PS_ENABLED, __IXGBE_RX_RSC_ENABLED, + __IXGBE_RX_CSUM_UDP_ZERO_ERR, + __IXGBE_RX_FCOE, +}; + +struct ixgbe_fwd_adapter { + unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + struct net_device *netdev; + struct ixgbe_adapter *real_adapter; + unsigned int tx_base_queue; + unsigned int rx_base_queue; + int pool; }; -#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) \ @@ -220,18 +246,21 @@ enum ixbge_ring_state_t { clear_bit(__IXGBE_RX_RSC_ENABLED, &(ring)->state) struct ixgbe_ring { struct ixgbe_ring *next; /* pointer to next ring in q_vector */ + struct ixgbe_q_vector *q_vector; /* backpointer to host q_vector */ + struct net_device *netdev; /* netdev ring belongs to */ + struct device *dev; /* device for DMA mapping */ + struct ixgbe_fwd_adapter *l2_accel_priv; 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; + dma_addr_t dma; /* phys. address of descriptor ring */ + unsigned int size; /* length in bytes */ 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 @@ -239,12 +268,17 @@ struct ixgbe_ring { * 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; + union { + u16 next_to_alloc; + struct { + u8 atr_sample_rate; + u8 atr_count; + }; + }; + u8 dcb_tc; struct ixgbe_queue_stats stats; struct u64_stats_sync syncp; @@ -252,11 +286,6 @@ struct ixgbe_ring { 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 { @@ -273,20 +302,52 @@ enum ixgbe_ring_f_enum { #define IXGBE_MAX_RSS_INDICES 16 #define IXGBE_MAX_VMDQ_INDICES 64 -#define IXGBE_MAX_FDIR_INDICES 64 -#ifdef IXGBE_FCOE +#define IXGBE_MAX_FDIR_INDICES 63 /* based on q_vector limit */ #define IXGBE_MAX_FCOE_INDICES 8 -#define MAX_RX_QUEUES (IXGBE_MAX_FDIR_INDICES + 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 */ +#define MAX_RX_QUEUES (IXGBE_MAX_FDIR_INDICES + 1) +#define MAX_TX_QUEUES (IXGBE_MAX_FDIR_INDICES + 1) +#define IXGBE_MAX_L2A_QUEUES 4 +#define IXGBE_MAX_L2A_QUEUES 4 +#define IXGBE_BAD_L2A_QUEUE 3 +#define IXGBE_MAX_MACVLANS 31 +#define IXGBE_MAX_DCBMACVLANS 8 + struct ixgbe_ring_feature { - int indices; - int mask; + u16 limit; /* upper limit on feature indices */ + u16 indices; /* current value of indices */ + u16 mask; /* Mask used for feature to ring mapping */ + u16 offset; /* offset to start of feature */ } ____cacheline_internodealigned_in_smp; +#define IXGBE_82599_VMDQ_8Q_MASK 0x78 +#define IXGBE_82599_VMDQ_4Q_MASK 0x7C +#define IXGBE_82599_VMDQ_2Q_MASK 0x7E + +/* + * FCoE requires that all Rx buffers be over 2200 bytes in length. Since + * this is twice the size of a half page we need to double the page order + * for FCoE enabled Rx queues. + */ +static inline unsigned int ixgbe_rx_bufsz(struct ixgbe_ring *ring) +{ +#ifdef IXGBE_FCOE + if (test_bit(__IXGBE_RX_FCOE, &ring->state)) + return (PAGE_SIZE < 8192) ? IXGBE_RXBUFFER_4K : + IXGBE_RXBUFFER_3K; +#endif + return IXGBE_RXBUFFER_2K; +} + +static inline unsigned int ixgbe_rx_pg_order(struct ixgbe_ring *ring) +{ +#ifdef IXGBE_FCOE + if (test_bit(__IXGBE_RX_FCOE, &ring->state)) + return (PAGE_SIZE < 8192) ? 1 : 0; +#endif + return 0; +} +#define ixgbe_rx_pg_size(_ring) (PAGE_SIZE << ixgbe_rx_pg_order(_ring)) + struct ixgbe_ring_container { struct ixgbe_ring *ring; /* pointer to linked list of rings */ unsigned int total_bytes; /* total bytes processed this int */ @@ -296,11 +357,15 @@ struct ixgbe_ring_container { u8 itr; /* current ITR setting for ring */ }; +/* iterator for handling rings in ring container */ +#define ixgbe_for_each_ring(pos, head) \ + for (pos = (head).ring; pos != NULL; pos = pos->next) + #define MAX_RX_PACKET_BUFFERS ((adapter->flags & IXGBE_FLAG_DCB_ENABLED) \ - ? 8 : 1) + ? 8 : 1) #define MAX_TX_PACKET_BUFFERS MAX_RX_PACKET_BUFFERS -/* MAX_MSIX_Q_VECTORS of these are allocated, +/* MAX_Q_VECTORS of these are allocated, * but we only use one per queue-specific vector. */ struct ixgbe_q_vector { @@ -315,9 +380,186 @@ struct ixgbe_q_vector { struct ixgbe_ring_container rx, tx; struct napi_struct napi; - cpumask_var_t affinity_mask; + cpumask_t affinity_mask; + int numa_node; + struct rcu_head rcu; /* to avoid race with update stats on free */ char name[IFNAMSIZ + 9]; + +#ifdef CONFIG_NET_RX_BUSY_POLL + unsigned int state; +#define IXGBE_QV_STATE_IDLE 0 +#define IXGBE_QV_STATE_NAPI 1 /* NAPI owns this QV */ +#define IXGBE_QV_STATE_POLL 2 /* poll owns this QV */ +#define IXGBE_QV_STATE_DISABLED 4 /* QV is disabled */ +#define IXGBE_QV_OWNED (IXGBE_QV_STATE_NAPI | IXGBE_QV_STATE_POLL) +#define IXGBE_QV_LOCKED (IXGBE_QV_OWNED | IXGBE_QV_STATE_DISABLED) +#define IXGBE_QV_STATE_NAPI_YIELD 8 /* NAPI yielded this QV */ +#define IXGBE_QV_STATE_POLL_YIELD 16 /* poll yielded this QV */ +#define IXGBE_QV_YIELD (IXGBE_QV_STATE_NAPI_YIELD | IXGBE_QV_STATE_POLL_YIELD) +#define IXGBE_QV_USER_PEND (IXGBE_QV_STATE_POLL | IXGBE_QV_STATE_POLL_YIELD) + spinlock_t lock; +#endif /* CONFIG_NET_RX_BUSY_POLL */ + + /* for dynamic allocation of rings associated with this q_vector */ + struct ixgbe_ring ring[0] ____cacheline_internodealigned_in_smp; }; +#ifdef CONFIG_NET_RX_BUSY_POLL +static inline void ixgbe_qv_init_lock(struct ixgbe_q_vector *q_vector) +{ + + spin_lock_init(&q_vector->lock); + q_vector->state = IXGBE_QV_STATE_IDLE; +} + +/* called from the device poll routine to get ownership of a q_vector */ +static inline bool ixgbe_qv_lock_napi(struct ixgbe_q_vector *q_vector) +{ + int rc = true; + spin_lock_bh(&q_vector->lock); + if (q_vector->state & IXGBE_QV_LOCKED) { + WARN_ON(q_vector->state & IXGBE_QV_STATE_NAPI); + q_vector->state |= IXGBE_QV_STATE_NAPI_YIELD; + rc = false; +#ifdef BP_EXTENDED_STATS + q_vector->tx.ring->stats.yields++; +#endif + } else { + /* we don't care if someone yielded */ + q_vector->state = IXGBE_QV_STATE_NAPI; + } + spin_unlock_bh(&q_vector->lock); + return rc; +} + +/* returns true is someone tried to get the qv while napi had it */ +static inline bool ixgbe_qv_unlock_napi(struct ixgbe_q_vector *q_vector) +{ + int rc = false; + spin_lock_bh(&q_vector->lock); + WARN_ON(q_vector->state & (IXGBE_QV_STATE_POLL | + IXGBE_QV_STATE_NAPI_YIELD)); + + if (q_vector->state & IXGBE_QV_STATE_POLL_YIELD) + rc = true; + /* will reset state to idle, unless QV is disabled */ + q_vector->state &= IXGBE_QV_STATE_DISABLED; + spin_unlock_bh(&q_vector->lock); + return rc; +} + +/* called from ixgbe_low_latency_poll() */ +static inline bool ixgbe_qv_lock_poll(struct ixgbe_q_vector *q_vector) +{ + int rc = true; + spin_lock_bh(&q_vector->lock); + if ((q_vector->state & IXGBE_QV_LOCKED)) { + q_vector->state |= IXGBE_QV_STATE_POLL_YIELD; + rc = false; +#ifdef BP_EXTENDED_STATS + q_vector->rx.ring->stats.yields++; +#endif + } else { + /* preserve yield marks */ + q_vector->state |= IXGBE_QV_STATE_POLL; + } + spin_unlock_bh(&q_vector->lock); + return rc; +} + +/* returns true if someone tried to get the qv while it was locked */ +static inline bool ixgbe_qv_unlock_poll(struct ixgbe_q_vector *q_vector) +{ + int rc = false; + spin_lock_bh(&q_vector->lock); + WARN_ON(q_vector->state & (IXGBE_QV_STATE_NAPI)); + + if (q_vector->state & IXGBE_QV_STATE_POLL_YIELD) + rc = true; + /* will reset state to idle, unless QV is disabled */ + q_vector->state &= IXGBE_QV_STATE_DISABLED; + spin_unlock_bh(&q_vector->lock); + return rc; +} + +/* true if a socket is polling, even if it did not get the lock */ +static inline bool ixgbe_qv_busy_polling(struct ixgbe_q_vector *q_vector) +{ + WARN_ON(!(q_vector->state & IXGBE_QV_OWNED)); + return q_vector->state & IXGBE_QV_USER_PEND; +} + +/* false if QV is currently owned */ +static inline bool ixgbe_qv_disable(struct ixgbe_q_vector *q_vector) +{ + int rc = true; + spin_lock_bh(&q_vector->lock); + if (q_vector->state & IXGBE_QV_OWNED) + rc = false; + q_vector->state |= IXGBE_QV_STATE_DISABLED; + spin_unlock_bh(&q_vector->lock); + + return rc; +} + +#else /* CONFIG_NET_RX_BUSY_POLL */ +static inline void ixgbe_qv_init_lock(struct ixgbe_q_vector *q_vector) +{ +} + +static inline bool ixgbe_qv_lock_napi(struct ixgbe_q_vector *q_vector) +{ + return true; +} + +static inline bool ixgbe_qv_unlock_napi(struct ixgbe_q_vector *q_vector) +{ + return false; +} + +static inline bool ixgbe_qv_lock_poll(struct ixgbe_q_vector *q_vector) +{ + return false; +} + +static inline bool ixgbe_qv_unlock_poll(struct ixgbe_q_vector *q_vector) +{ + return false; +} + +static inline bool ixgbe_qv_busy_polling(struct ixgbe_q_vector *q_vector) +{ + return false; +} + +static inline bool ixgbe_qv_disable(struct ixgbe_q_vector *q_vector) +{ + return true; +} + +#endif /* CONFIG_NET_RX_BUSY_POLL */ + +#ifdef CONFIG_IXGBE_HWMON + +#define IXGBE_HWMON_TYPE_LOC 0 +#define IXGBE_HWMON_TYPE_TEMP 1 +#define IXGBE_HWMON_TYPE_CAUTION 2 +#define IXGBE_HWMON_TYPE_MAX 3 + +struct hwmon_attr { + struct device_attribute dev_attr; + struct ixgbe_hw *hw; + struct ixgbe_thermal_diode_data *sensor; + char name[12]; +}; + +struct hwmon_buff { + struct attribute_group group; + const struct attribute_group *groups[2]; + struct attribute *attrs[IXGBE_MAX_SENSORS * 4 + 1]; + struct hwmon_attr hwmon_list[IXGBE_MAX_SENSORS * 4]; + unsigned int n_hwmon; +}; +#endif /* CONFIG_IXGBE_HWMON */ /* * microsecond values for various ITR rates shifted by 2 to fit itr register @@ -329,6 +571,13 @@ struct ixgbe_q_vector { #define IXGBE_10K_ITR 400 #define IXGBE_8K_ITR 500 +/* ixgbe_test_staterr - tests bits in Rx descriptor status and error fields */ +static inline __le32 ixgbe_test_staterr(union ixgbe_adv_rx_desc *rx_desc, + const u32 stat_err_bits) +{ + return rx_desc->wb.upper.status_error & cpu_to_le32(stat_err_bits); +} + static inline u16 ixgbe_desc_unused(struct ixgbe_ring *ring) { u16 ntc = ring->next_to_clean; @@ -337,14 +586,19 @@ static inline u16 ixgbe_desc_unused(struct ixgbe_ring *ring) return ((ntc > ntu) ? 0 : ring->count) + ntc - ntu - 1; } -#define IXGBE_RX_DESC_ADV(R, i) \ +static inline void ixgbe_write_tail(struct ixgbe_ring *ring, u32 value) +{ + writel(value, ring->tail); +} + +#define IXGBE_RX_DESC(R, i) \ (&(((union ixgbe_adv_rx_desc *)((R)->desc))[i])) -#define IXGBE_TX_DESC_ADV(R, i) \ +#define IXGBE_TX_DESC(R, i) \ (&(((union ixgbe_adv_tx_desc *)((R)->desc))[i])) -#define IXGBE_TX_CTXTDESC_ADV(R, i) \ +#define IXGBE_TX_CTXTDESC(R, i) \ (&(((struct ixgbe_adv_tx_context_desc *)((R)->desc))[i])) -#define IXGBE_MAX_JUMBO_FRAME_SIZE 16128 +#define IXGBE_MAX_JUMBO_FRAME_SIZE 9728 /* Maximum Supported Size 9.5KB */ #ifdef IXGBE_FCOE /* Use 3K as the baby jumbo frame size for FCoE */ #define IXGBE_FCOE_JUMBO_FRAME_SIZE 3072 @@ -354,54 +608,68 @@ static inline u16 ixgbe_desc_unused(struct ixgbe_ring *ring) #define NON_Q_VECTORS (OTHER_VECTOR) #define MAX_MSIX_VECTORS_82599 64 -#define MAX_MSIX_Q_VECTORS_82599 64 +#define MAX_Q_VECTORS_82599 64 #define MAX_MSIX_VECTORS_82598 18 -#define MAX_MSIX_Q_VECTORS_82598 16 +#define MAX_Q_VECTORS_82598 16 + +struct ixgbe_mac_addr { + u8 addr[ETH_ALEN]; + u16 queue; + u16 state; /* bitmask */ +}; +#define IXGBE_MAC_STATE_DEFAULT 0x1 +#define IXGBE_MAC_STATE_MODIFIED 0x2 +#define IXGBE_MAC_STATE_IN_USE 0x4 -#define MAX_MSIX_Q_VECTORS MAX_MSIX_Q_VECTORS_82599 +#define MAX_Q_VECTORS MAX_Q_VECTORS_82599 #define MAX_MSIX_COUNT MAX_MSIX_VECTORS_82599 -#define MIN_MSIX_Q_VECTORS 2 +#define MIN_MSIX_Q_VECTORS 1 #define MIN_MSIX_COUNT (MIN_MSIX_Q_VECTORS + NON_Q_VECTORS) +/* default to trying for four seconds */ +#define IXGBE_TRY_LINK_TIMEOUT (4 * HZ) + /* board specific private data structure */ struct ixgbe_adapter { + unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + /* OS defined structs */ + struct net_device *netdev; + struct pci_dev *pdev; + 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) +#define IXGBE_FLAG_MSI_CAPABLE (u32)(1 << 0) +#define IXGBE_FLAG_MSI_ENABLED (u32)(1 << 1) +#define IXGBE_FLAG_MSIX_CAPABLE (u32)(1 << 2) +#define IXGBE_FLAG_MSIX_ENABLED (u32)(1 << 3) +#define IXGBE_FLAG_RX_1BUF_CAPABLE (u32)(1 << 4) +#define IXGBE_FLAG_RX_PS_CAPABLE (u32)(1 << 5) +#define IXGBE_FLAG_RX_PS_ENABLED (u32)(1 << 6) +#define IXGBE_FLAG_IN_NETPOLL (u32)(1 << 7) +#define IXGBE_FLAG_DCA_ENABLED (u32)(1 << 8) +#define IXGBE_FLAG_DCA_CAPABLE (u32)(1 << 9) +#define IXGBE_FLAG_IMIR_ENABLED (u32)(1 << 10) +#define IXGBE_FLAG_MQ_CAPABLE (u32)(1 << 11) +#define IXGBE_FLAG_DCB_ENABLED (u32)(1 << 12) +#define IXGBE_FLAG_VMDQ_CAPABLE (u32)(1 << 13) +#define IXGBE_FLAG_VMDQ_ENABLED (u32)(1 << 14) +#define IXGBE_FLAG_FAN_FAIL_CAPABLE (u32)(1 << 15) +#define IXGBE_FLAG_NEED_LINK_UPDATE (u32)(1 << 16) +#define IXGBE_FLAG_NEED_LINK_CONFIG (u32)(1 << 17) +#define IXGBE_FLAG_FDIR_HASH_CAPABLE (u32)(1 << 18) +#define IXGBE_FLAG_FDIR_PERFECT_CAPABLE (u32)(1 << 19) +#define IXGBE_FLAG_FCOE_CAPABLE (u32)(1 << 20) +#define IXGBE_FLAG_FCOE_ENABLED (u32)(1 << 21) +#define IXGBE_FLAG_SRIOV_CAPABLE (u32)(1 << 22) +#define IXGBE_FLAG_SRIOV_ENABLED (u32)(1 << 23) u32 flags2; -#define IXGBE_FLAG2_RSC_CAPABLE (u32)(1) +#define IXGBE_FLAG2_RSC_CAPABLE (u32)(1 << 0) #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) @@ -409,60 +677,54 @@ struct ixgbe_adapter { #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) +#define IXGBE_FLAG2_RSS_FIELD_IPV4_UDP (u32)(1 << 8) +#define IXGBE_FLAG2_RSS_FIELD_IPV6_UDP (u32)(1 << 9) +#define IXGBE_FLAG2_PTP_PPS_ENABLED (u32)(1 << 10) +#define IXGBE_FLAG2_BRIDGE_MODE_VEB (u32)(1 << 11) - 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 */ + /* Tx fast path data */ + int num_tx_queues; + u16 tx_itr_setting; u16 tx_work_limit; + /* Rx fast path data */ + int num_rx_queues; + u16 rx_itr_setting; + /* 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; + u32 tx_timeout_count; /* RX */ - struct ixgbe_ring *rx_ring[MAX_RX_QUEUES] ____cacheline_aligned_in_smp; - int num_rx_queues; + struct ixgbe_ring *rx_ring[MAX_RX_QUEUES]; int num_rx_pools; /* == num_rx_queues in 82598 */ int num_rx_queues_per_pool; /* 1 if 82598, can be many if 82599 */ u64 hw_csum_rx_error; u64 hw_rx_no_dma_resources; + u64 rsc_total_count; + u64 rsc_total_flush; u64 non_eop_descs; - 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) + struct ixgbe_q_vector *q_vector[MAX_Q_VECTORS]; - /* OS defined structs */ - struct net_device *netdev; - struct pci_dev *pdev; + /* 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; + + int num_q_vectors; /* current number of q_vectors for device */ + int max_q_vectors; /* true count of q_vectors for device */ + struct ixgbe_ring_feature ring_feature[RING_F_ARRAY_SIZE]; + struct msix_entry *msix_entries; u32 test_icr; struct ixgbe_ring test_tx_ring; @@ -473,10 +735,6 @@ struct ixgbe_adapter { 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; @@ -485,25 +743,45 @@ struct ixgbe_adapter { bool link_up; unsigned long link_check_timeout; - struct work_struct service_task; struct timer_list service_timer; + struct work_struct service_task; + + struct hlist_head fdir_filter_list; + unsigned long fdir_overflow; /* number of times ATR was backed off */ + union ixgbe_atr_input fdir_mask; + int fdir_filter_count; u32 fdir_pballoc; u32 atr_sample_rate; - 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; + u8 __iomem *io_addr; /* Mainly for iounmap use */ u32 wol; + + u16 bd_number; + u16 eeprom_verh; u16 eeprom_verl; u16 eeprom_cap; - int node; - u32 led_reg; u32 interrupt_event; + u32 led_reg; + + struct ptp_clock *ptp_clock; + struct ptp_clock_info ptp_caps; + struct work_struct ptp_tx_work; + struct sk_buff *ptp_tx_skb; + struct hwtstamp_config tstamp_config; + unsigned long ptp_tx_start; + unsigned long last_overflow_check; + unsigned long last_rx_ptp_check; + unsigned long last_rx_timestamp; + spinlock_t tmreg_lock; + struct cyclecounter cc; + struct timecounter tc; + u32 base_incval; /* SR-IOV */ DECLARE_BITMAP(active_vfs, IXGBE_MAX_VF_FUNCTIONS); @@ -513,11 +791,19 @@ struct ixgbe_adapter { struct vf_macvlans vf_mvs; struct vf_macvlans *mv_list; - struct hlist_head fdir_filter_list; - union ixgbe_atr_input fdir_mask; - int fdir_filter_count; u32 timer_event_accumulator; u32 vferr_refcount; + struct ixgbe_mac_addr *mac_table; + struct kobject *info_kobj; +#ifdef CONFIG_IXGBE_HWMON + struct hwmon_buff *ixgbe_hwmon_buff; +#endif /* CONFIG_IXGBE_HWMON */ +#ifdef CONFIG_DEBUG_FS + struct dentry *ixgbe_dbg_adapter; +#endif /*CONFIG_DEBUG_FS*/ + + u8 default_up; + unsigned long fwd_bitmask; /* Bitmask indicating in use pools */ }; struct ixgbe_fdir_filter { @@ -527,20 +813,29 @@ struct ixgbe_fdir_filter { u16 action; }; -enum ixbge_state_t { +enum ixgbe_state_t { __IXGBE_TESTING, __IXGBE_RESETTING, __IXGBE_DOWN, + __IXGBE_DISABLED, + __IXGBE_REMOVING, __IXGBE_SERVICE_SCHED, + __IXGBE_SERVICE_INITED, __IXGBE_IN_SFP_INIT, + __IXGBE_PTP_RUNNING, + __IXGBE_PTP_TX_IN_PROGRESS, }; -struct ixgbe_rsc_cb { +struct ixgbe_cb { + union { /* Union defining head/tail partner */ + struct sk_buff *head; + struct sk_buff *tail; + }; dma_addr_t dma; - u16 skb_cnt; - bool delay_unmap; + u16 append_cnt; + bool page_released; }; -#define IXGBE_RSC_CB(skb) ((struct ixgbe_rsc_cb *)(skb)->cb) +#define IXGBE_CB(skb) ((struct ixgbe_cb *)(skb)->cb) enum ixgbe_boards { board_82598, @@ -553,83 +848,130 @@ 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[]; +#ifdef IXGBE_FCOE extern char ixgbe_default_device_descr[]; +#endif /* IXGBE_FCOE */ -extern void 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); +void ixgbe_up(struct ixgbe_adapter *adapter); +void ixgbe_down(struct ixgbe_adapter *adapter); +void ixgbe_reinit_locked(struct ixgbe_adapter *adapter); +void ixgbe_reset(struct ixgbe_adapter *adapter); +void ixgbe_set_ethtool_ops(struct net_device *netdev); +int ixgbe_setup_rx_resources(struct ixgbe_ring *); +int ixgbe_setup_tx_resources(struct ixgbe_ring *); +void ixgbe_free_rx_resources(struct ixgbe_ring *); +void ixgbe_free_tx_resources(struct ixgbe_ring *); +void ixgbe_configure_rx_ring(struct ixgbe_adapter *, struct ixgbe_ring *); +void ixgbe_configure_tx_ring(struct ixgbe_adapter *, struct ixgbe_ring *); +void ixgbe_disable_rx_queue(struct ixgbe_adapter *adapter, struct ixgbe_ring *); +void ixgbe_update_stats(struct ixgbe_adapter *adapter); +int ixgbe_init_interrupt_scheme(struct ixgbe_adapter *adapter); +int ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id, + u16 subdevice_id); +#ifdef CONFIG_PCI_IOV +void ixgbe_full_sync_mac_table(struct ixgbe_adapter *adapter); +#endif +int ixgbe_add_mac_filter(struct ixgbe_adapter *adapter, + u8 *addr, u16 queue); +int ixgbe_del_mac_filter(struct ixgbe_adapter *adapter, + u8 *addr, u16 queue); +void ixgbe_clear_interrupt_scheme(struct ixgbe_adapter *adapter); +netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *, struct ixgbe_adapter *, + struct ixgbe_ring *); +void ixgbe_unmap_and_free_tx_resource(struct ixgbe_ring *, + struct ixgbe_tx_buffer *); +void ixgbe_alloc_rx_buffers(struct ixgbe_ring *, u16); +void ixgbe_write_eitr(struct ixgbe_q_vector *); +int ixgbe_poll(struct napi_struct *napi, int budget); +int ethtool_ioctl(struct ifreq *ifr); +s32 ixgbe_reinit_fdir_tables_82599(struct ixgbe_hw *hw); +s32 ixgbe_init_fdir_signature_82599(struct ixgbe_hw *hw, u32 fdirctrl); +s32 ixgbe_init_fdir_perfect_82599(struct ixgbe_hw *hw, u32 fdirctrl); +s32 ixgbe_fdir_add_signature_filter_82599(struct ixgbe_hw *hw, + union ixgbe_atr_hash_dword input, + union ixgbe_atr_hash_dword common, + u8 queue); +s32 ixgbe_fdir_set_input_mask_82599(struct ixgbe_hw *hw, + union ixgbe_atr_input *input_mask); +s32 ixgbe_fdir_write_perfect_filter_82599(struct ixgbe_hw *hw, + union ixgbe_atr_input *input, + u16 soft_id, u8 queue); +s32 ixgbe_fdir_erase_perfect_filter_82599(struct ixgbe_hw *hw, + union ixgbe_atr_input *input, + u16 soft_id); +void ixgbe_atr_compute_perfect_hash_82599(union ixgbe_atr_input *input, + union ixgbe_atr_input *mask); +void ixgbe_set_rx_mode(struct net_device *netdev); +#ifdef CONFIG_IXGBE_DCB +void ixgbe_set_rx_drop_en(struct ixgbe_adapter *adapter); +#endif +int ixgbe_setup_tc(struct net_device *dev, u8 tc); +void ixgbe_tx_ctxtdesc(struct ixgbe_ring *, u32, u32, u32, u32); +void ixgbe_do_reset(struct net_device *netdev); +#ifdef CONFIG_IXGBE_HWMON +void ixgbe_sysfs_exit(struct ixgbe_adapter *adapter); +int ixgbe_sysfs_init(struct ixgbe_adapter *adapter); +#endif /* CONFIG_IXGBE_HWMON */ #ifdef IXGBE_FCOE -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); +void ixgbe_configure_fcoe(struct ixgbe_adapter *adapter); +int ixgbe_fso(struct ixgbe_ring *tx_ring, struct ixgbe_tx_buffer *first, + u8 *hdr_len); +int ixgbe_fcoe_ddp(struct ixgbe_adapter *adapter, + union ixgbe_adv_rx_desc *rx_desc, struct sk_buff *skb); +int ixgbe_fcoe_ddp_get(struct net_device *netdev, u16 xid, + struct scatterlist *sgl, unsigned int sgc); +int ixgbe_fcoe_ddp_target(struct net_device *netdev, u16 xid, + struct scatterlist *sgl, unsigned int sgc); +int ixgbe_fcoe_ddp_put(struct net_device *netdev, u16 xid); +int ixgbe_setup_fcoe_ddp_resources(struct ixgbe_adapter *adapter); +void ixgbe_free_fcoe_ddp_resources(struct ixgbe_adapter *adapter); +int ixgbe_fcoe_enable(struct net_device *netdev); +int ixgbe_fcoe_disable(struct net_device *netdev); #ifdef CONFIG_IXGBE_DCB -extern u8 ixgbe_fcoe_getapp(struct ixgbe_adapter *adapter); -extern u8 ixgbe_fcoe_setapp(struct ixgbe_adapter *adapter, u8 up); +u8 ixgbe_fcoe_getapp(struct ixgbe_adapter *adapter); +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); -extern int ixgbe_fcoe_get_hbainfo(struct net_device *netdev, - struct netdev_fcoe_hbainfo *info); +int ixgbe_fcoe_get_wwn(struct net_device *netdev, u64 *wwn, int type); +int ixgbe_fcoe_get_hbainfo(struct net_device *netdev, + struct netdev_fcoe_hbainfo *info); +u8 ixgbe_fcoe_get_tc(struct ixgbe_adapter *adapter); #endif /* IXGBE_FCOE */ +#ifdef CONFIG_DEBUG_FS +void ixgbe_dbg_adapter_init(struct ixgbe_adapter *adapter); +void ixgbe_dbg_adapter_exit(struct ixgbe_adapter *adapter); +void ixgbe_dbg_init(void); +void ixgbe_dbg_exit(void); +#else +static inline void ixgbe_dbg_adapter_init(struct ixgbe_adapter *adapter) {} +static inline void ixgbe_dbg_adapter_exit(struct ixgbe_adapter *adapter) {} +static inline void ixgbe_dbg_init(void) {} +static inline void ixgbe_dbg_exit(void) {} +#endif /* CONFIG_DEBUG_FS */ +static inline struct netdev_queue *txring_txq(const struct ixgbe_ring *ring) +{ + return netdev_get_tx_queue(ring->netdev, ring->queue_index); +} + +void ixgbe_ptp_init(struct ixgbe_adapter *adapter); +void ixgbe_ptp_suspend(struct ixgbe_adapter *adapter); +void ixgbe_ptp_stop(struct ixgbe_adapter *adapter); +void ixgbe_ptp_overflow_check(struct ixgbe_adapter *adapter); +void ixgbe_ptp_rx_hang(struct ixgbe_adapter *adapter); +void ixgbe_ptp_rx_hwtstamp(struct ixgbe_adapter *adapter, struct sk_buff *skb); +int ixgbe_ptp_set_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr); +int ixgbe_ptp_get_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr); +void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter); +void ixgbe_ptp_reset(struct ixgbe_adapter *adapter); +void ixgbe_ptp_check_pps_event(struct ixgbe_adapter *adapter, u32 eicr); +#ifdef CONFIG_PCI_IOV +void ixgbe_sriov_reinit(struct ixgbe_adapter *adapter); +#endif +netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, + struct ixgbe_adapter *adapter, + struct ixgbe_ring *tx_ring); #endif /* _IXGBE_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c index b406c367b19..15609331ec1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2014 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, @@ -20,6 +20,7 @@ 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 @@ -40,11 +41,10 @@ #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); + ixgbe_link_speed speed, + bool autoneg_wait_to_complete); static s32 ixgbe_read_i2c_eeprom_82598(struct ixgbe_hw *hw, u8 byte_offset, - u8 *eeprom_data); + u8 *eeprom_data); /** * ixgbe_set_pcie_completion_timeout - set pci-e completion timeout @@ -58,10 +58,12 @@ static s32 ixgbe_read_i2c_eeprom_82598(struct ixgbe_hw *hw, u8 byte_offset, **/ 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; + if (ixgbe_removed(hw->hw_addr)) + return; + /* only take action if timeout value is defaulted to 0 */ if (gcr & IXGBE_GCR_CMPL_TMOUT_MASK) goto out; @@ -80,40 +82,15 @@ static void ixgbe_set_pcie_completion_timeout(struct ixgbe_hw *hw) * 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_read_pci_cfg_word(hw, IXGBE_PCI_DEVICE_CONTROL2); pcie_devctl2 |= IXGBE_PCI_DEVICE_CONTROL2_16ms; - pci_write_config_word(adapter->pdev, - IXGBE_PCI_DEVICE_CONTROL2, pcie_devctl2); + ixgbe_write_pci_cfg_word(hw, IXGBE_PCI_DEVICE_CONTROL2, pcie_devctl2); out: /* disable completion timeout resend */ gcr &= ~IXGBE_GCR_CMPL_TMOUT_RESEND; IXGBE_WRITE_REG(hw, IXGBE_GCR, gcr); } -/** - * 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; @@ -124,9 +101,10 @@ static s32 ixgbe_get_invariants_82598(struct ixgbe_hw *hw) mac->mcft_size = IXGBE_82598_MC_TBL_SIZE; mac->vft_size = IXGBE_82598_VFT_TBL_SIZE; mac->num_rar_entries = IXGBE_82598_RAR_ENTRIES; + mac->rx_pb_size = IXGBE_82598_RX_PB_SIZE; mac->max_rx_queues = IXGBE_82598_MAX_RX_QUEUES; mac->max_tx_queues = IXGBE_82598_MAX_TX_QUEUES; - mac->max_msix_vectors = ixgbe_get_pcie_msix_count_82598(hw); + mac->max_msix_vectors = ixgbe_get_pcie_msix_count_generic(hw); return 0; } @@ -162,7 +140,7 @@ static s32 ixgbe_init_phy_ops_82598(struct ixgbe_hw *hw) 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; + &ixgbe_get_phy_firmware_version_tnx; break; case ixgbe_phy_nl: phy->ops.reset = &ixgbe_reset_phy_nl; @@ -178,8 +156,8 @@ static s32 ixgbe_init_phy_ops_82598(struct ixgbe_hw *hw) /* Check to see if SFP+ module is supported */ ret_val = ixgbe_get_sfp_init_sequence_offsets(hw, - &list_offset, - &data_offset); + &list_offset, + &data_offset); if (ret_val != 0) { ret_val = IXGBE_ERR_SFP_NOT_SUPPORTED; goto out; @@ -213,20 +191,18 @@ static s32 ixgbe_start_hw_82598(struct ixgbe_hw *hw) 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; + regval &= ~IXGBE_DCA_TXCTRL_DESC_WRO_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); + regval &= ~(IXGBE_DCA_RXCTRL_DATA_WRO_EN | + IXGBE_DCA_RXCTRL_HEAD_WRO_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); @@ -243,8 +219,8 @@ static s32 ixgbe_start_hw_82598(struct ixgbe_hw *hw) * 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) + ixgbe_link_speed *speed, + bool *autoneg) { s32 status = 0; u32 autoc = 0; @@ -347,24 +323,39 @@ out: /** * 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) +static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw) { s32 ret_val = 0; u32 fctrl_reg; u32 rmcs_reg; u32 reg; + u32 fcrtl, fcrth; u32 link_speed = 0; + int i; bool link_up; -#ifdef CONFIG_DCB - if (hw->fc.requested_mode == ixgbe_fc_pfc) + /* Validate the water mark configuration */ + if (!hw->fc.pause_time) { + ret_val = IXGBE_ERR_INVALID_LINK_SETTINGS; goto out; + } + + /* Low water mark of zero causes XOFF floods */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + if ((hw->fc.current_mode & ixgbe_fc_tx_pause) && + hw->fc.high_water[i]) { + if (!hw->fc.low_water[i] || + hw->fc.low_water[i] >= hw->fc.high_water[i]) { + hw_dbg(hw, "Invalid water mark configuration\n"); + ret_val = IXGBE_ERR_INVALID_LINK_SETTINGS; + 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 @@ -386,9 +377,7 @@ static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw, s32 packetbuf_num) } /* Negotiate the fc mode to use */ - ret_val = ixgbe_fc_autoneg(hw); - if (ret_val == IXGBE_ERR_FLOW_CONTROL) - goto out; + ixgbe_fc_autoneg(hw); /* Disable any previous flow control settings */ fctrl_reg = IXGBE_READ_REG(hw, IXGBE_FCTRL); @@ -405,9 +394,6 @@ static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw, s32 packetbuf_num) * 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) { @@ -440,11 +426,6 @@ static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw, s32 packetbuf_num) 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; @@ -458,28 +439,27 @@ static s32 ixgbe_fc_enable_82598(struct ixgbe_hw *hw, s32 packetbuf_num) 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) { - reg = hw->fc.low_water << 6; - if (hw->fc.send_xon) - reg |= IXGBE_FCRTL_XONE; - - IXGBE_WRITE_REG(hw, IXGBE_FCRTL(packetbuf_num), reg); - - reg = hw->fc.high_water[packetbuf_num] << 6; - reg |= IXGBE_FCRTH_FCEN; + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + if ((hw->fc.current_mode & ixgbe_fc_tx_pause) && + hw->fc.high_water[i]) { + fcrtl = (hw->fc.low_water[i] << 10) | IXGBE_FCRTL_XONE; + fcrth = (hw->fc.high_water[i] << 10) | IXGBE_FCRTH_FCEN; + IXGBE_WRITE_REG(hw, IXGBE_FCRTL(i), fcrtl); + IXGBE_WRITE_REG(hw, IXGBE_FCRTH(i), fcrth); + } else { + IXGBE_WRITE_REG(hw, IXGBE_FCRTL(i), 0); + IXGBE_WRITE_REG(hw, IXGBE_FCRTH(i), 0); + } - 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); + reg = hw->fc.pause_time * 0x00010001; + for (i = 0; i < (MAX_TRAFFIC_CLASS / 2); i++) + IXGBE_WRITE_REG(hw, IXGBE_FCTTV(i), reg); - IXGBE_WRITE_REG(hw, IXGBE_FCRTV, (hw->fc.pause_time >> 1)); + /* Configure flow control refresh threshold value */ + IXGBE_WRITE_REG(hw, IXGBE_FCRTV, hw->fc.pause_time / 2); out: return ret_val; @@ -493,7 +473,7 @@ out: * Restarts the link. Performs autonegotiation if needed. **/ static s32 ixgbe_start_mac_link_82598(struct ixgbe_hw *hw, - bool autoneg_wait_to_complete) + bool autoneg_wait_to_complete) { u32 autoc_reg; u32 links_reg; @@ -575,8 +555,8 @@ static s32 ixgbe_validate_link_ready(struct ixgbe_hw *hw) * 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) + ixgbe_link_speed *speed, bool *link_up, + bool link_up_wait_to_complete) { u32 links_reg; u32 i; @@ -592,7 +572,7 @@ static s32 ixgbe_check_mac_link_82598(struct ixgbe_hw *hw, 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); + &adapt_comp_reg); if (link_up_wait_to_complete) { for (i = 0; i < IXGBE_LINK_UP_TIME; i++) { if ((link_reg & 1) && @@ -604,11 +584,11 @@ static s32 ixgbe_check_mac_link_82598(struct ixgbe_hw *hw, } msleep(100); hw->phy.ops.read_reg(hw, 0xC79F, - MDIO_MMD_PMAPMD, - &link_reg); + MDIO_MMD_PMAPMD, + &link_reg); hw->phy.ops.read_reg(hw, 0xC00C, - MDIO_MMD_PMAPMD, - &adapt_comp_reg); + MDIO_MMD_PMAPMD, + &adapt_comp_reg); } } else { if ((link_reg & 1) && ((adapt_comp_reg & 1) == 0)) @@ -617,7 +597,7 @@ static s32 ixgbe_check_mac_link_82598(struct ixgbe_hw *hw, *link_up = false; } - if (*link_up == false) + if (!*link_up) goto out; } @@ -645,7 +625,7 @@ static s32 ixgbe_check_mac_link_82598(struct ixgbe_hw *hw, else *speed = IXGBE_LINK_SPEED_1GB_FULL; - if ((hw->device_id == IXGBE_DEV_ID_82598AT2) && (*link_up == true) && + if ((hw->device_id == IXGBE_DEV_ID_82598AT2) && *link_up && (ixgbe_validate_link_ready(hw) != 0)) *link_up = false; @@ -657,15 +637,15 @@ out: * 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) + ixgbe_link_speed speed, + bool autoneg_wait_to_complete) { + bool autoneg = false; s32 status = 0; ixgbe_link_speed link_capabilities = IXGBE_LINK_SPEED_UNKNOWN; u32 curr_autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC); @@ -681,7 +661,7 @@ static s32 ixgbe_setup_mac_link_82598(struct ixgbe_hw *hw, /* 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) { + 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; @@ -709,21 +689,19 @@ static s32 ixgbe_setup_mac_link_82598(struct ixgbe_hw *hw, * 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) + ixgbe_link_speed speed, + bool autoneg_wait_to_complete) { s32 status; /* Setup the PHY according to input speed */ - status = hw->phy.ops.setup_link_speed(hw, speed, autoneg, - autoneg_wait_to_complete); + status = hw->phy.ops.setup_link_speed(hw, speed, + autoneg_wait_to_complete); /* Set up MAC */ ixgbe_start_mac_link_82598(hw, autoneg_wait_to_complete); @@ -762,28 +740,28 @@ static s32 ixgbe_reset_hw_82598(struct ixgbe_hw *hw) 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); analog_val &= ~IXGBE_ATLAS_PDN_TX_REG_EN; hw->mac.ops.write_analog_reg8(hw, IXGBE_ATLAS_PDN_LPBK, - analog_val); + analog_val); hw->mac.ops.read_analog_reg8(hw, IXGBE_ATLAS_PDN_10G, - &analog_val); + &analog_val); analog_val &= ~IXGBE_ATLAS_PDN_TX_10G_QL_ALL; hw->mac.ops.write_analog_reg8(hw, IXGBE_ATLAS_PDN_10G, - analog_val); + analog_val); hw->mac.ops.read_analog_reg8(hw, IXGBE_ATLAS_PDN_1G, - &analog_val); + &analog_val); analog_val &= ~IXGBE_ATLAS_PDN_TX_1G_QL_ALL; hw->mac.ops.write_analog_reg8(hw, IXGBE_ATLAS_PDN_1G, - analog_val); + analog_val); hw->mac.ops.read_analog_reg8(hw, IXGBE_ATLAS_PDN_AN, - &analog_val); + &analog_val); analog_val &= ~IXGBE_ATLAS_PDN_TX_AN_QL_ALL; hw->mac.ops.write_analog_reg8(hw, IXGBE_ATLAS_PDN_AN, - analog_val); + analog_val); } /* Reset PHY */ @@ -982,7 +960,7 @@ static s32 ixgbe_clear_vfta_82598(struct ixgbe_hw *hw) for (vlanbyte = 0; vlanbyte < 4; vlanbyte++) for (offset = 0; offset < hw->mac.vft_size; offset++) IXGBE_WRITE_REG(hw, IXGBE_VFTAVIND(vlanbyte, offset), - 0); + 0); return 0; } @@ -1000,7 +978,7 @@ 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_ATLASCTL_WRITE_CMD | (reg << 8)); IXGBE_WRITE_FLUSH(hw); udelay(10); atlas_ctl = IXGBE_READ_REG(hw, IXGBE_ATLASCTL); @@ -1030,41 +1008,51 @@ static s32 ixgbe_write_analog_reg8_82598(struct ixgbe_hw *hw, u32 reg, u8 val) } /** - * ixgbe_read_i2c_eeprom_82598 - Reads 8 bit word over I2C interface. + * ixgbe_read_i2c_phy_82598 - Reads 8 bit word over I2C interface. * @hw: pointer to hardware structure - * @byte_offset: EEPROM byte offset to read + * @dev_addr: address to read from + * @byte_offset: byte offset to read from dev_addr * @eeprom_data: value read * - * Performs 8 byte read operation to SFP module's EEPROM over I2C interface. + * Performs 8 byte read operation to SFP module's data over I2C interface. **/ -static s32 ixgbe_read_i2c_eeprom_82598(struct ixgbe_hw *hw, u8 byte_offset, - u8 *eeprom_data) +static s32 ixgbe_read_i2c_phy_82598(struct ixgbe_hw *hw, u8 dev_addr, + u8 byte_offset, u8 *eeprom_data) { s32 status = 0; u16 sfp_addr = 0; u16 sfp_data = 0; u16 sfp_stat = 0; + u16 gssr; u32 i; + if (IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_LAN_ID_1) + gssr = IXGBE_GSSR_PHY1_SM; + else + gssr = IXGBE_GSSR_PHY0_SM; + + if (hw->mac.ops.acquire_swfw_sync(hw, gssr) != 0) + return IXGBE_ERR_SWFW_SYNC; + if (hw->phy.type == ixgbe_phy_nl) { /* * phy SDA/SCL registers are at addresses 0xC30A to * 0xC30D. These registers are used to talk to the SFP+ * module's EEPROM through the SDA/SCL (I2C) interface. */ - sfp_addr = (IXGBE_I2C_EEPROM_DEV_ADDR << 8) + byte_offset; + sfp_addr = (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); + hw->phy.ops.write_reg_mdi(hw, + IXGBE_MDIO_PMA_PMD_SDA_SCL_ADDR, + MDIO_MMD_PMAPMD, + sfp_addr); /* Poll status */ for (i = 0; i < 100; i++) { - hw->phy.ops.read_reg(hw, - IXGBE_MDIO_PMA_PMD_SDA_SCL_STAT, - MDIO_MMD_PMAPMD, - &sfp_stat); + hw->phy.ops.read_reg_mdi(hw, + IXGBE_MDIO_PMA_PMD_SDA_SCL_STAT, + MDIO_MMD_PMAPMD, + &sfp_stat); sfp_stat = sfp_stat & IXGBE_I2C_EEPROM_STATUS_MASK; if (sfp_stat != IXGBE_I2C_EEPROM_STATUS_IN_PROGRESS) break; @@ -1078,20 +1066,50 @@ static s32 ixgbe_read_i2c_eeprom_82598(struct ixgbe_hw *hw, u8 byte_offset, } /* Read data */ - hw->phy.ops.read_reg(hw, IXGBE_MDIO_PMA_PMD_SDA_SCL_DATA, - MDIO_MMD_PMAPMD, &sfp_data); + hw->phy.ops.read_reg_mdi(hw, IXGBE_MDIO_PMA_PMD_SDA_SCL_DATA, + MDIO_MMD_PMAPMD, &sfp_data); *eeprom_data = (u8)(sfp_data >> 8); } else { status = IXGBE_ERR_PHY; - goto out; } out: + hw->mac.ops.release_swfw_sync(hw, gssr); return status; } /** + * ixgbe_read_i2c_eeprom_82598 - Reads 8 bit word over I2C interface. + * @hw: pointer to hardware structure + * @byte_offset: EEPROM byte offset to read + * @eeprom_data: value read + * + * Performs 8 byte read operation to SFP module's EEPROM over I2C interface. + **/ +static s32 ixgbe_read_i2c_eeprom_82598(struct ixgbe_hw *hw, u8 byte_offset, + u8 *eeprom_data) +{ + return ixgbe_read_i2c_phy_82598(hw, IXGBE_I2C_EEPROM_DEV_ADDR, + byte_offset, eeprom_data); +} + +/** + * ixgbe_read_i2c_sff8472_82598 - Reads 8 bit word over I2C interface. + * @hw: pointer to hardware structure + * @byte_offset: byte offset at address 0xA2 + * @eeprom_data: value read + * + * Performs 8 byte read operation to SFP module's SFF-8472 data over I2C + **/ +static s32 ixgbe_read_i2c_sff8472_82598(struct ixgbe_hw *hw, u8 byte_offset, + u8 *sff8472_data) +{ + return ixgbe_read_i2c_phy_82598(hw, IXGBE_I2C_EEPROM_DEV_ADDR2, + byte_offset, sff8472_data); +} + +/** * ixgbe_get_supported_physical_layer_82598 - Returns physical layer type * @hw: pointer to hardware structure * @@ -1224,14 +1242,14 @@ static void ixgbe_set_lan_id_multi_port_pcie_82598(struct ixgbe_hw *hw) } /** - * ixgbe_set_rxpba_82598 - Configure packet buffers + * ixgbe_set_rxpba_82598 - Initialize RX packet buffer * @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) + * @num_pb: number of packet buffers to allocate + * @headroom: reserve n KB of headroom + * @strategy: packet buffer allocation strategy + **/ +static void ixgbe_set_rxpba_82598(struct ixgbe_hw *hw, int num_pb, + u32 headroom, int strategy) { u32 rxpktsize = IXGBE_RXPBSIZE_64KB; u8 i = 0; @@ -1260,8 +1278,6 @@ static void ixgbe_set_rxpba_82598(struct ixgbe_hw *hw, int num_pb, u32 headroom, /* 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 = { @@ -1300,6 +1316,10 @@ static struct ixgbe_mac_operations mac_ops_82598 = { .set_fw_drv_ver = NULL, .acquire_swfw_sync = &ixgbe_acquire_swfw_sync, .release_swfw_sync = &ixgbe_release_swfw_sync, + .get_thermal_sensor_data = NULL, + .init_thermal_sensor_thresh = NULL, + .prot_autoc_read = &prot_autoc_read_generic, + .prot_autoc_write = &prot_autoc_write_generic, }; static struct ixgbe_eeprom_operations eeprom_ops_82598 = { @@ -1315,13 +1335,16 @@ static struct ixgbe_eeprom_operations eeprom_ops_82598 = { static struct ixgbe_phy_operations phy_ops_82598 = { .identify = &ixgbe_identify_phy_generic, - .identify_sfp = &ixgbe_identify_sfp_module_generic, + .identify_sfp = &ixgbe_identify_module_generic, .init = &ixgbe_init_phy_ops_82598, .reset = &ixgbe_reset_phy_generic, .read_reg = &ixgbe_read_phy_reg_generic, .write_reg = &ixgbe_write_phy_reg_generic, + .read_reg_mdi = &ixgbe_read_phy_reg_mdi, + .write_reg_mdi = &ixgbe_write_phy_reg_mdi, .setup_link = &ixgbe_setup_phy_link_generic, .setup_link_speed = &ixgbe_setup_phy_link_speed_generic, + .read_i2c_sff8472 = &ixgbe_read_i2c_sff8472_82598, .read_i2c_eeprom = &ixgbe_read_i2c_eeprom_82598, .check_overtemp = &ixgbe_tn_check_overtemp, }; @@ -1333,4 +1356,3 @@ struct ixgbe_info ixgbe_82598_info = { .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 index 4e59083a3de..bc7c924240a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2014 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, @@ -20,6 +20,7 @@ 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 @@ -45,35 +46,59 @@ 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); + ixgbe_link_speed speed, + bool autoneg_wait_to_complete); +static void ixgbe_stop_mac_link_on_d3_82599(struct ixgbe_hw *hw); static s32 ixgbe_start_mac_link_82599(struct ixgbe_hw *hw, bool autoneg_wait_to_complete); static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw, - ixgbe_link_speed speed, - bool autoneg, - bool autoneg_wait_to_complete); + ixgbe_link_speed speed, + bool autoneg_wait_to_complete); static s32 ixgbe_setup_copper_link_82599(struct ixgbe_hw *hw, - ixgbe_link_speed speed, - bool autoneg, - bool autoneg_wait_to_complete); + ixgbe_link_speed speed, + bool autoneg_wait_to_complete); static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw); +static s32 ixgbe_read_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 *data); +static s32 ixgbe_write_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 data); +static s32 ixgbe_reset_pipeline_82599(struct ixgbe_hw *hw); static bool ixgbe_verify_lesm_fw_enabled_82599(struct ixgbe_hw *hw); +bool ixgbe_mng_enabled(struct ixgbe_hw *hw) +{ + u32 fwsm, manc, factps; + + fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM); + if ((fwsm & IXGBE_FWSM_MODE_MASK) != IXGBE_FWSM_FW_MODE_PT) + return false; + + manc = IXGBE_READ_REG(hw, IXGBE_MANC); + if (!(manc & IXGBE_MANC_RCV_TCO_EN)) + return false; + + factps = IXGBE_READ_REG(hw, IXGBE_FACTPS); + if (factps & IXGBE_FACTPS_MNGCG) + return false; + + return true; +} + static void ixgbe_init_mac_link_ops_82599(struct ixgbe_hw *hw) { struct ixgbe_mac_info *mac = &hw->mac; - /* enable the laser control functions for SFP+ fiber */ - if (mac->ops.get_media_type(hw) == ixgbe_media_type_fiber) { + /* enable the laser control functions for SFP+ fiber + * and MNG not enabled + */ + if ((mac->ops.get_media_type(hw) == ixgbe_media_type_fiber) && + !ixgbe_mng_enabled(hw)) { mac->ops.disable_tx_laser = - &ixgbe_disable_tx_laser_multispeed_fiber; + &ixgbe_disable_tx_laser_multispeed_fiber; mac->ops.enable_tx_laser = - &ixgbe_enable_tx_laser_multispeed_fiber; + &ixgbe_enable_tx_laser_multispeed_fiber; mac->ops.flap_tx_laser = &ixgbe_flap_tx_laser_multispeed_fiber; } else { mac->ops.disable_tx_laser = NULL; @@ -99,8 +124,6 @@ static void ixgbe_init_mac_link_ops_82599(struct ixgbe_hw *hw) 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) { @@ -109,23 +132,25 @@ static s32 ixgbe_setup_sfp_modules_82599(struct ixgbe_hw *hw) hw->phy.ops.reset = NULL; ret_val = ixgbe_get_sfp_init_sequence_offsets(hw, &list_offset, - &data_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); + 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); + if (hw->eeprom.ops.read(hw, ++data_offset, &data_value)) + goto setup_sfp_err; while (data_value != 0xffff) { IXGBE_WRITE_REG(hw, IXGBE_CORECTL, data_value); IXGBE_WRITE_FLUSH(hw); - hw->eeprom.ops.read(hw, ++data_offset, &data_value); + if (hw->eeprom.ops.read(hw, ++data_offset, &data_value)) + goto setup_sfp_err; } /* Release the semaphore */ @@ -137,32 +162,106 @@ static s32 ixgbe_setup_sfp_modules_82599(struct ixgbe_hw *hw) 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)); + /* Restart DSP and set SFI mode */ + ret_val = hw->mac.ops.prot_autoc_write(hw, + hw->mac.orig_autoc | IXGBE_AUTOC_LMS_10G_SERIAL, + false); - /* 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"); + if (ret_val) { + 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; + +setup_sfp_err: + /* Release the semaphore */ + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_MAC_CSR_SM); + /* Delay obtaining semaphore again to allow FW access, + * semaphore_delay is in ms usleep_range needs us. + */ + usleep_range(hw->eeprom.semaphore_delay * 1000, + hw->eeprom.semaphore_delay * 2000); + hw_err(hw, "eeprom read at offset %d failed\n", data_offset); + return IXGBE_ERR_SFP_SETUP_NOT_COMPLETE; +} + +/** + * prot_autoc_read_82599 - Hides MAC differences needed for AUTOC read + * @hw: pointer to hardware structure + * @locked: Return the if we locked for this read. + * @reg_val: Value we read from AUTOC + * + * For this part (82599) we need to wrap read-modify-writes with a possible + * FW/SW lock. It is assumed this lock will be freed with the next + * prot_autoc_write_82599(). Note, that locked can only be true in cases + * where this function doesn't return an error. + **/ +static s32 prot_autoc_read_82599(struct ixgbe_hw *hw, bool *locked, + u32 *reg_val) +{ + s32 ret_val; + + *locked = false; + /* If LESM is on then we need to hold the SW/FW semaphore. */ + if (ixgbe_verify_lesm_fw_enabled_82599(hw)) { + ret_val = hw->mac.ops.acquire_swfw_sync(hw, + IXGBE_GSSR_MAC_CSR_SM); + if (ret_val) + return IXGBE_ERR_SWFW_SYNC; + + *locked = true; + } + + *reg_val = IXGBE_READ_REG(hw, IXGBE_AUTOC); + return 0; +} + +/** + * prot_autoc_write_82599 - Hides MAC differences needed for AUTOC write + * @hw: pointer to hardware structure + * @reg_val: value to write to AUTOC + * @locked: bool to indicate whether the SW/FW lock was already taken by + * previous proc_autoc_read_82599. + * + * This part (82599) may need to hold a the SW/FW lock around all writes to + * AUTOC. Likewise after a write we need to do a pipeline reset. + **/ +static s32 prot_autoc_write_82599(struct ixgbe_hw *hw, u32 autoc, bool locked) +{ + s32 ret_val = 0; + + /* Blocked by MNG FW so bail */ + if (ixgbe_check_reset_blocked(hw)) + goto out; + + /* We only need to get the lock if: + * - We didn't do it already (in the read part of a read-modify-write) + * - LESM is enabled. + */ + if (!locked && ixgbe_verify_lesm_fw_enabled_82599(hw)) { + ret_val = hw->mac.ops.acquire_swfw_sync(hw, + IXGBE_GSSR_MAC_CSR_SM); + if (ret_val) + return IXGBE_ERR_SWFW_SYNC; + + locked = true; + } + + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc); + ret_val = ixgbe_reset_pipeline_82599(hw); + +out: + /* Free the SW/FW semaphore as we either grabbed it here or + * already had it when this function was called. + */ + if (locked) + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_MAC_CSR_SM); + + return ret_val; } static s32 ixgbe_get_invariants_82599(struct ixgbe_hw *hw) @@ -174,6 +273,7 @@ static s32 ixgbe_get_invariants_82599(struct ixgbe_hw *hw) mac->mcft_size = IXGBE_82599_MC_TBL_SIZE; mac->vft_size = IXGBE_82599_VFT_TBL_SIZE; mac->num_rar_entries = IXGBE_82599_RAR_ENTRIES; + mac->rx_pb_size = IXGBE_82599_RX_PB_SIZE; mac->max_rx_queues = IXGBE_82599_MAX_RX_QUEUES; mac->max_tx_queues = IXGBE_82599_MAX_TX_QUEUES; mac->max_msix_vectors = ixgbe_get_pcie_msix_count_generic(hw); @@ -195,6 +295,25 @@ 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; + u32 esdp; + + if (hw->device_id == IXGBE_DEV_ID_82599_QSFP_SF_QP) { + /* Store flag indicating I2C bus access control unit. */ + hw->phy.qsfp_shared_i2c_bus = true; + + /* Initialize access to QSFP+ I2C bus */ + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + esdp |= IXGBE_ESDP_SDP0_DIR; + esdp &= ~IXGBE_ESDP_SDP1_DIR; + esdp &= ~IXGBE_ESDP_SDP0; + esdp &= ~IXGBE_ESDP_SDP0_NATIVE; + esdp &= ~IXGBE_ESDP_SDP1_NATIVE; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp); + IXGBE_WRITE_FLUSH(hw); + + phy->ops.read_i2c_byte = &ixgbe_read_i2c_byte_82599; + phy->ops.write_i2c_byte = &ixgbe_write_i2c_byte_82599; + } /* Identify the PHY or SFP module */ ret_val = phy->ops.identify(hw); @@ -215,7 +334,7 @@ static s32 ixgbe_init_phy_ops_82599(struct ixgbe_hw *hw) 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; + &ixgbe_get_phy_firmware_version_tnx; break; default: break; @@ -228,22 +347,26 @@ static s32 ixgbe_init_phy_ops_82599(struct ixgbe_hw *hw) * 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 + * @autoneg: true when autoneg or autotry is enabled * * Determines the link capabilities by reading the AUTOC register. **/ static s32 ixgbe_get_link_capabilities_82599(struct ixgbe_hw *hw, - ixgbe_link_speed *speed, - bool *negotiation) + ixgbe_link_speed *speed, + bool *autoneg) { 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) { + hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core1 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core1 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1) { *speed = IXGBE_LINK_SPEED_1GB_FULL; - *negotiation = true; + *autoneg = true; goto out; } @@ -260,22 +383,22 @@ static s32 ixgbe_get_link_capabilities_82599(struct ixgbe_hw *hw, switch (autoc & IXGBE_AUTOC_LMS_MASK) { case IXGBE_AUTOC_LMS_1G_LINK_NO_AN: *speed = IXGBE_LINK_SPEED_1GB_FULL; - *negotiation = false; + *autoneg = false; break; case IXGBE_AUTOC_LMS_10G_LINK_NO_AN: *speed = IXGBE_LINK_SPEED_10GB_FULL; - *negotiation = false; + *autoneg = false; break; case IXGBE_AUTOC_LMS_1G_AN: *speed = IXGBE_LINK_SPEED_1GB_FULL; - *negotiation = true; + *autoneg = true; break; case IXGBE_AUTOC_LMS_10G_SERIAL: *speed = IXGBE_LINK_SPEED_10GB_FULL; - *negotiation = false; + *autoneg = false; break; case IXGBE_AUTOC_LMS_KX4_KX_KR: @@ -287,7 +410,7 @@ static s32 ixgbe_get_link_capabilities_82599(struct ixgbe_hw *hw, *speed |= IXGBE_LINK_SPEED_10GB_FULL; if (autoc & IXGBE_AUTOC_KX_SUPP) *speed |= IXGBE_LINK_SPEED_1GB_FULL; - *negotiation = true; + *autoneg = true; break; case IXGBE_AUTOC_LMS_KX4_KX_KR_SGMII: @@ -298,12 +421,12 @@ static s32 ixgbe_get_link_capabilities_82599(struct ixgbe_hw *hw, *speed |= IXGBE_LINK_SPEED_10GB_FULL; if (autoc & IXGBE_AUTOC_KX_SUPP) *speed |= IXGBE_LINK_SPEED_1GB_FULL; - *negotiation = true; + *autoneg = true; break; case IXGBE_AUTOC_LMS_SGMII_1G_100M: *speed = IXGBE_LINK_SPEED_1GB_FULL | IXGBE_LINK_SPEED_100_FULL; - *negotiation = false; + *autoneg = false; break; default: @@ -314,8 +437,13 @@ static s32 ixgbe_get_link_capabilities_82599(struct ixgbe_hw *hw, if (hw->phy.multispeed_fiber) { *speed |= IXGBE_LINK_SPEED_10GB_FULL | - IXGBE_LINK_SPEED_1GB_FULL; - *negotiation = true; + IXGBE_LINK_SPEED_1GB_FULL; + + /* QSFP must not enable auto-negotiation */ + if (hw->phy.media_type == ixgbe_media_type_fiber_qsfp) + *autoneg = false; + else + *autoneg = true; } out: @@ -369,6 +497,9 @@ static enum ixgbe_media_type ixgbe_get_media_type_82599(struct ixgbe_hw *hw) case IXGBE_DEV_ID_82599_LS: media_type = ixgbe_media_type_fiber_lco; break; + case IXGBE_DEV_ID_82599_QSFP_SF_QP: + media_type = ixgbe_media_type_fiber_qsfp; + break; default: media_type = ixgbe_media_type_unknown; break; @@ -378,6 +509,32 @@ out: } /** + * ixgbe_stop_mac_link_on_d3_82599 - Disables link on D3 + * @hw: pointer to hardware structure + * + * Disables link, should be called during D3 power down sequence. + * + **/ +static void ixgbe_stop_mac_link_on_d3_82599(struct ixgbe_hw *hw) +{ + u32 autoc2_reg, fwsm; + u16 ee_ctrl_2 = 0; + + hw->eeprom.ops.read(hw, IXGBE_EEPROM_CTRL_2, &ee_ctrl_2); + + /* Check to see if MNG FW could be enabled */ + fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM); + + if (((fwsm & IXGBE_FWSM_MODE_MASK) != IXGBE_FWSM_FW_MODE_PT) && + !hw->wol_enabled && + ee_ctrl_2 & IXGBE_EEPROM_CCD_BIT) { + autoc2_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC2); + autoc2_reg |= IXGBE_AUTOC2_LINK_DISABLE_ON_D3_MASK; + IXGBE_WRITE_REG(hw, IXGBE_AUTOC2, autoc2_reg); + } +} + +/** * ixgbe_start_mac_link_82599 - Setup MAC link settings * @hw: pointer to hardware structure * @autoneg_wait_to_complete: true when waiting for completion is needed @@ -386,20 +543,32 @@ out: * Restarts the link. Performs autonegotiation if needed. **/ static s32 ixgbe_start_mac_link_82599(struct ixgbe_hw *hw, - bool autoneg_wait_to_complete) + bool autoneg_wait_to_complete) { u32 autoc_reg; u32 links_reg; u32 i; s32 status = 0; + bool got_lock = false; + + if (ixgbe_verify_lesm_fw_enabled_82599(hw)) { + status = hw->mac.ops.acquire_swfw_sync(hw, + IXGBE_GSSR_MAC_CSR_SM); + if (status) + goto out; + + got_lock = true; + } /* Restart link */ - autoc_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC); - autoc_reg |= IXGBE_AUTOC_AN_RESTART; - IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc_reg); + ixgbe_reset_pipeline_82599(hw); + + if (got_lock) + hw->mac.ops.release_swfw_sync(hw, IXGBE_GSSR_MAC_CSR_SM); /* Only poll for autoneg to complete if specified to do so */ if (autoneg_wait_to_complete) { + autoc_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC); if ((autoc_reg & IXGBE_AUTOC_LMS_MASK) == IXGBE_AUTOC_LMS_KX4_KX_KR || (autoc_reg & IXGBE_AUTOC_LMS_MASK) == @@ -423,6 +592,7 @@ static s32 ixgbe_start_mac_link_82599(struct ixgbe_hw *hw, /* Add delay to filter out noises during initial link setup */ msleep(50); +out: return status; } @@ -438,6 +608,10 @@ static void ixgbe_disable_tx_laser_multispeed_fiber(struct ixgbe_hw *hw) { u32 esdp_reg = IXGBE_READ_REG(hw, IXGBE_ESDP); + /* Blocked by MNG FW so bail */ + if (ixgbe_check_reset_blocked(hw)) + return; + /* Disable tx laser; allow 100us to go dark per spec */ esdp_reg |= IXGBE_ESDP_SDP3; IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp_reg); @@ -478,6 +652,10 @@ static void ixgbe_enable_tx_laser_multispeed_fiber(struct ixgbe_hw *hw) **/ static void ixgbe_flap_tx_laser_multispeed_fiber(struct ixgbe_hw *hw) { + /* Blocked by MNG FW so bail */ + if (ixgbe_check_reset_blocked(hw)) + return; + if (hw->mac.autotry_restart) { ixgbe_disable_tx_laser_multispeed_fiber(hw); ixgbe_enable_tx_laser_multispeed_fiber(hw); @@ -489,15 +667,13 @@ static void ixgbe_flap_tx_laser_multispeed_fiber(struct ixgbe_hw *hw) * 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) + ixgbe_link_speed speed, + bool autoneg_wait_to_complete) { s32 status = 0; ixgbe_link_speed link_speed = IXGBE_LINK_SPEED_UNKNOWN; @@ -506,11 +682,11 @@ static s32 ixgbe_setup_mac_link_multispeed_fiber(struct ixgbe_hw *hw, u32 esdp_reg = IXGBE_READ_REG(hw, IXGBE_ESDP); u32 i = 0; bool link_up = false; - bool negotiation; + bool autoneg = false; /* Mask off requested but non-supported speeds */ status = hw->mac.ops.get_link_capabilities(hw, &link_speed, - &negotiation); + &autoneg); if (status != 0) return status; @@ -534,22 +710,32 @@ static s32 ixgbe_setup_mac_link_multispeed_fiber(struct ixgbe_hw *hw, 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); + switch (hw->phy.media_type) { + case ixgbe_media_type_fiber: + esdp_reg |= (IXGBE_ESDP_SDP5_DIR | IXGBE_ESDP_SDP5); + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp_reg); + IXGBE_WRITE_FLUSH(hw); + break; + case ixgbe_media_type_fiber_qsfp: + /* QSFP module automatically detects MAC link speed */ + break; + default: + hw_dbg(hw, "Unexpected media type.\n"); + break; + } /* Allow module to change analog characteristics (1G->10G) */ msleep(40); status = 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); + if (hw->mac.ops.flap_tx_laser) + hw->mac.ops.flap_tx_laser(hw); /* * Wait for the controller to acquire link. Per IEEE 802.3ap, @@ -586,23 +772,33 @@ static s32 ixgbe_setup_mac_link_multispeed_fiber(struct ixgbe_hw *hw, 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); + switch (hw->phy.media_type) { + case ixgbe_media_type_fiber: + esdp_reg &= ~IXGBE_ESDP_SDP5; + esdp_reg |= IXGBE_ESDP_SDP5_DIR; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp_reg); + IXGBE_WRITE_FLUSH(hw); + break; + case ixgbe_media_type_fiber_qsfp: + /* QSFP module automatically detects MAC link speed */ + break; + default: + hw_dbg(hw, "Unexpected media type.\n"); + break; + } /* Allow module to change analog characteristics (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); + if (hw->mac.ops.flap_tx_laser) + hw->mac.ops.flap_tx_laser(hw); /* Wait for the link partner to also set speed */ msleep(100); @@ -624,9 +820,8 @@ static s32 ixgbe_setup_mac_link_multispeed_fiber(struct ixgbe_hw *hw, */ if (speedcnt > 1) status = ixgbe_setup_mac_link_multispeed_fiber(hw, - highest_link_speed, - autoneg, - autoneg_wait_to_complete); + highest_link_speed, + autoneg_wait_to_complete); out: /* Set autoneg_advertised value based on input link speed */ @@ -645,13 +840,12 @@ out: * 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, + ixgbe_link_speed speed, bool autoneg_wait_to_complete) { s32 status = 0; @@ -682,7 +876,7 @@ static s32 ixgbe_setup_mac_link_smartspeed(struct ixgbe_hw *hw, /* 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, + status = ixgbe_setup_mac_link_82599(hw, speed, autoneg_wait_to_complete); if (status != 0) goto out; @@ -717,7 +911,7 @@ static s32 ixgbe_setup_mac_link_smartspeed(struct ixgbe_hw *hw, /* Turn SmartSpeed on to disable KR support */ hw->phy.smart_speed_active = true; - status = ixgbe_setup_mac_link_82599(hw, speed, autoneg, + status = ixgbe_setup_mac_link_82599(hw, speed, autoneg_wait_to_complete); if (status != 0) goto out; @@ -743,13 +937,12 @@ static s32 ixgbe_setup_mac_link_smartspeed(struct ixgbe_hw *hw, /* We didn't get link. Turn SmartSpeed back off. */ hw->phy.smart_speed_active = false; - status = ixgbe_setup_mac_link_82599(hw, speed, autoneg, + status = ixgbe_setup_mac_link_82599(hw, speed, autoneg_wait_to_complete); out: if (link_up && (link_speed == IXGBE_LINK_SPEED_1GB_FULL)) - hw_dbg(hw, "Smartspeed has downgraded the link speed from " - "the maximum advertised\n"); + hw_dbg(hw, "Smartspeed has downgraded the link speed from the maximum advertised\n"); return status; } @@ -757,29 +950,31 @@ out: * 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) + ixgbe_link_speed speed, + bool autoneg_wait_to_complete) { + bool autoneg = false; s32 status = 0; - u32 autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC); + u32 pma_pmd_1g, link_mode, links_reg, i; 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; + /* holds the value of AUTOC register at this current point in time */ + u32 current_autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC); + /* holds the cached value of AUTOC register */ + u32 orig_autoc = 0; + /* temporary variable used for comparison purposes */ + u32 autoc = current_autoc; + /* Check to see if speed passed in is supported. */ - hw->mac.ops.get_link_capabilities(hw, &link_capabilities, &autoneg); + status = hw->mac.ops.get_link_capabilities(hw, &link_capabilities, + &autoneg); if (status != 0) goto out; @@ -796,22 +991,26 @@ static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw, else orig_autoc = autoc; + link_mode = autoc & IXGBE_AUTOC_LMS_MASK; + pma_pmd_1g = autoc & IXGBE_AUTOC_1G_PMA_PMD_MASK; + if (link_mode == IXGBE_AUTOC_LMS_KX4_KX_KR || link_mode == IXGBE_AUTOC_LMS_KX4_KX_KR_1G_AN || link_mode == IXGBE_AUTOC_LMS_KX4_KX_KR_SGMII) { /* Set KX4/KX/KR support according to speed requested */ autoc &= ~(IXGBE_AUTOC_KX4_KX_SUPP_MASK | IXGBE_AUTOC_KR_SUPP); - if (speed & IXGBE_LINK_SPEED_10GB_FULL) + if (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)) { + (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)) { @@ -819,7 +1018,7 @@ static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw, autoc |= IXGBE_AUTOC_LMS_10G_SERIAL; } } else if ((pma_pmd_10g_serial == IXGBE_AUTOC2_10G_SFI) && - (link_mode == IXGBE_AUTOC_LMS_10G_SERIAL)) { + (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)) { @@ -831,10 +1030,11 @@ static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw, } } - if (autoc != start_autoc) { + if (autoc != current_autoc) { /* Restart link */ - autoc |= IXGBE_AUTOC_AN_RESTART; - IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc); + status = hw->mac.ops.prot_autoc_write(hw, autoc, false); + if (status) + goto out; /* Only poll for autoneg to complete if specified to do so */ if (autoneg_wait_to_complete) { @@ -851,9 +1051,8 @@ static s32 ixgbe_setup_mac_link_82599(struct ixgbe_hw *hw, } if (!(links_reg & IXGBE_LINKS_KX_AN_COMP)) { status = - IXGBE_ERR_AUTONEG_NOT_COMPLETE; - hw_dbg(hw, "Autoneg did not " - "complete.\n"); + IXGBE_ERR_AUTONEG_NOT_COMPLETE; + hw_dbg(hw, "Autoneg did not complete.\n"); } } } @@ -870,21 +1069,19 @@ out: * 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) + ixgbe_link_speed speed, + bool autoneg_wait_to_complete) { s32 status; /* Setup the PHY according to input speed */ - status = hw->phy.ops.setup_link_speed(hw, speed, autoneg, - autoneg_wait_to_complete); + status = hw->phy.ops.setup_link_speed(hw, speed, + autoneg_wait_to_complete); /* Set up MAC */ ixgbe_start_mac_link_82599(hw, autoneg_wait_to_complete); @@ -904,6 +1101,7 @@ static s32 ixgbe_reset_hw_82599(struct ixgbe_hw *hw) ixgbe_link_speed link_speed; s32 status; u32 ctrl, i, autoc, autoc2; + u32 curr_lms; bool link_up = false; /* Call adapter stop to disable tx/rx and clear interrupts */ @@ -935,6 +1133,9 @@ static s32 ixgbe_reset_hw_82599(struct ixgbe_hw *hw) if (hw->phy.reset_disable == false && hw->phy.ops.reset != NULL) hw->phy.ops.reset(hw); + /* remember AUTOC from before we reset */ + curr_lms = IXGBE_READ_REG(hw, IXGBE_AUTOC) & IXGBE_AUTOC_LMS_MASK; + mac_reset_top: /* * Issue global reset to the MAC. Needs to be SW reset if link is up. @@ -985,20 +1186,45 @@ mac_reset_top: */ autoc = IXGBE_READ_REG(hw, IXGBE_AUTOC); autoc2 = IXGBE_READ_REG(hw, IXGBE_AUTOC2); + + /* Enable link if disabled in NVM */ + if (autoc2 & IXGBE_AUTOC2_LINK_DISABLE_MASK) { + autoc2 &= ~IXGBE_AUTOC2_LINK_DISABLE_MASK; + IXGBE_WRITE_REG(hw, IXGBE_AUTOC2, autoc2); + IXGBE_WRITE_FLUSH(hw); + } + if (hw->mac.orig_link_settings_stored == false) { hw->mac.orig_autoc = autoc; hw->mac.orig_autoc2 = autoc2; hw->mac.orig_link_settings_stored = true; } else { - if (autoc != hw->mac.orig_autoc) - IXGBE_WRITE_REG(hw, IXGBE_AUTOC, (hw->mac.orig_autoc | - IXGBE_AUTOC_AN_RESTART)); + + /* If MNG FW is running on a multi-speed device that + * doesn't autoneg with out driver support we need to + * leave LMS in the state it was before we MAC reset. + * Likewise if we support WoL we don't want change the + * LMS state either. + */ + if ((hw->phy.multispeed_fiber && ixgbe_mng_enabled(hw)) || + hw->wol_enabled) + hw->mac.orig_autoc = + (hw->mac.orig_autoc & ~IXGBE_AUTOC_LMS_MASK) | + curr_lms; + + if (autoc != hw->mac.orig_autoc) { + status = hw->mac.ops.prot_autoc_write(hw, + hw->mac.orig_autoc, + false); + if (status) + goto reset_hw_out; + } 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_AUTOC2_UPPER_MASK); IXGBE_WRITE_REG(hw, IXGBE_AUTOC2, autoc2); } } @@ -1018,9 +1244,12 @@ mac_reset_top: 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) { + if (is_valid_ether_addr(hw->mac.san_addr)) { hw->mac.ops.set_rar(hw, hw->mac.num_rar_entries - 1, - hw->mac.san_addr, 0, IXGBE_RAH_AV); + hw->mac.san_addr, 0, IXGBE_RAH_AV); + + /* Save the SAN MAC RAR index */ + hw->mac.san_mac_rar_index = hw->mac.num_rar_entries - 1; /* Reserve the last RAR for the SAN MAC address */ hw->mac.num_rar_entries--; @@ -1028,7 +1257,7 @@ mac_reset_top: /* Store the alternative WWNN/WWPN prefix */ hw->mac.ops.get_wwn_prefix(hw, &hw->mac.wwnn_prefix, - &hw->mac.wwpn_prefix); + &hw->mac.wwpn_prefix); reset_hw_out: return status; @@ -1042,6 +1271,7 @@ 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; /* @@ -1055,8 +1285,7 @@ s32 ixgbe_reinit_fdir_tables_82599(struct ixgbe_hw *hw) udelay(10); } if (i >= IXGBE_FDIRCMD_CMD_POLL) { - hw_dbg(hw, "Flow Director previous command isn't complete, " - "aborting table re-initialization.\n"); + hw_dbg(hw, "Flow Director previous command isn't complete, aborting table re-initialization.\n"); return IXGBE_ERR_FDIR_REINIT_FAILED; } @@ -1070,12 +1299,12 @@ s32 ixgbe_reinit_fdir_tables_82599(struct ixgbe_hw *hw) * - write 0 to bit 8 of FDIRCMD register */ IXGBE_WRITE_REG(hw, IXGBE_FDIRCMD, - (IXGBE_READ_REG(hw, IXGBE_FDIRCMD) | - IXGBE_FDIRCMD_CLEARHT)); + (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_READ_REG(hw, IXGBE_FDIRCMD) & + ~IXGBE_FDIRCMD_CLEARHT)); IXGBE_WRITE_FLUSH(hw); /* * Clear FDIR Hash register to clear any leftover hashes @@ -1090,9 +1319,9 @@ s32 ixgbe_reinit_fdir_tables_82599(struct ixgbe_hw *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) + IXGBE_FDIRCTRL_INIT_DONE) break; - udelay(10); + usleep_range(1000, 2000); } if (i >= IXGBE_FDIR_INIT_DONE_POLL) { hw_dbg(hw, "Flow Director Signature poll time exceeded!\n"); @@ -1139,7 +1368,7 @@ static void ixgbe_fdir_enable_82599(struct ixgbe_hw *hw, u32 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) + IXGBE_FDIRCTRL_INIT_DONE) break; usleep_range(1000, 2000); } @@ -1224,7 +1453,7 @@ do { \ 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); +} while (0) /** * ixgbe_atr_compute_sig_hash_82599 - Compute the signature hash @@ -1300,9 +1529,9 @@ static u32 ixgbe_atr_compute_sig_hash_82599(union ixgbe_atr_hash_dword input, * @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) + union ixgbe_atr_hash_dword input, + union ixgbe_atr_hash_dword common, + u8 queue) { u64 fdirhashcmd; u32 fdircmd; @@ -1326,7 +1555,7 @@ s32 ixgbe_fdir_add_signature_filter_82599(struct ixgbe_hw *hw, /* configure FDIRCMD register */ fdircmd = IXGBE_FDIRCMD_CMD_ADD_FLOW | IXGBE_FDIRCMD_FILTER_UPDATE | - IXGBE_FDIRCMD_LAST | IXGBE_FDIRCMD_QUEUE_EN; + 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; @@ -1350,7 +1579,7 @@ do { \ bucket_hash ^= lo_hash_dword >> n; \ if (IXGBE_ATR_BUCKET_HASH_KEY & (0x01 << (n + 16))) \ bucket_hash ^= hi_hash_dword >> n; \ -} while (0); +} while (0) /** * ixgbe_atr_compute_perfect_hash_82599 - Compute the perfect filter hash @@ -1368,35 +1597,20 @@ void ixgbe_atr_compute_perfect_hash_82599(union ixgbe_atr_input *input, { u32 hi_hash_dword, lo_hash_dword, flow_vm_vlan; - u32 bucket_hash = 0; + u32 bucket_hash = 0, hi_dword = 0; + int i; /* 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]; + for (i = 0; i <= 10; i++) + input->dword_stream[i] &= input_mask->dword_stream[i]; /* record the flow_vm_vlan bits as they are a key part to the hash */ flow_vm_vlan = ntohl(input->dword_stream[0]); /* generate common hash dword */ - 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]); + for (i = 1; i <= 10; i++) + hi_dword ^= input->dword_stream[i]; + hi_hash_dword = ntohl(hi_dword); /* low dword is word swapped version of common */ lo_hash_dword = (hi_hash_dword >> 16) | (hi_hash_dword << 16); @@ -1415,21 +1629,8 @@ void ixgbe_atr_compute_perfect_hash_82599(union ixgbe_atr_input *input, 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); + for (i = 1; i <= 15; i++) + IXGBE_COMPUTE_BKT_HASH_ITERATION(i); /* * Limit hash to 13 bits since max bucket count is 8K. @@ -1450,6 +1651,7 @@ void ixgbe_atr_compute_perfect_hash_82599(union ixgbe_atr_input *input, 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); @@ -1684,7 +1886,7 @@ 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)); + (reg << 8)); IXGBE_WRITE_FLUSH(hw); udelay(10); core_ctl = IXGBE_READ_REG(hw, IXGBE_CORECTL); @@ -1735,7 +1937,6 @@ static s32 ixgbe_start_hw_82599(struct ixgbe_hw *hw) /* 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); @@ -1762,7 +1963,7 @@ static s32 ixgbe_identify_phy_82599(struct ixgbe_hw *hw) if (hw->mac.ops.get_media_type(hw) == ixgbe_media_type_copper) goto out; else - status = ixgbe_identify_sfp_module_generic(hw); + status = ixgbe_identify_module_generic(hw); } /* Set PHY type none if no PHY detected */ @@ -1868,10 +2069,12 @@ sfp_check: switch (hw->phy.type) { case ixgbe_phy_sfp_passive_tyco: case ixgbe_phy_sfp_passive_unknown: + case ixgbe_phy_qsfp_passive_unknown: physical_layer = IXGBE_PHYSICAL_LAYER_SFP_PLUS_CU; break; case ixgbe_phy_sfp_ftl_active: case ixgbe_phy_sfp_active_unknown: + case ixgbe_phy_qsfp_active_unknown: physical_layer = IXGBE_PHYSICAL_LAYER_SFP_ACTIVE_DA; break; case ixgbe_phy_sfp_avago: @@ -1889,6 +2092,15 @@ sfp_check: else if (comp_codes_1g & IXGBE_SFF_1GBASET_CAPABLE) physical_layer = IXGBE_PHYSICAL_LAYER_1000BASE_T; break; + case ixgbe_phy_qsfp_intel: + case ixgbe_phy_qsfp_unknown: + hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_QSFP_10GBE_COMP, &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; + break; default: break; } @@ -1906,38 +2118,17 @@ out: **/ 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"); + hw->mac.ops.disable_rx_buff(hw); 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); + + hw->mac.ops.enable_rx_buff(hw); return 0; } @@ -1956,6 +2147,7 @@ static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw) { s32 status = IXGBE_ERR_EEPROM_VERSION; u16 fw_offset, fw_ptp_cfg_offset; + u16 offset; u16 fw_version = 0; /* firmware check is only necessary for SFI devices */ @@ -1965,29 +2157,35 @@ static s32 ixgbe_verify_fw_version_82599(struct ixgbe_hw *hw) } /* get the offset to the Firmware Module block */ - hw->eeprom.ops.read(hw, IXGBE_FW_PTR, &fw_offset); + offset = IXGBE_FW_PTR; + if (hw->eeprom.ops.read(hw, offset, &fw_offset)) + goto fw_version_err; 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); + offset = fw_offset + IXGBE_FW_PASSTHROUGH_PATCH_CONFIG_PTR; + if (hw->eeprom.ops.read(hw, offset, &fw_ptp_cfg_offset)) + goto fw_version_err; if ((fw_ptp_cfg_offset == 0) || (fw_ptp_cfg_offset == 0xFFFF)) goto fw_version_out; /* get the firmware version */ - hw->eeprom.ops.read(hw, (fw_ptp_cfg_offset + - IXGBE_FW_PATCH_VERSION_4), - &fw_version); + offset = fw_ptp_cfg_offset + IXGBE_FW_PATCH_VERSION_4; + if (hw->eeprom.ops.read(hw, offset, &fw_version)) + goto fw_version_err; if (fw_version > 0x5) status = 0; fw_version_out: return status; + +fw_version_err: + hw_err(hw, "eeprom read at offset %d failed\n", offset); + return IXGBE_ERR_EEPROM_VERSION; } /** @@ -2094,6 +2292,166 @@ static s32 ixgbe_read_eeprom_82599(struct ixgbe_hw *hw, return ret_val; } +/** + * ixgbe_reset_pipeline_82599 - perform pipeline reset + * + * @hw: pointer to hardware structure + * + * Reset pipeline by asserting Restart_AN together with LMS change to ensure + * full pipeline reset. Note - We must hold the SW/FW semaphore before writing + * to AUTOC, so this function assumes the semaphore is held. + **/ +static s32 ixgbe_reset_pipeline_82599(struct ixgbe_hw *hw) +{ + s32 ret_val; + u32 anlp1_reg = 0; + u32 i, autoc_reg, autoc2_reg; + + /* Enable link if disabled in NVM */ + autoc2_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC2); + if (autoc2_reg & IXGBE_AUTOC2_LINK_DISABLE_MASK) { + autoc2_reg &= ~IXGBE_AUTOC2_LINK_DISABLE_MASK; + IXGBE_WRITE_REG(hw, IXGBE_AUTOC2, autoc2_reg); + IXGBE_WRITE_FLUSH(hw); + } + + autoc_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC); + autoc_reg |= IXGBE_AUTOC_AN_RESTART; + + /* Write AUTOC register with toggled LMS[2] bit and Restart_AN */ + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, + autoc_reg ^ (0x4 << IXGBE_AUTOC_LMS_SHIFT)); + + /* Wait for AN to leave state 0 */ + for (i = 0; i < 10; i++) { + usleep_range(4000, 8000); + anlp1_reg = IXGBE_READ_REG(hw, IXGBE_ANLP1); + if (anlp1_reg & IXGBE_ANLP1_AN_STATE_MASK) + break; + } + + if (!(anlp1_reg & IXGBE_ANLP1_AN_STATE_MASK)) { + hw_dbg(hw, "auto negotiation not completed\n"); + ret_val = IXGBE_ERR_RESET_FAILED; + goto reset_pipeline_out; + } + + ret_val = 0; + +reset_pipeline_out: + /* Write AUTOC register with original LMS field and Restart_AN */ + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc_reg); + IXGBE_WRITE_FLUSH(hw); + + return ret_val; +} + +/** + * ixgbe_read_i2c_byte_82599 - Reads 8 bit word over I2C + * @hw: pointer to hardware structure + * @byte_offset: byte offset to read + * @data: value read + * + * Performs byte read operation to SFP module's EEPROM over I2C interface at + * a specified device address. + **/ +static s32 ixgbe_read_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 *data) +{ + u32 esdp; + s32 status; + s32 timeout = 200; + + if (hw->phy.qsfp_shared_i2c_bus == true) { + /* Acquire I2C bus ownership. */ + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + esdp |= IXGBE_ESDP_SDP0; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp); + IXGBE_WRITE_FLUSH(hw); + + while (timeout) { + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + if (esdp & IXGBE_ESDP_SDP1) + break; + + usleep_range(5000, 10000); + timeout--; + } + + if (!timeout) { + hw_dbg(hw, "Driver can't access resource, acquiring I2C bus timeout.\n"); + status = IXGBE_ERR_I2C; + goto release_i2c_access; + } + } + + status = ixgbe_read_i2c_byte_generic(hw, byte_offset, dev_addr, data); + +release_i2c_access: + if (hw->phy.qsfp_shared_i2c_bus == true) { + /* Release I2C bus ownership. */ + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + esdp &= ~IXGBE_ESDP_SDP0; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp); + IXGBE_WRITE_FLUSH(hw); + } + + return status; +} + +/** + * ixgbe_write_i2c_byte_82599 - Writes 8 bit word over I2C + * @hw: pointer to hardware structure + * @byte_offset: byte offset to write + * @data: value to write + * + * Performs byte write operation to SFP module's EEPROM over I2C interface at + * a specified device address. + **/ +static s32 ixgbe_write_i2c_byte_82599(struct ixgbe_hw *hw, u8 byte_offset, + u8 dev_addr, u8 data) +{ + u32 esdp; + s32 status; + s32 timeout = 200; + + if (hw->phy.qsfp_shared_i2c_bus == true) { + /* Acquire I2C bus ownership. */ + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + esdp |= IXGBE_ESDP_SDP0; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp); + IXGBE_WRITE_FLUSH(hw); + + while (timeout) { + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + if (esdp & IXGBE_ESDP_SDP1) + break; + + usleep_range(5000, 10000); + timeout--; + } + + if (!timeout) { + hw_dbg(hw, "Driver can't access resource, acquiring I2C bus timeout.\n"); + status = IXGBE_ERR_I2C; + goto release_i2c_access; + } + } + + status = ixgbe_write_i2c_byte_generic(hw, byte_offset, dev_addr, data); + +release_i2c_access: + if (hw->phy.qsfp_shared_i2c_bus == true) { + /* Release I2C bus ownership. */ + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + esdp &= ~IXGBE_ESDP_SDP0; + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp); + IXGBE_WRITE_FLUSH(hw); + } + + return status; +} + static struct ixgbe_mac_operations mac_ops_82599 = { .init_hw = &ixgbe_init_hw_generic, .reset_hw = &ixgbe_reset_hw_82599, @@ -2102,6 +2460,8 @@ static struct ixgbe_mac_operations mac_ops_82599 = { .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, + .disable_rx_buff = &ixgbe_disable_rx_buff_generic, + .enable_rx_buff = &ixgbe_enable_rx_buff_generic, .get_mac_addr = &ixgbe_get_mac_addr_generic, .get_san_mac_addr = &ixgbe_get_san_mac_addr_generic, .get_device_caps = &ixgbe_get_device_caps_generic, @@ -2111,6 +2471,7 @@ static struct ixgbe_mac_operations mac_ops_82599 = { .set_lan_id = &ixgbe_set_lan_id_multi_port_pcie, .read_analog_reg8 = &ixgbe_read_analog_reg8_82599, .write_analog_reg8 = &ixgbe_write_analog_reg8_82599, + .stop_link_on_d3 = &ixgbe_stop_mac_link_on_d3_82599, .setup_link = &ixgbe_setup_mac_link_82599, .set_rxpba = &ixgbe_set_rxpba_generic, .check_link = &ixgbe_check_mac_link_generic, @@ -2122,6 +2483,7 @@ static struct ixgbe_mac_operations mac_ops_82599 = { .set_rar = &ixgbe_set_rar_generic, .clear_rar = &ixgbe_clear_rar_generic, .set_vmdq = &ixgbe_set_vmdq_generic, + .set_vmdq_san_mac = &ixgbe_set_vmdq_san_mac_generic, .clear_vmdq = &ixgbe_clear_vmdq_generic, .init_rx_addrs = &ixgbe_init_rx_addrs_generic, .update_mc_addr_list = &ixgbe_update_mc_addr_list_generic, @@ -2137,7 +2499,10 @@ static struct ixgbe_mac_operations mac_ops_82599 = { .set_vlan_anti_spoofing = &ixgbe_set_vlan_anti_spoofing, .acquire_swfw_sync = &ixgbe_acquire_swfw_sync, .release_swfw_sync = &ixgbe_release_swfw_sync, - + .get_thermal_sensor_data = &ixgbe_get_thermal_sensor_data_generic, + .init_thermal_sensor_thresh = &ixgbe_init_thermal_sensor_thresh_generic, + .prot_autoc_read = &prot_autoc_read_82599, + .prot_autoc_write = &prot_autoc_write_82599, }; static struct ixgbe_eeprom_operations eeprom_ops_82599 = { @@ -2153,7 +2518,7 @@ static struct ixgbe_eeprom_operations eeprom_ops_82599 = { static struct ixgbe_phy_operations phy_ops_82599 = { .identify = &ixgbe_identify_phy_82599, - .identify_sfp = &ixgbe_identify_sfp_module_generic, + .identify_sfp = &ixgbe_identify_module_generic, .init = &ixgbe_init_phy_ops_82599, .reset = &ixgbe_reset_phy_generic, .read_reg = &ixgbe_read_phy_reg_generic, @@ -2162,6 +2527,7 @@ static struct ixgbe_phy_operations phy_ops_82599 = { .setup_link_speed = &ixgbe_setup_phy_link_speed_generic, .read_i2c_byte = &ixgbe_read_i2c_byte_generic, .write_i2c_byte = &ixgbe_write_i2c_byte_generic, + .read_i2c_sff8472 = &ixgbe_read_i2c_sff8472_generic, .read_i2c_eeprom = &ixgbe_read_i2c_eeprom_generic, .write_i2c_eeprom = &ixgbe_write_i2c_eeprom_generic, .check_overtemp = &ixgbe_tn_check_overtemp, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 383b9413292..4e5385a2a46 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2014 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, @@ -20,6 +20,7 @@ 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 @@ -40,20 +41,13 @@ 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); + 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); @@ -64,6 +58,209 @@ static s32 ixgbe_detect_eeprom_page_size_generic(struct ixgbe_hw *hw, static s32 ixgbe_disable_pcie_master(struct ixgbe_hw *hw); /** + * ixgbe_device_supports_autoneg_fc - Check if phy supports autoneg flow + * control + * @hw: pointer to hardware structure + * + * There are several phys that do not support autoneg flow control. This + * function check the device id to see if the associated phy supports + * autoneg flow control. + **/ +bool ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw) +{ + bool supported = false; + ixgbe_link_speed speed; + bool link_up; + + switch (hw->phy.media_type) { + case ixgbe_media_type_fiber: + hw->mac.ops.check_link(hw, &speed, &link_up, false); + /* if link is down, assume supported */ + if (link_up) + supported = speed == IXGBE_LINK_SPEED_1GB_FULL ? + true : false; + else + supported = true; + break; + case ixgbe_media_type_backplane: + supported = true; + break; + case ixgbe_media_type_copper: + /* only some copper devices support flow control autoneg */ + switch (hw->device_id) { + case IXGBE_DEV_ID_82599_T3_LOM: + case IXGBE_DEV_ID_X540T: + case IXGBE_DEV_ID_X540T1: + supported = true; + break; + default: + break; + } + default: + break; + } + + return supported; +} + +/** + * 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 ret_val = 0; + u32 reg = 0, reg_bp = 0; + u16 reg_cu = 0; + bool locked = false; + + /* + * Validate the requested mode. Strict IEEE mode does not allow + * ixgbe_fc_rx_pause because it will cause us to fail at UNH. + */ + if (hw->fc.strict_ieee && hw->fc.requested_mode == ixgbe_fc_rx_pause) { + hw_dbg(hw, "ixgbe_fc_rx_pause not valid in strict IEEE mode\n"); + 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_backplane: + /* some MAC's need RMW protection on AUTOC */ + ret_val = hw->mac.ops.prot_autoc_read(hw, &locked, ®_bp); + if (ret_val) + goto out; + + /* only backplane uses autoc so fall though */ + case ixgbe_media_type_fiber: + reg = IXGBE_READ_REG(hw, IXGBE_PCS1GANA); + + break; + case ixgbe_media_type_copper: + hw->phy.ops.read_reg(hw, MDIO_AN_ADVERTISE, + MDIO_MMD_AN, ®_cu); + break; + default: + break; + } + + /* + * The possible values of fc.requested_mode are: + * 0: Flow control is completely disabled + * 1: Rx flow control is enabled (we can receive pause frames, + * but not send pause frames). + * 2: Tx flow control is enabled (we can send pause frames but + * we do not support receiving pause frames). + * 3: Both Rx and Tx flow control (symmetric) are enabled. + * other: Invalid. + */ + switch (hw->fc.requested_mode) { + case ixgbe_fc_none: + /* Flow control completely disabled by software override. */ + reg &= ~(IXGBE_PCS1GANA_SYM_PAUSE | IXGBE_PCS1GANA_ASM_PAUSE); + if (hw->phy.media_type == ixgbe_media_type_backplane) + reg_bp &= ~(IXGBE_AUTOC_SYM_PAUSE | + IXGBE_AUTOC_ASM_PAUSE); + else if (hw->phy.media_type == ixgbe_media_type_copper) + reg_cu &= ~(IXGBE_TAF_SYM_PAUSE | IXGBE_TAF_ASM_PAUSE); + break; + case ixgbe_fc_tx_pause: + /* + * Tx Flow control is enabled, and Rx Flow control is + * disabled by software override. + */ + reg |= IXGBE_PCS1GANA_ASM_PAUSE; + reg &= ~IXGBE_PCS1GANA_SYM_PAUSE; + if (hw->phy.media_type == ixgbe_media_type_backplane) { + reg_bp |= IXGBE_AUTOC_ASM_PAUSE; + reg_bp &= ~IXGBE_AUTOC_SYM_PAUSE; + } else if (hw->phy.media_type == ixgbe_media_type_copper) { + reg_cu |= IXGBE_TAF_ASM_PAUSE; + reg_cu &= ~IXGBE_TAF_SYM_PAUSE; + } + break; + case ixgbe_fc_rx_pause: + /* + * Rx Flow control is enabled and Tx Flow control is + * disabled by software override. Since there really + * isn't a way to advertise that we are capable of RX + * Pause ONLY, we will advertise that we support both + * symmetric and asymmetric Rx PAUSE, as such we fall + * through to the fc_full statement. Later, we will + * disable the adapter's ability to send PAUSE frames. + */ + case ixgbe_fc_full: + /* Flow control (both Rx and Tx) is enabled by SW override. */ + reg |= IXGBE_PCS1GANA_SYM_PAUSE | IXGBE_PCS1GANA_ASM_PAUSE; + if (hw->phy.media_type == ixgbe_media_type_backplane) + reg_bp |= IXGBE_AUTOC_SYM_PAUSE | + IXGBE_AUTOC_ASM_PAUSE; + else if (hw->phy.media_type == ixgbe_media_type_copper) + reg_cu |= IXGBE_TAF_SYM_PAUSE | IXGBE_TAF_ASM_PAUSE; + break; + default: + hw_dbg(hw, "Flow control param set incorrectly\n"); + 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) { + /* Need the SW/FW semaphore around AUTOC writes if 82599 and + * LESM is on, likewise reset_pipeline requries the lock as + * it also writes AUTOC. + */ + ret_val = hw->mac.ops.prot_autoc_write(hw, reg_bp, locked); + if (ret_val) + goto out; + + } else if ((hw->phy.media_type == ixgbe_media_type_copper) && + ixgbe_device_supports_autoneg_fc(hw)) { + hw->phy.ops.write_reg(hw, MDIO_AN_ADVERTISE, + MDIO_MMD_AN, reg_cu); + } + + hw_dbg(hw, "Set up FC; IXGBE_AUTOC = 0x%08X\n", reg); +out: + return ret_val; +} + +/** * ixgbe_start_hw_generic - Prepare hardware for Tx/Rx * @hw: pointer to hardware structure * @@ -74,6 +271,7 @@ static s32 ixgbe_disable_pcie_master(struct ixgbe_hw *hw); **/ s32 ixgbe_start_hw_generic(struct ixgbe_hw *hw) { + s32 ret_val; u32 ctrl_ext; /* Set the media type */ @@ -95,12 +293,15 @@ s32 ixgbe_start_hw_generic(struct ixgbe_hw *hw) IXGBE_WRITE_FLUSH(hw); /* Setup flow control */ - ixgbe_setup_fc(hw, 0); + ret_val = ixgbe_setup_fc(hw); + if (!ret_val) + goto out; /* Clear adapter stopped flag */ hw->adapter_stopped = false; - return 0; +out: + return ret_val; } /** @@ -128,14 +329,14 @@ s32 ixgbe_start_hw_gen2(struct ixgbe_hw *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; + regval &= ~IXGBE_DCA_TXCTRL_DESC_WRO_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); + regval &= ~(IXGBE_DCA_RXCTRL_DATA_WRO_EN | + IXGBE_DCA_RXCTRL_HEAD_WRO_EN); IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(i), regval); } @@ -284,7 +485,7 @@ s32 ixgbe_clear_hw_cntrs_generic(struct ixgbe_hw *hw) * 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) + u32 pba_num_size) { s32 ret_val; u16 data; @@ -411,55 +612,55 @@ s32 ixgbe_get_mac_addr_generic(struct ixgbe_hw *hw, u8 *mac_addr) 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) +enum ixgbe_bus_width ixgbe_convert_bus_width(u16 link_status) { - 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; + return ixgbe_bus_width_pcie_x1; case IXGBE_PCI_LINK_WIDTH_2: - hw->bus.width = ixgbe_bus_width_pcie_x2; - break; + return ixgbe_bus_width_pcie_x2; case IXGBE_PCI_LINK_WIDTH_4: - hw->bus.width = ixgbe_bus_width_pcie_x4; - break; + return ixgbe_bus_width_pcie_x4; case IXGBE_PCI_LINK_WIDTH_8: - hw->bus.width = ixgbe_bus_width_pcie_x8; - break; + return ixgbe_bus_width_pcie_x8; default: - hw->bus.width = ixgbe_bus_width_unknown; - break; + return ixgbe_bus_width_unknown; } +} +enum ixgbe_bus_speed ixgbe_convert_bus_speed(u16 link_status) +{ switch (link_status & IXGBE_PCI_LINK_SPEED) { case IXGBE_PCI_LINK_SPEED_2500: - hw->bus.speed = ixgbe_bus_speed_2500; - break; + return ixgbe_bus_speed_2500; case IXGBE_PCI_LINK_SPEED_5000: - hw->bus.speed = ixgbe_bus_speed_5000; - break; + return ixgbe_bus_speed_5000; + case IXGBE_PCI_LINK_SPEED_8000: + return ixgbe_bus_speed_8000; default: - hw->bus.speed = ixgbe_bus_speed_unknown; - break; + return ixgbe_bus_speed_unknown; } +} + +/** + * ixgbe_get_bus_info_generic - Generic set PCI bus info + * @hw: pointer to hardware structure + * + * Sets the PCI bus info (speed, width, type) within the ixgbe_hw structure + **/ +s32 ixgbe_get_bus_info_generic(struct ixgbe_hw *hw) +{ + u16 link_status; + + hw->bus.type = ixgbe_bus_type_pci_express; + + /* Get the negotiated link width and speed from PCI config space */ + link_status = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_LINK_STATUS); + + hw->bus.width = ixgbe_convert_bus_width(link_status); + hw->bus.speed = ixgbe_convert_bus_speed(link_status); - mac->ops.set_lan_id(hw); + hw->mac.ops.set_lan_id(hw); return 0; } @@ -617,9 +818,8 @@ s32 ixgbe_init_eeprom_params_generic(struct ixgbe_hw *hw) 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); + hw_dbg(hw, "Eeprom params: type = %d, size = %d, address bits: %d\n", + eeprom->type, eeprom->word_size, eeprom->address_bits); } return 0; @@ -944,7 +1144,7 @@ s32 ixgbe_read_eerd_buffer_generic(struct ixgbe_hw *hw, u16 offset, } for (i = 0; i < words; i++) { - eerd = ((offset + i) << IXGBE_EEPROM_RW_ADDR_SHIFT) + + eerd = ((offset + i) << IXGBE_EEPROM_RW_ADDR_SHIFT) | IXGBE_EEPROM_RW_REG_START; IXGBE_WRITE_REG(hw, IXGBE_EERD, eerd); @@ -998,7 +1198,7 @@ static s32 ixgbe_detect_eeprom_page_size_generic(struct ixgbe_hw *hw, */ hw->eeprom.word_page_size = IXGBE_EEPROM_PAGE_SIZE_MAX - data[0]; - hw_dbg(hw, "Detected EEPROM page size = %d words.", + hw_dbg(hw, "Detected EEPROM page size = %d words.