diff options
Diffstat (limited to 'drivers/net/ethernet/intel/igc')
19 files changed, 1870 insertions, 626 deletions
diff --git a/drivers/net/ethernet/intel/igc/Makefile b/drivers/net/ethernet/intel/igc/Makefile index 95d1e8c490a4..efc5e7983dad 100644 --- a/drivers/net/ethernet/intel/igc/Makefile +++ b/drivers/net/ethernet/intel/igc/Makefile @@ -7,5 +7,6 @@ obj-$(CONFIG_IGC) += igc.o -igc-objs := igc_main.o igc_mac.o igc_i225.o igc_base.o igc_nvm.o igc_phy.o \ -igc_diag.o igc_ethtool.o igc_ptp.o igc_dump.o igc_tsn.o igc_xdp.o +igc-y := igc_main.o igc_mac.o igc_i225.o igc_base.o igc_nvm.o igc_phy.o \ + igc_diag.o igc_ethtool.o igc_ptp.o igc_dump.o igc_tsn.o igc_xdp.o +igc-$(CONFIG_IGC_LEDS) += igc_leds.o diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 45430e246e9c..859a15e4ccba 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -40,6 +40,11 @@ void igc_ethtool_set_ops(struct net_device *); #define IGC_MAX_TX_TSTAMP_REGS 4 +struct igc_fpe_t { + struct ethtool_mmsv mmsv; + u32 tx_min_frag_size; +}; + enum igc_mac_filter_type { IGC_MAC_FILTER_TYPE_DST = 0, IGC_MAC_FILTER_TYPE_SRC @@ -72,13 +77,46 @@ struct igc_rx_packet_stats { u64 other_packets; }; +enum igc_tx_buffer_type { + IGC_TX_BUFFER_TYPE_SKB, + IGC_TX_BUFFER_TYPE_XDP, + IGC_TX_BUFFER_TYPE_XSK, +}; + +/* wrapper around a pointer to a socket buffer, + * so a DMA handle can be stored along with the buffer + */ +struct igc_tx_buffer { + union igc_adv_tx_desc *next_to_watch; + unsigned long time_stamp; + enum igc_tx_buffer_type type; + union { + struct sk_buff *skb; + struct xdp_frame *xdpf; + }; + unsigned int bytecount; + u16 gso_segs; + __be16 protocol; + + DEFINE_DMA_UNMAP_ADDR(dma); + DEFINE_DMA_UNMAP_LEN(len); + u32 tx_flags; + bool xsk_pending_ts; +}; + struct igc_tx_timestamp_request { - struct sk_buff *skb; /* reference to the packet being timestamped */ + union { /* reference to the packet being timestamped */ + struct sk_buff *skb; + struct igc_tx_buffer *xsk_tx_buffer; + }; + enum igc_tx_buffer_type buffer_type; unsigned long start; /* when the tstamp request started (jiffies) */ u32 mask; /* _TSYNCTXCTL_TXTT_{X} bit for this request */ u32 regl; /* which TXSTMPL_{X} register should be used */ u32 regh; /* which TXSTMPH_{X} register should be used */ u32 flags; /* flags that should be added to the tx_buffer */ + u8 xsk_queue_index; /* Tx queue which requesting timestamp */ + struct xsk_tx_metadata_compl xsk_meta; /* ref to xsk Tx metadata */ }; struct igc_inline_rx_tstamps { @@ -168,8 +206,7 @@ struct igc_ring { struct igc_adapter { struct net_device *netdev; - struct ethtool_eee eee; - u16 eee_advert; + struct ethtool_keee eee; unsigned long state; unsigned int flags; @@ -227,6 +264,10 @@ struct igc_adapter { */ spinlock_t qbv_tx_lock; + bool strict_priority_enable; + u8 num_tc; + u16 queue_per_tc[IGC_MAX_TX_QUEUES]; + /* OS defined structs */ struct pci_dev *pdev; /* lock for statistics */ @@ -283,6 +324,7 @@ struct igc_adapter { struct timespec64 prev_ptp_time; /* Pre-reset PTP clock */ ktime_t ptp_reset_start; /* Reset time in clock mono */ struct system_time_snapshot snapshot; + struct mutex ptm_lock; /* Only allow one PTM transaction at a time */ char fw_version[32]; @@ -295,6 +337,12 @@ struct igc_adapter { struct timespec64 start; struct timespec64 period; } perout[IGC_N_PEROUT]; + + struct igc_fpe_t fpe; + + /* LEDs */ + struct mutex led_mutex; + struct igc_led_classdev *leds; }; void igc_up(struct igc_adapter *adapter); @@ -319,6 +367,9 @@ void igc_disable_tx_ring(struct igc_ring *ring); void igc_enable_tx_ring(struct igc_ring *ring); int igc_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags); +/* AF_XDP TX metadata operations */ +extern const struct xsk_tx_metadata_ops igc_xsk_tx_metadata_ops; + /* igc_dump declarations */ void igc_rings_dump(struct igc_adapter *adapter); void igc_regs_dump(struct igc_adapter *adapter); @@ -343,9 +394,11 @@ extern char igc_driver_name[]; #define IGC_FLAG_RX_LEGACY BIT(16) #define IGC_FLAG_TSN_QBV_ENABLED BIT(17) #define IGC_FLAG_TSN_QAV_ENABLED BIT(18) +#define IGC_FLAG_TSN_PREEMPT_ENABLED BIT(19) -#define IGC_FLAG_TSN_ANY_ENABLED \ - (IGC_FLAG_TSN_QBV_ENABLED | IGC_FLAG_TSN_QAV_ENABLED) +#define IGC_FLAG_TSN_ANY_ENABLED \ + (IGC_FLAG_TSN_QBV_ENABLED | IGC_FLAG_TSN_QAV_ENABLED | \ + IGC_FLAG_TSN_PREEMPT_ENABLED) #define IGC_FLAG_RSS_FIELD_IPV4_UDP BIT(6) #define IGC_FLAG_RSS_FIELD_IPV6_UDP BIT(7) @@ -504,32 +557,6 @@ enum igc_boards { #define TXD_USE_COUNT(S) DIV_ROUND_UP((S), IGC_MAX_DATA_PER_TXD) #define DESC_NEEDED (MAX_SKB_FRAGS + 4) -enum igc_tx_buffer_type { - IGC_TX_BUFFER_TYPE_SKB, - IGC_TX_BUFFER_TYPE_XDP, - IGC_TX_BUFFER_TYPE_XSK, -}; - -/* wrapper around a pointer to a socket buffer, - * so a DMA handle can be stored along with the buffer - */ -struct igc_tx_buffer { - union igc_adv_tx_desc *next_to_watch; - unsigned long time_stamp; - enum igc_tx_buffer_type type; - union { - struct sk_buff *skb; - struct xdp_frame *xdpf; - }; - unsigned int bytecount; - u16 gso_segs; - __be16 protocol; - - DEFINE_DMA_UNMAP_ADDR(dma); - DEFINE_DMA_UNMAP_LEN(len); - u32 tx_flags; -}; - struct igc_rx_buffer { union { struct { @@ -553,6 +580,14 @@ struct igc_xdp_buff { struct igc_inline_rx_tstamps *rx_ts; /* data indication bit IGC_RXDADV_STAT_TSIP */ }; +struct igc_metadata_request { + struct igc_tx_buffer *tx_buffer; + struct xsk_tx_metadata *meta; + struct igc_ring *tx_ring; + u32 cmd_type; + u16 used_desc; +}; + struct igc_q_vector { struct igc_adapter *adapter; /* backlink */ void __iomem *itr_register; @@ -567,7 +602,6 @@ struct igc_q_vector { struct rcu_head rcu; /* to avoid race with update stats on free */ char name[IFNAMSIZ + 9]; - struct net_device poll_dev; /* for dynamic allocation of rings associated with this q_vector */ struct igc_ring ring[] ____cacheline_internodealigned_in_smp; @@ -585,7 +619,7 @@ enum igc_filter_match_flags { struct igc_nfc_filter { u8 match_flags; u16 etype; - __be16 vlan_etype; + u16 vlan_etype; u16 vlan_tci; u16 vlan_tci_mask; u8 src_addr[ETH_ALEN]; @@ -662,6 +696,7 @@ enum igc_ring_flags_t { IGC_RING_FLAG_TX_DETECT_HANG, IGC_RING_FLAG_AF_XDP_ZC, IGC_RING_FLAG_TX_HWTSTAMP, + IGC_RING_FLAG_RX_ALLOC_FAILED, }; #define ring_uses_large_buffer(ring) \ @@ -708,7 +743,10 @@ struct igc_nfc_rule *igc_get_nfc_rule(struct igc_adapter *adapter, u32 location); int igc_add_nfc_rule(struct igc_adapter *adapter, struct igc_nfc_rule *rule); void igc_del_nfc_rule(struct igc_adapter *adapter, struct igc_nfc_rule *rule); - +void igc_disable_empty_addr_recv(struct igc_adapter *adapter); +int igc_enable_empty_addr_recv(struct igc_adapter *adapter); +struct igc_ring *igc_get_tx_ring(struct igc_adapter *adapter, int cpu); +void igc_flush_tx_descriptors(struct igc_ring *ring); void igc_ptp_init(struct igc_adapter *adapter); void igc_ptp_reset(struct igc_adapter *adapter); void igc_ptp_suspend(struct igc_adapter *adapter); @@ -720,6 +758,9 @@ void igc_ptp_tx_hang(struct igc_adapter *adapter); void igc_ptp_read(struct igc_adapter *adapter, struct timespec64 *ts); void igc_ptp_tx_tstamp_event(struct igc_adapter *adapter); +int igc_led_setup(struct igc_adapter *adapter); +void igc_led_free(struct igc_adapter *adapter); + #define igc_rx_pg_size(_ring) (PAGE_SIZE << igc_rx_pg_order(_ring)) #define IGC_TXD_DCMD (IGC_ADVTXD_DCMD_EOP | IGC_ADVTXD_DCMD_RS) diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c index 9fae8bdec2a7..1613b562d17c 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.c +++ b/drivers/net/ethernet/intel/igc/igc_base.c @@ -68,6 +68,10 @@ static s32 igc_init_nvm_params_base(struct igc_hw *hw) u32 eecd = rd32(IGC_EECD); u16 size; + /* failed to read reg and got all F's */ + if (!(~eecd)) + return -ENXIO; + size = FIELD_GET(IGC_EECD_SIZE_EX_MASK, eecd); /* Added to a constant, "size" becomes the left-shift value @@ -221,6 +225,8 @@ static s32 igc_get_invariants_base(struct igc_hw *hw) /* NVM initialization */ ret_val = igc_init_nvm_params_base(hw); + if (ret_val) + goto out; switch (hw->mac.type) { case igc_i225: ret_val = igc_init_nvm_params_i225(hw); diff --git a/drivers/net/ethernet/intel/igc/igc_base.h b/drivers/net/ethernet/intel/igc/igc_base.h index bf8cdfbba9ff..6320eabb72fe 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.h +++ b/drivers/net/ethernet/intel/igc/igc_base.h @@ -49,6 +49,7 @@ struct igc_adv_tx_context_desc { #define IGC_ADVTXD_DCMD_DEXT 0x20000000 /* Descriptor extension (1=Adv) */ #define IGC_ADVTXD_DCMD_VLE 0x40000000 /* VLAN pkt enable */ #define IGC_ADVTXD_DCMD_TSE 0x80000000 /* TCP Seg enable */ +#define IGC_ADVTXD_PAYLEN_MASK 0XFFFFC000 /* Adv desc PAYLEN mask */ #define IGC_ADVTXD_PAYLEN_SHIFT 14 /* Adv desc PAYLEN shift */ #define IGC_RAR_ENTRIES 16 diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index 5f92b3c7c3d4..7189dfc389ad 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -4,6 +4,8 @@ #ifndef _IGC_DEFINES_H_ #define _IGC_DEFINES_H_ +#include <linux/bitfield.h> + /* Number of Transmit and Receive Descriptors must be a multiple of 8 */ #define REQ_TX_DESCRIPTOR_MULTIPLE 8 #define REQ_RX_DESCRIPTOR_MULTIPLE 8 @@ -176,7 +178,6 @@ /* PHY GPY 211 registers */ #define STANDARD_AN_REG_MASK 0x0007 /* MMD */ -#define ANEG_MULTIGBT_AN_CTRL 0x0020 /* MULTI GBT AN Control Register */ #define MMD_DEVADDR_SHIFT 16 /* Shift MMD to higher bits */ #define CR_2500T_FD_CAPS 0x0080 /* Advertise 2500T FD capability */ @@ -307,6 +308,8 @@ #define IGC_TXD_DTYP_C 0x00000000 /* Context Descriptor */ #define IGC_TXD_POPTS_IXSM 0x01 /* Insert IP checksum */ #define IGC_TXD_POPTS_TXSM 0x02 /* Insert TCP/UDP checksum */ +#define IGC_TXD_POPTS_SMD_MASK 0x3000 /* Indicates whether it's SMD-V or SMD-R */ + #define IGC_TXD_CMD_EOP 0x01000000 /* End of Packet */ #define IGC_TXD_CMD_IC 0x04000000 /* Insert Checksum */ #define IGC_TXD_CMD_DEXT 0x20000000 /* Desc extension (0 = legacy) */ @@ -362,6 +365,8 @@ #define IGC_SRRCTL_TIMER0SEL(timer) (((timer) & 0x3) << 17) /* Receive Descriptor bit definitions */ +#define IGC_RXD_STAT_SMD_TYPE_V 0x01 /* SMD-V Packet */ +#define IGC_RXD_STAT_SMD_TYPE_R 0x02 /* SMD-R Packet */ #define IGC_RXD_STAT_EOP 0x02 /* End of Packet */ #define IGC_RXD_STAT_IXSM 0x04 /* Ignore checksum */ #define IGC_RXD_STAT_UDPCS 0x10 /* UDP xsum calculated */ @@ -371,7 +376,8 @@ #define IGC_RXDEXT_STATERR_LB 0x00040000 /* Advanced Receive Descriptor bit definitions */ -#define IGC_RXDADV_STAT_TSIP 0x08000 /* timestamp in packet */ +#define IGC_RXDADV_STAT_SMD_TYPE_MASK 0x06000 +#define IGC_RXDADV_STAT_TSIP 0x08000 /* timestamp in packet */ #define IGC_RXDEXT_STATERR_L4E 0x20000000 #define IGC_RXDEXT_STATERR_IPE 0x40000000 @@ -395,15 +401,57 @@ #define IGC_RCTL_PMCF 0x00800000 /* pass MAC control frames */ #define IGC_RCTL_SECRC 0x04000000 /* Strip Ethernet CRC */ -#define I225_RXPBSIZE_DEFAULT 0x000000A2 /* RXPBSIZE default */ -#define I225_TXPBSIZE_DEFAULT 0x04000014 /* TXPBSIZE default */ -#define IGC_RXPBS_CFG_TS_EN 0x80000000 /* Timestamp in Rx buffer */ - -#define IGC_TXPBSIZE_TSN 0x04145145 /* 5k bytes buffer for each queue */ +/* Mask for RX packet buffer size */ +#define IGC_RXPBSIZE_EXP_MASK GENMASK(5, 0) +#define IGC_BMC2OSPBSIZE_MASK GENMASK(11, 6) +#define IGC_RXPBSIZE_BE_MASK GENMASK(17, 12) +/* Mask for timestamp in RX buffer */ +#define IGC_RXPBS_CFG_TS_EN_MASK GENMASK(31, 31) +/* High-priority RX packet buffer size (KB). Used for Express traffic when preemption is enabled */ +#define IGC_RXPBSIZE_EXP(x) FIELD_PREP(IGC_RXPBSIZE_EXP_MASK, (x)) +/* BMC to OS packet buffer size in KB */ +#define IGC_BMC2OSPBSIZE(x) FIELD_PREP(IGC_BMC2OSPBSIZE_MASK, (x)) +/* Low-priority RX packet buffer size (KB). Used for BE traffic when preemption is enabled */ +#define IGC_RXPBSIZE_BE(x) FIELD_PREP(IGC_RXPBSIZE_BE_MASK, (x)) +/* Enable RX packet buffer for timestamp descriptor, saving 16 bytes per packet if set */ +#define IGC_RXPBS_CFG_TS_EN FIELD_PREP(IGC_RXPBS_CFG_TS_EN_MASK, 1) +/* Default value following I225/I226 SW User Manual Section 8.3.1 */ +#define IGC_RXPBSIZE_EXP_BMC_DEFAULT ( \ + IGC_RXPBSIZE_EXP(34) | IGC_BMC2OSPBSIZE(2)) +#define IGC_RXPBSIZE_EXP_BMC_BE_TSN ( \ + IGC_RXPBSIZE_EXP(15) | IGC_BMC2OSPBSIZE(2) | IGC_RXPBSIZE_BE(15)) + +/* Mask for TX packet buffer size */ +#define IGC_TXPB0SIZE_MASK GENMASK(5, 0) +#define IGC_TXPB1SIZE_MASK GENMASK(11, 6) +#define IGC_TXPB2SIZE_MASK GENMASK(17, 12) +#define IGC_TXPB3SIZE_MASK GENMASK(23, 18) +/* Mask for OS to BMC packet buffer size */ +#define IGC_OS2BMCPBSIZE_MASK GENMASK(29, 24) +/* TX Packet buffer size in KB */ +#define IGC_TXPB0SIZE(x) FIELD_PREP(IGC_TXPB0SIZE_MASK, (x)) +#define IGC_TXPB1SIZE(x) FIELD_PREP(IGC_TXPB1SIZE_MASK, (x)) +#define IGC_TXPB2SIZE(x) FIELD_PREP(IGC_TXPB2SIZE_MASK, (x)) +#define IGC_TXPB3SIZE(x) FIELD_PREP(IGC_TXPB3SIZE_MASK, (x)) +/* OS to BMC packet buffer size in KB */ +#define IGC_OS2BMCPBSIZE(x) FIELD_PREP(IGC_OS2BMCPBSIZE_MASK, (x)) +/* Default value following I225/I226 SW User