\n", hw->eeprom.word_page_size); out: return status; @@ -1191,8 +1391,7 @@ static s32 ixgbe_get_eeprom_semaphore(struct ixgbe_hw *hw) } if (i == timeout) { - hw_dbg(hw, "Driver can't access the Eeprom - SMBI Semaphore " - "not granted.\n"); + 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 @@ -1237,14 +1436,12 @@ static s32 ixgbe_get_eeprom_semaphore(struct ixgbe_hw *hw) * 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"); + 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"); + hw_dbg(hw, "Software semaphore SMBI between device drivers not granted.\n"); } return status; @@ -1286,7 +1483,7 @@ static s32 ixgbe_ready_eeprom(struct ixgbe_hw *hw) */ 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); + 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; @@ -1335,7 +1532,7 @@ static void ixgbe_standby_eeprom(struct ixgbe_hw *hw) * @count: number of bits to shift out **/ static void ixgbe_shift_out_eeprom_bits(struct ixgbe_hw *hw, u16 data, - u16 count) + u16 count) { u32 eec; u32 mask; @@ -1539,7 +1736,7 @@ u16 ixgbe_calc_eeprom_checksum_generic(struct ixgbe_hw *hw) * caller does not need checksum_val, the value can be NULL. **/ s32 ixgbe_validate_eeprom_checksum_generic(struct ixgbe_hw *hw, - u16 *checksum_val) + u16 *checksum_val) { s32 status; u16 checksum; @@ -1602,30 +1799,6 @@ s32 ixgbe_update_eeprom_checksum_generic(struct ixgbe_hw *hw) } /** - * 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 @@ -1636,7 +1809,7 @@ s32 ixgbe_validate_mac_addr(u8 *mac_addr) * 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 enable_addr) { u32 rar_low, rar_high; u32 rar_entries = hw->mac.num_rar_entries; @@ -1729,8 +1902,7 @@ s32 ixgbe_init_rx_addrs_generic(struct ixgbe_hw *hw) * 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) { + if (!is_valid_ether_addr(hw->mac.addr)) { /* Get the MAC address from the RAR0 for later reference */ hw->mac.ops.get_mac_addr(hw, hw->mac.addr); @@ -1881,7 +2053,7 @@ s32 ixgbe_update_mc_addr_list_generic(struct ixgbe_hw *hw, if (hw->addr_ctrl.mta_in_use > 0) IXGBE_WRITE_REG(hw, IXGBE_MCSTCTRL, - IXGBE_MCSTCTRL_MFE | hw->mac.mc_filter_type); + IXGBE_MCSTCTRL_MFE | hw->mac.mc_filter_type); hw_dbg(hw, "ixgbe_update_mc_addr_list_generic Complete\n"); return 0; @@ -1899,7 +2071,7 @@ s32 ixgbe_enable_mc_generic(struct ixgbe_hw *hw) if (a->mta_in_use > 0) IXGBE_WRITE_REG(hw, IXGBE_MCSTCTRL, IXGBE_MCSTCTRL_MFE | - hw->mac.mc_filter_type); + hw->mac.mc_filter_type); return 0; } @@ -1923,30 +2095,42 @@ s32 ixgbe_disable_mc_generic(struct ixgbe_hw *hw) /** * 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 ixgbe_fc_enable_generic(struct ixgbe_hw *hw) { s32 ret_val = 0; u32 mflcn_reg, fccfg_reg; u32 reg; u32 fcrtl, fcrth; + int i; -#ifdef CONFIG_DCB - if (hw->fc.requested_mode == ixgbe_fc_pfc) + /* Validate the water mark configuration. */ + if (!hw->fc.pause_time) { + ret_val = IXGBE_ERR_INVALID_LINK_SETTINGS; goto out; + } + + /* Low water mark of zero causes XOFF floods */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + if ((hw->fc.current_mode & ixgbe_fc_tx_pause) && + hw->fc.high_water[i]) { + if (!hw->fc.low_water[i] || + hw->fc.low_water[i] >= hw->fc.high_water[i]) { + hw_dbg(hw, "Invalid water mark configuration\n"); + ret_val = IXGBE_ERR_INVALID_LINK_SETTINGS; + 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; + ixgbe_fc_autoneg(hw); /* Disable any previous flow control settings */ mflcn_reg = IXGBE_READ_REG(hw, IXGBE_MFLCN); - mflcn_reg &= ~(IXGBE_MFLCN_RFCE | IXGBE_MFLCN_RPFCE); + mflcn_reg &= ~(IXGBE_MFLCN_RPFCE_MASK | IXGBE_MFLCN_RFCE); fccfg_reg = IXGBE_READ_REG(hw, IXGBE_FCCFG); fccfg_reg &= ~(IXGBE_FCCFG_TFCE_802_3X | IXGBE_FCCFG_TFCE_PRIORITY); @@ -1959,9 +2143,6 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw, s32 packetbuf_num) * 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) { @@ -1994,11 +2175,6 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw, s32 packetbuf_num) 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; @@ -2011,93 +2187,85 @@ s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw, s32 packetbuf_num) IXGBE_WRITE_REG(hw, IXGBE_MFLCN, mflcn_reg); IXGBE_WRITE_REG(hw, IXGBE_FCCFG, fccfg_reg); - fcrth = hw->fc.high_water[packetbuf_num] << 10; - fcrtl = hw->fc.low_water << 10; + /* Set up and enable Rx high/low water mark thresholds, enable XON. */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + if ((hw->fc.current_mode & ixgbe_fc_tx_pause) && + hw->fc.high_water[i]) { + fcrtl = (hw->fc.low_water[i] << 10) | IXGBE_FCRTL_XONE; + IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(i), fcrtl); + fcrth = (hw->fc.high_water[i] << 10) | IXGBE_FCRTH_FCEN; + } else { + IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(i), 0); + /* + * In order to prevent Tx hangs when the internal Tx + * switch is enabled we must set the high water mark + * to the maximum FCRTH value. This allows the Tx + * switch to function even under heavy Rx workloads. + */ + fcrth = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(i)) - 32; + } - 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(i), fcrth); } - 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); + reg = hw->fc.pause_time * 0x00010001; + for (i = 0; i < (MAX_TRAFFIC_CLASS / 2); i++) + IXGBE_WRITE_REG(hw, IXGBE_FCTTV(i), reg); - IXGBE_WRITE_REG(hw, IXGBE_FCRTV, (hw->fc.pause_time >> 1)); + IXGBE_WRITE_REG(hw, IXGBE_FCRTV, hw->fc.pause_time / 2); out: return ret_val; } /** - * ixgbe_fc_autoneg - Configure flow control + * 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 * - * Compares our advertised flow control capabilities to those advertised by - * our link partner, and determines the proper flow control mode to use. + * Find the intersection between advertised settings and link partner's + * advertised settings **/ -s32 ixgbe_fc_autoneg(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) { - 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; - } + if ((!(adv_reg)) || (!(lp_reg))) + return IXGBE_ERR_FC_NOT_NEGOTIATED; -out: - if (ret_val == 0) { - hw->fc.fc_was_autonegged = true; + 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.fc_was_autonegged = false; - hw->fc.current_mode = hw->fc.requested_mode; + hw->fc.current_mode = ixgbe_fc_none; + hw_dbg(hw, "Flow Control = NONE.\n"); } - return ret_val; + return 0; } /** @@ -2109,7 +2277,7 @@ out: static s32 ixgbe_fc_autoneg_fiber(struct ixgbe_hw *hw) { u32 pcs_anadv_reg, pcs_lpab_reg, linkstat; - s32 ret_val; + s32 ret_val = IXGBE_ERR_FC_NOT_NEGOTIATED; /* * On multispeed fiber at 1g, bail out if @@ -2119,10 +2287,8 @@ static s32 ixgbe_fc_autoneg_fiber(struct ixgbe_hw *hw) 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; + (!!(linkstat & IXGBE_PCS1GLSTA_AN_TIMED_OUT) == 1)) goto out; - } pcs_anadv_reg = IXGBE_READ_REG(hw, IXGBE_PCS1GANA); pcs_lpab_reg = IXGBE_READ_REG(hw, IXGBE_PCS1GANLP); @@ -2146,7 +2312,7 @@ out: static s32 ixgbe_fc_autoneg_backplane(struct ixgbe_hw *hw) { u32 links2, anlp1_reg, autoc_reg, links; - s32 ret_val; + s32 ret_val = IXGBE_ERR_FC_NOT_NEGOTIATED; /* * On backplane, bail out if @@ -2154,21 +2320,13 @@ static s32 ixgbe_fc_autoneg_backplane(struct ixgbe_hw *hw) * - 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; + if ((links & IXGBE_LINKS_KX_AN_COMP) == 0) 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; + if ((links2 & IXGBE_LINKS2_AN_SUPPORTED) == 0) goto out; - } } /* * Read the 10g AN autoc and LP ability registers and resolve @@ -2210,241 +2368,110 @@ static s32 ixgbe_fc_autoneg_copper(struct ixgbe_hw *hw) } /** - * 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 + * ixgbe_fc_autoneg - Configure flow control * @hw: pointer to hardware structure * - * Called at init time to set up flow control. + * Compares our advertised flow control capabilities to those advertised by + * our link partner, and determines the proper flow control mode to use. **/ -static s32 ixgbe_setup_fc(struct ixgbe_hw *hw, s32 packetbuf_num) +void ixgbe_fc_autoneg(struct ixgbe_hw *hw) { - 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; - } + s32 ret_val = IXGBE_ERR_FC_NOT_NEGOTIATED; + ixgbe_link_speed speed; + bool link_up; /* - * Validate the water mark configuration. Zero water marks are invalid - * because it causes the controller to just blast out fc packets. + * AN should have completed when the cable was plugged in. + * Look for reasons to bail out. Bail out if: + * - FC autoneg is disabled, or if + * - link is not up. + * + * Since we're being called from an LSC, link is already known to be up. + * So use link_up_wait_to_complete=false. */ - if (!hw->fc.low_water || - !hw->fc.high_water[packetbuf_num] || - !hw->fc.pause_time) { - hw_dbg(hw, "Invalid water mark configuration\n"); - ret_val = IXGBE_ERR_INVALID_LINK_SETTINGS; + if (hw->fc.disable_fc_autoneg) 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; + hw->mac.ops.check_link(hw, &speed, &link_up, false); + if (!link_up) 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) { + /* 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: - reg = IXGBE_READ_REG(hw, IXGBE_PCS1GANA); - reg_bp = IXGBE_READ_REG(hw, IXGBE_AUTOC); + ret_val = ixgbe_fc_autoneg_backplane(hw); break; + /* Autoneg flow control on copper adapters */ case ixgbe_media_type_copper: - hw->phy.ops.read_reg(hw, MDIO_AN_ADVERTISE, - MDIO_MMD_AN, ®_cu); + if (ixgbe_device_supports_autoneg_fc(hw)) + ret_val = ixgbe_fc_autoneg_copper(hw); break; default: - ; + break; } - /* - * The possible values of fc.requested_mode are: - * 0: Flow control is completely disabled - * 1: Rx flow control is enabled (we can receive pause frames, - * but not send pause frames). - * 2: Tx flow control is enabled (we can send pause frames but - * we do not support receiving pause frames). - * 3: Both Rx and Tx flow control (symmetric) are enabled. -#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); +out: + if (ret_val == 0) { + hw->fc.fc_was_autonegged = true; + } else { + hw->fc.fc_was_autonegged = false; + hw->fc.current_mode = hw->fc.requested_mode; + } +} + +/** + * ixgbe_pcie_timeout_poll - Return number of times to poll for completion + * @hw: pointer to hardware structure + * + * System-wide timeout range is encoded in PCIe Device Control2 register. + * + * Add 10% to specified maximum and return the number of times to poll for + * completion timeout, in units of 100 microsec. Never return less than + * 800 = 80 millisec. + **/ +static u32 ixgbe_pcie_timeout_poll(struct ixgbe_hw *hw) +{ + s16 devctl2; + u32 pollcnt; + + devctl2 = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_DEVICE_CONTROL2); + devctl2 &= IXGBE_PCIDEVCTRL2_TIMEO_MASK; + + switch (devctl2) { + case IXGBE_PCIDEVCTRL2_65_130ms: + pollcnt = 1300; /* 130 millisec */ break; - case ixgbe_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); + case IXGBE_PCIDEVCTRL2_260_520ms: + pollcnt = 5200; /* 520 millisec */ 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); - } + case IXGBE_PCIDEVCTRL2_1_2s: + pollcnt = 20000; /* 2 sec */ 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); + case IXGBE_PCIDEVCTRL2_4_8s: + pollcnt = 80000; /* 8 sec */ break; -#ifdef CONFIG_DCB - case ixgbe_fc_pfc: - goto out; + case IXGBE_PCIDEVCTRL2_17_34s: + pollcnt = 34000; /* 34 sec */ break; -#endif /* CONFIG_DCB */ + case IXGBE_PCIDEVCTRL2_50_100us: /* 100 microsecs */ + case IXGBE_PCIDEVCTRL2_1_2ms: /* 2 millisecs */ + case IXGBE_PCIDEVCTRL2_16_32ms: /* 32 millisec */ + case IXGBE_PCIDEVCTRL2_16_32ms_def: /* 32 millisec default */ default: - hw_dbg(hw, "Flow control param set incorrectly\n"); - ret_val = IXGBE_ERR_CONFIG; - goto out; + pollcnt = 800; /* 80 millisec minimum */ 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; + /* add 10% to spec maximum */ + return (pollcnt * 11) / 10; } /** @@ -2458,16 +2485,16 @@ out: **/ static s32 ixgbe_disable_pcie_master(struct ixgbe_hw *hw) { - struct ixgbe_adapter *adapter = hw->back; s32 status = 0; - u32 i; + u32 i, poll; u16 value; /* Always set this bit to ensure any future transactions are blocked */ IXGBE_WRITE_REG(hw, IXGBE_CTRL, IXGBE_CTRL_GIO_DIS); /* Exit if master requests are blocked */ - if (!(IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_GIO)) + if (!(IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_GIO) || + ixgbe_removed(hw->hw_addr)) goto out; /* Poll for master request bit to clear */ @@ -2492,10 +2519,12 @@ static s32 ixgbe_disable_pcie_master(struct ixgbe_hw *hw) * Before proceeding, make sure that the PCIe block does not have * transactions pending. */ - for (i = 0; i < IXGBE_PCI_MASTER_DISABLE_TIMEOUT; i++) { + poll = ixgbe_pcie_timeout_poll(hw); + for (i = 0; i < poll; i++) { udelay(100); - pci_read_config_word(adapter->pdev, IXGBE_PCI_DEVICE_STATUS, - &value); + value = ixgbe_read_pci_cfg_word(hw, IXGBE_PCI_DEVICE_STATUS); + if (ixgbe_removed(hw->hw_addr)) + goto out; if (!(value & IXGBE_PCI_DEVICE_STATUS_TRANSACTION_PENDING)) goto out; } @@ -2517,42 +2546,39 @@ out: **/ s32 ixgbe_acquire_swfw_sync(struct ixgbe_hw *hw, u16 mask) { - u32 gssr; + u32 gssr = 0; u32 swmask = mask; u32 fwmask = mask << 5; - s32 timeout = 200; + u32 timeout = 200; + u32 i; - while (timeout) { + for (i = 0; i < timeout; i++) { /* - * SW EEPROM semaphore bit is used for access to all - * SW_FW_SYNC/GSSR bits (not just EEPROM) + * SW NVM semaphore bit is used for access to all + * SW_FW_SYNC bits (not just NVM) */ if (ixgbe_get_eeprom_semaphore(hw)) return IXGBE_ERR_SWFW_SYNC; gssr = IXGBE_READ_REG(hw, IXGBE_GSSR); - if (!(gssr & (fwmask | swmask))) - 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; + if (!(gssr & (fwmask | swmask))) { + gssr |= swmask; + IXGBE_WRITE_REG(hw, IXGBE_GSSR, gssr); + ixgbe_release_eeprom_semaphore(hw); + return 0; + } else { + /* Resource is currently in use by FW or SW */ + ixgbe_release_eeprom_semaphore(hw); + usleep_range(5000, 10000); + } } - gssr |= swmask; - IXGBE_WRITE_REG(hw, IXGBE_GSSR, gssr); + /* If time expired clear the bits holding the lock and retry */ + if (gssr & (fwmask | swmask)) + ixgbe_release_swfw_sync(hw, gssr & (fwmask | swmask)); - ixgbe_release_eeprom_semaphore(hw); - return 0; + usleep_range(5000, 10000); + return IXGBE_ERR_SWFW_SYNC; } /** @@ -2578,6 +2604,86 @@ void ixgbe_release_swfw_sync(struct ixgbe_hw *hw, u16 mask) } /** + * prot_autoc_read_generic - Hides MAC differences needed for AUTOC read + * @hw: pointer to hardware structure + * @reg_val: Value we read from AUTOC + * @locked: bool to indicate whether the SW/FW lock should be taken. Never + * true in this the generic case. + * + * The default case requires no protection so just to the register read. + **/ +s32 prot_autoc_read_generic(struct ixgbe_hw *hw, bool *locked, u32 *reg_val) +{ + *locked = false; + *reg_val = IXGBE_READ_REG(hw, IXGBE_AUTOC); + return 0; +} + +/** + * prot_autoc_write_generic - Hides MAC differences needed for AUTOC write + * @hw: pointer to hardware structure + * @reg_val: value to write to AUTOC + * @locked: bool to indicate whether the SW/FW lock was already taken by + * previous read. + **/ +s32 prot_autoc_write_generic(struct ixgbe_hw *hw, u32 reg_val, bool locked) +{ + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, reg_val); + return 0; +} + +/** + * ixgbe_disable_rx_buff_generic - Stops the receive data path + * @hw: pointer to hardware structure + * + * Stops the receive data path and waits for the HW to internally + * empty the Rx security block. + **/ +s32 ixgbe_disable_rx_buff_generic(struct ixgbe_hw *hw) +{ +#define IXGBE_MAX_SECRX_POLL 40 + int i; + int secrxreg; + + secrxreg = IXGBE_READ_REG(hw, IXGBE_SECRXCTRL); + secrxreg |= IXGBE_SECRXCTRL_RX_DIS; + IXGBE_WRITE_REG(hw, IXGBE_SECRXCTRL, secrxreg); + for (i = 0; i < IXGBE_MAX_SECRX_POLL; i++) { + secrxreg = IXGBE_READ_REG(hw, IXGBE_SECRXSTAT); + if (secrxreg & IXGBE_SECRXSTAT_SECRX_RDY) + break; + else + /* Use interrupt-safe sleep just in case */ + udelay(1000); + } + + /* For informational purposes only */ + if (i >= IXGBE_MAX_SECRX_POLL) + hw_dbg(hw, "Rx unit being enabled before security path fully disabled. Continuing with init.\n"); + + return 0; + +} + +/** + * ixgbe_enable_rx_buff - Enables the receive data path + * @hw: pointer to hardware structure + * + * Enables the receive data path + **/ +s32 ixgbe_enable_rx_buff_generic(struct ixgbe_hw *hw) +{ + int secrxreg; + + secrxreg = IXGBE_READ_REG(hw, IXGBE_SECRXCTRL); + secrxreg &= ~IXGBE_SECRXCTRL_RX_DIS; + IXGBE_WRITE_REG(hw, IXGBE_SECRXCTRL, secrxreg); + IXGBE_WRITE_FLUSH(hw); + + return 0; +} + +/** * ixgbe_enable_rx_dma_generic - Enable the Rx DMA unit * @hw: pointer to hardware structure * @regval: register value to write to RXCTRL @@ -2602,6 +2708,8 @@ s32 ixgbe_blink_led_start_generic(struct ixgbe_hw *hw, u32 index) bool link_up = false; u32 autoc_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC); u32 led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); + s32 ret_val = 0; + bool locked = false; /* * Link must be up to auto-blink the LEDs; @@ -2610,10 +2718,19 @@ s32 ixgbe_blink_led_start_generic(struct ixgbe_hw *hw, u32 index) hw->mac.ops.check_link(hw, &speed, &link_up, false); if (!link_up) { + ret_val = hw->mac.ops.prot_autoc_read(hw, &locked, &autoc_reg); + if (ret_val) + goto out; + autoc_reg |= IXGBE_AUTOC_AN_RESTART; autoc_reg |= IXGBE_AUTOC_FLU; - IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc_reg); + + ret_val = hw->mac.ops.prot_autoc_write(hw, autoc_reg, locked); + if (ret_val) + goto out; + IXGBE_WRITE_FLUSH(hw); + usleep_range(10000, 20000); } @@ -2622,7 +2739,8 @@ s32 ixgbe_blink_led_start_generic(struct ixgbe_hw *hw, u32 index) IXGBE_WRITE_REG(hw, IXGBE_LEDCTL, led_reg); IXGBE_WRITE_FLUSH(hw); - return 0; +out: + return ret_val; } /** @@ -2632,12 +2750,21 @@ s32 ixgbe_blink_led_start_generic(struct ixgbe_hw *hw, u32 index) **/ s32 ixgbe_blink_led_stop_generic(struct ixgbe_hw *hw, u32 index) { - u32 autoc_reg = IXGBE_READ_REG(hw, IXGBE_AUTOC); + u32 autoc_reg = 0; u32 led_reg = IXGBE_READ_REG(hw, IXGBE_LEDCTL); + s32 ret_val = 0; + bool locked = false; + + ret_val = hw->mac.ops.prot_autoc_read(hw, &locked, &autoc_reg); + if (ret_val) + goto out; autoc_reg &= ~IXGBE_AUTOC_FLU; autoc_reg |= IXGBE_AUTOC_AN_RESTART; - IXGBE_WRITE_REG(hw, IXGBE_AUTOC, autoc_reg); + + ret_val = hw->mac.ops.prot_autoc_write(hw, autoc_reg, locked); + if (ret_val) + goto out; led_reg &= ~IXGBE_LED_MODE_MASK(index); led_reg &= ~IXGBE_LED_BLINK(index); @@ -2645,7 +2772,8 @@ s32 ixgbe_blink_led_stop_generic(struct ixgbe_hw *hw, u32 index) IXGBE_WRITE_REG(hw, IXGBE_LEDCTL, led_reg); IXGBE_WRITE_FLUSH(hw); - return 0; +out: + return ret_val; } /** @@ -2658,15 +2786,21 @@ s32 ixgbe_blink_led_stop_generic(struct ixgbe_hw *hw, u32 index) * get and set mac_addr routines. **/ static s32 ixgbe_get_san_mac_addr_offset(struct ixgbe_hw *hw, - u16 *san_mac_offset) + u16 *san_mac_offset) { + s32 ret_val; + /* * 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); + ret_val = hw->eeprom.ops.read(hw, IXGBE_SAN_MAC_ADDR_PTR, + san_mac_offset); + if (ret_val) + hw_err(hw, "eeprom read at offset %d failed\n", + IXGBE_SAN_MAC_ADDR_PTR); - return 0; + return ret_val; } /** @@ -2683,38 +2817,43 @@ s32 ixgbe_get_san_mac_addr_generic(struct ixgbe_hw *hw, u8 *san_mac_addr) { u16 san_mac_data, san_mac_offset; u8 i; + s32 ret_val; /* * First read the EEPROM pointer to see if the MAC addresses are * available. If they're not, no point in calling set_lan_id() here. */ - ixgbe_get_san_mac_addr_offset(hw, &san_mac_offset); + ret_val = ixgbe_get_san_mac_addr_offset(hw, &san_mac_offset); + if (ret_val || san_mac_offset == 0 || san_mac_offset == 0xFFFF) - 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; - } + goto san_mac_addr_clr; /* make sure we know which port we need to program */ hw->mac.ops.set_lan_id(hw); /* apply the port offset to the address offset */ (hw->bus.func) ? (san_mac_offset += IXGBE_SAN_MAC_ADDR_PORT1_OFFSET) : - (san_mac_offset += IXGBE_SAN_MAC_ADDR_PORT0_OFFSET); + (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); + ret_val = hw->eeprom.ops.read(hw, san_mac_offset, + &san_mac_data); + if (ret_val) { + hw_err(hw, "eeprom read at offset %d failed\n", + san_mac_offset); + goto san_mac_addr_clr; + } san_mac_addr[i * 2] = (u8)(san_mac_data); san_mac_addr[i * 2 + 1] = (u8)(san_mac_data >> 8); san_mac_offset++; } - -san_mac_addr_out: return 0; + +san_mac_addr_clr: + /* No addresses available in this EEPROM. It's not necessarily an + * error though, so just wipe the local address and return. + */ + for (i = 0; i < 6; i++) + san_mac_addr[i] = 0xFF; + return ret_val; } /** @@ -2724,17 +2863,37 @@ san_mac_addr_out: * 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) +u16 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); + u16 msix_count = 1; + u16 max_msix_count; + u16 pcie_offset; + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + pcie_offset = IXGBE_PCIE_MSIX_82598_CAPS; + max_msix_count = IXGBE_MAX_MSIX_VECTORS_82598; + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + pcie_offset = IXGBE_PCIE_MSIX_82599_CAPS; + max_msix_count = IXGBE_MAX_MSIX_VECTORS_82599; + break; + default: + return msix_count; + } + + msix_count = ixgbe_read_pci_cfg_word(hw, pcie_offset); + if (ixgbe_removed(hw->hw_addr)) + msix_count = 0; msix_count &= IXGBE_PCIE_MSIX_TBL_SZ_MASK; - /* MSI-X count is zero-based in HW, so increment to give proper value */ + /* MSI-X count is zero-based in HW */ msix_count++; + if (msix_count > max_msix_count) + msix_count = max_msix_count; + return msix_count; } @@ -2758,6 +2917,9 @@ s32 ixgbe_clear_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq) mpsar_lo = IXGBE_READ_REG(hw, IXGBE_MPSAR_LO(rar)); mpsar_hi = IXGBE_READ_REG(hw, IXGBE_MPSAR_HI(rar)); + if (ixgbe_removed(hw->hw_addr)) + goto done; + if (!mpsar_lo && !mpsar_hi) goto done; @@ -2815,6 +2977,31 @@ s32 ixgbe_set_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq) } /** + * This function should only be involved in the IOV mode. + * In IOV mode, Default pool is next pool after the number of + * VFs advertized and not 0. + * MPSAR table needs to be updated for SAN_MAC RAR [hw->mac.san_mac_rar_index] + * + * ixgbe_set_vmdq_san_mac - Associate default VMDq pool index with a rx address + * @hw: pointer to hardware struct + * @vmdq: VMDq pool index + **/ +s32 ixgbe_set_vmdq_san_mac_generic(struct ixgbe_hw *hw, u32 vmdq) +{ + u32 rar = hw->mac.san_mac_rar_index; + + if (vmdq < 32) { + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_LO(rar), 1 << vmdq); + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_HI(rar), 0); + } else { + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_LO(rar), 0); + IXGBE_WRITE_REG(hw, IXGBE_MPSAR_HI(rar), 1 << (vmdq - 32)); + } + + return 0; +} + +/** * ixgbe_init_uta_tables_generic - Initialize the Unicast Table Array * @hw: pointer to hardware structure **/ @@ -2885,7 +3072,7 @@ static s32 ixgbe_find_vlvf_slot(struct ixgbe_hw *hw, u32 vlan) * Turn on/off specified VLAN in the VLAN filter table. **/ s32 ixgbe_set_vfta_generic(struct ixgbe_hw *hw, u32 vlan, u32 vind, - bool vlan_on) + bool vlan_on) { s32 regindex; u32 bitindex; @@ -3007,9 +3194,9 @@ s32 ixgbe_set_vfta_generic(struct ixgbe_hw *hw, u32 vlan, u32 vind, * Ignore it. */ vfta_changed = false; } - } - else + } else { IXGBE_WRITE_REG(hw, IXGBE_VLVF(vlvf_index), 0); + } } if (vfta_changed) @@ -3099,7 +3286,7 @@ s32 ixgbe_check_mac_link_generic(struct ixgbe_hw *hw, ixgbe_link_speed *speed, } /** - * ixgbe_get_wwn_prefix_generic Get alternative WWNN/WWPN prefix from + * ixgbe_get_wwn_prefix_generic - Get alternative WWNN/WWPN prefix from * the EEPROM * @hw: pointer to hardware structure * @wwnn_prefix: the alternative WWNN prefix @@ -3109,7 +3296,7 @@ s32 ixgbe_check_mac_link_generic(struct ixgbe_hw *hw, ixgbe_link_speed *speed, * 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 *wwpn_prefix) { u16 offset, caps; u16 alt_san_mac_blk_offset; @@ -3119,8 +3306,9 @@ s32 ixgbe_get_wwn_prefix_generic(struct ixgbe_hw *hw, u16 *wwnn_prefix, *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); + offset = IXGBE_ALT_SAN_MAC_ADDR_BLK_PTR; + if (hw->eeprom.ops.read(hw, offset, &alt_san_mac_blk_offset)) + goto wwn_prefix_err; if ((alt_san_mac_blk_offset == 0) || (alt_san_mac_blk_offset == 0xFFFF)) @@ -3128,41 +3316,26 @@ s32 ixgbe_get_wwn_prefix_generic(struct ixgbe_hw *hw, u16 *wwnn_prefix, /* 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 (hw->eeprom.ops.read(hw, offset, &caps)) + goto wwn_prefix_err; 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); + if (hw->eeprom.ops.read(hw, offset, wwnn_prefix)) + hw_err(hw, "eeprom read at offset %d failed\n", offset); offset = alt_san_mac_blk_offset + IXGBE_ALT_SAN_MAC_ADDR_WWPN_OFFSET; - hw->eeprom.ops.read(hw, offset, wwpn_prefix); + if (hw->eeprom.ops.read(hw, offset, wwpn_prefix)) + goto wwn_prefix_err; 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; - } +wwn_prefix_err: + hw_err(hw, "eeprom read at offset %d failed\n", offset); + return 0; } /** @@ -3189,20 +3362,22 @@ void ixgbe_set_mac_anti_spoofing(struct ixgbe_hw *hw, bool enable, int pf) * 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++) + for (j = 0; j < pf_target_reg; 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 + * emulation mode NICs. Do not set the bits assigned to the PF + */ + pfvfspoof &= (1 << pf_target_shift) - 1; + IXGBE_WRITE_REG(hw, IXGBE_PFVFSPOOF(j), pfvfspoof); + + /* + * Remaining pools belong to the PF so they do not need to have + * anti-spoofing enabled. */ - 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); + for (j++; j < IXGBE_PFVFSPOOF_REG_COUNT; j++) + IXGBE_WRITE_REG(hw, IXGBE_PFVFSPOOF(j), 0); } /** @@ -3314,6 +3489,7 @@ void ixgbe_set_rxpba_generic(struct ixgbe_hw *hw, * 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. **/ @@ -3336,7 +3512,7 @@ static u8 ixgbe_calculate_checksum(u8 *buffer, u32 length) * @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 + * @length: length of buffer, must be multiple of 4 bytes * * Communicates with the manageability block. On success return 0 * else return IXGBE_ERR_HOST_INTERFACE_COMMAND. @@ -3526,3 +3702,176 @@ void ixgbe_clear_tx_pending(struct ixgbe_hw *hw) IXGBE_WRITE_REG(hw, IXGBE_GCR_EXT, gcr_ext); IXGBE_WRITE_REG(hw, IXGBE_HLREG0, hlreg0); } + +static const u8 ixgbe_emc_temp_data[4] = { + IXGBE_EMC_INTERNAL_DATA, + IXGBE_EMC_DIODE1_DATA, + IXGBE_EMC_DIODE2_DATA, + IXGBE_EMC_DIODE3_DATA +}; +static const u8 ixgbe_emc_therm_limit[4] = { + IXGBE_EMC_INTERNAL_THERM_LIMIT, + IXGBE_EMC_DIODE1_THERM_LIMIT, + IXGBE_EMC_DIODE2_THERM_LIMIT, + IXGBE_EMC_DIODE3_THERM_LIMIT +}; + +/** + * ixgbe_get_ets_data - Extracts the ETS bit data + * @hw: pointer to hardware structure + * @ets_cfg: extected ETS data + * @ets_offset: offset of ETS data + * + * Returns error code. + **/ +static s32 ixgbe_get_ets_data(struct ixgbe_hw *hw, u16 *ets_cfg, + u16 *ets_offset) +{ + s32 status = 0; + + status = hw->eeprom.ops.read(hw, IXGBE_ETS_CFG, ets_offset); + if (status) + goto out; + + if ((*ets_offset == 0x0000) || (*ets_offset == 0xFFFF)) { + status = IXGBE_NOT_IMPLEMENTED; + goto out; + } + + status = hw->eeprom.ops.read(hw, *ets_offset, ets_cfg); + if (status) + goto out; + + if ((*ets_cfg & IXGBE_ETS_TYPE_MASK) != IXGBE_ETS_TYPE_EMC_SHIFTED) { + status = IXGBE_NOT_IMPLEMENTED; + goto out; + } + +out: + return status; +} + +/** + * ixgbe_get_thermal_sensor_data - Gathers thermal sensor data + * @hw: pointer to hardware structure + * + * Returns the thermal sensor data structure + **/ +s32 ixgbe_get_thermal_sensor_data_generic(struct ixgbe_hw *hw) +{ + s32 status = 0; + u16 ets_offset; + u16 ets_cfg; + u16 ets_sensor; + u8 num_sensors; + u8 i; + struct ixgbe_thermal_sensor_data *data = &hw->mac.thermal_sensor_data; + + /* Only support thermal sensors attached to physical port 0 */ + if ((IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_LAN_ID_1)) { + status = IXGBE_NOT_IMPLEMENTED; + goto out; + } + + status = ixgbe_get_ets_data(hw, &ets_cfg, &ets_offset); + if (status) + goto out; + + num_sensors = (ets_cfg & IXGBE_ETS_NUM_SENSORS_MASK); + if (num_sensors > IXGBE_MAX_SENSORS) + num_sensors = IXGBE_MAX_SENSORS; + + for (i = 0; i < num_sensors; i++) { + u8 sensor_index; + u8 sensor_location; + + status = hw->eeprom.ops.read(hw, (ets_offset + 1 + i), + &ets_sensor); + if (status) + goto out; + + sensor_index = ((ets_sensor & IXGBE_ETS_DATA_INDEX_MASK) >> + IXGBE_ETS_DATA_INDEX_SHIFT); + sensor_location = ((ets_sensor & IXGBE_ETS_DATA_LOC_MASK) >> + IXGBE_ETS_DATA_LOC_SHIFT); + + if (sensor_location != 0) { + status = hw->phy.ops.read_i2c_byte(hw, + ixgbe_emc_temp_data[sensor_index], + IXGBE_I2C_THERMAL_SENSOR_ADDR, + &data->sensor[i].temp); + if (status) + goto out; + } + } +out: + return status; +} + +/** + * ixgbe_init_thermal_sensor_thresh_generic - Inits thermal sensor thresholds + * @hw: pointer to hardware structure + * + * Inits the thermal sensor thresholds according to the NVM map + * and save off the threshold and location values into mac.thermal_sensor_data + **/ +s32 ixgbe_init_thermal_sensor_thresh_generic(struct ixgbe_hw *hw) +{ + s32 status = 0; + u16 ets_offset; + u16 ets_cfg; + u16 ets_sensor; + u8 low_thresh_delta; + u8 num_sensors; + u8 therm_limit; + u8 i; + struct ixgbe_thermal_sensor_data *data = &hw->mac.thermal_sensor_data; + + memset(data, 0, sizeof(struct ixgbe_thermal_sensor_data)); + + /* Only support thermal sensors attached to physical port 0 */ + if ((IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_LAN_ID_1)) { + status = IXGBE_NOT_IMPLEMENTED; + goto out; + } + + status = ixgbe_get_ets_data(hw, &ets_cfg, &ets_offset); + if (status) + goto out; + + low_thresh_delta = ((ets_cfg & IXGBE_ETS_LTHRES_DELTA_MASK) >> + IXGBE_ETS_LTHRES_DELTA_SHIFT); + num_sensors = (ets_cfg & IXGBE_ETS_NUM_SENSORS_MASK); + if (num_sensors > IXGBE_MAX_SENSORS) + num_sensors = IXGBE_MAX_SENSORS; + + for (i = 0; i < num_sensors; i++) { + u8 sensor_index; + u8 sensor_location; + + if (hw->eeprom.ops.read(hw, ets_offset + 1 + i, &ets_sensor)) { + hw_err(hw, "eeprom read at offset %d failed\n", + ets_offset + 1 + i); + continue; + } + sensor_index = ((ets_sensor & IXGBE_ETS_DATA_INDEX_MASK) >> + IXGBE_ETS_DATA_INDEX_SHIFT); + sensor_location = ((ets_sensor & IXGBE_ETS_DATA_LOC_MASK) >> + IXGBE_ETS_DATA_LOC_SHIFT); + therm_limit = ets_sensor & IXGBE_ETS_DATA_HTHRESH_MASK; + + hw->phy.ops.write_i2c_byte(hw, + ixgbe_emc_therm_limit[sensor_index], + IXGBE_I2C_THERMAL_SENSOR_ADDR, therm_limit); + + if (sensor_location == 0) + continue; + + data->sensor[i].location = sensor_location; + data->sensor[i].caution_thresh = therm_limit; + data->sensor[i].max_op_thresh = therm_limit - low_thresh_delta; + } +out: + return status; +} + diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h index 2c834c46bba..2ae5d4b8fc9 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2014 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, @@ -20,6 +20,7 @@ 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 @@ -31,15 +32,17 @@ #include "ixgbe_type.h" #include "ixgbe.h" -u32 ixgbe_get_pcie_msix_count_generic(struct ixgbe_hw *hw); +u16 ixgbe_get_pcie_msix_count_generic(struct ixgbe_hw *hw); s32 ixgbe_init_ops_generic(struct ixgbe_hw *hw); s32 ixgbe_init_hw_generic(struct ixgbe_hw *hw); s32 ixgbe_start_hw_generic(struct ixgbe_hw *hw); s32 ixgbe_start_hw_gen2(struct ixgbe_hw *hw); s32 ixgbe_clear_hw_cntrs_generic(struct ixgbe_hw *hw); s32 ixgbe_read_pba_string_generic(struct ixgbe_hw *hw, u8 *pba_num, - u32 pba_num_size); + u32 pba_num_size); s32 ixgbe_get_mac_addr_generic(struct ixgbe_hw *hw, u8 *mac_addr); +enum ixgbe_bus_width ixgbe_convert_bus_width(u16 link_status); +enum ixgbe_bus_speed ixgbe_convert_bus_speed(u16 link_status); s32 ixgbe_get_bus_info_generic(struct ixgbe_hw *hw); void ixgbe_set_lan_id_multi_port_pcie(struct ixgbe_hw *hw); s32 ixgbe_stop_adapter_generic(struct ixgbe_hw *hw); @@ -58,41 +61,48 @@ 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); + 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); + 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); + u32 enable_addr); s32 ixgbe_clear_rar_generic(struct ixgbe_hw *hw, u32 index); s32 ixgbe_init_rx_addrs_generic(struct ixgbe_hw *hw); s32 ixgbe_update_mc_addr_list_generic(struct ixgbe_hw *hw, struct net_device *netdev); s32 ixgbe_enable_mc_generic(struct ixgbe_hw *hw); s32 ixgbe_disable_mc_generic(struct ixgbe_hw *hw); +s32 ixgbe_disable_rx_buff_generic(struct ixgbe_hw *hw); +s32 ixgbe_enable_rx_buff_generic(struct ixgbe_hw *hw); s32 ixgbe_enable_rx_dma_generic(struct ixgbe_hw *hw, u32 regval); -s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw, s32 packetbuf_num); -s32 ixgbe_fc_autoneg(struct ixgbe_hw *hw); +s32 ixgbe_fc_enable_generic(struct ixgbe_hw *hw); +bool ixgbe_device_supports_autoneg_fc(struct ixgbe_hw *hw); +void 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_get_san_mac_addr_generic(struct ixgbe_hw *hw, u8 *san_mac_addr); s32 ixgbe_set_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq); +s32 ixgbe_set_vmdq_san_mac_generic(struct ixgbe_hw *hw, u32 vmdq); s32 ixgbe_clear_vmdq_generic(struct ixgbe_hw *hw, u32 rar, u32 vmdq); s32 ixgbe_init_uta_tables_generic(struct ixgbe_hw *hw); s32 ixgbe_set_vfta_generic(struct ixgbe_hw *hw, u32 vlan, - u32 vind, bool vlan_on); + 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); + 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); + u16 *wwpn_prefix); + +s32 prot_autoc_read_generic(struct ixgbe_hw *hw, bool *, u32 *reg_val); +s32 prot_autoc_write_generic(struct ixgbe_hw *hw, u32 reg_val, bool locked); + s32 ixgbe_blink_led_start_generic(struct ixgbe_hw *hw, u32 index); s32 ixgbe_blink_led_stop_generic(struct ixgbe_hw *hw, u32 index); void ixgbe_set_mac_anti_spoofing(struct ixgbe_hw *hw, bool enable, int pf); @@ -101,31 +111,82 @@ 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_clear_tx_pending(struct ixgbe_hw *hw); +bool ixgbe_mng_enabled(struct ixgbe_hw *hw); void ixgbe_set_rxpba_generic(struct ixgbe_hw *hw, int num_pb, u32 headroom, int strategy); -#define IXGBE_WRITE_REG(a, reg, value) writel((value), ((a)->hw_addr + (reg))) +#define IXGBE_I2C_THERMAL_SENSOR_ADDR 0xF8 +#define IXGBE_EMC_INTERNAL_DATA 0x00 +#define IXGBE_EMC_INTERNAL_THERM_LIMIT 0x20 +#define IXGBE_EMC_DIODE1_DATA 0x01 +#define IXGBE_EMC_DIODE1_THERM_LIMIT 0x19 +#define IXGBE_EMC_DIODE2_DATA 0x23 +#define IXGBE_EMC_DIODE2_THERM_LIMIT 0x1A +#define IXGBE_EMC_DIODE3_DATA 0x2A +#define IXGBE_EMC_DIODE3_THERM_LIMIT 0x30 + +s32 ixgbe_get_thermal_sensor_data_generic(struct ixgbe_hw *hw); +s32 ixgbe_init_thermal_sensor_thresh_generic(struct ixgbe_hw *hw); + +#define IXGBE_FAILED_READ_REG 0xffffffffU +#define IXGBE_FAILED_READ_CFG_DWORD 0xffffffffU +#define IXGBE_FAILED_READ_CFG_WORD 0xffffU + +u16 ixgbe_read_pci_cfg_word(struct ixgbe_hw *hw, u32 reg); +void ixgbe_write_pci_cfg_word(struct ixgbe_hw *hw, u32 reg, u16 value); + +static inline bool ixgbe_removed(void __iomem *addr) +{ + return unlikely(!addr); +} + +static inline void ixgbe_write_reg(struct ixgbe_hw *hw, u32 reg, u32 value) +{ + u8 __iomem *reg_addr = ACCESS_ONCE(hw->hw_addr); + + if (ixgbe_removed(reg_addr)) + return; + writel(value, reg_addr + reg); +} +#define IXGBE_WRITE_REG(a, reg, value) ixgbe_write_reg((a), (reg), (value)) #ifndef writeq -#define writeq(val, addr) writel((u32) (val), addr); \ - writel((u32) (val >> 32), (addr + 4)); +#define writeq writeq +static inline void writeq(u64 val, void __iomem *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))) +static inline void ixgbe_write_reg64(struct ixgbe_hw *hw, u32 reg, u64 value) +{ + u8 __iomem *reg_addr = ACCESS_ONCE(hw->hw_addr); + + if (ixgbe_removed(reg_addr)) + return; + writeq(value, reg_addr + reg); +} +#define IXGBE_WRITE_REG64(a, reg, value) ixgbe_write_reg64((a), (reg), (value)) + +u32 ixgbe_read_reg(struct ixgbe_hw *hw, u32 reg); +#define IXGBE_READ_REG(a, reg) ixgbe_read_reg((a), (reg)) -#define IXGBE_READ_REG(a, reg) readl((a)->hw_addr + (reg)) +#define IXGBE_WRITE_REG_ARRAY(a, reg, offset, value) \ + ixgbe_write_reg((a), (reg) + ((offset) << 2), (value)) -#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) \ + ixgbe_read_reg((a), (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 IXGBE_WRITE_FLUSH(a) IXGBE_READ_REG(a, IXGBE_STATUS) +#define ixgbe_hw_to_netdev(hw) (((struct ixgbe_adapter *)(hw)->back)->netdev) #define hw_dbg(hw, format, arg...) \ - netdev_dbg(((struct ixgbe_adapter *)(hw->back))->netdev, format, ##arg) + netdev_dbg(ixgbe_hw_to_netdev(hw), format, ## arg) +#define hw_err(hw, format, arg...) \ + netdev_err(ixgbe_hw_to_netdev(hw), format, ## arg) #define e_dev_info(format, arg...) \ dev_info(&adapter->pdev->dev, format, ## arg) #define e_dev_warn(format, arg...) \ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.c index 8bfaaee5ac5..a689ee0d4be 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2013 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, @@ -180,67 +180,83 @@ out: void ixgbe_dcb_unpack_pfc(struct ixgbe_dcb_config *cfg, u8 *pfc_en) { - int i; + struct tc_configuration *tc_config = &cfg->tc_config[0]; + int tc; - *pfc_en = 0; - for (i = 0; i < MAX_TRAFFIC_CLASS; i++) - *pfc_en |= !!(cfg->tc_config[i].dcb_pfc & 0xF) << i; + for (*pfc_en = 0, tc = 0; tc < MAX_TRAFFIC_CLASS; tc++) { + if (tc_config[tc].dcb_pfc != pfc_disabled) + *pfc_en |= 1 << tc; + } } void ixgbe_dcb_unpack_refill(struct ixgbe_dcb_config *cfg, int direction, u16 *refill) { - struct tc_bw_alloc *p; - int i; + struct tc_configuration *tc_config = &cfg->tc_config[0]; + int tc; - for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { - p = &cfg->tc_config[i].path[direction]; - refill[i] = p->data_credits_refill; - } + for (tc = 0; tc < MAX_TRAFFIC_CLASS; tc++) + refill[tc] = tc_config[tc].path[direction].data_credits_refill; } void ixgbe_dcb_unpack_max(struct ixgbe_dcb_config *cfg, u16 *max) { - int i; + struct tc_configuration *tc_config = &cfg->tc_config[0]; + int tc; - for (i = 0; i < MAX_TRAFFIC_CLASS; i++) - max[i] = cfg->tc_config[i].desc_credits_max; + for (tc = 0; tc < MAX_TRAFFIC_CLASS; tc++) + max[tc] = tc_config[tc].desc_credits_max; } void ixgbe_dcb_unpack_bwgid(struct ixgbe_dcb_config *cfg, int direction, u8 *bwgid) { - struct tc_bw_alloc *p; - int i; + struct tc_configuration *tc_config = &cfg->tc_config[0]; + int tc; - for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { - p = &cfg->tc_config[i].path[direction]; - bwgid[i] = p->bwg_id; - } + for (tc = 0; tc < MAX_TRAFFIC_CLASS; tc++) + bwgid[tc] = tc_config[tc].path[direction].bwg_id; } void ixgbe_dcb_unpack_prio(struct ixgbe_dcb_config *cfg, int direction, u8 *ptype) { - struct tc_bw_alloc *p; - int i; + struct tc_configuration *tc_config = &cfg->tc_config[0]; + int tc; - for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { - p = &cfg->tc_config[i].path[direction]; - ptype[i] = p->prio_type; + for (tc = 0; tc < MAX_TRAFFIC_CLASS; tc++) + ptype[tc] = tc_config[tc].path[direction].prio_type; +} + +u8 ixgbe_dcb_get_tc_from_up(struct ixgbe_dcb_config *cfg, int direction, u8 up) +{ + struct tc_configuration *tc_config = &cfg->tc_config[0]; + u8 prio_mask = 1 << up; + u8 tc = cfg->num_tcs.pg_tcs; + + /* If tc is 0 then DCB is likely not enabled or supported */ + if (!tc) + goto out; + + /* + * Test from maximum TC to 1 and report the first match we find. If + * we find no match we can assume that the TC is 0 since the TC must + * be set for all user priorities + */ + for (tc--; tc; tc--) { + if (prio_mask & tc_config[tc].path[direction].up_to_tc_bitmap) + break; } +out: + return tc; } void ixgbe_dcb_unpack_map(struct ixgbe_dcb_config *cfg, int direction, u8 *map) { - int i, up; - unsigned long bitmap; + u8 up; - for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { - bitmap = cfg->tc_config[i].path[direction].up_to_tc_bitmap; - for_each_set_bit(up, &bitmap, MAX_USER_PRIORITY) - map[up] = i; - } + for (up = 0; up < MAX_USER_PRIORITY; up++) + map[up] = ixgbe_dcb_get_tc_from_up(cfg, direction, up); } /** @@ -251,7 +267,7 @@ void ixgbe_dcb_unpack_map(struct ixgbe_dcb_config *cfg, int direction, u8 *map) * Configure dcb settings and enable dcb mode. */ s32 ixgbe_dcb_hw_config(struct ixgbe_hw *hw, - struct ixgbe_dcb_config *dcb_config) + struct ixgbe_dcb_config *dcb_config) { s32 ret = 0; u8 pfc_en; @@ -364,3 +380,25 @@ s32 ixgbe_dcb_hw_ets_config(struct ixgbe_hw *hw, } return 0; } + +static void ixgbe_dcb_read_rtrup2tc_82599(struct ixgbe_hw *hw, u8 *map) +{ + u32 reg, i; + + reg = IXGBE_READ_REG(hw, IXGBE_RTRUP2TC); + for (i = 0; i < MAX_USER_PRIORITY; i++) + map[i] = IXGBE_RTRUP2TC_UP_MASK & + (reg >> (i * IXGBE_RTRUP2TC_UP_SHIFT)); +} + +void ixgbe_dcb_read_rtrup2tc(struct ixgbe_hw *hw, u8 *map) +{ + switch (hw->mac.type) { + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + ixgbe_dcb_read_rtrup2tc_82599(hw, map); + break; + default: + break; + } +} diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h index 24333b71816..fc0a2dd5249 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2013 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, @@ -146,6 +146,7 @@ void ixgbe_dcb_unpack_max(struct ixgbe_dcb_config *, u16 *); void ixgbe_dcb_unpack_bwgid(struct ixgbe_dcb_config *, int, u8 *); void ixgbe_dcb_unpack_prio(struct ixgbe_dcb_config *, int, u8 *); void ixgbe_dcb_unpack_map(struct ixgbe_dcb_config *, int, u8 *); +u8 ixgbe_dcb_get_tc_from_up(struct ixgbe_dcb_config *, int, u8); /* DCB credits calculation */ s32 ixgbe_dcb_calculate_tc_credits(struct ixgbe_hw *, @@ -158,6 +159,8 @@ s32 ixgbe_dcb_hw_ets_config(struct ixgbe_hw *hw, u16 *refill, u16 *max, s32 ixgbe_dcb_hw_pfc_config(struct ixgbe_hw *hw, u8 pfc_en, u8 *tc_prio); s32 ixgbe_dcb_hw_config(struct ixgbe_hw *, struct ixgbe_dcb_config *); +void ixgbe_dcb_read_rtrup2tc(struct ixgbe_hw *hw, u8 *map); + /* DCB definitions for credit calculation */ #define DCB_CREDIT_QUANTUM 64 /* DCB Quantum */ #define MAX_CREDIT_REFILL 511 /* 0x1FF * 64B = 32704B */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c index d3695edfcb8..d3ba63f9ad3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2013 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, @@ -108,9 +108,8 @@ s32 ixgbe_dcb_config_tx_desc_arbiter_82598(struct ixgbe_hw *hw, /* 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); @@ -191,53 +190,46 @@ s32 ixgbe_dcb_config_tx_data_arbiter_82598(struct ixgbe_hw *hw, */ s32 ixgbe_dcb_config_pfc_82598(struct ixgbe_hw *hw, u8 pfc_en) { - u32 reg; + u32 fcrtl, reg; 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); + /* Enable Transmit Priority Flow Control */ + reg = IXGBE_READ_REG(hw, IXGBE_RMCS); + reg &= ~IXGBE_RMCS_TFCE_802_3X; + reg |= IXGBE_RMCS_TFCE_PRIORITY; + IXGBE_WRITE_REG(hw, IXGBE_RMCS, reg); - /* Configure flow control refresh threshold value */ - IXGBE_WRITE_REG(hw, IXGBE_FCRTV, 0x3400); - } + /* Enable Receive Priority Flow Control */ + reg = IXGBE_READ_REG(hw, IXGBE_FCTRL); + reg &= ~(IXGBE_FCTRL_RPFCE | IXGBE_FCTRL_RFCE); - /* - * 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); + if (pfc_en) + reg |= IXGBE_FCTRL_RPFCE; - reg = hw->fc.low_water << 10; + IXGBE_WRITE_REG(hw, IXGBE_FCTRL, reg); - if (enabled == pfc_enabled_tx || - enabled == pfc_enabled_full) - reg |= IXGBE_FCRTL_XONE; + /* Configure PFC Tx thresholds per TC */ + for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + if (!(pfc_en & (1 << i))) { + IXGBE_WRITE_REG(hw, IXGBE_FCRTL(i), 0); + IXGBE_WRITE_REG(hw, IXGBE_FCRTH(i), 0); + continue; + } + + fcrtl = (hw->fc.low_water[i] << 10) | IXGBE_FCRTL_XONE; + reg = (hw->fc.high_water[i] << 10) | IXGBE_FCRTH_FCEN; + IXGBE_WRITE_REG(hw, IXGBE_FCRTL(i), fcrtl); + IXGBE_WRITE_REG(hw, IXGBE_FCRTH(i), reg); + } - IXGBE_WRITE_REG(hw, IXGBE_FCRTL(i), reg); + /* Configure pause time */ + reg = hw->fc.pause_time * 0x00010001; + for (i = 0; i < (MAX_TRAFFIC_CLASS / 2); i++) + IXGBE_WRITE_REG(hw, IXGBE_FCTTV(i), reg); - reg = hw->fc.high_water[i] << 10; - if (enabled == pfc_enabled_tx || - enabled == pfc_enabled_full) - reg |= IXGBE_FCRTH_FCEN; + /* Configure flow control refresh threshold value */ + IXGBE_WRITE_REG(hw, IXGBE_FCRTV, hw->fc.pause_time / 2); - IXGBE_WRITE_REG(hw, IXGBE_FCRTH(i), reg); - } return 0; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.h index ba835708fca..3164f5453b8 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2013 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, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c index 888a419dc3d..3b932fe64ab 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2013 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, @@ -20,6 +20,7 @@ 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 @@ -211,24 +212,41 @@ s32 ixgbe_dcb_config_tx_data_arbiter_82599(struct ixgbe_hw *hw, */ s32 ixgbe_dcb_config_pfc_82599(struct ixgbe_hw *hw, u8 pfc_en, u8 *prio_tc) { - u32 i, j, reg; + u32 i, j, fcrtl, reg; u8 max_tc = 0; - for (i = 0; i < MAX_USER_PRIORITY; i++) + /* Enable Transmit Priority Flow Control */ + IXGBE_WRITE_REG(hw, IXGBE_FCCFG, IXGBE_FCCFG_TFCE_PRIORITY); + + /* Enable Receive Priority Flow Control */ + reg = IXGBE_READ_REG(hw, IXGBE_MFLCN); + reg |= IXGBE_MFLCN_DPF; + + /* + * X540 supports per TC Rx priority flow control. So + * clear all TCs and only enable those that should be + * enabled. + */ + reg &= ~(IXGBE_MFLCN_RPFCE_MASK | IXGBE_MFLCN_RFCE); + + if (hw->mac.type == ixgbe_mac_X540) + reg |= pfc_en << IXGBE_MFLCN_RPFCE_SHIFT; + + if (pfc_en) + reg |= IXGBE_MFLCN_RPFCE; + + IXGBE_WRITE_REG(hw, IXGBE_MFLCN, reg); + + for (i = 0; i < MAX_USER_PRIORITY; i++) { if (prio_tc[i] > max_tc) max_tc = prio_tc[i]; + } + /* Configure PFC Tx thresholds per TC */ - for (i = 0; i < MAX_TRAFFIC_CLASS; i++) { + for (i = 0; i <= max_tc; i++) { int enabled = 0; - if (i > max_tc) { - reg = 0; - IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(i), reg); - IXGBE_WRITE_REG(hw, IXGBE_FCRTH_82599(i), reg); - continue; - } - for (j = 0; j < MAX_USER_PRIORITY; j++) { if ((prio_tc[j] == i) && (pfc_en & (1 << j))) { enabled = 1; @@ -236,61 +254,30 @@ s32 ixgbe_dcb_config_pfc_82599(struct ixgbe_hw *hw, u8 pfc_en, u8 *prio_tc) } } - reg = hw->fc.low_water << 10; - - if (enabled) - reg |= IXGBE_FCRTL_XONE; - IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(i), reg); + if (enabled) { + reg = (hw->fc.high_water[i] << 10) | IXGBE_FCRTH_FCEN; + fcrtl = (hw->fc.low_water[i] << 10) | IXGBE_FCRTL_XONE; + IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(i), fcrtl); + } else { + reg = IXGBE_READ_REG(hw, IXGBE_RXPBSIZE(i)) - 32; + IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(i), 0); + } - reg = hw->fc.high_water[i] << 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 &= ~IXGBE_MFLCN_RPFCE_MASK; - reg |= pfc_en << IXGBE_MFLCN_RPFCE_SHIFT; - } + for (; i < MAX_TRAFFIC_CLASS; i++) { + IXGBE_WRITE_REG(hw, IXGBE_FCRTL_82599(i), 0); + IXGBE_WRITE_REG(hw, IXGBE_FCRTH_82599(i), 0); + } - IXGBE_WRITE_REG(hw, IXGBE_MFLCN, reg); - - } else { - /* X540 devices have a RX bit that should be cleared - * if PFC is disabled on all TCs but PFC features is - * enabled. - */ - if (hw->mac.type == ixgbe_mac_X540) { - reg = IXGBE_READ_REG(hw, IXGBE_MFLCN); - reg &= ~IXGBE_MFLCN_RPFCE_MASK; - IXGBE_WRITE_REG(hw, IXGBE_MFLCN, reg); - } + /* Configure pause time (2 TCs per register) */ + reg = hw->fc.pause_time * 0x00010001; + for (i = 0; i < (MAX_TRAFFIC_CLASS / 2); i++) + IXGBE_WRITE_REG(hw, IXGBE_FCTTV(i), reg); - for (i = 0; i < MAX_TRAFFIC_CLASS; i++) - hw->mac.ops.fc_enable(hw, i); - } + /* Configure flow control refresh threshold value */ + IXGBE_WRITE_REG(hw, IXGBE_FCRTV, hw->fc.pause_time / 2); return 0; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.h index 4dec47faeb0..90c370230e2 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2013 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, @@ -20,6 +20,7 @@ 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 @@ -30,21 +31,22 @@ /* DCB register definitions */ #define IXGBE_RTTDCS_TDPAC 0x00000001 /* 0 Round Robin, - * 1 WSP - Weighted Strict Priority - */ + * 1 WSP - Weighted Strict Priority + */ #define IXGBE_RTTDCS_VMPAC 0x00000002 /* 0 Round Robin, - * 1 WRR - Weighted 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! - */ + * clear! + */ #define IXGBE_RTTDCS_SPEED_CHG 0x80000000 /* Link speed change */ /* Receive UP2TC mapping */ #define IXGBE_RTRUP2TC_UP_SHIFT 3 +#define IXGBE_RTRUP2TC_UP_MASK 7 /* Transmit UP2TC mapping */ #define IXGBE_RTTUP2TC_UP_SHIFT 3 @@ -54,11 +56,11 @@ #define IXGBE_RTRPT4C_LSP 0x80000000 /* LSP enable bit */ #define IXGBE_RDRXCTL_MPBEN 0x00000010 /* DMA config for multiple packet - * buffers enable - */ + * buffers enable + */ #define IXGBE_RDRXCTL_MCEN 0x00000040 /* DMA config for multiple cores - * (RSS) enable - */ + * (RSS) enable + */ /* RTRPCS Bit Masks */ #define IXGBE_RTRPCS_RRM 0x00000002 /* Receive Recycle Mode enable */ @@ -79,8 +81,8 @@ /* RTTPCS Bit Masks */ #define IXGBE_RTTPCS_TPPAC 0x00000020 /* 0 Round Robin, - * 1 SP - Strict Priority - */ + * 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 diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c index 79a92fe987b..5172b6b12c0 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2013 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, @@ -30,6 +30,7 @@ #include <linux/dcbnl.h> #include "ixgbe_dcb_82598.h" #include "ixgbe_dcb_82599.h" +#include "ixgbe_sriov.h" /* Callbacks for DCB netlink in the kernel */ #define BIT_DCB_MODE 0x01 @@ -44,62 +45,102 @@ #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) +static int ixgbe_copy_dcb_cfg(struct ixgbe_adapter *adapter, int tc_max) { - struct tc_configuration *src_tc_cfg = NULL; - struct tc_configuration *dst_tc_cfg = NULL; - int i; + struct ixgbe_dcb_config *scfg = &adapter->temp_dcb_cfg; + struct ixgbe_dcb_config *dcfg = &adapter->dcb_cfg; + struct tc_configuration *src = NULL; + struct tc_configuration *dst = NULL; + int i, j; + int tx = DCB_TX_CONFIG; + int rx = DCB_RX_CONFIG; + int changes = 0; +#ifdef IXGBE_FCOE + struct dcb_app app = { + .selector = DCB_APP_IDTYPE_ETHTYPE, + .protocol = ETH_P_FCOE, + }; + u8 up = dcb_getapp(adapter->netdev, &app); - if (!src_dcb_cfg || !dst_dcb_cfg) - return -EINVAL; + if (up && !(up & (1 << adapter->fcoe.up))) + changes |= BIT_APP_UPCHG; +#endif for (i = DCB_PG_ATTR_TC_0; i < tc_max + DCB_PG_ATTR_TC_0; i++) { - src_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]; + src = &scfg->tc_config[i - DCB_PG_ATTR_TC_0]; + dst = &dcfg->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; + if (dst->path[tx].prio_type != src->path[tx].prio_type) { + dst->path[tx].prio_type = src->path[tx].prio_type; + changes |= BIT_PG_TX; + } - dst_tc_cfg->path[DCB_TX_CONFIG].bwg_id = - src_tc_cfg->path[DCB_TX_CONFIG].bwg_id; + if (dst->path[tx].bwg_id != src->path[tx].bwg_id) { + dst->path[tx].bwg_id = src->path[tx].bwg_id; + changes |= BIT_PG_TX; + } - dst_tc_cfg->path[DCB_TX_CONFIG].bwg_percent = - src_tc_cfg->path[DCB_TX_CONFIG].bwg_percent; + if (dst->path[tx].bwg_percent != src->path[tx].bwg_percent) { + dst->path[tx].bwg_percent = src->path[tx].bwg_percent; + changes |= BIT_PG_TX; + } - dst_tc_cfg->path[DCB_TX_CONFIG].up_to_tc_bitmap = - src_tc_cfg->path[DCB_TX_CONFIG].up_to_tc_bitmap; + if (dst->path[tx].up_to_tc_bitmap != + src->path[tx].up_to_tc_bitmap) { + dst->path[tx].up_to_tc_bitmap = + src->path[tx].up_to_tc_bitmap; + changes |= (BIT_PG_TX | BIT_PFC | BIT_APP_UPCHG); + } - dst_tc_cfg->path[DCB_RX_CONFIG].prio_type = - src_tc_cfg->path[DCB_RX_CONFIG].prio_type; + if (dst->path[rx].prio_type != src->path[rx].prio_type) { + dst->path[rx].prio_type = src->path[rx].prio_type; + changes |= BIT_PG_RX; + } - dst_tc_cfg->path[DCB_RX_CONFIG].bwg_id = - src_tc_cfg->path[DCB_RX_CONFIG].bwg_id; + if (dst->path[rx].bwg_id != src->path[rx].bwg_id) { + dst->path[rx].bwg_id = src->path[rx].bwg_id; + changes |= BIT_PG_RX; + } - dst_tc_cfg->path[DCB_RX_CONFIG].bwg_percent = - src_tc_cfg->path[DCB_RX_CONFIG].bwg_percent; + if (dst->path[rx].bwg_percent != src->path[rx].bwg_percent) { + dst->path[rx].bwg_percent = src->path[rx].bwg_percent; + changes |= BIT_PG_RX; + } - dst_tc_cfg->path[DCB_RX_CONFIG].up_to_tc_bitmap = - src_tc_cfg->path[DCB_RX_CONFIG].up_to_tc_bitmap; + if (dst->path[rx].up_to_tc_bitmap != + src->path[rx].up_to_tc_bitmap) { + dst->path[rx].up_to_tc_bitmap = + src->path[rx].up_to_tc_bitmap; + changes |= (BIT_PG_RX | BIT_PFC | BIT_APP_UPCHG); + } } for (i = DCB_PG_ATTR_BW_ID_0; i < DCB_PG_ATTR_BW_ID_MAX; i++) { - 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]; + j = i - DCB_PG_ATTR_BW_ID_0; + if (dcfg->bw_percentage[tx][j] != scfg->bw_percentage[tx][j]) { + dcfg->bw_percentage[tx][j] = scfg->bw_percentage[tx][j]; + changes |= BIT_PG_TX; + } + if (dcfg->bw_percentage[rx][j] != scfg->bw_percentage[rx][j]) { + dcfg->bw_percentage[rx][j] = scfg->bw_percentage[rx][j]; + changes |= BIT_PG_RX; + } } for (i = DCB_PFC_UP_ATTR_0; i < DCB_PFC_UP_ATTR_MAX; i++) { - 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; + j = i - DCB_PFC_UP_ATTR_0; + if (dcfg->tc_config[j].dcb_pfc != scfg->tc_config[j].dcb_pfc) { + dcfg->tc_config[j].dcb_pfc = scfg->tc_config[j].dcb_pfc; + changes |= BIT_PFC; + } } - dst_dcb_cfg->pfc_mode_enable = src_dcb_cfg->pfc_mode_enable; + if (dcfg->pfc_mode_enable != scfg->pfc_mode_enable) { + dcfg->pfc_mode_enable = scfg->pfc_mode_enable; + changes |= BIT_PFC; + } - return 0; + return changes; } static u8 ixgbe_dcbnl_get_state(struct net_device *netdev) @@ -111,30 +152,21 @@ static u8 ixgbe_dcbnl_get_state(struct net_device *netdev) static u8 ixgbe_dcbnl_set_state(struct net_device *netdev, u8 state) { - u8 err = 0; - u8 prio_tc[MAX_USER_PRIORITY] = {0}; - int i; struct ixgbe_adapter *adapter = netdev_priv(netdev); + int err = 0; /* Fail command if not in CEE mode */ if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_CEE)) return 1; /* verify there is something to do, if not then exit */ - if (!!state != !(adapter->flags & IXGBE_FLAG_DCB_ENABLED)) - return err; + if (!state == !(adapter->flags & IXGBE_FLAG_DCB_ENABLED)) + goto out; - if (state > 0) { - err = ixgbe_setup_tc(netdev, adapter->dcb_cfg.num_tcs.pg_tcs); - ixgbe_dcb_unpack_map(&adapter->dcb_cfg, DCB_TX_CONFIG, prio_tc); - } else { - err = ixgbe_setup_tc(netdev, 0); - } - - for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) - netdev_set_prio_tc_map(netdev, i, prio_tc[i]); - - return err; + err = ixgbe_setup_tc(netdev, + state ? adapter->dcb_cfg.num_tcs.pg_tcs : 0); +out: + return !!err; } static void ixgbe_dcbnl_get_perm_hw_addr(struct net_device *netdev, @@ -160,8 +192,8 @@ static void ixgbe_dcbnl_get_perm_hw_addr(struct net_device *netdev, } 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) + u8 prio, u8 bwg_id, u8 bw_pct, + u8 up_map) { struct ixgbe_adapter *adapter = netdev_priv(netdev); @@ -175,37 +207,19 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_tx(struct net_device *netdev, int tc, 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; - - if (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_PFC | BIT_APP_UPCHG; } static void ixgbe_dcbnl_set_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id, - u8 bw_pct) + 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) + u8 prio, u8 bwg_id, u8 bw_pct, + u8 up_map) { struct ixgbe_adapter *adapter = netdev_priv(netdev); @@ -219,37 +233,19 @@ static void ixgbe_dcbnl_set_pg_tc_cfg_rx(struct net_device *netdev, int tc, 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; - - if (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_PFC; } static void ixgbe_dcbnl_set_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id, - u8 bw_pct) + 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) + u8 *prio, u8 *bwg_id, u8 *bw_pct, + u8 *up_map) { struct ixgbe_adapter *adapter = netdev_priv(netdev); @@ -260,7 +256,7 @@ static void ixgbe_dcbnl_get_pg_tc_cfg_tx(struct net_device *netdev, int tc, } static void ixgbe_dcbnl_get_pg_bwg_cfg_tx(struct net_device *netdev, int bwg_id, - u8 *bw_pct) + u8 *bw_pct) { struct ixgbe_adapter *adapter = netdev_priv(netdev); @@ -268,8 +264,8 @@ static void ixgbe_dcbnl_get_pg_bwg_cfg_tx(struct net_device *netdev, int 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) + u8 *prio, u8 *bwg_id, u8 *bw_pct, + u8 *up_map) { struct ixgbe_adapter *adapter = netdev_priv(netdev); @@ -280,7 +276,7 @@ static void ixgbe_dcbnl_get_pg_tc_cfg_rx(struct net_device *netdev, int tc, } static void ixgbe_dcbnl_get_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id, - u8 *bw_pct) + u8 *bw_pct) { struct ixgbe_adapter *adapter = netdev_priv(netdev); @@ -288,27 +284,24 @@ static void ixgbe_dcbnl_get_pg_bwg_cfg_rx(struct net_device *netdev, int bwg_id, } static void ixgbe_dcbnl_set_pfc_cfg(struct net_device *netdev, int priority, - u8 setting) + 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->dcb_cfg.tc_config[priority].dcb_pfc) adapter->temp_dcb_cfg.pfc_mode_enable = true; - } } static void ixgbe_dcbnl_get_pfc_cfg(struct net_device *netdev, int priority, - u8 *setting) + u8 *setting) { struct ixgbe_adapter *adapter = netdev_priv(netdev); *setting = adapter->dcb_cfg.tc_config[priority].dcb_pfc; } -#ifdef IXGBE_FCOE static void ixgbe_dcbnl_devreset(struct net_device *dev) { struct ixgbe_adapter *adapter = netdev_priv(dev); @@ -327,62 +320,23 @@ static void ixgbe_dcbnl_devreset(struct net_device *dev) clear_bit(__IXGBE_RESETTING, &adapter->state); } -#endif static u8 ixgbe_dcbnl_set_all(struct net_device *netdev) { struct ixgbe_adapter *adapter = netdev_priv(netdev); - int ret, i; -#ifdef IXGBE_FCOE - struct dcb_app app = { - .selector = DCB_APP_IDTYPE_ETHTYPE, - .protocol = ETH_P_FCOE, - }; - u8 up; - - /* In IEEE mode, use the IEEE Ethertype selector value */ - if (adapter->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) { - app.selector = IEEE_8021QAZ_APP_SEL_ETHERTYPE; - up = dcb_ieee_getapp_mask(netdev, &app); - } else { - up = dcb_getapp(netdev, &app); - } -#endif + struct ixgbe_dcb_config *dcb_cfg = &adapter->dcb_cfg; + struct ixgbe_hw *hw = &adapter->hw; + int ret = DCB_NO_HW_CHG; + int i; /* Fail command if not in CEE mode */ if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_CEE)) - return 1; + return ret; - ret = ixgbe_copy_dcb_cfg(&adapter->temp_dcb_cfg, &adapter->dcb_cfg, - MAX_TRAFFIC_CLASS); - if (ret) - return DCB_NO_HW_CHG; - - 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; - } - } + adapter->dcb_set_bitmap |= ixgbe_copy_dcb_cfg(adapter, + MAX_TRAFFIC_CLASS); + if (!adapter->dcb_set_bitmap) + return ret; if (adapter->dcb_set_bitmap & (BIT_PG_TX|BIT_PG_RX)) { u16 refill[MAX_TRAFFIC_CLASS], max[MAX_TRAFFIC_CLASS]; @@ -396,49 +350,55 @@ static u8 ixgbe_dcbnl_set_all(struct net_device *netdev) 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_calculate_tc_credits(hw, dcb_cfg, max_frame, + DCB_TX_CONFIG); + ixgbe_dcb_calculate_tc_credits(hw, dcb_cfg, max_frame, + DCB_RX_CONFIG); - ixgbe_dcb_unpack_refill(&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_unpack_map(&adapter->dcb_cfg, - DCB_TX_CONFIG, prio_tc); + ixgbe_dcb_unpack_refill(dcb_cfg, DCB_TX_CONFIG, refill); + ixgbe_dcb_unpack_max(dcb_cfg, max); + ixgbe_dcb_unpack_bwgid(dcb_cfg, DCB_TX_CONFIG, bwg_id); + ixgbe_dcb_unpack_prio(dcb_cfg, DCB_TX_CONFIG, prio_type); + ixgbe_dcb_unpack_map(dcb_cfg, DCB_TX_CONFIG, prio_tc); - ixgbe_dcb_hw_ets_config(&adapter->hw, refill, max, - bwg_id, prio_type, prio_tc); + ixgbe_dcb_hw_ets_config(hw, refill, max, bwg_id, + prio_type, prio_tc); for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) netdev_set_prio_tc_map(netdev, i, prio_tc[i]); + + ret = DCB_HW_CHG_RST; } if (adapter->dcb_set_bitmap & BIT_PFC) { - u8 pfc_en; - u8 prio_tc[MAX_USER_PRIORITY]; + if (dcb_cfg->pfc_mode_enable) { + u8 pfc_en; + u8 prio_tc[MAX_USER_PRIORITY]; + + ixgbe_dcb_unpack_map(dcb_cfg, DCB_TX_CONFIG, prio_tc); + ixgbe_dcb_unpack_pfc(dcb_cfg, &pfc_en); + ixgbe_dcb_hw_pfc_config(hw, pfc_en, prio_tc); + } else { + hw->mac.ops.fc_enable(hw); + } + + ixgbe_set_rx_drop_en(adapter); - ixgbe_dcb_unpack_map(&adapter->dcb_cfg, - DCB_TX_CONFIG, prio_tc); - ixgbe_dcb_unpack_pfc(&adapter->dcb_cfg, &pfc_en); - ixgbe_dcb_hw_pfc_config(&adapter->hw, pfc_en, prio_tc); ret = DCB_HW_CHG; } - if (adapter->dcb_cfg.pfc_mode_enable) - adapter->hw.fc.current_mode = ixgbe_fc_pfc; - #ifdef IXGBE_FCOE /* Reprogam FCoE hardware offloads when the traffic class * FCoE is using changes. This happens if the APP info * changes or the up2tc mapping is updated. */ - if ((up && !(up & (1 << adapter->fcoe.up))) || - (adapter->dcb_set_bitmap & BIT_APP_UPCHG)) { + if (adapter->dcb_set_bitmap & BIT_APP_UPCHG) { + struct dcb_app app = { + .selector = DCB_APP_IDTYPE_ETHTYPE, + .protocol = ETH_P_FCOE, + }; + u8 up = dcb_getapp(netdev, &app); + adapter->fcoe.up = ffs(up) - 1; ixgbe_dcbnl_devreset(netdev); ret = DCB_HW_CHG_RST; @@ -486,10 +446,9 @@ static u8 ixgbe_dcbnl_getcap(struct net_device *netdev, int capid, u8 *cap) return 0; } -static u8 ixgbe_dcbnl_getnumtcs(struct net_device *netdev, int tcid, u8 *num) +static int 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) { @@ -500,17 +459,17 @@ static u8 ixgbe_dcbnl_getnumtcs(struct net_device *netdev, int tcid, u8 *num) *num = adapter->dcb_cfg.num_tcs.pfc_tcs; break; default: - rval = -EINVAL; + return -EINVAL; break; } } else { - rval = -EINVAL; + return -EINVAL; } - return rval; + return 0; } -static u8 ixgbe_dcbnl_setnumtcs(struct net_device *netdev, int tcid, u8 num) +static int ixgbe_dcbnl_setnumtcs(struct net_device *netdev, int tcid, u8 num) { return -EINVAL; } @@ -527,9 +486,6 @@ 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; } /** @@ -581,8 +537,9 @@ static int ixgbe_dcbnl_ieee_setets(struct net_device *dev, { struct ixgbe_adapter *adapter = netdev_priv(dev); int max_frame = dev->mtu + ETH_HLEN + ETH_FCS_LEN; - int i; + int i, err = 0; __u8 max_tc = 0; + __u8 map_chg = 0; if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) return -EINVAL; @@ -592,15 +549,25 @@ static int ixgbe_dcbnl_ieee_setets(struct net_device *dev, GFP_KERNEL); if (!adapter->ixgbe_ieee_ets) return -ENOMEM; - } - memcpy(adapter->ixgbe_ieee_ets, ets, sizeof(*adapter->ixgbe_ieee_ets)); + /* initialize UP2TC mappings to invalid value */ + for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) + adapter->ixgbe_ieee_ets->prio_tc[i] = + IEEE_8021QAZ_MAX_TCS; + /* if possible update UP2TC mappings from HW */ + ixgbe_dcb_read_rtrup2tc(&adapter->hw, + adapter->ixgbe_ieee_ets->prio_tc); + } for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { if (ets->prio_tc[i] > max_tc) max_tc = ets->prio_tc[i]; + if (ets->prio_tc[i] != adapter->ixgbe_ieee_ets->prio_tc[i]) + map_chg = 1; } + memcpy(adapter->ixgbe_ieee_ets, ets, sizeof(*adapter->ixgbe_ieee_ets)); + if (max_tc) max_tc++; @@ -608,12 +575,16 @@ static int ixgbe_dcbnl_ieee_setets(struct net_device *dev, return -EINVAL; if (max_tc != netdev_get_num_tc(dev)) - ixgbe_setup_tc(dev, max_tc); + err = ixgbe_setup_tc(dev, max_tc); + else if (map_chg) + ixgbe_dcbnl_devreset(dev); - for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) - netdev_set_prio_tc_map(dev, i, ets->prio_tc[i]); + if (err) + goto err_out; - return ixgbe_dcb_hw_ets(&adapter->hw, ets, max_frame); + err = ixgbe_dcb_hw_ets(&adapter->hw, ets, max_frame); +err_out: + return err; } static int ixgbe_dcbnl_ieee_getpfc(struct net_device *dev, @@ -645,7 +616,9 @@ static int ixgbe_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc) { struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_hw *hw = &adapter->hw; u8 *prio_tc; + int err; if (!(adapter->dcbx_cap & DCB_CAP_DCBX_VER_IEEE)) return -EINVAL; @@ -659,7 +632,16 @@ static int ixgbe_dcbnl_ieee_setpfc(struct net_device *dev, prio_tc = adapter->ixgbe_ieee_ets->prio_tc; memcpy(adapter->ixgbe_ieee_pfc, pfc, sizeof(*adapter->ixgbe_ieee_pfc)); - return ixgbe_dcb_hw_pfc_config(&adapter->hw, pfc->pfc_en, prio_tc); + + /* Enable link flow control parameters if PFC is disabled */ + if (pfc->pfc_en) + err = ixgbe_dcb_hw_pfc_config(hw, pfc->pfc_en, prio_tc); + else + err = hw->mac.ops.fc_enable(hw); + + ixgbe_set_rx_drop_en(adapter); + + return err; } static int ixgbe_dcbnl_ieee_setapp(struct net_device *dev, @@ -672,9 +654,11 @@ static int ixgbe_dcbnl_ieee_setapp(struct net_device *dev, return err; err = dcb_ieee_setapp(dev, app); + if (err) + return err; #ifdef IXGBE_FCOE - if (!err && app->selector == IEEE_8021QAZ_APP_SEL_ETHERTYPE && + if (app->selector == IEEE_8021QAZ_APP_SEL_ETHERTYPE && app->protocol == ETH_P_FCOE) { u8 app_mask = dcb_ieee_getapp_mask(dev, app); @@ -685,6 +669,23 @@ static int ixgbe_dcbnl_ieee_setapp(struct net_device *dev, ixgbe_dcbnl_devreset(dev); } #endif + + /* VF devices should use default UP when available */ + if (app->selector == IEEE_8021QAZ_APP_SEL_ETHERTYPE && + app->protocol == 0) { + int vf; + + adapter->default_up = app->priority; + + for (vf = 0; vf < adapter->num_vfs; vf++) { + struct vf_data_storage *vfinfo = &adapter->vfinfo[vf]; + + if (!vfinfo->pf_qos) + ixgbe_set_vmvir(adapter, vfinfo->pf_vlan, + app->priority, vf); + } + } + return 0; } @@ -712,6 +713,24 @@ static int ixgbe_dcbnl_ieee_delapp(struct net_device *dev, ixgbe_dcbnl_devreset(dev); } #endif + /* IF default priority is being removed clear VF default UP */ + if (app->selector == IEEE_8021QAZ_APP_SEL_ETHERTYPE && + app->protocol == 0 && adapter->default_up == app->priority) { + int vf; + long unsigned int app_mask = dcb_ieee_getapp_mask(dev, app); + int qos = app_mask ? find_first_bit(&app_mask, 8) : 0; + + adapter->default_up = qos; + + for (vf = 0; vf < adapter->num_vfs; vf++) { + struct vf_data_storage *vfinfo = &adapter->vfinfo[vf]; + + if (!vfinfo->pf_qos) + ixgbe_set_vmvir(adapter, vfinfo->pf_vlan, + qos, vf); + } + } + return err; } @@ -726,6 +745,7 @@ static u8 ixgbe_dcbnl_setdcbx(struct net_device *dev, u8 mode) struct ixgbe_adapter *adapter = netdev_priv(dev); struct ieee_ets ets = {0}; struct ieee_pfc pfc = {0}; + int err = 0; /* no support for LLD_MANAGED modes or CEE+IEEE */ if ((mode & DCB_CAP_DCBX_LLD_MANAGED) || @@ -756,10 +776,10 @@ static u8 ixgbe_dcbnl_setdcbx(struct net_device *dev, u8 mode) */ ixgbe_dcbnl_ieee_setets(dev, &ets); ixgbe_dcbnl_ieee_setpfc(dev, &pfc); - ixgbe_setup_tc(dev, 0); + err = ixgbe_setup_tc(dev, 0); } - return 0; + return err ? 1 : 0; } const struct dcbnl_rtnl_ops dcbnl_ops = { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c new file mode 100644 index 00000000000..5e2c1e35e51 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c @@ -0,0 +1,276 @@ +/******************************************************************************* + + Intel 10 Gigabit PCI Express Linux driver + Copyright(c) 1999 - 2013 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 <linux/debugfs.h> +#include <linux/module.h> + +#include "ixgbe.h" + +static struct dentry *ixgbe_dbg_root; + +static char ixgbe_dbg_reg_ops_buf[256] = ""; + +/** + * ixgbe_dbg_reg_ops_read - read for reg_ops datum + * @filp: the opened file + * @buffer: where to write the data for the user to read + * @count: the size of the user's buffer + * @ppos: file position offset + **/ +static ssize_t ixgbe_dbg_reg_ops_read(struct file *filp, char __user *buffer, + size_t count, loff_t *ppos) +{ + struct ixgbe_adapter *adapter = filp->private_data; + char *buf; + int len; + + /* don't allow partial reads */ + if (*ppos != 0) + return 0; + + buf = kasprintf(GFP_KERNEL, "%s: %s\n", + adapter->netdev->name, + ixgbe_dbg_reg_ops_buf); + if (!buf) + return -ENOMEM; + + if (count < strlen(buf)) { + kfree(buf); + return -ENOSPC; + } + + len = simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf)); + + kfree(buf); + return len; +} + +/** + * ixgbe_dbg_reg_ops_write - write into reg_ops datum + * @filp: the opened file + * @buffer: where to find the user's data + * @count: the length of the user's data + * @ppos: file position offset + **/ +static ssize_t ixgbe_dbg_reg_ops_write(struct file *filp, + const char __user *buffer, + size_t count, loff_t *ppos) +{ + struct ixgbe_adapter *adapter = filp->private_data; + int len; + + /* don't allow partial writes */ + if (*ppos != 0) + return 0; + if (count >= sizeof(ixgbe_dbg_reg_ops_buf)) + return -ENOSPC; + + len = simple_write_to_buffer(ixgbe_dbg_reg_ops_buf, + sizeof(ixgbe_dbg_reg_ops_buf)-1, + ppos, + buffer, + count); + if (len < 0) + return len; + + ixgbe_dbg_reg_ops_buf[len] = '\0'; + + if (strncmp(ixgbe_dbg_reg_ops_buf, "write", 5) == 0) { + u32 reg, value; + int cnt; + cnt = sscanf(&ixgbe_dbg_reg_ops_buf[5], "%x %x", ®, &value); + if (cnt == 2) { + IXGBE_WRITE_REG(&adapter->hw, reg, value); + value = IXGBE_READ_REG(&adapter->hw, reg); + e_dev_info("write: 0x%08x = 0x%08x\n", reg, value); + } else { + e_dev_info("write <reg> <value>\n"); + } + } else if (strncmp(ixgbe_dbg_reg_ops_buf, "read", 4) == 0) { + u32 reg, value; + int cnt; + cnt = sscanf(&ixgbe_dbg_reg_ops_buf[4], "%x", ®); + if (cnt == 1) { + value = IXGBE_READ_REG(&adapter->hw, reg); + e_dev_info("read 0x%08x = 0x%08x\n", reg, value); + } else { + e_dev_info("read <reg>\n"); + } + } else { + e_dev_info("Unknown command %s\n", ixgbe_dbg_reg_ops_buf); + e_dev_info("Available commands:\n"); + e_dev_info(" read <reg>\n"); + e_dev_info(" write <reg> <value>\n"); + } + return count; +} + +static const struct file_operations ixgbe_dbg_reg_ops_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = ixgbe_dbg_reg_ops_read, + .write = ixgbe_dbg_reg_ops_write, +}; + +static char ixgbe_dbg_netdev_ops_buf[256] = ""; + +/** + * ixgbe_dbg_netdev_ops_read - read for netdev_ops datum + * @filp: the opened file + * @buffer: where to write the data for the user to read + * @count: the size of the user's buffer + * @ppos: file position offset + **/ +static ssize_t ixgbe_dbg_netdev_ops_read(struct file *filp, + char __user *buffer, + size_t count, loff_t *ppos) +{ + struct ixgbe_adapter *adapter = filp->private_data; + char *buf; + int len; + + /* don't allow partial reads */ + if (*ppos != 0) + return 0; + + buf = kasprintf(GFP_KERNEL, "%s: %s\n", + adapter->netdev->name, + ixgbe_dbg_netdev_ops_buf); + if (!buf) + return -ENOMEM; + + if (count < strlen(buf)) { + kfree(buf); + return -ENOSPC; + } + + len = simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf)); + + kfree(buf); + return len; +} + +/** + * ixgbe_dbg_netdev_ops_write - write into netdev_ops datum + * @filp: the opened file + * @buffer: where to find the user's data + * @count: the length of the user's data + * @ppos: file position offset + **/ +static ssize_t ixgbe_dbg_netdev_ops_write(struct file *filp, + const char __user *buffer, + size_t count, loff_t *ppos) +{ + struct ixgbe_adapter *adapter = filp->private_data; + int len; + + /* don't allow partial writes */ + if (*ppos != 0) + return 0; + if (count >= sizeof(ixgbe_dbg_netdev_ops_buf)) + return -ENOSPC; + + len = simple_write_to_buffer(ixgbe_dbg_netdev_ops_buf, + sizeof(ixgbe_dbg_netdev_ops_buf)-1, + ppos, + buffer, + count); + if (len < 0) + return len; + + ixgbe_dbg_netdev_ops_buf[len] = '\0'; + + if (strncmp(ixgbe_dbg_netdev_ops_buf, "tx_timeout", 10) == 0) { + adapter->netdev->netdev_ops->ndo_tx_timeout(adapter->netdev); + e_dev_info("tx_timeout called\n"); + } else { + e_dev_info("Unknown command: %s\n", ixgbe_dbg_netdev_ops_buf); + e_dev_info("Available commands:\n"); + e_dev_info(" tx_timeout\n"); + } + return count; +} + +static const struct file_operations ixgbe_dbg_netdev_ops_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = ixgbe_dbg_netdev_ops_read, + .write = ixgbe_dbg_netdev_ops_write, +}; + +/** + * ixgbe_dbg_adapter_init - setup the debugfs directory for the adapter + * @adapter: the adapter that is starting up + **/ +void ixgbe_dbg_adapter_init(struct ixgbe_adapter *adapter) +{ + const char *name = pci_name(adapter->pdev); + struct dentry *pfile; + adapter->ixgbe_dbg_adapter = debugfs_create_dir(name, ixgbe_dbg_root); + if (adapter->ixgbe_dbg_adapter) { + pfile = debugfs_create_file("reg_ops", 0600, + adapter->ixgbe_dbg_adapter, adapter, + &ixgbe_dbg_reg_ops_fops); + if (!pfile) + e_dev_err("debugfs reg_ops for %s failed\n", name); + pfile = debugfs_create_file("netdev_ops", 0600, + adapter->ixgbe_dbg_adapter, adapter, + &ixgbe_dbg_netdev_ops_fops); + if (!pfile) + e_dev_err("debugfs netdev_ops for %s failed\n", name); + } else { + e_dev_err("debugfs entry for %s failed\n", name); + } +} + +/** + * ixgbe_dbg_adapter_exit - clear out the adapter's debugfs entries + * @pf: the pf that is stopping + **/ +void ixgbe_dbg_adapter_exit(struct ixgbe_adapter *adapter) +{ + debugfs_remove_recursive(adapter->ixgbe_dbg_adapter); + adapter->ixgbe_dbg_adapter = NULL; +} + +/** + * ixgbe_dbg_init - start up debugfs for the driver + **/ +void ixgbe_dbg_init(void) +{ + ixgbe_dbg_root = debugfs_create_dir(ixgbe_driver_name, NULL); + if (ixgbe_dbg_root == NULL) + pr_err("init of debugfs failed\n"); +} + +/** + * ixgbe_dbg_exit - clean out the driver's debugfs entries + **/ +void ixgbe_dbg_exit(void) +{ + debugfs_remove_recursive(ixgbe_dbg_root); +} diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index a62975480e3..a452730a327 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2014 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, @@ -20,6 +20,7 @@ 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 @@ -35,9 +36,11 @@ #include <linux/netdevice.h> #include <linux/ethtool.h> #include <linux/vmalloc.h> +#include <linux/highmem.h> #include <linux/uaccess.h> #include "ixgbe.h" +#include "ixgbe_phy.h" #define IXGBE_ALL_RAR_ENTRIES 16 @@ -138,8 +141,8 @@ static const struct ixgbe_stats ixgbe_gstrings_stats[] = { sizeof(((struct ixgbe_adapter *)0)->stats.pxofftxc)) \ / sizeof(u64)) #define IXGBE_STATS_LEN (IXGBE_GLOBAL_STATS_LEN + \ - IXGBE_PB_STATS_LEN + \ - IXGBE_QUEUE_STATS_LEN) + IXGBE_PB_STATS_LEN + \ + IXGBE_QUEUE_STATS_LEN) static const char ixgbe_gstrings_test[][ETH_GSTRING_LEN] = { "Register test (offline)", "Eeprom test (offline)", @@ -149,104 +152,69 @@ static const char ixgbe_gstrings_test[][ETH_GSTRING_LEN] = { #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 ethtool_cmd *ecmd) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; + ixgbe_link_speed supported_link; u32 link_speed = 0; + bool autoneg = false; 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; + hw->mac.ops.get_link_capabilities(hw, &supported_link, &autoneg); + + /* set the supported link speeds */ + if (supported_link & IXGBE_LINK_SPEED_10GB_FULL) + ecmd->supported |= SUPPORTED_10000baseT_Full; + if (supported_link & IXGBE_LINK_SPEED_1GB_FULL) + ecmd->supported |= SUPPORTED_1000baseT_Full; + if (supported_link & IXGBE_LINK_SPEED_100_FULL) + ecmd->supported |= SUPPORTED_100baseT_Full; + + /* set the advertised speeds */ + 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 modes in case phy.autoneg_advertised isn't set */ + if (supported_link & IXGBE_LINK_SPEED_10GB_FULL) + ecmd->advertising |= ADVERTISED_10000baseT_Full; + if (supported_link & IXGBE_LINK_SPEED_1GB_FULL) + ecmd->advertising |= ADVERTISED_1000baseT_Full; + if (supported_link & IXGBE_LINK_SPEED_100_FULL) + ecmd->advertising |= ADVERTISED_100baseT_Full; + + if (hw->phy.multispeed_fiber && !autoneg) { + if (supported_link & IXGBE_LINK_SPEED_10GB_FULL) + ecmd->advertising = ADVERTISED_10000baseT_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; + if (autoneg) { + ecmd->supported |= SUPPORTED_Autoneg; + ecmd->advertising |= ADVERTISED_Autoneg; + ecmd->autoneg = AUTONEG_ENABLE; + } else ecmd->autoneg = AUTONEG_DISABLE; - } - /* Get PHY type */ + ecmd->transceiver = XCVR_EXTERNAL; + + /* Determine the remaining settings based on the PHY type. */ switch (adapter->hw.phy.type) { case ixgbe_phy_tn: case ixgbe_phy_aq: case ixgbe_phy_cu_unknown: - /* Copper 10G-BASET */ + ecmd->supported |= SUPPORTED_TP; + ecmd->advertising |= ADVERTISED_TP; ecmd->port = PORT_TP; break; case ixgbe_phy_qt: + ecmd->supported |= SUPPORTED_FIBRE; + ecmd->advertising |= ADVERTISED_FIBRE; ecmd->port = PORT_FIBRE; break; case ixgbe_phy_nl: @@ -256,42 +224,57 @@ static int ixgbe_get_settings(struct net_device *netdev, 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 */ + switch (adapter->hw.phy.sfp_type) { case ixgbe_sfp_type_da_cu: case ixgbe_sfp_type_da_cu_core0: case ixgbe_sfp_type_da_cu_core1: + ecmd->supported |= SUPPORTED_FIBRE; + ecmd->advertising |= ADVERTISED_FIBRE; 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: + case ixgbe_sfp_type_1g_sx_core0: + case ixgbe_sfp_type_1g_sx_core1: + case ixgbe_sfp_type_1g_lx_core0: + case ixgbe_sfp_type_1g_lx_core1: + ecmd->supported |= SUPPORTED_FIBRE; + ecmd->advertising |= ADVERTISED_FIBRE; ecmd->port = PORT_FIBRE; break; case ixgbe_sfp_type_not_present: + ecmd->supported |= SUPPORTED_FIBRE; + ecmd->advertising |= ADVERTISED_FIBRE; ecmd->port = PORT_NONE; break; case ixgbe_sfp_type_1g_cu_core0: case ixgbe_sfp_type_1g_cu_core1: + ecmd->supported |= SUPPORTED_TP; + ecmd->advertising |= ADVERTISED_TP; ecmd->port = PORT_TP; - ecmd->supported = SUPPORTED_TP; - ecmd->advertising = (ADVERTISED_1000baseT_Full | - ADVERTISED_TP); break; case ixgbe_sfp_type_unknown: default: + ecmd->supported |= SUPPORTED_FIBRE; + ecmd->advertising |= ADVERTISED_FIBRE; ecmd->port = PORT_OTHER; break; } break; case ixgbe_phy_xaui: + ecmd->supported |= SUPPORTED_FIBRE; + ecmd->advertising |= ADVERTISED_FIBRE; ecmd->port = PORT_NONE; break; case ixgbe_phy_unknown: case ixgbe_phy_generic: case ixgbe_phy_sfp_unsupported: default: + ecmd->supported |= SUPPORTED_FIBRE; + ecmd->advertising |= ADVERTISED_FIBRE; ecmd->port = PORT_OTHER; break; } @@ -313,15 +296,15 @@ static int ixgbe_get_settings(struct net_device *netdev, } ecmd->duplex = DUPLEX_FULL; } else { - ethtool_cmd_speed_set(ecmd, -1); - ecmd->duplex = -1; + ethtool_cmd_speed_set(ecmd, SPEED_UNKNOWN); + ecmd->duplex = DUPLEX_UNKNOWN; } return 0; } static int ixgbe_set_settings(struct net_device *netdev, - struct ethtool_cmd *ecmd) + struct ethtool_cmd *ecmd) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; @@ -334,12 +317,17 @@ static int ixgbe_set_settings(struct net_device *netdev, * this function does not support duplex forcing, but can * limit the advertising of the adapter to the specified speed */ - if (ecmd->autoneg == AUTONEG_DISABLE) - return -EINVAL; - if (ecmd->advertising & ~ecmd->supported) return -EINVAL; + /* only allow one speed at a time if no autoneg */ + if (!ecmd->autoneg && hw->phy.multispeed_fiber) { + if (ecmd->advertising == + (ADVERTISED_10000baseT_Full | + ADVERTISED_1000baseT_Full)) + return -EINVAL; + } + old = hw->phy.autoneg_advertised; advertised = 0; if (ecmd->advertising & ADVERTISED_10000baseT_Full) @@ -355,10 +343,10 @@ static int ixgbe_set_settings(struct net_device *netdev, 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); + err = hw->mac.ops.setup_link(hw, advertised, true); if (err) { e_info(probe, "setup link failed with code %d\n", err); - hw->mac.ops.setup_link(hw, old, true, true); + hw->mac.ops.setup_link(hw, old, true); } } else { /* in this case we currently only support 10Gb/FULL */ @@ -373,15 +361,16 @@ static int ixgbe_set_settings(struct net_device *netdev, } static void ixgbe_get_pauseparam(struct net_device *netdev, - struct ethtool_pauseparam *pause) + struct ethtool_pauseparam *pause) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; - if (hw->fc.disable_fc_autoneg) - pause->autoneg = 0; - else + if (ixgbe_device_supports_autoneg_fc(hw) && + !hw->fc.disable_fc_autoneg) pause->autoneg = 1; + else + pause->autoneg = 0; if (hw->fc.current_mode == ixgbe_fc_rx_pause) { pause->rx_pause = 1; @@ -390,34 +379,27 @@ static void ixgbe_get_pauseparam(struct net_device *netdev, } 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 ethtool_pauseparam *pause) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; - struct ixgbe_fc_info fc; + struct ixgbe_fc_info fc = hw->fc; -#ifdef CONFIG_DCB - if (adapter->dcb_cfg.pfc_mode_enable || - ((hw->mac.type == ixgbe_mac_82598EB) && - (adapter->flags & IXGBE_FLAG_DCB_ENABLED))) + /* 82598 does no support link flow control with DCB enabled */ + if ((hw->mac.type == ixgbe_mac_82598EB) && + (adapter->flags & IXGBE_FLAG_DCB_ENABLED)) return -EINVAL; -#endif - fc = hw->fc; + /* some devices do not support autoneg of link flow control */ + if ((pause->autoneg == AUTONEG_ENABLE) && + !ixgbe_device_supports_autoneg_fc(hw)) + return -EINVAL; - if (pause->autoneg != AUTONEG_ENABLE) - fc.disable_fc_autoneg = true; - else - fc.disable_fc_autoneg = false; + fc.disable_fc_autoneg = (pause->autoneg != AUTONEG_ENABLE); if ((pause->rx_pause && pause->tx_pause) || pause->autoneg) fc.requested_mode = ixgbe_fc_full; @@ -425,14 +407,8 @@ static int ixgbe_set_pauseparam(struct net_device *netdev, 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 + fc.requested_mode = ixgbe_fc_none; /* if the thing changed then we'll update and use new autoneg */ if (memcmp(&fc, &hw->fc, sizeof(struct ixgbe_fc_info))) { @@ -460,14 +436,14 @@ static void ixgbe_set_msglevel(struct net_device *netdev, u32 data) static int ixgbe_get_regs_len(struct net_device *netdev) { -#define IXGBE_REGS_LEN 1129 +#define IXGBE_REGS_LEN 1139 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 ethtool_regs *regs, void *p) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; @@ -476,7 +452,8 @@ static void ixgbe_get_regs(struct net_device *netdev, memset(p, 0, IXGBE_REGS_LEN * sizeof(u32)); - regs->version = (1 << 24) | hw->revision_id << 16 | hw->device_id; + regs->version = hw->mac.type << 24 | hw->revision_id << 16 | + hw->device_id; /* General Registers */ regs_buff[0] = IXGBE_READ_REG(hw, IXGBE_CTRL); @@ -619,22 +596,53 @@ static void ixgbe_get_regs(struct net_device *netdev, 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)); + regs_buff[829] = IXGBE_READ_REG(hw, IXGBE_RMCS); /* same as FCCFG */ + regs_buff[831] = IXGBE_READ_REG(hw, IXGBE_PDPMCS); /* same as RTTPCS */ + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + regs_buff[830] = IXGBE_READ_REG(hw, IXGBE_DPMCS); + regs_buff[832] = IXGBE_READ_REG(hw, IXGBE_RUPPBMR); + for (i = 0; i < 8; i++) + regs_buff[833 + i] = + IXGBE_READ_REG(hw, IXGBE_RT2CR(i)); + for (i = 0; i < 8; i++) + regs_buff[841 + i] = + IXGBE_READ_REG(hw, IXGBE_RT2SR(i)); + for (i = 0; i < 8; i++) + regs_buff[849 + i] = + IXGBE_READ_REG(hw, IXGBE_TDTQ2TCCR(i)); + for (i = 0; i < 8; i++) + regs_buff[857 + i] = + IXGBE_READ_REG(hw, IXGBE_TDTQ2TCSR(i)); + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + regs_buff[830] = IXGBE_READ_REG(hw, IXGBE_RTTDCS); + regs_buff[832] = IXGBE_READ_REG(hw, IXGBE_RTRPCS); + for (i = 0; i < 8; i++) + regs_buff[833 + i] = + IXGBE_READ_REG(hw, IXGBE_RTRPT4C(i)); + for (i = 0; i < 8; i++) + regs_buff[841 + i] = + IXGBE_READ_REG(hw, IXGBE_RTRPT4S(i)); + for (i = 0; i < 8; i++) + regs_buff[849 + i] = + IXGBE_READ_REG(hw, IXGBE_RTTDT2C(i)); + for (i = 0; i < 8; i++) + regs_buff[857 + i] = + IXGBE_READ_REG(hw, IXGBE_RTTDT2S(i)); + break; + default: + break; + } + for (i = 0; i < 8; i++) - regs_buff[865 + i] = IXGBE_READ_REG(hw, IXGBE_TDPT2TCCR(i)); + regs_buff[865 + i] = + IXGBE_READ_REG(hw, IXGBE_TDPT2TCCR(i)); /* same as RTTPT2C */ for (i = 0; i < 8; i++) - regs_buff[873 + i] = IXGBE_READ_REG(hw, IXGBE_TDPT2TCSR(i)); + regs_buff[873 + i] = + IXGBE_READ_REG(hw, IXGBE_TDPT2TCSR(i)); /* same as RTTPT2S */ /* Statistics */ regs_buff[881] = IXGBE_GET_STAT(adapter, crcerrs); @@ -774,6 +782,20 @@ static void ixgbe_get_regs(struct net_device *netdev, /* 82599 X540 specific registers */ regs_buff[1128] = IXGBE_READ_REG(hw, IXGBE_MFLCN); + + /* 82599 X540 specific DCB registers */ + regs_buff[1129] = IXGBE_READ_REG(hw, IXGBE_RTRUP2TC); + regs_buff[1130] = IXGBE_READ_REG(hw, IXGBE_RTTUP2TC); + for (i = 0; i < 4; i++) + regs_buff[1131 + i] = IXGBE_READ_REG(hw, IXGBE_TXLLQ(i)); + regs_buff[1135] = IXGBE_READ_REG(hw, IXGBE_RTTBCNRM); + /* same as RTTQCNRM */ + regs_buff[1136] = IXGBE_READ_REG(hw, IXGBE_RTTBCNRD); + /* same as RTTQCNRR */ + + /* X540 specific DCB registers */ + regs_buff[1137] = IXGBE_READ_REG(hw, IXGBE_RTTQCNCR); + regs_buff[1138] = IXGBE_READ_REG(hw, IXGBE_RTTQCNTG); } static int ixgbe_get_eeprom_len(struct net_device *netdev) @@ -783,7 +805,7 @@ static int ixgbe_get_eeprom_len(struct net_device *netdev) } static int ixgbe_get_eeprom(struct net_device *netdev, - struct ethtool_eeprom *eeprom, u8 *bytes) + struct ethtool_eeprom *eeprom, u8 *bytes) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; @@ -889,7 +911,7 @@ err: } static void ixgbe_get_drvinfo(struct net_device *netdev, - struct ethtool_drvinfo *drvinfo) + struct ethtool_drvinfo *drvinfo) { struct ixgbe_adapter *adapter = netdev_priv(netdev); u32 nvm_track_id; @@ -911,7 +933,7 @@ static void ixgbe_get_drvinfo(struct net_device *netdev, } static void ixgbe_get_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_ring *tx_ring = adapter->tx_ring[0]; @@ -924,27 +946,26 @@ static void ixgbe_get_ringparam(struct net_device *netdev, } static int ixgbe_set_ringparam(struct net_device *netdev, - struct ethtool_ringparam *ring) + struct ethtool_ringparam *ring) { struct ixgbe_adapter *adapter = netdev_priv(netdev); - struct ixgbe_ring *temp_tx_ring, *temp_rx_ring; + struct ixgbe_ring *temp_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 = clamp_t(u32, ring->tx_pending, + IXGBE_MIN_TXD, 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)) { + new_rx_count = clamp_t(u32, ring->rx_pending, + IXGBE_MIN_RXD, IXGBE_MAX_RXD); + new_rx_count = ALIGN(new_rx_count, IXGBE_REQ_RX_DESCRIPTOR_MULTIPLE); + + if ((new_tx_count == adapter->tx_ring_count) && + (new_rx_count == adapter->rx_ring_count)) { /* nothing to do */ return 0; } @@ -962,81 +983,80 @@ static int ixgbe_set_ringparam(struct net_device *netdev, goto clear_reset; } - temp_tx_ring = vmalloc(adapter->num_tx_queues * sizeof(struct ixgbe_ring)); - if (!temp_tx_ring) { + /* allocate temporary buffer to store rings in */ + i = max_t(int, adapter->num_tx_queues, adapter->num_rx_queues); + temp_ring = vmalloc(i * sizeof(struct ixgbe_ring)); + + if (!temp_ring) { err = -ENOMEM; goto clear_reset; } + ixgbe_down(adapter); + + /* + * Setup new Tx resources and free the old Tx resources in that order. + * We can then assign the new resources to the rings via a memcpy. + * The advantage to this approach is that we are guaranteed to still + * have resources even in the case of an allocation failure. + */ if (new_tx_count != adapter->tx_ring_count) { for (i = 0; i < adapter->num_tx_queues; i++) { - memcpy(&temp_tx_ring[i], adapter->tx_ring[i], + memcpy(&temp_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]); + + temp_ring[i].count = new_tx_count; + err = ixgbe_setup_tx_resources(&temp_ring[i]); if (err) { while (i) { i--; - ixgbe_free_tx_resources(&temp_tx_ring[i]); + ixgbe_free_tx_resources(&temp_ring[i]); } - goto clear_reset; + goto err_setup; } } - need_update = true; - } - temp_rx_ring = vmalloc(adapter->num_rx_queues * sizeof(struct ixgbe_ring)); - if (!temp_rx_ring) { - err = -ENOMEM; - goto err_setup; + for (i = 0; i < adapter->num_tx_queues; i++) { + ixgbe_free_tx_resources(adapter->tx_ring[i]); + + memcpy(adapter->tx_ring[i], &temp_ring[i], + sizeof(struct ixgbe_ring)); + } + + adapter->tx_ring_count = new_tx_count; } + /* Repeat the process for the Rx rings if needed */ if (new_rx_count != adapter->rx_ring_count) { for (i = 0; i < adapter->num_rx_queues; i++) { - memcpy(&temp_rx_ring[i], adapter->rx_ring[i], + memcpy(&temp_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]); + + temp_ring[i].count = new_rx_count; + err = ixgbe_setup_rx_resources(&temp_ring[i]); if (err) { while (i) { i--; - ixgbe_free_rx_resources(&temp_rx_ring[i]); + ixgbe_free_rx_resources(&temp_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); + for (i = 0; i < adapter->num_rx_queues; i++) { + ixgbe_free_rx_resources(adapter->rx_ring[i]); - /* 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; + memcpy(adapter->rx_ring[i], &temp_ring[i], + sizeof(struct ixgbe_ring)); } - /* 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); + adapter->rx_ring_count = new_rx_count; } - vfree(temp_rx_ring); err_setup: - vfree(temp_tx_ring); + ixgbe_up(adapter); + vfree(temp_ring); clear_reset: clear_bit(__IXGBE_RESETTING, &adapter->state); return err; @@ -1055,7 +1075,7 @@ static int ixgbe_get_sset_count(struct net_device *netdev, int sset) } static void ixgbe_get_ethtool_stats(struct net_device *netdev, - struct ethtool_stats *stats, u64 *data) + struct ethtool_stats *stats, u64 *data) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct rtnl_link_stats64 temp; @@ -1077,26 +1097,41 @@ static void ixgbe_get_ethtool_stats(struct net_device *netdev, p = (char *) adapter + ixgbe_gstrings_stats[i].stat_offset; break; + default: + data[i] = 0; + continue; } data[i] = (ixgbe_gstrings_stats[i].sizeof_stat == - sizeof(u64)) ? *(u64 *)p : *(u32 *)p; + sizeof(u64)) ? *(u64 *)p : *(u32 *)p; } - for (j = 0; j < IXGBE_NUM_RX_QUEUES; j++) { + for (j = 0; j < netdev->num_tx_queues; j++) { ring = adapter->tx_ring[j]; if (!ring) { data[i] = 0; data[i+1] = 0; i += 2; +#ifdef BP_EXTENDED_STATS + data[i] = 0; + data[i+1] = 0; + data[i+2] = 0; + i += 3; +#endif continue; } do { - start = u64_stats_fetch_begin_bh(&ring->syncp); + start = u64_stats_fetch_begin_irq(&ring->syncp); data[i] = ring->stats.packets; data[i+1] = ring->stats.bytes; - } while (u64_stats_fetch_retry_bh(&ring->syncp, start)); + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); i += 2; +#ifdef BP_EXTENDED_STATS + data[i] = ring->stats.yields; + data[i+1] = ring->stats.misses; + data[i+2] = ring->stats.cleaned; + i += 3; +#endif } for (j = 0; j < IXGBE_NUM_RX_QUEUES; j++) { ring = adapter->rx_ring[j]; @@ -1104,15 +1139,27 @@ static void ixgbe_get_ethtool_stats(struct net_device *netdev, data[i] = 0; data[i+1] = 0; i += 2; +#ifdef BP_EXTENDED_STATS + data[i] = 0; + data[i+1] = 0; + data[i+2] = 0; + i += 3; +#endif continue; } do { - start = u64_stats_fetch_begin_bh(&ring->syncp); + start = u64_stats_fetch_begin_irq(&ring->syncp); data[i] = ring->stats.packets; data[i+1] = ring->stats.bytes; - } while (u64_stats_fetch_retry_bh(&ring->syncp, start)); + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); i += 2; +#ifdef BP_EXTENDED_STATS + data[i] = ring->stats.yields; + data[i+1] = ring->stats.misses; + data[i+2] = ring->stats.cleaned; + i += 3; +#endif } for (j = 0; j < IXGBE_MAX_PACKET_BUFFERS; j++) { @@ -1126,15 +1173,17 @@ static void ixgbe_get_ethtool_stats(struct net_device *netdev, } static void ixgbe_get_strings(struct net_device *netdev, u32 stringset, - u8 *data) + u8 *data) { char *p = (char *)data; int i; switch (stringset) { case ETH_SS_TEST: - memcpy(data, *ixgbe_gstrings_test, - IXGBE_TEST_LEN * ETH_GSTRING_LEN); + for (i = 0; i < IXGBE_TEST_LEN; i++) { + memcpy(data, ixgbe_gstrings_test[i], ETH_GSTRING_LEN); + data += ETH_GSTRING_LEN; + } break; case ETH_SS_STATS: for (i = 0; i < IXGBE_GLOBAL_STATS_LEN; i++) { @@ -1147,12 +1196,28 @@ static void ixgbe_get_strings(struct net_device *netdev, u32 stringset, p += ETH_GSTRING_LEN; sprintf(p, "tx_queue_%u_bytes", i); p += ETH_GSTRING_LEN; +#ifdef BP_EXTENDED_STATS + sprintf(p, "tx_queue_%u_bp_napi_yield", i); + p += ETH_GSTRING_LEN; + sprintf(p, "tx_queue_%u_bp_misses", i); + p += ETH_GSTRING_LEN; + sprintf(p, "tx_queue_%u_bp_cleaned", i); + p += ETH_GSTRING_LEN; +#endif /* BP_EXTENDED_STATS */ } for (i = 0; i < IXGBE_NUM_RX_QUEUES; i++) { sprintf(p, "rx_queue_%u_packets", i); p += ETH_GSTRING_LEN; sprintf(p, "rx_queue_%u_bytes", i); p += ETH_GSTRING_LEN; +#ifdef BP_EXTENDED_STATS + sprintf(p, "rx_queue_%u_bp_poll_yield", i); + p += ETH_GSTRING_LEN; + sprintf(p, "rx_queue_%u_bp_misses", i); + p += ETH_GSTRING_LEN; + sprintf(p, "rx_queue_%u_bp_cleaned", i); + p += ETH_GSTRING_LEN; +#endif /* BP_EXTENDED_STATS */ } for (i = 0; i < IXGBE_MAX_PACKET_BUFFERS; i++) { sprintf(p, "tx_pb_%u_pxon", i); @@ -1176,6 +1241,11 @@ static int ixgbe_link_test(struct ixgbe_adapter *adapter, u64 *data) struct ixgbe_hw *hw = &adapter->hw; bool link_up; u32 link_speed = 0; + + if (ixgbe_removed(hw->hw_addr)) { + *data = 1; + return 1; + } *data = 0; hw->mac.ops.check_link(hw, &link_speed, &link_up, true); @@ -1271,61 +1341,60 @@ static bool reg_pattern_test(struct ixgbe_adapter *adapter, u64 *data, int reg, static const u32 test_pattern[] = { 0x5A5A5A5A, 0xA5A5A5A5, 0x00000000, 0xFFFFFFFF}; + if (ixgbe_removed(adapter->hw.hw_addr)) { + *data = 1; + return 1; + } 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); + before = ixgbe_read_reg(&adapter->hw, reg); + ixgbe_write_reg(&adapter->hw, reg, test_pattern[pat] & write); + val = ixgbe_read_reg(&adapter->hw, reg); if (val != (test_pattern[pat] & write & mask)) { - e_err(drv, "pattern test reg %04X failed: got " - "0x%08X expected 0x%08X\n", + 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; + ixgbe_write_reg(&adapter->hw, reg, before); + return true; } - writel(before, adapter->hw.hw_addr + reg); + ixgbe_write_reg(&adapter->hw, reg, before); } - return 0; + return false; } 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 (ixgbe_removed(adapter->hw.hw_addr)) { + *data = 1; + return 1; + } + before = ixgbe_read_reg(&adapter->hw, reg); + ixgbe_write_reg(&adapter->hw, reg, write & mask); + val = ixgbe_read_reg(&adapter->hw, reg); if ((write & mask) != (val & mask)) { - e_err(drv, "set/check reg %04X test failed: got 0x%08X " - "expected 0x%08X\n", reg, (val & mask), (write & mask)); + 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; + ixgbe_write_reg(&adapter->hw, reg, before); + return true; } - writel(before, (adapter->hw.hw_addr + reg)); - return 0; + ixgbe_write_reg(&adapter->hw, reg, before); + return false; } -#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; + if (ixgbe_removed(adapter->hw.hw_addr)) { + e_err(drv, "Adapter removed - register test blocked\n"); + *data = 1; + return 1; + } switch (adapter->hw.mac.type) { case ixgbe_mac_82598EB: toggle = 0x7FFFF3FF; @@ -1348,18 +1417,18 @@ static int ixgbe_reg_test(struct ixgbe_adapter *adapter, u64 *data) * 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; + 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); + 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); + ixgbe_write_reg(&adapter->hw, IXGBE_STATUS, before); /* * Perform the remainder of the register test, looping through @@ -1367,38 +1436,47 @@ static int ixgbe_reg_test(struct ixgbe_adapter *adapter, u64 *data) */ while (test->reg) { for (i = 0; i < test->array_len; i++) { + bool b = false; + switch (test->test_type) { case PATTERN_TEST: - REG_PATTERN_TEST(test->reg + (i * 0x40), - test->mask, - test->write); + b = reg_pattern_test(adapter, data, + 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); + b = reg_set_and_check(adapter, data, + test->reg + (i * 0x40), + test->mask, + test->write); break; case WRITE_NO_TEST: - writel(test->write, - (adapter->hw.hw_addr + test->reg) - + (i * 0x40)); + ixgbe_write_reg(&adapter->hw, + test->reg + (i * 0x40), + test->write); break; case TABLE32_TEST: - REG_PATTERN_TEST(test->reg + (i * 4), - test->mask, - test->write); + b = reg_pattern_test(adapter, data, + test->reg + (i * 4), + test->mask, + test->write); break; case TABLE64_TEST_LO: - REG_PATTERN_TEST(test->reg + (i * 8), - test->mask, - test->write); + b = reg_pattern_test(adapter, data, + 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); + b = reg_pattern_test(adapter, data, + (test->reg + 4) + (i * 8), + test->mask, + test->write); break; } + if (b) + return 1; } test++; } @@ -1447,10 +1525,10 @@ static int ixgbe_intr_test(struct ixgbe_adapter *adapter, u64 *data) return -1; } } else if (!request_irq(irq, ixgbe_test_intr, IRQF_PROBE_SHARED, - netdev->name, netdev)) { + netdev->name, netdev)) { shared_int = false; } else if (request_irq(irq, ixgbe_test_intr, IRQF_SHARED, - netdev->name, netdev)) { + netdev->name, netdev)) { *data = 1; return -1; } @@ -1477,9 +1555,9 @@ static int ixgbe_intr_test(struct ixgbe_adapter *adapter, u64 *data) */ adapter->test_icr = 0; IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, - ~mask & 0x00007FFF); + ~mask & 0x00007FFF); IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS, - ~mask & 0x00007FFF); + ~mask & 0x00007FFF); IXGBE_WRITE_FLUSH(&adapter->hw); usleep_range(10000, 20000); @@ -1501,7 +1579,7 @@ static int ixgbe_intr_test(struct ixgbe_adapter *adapter, u64 *data) IXGBE_WRITE_FLUSH(&adapter->hw); usleep_range(10000, 20000); - if (!(adapter->test_icr &mask)) { + if (!(adapter->test_icr & mask)) { *data = 4; break; } @@ -1516,9 +1594,9 @@ static int ixgbe_intr_test(struct ixgbe_adapter *adapter, u64 *data) */ adapter->test_icr = 0; IXGBE_WRITE_REG(&adapter->hw, IXGBE_EIMC, - ~mask & 0x00007FFF); + ~mask & 0x00007FFF); IXGBE_WRITE_REG(&adapter->hw, IXGBE_EICS, - ~mask & 0x00007FFF); + ~mask & 0x00007FFF); IXGBE_WRITE_FLUSH(&adapter->hw); usleep_range(10000, 20000); @@ -1591,7 +1669,6 @@ static int ixgbe_setup_desc_rings(struct ixgbe_adapter *adapter) 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) @@ -1616,8 +1693,6 @@ static int ixgbe_setup_desc_rings(struct ixgbe_adapter *adapter) 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_2K; - rx_ring->numa_node = adapter->node; err = ixgbe_setup_rx_resources(rx_ring); if (err) { @@ -1645,16 +1720,9 @@ 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(hw, IXGBE_MACC); - reg_data |= IXGBE_MACC_FLU; - IXGBE_WRITE_REG(hw, IXGBE_MACC, reg_data); - } - /* right now we only support MAC loopback in the driver */ - reg_data = IXGBE_READ_REG(hw, IXGBE_HLREG0); /* Setup MAC loopback */ + reg_data = IXGBE_READ_REG(hw, IXGBE_HLREG0); reg_data |= IXGBE_HLREG0_LPBK; IXGBE_WRITE_REG(hw, IXGBE_HLREG0, reg_data); @@ -1662,10 +1730,19 @@ static int ixgbe_setup_loopback_test(struct ixgbe_adapter *adapter) reg_data |= IXGBE_FCTRL_BAM | IXGBE_FCTRL_SBP | IXGBE_FCTRL_MPE; IXGBE_WRITE_REG(hw, IXGBE_FCTRL, reg_data); - reg_data = IXGBE_READ_REG(hw, IXGBE_AUTOC); - reg_data &= ~IXGBE_AUTOC_LMS_MASK; - reg_data |= IXGBE_AUTOC_LMS_10G_LINK_NO_AN | IXGBE_AUTOC_FLU; - IXGBE_WRITE_REG(hw, IXGBE_AUTOC, 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(hw, IXGBE_MACC); + reg_data |= IXGBE_MACC_FLU; + IXGBE_WRITE_REG(hw, IXGBE_MACC, reg_data); + } else { + if (hw->mac.orig_autoc) { + reg_data = hw->mac.orig_autoc | IXGBE_AUTOC_FLU; + IXGBE_WRITE_REG(hw, IXGBE_AUTOC, reg_data); + } else { + return 10; + } + } IXGBE_WRITE_FLUSH(hw); usleep_range(10000, 20000); @@ -1703,63 +1780,72 @@ static void ixgbe_loopback_cleanup(struct ixgbe_adapter *adapter) } static void ixgbe_create_lbtest_frame(struct sk_buff *skb, - unsigned int frame_size) + 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); + frame_size >>= 1; + memset(&skb->data[frame_size], 0xAA, frame_size / 2 - 1); + memset(&skb->data[frame_size + 10], 0xBE, 1); + memset(&skb->data[frame_size + 12], 0xAF, 1); } -static int ixgbe_check_lbtest_frame(struct sk_buff *skb, - unsigned int frame_size) +static bool ixgbe_check_lbtest_frame(struct ixgbe_rx_buffer *rx_buffer, + 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; + unsigned char *data; + bool match = true; + + frame_size >>= 1; + + data = kmap(rx_buffer->page) + rx_buffer->page_offset; + + if (data[3] != 0xFF || + data[frame_size + 10] != 0xBE || + data[frame_size + 12] != 0xAF) + match = false; + + kunmap(rx_buffer->page); + + return match; } static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring, - struct ixgbe_ring *tx_ring, - unsigned int size) + 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; + struct ixgbe_rx_buffer *rx_buffer; + struct ixgbe_tx_buffer *tx_buffer; 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); + rx_desc = IXGBE_RX_DESC(rx_ring, rx_ntc); - while (staterr & IXGBE_RXD_STAT_DD) { + while (ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_DD)) { /* check Rx buffer */ - rx_buffer_info = &rx_ring->rx_buffer_info[rx_ntc]; + rx_buffer = &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; + /* sync Rx buffer for CPU read */ + dma_sync_single_for_cpu(rx_ring->dev, + rx_buffer->dma, + ixgbe_rx_bufsz(rx_ring), + DMA_FROM_DEVICE); /* verify contents of skb */ - if (!ixgbe_check_lbtest_frame(rx_buffer_info->skb, size)) + if (ixgbe_check_lbtest_frame(rx_buffer, size)) count++; + /* sync Rx buffer for device write */ + dma_sync_single_for_device(rx_ring->dev, + rx_buffer->dma, + ixgbe_rx_bufsz(rx_ring), + DMA_FROM_DEVICE); + /* 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); + tx_buffer = &tx_ring->tx_buffer_info[tx_ntc]; + ixgbe_unmap_and_free_tx_resource(tx_ring, tx_buffer); /* increment Rx/Tx next to clean counters */ rx_ntc++; @@ -1770,10 +1856,11 @@ static u16 ixgbe_clean_test_rings(struct ixgbe_ring *rx_ring, 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); + rx_desc = IXGBE_RX_DESC(rx_ring, rx_ntc); } + netdev_tx_reset_queue(txring_txq(tx_ring)); + /* re-map buffers to ring, store next to clean values */ ixgbe_alloc_rx_buffers(rx_ring, count); rx_ring->next_to_clean = rx_ntc; @@ -1790,6 +1877,10 @@ static int ixgbe_run_loopback_test(struct ixgbe_adapter *adapter) unsigned int size = 1024; netdev_tx_t tx_ret_val; struct sk_buff *skb; + u32 flags_orig = adapter->flags; + + /* DCB can modify the frames on Tx */ + adapter->flags &= ~IXGBE_FLAG_DCB_ENABLED; /* allocate test skb */ skb = alloc_skb(size, GFP_KERNEL); @@ -1842,6 +1933,7 @@ static int ixgbe_run_loopback_test(struct ixgbe_adapter *adapter) /* free the original skb */ kfree_skb(skb); + adapter->flags = flags_orig; return ret_val; } @@ -1864,34 +1956,35 @@ out: } static void ixgbe_diag_test(struct net_device *netdev, - struct ethtool_test *eth_test, u64 *data) + struct ethtool_test *eth_test, u64 *data) { struct ixgbe_adapter *adapter = netdev_priv(netdev); bool if_running = netif_running(netdev); + if (ixgbe_removed(adapter->hw.hw_addr)) { + e_err(hw, "Adapter removed - test blocked\n"); + data[0] = 1; + data[1] = 1; + data[2] = 1; + data[3] = 1; + data[4] = 1; + eth_test->flags |= ETH_TEST_FL_FAILED; + return; + } set_bit(__IXGBE_TESTING, &adapter->state); if (eth_test->flags == ETH_TEST_FL_OFFLINE) { - /* 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; + struct ixgbe_hw *hw = &adapter->hw; if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { int i; for (i = 0; i < adapter->num_vfs; i++) { if (adapter->vfinfo[i].clear_to_send) { - netdev_warn(netdev, "%s", - "offline diagnostic is not " - "supported when VFs are " - "present\n"); + netdev_warn(netdev, "offline diagnostic is not supported when VFs are present\n"); data[0] = 1; data[1] = 1; data[2] = 1; data[3] = 1; + data[4] = 1; eth_test->flags |= ETH_TEST_FL_FAILED; clear_bit(__IXGBE_TESTING, &adapter->state); @@ -1900,6 +1993,15 @@ static void ixgbe_diag_test(struct net_device *netdev, } } + /* Offline tests */ + e_info(hw, "offline testing starting\n"); + + /* Link test performed before hardware reset so autoneg doesn't + * interfere with test result + */ + if (ixgbe_link_test(adapter, &data[4])) + eth_test->flags |= ETH_TEST_FL_FAILED; + if (if_running) /* indicate we're in test mode */ dev_close(netdev); @@ -1924,8 +2026,7 @@ static void ixgbe_diag_test(struct net_device *netdev, * loopback diagnostic. */ if (adapter->flags & (IXGBE_FLAG_SRIOV_ENABLED | IXGBE_FLAG_VMDQ_ENABLED)) { - e_info(hw, "Skip MAC loopback diagnostic in VT " - "mode\n"); + e_info(hw, "Skip MAC loopback diagnostic in VT mode\n"); data[3] = 0; goto skip_loopback; } @@ -1938,16 +2039,20 @@ static void ixgbe_diag_test(struct net_device *netdev, skip_loopback: ixgbe_reset(adapter); + /* clear testing bit and return adapter to previous state */ clear_bit(__IXGBE_TESTING, &adapter->state); if (if_running) dev_open(netdev); + else if (hw->mac.ops.disable_tx_laser) + hw->mac.ops.disable_tx_laser(hw); } else { e_info(hw, "online testing starting\n"); + /* Online tests */ if (ixgbe_link_test(adapter, &data[4])) eth_test->flags |= ETH_TEST_FL_FAILED; - /* Online tests aren't run; pass by default */ + /* Offline tests aren't run; pass by default */ data[0] = 0; data[1] = 0; data[2] = 0; @@ -1955,61 +2060,21 @@ skip_loopback: 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 ethtool_wolinfo *wol) { struct ixgbe_hw *hw = &adapter->hw; - int retval = 1; - u16 wol_cap = adapter->eeprom_cap & IXGBE_DEVICE_CAPS_WOL_MASK; - - /* WOL not supported except for the following */ - switch(hw->device_id) { - case IXGBE_DEV_ID_82599_SFP: - /* Only these subdevices could supports WOL */ - switch (hw->subsystem_device_id) { - case IXGBE_SUBDEV_ID_82599_560FLR: - /* only support first port */ - if (hw->bus.func != 0) { - wol->supported = 0; - break; - } - case IXGBE_SUBDEV_ID_82599_SFP: - retval = 0; - break; - default: - wol->supported = 0; - break; - } - 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; - case IXGBE_DEV_ID_X540T: - /* check eeprom to see if enabled wol */ - if ((wol_cap == IXGBE_DEVICE_CAPS_WOL_PORT0_1) || - ((wol_cap == IXGBE_DEVICE_CAPS_WOL_PORT0) && - (hw->bus.func == 0))) { - retval = 0; - break; - } + int retval = 0; - /* All others not supported */ - wol->supported = 0; - break; - default: + /* WOL not supported for all devices */ + if (!ixgbe_wol_supported(adapter, hw->device_id, + hw->subsystem_device_id)) { + retval = 1; wol->supported = 0; } @@ -2017,12 +2082,12 @@ static int ixgbe_wol_exclusion(struct ixgbe_adapter *adapter, } static void ixgbe_get_wol(struct net_device *netdev, - struct ethtool_wolinfo *wol) + struct ethtool_wolinfo *wol) { struct ixgbe_adapter *adapter = netdev_priv(netdev); wol->supported = WAKE_UCAST | WAKE_MCAST | - WAKE_BCAST | WAKE_MAGIC; + WAKE_BCAST | WAKE_MAGIC; wol->wolopts = 0; if (ixgbe_wol_exclusion(adapter, wol) || @@ -2104,12 +2169,10 @@ static int ixgbe_set_phys_id(struct net_device *netdev, } static int ixgbe_get_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + 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 */ if (adapter->rx_itr_setting <= 1) ec->rx_coalesce_usecs = adapter->rx_itr_setting; @@ -2133,60 +2196,54 @@ static int ixgbe_get_coalesce(struct net_device *netdev, * 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) +static bool ixgbe_update_rsc(struct ixgbe_adapter *adapter) { struct net_device *netdev = adapter->netdev; - if (!(adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE)) + /* nothing to do if LRO or RSC are not enabled */ + if (!(adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE) || + !(netdev->features & NETIF_F_LRO)) return false; - /* if interrupt rate is too high then disable RSC */ - if (ec->rx_coalesce_usecs != 1 && - ec->rx_coalesce_usecs <= (IXGBE_MIN_RSC_ITR >> 2)) { - 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); + /* check the feature flag value and enable RSC if necessary */ + if (adapter->rx_itr_setting == 1 || + adapter->rx_itr_setting > IXGBE_MIN_RSC_ITR) { + if (!(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)) { adapter->flags2 |= IXGBE_FLAG2_RSC_ENABLED; + e_info(probe, "rx-usecs value high enough to re-enable RSC\n"); return true; } + /* if interrupt rate is too high then disable RSC */ + } else if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) { + adapter->flags2 &= ~IXGBE_FLAG2_RSC_ENABLED; + e_info(probe, "rx-usecs set too low, disabling RSC\n"); + return true; } return false; } static int ixgbe_set_coalesce(struct net_device *netdev, - struct ethtool_coalesce *ec) + struct ethtool_coalesce *ec) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_q_vector *q_vector; int i; - int num_vectors; - u16 tx_itr_param, rx_itr_param; + u16 tx_itr_param, rx_itr_param, tx_itr_prev; 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 (adapter->q_vector[0]->tx.count && adapter->q_vector[0]->rx.count) { + /* reject Tx specific changes in case of mixed RxTx vectors */ + if (ec->tx_coalesce_usecs) + return -EINVAL; + tx_itr_prev = adapter->rx_itr_setting; + } else { + tx_itr_prev = adapter->tx_itr_setting; + } if ((ec->rx_coalesce_usecs > (IXGBE_MAX_EITR >> 2)) || (ec->tx_coalesce_usecs > (IXGBE_MAX_EITR >> 2))) return -EINVAL; - /* check the old value and enable RSC if necessary */ - need_reset = ixgbe_update_rsc(adapter, ec); - if (ec->rx_coalesce_usecs > 1) adapter->rx_itr_setting = ec->rx_coalesce_usecs << 2; else @@ -2207,14 +2264,28 @@ static int ixgbe_set_coalesce(struct net_device *netdev, else tx_itr_param = adapter->tx_itr_setting; - if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) - num_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - else - num_vectors = 1; + /* mixed Rx/Tx */ + if (adapter->q_vector[0]->tx.count && adapter->q_vector[0]->rx.count) + adapter->tx_itr_setting = adapter->rx_itr_setting; + +#if IS_ENABLED(CONFIG_BQL) + /* detect ITR changes that require update of TXDCTL.WTHRESH */ + if ((adapter->tx_itr_setting != 1) && + (adapter->tx_itr_setting < IXGBE_100K_ITR)) { + if ((tx_itr_prev == 1) || + (tx_itr_prev >= IXGBE_100K_ITR)) + need_reset = true; + } else { + if ((tx_itr_prev != 1) && + (tx_itr_prev < IXGBE_100K_ITR)) + need_reset = true; + } +#endif + /* check the old value and enable RSC if necessary */ + need_reset |= ixgbe_update_rsc(adapter); - for (i = 0; i < num_vectors; i++) { + for (i = 0; i < adapter->num_q_vectors; i++) { q_vector = adapter->q_vector[i]; - q_vector->tx.work_limit = adapter->tx_work_limit; if (q_vector->tx.count && !q_vector->rx.count) /* tx only */ q_vector->itr = tx_itr_param; @@ -2241,13 +2312,13 @@ static int ixgbe_get_ethtool_fdir_entry(struct ixgbe_adapter *adapter, 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 hlist_node *node2; struct ixgbe_fdir_filter *rule = NULL; /* report total rule count */ cmd->data = (1024 << adapter->fdir_pballoc) - 2; - hlist_for_each_entry_safe(rule, node, node2, + hlist_for_each_entry_safe(rule, node2, &adapter->fdir_filter_list, fdir_node) { if (fsp->location <= rule->sw_idx) break; @@ -2308,14 +2379,14 @@ static int ixgbe_get_ethtool_fdir_all(struct ixgbe_adapter *adapter, struct ethtool_rxnfc *cmd, u32 *rule_locs) { - struct hlist_node *node, *node2; + struct hlist_node *node2; struct ixgbe_fdir_filter *rule; int cnt = 0; /* report total rule count */ cmd->data = (1024 << adapter->fdir_pballoc) - 2; - hlist_for_each_entry_safe(rule, node, node2, + hlist_for_each_entry_safe(rule, node2, &adapter->fdir_filter_list, fdir_node) { if (cnt == cmd->rule_cnt) return -EMSGSIZE; @@ -2328,6 +2399,48 @@ static int ixgbe_get_ethtool_fdir_all(struct ixgbe_adapter *adapter, return 0; } +static int ixgbe_get_rss_hash_opts(struct ixgbe_adapter *adapter, + struct ethtool_rxnfc *cmd) +{ + cmd->data = 0; + + /* Report default options for RSS on ixgbe */ + switch (cmd->flow_type) { + case TCP_V4_FLOW: + cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + /* fallthrough */ + case UDP_V4_FLOW: + if (adapter->flags2 & IXGBE_FLAG2_RSS_FIELD_IPV4_UDP) + cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + /* fallthrough */ + case SCTP_V4_FLOW: + case AH_ESP_V4_FLOW: + case AH_V4_FLOW: + case ESP_V4_FLOW: + case IPV4_FLOW: + cmd->data |= RXH_IP_SRC | RXH_IP_DST; + break; + case TCP_V6_FLOW: + cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + /* fallthrough */ + case UDP_V6_FLOW: + if (adapter->flags2 & IXGBE_FLAG2_RSS_FIELD_IPV6_UDP) + cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3; + /* fallthrough */ + case SCTP_V6_FLOW: + case AH_ESP_V6_FLOW: + case AH_V6_FLOW: + case ESP_V6_FLOW: + case IPV6_FLOW: + cmd->data |= RXH_IP_SRC | RXH_IP_DST; + break; + default: + return -EINVAL; + } + + return 0; +} + static int ixgbe_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, u32 *rule_locs) { @@ -2349,6 +2462,9 @@ static int ixgbe_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd, case ETHTOOL_GRXCLSRLALL: ret = ixgbe_get_ethtool_fdir_all(adapter, cmd, rule_locs); break; + case ETHTOOL_GRXFH: + ret = ixgbe_get_rss_hash_opts(adapter, cmd); + break; default: break; } @@ -2361,19 +2477,19 @@ static int ixgbe_update_ethtool_fdir_entry(struct ixgbe_adapter *adapter, u16 sw_idx) { struct ixgbe_hw *hw = &adapter->hw; - struct hlist_node *node, *node2, *parent; - struct ixgbe_fdir_filter *rule; + struct hlist_node *node2; + struct ixgbe_fdir_filter *rule, *parent; int err = -EINVAL; parent = NULL; rule = NULL; - hlist_for_each_entry_safe(rule, node, node2, + hlist_for_each_entry_safe(rule, node2, &adapter->fdir_filter_list, fdir_node) { /* hash found, or no matching entry */ if (rule->sw_idx >= sw_idx) break; - parent = node; + parent = rule; } /* if there is an old rule occupying our place remove it */ @@ -2402,7 +2518,7 @@ static int ixgbe_update_ethtool_fdir_entry(struct ixgbe_adapter *adapter, /* add filter to the list */ if (parent) - hlist_add_after(parent, &input->fdir_node); + hlist_add_after(&parent->fdir_node, &input->fdir_node); else hlist_add_head(&input->fdir_node, &adapter->fdir_filter_list); @@ -2583,6 +2699,110 @@ static int ixgbe_del_ethtool_fdir_entry(struct ixgbe_adapter *adapter, return err; } +#define UDP_RSS_FLAGS (IXGBE_FLAG2_RSS_FIELD_IPV4_UDP | \ + IXGBE_FLAG2_RSS_FIELD_IPV6_UDP) +static int ixgbe_set_rss_hash_opt(struct ixgbe_adapter *adapter, + struct ethtool_rxnfc *nfc) +{ + u32 flags2 = adapter->flags2; + + /* + * RSS does not support anything other than hashing + * to queues on src and dst IPs and ports + */ + if (nfc->data & ~(RXH_IP_SRC | RXH_IP_DST | + RXH_L4_B_0_1 | RXH_L4_B_2_3)) + return -EINVAL; + + switch (nfc->flow_type) { + case TCP_V4_FLOW: + case TCP_V6_FLOW: + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST) || + !(nfc->data & RXH_L4_B_0_1) || + !(nfc->data & RXH_L4_B_2_3)) + return -EINVAL; + break; + case UDP_V4_FLOW: + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST)) + return -EINVAL; + switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { + case 0: + flags2 &= ~IXGBE_FLAG2_RSS_FIELD_IPV4_UDP; + break; + case (RXH_L4_B_0_1 | RXH_L4_B_2_3): + flags2 |= IXGBE_FLAG2_RSS_FIELD_IPV4_UDP; + break; + default: + return -EINVAL; + } + break; + case UDP_V6_FLOW: + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST)) + return -EINVAL; + switch (nfc->data & (RXH_L4_B_0_1 | RXH_L4_B_2_3)) { + case 0: + flags2 &= ~IXGBE_FLAG2_RSS_FIELD_IPV6_UDP; + break; + case (RXH_L4_B_0_1 | RXH_L4_B_2_3): + flags2 |= IXGBE_FLAG2_RSS_FIELD_IPV6_UDP; + break; + default: + return -EINVAL; + } + break; + case AH_ESP_V4_FLOW: + case AH_V4_FLOW: + case ESP_V4_FLOW: + case SCTP_V4_FLOW: + case AH_ESP_V6_FLOW: + case AH_V6_FLOW: + case ESP_V6_FLOW: + case SCTP_V6_FLOW: + if (!(nfc->data & RXH_IP_SRC) || + !(nfc->data & RXH_IP_DST) || + (nfc->data & RXH_L4_B_0_1) || + (nfc->data & RXH_L4_B_2_3)) + return -EINVAL; + break; + default: + return -EINVAL; + } + + /* if we changed something we need to update flags */ + if (flags2 != adapter->flags2) { + struct ixgbe_hw *hw = &adapter->hw; + u32 mrqc = IXGBE_READ_REG(hw, IXGBE_MRQC); + + if ((flags2 & UDP_RSS_FLAGS) && + !(adapter->flags2 & UDP_RSS_FLAGS)) + e_warn(drv, "enabling UDP RSS: fragmented packets may arrive out of order to the stack above\n"); + + adapter->flags2 = flags2; + + /* Perform hash on these packet types */ + mrqc |= IXGBE_MRQC_RSS_FIELD_IPV4 + | IXGBE_MRQC_RSS_FIELD_IPV4_TCP + | IXGBE_MRQC_RSS_FIELD_IPV6 + | IXGBE_MRQC_RSS_FIELD_IPV6_TCP; + + mrqc &= ~(IXGBE_MRQC_RSS_FIELD_IPV4_UDP | + IXGBE_MRQC_RSS_FIELD_IPV6_UDP); + + if (flags2 & IXGBE_FLAG2_RSS_FIELD_IPV4_UDP) + mrqc |= IXGBE_MRQC_RSS_FIELD_IPV4_UDP; + + if (flags2 & IXGBE_FLAG2_RSS_FIELD_IPV6_UDP) + mrqc |= IXGBE_MRQC_RSS_FIELD_IPV6_UDP; + + IXGBE_WRITE_REG(hw, IXGBE_MRQC, mrqc); + } + + return 0; +} + static int ixgbe_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) { struct ixgbe_adapter *adapter = netdev_priv(dev); @@ -2595,6 +2815,9 @@ static int ixgbe_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) case ETHTOOL_SRXCLSRLDEL: ret = ixgbe_del_ethtool_fdir_entry(adapter, cmd); break; + case ETHTOOL_SRXFH: + ret = ixgbe_set_rss_hash_opt(adapter, cmd); + break; default: break; } @@ -2602,6 +2825,233 @@ static int ixgbe_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) return ret; } +static int ixgbe_get_ts_info(struct net_device *dev, + struct ethtool_ts_info *info) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + + switch (adapter->hw.mac.type) { + case ixgbe_mac_X540: + case ixgbe_mac_82599EB: + info->so_timestamping = + SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + + if (adapter->ptp_clock) + info->phc_index = ptp_clock_index(adapter->ptp_clock); + else + info->phc_index = -1; + + info->tx_types = + (1 << HWTSTAMP_TX_OFF) | + (1 << HWTSTAMP_TX_ON); + + info->rx_filters = + (1 << HWTSTAMP_FILTER_NONE) | + (1 << HWTSTAMP_FILTER_PTP_V1_L4_SYNC) | + (1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) | + (1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | + (1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT) | + (1 << HWTSTAMP_FILTER_PTP_V2_SYNC) | + (1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) | + (1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC) | + (1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ) | + (1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) | + (1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ) | + (1 << HWTSTAMP_FILTER_PTP_V2_EVENT); + break; + default: + return ethtool_op_get_ts_info(dev, info); + break; + } + return 0; +} + +static unsigned int ixgbe_max_channels(struct ixgbe_adapter *adapter) +{ + unsigned int max_combined; + u8 tcs = netdev_get_num_tc(adapter->netdev); + + if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) { + /* We only support one q_vector without MSI-X */ + max_combined = 1; + } else if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { + /* SR-IOV currently only allows one queue on the PF */ + max_combined = 1; + } else if (tcs > 1) { + /* For DCB report channels per traffic class */ + if (adapter->hw.mac.type == ixgbe_mac_82598EB) { + /* 8 TC w/ 4 queues per TC */ + max_combined = 4; + } else if (tcs > 4) { + /* 8 TC w/ 8 queues per TC */ + max_combined = 8; + } else { + /* 4 TC w/ 16 queues per TC */ + max_combined = 16; + } + } else if (adapter->atr_sample_rate) { + /* support up to 64 queues with ATR */ + max_combined = IXGBE_MAX_FDIR_INDICES; + } else { + /* support up to 16 queues with RSS */ + max_combined = IXGBE_MAX_RSS_INDICES; + } + + return max_combined; +} + +static void ixgbe_get_channels(struct net_device *dev, + struct ethtool_channels *ch) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + + /* report maximum channels */ + ch->max_combined = ixgbe_max_channels(adapter); + + /* report info for other vector */ + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) { + ch->max_other = NON_Q_VECTORS; + ch->other_count = NON_Q_VECTORS; + } + + /* record RSS queues */ + ch->combined_count = adapter->ring_feature[RING_F_RSS].indices; + + /* nothing else to report if RSS is disabled */ + if (ch->combined_count == 1) + return; + + /* we do not support ATR queueing if SR-IOV is enabled */ + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) + return; + + /* same thing goes for being DCB enabled */ + if (netdev_get_num_tc(dev) > 1) + return; + + /* if ATR is disabled we can exit */ + if (!adapter->atr_sample_rate) + return; + + /* report flow director queues as maximum channels */ + ch->combined_count = adapter->ring_feature[RING_F_FDIR].indices; +} + +static int ixgbe_set_channels(struct net_device *dev, + struct ethtool_channels *ch) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + unsigned int count = ch->combined_count; + + /* verify they are not requesting separate vectors */ + if (!count || ch->rx_count || ch->tx_count) + return -EINVAL; + + /* verify other_count has not changed */ + if (ch->other_count != NON_Q_VECTORS) + return -EINVAL; + + /* verify the number of channels does not exceed hardware limits */ + if (count > ixgbe_max_channels(adapter)) + return -EINVAL; + + /* update feature limits from largest to smallest supported values */ + adapter->ring_feature[RING_F_FDIR].limit = count; + + /* cap RSS limit at 16 */ + if (count > IXGBE_MAX_RSS_INDICES) + count = IXGBE_MAX_RSS_INDICES; + adapter->ring_feature[RING_F_RSS].limit = count; + +#ifdef IXGBE_FCOE + /* cap FCoE limit at 8 */ + if (count > IXGBE_FCRETA_SIZE) + count = IXGBE_FCRETA_SIZE; + adapter->ring_feature[RING_F_FCOE].limit = count; + +#endif + /* use setup TC to update any traffic class queue mapping */ + return ixgbe_setup_tc(dev, netdev_get_num_tc(dev)); +} + +static int ixgbe_get_module_info(struct net_device *dev, + struct ethtool_modinfo *modinfo) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_hw *hw = &adapter->hw; + u32 status; + u8 sff8472_rev, addr_mode; + bool page_swap = false; + + /* Check whether we support SFF-8472 or not */ + status = hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_SFF_8472_COMP, + &sff8472_rev); + if (status != 0) + return -EIO; + + /* addressing mode is not supported */ + status = hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_SFF_8472_SWAP, + &addr_mode); + if (status != 0) + return -EIO; + + if (addr_mode & IXGBE_SFF_ADDRESSING_MODE) { + e_err(drv, "Address change required to access page 0xA2, but not supported. Please report the module type to the driver maintainers.\n"); + page_swap = true; + } + + if (sff8472_rev == IXGBE_SFF_SFF_8472_UNSUP || page_swap) { + /* We have a SFP, but it does not support SFF-8472 */ + modinfo->type = ETH_MODULE_SFF_8079; + modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN; + } else { + /* We have a SFP which supports a revision of SFF-8472. */ + modinfo->type = ETH_MODULE_SFF_8472; + modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; + } + + return 0; +} + +static int ixgbe_get_module_eeprom(struct net_device *dev, + struct ethtool_eeprom *ee, + u8 *data) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct ixgbe_hw *hw = &adapter->hw; + u32 status = IXGBE_ERR_PHY_ADDR_INVALID; + u8 databyte = 0xFF; + int i = 0; + + if (ee->len == 0) + return -EINVAL; + + for (i = ee->offset; i < ee->offset + ee->len; i++) { + /* I2C reads can take long time */ + if (test_bit(__IXGBE_IN_SFP_INIT, &adapter->state)) + return -EBUSY; + + if (i < ETH_MODULE_SFF_8079_LEN) + status = hw->phy.ops.read_i2c_eeprom(hw, i, &databyte); + else + status = hw->phy.ops.read_i2c_sff8472(hw, i, &databyte); + + if (status != 0) + return -EIO; + + data[i - ee->offset] = databyte; + } + + return 0; +} + static const struct ethtool_ops ixgbe_ethtool_ops = { .get_settings = ixgbe_get_settings, .set_settings = ixgbe_set_settings, @@ -2630,9 +3080,14 @@ static const struct ethtool_ops ixgbe_ethtool_ops = { .set_coalesce = ixgbe_set_coalesce, .get_rxnfc = ixgbe_get_rxnfc, .set_rxnfc = ixgbe_set_rxnfc, + .get_channels = ixgbe_get_channels, + .set_channels = ixgbe_set_channels, + .get_ts_info = ixgbe_get_ts_info, + .get_module_info = ixgbe_get_module_info, + .get_module_eeprom = ixgbe_get_module_eeprom, }; void ixgbe_set_ethtool_ops(struct net_device *netdev) { - SET_ETHTOOL_OPS(netdev, &ixgbe_ethtool_ops); + netdev->ethtool_ops = &ixgbe_ethtool_ops; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c index 4bc79424980..25a3dfef33e 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2013 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, @@ -20,6 +20,7 @@ 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 @@ -38,7 +39,7 @@ /** * ixgbe_fcoe_clear_ddp - clear the given ddp context - * @ddp - ptr to the ixgbe_fcoe_ddp + * @ddp: ptr to the ixgbe_fcoe_ddp * * Returns : none * @@ -104,10 +105,10 @@ int ixgbe_fcoe_ddp_put(struct net_device *netdev, u16 xid) udelay(100); } if (ddp->sgl) - pci_unmap_sg(adapter->pdev, ddp->sgl, ddp->sgc, + dma_unmap_sg(&adapter->pdev->dev, ddp->sgl, ddp->sgc, DMA_FROM_DEVICE); if (ddp->pool) { - pci_pool_free(ddp->pool, ddp->udl, ddp->udp); + dma_pool_free(ddp->pool, ddp->udl, ddp->udp); ddp->pool = NULL; } @@ -134,6 +135,7 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid, struct ixgbe_hw *hw; struct ixgbe_fcoe *fcoe; struct ixgbe_fcoe_ddp *ddp; + struct ixgbe_fcoe_ddp_pool *ddp_pool; struct scatterlist *sg; unsigned int i, j, dmacount; unsigned int len; @@ -144,8 +146,6 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid, unsigned int thislen = 0; u32 fcbuff, fcdmarw, fcfltrw, fcrxctl; dma_addr_t addr = 0; - struct pci_pool *pool; - unsigned int cpu; if (!netdev || !sgl) return 0; @@ -162,11 +162,6 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid, 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", @@ -175,22 +170,32 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid, } ixgbe_fcoe_clear_ddp(ddp); + + if (!fcoe->ddp_pool) { + e_warn(drv, "No ddp_pool resources allocated\n"); + return 0; + } + + ddp_pool = per_cpu_ptr(fcoe->ddp_pool, get_cpu()); + if (!ddp_pool->pool) { + e_warn(drv, "xid=0x%x no ddp pool for fcoe\n", xid); + goto out_noddp; + } + /* setup dma from scsi command sgl */ - dmacount = pci_map_sg(adapter->pdev, sgl, sgc, DMA_FROM_DEVICE); + dmacount = dma_map_sg(&adapter->pdev->dev, sgl, sgc, DMA_FROM_DEVICE); if (dmacount == 0) { e_err(drv, "xid 0x%x DMA map error\n", xid); - return 0; + goto out_noddp; } /* alloc the udl from per cpu ddp pool */ - cpu = get_cpu(); - pool = *per_cpu_ptr(fcoe->pool, cpu); - ddp->udl = pci_pool_alloc(pool, GFP_ATOMIC, &ddp->udp); + ddp->udl = dma_pool_alloc(ddp_pool->pool, GFP_ATOMIC, &ddp->udp); if (!ddp->udl) { e_err(drv, "failed allocated ddp context\n"); goto out_noddp_unmap; } - ddp->pool = pool; + ddp->pool = ddp_pool->pool; ddp->sgl = sgl; ddp->sgc = sgc; @@ -201,7 +206,7 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid, while (len) { /* max number of buffers allowed in one DDP context */ if (j >= IXGBE_BUFFCNT_MAX) { - *per_cpu_ptr(fcoe->pcpu_noddp, cpu) += 1; + ddp_pool->noddp++; goto out_noddp_free; } @@ -241,7 +246,7 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid, */ if (lastsize == bufflen) { if (j >= IXGBE_BUFFCNT_MAX) { - *per_cpu_ptr(fcoe->pcpu_noddp_ext_buff, cpu) += 1; + ddp_pool->noddp_ext_buff++; goto out_noddp_free; } @@ -293,11 +298,12 @@ static int ixgbe_fcoe_ddp_setup(struct net_device *netdev, u16 xid, return 1; out_noddp_free: - pci_pool_free(pool, ddp->udl, ddp->udp); + dma_pool_free(ddp->pool, ddp->udl, ddp->udp); ixgbe_fcoe_clear_ddp(ddp); out_noddp_unmap: - pci_unmap_sg(adapter->pdev, sgl, sgc, DMA_FROM_DEVICE); + dma_unmap_sg(&adapter->pdev->dev, sgl, sgc, DMA_FROM_DEVICE); +out_noddp: put_cpu(); return 0; } @@ -357,22 +363,20 @@ int ixgbe_fcoe_ddp_target(struct net_device *netdev, u16 xid, */ int ixgbe_fcoe_ddp(struct ixgbe_adapter *adapter, union ixgbe_adv_rx_desc *rx_desc, - struct sk_buff *skb, - u32 staterr) + struct sk_buff *skb) { - 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; + __le32 fcerr = ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_FCERR); + __le32 ddp_err; + u32 fctl; + u16 xid; - fcerr = (staterr & IXGBE_RXDADV_ERR_FCERR); - fceofe = (staterr & IXGBE_RXDADV_ERR_FCEOFE); - if (fcerr == IXGBE_FCERR_BADCRC) - skb_checksum_none_assert(skb); + if (fcerr == cpu_to_le32(IXGBE_FCERR_BADCRC)) + skb->ip_summed = CHECKSUM_NONE; else skb->ip_summed = CHECKSUM_UNNECESSARY; @@ -382,6 +386,7 @@ int ixgbe_fcoe_ddp(struct ixgbe_adapter *adapter, 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); @@ -396,27 +401,39 @@ int ixgbe_fcoe_ddp(struct ixgbe_adapter *adapter, if (!ddp->udl) goto ddp_out; - if (fcerr | fceofe) + ddp_err = ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_FCEOFE | + IXGBE_RXDADV_ERR_FCERR); + if (ddp_err) goto ddp_out; - fcstat = (staterr & IXGBE_RXDADV_STAT_FCSTAT); - if (fcstat) { + switch (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_STAT_FCSTAT)) { + /* return 0 to bypass going to ULD for DDPed data */ + case cpu_to_le32(IXGBE_RXDADV_STAT_FCSTAT_DDP): /* update length of DDPed data */ ddp->len = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss); - /* 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 = 0; + break; + /* unmap the sg list when FCPRSP is received */ + case cpu_to_le32(IXGBE_RXDADV_STAT_FCSTAT_FCPRSP): + dma_unmap_sg(&adapter->pdev->dev, ddp->sgl, + ddp->sgc, DMA_FROM_DEVICE); + ddp->err = ddp_err; + ddp->sgl = NULL; + ddp->sgc = 0; + /* fall through */ + /* if DDP length is present pass it through to ULD */ + case cpu_to_le32(IXGBE_RXDADV_STAT_FCSTAT_NODDP): + /* update length of DDPed data */ + ddp->len = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss); + if (ddp->len) rc = ddp->len; + break; + /* no match will return as an error */ + case cpu_to_le32(IXGBE_RXDADV_STAT_FCSTAT_NOMTCH): + default: + break; } + /* In target mode, check the last data frame of the sequence. * For DDP in target mode, data is already DDPed but the header * indication of the last data frame ould allow is to tell if we @@ -426,6 +443,7 @@ int ixgbe_fcoe_ddp(struct ixgbe_adapter *adapter, */ if ((fh->fh_r_ctl == FC_RCTL_DD_SOL_DATA) && (fctl & FC_FC_END_SEQ)) { + skb_linearize(skb); crc = (struct fcoe_crc_eof *)skb_put(skb, sizeof(*crc)); crc->fcoe_eof = FC_EOF_T; } @@ -436,17 +454,18 @@ ddp_out: /** * ixgbe_fso - ixgbe FCoE Sequence Offload (FSO) * @tx_ring: tx desc ring - * @skb: associated skb - * @tx_flags: tx flags + * @first: first tx_buffer structure containing skb, tx_flags, and protocol * @hdr_len: hdr_len to be returned * * This sets up large send offload for FCoE * - * Returns : 0 indicates no FSO, > 0 for FSO, < 0 for error + * Returns : 0 indicates success, < 0 for error */ -int ixgbe_fso(struct ixgbe_ring *tx_ring, struct sk_buff *skb, - u32 tx_flags, u8 *hdr_len) +int ixgbe_fso(struct ixgbe_ring *tx_ring, + struct ixgbe_tx_buffer *first, + u8 *hdr_len) { + struct sk_buff *skb = first->skb; struct fc_frame_header *fh; u32 vlan_macip_lens; u32 fcoe_sof_eof = 0; @@ -519,66 +538,67 @@ int ixgbe_fso(struct ixgbe_ring *tx_ring, struct sk_buff *skb, *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)); + if (skb_is_gso(skb)) { + *hdr_len += skb_transport_offset(skb) + + sizeof(struct fc_frame_header); + /* update gso_segs and bytecount */ + first->gso_segs = DIV_ROUND_UP(skb->len - *hdr_len, + skb_shinfo(skb)->gso_size); + first->bytecount += (first->gso_segs - 1) * *hdr_len; + first->tx_flags |= IXGBE_TX_FLAGS_TSO; + } - /* mss_l4len_id: use 1 for FSO as TSO, no need for L4LEN */ + /* set flag indicating FCOE to ixgbe_tx_map call */ + first->tx_flags |= IXGBE_TX_FLAGS_FCOE | IXGBE_TX_FLAGS_CC; + + /* mss_l4len_id: use 0 for FSO as TSO, no need for L4LEN */ mss_l4len_idx = skb_shinfo(skb)->gso_size << IXGBE_ADVTXD_MSS_SHIFT; - 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; + vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK; /* write context desc */ ixgbe_tx_ctxtdesc(tx_ring, vlan_macip_lens, fcoe_sof_eof, IXGBE_ADVTXT_TUCMD_FCOE, mss_l4len_idx); - return skb_is_gso(skb); + return 0; } -static void ixgbe_fcoe_ddp_pools_free(struct ixgbe_fcoe *fcoe) +static void ixgbe_fcoe_dma_pool_free(struct ixgbe_fcoe *fcoe, unsigned int cpu) { - unsigned int cpu; - struct pci_pool **pool; + struct ixgbe_fcoe_ddp_pool *ddp_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; + ddp_pool = per_cpu_ptr(fcoe->ddp_pool, cpu); + if (ddp_pool->pool) + dma_pool_destroy(ddp_pool->pool); + ddp_pool->pool = NULL; } -static void ixgbe_fcoe_ddp_pools_alloc(struct ixgbe_adapter *adapter) +static int ixgbe_fcoe_dma_pool_alloc(struct ixgbe_fcoe *fcoe, + struct device *dev, + unsigned int cpu) { - struct ixgbe_fcoe *fcoe = &adapter->fcoe; - unsigned int cpu; - struct pci_pool **pool; + struct ixgbe_fcoe_ddp_pool *ddp_pool; + struct dma_pool *pool; char pool_name[32]; - fcoe->pool = alloc_percpu(struct pci_pool *); - if (!fcoe->pool) - return; + snprintf(pool_name, 32, "ixgbe_fcoe_ddp_%u", cpu); - /* 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; - } - } + pool = dma_pool_create(pool_name, dev, IXGBE_FCPTR_MAX, + IXGBE_FCPTR_ALIGN, PAGE_SIZE); + if (!pool) + return -ENOMEM; + + ddp_pool = per_cpu_ptr(fcoe->ddp_pool, cpu); + ddp_pool->pool = pool; + ddp_pool->noddp = 0; + ddp_pool->noddp_ext_buff = 0; + + return 0; } /** @@ -591,132 +611,169 @@ static void ixgbe_fcoe_ddp_pools_alloc(struct ixgbe_adapter *adapter) */ void ixgbe_configure_fcoe(struct ixgbe_adapter *adapter) { - int i, fcoe_q, fcoe_i; + struct ixgbe_ring_feature *fcoe = &adapter->ring_feature[RING_F_FCOE]; struct ixgbe_hw *hw = &adapter->hw; - struct ixgbe_fcoe *fcoe = &adapter->fcoe; - struct ixgbe_ring_feature *f = &adapter->ring_feature[RING_F_FCOE]; - unsigned int cpu; - - 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; - } + int i, fcoe_q, fcoe_i; + u32 etqf; - 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; - } + /* Minimal functionality for FCoE requires at least CRC offloads */ + if (!(adapter->netdev->features & NETIF_F_FCOE_CRC)) + return; - /* Alloc per cpu mem to count the ddp alloc failure number */ - fcoe->pcpu_noddp = alloc_percpu(u64); - if (!fcoe->pcpu_noddp) { - e_err(drv, "failed to alloc noddp counter\n"); - goto out_pcpu_noddp_alloc_fail; - } + /* Enable L2 EtherType filter for FCoE, needed for FCoE CRC and DDP */ + etqf = ETH_P_FCOE | IXGBE_ETQF_FCOE | IXGBE_ETQF_FILTER_EN; + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { + etqf |= IXGBE_ETQF_POOL_ENABLE; + etqf |= VMDQ_P(0) << IXGBE_ETQF_POOL_SHIFT; + } + IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_FCOE), etqf); + IXGBE_WRITE_REG(hw, IXGBE_ETQS(IXGBE_ETQF_FILTER_FCOE), 0); - fcoe->pcpu_noddp_ext_buff = alloc_percpu(u64); - if (!fcoe->pcpu_noddp_ext_buff) { - e_err(drv, "failed to alloc noddp extra buff cnt\n"); - goto out_pcpu_noddp_extra_buff_alloc_fail; - } + /* leave registers un-configured if FCoE is disabled */ + if (!(adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) + return; - for_each_possible_cpu(cpu) { - *per_cpu_ptr(fcoe->pcpu_noddp, cpu) = 0; - *per_cpu_ptr(fcoe->pcpu_noddp_ext_buff, cpu) = 0; - } + /* Use one or more Rx queues for FCoE by redirection table */ + for (i = 0; i < IXGBE_FCRETA_SIZE; i++) { + fcoe_i = fcoe->offset + (i % fcoe->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); - /* 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)); + /* Enable L2 EtherType filter for FIP */ + etqf = ETH_P_FIP | IXGBE_ETQF_FILTER_EN; + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { + etqf |= IXGBE_ETQF_POOL_ENABLE; + etqf |= VMDQ_P(0) << IXGBE_ETQF_POOL_SHIFT; } - /* 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_ETQF(IXGBE_ETQF_FILTER_FIP), etqf); + + /* Send FIP frames to the first FCoE queue */ + fcoe_q = adapter->rx_ring[fcoe->offset]->reg_idx; IXGBE_WRITE_REG(hw, IXGBE_ETQS(IXGBE_ETQF_FILTER_FIP), IXGBE_ETQS_QUEUE_EN | (fcoe_q << IXGBE_ETQS_RX_QUEUE_SHIFT)); - IXGBE_WRITE_REG(hw, IXGBE_FCRXCTRL, IXGBE_FCRXCTRL_FCCRCBO | + /* Configure FCoE Rx control */ + IXGBE_WRITE_REG(hw, IXGBE_FCRXCTRL, + IXGBE_FCRXCTRL_FCCRCBO | (FC_FCOE_VER << IXGBE_FCRXCTRL_FCOEVER_SHIFT)); - return; -out_pcpu_noddp_extra_buff_alloc_fail: - free_percpu(fcoe->pcpu_noddp); -out_pcpu_noddp_alloc_fail: - dma_unmap_single(&adapter->pdev->dev, - fcoe->extra_ddp_buffer_dma, - IXGBE_FCBUFF_MIN, - DMA_FROM_DEVICE); -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 + * ixgbe_free_fcoe_ddp_resources - 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) +void ixgbe_free_fcoe_ddp_resources(struct ixgbe_adapter *adapter) { - int i; struct ixgbe_fcoe *fcoe = &adapter->fcoe; + int cpu, i; - if (!fcoe->pool) + /* do nothing if no DDP pools were allocated */ + if (!fcoe->ddp_pool) return; for (i = 0; i < IXGBE_FCOE_DDP_MAX; i++) ixgbe_fcoe_ddp_put(adapter->netdev, i); + + for_each_possible_cpu(cpu) + ixgbe_fcoe_dma_pool_free(fcoe, cpu); + dma_unmap_single(&adapter->pdev->dev, fcoe->extra_ddp_buffer_dma, IXGBE_FCBUFF_MIN, DMA_FROM_DEVICE); - free_percpu(fcoe->pcpu_noddp); - free_percpu(fcoe->pcpu_noddp_ext_buff); kfree(fcoe->extra_ddp_buffer); - ixgbe_fcoe_ddp_pools_free(fcoe); + + fcoe->extra_ddp_buffer = NULL; + fcoe->extra_ddp_buffer_dma = 0; +} + +/** + * ixgbe_setup_fcoe_ddp_resources - setup all fcoe ddp context resources + * @adapter: ixgbe adapter + * + * Sets up ddp context resouces + * + * Returns : 0 indicates success or -EINVAL on failure + */ +int ixgbe_setup_fcoe_ddp_resources(struct ixgbe_adapter *adapter) +{ + struct ixgbe_fcoe *fcoe = &adapter->fcoe; + struct device *dev = &adapter->pdev->dev; + void *buffer; + dma_addr_t dma; + unsigned int cpu; + + /* do nothing if no DDP pools were allocated */ + if (!fcoe->ddp_pool) + return 0; + + /* Extra buffer to be shared by all DDPs for HW work around */ + buffer = kmalloc(IXGBE_FCBUFF_MIN, GFP_ATOMIC); + if (!buffer) + return -ENOMEM; + + dma = dma_map_single(dev, buffer, IXGBE_FCBUFF_MIN, DMA_FROM_DEVICE); + if (dma_mapping_error(dev, dma)) { + e_err(drv, "failed to map extra DDP buffer\n"); + kfree(buffer); + return -ENOMEM; + } + + fcoe->extra_ddp_buffer = buffer; + fcoe->extra_ddp_buffer_dma = dma; + + /* allocate pci pool for each cpu */ + for_each_possible_cpu(cpu) { + int err = ixgbe_fcoe_dma_pool_alloc(fcoe, dev, cpu); + if (!err) + continue; + + e_err(drv, "failed to alloc DDP pool on cpu:%d\n", cpu); + ixgbe_free_fcoe_ddp_resources(adapter); + return -ENOMEM; + } + + return 0; +} + +static int ixgbe_fcoe_ddp_enable(struct ixgbe_adapter *adapter) +{ + struct ixgbe_fcoe *fcoe = &adapter->fcoe; + + if (!(adapter->flags & IXGBE_FLAG_FCOE_CAPABLE)) + return -EINVAL; + + fcoe->ddp_pool = alloc_percpu(struct ixgbe_fcoe_ddp_pool); + + if (!fcoe->ddp_pool) { + e_err(drv, "failed to allocate percpu DDP resources\n"); + return -ENOMEM; + } + + adapter->netdev->fcoe_ddp_xid = IXGBE_FCOE_DDP_MAX - 1; + + return 0; +} + +static void ixgbe_fcoe_ddp_disable(struct ixgbe_adapter *adapter) +{ + struct ixgbe_fcoe *fcoe = &adapter->fcoe; + + adapter->netdev->fcoe_ddp_xid = 0; + + if (!fcoe->ddp_pool) + return; + + free_percpu(fcoe->ddp_pool); + fcoe->ddp_pool = NULL; } /** @@ -729,40 +786,41 @@ void ixgbe_cleanup_fcoe(struct ixgbe_adapter *adapter) */ int ixgbe_fcoe_enable(struct net_device *netdev) { - int rc = -EINVAL; struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_fcoe *fcoe = &adapter->fcoe; + atomic_inc(&fcoe->refcnt); if (!(adapter->flags & IXGBE_FLAG_FCOE_CAPABLE)) - goto out_enable; + return -EINVAL; - atomic_inc(&fcoe->refcnt); if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) - goto out_enable; + return -EINVAL; e_info(drv, "Enabling FCoE offload features.\n"); + + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) + e_warn(probe, "Enabling FCoE on PF will disable legacy VFs\n"); + if (netif_running(netdev)) netdev->netdev_ops->ndo_stop(netdev); - ixgbe_clear_interrupt_scheme(adapter); + /* Allocate per CPU memory to track DDP pools */ + ixgbe_fcoe_ddp_enable(adapter); + /* enable FCoE and notify stack */ 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; + netdev_features_change(netdev); + /* release existing queues and reallocate them */ + ixgbe_clear_interrupt_scheme(adapter); 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; + return 0; } /** @@ -775,41 +833,35 @@ out_enable: */ 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 (!atomic_dec_and_test(&adapter->fcoe.refcnt)) + return -EINVAL; if (!(adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) - goto out_disable; - - if (!atomic_dec_and_test(&fcoe->refcnt)) - goto out_disable; + return -EINVAL; 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); + /* Free per CPU memory to track DDP pools */ + ixgbe_fcoe_ddp_disable(adapter); + + /* disable FCoE and notify stack */ adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED; - adapter->ring_feature[RING_F_FCOE].indices = 0; - ixgbe_cleanup_fcoe(adapter); + netdev->features &= ~NETIF_F_FCOE_MTU; + + netdev_features_change(netdev); + + /* release existing queues and reallocate them */ + ixgbe_clear_interrupt_scheme(adapter); ixgbe_init_interrupt_scheme(adapter); if (netif_running(netdev)) netdev->netdev_ops->ndo_open(netdev); - rc = 0; -out_disable: - return rc; + return 0; } /** @@ -938,3 +990,18 @@ int ixgbe_fcoe_get_hbainfo(struct net_device *netdev, return 0; } + +/** + * ixgbe_fcoe_get_tc - get the current TC that fcoe is mapped to + * @adapter - pointer to the device adapter structure + * + * Return : TC that FCoE is mapped to + */ +u8 ixgbe_fcoe_get_tc(struct ixgbe_adapter *adapter) +{ +#ifdef CONFIG_IXGBE_DCB + return netdev_get_prio_tc_map(adapter->netdev, adapter->fcoe.up); +#else + return 0; +#endif +} diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h index 1dbed17c810..0772b7730fc 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2013 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, @@ -20,6 +20,7 @@ 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 @@ -62,22 +63,25 @@ struct ixgbe_fcoe_ddp { struct scatterlist *sgl; dma_addr_t udp; u64 *udl; - struct pci_pool *pool; + struct dma_pool *pool; +}; + +/* per cpu variables */ +struct ixgbe_fcoe_ddp_pool { + struct dma_pool *pool; + u64 noddp; + u64 noddp_ext_buff; }; struct ixgbe_fcoe { - struct pci_pool **pool; + struct ixgbe_fcoe_ddp_pool __percpu *ddp_pool; atomic_t refcnt; spinlock_t lock; struct ixgbe_fcoe_ddp ddp[IXGBE_FCOE_DDP_MAX]; - unsigned char *extra_ddp_buffer; + void *extra_ddp_buffer; dma_addr_t extra_ddp_buffer_dma; unsigned long mode; - u64 __percpu *pcpu_noddp; - u64 __percpu *pcpu_noddp_ext_buff; -#ifdef CONFIG_IXGBE_DCB u8 up; -#endif }; #endif /* _IXGBE_FCOE_H */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c new file mode 100644 index 00000000000..2d9451e3968 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -0,0 +1,1199 @@ +/******************************************************************************* + + Intel 10 Gigabit PCI Express Linux driver + Copyright(c) 1999 - 2013 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_sriov.h" + +#ifdef CONFIG_IXGBE_DCB +/** + * ixgbe_cache_ring_dcb_sriov - Descriptor ring to register mapping for SR-IOV + * @adapter: board private structure to initialize + * + * Cache the descriptor ring offsets for SR-IOV to the assigned rings. It + * will also try to cache the proper offsets if RSS/FCoE are enabled along + * with VMDq. + * + **/ +static bool ixgbe_cache_ring_dcb_sriov(struct ixgbe_adapter *adapter) +{ +#ifdef IXGBE_FCOE + struct ixgbe_ring_feature *fcoe = &adapter->ring_feature[RING_F_FCOE]; +#endif /* IXGBE_FCOE */ + struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; + int i; + u16 reg_idx; + u8 tcs = netdev_get_num_tc(adapter->netdev); + + /* verify we have DCB queueing enabled before proceeding */ + if (tcs <= 1) + return false; + + /* verify we have VMDq enabled before proceeding */ + if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) + return false; + + /* start at VMDq register offset for SR-IOV enabled setups */ + reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask); + for (i = 0; i < adapter->num_rx_queues; i++, reg_idx++) { + /* If we are greater than indices move to next pool */ + if ((reg_idx & ~vmdq->mask) >= tcs) + reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask); + adapter->rx_ring[i]->reg_idx = reg_idx; + } + + reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask); + for (i = 0; i < adapter->num_tx_queues; i++, reg_idx++) { + /* If we are greater than indices move to next pool */ + if ((reg_idx & ~vmdq->mask) >= tcs) + reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask); + adapter->tx_ring[i]->reg_idx = reg_idx; + } + +#ifdef IXGBE_FCOE + /* nothing to do if FCoE is disabled */ + if (!(adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) + return true; + + /* The work is already done if the FCoE ring is shared */ + if (fcoe->offset < tcs) + return true; + + /* The FCoE rings exist separately, we need to move their reg_idx */ + if (fcoe->indices) { + u16 queues_per_pool = __ALIGN_MASK(1, ~vmdq->mask); + u8 fcoe_tc = ixgbe_fcoe_get_tc(adapter); + + reg_idx = (vmdq->offset + vmdq->indices) * queues_per_pool; + for (i = fcoe->offset; i < adapter->num_rx_queues; i++) { + reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask) + fcoe_tc; + adapter->rx_ring[i]->reg_idx = reg_idx; + reg_idx++; + } + + reg_idx = (vmdq->offset + vmdq->indices) * queues_per_pool; + for (i = fcoe->offset; i < adapter->num_tx_queues; i++) { + reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask) + fcoe_tc; + adapter->tx_ring[i]->reg_idx = reg_idx; + reg_idx++; + } + } + +#endif /* IXGBE_FCOE */ + return true; +} + +/* ixgbe_get_first_reg_idx - Return first register index associated with ring */ +static void ixgbe_get_first_reg_idx(struct ixgbe_adapter *adapter, u8 tc, + unsigned int *tx, unsigned int *rx) +{ + struct 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: + /* TxQs/TC: 4 RxQs/TC: 8 */ + *tx = tc << 2; /* 0, 4, 8, 12, 16, 20, 24, 28 */ + *rx = tc << 3; /* 0, 8, 16, 24, 32, 40, 48, 56 */ + break; + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + if (num_tcs > 4) { + /* + * TCs : TC0/1 TC2/3 TC4-7 + * TxQs/TC: 32 16 8 + * RxQs/TC: 16 16 16 + */ + *rx = tc << 4; + if (tc < 3) + *tx = tc << 5; /* 0, 32, 64 */ + else if (tc < 5) + *tx = (tc + 2) << 4; /* 80, 96 */ + else + *tx = (tc + 8) << 3; /* 104, 112, 120 */ + } else { + /* + * TCs : TC0 TC1 TC2/3 + * TxQs/TC: 64 32 16 + * RxQs/TC: 32 32 32 + */ + *rx = tc << 5; + if (tc < 2) + *tx = tc << 6; /* 0, 64 */ + else + *tx = (tc + 4) << 4; /* 96, 112 */ + } + default: + break; + } +} + +/** + * ixgbe_cache_ring_dcb - Descriptor ring to register mapping for DCB + * @adapter: board private structure to initialize + * + * Cache the descriptor ring offsets for DCB to the assigned rings. + * + **/ +static bool ixgbe_cache_ring_dcb(struct ixgbe_adapter *adapter) +{ + struct net_device *dev = adapter->netdev; + unsigned int tx_idx, rx_idx; + int tc, offset, rss_i, i; + u8 num_tcs = netdev_get_num_tc(dev); + + /* verify we have DCB queueing enabled before proceeding */ + if (num_tcs <= 1) + return false; + + rss_i = adapter->ring_feature[RING_F_RSS].indices; + + for (tc = 0, offset = 0; tc < num_tcs; tc++, offset += rss_i) { + ixgbe_get_first_reg_idx(adapter, tc, &tx_idx, &rx_idx); + for (i = 0; i < rss_i; i++, tx_idx++, rx_idx++) { + adapter->tx_ring[offset + i]->reg_idx = tx_idx; + adapter->rx_ring[offset + i]->reg_idx = rx_idx; + adapter->tx_ring[offset + i]->dcb_tc = tc; + adapter->rx_ring[offset + i]->dcb_tc = tc; + } + } + + return true; +} + +#endif +/** + * ixgbe_cache_ring_sriov - Descriptor ring to register mapping for sriov + * @adapter: board private structure to initialize + * + * SR-IOV doesn't use any descriptor rings but changes the default if + * no other mapping is used. + * + */ +static bool ixgbe_cache_ring_sriov(struct ixgbe_adapter *adapter) +{ +#ifdef IXGBE_FCOE + struct ixgbe_ring_feature *fcoe = &adapter->ring_feature[RING_F_FCOE]; +#endif /* IXGBE_FCOE */ + struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; + struct ixgbe_ring_feature *rss = &adapter->ring_feature[RING_F_RSS]; + int i; + u16 reg_idx; + + /* only proceed if VMDq is enabled */ + if (!