Manual Section 8.3.2 */ +#define IGC_TXPBSIZE_DEFAULT ( \ + IGC_TXPB0SIZE(20) | IGC_TXPB1SIZE(0) | IGC_TXPB2SIZE(0) | \ + IGC_TXPB3SIZE(0) | IGC_OS2BMCPBSIZE(4)) +#define IGC_TXPBSIZE_TSN ( \ + IGC_TXPB0SIZE(7) | IGC_TXPB1SIZE(7) | IGC_TXPB2SIZE(7) | \ + IGC_TXPB3SIZE(7) | IGC_OS2BMCPBSIZE(4)) #define IGC_DTXMXPKTSZ_TSN 0x19 /* 1600 bytes of max TX DMA packet size */ #define IGC_DTXMXPKTSZ_DEFAULT 0x98 /* 9728-byte Jumbo frames */ +/* Retry Buffer Control */ +#define IGC_RETX_CTL 0x041C +#define IGC_RETX_CTL_WATERMARK_MASK 0xF +#define IGC_RETX_CTL_QBVFULLTH_SHIFT 8 /* QBV Retry Buffer Full Threshold */ +#define IGC_RETX_CTL_QBVFULLEN 0x1000 /* Enable QBV Retry Buffer Full Threshold */ + /* Transmit Scheduling Latency */ /* Latency between transmission scheduling (LaunchTime) and the time * the packet is transmitted to the network in nanosecond. @@ -532,8 +580,10 @@ /* Transmit Scheduling */ #define IGC_TQAVCTRL_TRANSMIT_MODE_TSN 0x00000001 +#define IGC_TQAVCTRL_PREEMPT_ENA 0x00000002 #define IGC_TQAVCTRL_ENHANCED_QAV 0x00000008 #define IGC_TQAVCTRL_FUTSCDDIS 0x00000080 +#define IGC_TQAVCTRL_MIN_FRAG_MASK 0x0000C000 #define IGC_TXQCTL_QUEUE_MODE_LAUNCHT 0x00000001 #define IGC_TXQCTL_STRICT_CYCLE 0x00000002 @@ -547,6 +597,15 @@ #define IGC_MAX_SR_QUEUES 2 +#define IGC_TXARB_TXQ_PRIO_0_MASK GENMASK(1, 0) +#define IGC_TXARB_TXQ_PRIO_1_MASK GENMASK(3, 2) +#define IGC_TXARB_TXQ_PRIO_2_MASK GENMASK(5, 4) +#define IGC_TXARB_TXQ_PRIO_3_MASK GENMASK(7, 6) +#define IGC_TXARB_TXQ_PRIO_0(x) FIELD_PREP(IGC_TXARB_TXQ_PRIO_0_MASK, (x)) +#define IGC_TXARB_TXQ_PRIO_1(x) FIELD_PREP(IGC_TXARB_TXQ_PRIO_1_MASK, (x)) +#define IGC_TXARB_TXQ_PRIO_2(x) FIELD_PREP(IGC_TXARB_TXQ_PRIO_2_MASK, (x)) +#define IGC_TXARB_TXQ_PRIO_3(x) FIELD_PREP(IGC_TXARB_TXQ_PRIO_3_MASK, (x)) + /* Receive Checksum Control */ #define IGC_RXCSUM_CRCOFL 0x00000800 /* CRC32 offload enable */ #define IGC_RXCSUM_PCSD 0x00002000 /* packet checksum disabled */ @@ -558,7 +617,10 @@ #define IGC_PTM_CTRL_SHRT_CYC(usec) (((usec) & 0x3f) << 2) #define IGC_PTM_CTRL_PTM_TO(usec) (((usec) & 0xff) << 8) -#define IGC_PTM_SHORT_CYC_DEFAULT 1 /* Default short cycle interval */ +/* A short cycle time of 1us theoretically should work, but appears to be too + * short in practice. + */ +#define IGC_PTM_SHORT_CYC_DEFAULT 4 /* Default short cycle interval */ #define IGC_PTM_CYC_TIME_DEFAULT 5 /* Default PTM cycle time */ #define IGC_PTM_TIMEOUT_DEFAULT 255 /* Default timeout for PTM errors */ @@ -577,6 +639,7 @@ #define IGC_PTM_STAT_T4M1_OVFL BIT(3) /* T4 minus T1 overflow */ #define IGC_PTM_STAT_ADJUST_1ST BIT(4) /* 1588 timer adjusted during 1st PTM cycle */ #define IGC_PTM_STAT_ADJUST_CYC BIT(5) /* 1588 timer adjusted during non-1st PTM cycle */ +#define IGC_PTM_STAT_ALL GENMASK(5, 0) /* Used to clear all status */ /* PCIe PTM Cycle Control */ #define IGC_PTM_CYCLE_CTRL_CYC_TIME(msec) ((msec) & 0x3ff) /* PTM Cycle Time (msec) */ @@ -635,6 +698,16 @@ #define IGC_MDIC_READY 0x10000000 #define IGC_MDIC_ERROR 0x40000000 +/* EEE Link Ability */ +#define IGC_EEE_2500BT_MASK BIT(0) +#define IGC_EEE_1000BT_MASK BIT(2) +#define IGC_EEE_100BT_MASK BIT(1) + +/* EEE Link-Partner Ability */ +#define IGC_LP_EEE_2500BT_MASK BIT(0) +#define IGC_LP_EEE_1000BT_MASK BIT(2) +#define IGC_LP_EEE_100BT_MASK BIT(1) + #define IGC_N0_QUEUE -1 #define IGC_MAX_MAC_HDR_LEN 127 diff --git a/drivers/net/ethernet/intel/igc/igc_diag.c b/drivers/net/ethernet/intel/igc/igc_diag.c index cc621970c0cd..a43d7244ee70 100644 --- a/drivers/net/ethernet/intel/igc/igc_diag.c +++ b/drivers/net/ethernet/intel/igc/igc_diag.c @@ -173,8 +173,7 @@ bool igc_link_test(struct igc_adapter *adapter, u64 *data) *data = 0; /* add delay to give enough time for autonegotioation to finish */ - if (adapter->hw.mac.autoneg) - ssleep(5); + ssleep(5); link_up = igc_has_link(adapter); if (!link_up) { diff --git a/drivers/net/ethernet/intel/igc/igc_ethtool.c b/drivers/net/ethernet/intel/igc/igc_ethtool.c index b95d2c86e803..3fc1eded9605 100644 --- a/drivers/net/ethernet/intel/igc/igc_ethtool.c +++ b/drivers/net/ethernet/intel/igc/igc_ethtool.c @@ -8,6 +8,7 @@ #include "igc.h" #include "igc_diag.h" +#include "igc_tsn.h" /* forward declaration */ struct igc_stats { @@ -981,7 +982,7 @@ static int igc_ethtool_get_nfc_rule(struct igc_adapter *adapter, if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_ETYPE) { fsp->flow_type |= FLOW_EXT; - fsp->h_ext.vlan_etype = rule->filter.vlan_etype; + fsp->h_ext.vlan_etype = htons(rule->filter.vlan_etype); fsp->m_ext.vlan_etype = ETHER_TYPE_FULL_MASK; } @@ -1249,7 +1250,7 @@ static void igc_ethtool_init_nfc_rule(struct igc_nfc_rule *rule, /* VLAN etype matching */ if ((fsp->flow_type & FLOW_EXT) && fsp->h_ext.vlan_etype) { - rule->filter.vlan_etype = fsp->h_ext.vlan_etype; + rule->filter.vlan_etype = ntohs(fsp->h_ext.vlan_etype); rule->filter.match_flags |= IGC_FILTER_FLAG_VLAN_ETYPE; } @@ -1540,6 +1541,10 @@ static int igc_ethtool_set_channels(struct net_device *netdev, if (ch->other_count != NON_Q_VECTORS) return -EINVAL; + /* Do not allow channel reconfiguration when mqprio is enabled */ + if (adapter->strict_priority_enable) + return -EINVAL; + /* Verify the number of channels doesn't exceed hw limits */ max_combined = igc_get_max_rss_queues(adapter); if (count > max_combined) @@ -1559,21 +1564,17 @@ static int igc_ethtool_set_channels(struct net_device *netdev, } static int igc_ethtool_get_ts_info(struct net_device *dev, - struct ethtool_ts_info *info) + struct kernel_ethtool_ts_info *info) { struct igc_adapter *adapter = netdev_priv(dev); if (adapter->ptp_clock) info->phc_index = ptp_clock_index(adapter->ptp_clock); - else - info->phc_index = -1; switch (adapter->hw.mac.type) { case igc_i225: 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; @@ -1623,18 +1624,89 @@ static int igc_ethtool_set_priv_flags(struct net_device *netdev, u32 priv_flags) } static int igc_ethtool_get_eee(struct net_device *netdev, - struct ethtool_eee *edata) + struct ethtool_keee *edata) { struct igc_adapter *adapter = netdev_priv(netdev); struct igc_hw *hw = &adapter->hw; - u32 eeer; + struct igc_phy_info *phy = &hw->phy; + u16 eee_advert, eee_lp_advert; + u32 eeer, ret_val; + + /* EEE supported */ + linkmode_set_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + edata->supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + edata->supported); + linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, + edata->supported); + + /* EEE Advertisement 1 - reg 7.60 */ + ret_val = phy->ops.read_reg(hw, (STANDARD_AN_REG_MASK << + MMD_DEVADDR_SHIFT) | + IGC_ANEG_EEE_AB1, + &eee_advert); + if (ret_val) { + netdev_err(adapter->netdev, + "Failed to read IEEE 7.60 register\n"); + return -EINVAL; + } - if (hw->dev_spec._base.eee_enable) - edata->advertised = - mmd_eee_adv_to_ethtool_adv_t(adapter->eee_advert); + if (eee_advert & IGC_EEE_1000BT_MASK) + linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + edata->advertised); - *edata = adapter->eee; - edata->supported = SUPPORTED_Autoneg; + if (eee_advert & IGC_EEE_100BT_MASK) + linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, + edata->advertised); + + /* EEE Advertisement 2 - reg 7.62 */ + ret_val = phy->ops.read_reg(hw, (STANDARD_AN_REG_MASK << + MMD_DEVADDR_SHIFT) | + IGC_ANEG_EEE_AB2, + &eee_advert); + if (ret_val) { + netdev_err(adapter->netdev, + "Failed to read IEEE 7.62 register\n"); + return -EINVAL; + } + + if (eee_advert & IGC_EEE_2500BT_MASK) + linkmode_set_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + edata->advertised); + + /* EEE Link-Partner Ability 1 - reg 7.61 */ + ret_val = phy->ops.read_reg(hw, (STANDARD_AN_REG_MASK << + MMD_DEVADDR_SHIFT) | + IGC_ANEG_EEE_LP_AB1, + &eee_lp_advert); + if (ret_val) { + netdev_err(adapter->netdev, + "Failed to read IEEE 7.61 register\n"); + return -EINVAL; + } + + if (eee_lp_advert & IGC_LP_EEE_1000BT_MASK) + linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, + edata->lp_advertised); + + if (eee_lp_advert & IGC_LP_EEE_100BT_MASK) + linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, + edata->lp_advertised); + + /* EEE Link-Partner Ability 2 - reg 7.63 */ + ret_val = phy->ops.read_reg(hw, (STANDARD_AN_REG_MASK << + MMD_DEVADDR_SHIFT) | + IGC_ANEG_EEE_LP_AB2, + &eee_lp_advert); + if (ret_val) { + netdev_err(adapter->netdev, + "Failed to read IEEE 7.63 register\n"); + return -EINVAL; + } + + if (eee_lp_advert & IGC_LP_EEE_2500BT_MASK) + linkmode_set_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, + edata->lp_advertised); eeer = rd32(IGC_EEER); @@ -1647,9 +1719,6 @@ static int igc_ethtool_get_eee(struct net_device *netdev, edata->eee_enabled = hw->dev_spec._base.eee_enable; - edata->advertised = SUPPORTED_Autoneg; - edata->lp_advertised = SUPPORTED_Autoneg; - /* Report correct negotiated EEE status for devices that * wrongly report EEE at half-duplex */ @@ -1657,21 +1726,21 @@ static int igc_ethtool_get_eee(struct net_device *netdev, edata->eee_enabled = false; edata->eee_active = false; edata->tx_lpi_enabled = false; - edata->advertised &= ~edata->advertised; + linkmode_zero(edata->advertised); } return 0; } static int igc_ethtool_set_eee(struct net_device *netdev, - struct ethtool_eee *edata) + struct ethtool_keee *edata) { struct igc_adapter *adapter = netdev_priv(netdev); struct igc_hw *hw = &adapter->hw; - struct ethtool_eee eee_curr; + struct ethtool_keee eee_curr; s32 ret_val; - memset(&eee_curr, 0, sizeof(struct ethtool_eee)); + memset(&eee_curr, 0, sizeof(struct ethtool_keee)); ret_val = igc_ethtool_get_eee(netdev, &eee_curr); if (ret_val) { @@ -1699,7 +1768,6 @@ static int igc_ethtool_set_eee(struct net_device *netdev, return -EINVAL; } - adapter->eee_advert = ethtool_adv_to_mmd_eee_adv_t(edata->advertised); if (hw->dev_spec._base.eee_enable != edata->eee_enabled) { hw->dev_spec._base.eee_enable = edata->eee_enabled; adapter->flags |= IGC_FLAG_EEE; @@ -1714,19 +1782,81 @@ static int igc_ethtool_set_eee(struct net_device *netdev, return 0; } -static int igc_ethtool_begin(struct net_device *netdev) +static int igc_ethtool_get_mm(struct net_device *netdev, + struct ethtool_mm_state *cmd) { struct igc_adapter *adapter = netdev_priv(netdev); + struct igc_fpe_t *fpe = &adapter->fpe; + + ethtool_mmsv_get_mm(&fpe->mmsv, cmd); + cmd->tx_min_frag_size = fpe->tx_min_frag_size; + cmd->rx_min_frag_size = IGC_RX_MIN_FRAG_SIZE; - pm_runtime_get_sync(&adapter->pdev->dev); return 0; } -static void igc_ethtool_complete(struct net_device *netdev) +static int igc_ethtool_set_mm(struct net_device *netdev, + struct ethtool_mm_cfg *cmd, + struct netlink_ext_ack *extack) { struct igc_adapter *adapter = netdev_priv(netdev); + struct igc_fpe_t *fpe = &adapter->fpe; + + fpe->tx_min_frag_size = igc_fpe_get_supported_frag_size(cmd->tx_min_frag_size); + if (fpe->tx_min_frag_size != cmd->tx_min_frag_size) + NL_SET_ERR_MSG_MOD(extack, + "tx-min-frag-size value set is unsupported. Rounded up to supported value (64, 128, 192, 256)"); + + if (fpe->mmsv.pmac_enabled != cmd->pmac_enabled) { + if (cmd->pmac_enabled) + static_branch_inc(&igc_fpe_enabled); + else + static_branch_dec(&igc_fpe_enabled); + } - pm_runtime_put(&adapter->pdev->dev); + ethtool_mmsv_set_mm(&fpe->mmsv, cmd); + + return igc_tsn_offload_apply(adapter); +} + +/** + * igc_ethtool_get_frame_ass_error - Get the frame assembly error count. + * @reg_value: Register value for IGC_PRMEXCPRCNT + * Return: The count of frame assembly errors. + */ +static u64 igc_ethtool_get_frame_ass_error(u32 reg_value) +{ + /* Out of order statistics */ + u32 ooo_frame_cnt, ooo_frag_cnt; + u32 miss_frame_frag_cnt; + + ooo_frame_cnt = FIELD_GET(IGC_PRMEXCPRCNT_OOO_FRAME_CNT, reg_value); + ooo_frag_cnt = FIELD_GET(IGC_PRMEXCPRCNT_OOO_FRAG_CNT, reg_value); + miss_frame_frag_cnt = FIELD_GET(IGC_PRMEXCPRCNT_MISS_FRAME_FRAG_CNT, + reg_value); + + return ooo_frame_cnt + ooo_frag_cnt + miss_frame_frag_cnt; +} + +static u64 igc_ethtool_get_frame_smd_error(u32 reg_value) +{ + return FIELD_GET(IGC_PRMEXCPRCNT_OOO_SMDC, reg_value); +} + +static void igc_ethtool_get_mm_stats(struct net_device *dev, + struct ethtool_mm_stats *stats) +{ + struct igc_adapter *adapter = netdev_priv(dev); + struct igc_hw *hw = &adapter->hw; + u32 reg_value; + + reg_value = rd32(IGC_PRMEXCPRCNT); + + stats->MACMergeFrameAssErrorCount = igc_ethtool_get_frame_ass_error(reg_value); + stats->MACMergeFrameSmdErrorCount = igc_ethtool_get_frame_smd_error(reg_value); + stats->MACMergeFrameAssOkCount = rd32(IGC_PRMPTDRCNT); + stats->MACMergeFragCountRx = rd32(IGC_PRMEVNTRCNT); + stats->MACMergeFragCountTx = rd32(IGC_PRMEVNTTCNT); } static int igc_ethtool_get_link_ksettings(struct net_device *netdev, @@ -1769,11 +1899,8 @@ static int igc_ethtool_get_link_ksettings(struct net_device *netdev, ethtool_link_ksettings_add_link_mode(cmd, advertising, 2500baseT_Full); /* set autoneg settings */ - if (hw->mac.autoneg == 1) { - ethtool_link_ksettings_add_link_mode(cmd, supported, Autoneg); - ethtool_link_ksettings_add_link_mode(cmd, advertising, - Autoneg); - } + ethtool_link_ksettings_add_link_mode(cmd, supported, Autoneg); + ethtool_link_ksettings_add_link_mode(cmd, advertising, Autoneg); /* Set pause flow control settings */ ethtool_link_ksettings_add_link_mode(cmd, supported, Pause); @@ -1826,10 +1953,7 @@ static int igc_ethtool_get_link_ksettings(struct net_device *netdev, cmd->base.duplex = DUPLEX_UNKNOWN; } cmd->base.speed = speed; - if (hw->mac.autoneg) - cmd->base.autoneg = AUTONEG_ENABLE; - else - cmd->base.autoneg = AUTONEG_DISABLE; + cmd->base.autoneg = AUTONEG_ENABLE; /* MDI-X => 2; MDI =>1; Invalid =>0 */ if (hw->phy.media_type == igc_media_type_copper) @@ -1903,7 +2027,6 @@ igc_ethtool_set_link_ksettings(struct net_device *netdev, advertised |= ADVERTISE_10_HALF; if (cmd->base.autoneg == AUTONEG_ENABLE) { - hw->mac.autoneg = 1; hw->phy.autoneg_advertised = advertised; if (adapter->fc_autoneg) hw->fc.requested_mode = igc_fc_default; @@ -2028,11 +2151,12 @@ static const struct ethtool_ops igc_ethtool_ops = { .set_priv_flags = igc_ethtool_set_priv_flags, .get_eee = igc_ethtool_get_eee, .set_eee = igc_ethtool_set_eee, - .begin = igc_ethtool_begin, - .complete = igc_ethtool_complete, .get_link_ksettings = igc_ethtool_get_link_ksettings, .set_link_ksettings = igc_ethtool_set_link_ksettings, .self_test = igc_ethtool_diag_test, + .get_mm = igc_ethtool_get_mm, + .get_mm_stats = igc_ethtool_get_mm_stats, + .set_mm = igc_ethtool_set_mm, }; void igc_ethtool_set_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/intel/igc/igc_hw.h b/drivers/net/ethernet/intel/igc/igc_hw.h index e1c572e0d4ef..be8a49a86d09 100644 --- a/drivers/net/ethernet/intel/igc/igc_hw.h +++ b/drivers/net/ethernet/intel/igc/igc_hw.h @@ -92,7 +92,6 @@ struct igc_mac_info { bool asf_firmware_present; bool arc_subsystem_valid; - bool autoneg; bool autoneg_failed; bool get_link_status; }; @@ -280,9 +279,4 @@ struct net_device *igc_get_hw_dev(struct igc_hw *hw); #define hw_dbg(format, arg...) \ netdev_dbg(igc_get_hw_dev(hw), format, ##arg) -s32 igc_read_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value); -s32 igc_write_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value); -void igc_read_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value); -void igc_write_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value); - #endif /* _IGC_HW_H_ */ diff --git a/drivers/net/ethernet/intel/igc/igc_leds.c b/drivers/net/ethernet/intel/igc/igc_leds.c new file mode 100644 index 000000000000..3929b25b6ae6 --- /dev/null +++ b/drivers/net/ethernet/intel/igc/igc_leds.c @@ -0,0 +1,302 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2024 Linutronix GmbH */ + +#include <linux/bits.h> +#include <linux/leds.h> +#include <linux/netdevice.h> +#include <linux/pm_runtime.h> +#include <uapi/linux/uleds.h> + +#include "igc.h" + +#define IGC_NUM_LEDS 3 + +#define IGC_LEDCTL_LED0_MODE_SHIFT 0 +#define IGC_LEDCTL_LED0_MODE_MASK GENMASK(3, 0) +#define IGC_LEDCTL_LED0_BLINK BIT(7) +#define IGC_LEDCTL_LED1_MODE_SHIFT 8 +#define IGC_LEDCTL_LED1_MODE_MASK GENMASK(11, 8) +#define IGC_LEDCTL_LED1_BLINK BIT(15) +#define IGC_LEDCTL_LED2_MODE_SHIFT 16 +#define IGC_LEDCTL_LED2_MODE_MASK GENMASK(19, 16) +#define IGC_LEDCTL_LED2_BLINK BIT(23) + +#define IGC_LEDCTL_MODE_ON 0x00 +#define IGC_LEDCTL_MODE_OFF 0x01 +#define IGC_LEDCTL_MODE_LINK_10 0x05 +#define IGC_LEDCTL_MODE_LINK_100 0x06 +#define IGC_LEDCTL_MODE_LINK_1000 0x07 +#define IGC_LEDCTL_MODE_LINK_2500 0x08 +#define IGC_LEDCTL_MODE_ACTIVITY 0x0b + +#define IGC_SUPPORTED_MODES \ + (BIT(TRIGGER_NETDEV_LINK_2500) | BIT(TRIGGER_NETDEV_LINK_1000) | \ + BIT(TRIGGER_NETDEV_LINK_100) | BIT(TRIGGER_NETDEV_LINK_10) | \ + BIT(TRIGGER_NETDEV_RX) | BIT(TRIGGER_NETDEV_TX)) + +#define IGC_ACTIVITY_MODES \ + (BIT(TRIGGER_NETDEV_RX) | BIT(TRIGGER_NETDEV_TX)) + +struct igc_led_classdev { + struct net_device *netdev; + struct led_classdev led; + int index; +}; + +#define lcdev_to_igc_ldev(lcdev) \ + container_of(lcdev, struct igc_led_classdev, led) + +static void igc_led_select(struct igc_adapter *adapter, int led, + u32 *mask, u32 *shift, u32 *blink) +{ + switch (led) { + case 0: + *mask = IGC_LEDCTL_LED0_MODE_MASK; + *shift = IGC_LEDCTL_LED0_MODE_SHIFT; + *blink = IGC_LEDCTL_LED0_BLINK; + break; + case 1: + *mask = IGC_LEDCTL_LED1_MODE_MASK; + *shift = IGC_LEDCTL_LED1_MODE_SHIFT; + *blink = IGC_LEDCTL_LED1_BLINK; + break; + case 2: + *mask = IGC_LEDCTL_LED2_MODE_MASK; + *shift = IGC_LEDCTL_LED2_MODE_SHIFT; + *blink = IGC_LEDCTL_LED2_BLINK; + break; + default: + *mask = *shift = *blink = 0; + netdev_err(adapter->netdev, "Unknown LED %d selected!\n", led); + } +} + +static void igc_led_set(struct igc_adapter *adapter, int led, u32 mode, + bool blink) +{ + u32 shift, mask, blink_bit, ledctl; + struct igc_hw *hw = &adapter->hw; + + igc_led_select(adapter, led, &mask, &shift, &blink_bit); + + pm_runtime_get_sync(&adapter->pdev->dev); + mutex_lock(&adapter->led_mutex); + + /* Set mode */ + ledctl = rd32(IGC_LEDCTL); + ledctl &= ~mask; + ledctl |= mode << shift; + + /* Configure blinking */ + if (blink) + ledctl |= blink_bit; + else + ledctl &= ~blink_bit; + wr32(IGC_LEDCTL, ledctl); + + mutex_unlock(&adapter->led_mutex); + pm_runtime_put(&adapter->pdev->dev); +} + +static u32 igc_led_get(struct igc_adapter *adapter, int led) +{ + u32 shift, mask, blink_bit, ledctl; + struct igc_hw *hw = &adapter->hw; + + igc_led_select(adapter, led, &mask, &shift, &blink_bit); + + pm_runtime_get_sync(&adapter->pdev->dev); + mutex_lock(&adapter->led_mutex); + ledctl = rd32(IGC_LEDCTL); + mutex_unlock(&adapter->led_mutex); + pm_runtime_put(&adapter->pdev->dev); + + return (ledctl & mask) >> shift; +} + +static int igc_led_brightness_set_blocking(struct led_classdev *led_cdev, + enum led_brightness brightness) +{ + struct igc_led_classdev *ldev = lcdev_to_igc_ldev(led_cdev); + struct igc_adapter *adapter = netdev_priv(ldev->netdev); + u32 mode; + + if (brightness) + mode = IGC_LEDCTL_MODE_ON; + else + mode = IGC_LEDCTL_MODE_OFF; + + netdev_dbg(adapter->netdev, "Set brightness for LED %d to mode %u!\n", + ldev->index, mode); + + igc_led_set(adapter, ldev->index, mode, false); + + return 0; +} + +static int igc_led_hw_control_is_supported(struct led_classdev *led_cdev, + unsigned long flags) +{ + if (flags & ~IGC_SUPPORTED_MODES) + return -EOPNOTSUPP; + + /* If Tx and Rx selected, activity can be offloaded unless some other + * mode is selected as well. + */ + if ((flags & BIT(TRIGGER_NETDEV_TX)) && + (flags & BIT(TRIGGER_NETDEV_RX)) && + !(flags & ~IGC_ACTIVITY_MODES)) + return 0; + + /* Single Rx or Tx activity is not supported. */ + if (flags & IGC_ACTIVITY_MODES) + return -EOPNOTSUPP; + + /* Only one mode can be active at a given time. */ + if (flags & (flags - 1)) + return -EOPNOTSUPP; + + return 0; +} + +static int igc_led_hw_control_set(struct led_classdev *led_cdev, + unsigned long flags) +{ + struct igc_led_classdev *ldev = lcdev_to_igc_ldev(led_cdev); + struct igc_adapter *adapter = netdev_priv(ldev->netdev); + u32 mode = IGC_LEDCTL_MODE_OFF; + bool blink = false; + + if (flags & BIT(TRIGGER_NETDEV_LINK_10)) + mode = IGC_LEDCTL_MODE_LINK_10; + if (flags & BIT(TRIGGER_NETDEV_LINK_100)) + mode = IGC_LEDCTL_MODE_LINK_100; + if (flags & BIT(TRIGGER_NETDEV_LINK_1000)) + mode = IGC_LEDCTL_MODE_LINK_1000; + if (flags & BIT(TRIGGER_NETDEV_LINK_2500)) + mode = IGC_LEDCTL_MODE_LINK_2500; + if ((flags & BIT(TRIGGER_NETDEV_TX)) && + (flags & BIT(TRIGGER_NETDEV_RX))) + mode = IGC_LEDCTL_MODE_ACTIVITY; + + netdev_dbg(adapter->netdev, "Set HW control for LED %d to mode %u!\n", + ldev->index, mode); + + /* blink is recommended for activity */ + if (mode == IGC_LEDCTL_MODE_ACTIVITY) + blink = true; + + igc_led_set(adapter, ldev->index, mode, blink); + + return 0; +} + +static int igc_led_hw_control_get(struct led_classdev *led_cdev, + unsigned long *flags) +{ + struct igc_led_classdev *ldev = lcdev_to_igc_ldev(led_cdev); + struct igc_adapter *adapter = netdev_priv(ldev->netdev); + u32 mode; + + mode = igc_led_get(adapter, ldev->index); + + switch (mode) { + case IGC_LEDCTL_MODE_ACTIVITY: + *flags = BIT(TRIGGER_NETDEV_TX) | BIT(TRIGGER_NETDEV_RX); + break; + case IGC_LEDCTL_MODE_LINK_10: + *flags = BIT(TRIGGER_NETDEV_LINK_10); + break; + case IGC_LEDCTL_MODE_LINK_100: + *flags = BIT(TRIGGER_NETDEV_LINK_100); + break; + case IGC_LEDCTL_MODE_LINK_1000: + *flags = BIT(TRIGGER_NETDEV_LINK_1000); + break; + case IGC_LEDCTL_MODE_LINK_2500: + *flags = BIT(TRIGGER_NETDEV_LINK_2500); + break; + } + + return 0; +} + +static struct device *igc_led_hw_control_get_device(struct led_classdev *led_cdev) +{ + struct igc_led_classdev *ldev = lcdev_to_igc_ldev(led_cdev); + + return &ldev->netdev->dev; +} + +static void igc_led_get_name(struct igc_adapter *adapter, int index, char *buf, + size_t buf_len) +{ + snprintf(buf, buf_len, "igc-%x%x-led%d", + pci_domain_nr(adapter->pdev->bus), + pci_dev_id(adapter->pdev), index); +} + +static int igc_setup_ldev(struct igc_led_classdev *ldev, + struct net_device *netdev, int index) +{ + struct igc_adapter *adapter = netdev_priv(netdev); + struct led_classdev *led_cdev = &ldev->led; + char led_name[LED_MAX_NAME_SIZE]; + + ldev->netdev = netdev; + ldev->index = index; + + igc_led_get_name(adapter, index, led_name, LED_MAX_NAME_SIZE); + led_cdev->name = led_name; + led_cdev->flags |= LED_RETAIN_AT_SHUTDOWN; + led_cdev->max_brightness = 1; + led_cdev->brightness_set_blocking = igc_led_brightness_set_blocking; + led_cdev->hw_control_trigger = "netdev"; + led_cdev->hw_control_is_supported = igc_led_hw_control_is_supported; + led_cdev->hw_control_set = igc_led_hw_control_set; + led_cdev->hw_control_get = igc_led_hw_control_get; + led_cdev->hw_control_get_device = igc_led_hw_control_get_device; + + return led_classdev_register(&netdev->dev, led_cdev); +} + +int igc_led_setup(struct igc_adapter *adapter) +{ + struct net_device *netdev = adapter->netdev; + struct igc_led_classdev *leds; + int i, err; + + mutex_init(&adapter->led_mutex); + + leds = kcalloc(IGC_NUM_LEDS, sizeof(*leds), GFP_KERNEL); + if (!leds) + return -ENOMEM; + + for (i = 0; i < IGC_NUM_LEDS; i++) { + err = igc_setup_ldev(leds + i, netdev, i); + if (err) + goto err; + } + + adapter->leds = leds; + + return 0; + +err: + for (i--; i >= 0; i--) + led_classdev_unregister(&((leds + i)->led)); + + kfree(leds); + return err; +} + +void igc_led_free(struct igc_adapter *adapter) +{ + struct igc_led_classdev *leds = adapter->leds; + int i; + + for (i = 0; i < IGC_NUM_LEDS; i++) + led_classdev_unregister(&((leds + i)->led)); + + kfree(leds); +} diff --git a/drivers/net/ethernet/intel/igc/igc_mac.c b/drivers/net/ethernet/intel/igc/igc_mac.c index a5c4b19d71a2..d344e0a1cd5e 100644 --- a/drivers/net/ethernet/intel/igc/igc_mac.c +++ b/drivers/net/ethernet/intel/igc/igc_mac.c @@ -386,14 +386,6 @@ s32 igc_check_for_copper_link(struct igc_hw *hw) */ igc_check_downshift(hw); - /* If we are forcing speed/duplex, then we simply return since - * we have already determined whether we have link or not. - */ - if (!mac->autoneg) { - ret_val = -IGC_ERR_CONFIG; - goto out; - } - /* Auto-Neg is enabled. Auto Speed Detection takes care * of MAC speed/duplex configuration. So we only need to * configure Collision Distance in the MAC. @@ -468,173 +460,171 @@ s32 igc_config_fc_after_link_up(struct igc_hw *hw) goto out; } - /* Check for the case where we have copper media and auto-neg is - * enabled. In this case, we need to check and see if Auto-Neg - * has completed, and if so, how the PHY and link partner has - * flow control configured. + /* In auto-neg, we need to check and see if Auto-Neg has completed, + * and if so, how the PHY and link partner has flow control + * configured. */ - if (mac->autoneg) { - /* Read the MII Status Register and check to see if AutoNeg - * has completed. We read this twice because this reg has - * some "sticky" (latched) bits. - */ - ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, - &mii_status_reg); - if (ret_val) - goto out; - ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, - &mii_status_reg); - if (ret_val) - goto out; - if (!(mii_status_reg & MII_SR_AUTONEG_COMPLETE)) { - hw_dbg("Copper PHY and Auto Neg has not completed.