(adapter->flags & IXGBE_FLAG_VMDQ_ENABLED)) + return false; + + /* start at VMDq register offset for SR-IOV enabled setups */ + reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask); + for (i = 0; i < adapter->num_rx_queues; i++, reg_idx++) { +#ifdef IXGBE_FCOE + /* Allow first FCoE queue to be mapped as RSS */ + if (fcoe->offset && (i > fcoe->offset)) + break; +#endif + /* If we are greater than indices move to next pool */ + if ((reg_idx & ~vmdq->mask) >= rss->indices) + reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask); + adapter->rx_ring[i]->reg_idx = reg_idx; + } + +#ifdef IXGBE_FCOE + /* FCoE uses a linear block of queues so just assigning 1:1 */ + for (; i < adapter->num_rx_queues; i++, reg_idx++) + adapter->rx_ring[i]->reg_idx = reg_idx; + +#endif + reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask); + for (i = 0; i < adapter->num_tx_queues; i++, reg_idx++) { +#ifdef IXGBE_FCOE + /* Allow first FCoE queue to be mapped as RSS */ + if (fcoe->offset && (i > fcoe->offset)) + break; +#endif + /* If we are greater than indices move to next pool */ + if ((reg_idx & rss->mask) >= rss->indices) + reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask); + adapter->tx_ring[i]->reg_idx = reg_idx; + } + +#ifdef IXGBE_FCOE + /* FCoE uses a linear block of queues so just assigning 1:1 */ + for (; i < adapter->num_tx_queues; i++, reg_idx++) + adapter->tx_ring[i]->reg_idx = reg_idx; + +#endif + + return true; +} + +/** + * ixgbe_cache_ring_rss - Descriptor ring to register mapping for RSS + * @adapter: board private structure to initialize + * + * Cache the descriptor ring offsets for RSS to the assigned rings. + * + **/ +static bool ixgbe_cache_ring_rss(struct ixgbe_adapter *adapter) +{ + int i; + + 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; +} + +/** + * ixgbe_cache_ring_register - Descriptor ring to register mapping + * @adapter: board private structure to initialize + * + * Once we know the feature-set enabled for the device, we'll cache + * the register offset the descriptor ring is assigned to. + * + * Note, the order the various feature calls is important. It must start with + * the "most" features enabled at the same time, then trickle down to the + * least amount of features turned on at once. + **/ +static void ixgbe_cache_ring_register(struct ixgbe_adapter *adapter) +{ + /* start with default case */ + adapter->rx_ring[0]->reg_idx = 0; + adapter->tx_ring[0]->reg_idx = 0; + +#ifdef CONFIG_IXGBE_DCB + if (ixgbe_cache_ring_dcb_sriov(adapter)) + return; + + if (ixgbe_cache_ring_dcb(adapter)) + return; + +#endif + if (ixgbe_cache_ring_sriov(adapter)) + return; + + ixgbe_cache_ring_rss(adapter); +} + +#define IXGBE_RSS_16Q_MASK 0xF +#define IXGBE_RSS_8Q_MASK 0x7 +#define IXGBE_RSS_4Q_MASK 0x3 +#define IXGBE_RSS_2Q_MASK 0x1 +#define IXGBE_RSS_DISABLED_MASK 0x0 + +#ifdef CONFIG_IXGBE_DCB +/** + * ixgbe_set_dcb_sriov_queues: Allocate queues for SR-IOV devices w/ DCB + * @adapter: board private structure to initialize + * + * When SR-IOV (Single Root IO Virtualiztion) is enabled, allocate queues + * and VM pools where appropriate. Also assign queues based on DCB + * priorities and map accordingly.. + * + **/ +static bool ixgbe_set_dcb_sriov_queues(struct ixgbe_adapter *adapter) +{ + int i; + u16 vmdq_i = adapter->ring_feature[RING_F_VMDQ].limit; + u16 vmdq_m = 0; +#ifdef IXGBE_FCOE + u16 fcoe_i = 0; +#endif + u8 tcs = netdev_get_num_tc(adapter->netdev); + + /* verify we have DCB queueing enabled before proceeding */ + if (tcs <= 1) + return false; + + /* verify we have VMDq enabled before proceeding */ + if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) + return false; + + /* Add starting offset to total pool count */ + vmdq_i += adapter->ring_feature[RING_F_VMDQ].offset; + + /* 16 pools w/ 8 TC per pool */ + if (tcs > 4) { + vmdq_i = min_t(u16, vmdq_i, 16); + vmdq_m = IXGBE_82599_VMDQ_8Q_MASK; + /* 32 pools w/ 4 TC per pool */ + } else { + vmdq_i = min_t(u16, vmdq_i, 32); + vmdq_m = IXGBE_82599_VMDQ_4Q_MASK; + } + +#ifdef IXGBE_FCOE + /* queues in the remaining pools are available for FCoE */ + fcoe_i = (128 / __ALIGN_MASK(1, ~vmdq_m)) - vmdq_i; + +#endif + /* remove the starting offset from the pool count */ + vmdq_i -= adapter->ring_feature[RING_F_VMDQ].offset; + + /* save features for later use */ + adapter->ring_feature[RING_F_VMDQ].indices = vmdq_i; + adapter->ring_feature[RING_F_VMDQ].mask = vmdq_m; + + /* + * We do not support DCB, VMDq, and RSS all simultaneously + * so we will disable RSS since it is the lowest priority + */ + adapter->ring_feature[RING_F_RSS].indices = 1; + adapter->ring_feature[RING_F_RSS].mask = IXGBE_RSS_DISABLED_MASK; + + /* disable ATR as it is not supported when VMDq is enabled */ + adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; + + adapter->num_rx_pools = vmdq_i; + adapter->num_rx_queues_per_pool = tcs; + + adapter->num_tx_queues = vmdq_i * tcs; + adapter->num_rx_queues = vmdq_i * tcs; + +#ifdef IXGBE_FCOE + if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) { + struct ixgbe_ring_feature *fcoe; + + fcoe = &adapter->ring_feature[RING_F_FCOE]; + + /* limit ourselves based on feature limits */ + fcoe_i = min_t(u16, fcoe_i, fcoe->limit); + + if (fcoe_i) { + /* alloc queues for FCoE separately */ + fcoe->indices = fcoe_i; + fcoe->offset = vmdq_i * tcs; + + /* add queues to adapter */ + adapter->num_tx_queues += fcoe_i; + adapter->num_rx_queues += fcoe_i; + } else if (tcs > 1) { + /* use queue belonging to FcoE TC */ + fcoe->indices = 1; + fcoe->offset = ixgbe_fcoe_get_tc(adapter); + } else { + adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED; + + fcoe->indices = 0; + fcoe->offset = 0; + } + } + +#endif /* IXGBE_FCOE */ + /* configure TC to queue mapping */ + for (i = 0; i < tcs; i++) + netdev_set_tc_queue(adapter->netdev, i, 1, i); + + return true; +} + +static bool ixgbe_set_dcb_queues(struct ixgbe_adapter *adapter) +{ + struct net_device *dev = adapter->netdev; + struct ixgbe_ring_feature *f; + int rss_i, rss_m, i; + int tcs; + + /* Map queue offset and counts onto allocated tx queues */ + tcs = netdev_get_num_tc(dev); + + /* verify we have DCB queueing enabled before proceeding */ + if (tcs <= 1) + return false; + + /* determine the upper limit for our current DCB mode */ + rss_i = dev->num_tx_queues / tcs; + if (adapter->hw.mac.type == ixgbe_mac_82598EB) { + /* 8 TC w/ 4 queues per TC */ + rss_i = min_t(u16, rss_i, 4); + rss_m = IXGBE_RSS_4Q_MASK; + } else if (tcs > 4) { + /* 8 TC w/ 8 queues per TC */ + rss_i = min_t(u16, rss_i, 8); + rss_m = IXGBE_RSS_8Q_MASK; + } else { + /* 4 TC w/ 16 queues per TC */ + rss_i = min_t(u16, rss_i, 16); + rss_m = IXGBE_RSS_16Q_MASK; + } + + /* set RSS mask and indices */ + f = &adapter->ring_feature[RING_F_RSS]; + rss_i = min_t(int, rss_i, f->limit); + f->indices = rss_i; + f->mask = rss_m; + + /* disable ATR as it is not supported when multiple TCs are enabled */ + adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; + +#ifdef IXGBE_FCOE + /* FCoE enabled queues require special configuration indexed + * by feature specific indices and offset. Here we map FCoE + * indices onto the DCB queue pairs allowing FCoE to own + * configuration later. + */ + if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) { + u8 tc = ixgbe_fcoe_get_tc(adapter); + + f = &adapter->ring_feature[RING_F_FCOE]; + f->indices = min_t(u16, rss_i, f->limit); + f->offset = rss_i * tc; + } + +#endif /* IXGBE_FCOE */ + for (i = 0; i < tcs; i++) + netdev_set_tc_queue(dev, i, rss_i, rss_i * i); + + adapter->num_tx_queues = rss_i * tcs; + adapter->num_rx_queues = rss_i * tcs; + + return true; +} + +#endif +/** + * ixgbe_set_sriov_queues - Allocate queues for SR-IOV devices + * @adapter: board private structure to initialize + * + * When SR-IOV (Single Root IO Virtualiztion) is enabled, allocate queues + * and VM pools where appropriate. If RSS is available, then also try and + * enable RSS and map accordingly. + * + **/ +static bool ixgbe_set_sriov_queues(struct ixgbe_adapter *adapter) +{ + u16 vmdq_i = adapter->ring_feature[RING_F_VMDQ].limit; + u16 vmdq_m = 0; + u16 rss_i = adapter->ring_feature[RING_F_RSS].limit; + u16 rss_m = IXGBE_RSS_DISABLED_MASK; +#ifdef IXGBE_FCOE + u16 fcoe_i = 0; +#endif + bool pools = (find_first_zero_bit(&adapter->fwd_bitmask, 32) > 1); + + /* only proceed if SR-IOV is enabled */ + if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) + return false; + + /* Add starting offset to total pool count */ + vmdq_i += adapter->ring_feature[RING_F_VMDQ].offset; + + /* double check we are limited to maximum pools */ + vmdq_i = min_t(u16, IXGBE_MAX_VMDQ_INDICES, vmdq_i); + + /* 64 pool mode with 2 queues per pool */ + if ((vmdq_i > 32) || (rss_i < 4) || (vmdq_i > 16 && pools)) { + vmdq_m = IXGBE_82599_VMDQ_2Q_MASK; + rss_m = IXGBE_RSS_2Q_MASK; + rss_i = min_t(u16, rss_i, 2); + /* 32 pool mode with 4 queues per pool */ + } else { + vmdq_m = IXGBE_82599_VMDQ_4Q_MASK; + rss_m = IXGBE_RSS_4Q_MASK; + rss_i = 4; + } + +#ifdef IXGBE_FCOE + /* queues in the remaining pools are available for FCoE */ + fcoe_i = 128 - (vmdq_i * __ALIGN_MASK(1, ~vmdq_m)); + +#endif + /* remove the starting offset from the pool count */ + vmdq_i -= adapter->ring_feature[RING_F_VMDQ].offset; + + /* save features for later use */ + adapter->ring_feature[RING_F_VMDQ].indices = vmdq_i; + adapter->ring_feature[RING_F_VMDQ].mask = vmdq_m; + + /* limit RSS based on user input and save for later use */ + adapter->ring_feature[RING_F_RSS].indices = rss_i; + adapter->ring_feature[RING_F_RSS].mask = rss_m; + + adapter->num_rx_pools = vmdq_i; + adapter->num_rx_queues_per_pool = rss_i; + + adapter->num_rx_queues = vmdq_i * rss_i; + adapter->num_tx_queues = vmdq_i * rss_i; + + /* disable ATR as it is not supported when VMDq is enabled */ + adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; + +#ifdef IXGBE_FCOE + /* + * FCoE can use rings from adjacent buffers to allow RSS + * like behavior. To account for this we need to add the + * FCoE indices to the total ring count. + */ + if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) { + struct ixgbe_ring_feature *fcoe; + + fcoe = &adapter->ring_feature[RING_F_FCOE]; + + /* limit ourselves based on feature limits */ + fcoe_i = min_t(u16, fcoe_i, fcoe->limit); + + if (vmdq_i > 1 && fcoe_i) { + /* alloc queues for FCoE separately */ + fcoe->indices = fcoe_i; + fcoe->offset = vmdq_i * rss_i; + } else { + /* merge FCoE queues with RSS queues */ + fcoe_i = min_t(u16, fcoe_i + rss_i, num_online_cpus()); + + /* limit indices to rss_i if MSI-X is disabled */ + if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) + fcoe_i = rss_i; + + /* attempt to reserve some queues for just FCoE */ + fcoe->indices = min_t(u16, fcoe_i, fcoe->limit); + fcoe->offset = fcoe_i - fcoe->indices; + + fcoe_i -= rss_i; + } + + /* add queues to adapter */ + adapter->num_tx_queues += fcoe_i; + adapter->num_rx_queues += fcoe_i; + } + +#endif + return true; +} + +/** + * ixgbe_set_rss_queues - Allocate queues for RSS + * @adapter: board private structure to initialize + * + * This is our "base" multiqueue mode. RSS (Receive Side Scaling) will try + * to allocate one Rx queue per CPU, and if available, one Tx queue per CPU. + * + **/ +static bool ixgbe_set_rss_queues(struct ixgbe_adapter *adapter) +{ + struct ixgbe_ring_feature *f; + u16 rss_i; + + /* set mask for 16 queue limit of RSS */ + f = &adapter->ring_feature[RING_F_RSS]; + rss_i = f->limit; + + f->indices = rss_i; + f->mask = IXGBE_RSS_16Q_MASK; + + /* disable ATR by default, it will be configured below */ + adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; + + /* + * Use Flow Director in addition to RSS to ensure the best + * distribution of flows across cores, even when an FDIR flow + * isn't matched. + */ + if (rss_i > 1 && adapter->atr_sample_rate) { + f = &adapter->ring_feature[RING_F_FDIR]; + + rss_i = f->indices = f->limit; + + if (!(adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE)) + adapter->flags |= IXGBE_FLAG_FDIR_HASH_CAPABLE; + } + +#ifdef IXGBE_FCOE + /* + * FCoE can exist on the same rings as standard network traffic + * however it is preferred to avoid that if possible. In order + * to get the best performance we allocate as many FCoE queues + * as we can and we place them at the end of the ring array to + * avoid sharing queues with standard RSS on systems with 24 or + * more CPUs. + */ + if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) { + struct net_device *dev = adapter->netdev; + u16 fcoe_i; + + f = &adapter->ring_feature[RING_F_FCOE]; + + /* merge FCoE queues with RSS queues */ + fcoe_i = min_t(u16, f->limit + rss_i, num_online_cpus()); + fcoe_i = min_t(u16, fcoe_i, dev->num_tx_queues); + + /* limit indices to rss_i if MSI-X is disabled */ + if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) + fcoe_i = rss_i; + + /* attempt to reserve some queues for just FCoE */ + f->indices = min_t(u16, fcoe_i, f->limit); + f->offset = fcoe_i - f->indices; + rss_i = max_t(u16, fcoe_i, rss_i); + } + +#endif /* IXGBE_FCOE */ + adapter->num_rx_queues = rss_i; + adapter->num_tx_queues = rss_i; + + return true; +} + +/** + * ixgbe_set_num_queues - Allocate queues for device, feature dependent + * @adapter: board private structure to initialize + * + * This is the top level queue allocation routine. The order here is very + * important, starting with the "most" number of features turned on at once, + * and ending with the smallest set of features. This way large combinations + * can be allocated if they're turned on, and smaller combinations are the + * fallthrough conditions. + * + **/ +static void ixgbe_set_num_queues(struct ixgbe_adapter *adapter) +{ + /* Start with base case */ + adapter->num_rx_queues = 1; + adapter->num_tx_queues = 1; + adapter->num_rx_pools = adapter->num_rx_queues; + adapter->num_rx_queues_per_pool = 1; + +#ifdef CONFIG_IXGBE_DCB + if (ixgbe_set_dcb_sriov_queues(adapter)) + return; + + if (ixgbe_set_dcb_queues(adapter)) + return; + +#endif + if (ixgbe_set_sriov_queues(adapter)) + return; + + ixgbe_set_rss_queues(adapter); +} + +static void ixgbe_acquire_msix_vectors(struct ixgbe_adapter *adapter, + int vectors) +{ + int vector_threshold; + + /* We'll want at least 2 (vector_threshold): + * 1) TxQ[0] + RxQ[0] handler + * 2) Other (Link Status Change, etc.) + */ + vector_threshold = MIN_MSIX_COUNT; + + /* + * The more we get, the more we will assign to Tx/Rx Cleanup + * for the separate queues...where Rx Cleanup >= Tx Cleanup. + * Right now, we simply care about how many we'll get; we'll + * set them up later while requesting irq's. + */ + vectors = pci_enable_msix_range(adapter->pdev, adapter->msix_entries, + vector_threshold, vectors); + + if (vectors < 0) { + /* 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. + */ + vectors -= NON_Q_VECTORS; + adapter->num_q_vectors = min(vectors, adapter->max_q_vectors); + } +} + +static void ixgbe_add_ring(struct ixgbe_ring *ring, + struct ixgbe_ring_container *head) +{ + ring->next = head->ring; + head->ring = ring; + head->count++; +} + +/** + * ixgbe_alloc_q_vector - Allocate memory for a single interrupt vector + * @adapter: board private structure to initialize + * @v_count: q_vectors allocated on adapter, used for ring interleaving + * @v_idx: index of vector in adapter struct + * @txr_count: total number of Tx rings to allocate + * @txr_idx: index of first Tx ring to allocate + * @rxr_count: total number of Rx rings to allocate + * @rxr_idx: index of first Rx ring to allocate + * + * We allocate one q_vector. If allocation fails we return -ENOMEM. + **/ +static int ixgbe_alloc_q_vector(struct ixgbe_adapter *adapter, + int v_count, int v_idx, + int txr_count, int txr_idx, + int rxr_count, int rxr_idx) +{ + struct ixgbe_q_vector *q_vector; + struct ixgbe_ring *ring; + int node = NUMA_NO_NODE; + int cpu = -1; + int ring_count, size; + u8 tcs = netdev_get_num_tc(adapter->netdev); + + ring_count = txr_count + rxr_count; + size = sizeof(struct ixgbe_q_vector) + + (sizeof(struct ixgbe_ring) * ring_count); + + /* customize cpu for Flow Director mapping */ + if ((tcs <= 1) && !(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) { + u16 rss_i = adapter->ring_feature[RING_F_RSS].indices; + if (rss_i > 1 && adapter->atr_sample_rate) { + if (cpu_online(v_idx)) { + cpu = v_idx; + node = cpu_to_node(cpu); + } + } + } + + /* allocate q_vector and rings */ + q_vector = kzalloc_node(size, GFP_KERNEL, node); + if (!q_vector) + q_vector = kzalloc(size, GFP_KERNEL); + if (!q_vector) + return -ENOMEM; + + /* setup affinity mask and node */ + if (cpu != -1) + cpumask_set_cpu(cpu, &q_vector->affinity_mask); + q_vector->numa_node = node; + +#ifdef CONFIG_IXGBE_DCA + /* initialize CPU for DCA */ + q_vector->cpu = -1; + +#endif + /* initialize NAPI */ + netif_napi_add(adapter->netdev, &q_vector->napi, + ixgbe_poll, 64); + napi_hash_add(&q_vector->napi); + + /* tie q_vector and adapter together */ + adapter->q_vector[v_idx] = q_vector; + q_vector->adapter = adapter; + q_vector->v_idx = v_idx; + + /* initialize work limits */ + q_vector->tx.work_limit = adapter->tx_work_limit; + + /* initialize pointer to rings */ + ring = q_vector->ring; + + /* intialize ITR */ + if (txr_count && !rxr_count) { + /* tx only vector */ + if (adapter->tx_itr_setting == 1) + q_vector->itr = IXGBE_10K_ITR; + else + q_vector->itr = adapter->tx_itr_setting; + } else { + /* rx or rx/tx vector */ + if (adapter->rx_itr_setting == 1) + q_vector->itr = IXGBE_20K_ITR; + else + q_vector->itr = adapter->rx_itr_setting; + } + + while (txr_count) { + /* assign generic ring traits */ + ring->dev = &adapter->pdev->dev; + ring->netdev = adapter->netdev; + + /* configure backlink on ring */ + ring->q_vector = q_vector; + + /* update q_vector Tx values */ + ixgbe_add_ring(ring, &q_vector->tx); + + /* apply Tx specific ring traits */ + ring->count = adapter->tx_ring_count; + if (adapter->num_rx_pools > 1) + ring->queue_index = + txr_idx % adapter->num_rx_queues_per_pool; + else + ring->queue_index = txr_idx; + + /* assign ring to adapter */ + adapter->tx_ring[txr_idx] = ring; + + /* update count and index */ + txr_count--; + txr_idx += v_count; + + /* push pointer to next ring */ + ring++; + } + + while (rxr_count) { + /* assign generic ring traits */ + ring->dev = &adapter->pdev->dev; + ring->netdev = adapter->netdev; + + /* configure backlink on ring */ + ring->q_vector = q_vector; + + /* update q_vector Rx values */ + ixgbe_add_ring(ring, &q_vector->rx); + + /* + * 82599 errata, UDP frames with a 0 checksum + * can be marked as checksum errors. + */ + if (adapter->hw.mac.type == ixgbe_mac_82599EB) + set_bit(__IXGBE_RX_CSUM_UDP_ZERO_ERR, &ring->state); + +#ifdef IXGBE_FCOE + if (adapter->netdev->features & NETIF_F_FCOE_MTU) { + struct ixgbe_ring_feature *f; + f = &adapter->ring_feature[RING_F_FCOE]; + if ((rxr_idx >= f->offset) && + (rxr_idx < f->offset + f->indices)) + set_bit(__IXGBE_RX_FCOE, &ring->state); + } + +#endif /* IXGBE_FCOE */ + /* apply Rx specific ring traits */ + ring->count = adapter->rx_ring_count; + if (adapter->num_rx_pools > 1) + ring->queue_index = + rxr_idx % adapter->num_rx_queues_per_pool; + else + ring->queue_index = rxr_idx; + + /* assign ring to adapter */ + adapter->rx_ring[rxr_idx] = ring; + + /* update count and index */ + rxr_count--; + rxr_idx += v_count; + + /* push pointer to next ring */ + ring++; + } + + return 0; +} + +/** + * ixgbe_free_q_vector - Free memory allocated for specific interrupt vector + * @adapter: board private structure to initialize + * @v_idx: Index of vector to be freed + * + * This function frees the memory allocated to the q_vector. In addition if + * NAPI is enabled it will delete any references to the NAPI struct prior + * to freeing the q_vector. + **/ +static void ixgbe_free_q_vector(struct ixgbe_adapter *adapter, int v_idx) +{ + struct ixgbe_q_vector *q_vector = adapter->q_vector[v_idx]; + struct ixgbe_ring *ring; + + ixgbe_for_each_ring(ring, q_vector->tx) + adapter->tx_ring[ring->queue_index] = NULL; + + ixgbe_for_each_ring(ring, q_vector->rx) + adapter->rx_ring[ring->queue_index] = NULL; + + adapter->q_vector[v_idx] = NULL; + napi_hash_del(&q_vector->napi); + netif_napi_del(&q_vector->napi); + + /* + * ixgbe_get_stats64() might access the rings on this vector, + * we must wait a grace period before freeing it. + */ + kfree_rcu(q_vector, rcu); +} + +/** + * ixgbe_alloc_q_vectors - Allocate memory for interrupt vectors + * @adapter: board private structure to initialize + * + * We allocate one q_vector per queue interrupt. If allocation fails we + * return -ENOMEM. + **/ +static int ixgbe_alloc_q_vectors(struct ixgbe_adapter *adapter) +{ + int q_vectors = adapter->num_q_vectors; + int rxr_remaining = adapter->num_rx_queues; + int txr_remaining = adapter->num_tx_queues; + int rxr_idx = 0, txr_idx = 0, v_idx = 0; + int err; + + /* only one q_vector if MSI-X is disabled. */ + if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) + q_vectors = 1; + + if (q_vectors >= (rxr_remaining + txr_remaining)) { + for (; rxr_remaining; v_idx++) { + err = ixgbe_alloc_q_vector(adapter, q_vectors, v_idx, + 0, 0, 1, rxr_idx); + + if (err) + goto err_out; + + /* update counts and index */ + rxr_remaining--; + rxr_idx++; + } + } + + for (; v_idx < q_vectors; v_idx++) { + int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - v_idx); + int tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - v_idx); + err = ixgbe_alloc_q_vector(adapter, q_vectors, v_idx, + tqpv, txr_idx, + rqpv, rxr_idx); + + if (err) + goto err_out; + + /* update counts and index */ + rxr_remaining -= rqpv; + txr_remaining -= tqpv; + rxr_idx++; + txr_idx++; + } + + return 0; + +err_out: + adapter->num_tx_queues = 0; + adapter->num_rx_queues = 0; + adapter->num_q_vectors = 0; + + while (v_idx--) + ixgbe_free_q_vector(adapter, v_idx); + + return -ENOMEM; +} + +/** + * ixgbe_free_q_vectors - Free memory allocated for interrupt vectors + * @adapter: board private structure to initialize + * + * This function frees the memory allocated to the q_vectors. In addition if + * NAPI is enabled it will delete any references to the NAPI struct prior + * to freeing the q_vector. + **/ +static void ixgbe_free_q_vectors(struct ixgbe_adapter *adapter) +{ + int v_idx = adapter->num_q_vectors; + + adapter->num_tx_queues = 0; + adapter->num_rx_queues = 0; + adapter->num_q_vectors = 0; + + while (v_idx--) + ixgbe_free_q_vector(adapter, v_idx); +} + +static void ixgbe_reset_interrupt_capability(struct ixgbe_adapter *adapter) +{ + if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) { + adapter->flags &= ~IXGBE_FLAG_MSIX_ENABLED; + pci_disable_msix(adapter->pdev); + kfree(adapter->msix_entries); + adapter->msix_entries = NULL; + } else if (adapter->flags & IXGBE_FLAG_MSI_ENABLED) { + adapter->flags &= ~IXGBE_FLAG_MSI_ENABLED; + pci_disable_msi(adapter->pdev); + } +} + +/** + * ixgbe_set_interrupt_capability - set MSI-X or MSI if supported + * @adapter: board private structure to initialize + * + * Attempt to configure the interrupts using the best available + * capabilities of the hardware and the kernel. + **/ +static void ixgbe_set_interrupt_capability(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int vector, v_budget, err; + + /* + * It's easy to be greedy for MSI-X vectors, but it really + * doesn't do us much good if we have a lot more vectors + * than CPU's. So let's be conservative and only ask for + * (roughly) the same number of vectors as there are CPU's. + * The default is to use pairs of vectors. + */ + v_budget = max(adapter->num_rx_queues, adapter->num_tx_queues); + v_budget = min_t(int, v_budget, num_online_cpus()); + v_budget += NON_Q_VECTORS; + + /* + * 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_t(int, v_budget, 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) + return; + } + + /* disable DCB if number of TCs exceeds 1 */ + if (netdev_get_num_tc(adapter->netdev) > 1) { + e_err(probe, "num TCs exceeds number of queues - disabling DCB\n"); + netdev_reset_tc(adapter->netdev); + + if (adapter->hw.mac.type == ixgbe_mac_82598EB) + adapter->hw.fc.requested_mode = adapter->last_lfc_mode; + + adapter->flags &= ~IXGBE_FLAG_DCB_ENABLED; + adapter->temp_dcb_cfg.pfc_mode_enable = false; + adapter->dcb_cfg.pfc_mode_enable = false; + } + adapter->dcb_cfg.num_tcs.pg_tcs = 1; + adapter->dcb_cfg.num_tcs.pfc_tcs = 1; + + /* disable SR-IOV */ + ixgbe_disable_sriov(adapter); + + /* disable RSS */ + adapter->ring_feature[RING_F_RSS].limit = 1; + + ixgbe_set_num_queues(adapter); + adapter->num_q_vectors = 1; + + err = pci_enable_msi(adapter->pdev); + if (err) { + netif_printk(adapter, hw, KERN_DEBUG, adapter->netdev, + "Unable to allocate MSI interrupt, falling back to legacy. Error: %d\n", + err); + return; + } + adapter->flags |= IXGBE_FLAG_MSI_ENABLED; +} + +/** + * ixgbe_init_interrupt_scheme - Determine proper interrupt scheme + * @adapter: board private structure to initialize + * + * We determine which interrupt scheme to use based on... + * - Kernel support (MSI, MSI-X) + * - which can be user-defined (via MODULE_PARAM) + * - Hardware queue count (num_*_queues) + * - defined by miscellaneous hardware support/features (RSS, etc.) + **/ +int ixgbe_init_interrupt_scheme(struct ixgbe_adapter *adapter) +{ + int err; + + /* Number of supported queues */ + ixgbe_set_num_queues(adapter); + + /* Set interrupt mode */ + ixgbe_set_interrupt_capability(adapter); + + err = ixgbe_alloc_q_vectors(adapter); + if (err) { + e_dev_err("Unable to allocate memory for queue vectors\n"); + goto err_alloc_q_vectors; + } + + ixgbe_cache_ring_register(adapter); + + e_dev_info("Multiqueue %s: Rx Queue count = %u, Tx Queue count = %u\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_q_vectors: + ixgbe_reset_interrupt_capability(adapter); + return err; +} + +/** + * ixgbe_clear_interrupt_scheme - Clear the current interrupt scheme settings + * @adapter: board private structure to clear interrupt scheme on + * + * We go through and clear interrupt specific resources and reset the structure + * to pre-load conditions + **/ +void ixgbe_clear_interrupt_scheme(struct ixgbe_adapter *adapter) +{ + adapter->num_tx_queues = 0; + adapter->num_rx_queues = 0; + + ixgbe_free_q_vectors(adapter); + ixgbe_reset_interrupt_capability(adapter); +} + +void ixgbe_tx_ctxtdesc(struct ixgbe_ring *tx_ring, u32 vlan_macip_lens, + u32 fcoe_sof_eof, u32 type_tucmd, u32 mss_l4len_idx) +{ + struct ixgbe_adv_tx_context_desc *context_desc; + u16 i = tx_ring->next_to_use; + + context_desc = IXGBE_TX_CTXTDESC(tx_ring, i); + + i++; + tx_ring->next_to_use = (i < tx_ring->count) ? i : 0; + + /* set bits to identify this as an advanced context descriptor */ + type_tucmd |= IXGBE_TXD_CMD_DEXT | IXGBE_ADVTXD_DTYP_CTXT; + + context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens); + context_desc->seqnum_seed = cpu_to_le32(fcoe_sof_eof); + context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd); + context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx); +} + diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 3dc6cef5810..f5aa3311ea2 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2014 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, @@ -20,6 +20,7 @@ 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 @@ -44,6 +45,8 @@ #include <linux/ethtool.h> #include <linux/if.h> #include <linux/if_vlan.h> +#include <linux/if_macvlan.h> +#include <linux/if_bridge.h> #include <linux/prefetch.h> #include <scsi/fc/fc_fcoe.h> @@ -55,16 +58,17 @@ char ixgbe_driver_name[] = "ixgbe"; static const char ixgbe_driver_string[] = "Intel(R) 10 Gigabit PCI Express Network Driver"; +#ifdef IXGBE_FCOE char ixgbe_default_device_descr[] = "Intel(R) 10 Gigabit Network Connection"; -#define MAJ 3 -#define MIN 6 -#define BUILD 7 -#define DRV_VERSION __stringify(MAJ) "." __stringify(MIN) "." \ - __stringify(BUILD) "-k" +#else +static char ixgbe_default_device_descr[] = + "Intel(R) 10 Gigabit Network Connection"; +#endif +#define DRV_VERSION "3.19.1-k" const char ixgbe_driver_version[] = DRV_VERSION; static const char ixgbe_copyright[] = - "Copyright (c) 1999-2012 Intel Corporation."; + "Copyright (c) 1999-2014 Intel Corporation."; static const struct ixgbe_info *ixgbe_info_tbl[] = { [board_82598] = &ixgbe_82598_info, @@ -107,8 +111,10 @@ static DEFINE_PCI_DEVICE_TABLE(ixgbe_pci_tbl) = { {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540T), board_X540 }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_SF2), board_82599 }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_LS), board_82599 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_QSFP_SF_QP), board_82599 }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599EN_SFP), board_82599 }, {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_82599_SFP_SF_QP), board_82599 }, + {PCI_VDEVICE(INTEL, IXGBE_DEV_ID_X540T1), board_X540 }, /* required last entry */ {0, } }; @@ -128,29 +134,275 @@ static struct notifier_block dca_notifier = { 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"); + "Maximum number of virtual functions to allocate per physical function - default is zero and maximum value is 63. (Deprecated)"); #endif /* CONFIG_PCI_IOV */ +static unsigned int allow_unsupported_sfp; +module_param(allow_unsupported_sfp, uint, 0); +MODULE_PARM_DESC(allow_unsupported_sfp, + "Allow unsupported and untested SFP+ modules on 82599-based adapters"); + +#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV|NETIF_MSG_PROBE|NETIF_MSG_LINK) +static int debug = -1; +module_param(debug, int, 0); +MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); + MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION("Intel(R) 10 Gigabit PCI Express Network Driver"); MODULE_LICENSE("GPL"); MODULE_VERSION(DRV_VERSION); -#define DEFAULT_DEBUG_LEVEL_SHIFT 3 +static bool ixgbe_check_cfg_remove(struct ixgbe_hw *hw, struct pci_dev *pdev); + +static int ixgbe_read_pci_cfg_word_parent(struct ixgbe_adapter *adapter, + u32 reg, u16 *value) +{ + struct pci_dev *parent_dev; + struct pci_bus *parent_bus; + + parent_bus = adapter->pdev->bus->parent; + if (!parent_bus) + return -1; + + parent_dev = parent_bus->self; + if (!parent_dev) + return -1; + + if (!pci_is_pcie(parent_dev)) + return -1; + + pcie_capability_read_word(parent_dev, reg, value); + if (*value == IXGBE_FAILED_READ_CFG_WORD && + ixgbe_check_cfg_remove(&adapter->hw, parent_dev)) + return -1; + return 0; +} + +static s32 ixgbe_get_parent_bus_info(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u16 link_status = 0; + int err; + + hw->bus.type = ixgbe_bus_type_pci_express; + + /* Get the negotiated link width and speed from PCI config space of the + * parent, as this device is behind a switch + */ + err = ixgbe_read_pci_cfg_word_parent(adapter, 18, &link_status); + + /* assume caller will handle error case */ + if (err) + return err; + + hw->bus.width = ixgbe_convert_bus_width(link_status); + hw->bus.speed = ixgbe_convert_bus_speed(link_status); + + return 0; +} + +/** + * ixgbe_check_from_parent - Determine whether PCIe info should come from parent + * @hw: hw specific details + * + * This function is used by probe to determine whether a device's PCI-Express + * bandwidth details should be gathered from the parent bus instead of from the + * device. Used to ensure that various locations all have the correct device ID + * checks. + */ +static inline bool ixgbe_pcie_from_parent(struct ixgbe_hw *hw) +{ + switch (hw->device_id) { + case IXGBE_DEV_ID_82599_SFP_SF_QP: + case IXGBE_DEV_ID_82599_QSFP_SF_QP: + return true; + default: + return false; + } +} + +static void ixgbe_check_minimum_link(struct ixgbe_adapter *adapter, + int expected_gts) +{ + int max_gts = 0; + enum pci_bus_speed speed = PCI_SPEED_UNKNOWN; + enum pcie_link_width width = PCIE_LNK_WIDTH_UNKNOWN; + struct pci_dev *pdev; + + /* determine whether to use the the parent device + */ + if (ixgbe_pcie_from_parent(&adapter->hw)) + pdev = adapter->pdev->bus->parent->self; + else + pdev = adapter->pdev; + + if (pcie_get_minimum_link(pdev, &speed, &width) || + speed == PCI_SPEED_UNKNOWN || width == PCIE_LNK_WIDTH_UNKNOWN) { + e_dev_warn("Unable to determine PCI Express bandwidth.\n"); + return; + } + + switch (speed) { + case PCIE_SPEED_2_5GT: + /* 8b/10b encoding reduces max throughput by 20% */ + max_gts = 2 * width; + break; + case PCIE_SPEED_5_0GT: + /* 8b/10b encoding reduces max throughput by 20% */ + max_gts = 4 * width; + break; + case PCIE_SPEED_8_0GT: + /* 128b/130b encoding reduces throughput by less than 2% */ + max_gts = 8 * width; + break; + default: + e_dev_warn("Unable to determine PCI Express bandwidth.\n"); + return; + } + + e_dev_info("PCI Express bandwidth of %dGT/s available\n", + max_gts); + e_dev_info("(Speed:%s, Width: x%d, Encoding Loss:%s)\n", + (speed == PCIE_SPEED_8_0GT ? "8.0GT/s" : + speed == PCIE_SPEED_5_0GT ? "5.0GT/s" : + speed == PCIE_SPEED_2_5GT ? "2.5GT/s" : + "Unknown"), + width, + (speed == PCIE_SPEED_2_5GT ? "20%" : + speed == PCIE_SPEED_5_0GT ? "20%" : + speed == PCIE_SPEED_8_0GT ? "<2%" : + "Unknown")); + + if (max_gts < expected_gts) { + e_dev_warn("This is not sufficient for optimal performance of this card.\n"); + e_dev_warn("For optimal performance, at least %dGT/s of bandwidth is required.\n", + expected_gts); + e_dev_warn("A slot with more lanes and/or higher speed is suggested.\n"); + } +} static void ixgbe_service_event_schedule(struct ixgbe_adapter *adapter) { if (!test_bit(__IXGBE_DOWN, &adapter->state) && + !test_bit(__IXGBE_REMOVING, &adapter->state) && !test_and_set_bit(__IXGBE_SERVICE_SCHED, &adapter->state)) schedule_work(&adapter->service_task); } +static void ixgbe_remove_adapter(struct ixgbe_hw *hw) +{ + struct ixgbe_adapter *adapter = hw->back; + + if (!hw->hw_addr) + return; + hw->hw_addr = NULL; + e_dev_err("Adapter removed\n"); + if (test_bit(__IXGBE_SERVICE_INITED, &adapter->state)) + ixgbe_service_event_schedule(adapter); +} + +static void ixgbe_check_remove(struct ixgbe_hw *hw, u32 reg) +{ + u32 value; + + /* The following check not only optimizes a bit by not + * performing a read on the status register when the + * register just read was a status register read that + * returned IXGBE_FAILED_READ_REG. It also blocks any + * potential recursion. + */ + if (reg == IXGBE_STATUS) { + ixgbe_remove_adapter(hw); + return; + } + value = ixgbe_read_reg(hw, IXGBE_STATUS); + if (value == IXGBE_FAILED_READ_REG) + ixgbe_remove_adapter(hw); +} + +/** + * ixgbe_read_reg - Read from device register + * @hw: hw specific details + * @reg: offset of register to read + * + * Returns : value read or IXGBE_FAILED_READ_REG if removed + * + * This function is used to read device registers. It checks for device + * removal by confirming any read that returns all ones by checking the + * status register value for all ones. This function avoids reading from + * the hardware if a removal was previously detected in which case it + * returns IXGBE_FAILED_READ_REG (all ones). + */ +u32 ixgbe_read_reg(struct ixgbe_hw *hw, u32 reg) +{ + u8 __iomem *reg_addr = ACCESS_ONCE(hw->hw_addr); + u32 value; + + if (ixgbe_removed(reg_addr)) + return IXGBE_FAILED_READ_REG; + value = readl(reg_addr + reg); + if (unlikely(value == IXGBE_FAILED_READ_REG)) + ixgbe_check_remove(hw, reg); + return value; +} + +static bool ixgbe_check_cfg_remove(struct ixgbe_hw *hw, struct pci_dev *pdev) +{ + u16 value; + + pci_read_config_word(pdev, PCI_VENDOR_ID, &value); + if (value == IXGBE_FAILED_READ_CFG_WORD) { + ixgbe_remove_adapter(hw); + return true; + } + return false; +} + +u16 ixgbe_read_pci_cfg_word(struct ixgbe_hw *hw, u32 reg) +{ + struct ixgbe_adapter *adapter = hw->back; + u16 value; + + if (ixgbe_removed(hw->hw_addr)) + return IXGBE_FAILED_READ_CFG_WORD; + pci_read_config_word(adapter->pdev, reg, &value); + if (value == IXGBE_FAILED_READ_CFG_WORD && + ixgbe_check_cfg_remove(hw, adapter->pdev)) + return IXGBE_FAILED_READ_CFG_WORD; + return value; +} + +#ifdef CONFIG_PCI_IOV +static u32 ixgbe_read_pci_cfg_dword(struct ixgbe_hw *hw, u32 reg) +{ + struct ixgbe_adapter *adapter = hw->back; + u32 value; + + if (ixgbe_removed(hw->hw_addr)) + return IXGBE_FAILED_READ_CFG_DWORD; + pci_read_config_dword(adapter->pdev, reg, &value); + if (value == IXGBE_FAILED_READ_CFG_DWORD && + ixgbe_check_cfg_remove(hw, adapter->pdev)) + return IXGBE_FAILED_READ_CFG_DWORD; + return value; +} +#endif /* CONFIG_PCI_IOV */ + +void ixgbe_write_pci_cfg_word(struct ixgbe_hw *hw, u32 reg, u16 value) +{ + struct ixgbe_adapter *adapter = hw->back; + + if (ixgbe_removed(hw->hw_addr)) + return; + pci_write_config_word(adapter->pdev, reg, value); +} + static void ixgbe_service_event_complete(struct ixgbe_adapter *adapter) { BUG_ON(!test_bit(__IXGBE_SERVICE_SCHED, &adapter->state)); /* flush memory to make sure state is correct before next watchdog */ - smp_mb__before_clear_bit(); + smp_mb__before_atomic(); clear_bit(__IXGBE_SERVICE_SCHED, &adapter->state); } @@ -284,7 +536,7 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter) struct ixgbe_reg_info *reginfo; int n = 0; struct ixgbe_ring *tx_ring; - struct ixgbe_tx_buffer *tx_buffer_info; + struct ixgbe_tx_buffer *tx_buffer; union ixgbe_adv_tx_desc *tx_desc; struct my_u0 { u64 a; u64 b; } *u0; struct ixgbe_ring *rx_ring; @@ -321,17 +573,18 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter) goto exit; dev_info(&adapter->pdev->dev, "TX Rings Summary\n"); - pr_info("Queue [NTU] [NTC] [bi(ntc)->dma ] leng ntw timestamp\n"); + pr_info(" %s %s %s %s\n", + "Queue [NTU] [NTC] [bi(ntc)->dma ]", + "leng", "ntw", "timestamp"); for (n = 0; n < adapter->num_tx_queues; n++) { 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 %p %016llX\n", + tx_buffer = &tx_ring->tx_buffer_info[tx_ring->next_to_clean]; + pr_info(" %5d %5X %5X %016llX %08X %p %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); + (u64)dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + tx_buffer->next_to_watch, + (u64)tx_buffer->time_stamp); } /* Print TX Rings */ @@ -342,13 +595,37 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter) /* Transmit Descriptor Formats * - * Advanced Transmit Descriptor + * 82598 Advanced Transmit Descriptor * +--------------------------------------------------------------+ * 0 | Buffer Address [63:0] | * +--------------------------------------------------------------+ - * 8 | PAYLEN | PORTS | IDX | STA | DCMD |DTYP | RSV | DTALEN | + * 8 | PAYLEN | POPTS | IDX | STA | DCMD |DTYP | RSV | DTALEN | * +--------------------------------------------------------------+ * 63 46 45 40 39 36 35 32 31 24 23 20 19 0 + * + * 82598 Advanced Transmit Descriptor (Write-Back Format) + * +--------------------------------------------------------------+ + * 0 | RSV [63:0] | + * +--------------------------------------------------------------+ + * 8 | RSV | STA | NXTSEQ | + * +--------------------------------------------------------------+ + * 63 36 35 32 31 0 + * + * 82599+ Advanced Transmit Descriptor + * +--------------------------------------------------------------+ + * 0 | Buffer Address [63:0] | + * +--------------------------------------------------------------+ + * 8 |PAYLEN |POPTS|CC|IDX |STA |DCMD |DTYP |MAC |RSV |DTALEN | + * +--------------------------------------------------------------+ + * 63 46 45 40 39 38 36 35 32 31 24 23 20 19 18 17 16 15 0 + * + * 82599+ Advanced Transmit Descriptor (Write-Back Format) + * +--------------------------------------------------------------+ + * 0 | RSV [63:0] | + * +--------------------------------------------------------------+ + * 8 | RSV | STA | RSV | + * +--------------------------------------------------------------+ + * 63 36 35 32 31 0 */ for (n = 0; n < adapter->num_tx_queues; n++) { @@ -356,39 +633,43 @@ static void ixgbe_dump(struct ixgbe_adapter *adapter) 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"); + pr_info("%s%s %s %s %s %s\n", + "T [desc] [address 63:0 ] ", + "[PlPOIdStDDt Ln] [bi->dma ] ", + "leng", "ntw", "timestamp", "bi->skb"); for (i = 0; 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]; + tx_desc = IXGBE_TX_DESC(tx_ring, i); + tx_buffer = &tx_ring->tx_buffer_info[i]; u0 = (struct my_u0 *)tx_desc; - pr_info("T [0x%03X] %016llX %016llX %016llX" - " %04X %p %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); + if (dma_unmap_len(tx_buffer, len) > 0) { + pr_info("T [0x%03X] %016llX %016llX %016llX %08X %p %016llX %p", + i, + le64_to_cpu(u0->a), + le64_to_cpu(u0->b), + (u64)dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + tx_buffer->next_to_watch, + (u64)tx_buffer->time_stamp, + tx_buffer->skb); + 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->skb) + print_hex_dump(KERN_INFO, "", + DUMP_PREFIX_ADDRESS, 16, 1, + tx_buffer->skb->data, + dma_unmap_len(tx_buffer, len), + true); + } } } @@ -408,7 +689,9 @@ rx_ring_summary: dev_info(&adapter->pdev->dev, "RX Rings Dump\n"); - /* Advanced Receive Descriptor (Read) Format + /* Receive Descriptor Formats + * + * 82598 Advanced Receive Descriptor (Read) Format * 63 1 0 * +-----------------------------------------------------+ * 0 | Packet Buffer Address [63:1] |A0/NSE| @@ -417,32 +700,57 @@ rx_ring_summary: * +-----------------------------------------------------+ * * - * Advanced Receive Descriptor (Write-Back) Format + * 82598 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 | + * 0 | RSS Hash / |SPH| HDR_LEN | RSV |Packet| RSS | + * | Packet | IP | | | | Type | Type | + * | Checksum | Ident | | | | | | * +------------------------------------------------------+ * 8 | VLAN Tag | Length | Extended Error | Extended Status | * +------------------------------------------------------+ * 63 48 47 32 31 20 19 0 + * + * 82599+ Advanced Receive Descriptor (Read) Format + * 63 1 0 + * +-----------------------------------------------------+ + * 0 | Packet Buffer Address [63:1] |A0/NSE| + * +----------------------------------------------+------+ + * 8 | Header Buffer Address [63:1] | DD | + * +-----------------------------------------------------+ + * + * + * 82599+ Advanced Receive Descriptor (Write-Back) Format + * + * 63 48 47 32 31 30 21 20 17 16 4 3 0 + * +------------------------------------------------------+ + * 0 |RSS / Frag Checksum|SPH| HDR_LEN |RSC- |Packet| RSS | + * |/ RTT / PCoE_PARAM | | | CNT | Type | Type | + * |/ Flow Dir Flt ID | | | | | | + * +------------------------------------------------------+ + * 8 | VLAN Tag | Length |Extended Error| Xtnd Status/NEXTP | + * +------------------------------------------------------+ + * 63 48 47 32 31 20 19 0 */ + for (n = 0; n < adapter->num_rx_queues; n++) { rx_ring = adapter->rx_ring[n]; pr_info("------------------------------------\n"); pr_info("RX QUEUE INDEX = %d\n", rx_ring->queue_index); pr_info("------------------------------------\n"); - pr_info("R [desc] [ PktBuf A0] " - "[ HeadBuf DD] [bi->dma ] [bi->skb] " + pr_info("%s%s%s", + "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] " + pr_info("%s%s%s", + "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); + rx_desc = IXGBE_RX_DESC(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) { @@ -460,21 +768,13 @@ rx_ring_summary: (u64)rx_buffer_info->dma, rx_buffer_info->skb); - if (netif_msg_pktdata(adapter)) { + if (netif_msg_pktdata(adapter) && + rx_buffer_info->dma) { 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_2K) - 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); + page_address(rx_buffer_info->page) + + rx_buffer_info->page_offset, + ixgbe_rx_bufsz(rx_ring), true); } } @@ -512,7 +812,7 @@ static void ixgbe_get_hw_control(struct ixgbe_adapter *adapter) 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 @@ -584,81 +884,96 @@ static inline void ixgbe_irq_rearm_queues(struct ixgbe_adapter *adapter, } } -static inline void ixgbe_unmap_tx_resource(struct ixgbe_ring *ring, - struct ixgbe_tx_buffer *tx_buffer) +void ixgbe_unmap_and_free_tx_resource(struct ixgbe_ring *ring, + struct ixgbe_tx_buffer *tx_buffer) { - if (tx_buffer->dma) { - if (tx_buffer->tx_flags & IXGBE_TX_FLAGS_MAPPED_AS_PAGE) - dma_unmap_page(ring->dev, - tx_buffer->dma, - tx_buffer->length, - DMA_TO_DEVICE); - else + if (tx_buffer->skb) { + dev_kfree_skb_any(tx_buffer->skb); + if (dma_unmap_len(tx_buffer, len)) dma_unmap_single(ring->dev, - tx_buffer->dma, - tx_buffer->length, - DMA_TO_DEVICE); + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + } else if (dma_unmap_len(tx_buffer, len)) { + dma_unmap_page(ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); } - tx_buffer->dma = 0; + tx_buffer->next_to_watch = NULL; + tx_buffer->skb = NULL; + dma_unmap_len_set(tx_buffer, len, 0); + /* tx_buffer must be completely set up in the transmit path */ } -void ixgbe_unmap_and_free_tx_resource(struct ixgbe_ring *tx_ring, - struct ixgbe_tx_buffer *tx_buffer_info) +static void ixgbe_update_xoff_rx_lfc(struct ixgbe_adapter *adapter) { - ixgbe_unmap_tx_resource(tx_ring, tx_buffer_info); - if (tx_buffer_info->skb) - dev_kfree_skb_any(tx_buffer_info->skb); - tx_buffer_info->skb = NULL; - /* tx_buffer_info must be completely set up in the transmit path */ + struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_hw_stats *hwstats = &adapter->stats; + int i; + u32 data; + + if ((hw->fc.current_mode != ixgbe_fc_full) && + (hw->fc.current_mode != ixgbe_fc_rx_pause)) + return; + + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + data = IXGBE_READ_REG(hw, IXGBE_LXOFFRXC); + break; + default: + data = IXGBE_READ_REG(hw, IXGBE_LXOFFRXCNT); + } + hwstats->lxoffrxc += data; + + /* refill credits (no tx hang) if we received xoff */ + if (!data) + return; + + for (i = 0; i < adapter->num_tx_queues; i++) + clear_bit(__IXGBE_HANG_CHECK_ARMED, + &adapter->tx_ring[i]->state); } 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}; + u8 tc; int i; + bool pfc_en = adapter->dcb_cfg.pfc_mode_enable; - 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; + if (adapter->ixgbe_ieee_pfc) + pfc_en |= !!(adapter->ixgbe_ieee_pfc->pfc_en); - 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)) + if (!(adapter->flags & IXGBE_FLAG_DCB_ENABLED) || !pfc_en) { + ixgbe_update_xoff_rx_lfc(adapter); return; + } /* update stats for each tc, only valid with PFC enabled */ for (i = 0; i < MAX_TX_PACKET_BUFFERS; i++) { + u32 pxoffrxc; + switch (hw->mac.type) { case ixgbe_mac_82598EB: - xoff[i] = IXGBE_READ_REG(hw, IXGBE_PXOFFRXC(i)); + pxoffrxc = IXGBE_READ_REG(hw, IXGBE_PXOFFRXC(i)); break; default: - xoff[i] = IXGBE_READ_REG(hw, IXGBE_PXOFFRXCNT(i)); + pxoffrxc = IXGBE_READ_REG(hw, IXGBE_PXOFFRXCNT(i)); } - hwstats->pxoffrxc[i] += xoff[i]; + hwstats->pxoffrxc[i] += pxoffrxc; + /* Get the TC for given UP */ + tc = netdev_get_prio_tc_map(adapter->netdev, i); + xoff[tc] += pxoffrxc; } /* disarm tx queues that have received xoff frames */ for (i = 0; i < adapter->num_tx_queues; i++) { struct ixgbe_ring *tx_ring = adapter->tx_ring[i]; - u8 tc = tx_ring->dcb_tc; + tc = tx_ring->dcb_tc; if (xoff[tc]) clear_bit(__IXGBE_HANG_CHECK_ARMED, &tx_ring->state); } @@ -666,16 +981,23 @@ static void ixgbe_update_xoff_received(struct ixgbe_adapter *adapter) static u64 ixgbe_get_tx_completed(struct ixgbe_ring *ring) { - return ring->tx_stats.completed; + return ring->stats.packets; } static u64 ixgbe_get_tx_pending(struct ixgbe_ring *ring) { - struct ixgbe_adapter *adapter = netdev_priv(ring->netdev); - struct ixgbe_hw *hw = &adapter->hw; + struct ixgbe_adapter *adapter; + struct ixgbe_hw *hw; + u32 head, tail; - u32 head = IXGBE_READ_REG(hw, IXGBE_TDH(ring->reg_idx)); - u32 tail = IXGBE_READ_REG(hw, IXGBE_TDT(ring->reg_idx)); + if (ring->l2_accel_priv) + adapter = ring->l2_accel_priv->real_adapter; + else + adapter = netdev_priv(ring->netdev); + + hw = &adapter->hw; + head = IXGBE_READ_REG(hw, IXGBE_TDH(ring->reg_idx)); + tail = IXGBE_READ_REG(hw, IXGBE_TDT(ring->reg_idx)); if (head != tail) return (head < tail) ? @@ -729,6 +1051,7 @@ 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; + e_warn(drv, "initiating reset due to tx timeout\n"); ixgbe_service_event_schedule(adapter); } } @@ -746,56 +1069,88 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, union ixgbe_adv_tx_desc *tx_desc; unsigned int total_bytes = 0, total_packets = 0; unsigned int budget = q_vector->tx.work_limit; - u16 i = tx_ring->next_to_clean; + unsigned int i = tx_ring->next_to_clean; + + if (test_bit(__IXGBE_DOWN, &adapter->state)) + return true; tx_buffer = &tx_ring->tx_buffer_info[i]; - tx_desc = IXGBE_TX_DESC_ADV(tx_ring, i); + tx_desc = IXGBE_TX_DESC(tx_ring, i); + i -= tx_ring->count; - for (; budget; budget--) { + do { union ixgbe_adv_tx_desc *eop_desc = tx_buffer->next_to_watch; /* if next_to_watch is not set then there is no work pending */ if (!eop_desc) break; + /* prevent any other reads prior to eop_desc */ + read_barrier_depends(); + /* if DD is not set pending work has not been completed */ if (!(eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD))) break; - /* count the packet as being completed */ - tx_ring->tx_stats.completed++; - /* clear next_to_watch to prevent false hangs */ tx_buffer->next_to_watch = NULL; - /* prevent any other reads prior to eop_desc being verified */ - rmb(); + /* update the statistics for this packet */ + total_bytes += tx_buffer->bytecount; + total_packets += tx_buffer->gso_segs; - do { - ixgbe_unmap_tx_resource(tx_ring, tx_buffer); - tx_desc->wb.status = 0; - if (likely(tx_desc == eop_desc)) { - eop_desc = NULL; - dev_kfree_skb_any(tx_buffer->skb); - tx_buffer->skb = NULL; + /* free the skb */ + dev_kfree_skb_any(tx_buffer->skb); - total_bytes += tx_buffer->bytecount; - total_packets += tx_buffer->gso_segs; - } + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + + /* clear tx_buffer data */ + tx_buffer->skb = NULL; + dma_unmap_len_set(tx_buffer, len, 0); + /* unmap remaining buffers */ + while (tx_desc != eop_desc) { tx_buffer++; tx_desc++; i++; - if (unlikely(i == tx_ring->count)) { - i = 0; - + if (unlikely(!i)) { + i -= tx_ring->count; tx_buffer = tx_ring->tx_buffer_info; - tx_desc = IXGBE_TX_DESC_ADV(tx_ring, 0); + tx_desc = IXGBE_TX_DESC(tx_ring, 0); } - } while (eop_desc); - } + /* unmap any remaining paged data */ + if (dma_unmap_len(tx_buffer, len)) { + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + } + } + + /* move us one more past the eop_desc for start of next pkt */ + tx_buffer++; + tx_desc++; + i++; + if (unlikely(!i)) { + i -= tx_ring->count; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = IXGBE_TX_DESC(tx_ring, 0); + } + /* issue prefetch for next Tx descriptor */ + prefetch(tx_desc); + + /* update budget accounting */ + budget--; + } while (likely(budget)); + + i += tx_ring->count; tx_ring->next_to_clean = i; u64_stats_update_begin(&tx_ring->syncp); tx_ring->stats.bytes += total_bytes; @@ -807,7 +1162,6 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, 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, i); e_err(drv, "Detected Tx Unit Hang\n" " Tx Queue <%d>\n" " TDH, TDT <%x>, <%x>\n" @@ -835,6 +1189,9 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, return true; } + netdev_tx_completed_queue(txring_txq(tx_ring), + total_packets, total_bytes); + #define TX_WAKE_THRESHOLD (DESC_NEEDED * 2) if (unlikely(total_packets && netif_carrier_ok(tx_ring->netdev) && (ixgbe_desc_unused(tx_ring) >= TX_WAKE_THRESHOLD))) { @@ -842,9 +1199,11 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, * 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); + 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; } } @@ -853,63 +1212,67 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, } #ifdef CONFIG_IXGBE_DCA -static void ixgbe_update_rx_dca(struct ixgbe_adapter *adapter, - struct ixgbe_ring *rx_ring, +static void ixgbe_update_tx_dca(struct ixgbe_adapter *adapter, + struct ixgbe_ring *tx_ring, int cpu) { struct ixgbe_hw *hw = &adapter->hw; - u32 rxctrl; - u8 reg_idx = rx_ring->reg_idx; + u32 txctrl = dca3_get_tag(tx_ring->dev, cpu); + u16 reg_offset; - 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(rx_ring->dev, cpu); + reg_offset = IXGBE_DCA_TXCTRL(tx_ring->reg_idx); break; case ixgbe_mac_82599EB: case ixgbe_mac_X540: - rxctrl &= ~IXGBE_DCA_RXCTRL_CPUID_MASK_82599; - rxctrl |= (dca3_get_tag(rx_ring->dev, cpu) << - IXGBE_DCA_RXCTRL_CPUID_SHIFT_82599); + reg_offset = IXGBE_DCA_TXCTRL_82599(tx_ring->reg_idx); + txctrl <<= IXGBE_DCA_TXCTRL_CPUID_SHIFT_82599; break; default: - break; + /* for unknown hardware do not write register */ + return; } - 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); + + /* + * We can enable relaxed ordering for reads, but not writes when + * DCA is enabled. This is due to a known issue in some chipsets + * which will cause the DCA tag to be cleared. + */ + txctrl |= IXGBE_DCA_TXCTRL_DESC_RRO_EN | + IXGBE_DCA_TXCTRL_DATA_RRO_EN | + IXGBE_DCA_TXCTRL_DESC_DCA_EN; + + IXGBE_WRITE_REG(hw, reg_offset, txctrl); } -static void ixgbe_update_tx_dca(struct ixgbe_adapter *adapter, - struct ixgbe_ring *tx_ring, +static void ixgbe_update_rx_dca(struct ixgbe_adapter *adapter, + struct ixgbe_ring *rx_ring, int cpu) { struct ixgbe_hw *hw = &adapter->hw; - u32 txctrl; - u8 reg_idx = tx_ring->reg_idx; + u32 rxctrl = dca3_get_tag(rx_ring->dev, cpu); + u8 reg_idx = rx_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(tx_ring->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(tx_ring->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); + rxctrl <<= IXGBE_DCA_RXCTRL_CPUID_SHIFT_82599; break; default: break; } + + /* + * We can enable relaxed ordering for reads, but not writes when + * DCA is enabled. This is due to a known issue in some chipsets + * which will cause the DCA tag to be cleared. + */ + rxctrl |= IXGBE_DCA_RXCTRL_DESC_RRO_EN | + IXGBE_DCA_RXCTRL_DESC_DCA_EN; + + IXGBE_WRITE_REG(hw, IXGBE_DCA_RXCTRL(reg_idx), rxctrl); } static void ixgbe_update_dca(struct ixgbe_q_vector *q_vector) @@ -921,10 +1284,10 @@ static void ixgbe_update_dca(struct ixgbe_q_vector *q_vector) if (q_vector->cpu == cpu) goto out_no_update; - for (ring = q_vector->tx.ring; ring != NULL; ring = ring->next) + ixgbe_for_each_ring(ring, q_vector->tx) ixgbe_update_tx_dca(adapter, ring, cpu); - for (ring = q_vector->rx.ring; ring != NULL; ring = ring->next) + ixgbe_for_each_ring(ring, q_vector->rx) ixgbe_update_rx_dca(adapter, ring, cpu); q_vector->cpu = cpu; @@ -934,7 +1297,6 @@ out_no_update: static void ixgbe_setup_dca(struct ixgbe_adapter *adapter) { - int num_q_vectors; int i; if (!(adapter->flags & IXGBE_FLAG_DCA_ENABLED)) @@ -943,12 +1305,7 @@ static void ixgbe_setup_dca(struct ixgbe_adapter *adapter) /* 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++) { + for (i = 0; i < adapter->num_q_vectors; i++) { adapter->q_vector[i]->cpu = -1; ixgbe_update_dca(adapter->q_vector[i]); } @@ -984,99 +1341,76 @@ static int __ixgbe_notify_dca(struct device *dev, void *data) return 0; } -#endif /* CONFIG_IXGBE_DCA */ -static inline void ixgbe_rx_hash(union ixgbe_adv_rx_desc *rx_desc, +#endif /* CONFIG_IXGBE_DCA */ +static inline void ixgbe_rx_hash(struct ixgbe_ring *ring, + union ixgbe_adv_rx_desc *rx_desc, struct sk_buff *skb) { - skb->rxhash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss); + if (ring->netdev->features & NETIF_F_RXHASH) + skb_set_hash(skb, + le32_to_cpu(rx_desc->wb.lower.hi_dword.rss), + PKT_HASH_TYPE_L3); } +#ifdef IXGBE_FCOE /** * ixgbe_rx_is_fcoe - check the rx desc for incoming pkt type - * @adapter: address of board private structure + * @ring: structure containing ring specific data * @rx_desc: advanced rx descriptor * * Returns : true if it is FCoE pkt */ -static inline bool ixgbe_rx_is_fcoe(struct ixgbe_adapter *adapter, +static inline bool ixgbe_rx_is_fcoe(struct ixgbe_ring *ring, union ixgbe_adv_rx_desc *rx_desc) { __le16 pkt_info = rx_desc->wb.lower.lo_dword.hs_rss.pkt_info; - return (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) && + return test_bit(__IXGBE_RX_FCOE, &ring->state) && ((pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_ETQF_MASK)) == (cpu_to_le16(IXGBE_ETQF_FILTER_FCOE << IXGBE_RXDADV_PKTTYPE_ETQF_SHIFT))); } -/** - * 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); -} - +#endif /* IXGBE_FCOE */ /** * 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 + * @ring: structure containing ring specific data + * @rx_desc: current Rx descriptor being processed * @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, +static inline void ixgbe_rx_checksum(struct ixgbe_ring *ring, union ixgbe_adv_rx_desc *rx_desc, - struct sk_buff *skb, - u32 status_err) + struct sk_buff *skb) { - skb->ip_summed = CHECKSUM_NONE; + skb_checksum_none_assert(skb); /* Rx csum disabled */ - if (!(adapter->flags & IXGBE_FLAG_RX_CSUM_ENABLED)) + if (!(ring->netdev->features & NETIF_F_RXCSUM)) return; /* if IP and error */ - if ((status_err & IXGBE_RXD_STAT_IPCS) && - (status_err & IXGBE_RXDADV_ERR_IPE)) { - adapter->hw_csum_rx_error++; + if (ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_IPCS) && + ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_IPE)) { + ring->rx_stats.csum_err++; return; } - if (!(status_err & IXGBE_RXD_STAT_L4CS)) + if (!ixgbe_test_staterr(rx_desc, 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; + if (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_ERR_TCPE)) { + __le16 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)) + if ((pkt_info & cpu_to_le16(IXGBE_RXDADV_PKTTYPE_UDP)) && + test_bit(__IXGBE_RX_CSUM_UDP_ZERO_ERR, &ring->state)) return; - adapter->hw_csum_rx_error++; + ring->rx_stats.csum_err++; return; } @@ -1086,6 +1420,10 @@ static inline void ixgbe_rx_checksum(struct ixgbe_adapter *adapter, static inline void ixgbe_release_rx_desc(struct ixgbe_ring *rx_ring, u32 val) { + rx_ring->next_to_use = val; + + /* update next to alloc since we have filled the ring */ + rx_ring->next_to_alloc = val; /* * Force memory writes to complete before letting h/w * know there are new descriptors to fetch. (Only @@ -1093,11 +1431,54 @@ static inline void ixgbe_release_rx_desc(struct ixgbe_ring *rx_ring, u32 val) * such as IA-64). */ wmb(); - writel(val, rx_ring->tail); + ixgbe_write_tail(rx_ring, val); +} + +static bool ixgbe_alloc_mapped_page(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *bi) +{ + struct page *page = bi->page; + dma_addr_t dma = bi->dma; + + /* since we are recycling buffers we should seldom need to alloc */ + if (likely(dma)) + return true; + + /* alloc new page for storage */ + if (likely(!page)) { + page = __skb_alloc_pages(GFP_ATOMIC | __GFP_COLD | __GFP_COMP, + bi->skb, ixgbe_rx_pg_order(rx_ring)); + if (unlikely(!page)) { + rx_ring->rx_stats.alloc_rx_page_failed++; + return false; + } + bi->page = page; + } + + /* map page for use */ + dma = dma_map_page(rx_ring->dev, page, 0, + ixgbe_rx_pg_size(rx_ring), DMA_FROM_DEVICE); + + /* + * if mapping failed free memory back to system since + * there isn't much point in holding memory we can't use + */ + if (dma_mapping_error(rx_ring->dev, dma)) { + __free_pages(page, ixgbe_rx_pg_order(rx_ring)); + bi->page = NULL; + + rx_ring->rx_stats.alloc_rx_page_failed++; + return false; + } + + bi->dma = dma; + bi->page_offset = 0; + + return true; } /** - * ixgbe_alloc_rx_buffers - Replace used receive buffers; packet split + * ixgbe_alloc_rx_buffers - Replace used receive buffers * @rx_ring: ring to place buffers on * @cleaned_count: number of buffers to replace **/ @@ -1105,327 +1486,636 @@ 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) + /* nothing to do */ + if (!cleaned_count) 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; - } + rx_desc = IXGBE_RX_DESC(rx_ring, i); + bi = &rx_ring->rx_buffer_info[i]; + i -= rx_ring->count; - 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; - } + do { + if (!ixgbe_alloc_mapped_page(rx_ring, bi)) + break; + + /* + * Refresh the desc even if buffer_addrs didn't change + * because each write-back erases this info. + */ + rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset); + + rx_desc++; + bi++; + i++; + if (unlikely(!i)) { + rx_desc = IXGBE_RX_DESC(rx_ring, 0); + bi = rx_ring->rx_buffer_info; + i -= rx_ring->count; } - if (ring_is_ps_enabled(rx_ring)) { - if (!bi->page) { - bi->page = alloc_page(GFP_ATOMIC | __GFP_COLD); - if (!bi->page) { - rx_ring->rx_stats.alloc_rx_page_failed++; - goto no_buffers; - } - } + /* clear the hdr_addr for the next_to_use descriptor */ + rx_desc->read.hdr_addr = 0; - 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; - } - } + cleaned_count--; + } while (cleaned_count); - /* Refresh the desc even if buffer_addrs didn't change - * because each write-back erases this info. */ - rx_desc->read.pkt_addr = cpu_to_le64(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 += rx_ring->count; - i++; - if (i == rx_ring->count) - i = 0; + if (rx_ring->next_to_use != i) + ixgbe_release_rx_desc(rx_ring, i); +} + +/** + * ixgbe_get_headlen - determine size of header for RSC/LRO/GRO/FCOE + * @data: pointer to the start of the headers + * @max_len: total length of section to find headers in + * + * This function is meant to determine the length of headers that will + * be recognized by hardware for LRO, GRO, and RSC offloads. The main + * motivation of doing this is to only perform one pull for IPv4 TCP + * packets so that we can do basic things like calculating the gso_size + * based on the average data per packet. + **/ +static unsigned int ixgbe_get_headlen(unsigned char *data, + unsigned int max_len) +{ + union { + unsigned char *network; + /* l2 headers */ + struct ethhdr *eth; + struct vlan_hdr *vlan; + /* l3 headers */ + struct iphdr *ipv4; + struct ipv6hdr *ipv6; + } hdr; + __be16 protocol; + u8 nexthdr = 0; /* default to not TCP */ + u8 hlen; + + /* this should never happen, but better safe than sorry */ + if (max_len < ETH_HLEN) + return max_len; + + /* initialize network frame pointer */ + hdr.network = data; + + /* set first protocol and move network header forward */ + protocol = hdr.eth->h_proto; + hdr.network += ETH_HLEN; + + /* handle any vlan tag if present */ + if (protocol == htons(ETH_P_8021Q)) { + if ((hdr.network - data) > (max_len - VLAN_HLEN)) + return max_len; + + protocol = hdr.vlan->h_vlan_encapsulated_proto; + hdr.network += VLAN_HLEN; } -no_buffers: - if (rx_ring->next_to_use != i) { - rx_ring->next_to_use = i; - ixgbe_release_rx_desc(rx_ring, i); + /* handle L3 protocols */ + if (protocol == htons(ETH_P_IP)) { + if ((hdr.network - data) > (max_len - sizeof(struct iphdr))) + return max_len; + + /* access ihl as a u8 to avoid unaligned access on ia64 */ + hlen = (hdr.network[0] & 0x0F) << 2; + + /* verify hlen meets minimum size requirements */ + if (hlen < sizeof(struct iphdr)) + return hdr.network - data; + + /* record next protocol if header is present */ + if (!(hdr.ipv4->frag_off & htons(IP_OFFSET))) + nexthdr = hdr.ipv4->protocol; + } else if (protocol == htons(ETH_P_IPV6)) { + if ((hdr.network - data) > (max_len - sizeof(struct ipv6hdr))) + return max_len; + + /* record next protocol */ + nexthdr = hdr.ipv6->nexthdr; + hlen = sizeof(struct ipv6hdr); +#ifdef IXGBE_FCOE + } else if (protocol == htons(ETH_P_FCOE)) { + if ((hdr.network - data) > (max_len - FCOE_HEADER_LEN)) + return max_len; + hlen = FCOE_HEADER_LEN; +#endif + } else { + return hdr.network - data; } + + /* relocate pointer to start of L4 header */ + hdr.network += hlen; + + /* finally sort out TCP/UDP */ + if (nexthdr == IPPROTO_TCP) { + if ((hdr.network - data) > (max_len - sizeof(struct tcphdr))) + return max_len; + + /* access doff as a u8 to avoid unaligned access on ia64 */ + hlen = (hdr.network[12] & 0xF0) >> 2; + + /* verify hlen meets minimum size requirements */ + if (hlen < sizeof(struct tcphdr)) + return hdr.network - data; + + hdr.network += hlen; + } else if (nexthdr == IPPROTO_UDP) { + if ((hdr.network - data) > (max_len - sizeof(struct udphdr))) + return max_len; + + hdr.network += sizeof(struct udphdr); + } + + /* + * If everything has gone correctly hdr.network should be the + * data section of the packet and will be the end of the header. + * If not then it probably represents the end of the last recognized + * header. + */ + if ((hdr.network - data) < max_len) + return hdr.network - data; + else + return max_len; } -static inline u16 ixgbe_get_hlen(union ixgbe_adv_rx_desc *rx_desc) +static void ixgbe_set_rsc_gso_size(struct ixgbe_ring *ring, + struct sk_buff *skb) { - /* 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; + u16 hdr_len = skb_headlen(skb); + + /* set gso_size to avoid messing up TCP MSS */ + skb_shinfo(skb)->gso_size = DIV_ROUND_UP((skb->len - hdr_len), + IXGBE_CB(skb)->append_cnt); + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; +} + +static void ixgbe_update_rsc_stats(struct ixgbe_ring *rx_ring, + struct sk_buff *skb) +{ + /* if append_cnt is 0 then frame is not RSC */ + if (!IXGBE_CB(skb)->append_cnt) + return; + + rx_ring->rx_stats.rsc_count += IXGBE_CB(skb)->append_cnt; + rx_ring->rx_stats.rsc_flush++; + + ixgbe_set_rsc_gso_size(rx_ring, skb); + + /* gso_size is computed using append_cnt so always clear it last */ + IXGBE_CB(skb)->append_cnt = 0; } /** - * ixgbe_transform_rsc_queue - change rsc queue into a full packet - * @skb: pointer to the last skb in the rsc queue + * ixgbe_process_skb_fields - Populate skb header fields from Rx descriptor + * @rx_ring: rx descriptor ring packet is being transacted on + * @rx_desc: pointer to the EOP Rx descriptor + * @skb: pointer to current skb being populated * - * This function 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. + * This function checks the ring, descriptor, and packet information in + * order to populate the hash, checksum, VLAN, timestamp, protocol, and + * other fields within the skb. **/ -static inline struct sk_buff *ixgbe_transform_rsc_queue(struct sk_buff *skb) +static void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) { - unsigned int frag_list_size = 0; - unsigned int skb_cnt = 1; + struct net_device *dev = rx_ring->netdev; + + ixgbe_update_rsc_stats(rx_ring, skb); + + ixgbe_rx_hash(rx_ring, rx_desc, skb); + + ixgbe_rx_checksum(rx_ring, rx_desc, skb); - while (skb->prev) { - struct sk_buff *prev = skb->prev; - frag_list_size += skb->len; - skb->prev = NULL; - skb = prev; - skb_cnt++; + if (unlikely(ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_STAT_TS))) + ixgbe_ptp_rx_hwtstamp(rx_ring->q_vector->adapter, skb); + + if ((dev->features & NETIF_F_HW_VLAN_CTAG_RX) && + ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_VP)) { + u16 vid = le16_to_cpu(rx_desc->wb.upper.vlan); + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vid); } - 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; + skb_record_rx_queue(skb, rx_ring->queue_index); - return skb; + skb->protocol = eth_type_trans(skb, dev); } -static inline bool ixgbe_get_rsc_state(union ixgbe_adv_rx_desc *rx_desc) +static void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector, + struct sk_buff *skb) { - return !!(le32_to_cpu(rx_desc->wb.lower.lo_dword.data) & - IXGBE_RXDADV_RSCCNT_MASK); + struct ixgbe_adapter *adapter = q_vector->adapter; + + if (ixgbe_qv_busy_polling(q_vector)) + netif_receive_skb(skb); + else if (!(adapter->flags & IXGBE_FLAG_IN_NETPOLL)) + napi_gro_receive(&q_vector->napi, skb); + else + netif_rx(skb); } -static bool ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, - struct ixgbe_ring *rx_ring, - int budget) +/** + * ixgbe_is_non_eop - process handling of non-EOP buffers + * @rx_ring: Rx ring being processed + * @rx_desc: Rx descriptor for current buffer + * @skb: Current socket buffer containing buffer in progress + * + * This function updates next to clean. If the buffer is an EOP buffer + * this function exits returning false, otherwise it will place the + * sk_buff in the next buffer to be chained and return true indicating + * that this is in fact a non-EOP buffer. + **/ +static bool ixgbe_is_non_eop(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) { - 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); - - /* linear means we are building an skb from multiple pages */ - if (!skb_is_nonlinear(skb)) { - 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; + u32 ntc = rx_ring->next_to_clean + 1; - 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); - } + /* fetch, update, and store next to clean */ + ntc = (ntc < rx_ring->count) ? ntc : 0; + rx_ring->next_to_clean = ntc; - skb_put(skb, hlen); - } else { - /* assume packet split since header is unmapped */ - upper_len = le16_to_cpu(rx_desc->wb.upper.length); - } + prefetch(IXGBE_RX_DESC(rx_ring, ntc)); - 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; + /* update RSC append count if present */ + if (ring_is_rsc_enabled(rx_ring)) { + __le32 rsc_enabled = rx_desc->wb.lower.lo_dword.data & + cpu_to_le32(IXGBE_RXDADV_RSCCNT_MASK); + + if (unlikely(rsc_enabled)) { + u32 rsc_cnt = le32_to_cpu(rsc_enabled); - skb->len += upper_len; - skb->data_len += upper_len; - skb->truesize += PAGE_SIZE / 2; + rsc_cnt >>= IXGBE_RXDADV_RSCCNT_SHIFT; + IXGBE_CB(skb)->append_cnt += rsc_cnt - 1; + + /* update ntc based on RSC value */ + ntc = le32_to_cpu(rx_desc->wb.upper.status_error); + ntc &= IXGBE_RXDADV_NEXTP_MASK; + ntc >>= IXGBE_RXDADV_NEXTP_SHIFT; } + } - i++; - if (i == rx_ring->count) - i = 0; + /* if we are the last buffer then there is nothing else to do */ + if (likely(ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))) + return false; - next_rxd = IXGBE_RX_DESC_ADV(rx_ring, i); - prefetch(next_rxd); - cleaned_count++; + /* place skb in next buffer to be received */ + rx_ring->rx_buffer_info[ntc].skb = skb; + rx_ring->rx_stats.non_eop_descs++; - 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]; - } + return true; +} - 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; - } +/** + * ixgbe_pull_tail - ixgbe specific version of skb_pull_tail + * @rx_ring: rx descriptor ring packet is being transacted on + * @skb: pointer to current skb being adjusted + * + * This function is an ixgbe specific version of __pskb_pull_tail. The + * main difference between this version and the original function is that + * this function can make several assumptions about the state of things + * that allow for significant optimizations versus the standard function. + * As a result we can do things like drop a frag and maintain an accurate + * truesize for the skb. + */ +static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring, + struct sk_buff *skb) +{ + struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; + unsigned char *va; + unsigned int pull_len; - 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; - } - } + /* + * it is valid to use page_address instead of kmap since we are + * working with pages allocated out of the lomem pool per + * alloc_page(GFP_ATOMIC) + */ + va = skb_frag_address(frag); - 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++; - } + /* + * we need the header to contain the greater of either ETH_HLEN or + * 60 bytes if the skb->len is less than 60 for skb_pad. + */ + pull_len = ixgbe_get_headlen(va, IXGBE_RX_HDR_SIZE); - /* 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; - } + /* align pull length to size of long to optimize memcpy performance */ + skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long))); - ixgbe_rx_checksum(adapter, rx_desc, skb, staterr); - if (adapter->netdev->features & NETIF_F_RXHASH) - ixgbe_rx_hash(rx_desc, skb); + /* update all of the pointers */ + skb_frag_size_sub(frag, pull_len); + frag->page_offset += pull_len; + skb->data_len -= pull_len; + skb->tail += pull_len; +} - /* probably a little skewed due to removing CRC */ - total_rx_bytes += skb->len; - total_rx_packets++; +/** + * ixgbe_dma_sync_frag - perform DMA sync for first frag of SKB + * @rx_ring: rx descriptor ring packet is being transacted on + * @skb: pointer to current skb being updated + * + * This function provides a basic DMA sync up for the first fragment of an + * skb. The reason for doing this is that the first fragment cannot be + * unmapped until we have reached the end of packet descriptor for a buffer + * chain. + */ +static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring, + struct sk_buff *skb) +{ + /* if the page was released unmap it, else just sync our portion */ + if (unlikely(IXGBE_CB(skb)->page_released)) { + dma_unmap_page(rx_ring->dev, IXGBE_CB(skb)->dma, + ixgbe_rx_pg_size(rx_ring), DMA_FROM_DEVICE); + IXGBE_CB(skb)->page_released = false; + } else { + struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; + + dma_sync_single_range_for_cpu(rx_ring->dev, + IXGBE_CB(skb)->dma, + frag->page_offset, + ixgbe_rx_bufsz(rx_ring), + DMA_FROM_DEVICE); + } + IXGBE_CB(skb)->dma = 0; +} + +/** + * ixgbe_cleanup_headers - Correct corrupted or empty headers + * @rx_ring: rx descriptor ring packet is being transacted on + * @rx_desc: pointer to the EOP Rx descriptor + * @skb: pointer to current skb being fixed + * + * Check for corrupted packet headers caused by senders on the local L2 + * embedded NIC switch not setting up their Tx Descriptors right. These + * should be very rare. + * + * Also address the case where we are pulling data in on pages only + * and as such no data is present in the skb header. + * + * In addition if skb is not at least 60 bytes we need to pad it so that + * it is large enough to qualify as a valid Ethernet frame. + * + * Returns true if an error was encountered and skb was freed. + **/ +static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + struct net_device *netdev = rx_ring->netdev; + + /* verify that the packet does not have any known errors */ + if (unlikely(ixgbe_test_staterr(rx_desc, + IXGBE_RXDADV_ERR_FRAME_ERR_MASK) && + !(netdev->features & NETIF_F_RXALL))) { + dev_kfree_skb_any(skb); + return true; + } + + /* place header in linear portion of buffer */ + if (skb_is_nonlinear(skb)) + ixgbe_pull_tail(rx_ring, skb); - 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) { - dev_kfree_skb_any(skb); - goto next_desc; - } + /* do not attempt to pad FCoE Frames as this will disrupt DDP */ + if (ixgbe_rx_is_fcoe(rx_ring, rx_desc)) + return false; + +#endif + /* if skb_pad returns an error the skb was freed */ + if (unlikely(skb->len < 60)) { + int pad_len = 60 - skb->len; + + if (skb_pad(skb, pad_len)) + return true; + __skb_put(skb, pad_len); + } + + return false; +} + +/** + * ixgbe_reuse_rx_page - page flip buffer and store it back on the ring + * @rx_ring: rx descriptor ring to store buffers on + * @old_buff: donor buffer to have page reused + * + * Synchronizes page for reuse by the adapter + **/ +static void ixgbe_reuse_rx_page(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *old_buff) +{ + struct ixgbe_rx_buffer *new_buff; + u16 nta = rx_ring->next_to_alloc; + + new_buff = &rx_ring->rx_buffer_info[nta]; + + /* update, and store next to alloc */ + nta++; + rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; + + /* transfer page from old buffer to new buffer */ + new_buff->page = old_buff->page; + new_buff->dma = old_buff->dma; + new_buff->page_offset = old_buff->page_offset; + + /* sync the buffer for use by the device */ + dma_sync_single_range_for_device(rx_ring->dev, new_buff->dma, + new_buff->page_offset, + ixgbe_rx_bufsz(rx_ring), + DMA_FROM_DEVICE); +} + +/** + * ixgbe_add_rx_frag - Add contents of Rx buffer to sk_buff + * @rx_ring: rx descriptor ring to transact packets on + * @rx_buffer: buffer containing page to add + * @rx_desc: descriptor containing length of buffer written by hardware + * @skb: sk_buff to place the data into + * + * This function will add the data contained in rx_buffer->page to the skb. + * This is done either through a direct copy if the data in the buffer is + * less than the skb header size, otherwise it will just attach the page as + * a frag to the skb. + * + * The function will then update the page offset if necessary and return + * true if the buffer can be reused by the adapter. + **/ +static bool ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring, + struct ixgbe_rx_buffer *rx_buffer, + union ixgbe_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + struct page *page = rx_buffer->page; + unsigned int size = le16_to_cpu(rx_desc->wb.upper.length); +#if (PAGE_SIZE < 8192) + unsigned int truesize = ixgbe_rx_bufsz(rx_ring); +#else + unsigned int truesize = ALIGN(size, L1_CACHE_BYTES); + unsigned int last_offset = ixgbe_rx_pg_size(rx_ring) - + ixgbe_rx_bufsz(rx_ring); +#endif + + if ((size <= IXGBE_RX_HDR_SIZE) && !skb_is_nonlinear(skb)) { + unsigned char *va = page_address(page) + rx_buffer->page_offset; + + memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); + + /* we can reuse buffer as-is, just make sure it is local */ + if (likely(page_to_nid(page) == numa_node_id())) + return true; + + /* this page cannot be reused so discard it */ + put_page(page); + return false; + } + + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, + rx_buffer->page_offset, size, truesize); + + /* avoid re-using remote pages */ + if (unlikely(page_to_nid(page) != numa_node_id())) + return false; + +#if (PAGE_SIZE < 8192) + /* if we are only owner of page we can reuse it */ + if (unlikely(page_count(page) != 1)) + return false; + + /* flip page offset to other buffer */ + rx_buffer->page_offset ^= truesize; + + /* + * since we are the only owner of the page and we need to + * increment it, just set the value to 2 in order to avoid + * an unecessary locked operation + */ + atomic_set(&page->_count, 2); +#else + /* move offset up to the next cache line */ + rx_buffer->page_offset += truesize; + + if (rx_buffer->page_offset > last_offset) + return false; + + /* bump ref count on page before it is given to the stack */ + get_page(page); +#endif + + return true; +} + +static struct sk_buff *ixgbe_fetch_rx_buffer(struct ixgbe_ring *rx_ring, + union ixgbe_adv_rx_desc *rx_desc) +{ + struct ixgbe_rx_buffer *rx_buffer; + struct sk_buff *skb; + struct page *page; + + rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + page = rx_buffer->page; + prefetchw(page); + + skb = rx_buffer->skb; + + if (likely(!skb)) { + void *page_addr = page_address(page) + + rx_buffer->page_offset; + + /* prefetch first cache line of first page */ + prefetch(page_addr); +#if L1_CACHE_BYTES < 128 + prefetch(page_addr + L1_CACHE_BYTES); +#endif + + /* allocate a skb to store the frags */ + skb = netdev_alloc_skb_ip_align(rx_ring->netdev, + IXGBE_RX_HDR_SIZE); + if (unlikely(!skb)) { + rx_ring->rx_stats.alloc_rx_buff_failed++; + return NULL; } -#endif /* IXGBE_FCOE */ - ixgbe_receive_skb(q_vector, skb, staterr, rx_ring, rx_desc); - budget--; -next_desc: - rx_desc->wb.upper.status_error = 0; + /* + * we will be copying header into skb->data in + * pskb_may_pull so it is in our interest to prefetch + * it now to avoid a possible cache miss + */ + prefetchw(skb->data); - if (!budget) - break; + /* + * Delay unmapping of the first packet. It carries the + * header information, HW may still access the header + * after the writeback. Only unmap it when EOP is + * reached + */ + if (likely(ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP))) + goto dma_sync; + + IXGBE_CB(skb)->dma = rx_buffer->dma; + } else { + if (ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_EOP)) + ixgbe_dma_sync_frag(rx_ring, skb); + +dma_sync: + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + ixgbe_rx_bufsz(rx_ring), + DMA_FROM_DEVICE); + } + + /* pull page into skb */ + if (ixgbe_add_rx_frag(rx_ring, rx_buffer, rx_desc, skb)) { + /* hand second half of page back to the ring */ + ixgbe_reuse_rx_page(rx_ring, rx_buffer); + } else if (IXGBE_CB(skb)->dma == rx_buffer->dma) { + /* the page has been released from the ring */ + IXGBE_CB(skb)->page_released = true; + } else { + /* we are not reusing the buffer so unmap it */ + dma_unmap_page(rx_ring->dev, rx_buffer->dma, + ixgbe_rx_pg_size(rx_ring), + DMA_FROM_DEVICE); + } + + /* clear contents of buffer_info */ + rx_buffer->skb = NULL; + rx_buffer->dma = 0; + rx_buffer->page = NULL; + + return skb; +} + +/** + * ixgbe_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf + * @q_vector: structure containing interrupt and ring information + * @rx_ring: rx descriptor ring to transact packets on + * @budget: Total limit on number of packets to process + * + * This function provides a "bounce buffer" approach to Rx interrupt + * processing. The advantage to this is that on systems that have + * expensive overhead for IOMMU access this provides a means of avoiding + * it by maintaining the mapping of the page to the syste. + * + * Returns amount of work completed + **/ +static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, + struct ixgbe_ring *rx_ring, + const int budget) +{ + unsigned int total_rx_bytes = 0, total_rx_packets = 0; +#ifdef IXGBE_FCOE + struct ixgbe_adapter *adapter = q_vector->adapter; + int ddp_bytes; + unsigned int mss = 0; +#endif /* IXGBE_FCOE */ + u16 cleaned_count = ixgbe_desc_unused(rx_ring); + + while (likely(total_rx_packets < budget)) { + union ixgbe_adv_rx_desc *rx_desc; + struct sk_buff *skb; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= IXGBE_RX_BUFFER_WRITE) { @@ -1433,31 +2123,72 @@ next_desc: cleaned_count = 0; } - /* use prefetched values */ - rx_desc = next_rxd; - staterr = le32_to_cpu(rx_desc->wb.upper.status_error); - } + rx_desc = IXGBE_RX_DESC(rx_ring, rx_ring->next_to_clean); - rx_ring->next_to_clean = i; - cleaned_count = ixgbe_desc_unused(rx_ring); + if (!ixgbe_test_staterr(rx_desc, IXGBE_RXD_STAT_DD)) + break; - if (cleaned_count) - ixgbe_alloc_rx_buffers(rx_ring, cleaned_count); + /* + * This memory barrier is needed to keep us from reading + * any other fields out of the rx_desc until we know the + * RXD_STAT_DD bit is set + */ + rmb(); + + /* retrieve a buffer from the ring */ + skb = ixgbe_fetch_rx_buffer(rx_ring, rx_desc); + + /* exit if we failed to retrieve a buffer */ + if (!skb) + break; + + cleaned_count++; + + /* place incomplete frames back on ring for completion */ + if (ixgbe_is_non_eop(rx_ring, rx_desc, skb)) + continue; + + /* verify the packet layout is correct */ + if (ixgbe_cleanup_headers(rx_ring, rx_desc, skb)) + continue; + + /* probably a little skewed due to removing CRC */ + total_rx_bytes += skb->len; + + /* populate checksum, timestamp, VLAN, and protocol */ + ixgbe_process_skb_fields(rx_ring, rx_desc, skb); #ifdef IXGBE_FCOE - /* 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); - } + /* if ddp, not passing to ULD unless for FCP_RSP or error */ + if (ixgbe_rx_is_fcoe(rx_ring, rx_desc)) { + ddp_bytes = ixgbe_fcoe_ddp(adapter, rx_desc, skb); + /* include DDPed FCoE data */ + if (ddp_bytes > 0) { + if (!mss) { + mss = rx_ring->netdev->mtu - + sizeof(struct fcoe_hdr) - + sizeof(struct fc_frame_header) - + sizeof(struct fcoe_crc_eof); + if (mss > 512) + mss &= ~511; + } + total_rx_bytes += ddp_bytes; + total_rx_packets += DIV_ROUND_UP(ddp_bytes, + mss); + } + if (!ddp_bytes) { + dev_kfree_skb_any(skb); + continue; + } + } + #endif /* IXGBE_FCOE */ + skb_mark_napi_id(skb, &q_vector->napi); + ixgbe_rx_skb(q_vector, skb); + + /* update budget accounting */ + total_rx_packets++; + } u64_stats_update_begin(&rx_ring->syncp); rx_ring->stats.packets += total_rx_packets; @@ -1466,9 +2197,46 @@ next_desc: q_vector->rx.total_packets += total_rx_packets; q_vector->rx.total_bytes += total_rx_bytes; - return !!budget; + if (cleaned_count) + ixgbe_alloc_rx_buffers(rx_ring, cleaned_count); + + return total_rx_packets; } +#ifdef CONFIG_NET_RX_BUSY_POLL +/* must be called with local_bh_disable()d */ +static int ixgbe_low_latency_recv(struct napi_struct *napi) +{ + struct ixgbe_q_vector *q_vector = + container_of(napi, struct ixgbe_q_vector, napi); + struct ixgbe_adapter *adapter = q_vector->adapter; + struct ixgbe_ring *ring; + int found = 0; + + if (test_bit(__IXGBE_DOWN, &adapter->state)) + return LL_FLUSH_FAILED; + + if (!ixgbe_qv_lock_poll(q_vector)) + return LL_FLUSH_BUSY; + + ixgbe_for_each_ring(ring, q_vector->rx) { + found = ixgbe_clean_rx_irq(q_vector, ring, 4); +#ifdef BP_EXTENDED_STATS + if (found) + ring->stats.cleaned += found; + else + ring->stats.misses++; +#endif + if (found) + break; + } + + ixgbe_qv_unlock_poll(q_vector); + + return found; +} +#endif /* CONFIG_NET_RX_BUSY_POLL */ + /** * ixgbe_configure_msix - Configure MSI-X hardware * @adapter: board private structure @@ -1479,11 +2247,9 @@ next_desc: static void ixgbe_configure_msix(struct ixgbe_adapter *adapter) { struct ixgbe_q_vector *q_vector; - int q_vectors, v_idx; + int v_idx; u32 mask; - q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - /* Populate MSIX to EITR Select */ if (adapter->num_vfs > 32) { u32 eitrsel = (1 << (adapter->num_vfs - 32)) - 1; @@ -1494,30 +2260,16 @@ static void ixgbe_configure_msix(struct ixgbe_adapter *adapter) * Populate the IVAR table and set the ITR values to the * corresponding register. */ - for (v_idx = 0; v_idx < q_vectors; v_idx++) { + for (v_idx = 0; v_idx < adapter->num_q_vectors; v_idx++) { struct ixgbe_ring *ring; q_vector = adapter->q_vector[v_idx]; - for (ring = q_vector->rx.ring; ring != NULL; ring = ring->next) + ixgbe_for_each_ring(ring, q_vector->rx) ixgbe_set_ivar(adapter, 0, ring->reg_idx, v_idx); - for (ring = q_vector->tx.ring; ring != NULL; ring = ring->next) + ixgbe_for_each_ring(ring, q_vector->tx) ixgbe_set_ivar(adapter, 1, ring->reg_idx, v_idx); - if (q_vector->tx.ring && !q_vector->rx.ring) { - /* tx only vector */ - if (adapter->tx_itr_setting == 1) - q_vector->itr = IXGBE_10K_ITR; - else - q_vector->itr = adapter->tx_itr_setting; - } else { - /* rx or rx/tx vector */ - if (adapter->rx_itr_setting == 1) - q_vector->itr = IXGBE_20K_ITR; - else - q_vector->itr = adapter->rx_itr_setting; - } - ixgbe_write_eitr(q_vector); } @@ -1569,38 +2321,40 @@ enum latency_range { 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; + u64 bytes_perint; 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) + * 0-10MB/s lowest (100000 ints/s) + * 10-20MB/s low (20000 ints/s) + * 20-1249MB/s bulk (8000 ints/s) */ /* what was last interrupt timeslice? */ timepassed_us = q_vector->itr >> 2; + if (timepassed_us == 0) + return; + bytes_perint = bytes / timepassed_us; /* bytes/usec */ switch (itr_setting) { case lowest_latency: - if (bytes_perint > adapter->eitr_low) + if (bytes_perint > 10) itr_setting = low_latency; break; case low_latency: - if (bytes_perint > adapter->eitr_high) + if (bytes_perint > 20) itr_setting = bulk_latency; - else if (bytes_perint <= adapter->eitr_low) + else if (bytes_perint <= 10) itr_setting = lowest_latency; break; case bulk_latency: - if (bytes_perint <= adapter->eitr_high) + if (bytes_perint <= 20) itr_setting = low_latency; break; } @@ -1626,7 +2380,7 @@ void ixgbe_write_eitr(struct ixgbe_q_vector *q_vector) struct ixgbe_adapter *adapter = q_vector->adapter; struct ixgbe_hw *hw = &adapter->hw; int v_idx = q_vector->v_idx; - u32 itr_reg = q_vector->itr; + u32 itr_reg = q_vector->itr & IXGBE_MAX_EITR; switch (adapter->hw.mac.type) { case ixgbe_mac_82598EB: @@ -1678,14 +2432,14 @@ static void ixgbe_set_itr(struct ixgbe_q_vector *q_vector) ((9 * new_itr) + q_vector->itr); /* save the algorithm value here */ - q_vector->itr = new_itr & IXGBE_MAX_EITR; + q_vector->itr = new_itr; ixgbe_write_eitr(q_vector); } } /** - * ixgbe_check_overtemp_subtask - check for over tempurature + * ixgbe_check_overtemp_subtask - check for over temperature * @adapter: pointer to adapter **/ static void ixgbe_check_overtemp_subtask(struct ixgbe_adapter *adapter) @@ -1716,10 +2470,10 @@ static void ixgbe_check_overtemp_subtask(struct ixgbe_adapter *adapter) return; if (!(eicr & IXGBE_EICR_LSC) && hw->mac.ops.check_link) { - u32 autoneg; + u32 speed; bool link_up = false; - hw->mac.ops.check_link(hw, &autoneg, &link_up, false); + hw->mac.ops.check_link(hw, &speed, &link_up, false); if (link_up) return; @@ -1914,6 +2668,10 @@ static inline void ixgbe_irq_enable(struct ixgbe_adapter *adapter, bool queues, default: break; } + + if (adapter->hw.mac.type == ixgbe_mac_X540) + mask |= IXGBE_EIMS_TIMESYNC; + if ((adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) && !(adapter->flags2 & IXGBE_FLAG2_FDIR_REQUIRES_REINIT)) mask |= IXGBE_EIMS_FLOW_DIR; @@ -1938,6 +2696,16 @@ static irqreturn_t ixgbe_msix_other(int irq, void *data) * with the write to EICR. */ eicr = IXGBE_READ_REG(hw, IXGBE_EICS); + + /* The lower 16bits of the EICR register are for the queue interrupts + * which should be masked here in order to not accidently clear them if + * the bits are high when ixgbe_msix_other is called. There is a race + * condition otherwise which results in possible performance loss + * especially if the ixgbe_msix_other interrupt is triggering + * consistently (as it would when PPS is turned on for the X540 device) + */ + eicr &= 0xFFFF0000; + IXGBE_WRITE_REG(hw, IXGBE_EICR, eicr); if (eicr & IXGBE_EICR_LSC) @@ -1949,9 +2717,12 @@ static irqreturn_t ixgbe_msix_other(int irq, void *data) switch (hw->mac.type) { case ixgbe_mac_82599EB: case ixgbe_mac_X540: - if (eicr & IXGBE_EICR_ECC) - e_info(link, "Received unrecoverable ECC Err, please " - "reboot\n"); + if (eicr & IXGBE_EICR_ECC) { + e_info(link, "Received ECC Err, initiating reset\n"); + adapter->flags2 |= IXGBE_FLAG2_RESET_REQUESTED; + ixgbe_service_event_schedule(adapter); + IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_ECC); + } /* Handle Flow Director Full threshold interrupt */ if (eicr & IXGBE_EICR_FLOW_DIR) { int reinit_count = 0; @@ -1978,6 +2749,9 @@ static irqreturn_t ixgbe_msix_other(int irq, void *data) ixgbe_check_fan_failure(adapter, eicr); + if (unlikely(eicr & IXGBE_EICR_TIMESYNC)) + ixgbe_ptp_check_pps_event(adapter, eicr); + /* re-enable the original interrupt state, no lsc, no queues */ if (!test_bit(__IXGBE_DOWN, &adapter->state)) ixgbe_irq_enable(adapter, false, false); @@ -1997,76 +2771,57 @@ static irqreturn_t ixgbe_msix_clean_rings(int irq, void *data) return IRQ_HANDLED; } -static inline void map_vector_to_rxq(struct ixgbe_adapter *a, int v_idx, - int r_idx) +/** + * ixgbe_poll - NAPI Rx polling callback + * @napi: structure for representing this polling device + * @budget: how many packets driver is allowed to clean + * + * This function is used for legacy and MSI, NAPI mode + **/ +int ixgbe_poll(struct napi_struct *napi, int budget) { - struct ixgbe_q_vector *q_vector = a->q_vector[v_idx]; - struct ixgbe_ring *rx_ring = a->rx_ring[r_idx]; + struct ixgbe_q_vector *q_vector = + container_of(napi, struct ixgbe_q_vector, napi); + struct ixgbe_adapter *adapter = q_vector->adapter; + struct ixgbe_ring *ring; + int per_ring_budget; + bool clean_complete = true; - rx_ring->q_vector = q_vector; - rx_ring->next = q_vector->rx.ring; - q_vector->rx.ring = rx_ring; - q_vector->rx.count++; -} +#ifdef CONFIG_IXGBE_DCA + if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) + ixgbe_update_dca(q_vector); +#endif -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]; + ixgbe_for_each_ring(ring, q_vector->tx) + clean_complete &= !!ixgbe_clean_tx_irq(q_vector, ring); - tx_ring->q_vector = q_vector; - tx_ring->next = q_vector->tx.ring; - q_vector->tx.ring = tx_ring; - q_vector->tx.count++; - q_vector->tx.work_limit = a->tx_work_limit; -} + if (!ixgbe_qv_lock_napi(q_vector)) + return budget; -/** - * 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 void ixgbe_map_rings_to_vectors(struct ixgbe_adapter *adapter) -{ - int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - int rxr_remaining = adapter->num_rx_queues, rxr_idx = 0; - int txr_remaining = adapter->num_tx_queues, txr_idx = 0; - int v_start = 0; + /* attempt to distribute budget to each queue fairly, but don't allow + * the budget to go below 1 because we'll exit polling */ + if (q_vector->rx.count > 1) + per_ring_budget = max(budget/q_vector->rx.count, 1); + else + per_ring_budget = budget; - /* only one q_vector if MSI-X is disabled. */ - if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) - q_vectors = 1; + ixgbe_for_each_ring(ring, q_vector->rx) + clean_complete &= (ixgbe_clean_rx_irq(q_vector, ring, + per_ring_budget) < per_ring_budget); - /* - * 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 (; v_start < q_vectors && rxr_remaining; v_start++) { - int rqpv = DIV_ROUND_UP(rxr_remaining, q_vectors - v_start); - for (; rqpv; rqpv--, rxr_idx++, rxr_remaining--) - map_vector_to_rxq(adapter, v_start, rxr_idx); - } + ixgbe_qv_unlock_napi(q_vector); + /* If all work not completed, return budget and keep polling */ + if (!clean_complete) + return budget; - /* - * If there are not enough q_vectors for each ring to have it's own - * vector then we must pair up Rx/Tx on a each vector - */ - if ((v_start + txr_remaining) > q_vectors) - v_start = 0; + /* all work done, exit the polling mode */ + 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)); - for (; v_start < q_vectors && txr_remaining; v_start++) { - int tqpv = DIV_ROUND_UP(txr_remaining, q_vectors - v_start); - for (; tqpv; tqpv--, txr_idx++, txr_remaining--) - map_vector_to_txq(adapter, v_start, txr_idx); - } + return 0; } /** @@ -2079,11 +2834,10 @@ static void ixgbe_map_rings_to_vectors(struct ixgbe_adapter *adapter) static int ixgbe_request_msix_irqs(struct ixgbe_adapter *adapter) { struct net_device *netdev = adapter->netdev; - int q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; int vector, err; int ri = 0, ti = 0; - for (vector = 0; vector < q_vectors; vector++) { + for (vector = 0; vector < adapter->num_q_vectors; vector++) { struct ixgbe_q_vector *q_vector = adapter->q_vector[vector]; struct msix_entry *entry = &adapter->msix_entries[vector]; @@ -2112,14 +2866,14 @@ static int ixgbe_request_msix_irqs(struct ixgbe_adapter *adapter) if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) { /* assign the mask for this irq */ irq_set_affinity_hint(entry->vector, - q_vector->affinity_mask); + &q_vector->affinity_mask); } } err = request_irq(adapter->msix_entries[vector].vector, ixgbe_msix_other, 0, netdev->name, adapter); if (err) { - e_err(probe, "request_irq for msix_lsc failed: %d\n", err); + e_err(probe, "request_irq for msix_other failed: %d\n", err); goto free_queue_irqs; } @@ -2153,7 +2907,7 @@ static irqreturn_t ixgbe_intr(int irq, void *data) u32 eicr; /* - * Workaround for silicon errata on 82598. Mask the interrupts + * Workaround for silicon errata #26 on 82598. Mask the interrupt * before the read of EICR. */ IXGBE_WRITE_REG(hw, IXGBE_EIMC, IXGBE_IRQ_CLEAR_MASK); @@ -2182,9 +2936,12 @@ static irqreturn_t ixgbe_intr(int irq, void *data) ixgbe_check_sfp_event(adapter, eicr); /* Fall through */ case ixgbe_mac_X540: - if (eicr & IXGBE_EICR_ECC) - e_info(link, "Received unrecoverable ECC err, please " - "reboot\n"); + if (eicr & IXGBE_EICR_ECC) { + e_info(link, "Received ECC Err, initiating reset\n"); + adapter->flags2 |= IXGBE_FLAG2_RESET_REQUESTED; + ixgbe_service_event_schedule(adapter); + IXGBE_WRITE_REG(hw, IXGBE_EICR, IXGBE_EICR_ECC); + } ixgbe_check_overtemp_event(adapter, eicr); break; default: @@ -2192,48 +2949,22 @@ static irqreturn_t ixgbe_intr(int irq, void *data) } ixgbe_check_fan_failure(adapter, eicr); + if (unlikely(eicr & IXGBE_EICR_TIMESYNC)) + ixgbe_ptp_check_pps_event(adapter, eicr); - if (napi_schedule_prep(&(q_vector->napi))) { - /* would disable interrupts here but EIAM disabled it */ - __napi_schedule(&(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 q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - int i; - - /* legacy and MSI only use one vector */ - if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) - q_vectors = 1; - - for (i = 0; i < adapter->num_rx_queues; i++) { - adapter->rx_ring[i]->q_vector = NULL; - adapter->rx_ring[i]->next = NULL; - } - for (i = 0; i < adapter->num_tx_queues; i++) { - adapter->tx_ring[i]->q_vector = NULL; - adapter->tx_ring[i]->next = NULL; - } - - for (i = 0; i < q_vectors; i++) { - struct ixgbe_q_vector *q_vector = adapter->q_vector[i]; - memset(&q_vector->rx, 0, sizeof(struct ixgbe_ring_container)); - memset(&q_vector->tx, 0, sizeof(struct ixgbe_ring_container)); - } -} - /** * ixgbe_request_irq - initialize interrupts * @adapter: board private structure @@ -2246,9 +2977,6 @@ static int ixgbe_request_irq(struct ixgbe_adapter *adapter) struct net_device *netdev = adapter->netdev; int err; - /* map all of the rings to the q_vectors */ - ixgbe_map_rings_to_vectors(adapter); - if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) err = ixgbe_request_msix_irqs(adapter); else if (adapter->flags & IXGBE_FLAG_MSI_ENABLED) @@ -2258,45 +2986,36 @@ static int ixgbe_request_irq(struct ixgbe_adapter *adapter) err = request_irq(adapter->pdev->irq, ixgbe_intr, IRQF_SHARED, netdev->name, adapter); - if (err) { + if (err) e_err(probe, "request_irq failed, Error %d\n", err); - /* place q_vectors and rings back into a known good state */ - ixgbe_reset_q_vectors(adapter); - } - return err; } static void ixgbe_free_irq(struct ixgbe_adapter *adapter) { - if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) { - int i, q_vectors; + int vector; - q_vectors = adapter->num_msix_vectors; - i = q_vectors - 1; - free_irq(adapter->msix_entries[i].vector, adapter); - i--; + if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) { + free_irq(adapter->pdev->irq, adapter); + return; + } - for (; i >= 0; i--) { - /* free only the irqs that were actually requested */ - if (!adapter->q_vector[i]->rx.ring && - !adapter->q_vector[i]->tx.ring) - continue; + for (vector = 0; vector < adapter->num_q_vectors; vector++) { + struct ixgbe_q_vector *q_vector = adapter->q_vector[vector]; + struct msix_entry *entry = &adapter->msix_entries[vector]; - /* clear the affinity_mask in the IRQ descriptor */ - irq_set_affinity_hint(adapter->msix_entries[i].vector, - NULL); + /* free only the irqs that were actually requested */ + if (!q_vector->rx.ring && !q_vector->tx.ring) + continue; - free_irq(adapter->msix_entries[i].vector, - adapter->q_vector[i]); - } - } else { - free_irq(adapter->pdev->irq, adapter); + /* clear the affinity_mask in the IRQ descriptor */ + irq_set_affinity_hint(entry->vector, NULL); + + free_irq(entry->vector, q_vector); } - /* clear q_vector state information */ - ixgbe_reset_q_vectors(adapter); + free_irq(adapter->msix_entries[vector++].vector, adapter); } /** @@ -2320,9 +3039,12 @@ static inline void ixgbe_irq_disable(struct ixgbe_adapter *adapter) } 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); + int vector; + + for (vector = 0; vector < adapter->num_q_vectors; vector++) + synchronize_irq(adapter->msix_entries[vector].vector); + + synchronize_irq(adapter->msix_entries[vector++].vector); } else { synchronize_irq(adapter->pdev->irq); } @@ -2336,12 +3058,6 @@ static void ixgbe_configure_msi_and_legacy(struct ixgbe_adapter *adapter) { struct ixgbe_q_vector *q_vector = adapter->q_vector[0]; - /* rx/tx vector */ - if (adapter->rx_itr_setting == 1) - q_vector->itr = IXGBE_20K_ITR; - else - q_vector->itr = adapter->rx_itr_setting; - ixgbe_write_eitr(q_vector); ixgbe_set_ivar(adapter, 0, 0, 0); @@ -2377,28 +3093,36 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter, 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); + ring->tail = adapter->io_addr + IXGBE_TDT(reg_idx); /* * set WTHRESH to encourage burst writeback, it should not be set - * higher than 1 when ITR is 0 as it could cause false TX hangs + * higher than 1 when: + * - ITR is 0 as it could cause false TX hangs + * - ITR is set to > 100k int/sec and BQL is enabled * * In order to avoid issues WTHRESH + PTHRESH should always be equal * to or less than the number of on chip descriptors, which is * currently 40. */ - if (!adapter->tx_itr_setting || !adapter->rx_itr_setting) +#if IS_ENABLED(CONFIG_BQL) + if (!ring->q_vector || (ring->q_vector->itr < IXGBE_100K_ITR)) +#else + if (!ring->q_vector || (ring->q_vector->itr < 8)) +#endif txdctl |= (1 << 16); /* WTHRESH = 1 */ else txdctl |= (8 << 16); /* WTHRESH = 8 */ - /* PTHRESH=32 is needed to avoid a Tx hang with DFP enabled. */ + /* + * Setting PTHRESH to 32 both improves performance + * and avoids a TX hang with DFP enabled + */ txdctl |= (1 << 8) | /* HTHRESH = 1 */ 32; /* PTHRESH = 32 */ /* reinitialize flowdirector state */ - if ((adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) && - adapter->atr_sample_rate) { + if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) { ring->atr_sample_rate = adapter->atr_sample_rate; ring->atr_count = 0; set_bit(__IXGBE_TX_FDIR_INIT_DONE, &ring->state); @@ -2406,6 +3130,16 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter, ring->atr_sample_rate = 0; } + /* initialize XPS */ + if (!test_and_set_bit(__IXGBE_TX_XPS_INIT_DONE, &ring->state)) { + struct ixgbe_q_vector *q_vector = ring->q_vector; + + if (q_vector) + netif_set_xps_queue(ring->netdev, + &q_vector->affinity_mask, + ring->queue_index); + } + clear_bit(__IXGBE_HANG_CHECK_ARMED, &ring->state); /* enable queue */ @@ -2428,8 +3162,7 @@ void ixgbe_configure_tx_ring(struct ixgbe_adapter *adapter, static void ixgbe_setup_mtqc(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - u32 rttdcs; - u32 reg; + u32 rttdcs, mtqc; u8 tcs = netdev_get_num_tc(adapter->netdev); if (hw->mac.type == ixgbe_mac_82598EB) @@ -2441,28 +3174,32 @@ static void ixgbe_setup_mtqc(struct ixgbe_adapter *adapter) 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; + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { + mtqc = IXGBE_MTQC_VT_ENA; + if (tcs > 4) + mtqc |= IXGBE_MTQC_RT_ENA | IXGBE_MTQC_8TC_8TQ; + else if (tcs > 1) + mtqc |= IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ; + else if (adapter->ring_feature[RING_F_RSS].indices == 4) + mtqc |= IXGBE_MTQC_32VF; + else + mtqc |= IXGBE_MTQC_64VF; + } else { + if (tcs > 4) + mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_8TC_8TQ; + else if (tcs > 1) + mtqc = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_4TC_4TQ; else - reg = IXGBE_MTQC_RT_ENA | IXGBE_MTQC_8TC_8TQ; + mtqc = IXGBE_MTQC_64Q_1PB; + } - IXGBE_WRITE_REG(hw, IXGBE_MTQC, reg); + IXGBE_WRITE_REG(hw, IXGBE_MTQC, mtqc); - /* 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; + /* Enable Security TX Buffer IFG for multiple pb */ + if (tcs) { + u32 sectx = IXGBE_READ_REG(hw, IXGBE_SECTXMINIFG); + sectx |= IXGBE_SECTX_DCB; + IXGBE_WRITE_REG(hw, IXGBE_SECTXMINIFG, sectx); } /* re-enable the arbiter */ @@ -2496,51 +3233,90 @@ static void ixgbe_configure_tx(struct ixgbe_adapter *adapter) ixgbe_configure_tx_ring(adapter, adapter->tx_ring[i]); } +static void ixgbe_enable_rx_drop(struct ixgbe_adapter *adapter, + struct ixgbe_ring *ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + u8 reg_idx = ring->reg_idx; + u32 srrctl = IXGBE_READ_REG(hw, IXGBE_SRRCTL(reg_idx)); + + srrctl |= IXGBE_SRRCTL_DROP_EN; + + IXGBE_WRITE_REG(hw, IXGBE_SRRCTL(reg_idx), srrctl); +} + +static void ixgbe_disable_rx_drop(struct ixgbe_adapter *adapter, + struct ixgbe_ring *ring) +{ + struct ixgbe_hw *hw = &adapter->hw; + u8 reg_idx = ring->reg_idx; + u32 srrctl = IXGBE_READ_REG(hw, IXGBE_SRRCTL(reg_idx)); + + srrctl &= ~IXGBE_SRRCTL_DROP_EN; + + IXGBE_WRITE_REG(hw, IXGBE_SRRCTL(reg_idx), srrctl); +} + +#ifdef CONFIG_IXGBE_DCB +void ixgbe_set_rx_drop_en(struct ixgbe_adapter *adapter) +#else +static void ixgbe_set_rx_drop_en(struct ixgbe_adapter *adapter) +#endif +{ + int i; + bool pfc_en = adapter->dcb_cfg.pfc_mode_enable; + + if (adapter->ixgbe_ieee_pfc) + pfc_en |= !!(adapter->ixgbe_ieee_pfc->pfc_en); + + /* + * We should set the drop enable bit if: + * SR-IOV is enabled + * or + * Number of Rx queues > 1 and flow control is disabled + * + * This allows us to avoid head of line blocking for security + * and performance reasons. + */ + if (adapter->num_vfs || (adapter->num_rx_queues > 1 && + !(adapter->hw.fc.current_mode & ixgbe_fc_tx_pause) && !pfc_en)) { + for (i = 0; i < adapter->num_rx_queues; i++) + ixgbe_enable_rx_drop(adapter, adapter->rx_ring[i]); + } else { + for (i = 0; i < adapter->num_rx_queues; i++) + ixgbe_disable_rx_drop(adapter, adapter->rx_ring[i]); + } +} + #define IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT 2 static void ixgbe_configure_srrctl(struct ixgbe_adapter *adapter, struct ixgbe_ring *rx_ring) { + struct ixgbe_hw *hw = &adapter->hw; u32 srrctl; u8 reg_idx = rx_ring->reg_idx; - 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; - } + if (hw->mac.type == ixgbe_mac_82598EB) { + u16 mask = adapter->ring_feature[RING_F_RSS].mask; - srrctl = IXGBE_READ_REG(&adapter->hw, IXGBE_SRRCTL(reg_idx)); + /* + * if VMDq is not active we must program one srrctl register + * per RSS queue since we have enabled RDRXCTL.MVMEN + */ + reg_idx &= mask; + } - srrctl &= ~IXGBE_SRRCTL_BSIZEHDR_MASK; - srrctl &= ~IXGBE_SRRCTL_BSIZEPKT_MASK; - if (adapter->num_vfs) - srrctl |= IXGBE_SRRCTL_DROP_EN; + /* configure header buffer length, needed for RSC */ + srrctl = IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT; - srrctl |= (IXGBE_RX_HDR_SIZE << IXGBE_SRRCTL_BSIZEHDRSIZE_SHIFT) & - IXGBE_SRRCTL_BSIZEHDR_MASK; + /* configure the packet buffer length */ + srrctl |= ixgbe_rx_bufsz(rx_ring) >> IXGBE_SRRCTL_BSIZEPKT_SHIFT; - 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; - } + /* configure descriptor type */ + srrctl |= IXGBE_SRRCTL_DESCTYPE_ADV_ONEBUF; - IXGBE_WRITE_REG(&adapter->hw, IXGBE_SRRCTL(reg_idx), srrctl); + IXGBE_WRITE_REG(hw, IXGBE_SRRCTL(reg_idx), srrctl); } static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter) @@ -2552,11 +3328,15 @@ static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter) 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; + u16 rss_i = adapter->ring_feature[RING_F_RSS].indices; - if (tcs) - maxq = min(maxq, adapter->num_tx_queues / tcs); + /* + * Program table for at least 2 queues w/ SR-IOV so that VFs can + * make full use of any rings they may have. We will use the + * PSRTYPE register to control how many rings we use within the PF. + */ + if ((adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) && (rss_i < 2)) + rss_i = 2; /* Fill out hash function seeds */ for (i = 0; i < 10; i++) @@ -2564,7 +3344,7 @@ static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter) /* Fill out redirection table */ for (i = 0, j = 0; i < 128; i++, j++) { - if (j == maxq) + if (j == rss_i) j = 0; /* reta = 4-byte sliding window of * 0x00..(indices-1)(indices-1)00..etc. */ @@ -2578,35 +3358,41 @@ static void ixgbe_setup_mrqc(struct ixgbe_adapter *adapter) 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; + if (adapter->hw.mac.type == ixgbe_mac_82598EB) { + if (adapter->ring_feature[RING_F_RSS].mask) + 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; + u8 tcs = netdev_get_num_tc(adapter->netdev); + + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { + if (tcs > 4) + mrqc = IXGBE_MRQC_VMDQRT8TCEN; /* 8 TCs */ + else if (tcs > 1) + mrqc = IXGBE_MRQC_VMDQRT4TCEN; /* 4 TCs */ + else if (adapter->ring_feature[RING_F_RSS].indices == 4) + mrqc = IXGBE_MRQC_VMDQRSS32EN; else + mrqc = IXGBE_MRQC_VMDQRSS64EN; + } else { + if (tcs > 4) mrqc = IXGBE_MRQC_RTRSS8TCEN; - break; - case (IXGBE_FLAG_SRIOV_ENABLED): - mrqc = IXGBE_MRQC_VMDQEN; - break; - default: - break; + else if (tcs > 1) + mrqc = IXGBE_MRQC_RTRSS4TCEN; + else + mrqc = IXGBE_MRQC_RSSEN; } } /* Perform hash on these packet types */ - mrqc |= IXGBE_MRQC_RSS_FIELD_IPV4 - | IXGBE_MRQC_RSS_FIELD_IPV4_TCP - | IXGBE_MRQC_RSS_FIELD_IPV6 - | IXGBE_MRQC_RSS_FIELD_IPV6_TCP; + mrqc |= IXGBE_MRQC_RSS_FIELD_IPV4 | + IXGBE_MRQC_RSS_FIELD_IPV4_TCP | + IXGBE_MRQC_RSS_FIELD_IPV6 | + IXGBE_MRQC_RSS_FIELD_IPV6_TCP; + + if (adapter->flags2 & IXGBE_FLAG2_RSS_FIELD_IPV4_UDP) + mrqc |= IXGBE_MRQC_RSS_FIELD_IPV4_UDP; + if (adapter->flags2 & IXGBE_FLAG2_RSS_FIELD_IPV6_UDP) + mrqc |= IXGBE_MRQC_RSS_FIELD_IPV6_UDP; IXGBE_WRITE_REG(hw, IXGBE_MRQC, mrqc); } @@ -2621,13 +3407,11 @@ static void ixgbe_configure_rscctl(struct ixgbe_adapter *adapter, { 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; /* @@ -2635,54 +3419,10 @@ static void ixgbe_configure_rscctl(struct ixgbe_adapter *adapter, * total size of max desc * buf_len is not greater * than 65536 */ - if (ring_is_ps_enabled(ring)) { -#if (PAGE_SIZE < 8192) - rscctrl |= IXGBE_RSCCTL_MAXDESC_16; -#elif (PAGE_SIZE < 16384) - rscctrl |= IXGBE_RSCCTL_MAXDESC_8; -#elif (PAGE_SIZE < 32768) - rscctrl |= IXGBE_RSCCTL_MAXDESC_4; -#else - rscctrl |= IXGBE_RSCCTL_MAXDESC_1; -#endif - } else { - if (rx_buf_len <= IXGBE_RXBUFFER_4K) - rscctrl |= IXGBE_RSCCTL_MAXDESC_16; - else if (rx_buf_len <= IXGBE_RXBUFFER_8K) - rscctrl |= IXGBE_RSCCTL_MAXDESC_8; - else - rscctrl |= IXGBE_RSCCTL_MAXDESC_4; - } + rscctrl |= IXGBE_RSCCTL_MAXDESC_16; 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) @@ -2692,6 +3432,8 @@ static void ixgbe_rx_desc_queue_enable(struct ixgbe_adapter *adapter, u32 rxdctl; u8 reg_idx = ring->reg_idx; + if (ixgbe_removed(hw->hw_addr)) + return; /* RXDCTL.EN will return 0 on 82598 if link is down, so skip it */ if (hw->mac.type == ixgbe_mac_82598EB && !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP)) @@ -2716,6 +3458,8 @@ void ixgbe_disable_rx_queue(struct ixgbe_adapter *adapter, u32 rxdctl; u8 reg_idx = ring->reg_idx; + if (ixgbe_removed(hw->hw_addr)) + return; rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx)); rxdctl &= ~IXGBE_RXDCTL_ENABLE; @@ -2756,19 +3500,11 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, 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); + ring->tail = adapter->io_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: @@ -2792,7 +3528,8 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, static void ixgbe_setup_psrtype(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - int p; + int rss_i = adapter->ring_feature[RING_F_RSS].indices; + u16 pool; /* PSRTYPE must be initialized in non 82598 adapters */ u32 psrtype = IXGBE_PSRTYPE_TCPHDR | @@ -2804,58 +3541,67 @@ static void ixgbe_setup_psrtype(struct ixgbe_adapter *adapter) if (hw->mac.type == ixgbe_mac_82598EB) return; - if (adapter->flags & IXGBE_FLAG_RSS_ENABLED) - psrtype |= (adapter->num_rx_queues_per_pool << 29); + if (rss_i > 3) + psrtype |= 2 << 29; + else if (rss_i > 1) + psrtype |= 1 << 29; - for (p = 0; p < adapter->num_rx_pools; p++) - IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(adapter->num_vfs + p), - psrtype); + for_each_set_bit(pool, &adapter->fwd_bitmask, 32) + IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(VMDQ_P(pool)), psrtype); } static void ixgbe_configure_virtualization(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - u32 gcr_ext; - u32 vt_reg_bits; u32 reg_offset, vf_shift; - u32 vmdctl; + u32 gcr_ext, vmdctl; int i; 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); + vmdctl |= IXGBE_VMD_CTL_VMDQ_EN; + vmdctl &= ~IXGBE_VT_CTL_POOL_MASK; + vmdctl |= VMDQ_P(0) << IXGBE_VT_CTL_POOL_SHIFT; + vmdctl |= IXGBE_VT_CTL_REPLEN; + IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, vmdctl); - vf_shift = adapter->num_vfs % 32; - reg_offset = (adapter->num_vfs >= 32) ? 1 : 0; + vf_shift = VMDQ_P(0) % 32; + reg_offset = (VMDQ_P(0) >= 32) ? 1 : 0; /* Enable only the PF's pool for Tx/Rx */ - IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset), (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); + IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset), (~0) << vf_shift); + IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset ^ 1), reg_offset - 1); + IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset), (~0) << vf_shift); + IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset ^ 1), reg_offset - 1); + if (adapter->flags2 & IXGBE_FLAG2_BRIDGE_MODE_VEB) + IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, IXGBE_PFDTXGSWC_VT_LBEN); /* Map PF MAC address in RAR Entry 0 to first pool following VFs */ - hw->mac.ops.set_vmdq(hw, 0, adapter->num_vfs); + hw->mac.ops.set_vmdq(hw, 0, VMDQ_P(0)); /* * 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; + switch (adapter->ring_feature[RING_F_VMDQ].mask) { + case IXGBE_82599_VMDQ_8Q_MASK: + gcr_ext = IXGBE_GCR_EXT_VT_MODE_16; + break; + case IXGBE_82599_VMDQ_4Q_MASK: + gcr_ext = IXGBE_GCR_EXT_VT_MODE_32; + break; + default: + gcr_ext = IXGBE_GCR_EXT_VT_MODE_64; + break; + } + IXGBE_WRITE_REG(hw, IXGBE_GCR_EXT, gcr_ext); - /* 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->num_vfs != 0), + hw->mac.ops.set_mac_anti_spoofing(hw, (adapter->num_vfs != 0), adapter->num_vfs); /* For VFs that have spoof checking turned off */ for (i = 0; i < adapter->num_vfs; i++) { @@ -2869,23 +3615,10 @@ 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; - #ifdef IXGBE_FCOE /* adjust max frame to be able to do baby jumbo for FCoE */ if ((adapter->flags & IXGBE_FLAG_FCOE_ENABLED) && @@ -2893,6 +3626,11 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter) max_frame = IXGBE_FCOE_JUMBO_FRAME_SIZE; #endif /* IXGBE_FCOE */ + + /* adjust max frame to be at least the size of a standard frame */ + if (max_frame < (ETH_FRAME_LEN + ETH_FCS_LEN)) + max_frame = (ETH_FRAME_LEN + ETH_FCS_LEN); + mhadd = IXGBE_READ_REG(hw, IXGBE_MHADD); if (max_frame != (mhadd >> IXGBE_MHADD_MFS_SHIFT)) { mhadd &= ~IXGBE_MHADD_MFS_MASK; @@ -2901,30 +3639,6 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter) IXGBE_WRITE_REG(hw, IXGBE_MHADD, mhadd); } - /* MHADD will allow an extra 4 bytes past for vlan tagged frames */ - max_frame += VLAN_HLEN; - - /* 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; - /* - * Make best use of allocation by using all but 1K of a - * power of 2 allocation that will be used for skb->head. - */ - else if (max_frame <= IXGBE_RXBUFFER_3K) - rx_buf_len = IXGBE_RXBUFFER_3K; - else if (max_frame <= IXGBE_RXBUFFER_7K) - rx_buf_len = IXGBE_RXBUFFER_7K; - else if (max_frame <= IXGBE_RXBUFFER_15K) - rx_buf_len = IXGBE_RXBUFFER_15K; - else - rx_buf_len = IXGBE_MAX_RXBUFFER; - } - hlreg0 = IXGBE_READ_REG(hw, IXGBE_HLREG0); /* set jumbo enable since MHADD.MFS is keeping size locked at max_frame */ hlreg0 |= IXGBE_HLREG0_JUMBOEN; @@ -2936,34 +3650,10 @@ static void ixgbe_set_rx_buffer_len(struct ixgbe_adapter *adapter) */ 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 */ } } @@ -3014,7 +3704,7 @@ static void ixgbe_configure_rx(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; int i; - u32 rxctrl; + u32 rxctrl, rfctl; /* disable receives while setting up the descriptors */ rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL); @@ -3023,11 +3713,16 @@ static void ixgbe_configure_rx(struct ixgbe_adapter *adapter) ixgbe_setup_psrtype(adapter); ixgbe_setup_rdrxctl(adapter); + /* RSC Setup */ + rfctl = IXGBE_READ_REG(hw, IXGBE_RFCTL); + rfctl &= ~IXGBE_RFCTL_RSC_DIS; + if (!(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)) + rfctl |= IXGBE_RFCTL_RSC_DIS; + IXGBE_WRITE_REG(hw, IXGBE_RFCTL, rfctl); + /* 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); @@ -3047,62 +3742,33 @@ static void ixgbe_configure_rx(struct ixgbe_adapter *adapter) hw->mac.ops.enable_rx_dma(hw, rxctrl); } -static int ixgbe_vlan_rx_add_vid(struct net_device *netdev, u16 vid) +static int ixgbe_vlan_rx_add_vid(struct net_device *netdev, + __be16 proto, u16 vid) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; - int pool_ndx = adapter->num_vfs; /* add VID to filter table */ - hw->mac.ops.set_vfta(&adapter->hw, vid, pool_ndx, true); + hw->mac.ops.set_vfta(&adapter->hw, vid, VMDQ_P(0), true); set_bit(vid, adapter->active_vlans); return 0; } -static int ixgbe_vlan_rx_kill_vid(struct net_device *netdev, u16 vid) +static int ixgbe_vlan_rx_kill_vid(struct net_device *netdev, + __be16 proto, u16 vid) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; - int pool_ndx = adapter->num_vfs; /* remove VID from filter table */ - hw->mac.ops.set_vfta(&adapter->hw, vid, pool_ndx, false); + hw->mac.ops.set_vfta(&adapter->hw, vid, VMDQ_P(0), false); clear_bit(vid, adapter->active_vlans); return 0; } /** - * 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 */ @@ -3121,7 +3787,11 @@ static void ixgbe_vlan_strip_disable(struct ixgbe_adapter *adapter) case ixgbe_mac_82599EB: case ixgbe_mac_X540: for (i = 0; i < adapter->num_rx_queues; i++) { - j = adapter->rx_ring[i]->reg_idx; + struct ixgbe_ring *ring = adapter->rx_ring[i]; + + if (ring->l2_accel_priv) + continue; + j = ring->reg_idx; vlnctrl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(j)); vlnctrl &= ~IXGBE_RXDCTL_VME; IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(j), vlnctrl); @@ -3151,7 +3821,11 @@ static void ixgbe_vlan_strip_enable(struct ixgbe_adapter *adapter) case ixgbe_mac_82599EB: case ixgbe_mac_X540: for (i = 0; i < adapter->num_rx_queues; i++) { - j = adapter->rx_ring[i]->reg_idx; + struct ixgbe_ring *ring = adapter->rx_ring[i]; + + if (ring->l2_accel_priv) + continue; + j = ring->reg_idx; vlnctrl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(j)); vlnctrl |= IXGBE_RXDCTL_VME; IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(j), vlnctrl); @@ -3166,12 +3840,164 @@ static void ixgbe_restore_vlan(struct ixgbe_adapter *adapter) { u16 vid; - ixgbe_vlan_rx_add_vid(adapter->netdev, 0); + ixgbe_vlan_rx_add_vid(adapter->netdev, htons(ETH_P_8021Q), 0); for_each_set_bit(vid, adapter->active_vlans, VLAN_N_VID) - ixgbe_vlan_rx_add_vid(adapter->netdev, vid); + ixgbe_vlan_rx_add_vid(adapter->netdev, htons(ETH_P_8021Q), vid); +} + +/** + * ixgbe_write_mc_addr_list - write multicast addresses to MTA + * @netdev: network interface device structure + * + * Writes multicast address list to the MTA hash table. + * Returns: -ENOMEM on failure + * 0 on no addresses written + * X on writing X addresses to MTA + **/ +static int ixgbe_write_mc_addr_list(struct net_device *netdev) +{ + struct ixgbe_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; + + if (!netif_running(netdev)) + return 0; + + if (hw->mac.ops.update_mc_addr_list) + hw->mac.ops.update_mc_addr_list(hw, netdev); + else + return -ENOMEM; + +#ifdef CONFIG_PCI_IOV + ixgbe_restore_vf_multicasts(adapter); +#endif + + return netdev_mc_count(netdev); +} + +#ifdef CONFIG_PCI_IOV +void ixgbe_full_sync_mac_table(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int i; + for (i = 0; i < hw->mac.num_rar_entries; i++) { + if (adapter->mac_table[i].state & IXGBE_MAC_STATE_IN_USE) + hw->mac.ops.set_rar(hw, i, adapter->mac_table[i].addr, + adapter->mac_table[i].queue, + IXGBE_RAH_AV); + else + hw->mac.ops.clear_rar(hw, i); + + adapter->mac_table[i].state &= ~(IXGBE_MAC_STATE_MODIFIED); + } +} +#endif + +static void ixgbe_sync_mac_table(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int i; + for (i = 0; i < hw->mac.num_rar_entries; i++) { + if (adapter->mac_table[i].state & IXGBE_MAC_STATE_MODIFIED) { + if (adapter->mac_table[i].state & + IXGBE_MAC_STATE_IN_USE) + hw->mac.ops.set_rar(hw, i, + adapter->mac_table[i].addr, + adapter->mac_table[i].queue, + IXGBE_RAH_AV); + else + hw->mac.ops.clear_rar(hw, i); + + adapter->mac_table[i].state &= + ~(IXGBE_MAC_STATE_MODIFIED); + } + } +} + +static void ixgbe_flush_sw_mac_table(struct ixgbe_adapter *adapter) +{ + int i; + struct ixgbe_hw *hw = &adapter->hw; + + for (i = 0; i < hw->mac.num_rar_entries; i++) { + adapter->mac_table[i].state |= IXGBE_MAC_STATE_MODIFIED; + adapter->mac_table[i].state &= ~IXGBE_MAC_STATE_IN_USE; + memset(adapter->mac_table[i].addr, 0, ETH_ALEN); + adapter->mac_table[i].queue = 0; + } + ixgbe_sync_mac_table(adapter); +} + +static int ixgbe_available_rars(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int i, count = 0; + + for (i = 0; i < hw->mac.num_rar_entries; i++) { + if (adapter->mac_table[i].state == 0) + count++; + } + return count; +} + +/* this function destroys the first RAR entry */ +static void ixgbe_mac_set_default_filter(struct ixgbe_adapter *adapter, + u8 *addr) +{ + struct ixgbe_hw *hw = &adapter->hw; + + memcpy(&adapter->mac_table[0].addr, addr, ETH_ALEN); + adapter->mac_table[0].queue = VMDQ_P(0); + adapter->mac_table[0].state = (IXGBE_MAC_STATE_DEFAULT | + IXGBE_MAC_STATE_IN_USE); + hw->mac.ops.set_rar(hw, 0, adapter->mac_table[0].addr, + adapter->mac_table[0].queue, + IXGBE_RAH_AV); +} + +int ixgbe_add_mac_filter(struct ixgbe_adapter *adapter, u8 *addr, u16 queue) +{ + struct ixgbe_hw *hw = &adapter->hw; + int i; + + if (is_zero_ether_addr(addr)) + return -EINVAL; + + for (i = 0; i < hw->mac.num_rar_entries; i++) { + if (adapter->mac_table[i].state & IXGBE_MAC_STATE_IN_USE) + continue; + adapter->mac_table[i].state |= (IXGBE_MAC_STATE_MODIFIED | + IXGBE_MAC_STATE_IN_USE); + ether_addr_copy(adapter->mac_table[i].addr, addr); + adapter->mac_table[i].queue = queue; + ixgbe_sync_mac_table(adapter); + return i; + } + return -ENOMEM; } +int ixgbe_del_mac_filter(struct ixgbe_adapter *adapter, u8 *addr, u16 queue) +{ + /* search table for addr, if found, set to 0 and sync */ + int i; + struct ixgbe_hw *hw = &adapter->hw; + + if (is_zero_ether_addr(addr)) + return -EINVAL; + + for (i = 0; i < hw->mac.num_rar_entries; i++) { + if (ether_addr_equal(addr, adapter->mac_table[i].addr) && + adapter->mac_table[i].queue == queue) { + adapter->mac_table[i].state |= IXGBE_MAC_STATE_MODIFIED; + adapter->mac_table[i].state &= ~IXGBE_MAC_STATE_IN_USE; + memset(adapter->mac_table[i].addr, 0, ETH_ALEN); + adapter->mac_table[i].queue = 0; + ixgbe_sync_mac_table(adapter); + return 0; + } + } + return -ENOMEM; +} /** * ixgbe_write_uc_addr_list - write unicast addresses to RAR table * @netdev: network interface device structure @@ -3181,36 +4007,23 @@ static void ixgbe_restore_vlan(struct ixgbe_adapter *adapter) * 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) +static int ixgbe_write_uc_addr_list(struct net_device *netdev, int vfn) { 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) + if (netdev_uc_count(netdev) > ixgbe_available_rars(adapter)) return -ENOMEM; - if (!netdev_uc_empty(netdev) && rar_entries) { + if (!netdev_uc_empty(netdev)) { 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); + ixgbe_del_mac_filter(adapter, ha->addr, vfn); + ixgbe_add_mac_filter(adapter, ha->addr, vfn); 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; } @@ -3228,64 +4041,88 @@ 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; + u32 vlnctrl; int count; /* Check for Promiscuous and All Multicast modes */ - fctrl = IXGBE_READ_REG(hw, IXGBE_FCTRL); + vlnctrl = IXGBE_READ_REG(hw, IXGBE_VLNCTRL); /* set all bits that we expect to always be set */ + fctrl &= ~IXGBE_FCTRL_SBP; /* disable store-bad-packets */ fctrl |= IXGBE_FCTRL_BAM; fctrl |= IXGBE_FCTRL_DPF; /* discard pause frames when FC enabled */ fctrl |= IXGBE_FCTRL_PMCF; /* clear the bits we are changing the status of */ fctrl &= ~(IXGBE_FCTRL_UPE | IXGBE_FCTRL_MPE); - + vlnctrl &= ~(IXGBE_VLNCTRL_VFE | IXGBE_VLNCTRL_CFIEN); 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); + vmolr |= IXGBE_VMOLR_MPE; + /* Only disable hardware filter vlans in promiscuous mode + * if SR-IOV and VMDQ are disabled - otherwise ensure + * that hardware VLAN filters remain enabled. + */ + if (!(adapter->flags & (IXGBE_FLAG_VMDQ_ENABLED | + IXGBE_FLAG_SRIOV_ENABLED))) + vlnctrl |= (IXGBE_VLNCTRL_VFE | IXGBE_VLNCTRL_CFIEN); } 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); + vlnctrl |= IXGBE_VLNCTRL_VFE; 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)) & + /* + * 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, VMDQ_P(0)); + if (count < 0) { + fctrl |= IXGBE_FCTRL_UPE; + vmolr |= IXGBE_VMOLR_ROPE; + } + + /* Write addresses to the MTA, if the attempt fails + * then we should just turn on promiscuous mode so + * that we can at least receive multicast traffic + */ + count = ixgbe_write_mc_addr_list(netdev); + if (count < 0) { + fctrl |= IXGBE_FCTRL_MPE; + vmolr |= IXGBE_VMOLR_MPE; + } else if (count) { + vmolr |= IXGBE_VMOLR_ROMPE; + } + + if (hw->mac.type != ixgbe_mac_82598EB) { + vmolr |= IXGBE_READ_REG(hw, IXGBE_VMOLR(VMDQ_P(0))) & ~(IXGBE_VMOLR_MPE | IXGBE_VMOLR_ROMPE | IXGBE_VMOLR_ROPE); - IXGBE_WRITE_REG(hw, IXGBE_VMOLR(adapter->num_vfs), vmolr); + IXGBE_WRITE_REG(hw, IXGBE_VMOLR(VMDQ_P(0)), vmolr); } + /* This is useful for sniffing bad packets. */ + if (adapter->netdev->features & NETIF_F_RXALL) { + /* UPE and MPE will be handled by normal PROMISC logic + * in e1000e_set_rx_mode */ + fctrl |= (IXGBE_FCTRL_SBP | /* Receive bad packets */ + IXGBE_FCTRL_BAM | /* RX All Bcast Pkts */ + IXGBE_FCTRL_PMCF); /* RX All MAC Ctrl Pkts */ + + fctrl &= ~(IXGBE_FCTRL_DPF); + /* NOTE: VLAN filtering is disabled by setting PROMISC */ + } + + IXGBE_WRITE_REG(hw, IXGBE_VLNCTRL, vlnctrl); IXGBE_WRITE_REG(hw, IXGBE_FCTRL, fctrl); - if (netdev->features & NETIF_F_HW_VLAN_RX) + if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX) ixgbe_vlan_strip_enable(adapter); else ixgbe_vlan_strip_disable(adapter); @@ -3294,37 +4131,28 @@ void ixgbe_set_rx_mode(struct net_device *netdev) 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++) { - q_vector = adapter->q_vector[q_idx]; - napi_enable(&q_vector->napi); + for (q_idx = 0; q_idx < adapter->num_q_vectors; q_idx++) { + ixgbe_qv_init_lock(adapter->q_vector[q_idx]); + napi_enable(&adapter->q_vector[q_idx]->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); + for (q_idx = 0; q_idx < adapter->num_q_vectors; q_idx++) { + napi_disable(&adapter->q_vector[q_idx]->napi); + while (!ixgbe_qv_disable(adapter->q_vector[q_idx])) { + pr_info("QV %d locked\n", q_idx); + usleep_range(1000, 20000); + } } } #ifdef CONFIG_IXGBE_DCB -/* +/** * ixgbe_configure_dcb - Configure DCB hardware * @adapter: ixgbe adapter struct * @@ -3346,12 +4174,6 @@ static void ixgbe_configure_dcb(struct ixgbe_adapter *adapter) 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); - #ifdef IXGBE_FCOE if (adapter->netdev->features & NETIF_F_FCOE_MTU) max_frame = max(max_frame, IXGBE_FCOE_JUMBO_FRAME_SIZE); @@ -3375,19 +4197,16 @@ static void ixgbe_configure_dcb(struct ixgbe_adapter *adapter) /* 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; + u32 msb = 0; + u16 rss_i = adapter->ring_feature[RING_F_RSS].indices - 1; - while (cnt >>= 1) - msb++; - - reg |= msb << IXGBE_RQTC_SHIFT_TC(i); + while (rss_i) { + msb++; + rss_i >>= 1; } - IXGBE_WRITE_REG(hw, IXGBE_RQTC, reg); + + /* write msb to all 8 TCs in one write */ + IXGBE_WRITE_REG(hw, IXGBE_RQTC, msb * 0x11111111); } } #endif @@ -3395,11 +4214,11 @@ static void ixgbe_configure_dcb(struct ixgbe_adapter *adapter) /* Additional bittime to account for IXGBE framing */ #define IXGBE_ETH_FRAMING 20 -/* +/** * ixgbe_hpbthresh - calculate high water mark for flow control * * @adapter: board private structure to calculate for - * @pb - packet buffer to calculate + * @pb: packet buffer to calculate */ static int ixgbe_hpbthresh(struct ixgbe_adapter *adapter, int pb) { @@ -3413,16 +4232,10 @@ static int ixgbe_hpbthresh(struct ixgbe_adapter *adapter, int pb) #ifdef IXGBE_FCOE /* FCoE traffic class uses FCOE jumbo frames */ - if (dev->features & NETIF_F_FCOE_MTU) { - int fcoe_pb = 0; - -#ifdef CONFIG_IXGBE_DCB - fcoe_pb = netdev_get_prio_tc_map(dev, adapter->fcoe.up); - -#endif - if (fcoe_pb == pb && tc < IXGBE_FCOE_JUMBO_FRAME_SIZE) - tc = IXGBE_FCOE_JUMBO_FRAME_SIZE; - } + if ((dev->features & NETIF_F_FCOE_MTU) && + (tc < IXGBE_FCOE_JUMBO_FRAME_SIZE) && + (pb == ixgbe_fcoe_get_tc(adapter))) + tc = IXGBE_FCOE_JUMBO_FRAME_SIZE; #endif /* Calculate delay value for device */ @@ -3459,13 +4272,13 @@ static int ixgbe_hpbthresh(struct ixgbe_adapter *adapter, int pb) return marker; } -/* +/** * ixgbe_lpbthresh - calculate low water mark for for flow control * * @adapter: board private structure to calculate for - * @pb - packet buffer to calculate + * @pb: packet buffer to calculate */ -static int ixgbe_lpbthresh(struct ixgbe_adapter *adapter) +static int ixgbe_lpbthresh(struct ixgbe_adapter *adapter, int pb) { struct ixgbe_hw *hw = &adapter->hw; struct net_device *dev = adapter->netdev; @@ -3475,6 +4288,14 @@ static int ixgbe_lpbthresh(struct ixgbe_adapter *adapter) /* Calculate max LAN frame size */ tc = dev->mtu + ETH_HLEN + ETH_FCS_LEN; +#ifdef IXGBE_FCOE + /* FCoE traffic class uses FCOE jumbo frames */ + if ((dev->features & NETIF_F_FCOE_MTU) && + (tc < IXGBE_FCOE_JUMBO_FRAME_SIZE) && + (pb == netdev_get_prio_tc_map(dev, adapter->fcoe.up))) + tc = IXGBE_FCOE_JUMBO_FRAME_SIZE; +#endif + /* Calculate delay value for device */ switch (hw->mac.type) { case ixgbe_mac_X540: @@ -3501,15 +4322,17 @@ static void ixgbe_pbthresh_setup(struct ixgbe_adapter *adapter) if (!num_tc) num_tc = 1; - hw->fc.low_water = ixgbe_lpbthresh(adapter); - for (i = 0; i < num_tc; i++) { hw->fc.high_water[i] = ixgbe_hpbthresh(adapter, i); + hw->fc.low_water[i] = ixgbe_lpbthresh(adapter, i); /* Low water marks must not be larger than high water marks */ - if (hw->fc.low_water > hw->fc.high_water[i]) - hw->fc.low_water = 0; + if (hw->fc.low_water[i] > hw->fc.high_water[i]) + hw->fc.low_water[i] = 0; } + + for (; i < MAX_TRAFFIC_CLASS; i++) + hw->fc.high_water[i] = 0; } static void ixgbe_configure_pb(struct ixgbe_adapter *adapter) @@ -3531,7 +4354,7 @@ static void ixgbe_configure_pb(struct ixgbe_adapter *adapter) static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - struct hlist_node *node, *node2; + struct hlist_node *node2; struct ixgbe_fdir_filter *filter; spin_lock(&adapter->fdir_perfect_lock); @@ -3539,7 +4362,7 @@ static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter) 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, + hlist_for_each_entry_safe(filter, node2, &adapter->fdir_filter_list, fdir_node) { ixgbe_fdir_write_perfect_filter_82599(hw, &filter->filter, @@ -3552,21 +4375,244 @@ static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter) spin_unlock(&adapter->fdir_perfect_lock); } +static void ixgbe_macvlan_set_rx_mode(struct net_device *dev, unsigned int pool, + struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 vmolr; + + /* No unicast promiscuous support for VMDQ devices. */ + vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(pool)); + vmolr |= (IXGBE_VMOLR_ROMPE | IXGBE_VMOLR_BAM | IXGBE_VMOLR_AUPE); + + /* clear the affected bit */ + vmolr &= ~IXGBE_VMOLR_MPE; + + if (dev->flags & IFF_ALLMULTI) { + vmolr |= IXGBE_VMOLR_MPE; + } else { + vmolr |= IXGBE_VMOLR_ROMPE; + hw->mac.ops.update_mc_addr_list(hw, dev); + } + ixgbe_write_uc_addr_list(adapter->netdev, pool); + IXGBE_WRITE_REG(hw, IXGBE_VMOLR(pool), vmolr); +} + +static void ixgbe_fwd_psrtype(struct ixgbe_fwd_adapter *vadapter) +{ + struct ixgbe_adapter *adapter = vadapter->real_adapter; + int rss_i = adapter->num_rx_queues_per_pool; + struct ixgbe_hw *hw = &adapter->hw; + u16 pool = vadapter->pool; + u32 psrtype = IXGBE_PSRTYPE_TCPHDR | + IXGBE_PSRTYPE_UDPHDR | + IXGBE_PSRTYPE_IPV4HDR | + IXGBE_PSRTYPE_L2HDR | + IXGBE_PSRTYPE_IPV6HDR; + + if (hw->mac.type == ixgbe_mac_82598EB) + return; + + if (rss_i > 3) + psrtype |= 2 << 29; + else if (rss_i > 1) + psrtype |= 1 << 29; + + IXGBE_WRITE_REG(hw, IXGBE_PSRTYPE(VMDQ_P(pool)), psrtype); +} + +/** + * 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; + + rx_buffer = &rx_ring->rx_buffer_info[i]; + if (rx_buffer->skb) { + struct sk_buff *skb = rx_buffer->skb; + if (IXGBE_CB(skb)->page_released) { + dma_unmap_page(dev, + IXGBE_CB(skb)->dma, + ixgbe_rx_bufsz(rx_ring), + DMA_FROM_DEVICE); + IXGBE_CB(skb)->page_released = false; + } + dev_kfree_skb(skb); + } + rx_buffer->skb = NULL; + if (rx_buffer->dma) + dma_unmap_page(dev, rx_buffer->dma, + ixgbe_rx_pg_size(rx_ring), + DMA_FROM_DEVICE); + rx_buffer->dma = 0; + if (rx_buffer->page) + __free_pages(rx_buffer->page, + ixgbe_rx_pg_order(rx_ring)); + rx_buffer->page = NULL; + } + + 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_alloc = 0; + rx_ring->next_to_clean = 0; + rx_ring->next_to_use = 0; +} + +static void ixgbe_disable_fwd_ring(struct ixgbe_fwd_adapter *vadapter, + struct ixgbe_ring *rx_ring) +{ + struct ixgbe_adapter *adapter = vadapter->real_adapter; + int index = rx_ring->queue_index + vadapter->rx_base_queue; + + /* shutdown specific queue receive and wait for dma to settle */ + ixgbe_disable_rx_queue(adapter, rx_ring); + usleep_range(10000, 20000); + ixgbe_irq_disable_queues(adapter, ((u64)1 << index)); + ixgbe_clean_rx_ring(rx_ring); + rx_ring->l2_accel_priv = NULL; +} + +static int ixgbe_fwd_ring_down(struct net_device *vdev, + struct ixgbe_fwd_adapter *accel) +{ + struct ixgbe_adapter *adapter = accel->real_adapter; + unsigned int rxbase = accel->rx_base_queue; + unsigned int txbase = accel->tx_base_queue; + int i; + + netif_tx_stop_all_queues(vdev); + + for (i = 0; i < adapter->num_rx_queues_per_pool; i++) { + ixgbe_disable_fwd_ring(accel, adapter->rx_ring[rxbase + i]); + adapter->rx_ring[rxbase + i]->netdev = adapter->netdev; + } + + for (i = 0; i < adapter->num_rx_queues_per_pool; i++) { + adapter->tx_ring[txbase + i]->l2_accel_priv = NULL; + adapter->tx_ring[txbase + i]->netdev = adapter->netdev; + } + + + return 0; +} + +static int ixgbe_fwd_ring_up(struct net_device *vdev, + struct ixgbe_fwd_adapter *accel) +{ + struct ixgbe_adapter *adapter = accel->real_adapter; + unsigned int rxbase, txbase, queues; + int i, baseq, err = 0; + + if (!test_bit(accel->pool, &adapter->fwd_bitmask)) + return 0; + + baseq = accel->pool * adapter->num_rx_queues_per_pool; + netdev_dbg(vdev, "pool %i:%i queues %i:%i VSI bitmask %lx\n", + accel->pool, adapter->num_rx_pools, + baseq, baseq + adapter->num_rx_queues_per_pool, + adapter->fwd_bitmask); + + accel->netdev = vdev; + accel->rx_base_queue = rxbase = baseq; + accel->tx_base_queue = txbase = baseq; + + for (i = 0; i < adapter->num_rx_queues_per_pool; i++) + ixgbe_disable_fwd_ring(accel, adapter->rx_ring[rxbase + i]); + + for (i = 0; i < adapter->num_rx_queues_per_pool; i++) { + adapter->rx_ring[rxbase + i]->netdev = vdev; + adapter->rx_ring[rxbase + i]->l2_accel_priv = accel; + ixgbe_configure_rx_ring(adapter, adapter->rx_ring[rxbase + i]); + } + + for (i = 0; i < adapter->num_rx_queues_per_pool; i++) { + adapter->tx_ring[txbase + i]->netdev = vdev; + adapter->tx_ring[txbase + i]->l2_accel_priv = accel; + } + + queues = min_t(unsigned int, + adapter->num_rx_queues_per_pool, vdev->num_tx_queues); + err = netif_set_real_num_tx_queues(vdev, queues); + if (err) + goto fwd_queue_err; + + err = netif_set_real_num_rx_queues(vdev, queues); + if (err) + goto fwd_queue_err; + + if (is_valid_ether_addr(vdev->dev_addr)) + ixgbe_add_mac_filter(adapter, vdev->dev_addr, accel->pool); + + ixgbe_fwd_psrtype(accel); + ixgbe_macvlan_set_rx_mode(vdev, accel->pool, adapter); + return err; +fwd_queue_err: + ixgbe_fwd_ring_down(vdev, accel); + return err; +} + +static void ixgbe_configure_dfwd(struct ixgbe_adapter *adapter) +{ + struct net_device *upper; + struct list_head *iter; + int err; + + netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) { + if (netif_is_macvlan(upper)) { + struct macvlan_dev *dfwd = netdev_priv(upper); + struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv; + + if (dfwd->fwd_priv) { + err = ixgbe_fwd_ring_up(upper, vadapter); + if (err) + continue; + } + } + } +} + static void ixgbe_configure(struct ixgbe_adapter *adapter) { + struct ixgbe_hw *hw = &adapter->hw; + ixgbe_configure_pb(adapter); #ifdef CONFIG_IXGBE_DCB ixgbe_configure_dcb(adapter); #endif + /* + * We must restore virtualization before VLANs or else + * the VLVF registers will not be populated + */ + ixgbe_configure_virtualization(adapter); ixgbe_set_rx_mode(adapter->netdev); ixgbe_restore_vlan(adapter); -#ifdef IXGBE_FCOE - if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) - ixgbe_configure_fcoe(adapter); + switch (hw->mac.type) { + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + hw->mac.ops.disable_rx_buff(hw); + break; + default: + break; + } -#endif /* IXGBE_FCOE */ if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) { ixgbe_init_fdir_signature_82599(&adapter->hw, adapter->fdir_pballoc); @@ -3576,10 +4622,23 @@ static void ixgbe_configure(struct ixgbe_adapter *adapter) ixgbe_fdir_filter_restore(adapter); } - ixgbe_configure_virtualization(adapter); + switch (hw->mac.type) { + case ixgbe_mac_82599EB: + case ixgbe_mac_X540: + hw->mac.ops.enable_rx_buff(hw); + break; + default: + break; + } +#ifdef IXGBE_FCOE + /* configure FCoE L2 filters, redirection table, and Rx control */ + ixgbe_configure_fcoe(adapter); + +#endif /* IXGBE_FCOE */ ixgbe_configure_tx(adapter); ixgbe_configure_rx(adapter); + ixgbe_configure_dfwd(adapter); } static inline bool ixgbe_is_sfp(struct ixgbe_hw *hw) @@ -3593,6 +4652,12 @@ static inline bool ixgbe_is_sfp(struct ixgbe_hw *hw) case ixgbe_phy_sfp_passive_unknown: case ixgbe_phy_sfp_active_unknown: case ixgbe_phy_sfp_ftl_active: + case ixgbe_phy_qsfp_passive_unknown: + case ixgbe_phy_qsfp_active_unknown: + case ixgbe_phy_qsfp_intel: + case ixgbe_phy_qsfp_unknown: + /* ixgbe_phy_none is set when no SFP module is present */ + case ixgbe_phy_none: return true; case ixgbe_phy_nl: if (hw->mac.type == ixgbe_mac_82598EB) @@ -3628,25 +4693,25 @@ static void ixgbe_sfp_link_config(struct ixgbe_adapter *adapter) **/ static int ixgbe_non_sfp_link_config(struct ixgbe_hw *hw) { - u32 autoneg; - bool negotiation, link_up = false; + u32 speed; + bool autoneg, 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); + ret = hw->mac.ops.check_link(hw, &speed, &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); + speed = hw->phy.autoneg_advertised; + if ((!speed) && (hw->mac.ops.get_link_capabilities)) + ret = hw->mac.ops.get_link_capabilities(hw, &speed, + &autoneg); if (ret) goto link_cfg_out; if (hw->mac.ops.setup_link) - ret = hw->mac.ops.setup_link(hw, autoneg, negotiation, link_up); + ret = hw->mac.ops.setup_link(hw, speed, link_up); link_cfg_out: return ret; } @@ -3686,7 +4751,18 @@ static void ixgbe_setup_gpie(struct ixgbe_adapter *adapter) if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { gpie &= ~IXGBE_GPIE_VTMODE_MASK; - gpie |= IXGBE_GPIE_VTMODE_64; + + switch (adapter->ring_feature[RING_F_VMDQ].mask) { + case IXGBE_82599_VMDQ_8Q_MASK: + gpie |= IXGBE_GPIE_VTMODE_16; + break; + case IXGBE_82599_VMDQ_4Q_MASK: + gpie |= IXGBE_GPIE_VTMODE_32; + break; + default: + gpie |= IXGBE_GPIE_VTMODE_64; + break; + } } /* Enable Thermal over heat sensor interrupt */ @@ -3729,13 +4805,11 @@ static void ixgbe_up_complete(struct ixgbe_adapter *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)))) + /* enable the optics for 82599 SFP+ fiber */ + if (hw->mac.ops.enable_tx_laser) hw->mac.ops.enable_tx_laser(hw); + smp_mb__before_atomic(); clear_bit(__IXGBE_DOWN, &adapter->state); ixgbe_napi_enable_all(adapter); @@ -3761,9 +4835,6 @@ static void ixgbe_up_complete(struct ixgbe_adapter *adapter) 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; @@ -3808,8 +4879,12 @@ void ixgbe_up(struct ixgbe_adapter *adapter) void ixgbe_reset(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; + struct net_device *netdev = adapter->netdev; int err; + u8 old_addr[ETH_ALEN]; + if (ixgbe_removed(hw->hw_addr)) + return; /* lock SFP init bit to prevent race conditions with the watchdog */ while (test_and_set_bit(__IXGBE_IN_SFP_INIT, &adapter->state)) usleep_range(1000, 2000); @@ -3842,74 +4917,17 @@ void ixgbe_reset(struct ixgbe_adapter *adapter) } clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state); + /* do not flush user set addresses */ + memcpy(old_addr, &adapter->mac_table[0].addr, netdev->addr_len); + ixgbe_flush_sw_mac_table(adapter); + ixgbe_mac_set_default_filter(adapter, old_addr); - /* 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; + /* update SAN MAC vmdq pool selection */ + if (hw->mac.san_mac_rar_index) + hw->mac.ops.set_vmdq_san_mac(hw, VMDQ_P(0)); - /* 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; + if (test_bit(__IXGBE_PTP_RUNNING, &adapter->state)) + ixgbe_ptp_reset(adapter); } /** @@ -3932,6 +4950,8 @@ static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring) ixgbe_unmap_and_free_tx_resource(tx_ring, tx_buffer_info); } + netdev_tx_reset_queue(txring_txq(tx_ring)); + size = sizeof(struct ixgbe_tx_buffer) * tx_ring->count; memset(tx_ring->tx_buffer_info, 0, size); @@ -3968,12 +4988,12 @@ static void ixgbe_clean_all_tx_rings(struct ixgbe_adapter *adapter) static void ixgbe_fdir_filter_exit(struct ixgbe_adapter *adapter) { - struct hlist_node *node, *node2; + struct hlist_node *node2; struct ixgbe_fdir_filter *filter; spin_lock(&adapter->fdir_perfect_lock); - hlist_for_each_entry_safe(filter, node, node2, + hlist_for_each_entry_safe(filter, node2, &adapter->fdir_filter_list, fdir_node) { hlist_del(&filter->fdir_node); kfree(filter); @@ -3987,11 +5007,14 @@ void ixgbe_down(struct ixgbe_adapter *adapter) { struct net_device *netdev = adapter->netdev; struct ixgbe_hw *hw = &adapter->hw; + struct net_device *upper; + struct list_head *iter; u32 rxctrl; int i; /* signal that we are down to the interrupt handler */ - set_bit(__IXGBE_DOWN, &adapter->state); + if (test_and_set_bit(__IXGBE_DOWN, &adapter->state)) + return; /* do nothing if already down */ /* disable receives */ rxctrl = IXGBE_READ_REG(hw, IXGBE_RXCTRL); @@ -4010,6 +5033,19 @@ void ixgbe_down(struct ixgbe_adapter *adapter) netif_carrier_off(netdev); netif_tx_disable(netdev); + /* disable any upper devices */ + netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) { + if (netif_is_macvlan(upper)) { + struct macvlan_dev *vlan = netdev_priv(upper); + + if (vlan->fwd_priv) { + netif_tx_stop_all_queues(upper); + netif_carrier_off(upper); + netif_tx_disable(upper); + } + } + } + ixgbe_irq_disable(adapter); ixgbe_napi_disable_all(adapter); @@ -4056,11 +5092,8 @@ void ixgbe_down(struct ixgbe_adapter *adapter) 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)))) + /* power down the optics for 82599 SFP+ fiber */ + if (hw->mac.ops.disable_tx_laser) hw->mac.ops.disable_tx_laser(hw); ixgbe_clean_all_tx_rings(adapter); @@ -4073,55 +5106,6 @@ void ixgbe_down(struct ixgbe_adapter *adapter) } /** - * 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; - struct ixgbe_ring *ring; - int per_ring_budget; - bool clean_complete = true; - -#ifdef CONFIG_IXGBE_DCA - if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) - ixgbe_update_dca(q_vector); -#endif - - for (ring = q_vector->tx.ring; ring != NULL; ring = ring->next) - clean_complete &= !!ixgbe_clean_tx_irq(q_vector, ring); - - /* attempt to distribute budget to each queue fairly, but don't allow - * the budget to go below 1 because we'll exit polling */ - if (q_vector->rx.count > 1) - per_ring_budget = max(budget/q_vector->rx.count, 1); - else - per_ring_budget = budget; - - for (ring = q_vector->rx.ring; ring != NULL; ring = ring->next) - clean_complete &= ixgbe_clean_rx_irq(q_vector, ring, - per_ring_budget); - - /* If all work not completed, return budget and keep polling */ - if (!clean_complete) - return budget; - - /* all work done, exit the polling mode */ - 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; -} - -/** * ixgbe_tx_timeout - Respond to a Tx Hang * @netdev: network interface device structure **/ @@ -4134,802 +5118,6 @@ static void ixgbe_tx_timeout(struct net_device *netdev) } /** - * 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_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: - if ((adapter->netdev->reg_state == NETREG_UNREGISTERED) || - (adapter->netdev->reg_state == NETREG_UNREGISTERING)) - return 0; - - /* 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 > 4) { - 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 { - *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 v_idx, num_q_vectors; - struct ixgbe_q_vector *q_vector; - - if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) - num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - else - num_q_vectors = 1; - - for (v_idx = 0; v_idx < num_q_vectors; v_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; - q_vector->v_idx = v_idx; - - /* Allocate the affinity_hint cpumask, configure the mask */ - if (!alloc_cpumask_var(&q_vector->affinity_mask, GFP_KERNEL)) - goto err_out; - cpumask_set_cpu(v_idx, q_vector->affinity_mask); - netif_napi_add(adapter->netdev, &q_vector->napi, - ixgbe_poll, 64); - adapter->q_vector[v_idx] = q_vector; - } - - return 0; - -err_out: - while (v_idx) { - v_idx--; - q_vector = adapter->q_vector[v_idx]; - netif_napi_del(&q_vector->napi); - free_cpumask_var(q_vector->affinity_mask); - kfree(q_vector); - adapter->q_vector[v_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 v_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 (v_idx = 0; v_idx < num_q_vectors; v_idx++) { - struct ixgbe_q_vector *q_vector = adapter->q_vector[v_idx]; - adapter->q_vector[v_idx] = NULL; - netif_napi_del(&q_vector->napi); - free_cpumask_var(q_vector->affinity_mask); - 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 * @@ -4937,11 +5125,12 @@ void ixgbe_clear_interrupt_scheme(struct ixgbe_adapter *adapter) * 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) +static int ixgbe_sw_init(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; struct pci_dev *pdev = adapter->pdev; - unsigned int rss; + unsigned int rss, fdir; + u32 fwsm; #ifdef CONFIG_IXGBE_DCB int j; struct tc_configuration *tc; @@ -4955,44 +5144,71 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter) 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; + /* Set common capability flags and settings */ + rss = min_t(int, IXGBE_MAX_RSS_INDICES, num_online_cpus()); + adapter->ring_feature[RING_F_RSS].limit = rss; + adapter->flags2 |= IXGBE_FLAG2_RSC_CAPABLE; + adapter->flags2 |= IXGBE_FLAG2_RSC_ENABLED; + adapter->max_q_vectors = MAX_Q_VECTORS_82599; + adapter->atr_sample_rate = 20; + fdir = min_t(int, IXGBE_MAX_FDIR_INDICES, num_online_cpus()); + adapter->ring_feature[RING_F_FDIR].limit = fdir; + adapter->fdir_pballoc = IXGBE_FDIR_PBALLOC_64K; +#ifdef CONFIG_IXGBE_DCA + adapter->flags |= IXGBE_FLAG_DCA_CAPABLE; +#endif +#ifdef IXGBE_FCOE + adapter->flags |= IXGBE_FLAG_FCOE_CAPABLE; + adapter->flags &= ~IXGBE_FLAG_FCOE_ENABLED; +#ifdef CONFIG_IXGBE_DCB + /* Default traffic class to use for FCoE */ + adapter->fcoe.up = IXGBE_FCOE_DEFTC; +#endif /* CONFIG_IXGBE_DCB */ +#endif /* IXGBE_FCOE */ + + adapter->mac_table = kzalloc(sizeof(struct ixgbe_mac_addr) * + hw->mac.num_rar_entries, + GFP_ATOMIC); + + /* Set MAC specific capability flags and exceptions */ switch (hw->mac.type) { case ixgbe_mac_82598EB: + adapter->flags2 &= ~IXGBE_FLAG2_RSC_CAPABLE; + adapter->flags2 &= ~IXGBE_FLAG2_RSC_ENABLED; + 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_X540: - adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE; - case ixgbe_mac_82599EB: - 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; + + adapter->max_q_vectors = MAX_Q_VECTORS_82598; + adapter->ring_feature[RING_F_FDIR].limit = 0; + adapter->atr_sample_rate = 0; + adapter->fdir_pballoc = 0; #ifdef IXGBE_FCOE - adapter->flags |= IXGBE_FLAG_FCOE_CAPABLE; + adapter->flags &= ~IXGBE_FLAG_FCOE_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 + adapter->fcoe.up = 0; +#endif /* IXGBE_DCB */ #endif /* IXGBE_FCOE */ break; + case ixgbe_mac_82599EB: + if (hw->device_id == IXGBE_DEV_ID_82599_T3_LOM) + adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE; + break; + case ixgbe_mac_X540: + fwsm = IXGBE_READ_REG(hw, IXGBE_FWSM); + if (fwsm & IXGBE_FWSM_TS_ENABLED) + adapter->flags2 |= IXGBE_FLAG2_TEMP_SENSOR_CAPABLE; + break; default: break; } +#ifdef IXGBE_FCOE + /* FCoE support exists, always init the FCoE lock */ + spin_lock_init(&adapter->fcoe.lock); + +#endif /* n-tuple support exists, always init our spinlock */ spin_lock_init(&adapter->fdir_perfect_lock); @@ -5028,30 +5244,38 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter) 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); + memcpy(&adapter->temp_dcb_cfg, &adapter->dcb_cfg, + sizeof(adapter->temp_dcb_cfg)); #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 ixgbe_pbthresh_setup(adapter); hw->fc.pause_time = IXGBE_DEFAULT_FCPAUSE; hw->fc.send_xon = true; - hw->fc.disable_fc_autoneg = false; + hw->fc.disable_fc_autoneg = ixgbe_device_supports_autoneg_fc(hw); + +#ifdef CONFIG_PCI_IOV + if (max_vfs > 0) + e_dev_warn("Enabling SR-IOV VFs using the max_vfs module parameter is deprecated - please use the pci sysfs interface instead.\n"); + + /* assign number of SR-IOV VFs */ + if (hw->mac.type != ixgbe_mac_82598EB) { + if (max_vfs > IXGBE_MAX_VFS_DRV_LIMIT) { + adapter->num_vfs = 0; + e_dev_warn("max_vfs parameter out of range. Not assigning any SR-IOV VFs\n"); + } else { + adapter->num_vfs = max_vfs; + } + } +#endif /* CONFIG_PCI_IOV */ /* enable itr by default in dynamic mode */ adapter->rx_itr_setting = 1; adapter->tx_itr_setting = 1; - /* set defaults for eitr in MegaBytes */ - adapter->eitr_low = 10; - adapter->eitr_high = 20; - /* set default ring sizes */ adapter->tx_ring_count = IXGBE_DEFAULT_TXD; adapter->rx_ring_count = IXGBE_DEFAULT_RXD; @@ -5065,12 +5289,8 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter) return -EIO; } - /* enable rx csum by default */ - adapter->flags |= IXGBE_FLAG_RX_CSUM_ENABLED; - - /* get assigned NUMA node */ - adapter->node = dev_to_node(&pdev->dev); - + /* PF holds first pool slot */ + set_bit(0, &adapter->fwd_bitmask); set_bit(__IXGBE_DOWN, &adapter->state); return 0; @@ -5085,21 +5305,36 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter) int ixgbe_setup_tx_resources(struct ixgbe_ring *tx_ring) { struct device *dev = tx_ring->dev; + int orig_node = dev_to_node(dev); + int numa_node = -1; int size; size = sizeof(struct ixgbe_tx_buffer) * tx_ring->count; - tx_ring->tx_buffer_info = vzalloc_node(size, tx_ring->numa_node); + + if (tx_ring->q_vector) + numa_node = tx_ring->q_vector->numa_node; + + tx_ring->tx_buffer_info = vzalloc_node(size, numa_node); if (!tx_ring->tx_buffer_info) tx_ring->tx_buffer_info = vzalloc(size); if (!tx_ring->tx_buffer_info) goto err; + u64_stats_init(&tx_ring->syncp); + /* round up to nearest 4K */ tx_ring->size = tx_ring->count * sizeof(union ixgbe_adv_tx_desc); tx_ring->size = ALIGN(tx_ring->size, 4096); - tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size, - &tx_ring->dma, GFP_KERNEL); + set_dev_node(dev, numa_node); + tx_ring->desc = dma_alloc_coherent(dev, + tx_ring->size, + &tx_ring->dma, + GFP_KERNEL); + set_dev_node(dev, orig_node); + if (!tx_ring->desc) + tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size, + &tx_ring->dma, GFP_KERNEL); if (!tx_ring->desc) goto err; @@ -5132,10 +5367,16 @@ static int ixgbe_setup_all_tx_resources(struct ixgbe_adapter *adapter) err = ixgbe_setup_tx_resources(adapter->tx_ring[i]); if (!err) continue; + e_err(probe, "Allocation for Tx Queue %u failed\n", i); - break; + goto err_setup_tx; } + return 0; +err_setup_tx: + /* rewind the index freeing the rings as we go */ + while (i--) + ixgbe_free_tx_resources(adapter->tx_ring[i]); return err; } @@ -5148,22 +5389,36 @@ static int ixgbe_setup_all_tx_resources(struct ixgbe_adapter *adapter) int ixgbe_setup_rx_resources(struct ixgbe_ring *rx_ring) { struct device *dev = rx_ring->dev; + int orig_node = dev_to_node(dev); + int numa_node = -1; int size; size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count; - rx_ring->rx_buffer_info = vzalloc_node(size, rx_ring->numa_node); + + if (rx_ring->q_vector) + numa_node = rx_ring->q_vector->numa_node; + + rx_ring->rx_buffer_info = vzalloc_node(size, numa_node); if (!rx_ring->rx_buffer_info) rx_ring->rx_buffer_info = vzalloc(size); if (!rx_ring->rx_buffer_info) goto err; + u64_stats_init(&rx_ring->syncp); + /* Round up to nearest 4K */ rx_ring->size = rx_ring->count * sizeof(union ixgbe_adv_rx_desc); rx_ring->size = ALIGN(rx_ring->size, 4096); - rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size, - &rx_ring->dma, GFP_KERNEL); - + set_dev_node(dev, numa_node); + rx_ring->desc = dma_alloc_coherent(dev, + rx_ring->size, + &rx_ring->dma, + GFP_KERNEL); + set_dev_node(dev, orig_node); + if (!rx_ring->desc) + rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size, + &rx_ring->dma, GFP_KERNEL); if (!rx_ring->desc) goto err; @@ -5196,10 +5451,20 @@ static int ixgbe_setup_all_rx_resources(struct ixgbe_adapter *adapter) err = ixgbe_setup_rx_resources(adapter->rx_ring[i]); if (!err) continue; + e_err(probe, "Allocation for Rx Queue %u failed\n", i); - break; + goto err_setup_rx; } +#ifdef IXGBE_FCOE + err = ixgbe_setup_fcoe_ddp_resources(adapter); + if (!err) +#endif + return 0; +err_setup_rx: + /* rewind the index freeing the rings as we go */ + while (i--) + ixgbe_free_rx_resources(adapter->rx_ring[i]); return err; } @@ -5274,6 +5539,10 @@ static void ixgbe_free_all_rx_resources(struct ixgbe_adapter *adapter) { int i; +#ifdef IXGBE_FCOE + ixgbe_free_fcoe_ddp_resources(adapter); + +#endif for (i = 0; i < adapter->num_rx_queues; i++) if (adapter->rx_ring[i]->desc) ixgbe_free_rx_resources(adapter->rx_ring[i]); @@ -5289,20 +5558,24 @@ static void ixgbe_free_all_rx_resources(struct ixgbe_adapter *adapter) static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu) { struct ixgbe_adapter *adapter = netdev_priv(netdev); - struct ixgbe_hw *hw = &adapter->hw; int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN; /* MTU < 68 is an error and causes problems on some kernels */ - if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED && - hw->mac.type != ixgbe_mac_X540) { - if ((new_mtu < 68) || (max_frame > MAXIMUM_ETHERNET_VLAN_SIZE)) - return -EINVAL; - } else { - if ((new_mtu < 68) || (max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE)) - return -EINVAL; - } + if ((new_mtu < 68) || (max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE)) + return -EINVAL; + + /* + * For 82599EB we cannot allow legacy VFs to enable their receive + * paths when MTU greater than 1500 is configured. So display a + * warning that legacy VFs will be disabled. + */ + if ((adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) && + (adapter->hw.mac.type == ixgbe_mac_82599EB) && + (max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN))) + e_warn(probe, "Setting MTU > 1500 will disable legacy VFs\n"); e_info(probe, "changing MTU from %d to %d\n", netdev->mtu, new_mtu); + /* must set new MTU before calling down or up */ netdev->mtu = new_mtu; @@ -5327,7 +5600,7 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu) static int ixgbe_open(struct net_device *netdev) { struct ixgbe_adapter *adapter = netdev_priv(netdev); - int err; + int err, queues; /* disallow open during test */ if (test_bit(__IXGBE_TESTING, &adapter->state)) @@ -5351,20 +5624,54 @@ static int ixgbe_open(struct net_device *netdev) if (err) goto err_req_irq; + /* Notify the stack of the actual queue counts. */ + if (adapter->num_rx_pools > 1) + queues = adapter->num_rx_queues_per_pool; + else + queues = adapter->num_tx_queues; + + err = netif_set_real_num_tx_queues(netdev, queues); + if (err) + goto err_set_queues; + + if (adapter->num_rx_pools > 1 && + adapter->num_rx_queues > IXGBE_MAX_L2A_QUEUES) + queues = IXGBE_MAX_L2A_QUEUES; + else + queues = adapter->num_rx_queues; + err = netif_set_real_num_rx_queues(netdev, queues); + if (err) + goto err_set_queues; + + ixgbe_ptp_init(adapter); + ixgbe_up_complete(adapter); return 0; +err_set_queues: + ixgbe_free_irq(adapter); err_req_irq: -err_setup_rx: ixgbe_free_all_rx_resources(adapter); -err_setup_tx: +err_setup_rx: ixgbe_free_all_tx_resources(adapter); +err_setup_tx: ixgbe_reset(adapter); return err; } +static void ixgbe_close_suspend(struct ixgbe_adapter *adapter) +{ + ixgbe_ptp_suspend(adapter); + + ixgbe_down(adapter); + ixgbe_free_irq(adapter); + + ixgbe_free_all_tx_resources(adapter); + ixgbe_free_all_rx_resources(adapter); +} + /** * ixgbe_close - Disables a network interface * @netdev: network interface device structure @@ -5380,13 +5687,11 @@ static int ixgbe_close(struct net_device *netdev) { struct ixgbe_adapter *adapter = netdev_priv(netdev); - ixgbe_down(adapter); - ixgbe_free_irq(adapter); + ixgbe_ptp_stop(adapter); - ixgbe_fdir_filter_exit(adapter); + ixgbe_close_suspend(adapter); - ixgbe_free_all_tx_resources(adapter); - ixgbe_free_all_rx_resources(adapter); + ixgbe_fdir_filter_exit(adapter); ixgbe_release_hw_control(adapter); @@ -5400,6 +5705,7 @@ static int ixgbe_resume(struct pci_dev *pdev) struct net_device *netdev = adapter->netdev; u32 err; + adapter->hw.hw_addr = adapter->io_addr; pci_set_power_state(pdev, PCI_D0); pci_restore_state(pdev); /* @@ -5413,25 +5719,25 @@ static int ixgbe_resume(struct pci_dev *pdev) e_dev_err("Cannot enable PCI device from suspend\n"); return err; } + smp_mb__before_atomic(); + clear_bit(__IXGBE_DISABLED, &adapter->state); pci_set_master(pdev); pci_wake_from_d3(pdev, false); - err = ixgbe_init_interrupt_scheme(adapter); - if (err) { - e_dev_err("Cannot initialize interrupts for device\n"); - return err; - } - ixgbe_reset(adapter); IXGBE_WRITE_REG(&adapter->hw, IXGBE_WUS, ~0); - if (netif_running(netdev)) { + rtnl_lock(); + err = ixgbe_init_interrupt_scheme(adapter); + if (!err && netif_running(netdev)) err = ixgbe_open(netdev); - if (err) - return err; - } + + rtnl_unlock(); + + if (err) + return err; netif_device_attach(netdev); @@ -5452,18 +5758,12 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) netif_device_detach(netdev); - if (netif_running(netdev)) { - ixgbe_down(adapter); - ixgbe_free_irq(adapter); - ixgbe_free_all_tx_resources(adapter); - ixgbe_free_all_rx_resources(adapter); - } + rtnl_lock(); + if (netif_running(netdev)) + ixgbe_close_suspend(adapter); + rtnl_unlock(); ixgbe_clear_interrupt_scheme(adapter); -#ifdef CONFIG_DCB - kfree(adapter->ixgbe_ieee_pfc); - kfree(adapter->ixgbe_ieee_ets); -#endif #ifdef CONFIG_PM retval = pci_save_state(pdev); @@ -5471,9 +5771,16 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) return retval; #endif + if (hw->mac.ops.stop_link_on_d3) + hw->mac.ops.stop_link_on_d3(hw); + if (wufc) { ixgbe_set_rx_mode(netdev); + /* enable the optics for 82599 SFP+ fiber as we can WoL */ + if (hw->mac.ops.enable_tx_laser) + hw->mac.ops.enable_tx_laser(hw); + /* turn on all-multi mode if wake on multicast is enabled */ if (wufc & IXGBE_WUFC_MC) { fctrl = IXGBE_READ_REG(hw, IXGBE_FCTRL); @@ -5507,7 +5814,8 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) ixgbe_release_hw_control(adapter); - pci_disable_device(pdev); + if (!test_and_set_bit(__IXGBE_DISABLED, &adapter->state)) + pci_disable_device(pdev); return 0; } @@ -5558,12 +5866,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) u32 i, missed_rx = 0, mpc, bprc, lxon, lxoff, xon_off_tot; u64 non_eop_descs = 0, restart_queue = 0, tx_busy = 0; u64 alloc_rx_page_failed = 0, alloc_rx_buff_failed = 0; - u64 bytes = 0, packets = 0; -#ifdef IXGBE_FCOE - struct ixgbe_fcoe *fcoe = &adapter->fcoe; - unsigned int cpu; - u64 fcoe_noddp_counts_sum = 0, fcoe_noddp_ext_buff_counts_sum = 0; -#endif /* IXGBE_FCOE */ + u64 bytes = 0, packets = 0, hw_csum_rx_error = 0; if (test_bit(__IXGBE_DOWN, &adapter->state) || test_bit(__IXGBE_RESETTING, &adapter->state)) @@ -5572,9 +5875,6 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) { u64 rsc_count = 0; u64 rsc_flush = 0; - for (i = 0; i < 16; i++) - adapter->hw_rx_no_dma_resources += - IXGBE_READ_REG(hw, IXGBE_QPRDC(i)); for (i = 0; i < adapter->num_rx_queues; i++) { rsc_count += adapter->rx_ring[i]->rx_stats.rsc_count; rsc_flush += adapter->rx_ring[i]->rx_stats.rsc_flush; @@ -5588,12 +5888,14 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) non_eop_descs += rx_ring->rx_stats.non_eop_descs; alloc_rx_page_failed += rx_ring->rx_stats.alloc_rx_page_failed; alloc_rx_buff_failed += rx_ring->rx_stats.alloc_rx_buff_failed; + hw_csum_rx_error += rx_ring->rx_stats.csum_err; bytes += rx_ring->stats.bytes; packets += rx_ring->stats.packets; } adapter->non_eop_descs = non_eop_descs; adapter->alloc_rx_page_failed = alloc_rx_page_failed; adapter->alloc_rx_buff_failed = alloc_rx_buff_failed; + adapter->hw_csum_rx_error = hw_csum_rx_error; netdev->stats.rx_bytes = bytes; netdev->stats.rx_packets = packets; @@ -5675,6 +5977,9 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) hwstats->b2ospc += IXGBE_READ_REG(hw, IXGBE_B2OSPC); hwstats->b2ogprc += IXGBE_READ_REG(hw, IXGBE_B2OGPRC); case ixgbe_mac_82599EB: + for (i = 0; i < 16; i++) + adapter->hw_rx_no_dma_resources += + IXGBE_READ_REG(hw, IXGBE_QPRDC(i)); hwstats->gorc += IXGBE_READ_REG(hw, IXGBE_GORCL); IXGBE_READ_REG(hw, IXGBE_GORCH); /* to clear */ hwstats->gotc += IXGBE_READ_REG(hw, IXGBE_GOTCL); @@ -5692,17 +5997,19 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) hwstats->fcoedwrc += IXGBE_READ_REG(hw, IXGBE_FCOEDWRC); hwstats->fcoedwtc += IXGBE_READ_REG(hw, IXGBE_FCOEDWTC); /* Add up per cpu counters for total ddp aloc fail */ - if (fcoe->pcpu_noddp && fcoe->pcpu_noddp_ext_buff) { + if (adapter->fcoe.ddp_pool) { + struct ixgbe_fcoe *fcoe = &adapter->fcoe; + struct ixgbe_fcoe_ddp_pool *ddp_pool; + unsigned int cpu; + u64 noddp = 0, noddp_ext_buff = 0; for_each_possible_cpu(cpu) { - fcoe_noddp_counts_sum += - *per_cpu_ptr(fcoe->pcpu_noddp, cpu); - fcoe_noddp_ext_buff_counts_sum += - *per_cpu_ptr(fcoe-> - pcpu_noddp_ext_buff, cpu); + ddp_pool = per_cpu_ptr(fcoe->ddp_pool, cpu); + noddp += ddp_pool->noddp; + noddp_ext_buff += ddp_pool->noddp_ext_buff; } + hwstats->fcoe_noddp = noddp; + hwstats->fcoe_noddp_ext_buff = noddp_ext_buff; } - hwstats->fcoe_noddp = fcoe_noddp_counts_sum; - hwstats->fcoe_noddp_ext_buff = fcoe_noddp_ext_buff_counts_sum; #endif /* IXGBE_FCOE */ break; default: @@ -5760,7 +6067,7 @@ void ixgbe_update_stats(struct ixgbe_adapter *adapter) /** * ixgbe_fdir_reinit_subtask - worker thread to reinit FDIR filter table - * @adapter - pointer to the device adapter structure + * @adapter: pointer to the device adapter structure **/ static void ixgbe_fdir_reinit_subtask(struct ixgbe_adapter *adapter) { @@ -5785,7 +6092,7 @@ static void ixgbe_fdir_reinit_subtask(struct ixgbe_adapter *adapter) if (ixgbe_reinit_fdir_tables_82599(hw) == 0) { for (i = 0; i < adapter->num_tx_queues; i++) set_bit(__IXGBE_TX_FDIR_INIT_DONE, - &(adapter->tx_ring[i]->state)); + &(adapter->tx_ring[i]->state)); /* re-enable flow director interrupts */ IXGBE_WRITE_REG(hw, IXGBE_EIMS, IXGBE_EIMS_FLOW_DIR); } else { @@ -5796,7 +6103,7 @@ static void ixgbe_fdir_reinit_subtask(struct ixgbe_adapter *adapter) /** * ixgbe_check_hang_subtask - check for hung queues and dropped interrupts - * @adapter - pointer to the device adapter structure + * @adapter: pointer to the device adapter structure * * This function serves two purposes. First it strobes the interrupt lines * in order to make certain interrupts are occurring. Secondly it sets the @@ -5809,8 +6116,9 @@ static void ixgbe_check_hang_subtask(struct ixgbe_adapter *adapter) u64 eics = 0; int i; - /* If we're down or resetting, just bail */ + /* If we're down, removing or resetting, just bail */ if (test_bit(__IXGBE_DOWN, &adapter->state) || + test_bit(__IXGBE_REMOVING, &adapter->state) || test_bit(__IXGBE_RESETTING, &adapter->state)) return; @@ -5830,7 +6138,7 @@ static void ixgbe_check_hang_subtask(struct ixgbe_adapter *adapter) (IXGBE_EICS_TCP_TIMER | IXGBE_EICS_OTHER)); } else { /* get one bit for every active tx/rx interrupt vector */ - for (i = 0; i < adapter->num_msix_vectors - NON_Q_VECTORS; i++) { + for (i = 0; i < adapter->num_q_vectors; i++) { struct ixgbe_q_vector *qv = adapter->q_vector[i]; if (qv->rx.ring || qv->tx.ring) eics |= ((u64)1 << i); @@ -5844,15 +6152,15 @@ static void ixgbe_check_hang_subtask(struct ixgbe_adapter *adapter) /** * ixgbe_watchdog_update_link - update the link status - * @adapter - pointer to the device adapter structure - * @link_speed - pointer to a u32 to store the link_speed + * @adapter: pointer to the device adapter structure + * @link_speed: pointer to a u32 to store the link_speed **/ static void ixgbe_watchdog_update_link(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; u32 link_speed = adapter->link_speed; bool link_up = adapter->link_up; - int i; + bool pfc_en = adapter->dcb_cfg.pfc_mode_enable; if (!