\n"); - goto out; - } + /* Read the MII Status Register and check to see if AutoNeg + * has completed. We read this twice because this reg has + * some "sticky" (latched) bits. + */ + ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, + &mii_status_reg); + if (ret_val) + goto out; + ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, + &mii_status_reg); + if (ret_val) + goto out; - /* The AutoNeg process has completed, so we now need to - * read both the Auto Negotiation Advertisement - * Register (Address 4) and the Auto_Negotiation Base - * Page Ability Register (Address 5) to determine how - * flow control was negotiated. - */ - ret_val = hw->phy.ops.read_reg(hw, PHY_AUTONEG_ADV, - &mii_nway_adv_reg); - if (ret_val) - goto out; - ret_val = hw->phy.ops.read_reg(hw, PHY_LP_ABILITY, - &mii_nway_lp_ability_reg); - if (ret_val) - goto out; - /* Two bits in the Auto Negotiation Advertisement Register - * (Address 4) and two bits in the Auto Negotiation Base - * Page Ability Register (Address 5) determine flow control - * for both the PHY and the link partner. The following - * table, taken out of the IEEE 802.3ab/D6.0 dated March 25, - * 1999, describes these PAUSE resolution bits and how flow - * control is determined based upon these settings. - * NOTE: DC = Don't Care - * - * LOCAL DEVICE | LINK PARTNER - * PAUSE | ASM_DIR | PAUSE | ASM_DIR | NIC Resolution - *-------|---------|-------|---------|-------------------- - * 0 | 0 | DC | DC | igc_fc_none - * 0 | 1 | 0 | DC | igc_fc_none - * 0 | 1 | 1 | 0 | igc_fc_none - * 0 | 1 | 1 | 1 | igc_fc_tx_pause - * 1 | 0 | 0 | DC | igc_fc_none - * 1 | DC | 1 | DC | igc_fc_full - * 1 | 1 | 0 | 0 | igc_fc_none - * 1 | 1 | 0 | 1 | igc_fc_rx_pause - * - * Are both PAUSE bits set to 1? If so, this implies - * Symmetric Flow Control is enabled at both ends. The - * ASM_DIR bits are irrelevant per the spec. - * - * For Symmetric Flow Control: - * - * LOCAL DEVICE | LINK PARTNER - * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result - *-------|---------|-------|---------|-------------------- - * 1 | DC | 1 | DC | IGC_fc_full - * - */ - if ((mii_nway_adv_reg & NWAY_AR_PAUSE) && - (mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE)) { - /* 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 == igc_fc_full) { - hw->fc.current_mode = igc_fc_full; - hw_dbg("Flow Control = FULL.\n"); - } else { - hw->fc.current_mode = igc_fc_rx_pause; - hw_dbg("Flow Control = RX PAUSE frames only.\n"); - } - } + if (!(mii_status_reg & MII_SR_AUTONEG_COMPLETE)) { + hw_dbg("Copper PHY and Auto Neg has not completed.\n"); + goto out; + } - /* For receiving PAUSE frames ONLY. - * - * LOCAL DEVICE | LINK PARTNER - * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result - *-------|---------|-------|---------|-------------------- - * 0 | 1 | 1 | 1 | igc_fc_tx_pause - */ - else if (!(mii_nway_adv_reg & NWAY_AR_PAUSE) && - (mii_nway_adv_reg & NWAY_AR_ASM_DIR) && - (mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE) && - (mii_nway_lp_ability_reg & NWAY_LPAR_ASM_DIR)) { - hw->fc.current_mode = igc_fc_tx_pause; - hw_dbg("Flow Control = TX PAUSE frames only.\n"); - } - /* For transmitting PAUSE frames ONLY. - * - * LOCAL DEVICE | LINK PARTNER - * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result - *-------|---------|-------|---------|-------------------- - * 1 | 1 | 0 | 1 | igc_fc_rx_pause - */ - else if ((mii_nway_adv_reg & NWAY_AR_PAUSE) && - (mii_nway_adv_reg & NWAY_AR_ASM_DIR) && - !(mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE) && - (mii_nway_lp_ability_reg & NWAY_LPAR_ASM_DIR)) { - hw->fc.current_mode = igc_fc_rx_pause; - hw_dbg("Flow Control = RX PAUSE frames only.\n"); - } - /* Per the IEEE spec, at this point flow control should be - * disabled. However, we want to consider that we could - * be connected to a legacy switch that doesn't advertise - * desired flow control, but can be forced on the link - * partner. So if we advertised no flow control, that is - * what we will resolve to. If we advertised some kind of - * receive capability (Rx Pause Only or Full Flow Control) - * and the link partner advertised none, we will configure - * ourselves to enable Rx Flow Control only. We can do - * this safely for two reasons: If the link partner really - * didn't want flow control enabled, and we enable Rx, no - * harm done since we won't be receiving any PAUSE frames - * anyway. If the intent on the link partner was to have - * flow control enabled, then by us enabling RX only, we - * can at least receive pause frames and process them. - * This is a good idea because in most cases, since we are - * predominantly a server NIC, more times than not we will - * be asked to delay transmission of packets than asking - * our link partner to pause transmission of frames. + /* The AutoNeg process has completed, so we now need to + * read both the Auto Negotiation Advertisement + * Register (Address 4) and the Auto_Negotiation Base + * Page Ability Register (Address 5) to determine how + * flow control was negotiated. + */ + ret_val = hw->phy.ops.read_reg(hw, PHY_AUTONEG_ADV, + &mii_nway_adv_reg); + if (ret_val) + goto out; + ret_val = hw->phy.ops.read_reg(hw, PHY_LP_ABILITY, + &mii_nway_lp_ability_reg); + if (ret_val) + goto out; + /* Two bits in the Auto Negotiation Advertisement Register + * (Address 4) and two bits in the Auto Negotiation Base + * Page Ability Register (Address 5) determine flow control + * for both the PHY and the link partner. The following + * table, taken out of the IEEE 802.3ab/D6.0 dated March 25, + * 1999, describes these PAUSE resolution bits and how flow + * control is determined based upon these settings. + * NOTE: DC = Don't Care + * + * LOCAL DEVICE | LINK PARTNER + * PAUSE | ASM_DIR | PAUSE | ASM_DIR | NIC Resolution + *-------|---------|-------|---------|-------------------- + * 0 | 0 | DC | DC | igc_fc_none + * 0 | 1 | 0 | DC | igc_fc_none + * 0 | 1 | 1 | 0 | igc_fc_none + * 0 | 1 | 1 | 1 | igc_fc_tx_pause + * 1 | 0 | 0 | DC | igc_fc_none + * 1 | DC | 1 | DC | igc_fc_full + * 1 | 1 | 0 | 0 | igc_fc_none + * 1 | 1 | 0 | 1 | igc_fc_rx_pause + * + * Are both PAUSE bits set to 1? If so, this implies + * Symmetric Flow Control is enabled at both ends. The + * ASM_DIR bits are irrelevant per the spec. + * + * For Symmetric Flow Control: + * + * LOCAL DEVICE | LINK PARTNER + * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result + *-------|---------|-------|---------|-------------------- + * 1 | DC | 1 | DC | IGC_fc_full + * + */ + if ((mii_nway_adv_reg & NWAY_AR_PAUSE) && + (mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE)) { + /* 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. */ - else if ((hw->fc.requested_mode == igc_fc_none) || - (hw->fc.requested_mode == igc_fc_tx_pause) || - (hw->fc.strict_ieee)) { - hw->fc.current_mode = igc_fc_none; - hw_dbg("Flow Control = NONE.\n"); + if (hw->fc.requested_mode == igc_fc_full) { + hw->fc.current_mode = igc_fc_full; + hw_dbg("Flow Control = FULL.\n"); } else { hw->fc.current_mode = igc_fc_rx_pause; hw_dbg("Flow Control = RX PAUSE frames only.\n"); } + } - /* Now we need to do one last check... If we auto- - * negotiated to HALF DUPLEX, flow control should not be - * enabled per IEEE 802.3 spec. - */ - ret_val = hw->mac.ops.get_speed_and_duplex(hw, &speed, &duplex); - if (ret_val) { - hw_dbg("Error getting link speed and duplex\n"); - goto out; - } + /* For receiving PAUSE frames ONLY. + * + * LOCAL DEVICE | LINK PARTNER + * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result + *-------|---------|-------|---------|-------------------- + * 0 | 1 | 1 | 1 | igc_fc_tx_pause + */ + else if (!(mii_nway_adv_reg & NWAY_AR_PAUSE) && + (mii_nway_adv_reg & NWAY_AR_ASM_DIR) && + (mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE) && + (mii_nway_lp_ability_reg & NWAY_LPAR_ASM_DIR)) { + hw->fc.current_mode = igc_fc_tx_pause; + hw_dbg("Flow Control = TX PAUSE frames only.\n"); + } + /* For transmitting PAUSE frames ONLY. + * + * LOCAL DEVICE | LINK PARTNER + * PAUSE | ASM_DIR | PAUSE | ASM_DIR | Result + *-------|---------|-------|---------|-------------------- + * 1 | 1 | 0 | 1 | igc_fc_rx_pause + */ + else if ((mii_nway_adv_reg & NWAY_AR_PAUSE) && + (mii_nway_adv_reg & NWAY_AR_ASM_DIR) && + !(mii_nway_lp_ability_reg & NWAY_LPAR_PAUSE) && + (mii_nway_lp_ability_reg & NWAY_LPAR_ASM_DIR)) { + hw->fc.current_mode = igc_fc_rx_pause; + hw_dbg("Flow Control = RX PAUSE frames only.\n"); + } + /* Per the IEEE spec, at this point flow control should be + * disabled. However, we want to consider that we could + * be connected to a legacy switch that doesn't advertise + * desired flow control, but can be forced on the link + * partner. So if we advertised no flow control, that is + * what we will resolve to. If we advertised some kind of + * receive capability (Rx Pause Only or Full Flow Control) + * and the link partner advertised none, we will configure + * ourselves to enable Rx Flow Control only. We can do + * this safely for two reasons: If the link partner really + * didn't want flow control enabled, and we enable Rx, no + * harm done since we won't be receiving any PAUSE frames + * anyway. If the intent on the link partner was to have + * flow control enabled, then by us enabling RX only, we + * can at least receive pause frames and process them. + * This is a good idea because in most cases, since we are + * predominantly a server NIC, more times than not we will + * be asked to delay transmission of packets than asking + * our link partner to pause transmission of frames. + */ + else if ((hw->fc.requested_mode == igc_fc_none) || + (hw->fc.requested_mode == igc_fc_tx_pause) || + (hw->fc.strict_ieee)) { + hw->fc.current_mode = igc_fc_none; + hw_dbg("Flow Control = NONE.\n"); + } else { + hw->fc.current_mode = igc_fc_rx_pause; + hw_dbg("Flow Control = RX PAUSE frames only.\n"); + } - if (duplex == HALF_DUPLEX) - hw->fc.current_mode = igc_fc_none; + /* Now we need to do one last check... If we auto- + * negotiated to HALF DUPLEX, flow control should not be + * enabled per IEEE 802.3 spec. + */ + ret_val = hw->mac.ops.get_speed_and_duplex(hw, &speed, &duplex); + if (ret_val) { + hw_dbg("Error getting link speed and duplex\n"); + goto out; + } - /* Now we call a subroutine to actually force the MAC - * controller to use the correct flow control settings. - */ - ret_val = igc_force_mac_fc(hw); - if (ret_val) { - hw_dbg("Error forcing flow control settings\n"); - goto out; - } + if (duplex == HALF_DUPLEX) + hw->fc.current_mode = igc_fc_none; + + /* Now we call a subroutine to actually force the MAC + * controller to use the correct flow control settings. + */ + ret_val = igc_force_mac_fc(hw); + if (ret_val) { + hw_dbg("Error forcing flow control settings\n"); + goto out; } out: diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index ba8d3fe186ae..27575a1e1777 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -12,6 +12,7 @@ #include <linux/bpf_trace.h> #include <net/xdp_sock_drv.h> #include <linux/pci.h> +#include <linux/mdio.h> #include <net/ipv6.h> @@ -31,7 +32,6 @@ static int debug = -1; -MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION(DRV_SUMMARY); MODULE_LICENSE("GPL v2"); module_param(debug, int, 0); @@ -1092,10 +1092,12 @@ static int igc_init_empty_frame(struct igc_ring *ring, dma = dma_map_single(ring->dev, skb->data, size, DMA_TO_DEVICE); if (dma_mapping_error(ring->dev, dma)) { - netdev_err_once(ring->netdev, "Failed to map DMA for TX\n"); + net_err_ratelimited("%s: DMA mapping error for empty frame\n", + netdev_name(ring->netdev)); return -ENOMEM; } + buffer->type = IGC_TX_BUFFER_TYPE_SKB; buffer->skb = skb; buffer->protocol = 0; buffer->bytecount = skb->len; @@ -1107,20 +1109,12 @@ static int igc_init_empty_frame(struct igc_ring *ring, return 0; } -static int igc_init_tx_empty_descriptor(struct igc_ring *ring, - struct sk_buff *skb, - struct igc_tx_buffer *first) +static void igc_init_tx_empty_descriptor(struct igc_ring *ring, + struct sk_buff *skb, + struct igc_tx_buffer *first) { union igc_adv_tx_desc *desc; u32 cmd_type, olinfo_status; - int err; - - if (!igc_desc_unused(ring)) - return -EBUSY; - - err = igc_init_empty_frame(ring, first, skb); - if (err) - return err; cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT | IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD | @@ -1139,8 +1133,6 @@ static int igc_init_tx_empty_descriptor(struct igc_ring *ring, ring->next_to_use++; if (ring->next_to_use == ring->count) ring->next_to_use = 0; - - return 0; } #define IGC_EMPTY_FRAME_SIZE 60 @@ -1566,6 +1558,40 @@ static bool igc_request_tx_tstamp(struct igc_adapter *adapter, struct sk_buff *s return false; } +static int igc_insert_empty_frame(struct igc_ring *tx_ring) +{ + struct igc_tx_buffer *empty_info; + struct sk_buff *empty_skb; + void *data; + int ret; + + empty_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + empty_skb = alloc_skb(IGC_EMPTY_FRAME_SIZE, GFP_ATOMIC); + if (unlikely(!empty_skb)) { + net_err_ratelimited("%s: skb alloc error for empty frame\n", + netdev_name(tx_ring->netdev)); + return -ENOMEM; + } + + data = skb_put(empty_skb, IGC_EMPTY_FRAME_SIZE); + memset(data, 0, IGC_EMPTY_FRAME_SIZE); + + /* Prepare DMA mapping and Tx buffer information */ + ret = igc_init_empty_frame(tx_ring, empty_info, empty_skb); + if (unlikely(ret)) { + dev_kfree_skb_any(empty_skb); + return ret; + } + + /* Prepare advanced context descriptor for empty packet */ + igc_tx_ctxtdesc(tx_ring, 0, false, 0, 0, 0); + + /* Prepare