(adapter->flags & IXGBE_FLAG_NEED_LINK_UPDATE)) return; @@ -5864,13 +6172,13 @@ static void ixgbe_watchdog_update_link(struct ixgbe_adapter *adapter) link_speed = IXGBE_LINK_SPEED_10GB_FULL; link_up = true; } - if (link_up) { - if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) { - for (i = 0; i < MAX_TRAFFIC_CLASS; i++) - hw->mac.ops.fc_enable(hw, i); - } else { - hw->mac.ops.fc_enable(hw, 0); - } + + if (adapter->ixgbe_ieee_pfc) + pfc_en |= !!(adapter->ixgbe_ieee_pfc->pfc_en); + + if (link_up && !((adapter->flags & IXGBE_FLAG_DCB_ENABLED) && pfc_en)) { + hw->mac.ops.fc_enable(hw); + ixgbe_set_rx_drop_en(adapter); } if (link_up || @@ -5885,15 +6193,34 @@ static void ixgbe_watchdog_update_link(struct ixgbe_adapter *adapter) adapter->link_speed = link_speed; } +static void ixgbe_update_default_up(struct ixgbe_adapter *adapter) +{ +#ifdef CONFIG_IXGBE_DCB + struct net_device *netdev = adapter->netdev; + struct dcb_app app = { + .selector = IEEE_8021QAZ_APP_SEL_ETHERTYPE, + .protocol = 0, + }; + u8 up = 0; + + if (adapter->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) + up = dcb_ieee_getapp_mask(netdev, &app); + + adapter->default_up = (up > 1) ? (ffs(up) - 1) : 0; +#endif +} + /** * ixgbe_watchdog_link_is_up - update netif_carrier status and * print link up message - * @adapter - pointer to the device adapter structure + * @adapter: pointer to the device adapter structure **/ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter) { struct net_device *netdev = adapter->netdev; struct ixgbe_hw *hw = &adapter->hw; + struct net_device *upper; + struct list_head *iter; u32 link_speed = adapter->link_speed; bool flow_rx, flow_tx; @@ -5924,6 +6251,12 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter) flow_rx = false; break; } + + adapter->last_rx_ptp_check = jiffies; + + if (test_bit(__IXGBE_PTP_RUNNING, &adapter->state)) + ixgbe_ptp_start_cyclecounter(adapter); + e_info(drv, "NIC Link is Up %s, Flow Control: %s\n", (link_speed == IXGBE_LINK_SPEED_10GB_FULL ? "10 Gbps" : @@ -5938,14 +6271,35 @@ static void ixgbe_watchdog_link_is_up(struct ixgbe_adapter *adapter) netif_carrier_on(netdev); ixgbe_check_vf_rate_limit(adapter); + + /* enable transmits */ + netif_tx_wake_all_queues(adapter->netdev); + + /* enable any upper devices */ + rtnl_lock(); + netdev_for_each_all_upper_dev_rcu(adapter->netdev, upper, iter) { + if (netif_is_macvlan(upper)) { + struct macvlan_dev *vlan = netdev_priv(upper); + + if (vlan->fwd_priv) + netif_tx_wake_all_queues(upper); + } + } + rtnl_unlock(); + + /* update the default user priority for VFs */ + ixgbe_update_default_up(adapter); + + /* ping all the active vfs to let them know link has changed */ + ixgbe_ping_all_vfs(adapter); } /** * ixgbe_watchdog_link_is_down - update netif_carrier status and * print link down message - * @adapter - pointer to the adapter structure + * @adapter: pointer to the adapter structure **/ -static void ixgbe_watchdog_link_is_down(struct ixgbe_adapter* adapter) +static void ixgbe_watchdog_link_is_down(struct ixgbe_adapter *adapter) { struct net_device *netdev = adapter->netdev; struct ixgbe_hw *hw = &adapter->hw; @@ -5961,13 +6315,19 @@ static void ixgbe_watchdog_link_is_down(struct ixgbe_adapter* adapter) if (ixgbe_is_sfp(hw) && hw->mac.type == ixgbe_mac_82598EB) adapter->flags2 |= IXGBE_FLAG2_SEARCH_FOR_SFP; + if (test_bit(__IXGBE_PTP_RUNNING, &adapter->state)) + ixgbe_ptp_start_cyclecounter(adapter); + e_info(drv, "NIC Link is Down\n"); netif_carrier_off(netdev); + + /* ping all the active vfs to let them know link has changed */ + ixgbe_ping_all_vfs(adapter); } /** * ixgbe_watchdog_flush_tx - flush queues on link down - * @adapter - pointer to the device adapter structure + * @adapter: pointer to the device adapter structure **/ static void ixgbe_watchdog_flush_tx(struct ixgbe_adapter *adapter) { @@ -5989,6 +6349,7 @@ static void ixgbe_watchdog_flush_tx(struct ixgbe_adapter *adapter) * to get done, so reset controller to flush Tx. * (Do the reset outside of interrupt context). */ + e_warn(drv, "initiating reset to clear Tx work after link loss\n"); adapter->flags2 |= IXGBE_FLAG2_RESET_REQUESTED; } } @@ -5998,8 +6359,9 @@ static void ixgbe_spoof_check(struct ixgbe_adapter *adapter) { u32 ssvpc; - /* Do not perform spoof check for 82598 */ - if (adapter->hw.mac.type == ixgbe_mac_82598EB) + /* Do not perform spoof check for 82598 or if not in IOV mode */ + if (adapter->hw.mac.type == ixgbe_mac_82598EB || + adapter->num_vfs == 0) return; ssvpc = IXGBE_READ_REG(&adapter->hw, IXGBE_SSVPC); @@ -6011,17 +6373,18 @@ static void ixgbe_spoof_check(struct ixgbe_adapter *adapter) if (!ssvpc) return; - e_warn(drv, "%d Spoofed packets detected\n", ssvpc); + e_warn(drv, "%u Spoofed packets detected\n", ssvpc); } /** * ixgbe_watchdog_subtask - check and bring link up - * @adapter - pointer to the device adapter structure + * @adapter: pointer to the device adapter structure **/ static void ixgbe_watchdog_subtask(struct ixgbe_adapter *adapter) { - /* if interface is down do nothing */ + /* if interface is down, removing or resetting, do nothing */ if (test_bit(__IXGBE_DOWN, &adapter->state) || + test_bit(__IXGBE_REMOVING, &adapter->state) || test_bit(__IXGBE_RESETTING, &adapter->state)) return; @@ -6040,7 +6403,7 @@ static void ixgbe_watchdog_subtask(struct ixgbe_adapter *adapter) /** * ixgbe_sfp_detection_subtask - poll for SFP+ cable - * @adapter - the ixgbe adapter structure + * @adapter: the ixgbe adapter structure **/ static void ixgbe_sfp_detection_subtask(struct ixgbe_adapter *adapter) { @@ -6107,13 +6470,13 @@ sfp_out: /** * ixgbe_sfp_link_config_subtask - set up link SFP after module install - * @adapter - the ixgbe adapter structure + * @adapter: the ixgbe adapter structure **/ static void ixgbe_sfp_link_config_subtask(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - u32 autoneg; - bool negotiation; + u32 speed; + bool autoneg = false; if (!(adapter->flags & IXGBE_FLAG_NEED_LINK_CONFIG)) return; @@ -6124,11 +6487,19 @@ static void ixgbe_sfp_link_config_subtask(struct ixgbe_adapter *adapter) adapter->flags &= ~IXGBE_FLAG_NEED_LINK_CONFIG; - autoneg = hw->phy.autoneg_advertised; - if ((!autoneg) && (hw->mac.ops.get_link_capabilities)) - hw->mac.ops.get_link_capabilities(hw, &autoneg, &negotiation); + speed = hw->phy.autoneg_advertised; + if ((!speed) && (hw->mac.ops.get_link_capabilities)) { + hw->mac.ops.get_link_capabilities(hw, &speed, &autoneg); + + /* setup the highest link when no autoneg */ + if (!autoneg) { + if (speed & IXGBE_LINK_SPEED_10GB_FULL) + speed = IXGBE_LINK_SPEED_10GB_FULL; + } + } + if (hw->mac.ops.setup_link) - hw->mac.ops.setup_link(hw, autoneg, negotiation, true); + hw->mac.ops.setup_link(hw, speed, true); adapter->flags |= IXGBE_FLAG_NEED_LINK_UPDATE; adapter->link_check_timeout = jiffies; @@ -6190,41 +6561,32 @@ static void ixgbe_service_timer(unsigned long data) unsigned long next_event_offset; bool ready = true; -#ifdef CONFIG_PCI_IOV - ready = false; + /* poll faster when waiting for link */ + if (adapter->flags & IXGBE_FLAG_NEED_LINK_UPDATE) + next_event_offset = HZ / 10; + else + next_event_offset = HZ * 2; +#ifdef CONFIG_PCI_IOV /* * don't bother with SR-IOV VF DMA hang check if there are * no VFs or the link is down */ if (!adapter->num_vfs || - (adapter->flags & IXGBE_FLAG_NEED_LINK_UPDATE)) { - ready = true; + (adapter->flags & IXGBE_FLAG_NEED_LINK_UPDATE)) goto normal_timer_service; - } /* If we have VFs allocated then we must check for DMA hangs */ ixgbe_check_for_bad_vf(adapter); next_event_offset = HZ / 50; adapter->timer_event_accumulator++; - if (adapter->timer_event_accumulator >= 100) { - ready = true; + if (adapter->timer_event_accumulator >= 100) adapter->timer_event_accumulator = 0; - } - - goto schedule_event; - -normal_timer_service: -#endif - /* poll faster when waiting for link */ - if (adapter->flags & IXGBE_FLAG_NEED_LINK_UPDATE) - next_event_offset = HZ / 10; else - next_event_offset = HZ * 2; + ready = false; -#ifdef CONFIG_PCI_IOV -schedule_event: +normal_timer_service: #endif /* Reset the timer */ mod_timer(&adapter->service_timer, next_event_offset + jiffies); @@ -6240,8 +6602,9 @@ static void ixgbe_reset_subtask(struct ixgbe_adapter *adapter) adapter->flags2 &= ~IXGBE_FLAG2_RESET_REQUESTED; - /* If we're already down or resetting, just bail */ + /* If we're already down, removing or resetting, just bail */ if (test_bit(__IXGBE_DOWN, &adapter->state) || + test_bit(__IXGBE_REMOVING, &adapter->state) || test_bit(__IXGBE_RESETTING, &adapter->state)) return; @@ -6249,7 +6612,9 @@ static void ixgbe_reset_subtask(struct ixgbe_adapter *adapter) netdev_err(adapter->netdev, "Reset adapter\n"); adapter->tx_timeout_count++; + rtnl_lock(); ixgbe_reinit_locked(adapter); + rtnl_unlock(); } /** @@ -6261,7 +6626,15 @@ static void ixgbe_service_task(struct work_struct *work) struct ixgbe_adapter *adapter = container_of(work, struct ixgbe_adapter, service_task); - + if (ixgbe_removed(adapter->hw.hw_addr)) { + if (!test_bit(__IXGBE_DOWN, &adapter->state)) { + rtnl_lock(); + ixgbe_down(adapter); + rtnl_unlock(); + } + ixgbe_service_event_complete(adapter); + return; + } ixgbe_reset_subtask(adapter); ixgbe_sfp_detection_subtask(adapter); ixgbe_sfp_link_config_subtask(adapter); @@ -6270,49 +6643,37 @@ static void ixgbe_service_task(struct work_struct *work) ixgbe_fdir_reinit_subtask(adapter); ixgbe_check_hang_subtask(adapter); - ixgbe_service_event_complete(adapter); -} - -void ixgbe_tx_ctxtdesc(struct ixgbe_ring *tx_ring, u32 vlan_macip_lens, - u32 fcoe_sof_eof, u32 type_tucmd, u32 mss_l4len_idx) -{ - struct ixgbe_adv_tx_context_desc *context_desc; - u16 i = tx_ring->next_to_use; - - context_desc = IXGBE_TX_CTXTDESC_ADV(tx_ring, i); - - i++; - tx_ring->next_to_use = (i < tx_ring->count) ? i : 0; - - /* set bits to identify this as an advanced context descriptor */ - type_tucmd |= IXGBE_TXD_CMD_DEXT | IXGBE_ADVTXD_DTYP_CTXT; + if (test_bit(__IXGBE_PTP_RUNNING, &adapter->state)) { + ixgbe_ptp_overflow_check(adapter); + ixgbe_ptp_rx_hang(adapter); + } - context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens); - context_desc->seqnum_seed = cpu_to_le32(fcoe_sof_eof); - context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd); - context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx); + ixgbe_service_event_complete(adapter); } -static int ixgbe_tso(struct ixgbe_ring *tx_ring, struct sk_buff *skb, - u32 tx_flags, __be16 protocol, u8 *hdr_len) +static int ixgbe_tso(struct ixgbe_ring *tx_ring, + struct ixgbe_tx_buffer *first, + u8 *hdr_len) { - int err; + struct sk_buff *skb = first->skb; u32 vlan_macip_lens, type_tucmd; u32 mss_l4len_idx, l4len; + int err; + + if (skb->ip_summed != CHECKSUM_PARTIAL) + return 0; if (!skb_is_gso(skb)) return 0; - if (skb_header_cloned(skb)) { - err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); - if (err) - return err; - } + err = skb_cow_head(skb, 0); + if (err < 0) + return err; /* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */ type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_TCP; - if (protocol == __constant_htons(ETH_P_IP)) { + if (first->protocol == htons(ETH_P_IP)) { struct iphdr *iph = ip_hdr(skb); iph->tot_len = 0; iph->check = 0; @@ -6321,54 +6682,63 @@ static int ixgbe_tso(struct ixgbe_ring *tx_ring, struct sk_buff *skb, IPPROTO_TCP, 0); type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4; + first->tx_flags |= IXGBE_TX_FLAGS_TSO | + IXGBE_TX_FLAGS_CSUM | + IXGBE_TX_FLAGS_IPV4; } else if (skb_is_gso_v6(skb)) { ipv6_hdr(skb)->payload_len = 0; tcp_hdr(skb)->check = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, 0, IPPROTO_TCP, 0); + first->tx_flags |= IXGBE_TX_FLAGS_TSO | + IXGBE_TX_FLAGS_CSUM; } + /* compute header lengths */ l4len = tcp_hdrlen(skb); *hdr_len = skb_transport_offset(skb) + l4len; - /* mss_l4len_id: use 1 as index for TSO */ + /* update gso size and bytecount with header size */ + first->gso_segs = skb_shinfo(skb)->gso_segs; + first->bytecount += (first->gso_segs - 1) * *hdr_len; + + /* mss_l4len_id: use 0 as index for TSO */ mss_l4len_idx = l4len << IXGBE_ADVTXD_L4LEN_SHIFT; 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_network_header_len(skb); vlan_macip_lens |= skb_network_offset(skb) << IXGBE_ADVTXD_MACLEN_SHIFT; - vlan_macip_lens |= tx_flags & IXGBE_TX_FLAGS_VLAN_MASK; + vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK; ixgbe_tx_ctxtdesc(tx_ring, vlan_macip_lens, 0, type_tucmd, - mss_l4len_idx); + mss_l4len_idx); return 1; } -static bool ixgbe_tx_csum(struct ixgbe_ring *tx_ring, - struct sk_buff *skb, u32 tx_flags, - __be16 protocol) +static void ixgbe_tx_csum(struct ixgbe_ring *tx_ring, + struct ixgbe_tx_buffer *first) { + struct sk_buff *skb = first->skb; u32 vlan_macip_lens = 0; u32 mss_l4len_idx = 0; u32 type_tucmd = 0; if (skb->ip_summed != CHECKSUM_PARTIAL) { - if (!(tx_flags & IXGBE_TX_FLAGS_HW_VLAN) && - !(tx_flags & IXGBE_TX_FLAGS_TXSW)) - return false; + if (!(first->tx_flags & IXGBE_TX_FLAGS_HW_VLAN) && + !(first->tx_flags & IXGBE_TX_FLAGS_CC)) + return; } else { u8 l4_hdr = 0; - switch (protocol) { - case __constant_htons(ETH_P_IP): + switch (first->protocol) { + case htons(ETH_P_IP): vlan_macip_lens |= skb_network_header_len(skb); type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4; l4_hdr = ip_hdr(skb)->protocol; break; - case __constant_htons(ETH_P_IPV6): + case htons(ETH_P_IPV6): vlan_macip_lens |= skb_network_header_len(skb); l4_hdr = ipv6_hdr(skb)->nexthdr; break; @@ -6376,7 +6746,7 @@ static bool ixgbe_tx_csum(struct ixgbe_ring *tx_ring, if (unlikely(net_ratelimit())) { dev_warn(tx_ring->dev, "partial checksum but proto=%x!\n", - skb->protocol); + first->protocol); } break; } @@ -6400,237 +6770,223 @@ static bool ixgbe_tx_csum(struct ixgbe_ring *tx_ring, if (unlikely(net_ratelimit())) { dev_warn(tx_ring->dev, "partial checksum but l4 proto=%x!\n", - skb->protocol); + l4_hdr); } break; } + + /* update TX checksum flag */ + first->tx_flags |= IXGBE_TX_FLAGS_CSUM; } + /* vlan_macip_lens: MACLEN, VLAN tag */ vlan_macip_lens |= skb_network_offset(skb) << IXGBE_ADVTXD_MACLEN_SHIFT; - vlan_macip_lens |= tx_flags & IXGBE_TX_FLAGS_VLAN_MASK; + vlan_macip_lens |= first->tx_flags & IXGBE_TX_FLAGS_VLAN_MASK; ixgbe_tx_ctxtdesc(tx_ring, vlan_macip_lens, 0, type_tucmd, mss_l4len_idx); - - return (skb->ip_summed == CHECKSUM_PARTIAL); } -static __le32 ixgbe_tx_cmd_type(u32 tx_flags) +#define IXGBE_SET_FLAG(_input, _flag, _result) \ + ((_flag <= _result) ? \ + ((u32)(_input & _flag) * (_result / _flag)) : \ + ((u32)(_input & _flag) / (_flag / _result))) + +static u32 ixgbe_tx_cmd_type(struct sk_buff *skb, u32 tx_flags) { /* set type for advanced descriptor with frame checksum insertion */ - __le32 cmd_type = cpu_to_le32(IXGBE_ADVTXD_DTYP_DATA | - IXGBE_ADVTXD_DCMD_IFCS | - IXGBE_ADVTXD_DCMD_DEXT); + u32 cmd_type = IXGBE_ADVTXD_DTYP_DATA | + IXGBE_ADVTXD_DCMD_DEXT | + IXGBE_ADVTXD_DCMD_IFCS; /* set HW vlan bit if vlan is present */ - if (tx_flags & IXGBE_TX_FLAGS_HW_VLAN) - cmd_type |= cpu_to_le32(IXGBE_ADVTXD_DCMD_VLE); + cmd_type |= IXGBE_SET_FLAG(tx_flags, IXGBE_TX_FLAGS_HW_VLAN, + IXGBE_ADVTXD_DCMD_VLE); /* set segmentation enable bits for TSO/FSO */ -#ifdef IXGBE_FCOE - if ((tx_flags & IXGBE_TX_FLAGS_TSO) || (tx_flags & IXGBE_TX_FLAGS_FSO)) -#else - if (tx_flags & IXGBE_TX_FLAGS_TSO) -#endif - cmd_type |= cpu_to_le32(IXGBE_ADVTXD_DCMD_TSE); + cmd_type |= IXGBE_SET_FLAG(tx_flags, IXGBE_TX_FLAGS_TSO, + IXGBE_ADVTXD_DCMD_TSE); + + /* set timestamp bit if present */ + cmd_type |= IXGBE_SET_FLAG(tx_flags, IXGBE_TX_FLAGS_TSTAMP, + IXGBE_ADVTXD_MAC_TSTAMP); + + /* insert frame checksum */ + cmd_type ^= IXGBE_SET_FLAG(skb->no_fcs, 1, IXGBE_ADVTXD_DCMD_IFCS); return cmd_type; } -static __le32 ixgbe_tx_olinfo_status(u32 tx_flags, unsigned int paylen) +static void ixgbe_tx_olinfo_status(union ixgbe_adv_tx_desc *tx_desc, + u32 tx_flags, unsigned int paylen) { - __le32 olinfo_status = - cpu_to_le32(paylen << IXGBE_ADVTXD_PAYLEN_SHIFT); - - if (tx_flags & IXGBE_TX_FLAGS_TSO) { - olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_POPTS_TXSM | - (1 << IXGBE_ADVTXD_IDX_SHIFT)); - /* enble IPv4 checksum for TSO */ - if (tx_flags & IXGBE_TX_FLAGS_IPV4) - olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_POPTS_IXSM); - } + u32 olinfo_status = paylen << IXGBE_ADVTXD_PAYLEN_SHIFT; /* enable L4 checksum for TSO and TX checksum offload */ - if (tx_flags & IXGBE_TX_FLAGS_CSUM) - olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_POPTS_TXSM); + olinfo_status |= IXGBE_SET_FLAG(tx_flags, + IXGBE_TX_FLAGS_CSUM, + IXGBE_ADVTXD_POPTS_TXSM); -#ifdef IXGBE_FCOE - /* use index 1 context for FCOE/FSO */ - if (tx_flags & IXGBE_TX_FLAGS_FCOE) - olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_CC | - (1 << IXGBE_ADVTXD_IDX_SHIFT)); + /* enble IPv4 checksum for TSO */ + olinfo_status |= IXGBE_SET_FLAG(tx_flags, + IXGBE_TX_FLAGS_IPV4, + IXGBE_ADVTXD_POPTS_IXSM); -#endif /* * Check Context must be set if Tx switch is enabled, which it * always is for case where virtual functions are running */ - if (tx_flags & IXGBE_TX_FLAGS_TXSW) - olinfo_status |= cpu_to_le32(IXGBE_ADVTXD_CC); + olinfo_status |= IXGBE_SET_FLAG(tx_flags, + IXGBE_TX_FLAGS_CC, + IXGBE_ADVTXD_CC); - return olinfo_status; + tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); } #define IXGBE_TXD_CMD (IXGBE_TXD_CMD_EOP | \ IXGBE_TXD_CMD_RS) static void ixgbe_tx_map(struct ixgbe_ring *tx_ring, - struct sk_buff *skb, struct ixgbe_tx_buffer *first, - u32 tx_flags, const u8 hdr_len) { - struct device *dev = tx_ring->dev; - struct ixgbe_tx_buffer *tx_buffer_info; + struct sk_buff *skb = first->skb; + struct ixgbe_tx_buffer *tx_buffer; union ixgbe_adv_tx_desc *tx_desc; - dma_addr_t dma; - __le32 cmd_type, olinfo_status; struct skb_frag_struct *frag; - unsigned int f = 0; - unsigned int data_len = skb->data_len; - unsigned int size = skb_headlen(skb); - u32 offset = 0; - u32 paylen = skb->len - hdr_len; + dma_addr_t dma; + unsigned int data_len, size; + u32 tx_flags = first->tx_flags; + u32 cmd_type = ixgbe_tx_cmd_type(skb, tx_flags); u16 i = tx_ring->next_to_use; - u16 gso_segs; + + tx_desc = IXGBE_TX_DESC(tx_ring, i); + + ixgbe_tx_olinfo_status(tx_desc, tx_flags, skb->len - hdr_len); + + size = skb_headlen(skb); + data_len = skb->data_len; #ifdef IXGBE_FCOE if (tx_flags & IXGBE_TX_FLAGS_FCOE) { - if (data_len >= sizeof(struct fcoe_crc_eof)) { - data_len -= sizeof(struct fcoe_crc_eof); - } else { + if (data_len < sizeof(struct fcoe_crc_eof)) { size -= sizeof(struct fcoe_crc_eof) - data_len; data_len = 0; + } else { + data_len -= sizeof(struct fcoe_crc_eof); } } #endif - dma = dma_map_single(dev, skb->data, size, DMA_TO_DEVICE); - if (dma_mapping_error(dev, dma)) - goto dma_error; + dma = dma_map_single(tx_ring->dev, skb->data, size, DMA_TO_DEVICE); - cmd_type = ixgbe_tx_cmd_type(tx_flags); - olinfo_status = ixgbe_tx_olinfo_status(tx_flags, paylen); + tx_buffer = first; - tx_desc = IXGBE_TX_DESC_ADV(tx_ring, i); + for (frag = &skb_shinfo(skb)->frags[0];; frag++) { + if (dma_mapping_error(tx_ring->dev, dma)) + goto dma_error; - for (;;) { - while (size > IXGBE_MAX_DATA_PER_TXD) { - tx_desc->read.buffer_addr = cpu_to_le64(dma + offset); - tx_desc->read.cmd_type_len = - cmd_type | cpu_to_le32(IXGBE_MAX_DATA_PER_TXD); - tx_desc->read.olinfo_status = olinfo_status; + /* record length, and DMA address */ + dma_unmap_len_set(tx_buffer, len, size); + dma_unmap_addr_set(tx_buffer, dma, dma); - offset += IXGBE_MAX_DATA_PER_TXD; - size -= IXGBE_MAX_DATA_PER_TXD; + tx_desc->read.buffer_addr = cpu_to_le64(dma); + + while (unlikely(size > IXGBE_MAX_DATA_PER_TXD)) { + tx_desc->read.cmd_type_len = + cpu_to_le32(cmd_type ^ IXGBE_MAX_DATA_PER_TXD); - tx_desc++; i++; + tx_desc++; if (i == tx_ring->count) { - tx_desc = IXGBE_TX_DESC_ADV(tx_ring, 0); + tx_desc = IXGBE_TX_DESC(tx_ring, 0); i = 0; } - } + tx_desc->read.olinfo_status = 0; - tx_buffer_info = &tx_ring->tx_buffer_info[i]; - tx_buffer_info->length = offset + size; - tx_buffer_info->tx_flags = tx_flags; - tx_buffer_info->dma = dma; + dma += IXGBE_MAX_DATA_PER_TXD; + size -= IXGBE_MAX_DATA_PER_TXD; - tx_desc->read.buffer_addr = cpu_to_le64(dma + offset); - tx_desc->read.cmd_type_len = cmd_type | cpu_to_le32(size); - tx_desc->read.olinfo_status = olinfo_status; + tx_desc->read.buffer_addr = cpu_to_le64(dma); + } - if (!data_len) + if (likely(!data_len)) break; - frag = &skb_shinfo(skb)->frags[f]; + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type ^ size); + + i++; + tx_desc++; + if (i == tx_ring->count) { + tx_desc = IXGBE_TX_DESC(tx_ring, 0); + i = 0; + } + tx_desc->read.olinfo_status = 0; + #ifdef IXGBE_FCOE size = min_t(unsigned int, data_len, skb_frag_size(frag)); #else size = skb_frag_size(frag); #endif data_len -= size; - f++; - offset = 0; - tx_flags |= IXGBE_TX_FLAGS_MAPPED_AS_PAGE; + dma = skb_frag_dma_map(tx_ring->dev, frag, 0, size, + DMA_TO_DEVICE); - dma = skb_frag_dma_map(dev, frag, 0, size, DMA_TO_DEVICE); - if (dma_mapping_error(dev, dma)) - goto dma_error; - - tx_desc++; - i++; - if (i == tx_ring->count) { - tx_desc = IXGBE_TX_DESC_ADV(tx_ring, 0); - i = 0; - } + tx_buffer = &tx_ring->tx_buffer_info[i]; } - tx_desc->read.cmd_type_len |= cpu_to_le32(IXGBE_TXD_CMD); + /* write last descriptor with RS and EOP bits */ + cmd_type |= size | IXGBE_TXD_CMD; + tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); - i++; - if (i == tx_ring->count) - i = 0; - - tx_ring->next_to_use = i; - - if (tx_flags & IXGBE_TX_FLAGS_TSO) - gso_segs = skb_shinfo(skb)->gso_segs; -#ifdef IXGBE_FCOE - /* adjust for FCoE Sequence Offload */ - else if (tx_flags & IXGBE_TX_FLAGS_FSO) - gso_segs = DIV_ROUND_UP(skb->len - hdr_len, - skb_shinfo(skb)->gso_size); -#endif /* IXGBE_FCOE */ - else - gso_segs = 1; - - /* multiply data chunks by size of headers */ - tx_buffer_info->bytecount = paylen + (gso_segs * hdr_len); - tx_buffer_info->gso_segs = gso_segs; - tx_buffer_info->skb = skb; + netdev_tx_sent_queue(txring_txq(tx_ring), first->bytecount); /* set the timestamp */ first->time_stamp = jiffies; /* - * 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). + * Force memory writes to complete before letting h/w know there + * are new descriptors to fetch. (Only applicable for weak-ordered + * memory model archs, such as IA-64). + * + * We also need this memory barrier to make certain all of the + * status bits have been updated before next_to_watch is written. */ wmb(); /* set next_to_watch value indicating a packet is present */ first->next_to_watch = tx_desc; + i++; + if (i == tx_ring->count) + i = 0; + + tx_ring->next_to_use = i; + /* notify HW of packet */ - writel(i, tx_ring->tail); + ixgbe_write_tail(tx_ring, i); return; dma_error: - dev_err(dev, "TX DMA map failed\n"); + dev_err(tx_ring->dev, "TX DMA map failed\n"); /* clear dma mappings for failed tx_buffer_info map */ for (;;) { - tx_buffer_info = &tx_ring->tx_buffer_info[i]; - ixgbe_unmap_tx_resource(tx_ring, tx_buffer_info); - if (tx_buffer_info == first) + tx_buffer = &tx_ring->tx_buffer_info[i]; + ixgbe_unmap_and_free_tx_resource(tx_ring, tx_buffer); + if (tx_buffer == first) break; if (i == 0) i = tx_ring->count; i--; } - dev_kfree_skb_any(skb); - tx_ring->next_to_use = i; } -static void ixgbe_atr(struct ixgbe_ring *ring, struct sk_buff *skb, - u32 tx_flags, __be16 protocol) +static void ixgbe_atr(struct ixgbe_ring *ring, + struct ixgbe_tx_buffer *first) { struct ixgbe_q_vector *q_vector = ring->q_vector; union ixgbe_atr_hash_dword input = { .dword = 0 }; @@ -6654,16 +7010,16 @@ static void ixgbe_atr(struct ixgbe_ring *ring, struct sk_buff *skb, ring->atr_count++; /* snag network header to get L4 type and address */ - hdr.network = skb_network_header(skb); + hdr.network = skb_network_header(first->skb); /* Currently only IPv4/IPv6 with TCP is supported */ - if ((protocol != __constant_htons(ETH_P_IPV6) || + if ((first->protocol != htons(ETH_P_IPV6) || hdr.ipv6->nexthdr != IPPROTO_TCP) && - (protocol != __constant_htons(ETH_P_IP) || + (first->protocol != htons(ETH_P_IP) || hdr.ipv4->protocol != IPPROTO_TCP)) return; - th = tcp_hdr(skb); + th = tcp_hdr(first->skb); /* skip this packet since it is invalid or the socket is closing */ if (!th || th->fin) @@ -6676,7 +7032,7 @@ static void ixgbe_atr(struct ixgbe_ring *ring, struct sk_buff *skb, /* reset sample count */ ring->atr_count = 0; - vlan_id = htons(tx_flags >> IXGBE_TX_FLAGS_VLAN_SHIFT); + vlan_id = htons(first->tx_flags >> IXGBE_TX_FLAGS_VLAN_SHIFT); /* * src and dst are inverted, think how the receiver sees them @@ -6691,13 +7047,13 @@ static void ixgbe_atr(struct ixgbe_ring *ring, struct sk_buff *skb, * since src port and flex bytes occupy the same word XOR them together * and write the value to source port portion of compressed dword */ - if (tx_flags & (IXGBE_TX_FLAGS_SW_VLAN | IXGBE_TX_FLAGS_HW_VLAN)) - common.port.src ^= th->dest ^ __constant_htons(ETH_P_8021Q); + if (first->tx_flags & (IXGBE_TX_FLAGS_SW_VLAN | IXGBE_TX_FLAGS_HW_VLAN)) + common.port.src ^= th->dest ^ htons(ETH_P_8021Q); else - common.port.src ^= th->dest ^ protocol; + common.port.src ^= th->dest ^ first->protocol; common.port.dst ^= th->source; - if (protocol == __constant_htons(ETH_P_IP)) { + if (first->protocol == htons(ETH_P_IP)) { input.formatted.flow_type = IXGBE_ATR_FLOW_TYPE_TCPV4; common.ip ^= hdr.ipv4->saddr ^ hdr.ipv4->daddr; } else { @@ -6743,30 +7099,48 @@ static inline int ixgbe_maybe_stop_tx(struct ixgbe_ring *tx_ring, u16 size) return __ixgbe_maybe_stop_tx(tx_ring, size); } -static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb) +static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv, select_queue_fallback_t fallback) { - struct ixgbe_adapter *adapter = netdev_priv(dev); - int txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : - smp_processor_id(); + struct ixgbe_fwd_adapter *fwd_adapter = accel_priv; #ifdef IXGBE_FCOE - __be16 protocol = vlan_get_protocol(skb); - - if (((protocol == htons(ETH_P_FCOE)) || - (protocol == htons(ETH_P_FIP))) && - (adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) { - txq &= (adapter->ring_feature[RING_F_FCOE].indices - 1); - txq += adapter->ring_feature[RING_F_FCOE].mask; - return txq; - } + struct ixgbe_adapter *adapter; + struct ixgbe_ring_feature *f; + int txq; #endif - if (adapter->flags & IXGBE_FLAG_FDIR_HASH_CAPABLE) { - while (unlikely(txq >= dev->real_num_tx_queues)) - txq -= dev->real_num_tx_queues; - return txq; + if (fwd_adapter) + return skb->queue_mapping + fwd_adapter->tx_base_queue; + +#ifdef IXGBE_FCOE + + /* + * only execute the code below if protocol is FCoE + * or FIP and we have FCoE enabled on the adapter + */ + switch (vlan_get_protocol(skb)) { + case htons(ETH_P_FCOE): + case htons(ETH_P_FIP): + adapter = netdev_priv(dev); + + if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) + break; + default: + return fallback(dev, skb); } - return skb_tx_hash(dev, skb); + f = &adapter->ring_feature[RING_F_FCOE]; + + txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : + smp_processor_id(); + + while (txq >= f->indices) + txq -= f->indices; + + return txq + f->offset; +#else + return fallback(dev, skb); +#endif } netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, @@ -6776,52 +7150,72 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, struct ixgbe_tx_buffer *first; int tso; u32 tx_flags = 0; -#if PAGE_SIZE > IXGBE_MAX_DATA_PER_TXD unsigned short f; -#endif u16 count = TXD_USE_COUNT(skb_headlen(skb)); __be16 protocol = skb->protocol; u8 hdr_len = 0; /* * need: 1 descriptor per page * PAGE_SIZE/IXGBE_MAX_DATA_PER_TXD, - * + 1 desc for skb_head_len/IXGBE_MAX_DATA_PER_TXD, + * + 1 desc for skb_headlen/IXGBE_MAX_DATA_PER_TXD, * + 2 desc gap to keep tail from touching head, * + 1 desc for context descriptor, * otherwise try next time */ -#if PAGE_SIZE > IXGBE_MAX_DATA_PER_TXD for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size); -#else - count += skb_shinfo(skb)->nr_frags; -#endif + if (ixgbe_maybe_stop_tx(tx_ring, count + 3)) { tx_ring->tx_stats.tx_busy++; return NETDEV_TX_BUSY; } -#ifdef CONFIG_PCI_IOV - if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) - tx_flags |= IXGBE_TX_FLAGS_TXSW; + /* record the location of the first descriptor for this packet */ + first = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + first->skb = skb; + first->bytecount = skb->len; + first->gso_segs = 1; -#endif /* if we have a HW VLAN tag being added default to the HW one */ if (vlan_tx_tag_present(skb)) { tx_flags |= vlan_tx_tag_get(skb) << IXGBE_TX_FLAGS_VLAN_SHIFT; tx_flags |= IXGBE_TX_FLAGS_HW_VLAN; /* else if it is a SW VLAN check the next protocol and store the tag */ - } else if (protocol == __constant_htons(ETH_P_8021Q)) { + } else if (protocol == htons(ETH_P_8021Q)) { struct vlan_hdr *vhdr, _vhdr; vhdr = skb_header_pointer(skb, ETH_HLEN, sizeof(_vhdr), &_vhdr); if (!vhdr) goto out_drop; protocol = vhdr->h_vlan_encapsulated_proto; - tx_flags |= ntohs(vhdr->h_vlan_TCI) << IXGBE_TX_FLAGS_VLAN_SHIFT; + tx_flags |= ntohs(vhdr->h_vlan_TCI) << + IXGBE_TX_FLAGS_VLAN_SHIFT; tx_flags |= IXGBE_TX_FLAGS_SW_VLAN; } + if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP && + !test_and_set_bit_lock(__IXGBE_PTP_TX_IN_PROGRESS, + &adapter->state))) { + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + tx_flags |= IXGBE_TX_FLAGS_TSTAMP; + + /* schedule check for Tx timestamp */ + adapter->ptp_tx_skb = skb_get(skb); + adapter->ptp_tx_start = jiffies; + schedule_work(&adapter->ptp_tx_work); + } + + skb_tx_timestamp(skb); + +#ifdef CONFIG_PCI_IOV + /* + * Use the l2switch_enable flag - would be false if the DMA + * Tx switch had been disabled. + */ + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) + tx_flags |= IXGBE_TX_FLAGS_CC; + +#endif /* DCB maps skb priorities 0-7 onto 3 bit PCP of VLAN tag. */ if ((adapter->flags & IXGBE_FLAG_DCB_ENABLED) && ((tx_flags & (IXGBE_TX_FLAGS_HW_VLAN | IXGBE_TX_FLAGS_SW_VLAN)) || @@ -6831,8 +7225,8 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, IXGBE_TX_FLAGS_VLAN_PRIO_SHIFT; if (tx_flags & IXGBE_TX_FLAGS_SW_VLAN) { struct vlan_ethhdr *vhdr; - if (skb_header_cloned(skb) && - pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + + if (skb_cow_head(skb, 0)) goto out_drop; vhdr = (struct vlan_ethhdr *)skb->data; vhdr->h_vlan_TCI = htons(tx_flags >> @@ -6842,65 +7236,77 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, } } - /* record the location of the first descriptor for this packet */ - first = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + /* record initial flags and protocol */ + first->tx_flags = tx_flags; + first->protocol = protocol; #ifdef IXGBE_FCOE /* setup tx offload for FCoE */ - if ((protocol == __constant_htons(ETH_P_FCOE)) && - (adapter->flags & IXGBE_FLAG_FCOE_ENABLED)) { - tso = ixgbe_fso(tx_ring, skb, tx_flags, &hdr_len); + if ((protocol == htons(ETH_P_FCOE)) && + (tx_ring->netdev->features & (NETIF_F_FSO | NETIF_F_FCOE_CRC))) { + tso = ixgbe_fso(tx_ring, first, &hdr_len); if (tso < 0) goto out_drop; - else if (tso) - tx_flags |= IXGBE_TX_FLAGS_FSO | - IXGBE_TX_FLAGS_FCOE; - else - tx_flags |= IXGBE_TX_FLAGS_FCOE; goto xmit_fcoe; } #endif /* IXGBE_FCOE */ - /* setup IPv4/IPv6 offloads */ - if (protocol == __constant_htons(ETH_P_IP)) - tx_flags |= IXGBE_TX_FLAGS_IPV4; - - tso = ixgbe_tso(tx_ring, skb, tx_flags, protocol, &hdr_len); + tso = ixgbe_tso(tx_ring, first, &hdr_len); if (tso < 0) goto out_drop; - else if (tso) - tx_flags |= IXGBE_TX_FLAGS_TSO; - else if (ixgbe_tx_csum(tx_ring, skb, tx_flags, protocol)) - tx_flags |= IXGBE_TX_FLAGS_CSUM; + else if (!tso) + ixgbe_tx_csum(tx_ring, first); /* add the ATR filter if ATR is on */ if (test_bit(__IXGBE_TX_FDIR_INIT_DONE, &tx_ring->state)) - ixgbe_atr(tx_ring, skb, tx_flags, protocol); + ixgbe_atr(tx_ring, first); #ifdef IXGBE_FCOE xmit_fcoe: #endif /* IXGBE_FCOE */ - ixgbe_tx_map(tx_ring, skb, first, tx_flags, hdr_len); + ixgbe_tx_map(tx_ring, first, hdr_len); ixgbe_maybe_stop_tx(tx_ring, DESC_NEEDED); return NETDEV_TX_OK; out_drop: - dev_kfree_skb_any(skb); + dev_kfree_skb_any(first->skb); + first->skb = NULL; + return NETDEV_TX_OK; } -static netdev_tx_t ixgbe_xmit_frame(struct sk_buff *skb, struct net_device *netdev) +static netdev_tx_t __ixgbe_xmit_frame(struct sk_buff *skb, + struct net_device *netdev, + struct ixgbe_ring *ring) { struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_ring *tx_ring; - tx_ring = adapter->tx_ring[skb->queue_mapping]; + /* + * The minimum packet size for olinfo paylen is 17 so pad the skb + * in order to meet this minimum size requirement. + */ + if (unlikely(skb->len < 17)) { + if (skb_pad(skb, 17 - skb->len)) + return NETDEV_TX_OK; + skb->len = 17; + skb_set_tail_pointer(skb, 17); + } + + tx_ring = ring ? ring : adapter->tx_ring[skb->queue_mapping]; + return ixgbe_xmit_frame_ring(skb, adapter, tx_ring); } +static netdev_tx_t ixgbe_xmit_frame(struct sk_buff *skb, + struct net_device *netdev) +{ + return __ixgbe_xmit_frame(skb, netdev, NULL); +} + /** * ixgbe_set_mac - Change the Ethernet Address of the NIC * @netdev: network interface device structure @@ -6913,17 +7319,17 @@ static int ixgbe_set_mac(struct net_device *netdev, void *p) struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; struct sockaddr *addr = p; + int ret; if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; + ixgbe_del_mac_filter(adapter, hw->mac.addr, VMDQ_P(0)); memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len); memcpy(hw->mac.addr, addr->sa_data, netdev->addr_len); - hw->mac.ops.set_rar(hw, 0, hw->mac.addr, adapter->num_vfs, - IXGBE_RAH_AV); - - return 0; + ret = ixgbe_add_mac_filter(adapter, hw->mac.addr, VMDQ_P(0)); + return ret > 0 ? 0 : ret; } static int @@ -6957,7 +7363,14 @@ static int ixgbe_ioctl(struct net_device *netdev, struct ifreq *req, int cmd) { struct ixgbe_adapter *adapter = netdev_priv(netdev); - return mdio_mii_ioctl(&adapter->hw.phy.mdio, if_mii(req), cmd); + switch (cmd) { + case SIOCSHWTSTAMP: + return ixgbe_ptp_set_ts_config(adapter, req); + case SIOCGHWTSTAMP: + return ixgbe_ptp_get_ts_config(adapter, req); + default: + return mdio_mii_ioctl(&adapter->hw.phy.mdio, if_mii(req), cmd); + } } /** @@ -6971,12 +7384,15 @@ static int ixgbe_add_sanmac_netdev(struct net_device *dev) { int err = 0; struct ixgbe_adapter *adapter = netdev_priv(dev); - struct ixgbe_mac_info *mac = &adapter->hw.mac; + struct ixgbe_hw *hw = &adapter->hw; - if (is_valid_ether_addr(mac->san_addr)) { + if (is_valid_ether_addr(hw->mac.san_addr)) { rtnl_lock(); - err = dev_addr_add(dev, mac->san_addr, NETDEV_HW_ADDR_T_SAN); + err = dev_addr_add(dev, hw->mac.san_addr, NETDEV_HW_ADDR_T_SAN); rtnl_unlock(); + + /* update SAN MAC vmdq pool selection */ + hw->mac.ops.set_vmdq_san_mac(hw, VMDQ_P(0)); } return err; } @@ -7019,18 +7435,15 @@ static void ixgbe_netpoll(struct net_device *netdev) adapter->flags |= IXGBE_FLAG_IN_NETPOLL; if (adapter->flags & IXGBE_FLAG_MSIX_ENABLED) { - int num_q_vectors = adapter->num_msix_vectors - NON_Q_VECTORS; - for (i = 0; i < num_q_vectors; i++) { - struct ixgbe_q_vector *q_vector = adapter->q_vector[i]; - ixgbe_msix_clean_rings(0, q_vector); - } + for (i = 0; i < adapter->num_q_vectors; i++) + ixgbe_msix_clean_rings(0, adapter->q_vector[i]); } else { ixgbe_intr(adapter->pdev->irq, netdev); } adapter->flags &= ~IXGBE_FLAG_IN_NETPOLL; } -#endif +#endif static struct rtnl_link_stats64 *ixgbe_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) { @@ -7045,10 +7458,10 @@ static struct rtnl_link_stats64 *ixgbe_get_stats64(struct net_device *netdev, if (ring) { do { - start = u64_stats_fetch_begin_bh(&ring->syncp); + start = u64_stats_fetch_begin_irq(&ring->syncp); packets = ring->stats.packets; bytes = ring->stats.bytes; - } while (u64_stats_fetch_retry_bh(&ring->syncp, start)); + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); stats->rx_packets += packets; stats->rx_bytes += bytes; } @@ -7061,10 +7474,10 @@ static struct rtnl_link_stats64 *ixgbe_get_stats64(struct net_device *netdev, if (ring) { do { - start = u64_stats_fetch_begin_bh(&ring->syncp); + start = u64_stats_fetch_begin_irq(&ring->syncp); packets = ring->stats.packets; bytes = ring->stats.bytes; - } while (u64_stats_fetch_retry_bh(&ring->syncp, start)); + } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); stats->tx_packets += packets; stats->tx_bytes += bytes; } @@ -7079,8 +7492,10 @@ static struct rtnl_link_stats64 *ixgbe_get_stats64(struct net_device *netdev, return stats; } -/* ixgbe_validate_rtr - verify 802.1Qp to Rx packet buffer mapping is valid. - * #adapter: pointer to ixgbe_adapter +#ifdef CONFIG_IXGBE_DCB +/** + * ixgbe_validate_rtr - verify 802.1Qp to Rx packet buffer mapping is valid. + * @adapter: pointer to ixgbe_adapter * @tc: number of traffic classes currently enabled * * Configure a valid 802.1Qp to Rx packet buffer mapping ie confirm @@ -7115,9 +7530,34 @@ static void ixgbe_validate_rtr(struct ixgbe_adapter *adapter, u8 tc) return; } +/** + * ixgbe_set_prio_tc_map - Configure netdev prio tc map + * @adapter: Pointer to adapter struct + * + * Populate the netdev user priority to tc map + */ +static void ixgbe_set_prio_tc_map(struct ixgbe_adapter *adapter) +{ + struct net_device *dev = adapter->netdev; + struct ixgbe_dcb_config *dcb_cfg = &adapter->dcb_cfg; + struct ieee_ets *ets = adapter->ixgbe_ieee_ets; + u8 prio; -/* ixgbe_setup_tc - routine to configure net_device for multiple traffic - * classes. + for (prio = 0; prio < MAX_USER_PRIORITY; prio++) { + u8 tc = 0; + + if (adapter->dcbx_cap & DCB_CAP_DCBX_VER_CEE) + tc = ixgbe_dcb_get_tc_from_up(dcb_cfg, 0, prio); + else if (ets) + tc = ets->prio_tc[prio]; + + netdev_set_prio_tc_map(dev, prio, tc); + } +} + +#endif /* CONFIG_IXGBE_DCB */ +/** + * ixgbe_setup_tc - configure net_device for multiple traffic classes * * @netdev: net device to configure * @tc: number of traffic classes to enable @@ -7126,18 +7566,18 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc) { struct ixgbe_adapter *adapter = netdev_priv(dev); struct ixgbe_hw *hw = &adapter->hw; - - /* Multiple traffic classes requires multiple queues */ - if (!(adapter->flags & IXGBE_FLAG_MSIX_ENABLED)) { - e_err(drv, "Enable failed, needs MSI-X\n"); - return -EINVAL; - } + bool pools; /* Hardware supports up to 8 traffic classes */ if (tc > adapter->dcb_cfg.num_tcs.pg_tcs || - (hw->mac.type == ixgbe_mac_82598EB && tc < MAX_TRAFFIC_CLASS)) + (hw->mac.type == ixgbe_mac_82598EB && + tc < MAX_TRAFFIC_CLASS)) return -EINVAL; + pools = (find_first_zero_bit(&adapter->fwd_bitmask, 32) > 1); + if (tc && pools && adapter->num_rx_pools > IXGBE_MAX_DCBMACVLANS) + return -EBUSY; + /* Hardware has to reinitialize queues and interrupts to * match packet buffer alignment. Unfortunately, the * hardware is not flexible enough to do this dynamically. @@ -7146,35 +7586,51 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc) ixgbe_close(dev); ixgbe_clear_interrupt_scheme(adapter); +#ifdef CONFIG_IXGBE_DCB if (tc) { netdev_set_num_tc(dev, tc); - adapter->last_lfc_mode = adapter->hw.fc.current_mode; + ixgbe_set_prio_tc_map(adapter); adapter->flags |= IXGBE_FLAG_DCB_ENABLED; - adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; - if (adapter->hw.mac.type == ixgbe_mac_82598EB) + if (adapter->hw.mac.type == ixgbe_mac_82598EB) { + adapter->last_lfc_mode = adapter->hw.fc.requested_mode; adapter->hw.fc.requested_mode = ixgbe_fc_none; + } } else { netdev_reset_tc(dev); - adapter->hw.fc.requested_mode = adapter->last_lfc_mode; + if (adapter->hw.mac.type == ixgbe_mac_82598EB) + adapter->hw.fc.requested_mode = adapter->last_lfc_mode; adapter->flags &= ~IXGBE_FLAG_DCB_ENABLED; - adapter->flags |= IXGBE_FLAG_FDIR_HASH_CAPABLE; adapter->temp_dcb_cfg.pfc_mode_enable = false; adapter->dcb_cfg.pfc_mode_enable = false; } - ixgbe_init_interrupt_scheme(adapter); ixgbe_validate_rtr(adapter, tc); + +#endif /* CONFIG_IXGBE_DCB */ + ixgbe_init_interrupt_scheme(adapter); + if (netif_running(dev)) - ixgbe_open(dev); + return ixgbe_open(dev); return 0; } +#ifdef CONFIG_PCI_IOV +void ixgbe_sriov_reinit(struct ixgbe_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + + rtnl_lock(); + ixgbe_setup_tc(netdev, netdev_get_num_tc(netdev)); + rtnl_unlock(); +} + +#endif void ixgbe_do_reset(struct net_device *netdev) { struct ixgbe_adapter *adapter = netdev_priv(netdev); @@ -7186,59 +7642,42 @@ void ixgbe_do_reset(struct net_device *netdev) } static netdev_features_t ixgbe_fix_features(struct net_device *netdev, - netdev_features_t data) + netdev_features_t features) { struct ixgbe_adapter *adapter = netdev_priv(netdev); -#ifdef CONFIG_DCB - if (adapter->flags & IXGBE_FLAG_DCB_ENABLED) - data &= ~NETIF_F_HW_VLAN_RX; -#endif - - /* return error if RXHASH is being enabled when RSS is not supported */ - if (!(adapter->flags & IXGBE_FLAG_RSS_ENABLED)) - data &= ~NETIF_F_RXHASH; - /* If Rx checksum is disabled, then RSC/LRO should also be disabled */ - if (!(data & NETIF_F_RXCSUM)) - data &= ~NETIF_F_LRO; + if (!(features & NETIF_F_RXCSUM)) + features &= ~NETIF_F_LRO; - /* Turn off LRO if not RSC capable or invalid ITR settings */ - if (!(adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE)) { - data &= ~NETIF_F_LRO; - } else if (!(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) && - (adapter->rx_itr_setting != 1 && - adapter->rx_itr_setting > IXGBE_MAX_RSC_INT_RATE)) { - data &= ~NETIF_F_LRO; - e_info(probe, "rx-usecs set too low, not enabling RSC\n"); - } + /* Turn off LRO if not RSC capable */ + if (!(adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE)) + features &= ~NETIF_F_LRO; - return data; + return features; } static int ixgbe_set_features(struct net_device *netdev, - netdev_features_t data) + netdev_features_t features) { struct ixgbe_adapter *adapter = netdev_priv(netdev); + netdev_features_t changed = netdev->features ^ features; bool need_reset = false; - /* If Rx checksum is disabled, then RSC/LRO should also be disabled */ - if (!(data & NETIF_F_RXCSUM)) - adapter->flags &= ~IXGBE_FLAG_RX_CSUM_ENABLED; - else - adapter->flags |= IXGBE_FLAG_RX_CSUM_ENABLED; - /* Make sure RSC matches LRO, reset if change */ - if (!!(data & NETIF_F_LRO) != - !!(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)) { - adapter->flags2 ^= IXGBE_FLAG2_RSC_ENABLED; - switch (adapter->hw.mac.type) { - case ixgbe_mac_X540: - case ixgbe_mac_82599EB: + if (!(features & NETIF_F_LRO)) { + if (adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED) need_reset = true; - break; - default: - break; + adapter->flags2 &= ~IXGBE_FLAG2_RSC_ENABLED; + } else if ((adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE) && + !(adapter->flags2 & IXGBE_FLAG2_RSC_ENABLED)) { + if (adapter->rx_itr_setting == 1 || + adapter->rx_itr_setting > IXGBE_MIN_RSC_ITR) { + adapter->flags2 |= IXGBE_FLAG2_RSC_ENABLED; + need_reset = true; + } else if ((changed ^ features) & NETIF_F_LRO) { + e_info(probe, "rx-usecs set too low, " + "disabling RSC\n"); } } @@ -7246,27 +7685,235 @@ static int ixgbe_set_features(struct net_device *netdev, * Check if Flow Director n-tuple support was enabled or disabled. If * the state changed, we need to reset. */ - if (!(adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE)) { + switch (features & NETIF_F_NTUPLE) { + case NETIF_F_NTUPLE: /* turn off ATR, enable perfect filters and reset */ - if (data & NETIF_F_NTUPLE) { - adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; - adapter->flags |= IXGBE_FLAG_FDIR_PERFECT_CAPABLE; + if (!(adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE)) need_reset = true; - } - } else if (!(data & NETIF_F_NTUPLE)) { - /* turn off Flow Director, set ATR and reset */ + + adapter->flags &= ~IXGBE_FLAG_FDIR_HASH_CAPABLE; + adapter->flags |= IXGBE_FLAG_FDIR_PERFECT_CAPABLE; + break; + default: + /* turn off perfect filters, enable ATR and reset */ + if (adapter->flags & IXGBE_FLAG_FDIR_PERFECT_CAPABLE) + need_reset = true; + adapter->flags &= ~IXGBE_FLAG_FDIR_PERFECT_CAPABLE; - if ((adapter->flags & IXGBE_FLAG_RSS_ENABLED) && - !(adapter->flags & IXGBE_FLAG_DCB_ENABLED)) - adapter->flags |= IXGBE_FLAG_FDIR_HASH_CAPABLE; - need_reset = true; + + /* We cannot enable ATR if SR-IOV is enabled */ + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) + break; + + /* We cannot enable ATR if we have 2 or more traffic classes */ + if (netdev_get_num_tc(netdev) > 1) + break; + + /* We cannot enable ATR if RSS is disabled */ + if (adapter->ring_feature[RING_F_RSS].limit <= 1) + break; + + /* A sample rate of 0 indicates ATR disabled */ + if (!adapter->atr_sample_rate) + break; + + adapter->flags |= IXGBE_FLAG_FDIR_HASH_CAPABLE; + break; } + if (features & NETIF_F_HW_VLAN_CTAG_RX) + ixgbe_vlan_strip_enable(adapter); + else + ixgbe_vlan_strip_disable(adapter); + + if (changed & NETIF_F_RXALL) + need_reset = true; + + netdev->features = features; if (need_reset) ixgbe_do_reset(netdev); return 0; +} + +static int ixgbe_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], + struct net_device *dev, + const unsigned char *addr, + u16 flags) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + int err; + + if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) + return ndo_dflt_fdb_add(ndm, tb, dev, addr, flags); + + /* Hardware does not support aging addresses so if a + * ndm_state is given only allow permanent addresses + */ + if (ndm->ndm_state && !(ndm->ndm_state & NUD_PERMANENT)) { + pr_info("%s: FDB only supports static addresses\n", + ixgbe_driver_name); + return -EINVAL; + } + + if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) { + u32 rar_uc_entries = IXGBE_MAX_PF_MACVLANS; + + if (netdev_uc_count(dev) < rar_uc_entries) + err = dev_uc_add_excl(dev, addr); + else + err = -ENOMEM; + } else if (is_multicast_ether_addr(addr)) { + err = dev_mc_add_excl(dev, addr); + } else { + err = -EINVAL; + } + + /* Only return duplicate errors if NLM_F_EXCL is set */ + if (err == -EEXIST && !(flags & NLM_F_EXCL)) + err = 0; + + return err; +} + +static int ixgbe_ndo_bridge_setlink(struct net_device *dev, + struct nlmsghdr *nlh) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + struct nlattr *attr, *br_spec; + int rem; + + if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) + return -EOPNOTSUPP; + + br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); + + nla_for_each_nested(attr, br_spec, rem) { + __u16 mode; + u32 reg = 0; + + if (nla_type(attr) != IFLA_BRIDGE_MODE) + continue; + + mode = nla_get_u16(attr); + if (mode == BRIDGE_MODE_VEPA) { + reg = 0; + adapter->flags2 &= ~IXGBE_FLAG2_BRIDGE_MODE_VEB; + } else if (mode == BRIDGE_MODE_VEB) { + reg = IXGBE_PFDTXGSWC_VT_LBEN; + adapter->flags2 |= IXGBE_FLAG2_BRIDGE_MODE_VEB; + } else + return -EINVAL; + + IXGBE_WRITE_REG(&adapter->hw, IXGBE_PFDTXGSWC, reg); + + e_info(drv, "enabling bridge mode: %s\n", + mode == BRIDGE_MODE_VEPA ? "VEPA" : "VEB"); + } + + return 0; +} + +static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, + struct net_device *dev, + u32 filter_mask) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + u16 mode; + + if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) + return 0; + + if (adapter->flags2 & IXGBE_FLAG2_BRIDGE_MODE_VEB) + mode = BRIDGE_MODE_VEB; + else + mode = BRIDGE_MODE_VEPA; + return ndo_dflt_bridge_getlink(skb, pid, seq, dev, mode); +} + +static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev) +{ + struct ixgbe_fwd_adapter *fwd_adapter = NULL; + struct ixgbe_adapter *adapter = netdev_priv(pdev); + unsigned int limit; + int pool, err; + +#ifdef CONFIG_RPS + if (vdev->num_rx_queues != vdev->num_tx_queues) { + netdev_info(pdev, "%s: Only supports a single queue count for TX and RX\n", + vdev->name); + return ERR_PTR(-EINVAL); + } +#endif + /* Check for hardware restriction on number of rx/tx queues */ + if (vdev->num_tx_queues > IXGBE_MAX_L2A_QUEUES || + vdev->num_tx_queues == IXGBE_BAD_L2A_QUEUE) { + netdev_info(pdev, + "%s: Supports RX/TX Queue counts 1,2, and 4\n", + pdev->name); + return ERR_PTR(-EINVAL); + } + + if (((adapter->flags & IXGBE_FLAG_DCB_ENABLED) && + adapter->num_rx_pools > IXGBE_MAX_DCBMACVLANS - 1) || + (adapter->num_rx_pools > IXGBE_MAX_MACVLANS)) + return ERR_PTR(-EBUSY); + + fwd_adapter = kcalloc(1, sizeof(struct ixgbe_fwd_adapter), GFP_KERNEL); + if (!fwd_adapter) + return ERR_PTR(-ENOMEM); + + pool = find_first_zero_bit(&adapter->fwd_bitmask, 32); + adapter->num_rx_pools++; + set_bit(pool, &adapter->fwd_bitmask); + limit = find_last_bit(&adapter->fwd_bitmask, 32); + + /* Enable VMDq flag so device will be set in VM mode */ + adapter->flags |= IXGBE_FLAG_VMDQ_ENABLED | IXGBE_FLAG_SRIOV_ENABLED; + adapter->ring_feature[RING_F_VMDQ].limit = limit + 1; + adapter->ring_feature[RING_F_RSS].limit = vdev->num_tx_queues; + + /* Force reinit of ring allocation with VMDQ enabled */ + err = ixgbe_setup_tc(pdev, netdev_get_num_tc(pdev)); + if (err) + goto fwd_add_err; + fwd_adapter->pool = pool; + fwd_adapter->real_adapter = adapter; + err = ixgbe_fwd_ring_up(vdev, fwd_adapter); + if (err) + goto fwd_add_err; + netif_tx_start_all_queues(vdev); + return fwd_adapter; +fwd_add_err: + /* unwind counter and free adapter struct */ + netdev_info(pdev, + "%s: dfwd hardware acceleration failed\n", vdev->name); + clear_bit(pool, &adapter->fwd_bitmask); + adapter->num_rx_pools--; + kfree(fwd_adapter); + return ERR_PTR(err); +} + +static void ixgbe_fwd_del(struct net_device *pdev, void *priv) +{ + struct ixgbe_fwd_adapter *fwd_adapter = priv; + struct ixgbe_adapter *adapter = fwd_adapter->real_adapter; + unsigned int limit; + + clear_bit(fwd_adapter->pool, &adapter->fwd_bitmask); + adapter->num_rx_pools--; + + limit = find_last_bit(&adapter->fwd_bitmask, 32); + adapter->ring_feature[RING_F_VMDQ].limit = limit + 1; + ixgbe_fwd_ring_down(fwd_adapter->netdev, fwd_adapter); + ixgbe_setup_tc(pdev, netdev_get_num_tc(pdev)); + netdev_dbg(pdev, "pool %i:%i queues %i:%i VSI bitmask %lx\n", + fwd_adapter->pool, adapter->num_rx_pools, + fwd_adapter->rx_base_queue, + fwd_adapter->rx_base_queue + adapter->num_rx_queues_per_pool, + adapter->fwd_bitmask); + kfree(fwd_adapter); } static const struct net_device_ops ixgbe_netdev_ops = { @@ -7274,7 +7921,7 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_stop = ixgbe_close, .ndo_start_xmit = ixgbe_xmit_frame, .ndo_select_queue = ixgbe_select_queue, - .ndo_set_rx_mode = ixgbe_set_rx_mode, + .ndo_set_rx_mode = ixgbe_set_rx_mode, .ndo_validate_addr = eth_validate_addr, .ndo_set_mac_address = ixgbe_set_mac, .ndo_change_mtu = ixgbe_change_mtu, @@ -7284,14 +7931,19 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_do_ioctl = ixgbe_ioctl, .ndo_set_vf_mac = ixgbe_ndo_set_vf_mac, .ndo_set_vf_vlan = ixgbe_ndo_set_vf_vlan, - .ndo_set_vf_tx_rate = ixgbe_ndo_set_vf_bw, - .ndo_set_vf_spoofchk = ixgbe_ndo_set_vf_spoofchk, + .ndo_set_vf_rate = ixgbe_ndo_set_vf_bw, + .ndo_set_vf_spoofchk = ixgbe_ndo_set_vf_spoofchk, .ndo_get_vf_config = ixgbe_ndo_get_vf_config, .ndo_get_stats64 = ixgbe_get_stats64, +#ifdef CONFIG_IXGBE_DCB .ndo_setup_tc = ixgbe_setup_tc, +#endif #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = ixgbe_netpoll, #endif +#ifdef CONFIG_NET_RX_BUSY_POLL + .ndo_busy_poll = ixgbe_low_latency_recv, +#endif #ifdef IXGBE_FCOE .ndo_fcoe_ddp_setup = ixgbe_fcoe_ddp_get, .ndo_fcoe_ddp_target = ixgbe_fcoe_ddp_target, @@ -7303,25 +7955,109 @@ static const struct net_device_ops ixgbe_netdev_ops = { #endif /* IXGBE_FCOE */ .ndo_set_features = ixgbe_set_features, .ndo_fix_features = ixgbe_fix_features, + .ndo_fdb_add = ixgbe_ndo_fdb_add, + .ndo_bridge_setlink = ixgbe_ndo_bridge_setlink, + .ndo_bridge_getlink = ixgbe_ndo_bridge_getlink, + .ndo_dfwd_add_station = ixgbe_fwd_add, + .ndo_dfwd_del_station = ixgbe_fwd_del, }; -static void __devinit ixgbe_probe_vf(struct ixgbe_adapter *adapter, - const struct ixgbe_info *ii) +/** + * ixgbe_enumerate_functions - Get the number of ports this device has + * @adapter: adapter structure + * + * This function enumerates the phsyical functions co-located on a single slot, + * in order to determine how many ports a device has. This is most useful in + * determining the required GT/s of PCIe bandwidth necessary for optimal + * performance. + **/ +static inline int ixgbe_enumerate_functions(struct ixgbe_adapter *adapter) +{ + struct list_head *entry; + int physfns = 0; + + /* Some cards can not use the generic count PCIe functions method, + * because they are behind a parent switch, so we hardcode these with + * the correct number of functions. + */ + if (ixgbe_pcie_from_parent(&adapter->hw)) { + physfns = 4; + } else { + list_for_each(entry, &adapter->pdev->bus_list) { + struct pci_dev *pdev = + list_entry(entry, struct pci_dev, bus_list); + /* don't count virtual functions */ + if (!pdev->is_virtfn) + physfns++; + } + } + + return physfns; +} + +/** + * ixgbe_wol_supported - Check whether device supports WoL + * @hw: hw specific details + * @device_id: the device ID + * @subdev_id: the subsystem device ID + * + * This function is used by probe and ethtool to determine + * which devices have WoL support + * + **/ +int ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id, + u16 subdevice_id) { -#ifdef CONFIG_PCI_IOV struct ixgbe_hw *hw = &adapter->hw; + u16 wol_cap = adapter->eeprom_cap & IXGBE_DEVICE_CAPS_WOL_MASK; + int is_wol_supported = 0; - if (hw->mac.type == ixgbe_mac_82598EB) - return; + switch (device_id) { + case IXGBE_DEV_ID_82599_SFP: + /* Only these subdevices could supports WOL */ + switch (subdevice_id) { + case IXGBE_SUBDEV_ID_82599_SFP_WOL0: + case IXGBE_SUBDEV_ID_82599_560FLR: + /* only support first port */ + if (hw->bus.func != 0) + break; + case IXGBE_SUBDEV_ID_82599_SP_560FLR: + case IXGBE_SUBDEV_ID_82599_SFP: + case IXGBE_SUBDEV_ID_82599_RNDC: + case IXGBE_SUBDEV_ID_82599_ECNA_DP: + case IXGBE_SUBDEV_ID_82599_LOM_SFP: + is_wol_supported = 1; + break; + } + break; + case IXGBE_DEV_ID_82599EN_SFP: + /* Only this subdevice supports WOL */ + switch (subdevice_id) { + case IXGBE_SUBDEV_ID_82599EN_SFP_OCP1: + is_wol_supported = 1; + break; + } + break; + case IXGBE_DEV_ID_82599_COMBO_BACKPLANE: + /* All except this subdevice support WOL */ + if (subdevice_id != IXGBE_SUBDEV_ID_82599_KX4_KR_MEZZ) + is_wol_supported = 1; + break; + case IXGBE_DEV_ID_82599_KX4: + is_wol_supported = 1; + break; + case IXGBE_DEV_ID_X540T: + case IXGBE_DEV_ID_X540T1: + /* check eeprom to see if enabled wol */ + if ((wol_cap == IXGBE_DEVICE_CAPS_WOL_PORT0_1) || + ((wol_cap == IXGBE_DEVICE_CAPS_WOL_PORT0) && + (hw->bus.func == 0))) { + is_wol_supported = 1; + } + break; + } - /* The 82599 supports up to 64 VFs per physical function - * but this implementation limits allocation to 63 so that - * basic networking resources are still available to the - * physical function - */ - adapter->num_vfs = (max_vfs > 63) ? 63 : max_vfs; - ixgbe_enable_sriov(adapter, ii); -#endif /* CONFIG_PCI_IOV */ + return is_wol_supported; } /** @@ -7335,22 +8071,20 @@ static void __devinit ixgbe_probe_vf(struct ixgbe_adapter *adapter, * The OS initialization, configuring of the adapter private structure, * and a hardware reset occur. **/ -static int __devinit ixgbe_probe(struct pci_dev *pdev, - const struct pci_device_id *ent) +static int ixgbe_probe(struct pci_dev *pdev, const struct pci_device_id *ent) { struct net_device *netdev; struct ixgbe_adapter *adapter = NULL; struct ixgbe_hw *hw; const struct ixgbe_info *ii = ixgbe_info_tbl[ent->driver_data]; static int cards_found; - int i, err, pci_using_dac; + int i, err, pci_using_dac, expected_gts; + unsigned int indices = MAX_TX_QUEUES; u8 part_str[IXGBE_PBANUM_LENGTH]; - unsigned int indices = num_possible_cpus(); #ifdef IXGBE_FCOE u16 device_caps; #endif u32 eec; - u16 wol_cap; /* Catch broken hardware that put the wrong VF device ID in * the PCIe SR-IOV capability. @@ -7365,19 +8099,14 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, if (err) return err; - if (!dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)) && - !dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64))) { + if (!dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) { pci_using_dac = 1; } else { - err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); + err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32)); if (err) { - err = dma_set_coherent_mask(&pdev->dev, - DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, - "No usable DMA configuration, aborting\n"); - goto err_dma; - } + dev_err(&pdev->dev, + "No usable DMA configuration, aborting\n"); + goto err_dma; } pci_using_dac = 0; } @@ -7395,19 +8124,15 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, pci_set_master(pdev); pci_save_state(pdev); + if (ii->mac == ixgbe_mac_82598EB) { #ifdef CONFIG_IXGBE_DCB - indices *= MAX_TRAFFIC_CLASS; + /* 8 TC w/ 4 queues per TC */ + indices = 4 * MAX_TRAFFIC_CLASS; +#else + indices = IXGBE_MAX_RSS_INDICES; #endif + } - if (ii->mac == ixgbe_mac_82598EB) - indices = min_t(unsigned int, indices, IXGBE_MAX_RSS_INDICES); - else - indices = min_t(unsigned int, indices, IXGBE_MAX_FDIR_INDICES); - -#ifdef IXGBE_FCOE - indices += min_t(unsigned int, num_possible_cpus(), - IXGBE_MAX_FCOE_INDICES); -#endif netdev = alloc_etherdev_mq(sizeof(struct ixgbe_adapter), indices); if (!netdev) { err = -ENOMEM; @@ -7423,20 +8148,16 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, adapter->pdev = pdev; hw = &adapter->hw; hw->back = adapter; - adapter->msg_enable = (1 << DEFAULT_DEBUG_LEVEL_SHIFT) - 1; + adapter->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE); hw->hw_addr = ioremap(pci_resource_start(pdev, 0), pci_resource_len(pdev, 0)); + adapter->io_addr = hw->hw_addr; if (!hw->hw_addr) { err = -EIO; goto err_ioremap; } - for (i = 1; i <= 5; i++) { - if (pci_resource_len(pdev, i) == 0) - continue; - } - netdev->netdev_ops = &ixgbe_netdev_ops; ixgbe_set_ethtool_ops(netdev); netdev->watchdog_timeo = 5 * HZ; @@ -7451,6 +8172,10 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, /* EEPROM */ memcpy(&hw->eeprom.ops, ii->eeprom_ops, sizeof(hw->eeprom.ops)); eec = IXGBE_READ_REG(hw, IXGBE_EEC); + if (ixgbe_removed(hw->hw_addr)) { + err = -EIO; + goto err_ioremap; + } /* If EEPROM is valid (bit 8 = 1), use default otherwise use bit bang */ if (!(eec & (1 << 8))) hw->eeprom.ops.read = &ixgbe_read_eeprom_bit_bang_generic; @@ -7493,6 +8218,9 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, e_crit(probe, "Fan has stopped, replace the adapter\n"); } + if (allow_unsupported_sfp) + hw->allow_unsupported_sfp = allow_unsupported_sfp; + /* reset_hw fills in the perm_addr as well */ hw->phy.reset_if_overtemp = true; err = hw->mac.ops.reset_hw(hw); @@ -7501,30 +8229,38 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, hw->mac.type == ixgbe_mac_82598EB) { err = 0; } else if (err == IXGBE_ERR_SFP_NOT_SUPPORTED) { - e_dev_err("failed to load because an unsupported SFP+ " - "module type was detected.\n"); - e_dev_err("Reload the driver after installing a supported " - "module.\n"); + e_dev_err("failed to load because an unsupported SFP+ or QSFP module type was detected.\n"); + e_dev_err("Reload the driver after installing a supported module.\n"); goto err_sw_init; } else if (err) { e_dev_err("HW Init failed: %d\n", err); goto err_sw_init; } - ixgbe_probe_vf(adapter, ii); +#ifdef CONFIG_PCI_IOV + /* SR-IOV not supported on the 82598 */ + if (adapter->hw.mac.type == ixgbe_mac_82598EB) + goto skip_sriov; + /* Mailbox */ + ixgbe_init_mbx_params_pf(hw); + memcpy(&hw->mbx.ops, ii->mbx_ops, sizeof(hw->mbx.ops)); + pci_sriov_set_totalvfs(pdev, IXGBE_MAX_VFS_DRV_LIMIT); + ixgbe_enable_sriov(adapter); +skip_sriov: +#endif netdev->features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | - NETIF_F_HW_VLAN_TX | - NETIF_F_HW_VLAN_RX | - NETIF_F_HW_VLAN_FILTER | + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_RXHASH | NETIF_F_RXCSUM; - netdev->hw_features = netdev->features; + netdev->hw_features = netdev->features | NETIF_F_HW_L2FW_DOFFLOAD; switch (adapter->hw.mac.type) { case ixgbe_mac_82599EB: @@ -7537,6 +8273,8 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, break; } + netdev->hw_features |= NETIF_F_RXALL; + netdev->vlan_features |= NETIF_F_TSO; netdev->vlan_features |= NETIF_F_TSO6; netdev->vlan_features |= NETIF_F_IP_CSUM; @@ -7544,10 +8282,7 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, netdev->vlan_features |= NETIF_F_SG; netdev->priv_flags |= IFF_UNICAST_FLT; - - if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) - adapter->flags &= ~(IXGBE_FLAG_RSS_ENABLED | - IXGBE_FLAG_DCB_ENABLED); + netdev->priv_flags |= IFF_SUPP_NOFCS; #ifdef CONFIG_IXGBE_DCB netdev->dcbnl_ops = &dcbnl_ops; @@ -7555,16 +8290,24 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, #ifdef IXGBE_FCOE if (adapter->flags & IXGBE_FLAG_FCOE_CAPABLE) { + unsigned int fcoe_l; + if (hw->mac.ops.get_device_caps) { hw->mac.ops.get_device_caps(hw, &device_caps); if (device_caps & IXGBE_DEVICE_CAPS_FCOE_OFFLOADS) adapter->flags &= ~IXGBE_FLAG_FCOE_CAPABLE; } - } - if (adapter->flags & IXGBE_FLAG_FCOE_CAPABLE) { - netdev->vlan_features |= NETIF_F_FCOE_CRC; - netdev->vlan_features |= NETIF_F_FSO; - netdev->vlan_features |= NETIF_F_FCOE_MTU; + + + fcoe_l = min_t(int, IXGBE_FCRETA_SIZE, num_online_cpus()); + adapter->ring_feature[RING_F_FCOE].limit = fcoe_l; + + netdev->features |= NETIF_F_FSO | + NETIF_F_FCOE_CRC; + + netdev->vlan_features |= NETIF_F_FSO | + NETIF_F_FCOE_CRC | + NETIF_F_FCOE_MTU; } #endif /* IXGBE_FCOE */ if (pci_using_dac) { @@ -7581,67 +8324,42 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, if (hw->eeprom.ops.validate_checksum(hw, NULL) < 0) { e_dev_err("The EEPROM Checksum Is Not Valid\n"); err = -EIO; - goto err_eeprom; + goto err_sw_init; } memcpy(netdev->dev_addr, hw->mac.perm_addr, netdev->addr_len); - memcpy(netdev->perm_addr, hw->mac.perm_addr, netdev->addr_len); - if (ixgbe_validate_mac_addr(netdev->perm_addr)) { + if (!is_valid_ether_addr(netdev->dev_addr)) { e_dev_err("invalid MAC address\n"); err = -EIO; - goto err_eeprom; + goto err_sw_init; } + ixgbe_mac_set_default_filter(adapter, hw->mac.perm_addr); + setup_timer(&adapter->service_timer, &ixgbe_service_timer, - (unsigned long) adapter); + (unsigned long) adapter); + if (ixgbe_removed(hw->hw_addr)) { + err = -EIO; + goto err_sw_init; + } INIT_WORK(&adapter->service_task, ixgbe_service_task); + set_bit(__IXGBE_SERVICE_INITED, &adapter->state); clear_bit(__IXGBE_SERVICE_SCHED, &adapter->state); err = ixgbe_init_interrupt_scheme(adapter); if (err) goto err_sw_init; - if (!(adapter->flags & IXGBE_FLAG_RSS_ENABLED)) { - netdev->hw_features &= ~NETIF_F_RXHASH; - netdev->features &= ~NETIF_F_RXHASH; - } - - /* WOL not supported for all but the following */ + /* WOL not supported for all devices */ adapter->wol = 0; - switch (pdev->device) { - case IXGBE_DEV_ID_82599_SFP: - /* Only these subdevice supports WOL */ - switch (pdev->subsystem_device) { - case IXGBE_SUBDEV_ID_82599_560FLR: - /* only support first port */ - if (hw->bus.func != 0) - break; - case IXGBE_SUBDEV_ID_82599_SFP: - adapter->wol = IXGBE_WUFC_MAG; - break; - } - break; - case IXGBE_DEV_ID_82599_COMBO_BACKPLANE: - /* All except this subdevice support WOL */ - if (pdev->subsystem_device != IXGBE_SUBDEV_ID_82599_KX4_KR_MEZZ) - adapter->wol = IXGBE_WUFC_MAG; - break; - case IXGBE_DEV_ID_82599_KX4: + hw->eeprom.ops.read(hw, 0x2c, &adapter->eeprom_cap); + hw->wol_enabled = ixgbe_wol_supported(adapter, pdev->device, + pdev->subsystem_device); + if (hw->wol_enabled) adapter->wol = IXGBE_WUFC_MAG; - break; - case IXGBE_DEV_ID_X540T: - /* Check eeprom to see if it is enabled */ - hw->eeprom.ops.read(hw, 0x2c, &adapter->eeprom_cap); - wol_cap = adapter->eeprom_cap & IXGBE_DEVICE_CAPS_WOL_MASK; - if ((wol_cap == IXGBE_DEVICE_CAPS_WOL_PORT0_1) || - ((wol_cap == IXGBE_DEVICE_CAPS_WOL_PORT0) && - (hw->bus.func == 0))) - adapter->wol = IXGBE_WUFC_MAG; - break; - } device_set_wakeup_enable(&adapter->pdev->dev, adapter->wol); /* save off EEPROM version number */ @@ -7650,17 +8368,23 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, /* pick up the PCI bus settings for reporting later */ hw->mac.ops.get_bus_info(hw); + if (ixgbe_pcie_from_parent(hw)) + ixgbe_get_parent_bus_info(adapter); - /* print bus type/speed/width info */ - e_dev_info("(PCI Express:%s:%s) %pM\n", - (hw->bus.speed == ixgbe_bus_speed_5000 ? "5.0GT/s" : - hw->bus.speed == ixgbe_bus_speed_2500 ? "2.5GT/s" : - "Unknown"), - (hw->bus.width == ixgbe_bus_width_pcie_x8 ? "Width x8" : - hw->bus.width == ixgbe_bus_width_pcie_x4 ? "Width x4" : - hw->bus.width == ixgbe_bus_width_pcie_x1 ? "Width x1" : - "Unknown"), - netdev->dev_addr); + /* calculate the expected PCIe bandwidth required for optimal + * performance. Note that some older parts will never have enough + * bandwidth due to being older generation PCIe parts. We clamp these + * parts to ensure no warning is displayed if it can't be fixed. + */ + switch (hw->mac.type) { + case ixgbe_mac_82598EB: + expected_gts = min(ixgbe_enumerate_functions(adapter) * 10, 16); + break; + default: + expected_gts = ixgbe_enumerate_functions(adapter) * 10; + break; + } + ixgbe_check_minimum_link(adapter, expected_gts); err = ixgbe_read_pba_string_generic(hw, part_str, IXGBE_PBANUM_LENGTH); if (err) @@ -7668,21 +8392,15 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, if (ixgbe_is_sfp(hw) && hw->phy.sfp_type != ixgbe_sfp_type_not_present) e_dev_info("MAC: %d, PHY: %d, SFP+: %d, PBA No: %s\n", hw->mac.type, hw->phy.type, hw->phy.sfp_type, - part_str); + part_str); else e_dev_info("MAC: %d, PHY: %d, PBA No: %s\n", hw->mac.type, hw->phy.type, part_str); - if (hw->bus.width <= ixgbe_bus_width_pcie_x4) { - e_dev_warn("PCI-Express bandwidth available for this card is " - "not sufficient for optimal performance.\n"); - e_dev_warn("For optimal performance a x8 PCI-Express slot " - "is required.\n"); - } + e_dev_info("%pM\n", netdev->dev_addr); /* reset the hardware with the new settings */ err = hw->mac.ops.start_hw(hw); - if (err == IXGBE_ERR_EEPROM_VERSION) { /* We are running on a pre-production device, log a warning */ e_dev_warn("This device is a pre-production adapter/LOM. " @@ -7697,11 +8415,8 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, if (err) goto err_register; - /* 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)))) + /* power down the optics for 82599 SFP+ fiber */ + if (hw->mac.ops.disable_tx_laser) hw->mac.ops.disable_tx_laser(hw); /* carrier off reporting is important to ethtool even BEFORE open */ @@ -7731,17 +8446,30 @@ static int __devinit ixgbe_probe(struct pci_dev *pdev, e_dev_info("%s\n", ixgbe_default_device_descr); cards_found++; + +#ifdef CONFIG_IXGBE_HWMON + if (ixgbe_sysfs_init(adapter)) + e_err(probe, "failed to allocate sysfs resources\n"); +#endif /* CONFIG_IXGBE_HWMON */ + + ixgbe_dbg_adapter_init(adapter); + + /* setup link for SFP devices with MNG FW, else wait for IXGBE_UP */ + if (ixgbe_mng_enabled(hw) && ixgbe_is_sfp(hw) && hw->mac.ops.setup_link) + hw->mac.ops.setup_link(hw, + IXGBE_LINK_SPEED_10GB_FULL | IXGBE_LINK_SPEED_1GB_FULL, + true); + return 0; err_register: ixgbe_release_hw_control(adapter); ixgbe_clear_interrupt_scheme(adapter); err_sw_init: -err_eeprom: - if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) - ixgbe_disable_sriov(adapter); + ixgbe_disable_sriov(adapter); adapter->flags2 &= ~IXGBE_FLAG2_SEARCH_FOR_SFP; - iounmap(hw->hw_addr); + iounmap(adapter->io_addr); + kfree(adapter->mac_table); err_ioremap: free_netdev(netdev); err_alloc_etherdev: @@ -7749,7 +8477,8 @@ err_alloc_etherdev: pci_select_bars(pdev, IORESOURCE_MEM)); err_pci_reg: err_dma: - pci_disable_device(pdev); + if (!test_and_set_bit(__IXGBE_DISABLED, &adapter->state)) + pci_disable_device(pdev); return err; } @@ -7762,14 +8491,17 @@ err_dma: * Hot-Plug event, or because the driver is going to be removed from * memory. **/ -static void __devexit ixgbe_remove(struct pci_dev *pdev) +static void ixgbe_remove(struct pci_dev *pdev) { struct ixgbe_adapter *adapter = pci_get_drvdata(pdev); struct net_device *netdev = adapter->netdev; - set_bit(__IXGBE_DOWN, &adapter->state); + ixgbe_dbg_adapter_exit(adapter); + + set_bit(__IXGBE_REMOVING, &adapter->state); cancel_work_sync(&adapter->service_task); + #ifdef CONFIG_IXGBE_DCA if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) { adapter->flags &= ~IXGBE_FLAG_DCA_ENABLED; @@ -7778,11 +8510,9 @@ static void __devexit ixgbe_remove(struct pci_dev *pdev) } #endif -#ifdef IXGBE_FCOE - if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED) - ixgbe_cleanup_fcoe(adapter); - -#endif /* IXGBE_FCOE */ +#ifdef CONFIG_IXGBE_HWMON + ixgbe_sysfs_exit(adapter); +#endif /* CONFIG_IXGBE_HWMON */ /* remove the added san mac */ ixgbe_del_sanmac_netdev(netdev); @@ -7790,29 +8520,36 @@ static void __devexit ixgbe_remove(struct pci_dev *pdev) if (netdev->reg_state == NETREG_REGISTERED) unregister_netdev(netdev); - if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) { - if (!(ixgbe_check_vf_assignment(adapter))) - ixgbe_disable_sriov(adapter); - else - e_dev_warn("Unloading driver while VFs are assigned " - "- VFs will not be deallocated\n"); - } - +#ifdef CONFIG_PCI_IOV + /* + * Only disable SR-IOV on unload if the user specified the now + * deprecated max_vfs module parameter. + */ + if (max_vfs) + ixgbe_disable_sriov(adapter); +#endif ixgbe_clear_interrupt_scheme(adapter); ixgbe_release_hw_control(adapter); - iounmap(adapter->hw.hw_addr); +#ifdef CONFIG_DCB + kfree(adapter->ixgbe_ieee_pfc); + kfree(adapter->ixgbe_ieee_ets); + +#endif + iounmap(adapter->io_addr); pci_release_selected_regions(pdev, pci_select_bars(pdev, IORESOURCE_MEM)); e_dev_info("complete\n"); + kfree(adapter->mac_table); free_netdev(netdev); pci_disable_pcie_error_reporting(pdev); - pci_disable_device(pdev); + if (!test_and_set_bit(__IXGBE_DISABLED, &adapter->state)) + pci_disable_device(pdev); } /** @@ -7830,6 +8567,7 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev, struct net_device *netdev = adapter->netdev; #ifdef CONFIG_PCI_IOV + struct ixgbe_hw *hw = &adapter->hw; struct pci_dev *bdev, *vfdev; u32 dw0, dw1, dw2, dw3; int vf, pos; @@ -7840,7 +8578,7 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev, goto skip_bad_vf_detection; bdev = pdev->bus->self; - while (bdev && (bdev->pcie_type != PCI_EXP_TYPE_ROOT_PORT)) + while (bdev && (pci_pcie_type(bdev) != PCI_EXP_TYPE_ROOT_PORT)) bdev = bdev->bus->self; if (!bdev) @@ -7850,10 +8588,12 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev, if (!pos) goto skip_bad_vf_detection; - pci_read_config_dword(bdev, pos + PCI_ERR_HEADER_LOG, &dw0); - pci_read_config_dword(bdev, pos + PCI_ERR_HEADER_LOG + 4, &dw1); - pci_read_config_dword(bdev, pos + PCI_ERR_HEADER_LOG + 8, &dw2); - pci_read_config_dword(bdev, pos + PCI_ERR_HEADER_LOG + 12, &dw3); + dw0 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG); + dw1 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG + 4); + dw2 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG + 8); + dw3 = ixgbe_read_pci_cfg_dword(hw, pos + PCI_ERR_HEADER_LOG + 12); + if (ixgbe_removed(hw->hw_addr)) + goto skip_bad_vf_detection; req_id = dw1 >> 16; /* On the 82599 if bit 7 of the requestor ID is set then it's a VF */ @@ -7882,11 +8622,11 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev, } /* Find the pci device of the offending VF */ - vfdev = pci_get_device(IXGBE_INTEL_VENDOR_ID, device_id, NULL); + vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, device_id, NULL); while (vfdev) { if (vfdev->devfn == (req_id & 0xFF)) break; - vfdev = pci_get_device(IXGBE_INTEL_VENDOR_ID, + vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, device_id, vfdev); } /* @@ -7897,6 +8637,8 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev, if (vfdev) { e_dev_err("Issuing VFLR to VF %d\n", vf); pci_write_config_dword(vfdev, 0xA8, 0x00008000); + /* Free device reference count */ + pci_dev_put(vfdev); } pci_cleanup_aer_uncorrect_error_status(pdev); @@ -7914,14 +8656,23 @@ static pci_ers_result_t ixgbe_io_error_detected(struct pci_dev *pdev, skip_bad_vf_detection: #endif /* CONFIG_PCI_IOV */ + if (!test_bit(__IXGBE_SERVICE_INITED, &adapter->state)) + return PCI_ERS_RESULT_DISCONNECT; + + rtnl_lock(); netif_device_detach(netdev); - if (state == pci_channel_io_perm_failure) + if (state == pci_channel_io_perm_failure) { + rtnl_unlock(); return PCI_ERS_RESULT_DISCONNECT; + } if (netif_running(netdev)) ixgbe_down(adapter); - pci_disable_device(pdev); + + if (!test_and_set_bit(__IXGBE_DISABLED, &adapter->state)) + pci_disable_device(pdev); + rtnl_unlock(); /* Request a slot reset. */ return PCI_ERS_RESULT_NEED_RESET; @@ -7943,6 +8694,9 @@ static pci_ers_result_t ixgbe_io_slot_reset(struct pci_dev *pdev) e_err(probe, "Cannot re-enable PCI device after reset.\n"); result = PCI_ERS_RESULT_DISCONNECT; } else { + smp_mb__before_atomic(); + clear_bit(__IXGBE_DISABLED, &adapter->state); + adapter->hw.hw_addr = adapter->io_addr; pci_set_master(pdev); pci_restore_state(pdev); pci_save_state(pdev); @@ -7990,7 +8744,7 @@ static void ixgbe_io_resume(struct pci_dev *pdev) netif_device_attach(netdev); } -static struct pci_error_handlers ixgbe_err_handler = { +static const struct pci_error_handlers ixgbe_err_handler = { .error_detected = ixgbe_io_error_detected, .slot_reset = ixgbe_io_slot_reset, .resume = ixgbe_io_resume, @@ -8000,12 +8754,13 @@ static struct pci_driver ixgbe_driver = { .name = ixgbe_driver_name, .id_table = ixgbe_pci_tbl, .probe = ixgbe_probe, - .remove = __devexit_p(ixgbe_remove), + .remove = ixgbe_remove, #ifdef CONFIG_PM .suspend = ixgbe_suspend, .resume = ixgbe_resume, #endif .shutdown = ixgbe_shutdown, + .sriov_configure = ixgbe_pci_sriov_configure, .err_handler = &ixgbe_err_handler }; @@ -8021,12 +8776,19 @@ static int __init ixgbe_init_module(void) pr_info("%s - version %s\n", ixgbe_driver_string, ixgbe_driver_version); pr_info("%s\n", ixgbe_copyright); + ixgbe_dbg_init(); + + ret = pci_register_driver(&ixgbe_driver); + if (ret) { + ixgbe_dbg_exit(); + return ret; + } + #ifdef CONFIG_IXGBE_DCA dca_register_notify(&dca_notifier); #endif - ret = pci_register_driver(&ixgbe_driver); - return ret; + return 0; } module_init(ixgbe_init_module); @@ -8043,6 +8805,9 @@ static void __exit ixgbe_exit_module(void) dca_unregister_notify(&dca_notifier); #endif pci_unregister_driver(&ixgbe_driver); + + ixgbe_dbg_exit(); + rcu_barrier(); /* Wait for completion of call_rcu()'s */ } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c index 1f3e32b576a..1918e0abf73 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2013 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, @@ -20,6 +20,7 @@ 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 @@ -27,8 +28,7 @@ #include <linux/pci.h> #include <linux/delay.h> -#include "ixgbe_type.h" -#include "ixgbe_common.h" +#include "ixgbe.h" #include "ixgbe_mbx.h" /** @@ -223,7 +223,7 @@ out: * received an ack to that message within delay * timeout period **/ static s32 ixgbe_write_posted_mbx(struct ixgbe_hw *hw, u32 *msg, u16 size, - u16 mbx_id) + u16 mbx_id) { struct ixgbe_mbx_info *mbx = &hw->mbx; s32 ret_val = IXGBE_ERR_MBX; @@ -269,7 +269,7 @@ static s32 ixgbe_check_for_msg_pf(struct ixgbe_hw *hw, u16 vf_number) u32 vf_bit = vf_number % 16; if (!ixgbe_check_for_bit_pf(hw, IXGBE_MBVFICR_VFREQ_VF1 << vf_bit, - index)) { + index)) { ret_val = 0; hw->mbx.stats.reqs++; } @@ -291,7 +291,7 @@ static s32 ixgbe_check_for_ack_pf(struct ixgbe_hw *hw, u16 vf_number) u32 vf_bit = vf_number % 16; if (!ixgbe_check_for_bit_pf(hw, IXGBE_MBVFICR_VFACK_VF1 << vf_bit, - index)) { + index)) { ret_val = 0; hw->mbx.stats.acks++; } @@ -366,7 +366,7 @@ static s32 ixgbe_obtain_mbx_lock_pf(struct ixgbe_hw *hw, u16 vf_number) * returns SUCCESS if it successfully copied message into the buffer **/ static s32 ixgbe_write_mbx_pf(struct ixgbe_hw *hw, u32 *msg, u16 size, - u16 vf_number) + u16 vf_number) { s32 ret_val; u16 i; @@ -407,7 +407,7 @@ out_no_write: * a message due to a VF request so no polling for message is needed. **/ static s32 ixgbe_read_mbx_pf(struct ixgbe_hw *hw, u32 *msg, u16 size, - u16 vf_number) + u16 vf_number) { s32 ret_val; u16 i; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h index 310bdd96107..a5cb755de3a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2013 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, @@ -20,6 +20,7 @@ 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 @@ -53,21 +54,48 @@ * Message ACK's are the value or'd with 0xF0000000 */ #define IXGBE_VT_MSGTYPE_ACK 0x80000000 /* Messages below or'd with - * this are the ACK */ + * this are the ACK */ #define IXGBE_VT_MSGTYPE_NACK 0x40000000 /* Messages below or'd with - * this are the NACK */ + * this are the NACK */ #define IXGBE_VT_MSGTYPE_CTS 0x20000000 /* Indicates that VF is still - clear to send requests */ + clear to send requests */ #define IXGBE_VT_MSGINFO_SHIFT 16 /* bits 23:16 are used for exra info for certain messages */ #define IXGBE_VT_MSGINFO_MASK (0xFF << IXGBE_VT_MSGINFO_SHIFT) +/* definitions to support mailbox API version negotiation */ + +/* + * Each element denotes a version of the API; existing numbers may not + * change; any additions must go at the end + */ +enum ixgbe_pfvf_api_rev { + ixgbe_mbox_api_10, /* API version 1.0, linux/freebsd VF driver */ + ixgbe_mbox_api_20, /* API version 2.0, solaris Phase1 VF driver */ + ixgbe_mbox_api_11, /* API version 1.1, linux/freebsd VF driver */ + /* This value should always be last */ + ixgbe_mbox_api_unknown, /* indicates that API version is not known */ +}; + +/* mailbox API, legacy requests */ #define IXGBE_VF_RESET 0x01 /* VF requests reset */ #define IXGBE_VF_SET_MAC_ADDR 0x02 /* VF requests PF to set MAC addr */ #define IXGBE_VF_SET_MULTICAST 0x03 /* VF requests PF to set MC addr */ #define IXGBE_VF_SET_VLAN 0x04 /* VF requests PF to set VLAN */ -#define IXGBE_VF_SET_LPE 0x05 /* VF requests PF to set VMOLR.LPE */ -#define IXGBE_VF_SET_MACVLAN 0x06 /* VF requests PF for unicast filter */ + +/* mailbox API, version 1.0 VF requests */ +#define IXGBE_VF_SET_LPE 0x05 /* VF requests PF to set VMOLR.LPE */ +#define IXGBE_VF_SET_MACVLAN 0x06 /* VF requests PF for unicast filter */ +#define IXGBE_VF_API_NEGOTIATE 0x08 /* negotiate API version */ + +/* mailbox API, version 1.1 VF requests */ +#define IXGBE_VF_GET_QUEUES 0x09 /* get queue configuration */ + +/* GET_QUEUES return data indices within the mailbox */ +#define IXGBE_VF_TX_QUEUES 1 /* number of Tx queues supported */ +#define IXGBE_VF_RX_QUEUES 2 /* number of Rx queues supported */ +#define IXGBE_VF_TRANS_VLAN 3 /* Indication of port vlan */ +#define IXGBE_VF_DEF_QUEUE 4 /* Default queue offset */ /* length of permanent address message returned from PF */ #define IXGBE_VF_PERMADDR_MSG_LEN 4 diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index b91773551a3..ff68b7a9def 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2014 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, @@ -20,6 +20,7 @@ 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 @@ -29,7 +30,7 @@ #include <linux/delay.h> #include <linux/sched.h> -#include "ixgbe_common.h" +#include "ixgbe.h" #include "ixgbe_phy.h" static void ixgbe_i2c_start(struct ixgbe_hw *hw); @@ -46,6 +47,7 @@ static bool ixgbe_get_i2c_data(u32 *i2cctl); static void ixgbe_i2c_bus_clear(struct ixgbe_hw *hw); static enum ixgbe_phy_type ixgbe_get_phy_type_from_id(u32 phy_id); static s32 ixgbe_get_phy_id(struct ixgbe_hw *hw); +static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw); /** * ixgbe_identify_phy_generic - Get physical layer module @@ -65,7 +67,7 @@ s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw) if (mdio45_probe(&hw->phy.mdio, phy_addr) == 0) { ixgbe_get_phy_id(hw); hw->phy.type = - ixgbe_get_phy_type_from_id(hw->phy.id); + ixgbe_get_phy_type_from_id(hw->phy.id); if (hw->phy.type == ixgbe_phy_unknown) { hw->phy.ops.read_reg(hw, @@ -97,6 +99,32 @@ s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw) } /** + * ixgbe_check_reset_blocked - check status of MNG FW veto bit + * @hw: pointer to the hardware structure + * + * This function checks the MMNGC.MNG_VETO bit to see if there are + * any constraints on link from manageability. For MAC's that don't + * have this bit just return false since the link can not be blocked + * via this method. + **/ +bool ixgbe_check_reset_blocked(struct ixgbe_hw *hw) +{ + u32 mmngc; + + /* If we don't have this bit, it can't be blocking */ + if (hw->mac.type == ixgbe_mac_82598EB) + return false; + + mmngc = IXGBE_READ_REG(hw, IXGBE_MMNGC); + if (mmngc & IXGBE_MMNGC_MNG_VETO) { + hw_dbg(hw, "MNG_VETO bit detected.\n"); + return true; + } + + return false; +} + +/** * ixgbe_get_phy_id - Get the phy type * @hw: pointer to hardware structure * @@ -108,12 +136,12 @@ static s32 ixgbe_get_phy_id(struct ixgbe_hw *hw) u16 phy_id_low = 0; status = hw->phy.ops.read_reg(hw, MDIO_DEVID1, MDIO_MMD_PMAPMD, - &phy_id_high); + &phy_id_high); if (status == 0) { hw->phy.id = (u32)(phy_id_high << 16); status = hw->phy.ops.read_reg(hw, MDIO_DEVID2, MDIO_MMD_PMAPMD, - &phy_id_low); + &phy_id_low); hw->phy.id |= (u32)(phy_id_low & IXGBE_PHY_REVISION_MASK); hw->phy.revision = (u32)(phy_id_low & ~IXGBE_PHY_REVISION_MASK); } @@ -171,6 +199,10 @@ s32 ixgbe_reset_phy_generic(struct ixgbe_hw *hw) (IXGBE_ERR_OVERTEMP == hw->phy.ops.check_overtemp(hw))) goto out; + /* Blocked by MNG FW so bail */ + if (ixgbe_check_reset_blocked(hw)) + goto out; + /* * Perform soft PHY reset to the PHY_XS. * This will cause a soft reset to the PHY @@ -204,18 +236,91 @@ out: } /** + * ixgbe_read_phy_mdi - Reads a value from a specified PHY register without + * the SWFW lock + * @hw: pointer to hardware structure + * @reg_addr: 32 bit address of PHY register to read + * @phy_data: Pointer to read data from PHY register + **/ +s32 ixgbe_read_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, u32 device_type, + u16 *phy_data) +{ + u32 i, data, command; + + /* Setup and write the address cycle command */ + command = ((reg_addr << IXGBE_MSCA_NP_ADDR_SHIFT) | + (device_type << IXGBE_MSCA_DEV_TYPE_SHIFT) | + (hw->phy.mdio.prtad << IXGBE_MSCA_PHY_ADDR_SHIFT) | + (IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND)); + + IXGBE_WRITE_REG(hw, IXGBE_MSCA, command); + + /* Check every 10 usec to see if the address cycle completed. + * The MDI Command bit will clear when the operation is + * complete + */ + for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) { + udelay(10); + + command = IXGBE_READ_REG(hw, IXGBE_MSCA); + if ((command & IXGBE_MSCA_MDI_COMMAND) == 0) + break; + } + + + if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { + hw_dbg(hw, "PHY address command did not complete.\n"); + return IXGBE_ERR_PHY; + } + + /* Address cycle complete, setup and write the read + * command + */ + command = ((reg_addr << IXGBE_MSCA_NP_ADDR_SHIFT) | + (device_type << IXGBE_MSCA_DEV_TYPE_SHIFT) | + (hw->phy.mdio.prtad << IXGBE_MSCA_PHY_ADDR_SHIFT) | + (IXGBE_MSCA_READ | IXGBE_MSCA_MDI_COMMAND)); + + IXGBE_WRITE_REG(hw, IXGBE_MSCA, command); + + /* Check every 10 usec to see if the address cycle + * completed. The MDI Command bit will clear when the + * operation is complete + */ + for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) { + udelay(10); + + command = IXGBE_READ_REG(hw, IXGBE_MSCA); + if ((command & IXGBE_MSCA_MDI_COMMAND) == 0) + break; + } + + if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { + hw_dbg(hw, "PHY read command didn't complete\n"); + return IXGBE_ERR_PHY; + } + + /* Read operation is complete. Get the data + * from MSRWD + */ + data = IXGBE_READ_REG(hw, IXGBE_MSRWD); + data >>= IXGBE_MSRWD_READ_DATA_SHIFT; + *phy_data = (u16)(data); + + return 0; +} + +/** * ixgbe_read_phy_reg_generic - Reads a value from a specified PHY register + * using the SWFW lock - this function is needed in most cases * @hw: pointer to hardware structure * @reg_addr: 32 bit address of PHY register to read * @phy_data: Pointer to read data from PHY register **/ s32 ixgbe_read_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, - u32 device_type, u16 *phy_data) + u32 device_type, u16 *phy_data) { - u32 command; - u32 i; - u32 data; - s32 status = 0; + s32 status; u16 gssr; if (IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_LAN_ID_1) @@ -223,97 +328,102 @@ s32 ixgbe_read_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, else gssr = IXGBE_GSSR_PHY0_SM; - if (hw->mac.ops.acquire_swfw_sync(hw, gssr) != 0) + if (hw->mac.ops.acquire_swfw_sync(hw, gssr) == 0) { + status = ixgbe_read_phy_reg_mdi(hw, reg_addr, device_type, + phy_data); + hw->mac.ops.release_swfw_sync(hw, gssr); + } else { status = IXGBE_ERR_SWFW_SYNC; + } - if (status == 0) { - /* Setup and write the address cycle command */ - command = ((reg_addr << IXGBE_MSCA_NP_ADDR_SHIFT) | - (device_type << IXGBE_MSCA_DEV_TYPE_SHIFT) | - (hw->phy.mdio.prtad << IXGBE_MSCA_PHY_ADDR_SHIFT) | - (IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND)); + return status; +} - IXGBE_WRITE_REG(hw, IXGBE_MSCA, command); +/** + * ixgbe_write_phy_reg_mdi - Writes a value to specified PHY register + * without SWFW lock + * @hw: pointer to hardware structure + * @reg_addr: 32 bit PHY register to write + * @device_type: 5 bit device type + * @phy_data: Data to write to the PHY register + **/ +s32 ixgbe_write_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u16 phy_data) +{ + u32 i, command; - /* - * Check every 10 usec to see if the address cycle completed. - * The MDI Command bit will clear when the operation is - * complete - */ - for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) { - udelay(10); + /* Put the data in the MDI single read and write data register*/ + IXGBE_WRITE_REG(hw, IXGBE_MSRWD, (u32)phy_data); - command = IXGBE_READ_REG(hw, IXGBE_MSCA); + /* Setup and write the address cycle command */ + command = ((reg_addr << IXGBE_MSCA_NP_ADDR_SHIFT) | + (device_type << IXGBE_MSCA_DEV_TYPE_SHIFT) | + (hw->phy.mdio.prtad << IXGBE_MSCA_PHY_ADDR_SHIFT) | + (IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND)); - if ((command & IXGBE_MSCA_MDI_COMMAND) == 0) - break; - } + IXGBE_WRITE_REG(hw, IXGBE_MSCA, command); - if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { - hw_dbg(hw, "PHY address command did not complete.\n"); - status = IXGBE_ERR_PHY; - } + /* + * Check every 10 usec to see if the address cycle completed. + * The MDI Command bit will clear when the operation is + * complete + */ + for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) { + udelay(10); - if (status == 0) { - /* - * Address cycle complete, setup and write the read - * command - */ - command = ((reg_addr << IXGBE_MSCA_NP_ADDR_SHIFT) | - (device_type << IXGBE_MSCA_DEV_TYPE_SHIFT) | - (hw->phy.mdio.prtad << - IXGBE_MSCA_PHY_ADDR_SHIFT) | - (IXGBE_MSCA_READ | IXGBE_MSCA_MDI_COMMAND)); - - IXGBE_WRITE_REG(hw, IXGBE_MSCA, command); - - /* - * Check every 10 usec to see if the address cycle - * completed. The MDI Command bit will clear when the - * operation is complete - */ - for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) { - udelay(10); + command = IXGBE_READ_REG(hw, IXGBE_MSCA); + if ((command & IXGBE_MSCA_MDI_COMMAND) == 0) + break; + } - command = IXGBE_READ_REG(hw, IXGBE_MSCA); + if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { + hw_dbg(hw, "PHY address cmd didn't complete\n"); + return IXGBE_ERR_PHY; + } - if ((command & IXGBE_MSCA_MDI_COMMAND) == 0) - break; - } + /* + * Address cycle complete, setup and write the write + * command + */ + command = ((reg_addr << IXGBE_MSCA_NP_ADDR_SHIFT) | + (device_type << IXGBE_MSCA_DEV_TYPE_SHIFT) | + (hw->phy.mdio.prtad << IXGBE_MSCA_PHY_ADDR_SHIFT) | + (IXGBE_MSCA_WRITE | IXGBE_MSCA_MDI_COMMAND)); - if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { - hw_dbg(hw, "PHY read command didn't complete\n"); - status = IXGBE_ERR_PHY; - } else { - /* - * Read operation is complete. Get the data - * from MSRWD - */ - data = IXGBE_READ_REG(hw, IXGBE_MSRWD); - data >>= IXGBE_MSRWD_READ_DATA_SHIFT; - *phy_data = (u16)(data); - } - } + IXGBE_WRITE_REG(hw, IXGBE_MSCA, command); - hw->mac.ops.release_swfw_sync(hw, gssr); + /* Check every 10 usec to see if the address cycle + * completed. The MDI Command bit will clear when the + * operation is complete + */ + for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) { + udelay(10); + + command = IXGBE_READ_REG(hw, IXGBE_MSCA); + if ((command & IXGBE_MSCA_MDI_COMMAND) == 0) + break; } - return status; + if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { + hw_dbg(hw, "PHY write cmd didn't complete\n"); + return IXGBE_ERR_PHY; + } + + return 0; } /** * ixgbe_write_phy_reg_generic - Writes a value to specified PHY register + * using SWFW lock- this function is needed in most cases * @hw: pointer to hardware structure * @reg_addr: 32 bit PHY register to write * @device_type: 5 bit device type * @phy_data: Data to write to the PHY register **/ s32 ixgbe_write_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, - u32 device_type, u16 phy_data) + u32 device_type, u16 phy_data) { - u32 command; - u32 i; - s32 status = 0; + s32 status; u16 gssr; if (IXGBE_READ_REG(hw, IXGBE_STATUS) & IXGBE_STATUS_LAN_ID_1) @@ -321,74 +431,12 @@ s32 ixgbe_write_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, else gssr = IXGBE_GSSR_PHY0_SM; - if (hw->mac.ops.acquire_swfw_sync(hw, gssr) != 0) - status = IXGBE_ERR_SWFW_SYNC; - - if (status == 0) { - /* Put the data in the MDI single read and write data register*/ - IXGBE_WRITE_REG(hw, IXGBE_MSRWD, (u32)phy_data); - - /* Setup and write the address cycle command */ - command = ((reg_addr << IXGBE_MSCA_NP_ADDR_SHIFT) | - (device_type << IXGBE_MSCA_DEV_TYPE_SHIFT) | - (hw->phy.mdio.prtad << IXGBE_MSCA_PHY_ADDR_SHIFT) | - (IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND)); - - IXGBE_WRITE_REG(hw, IXGBE_MSCA, command); - - /* - * Check every 10 usec to see if the address cycle completed. - * The MDI Command bit will clear when the operation is - * complete - */ - for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) { - udelay(10); - - command = IXGBE_READ_REG(hw, IXGBE_MSCA); - - if ((command & IXGBE_MSCA_MDI_COMMAND) == 0) - break; - } - - if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { - hw_dbg(hw, "PHY address cmd didn't complete\n"); - status = IXGBE_ERR_PHY; - } - - if (status == 0) { - /* - * Address cycle complete, setup and write the write - * command - */ - command = ((reg_addr << IXGBE_MSCA_NP_ADDR_SHIFT) | - (device_type << IXGBE_MSCA_DEV_TYPE_SHIFT) | - (hw->phy.mdio.prtad << - IXGBE_MSCA_PHY_ADDR_SHIFT) | - (IXGBE_MSCA_WRITE | IXGBE_MSCA_MDI_COMMAND)); - - IXGBE_WRITE_REG(hw, IXGBE_MSCA, command); - - /* - * Check every 10 usec to see if the address cycle - * completed. The MDI Command bit will clear when the - * operation is complete - */ - for (i = 0; i < IXGBE_MDIO_COMMAND_TIMEOUT; i++) { - udelay(10); - - command = IXGBE_READ_REG(hw, IXGBE_MSCA); - - if ((command & IXGBE_MSCA_MDI_COMMAND) == 0) - break; - } - - if ((command & IXGBE_MSCA_MDI_COMMAND) != 0) { - hw_dbg(hw, "PHY address cmd didn't complete\n"); - status = IXGBE_ERR_PHY; - } - } - + if (hw->mac.ops.acquire_swfw_sync(hw, gssr) == 0) { + status = ixgbe_write_phy_reg_mdi(hw, reg_addr, device_type, + phy_data); hw->mac.ops.release_swfw_sync(hw, gssr); + } else { + status = IXGBE_ERR_SWFW_SYNC; } return status; @@ -459,6 +507,10 @@ s32 ixgbe_setup_phy_link_generic(struct ixgbe_hw *hw) autoneg_reg); } + /* Blocked by MNG FW so don't reset PHY */ + if (ixgbe_check_reset_blocked(hw)) + return status; + /* Restart PHY autonegotiation and wait for completion */ hw->phy.ops.read_reg(hw, MDIO_CTRL1, MDIO_MMD_AN, &autoneg_reg); @@ -484,7 +536,7 @@ s32 ixgbe_setup_phy_link_generic(struct ixgbe_hw *hw) if (time_out == max_time_out) { status = IXGBE_ERR_LINK_SETUP; - hw_dbg(hw, "ixgbe_setup_phy_link_generic: time out"); + hw_dbg(hw, "ixgbe_setup_phy_link_generic: time out\n"); } return status; @@ -494,12 +546,10 @@ s32 ixgbe_setup_phy_link_generic(struct ixgbe_hw *hw) * ixgbe_setup_phy_link_speed_generic - Sets the auto advertised capabilities * @hw: pointer to hardware structure * @speed: new link speed - * @autoneg: true if autonegotiation enabled **/ s32 ixgbe_setup_phy_link_speed_generic(struct ixgbe_hw *hw, - ixgbe_link_speed speed, - bool autoneg, - bool autoneg_wait_to_complete) + ixgbe_link_speed speed, + bool autoneg_wait_to_complete) { /* @@ -532,8 +582,8 @@ s32 ixgbe_setup_phy_link_speed_generic(struct ixgbe_hw *hw, * Determines the link capabilities by reading the AUTOC register. */ s32 ixgbe_get_copper_link_capabilities_generic(struct ixgbe_hw *hw, - ixgbe_link_speed *speed, - bool *autoneg) + ixgbe_link_speed *speed, + bool *autoneg) { s32 status = IXGBE_ERR_LINK_SETUP; u16 speed_ability; @@ -542,7 +592,7 @@ s32 ixgbe_get_copper_link_capabilities_generic(struct ixgbe_hw *hw, *autoneg = true; status = hw->phy.ops.read_reg(hw, MDIO_SPEED, MDIO_MMD_PMAPMD, - &speed_ability); + &speed_ability); if (status == 0) { if (speed_ability & MDIO_SPEED_10G) @@ -667,6 +717,10 @@ s32 ixgbe_setup_phy_link_tnx(struct ixgbe_hw *hw) autoneg_reg); } + /* Blocked by MNG FW so don't reset PHY */ + if (ixgbe_check_reset_blocked(hw)) + return status; + /* Restart PHY autonegotiation and wait for completion */ hw->phy.ops.read_reg(hw, MDIO_CTRL1, MDIO_MMD_AN, &autoneg_reg); @@ -691,7 +745,7 @@ s32 ixgbe_setup_phy_link_tnx(struct ixgbe_hw *hw) if (time_out == max_time_out) { status = IXGBE_ERR_LINK_SETUP; - hw_dbg(hw, "ixgbe_setup_phy_link_tnx: time out"); + hw_dbg(hw, "ixgbe_setup_phy_link_tnx: time out\n"); } return status; @@ -744,15 +798,19 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw) s32 ret_val = 0; u32 i; + /* Blocked by MNG FW so bail */ + if (ixgbe_check_reset_blocked(hw)) + goto out; + hw->phy.ops.read_reg(hw, MDIO_CTRL1, MDIO_MMD_PHYXS, &phy_data); /* reset the PHY and poll for completion */ hw->phy.ops.write_reg(hw, MDIO_CTRL1, MDIO_MMD_PHYXS, - (phy_data | MDIO_CTRL1_RESET)); + (phy_data | MDIO_CTRL1_RESET)); for (i = 0; i < 100; i++) { hw->phy.ops.read_reg(hw, MDIO_CTRL1, MDIO_MMD_PHYXS, - &phy_data); + &phy_data); if ((phy_data & MDIO_CTRL1_RESET) == 0) break; usleep_range(10000, 20000); @@ -766,7 +824,7 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw) /* Get init offsets */ ret_val = ixgbe_get_sfp_init_sequence_offsets(hw, &list_offset, - &data_offset); + &data_offset); if (ret_val != 0) goto out; @@ -777,8 +835,10 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw) * Read control word from PHY init contents offset */ ret_val = hw->eeprom.ops.read(hw, data_offset, &eword); + if (ret_val) + goto err_eeprom; control = (eword & IXGBE_CONTROL_MASK_NL) >> - IXGBE_CONTROL_SHIFT_NL; + IXGBE_CONTROL_SHIFT_NL; edata = eword & IXGBE_DATA_MASK_NL; switch (control) { case IXGBE_DELAY_NL: @@ -789,12 +849,17 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw) case IXGBE_DATA_NL: hw_dbg(hw, "DATA:\n"); data_offset++; - hw->eeprom.ops.read(hw, data_offset++, - &phy_offset); + ret_val = hw->eeprom.ops.read(hw, data_offset++, + &phy_offset); + if (ret_val) + goto err_eeprom; for (i = 0; i < edata; i++) { - hw->eeprom.ops.read(hw, data_offset, &eword); + ret_val = hw->eeprom.ops.read(hw, data_offset, + &eword); + if (ret_val) + goto err_eeprom; hw->phy.ops.write_reg(hw, phy_offset, - MDIO_MMD_PMAPMD, eword); + MDIO_MMD_PMAPMD, eword); hw_dbg(hw, "Wrote %4.4x to %4.4x\n", eword, phy_offset); data_offset++; @@ -824,16 +889,47 @@ s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw) out: return ret_val; + +err_eeprom: + hw_err(hw, "eeprom read at offset %d failed\n", data_offset); + return IXGBE_ERR_PHY; } /** - * ixgbe_identify_sfp_module_generic - Identifies SFP modules + * ixgbe_identify_module_generic - Identifies module type * @hw: pointer to hardware structure * + * Determines HW type and calls appropriate function. + **/ +s32 ixgbe_identify_module_generic(struct ixgbe_hw *hw) +{ + s32 status = IXGBE_ERR_SFP_NOT_PRESENT; + + switch (hw->mac.ops.get_media_type(hw)) { + case ixgbe_media_type_fiber: + status = ixgbe_identify_sfp_module_generic(hw); + break; + case ixgbe_media_type_fiber_qsfp: + status = ixgbe_identify_qsfp_module_generic(hw); + break; + default: + hw->phy.sfp_type = ixgbe_sfp_type_not_present; + status = IXGBE_ERR_SFP_NOT_PRESENT; + break; + } + + return status; +} + +/** + * ixgbe_identify_sfp_module_generic - Identifies SFP modules + * @hw: pointer to hardware structure +* * Searches for and identifies the SFP module and assigns appropriate PHY type. **/ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) { + struct ixgbe_adapter *adapter = hw->back; s32 status = IXGBE_ERR_PHY_ADDR_INVALID; u32 vendor_oui = 0; enum ixgbe_sfp_type stored_sfp_type = hw->phy.sfp_type; @@ -853,11 +949,9 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) status = hw->phy.ops.read_i2c_eeprom(hw, IXGBE_SFF_IDENTIFIER, - &identifier); + &identifier); - if (status == IXGBE_ERR_SWFW_SYNC || - status == IXGBE_ERR_I2C || - status == IXGBE_ERR_SFP_NOT_PRESENT) + if (status != 0) goto err_read_i2c_eeprom; /* LAN ID is needed for sfp_type determination */ @@ -871,26 +965,20 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) IXGBE_SFF_1GBE_COMP_CODES, &comp_codes_1g); - if (status == IXGBE_ERR_SWFW_SYNC || - status == IXGBE_ERR_I2C || - status == IXGBE_ERR_SFP_NOT_PRESENT) + if (status != 0) goto err_read_i2c_eeprom; status = hw->phy.ops.read_i2c_eeprom(hw, IXGBE_SFF_10GBE_COMP_CODES, &comp_codes_10g); - if (status == IXGBE_ERR_SWFW_SYNC || - status == IXGBE_ERR_I2C || - status == IXGBE_ERR_SFP_NOT_PRESENT) + if (status != 0) goto err_read_i2c_eeprom; status = hw->phy.ops.read_i2c_eeprom(hw, IXGBE_SFF_CABLE_TECHNOLOGY, &cable_tech); - if (status == IXGBE_ERR_SWFW_SYNC || - status == IXGBE_ERR_I2C || - status == IXGBE_ERR_SFP_NOT_PRESENT) + if (status != 0) goto err_read_i2c_eeprom; /* ID Module @@ -906,6 +994,8 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) * 8 SFP_act_lmt_DA_CORE1 - 82599-specific * 9 SFP_1g_cu_CORE0 - 82599-specific * 10 SFP_1g_cu_CORE1 - 82599-specific + * 11 SFP_1g_sx_CORE0 - 82599-specific + * 12 SFP_1g_sx_CORE1 - 82599-specific */ if (hw->mac.type == ixgbe_mac_82598EB) { if (cable_tech & IXGBE_SFF_DA_PASSIVE_CABLE) @@ -920,10 +1010,10 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) if (cable_tech & IXGBE_SFF_DA_PASSIVE_CABLE) { if (hw->bus.lan_id == 0) hw->phy.sfp_type = - ixgbe_sfp_type_da_cu_core0; + ixgbe_sfp_type_da_cu_core0; else hw->phy.sfp_type = - ixgbe_sfp_type_da_cu_core1; + ixgbe_sfp_type_da_cu_core1; } else if (cable_tech & IXGBE_SFF_DA_ACTIVE_CABLE) { hw->phy.ops.read_i2c_eeprom( hw, IXGBE_SFF_CABLE_SPEC_COMP, @@ -945,10 +1035,10 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) IXGBE_SFF_10GBASELR_CAPABLE)) { if (hw->bus.lan_id == 0) hw->phy.sfp_type = - ixgbe_sfp_type_srlr_core0; + ixgbe_sfp_type_srlr_core0; else hw->phy.sfp_type = - ixgbe_sfp_type_srlr_core1; + ixgbe_sfp_type_srlr_core1; } else if (comp_codes_1g & IXGBE_SFF_1GBASET_CAPABLE) { if (hw->bus.lan_id == 0) hw->phy.sfp_type = @@ -956,6 +1046,20 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) else hw->phy.sfp_type = ixgbe_sfp_type_1g_cu_core1; + } else if (comp_codes_1g & IXGBE_SFF_1GBASESX_CAPABLE) { + if (hw->bus.lan_id == 0) + hw->phy.sfp_type = + ixgbe_sfp_type_1g_sx_core0; + else + hw->phy.sfp_type = + ixgbe_sfp_type_1g_sx_core1; + } else if (comp_codes_1g & IXGBE_SFF_1GBASELX_CAPABLE) { + if (hw->bus.lan_id == 0) + hw->phy.sfp_type = + ixgbe_sfp_type_1g_lx_core0; + else + hw->phy.sfp_type = + ixgbe_sfp_type_1g_lx_core1; } else { hw->phy.sfp_type = ixgbe_sfp_type_unknown; } @@ -976,30 +1080,24 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) if (hw->phy.type != ixgbe_phy_nl) { hw->phy.id = identifier; status = hw->phy.ops.read_i2c_eeprom(hw, - IXGBE_SFF_VENDOR_OUI_BYTE0, - &oui_bytes[0]); + IXGBE_SFF_VENDOR_OUI_BYTE0, + &oui_bytes[0]); - if (status == IXGBE_ERR_SWFW_SYNC || - status == IXGBE_ERR_I2C || - status == IXGBE_ERR_SFP_NOT_PRESENT) + if (status != 0) goto err_read_i2c_eeprom; status = hw->phy.ops.read_i2c_eeprom(hw, - IXGBE_SFF_VENDOR_OUI_BYTE1, - &oui_bytes[1]); + IXGBE_SFF_VENDOR_OUI_BYTE1, + &oui_bytes[1]); - if (status == IXGBE_ERR_SWFW_SYNC || - status == IXGBE_ERR_I2C || - status == IXGBE_ERR_SFP_NOT_PRESENT) + if (status != 0) goto err_read_i2c_eeprom; status = hw->phy.ops.read_i2c_eeprom(hw, - IXGBE_SFF_VENDOR_OUI_BYTE2, - &oui_bytes[2]); + IXGBE_SFF_VENDOR_OUI_BYTE2, + &oui_bytes[2]); - if (status == IXGBE_ERR_SWFW_SYNC || - status == IXGBE_ERR_I2C || - status == IXGBE_ERR_SFP_NOT_PRESENT) + if (status != 0) goto err_read_i2c_eeprom; vendor_oui = @@ -1048,7 +1146,11 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) /* Verify supported 1G SFP modules */ if (comp_codes_10g == 0 && !(hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core1 || - hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core0)) { + hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core1 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1)) { hw->phy.type = ixgbe_phy_sfp_unsupported; status = IXGBE_ERR_SFP_NOT_SUPPORTED; goto out; @@ -1062,15 +1164,26 @@ s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw) hw->mac.ops.get_device_caps(hw, &enforce_sfp); if (!(enforce_sfp & IXGBE_DEVICE_CAPS_ALLOW_ANY_SFP) && - !((hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core0) || - (hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core1))) { + !(hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_cu_core1 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_lx_core1 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core0 || + hw->phy.sfp_type == ixgbe_sfp_type_1g_sx_core1)) { /* Make sure we're a supported PHY type */ if (hw->phy.type == ixgbe_phy_sfp_intel) { status = 0; } else { - hw_dbg(hw, "SFP+ module not supported\n"); - hw->phy.type = ixgbe_phy_sfp_unsupported; - status = IXGBE_ERR_SFP_NOT_SUPPORTED; + if (hw->allow_unsupported_sfp) { + e_warn(drv, "WARNING: Intel (R) Network Connections are quality tested using Intel (R) Ethernet Optics. Using untested modules is not supported and may cause unstable operation or damage to the module or the adapter. Intel Corporation is not responsible for any harm caused by using untested modules.\n"); + status = 0; + } else { + hw_dbg(hw, + "SFP+ module not supported\n"); + hw->phy.type = + ixgbe_phy_sfp_unsupported; + status = IXGBE_ERR_SFP_NOT_SUPPORTED; + } } } else { status = 0; @@ -1090,6 +1203,197 @@ err_read_i2c_eeprom: } /** + * ixgbe_identify_qsfp_module_generic - Identifies QSFP modules + * @hw: pointer to hardware structure + * + * Searches for and identifies the QSFP module and assigns appropriate PHY type + **/ +static s32 ixgbe_identify_qsfp_module_generic(struct ixgbe_hw *hw) +{ + struct ixgbe_adapter *adapter = hw->back; + s32 status = IXGBE_ERR_PHY_ADDR_INVALID; + u32 vendor_oui = 0; + enum ixgbe_sfp_type stored_sfp_type = hw->phy.sfp_type; + u8 identifier = 0; + u8 comp_codes_1g = 0; + u8 comp_codes_10g = 0; + u8 oui_bytes[3] = {0, 0, 0}; + u16 enforce_sfp = 0; + u8 connector = 0; + u8 cable_length = 0; + u8 device_tech = 0; + bool active_cable = false; + + if (hw->mac.ops.get_media_type(hw) != ixgbe_media_type_fiber_qsfp) { + hw->phy.sfp_type = ixgbe_sfp_type_not_present; + status = IXGBE_ERR_SFP_NOT_PRESENT; + goto out; + } + + status = hw->phy.ops.read_i2c_eeprom(hw, IXGBE_SFF_IDENTIFIER, + &identifier); + + if (status != 0) + goto err_read_i2c_eeprom; + + if (identifier != IXGBE_SFF_IDENTIFIER_QSFP_PLUS) { + hw->phy.type = ixgbe_phy_sfp_unsupported; + status = IXGBE_ERR_SFP_NOT_SUPPORTED; + goto out; + } + + hw->phy.id = identifier; + + /* LAN ID is needed for sfp_type determination */ + hw->mac.ops.set_lan_id(hw); + + status = hw->phy.ops.read_i2c_eeprom(hw, IXGBE_SFF_QSFP_10GBE_COMP, + &comp_codes_10g); + + if (status != 0) + goto err_read_i2c_eeprom; + + status = hw->phy.ops.read_i2c_eeprom(hw, IXGBE_SFF_QSFP_1GBE_COMP, + &comp_codes_1g); + + if (status != 0) + goto err_read_i2c_eeprom; + + if (comp_codes_10g & IXGBE_SFF_QSFP_DA_PASSIVE_CABLE) { + hw->phy.type = ixgbe_phy_qsfp_passive_unknown; + if (hw->bus.lan_id == 0) + hw->phy.sfp_type = ixgbe_sfp_type_da_cu_core0; + else + hw->phy.sfp_type = ixgbe_sfp_type_da_cu_core1; + } else if (comp_codes_10g & (IXGBE_SFF_10GBASESR_CAPABLE | + IXGBE_SFF_10GBASELR_CAPABLE)) { + if (hw->bus.lan_id == 0) + hw->phy.sfp_type = ixgbe_sfp_type_srlr_core0; + else + hw->phy.sfp_type = ixgbe_sfp_type_srlr_core1; + } else { + if (comp_codes_10g & IXGBE_SFF_QSFP_DA_ACTIVE_CABLE) + active_cable = true; + + if (!active_cable) { + /* check for active DA cables that pre-date + * SFF-8436 v3.6 + */ + hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_QSFP_CONNECTOR, + &connector); + + hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_QSFP_CABLE_LENGTH, + &cable_length); + + hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_QSFP_DEVICE_TECH, + &device_tech); + + if ((connector == + IXGBE_SFF_QSFP_CONNECTOR_NOT_SEPARABLE) && + (cable_length > 0) && + ((device_tech >> 4) == + IXGBE_SFF_QSFP_TRANSMITER_850NM_VCSEL)) + active_cable = true; + } + + if (active_cable) { + hw->phy.type = ixgbe_phy_qsfp_active_unknown; + if (hw->bus.lan_id == 0) + hw->phy.sfp_type = + ixgbe_sfp_type_da_act_lmt_core0; + else + hw->phy.sfp_type = + ixgbe_sfp_type_da_act_lmt_core1; + } else { + /* unsupported module type */ + hw->phy.type = ixgbe_phy_sfp_unsupported; + status = IXGBE_ERR_SFP_NOT_SUPPORTED; + goto out; + } + } + + if (hw->phy.sfp_type != stored_sfp_type) + hw->phy.sfp_setup_needed = true; + + /* Determine if the QSFP+ PHY is dual speed or not. */ + hw->phy.multispeed_fiber = false; + if (((comp_codes_1g & IXGBE_SFF_1GBASESX_CAPABLE) && + (comp_codes_10g & IXGBE_SFF_10GBASESR_CAPABLE)) || + ((comp_codes_1g & IXGBE_SFF_1GBASELX_CAPABLE) && + (comp_codes_10g & IXGBE_SFF_10GBASELR_CAPABLE))) + hw->phy.multispeed_fiber = true; + + /* Determine PHY vendor for optical modules */ + if (comp_codes_10g & (IXGBE_SFF_10GBASESR_CAPABLE | + IXGBE_SFF_10GBASELR_CAPABLE)) { + status = hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_QSFP_VENDOR_OUI_BYTE0, + &oui_bytes[0]); + + if (status != 0) + goto err_read_i2c_eeprom; + + status = hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_QSFP_VENDOR_OUI_BYTE1, + &oui_bytes[1]); + + if (status != 0) + goto err_read_i2c_eeprom; + + status = hw->phy.ops.read_i2c_eeprom(hw, + IXGBE_SFF_QSFP_VENDOR_OUI_BYTE2, + &oui_bytes[2]); + + if (status != 0) + goto err_read_i2c_eeprom; + + vendor_oui = + ((oui_bytes[0] << IXGBE_SFF_VENDOR_OUI_BYTE0_SHIFT) | + (oui_bytes[1] << IXGBE_SFF_VENDOR_OUI_BYTE1_SHIFT) | + (oui_bytes[2] << IXGBE_SFF_VENDOR_OUI_BYTE2_SHIFT)); + + if (vendor_oui == IXGBE_SFF_VENDOR_OUI_INTEL) + hw->phy.type = ixgbe_phy_qsfp_intel; + else + hw->phy.type = ixgbe_phy_qsfp_unknown; + + hw->mac.ops.get_device_caps(hw, &enforce_sfp); + if (!(enforce_sfp & IXGBE_DEVICE_CAPS_ALLOW_ANY_SFP)) { + /* Make sure we're a supported PHY type */ + if (hw->phy.type == ixgbe_phy_qsfp_intel) { + status = 0; + } else { + if (hw->allow_unsupported_sfp == true) { + e_warn(drv, "WARNING: Intel (R) Network Connections are quality tested using Intel (R) Ethernet Optics. Using untested modules is not supported and may cause unstable operation or damage to the module or the adapter. Intel Corporation is not responsible for any harm caused by using untested modules.\n"); + status = 0; + } else { + hw_dbg(hw, + "QSFP module not supported\n"); + hw->phy.type = + ixgbe_phy_sfp_unsupported; + status = IXGBE_ERR_SFP_NOT_SUPPORTED; + } + } + } else { + status = 0; + } + } + +out: + return status; + +err_read_i2c_eeprom: + hw->phy.sfp_type = ixgbe_sfp_type_not_present; + hw->phy.id = 0; + hw->phy.type = ixgbe_phy_unknown; + + return IXGBE_ERR_SFP_NOT_PRESENT; +} + +/** * ixgbe_get_sfp_init_sequence_offsets - Provides offset of PHY init sequence * @hw: pointer to hardware structure * @list_offset: offset to the SFP ID list @@ -1099,8 +1403,8 @@ err_read_i2c_eeprom: * so it returns the offsets to the phy init sequence block. **/ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, - u16 *list_offset, - u16 *data_offset) + u16 *list_offset, + u16 *data_offset) { u16 sfp_id; u16 sfp_type = hw->phy.sfp_type; @@ -1120,14 +1424,22 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, * SR modules */ if (sfp_type == ixgbe_sfp_type_da_act_lmt_core0 || - sfp_type == ixgbe_sfp_type_1g_cu_core0) + sfp_type == ixgbe_sfp_type_1g_lx_core0 || + sfp_type == ixgbe_sfp_type_1g_cu_core0 || + sfp_type == ixgbe_sfp_type_1g_sx_core0) sfp_type = ixgbe_sfp_type_srlr_core0; else if (sfp_type == ixgbe_sfp_type_da_act_lmt_core1 || - sfp_type == ixgbe_sfp_type_1g_cu_core1) + sfp_type == ixgbe_sfp_type_1g_lx_core1 || + sfp_type == ixgbe_sfp_type_1g_cu_core1 || + sfp_type == ixgbe_sfp_type_1g_sx_core1) sfp_type = ixgbe_sfp_type_srlr_core1; /* Read offset to PHY init contents */ - hw->eeprom.ops.read(hw, IXGBE_PHY_INIT_OFFSET_NL, list_offset); + if (hw->eeprom.ops.read(hw, IXGBE_PHY_INIT_OFFSET_NL, list_offset)) { + hw_err(hw, "eeprom read at %d failed\n", + IXGBE_PHY_INIT_OFFSET_NL); + return IXGBE_ERR_SFP_NO_INIT_SEQ_PRESENT; + } if ((!*list_offset) || (*list_offset == 0xFFFF)) return IXGBE_ERR_SFP_NO_INIT_SEQ_PRESENT; @@ -1139,12 +1451,14 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, * Find the matching SFP ID in the EEPROM * and program the init sequence */ - hw->eeprom.ops.read(hw, *list_offset, &sfp_id); + if (hw->eeprom.ops.read(hw, *list_offset, &sfp_id)) + goto err_phy; while (sfp_id != IXGBE_PHY_INIT_END_NL) { if (sfp_id == sfp_type) { (*list_offset)++; - hw->eeprom.ops.read(hw, *list_offset, data_offset); + if (hw->eeprom.ops.read(hw, *list_offset, data_offset)) + goto err_phy; if ((!*data_offset) || (*data_offset == 0xFFFF)) { hw_dbg(hw, "SFP+ module not supported\n"); return IXGBE_ERR_SFP_NOT_SUPPORTED; @@ -1154,7 +1468,7 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, } else { (*list_offset) += 2; if (hw->eeprom.ops.read(hw, *list_offset, &sfp_id)) - return IXGBE_ERR_PHY; + goto err_phy; } } @@ -1164,6 +1478,10 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, } return 0; + +err_phy: + hw_err(hw, "eeprom read at offset %d failed\n", *list_offset); + return IXGBE_ERR_PHY; } /** @@ -1175,11 +1493,27 @@ s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, * Performs byte read operation to SFP module's EEPROM over I2C interface. **/ s32 ixgbe_read_i2c_eeprom_generic(struct ixgbe_hw *hw, u8 byte_offset, - u8 *eeprom_data) + u8 *eeprom_data) +{ + return hw->phy.ops.read_i2c_byte(hw, byte_offset, + IXGBE_I2C_EEPROM_DEV_ADDR, + eeprom_data); +} + +/** + * ixgbe_read_i2c_sff8472_generic - Reads 8 bit word over I2C interface + * @hw: pointer to hardware structure + * @byte_offset: byte offset at address 0xA2 + * @eeprom_data: value read + * + * Performs byte read operation to SFP module's SFF-8472 data over I2C + **/ +s32 ixgbe_read_i2c_sff8472_generic(struct ixgbe_hw *hw, u8 byte_offset, + u8 *sff8472_data) { return hw->phy.ops.read_i2c_byte(hw, byte_offset, - IXGBE_I2C_EEPROM_DEV_ADDR, - eeprom_data); + IXGBE_I2C_EEPROM_DEV_ADDR2, + sff8472_data); } /** @@ -1191,11 +1525,11 @@ s32 ixgbe_read_i2c_eeprom_generic(struct ixgbe_hw *hw, u8 byte_offset, * Performs byte write operation to SFP module's EEPROM over I2C interface. **/ s32 ixgbe_write_i2c_eeprom_generic(struct ixgbe_hw *hw, u8 byte_offset, - u8 eeprom_data) + u8 eeprom_data) { return hw->phy.ops.write_i2c_byte(hw, byte_offset, - IXGBE_I2C_EEPROM_DEV_ADDR, - eeprom_data); + IXGBE_I2C_EEPROM_DEV_ADDR, + eeprom_data); } /** @@ -1208,7 +1542,7 @@ s32 ixgbe_write_i2c_eeprom_generic(struct ixgbe_hw *hw, u8 byte_offset, * a specified device address. **/ s32 ixgbe_read_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset, - u8 dev_addr, u8 *data) + u8 dev_addr, u8 *data) { s32 status = 0; u32 max_retry = 10; @@ -1270,9 +1604,9 @@ s32 ixgbe_read_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset, break; fail: + ixgbe_i2c_bus_clear(hw); hw->mac.ops.release_swfw_sync(hw, swfw_mask); msleep(100); - ixgbe_i2c_bus_clear(hw); retry++; if (retry < max_retry) hw_dbg(hw, "I2C byte read error - Retrying.\n"); @@ -1297,7 +1631,7 @@ read_byte_out: * a specified device address. **/ s32 ixgbe_write_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset, - u8 dev_addr, u8 data) + u8 dev_addr, u8 data) { s32 status = 0; u32 max_retry = 1; @@ -1574,13 +1908,21 @@ static s32 ixgbe_clock_out_i2c_bit(struct ixgbe_hw *hw, bool data) **/ static void ixgbe_raise_i2c_clk(struct ixgbe_hw *hw, u32 *i2cctl) { - *i2cctl |= IXGBE_I2C_CLK_OUT; - - IXGBE_WRITE_REG(hw, IXGBE_I2CCTL, *i2cctl); - IXGBE_WRITE_FLUSH(hw); + u32 i = 0; + u32 timeout = IXGBE_I2C_CLOCK_STRETCHING_TIMEOUT; + u32 i2cctl_r = 0; - /* SCL rise time (1000ns) */ - udelay(IXGBE_I2C_T_RISE); + for (i = 0; i < timeout; i++) { + *i2cctl |= IXGBE_I2C_CLK_OUT; + IXGBE_WRITE_REG(hw, IXGBE_I2CCTL, *i2cctl); + IXGBE_WRITE_FLUSH(hw); + /* SCL rise time (1000ns) */ + udelay(IXGBE_I2C_T_RISE); + + i2cctl_r = IXGBE_READ_REG(hw, IXGBE_I2CCTL); + if (i2cctl_r & IXGBE_I2C_CLK_IN) + break; + } } /** @@ -1704,7 +2046,7 @@ s32 ixgbe_tn_check_overtemp(struct ixgbe_hw *hw) /* Check that the LASI temp alarm status was triggered */ hw->phy.ops.read_reg(hw, IXGBE_TN_LASI_STATUS_REG, - MDIO_MMD_PMAPMD, &phy_data); + MDIO_MMD_PMAPMD, &phy_data); if (!(phy_data & IXGBE_TN_LASI_STATUS_TEMP_ALARM)) goto out; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h index cc18165b4c0..54071ed17e3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2014 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, @@ -20,6 +20,7 @@ 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 @@ -30,34 +31,52 @@ #include "ixgbe_type.h" #define IXGBE_I2C_EEPROM_DEV_ADDR 0xA0 +#define IXGBE_I2C_EEPROM_DEV_ADDR2 0xA2 /* EEPROM byte offsets */ -#define IXGBE_SFF_IDENTIFIER 0x0 -#define IXGBE_SFF_IDENTIFIER_SFP 0x3 -#define IXGBE_SFF_VENDOR_OUI_BYTE0 0x25 -#define IXGBE_SFF_VENDOR_OUI_BYTE1 0x26 -#define IXGBE_SFF_VENDOR_OUI_BYTE2 0x27 -#define IXGBE_SFF_1GBE_COMP_CODES 0x6 -#define IXGBE_SFF_10GBE_COMP_CODES 0x3 -#define IXGBE_SFF_CABLE_TECHNOLOGY 0x8 -#define IXGBE_SFF_CABLE_SPEC_COMP 0x3C +#define IXGBE_SFF_IDENTIFIER 0x0 +#define IXGBE_SFF_IDENTIFIER_SFP 0x3 +#define IXGBE_SFF_VENDOR_OUI_BYTE0 0x25 +#define IXGBE_SFF_VENDOR_OUI_BYTE1 0x26 +#define IXGBE_SFF_VENDOR_OUI_BYTE2 0x27 +#define IXGBE_SFF_1GBE_COMP_CODES 0x6 +#define IXGBE_SFF_10GBE_COMP_CODES 0x3 +#define IXGBE_SFF_CABLE_TECHNOLOGY 0x8 +#define IXGBE_SFF_CABLE_SPEC_COMP 0x3C +#define IXGBE_SFF_SFF_8472_SWAP 0x5C +#define IXGBE_SFF_SFF_8472_COMP 0x5E +#define IXGBE_SFF_SFF_8472_OSCB 0x6E +#define IXGBE_SFF_SFF_8472_ESCB 0x76 +#define IXGBE_SFF_IDENTIFIER_QSFP_PLUS 0xD +#define IXGBE_SFF_QSFP_VENDOR_OUI_BYTE0 0xA5 +#define IXGBE_SFF_QSFP_VENDOR_OUI_BYTE1 0xA6 +#define IXGBE_SFF_QSFP_VENDOR_OUI_BYTE2 0xA7 +#define IXGBE_SFF_QSFP_CONNECTOR 0x82 +#define IXGBE_SFF_QSFP_10GBE_COMP 0x83 +#define IXGBE_SFF_QSFP_1GBE_COMP 0x86 +#define IXGBE_SFF_QSFP_CABLE_LENGTH 0x92 +#define IXGBE_SFF_QSFP_DEVICE_TECH 0x93 /* Bitmasks */ -#define IXGBE_SFF_DA_PASSIVE_CABLE 0x4 -#define IXGBE_SFF_DA_ACTIVE_CABLE 0x8 -#define IXGBE_SFF_DA_SPEC_ACTIVE_LIMITING 0x4 -#define IXGBE_SFF_1GBASESX_CAPABLE 0x1 -#define IXGBE_SFF_1GBASELX_CAPABLE 0x2 -#define IXGBE_SFF_1GBASET_CAPABLE 0x8 -#define IXGBE_SFF_10GBASESR_CAPABLE 0x10 -#define IXGBE_SFF_10GBASELR_CAPABLE 0x20 -#define IXGBE_I2C_EEPROM_READ_MASK 0x100 -#define IXGBE_I2C_EEPROM_STATUS_MASK 0x3 -#define IXGBE_I2C_EEPROM_STATUS_NO_OPERATION 0x0 -#define IXGBE_I2C_EEPROM_STATUS_PASS 0x1 -#define IXGBE_I2C_EEPROM_STATUS_FAIL 0x2 -#define IXGBE_I2C_EEPROM_STATUS_IN_PROGRESS 0x3 - +#define IXGBE_SFF_DA_PASSIVE_CABLE 0x4 +#define IXGBE_SFF_DA_ACTIVE_CABLE 0x8 +#define IXGBE_SFF_DA_SPEC_ACTIVE_LIMITING 0x4 +#define IXGBE_SFF_1GBASESX_CAPABLE 0x1 +#define IXGBE_SFF_1GBASELX_CAPABLE 0x2 +#define IXGBE_SFF_1GBASET_CAPABLE 0x8 +#define IXGBE_SFF_10GBASESR_CAPABLE 0x10 +#define IXGBE_SFF_10GBASELR_CAPABLE 0x20 +#define IXGBE_SFF_ADDRESSING_MODE 0x4 +#define IXGBE_SFF_QSFP_DA_ACTIVE_CABLE 0x1 +#define IXGBE_SFF_QSFP_DA_PASSIVE_CABLE 0x8 +#define IXGBE_SFF_QSFP_CONNECTOR_NOT_SEPARABLE 0x23 +#define IXGBE_SFF_QSFP_TRANSMITER_850NM_VCSEL 0x0 +#define IXGBE_I2C_EEPROM_READ_MASK 0x100 +#define IXGBE_I2C_EEPROM_STATUS_MASK 0x3 +#define IXGBE_I2C_EEPROM_STATUS_NO_OPERATION 0x0 +#define IXGBE_I2C_EEPROM_STATUS_PASS 0x1 +#define IXGBE_I2C_EEPROM_STATUS_FAIL 0x2 +#define IXGBE_I2C_EEPROM_STATUS_IN_PROGRESS 0x3 /* Flow control defines */ #define IXGBE_TAF_SYM_PAUSE 0x400 #define IXGBE_TAF_ASM_PAUSE 0x800 @@ -88,44 +107,54 @@ #define IXGBE_TN_LASI_STATUS_REG 0x9005 #define IXGBE_TN_LASI_STATUS_TEMP_ALARM 0x0008 +/* SFP+ SFF-8472 Compliance code */ +#define IXGBE_SFF_SFF_8472_UNSUP 0x00 + s32 ixgbe_init_phy_ops_generic(struct ixgbe_hw *hw); s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw); s32 ixgbe_reset_phy_generic(struct ixgbe_hw *hw); s32 ixgbe_read_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, - u32 device_type, u16 *phy_data); + u32 device_type, u16 *phy_data); s32 ixgbe_write_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, - u32 device_type, u16 phy_data); + u32 device_type, u16 phy_data); +s32 ixgbe_read_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u16 *phy_data); +s32 ixgbe_write_phy_reg_mdi(struct ixgbe_hw *hw, u32 reg_addr, + u32 device_type, u16 phy_data); s32 ixgbe_setup_phy_link_generic(struct ixgbe_hw *hw); s32 ixgbe_setup_phy_link_speed_generic(struct ixgbe_hw *hw, - ixgbe_link_speed speed, - bool autoneg, - bool autoneg_wait_to_complete); + ixgbe_link_speed speed, + bool autoneg_wait_to_complete); s32 ixgbe_get_copper_link_capabilities_generic(struct ixgbe_hw *hw, - ixgbe_link_speed *speed, - bool *autoneg); + ixgbe_link_speed *speed, + bool *autoneg); +bool ixgbe_check_reset_blocked(struct ixgbe_hw *hw); /* PHY specific */ s32 ixgbe_check_phy_link_tnx(struct ixgbe_hw *hw, - ixgbe_link_speed *speed, - bool *link_up); + ixgbe_link_speed *speed, + bool *link_up); s32 ixgbe_setup_phy_link_tnx(struct ixgbe_hw *hw); s32 ixgbe_get_phy_firmware_version_tnx(struct ixgbe_hw *hw, - u16 *firmware_version); + u16 *firmware_version); s32 ixgbe_get_phy_firmware_version_generic(struct ixgbe_hw *hw, - u16 *firmware_version); + u16 *firmware_version); s32 ixgbe_reset_phy_nl(struct ixgbe_hw *hw); +s32 ixgbe_identify_module_generic(struct ixgbe_hw *hw); s32 ixgbe_identify_sfp_module_generic(struct ixgbe_hw *hw); s32 ixgbe_get_sfp_init_sequence_offsets(struct ixgbe_hw *hw, - u16 *list_offset, - u16 *data_offset); + u16 *list_offset, + u16 *data_offset); s32 ixgbe_tn_check_overtemp(struct ixgbe_hw *hw); s32 ixgbe_read_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset, - u8 dev_addr, u8 *data); + u8 dev_addr, u8 *data); s32 ixgbe_write_i2c_byte_generic(struct ixgbe_hw *hw, u8 byte_offset, - u8 dev_addr, u8 data); + u8 dev_addr, u8 data); s32 ixgbe_read_i2c_eeprom_generic(struct ixgbe_hw *hw, u8 byte_offset, - u8 *eeprom_data); + u8 *eeprom_data); +s32 ixgbe_read_i2c_sff8472_generic(struct ixgbe_hw *hw, u8 byte_offset, + u8 *sff8472_data); s32 ixgbe_write_i2c_eeprom_generic(struct ixgbe_hw *hw, u8 byte_offset, - u8 eeprom_data); + u8 eeprom_data); #endif /* _IXGBE_PHY_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c new file mode 100644 index 00000000000..68f87ecb8a7 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -0,0 +1,1007 @@ +/******************************************************************************* + + Intel 10 Gigabit PCI Express Linux driver + Copyright(c) 1999 - 2013 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/ptp_classify.h> + +/* + * The 82599 and the X540 do not have true 64bit nanosecond scale + * counter registers. Instead, SYSTIME is defined by a fixed point + * system which allows the user to define the scale counter increment + * value at every level change of the oscillator driving the SYSTIME + * value. For both devices the TIMINCA:IV field defines this + * increment. On the X540 device, 31 bits are provided. However on the + * 82599 only provides 24 bits. The time unit is determined by the + * clock frequency of the oscillator in combination with the TIMINCA + * register. When these devices link at 10Gb the oscillator has a + * period of 6.4ns. In order to convert the scale counter into + * nanoseconds the cyclecounter and timecounter structures are + * used. The SYSTIME registers need to be converted to ns values by use + * of only a right shift (division by power of 2). The following math + * determines the largest incvalue that will fit into the available + * bits in the TIMINCA register. + * + * PeriodWidth: Number of bits to store the clock period + * MaxWidth: The maximum width value of the TIMINCA register + * Period: The clock period for the oscillator + * round(): discard the fractional portion of the calculation + * + * Period * [ 2 ^ ( MaxWidth - PeriodWidth ) ] + * + * For the X540, MaxWidth is 31 bits, and the base period is 6.4 ns + * For the 82599, MaxWidth is 24 bits, and the base period is 6.4 ns + * + * The period also changes based on the link speed: + * At 10Gb link or no link, the period remains the same. + * At 1Gb link, the period is multiplied by 10. (64ns) + * At 100Mb link, the period is multiplied by 100. (640ns) + * + * The calculated value allows us to right shift the SYSTIME register + * value in order to quickly convert it into a nanosecond clock, + * while allowing for the maximum possible adjustment value. + * + * These diagrams are only for the 10Gb link period + * + * SYSTIMEH SYSTIMEL + * +--------------+ +--------------+ + * X540 | 32 | | 1 | 3 | 28 | + * *--------------+ +--------------+ + * \________ 36 bits ______/ fract + * + * +--------------+ +--------------+ + * 82599 | 32 | | 8 | 3 | 21 | + * *--------------+ +--------------+ + * \________ 43 bits ______/ fract + * + * The 36 bit X540 SYSTIME overflows every + * 2^36 * 10^-9 / 60 = 1.14 minutes or 69 seconds + * + * The 43 bit 82599 SYSTIME overflows every + * 2^43 * 10^-9 / 3600 = 2.4 hours + */ +#define IXGBE_INCVAL_10GB 0x66666666 +#define IXGBE_INCVAL_1GB 0x40000000 +#define IXGBE_INCVAL_100 0x50000000 + +#define IXGBE_INCVAL_SHIFT_10GB 28 +#define IXGBE_INCVAL_SHIFT_1GB 24 +#define IXGBE_INCVAL_SHIFT_100 21 + +#define IXGBE_INCVAL_SHIFT_82599 7 +#define IXGBE_INCPER_SHIFT_82599 24 +#define IXGBE_MAX_TIMEADJ_VALUE 0x7FFFFFFFFFFFFFFFULL + +#define IXGBE_OVERFLOW_PERIOD (HZ * 30) +#define IXGBE_PTP_TX_TIMEOUT (HZ * 15) + +#ifndef NSECS_PER_SEC +#define NSECS_PER_SEC 1000000000ULL +#endif + +/** + * ixgbe_ptp_setup_sdp + * @hw: the hardware private structure + * + * this function enables or disables the clock out feature on SDP0 for + * the X540 device. It will create a 1second periodic output that can + * be used as the PPS (via an interrupt). + * + * It calculates when the systime will be on an exact second, and then + * aligns the start of the PPS signal to that value. The shift is + * necessary because it can change based on the link speed. + */ +static void ixgbe_ptp_setup_sdp(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + int shift = adapter->cc.shift; + u32 esdp, tsauxc, clktiml, clktimh, trgttiml, trgttimh, rem; + u64 ns = 0, clock_edge = 0; + + if ((adapter->flags2 & IXGBE_FLAG2_PTP_PPS_ENABLED) && + (hw->mac.type == ixgbe_mac_X540)) { + + /* disable the pin first */ + IXGBE_WRITE_REG(hw, IXGBE_TSAUXC, 0x0); + IXGBE_WRITE_FLUSH(hw); + + esdp = IXGBE_READ_REG(hw, IXGBE_ESDP); + + /* + * enable the SDP0 pin as output, and connected to the + * native function for Timesync (ClockOut) + */ + esdp |= (IXGBE_ESDP_SDP0_DIR | + IXGBE_ESDP_SDP0_NATIVE); + + /* + * enable the Clock Out feature on SDP0, and allow + * interrupts to occur when the pin changes + */ + tsauxc = (IXGBE_TSAUXC_EN_CLK | + IXGBE_TSAUXC_SYNCLK | + IXGBE_TSAUXC_SDP0_INT); + + /* clock period (or pulse length) */ + clktiml = (u32)(NSECS_PER_SEC << shift); + clktimh = (u32)((NSECS_PER_SEC << shift) >> 32); + + /* + * Account for the cyclecounter wrap-around value by + * using the converted ns value of the current time to + * check for when the next aligned second would occur. + */ + clock_edge |= (u64)IXGBE_READ_REG(hw, IXGBE_SYSTIML); + clock_edge |= (u64)IXGBE_READ_REG(hw, IXGBE_SYSTIMH) << 32; + ns = timecounter_cyc2time(&adapter->tc, clock_edge); + + div_u64_rem(ns, NSECS_PER_SEC, &rem); + clock_edge += ((NSECS_PER_SEC - (u64)rem) << shift); + + /* specify the initial clock start time */ + trgttiml = (u32)clock_edge; + trgttimh = (u32)(clock_edge >> 32); + + IXGBE_WRITE_REG(hw, IXGBE_CLKTIML, clktiml); + IXGBE_WRITE_REG(hw, IXGBE_CLKTIMH, clktimh); + IXGBE_WRITE_REG(hw, IXGBE_TRGTTIML0, trgttiml); + IXGBE_WRITE_REG(hw, IXGBE_TRGTTIMH0, trgttimh); + + IXGBE_WRITE_REG(hw, IXGBE_ESDP, esdp); + IXGBE_WRITE_REG(hw, IXGBE_TSAUXC, tsauxc); + } else { + IXGBE_WRITE_REG(hw, IXGBE_TSAUXC, 0x0); + } + + IXGBE_WRITE_FLUSH(hw); +} + +/** + * ixgbe_ptp_read - read raw cycle counter (to be used by time counter) + * @cc: the cyclecounter structure + * + * this function reads the cyclecounter registers and is called by the + * cyclecounter structure used to construct a ns counter from the + * arbitrary fixed point registers + */ +static cycle_t ixgbe_ptp_read(const struct cyclecounter *cc) +{ + struct ixgbe_adapter *adapter = + container_of(cc, struct ixgbe_adapter, cc); + struct ixgbe_hw *hw = &adapter->hw; + u64 stamp = 0; + + stamp |= (u64)IXGBE_READ_REG(hw, IXGBE_SYSTIML); + stamp |= (u64)IXGBE_READ_REG(hw, IXGBE_SYSTIMH) << 32; + + return stamp; +} + +/** + * ixgbe_ptp_adjfreq + * @ptp: the ptp clock structure + * @ppb: parts per billion adjustment from base + * + * adjust the frequency of the ptp cycle counter by the + * indicated ppb from the base frequency. + */ +static int ixgbe_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +{ + struct ixgbe_adapter *adapter = + container_of(ptp, struct ixgbe_adapter, ptp_caps); + struct ixgbe_hw *hw = &adapter->hw; + u64 freq; + u32 diff, incval; + int neg_adj = 0; + + if (ppb < 0) { + neg_adj = 1; + ppb = -ppb; + } + + smp_mb(); + incval = ACCESS_ONCE(adapter->base_incval); + + freq = incval; + freq *= ppb; + diff = div_u64(freq, 1000000000ULL); + + incval = neg_adj ? (incval - diff) : (incval + diff); + + switch (hw->mac.type) { + case ixgbe_mac_X540: + IXGBE_WRITE_REG(hw, IXGBE_TIMINCA, incval); + break; + case ixgbe_mac_82599EB: + IXGBE_WRITE_REG(hw, IXGBE_TIMINCA, + (1 << IXGBE_INCPER_SHIFT_82599) | + incval); + break; + default: + break; + } + + return 0; +} + +/** + * ixgbe_ptp_adjtime + * @ptp: the ptp clock structure + * @delta: offset to adjust the cycle counter by + * + * adjust the timer by resetting the timecounter structure. + */ +static int ixgbe_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + struct ixgbe_adapter *adapter = + container_of(ptp, struct ixgbe_adapter, ptp_caps); + unsigned long flags; + u64 now; + + spin_lock_irqsave(&adapter->tmreg_lock, flags); + + now = timecounter_read(&adapter->tc); + now += delta; + + /* reset the timecounter */ + timecounter_init(&adapter->tc, + &adapter->cc, + now); + + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + + ixgbe_ptp_setup_sdp(adapter); + + return 0; +} + +/** + * ixgbe_ptp_gettime + * @ptp: the ptp clock structure + * @ts: timespec structure to hold the current time value + * + * read the timecounter and return the correct value on ns, + * after converting it into a struct timespec. + */ +static int ixgbe_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +{ + struct ixgbe_adapter *adapter = + container_of(ptp, struct ixgbe_adapter, ptp_caps); + u64 ns; + u32 remainder; + unsigned long flags; + + spin_lock_irqsave(&adapter->tmreg_lock, flags); + ns = timecounter_read(&adapter->tc); + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + + ts->tv_sec = div_u64_rem(ns, 1000000000ULL, &remainder); + ts->tv_nsec = remainder; + + return 0; +} + +/** + * ixgbe_ptp_settime + * @ptp: the ptp clock structure + * @ts: the timespec containing the new time for the cycle counter + * + * reset the timecounter to use a new base value instead of the kernel + * wall timer value. + */ +static int ixgbe_ptp_settime(struct ptp_clock_info *ptp, + const struct timespec *ts) +{ + struct ixgbe_adapter *adapter = + container_of(ptp, struct ixgbe_adapter, ptp_caps); + u64 ns; + unsigned long flags; + + ns = ts->tv_sec * 1000000000ULL; + ns += ts->tv_nsec; + + /* reset the timecounter */ + spin_lock_irqsave(&adapter->tmreg_lock, flags); + timecounter_init(&adapter->tc, &adapter->cc, ns); + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + + ixgbe_ptp_setup_sdp(adapter); + return 0; +} + +/** + * ixgbe_ptp_feature_enable + * @ptp: the ptp clock structure + * @rq: the requested feature to change + * @on: whether to enable or disable the feature + * + * enable (or disable) ancillary features of the phc subsystem. + * our driver only supports the PPS feature on the X540 + */ +static int ixgbe_ptp_feature_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on) +{ + struct ixgbe_adapter *adapter = + container_of(ptp, struct ixgbe_adapter, ptp_caps); + + /** + * When PPS is enabled, unmask the interrupt for the ClockOut + * feature, so that the interrupt handler can send the PPS + * event when the clock SDP triggers. Clear mask when PPS is + * disabled + */ + if (rq->type == PTP_CLK_REQ_PPS) { + switch (adapter->hw.mac.type) { + case ixgbe_mac_X540: + if (on) + adapter->flags2 |= IXGBE_FLAG2_PTP_PPS_ENABLED; + else + adapter->flags2 &= ~IXGBE_FLAG2_PTP_PPS_ENABLED; + + ixgbe_ptp_setup_sdp(adapter); + return 0; + default: + break; + } + } + + return -ENOTSUPP; +} + +/** + * ixgbe_ptp_check_pps_event + * @adapter: the private adapter structure + * @eicr: the interrupt cause register value + * + * This function is called by the interrupt routine when checking for + * interrupts. It will check and handle a pps event. + */ +void ixgbe_ptp_check_pps_event(struct ixgbe_adapter *adapter, u32 eicr) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct ptp_clock_event event; + + event.type = PTP_CLOCK_PPS; + + /* this check is necessary in case the interrupt was enabled via some + * alternative means (ex. debug_fs). Better to check here than + * everywhere that calls this function. + */ + if (!adapter->ptp_clock) + return; + + switch (hw->mac.type) { + case ixgbe_mac_X540: + ptp_clock_event(adapter->ptp_clock, &event); + break; + default: + break; + } +} + +/** + * ixgbe_ptp_overflow_check - watchdog task to detect SYSTIME overflow + * @adapter: private adapter struct + * + * this watchdog task periodically reads the timecounter + * in order to prevent missing when the system time registers wrap + * around. This needs to be run approximately twice a minute. + */ +void ixgbe_ptp_overflow_check(struct ixgbe_adapter *adapter) +{ + bool timeout = time_is_before_jiffies(adapter->last_overflow_check + + IXGBE_OVERFLOW_PERIOD); + struct timespec ts; + + if (timeout) { + ixgbe_ptp_gettime(&adapter->ptp_caps, &ts); + adapter->last_overflow_check = jiffies; + } +} + +/** + * ixgbe_ptp_rx_hang - detect error case when Rx timestamp registers latched + * @adapter: private network adapter structure + * + * this watchdog task is scheduled to detect error case where hardware has + * dropped an Rx packet that was timestamped when the ring is full. The + * particular error is rare but leaves the device in a state unable to timestamp + * any future packets. + */ +void ixgbe_ptp_rx_hang(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 tsyncrxctl = IXGBE_READ_REG(hw, IXGBE_TSYNCRXCTL); + unsigned long rx_event; + + /* if we don't have a valid timestamp in the registers, just update the + * timeout counter and exit + */ + if (!(tsyncrxctl & IXGBE_TSYNCRXCTL_VALID)) { + adapter->last_rx_ptp_check = jiffies; + return; + } + + /* determine the most recent watchdog or rx_timestamp event */ + rx_event = adapter->last_rx_ptp_check; + if (time_after(adapter->last_rx_timestamp, rx_event)) + rx_event = adapter->last_rx_timestamp; + + /* only need to read the high RXSTMP register to clear the lock */ + if (time_is_before_jiffies(rx_event + 5*HZ)) { + IXGBE_READ_REG(hw, IXGBE_RXSTMPH); + adapter->last_rx_ptp_check = jiffies; + + e_warn(drv, "clearing RX Timestamp hang\n"); + } +} + +/** + * ixgbe_ptp_tx_hwtstamp - utility function which checks for TX time stamp + * @adapter: the private adapter struct + * + * if the timestamp is valid, we convert it into the timecounter ns + * value, then store that result into the shhwtstamps structure which + * is passed up the network stack + */ +static void ixgbe_ptp_tx_hwtstamp(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct skb_shared_hwtstamps shhwtstamps; + u64 regval = 0, ns; + unsigned long flags; + + regval |= (u64)IXGBE_READ_REG(hw, IXGBE_TXSTMPL); + regval |= (u64)IXGBE_READ_REG(hw, IXGBE_TXSTMPH) << 32; + + spin_lock_irqsave(&adapter->tmreg_lock, flags); + ns = timecounter_cyc2time(&adapter->tc, regval); + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + + memset(&shhwtstamps, 0, sizeof(shhwtstamps)); + shhwtstamps.hwtstamp = ns_to_ktime(ns); + skb_tstamp_tx(adapter->ptp_tx_skb, &shhwtstamps); + + dev_kfree_skb_any(adapter->ptp_tx_skb); + adapter->ptp_tx_skb = NULL; + clear_bit_unlock(__IXGBE_PTP_TX_IN_PROGRESS, &adapter->state); +} + +/** + * ixgbe_ptp_tx_hwtstamp_work + * @work: pointer to the work struct + * + * This work item polls TSYNCTXCTL valid bit to determine when a Tx hardware + * timestamp has been taken for the current skb. It is necesary, because the + * descriptor's "done" bit does not correlate with the timestamp event. + */ +static void ixgbe_ptp_tx_hwtstamp_work(struct work_struct *work) +{ + struct ixgbe_adapter *adapter = container_of(work, struct ixgbe_adapter, + ptp_tx_work); + struct ixgbe_hw *hw = &adapter->hw; + bool timeout = time_is_before_jiffies(adapter->ptp_tx_start + + IXGBE_PTP_TX_TIMEOUT); + u32 tsynctxctl; + + if (timeout) { + dev_kfree_skb_any(adapter->ptp_tx_skb); + adapter->ptp_tx_skb = NULL; + clear_bit_unlock(__IXGBE_PTP_TX_IN_PROGRESS, &adapter->state); + e_warn(drv, "clearing Tx Timestamp hang\n"); + return; + } + + tsynctxctl = IXGBE_READ_REG(hw, IXGBE_TSYNCTXCTL); + if (tsynctxctl & IXGBE_TSYNCTXCTL_VALID) + ixgbe_ptp_tx_hwtstamp(adapter); + else + /* reschedule to keep checking if it's not available yet */ + schedule_work(&adapter->ptp_tx_work); +} + +/** + * ixgbe_ptp_rx_hwtstamp - utility function which checks for RX time stamp + * @adapter: pointer to adapter struct + * @skb: particular skb to send timestamp with + * + * if the timestamp is valid, we convert it into the timecounter ns + * value, then store that result into the shhwtstamps structure which + * is passed up the network stack + */ +void ixgbe_ptp_rx_hwtstamp(struct ixgbe_adapter *adapter, struct sk_buff *skb) +{ + struct ixgbe_hw *hw = &adapter->hw; + struct skb_shared_hwtstamps *shhwtstamps; + u64 regval = 0, ns; + u32 tsyncrxctl; + unsigned long flags; + + tsyncrxctl = IXGBE_READ_REG(hw, IXGBE_TSYNCRXCTL); + if (!(tsyncrxctl & IXGBE_TSYNCRXCTL_VALID)) + return; + + regval |= (u64)IXGBE_READ_REG(hw, IXGBE_RXSTMPL); + regval |= (u64)IXGBE_READ_REG(hw, IXGBE_RXSTMPH) << 32; + + spin_lock_irqsave(&adapter->tmreg_lock, flags); + ns = timecounter_cyc2time(&adapter->tc, regval); + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + + shhwtstamps = skb_hwtstamps(skb); + shhwtstamps->hwtstamp = ns_to_ktime(ns); + + /* Update the last_rx_timestamp timer in order to enable watchdog check + * for error case of latched timestamp on a dropped packet. + */ + adapter->last_rx_timestamp = jiffies; +} + +int ixgbe_ptp_get_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr) +{ + struct hwtstamp_config *config = &adapter->tstamp_config; + + return copy_to_user(ifr->ifr_data, config, + sizeof(*config)) ? -EFAULT : 0; +} + +/** + * ixgbe_ptp_set_timestamp_mode - setup the hardware for the requested mode + * @adapter: the private ixgbe adapter structure + * @config: the hwtstamp configuration requested + * + * Outgoing time stamping can be enabled and disabled. Play nice and + * disable it when requested, although it shouldn't cause any overhead + * when no packet needs it. At most one packet in the queue may be + * marked for time stamping, otherwise it would be impossible to tell + * for sure to which packet the hardware time stamp belongs. + * + * Incoming time stamping has to be configured via the hardware + * filters. Not all combinations are supported, in particular event + * type has to be specified. Matching the kind of event packet is + * not supported, with the exception of "all V2 events regardless of + * level 2 or 4". + * + * Since hardware always timestamps Path delay packets when timestamping V2 + * packets, regardless of the type specified in the register, only use V2 + * Event mode. This more accurately tells the user what the hardware is going + * to do anyways. + * + * Note: this may modify the hwtstamp configuration towards a more general + * mode, if required to support the specifically requested mode. + */ +static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter, + struct hwtstamp_config *config) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 tsync_tx_ctl = IXGBE_TSYNCTXCTL_ENABLED; + u32 tsync_rx_ctl = IXGBE_TSYNCRXCTL_ENABLED; + u32 tsync_rx_mtrl = PTP_EV_PORT << 16; + bool is_l2 = false; + u32 regval; + + /* reserved for future extensions */ + if (config->flags) + return -EINVAL; + + switch (config->tx_type) { + case HWTSTAMP_TX_OFF: + tsync_tx_ctl = 0; + case HWTSTAMP_TX_ON: + break; + default: + return -ERANGE; + } + + switch (config->rx_filter) { + case HWTSTAMP_FILTER_NONE: + tsync_rx_ctl = 0; + tsync_rx_mtrl = 0; + break; + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L4_V1; + tsync_rx_mtrl |= IXGBE_RXMTRL_V1_SYNC_MSG; + break; + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_L4_V1; + tsync_rx_mtrl |= IXGBE_RXMTRL_V1_DELAY_REQ_MSG; + break; + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + tsync_rx_ctl |= IXGBE_TSYNCRXCTL_TYPE_EVENT_V2; + is_l2 = true; + config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + break; + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_ALL: + default: + /* + * register RXMTRL must be set in order to do V1 packets, + * therefore it is not possible to time stamp both V1 Sync and + * Delay_Req messages and hardware does not support + * timestamping all packets => return error + */ + config->rx_filter = HWTSTAMP_FILTER_NONE; + return -ERANGE; + } + + if (hw->mac.type == ixgbe_mac_82598EB) { + if (tsync_rx_ctl | tsync_tx_ctl) + return -ERANGE; + return 0; + } + + /* define ethertype filter for timestamping L2 packets */ + if (is_l2) + IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_1588), + (IXGBE_ETQF_FILTER_EN | /* enable filter */ + IXGBE_ETQF_1588 | /* enable timestamping */ + ETH_P_1588)); /* 1588 eth protocol type */ + else + IXGBE_WRITE_REG(hw, IXGBE_ETQF(IXGBE_ETQF_FILTER_1588), 0); + + /* enable/disable TX */ + regval = IXGBE_READ_REG(hw, IXGBE_TSYNCTXCTL); + regval &= ~IXGBE_TSYNCTXCTL_ENABLED; + regval |= tsync_tx_ctl; + IXGBE_WRITE_REG(hw, IXGBE_TSYNCTXCTL, regval); + + /* enable/disable RX */ + regval = IXGBE_READ_REG(hw, IXGBE_TSYNCRXCTL); + regval &= ~(IXGBE_TSYNCRXCTL_ENABLED | IXGBE_TSYNCRXCTL_TYPE_MASK); + regval |= tsync_rx_ctl; + IXGBE_WRITE_REG(hw, IXGBE_TSYNCRXCTL, regval); + + /* define which PTP packets are time stamped */ + IXGBE_WRITE_REG(hw, IXGBE_RXMTRL, tsync_rx_mtrl); + + IXGBE_WRITE_FLUSH(hw); + + /* clear TX/RX time stamp registers, just to be sure */ + regval = IXGBE_READ_REG(hw, IXGBE_TXSTMPH); + regval = IXGBE_READ_REG(hw, IXGBE_RXSTMPH); + + return 0; +} + +/** + * ixgbe_ptp_set_ts_config - user entry point for timestamp mode + * @adapter: pointer to adapter struct + * @ifreq: ioctl data + * + * Set hardware to requested mode. If unsupported, return an error with no + * changes. Otherwise, store the mode for future reference. + */ +int ixgbe_ptp_set_ts_config(struct ixgbe_adapter *adapter, struct ifreq *ifr) +{ + struct hwtstamp_config config; + int err; + + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) + return -EFAULT; + + err = ixgbe_ptp_set_timestamp_mode(adapter, &config); + if (err) + return err; + + /* save these settings for future reference */ + memcpy(&adapter->tstamp_config, &config, + sizeof(adapter->tstamp_config)); + + return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? + -EFAULT : 0; +} + +/** + * ixgbe_ptp_start_cyclecounter - create the cycle counter from hw + * @adapter: pointer to the adapter structure + * + * This function should be called to set the proper values for the TIMINCA + * register and tell the cyclecounter structure what the tick rate of SYSTIME + * is. It does not directly modify SYSTIME registers or the timecounter + * structure. It should be called whenever a new TIMINCA value is necessary, + * such as during initialization or when the link speed changes. + */ +void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 incval = 0; + u32 shift = 0; + unsigned long flags; + + /** + * Scale the NIC cycle counter by a large factor so that + * relatively small corrections to the frequency can be added + * or subtracted. The drawbacks of a large factor include + * (a) the clock register overflows more quickly, (b) the cycle + * counter structure must be able to convert the systime value + * to nanoseconds using only a multiplier and a right-shift, + * and (c) the value must fit within the timinca register space + * => math based on internal DMA clock rate and available bits + * + * Note that when there is no link, internal DMA clock is same as when + * link speed is 10Gb. Set the registers correctly even when link is + * down to preserve the clock setting + */ + switch (adapter->link_speed) { + case IXGBE_LINK_SPEED_100_FULL: + incval = IXGBE_INCVAL_100; + shift = IXGBE_INCVAL_SHIFT_100; + break; + case IXGBE_LINK_SPEED_1GB_FULL: + incval = IXGBE_INCVAL_1GB; + shift = IXGBE_INCVAL_SHIFT_1GB; + break; + case IXGBE_LINK_SPEED_10GB_FULL: + default: + incval = IXGBE_INCVAL_10GB; + shift = IXGBE_INCVAL_SHIFT_10GB; + break; + } + + /** + * Modify the calculated values to fit within the correct + * number of bits specified by the hardware. The 82599 doesn't + * have the same space as the X540, so bitshift the calculated + * values to fit. + */ + switch (hw->mac.type) { + case ixgbe_mac_X540: + IXGBE_WRITE_REG(hw, IXGBE_TIMINCA, incval); + break; + case ixgbe_mac_82599EB: + incval >>= IXGBE_INCVAL_SHIFT_82599; + shift -= IXGBE_INCVAL_SHIFT_82599; + IXGBE_WRITE_REG(hw, IXGBE_TIMINCA, + (1 << IXGBE_INCPER_SHIFT_82599) | + incval); + break; + default: + /* other devices aren't supported */ + return; + } + + /* update the base incval used to calculate frequency adjustment */ + ACCESS_ONCE(adapter->base_incval) = incval; + smp_mb(); + + /* need lock to prevent incorrect read while modifying cyclecounter */ + spin_lock_irqsave(&adapter->tmreg_lock, flags); + + memset(&adapter->cc, 0, sizeof(adapter->cc)); + adapter->cc.read = ixgbe_ptp_read; + adapter->cc.mask = CLOCKSOURCE_MASK(64); + adapter->cc.shift = shift; + adapter->cc.mult = 1; + + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); +} + +/** + * ixgbe_ptp_reset + * @adapter: the ixgbe private board structure + * + * When the MAC resets, all the hardware bits for timesync are reset. This + * function is used to re-enable the device for PTP based on current settings. + * We do lose the current clock time, so just reset the cyclecounter to the + * system real clock time. + * + * This function will maintain hwtstamp_config settings, and resets the SDP + * output if it was enabled. + */ +void ixgbe_ptp_reset(struct ixgbe_adapter *adapter) +{ + struct ixgbe_hw *hw = &adapter->hw; + unsigned long flags; + + /* set SYSTIME registers to 0 just in case */ + IXGBE_WRITE_REG(hw, IXGBE_SYSTIML, 0x00000000); + IXGBE_WRITE_REG(hw, IXGBE_SYSTIMH, 0x00000000); + IXGBE_WRITE_FLUSH(hw); + + /* reset the hardware timestamping mode */ + ixgbe_ptp_set_timestamp_mode(adapter, &adapter->tstamp_config); + + ixgbe_ptp_start_cyclecounter(adapter); + + spin_lock_irqsave(&adapter->tmreg_lock, flags); + + /* reset the ns time counter */ + timecounter_init(&adapter->tc, &adapter->cc, + ktime_to_ns(ktime_get_real())); + + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + + /* + * Now that the shift has been calculated and the systime + * registers reset, (re-)enable the Clock out feature + */ + ixgbe_ptp_setup_sdp(adapter); +} + +/** + * ixgbe_ptp_create_clock + * @adapter: the ixgbe private adapter structure + * + * This function performs setup of the user entry point function table and + * initializes the PTP clock device, which is used to access the clock-like + * features of the PTP core. It will be called by ixgbe_ptp_init, only if + * there isn't already a clock device (such as after a suspend/resume cycle, + * where the clock device wasn't destroyed). + */ +static int ixgbe_ptp_create_clock(struct ixgbe_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + long err; + + /* do nothing if we already have a clock device */ + if (!IS_ERR_OR_NULL(adapter->ptp_clock)) + return 0; + + switch (adapter->hw.mac.type) { + case ixgbe_mac_X540: + snprintf(adapter->ptp_caps.name, + sizeof(adapter->ptp_caps.name), + "%s", netdev->name); + adapter->ptp_caps.owner = THIS_MODULE; + adapter->ptp_caps.max_adj = 250000000; + adapter->ptp_caps.n_alarm = 0; + adapter->ptp_caps.n_ext_ts = 0; + adapter->ptp_caps.n_per_out = 0; + adapter->ptp_caps.pps = 1; + adapter->ptp_caps.adjfreq = ixgbe_ptp_adjfreq; + adapter->ptp_caps.adjtime = ixgbe_ptp_adjtime; + adapter->ptp_caps.gettime = ixgbe_ptp_gettime; + adapter->ptp_caps.settime = ixgbe_ptp_settime; + adapter->ptp_caps.enable = ixgbe_ptp_feature_enable; + break; + case ixgbe_mac_82599EB: + snprintf(adapter->ptp_caps.name, + sizeof(adapter->ptp_caps.name), + "%s", netdev->name); + adapter->ptp_caps.owner = THIS_MODULE; + adapter->ptp_caps.max_adj = 250000000; + adapter->ptp_caps.n_alarm = 0; + adapter->ptp_caps.n_ext_ts = 0; + adapter->ptp_caps.n_per_out = 0; + adapter->ptp_caps.pps = 0; + adapter->ptp_caps.adjfreq = ixgbe_ptp_adjfreq; + adapter->ptp_caps.adjtime = ixgbe_ptp_adjtime; + adapter->ptp_caps.gettime = ixgbe_ptp_gettime; + adapter->ptp_caps.settime = ixgbe_ptp_settime; + adapter->ptp_caps.enable = ixgbe_ptp_feature_enable; + break; + default: + adapter->ptp_clock = NULL; + return -EOPNOTSUPP; + } + + adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps, + &adapter->pdev->dev); + if (IS_ERR(adapter->ptp_clock)) { + err = PTR_ERR(adapter->ptp_clock); + adapter->ptp_clock = NULL; + e_dev_err("ptp_clock_register failed\n"); + return err; + } else + e_dev_info("registered PHC device on %s\n", netdev->name); + + /* set default timestamp mode to disabled here. We do this in + * create_clock instead of init, because we don't want to override the + * previous settings during a resume cycle. + */ + adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; + adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF; + + return 0; +} + +/** + * ixgbe_ptp_init + * @adapter: the ixgbe private adapter structure + * + * This function performs the required steps for enabling PTP + * support. If PTP support has already been loaded it simply calls the + * cyclecounter init routine and exits. + */ +void ixgbe_ptp_init(struct ixgbe_adapter *adapter) +{ + /* initialize the spin lock first since we can't control when a user + * will call the entry functions once we have initialized the clock + * device + */ + spin_lock_init(&adapter->tmreg_lock); + + /* obtain a PTP device, or re-use an existing device */ + if (ixgbe_ptp_create_clock(adapter)) + return; + + /* we have a clock so we can initialize work now */ + INIT_WORK(&adapter->ptp_tx_work, ixgbe_ptp_tx_hwtstamp_work); + + /* reset the PTP related hardware bits */ + ixgbe_ptp_reset(adapter); + + /* enter the IXGBE_PTP_RUNNING state */ + set_bit(__IXGBE_PTP_RUNNING, &adapter->state); + + return; +} + +/** + * ixgbe_ptp_suspend - stop PTP work items + * @ adapter: pointer to adapter struct + * + * this function suspends PTP activity, and prevents more PTP work from being + * generated, but does not destroy the PTP clock device. + */ +void ixgbe_ptp_suspend(struct ixgbe_adapter *adapter) +{ + /* Leave the IXGBE_PTP_RUNNING state. */ + if (!test_and_clear_bit(__IXGBE_PTP_RUNNING, &adapter->state)) + return; + + /* since this might be called in suspend, we don't clear the state, + * but simply reset the auxiliary PPS signal control register + */ + IXGBE_WRITE_REG(&adapter->hw, IXGBE_TSAUXC, 0x0); + + /* ensure that we cancel any pending PTP Tx work item in progress */ + cancel_work_sync(&adapter->ptp_tx_work); + if (adapter->ptp_tx_skb) { + dev_kfree_skb_any(adapter->ptp_tx_skb); + adapter->ptp_tx_skb = NULL; + clear_bit_unlock(__IXGBE_PTP_TX_IN_PROGRESS, &adapter->state); + } +} + +/** + * ixgbe_ptp_stop - close the PTP device + * @adapter: pointer to adapter struct + * + * completely destroy the PTP device, should only be called when the device is + * being fully closed. + */ +void ixgbe_ptp_stop(struct ixgbe_adapter *adapter) +{ + /* first, suspend PTP activity */ + ixgbe_ptp_suspend(adapter); + + /* disable the PTP clock device */ + if (adapter->ptp_clock) { + ptp_clock_unregister(adapter->ptp_clock); + adapter->ptp_clock = NULL; + e_dev_info("removed PHC on %s\n", + adapter->netdev->name); + } +} diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index b01ecb4d2bb..16b3a1cd9db 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2013 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, @@ -20,6 +20,7 @@ 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 @@ -35,7 +36,7 @@ #include <linux/ip.h> #include <linux/tcp.h> #include <linux/ipv6.h> -#ifdef NETIF_F_HW_VLAN_TX +#ifdef NETIF_F_HW_VLAN_CTAG_TX #include <linux/if_vlan.h> #endif @@ -44,78 +45,21 @@ #include "ixgbe_sriov.h" #ifdef CONFIG_PCI_IOV -static int ixgbe_find_enabled_vfs(struct ixgbe_adapter *adapter) -{ - struct pci_dev *pdev = adapter->pdev; - struct pci_dev *pvfdev; - u16 vf_devfn = 0; - int device_id; - int vfs_found = 0; - - switch (adapter->hw.mac.type) { - case ixgbe_mac_82599EB: - device_id = IXGBE_DEV_ID_82599_VF; - break; - case ixgbe_mac_X540: - device_id = IXGBE_DEV_ID_X540_VF; - break; - default: - device_id = 0; - break; - } - - vf_devfn = pdev->devfn + 0x80; - pvfdev = pci_get_device(IXGBE_INTEL_VENDOR_ID, device_id, NULL); - while (pvfdev) { - if (pvfdev->devfn == vf_devfn && - (pvfdev->bus->number >= pdev->bus->number)) - vfs_found++; - vf_devfn += 2; - pvfdev = pci_get_device(IXGBE_INTEL_VENDOR_ID, - device_id, pvfdev); - } - - return vfs_found; -} - -void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, - const struct ixgbe_info *ii) +static int __ixgbe_enable_sriov(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - int err = 0; int num_vf_macvlans, i; struct vf_macvlans *mv_list; - int pre_existing_vfs = 0; - pre_existing_vfs = ixgbe_find_enabled_vfs(adapter); - if (!pre_existing_vfs && !adapter->num_vfs) - return; - - /* If there are pre-existing VFs then we have to force - * use of that many because they were not deleted the last - * time someone removed the PF driver. That would have - * been because they were allocated to guest VMs and can't - * be removed. Go ahead and just re-enable the old amount. - * If the user wants to change the number of VFs they can - * use ethtool while making sure no VFs are allocated to - * guest VMs... i.e. the right way. - */ - if (pre_existing_vfs) { - adapter->num_vfs = pre_existing_vfs; - dev_warn(&adapter->pdev->dev, "Virtual Functions already " - "enabled for this device - Please reload all " - "VF drivers to avoid spoofed packet errors\n"); - } else { - err = pci_enable_sriov(adapter->pdev, adapter->num_vfs); - } - if (err) { - e_err(probe, "Failed to enable PCI sriov: %d\n", err); - goto err_novfs; - } adapter->flags |= IXGBE_FLAG_SRIOV_ENABLED; - e_info(probe, "SR-IOV enabled with %d VFs\n", adapter->num_vfs); + /* Enable VMDq flag so device will be set in VM mode */ + adapter->flags |= IXGBE_FLAG_VMDQ_ENABLED; + if (!adapter->ring_feature[RING_F_VMDQ].limit) + adapter->ring_feature[RING_F_VMDQ].limit = 1; + adapter->ring_feature[RING_F_VMDQ].offset = adapter->num_vfs; + num_vf_macvlans = hw->mac.num_rar_entries - (IXGBE_MAX_PF_MACVLANS + 1 + adapter->num_vfs); @@ -128,13 +72,15 @@ void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, for (i = 0; i < num_vf_macvlans; i++) { mv_list->vf = -1; mv_list->free = true; - mv_list->rar_entry = hw->mac.num_rar_entries - - (i + adapter->num_vfs + 1); list_add(&mv_list->l, &adapter->vf_mvs.l); mv_list++; } } + /* Initialize default switching mode VEB */ + IXGBE_WRITE_REG(hw, IXGBE_PFDTXGSWC, IXGBE_PFDTXGSWC_VT_LBEN); + adapter->flags2 |= IXGBE_FLAG2_BRIDGE_MODE_VEB; + /* If call to enable VFs succeeded then allocate memory * for per VF control structures. */ @@ -142,49 +88,125 @@ void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, kcalloc(adapter->num_vfs, sizeof(struct vf_data_storage), GFP_KERNEL); if (adapter->vfinfo) { - /* Now that we're sure SR-IOV is enabled - * and memory allocated set up the mailbox parameters - */ - ixgbe_init_mbx_params_pf(hw); - memcpy(&hw->mbx.ops, ii->mbx_ops, - sizeof(hw->mbx.ops)); + /* limit trafffic classes based on VFs enabled */ + if ((adapter->hw.mac.type == ixgbe_mac_82599EB) && + (adapter->num_vfs < 16)) { + adapter->dcb_cfg.num_tcs.pg_tcs = MAX_TRAFFIC_CLASS; + adapter->dcb_cfg.num_tcs.pfc_tcs = MAX_TRAFFIC_CLASS; + } else if (adapter->num_vfs < 32) { + adapter->dcb_cfg.num_tcs.pg_tcs = 4; + adapter->dcb_cfg.num_tcs.pfc_tcs = 4; + } else { + adapter->dcb_cfg.num_tcs.pg_tcs = 1; + adapter->dcb_cfg.num_tcs.pfc_tcs = 1; + } + + /* We do not support RSS w/ SR-IOV */ + adapter->ring_feature[RING_F_RSS].limit = 1; /* Disable RSC when in SR-IOV mode */ adapter->flags2 &= ~(IXGBE_FLAG2_RSC_CAPABLE | IXGBE_FLAG2_RSC_ENABLED); + + /* enable spoof checking for all VFs */ for (i = 0; i < adapter->num_vfs; i++) adapter->vfinfo[i].spoofchk_enabled = true; + return 0; + } + + return -ENOMEM; +} + +/* Note this function is called when the user wants to enable SR-IOV + * VFs using the now deprecated module parameter + */ +void ixgbe_enable_sriov(struct ixgbe_adapter *adapter) +{ + int pre_existing_vfs = 0; + + pre_existing_vfs = pci_num_vf(adapter->pdev); + if (!pre_existing_vfs && !adapter->num_vfs) return; + + /* If there are pre-existing VFs then we have to force + * use of that many - over ride any module parameter value. + * This may result from the user unloading the PF driver + * while VFs were assigned to guest VMs or because the VFs + * have been created via the new PCI SR-IOV sysfs interface. + */ + if (pre_existing_vfs) { + adapter->num_vfs = pre_existing_vfs; + dev_warn(&adapter->pdev->dev, + "Virtual Functions already enabled for this device - Please reload all VF drivers to avoid spoofed packet errors\n"); + } else { + int err; + /* + * The 82599 supports up to 64 VFs per physical function + * but this implementation limits allocation to 63 so that + * basic networking resources are still available to the + * physical function. If the user requests greater thn + * 63 VFs then it is an error - reset to default of zero. + */ + adapter->num_vfs = min_t(unsigned int, adapter->num_vfs, IXGBE_MAX_VFS_DRV_LIMIT); + + err = pci_enable_sriov(adapter->pdev, adapter->num_vfs); + if (err) { + e_err(probe, "Failed to enable PCI sriov: %d\n", err); + adapter->num_vfs = 0; + return; + } } - /* Oh oh */ + if (!