advanced data descriptor for empty packet */ + igc_init_tx_empty_descriptor(tx_ring, empty_skb, empty_info); + + return 0; +} + static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, struct igc_ring *tx_ring) { @@ -1585,6 +1611,7 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, * + 1 desc for skb_headlen/IGC_MAX_DATA_PER_TXD, * + 2 desc gap to keep tail from touching head, * + 1 desc for context descriptor, + * + 2 desc for inserting an empty packet for launch time, * otherwise try next time */ for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) @@ -1604,24 +1631,16 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, launch_time = igc_tx_launchtime(tx_ring, txtime, &first_flag, &insert_empty); if (insert_empty) { - struct igc_tx_buffer *empty_info; - struct sk_buff *empty; - void *data; - - empty_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use]; - empty = alloc_skb(IGC_EMPTY_FRAME_SIZE, GFP_ATOMIC); - if (!empty) - goto done; - - data = skb_put(empty, IGC_EMPTY_FRAME_SIZE); - memset(data, 0, IGC_EMPTY_FRAME_SIZE); - - igc_tx_ctxtdesc(tx_ring, 0, false, 0, 0, 0); - - if (igc_init_tx_empty_descriptor(tx_ring, - empty, - empty_info) < 0) - dev_kfree_skb_any(empty); + /* Reset the launch time if the required empty frame fails to + * be inserted. However, this packet is not dropped, so it + * "dirties" the current Qbv cycle. This ensures that the + * upcoming packet, which is scheduled in the next Qbv cycle, + * does not require an empty frame. This way, the launch time + * continues to function correctly despite the current failure + * to insert the empty frame. + */ + if (igc_insert_empty_frame(tx_ring)) + launch_time = 0; } done: @@ -1642,10 +1661,6 @@ done: if (unlikely(test_bit(IGC_RING_FLAG_TX_HWTSTAMP, &tx_ring->flags) && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { - /* FIXME: add support for retrieving timestamps from - * the other timer registers before skipping the - * timestamping request. - */ unsigned long flags; u32 tstamp_flags; @@ -1653,7 +1668,8 @@ done: if (igc_request_tx_tstamp(adapter, skb, &tstamp_flags)) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; tx_flags |= IGC_TX_FLAGS_TSTAMP | tstamp_flags; - if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_USE_CYCLES) + if (skb->sk && + READ_ONCE(skb->sk->sk_tsflags) & SOF_TIMESTAMPING_BIND_PHC) tx_flags |= IGC_TX_FLAGS_TSTAMP_TIMER_1; } else { adapter->tx_hwtstamp_skipped++; @@ -2127,10 +2143,6 @@ static bool igc_cleanup_headers(struct igc_ring *rx_ring, union igc_adv_rx_desc *rx_desc, struct sk_buff *skb) { - /* XDP packets use error pointer so abort at this point */ - if (IS_ERR(skb)) - return true; - if (unlikely(igc_test_staterr(rx_desc, IGC_RXDEXT_STATERR_RXE))) { struct net_device *netdev = rx_ring->netdev; @@ -2195,6 +2207,7 @@ static bool igc_alloc_mapped_page(struct igc_ring *rx_ring, page = dev_alloc_pages(igc_rx_pg_order(rx_ring)); if (unlikely(!page)) { rx_ring->rx_stats.alloc_failed++; + set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); return false; } @@ -2211,6 +2224,7 @@ static bool igc_alloc_mapped_page(struct igc_ring *rx_ring, __free_page(page); rx_ring->rx_stats.alloc_failed++; + set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); return false; } @@ -2450,8 +2464,7 @@ unmap: return -ENOMEM; } -static struct igc_ring *igc_xdp_get_tx_ring(struct igc_adapter *adapter, - int cpu) +struct igc_ring *igc_get_tx_ring(struct igc_adapter *adapter, int cpu) { int index = cpu; @@ -2475,7 +2488,7 @@ static int igc_xdp_xmit_back(struct igc_adapter *adapter, struct xdp_buff *xdp) if (unlikely(!xdpf)) return -EFAULT; - ring = igc_xdp_get_tx_ring(adapter, cpu); + ring = igc_get_tx_ring(adapter, cpu); nq = txring_txq(ring); __netif_tx_lock(nq, cpu); @@ -2517,8 +2530,7 @@ out_failure: } } -static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter, - struct xdp_buff *xdp) +static int igc_xdp_run_prog(struct igc_adapter *adapter, struct xdp_buff *xdp) { struct bpf_prog *prog; int res; @@ -2532,11 +2544,11 @@ static struct sk_buff *igc_xdp_run_prog(struct igc_adapter *adapter, res = __igc_xdp_run_prog(adapter, prog, xdp); out: - return ERR_PTR(-res); + return res; } /* This function assumes __netif_tx_lock is held by the caller. */ -static void igc_flush_tx_descriptors(struct igc_ring *ring) +void igc_flush_tx_descriptors(struct igc_ring *ring) { /* Once tail pointer is updated, hardware can fetch the descriptors * any time so we issue a write membar here to ensure all memory @@ -2553,7 +2565,7 @@ static void igc_finalize_xdp(struct igc_adapter *adapter, int status) struct igc_ring *ring; if (status & IGC_XDP_TX) { - ring = igc_xdp_get_tx_ring(adapter, cpu); + ring = igc_get_tx_ring(adapter, cpu); nq = txring_txq(ring); __netif_tx_lock(nq, cpu); @@ -2587,6 +2599,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) struct sk_buff *skb = rx_ring->skb; u16 cleaned_count = igc_desc_unused(rx_ring); int xdp_status = 0, rx_buffer_pgcnt; + int xdp_res = 0; while (likely(total_packets < budget)) { struct igc_xdp_buff ctx = { .rx_ts = NULL }; @@ -2624,6 +2637,14 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) size -= IGC_TS_HDR_LEN; } + if (igc_fpe_is_pmac_enabled(adapter) && + igc_fpe_handle_mpacket(adapter, rx_desc, size, pktbuf)) { + /* Advance the ring next-to-clean */ + igc_is_non_eop(rx_ring, rx_desc); + cleaned_count++; + continue; + } + if (!skb) { xdp_init_buff(&ctx.xdp, truesize, &rx_ring->xdp_rxq); xdp_prepare_buff(&ctx.xdp, pktbuf - igc_rx_offset(rx_ring), @@ -2632,12 +2653,10 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) xdp_buff_clear_frags_flag(&ctx.xdp); ctx.rx_desc = rx_desc; - skb = igc_xdp_run_prog(adapter, &ctx.xdp); + xdp_res = igc_xdp_run_prog(adapter, &ctx.xdp); } - if (IS_ERR(skb)) { - unsigned int xdp_res = -PTR_ERR(skb); - + if (xdp_res) { switch (xdp_res) { case IGC_XDP_CONSUMED: rx_buffer->pagecnt_bias++; @@ -2659,9 +2678,10 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) skb = igc_construct_skb(rx_ring, rx_buffer, &ctx); /* exit if we failed to retrieve a buffer */ - if (!skb) { + if (!xdp_res && !skb) { rx_ring->rx_stats.alloc_failed++; rx_buffer->pagecnt_bias++; + set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); break; } @@ -2673,7 +2693,7 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) continue; /* verify the packet layout is correct */ - if (igc_cleanup_headers(rx_ring, rx_desc, skb)) { + if (xdp_res || igc_cleanup_headers(rx_ring, rx_desc, skb)) { skb = NULL; continue; } @@ -2708,16 +2728,16 @@ static int igc_clean_rx_irq(struct igc_q_vector *q_vector, const int budget) } static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring, - struct xdp_buff *xdp) + struct igc_xdp_buff *ctx) { + struct xdp_buff *xdp = &ctx->xdp; unsigned int totalsize = xdp->data_end - xdp->data_meta; unsigned int metasize = xdp->data - xdp->data_meta; struct sk_buff *skb; net_prefetch(xdp->data_meta); - skb = __napi_alloc_skb(&ring->q_vector->napi, totalsize, - GFP_ATOMIC | __GFP_NOWARN); + skb = napi_alloc_skb(&ring->q_vector->napi, totalsize); if (unlikely(!skb)) return NULL; @@ -2729,26 +2749,28 @@ static struct sk_buff *igc_construct_skb_zc(struct igc_ring *ring, __skb_pull(skb, metasize); } + if (ctx->rx_ts) { + skb_shinfo(skb)->tx_flags |= SKBTX_HW_TSTAMP_NETDEV; + skb_hwtstamps(skb)->netdev_data = ctx->rx_ts; + } + return skb; } static void igc_dispatch_skb_zc(struct igc_q_vector *q_vector, union igc_adv_rx_desc *desc, - struct xdp_buff *xdp, - ktime_t timestamp) + struct igc_xdp_buff *ctx) { struct igc_ring *ring = q_vector->rx.ring; struct sk_buff *skb; - skb = igc_construct_skb_zc(ring, xdp); + skb = igc_construct_skb_zc(ring, ctx); if (!skb) { ring->rx_stats.alloc_failed++; + set_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &ring->flags); return; } - if (timestamp) - skb_hwtstamps(skb)->hwtstamp = timestamp; - if (igc_cleanup_headers(ring, desc, skb)) return; @@ -2784,7 +2806,6 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget) union igc_adv_rx_desc *desc; struct igc_rx_buffer *bi; struct igc_xdp_buff *ctx; - ktime_t timestamp = 0; unsigned int size; int res; @@ -2814,15 +2835,17 @@ static int igc_clean_rx_irq_zc(struct igc_q_vector *q_vector, const int budget) */ bi->xdp->data_meta += IGC_TS_HDR_LEN; size -= IGC_TS_HDR_LEN; + } else { + ctx->rx_ts = NULL; } bi->xdp->data_end = bi->xdp->data + size; - xsk_buff_dma_sync_for_cpu(bi->xdp, ring->xsk_pool); + xsk_buff_dma_sync_for_cpu(bi->xdp); res = __igc_xdp_run_prog(adapter, prog, bi->xdp); switch (res) { case IGC_XDP_PASS: - igc_dispatch_skb_zc(q_vector, desc, bi->xdp, timestamp); + igc_dispatch_skb_zc(q_vector, desc, ctx); fallthrough; case IGC_XDP_CONSUMED: xsk_buff_free(bi->xdp); @@ -2878,6 +2901,128 @@ static void igc_update_tx_stats(struct igc_q_vector *q_vector, q_vector->tx.total_packets += packets; } +static void igc_xsk_request_timestamp(void *_priv) +{ + struct igc_metadata_request *meta_req = _priv; + struct igc_ring *tx_ring = meta_req->tx_ring; + struct igc_tx_timestamp_request *tstamp; + u32 tx_flags = IGC_TX_FLAGS_TSTAMP; + struct igc_adapter *adapter; + unsigned long lock_flags; + bool found = false; + int i; + + if (test_bit(IGC_RING_FLAG_TX_HWTSTAMP, &tx_ring->flags)) { + adapter = netdev_priv(tx_ring->netdev); + + spin_lock_irqsave(&adapter->ptp_tx_lock, lock_flags); + + /* Search for available tstamp regs */ + for (i = 0; i < IGC_MAX_TX_TSTAMP_REGS; i++) { + tstamp = &adapter->tx_tstamp[i]; + + /* tstamp->skb and tstamp->xsk_tx_buffer are in union. + * When tstamp->skb is equal to NULL, + * tstamp->xsk_tx_buffer is equal to NULL as well. + * This condition means that the particular tstamp reg + * is not occupied by other packet. + */ + if (!tstamp->skb) { + found = true; + break; + } + } + + /* Return if no available tstamp regs */ + if (!found) { + adapter->tx_hwtstamp_skipped++; + spin_unlock_irqrestore(&adapter->ptp_tx_lock, + lock_flags); + return; + } + + tstamp->start = jiffies; + tstamp->xsk_queue_index = tx_ring->queue_index; + tstamp->xsk_tx_buffer = meta_req->tx_buffer; + tstamp->buffer_type = IGC_TX_BUFFER_TYPE_XSK; + + /* Hold the transmit completion until timestamp is ready */ + meta_req->tx_buffer->xsk_pending_ts = true; + + /* Keep the pointer to tx_timestamp, which is located in XDP + * metadata area. It is the location to store the value of + * tx hardware timestamp. + */ + xsk_tx_metadata_to_compl(meta_req->meta, &tstamp->xsk_meta); + + /* Set timestamp bit based on the _TSTAMP(_X) bit. */ + tx_flags |= tstamp->flags; + meta_req->cmd_type |= IGC_SET_FLAG(tx_flags, + IGC_TX_FLAGS_TSTAMP, + (IGC_ADVTXD_MAC_TSTAMP)); + meta_req->cmd_type |= IGC_SET_FLAG(tx_flags, + IGC_TX_FLAGS_TSTAMP_1, + (IGC_ADVTXD_TSTAMP_REG_1)); + meta_req->cmd_type |= IGC_SET_FLAG(tx_flags, + IGC_TX_FLAGS_TSTAMP_2, + (IGC_ADVTXD_TSTAMP_REG_2)); + meta_req->cmd_type |= IGC_SET_FLAG(tx_flags, + IGC_TX_FLAGS_TSTAMP_3, + (IGC_ADVTXD_TSTAMP_REG_3)); + + spin_unlock_irqrestore(&adapter->ptp_tx_lock, lock_flags); + } +} + +static u64 igc_xsk_fill_timestamp(void *_priv) +{ + return *(u64 *)_priv; +} + +static void igc_xsk_request_launch_time(u64 launch_time, void *_priv) +{ + struct igc_metadata_request *meta_req = _priv; + struct igc_ring *tx_ring = meta_req->tx_ring; + __le32 launch_time_offset; + bool insert_empty = false; + bool first_flag = false; + u16 used_desc = 0; + + if (!tx_ring->launchtime_enable) + return; + + launch_time_offset = igc_tx_launchtime(tx_ring, + ns_to_ktime(launch_time), + &first_flag, &insert_empty); + if (insert_empty) { + /* Disregard the launch time request if the required empty frame + * fails to be inserted. + */ + if (igc_insert_empty_frame(tx_ring)) + return; + + meta_req->tx_buffer = + &tx_ring->tx_buffer_info[tx_ring->next_to_use]; + /* Inserting an empty packet requires two descriptors: + * one data descriptor and one context descriptor. + */ + used_desc += 2; + } + + /* Use one context descriptor to specify launch time and first flag. */ + igc_tx_ctxtdesc(tx_ring, launch_time_offset, first_flag, 0, 0, 0); + used_desc += 1; + + /* Update the number of used descriptors in this request */ + meta_req->used_desc += used_desc; +} + +const struct xsk_tx_metadata_ops igc_xsk_tx_metadata_ops = { + .tmo_request_timestamp = igc_xsk_request_timestamp, + .tmo_fill_timestamp = igc_xsk_fill_timestamp, + .tmo_request_launch_time = igc_xsk_request_launch_time, +}; + static void igc_xdp_xmit_zc(struct igc_ring *ring) { struct xsk_buff_pool *pool = ring->xsk_pool; @@ -2898,25 +3043,51 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) ntu = ring->next_to_use; budget = igc_desc_unused(ring); - while (xsk_tx_peek_desc(pool, &xdp_desc) && budget--) { - u32 cmd_type, olinfo_status; + /* Packets with launch time require one data descriptor and one context + * descriptor. When the launch time falls into the next Qbv cycle, we + * may need to insert an empty packet, which requires