__ixgbe_enable_sriov(adapter)) + return; + + /* If we have gotten to this point then there is no memory available + * to manage the VF devices - print message and bail. + */ e_err(probe, "Unable to allocate memory for VF Data Storage - " "SRIOV disabled\n"); - pci_disable_sriov(adapter->pdev); - -err_novfs: - adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED; - adapter->num_vfs = 0; + ixgbe_disable_sriov(adapter); } -#endif /* #ifdef CONFIG_PCI_IOV */ -void ixgbe_disable_sriov(struct ixgbe_adapter *adapter) +#endif /* #ifdef CONFIG_PCI_IOV */ +int ixgbe_disable_sriov(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - u32 gcr; u32 gpie; u32 vmdctl; - int i; + int rss; + + /* set num VFs to 0 to prevent access to vfinfo */ + adapter->num_vfs = 0; + + /* free VF control structures */ + kfree(adapter->vfinfo); + adapter->vfinfo = NULL; + + /* free macvlan list */ + kfree(adapter->mv_list); + adapter->mv_list = NULL; + + /* if SR-IOV is already disabled then there is nothing to do */ + if (!(adapter->flags & IXGBE_FLAG_SRIOV_ENABLED)) + return 0; #ifdef CONFIG_PCI_IOV + /* + * If our VFs are assigned we cannot shut down SR-IOV + * without causing issues, so just leave the hardware + * available but disabled + */ + if (pci_vfs_assigned(adapter->pdev)) { + e_dev_warn("Unloading driver while VFs are assigned - VFs will not be deallocated\n"); + return -EPERM; + } /* disable iov and allow time for transactions to clear */ pci_disable_sriov(adapter->pdev); #endif /* 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); + IXGBE_WRITE_REG(hw, IXGBE_GCR_EXT, 0); gpie = IXGBE_READ_REG(hw, IXGBE_GPIE); gpie &= ~IXGBE_GPIE_VTMODE_MASK; IXGBE_WRITE_REG(hw, IXGBE_GPIE, gpie); @@ -195,31 +217,115 @@ void ixgbe_disable_sriov(struct ixgbe_adapter *adapter) IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, vmdctl); IXGBE_WRITE_FLUSH(hw); + /* Disable VMDq flag so device will be set in VM mode */ + if (adapter->ring_feature[RING_F_VMDQ].limit == 1) { + adapter->flags &= ~IXGBE_FLAG_VMDQ_ENABLED; + adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED; + rss = min_t(int, IXGBE_MAX_RSS_INDICES, num_online_cpus()); + } else { + rss = min_t(int, IXGBE_MAX_L2A_QUEUES, num_online_cpus()); + } + + adapter->ring_feature[RING_F_VMDQ].offset = 0; + adapter->ring_feature[RING_F_RSS].limit = rss; + /* take a breather then clean up driver data */ msleep(100); + return 0; +} - /* Release reference to VF devices */ - for (i = 0; i < adapter->num_vfs; i++) { - if (adapter->vfinfo[i].vfdev) - pci_dev_put(adapter->vfinfo[i].vfdev); +static int ixgbe_pci_sriov_enable(struct pci_dev *dev, int num_vfs) +{ +#ifdef CONFIG_PCI_IOV + struct ixgbe_adapter *adapter = pci_get_drvdata(dev); + int err = 0; + int i; + int pre_existing_vfs = pci_num_vf(dev); + + if (pre_existing_vfs && pre_existing_vfs != num_vfs) + err = ixgbe_disable_sriov(adapter); + else if (pre_existing_vfs && pre_existing_vfs == num_vfs) + goto out; + + if (err) + goto err_out; + + /* While the SR-IOV capability structure reports total VFs to be + * 64 we limit the actual number that can be allocated to 63 so + * that some transmit/receive resources can be reserved to the + * PF. The PCI bus driver already checks for other values out of + * range. + */ + if (num_vfs > IXGBE_MAX_VFS_DRV_LIMIT) { + err = -EPERM; + goto err_out; } - kfree(adapter->vfinfo); - kfree(adapter->mv_list); - adapter->vfinfo = NULL; - adapter->num_vfs = 0; - adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED; + adapter->num_vfs = num_vfs; + + err = __ixgbe_enable_sriov(adapter); + if (err) + goto err_out; + + for (i = 0; i < adapter->num_vfs; i++) + ixgbe_vf_configuration(dev, (i | 0x10000000)); + + err = pci_enable_sriov(dev, num_vfs); + if (err) { + e_dev_warn("Failed to enable PCI sriov: %d\n", err); + goto err_out; + } + ixgbe_sriov_reinit(adapter); + +out: + return num_vfs; + +err_out: + return err; +#endif + return 0; +} + +static int ixgbe_pci_sriov_disable(struct pci_dev *dev) +{ + struct ixgbe_adapter *adapter = pci_get_drvdata(dev); + int err; +#ifdef CONFIG_PCI_IOV + u32 current_flags = adapter->flags; +#endif + + err = ixgbe_disable_sriov(adapter); + + /* Only reinit if no error and state changed */ +#ifdef CONFIG_PCI_IOV + if (!err && current_flags != adapter->flags) + ixgbe_sriov_reinit(adapter); +#endif + + return err; +} + +int ixgbe_pci_sriov_configure(struct pci_dev *dev, int num_vfs) +{ + if (num_vfs == 0) + return ixgbe_pci_sriov_disable(dev); + else + return ixgbe_pci_sriov_enable(dev, num_vfs); } static int ixgbe_set_vf_multicasts(struct ixgbe_adapter *adapter, - int entries, u16 *hash_list, u32 vf) + u32 *msgbuf, u32 vf) { + int entries = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) + >> IXGBE_VT_MSGINFO_SHIFT; + u16 *hash_list = (u16 *)&msgbuf[1]; struct vf_data_storage *vfinfo = &adapter->vfinfo[vf]; struct ixgbe_hw *hw = &adapter->hw; int i; u32 vector_bit; u32 vector_reg; u32 mta_reg; + u32 vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(vf)); /* only so many hash values supported */ entries = min(entries, IXGBE_MAX_VF_MC_ENTRIES); @@ -246,25 +352,13 @@ static int ixgbe_set_vf_multicasts(struct ixgbe_adapter *adapter, mta_reg |= (1 << vector_bit); IXGBE_WRITE_REG(hw, IXGBE_MTA(vector_reg), mta_reg); } + vmolr |= IXGBE_VMOLR_ROMPE; + IXGBE_WRITE_REG(hw, IXGBE_VMOLR(vf), vmolr); return 0; } -static void ixgbe_restore_vf_macvlans(struct ixgbe_adapter *adapter) -{ - struct ixgbe_hw *hw = &adapter->hw; - struct list_head *pos; - struct vf_macvlans *entry; - - list_for_each(pos, &adapter->vf_mvs.l) { - entry = list_entry(pos, struct vf_macvlans, l); - if (entry->free == false) - hw->mac.ops.set_rar(hw, entry->rar_entry, - entry->vf_macvlan, - entry->vf, IXGBE_RAH_AV); - } -} - +#ifdef CONFIG_PCI_IOV void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; @@ -275,6 +369,7 @@ void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter) u32 mta_reg; for (i = 0; i < adapter->num_vfs; i++) { + u32 vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(i)); vfinfo = &adapter->vfinfo[i]; for (j = 0; j < vfinfo->num_vf_mc_hashes; j++) { hw->addr_ctrl.mta_in_use++; @@ -284,50 +379,118 @@ void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter) mta_reg |= (1 << vector_bit); IXGBE_WRITE_REG(hw, IXGBE_MTA(vector_reg), mta_reg); } + + if (vfinfo->num_vf_mc_hashes) + vmolr |= IXGBE_VMOLR_ROMPE; + else + vmolr &= ~IXGBE_VMOLR_ROMPE; + IXGBE_WRITE_REG(hw, IXGBE_VMOLR(i), vmolr); } /* Restore any VF macvlans */ - ixgbe_restore_vf_macvlans(adapter); + ixgbe_full_sync_mac_table(adapter); } +#endif static int ixgbe_set_vf_vlan(struct ixgbe_adapter *adapter, int add, int vid, u32 vf) { + /* VLAN 0 is a special case, don't allow it to be removed */ + if (!vid && !add) + return 0; + return adapter->hw.mac.ops.set_vfta(&adapter->hw, vid, vf, (bool)add); } -static void ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 *msgbuf) +static s32 ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) { struct ixgbe_hw *hw = &adapter->hw; - int new_mtu = msgbuf[1]; + int max_frame = msgbuf[1]; u32 max_frs; - int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN; - /* Only X540 supports jumbo frames in IOV mode */ - if (adapter->hw.mac.type != ixgbe_mac_X540) - return; + /* + * For 82599EB we have to keep all PFs and VFs operating with + * the same max_frame value in order to avoid sending an oversize + * frame to a VF. In order to guarantee this is handled correctly + * for all cases we have several special exceptions to take into + * account before we can enable the VF for receive + */ + if (adapter->hw.mac.type == ixgbe_mac_82599EB) { + struct net_device *dev = adapter->netdev; + int pf_max_frame = dev->mtu + ETH_HLEN; + u32 reg_offset, vf_shift, vfre; + s32 err = 0; + +#ifdef CONFIG_FCOE + if (dev->features & NETIF_F_FCOE_MTU) + pf_max_frame = max_t(int, pf_max_frame, + IXGBE_FCOE_JUMBO_FRAME_SIZE); + +#endif /* CONFIG_FCOE */ + switch (adapter->vfinfo[vf].vf_api) { + case ixgbe_mbox_api_11: + /* + * Version 1.1 supports jumbo frames on VFs if PF has + * jumbo frames enabled which means legacy VFs are + * disabled + */ + if (pf_max_frame > ETH_FRAME_LEN) + break; + default: + /* + * If the PF or VF are running w/ jumbo frames enabled + * we need to shut down the VF Rx path as we cannot + * support jumbo frames on legacy VFs + */ + if ((pf_max_frame > ETH_FRAME_LEN) || + (max_frame > (ETH_FRAME_LEN + ETH_FCS_LEN))) + err = -EINVAL; + break; + } + + /* determine VF receive enable location */ + vf_shift = vf % 32; + reg_offset = vf / 32; + + /* enable or disable receive depending on error */ + vfre = IXGBE_READ_REG(hw, IXGBE_VFRE(reg_offset)); + if (err) + vfre &= ~(1 << vf_shift); + else + vfre |= 1 << vf_shift; + IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset), vfre); + + if (err) { + e_err(drv, "VF max_frame %d out of range\n", max_frame); + return err; + } + } /* MTU < 68 is an error and causes problems on some kernels */ - if ((new_mtu < 68) || (max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE)) { - e_err(drv, "VF mtu %d out of range\n", new_mtu); - return; + if (max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE) { + e_err(drv, "VF max_frame %d out of range\n", max_frame); + return -EINVAL; } - max_frs = (IXGBE_READ_REG(hw, IXGBE_MAXFRS) & - IXGBE_MHADD_MFS_MASK) >> IXGBE_MHADD_MFS_SHIFT; - if (max_frs < new_mtu) { - max_frs = new_mtu << IXGBE_MHADD_MFS_SHIFT; + /* pull current max frame size from hardware */ + max_frs = IXGBE_READ_REG(hw, IXGBE_MAXFRS); + max_frs &= IXGBE_MHADD_MFS_MASK; + max_frs >>= IXGBE_MHADD_MFS_SHIFT; + + if (max_frs < max_frame) { + max_frs = max_frame << IXGBE_MHADD_MFS_SHIFT; IXGBE_WRITE_REG(hw, IXGBE_MAXFRS, max_frs); } - e_info(hw, "VF requests change max MTU to %d\n", new_mtu); + e_info(hw, "VF requests change max MTU to %d\n", max_frame); + + return 0; } static void ixgbe_set_vmolr(struct ixgbe_hw *hw, u32 vf, bool aupe) { u32 vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(vf)); - vmolr |= (IXGBE_VMOLR_ROMPE | - IXGBE_VMOLR_BAM); + vmolr |= IXGBE_VMOLR_BAM; if (aupe) vmolr |= IXGBE_VMOLR_AUPE; else @@ -335,34 +498,37 @@ static void ixgbe_set_vmolr(struct ixgbe_hw *hw, u32 vf, bool aupe) IXGBE_WRITE_REG(hw, IXGBE_VMOLR(vf), vmolr); } -static void ixgbe_set_vmvir(struct ixgbe_adapter *adapter, u32 vid, u32 vf) +static void ixgbe_clear_vmvir(struct ixgbe_adapter *adapter, u32 vf) { struct ixgbe_hw *hw = &adapter->hw; - if (vid) - IXGBE_WRITE_REG(hw, IXGBE_VMVIR(vf), - (vid | IXGBE_VMVIR_VLANA_DEFAULT)); - else - IXGBE_WRITE_REG(hw, IXGBE_VMVIR(vf), 0); + IXGBE_WRITE_REG(hw, IXGBE_VMVIR(vf), 0); } - static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf) { struct ixgbe_hw *hw = &adapter->hw; - int rar_entry = hw->mac.num_rar_entries - (vf + 1); + struct vf_data_storage *vfinfo = &adapter->vfinfo[vf]; + u8 num_tcs = netdev_get_num_tc(adapter->netdev); + + /* add PF assigned VLAN or VLAN 0 */ + ixgbe_set_vf_vlan(adapter, true, vfinfo->pf_vlan, vf); /* reset offloads to defaults */ - if (adapter->vfinfo[vf].pf_vlan) { - ixgbe_set_vf_vlan(adapter, true, - adapter->vfinfo[vf].pf_vlan, vf); - ixgbe_set_vmvir(adapter, - (adapter->vfinfo[vf].pf_vlan | - (adapter->vfinfo[vf].pf_qos << - VLAN_PRIO_SHIFT)), vf); - ixgbe_set_vmolr(hw, vf, false); + ixgbe_set_vmolr(hw, vf, !vfinfo->pf_vlan); + + /* set outgoing tags for VFs */ + if (!vfinfo->pf_vlan && !vfinfo->pf_qos && !num_tcs) { + ixgbe_clear_vmvir(adapter, vf); } else { - ixgbe_set_vmvir(adapter, 0, vf); - ixgbe_set_vmolr(hw, vf, true); + if (vfinfo->pf_qos || !num_tcs) + ixgbe_set_vmvir(adapter, vfinfo->pf_vlan, + vfinfo->pf_qos, vf); + else + ixgbe_set_vmvir(adapter, vfinfo->pf_vlan, + adapter->default_up, vf); + + if (vfinfo->spoofchk_enabled) + hw->mac.ops.set_vlan_anti_spoofing(hw, true, vf); } /* reset multicast table array for vf */ @@ -371,17 +537,18 @@ static inline void ixgbe_vf_reset_event(struct ixgbe_adapter *adapter, u32 vf) /* Flush and reset the mta with the new values */ ixgbe_set_rx_mode(adapter->netdev); - hw->mac.ops.clear_rar(hw, rar_entry); + ixgbe_del_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf); + + /* reset VF api back to unknown */ + adapter->vfinfo[vf].vf_api = ixgbe_mbox_api_10; } static int ixgbe_set_vf_mac(struct ixgbe_adapter *adapter, int vf, unsigned char *mac_addr) { - struct ixgbe_hw *hw = &adapter->hw; - int rar_entry = hw->mac.num_rar_entries - (vf + 1); - - memcpy(adapter->vfinfo[vf].vf_mac_addresses, mac_addr, 6); - hw->mac.ops.set_rar(hw, rar_entry, mac_addr, vf, IXGBE_RAH_AV); + ixgbe_del_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf); + memcpy(adapter->vfinfo[vf].vf_mac_addresses, mac_addr, ETH_ALEN); + ixgbe_add_mac_filter(adapter, adapter->vfinfo[vf].vf_mac_addresses, vf); return 0; } @@ -389,7 +556,6 @@ static int ixgbe_set_vf_mac(struct ixgbe_adapter *adapter, static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter, int vf, int index, unsigned char *mac_addr) { - struct ixgbe_hw *hw = &adapter->hw; struct list_head *pos; struct vf_macvlans *entry; @@ -400,7 +566,8 @@ static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter, entry->vf = -1; entry->free = true; entry->is_macvlan = false; - hw->mac.ops.clear_rar(hw, entry->rar_entry); + ixgbe_del_mac_filter(adapter, + entry->vf_macvlan, vf); } } } @@ -436,99 +603,336 @@ static int ixgbe_set_vf_macvlan(struct ixgbe_adapter *adapter, entry->vf = vf; memcpy(entry->vf_macvlan, mac_addr, ETH_ALEN); - hw->mac.ops.set_rar(hw, entry->rar_entry, mac_addr, vf, IXGBE_RAH_AV); + ixgbe_add_mac_filter(adapter, mac_addr, vf); return 0; } -int ixgbe_check_vf_assignment(struct ixgbe_adapter *adapter) -{ -#ifdef CONFIG_PCI_IOV - int i; - for (i = 0; i < adapter->num_vfs; i++) { - if (adapter->vfinfo[i].vfdev->dev_flags & - PCI_DEV_FLAGS_ASSIGNED) - return true; - } -#endif - return false; -} - int ixgbe_vf_configuration(struct pci_dev *pdev, unsigned int event_mask) { - unsigned char vf_mac_addr[6]; struct ixgbe_adapter *adapter = pci_get_drvdata(pdev); unsigned int vfn = (event_mask & 0x3f); - struct pci_dev *pvfdev; - unsigned int device_id; - u16 thisvf_devfn = (pdev->devfn + 0x80 + (vfn << 1)) | - (pdev->devfn & 1); bool enable = ((event_mask & 0x10000000U) != 0); - if (enable) { - random_ether_addr(vf_mac_addr); - e_info(probe, "IOV: VF %d is enabled MAC %pM\n", - vfn, vf_mac_addr); - /* - * Store away the VF "permananet" MAC address, it will ask - * for it later. - */ - memcpy(adapter->vfinfo[vfn].vf_mac_addresses, vf_mac_addr, 6); - - switch (adapter->hw.mac.type) { - case ixgbe_mac_82599EB: - device_id = IXGBE_DEV_ID_82599_VF; - break; - case ixgbe_mac_X540: - device_id = IXGBE_DEV_ID_X540_VF; - break; - default: - device_id = 0; - break; - } - - pvfdev = pci_get_device(IXGBE_INTEL_VENDOR_ID, device_id, NULL); - while (pvfdev) { - if (pvfdev->devfn == thisvf_devfn) - break; - pvfdev = pci_get_device(IXGBE_INTEL_VENDOR_ID, - device_id, pvfdev); - } - if (pvfdev) - adapter->vfinfo[vfn].vfdev = pvfdev; - else - e_err(drv, "Couldn't find pci dev ptr for VF %4.4x\n", - thisvf_devfn); - } + if (enable) + eth_zero_addr(adapter->vfinfo[vfn].vf_mac_addresses); return 0; } -static inline void ixgbe_vf_reset_msg(struct ixgbe_adapter *adapter, u32 vf) +static int ixgbe_vf_reset_msg(struct ixgbe_adapter *adapter, u32 vf) { + struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; struct ixgbe_hw *hw = &adapter->hw; - u32 reg; - u32 reg_offset, vf_shift; + unsigned char *vf_mac = adapter->vfinfo[vf].vf_mac_addresses; + u32 reg, reg_offset, vf_shift; + u32 msgbuf[4] = {0, 0, 0, 0}; + u8 *addr = (u8 *)(&msgbuf[1]); + u32 q_per_pool = __ALIGN_MASK(1, ~vmdq->mask); + int i; + + e_info(probe, "VF Reset msg received from vf %d\n", vf); + + /* reset the filters for the device */ + ixgbe_vf_reset_event(adapter, vf); + + /* set vf mac address */ + if (!is_zero_ether_addr(vf_mac)) + ixgbe_set_vf_mac(adapter, vf, vf_mac); vf_shift = vf % 32; reg_offset = vf / 32; - /* enable transmit and receive for vf */ + /* enable transmit for vf */ reg = IXGBE_READ_REG(hw, IXGBE_VFTE(reg_offset)); - reg |= (reg | (1 << vf_shift)); + reg |= 1 << vf_shift; IXGBE_WRITE_REG(hw, IXGBE_VFTE(reg_offset), reg); + /* force drop enable for all VF Rx queues */ + for (i = vf * q_per_pool; i < ((vf + 1) * q_per_pool); i++) { + /* flush previous write */ + IXGBE_WRITE_FLUSH(hw); + + /* indicate to hardware that we want to set drop enable */ + reg = IXGBE_QDE_WRITE | IXGBE_QDE_ENABLE; + reg |= i << IXGBE_QDE_IDX_SHIFT; + IXGBE_WRITE_REG(hw, IXGBE_QDE, reg); + } + + /* enable receive for vf */ reg = IXGBE_READ_REG(hw, IXGBE_VFRE(reg_offset)); - reg |= (reg | (1 << vf_shift)); + reg |= 1 << vf_shift; + /* + * The 82599 cannot support a mix of jumbo and non-jumbo PF/VFs. + * For more info take a look at ixgbe_set_vf_lpe + */ + if (adapter->hw.mac.type == ixgbe_mac_82599EB) { + struct net_device *dev = adapter->netdev; + int pf_max_frame = dev->mtu + ETH_HLEN; + +#ifdef CONFIG_FCOE + if (dev->features & NETIF_F_FCOE_MTU) + pf_max_frame = max_t(int, pf_max_frame, + IXGBE_FCOE_JUMBO_FRAME_SIZE); + +#endif /* CONFIG_FCOE */ + if (pf_max_frame > ETH_FRAME_LEN) + reg &= ~(1 << vf_shift); + } IXGBE_WRITE_REG(hw, IXGBE_VFRE(reg_offset), reg); + /* enable VF mailbox for further messages */ + adapter->vfinfo[vf].clear_to_send = true; + /* Enable counting of spoofed packets in the SSVPC register */ reg = IXGBE_READ_REG(hw, IXGBE_VMECM(reg_offset)); reg |= (1 << vf_shift); IXGBE_WRITE_REG(hw, IXGBE_VMECM(reg_offset), reg); - ixgbe_vf_reset_event(adapter, vf); + /* + * Reset the VFs TDWBAL and TDWBAH registers + * which are not cleared by an FLR + */ + for (i = 0; i < q_per_pool; i++) { + IXGBE_WRITE_REG(hw, IXGBE_PVFTDWBAHn(q_per_pool, vf, i), 0); + IXGBE_WRITE_REG(hw, IXGBE_PVFTDWBALn(q_per_pool, vf, i), 0); + } + + /* reply to reset with ack and vf mac address */ + msgbuf[0] = IXGBE_VF_RESET; + if (!is_zero_ether_addr(vf_mac)) { + msgbuf[0] |= IXGBE_VT_MSGTYPE_ACK; + memcpy(addr, vf_mac, ETH_ALEN); + } else { + msgbuf[0] |= IXGBE_VT_MSGTYPE_NACK; + dev_warn(&adapter->pdev->dev, + "VF %d has no MAC address assigned, you may have to assign one manually\n", + vf); + } + + /* + * Piggyback the multicast filter type so VF can compute the + * correct vectors + */ + msgbuf[3] = hw->mac.mc_filter_type; + ixgbe_write_mbx(hw, msgbuf, IXGBE_VF_PERMADDR_MSG_LEN, vf); + + return 0; +} + +static int ixgbe_set_vf_mac_addr(struct ixgbe_adapter *adapter, + u32 *msgbuf, u32 vf) +{ + u8 *new_mac = ((u8 *)(&msgbuf[1])); + + if (!is_valid_ether_addr(new_mac)) { + e_warn(drv, "VF %d attempted to set invalid mac\n", vf); + return -1; + } + + if (adapter->vfinfo[vf].pf_set_mac && + !ether_addr_equal(adapter->vfinfo[vf].vf_mac_addresses, new_mac)) { + e_warn(drv, + "VF %d attempted to override administratively set MAC address\n" + "Reload the VF driver to resume operations\n", + vf); + return -1; + } + + return ixgbe_set_vf_mac(adapter, vf, new_mac) < 0; +} + +static int ixgbe_find_vlvf_entry(struct ixgbe_hw *hw, u32 vlan) +{ + u32 vlvf; + s32 regindex; + + /* short cut the special case */ + if (vlan == 0) + return 0; + + /* Search for the vlan id in the VLVF entries */ + for (regindex = 1; regindex < IXGBE_VLVF_ENTRIES; regindex++) { + vlvf = IXGBE_READ_REG(hw, IXGBE_VLVF(regindex)); + if ((vlvf & VLAN_VID_MASK) == vlan) + break; + } + + /* Return a negative value if not found */ + if (regindex >= IXGBE_VLVF_ENTRIES) + regindex = -1; + + return regindex; +} + +static int ixgbe_set_vf_vlan_msg(struct ixgbe_adapter *adapter, + u32 *msgbuf, u32 vf) +{ + struct ixgbe_hw *hw = &adapter->hw; + int add = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) >> IXGBE_VT_MSGINFO_SHIFT; + int vid = (msgbuf[1] & IXGBE_VLVF_VLANID_MASK); + int err; + s32 reg_ndx; + u32 vlvf; + u32 bits; + u8 tcs = netdev_get_num_tc(adapter->netdev); + + if (adapter->vfinfo[vf].pf_vlan || tcs) { + e_warn(drv, + "VF %d attempted to override administratively set VLAN configuration\n" + "Reload the VF driver to resume operations\n", + vf); + return -1; + } + + if (add) + adapter->vfinfo[vf].vlan_count++; + else if (adapter->vfinfo[vf].vlan_count) + adapter->vfinfo[vf].vlan_count--; + + /* in case of promiscuous mode any VLAN filter set for a VF must + * also have the PF pool added to it. + */ + if (add && adapter->netdev->flags & IFF_PROMISC) + err = ixgbe_set_vf_vlan(adapter, add, vid, VMDQ_P(0)); + + err = ixgbe_set_vf_vlan(adapter, add, vid, vf); + if (!err && adapter->vfinfo[vf].spoofchk_enabled) + hw->mac.ops.set_vlan_anti_spoofing(hw, true, vf); + + /* Go through all the checks to see if the VLAN filter should + * be wiped completely. + */ + if (!add && adapter->netdev->flags & IFF_PROMISC) { + reg_ndx = ixgbe_find_vlvf_entry(hw, vid); + if (reg_ndx < 0) + goto out; + vlvf = IXGBE_READ_REG(hw, IXGBE_VLVF(reg_ndx)); + /* See if any other pools are set for this VLAN filter + * entry other than the PF. + */ + if (VMDQ_P(0) < 32) { + bits = IXGBE_READ_REG(hw, IXGBE_VLVFB(reg_ndx * 2)); + bits &= ~(1 << VMDQ_P(0)); + bits |= IXGBE_READ_REG(hw, + IXGBE_VLVFB(reg_ndx * 2) + 1); + } else { + bits = IXGBE_READ_REG(hw, + IXGBE_VLVFB(reg_ndx * 2) + 1); + bits &= ~(1 << (VMDQ_P(0) - 32)); + bits |= IXGBE_READ_REG(hw, IXGBE_VLVFB(reg_ndx * 2)); + } + + /* If the filter was removed then ensure PF pool bit + * is cleared if the PF only added itself to the pool + * because the PF is in promiscuous mode. + */ + if ((vlvf & VLAN_VID_MASK) == vid && + !test_bit(vid, adapter->active_vlans) && !bits) + ixgbe_set_vf_vlan(adapter, add, vid, VMDQ_P(0)); + } + +out: + + return err; +} + +static int ixgbe_set_vf_macvlan_msg(struct ixgbe_adapter *adapter, + u32 *msgbuf, u32 vf) +{ + u8 *new_mac = ((u8 *)(&msgbuf[1])); + int index = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) >> + IXGBE_VT_MSGINFO_SHIFT; + int err; + + if (adapter->vfinfo[vf].pf_set_mac && index > 0) { + e_warn(drv, + "VF %d requested MACVLAN filter but is administratively denied\n", + vf); + return -1; + } + + /* An non-zero index indicates the VF is setting a filter */ + if (index) { + if (!is_valid_ether_addr(new_mac)) { + e_warn(drv, "VF %d attempted to set invalid mac\n", vf); + return -1; + } + + /* + * If the VF is allowed to set MAC filters then turn off + * anti-spoofing to avoid false positives. + */ + if (adapter->vfinfo[vf].spoofchk_enabled) + ixgbe_ndo_set_vf_spoofchk(adapter->netdev, vf, false); + } + + err = ixgbe_set_vf_macvlan(adapter, vf, index, new_mac); + if (err == -ENOSPC) + e_warn(drv, + "VF %d has requested a MACVLAN filter but there is no space for it\n", + vf); + + return err < 0; +} + +static int ixgbe_negotiate_vf_api(struct ixgbe_adapter *adapter, + u32 *msgbuf, u32 vf) +{ + int api = msgbuf[1]; + + switch (api) { + case ixgbe_mbox_api_10: + case ixgbe_mbox_api_11: + adapter->vfinfo[vf].vf_api = api; + return 0; + default: + break; + } + + e_info(drv, "VF %d requested invalid api version %u\n", vf, api); + + return -1; +} + +static int ixgbe_get_vf_queues(struct ixgbe_adapter *adapter, + u32 *msgbuf, u32 vf) +{ + struct net_device *dev = adapter->netdev; + struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; + unsigned int default_tc = 0; + u8 num_tcs = netdev_get_num_tc(dev); + + /* verify the PF is supporting the correct APIs */ + switch (adapter->vfinfo[vf].vf_api) { + case ixgbe_mbox_api_20: + case ixgbe_mbox_api_11: + break; + default: + return -1; + } + + /* only allow 1 Tx queue for bandwidth limiting */ + msgbuf[IXGBE_VF_TX_QUEUES] = __ALIGN_MASK(1, ~vmdq->mask); + msgbuf[IXGBE_VF_RX_QUEUES] = __ALIGN_MASK(1, ~vmdq->mask); + + /* if TCs > 1 determine which TC belongs to default user priority */ + if (num_tcs > 1) + default_tc = netdev_get_prio_tc_map(dev, adapter->default_up); + + /* notify VF of need for VLAN tag stripping, and correct queue */ + if (num_tcs) + msgbuf[IXGBE_VF_TRANS_VLAN] = num_tcs; + else if (adapter->vfinfo[vf].pf_vlan || adapter->vfinfo[vf].pf_qos) + msgbuf[IXGBE_VF_TRANS_VLAN] = 1; + else + msgbuf[IXGBE_VF_TRANS_VLAN] = 0; + + /* notify VF of default queue */ + msgbuf[IXGBE_VF_DEF_QUEUE] = default_tc; + + return 0; } static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) @@ -537,53 +941,28 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) u32 msgbuf[IXGBE_VFMAILBOX_SIZE]; struct ixgbe_hw *hw = &adapter->hw; s32 retval; - int entries; - u16 *hash_list; - int add, vid, index; - u8 *new_mac; retval = ixgbe_read_mbx(hw, msgbuf, mbx_size, vf); - if (retval) + if (retval) { pr_err("Error receiving message from VF\n"); + return retval; + } /* this is a message we already processed, do nothing */ if (msgbuf[0] & (IXGBE_VT_MSGTYPE_ACK | IXGBE_VT_MSGTYPE_NACK)) return retval; + /* flush the ack before we write any messages back */ + IXGBE_WRITE_FLUSH(hw); + + if (msgbuf[0] == IXGBE_VF_RESET) + return ixgbe_vf_reset_msg(adapter, vf); + /* * until the vf completes a virtual function reset it should not be * allowed to start any configuration. */ - - if (msgbuf[0] == IXGBE_VF_RESET) { - unsigned char *vf_mac = adapter->vfinfo[vf].vf_mac_addresses; - new_mac = (u8 *)(&msgbuf[1]); - e_info(probe, "VF Reset msg received from vf %d\n", vf); - adapter->vfinfo[vf].clear_to_send = false; - ixgbe_vf_reset_msg(adapter, vf); - adapter->vfinfo[vf].clear_to_send = true; - - if (is_valid_ether_addr(new_mac) && - !adapter->vfinfo[vf].pf_set_mac) - ixgbe_set_vf_mac(adapter, vf, vf_mac); - else - ixgbe_set_vf_mac(adapter, - vf, adapter->vfinfo[vf].vf_mac_addresses); - - /* reply to reset with ack and vf mac address */ - msgbuf[0] = IXGBE_VF_RESET | IXGBE_VT_MSGTYPE_ACK; - memcpy(new_mac, vf_mac, ETH_ALEN); - /* - * Piggyback the multicast filter type so VF can compute the - * correct vectors - */ - msgbuf[3] = hw->mac.mc_filter_type; - ixgbe_write_mbx(hw, msgbuf, IXGBE_VF_PERMADDR_MSG_LEN, vf); - - return retval; - } - if (!adapter->vfinfo[vf].clear_to_send) { msgbuf[0] |= IXGBE_VT_MSGTYPE_NACK; ixgbe_write_mbx(hw, msgbuf, 1, vf); @@ -592,64 +971,25 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) switch ((msgbuf[0] & 0xFFFF)) { case IXGBE_VF_SET_MAC_ADDR: - new_mac = ((u8 *)(&msgbuf[1])); - if (is_valid_ether_addr(new_mac) && - !adapter->vfinfo[vf].pf_set_mac) { - ixgbe_set_vf_mac(adapter, vf, new_mac); - } else if (memcmp(adapter->vfinfo[vf].vf_mac_addresses, - new_mac, ETH_ALEN)) { - e_warn(drv, "VF %d attempted to override " - "administratively set MAC address\nReload " - "the VF driver to resume operations\n", vf); - retval = -1; - } + retval = ixgbe_set_vf_mac_addr(adapter, msgbuf, vf); break; case IXGBE_VF_SET_MULTICAST: - entries = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) - >> IXGBE_VT_MSGINFO_SHIFT; - hash_list = (u16 *)&msgbuf[1]; - retval = ixgbe_set_vf_multicasts(adapter, entries, - hash_list, vf); - break; - case IXGBE_VF_SET_LPE: - ixgbe_set_vf_lpe(adapter, msgbuf); + retval = ixgbe_set_vf_multicasts(adapter, msgbuf, vf); break; case IXGBE_VF_SET_VLAN: - add = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) - >> IXGBE_VT_MSGINFO_SHIFT; - vid = (msgbuf[1] & IXGBE_VLVF_VLANID_MASK); - if (adapter->vfinfo[vf].pf_vlan) { - e_warn(drv, "VF %d attempted to override " - "administratively set VLAN configuration\n" - "Reload the VF driver to resume operations\n", - vf); - retval = -1; - } else { - if (add) - adapter->vfinfo[vf].vlan_count++; - else if (adapter->vfinfo[vf].vlan_count) - adapter->vfinfo[vf].vlan_count--; - retval = ixgbe_set_vf_vlan(adapter, add, vid, vf); - if (!retval && adapter->vfinfo[vf].spoofchk_enabled) - hw->mac.ops.set_vlan_anti_spoofing(hw, true, vf); - } + retval = ixgbe_set_vf_vlan_msg(adapter, msgbuf, vf); + break; + case IXGBE_VF_SET_LPE: + retval = ixgbe_set_vf_lpe(adapter, msgbuf, vf); break; case IXGBE_VF_SET_MACVLAN: - index = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) >> - IXGBE_VT_MSGINFO_SHIFT; - /* - * If the VF is allowed to set MAC filters then turn off - * anti-spoofing to avoid false positives. An index - * greater than 0 will indicate the VF is setting a - * macvlan MAC filter. - */ - if (index > 0 && adapter->vfinfo[vf].spoofchk_enabled) - ixgbe_ndo_set_vf_spoofchk(adapter->netdev, vf, false); - retval = ixgbe_set_vf_macvlan(adapter, vf, index, - (unsigned char *)(&msgbuf[1])); - if (retval == -ENOSPC) - e_warn(drv, "VF %d has requested a MACVLAN filter " - "but there is no space for it\n", vf); + retval = ixgbe_set_vf_macvlan_msg(adapter, msgbuf, vf); + break; + case IXGBE_VF_API_NEGOTIATE: + retval = ixgbe_negotiate_vf_api(adapter, msgbuf, vf); + break; + case IXGBE_VF_GET_QUEUES: + retval = ixgbe_get_vf_queues(adapter, msgbuf, vf); break; default: e_err(drv, "Unhandled Msg %8.8x\n", msgbuf[0]); @@ -665,7 +1005,7 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) msgbuf[0] |= IXGBE_VT_MSGTYPE_CTS; - ixgbe_write_mbx(hw, msgbuf, 1, vf); + ixgbe_write_mbx(hw, msgbuf, mbx_size, vf); return retval; } @@ -753,10 +1093,16 @@ int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos) if ((vf >= adapter->num_vfs) || (vlan > 4095) || (qos > 7)) return -EINVAL; if (vlan || qos) { + if (adapter->vfinfo[vf].pf_vlan) + err = ixgbe_set_vf_vlan(adapter, false, + adapter->vfinfo[vf].pf_vlan, + vf); + if (err) + goto out; err = ixgbe_set_vf_vlan(adapter, true, vlan, vf); if (err) goto out; - ixgbe_set_vmvir(adapter, vlan | (qos << VLAN_PRIO_SHIFT), vf); + ixgbe_set_vmvir(adapter, vlan, qos, vf); ixgbe_set_vmolr(hw, vf, false); if (adapter->vfinfo[vf].spoofchk_enabled) hw->mac.ops.set_vlan_anti_spoofing(hw, true, vf); @@ -776,21 +1122,21 @@ int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos) } else { err = ixgbe_set_vf_vlan(adapter, false, adapter->vfinfo[vf].pf_vlan, vf); - ixgbe_set_vmvir(adapter, vlan, vf); + ixgbe_clear_vmvir(adapter, vf); ixgbe_set_vmolr(hw, vf, true); hw->mac.ops.set_vlan_anti_spoofing(hw, false, vf); if (adapter->vfinfo[vf].vlan_count) adapter->vfinfo[vf].vlan_count--; adapter->vfinfo[vf].pf_vlan = 0; adapter->vfinfo[vf].pf_qos = 0; - } + } out: - return err; + return err; } -static int ixgbe_link_mbps(int internal_link_speed) +static int ixgbe_link_mbps(struct ixgbe_adapter *adapter) { - switch (internal_link_speed) { + switch (adapter->link_speed) { case IXGBE_LINK_SPEED_100_FULL: return 100; case IXGBE_LINK_SPEED_1GB_FULL: @@ -802,27 +1148,30 @@ static int ixgbe_link_mbps(int internal_link_speed) } } -static void ixgbe_set_vf_rate_limit(struct ixgbe_hw *hw, int vf, int tx_rate, - int link_speed) +static void ixgbe_set_vf_rate_limit(struct ixgbe_adapter *adapter, int vf) { - int rf_dec, rf_int; - u32 bcnrc_val; + struct ixgbe_ring_feature *vmdq = &adapter->ring_feature[RING_F_VMDQ]; + struct ixgbe_hw *hw = &adapter->hw; + u32 bcnrc_val = 0; + u16 queue, queues_per_pool; + u16 tx_rate = adapter->vfinfo[vf].tx_rate; + + if (tx_rate) { + /* start with base link speed value */ + bcnrc_val = adapter->vf_rate_link_speed; - if (tx_rate != 0) { /* Calculate the rate factor values to set */ - rf_int = link_speed / tx_rate; - rf_dec = (link_speed - (rf_int * tx_rate)); - rf_dec = (rf_dec * (1<<IXGBE_RTTBCNRC_RF_INT_SHIFT)) / tx_rate; - - bcnrc_val = IXGBE_RTTBCNRC_RS_ENA; - bcnrc_val |= ((rf_int<<IXGBE_RTTBCNRC_RF_INT_SHIFT) & - IXGBE_RTTBCNRC_RF_INT_MASK); - bcnrc_val |= (rf_dec & IXGBE_RTTBCNRC_RF_DEC_MASK); - } else { - bcnrc_val = 0; + bcnrc_val <<= IXGBE_RTTBCNRC_RF_INT_SHIFT; + bcnrc_val /= tx_rate; + + /* clear everything but the rate factor */ + bcnrc_val &= IXGBE_RTTBCNRC_RF_INT_MASK | + IXGBE_RTTBCNRC_RF_DEC_MASK; + + /* enable the rate scheduler */ + bcnrc_val |= IXGBE_RTTBCNRC_RS_ENA; } - IXGBE_WRITE_REG(hw, IXGBE_RTTDQSEL, 2*vf); /* vf Y uses queue 2*Y */ /* * Set global transmit compensation time to the MMW_SIZE in RTTBCNRM * register. Typically MMW_SIZE=0x014 if 9728-byte jumbo is supported @@ -839,53 +1188,72 @@ static void ixgbe_set_vf_rate_limit(struct ixgbe_hw *hw, int vf, int tx_rate, break; } - IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRC, bcnrc_val); + /* determine how many queues per pool based on VMDq mask */ + queues_per_pool = __ALIGN_MASK(1, ~vmdq->mask); + + /* write value for all Tx queues belonging to VF */ + for (queue = 0; queue < queues_per_pool; queue++) { + unsigned int reg_idx = (vf * queues_per_pool) + queue; + + IXGBE_WRITE_REG(hw, IXGBE_RTTDQSEL, reg_idx); + IXGBE_WRITE_REG(hw, IXGBE_RTTBCNRC, bcnrc_val); + } } void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter) { - int actual_link_speed, i; - bool reset_rate = false; + int i; /* VF Tx rate limit was not set */ - if (adapter->vf_rate_link_speed == 0) + if (!adapter->vf_rate_link_speed) return; - actual_link_speed = ixgbe_link_mbps(adapter->link_speed); - if (actual_link_speed != adapter->vf_rate_link_speed) { - reset_rate = true; + if (ixgbe_link_mbps(adapter) != adapter->vf_rate_link_speed) { adapter->vf_rate_link_speed = 0; dev_info(&adapter->pdev->dev, - "Link speed has been changed. VF Transmit rate " - "is disabled\n"); + "Link speed has been changed. VF Transmit rate is disabled\n"); } for (i = 0; i < adapter->num_vfs; i++) { - if (reset_rate) + if (!adapter->vf_rate_link_speed) adapter->vfinfo[i].tx_rate = 0; - ixgbe_set_vf_rate_limit(&adapter->hw, i, - adapter->vfinfo[i].tx_rate, - actual_link_speed); + ixgbe_set_vf_rate_limit(adapter, i); } } -int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate) +int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int min_tx_rate, + int max_tx_rate) { struct ixgbe_adapter *adapter = netdev_priv(netdev); - struct ixgbe_hw *hw = &adapter->hw; - int actual_link_speed; + int link_speed; - actual_link_speed = ixgbe_link_mbps(adapter->link_speed); - if ((vf >= adapter->num_vfs) || (!adapter->link_up) || - (tx_rate > actual_link_speed) || (actual_link_speed != 10000) || - ((tx_rate != 0) && (tx_rate <= 10))) - /* rate limit cannot be set to 10Mb or less in 10Gb adapters */ + /* verify VF is active */ + if (vf >= adapter->num_vfs) + return -EINVAL; + + /* verify link is up */ + if (!adapter->link_up) + return -EINVAL; + + /* verify we are linked at 10Gbps */ + link_speed = ixgbe_link_mbps(adapter); + if (link_speed != 10000) return -EINVAL; - adapter->vf_rate_link_speed = actual_link_speed; - adapter->vfinfo[vf].tx_rate = (u16)tx_rate; - ixgbe_set_vf_rate_limit(hw, vf, tx_rate, actual_link_speed); + if (min_tx_rate) + return -EINVAL; + + /* rate limit cannot be less than 10Mbs or greater than link speed */ + if (max_tx_rate && ((max_tx_rate <= 10) || (max_tx_rate > link_speed))) + return -EINVAL; + + /* store values */ + adapter->vf_rate_link_speed = link_speed; + adapter->vfinfo[vf].tx_rate = max_tx_rate; + + /* update hardware configuration */ + ixgbe_set_vf_rate_limit(adapter, vf); return 0; } @@ -924,7 +1292,8 @@ int ixgbe_ndo_get_vf_config(struct net_device *netdev, return -EINVAL; ivi->vf = vf; memcpy(&ivi->mac, adapter->vfinfo[vf].vf_mac_addresses, ETH_ALEN); - ivi->tx_rate = adapter->vfinfo[vf].tx_rate; + ivi->max_tx_rate = adapter->vfinfo[vf].tx_rate; + ivi->min_tx_rate = 0; ivi->vlan = adapter->vfinfo[vf].pf_vlan; ivi->qos = adapter->vfinfo[vf].pf_qos; ivi->spoofchk = adapter->vfinfo[vf].spoofchk_enabled; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h index 2ab38d5fda9..32c26d586c0 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2013 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, @@ -20,6 +20,7 @@ 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 @@ -28,7 +29,14 @@ #ifndef _IXGBE_SRIOV_H_ #define _IXGBE_SRIOV_H_ +/* ixgbe driver limit the max number of VFs could be enabled to + * 63 (IXGBE_MAX_VF_FUNCTIONS - 1) + */ +#define IXGBE_MAX_VFS_DRV_LIMIT (IXGBE_MAX_VF_FUNCTIONS - 1) + +#ifdef CONFIG_PCI_IOV void ixgbe_restore_vf_multicasts(struct ixgbe_adapter *adapter); +#endif void ixgbe_msg_task(struct ixgbe_adapter *adapter); int ixgbe_vf_configuration(struct pci_dev *pdev, unsigned int event_mask); void ixgbe_disable_tx_rx(struct ixgbe_adapter *adapter); @@ -36,18 +44,26 @@ void ixgbe_ping_all_vfs(struct ixgbe_adapter *adapter); int ixgbe_ndo_set_vf_mac(struct net_device *netdev, int queue, u8 *mac); int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int queue, u16 vlan, u8 qos); -int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate); +int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int min_tx_rate, + int max_tx_rate); int ixgbe_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting); int ixgbe_ndo_get_vf_config(struct net_device *netdev, int vf, struct ifla_vf_info *ivi); void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter); -void ixgbe_disable_sriov(struct ixgbe_adapter *adapter); -int ixgbe_check_vf_assignment(struct ixgbe_adapter *adapter); +int ixgbe_disable_sriov(struct ixgbe_adapter *adapter); #ifdef CONFIG_PCI_IOV -void ixgbe_enable_sriov(struct ixgbe_adapter *adapter, - const struct ixgbe_info *ii); +void ixgbe_enable_sriov(struct ixgbe_adapter *adapter); #endif +int ixgbe_pci_sriov_configure(struct pci_dev *dev, int num_vfs); + +static inline void ixgbe_set_vmvir(struct ixgbe_adapter *adapter, + u16 vid, u16 qos, u32 vf) +{ + struct ixgbe_hw *hw = &adapter->hw; + u32 vmvir = vid | (qos << VLAN_PRIO_SHIFT) | IXGBE_VMVIR_VLANA_DEFAULT; + IXGBE_WRITE_REG(hw, IXGBE_VMVIR(vf), vmvir); +} #endif /* _IXGBE_SRIOV_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c new file mode 100644 index 00000000000..ef6df3d6437 --- /dev/null +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c @@ -0,0 +1,230 @@ +/******************************************************************************* + + Intel 10 Gigabit PCI Express Linux driver + Copyright(c) 1999 - 2013 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_common.h" +#include "ixgbe_type.h" + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/sysfs.h> +#include <linux/kobject.h> +#include <linux/device.h> +#include <linux/netdevice.h> +#include <linux/hwmon.h> + +/* hwmon callback functions */ +static ssize_t ixgbe_hwmon_show_location(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct hwmon_attr *ixgbe_attr = container_of(attr, struct hwmon_attr, + dev_attr); + return sprintf(buf, "loc%u\n", + ixgbe_attr->sensor->location); +} + +static ssize_t ixgbe_hwmon_show_temp(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct hwmon_attr *ixgbe_attr = container_of(attr, struct hwmon_attr, + dev_attr); + unsigned int value; + + /* reset the temp field */ + ixgbe_attr->hw->mac.ops.get_thermal_sensor_data(ixgbe_attr->hw); + + value = ixgbe_attr->sensor->temp; + + /* display millidegree */ + value *= 1000; + + return sprintf(buf, "%u\n", value); +} + +static ssize_t ixgbe_hwmon_show_cautionthresh(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct hwmon_attr *ixgbe_attr = container_of(attr, struct hwmon_attr, + dev_attr); + unsigned int value = ixgbe_attr->sensor->caution_thresh; + + /* display millidegree */ + value *= 1000; + + return sprintf(buf, "%u\n", value); +} + +static ssize_t ixgbe_hwmon_show_maxopthresh(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct hwmon_attr *ixgbe_attr = container_of(attr, struct hwmon_attr, + dev_attr); + unsigned int value = ixgbe_attr->sensor->max_op_thresh; + + /* display millidegree */ + value *= 1000; + + return sprintf(buf, "%u\n", value); +} + +/** + * ixgbe_add_hwmon_attr - Create hwmon attr table for a hwmon sysfs file. + * @adapter: pointer to the adapter structure + * @offset: offset in the eeprom sensor data table + * @type: type of sensor data to display + * + * For each file we want in hwmon's sysfs interface we need a device_attribute + * This is included in our hwmon_attr struct that contains the references to + * the data structures we need to get the data to display. + */ +static int ixgbe_add_hwmon_attr(struct ixgbe_adapter *adapter, + unsigned int offset, int type) { + int rc; + unsigned int n_attr; + struct hwmon_attr *ixgbe_attr; + + n_attr = adapter->ixgbe_hwmon_buff->n_hwmon; + ixgbe_attr = &adapter->ixgbe_hwmon_buff->hwmon_list[n_attr]; + + switch (type) { + case IXGBE_HWMON_TYPE_LOC: + ixgbe_attr->dev_attr.show = ixgbe_hwmon_show_location; + snprintf(ixgbe_attr->name, sizeof(ixgbe_attr->name), + "temp%u_label", offset + 1); + break; + case IXGBE_HWMON_TYPE_TEMP: + ixgbe_attr->dev_attr.show = ixgbe_hwmon_show_temp; + snprintf(ixgbe_attr->name, sizeof(ixgbe_attr->name), + "temp%u_input", offset + 1); + break; + case IXGBE_HWMON_TYPE_CAUTION: + ixgbe_attr->dev_attr.show = ixgbe_hwmon_show_cautionthresh; + snprintf(ixgbe_attr->name, sizeof(ixgbe_attr->name), + "temp%u_max", offset + 1); + break; + case IXGBE_HWMON_TYPE_MAX: + ixgbe_attr->dev_attr.show = ixgbe_hwmon_show_maxopthresh; + snprintf(ixgbe_attr->name, sizeof(ixgbe_attr->name), + "temp%u_crit", offset + 1); + break; + default: + rc = -EPERM; + return rc; + } + + /* These always the same regardless of type */ + ixgbe_attr->sensor = + &adapter->hw.mac.thermal_sensor_data.sensor[offset]; + ixgbe_attr->hw = &adapter->hw; + ixgbe_attr->dev_attr.store = NULL; + ixgbe_attr->dev_attr.attr.mode = S_IRUGO; + ixgbe_attr->dev_attr.attr.name = ixgbe_attr->name; + sysfs_attr_init(&ixgbe_attr->dev_attr.attr); + + adapter->ixgbe_hwmon_buff->attrs[n_attr] = &ixgbe_attr->dev_attr.attr; + + ++adapter->ixgbe_hwmon_buff->n_hwmon; + + return 0; +} + +static void ixgbe_sysfs_del_adapter(struct ixgbe_adapter *adapter) +{ +} + +/* called from ixgbe_main.c */ +void ixgbe_sysfs_exit(struct ixgbe_adapter *adapter) +{ + ixgbe_sysfs_del_adapter(adapter); +} + +/* called from ixgbe_main.c */ +int ixgbe_sysfs_init(struct ixgbe_adapter *adapter) +{ + struct hwmon_buff *ixgbe_hwmon; + struct device *hwmon_dev; + unsigned int i; + int rc = 0; + + /* If this method isn't defined we don't support thermals */ + if (adapter->hw.mac.ops.init_thermal_sensor_thresh == NULL) { + goto exit; + } + + /* Don't create thermal hwmon interface if no sensors present */ + if (adapter->hw.mac.ops.init_thermal_sensor_thresh(&adapter->hw)) + goto exit; + + ixgbe_hwmon = devm_kzalloc(&adapter->pdev->dev, sizeof(*ixgbe_hwmon), + GFP_KERNEL); + if (ixgbe_hwmon == NULL) { + rc = -ENOMEM; + goto exit; + } + adapter->ixgbe_hwmon_buff = ixgbe_hwmon; + + for (i = 0; i < IXGBE_MAX_SENSORS; i++) { + /* + * Only create hwmon sysfs entries for sensors that have + * meaningful data for. + */ + if (adapter->hw.mac.thermal_sensor_data.sensor[i].location == 0) + continue; + + /* Bail if any hwmon attr struct fails to initialize */ + rc = ixgbe_add_hwmon_attr(adapter, i, IXGBE_HWMON_TYPE_CAUTION); + if (rc) + goto exit; + rc = ixgbe_add_hwmon_attr(adapter, i, IXGBE_HWMON_TYPE_LOC); + if (rc) + goto exit; + rc = ixgbe_add_hwmon_attr(adapter, i, IXGBE_HWMON_TYPE_TEMP); + if (rc) + goto exit; + rc = ixgbe_add_hwmon_attr(adapter, i, IXGBE_HWMON_TYPE_MAX); + if (rc) + goto exit; + } + + ixgbe_hwmon->groups[0] = &ixgbe_hwmon->group; + ixgbe_hwmon->group.attrs = ixgbe_hwmon->attrs; + + hwmon_dev = devm_hwmon_device_register_with_groups(&adapter->pdev->dev, + "ixgbe", + ixgbe_hwmon, + ixgbe_hwmon->groups); + if (IS_ERR(hwmon_dev)) + rc = PTR_ERR(hwmon_dev); +exit: + return rc; +} + diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index 9b95bef6097..9a89f98b35f 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2014 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, @@ -20,6 +20,7 @@ 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 @@ -32,9 +33,6 @@ #include <linux/mdio.h> #include <linux/netdevice.h> -/* Vendor ID */ -#define IXGBE_INTEL_VENDOR_ID 0x8086 - /* Device IDs */ #define IXGBE_DEV_ID_82598 0x10B6 #define IXGBE_DEV_ID_82598_BX 0x1508 @@ -57,16 +55,24 @@ #define IXGBE_DEV_ID_82599_BACKPLANE_FCOE 0x152a #define IXGBE_DEV_ID_82599_SFP_FCOE 0x1529 #define IXGBE_SUBDEV_ID_82599_SFP 0x11A9 +#define IXGBE_SUBDEV_ID_82599_SFP_WOL0 0x1071 +#define IXGBE_SUBDEV_ID_82599_RNDC 0x1F72 #define IXGBE_SUBDEV_ID_82599_560FLR 0x17D0 +#define IXGBE_SUBDEV_ID_82599_SP_560FLR 0x211B +#define IXGBE_SUBDEV_ID_82599_ECNA_DP 0x0470 +#define IXGBE_SUBDEV_ID_82599_LOM_SFP 0x8976 #define IXGBE_DEV_ID_82599_SFP_EM 0x1507 #define IXGBE_DEV_ID_82599_SFP_SF2 0x154D #define IXGBE_DEV_ID_82599EN_SFP 0x1557 +#define IXGBE_SUBDEV_ID_82599EN_SFP_OCP1 0x0001 #define IXGBE_DEV_ID_82599_XAUI_LOM 0x10FC #define IXGBE_DEV_ID_82599_COMBO_BACKPLANE 0x10F8 #define IXGBE_SUBDEV_ID_82599_KX4_KR_MEZZ 0x000C #define IXGBE_DEV_ID_82599_LS 0x154F #define IXGBE_DEV_ID_X540T 0x1528 #define IXGBE_DEV_ID_82599_SFP_SF_QP 0x154A +#define IXGBE_DEV_ID_82599_QSFP_SF_QP 0x1558 +#define IXGBE_DEV_ID_X540T1 0x1560 /* VF Device IDs */ #define IXGBE_DEV_ID_82599_VF 0x10ED @@ -110,6 +116,28 @@ #define IXGBE_I2C_CLK_OUT 0x00000002 #define IXGBE_I2C_DATA_IN 0x00000004 #define IXGBE_I2C_DATA_OUT 0x00000008 +#define IXGBE_I2C_CLOCK_STRETCHING_TIMEOUT 500 + +#define IXGBE_I2C_THERMAL_SENSOR_ADDR 0xF8 +#define IXGBE_EMC_INTERNAL_DATA 0x00 +#define IXGBE_EMC_INTERNAL_THERM_LIMIT 0x20 +#define IXGBE_EMC_DIODE1_DATA 0x01 +#define IXGBE_EMC_DIODE1_THERM_LIMIT 0x19 +#define IXGBE_EMC_DIODE2_DATA 0x23 +#define IXGBE_EMC_DIODE2_THERM_LIMIT 0x1A + +#define IXGBE_MAX_SENSORS 3 + +struct ixgbe_thermal_diode_data { + u8 location; + u8 temp; + u8 caution_thresh; + u8 max_op_thresh; +}; + +struct ixgbe_thermal_sensor_data { + struct ixgbe_thermal_diode_data sensor[IXGBE_MAX_SENSORS]; +}; /* Interrupt Registers */ #define IXGBE_EICR 0x00800 @@ -132,7 +160,7 @@ #define IXGBE_MAX_EITR 0x00000FF8 #define IXGBE_MIN_EITR 8 #define IXGBE_EITR(_i) (((_i) <= 23) ? (0x00820 + ((_i) * 4)) : \ - (0x012300 + (((_i) - 24) * 4))) + (0x012300 + (((_i) - 24) * 4))) #define IXGBE_EITR_ITR_INT_MASK 0x00000FF8 #define IXGBE_EITR_LLI_MOD 0x00008000 #define IXGBE_EITR_CNT_WDIS 0x80000000 @@ -185,7 +213,7 @@ * 64-127: 0x0D014 + (n-64)*0x40 */ #define IXGBE_SRRCTL(_i) (((_i) <= 15) ? (0x02100 + ((_i) * 4)) : \ - (((_i) < 64) ? (0x01014 + ((_i) * 0x40)) : \ + (((_i) < 64) ? (0x01014 + ((_i) * 0x40)) : \ (0x0D014 + (((_i) - 64) * 0x40)))) /* * Rx DCA Control Register: @@ -194,11 +222,11 @@ * 64-127: 0x0D00C + (n-64)*0x40 */ #define IXGBE_DCA_RXCTRL(_i) (((_i) <= 15) ? (0x02200 + ((_i) * 4)) : \ - (((_i) < 64) ? (0x0100C + ((_i) * 0x40)) : \ + (((_i) < 64) ? (0x0100C + ((_i) * 0x40)) : \ (0x0D00C + (((_i) - 64) * 0x40)))) #define IXGBE_RDRXCTL 0x02F00 #define IXGBE_RXPBSIZE(_i) (0x03C00 + ((_i) * 4)) - /* 8 of these 0x03C00 - 0x03C1C */ + /* 8 of these 0x03C00 - 0x03C1C */ #define IXGBE_RXCTRL 0x03000 #define IXGBE_DROPEN 0x03D04 #define IXGBE_RXPBSIZE_SHIFT 10 @@ -211,14 +239,14 @@ /* Multicast Table Array - 128 entries */ #define IXGBE_MTA(_i) (0x05200 + ((_i) * 4)) #define IXGBE_RAL(_i) (((_i) <= 15) ? (0x05400 + ((_i) * 8)) : \ - (0x0A200 + ((_i) * 8))) + (0x0A200 + ((_i) * 8))) #define IXGBE_RAH(_i) (((_i) <= 15) ? (0x05404 + ((_i) * 8)) : \ - (0x0A204 + ((_i) * 8))) + (0x0A204 + ((_i) * 8))) #define IXGBE_MPSAR_LO(_i) (0x0A600 + ((_i) * 8)) #define IXGBE_MPSAR_HI(_i) (0x0A604 + ((_i) * 8)) /* Packet split receive type */ #define IXGBE_PSRTYPE(_i) (((_i) <= 15) ? (0x05480 + ((_i) * 4)) : \ - (0x0EA00 + ((_i) * 4))) + (0x0EA00 + ((_i) * 4))) /* array of 4096 1-bit vlan filters */ #define IXGBE_VFTA(_i) (0x0A000 + ((_i) * 4)) /*array of 4096 4-bit vlan vmdq indices */ @@ -535,6 +563,10 @@ #define IXGBE_RTTDQSEL 0x04904 #define IXGBE_RTTDT1C 0x04908 #define IXGBE_RTTDT1S 0x0490C +#define IXGBE_RTTQCNCR 0x08B00 +#define IXGBE_RTTQCNTG 0x04A90 +#define IXGBE_RTTBCNRD 0x0498C +#define IXGBE_RTTQCNRR 0x0498C #define IXGBE_RTTDTECC 0x04990 #define IXGBE_RTTDTECC_NO_BCN 0x00000100 #define IXGBE_RTTBCNRC 0x04984 @@ -544,6 +576,7 @@ #define IXGBE_RTTBCNRC_RF_INT_MASK \ (IXGBE_RTTBCNRC_RF_DEC_MASK << IXGBE_RTTBCNRC_RF_INT_SHIFT) #define IXGBE_RTTBCNRM 0x04980 +#define IXGBE_RTTQCNRM 0x04980 /* FCoE DMA Context Registers */ #define IXGBE_FCPTRL 0x02410 /* FC User Desc. PTR Low */ @@ -663,7 +696,7 @@ #define IXGBE_RQSMR(_i) (0x02300 + ((_i) * 4)) #define IXGBE_TQSMR(_i) (((_i) <= 7) ? (0x07300 + ((_i) * 4)) : \ - (0x08600 + ((_i) * 4))) + (0x08600 + ((_i) * 4))) #define IXGBE_TQSM(_i) (0x08600 + ((_i) * 4)) #define IXGBE_QPRC(_i) (0x01030 + ((_i) * 0x40)) /* 16 of these */ @@ -707,6 +740,13 @@ #define IXGBE_MDEF_EXT(_i) (0x05160 + ((_i) * 4)) /* 8 of these (0-7) */ #define IXGBE_LSWFW 0x15014 +/* Management Bit Fields and Masks */ +#define IXGBE_MANC_RCV_TCO_EN 0x00020000 /* Rcv TCO packet enable */ + +/* Firmware Semaphore Register */ +#define IXGBE_FWSM_MODE_MASK 0xE +#define IXGBE_FWSM_FW_MODE_PT 0x4 + /* ARC Subsystem registers */ #define IXGBE_HICR 0x15F00 #define IXGBE_FWSTS 0x15F0C @@ -780,7 +820,7 @@ #define IXGBE_GCR_EXT_VT_MODE_32 0x00000002 #define IXGBE_GCR_EXT_VT_MODE_64 0x00000003 #define IXGBE_GCR_EXT_SRIOV (IXGBE_GCR_EXT_MSIX_EN | \ - IXGBE_GCR_EXT_VT_MODE_64) + IXGBE_GCR_EXT_VT_MODE_64) /* Time Sync Registers */ #define IXGBE_TSYNCRXCTL 0x05188 /* Rx Time Sync Control register - RW */ @@ -802,6 +842,8 @@ #define IXGBE_TRGTTIMH0 0x08C28 /* Target Time Register 0 High - RW */ #define IXGBE_TRGTTIML1 0x08C2C /* Target Time Register 1 Low - RW */ #define IXGBE_TRGTTIMH1 0x08C30 /* Target Time Register 1 High - RW */ +#define IXGBE_CLKTIML 0x08C34 /* Clock Out Time Register Low - RW */ +#define IXGBE_CLKTIMH 0x08C38 /* Clock Out Time Register High - RW */ #define IXGBE_FREQOUT0 0x08C34 /* Frequency Out 0 Control register - RW */ #define IXGBE_FREQOUT1 0x08C38 /* Frequency Out 1 Control register - RW */ #define IXGBE_AUXSTMPL0 0x08C3C /* Auxiliary Time Stamp 0 register Low - RO */ @@ -995,6 +1037,7 @@ #define IXGBE_CTRL_RST_MASK (IXGBE_CTRL_LNK_RST | IXGBE_CTRL_RST) /* FACTPS */ +#define IXGBE_FACTPS_MNGCG 0x20000000 /* Manageblility Clock Gated */ #define IXGBE_FACTPS_LFS 0x40000000 /* LAN Function Select */ /* MHADD Bit Masks */ @@ -1021,14 +1064,16 @@ #define IXGBE_DCA_RXCTRL_HEAD_DCA_EN (1 << 6) /* DCA Rx Desc header enable */ #define IXGBE_DCA_RXCTRL_DATA_DCA_EN (1 << 7) /* DCA Rx Desc payload enable */ #define IXGBE_DCA_RXCTRL_DESC_RRO_EN (1 << 9) /* DCA Rx rd Desc Relax Order */ -#define IXGBE_DCA_RXCTRL_DESC_WRO_EN (1 << 13) /* DCA Rx wr Desc Relax Order */ -#define IXGBE_DCA_RXCTRL_DESC_HSRO_EN (1 << 15) /* DCA Rx Split Header RO */ +#define IXGBE_DCA_RXCTRL_DATA_WRO_EN (1 << 13) /* Rx wr data Relax Order */ +#define IXGBE_DCA_RXCTRL_HEAD_WRO_EN (1 << 15) /* Rx wr header RO */ #define IXGBE_DCA_TXCTRL_CPUID_MASK 0x0000001F /* Tx CPUID Mask */ #define IXGBE_DCA_TXCTRL_CPUID_MASK_82599 0xFF000000 /* Tx CPUID Mask */ #define IXGBE_DCA_TXCTRL_CPUID_SHIFT_82599 24 /* Tx CPUID Shift */ #define IXGBE_DCA_TXCTRL_DESC_DCA_EN (1 << 5) /* DCA Tx Desc enable */ -#define IXGBE_DCA_TXCTRL_TX_WB_RO_EN (1 << 11) /* Tx Desc writeback RO bit */ +#define IXGBE_DCA_TXCTRL_DESC_RRO_EN (1 << 9) /* Tx rd Desc Relax Order */ +#define IXGBE_DCA_TXCTRL_DESC_WRO_EN (1 << 11) /* Tx Desc writeback RO bit */ +#define IXGBE_DCA_TXCTRL_DATA_RRO_EN (1 << 13) /* Tx rd data Relax Order */ #define IXGBE_DCA_MAX_QUEUES_82598 16 /* DCA regs only on 16 queues */ /* MSCA Bit Masks */ @@ -1285,6 +1330,7 @@ enum { #define IXGBE_EICR_LINKSEC 0x00200000 /* PN Threshold */ #define IXGBE_EICR_MNG 0x00400000 /* Manageability Event Interrupt */ #define IXGBE_EICR_TS 0x00800000 /* Thermal Sensor Event */ +#define IXGBE_EICR_TIMESYNC 0x01000000 /* Timesync Event */ #define IXGBE_EICR_GPI_SDP0 0x01000000 /* Gen Purpose Interrupt on SDP0 */ #define IXGBE_EICR_GPI_SDP1 0x02000000 /* Gen Purpose Interrupt on SDP1 */ #define IXGBE_EICR_GPI_SDP2 0x04000000 /* Gen Purpose Interrupt on SDP2 */ @@ -1302,6 +1348,7 @@ enum { #define IXGBE_EICS_MAILBOX IXGBE_EICR_MAILBOX /* VF to PF Mailbox Int */ #define IXGBE_EICS_LSC IXGBE_EICR_LSC /* Link Status Change */ #define IXGBE_EICS_MNG IXGBE_EICR_MNG /* MNG Event Interrupt */ +#define IXGBE_EICS_TIMESYNC IXGBE_EICR_TIMESYNC /* Timesync Event */ #define IXGBE_EICS_GPI_SDP0 IXGBE_EICR_GPI_SDP0 /* SDP0 Gen Purpose Int */ #define IXGBE_EICS_GPI_SDP1 IXGBE_EICR_GPI_SDP1 /* SDP1 Gen Purpose Int */ #define IXGBE_EICS_GPI_SDP2 IXGBE_EICR_GPI_SDP2 /* SDP2 Gen Purpose Int */ @@ -1320,6 +1367,7 @@ enum { #define IXGBE_EIMS_LSC IXGBE_EICR_LSC /* Link Status Change */ #define IXGBE_EIMS_MNG IXGBE_EICR_MNG /* MNG Event Interrupt */ #define IXGBE_EIMS_TS IXGBE_EICR_TS /* Thermel Sensor Event */ +#define IXGBE_EIMS_TIMESYNC IXGBE_EICR_TIMESYNC /* Timesync Event */ #define IXGBE_EIMS_GPI_SDP0 IXGBE_EICR_GPI_SDP0 /* SDP0 Gen Purpose Int */ #define IXGBE_EIMS_GPI_SDP1 IXGBE_EICR_GPI_SDP1 /* SDP1 Gen Purpose Int */ #define IXGBE_EIMS_GPI_SDP2 IXGBE_EICR_GPI_SDP2 /* SDP2 Gen Purpose Int */ @@ -1337,6 +1385,7 @@ enum { #define IXGBE_EIMC_MAILBOX IXGBE_EICR_MAILBOX /* VF to PF Mailbox Int */ #define IXGBE_EIMC_LSC IXGBE_EICR_LSC /* Link Status Change */ #define IXGBE_EIMC_MNG IXGBE_EICR_MNG /* MNG Event Interrupt */ +#define IXGBE_EIMC_TIMESYNC IXGBE_EICR_TIMESYNC /* Timesync Event */ #define IXGBE_EIMC_GPI_SDP0 IXGBE_EICR_GPI_SDP0 /* SDP0 Gen Purpose Int */ #define IXGBE_EIMC_GPI_SDP1 IXGBE_EICR_GPI_SDP1 /* SDP1 Gen Purpose Int */ #define IXGBE_EIMC_GPI_SDP2 IXGBE_EICR_GPI_SDP2 /* SDP2 Gen Purpose Int */ @@ -1347,10 +1396,10 @@ enum { #define IXGBE_EIMC_OTHER IXGBE_EICR_OTHER /* INT Cause Active */ #define IXGBE_EIMS_ENABLE_MASK ( \ - IXGBE_EIMS_RTX_QUEUE | \ - IXGBE_EIMS_LSC | \ - IXGBE_EIMS_TCP_TIMER | \ - IXGBE_EIMS_OTHER) + IXGBE_EIMS_RTX_QUEUE | \ + IXGBE_EIMS_LSC | \ + IXGBE_EIMS_TCP_TIMER | \ + IXGBE_EIMS_OTHER) /* Immediate Interrupt Rx (A.K.A. Low Latency Interrupt) */ #define IXGBE_IMIR_PORT_IM_EN 0x00010000 /* TCP port enable */ @@ -1422,6 +1471,7 @@ enum { #define IXGBE_ETQF_1588 0x40000000 /* bit 30 */ #define IXGBE_ETQF_FILTER_EN 0x80000000 /* bit 31 */ #define IXGBE_ETQF_POOL_ENABLE (1 << 26) /* bit 26 */ +#define IXGBE_ETQF_POOL_SHIFT 20 #define IXGBE_ETQS_RX_QUEUE 0x007F0000 /* bits 22:16 */ #define IXGBE_ETQS_RX_QUEUE_SHIFT 16 @@ -1477,8 +1527,12 @@ enum { #define IXGBE_ESDP_SDP4 0x00000010 /* SDP4 Data Value */ #define IXGBE_ESDP_SDP5 0x00000020 /* SDP5 Data Value */ #define IXGBE_ESDP_SDP6 0x00000040 /* SDP6 Data Value */ +#define IXGBE_ESDP_SDP0_DIR 0x00000100 /* SDP0 IO direction */ +#define IXGBE_ESDP_SDP1_DIR 0x00000200 /* SDP1 IO direction */ #define IXGBE_ESDP_SDP4_DIR 0x00000004 /* SDP4 IO direction */ #define IXGBE_ESDP_SDP5_DIR 0x00002000 /* SDP5 IO direction */ +#define IXGBE_ESDP_SDP0_NATIVE 0x00010000 /* SDP0 Native Function */ +#define IXGBE_ESDP_SDP1_NATIVE 0x00020000 /* SDP1 IO mode */ /* LEDCTL Bit Masks */ #define IXGBE_LED_IVRT_BASE 0x00000040 @@ -1549,12 +1603,17 @@ enum { #define IXGBE_AUTOC2_10G_KR (0x0 << IXGBE_AUTOC2_10G_SERIAL_PMA_PMD_SHIFT) #define IXGBE_AUTOC2_10G_XFI (0x1 << IXGBE_AUTOC2_10G_SERIAL_PMA_PMD_SHIFT) #define IXGBE_AUTOC2_10G_SFI (0x2 << IXGBE_AUTOC2_10G_SERIAL_PMA_PMD_SHIFT) +#define IXGBE_AUTOC2_LINK_DISABLE_ON_D3_MASK 0x50000000 +#define IXGBE_AUTOC2_LINK_DISABLE_MASK 0x70000000 #define IXGBE_MACC_FLU 0x00000001 #define IXGBE_MACC_FSV_10G 0x00030000 #define IXGBE_MACC_FS 0x00040000 #define IXGBE_MAC_RX2TX_LPBK 0x00000002 +/* Veto Bit definiton */ +#define IXGBE_MMNGC_MNG_VETO 0x00000001 + /* LINKS Bit Masks */ #define IXGBE_LINKS_KX_AN_COMP 0x80000000 #define IXGBE_LINKS_UP 0x40000000 @@ -1675,11 +1734,29 @@ enum { #define IXGBE_PBANUM0_PTR 0x15 #define IXGBE_PBANUM1_PTR 0x16 #define IXGBE_FREE_SPACE_PTR 0X3E + +/* External Thermal Sensor Config */ +#define IXGBE_ETS_CFG 0x26 +#define IXGBE_ETS_LTHRES_DELTA_MASK 0x07C0 +#define IXGBE_ETS_LTHRES_DELTA_SHIFT 6 +#define IXGBE_ETS_TYPE_MASK 0x0038 +#define IXGBE_ETS_TYPE_SHIFT 3 +#define IXGBE_ETS_TYPE_EMC 0x000 +#define IXGBE_ETS_TYPE_EMC_SHIFTED 0x000 +#define IXGBE_ETS_NUM_SENSORS_MASK 0x0007 +#define IXGBE_ETS_DATA_LOC_MASK 0x3C00 +#define IXGBE_ETS_DATA_LOC_SHIFT 10 +#define IXGBE_ETS_DATA_INDEX_MASK 0x0300 +#define IXGBE_ETS_DATA_INDEX_SHIFT 8 +#define IXGBE_ETS_DATA_HTHRESH_MASK 0x00FF + #define IXGBE_SAN_MAC_ADDR_PTR 0x28 #define IXGBE_DEVICE_CAPS 0x2C #define IXGBE_SERIAL_NUMBER_MAC_ADDR 0x11 #define IXGBE_PCIE_MSIX_82599_CAPS 0x72 +#define IXGBE_MAX_MSIX_VECTORS_82599 0x40 #define IXGBE_PCIE_MSIX_82598_CAPS 0x62 +#define IXGBE_MAX_MSIX_VECTORS_82598 0x13 /* MSI-X capability fields masks */ #define IXGBE_PCIE_MSIX_TBL_SZ_MASK 0x7FF @@ -1716,6 +1793,9 @@ enum { #define IXGBE_EEPROM_RD_BUFFER_MAX_COUNT 512 /* EEPROM words # read in burst */ #define IXGBE_EEPROM_WR_BUFFER_MAX_COUNT 256 /* EEPROM words # wr in burst */ +#define IXGBE_EEPROM_CTRL_2 1 /* EEPROM CTRL word 2 */ +#define IXGBE_EEPROM_CCD_BIT 2 /* EEPROM Core Clock Disable bit */ + #ifndef IXGBE_EEPROM_GRANT_ATTEMPTS #define IXGBE_EEPROM_GRANT_ATTEMPTS 1000 /* EEPROM # attempts to gain grant */ #endif @@ -1776,21 +1856,24 @@ enum { #define IXGBE_PCI_LINK_SPEED 0xF #define IXGBE_PCI_LINK_SPEED_2500 0x1 #define IXGBE_PCI_LINK_SPEED_5000 0x2 +#define IXGBE_PCI_LINK_SPEED_8000 0x3 #define IXGBE_PCI_HEADER_TYPE_REGISTER 0x0E #define IXGBE_PCI_HEADER_TYPE_MULTIFUNC 0x80 #define IXGBE_PCI_DEVICE_CONTROL2_16ms 0x0005 -/* Number of 100 microseconds we wait for PCI Express master disable */ -#define IXGBE_PCI_MASTER_DISABLE_TIMEOUT 800 - -/* Check whether address is multicast. This is little-endian specific check.*/ -#define IXGBE_IS_MULTICAST(Address) \ - (bool)(((u8 *)(Address))[0] & ((u8)0x01)) +#define IXGBE_PCIDEVCTRL2_TIMEO_MASK 0xf +#define IXGBE_PCIDEVCTRL2_16_32ms_def 0x0 +#define IXGBE_PCIDEVCTRL2_50_100us 0x1 +#define IXGBE_PCIDEVCTRL2_1_2ms 0x2 +#define IXGBE_PCIDEVCTRL2_16_32ms 0x5 +#define IXGBE_PCIDEVCTRL2_65_130ms 0x6 +#define IXGBE_PCIDEVCTRL2_260_520ms 0x9 +#define IXGBE_PCIDEVCTRL2_1_2s 0xa +#define IXGBE_PCIDEVCTRL2_4_8s 0xd +#define IXGBE_PCIDEVCTRL2_17_34s 0xe -/* Check whether an address is broadcast. */ -#define IXGBE_IS_BROADCAST(Address) \ - ((((u8 *)(Address))[0] == ((u8)0xff)) && \ - (((u8 *)(Address))[1] == ((u8)0xff))) +/* Number of 100 microseconds we wait for PCI Express master disable */ +#define IXGBE_PCI_MASTER_DISABLE_TIMEOUT 800 /* RAH */ #define IXGBE_RAH_VIND_MASK 0x003C0000 @@ -1802,6 +1885,7 @@ enum { #define IXGBE_RFCTL_ISCSI_DIS 0x00000001 #define IXGBE_RFCTL_ISCSI_DWC_MASK 0x0000003E #define IXGBE_RFCTL_ISCSI_DWC_SHIFT 1 +#define IXGBE_RFCTL_RSC_DIS 0x00000020 #define IXGBE_RFCTL_NFSW_DIS 0x00000040 #define IXGBE_RFCTL_NFSR_DIS 0x00000080 #define IXGBE_RFCTL_NFS_VER_MASK 0x00000300 @@ -1837,6 +1921,40 @@ enum { #define IXGBE_RXDCTL_RLPML_EN 0x00008000 #define IXGBE_RXDCTL_VME 0x40000000 /* VLAN mode enable */ +#define IXGBE_TSAUXC_EN_CLK 0x00000004 +#define IXGBE_TSAUXC_SYNCLK 0x00000008 +#define IXGBE_TSAUXC_SDP0_INT 0x00000040 + +#define IXGBE_TSYNCTXCTL_VALID 0x00000001 /* Tx timestamp valid */ +#define IXGBE_TSYNCTXCTL_ENABLED 0x00000010 /* Tx timestamping enabled */ + +#define IXGBE_TSYNCRXCTL_VALID 0x00000001 /* Rx timestamp valid */ +#define IXGBE_TSYNCRXCTL_TYPE_MASK 0x0000000E /* Rx type mask */ +#define IXGBE_TSYNCRXCTL_TYPE_L2_V2 0x00 +#define IXGBE_TSYNCRXCTL_TYPE_L4_V1 0x02 +#define IXGBE_TSYNCRXCTL_TYPE_L2_L4_V2 0x04 +#define IXGBE_TSYNCRXCTL_TYPE_EVENT_V2 0x0A +#define IXGBE_TSYNCRXCTL_ENABLED 0x00000010 /* Rx Timestamping enabled */ + +#define IXGBE_RXMTRL_V1_CTRLT_MASK 0x000000FF +#define IXGBE_RXMTRL_V1_SYNC_MSG 0x00 +#define IXGBE_RXMTRL_V1_DELAY_REQ_MSG 0x01 +#define IXGBE_RXMTRL_V1_FOLLOWUP_MSG 0x02 +#define IXGBE_RXMTRL_V1_DELAY_RESP_MSG 0x03 +#define IXGBE_RXMTRL_V1_MGMT_MSG 0x04 + +#define IXGBE_RXMTRL_V2_MSGID_MASK 0x0000FF00 +#define IXGBE_RXMTRL_V2_SYNC_MSG 0x0000 +#define IXGBE_RXMTRL_V2_DELAY_REQ_MSG 0x0100 +#define IXGBE_RXMTRL_V2_PDELAY_REQ_MSG 0x0200 +#define IXGBE_RXMTRL_V2_PDELAY_RESP_MSG 0x0300 +#define IXGBE_RXMTRL_V2_FOLLOWUP_MSG 0x0800 +#define IXGBE_RXMTRL_V2_DELAY_RESP_MSG 0x0900 +#define IXGBE_RXMTRL_V2_PDELAY_FOLLOWUP_MSG 0x0A00 +#define IXGBE_RXMTRL_V2_ANNOUNCE_MSG 0x0B00 +#define IXGBE_RXMTRL_V2_SIGNALING_MSG 0x0C00 +#define IXGBE_RXMTRL_V2_MGMT_MSG 0x0D00 + #define IXGBE_FCTRL_SBP 0x00000002 /* Store Bad Packet */ #define IXGBE_FCTRL_MPE 0x00000100 /* Multicast Promiscuous Ena*/ #define IXGBE_FCTRL_UPE 0x00000200 /* Unicast Promiscuous Ena */ @@ -1850,7 +1968,7 @@ enum { #define IXGBE_MFLCN_DPF 0x00000002 /* Discard Pause Frame */ #define IXGBE_MFLCN_RPFCE 0x00000004 /* Receive Priority FC Enable */ #define IXGBE_MFLCN_RFCE 0x00000008 /* Receive FC Enable */ -#define IXGBE_MFLCN_RPFCE_MASK 0x00000FF0 /* Receive FC Mask */ +#define IXGBE_MFLCN_RPFCE_MASK 0x00000FF4 /* Receive FC Mask */ #define IXGBE_MFLCN_RPFCE_SHIFT 4 @@ -1878,10 +1996,13 @@ enum { #define IXGBE_MRQC_RSS_FIELD_IPV6_EX_UDP 0x01000000 #define IXGBE_MRQC_L3L4TXSWEN 0x00008000 +#define IXGBE_FWSM_TS_ENABLED 0x1 + /* Queue Drop Enable */ -#define IXGBE_QDE_ENABLE 0x00000001 -#define IXGBE_QDE_IDX_MASK 0x00007F00 -#define IXGBE_QDE_IDX_SHIFT 8 +#define IXGBE_QDE_ENABLE 0x00000001 +#define IXGBE_QDE_IDX_MASK 0x00007F00 +#define IXGBE_QDE_IDX_SHIFT 8 +#define IXGBE_QDE_WRITE 0x00010000 #define IXGBE_TXD_POPTS_IXSM 0x01 /* Insert IP checksum */ #define IXGBE_TXD_POPTS_TXSM 0x02 /* Insert TCP/UDP checksum */ @@ -1966,6 +2087,7 @@ enum { #define IXGBE_RXDADV_STAT_FCSTAT_NODDP 0x00000010 /* 01: Ctxt w/o DDP */ #define IXGBE_RXDADV_STAT_FCSTAT_FCPRSP 0x00000020 /* 10: Recv. FCP_RSP */ #define IXGBE_RXDADV_STAT_FCSTAT_DDP 0x00000030 /* 11: Ctxt w/ DDP */ +#define IXGBE_RXDADV_STAT_TS 0x00010000 /* IEEE 1588 Time Stamp */ /* PSRTYPE bit definitions */ #define IXGBE_PSRTYPE_TCPHDR 0x00000010 @@ -2039,18 +2161,18 @@ enum { /* Masks to determine if packets should be dropped due to frame errors */ #define IXGBE_RXD_ERR_FRAME_ERR_MASK ( \ - IXGBE_RXD_ERR_CE | \ - IXGBE_RXD_ERR_LE | \ - IXGBE_RXD_ERR_PE | \ - IXGBE_RXD_ERR_OSE | \ - IXGBE_RXD_ERR_USE) + IXGBE_RXD_ERR_CE | \ + IXGBE_RXD_ERR_LE | \ + IXGBE_RXD_ERR_PE | \ + IXGBE_RXD_ERR_OSE | \ + IXGBE_RXD_ERR_USE) #define IXGBE_RXDADV_ERR_FRAME_ERR_MASK ( \ - IXGBE_RXDADV_ERR_CE | \ - IXGBE_RXDADV_ERR_LE | \ - IXGBE_RXDADV_ERR_PE | \ - IXGBE_RXDADV_ERR_OSE | \ - IXGBE_RXDADV_ERR_USE) + IXGBE_RXDADV_ERR_CE | \ + IXGBE_RXDADV_ERR_LE | \ + IXGBE_RXDADV_ERR_PE | \ + IXGBE_RXDADV_ERR_OSE | \ + IXGBE_RXDADV_ERR_USE) /* Multicast bit mask */ #define IXGBE_MCSTCTRL_MFE 0x4 @@ -2071,6 +2193,14 @@ enum { #define IXGBE_MBVFICR(_i) (0x00710 + ((_i) * 4)) #define IXGBE_VFLRE(_i) ((((_i) & 1) ? 0x001C0 : 0x00600)) #define IXGBE_VFLREC(_i) (0x00700 + ((_i) * 4)) +/* Translated register #defines */ +#define IXGBE_PVFTDWBAL(P) (0x06038 + (0x40 * (P))) +#define IXGBE_PVFTDWBAH(P) (0x0603C + (0x40 * (P))) + +#define IXGBE_PVFTDWBALn(q_per_pool, vf_number, vf_q_index) \ + (IXGBE_PVFTDWBAL((q_per_pool)*(vf_number) + (vf_q_index))) +#define IXGBE_PVFTDWBAHn(q_per_pool, vf_number, vf_q_index) \ + (IXGBE_PVFTDWBAH((q_per_pool)*(vf_number) + (vf_q_index))) enum ixgbe_fdir_pballoc_type { IXGBE_FDIR_PBALLOC_NONE = 0, @@ -2243,6 +2373,7 @@ struct ixgbe_adv_tx_context_desc { /* Adv Transmit Descriptor Config Masks */ #define IXGBE_ADVTXD_DTALEN_MASK 0x0000FFFF /* Data buf length(bytes) */ #define IXGBE_ADVTXD_MAC_LINKSEC 0x00040000 /* Insert LinkSec */ +#define IXGBE_ADVTXD_MAC_TSTAMP 0x00080000 /* IEEE 1588 Time Stamp */ #define IXGBE_ADVTXD_IPSEC_SA_INDEX_MASK 0x000003FF /* IPSec SA index */ #define IXGBE_ADVTXD_IPSEC_ESP_LEN_MASK 0x000001FF /* IPSec ESP length */ #define IXGBE_ADVTXD_DTYP_MASK 0x00F00000 /* DTYP mask */ @@ -2262,9 +2393,9 @@ struct ixgbe_adv_tx_context_desc { #define IXGBE_ADVTXD_CC 0x00000080 /* Check Context */ #define IXGBE_ADVTXD_POPTS_SHIFT 8 /* Adv desc POPTS shift */ #define IXGBE_ADVTXD_POPTS_IXSM (IXGBE_TXD_POPTS_IXSM << \ - IXGBE_ADVTXD_POPTS_SHIFT) + IXGBE_ADVTXD_POPTS_SHIFT) #define IXGBE_ADVTXD_POPTS_TXSM (IXGBE_TXD_POPTS_TXSM << \ - IXGBE_ADVTXD_POPTS_SHIFT) + IXGBE_ADVTXD_POPTS_SHIFT) #define IXGBE_ADVTXD_POPTS_ISCO_1ST 0x00000000 /* 1st TSO of iSCSI PDU */ #define IXGBE_ADVTXD_POPTS_ISCO_MDL 0x00000800 /* Middle TSO of iSCSI PDU */ #define IXGBE_ADVTXD_POPTS_ISCO_LAST 0x00001000 /* Last TSO of iSCSI PDU */ @@ -2304,10 +2435,10 @@ typedef u32 ixgbe_link_speed; #define IXGBE_LINK_SPEED_1GB_FULL 0x0020 #define IXGBE_LINK_SPEED_10GB_FULL 0x0080 #define IXGBE_LINK_SPEED_82598_AUTONEG (IXGBE_LINK_SPEED_1GB_FULL | \ - IXGBE_LINK_SPEED_10GB_FULL) + IXGBE_LINK_SPEED_10GB_FULL) #define IXGBE_LINK_SPEED_82599_AUTONEG (IXGBE_LINK_SPEED_100_FULL | \ - IXGBE_LINK_SPEED_1GB_FULL | \ - IXGBE_LINK_SPEED_10GB_FULL) + IXGBE_LINK_SPEED_1GB_FULL | \ + IXGBE_LINK_SPEED_10GB_FULL) /* Physical layer type */ @@ -2333,7 +2464,7 @@ typedef u32 ixgbe_physical_layer; */ /* BitTimes (BT) conversion */ -#define IXGBE_BT2KB(BT) ((BT + 1023) / (8 * 1024)) +#define IXGBE_BT2KB(BT) ((BT + (8 * 1024 - 1)) / (8 * 1024)) #define IXGBE_B2BT(BT) (BT * 8) /* Calculate Delay to respond to PFC */ @@ -2364,24 +2495,31 @@ typedef u32 ixgbe_physical_layer; #define IXGBE_PCI_DELAY 10000 /* Calculate X540 delay value in bit times */ -#define IXGBE_FILL_RATE (36 / 25) - -#define IXGBE_DV_X540(LINK, TC) (IXGBE_FILL_RATE * \ - (IXGBE_B2BT(LINK) + IXGBE_PFC_D + \ - (2 * IXGBE_CABLE_DC) + \ - (2 * IXGBE_ID_X540) + \ - IXGBE_HD + IXGBE_B2BT(TC))) +#define IXGBE_DV_X540(_max_frame_link, _max_frame_tc) \ + ((36 * \ + (IXGBE_B2BT(_max_frame_link) + \ + IXGBE_PFC_D + \ + (2 * IXGBE_CABLE_DC) + \ + (2 * IXGBE_ID_X540) + \ + IXGBE_HD) / 25 + 1) + \ + 2 * IXGBE_B2BT(_max_frame_tc)) /* Calculate 82599, 82598 delay value in bit times */ -#define IXGBE_DV(LINK, TC) (IXGBE_FILL_RATE * \ - (IXGBE_B2BT(LINK) + IXGBE_PFC_D + \ - (2 * IXGBE_CABLE_DC) + (2 * IXGBE_ID) + \ - IXGBE_HD + IXGBE_B2BT(TC))) +#define IXGBE_DV(_max_frame_link, _max_frame_tc) \ + ((36 * \ + (IXGBE_B2BT(_max_frame_link) + \ + IXGBE_PFC_D + \ + (2 * IXGBE_CABLE_DC) + \ + (2 * IXGBE_ID) + \ + IXGBE_HD) / 25 + 1) + \ + 2 * IXGBE_B2BT(_max_frame_tc)) /* Calculate low threshold delay values */ -#define IXGBE_LOW_DV_X540(TC) (2 * IXGBE_B2BT(TC) + \ - (IXGBE_FILL_RATE * IXGBE_PCI_DELAY)) -#define IXGBE_LOW_DV(TC) (2 * IXGBE_LOW_DV_X540(TC)) +#define IXGBE_LOW_DV_X540(_max_frame_tc) \ + (2 * IXGBE_B2BT(_max_frame_tc) + \ + (36 * IXGBE_PCI_DELAY / 25) + 1) +#define IXGBE_LOW_DV(_max_frame_tc) \ + (2 * IXGBE_LOW_DV_X540(_max_frame_tc)) /* Software ATR hash keys */ #define IXGBE_ATR_BUCKET_HASH_KEY 0x3DAD14E2 @@ -2482,6 +2620,10 @@ enum ixgbe_phy_type { ixgbe_phy_sfp_ftl_active, ixgbe_phy_sfp_unknown, ixgbe_phy_sfp_intel, + ixgbe_phy_qsfp_passive_unknown, + ixgbe_phy_qsfp_active_unknown, + ixgbe_phy_qsfp_intel, + ixgbe_phy_qsfp_unknown, ixgbe_phy_sfp_unsupported, ixgbe_phy_generic }; @@ -2511,6 +2653,10 @@ enum ixgbe_sfp_type { ixgbe_sfp_type_da_act_lmt_core1 = 8, ixgbe_sfp_type_1g_cu_core0 = 9, ixgbe_sfp_type_1g_cu_core1 = 10, + ixgbe_sfp_type_1g_sx_core0 = 11, + ixgbe_sfp_type_1g_sx_core1 = 12, + ixgbe_sfp_type_1g_lx_core0 = 13, + ixgbe_sfp_type_1g_lx_core1 = 14, ixgbe_sfp_type_not_present = 0xFFFE, ixgbe_sfp_type_unknown = 0xFFFF }; @@ -2518,6 +2664,7 @@ enum ixgbe_sfp_type { enum ixgbe_media_type { ixgbe_media_type_unknown = 0, ixgbe_media_type_fiber, + ixgbe_media_type_fiber_qsfp, ixgbe_media_type_fiber_lco, ixgbe_media_type_copper, ixgbe_media_type_backplane, @@ -2531,9 +2678,6 @@ enum ixgbe_fc_mode { ixgbe_fc_rx_pause, ixgbe_fc_tx_pause, ixgbe_fc_full, -#ifdef CONFIG_DCB - ixgbe_fc_pfc, -#endif ixgbe_fc_default }; @@ -2564,6 +2708,7 @@ enum ixgbe_bus_speed { ixgbe_bus_speed_133 = 133, ixgbe_bus_speed_2500 = 2500, ixgbe_bus_speed_5000 = 5000, + ixgbe_bus_speed_8000 = 8000, ixgbe_bus_speed_reserved }; @@ -2601,7 +2746,7 @@ struct ixgbe_bus_info { /* Flow control parameters */ struct ixgbe_fc_info { u32 high_water[MAX_TRAFFIC_CLASS]; /* Flow Control High-water */ - u32 low_water; /* Flow Control Low-water */ + u32 low_water[MAX_TRAFFIC_CLASS]; /* Flow Control Low-water */ u16 pause_time; /* Flow Control Pause timer */ bool send_xon; /* Flow control send XON */ bool strict_ieee; /* Strict IEEE mode */ @@ -2695,7 +2840,7 @@ struct ixgbe_hw; /* iterator type for walking multicast address lists */ typedef u8* (*ixgbe_mc_addr_itr) (struct ixgbe_hw *hw, u8 **mc_addr_ptr, - u32 *vmdq); + u32 *vmdq); /* Function pointer table */ struct ixgbe_eeprom_operations { @@ -2726,18 +2871,23 @@ struct ixgbe_mac_operations { s32 (*read_analog_reg8)(struct ixgbe_hw*, u32, u8*); s32 (*write_analog_reg8)(struct ixgbe_hw*, u32, u8); s32 (*setup_sfp)(struct ixgbe_hw *); + s32 (*disable_rx_buff)(struct ixgbe_hw *); + s32 (*enable_rx_buff)(struct ixgbe_hw *); s32 (*enable_rx_dma)(struct ixgbe_hw *, u32); s32 (*acquire_swfw_sync)(struct ixgbe_hw *, u16); void (*release_swfw_sync)(struct ixgbe_hw *, u16); + s32 (*prot_autoc_read)(struct ixgbe_hw *, bool *, u32 *); + s32 (*prot_autoc_write)(struct ixgbe_hw *, u32, bool); /* Link */ void (*disable_tx_laser)(struct ixgbe_hw *); void (*enable_tx_laser)(struct ixgbe_hw *); void (*flap_tx_laser)(struct ixgbe_hw *); - s32 (*setup_link)(struct ixgbe_hw *, ixgbe_link_speed, bool, bool); + void (*stop_link_on_d3)(struct ixgbe_hw *); + s32 (*setup_link)(struct ixgbe_hw *, ixgbe_link_speed, bool); s32 (*check_link)(struct ixgbe_hw *, ixgbe_link_speed *, bool *, bool); s32 (*get_link_capabilities)(struct ixgbe_hw *, ixgbe_link_speed *, - bool *); + bool *); /* Packet Buffer Manipulation */ void (*set_rxpba)(struct ixgbe_hw *, int, u32, int); @@ -2752,6 +2902,7 @@ struct ixgbe_mac_operations { s32 (*set_rar)(struct ixgbe_hw *, u32, u8 *, u32, u32); s32 (*clear_rar)(struct ixgbe_hw *, u32); s32 (*set_vmdq)(struct ixgbe_hw *, u32, u32); + s32 (*set_vmdq_san_mac)(struct ixgbe_hw *, u32); s32 (*clear_vmdq)(struct ixgbe_hw *, u32, u32); s32 (*init_rx_addrs)(struct ixgbe_hw *); s32 (*update_mc_addr_list)(struct ixgbe_hw *, struct net_device *); @@ -2764,10 +2915,12 @@ struct ixgbe_mac_operations { void (*set_vlan_anti_spoofing)(struct ixgbe_hw *, bool, int); /* Flow Control */ - s32 (*fc_enable)(struct ixgbe_hw *, s32); + s32 (*fc_enable)(struct ixgbe_hw *); /* Manageability interface */ s32 (*set_fw_drv_ver)(struct ixgbe_hw *, u8, u8, u8, u8); + s32 (*get_thermal_sensor_data)(struct ixgbe_hw *); + s32 (*init_thermal_sensor_thresh)(struct ixgbe_hw *hw); }; struct ixgbe_phy_operations { @@ -2777,13 +2930,15 @@ struct ixgbe_phy_operations { s32 (*reset)(struct ixgbe_hw *); s32 (*read_reg)(struct ixgbe_hw *, u32, u32, u16 *); s32 (*write_reg)(struct ixgbe_hw *, u32, u32, u16); + s32 (*read_reg_mdi)(struct ixgbe_hw *, u32, u32, u16 *); + s32 (*write_reg_mdi)(struct ixgbe_hw *, u32, u32, u16); s32 (*setup_link)(struct ixgbe_hw *); - s32 (*setup_link_speed)(struct ixgbe_hw *, ixgbe_link_speed, bool, - bool); + s32 (*setup_link_speed)(struct ixgbe_hw *, ixgbe_link_speed, bool); s32 (*check_link)(struct ixgbe_hw *, ixgbe_link_speed *, bool *); s32 (*get_firmware_version)(struct ixgbe_hw *, u16 *); s32 (*read_i2c_byte)(struct ixgbe_hw *, u8, u8, u8 *); s32 (*write_i2c_byte)(struct ixgbe_hw *, u8, u8, u8); + s32 (*read_i2c_sff8472)(struct ixgbe_hw *, u8 , u8 *); s32 (*read_i2c_eeprom)(struct ixgbe_hw *, u8 , u8 *); s32 (*write_i2c_eeprom)(struct ixgbe_hw *, u8, u8); s32 (*check_overtemp)(struct ixgbe_hw *); @@ -2809,6 +2964,7 @@ struct ixgbe_mac_info { u16 wwnn_prefix; /* prefix for World Wide Port Name (WWPN) */ u16 wwpn_prefix; + u16 max_msix_vectors; #define IXGBE_MAX_MTA 128 u32 mta_shadow[IXGBE_MAX_MTA]; s32 mc_filter_type; @@ -2819,12 +2975,13 @@ struct ixgbe_mac_info { u32 rx_pb_size; u32 max_tx_queues; u32 max_rx_queues; - u32 max_msix_vectors; u32 orig_autoc; u32 orig_autoc2; bool orig_link_settings_stored; bool autotry_restart; u8 flags; + u8 san_mac_rar_index; + struct ixgbe_thermal_sensor_data thermal_sensor_data; }; struct ixgbe_phy_info { @@ -2842,6 +2999,7 @@ struct ixgbe_phy_info { bool smart_speed_active; bool multispeed_fiber; bool reset_if_overtemp; + bool qsfp_shared_i2c_bus; }; #include "ixgbe_mbx.h" @@ -2892,6 +3050,8 @@ struct ixgbe_hw { u8 revision_id; bool adapter_stopped; bool force_full_reset; + bool allow_unsupported_sfp; + bool wol_enabled; }; struct ixgbe_info { @@ -2933,7 +3093,6 @@ struct ixgbe_info { #define IXGBE_ERR_OVERTEMP -26 #define IXGBE_ERR_FC_NOT_NEGOTIATED -27 #define IXGBE_ERR_FC_NOT_SUPPORTED -28 -#define IXGBE_ERR_FLOW_CONTROL -29 #define IXGBE_ERR_SFP_SETUP_NOT_COMPLETE -30 #define IXGBE_ERR_PBA_SECTION -31 #define IXGBE_ERR_INVALID_ARGUMENT -32 diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c index f838a2be8cf..40dd798e129 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c @@ -1,7 +1,7 @@ /******************************************************************************* Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. + Copyright(c) 1999 - 2013 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, @@ -20,6 +20,7 @@ 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 @@ -32,12 +33,12 @@ #include "ixgbe.h" #include "ixgbe_phy.h" -#define IXGBE_X540_MAX_TX_QUEUES 128 -#define IXGBE_X540_MAX_RX_QUEUES 128 -#define IXGBE_X540_RAR_ENTRIES 128 -#define IXGBE_X540_MC_TBL_SIZE 128 -#define IXGBE_X540_VFT_TBL_SIZE 128 -#define IXGBE_X540_RX_PB_SIZE 384 +#define IXGBE_X540_MAX_TX_QUEUES 128 +#define IXGBE_X540_MAX_RX_QUEUES 128 +#define IXGBE_X540_RAR_ENTRIES 128 +#define IXGBE_X540_MC_TBL_SIZE 128 +#define IXGBE_X540_VFT_TBL_SIZE 128 +#define IXGBE_X540_RX_PB_SIZE 384 static s32 ixgbe_update_flash_X540(struct ixgbe_hw *hw); static s32 ixgbe_poll_flash_update_done_X540(struct ixgbe_hw *hw); @@ -61,6 +62,7 @@ static s32 ixgbe_get_invariants_X540(struct ixgbe_hw *hw) mac->mcft_size = IXGBE_X540_MC_TBL_SIZE; mac->vft_size = IXGBE_X540_VFT_TBL_SIZE; mac->num_rar_entries = IXGBE_X540_RAR_ENTRIES; + mac->rx_pb_size = IXGBE_X540_RX_PB_SIZE; mac->max_rx_queues = IXGBE_X540_MAX_RX_QUEUES; mac->max_tx_queues = IXGBE_X540_MAX_TX_QUEUES; mac->max_msix_vectors = ixgbe_get_pcie_msix_count_generic(hw); @@ -72,15 +74,14 @@ static s32 ixgbe_get_invariants_X540(struct ixgbe_hw *hw) * ixgbe_setup_mac_link_X540 - Set the auto advertised capabilitires * @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 **/ static s32 ixgbe_setup_mac_link_X540(struct ixgbe_hw *hw, - ixgbe_link_speed speed, bool autoneg, - bool autoneg_wait_to_complete) + ixgbe_link_speed speed, + bool autoneg_wait_to_complete) { - return hw->phy.ops.setup_link_speed(hw, speed, autoneg, - autoneg_wait_to_complete); + return hw->phy.ops.setup_link_speed(hw, speed, + autoneg_wait_to_complete); } /** @@ -152,9 +153,12 @@ mac_reset_top: 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) { + if (is_valid_ether_addr(hw->mac.san_addr)) { hw->mac.ops.set_rar(hw, hw->mac.num_rar_entries - 1, - hw->mac.san_addr, 0, IXGBE_RAH_AV); + hw->mac.san_addr, 0, IXGBE_RAH_AV); + + /* Save the SAN MAC RAR index */ + hw->mac.san_mac_rar_index = hw->mac.num_rar_entries - 1; /* Reserve the last RAR for the SAN MAC address */ hw->mac.num_rar_entries--; @@ -162,7 +166,7 @@ mac_reset_top: /* Store the alternative WWNN/WWPN prefix */ hw->mac.ops.get_wwn_prefix(hw, &hw->mac.wwnn_prefix, - &hw->mac.wwpn_prefix); + &hw->mac.wwpn_prefix); reset_hw_out: return status; @@ -185,7 +189,6 @@ static s32 ixgbe_start_hw_X540(struct ixgbe_hw *hw) goto out; ret_val = ixgbe_start_hw_gen2(hw); - hw->mac.rx_pb_size = IXGBE_X540_RX_PB_SIZE; out: return ret_val; } @@ -234,9 +237,9 @@ static s32 ixgbe_init_eeprom_params_X540(struct ixgbe_hw *hw) eec = IXGBE_READ_REG(hw, IXGBE_EEC); eeprom_size = (u16)((eec & IXGBE_EEC_SIZE) >> - IXGBE_EEC_SIZE_SHIFT); + IXGBE_EEC_SIZE_SHIFT); eeprom->word_size = 1 << (eeprom_size + - IXGBE_EEPROM_WORD_SIZE_SHIFT); + IXGBE_EEPROM_WORD_SIZE_SHIFT); hw_dbg(hw, "Eeprom params: type = %d, size = %d\n", eeprom->type, eeprom->word_size); @@ -709,8 +712,7 @@ static s32 ixgbe_get_swfw_sync_semaphore(struct ixgbe_hw *hw) udelay(50); } } else { - hw_dbg(hw, "Software semaphore SMBI between device drivers " - "not granted.\n"); + hw_dbg(hw, "Software semaphore SMBI between device drivers not granted.\n"); } return status; @@ -760,7 +762,7 @@ static s32 ixgbe_blink_led_start_X540(struct ixgbe_hw *hw, u32 index) * This will be reversed when we stop the blinking. */ hw->mac.ops.check_link(hw, &speed, &link_up, false); - if (link_up == false) { + if (!link_up) { macc_reg = IXGBE_READ_REG(hw, IXGBE_MACC); macc_reg |= IXGBE_MACC_FLU | IXGBE_MACC_FSV_10G | IXGBE_MACC_FS; IXGBE_WRITE_REG(hw, IXGBE_MACC, macc_reg); @@ -810,7 +812,7 @@ static struct ixgbe_mac_operations mac_ops_X540 = { .clear_hw_cntrs = &ixgbe_clear_hw_cntrs_generic, .get_media_type = &ixgbe_get_media_type_X540, .get_supported_physical_layer = - &ixgbe_get_supported_physical_layer_X540, + &ixgbe_get_supported_physical_layer_X540, .enable_rx_dma = &ixgbe_enable_rx_dma_generic, .get_mac_addr = &ixgbe_get_mac_addr_generic, .get_san_mac_addr = &ixgbe_get_san_mac_addr_generic, @@ -832,6 +834,7 @@ static struct ixgbe_mac_operations mac_ops_X540 = { .set_rar = &ixgbe_set_rar_generic, .clear_rar = &ixgbe_clear_rar_generic, .set_vmdq = &ixgbe_set_vmdq_generic, + .set_vmdq_san_mac = &ixgbe_set_vmdq_san_mac_generic, .clear_vmdq = &ixgbe_clear_vmdq_generic, .init_rx_addrs = &ixgbe_init_rx_addrs_generic, .update_mc_addr_list = &ixgbe_update_mc_addr_list_generic, @@ -847,6 +850,12 @@ static struct ixgbe_mac_operations mac_ops_X540 = { .set_vlan_anti_spoofing = &ixgbe_set_vlan_anti_spoofing, .acquire_swfw_sync = &ixgbe_acquire_swfw_sync_X540, .release_swfw_sync = &ixgbe_release_swfw_sync_X540, + .disable_rx_buff = &ixgbe_disable_rx_buff_generic, + .enable_rx_buff = &ixgbe_enable_rx_buff_generic, + .get_thermal_sensor_data = NULL, + .init_thermal_sensor_thresh = NULL, + .prot_autoc_read = &prot_autoc_read_generic, + .prot_autoc_write = &prot_autoc_write_generic, }; static struct ixgbe_eeprom_operations eeprom_ops_X540 = { @@ -871,6 +880,7 @@ static struct ixgbe_phy_operations phy_ops_X540 = { .setup_link_speed = &ixgbe_setup_phy_link_speed_generic, .read_i2c_byte = &ixgbe_read_i2c_byte_generic, .write_i2c_byte = &ixgbe_write_i2c_byte_generic, + .read_i2c_sff8472 = &ixgbe_read_i2c_sff8472_generic, .read_i2c_eeprom = &ixgbe_read_i2c_eeprom_generic, .write_i2c_eeprom = &ixgbe_write_i2c_eeprom_generic, .check_overtemp = &ixgbe_tn_check_overtemp, |