two more + * descriptors. Therefore, to be safe, we always ensure we have at least + * 4 descriptors available. + */ + while (budget >= 4 && xsk_tx_peek_desc(pool, &xdp_desc)) { + struct igc_metadata_request meta_req; + struct xsk_tx_metadata *meta = NULL; struct igc_tx_buffer *bi; + u32 olinfo_status; dma_addr_t dma; - cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT | - IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD | - xdp_desc.len; + meta_req.cmd_type = IGC_ADVTXD_DTYP_DATA | + IGC_ADVTXD_DCMD_DEXT | + IGC_ADVTXD_DCMD_IFCS | + IGC_TXD_DCMD | xdp_desc.len; olinfo_status = xdp_desc.len << IGC_ADVTXD_PAYLEN_SHIFT; dma = xsk_buff_raw_get_dma(pool, xdp_desc.addr); + meta = xsk_buff_get_metadata(pool, xdp_desc.addr); xsk_buff_raw_dma_sync_for_device(pool, dma, xdp_desc.len); + bi = &ring->tx_buffer_info[ntu]; + + meta_req.tx_ring = ring; + meta_req.tx_buffer = bi; + meta_req.meta = meta; + meta_req.used_desc = 0; + xsk_tx_metadata_request(meta, &igc_xsk_tx_metadata_ops, + &meta_req); + + /* xsk_tx_metadata_request() may have updated next_to_use */ + ntu = ring->next_to_use; + + /* xsk_tx_metadata_request() may have updated Tx buffer info */ + bi = meta_req.tx_buffer; + + /* xsk_tx_metadata_request() may use a few descriptors */ + budget -= meta_req.used_desc; tx_desc = IGC_TX_DESC(ring, ntu); - tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type); + tx_desc->read.cmd_type_len = cpu_to_le32(meta_req.cmd_type); tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status); tx_desc->read.buffer_addr = cpu_to_le64(dma); - bi = &ring->tx_buffer_info[ntu]; bi->type = IGC_TX_BUFFER_TYPE_XSK; bi->protocol = 0; bi->bytecount = xdp_desc.len; @@ -2929,9 +3100,11 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) ntu++; if (ntu == ring->count) ntu = 0; + + ring->next_to_use = ntu; + budget--; } - ring->next_to_use = ntu; if (tx_desc) { igc_flush_tx_descriptors(ring); xsk_tx_release(pool); @@ -2979,6 +3152,18 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget) if (!(eop_desc->wb.status & cpu_to_le32(IGC_TXD_STAT_DD))) break; + if (igc_fpe_is_pmac_enabled(adapter) && + igc_fpe_transmitted_smd_v(tx_desc)) + ethtool_mmsv_event_handle(&adapter->fpe.mmsv, + ETHTOOL_MMSV_LD_SENT_VERIFY_MPACKET); + + /* Hold the completions while there's a pending tx hardware + * timestamp request from XDP Tx metadata. + */ + if (tx_buffer->type == IGC_TX_BUFFER_TYPE_XSK && + tx_buffer->xsk_pending_ts) + break; + /* clear next_to_watch to prevent false hangs */ tx_buffer->next_to_watch = NULL; @@ -3385,7 +3570,7 @@ static int igc_flex_filter_select(struct igc_adapter *adapter, u32 fhftsl; if (input->index >= MAX_FLEX_FILTER) { - dev_err(&adapter->pdev->dev, "Wrong Flex Filter index selected!\n"); + netdev_err(adapter->netdev, "Wrong Flex Filter index selected!\n"); return -EINVAL; } @@ -3420,7 +3605,6 @@ static int igc_flex_filter_select(struct igc_adapter *adapter, static int igc_write_flex_filter_ll(struct igc_adapter *adapter, struct igc_flex_filter *input) { - struct device *dev = &adapter->pdev->dev; struct igc_hw *hw = &adapter->hw; u8 *data = input->data; u8 *mask = input->mask; @@ -3434,7 +3618,7 @@ static int igc_write_flex_filter_ll(struct igc_adapter *adapter, * out early to avoid surprises later. */ if (input->length % 8 != 0) { - dev_err(dev, "The length of a flex filter has to be 8 byte aligned!\n"); + netdev_err(adapter->netdev, "The length of a flex filter has to be 8 byte aligned!\n"); return -EINVAL; } @@ -3504,8 +3688,8 @@ static int igc_write_flex_filter_ll(struct igc_adapter *adapter, } wr32(IGC_WUFC, wufc); - dev_dbg(&adapter->pdev->dev, "Added flex filter %u to HW.\n", - input->index); + netdev_dbg(adapter->netdev, "Added flex filter %u to HW.\n", + input->index); return 0; } @@ -3577,9 +3761,9 @@ static bool igc_flex_filter_in_use(struct igc_adapter *adapter) static int igc_add_flex_filter(struct igc_adapter *adapter, struct igc_nfc_rule *rule) { - struct igc_flex_filter flex = { }; struct igc_nfc_filter *filter = &rule->filter; unsigned int eth_offset, user_offset; + struct igc_flex_filter flex = { }; int ret, index; bool vlan; @@ -3615,10 +3799,12 @@ static int igc_add_flex_filter(struct igc_adapter *adapter, ETH_ALEN, NULL); /* Add VLAN etype */ - if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_ETYPE) - igc_flex_filter_add_field(&flex, &filter->vlan_etype, 12, - sizeof(filter->vlan_etype), - NULL); + if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_ETYPE) { + __be16 vlan_etype = cpu_to_be16(filter->vlan_etype); + + igc_flex_filter_add_field(&flex, &vlan_etype, 12, + sizeof(vlan_etype), NULL); + } /* Add VLAN TCI */ if (rule->filter.match_flags & IGC_FILTER_FLAG_VLAN_TCI) @@ -3863,6 +4049,30 @@ static int igc_uc_unsync(struct net_device *netdev, const unsigned char *addr) } /** + * igc_enable_empty_addr_recv - Enable Rx of packets with all-zeroes MAC address + * @adapter: Pointer to the igc_adapter structure. + * + * Frame preemption verification requires that packets with the all-zeroes + * MAC address are allowed to be received by the driver. This function adds the + * all-zeroes destination address to the list of acceptable addresses. + * + * Return: 0 on success, negative value otherwise. + */ +int igc_enable_empty_addr_recv(struct igc_adapter *adapter) +{ + u8 empty[ETH_ALEN] = {}; + + return igc_add_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST, empty, -1); +} + +void igc_disable_empty_addr_recv(struct igc_adapter *adapter) +{ + u8 empty[ETH_ALEN] = {}; + + igc_del_mac_filter(adapter, IGC_MAC_FILTER_TYPE_DST, empty); +} + +/** * igc_set_rx_mode - Secondary Unicast, Multicast and Promiscuous mode set * @netdev: network interface device structure * @@ -4848,6 +5058,22 @@ static int igc_sw_init(struct igc_adapter *adapter) return 0; } +static void igc_set_queue_napi(struct igc_adapter *adapter, int vector, + struct napi_struct *napi) +{ + struct igc_q_vector *q_vector = adapter->q_vector[vector]; + + if (q_vector->rx.ring) + netif_queue_set_napi(adapter->netdev, + q_vector->rx.ring->queue_index, + NETDEV_QUEUE_TYPE_RX, napi); + + if (q_vector->tx.ring) + netif_queue_set_napi(adapter->netdev, + q_vector->tx.ring->queue_index, + NETDEV_QUEUE_TYPE_TX, napi); +} + /** * igc_up - Open the interface and prepare it to handle traffic * @adapter: board private structure @@ -4855,6 +5081,7 @@ static int igc_sw_init(struct igc_adapter *adapter) void igc_up(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; + struct napi_struct *napi; int i = 0; /* hardware has been reset, we need to reload some things */ @@ -4862,8 +5089,11 @@ void igc_up(struct igc_adapter *adapter) clear_bit(__IGC_DOWN, &adapter->state); - for (i = 0; i < adapter->num_q_vectors; i++) - napi_enable(&adapter->q_vector[i]->napi); + for (i = 0; i < adapter->num_q_vectors; i++) { + napi = &adapter->q_vector[i]->napi; + napi_enable(napi); + igc_set_queue_napi(adapter, i, napi); + } if (adapter->msix_entries) igc_configure_msix(adapter); @@ -5092,12 +5322,13 @@ void igc_down(struct igc_adapter *adapter) for (i = 0; i < adapter->num_q_vectors; i++) { if (adapter->q_vector[i]) { napi_synchronize(&adapter->q_vector[i]->napi); + igc_set_queue_napi(adapter, i, NULL); napi_disable(&adapter->q_vector[i]->napi); } } - del_timer_sync(&adapter->watchdog_timer); - del_timer_sync(&adapter->phy_info_timer); + timer_delete_sync(&adapter->watchdog_timer); + timer_delete_sync(&adapter->phy_info_timer); /* record the stats before reset*/ spin_lock(&adapter->stats64_lock); @@ -5116,6 +5347,9 @@ void igc_down(struct igc_adapter *adapter) igc_disable_all_tx_rings_hw(adapter); igc_clean_all_tx_rings(adapter); igc_clean_all_rx_rings(adapter); + + if (adapter->fpe.mmsv.pmac_enabled) + ethtool_mmsv_stop(&adapter->fpe.mmsv); } void igc_reinit_locked(struct igc_adapter *adapter) @@ -5179,7 +5413,7 @@ static int igc_change_mtu(struct net_device *netdev, int new_mtu) igc_down(adapter); netdev_dbg(netdev, "changing MTU from %d to %d\n", netdev->mtu, new_mtu); - netdev->mtu = new_mtu; + WRITE_ONCE(netdev->mtu, new_mtu); if (netif_running(netdev)) igc_up(adapter); @@ -5276,7 +5510,7 @@ igc_features_check(struct sk_buff *skb, struct net_device *dev, unsigned int network_hdr_len, mac_hdr_len; /* Make certain the headers can be described by a context descriptor */ - mac_hdr_len = skb_network_header(skb) - skb->data; + mac_hdr_len = skb_network_offset(skb); if (unlikely(mac_hdr_len > IGC_MAX_MAC_HDR_LEN)) return features & ~(NETIF_F_HW_CSUM | NETIF_F_SCTP_CRC | @@ -5302,25 +5536,22 @@ igc_features_check(struct sk_buff *skb, struct net_device *dev, static void igc_tsync_interrupt(struct igc_adapter *adapter) { - u32 ack, tsauxc, sec, nsec, tsicr; struct igc_hw *hw = &adapter->hw; + u32 tsauxc, sec, nsec, tsicr; struct ptp_clock_event event; struct timespec64 ts; tsicr = rd32(IGC_TSICR); - ack = 0; if (tsicr & IGC_TSICR_SYS_WRAP) { event.type = PTP_CLOCK_PPS; if (adapter->ptp_caps.pps) ptp_clock_event(adapter->ptp_clock, &event); - ack |= IGC_TSICR_SYS_WRAP; } if (tsicr & IGC_TSICR_TXTS) { /* retrieve hardware timestamp */ igc_ptp_tx_tstamp_event(adapter); - ack |= IGC_TSICR_TXTS; } if (tsicr & IGC_TSICR_TT0) { @@ -5334,7 +5565,6 @@ static void igc_tsync_interrupt(struct igc_adapter *adapter) wr32(IGC_TSAUXC, tsauxc); adapter->perout[0].start = ts; spin_unlock(&adapter->tmreg_lock); - ack |= IGC_TSICR_TT0; } if (tsicr & IGC_TSICR_TT1) { @@ -5348,7 +5578,6 @@ static void igc_tsync_interrupt(struct igc_adapter *adapter) wr32(IGC_TSAUXC, tsauxc); adapter->perout[1].start = ts; spin_unlock(&adapter->tmreg_lock); - ack |= IGC_TSICR_TT1; } if (tsicr & IGC_TSICR_AUTT0) { @@ -5358,7 +5587,6 @@ static void igc_tsync_interrupt(struct igc_adapter *adapter) event.index = 0; event.timestamp = sec * NSEC_PER_SEC + nsec; ptp_clock_event(adapter->ptp_clock, &event); - ack |= IGC_TSICR_AUTT0; } if (tsicr & IGC_TSICR_AUTT1) { @@ -5368,11 +5596,7 @@ static void igc_tsync_interrupt(struct igc_adapter *adapter) event.index = 1; event.timestamp = sec * NSEC_PER_SEC + nsec; ptp_clock_event(adapter->ptp_clock, &event); - ack |= IGC_TSICR_AUTT1; } - - /* acknowledge the interrupts */ - wr32(IGC_TSICR, ack); } /** @@ -5486,6 +5710,9 @@ static int igc_request_msix(struct igc_adapter *adapter) q_vector); if (err) goto err_free; + + netif_napi_set_irq(&q_vector->napi, + adapter->msix_entries[vector].vector); } igc_configure_msix(adapter); @@ -5647,6 +5874,10 @@ static void igc_watchdog_task(struct work_struct *work) */ igc_tsn_adjust_txtime_offset(adapter); + if (adapter->fpe.mmsv.pmac_enabled) + ethtool_mmsv_link_state_handle(&adapter->fpe.mmsv, + true); + if (adapter->link_speed != SPEED_1000) goto no_wait; @@ -5682,6 +5913,10 @@ no_wait: netdev_info(netdev, "NIC Link is Down\n"); netif_carrier_off(netdev); + if (adapter->fpe.mmsv.pmac_enabled) + ethtool_mmsv_link_state_handle(&adapter->fpe.mmsv, + false); + /* link state has changed, schedule phy info update */ if (!test_bit(__IGC_DOWN, &adapter->state)) mod_timer(&adapter->phy_info_timer, @@ -5721,11 +5956,29 @@ no_wait: if (adapter->flags & IGC_FLAG_HAS_MSIX) { u32 eics = 0; - for (i = 0; i < adapter->num_q_vectors; i++) - eics |= adapter->q_vector[i]->eims_value; - wr32(IGC_EICS, eics); + for (i = 0; i < adapter->num_q_vectors; i++) { + struct igc_q_vector *q_vector = adapter->q_vector[i]; + struct igc_ring *rx_ring; + + if (!q_vector->rx.ring) + continue; + + rx_ring = adapter->rx_ring[q_vector->rx.ring->queue_index]; + + if (test_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags)) { + eics |= q_vector->eims_value; + clear_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); + } + } + if (eics) + wr32(IGC_EICS, eics); } else { - wr32(IGC_ICS, IGC_ICS_RXDMT0); + struct igc_ring *rx_ring = adapter->rx_ring[0]; + + if (test_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags)) { + clear_bit(IGC_RING_FLAG_RX_ALLOC_FAILED, &rx_ring->flags); + wr32(IGC_ICS, IGC_ICS_RXDMT0); + } } igc_ptp_tx_hang(adapter); @@ -5910,6 +6163,7 @@ static int __igc_open(struct net_device *netdev, bool resuming) struct igc_adapter *adapter = netdev_priv(netdev); struct pci_dev *pdev = adapter->pdev; struct igc_hw *hw = &adapter->hw; + struct napi_struct *napi; int err = 0; int i = 0; @@ -5943,19 +6197,13 @@ static int __igc_open(struct net_device *netdev, bool resuming) if (err) goto err_req_irq; - /* Notify the stack of the actual queue counts. */ - err = netif_set_real_num_tx_queues(netdev, adapter->num_tx_queues); - if (err) - goto err_set_queues; - - err = netif_set_real_num_rx_queues(netdev, adapter->num_rx_queues); - if (err) - goto err_set_queues; - clear_bit(__IGC_DOWN, &adapter->state); - for (i = 0; i < adapter->num_q_vectors; i++) - napi_enable(&adapter->q_vector[i]->napi); + for (i = 0; i < adapter->num_q_vectors; i++) { + napi = &adapter->q_vector[i]->napi; + napi_enable(napi); + igc_set_queue_napi(adapter, i, napi); + } /* Clear any pending interrupts. */ rd32(IGC_ICR); @@ -5972,8 +6220,6 @@ static int __igc_open(struct net_device *netdev, bool resuming) return IGC_SUCCESS; -err_set_queues: - igc_free_irq(adapter); err_req_irq: igc_release_hw_control(adapter); igc_power_down_phy_copper_base(&adapter->hw); @@ -5990,6 +6236,17 @@ err_setup_tx: int igc_open(struct net_device *netdev) { + struct igc_adapter *adapter = netdev_priv(netdev); + int err; + + /* Notify the stack of the actual queue counts. */ + err = netif_set_real_num_queues(netdev, adapter->num_tx_queues, + adapter->num_rx_queues); + if (err) { + netdev_err(netdev, "error setting real queue count\n"); + return err; + } + return __igc_open(netdev, false); } @@ -6220,21 +6477,6 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, size_t n; int i; - switch (qopt->cmd) { - case TAPRIO_CMD_REPLACE: - break; - case TAPRIO_CMD_DESTROY: - return igc_tsn_clear_schedule(adapter); - case TAPRIO_CMD_STATS: - igc_taprio_stats(adapter->netdev, &qopt->stats); - return 0; - case TAPRIO_CMD_QUEUE_STATS: - igc_taprio_queue_stats(adapter->netdev, &qopt->queue_stats); - return 0; - default: - return -EOPNOTSUPP; - } - if (qopt->base_time < 0) return -ERANGE; @@ -6244,12 +6486,20 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter, if (!validate_schedule(adapter, qopt)) return -EINVAL; + /* preemptible isn't supported yet */ + if (qopt->mqprio.preemptible_tcs) + return -EOPNOTSUPP; + + igc_ptp_read(adapter, &now); + + if (igc_tsn_is_taprio_activated_by_user(adapter) && + is_base_time_past(qopt->base_time, &now)) + adapter->qbv_config_change_errors++; + adapter->cycle_time = qopt->cycle_time; adapter->base_time = qopt->base_time; adapter->taprio_offload_enable = true; - igc_ptp_read(adapter, &now); - for (n = 0; n < qopt->num_entries; n++) { struct tc_taprio_sched_entry *e = &qopt->entries[n]; @@ -6343,7 +6593,23 @@ static int igc_tsn_enable_qbv_scheduling(struct igc_adapter *adapter, if (hw->mac.type != igc_i225) return -EOPNOTSUPP; - err = igc_save_qbv_schedule(adapter, qopt); + switch (qopt->cmd) { + case TAPRIO_CMD_REPLACE: + err = igc_save_qbv_schedule(adapter, qopt); + break; + case TAPRIO_CMD_DESTROY: + err = igc_tsn_clear_schedule(adapter); + break; + case TAPRIO_CMD_STATS: + igc_taprio_stats(adapter->netdev, &qopt->stats); + return 0; + case TAPRIO_CMD_QUEUE_STATS: + igc_taprio_queue_stats(adapter->netdev, &qopt->queue_stats); + return 0; + default: + return -EOPNOTSUPP; + } + if (err) return err; @@ -6424,6 +6690,13 @@ static int igc_tc_query_caps(struct igc_adapter *adapter, struct igc_hw *hw = &adapter->hw; switch (base->type) { + case TC_SETUP_QDISC_MQPRIO: { + struct tc_mqprio_caps *caps = base->caps; + + caps->validate_queue_counts = true; + + return 0; + } case TC_SETUP_QDISC_TAPRIO: { struct tc_taprio_caps *caps = base->caps; @@ -6441,6 +6714,81 @@ static int igc_tc_query_caps(struct igc_adapter *adapter, } } +static void igc_save_mqprio_params(struct igc_adapter *adapter, u8 num_tc, + u16 *offset) +{ + int i; + + adapter->strict_priority_enable = true; + adapter->num_tc = num_tc; + + for (i = 0; i < num_tc; i++) + adapter->queue_per_tc[i] = offset[i]; +} + +static int igc_tsn_enable_mqprio(struct igc_adapter *adapter, + struct tc_mqprio_qopt_offload *mqprio) +{ + struct igc_hw *hw = &adapter->hw; + int err, i; + + if (hw->mac.type != igc_i225) + return -EOPNOTSUPP; + + if (!mqprio->qopt.num_tc) { + adapter->strict_priority_enable = false; + netdev_reset_tc(adapter->netdev); + goto apply; + } + + /* There are as many TCs as Tx queues. */ + if (mqprio->qopt.num_tc != adapter->num_tx_queues) { + NL_SET_ERR_MSG_FMT_MOD(mqprio->extack, + "Only %d traffic classes supported", + adapter->num_tx_queues); + return -EOPNOTSUPP; + } + + /* Only one queue per TC is supported. */ + for (i = 0; i < mqprio->qopt.num_tc; i++) { + if (mqprio->qopt.count[i] != 1) { + NL_SET_ERR_MSG_MOD(mqprio->extack, + "Only one queue per TC supported"); + return -EOPNOTSUPP; + } + } + + /* Preemption is not supported yet. */ + if (mqprio->preemptible_tcs) { + NL_SET_ERR_MSG_MOD(mqprio->extack, + "Preemption is not supported yet"); + return -EOPNOTSUPP; + } + + igc_save_mqprio_params(adapter, mqprio->qopt.num_tc, + mqprio->qopt.offset); + + err = netdev_set_num_tc(adapter->netdev, adapter->num_tc); + if (err) + return err; + + for (i = 0; i < adapter->num_tc; i++) { + err = netdev_set_tc_queue(adapter->netdev, i, 1, + adapter->queue_per_tc[i]); + if (err) + return err; + } + + /* In case the card is configured with less than four queues. */ + for (; i < IGC_MAX_TX_QUEUES; i++) + adapter->queue_per_tc[i] = i; + + mqprio->qopt.hw = TC_MQPRIO_HW_OFFLOAD_TCS; + +apply: + return igc_tsn_offload_apply(adapter); +} + static int igc_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { @@ -6460,6 +6808,9 @@ static int igc_setup_tc(struct net_device *dev, enum tc_setup_type type, case TC_SETUP_QDISC_CBS: return igc_tsn_enable_cbs(adapter, type_data); + case TC_SETUP_QDISC_MQPRIO: + return igc_tsn_enable_mqprio(adapter, type_data); + default: return -EOPNOTSUPP; } @@ -6487,7 +6838,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, int cpu = smp_processor_id(); struct netdev_queue *nq; struct igc_ring *ring; - int i, drops; + int i, nxmit; if (unlikely(!netif_carrier_ok(dev))) return -ENETDOWN; @@ -6495,7 +6846,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) return -EINVAL; - ring = igc_xdp_get_tx_ring(adapter, cpu); + ring = igc_get_tx_ring(adapter, cpu); nq = txring_txq(ring); __netif_tx_lock(nq, cpu); @@ -6503,16 +6854,15 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, /* Avoid transmit queue timeout since we share it with the slow path */ txq_trans_cond_update(nq); - drops = 0; + nxmit = 0; for (i = 0; i < num_frames; i++) { int err; struct xdp_frame *xdpf = frames[i]; err = igc_xdp_init_tx_descriptor(ring, xdpf); - if (err) { - xdp_return_frame_rx_napi(xdpf); - drops++; - } + if (err) + break; + nxmit++; } if (flags & XDP_XMIT_FLUSH) @@ -6520,7 +6870,7 @@ static int igc_xdp_xmit(struct net_device *dev, int num_frames, __netif_tx_unlock(nq); - return num_frames - drops; + return nxmit; } static void igc_trigger_rxtxq_interrupt(struct igc_adapter *adapter, @@ -6598,45 +6948,6 @@ static const struct net_device_ops igc_netdev_ops = { .ndo_get_tstamp = igc_get_tstamp, }; -/* PCIe configuration access */ -void igc_read_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value) -{ - struct igc_adapter *adapter = hw->back; - - pci_read_config_word(adapter->pdev, reg, value); -} - -void igc_write_pci_cfg(struct igc_hw *hw, u32 reg, u16 *value) -{ - struct igc_adapter *adapter = hw->back; - - pci_write_config_word(adapter->pdev, reg, *value); -} - -s32 igc_read_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value) -{ - struct igc_adapter *adapter = hw->back; - - if (!pci_is_pcie(adapter->pdev)) - return -IGC_ERR_CONFIG; - - pcie_capability_read_word(adapter->pdev, reg, value); - - return IGC_SUCCESS; -} - -s32 igc_write_pcie_cap_reg(struct igc_hw *hw, u32 reg, u16 *value) -{ - struct igc_adapter *adapter = hw->back; - - if (!pci_is_pcie(adapter->pdev)) - return -IGC_ERR_CONFIG; - - pcie_capability_write_word(adapter->pdev, reg, *value); - - return IGC_SUCCESS; -} - u32 igc_rd32(struct igc_hw *hw, u32 reg) { struct igc_adapter *igc = container_of(hw, struct igc_adapter, hw); @@ -6817,6 +7128,7 @@ static int igc_probe(struct pci_dev *pdev, netdev->netdev_ops = &igc_netdev_ops; netdev->xdp_metadata_ops = &igc_xdp_metadata_ops; + netdev->xsk_tx_metadata_ops = &igc_xsk_tx_metadata_ops; igc_ethtool_set_ops(netdev); netdev->watchdog_timeo = 5 * HZ; @@ -6880,6 +7192,9 @@ static int igc_probe(struct pci_dev *pdev, netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT | NETDEV_XDP_ACT_XSK_ZEROCOPY; + /* enable HW vlan tag insertion/stripping by default */ + netdev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; + /* MTU range: 68 - 9216 */ netdev->min_mtu = ETH_MIN_MTU; netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE; @@ -6912,8 +7227,8 @@ static int igc_probe(struct pci_dev *pdev, } /* configure RXPBSIZE and TXPBSIZE */ - wr32(IGC_RXPBS, I225_RXPBSIZE_DEFAULT); - wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT); + wr32(IGC_RXPBS, IGC_RXPBSIZE_EXP_BMC_DEFAULT); + wr32(IGC_TXPBS, IGC_TXPBSIZE_DEFAULT); timer_setup(&adapter->watchdog_timer, igc_watchdog, 0); timer_setup(&adapter->phy_info_timer, igc_update_phy_info, 0); @@ -6921,12 +7236,11 @@ static int igc_probe(struct pci_dev *pdev, INIT_WORK(&adapter->reset_task, igc_reset_task); INIT_WORK(&adapter->watchdog_task, igc_watchdog_task); - hrtimer_init(&adapter->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); - adapter->hrtimer.function = &igc_qbv_scheduling_timer; + hrtimer_setup(&adapter->hrtimer, &igc_qbv_scheduling_timer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL); /* Initialize link properties that are user-changeable */ adapter->fc_autoneg = true; - hw->mac.autoneg = true; hw->phy.autoneg_advertised = 0xaf; hw->fc.requested_mode = igc_fc_default; @@ -6946,6 +7260,8 @@ static int igc_probe(struct pci_dev *pdev, igc_tsn_clear_schedule(adapter); + igc_fpe_init(adapter); + /* reset the hardware with the new settings */ igc_reset(adapter); @@ -6977,10 +7293,17 @@ static int igc_probe(struct pci_dev *pdev, pm_runtime_put_noidle(&pdev->dev); + if (IS_ENABLED(CONFIG_IGC_LEDS)) { + err = igc_led_setup(adapter); + if (err) + goto err_register; + } + return 0; err_register: igc_release_hw_control(adapter); + igc_ptp_stop(adapter); err_eeprom: if (!igc_check_reset_block(hw)) igc_reset_phy(hw); @@ -7022,13 +7345,16 @@ static void igc_remove(struct pci_dev *pdev) set_bit(__IGC_DOWN, &adapter->state); - del_timer_sync(&adapter->watchdog_timer); - del_timer_sync(&adapter->phy_info_timer); + timer_delete_sync(&adapter->watchdog_timer); + timer_delete_sync(&adapter->phy_info_timer); cancel_work_sync(&adapter->reset_task); cancel_work_sync(&adapter->watchdog_task); hrtimer_cancel(&adapter->hrtimer); + if (IS_ENABLED(CONFIG_IGC_LEDS)) + igc_led_free(adapter); + /* Release control of h/w to f/w. If f/w is AMT enabled, this * would have already happened in close and is redundant. */ @@ -7113,8 +7439,7 @@ static int __igc_shutdown(struct pci_dev *pdev, bool *enable_wake, return 0; } -#ifdef CONFIG_PM -static int __maybe_unused igc_runtime_suspend(struct device *dev) +static int igc_runtime_suspend(struct device *dev) { return __igc_shutdown(to_pci_dev(dev), NULL, 1); } @@ -7149,7 +7474,7 @@ static void igc_deliver_wake_packet(struct net_device *netdev) netif_rx(skb); } -static int __maybe_unused igc_resume(struct device *dev) +static int __igc_resume(struct device *dev, bool rpm) { struct pci_dev *pdev = to_pci_dev(dev); struct net_device *netdev = pci_get_drvdata(pdev); @@ -7191,23 +7516,30 @@ static int __maybe_unused igc_resume(struct device *dev) wr32(IGC_WUS, ~0); - rtnl_lock(); - if (!err && netif_running(netdev)) + if (netif_running(netdev)) { + if (!rpm) + rtnl_lock(); err = __igc_open(netdev, true); - - if (!err) - netif_device_attach(netdev); - rtnl_unlock(); + if (!rpm) + rtnl_unlock(); + if (!err) + netif_device_attach(netdev); + } return err; } -static int __maybe_unused igc_runtime_resume(struct device *dev) +static int igc_resume(struct device *dev) +{ + return __igc_resume(dev, false); +} + +static int igc_runtime_resume(struct device *dev) { - return igc_resume(dev); + return __igc_resume(dev, true); } -static int __maybe_unused igc_suspend(struct device *dev) +static int igc_suspend(struct device *dev) { return __igc_shutdown(to_pci_dev(dev), NULL, 0); } @@ -7222,7 +7554,6 @@ static int __maybe_unused igc_runtime_idle(struct device *dev) return -EBUSY; } -#endif /* CONFIG_PM */ static void igc_shutdown(struct pci_dev *pdev) { @@ -7250,14 +7581,18 @@ static pci_ers_result_t igc_io_error_detected(struct pci_dev *pdev, struct net_device *netdev = pci_get_drvdata(pdev); struct igc_adapter *adapter = netdev_priv(netdev); + 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)) igc_down(adapter); pci_disable_device(pdev); + rtnl_unlock(); /* Request a slot reset. */ return PCI_ERS_RESULT_NEED_RESET; @@ -7268,7 +7603,7 @@ static pci_ers_result_t igc_io_error_detected(struct pci_dev *pdev, * @pdev: Pointer to PCI device * * Restart the card from scratch, as if from a cold-boot. Implementation - * resembles the first-half of the igc_resume routine. + * resembles the first-half of the __igc_resume routine. **/ static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev) { @@ -7307,7 +7642,7 @@ static pci_ers_result_t igc_io_slot_reset(struct pci_dev *pdev) * * This callback is called when the error recovery driver tells us that * its OK to resume normal operation. Implementation resembles the - * second-half of the igc_resume routine. + * second-half of the __igc_resume routine. */ static void igc_io_resume(struct pci_dev *pdev) { @@ -7317,6 +7652,7 @@ static void igc_io_resume(struct pci_dev *pdev) rtnl_lock(); if (netif_running(netdev)) { if (igc_open(netdev)) { + rtnl_unlock(); netdev_err(netdev, "igc_open failed after reset\n"); return; } @@ -7337,22 +7673,16 @@ static const struct pci_error_handlers igc_err_handler = { .resume = igc_io_resume, }; -#ifdef CONFIG_PM -static const struct dev_pm_ops igc_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(igc_suspend, igc_resume) - SET_RUNTIME_PM_OPS(igc_runtime_suspend, igc_runtime_resume, - igc_runtime_idle) -}; -#endif +static _DEFINE_DEV_PM_OPS(igc_pm_ops, igc_suspend, igc_resume, + igc_runtime_suspend, igc_runtime_resume, + igc_runtime_idle); static struct pci_driver igc_driver = { .name = igc_driver_name, .id_table = igc_pci_tbl, .probe = igc_probe, .remove = igc_remove, -#ifdef CONFIG_PM - .driver.pm = &igc_pm_ops, -#endif + .driver.pm = pm_ptr(&igc_pm_ops), .shutdown = igc_shutdown, .err_handler = &igc_err_handler, }; diff --git a/drivers/net/ethernet/intel/igc/igc_nvm.c b/drivers/net/ethernet/intel/igc/igc_nvm.c index 58f81aba0144..efd121c03967 100644 --- a/drivers/net/ethernet/intel/igc/igc_nvm.c +++ b/drivers/net/ethernet/intel/igc/igc_nvm.c @@ -36,56 +36,6 @@ static s32 igc_poll_eerd_eewr_done(struct igc_hw *hw, int ee_reg) } /** - * igc_acquire_nvm - Generic request for access to EEPROM - * @hw: pointer to the HW structure - * - * Set the EEPROM access request bit and wait for EEPROM access grant bit. - * Return successful if access grant bit set, else clear the request for - * EEPROM access and return -IGC_ERR_NVM (-1). - */ -s32 igc_acquire_nvm(struct igc_hw *hw) -{ - s32 timeout = IGC_NVM_GRANT_ATTEMPTS; - u32 eecd = rd32(IGC_EECD); - s32 ret_val = 0; - - wr32(IGC_EECD, eecd | IGC_EECD_REQ); - eecd = rd32(IGC_EECD); - - while (timeout) { - if (eecd & IGC_EECD_GNT) - break; - udelay(5); - eecd = rd32(IGC_EECD); - timeout--; - } - - if (!timeout) { - eecd &= ~IGC_EECD_REQ; - wr32(IGC_EECD, eecd); - hw_dbg("Could not acquire NVM grant\n"); - ret_val = -IGC_ERR_NVM; - } - - return ret_val; -} - -/** - * igc_release_nvm - Release exclusive access to EEPROM - * @hw: pointer to the HW structure - * - * Stop any current commands to the EEPROM and clear the EEPROM request bit. - */ -void igc_release_nvm(struct igc_hw *hw) -{ - u32 eecd; - - eecd = rd32(IGC_EECD); - eecd &= ~IGC_EECD_REQ; - wr32(IGC_EECD, eecd); -} - -/** * igc_read_nvm_eerd - Reads EEPROM using EERD register * @hw: pointer to the HW structure * @offset: offset of word in the EEPROM to read diff --git a/drivers/net/ethernet/intel/igc/igc_nvm.h b/drivers/net/ethernet/intel/igc/igc_nvm.h index f9fc2e9cfb03..ab78d0c64547 100644 --- a/drivers/net/ethernet/intel/igc/igc_nvm.h +++ b/drivers/net/ethernet/intel/igc/igc_nvm.h @@ -4,8 +4,6 @@ #ifndef _IGC_NVM_H_ #define _IGC_NVM_H_ -s32 igc_acquire_nvm(struct igc_hw *hw); -void igc_release_nvm(struct igc_hw *hw); s32 igc_read_mac_addr(struct igc_hw *hw); s32 igc_read_nvm_eerd(struct igc_hw *hw, u16 offset, u16 words, u16 *data); s32 igc_validate_nvm_checksum(struct igc_hw *hw); diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c index 861f37076861..6c4d204aecfa 100644 --- a/drivers/net/ethernet/intel/igc/igc_phy.c +++ b/drivers/net/ethernet/intel/igc/igc_phy.c @@ -240,7 +240,7 @@ static s32 igc_phy_setup_autoneg(struct igc_hw *hw) /* Read the MULTI GBT AN Control Register - reg 7.32 */ ret_val = phy->ops.read_reg(hw, (STANDARD_AN_REG_MASK << MMD_DEVADDR_SHIFT) | - ANEG_MULTIGBT_AN_CTRL, + IGC_ANEG_MULTIGBT_AN_CTRL, &aneg_multigbt_an_ctrl); if (ret_val) @@ -380,7 +380,7 @@ static s32 igc_phy_setup_autoneg(struct igc_hw *hw) ret_val = phy->ops.write_reg(hw, (STANDARD_AN_REG_MASK << MMD_DEVADDR_SHIFT) | - ANEG_MULTIGBT_AN_CTRL, + IGC_ANEG_MULTIGBT_AN_CTRL, aneg_multigbt_an_ctrl); return ret_val; @@ -494,24 +494,12 @@ s32 igc_setup_copper_link(struct igc_hw *hw) s32 ret_val = 0; bool link; - if (hw->mac.autoneg) { - /* Setup autoneg and flow control advertisement and perform - * autonegotiation. - */ - ret_val = igc_copper_link_autoneg(hw); - if (ret_val) - goto out; - } else { - /* PHY will be set to 10H, 10F, 100H or 100F - * depending on user settings. - */ - hw_dbg("Forcing Speed and Duplex\n"); - ret_val = hw->phy.ops.force_speed_duplex(hw); - if (ret_val) { - hw_dbg("Error Forcing Speed and Duplex\n"); - goto out; - } - } + /* Setup autoneg and flow control advertisement and perform + * autonegotiation. + */ + ret_val = igc_copper_link_autoneg(hw); + if (ret_val) + goto out; /* Check link status. Wait up to 100 microseconds for link to become * valid. diff --git a/drivers/net/ethernet/intel/igc/igc_ptp.c b/drivers/net/ethernet/intel/igc/igc_ptp.c index 885faaa7b9de..f4f5c28615d3 100644 --- a/drivers/net/ethernet/intel/igc/igc_ptp.c +++ b/drivers/net/ethernet/intel/igc/igc_ptp.c @@ -11,6 +11,7 @@ #include <linux/ktime.h> #include <linux/delay.h> #include <linux/iopoll.h> +#include <net/xdp_sock_drv.h> #define INCVALUE_MASK 0x7fffffff #define ISGN 0x80000000 @@ -256,13 +257,6 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp, switch (rq->type) { case PTP_CLK_REQ_EXTTS: - /* Reject requests with unsupported flags */ - if (rq->extts.flags & ~(PTP_ENABLE_FEATURE | - PTP_RISING_EDGE | - PTP_FALLING_EDGE | - PTP_STRICT_FLAGS)) - return -EOPNOTSUPP; - /* Reject requests failing to enable both edges. */ if ((rq->extts.flags & PTP_STRICT_FLAGS) && (rq->extts.flags & PTP_ENABLE_FEATURE) && @@ -299,10 +293,6 @@ static int igc_ptp_feature_enable_i225(struct ptp_clock_info *ptp, return 0; case PTP_CLK_REQ_PEROUT: - /* Reject requests with unsupported flags */ - if (rq->perout.flags) - return -EOPNOTSUPP; - if (on) { pin = ptp_find_pin(igc->ptp_clock, PTP_PF_PEROUT, rq->perout.index); @@ -545,6 +535,30 @@ static void igc_ptp_enable_rx_timestamp(struct igc_adapter *adapter) wr32(IGC_TSYNCRXCTL, val); } +static void igc_ptp_free_tx_buffer(struct igc_adapter *adapter, + struct igc_tx_timestamp_request *tstamp) +{ + if (tstamp->buffer_type == IGC_TX_BUFFER_TYPE_XSK) { + /* Release the transmit completion */ + tstamp->xsk_tx_buffer->xsk_pending_ts = false; + + /* Note: tstamp->skb and tstamp->xsk_tx_buffer are in union. + * By setting tstamp->xsk_tx_buffer to NULL, tstamp->skb will + * become NULL as well. + */ + tstamp->xsk_tx_buffer = NULL; + tstamp->buffer_type = 0; + + /* Trigger txrx interrupt for transmit completion */ + igc_xsk_wakeup(adapter->netdev, tstamp->xsk_queue_index, 0); + + return; + } + + dev_kfree_skb_any(tstamp->skb); + tstamp->skb = NULL; +} + static void igc_ptp_clear_tx_tstamp(struct igc_adapter *adapter) { unsigned long flags; @@ -555,8 +569,8 @@ static void igc_ptp_clear_tx_tstamp(struct igc_adapter *adapter) for (i = 0; i < IGC_MAX_TX_TSTAMP_REGS; i++) { struct igc_tx_timestamp_request *tstamp = &adapter->tx_tstamp[i]; - dev_kfree_skb_any(tstamp->skb); - tstamp->skb = NULL; + if (tstamp->skb) + igc_ptp_free_tx_buffer(adapter, tstamp); } spin_unlock_irqrestore(&adapter->ptp_tx_lock, flags); @@ -657,8 +671,9 @@ static int igc_ptp_set_timestamp_mode(struct igc_adapter *adapter, static void igc_ptp_tx_timeout(struct igc_adapter *adapter, struct igc_tx_timestamp_request *tstamp) { - dev_kfree_skb_any(tstamp->skb); - tstamp->skb = NULL; + if (tstamp->skb) + igc_ptp_free_tx_buffer(adapter, tstamp); + adapter->tx_hwtstamp_timeouts++; netdev_warn(adapter->netdev, "Tx timestamp timeout\n"); @@ -729,10 +744,21 @@ static void igc_ptp_tx_reg_to_stamp(struct igc_adapter *adapter, shhwtstamps.hwtstamp = ktime_add_ns(shhwtstamps.hwtstamp, adjust); - tstamp->skb = NULL; + /* Copy the tx hardware timestamp into xdp metadata or skb */ + if (tstamp->buffer_type == IGC_TX_BUFFER_TYPE_XSK) { + struct xsk_buff_pool *xsk_pool; + + xsk_pool = adapter->tx_ring[tstamp->xsk_queue_index]->xsk_pool; + if (xsk_pool && xp_tx_metadata_enabled(xsk_pool)) { + xsk_tx_metadata_complete(&tstamp->xsk_meta, + &igc_xsk_tx_metadata_ops, + &shhwtstamps.hwtstamp); + } + } else { + skb_tstamp_tx(skb, &shhwtstamps); + } - skb_tstamp_tx(skb, &shhwtstamps); - dev_kfree_skb_any(skb); + igc_ptp_free_tx_buffer(adapter, tstamp); } /** @@ -901,7 +927,11 @@ static bool igc_is_crosststamp_supported(struct igc_adapter *adapter) static struct system_counterval_t igc_device_tstamp_to_system(u64 tstamp) { #if IS_ENABLED(CONFIG_X86_TSC) && !defined(CONFIG_UML) - return convert_art_ns_to_tsc(tstamp); + return (struct system_counterval_t) { + .cs_id = CSID_X86_ART, + .cycles = tstamp, + .use_nsecs = true, + }; #else return (struct system_counterval_t) { }; #endif @@ -933,45 +963,62 @@ static void igc_ptm_log_error(struct igc_adapter *adapter, u32 ptm_stat) } } +/* The PTM lock: adapter->ptm_lock must be held when calling igc_ptm_trigger() */ +static void igc_ptm_trigger(struct igc_hw *hw) +{ + u32 ctrl; + + /* To "manually" start the PTM cycle we need to set the + * trigger (TRIG) bit + */ + ctrl = rd32(IGC_PTM_CTRL); + ctrl |= IGC_PTM_CTRL_TRIG; + wr32(IGC_PTM_CTRL, ctrl); + /* Perform flush after write to CTRL register otherwise + * transaction may not start + */ + wrfl(); +} + +/* The PTM lock: adapter->ptm_lock must be held when calling igc_ptm_reset() */ +static void igc_ptm_reset(struct igc_hw *hw) +{ + u32 ctrl; + + ctrl = rd32(IGC_PTM_CTRL); + ctrl &= ~IGC_PTM_CTRL_TRIG; + wr32(IGC_PTM_CTRL, ctrl); + /* Write to clear all status */ + wr32(IGC_PTM_STAT, IGC_PTM_STAT_ALL); +} + static int igc_phc_get_syncdevicetime(ktime_t *device, struct system_counterval_t *system, void *ctx) { - u32 stat, t2_curr_h, t2_curr_l, ctrl; struct igc_adapter *adapter = ctx; struct igc_hw *hw = &adapter->hw; + u32 stat, t2_curr_h, t2_curr_l; int err, count = 100; ktime_t t1, t2_curr; - /* Get a snapshot of system clocks to use as historic value. */ - ktime_get_snapshot(&adapter->snapshot); - + /* Doing this in a loop because in the event of a + * badly timed (ha!) system clock adjustment, we may + * get PTM errors from the PCI root, but these errors + * are transitory. Repeating the process returns valid + * data eventually. + */ do { - /* Doing this in a loop because in the event of a - * badly timed (ha!) system clock adjustment, we may - * get PTM errors from the PCI root, but these errors - * are transitory. Repeating the process returns valid - * data eventually. - */ - - /* To "manually" start the PTM cycle we need to clear and - * then set again the TRIG bit. - */ - ctrl = rd32(IGC_PTM_CTRL); - ctrl &= ~IGC_PTM_CTRL_TRIG; - wr32(IGC_PTM_CTRL, ctrl); - ctrl |= IGC_PTM_CTRL_TRIG; - wr32(IGC_PTM_CTRL, ctrl); + /* Get a snapshot of system clocks to use as historic value. */ + ktime_get_snapshot(&adapter->snapshot); - /* The cycle only starts "for real" when software notifies - * that it has read the registers, this is done by setting - * VALID bit. - */ - wr32(IGC_PTM_STAT, IGC_PTM_STAT_VALID); + igc_ptm_trigger(hw); err = readx_poll_timeout(rd32, IGC_PTM_STAT, stat, stat, IGC_PTM_STAT_SLEEP, IGC_PTM_STAT_TIMEOUT); + igc_ptm_reset(hw); + if (err < 0) { netdev_err(adapter->netdev, "Timeout reading IGC_PTM_STAT register\n"); return err; @@ -980,15 +1027,7 @@ static int igc_phc_get_syncdevicetime(ktime_t *device, if ((stat & IGC_PTM_STAT_VALID) == IGC_PTM_STAT_VALID) break; - if (stat & ~IGC_PTM_STAT_VALID) { - /* An error occurred, log it. */ - igc_ptm_log_error(adapter, stat); - /* The STAT register is write-1-to-clear (W1C), - * so write the previous error status to clear it. - */ - wr32(IGC_PTM_STAT, stat); - continue; - } + igc_ptm_log_error(adapter, stat); } while (--count); if (!count) { @@ -1020,9 +1059,16 @@ static int igc_ptp_getcrosststamp(struct ptp_clock_info *ptp, { struct igc_adapter *adapter = container_of(ptp, struct igc_adapter, ptp_caps); + int ret; - return get_device_system_crosststamp(igc_phc_get_syncdevicetime, - adapter, &adapter->snapshot, cts); + /* This blocks until any in progress PTM transactions complete */ + mutex_lock(&adapter->ptm_lock); + + ret = get_device_system_crosststamp(igc_phc_get_syncdevicetime, + adapter, &adapter->snapshot, cts); + mutex_unlock(&adapter->ptm_lock); + + return ret; } static int igc_ptp_getcyclesx64(struct ptp_clock_info *ptp, @@ -1105,6 +1151,9 @@ void igc_ptp_init(struct igc_adapter *adapter) adapter->ptp_caps.pin_config = adapter->sdp_config; adapter->ptp_caps.n_ext_ts = IGC_N_EXTTS; adapter->ptp_caps.n_per_out = IGC_N_PEROUT; + adapter->ptp_caps.supported_extts_flags = PTP_RISING_EDGE | + PTP_FALLING_EDGE | + PTP_STRICT_FLAGS; adapter->ptp_caps.n_pins = IGC_N_SDP; adapter->ptp_caps.verify = igc_ptp_verify_pin; @@ -1121,6 +1170,7 @@ void igc_ptp_init(struct igc_adapter *adapter) spin_lock_init(&adapter->ptp_tx_lock); spin_lock_init(&adapter->free_timer_lock); spin_lock_init(&adapter->tmreg_lock); + mutex_init(&adapter->ptm_lock); adapter->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; adapter->tstamp_config.tx_type = HWTSTAMP_TX_OFF; @@ -1133,6 +1183,7 @@ void igc_ptp_init(struct igc_adapter *adapter) if (IS_ERR(adapter->ptp_clock)) { adapter->ptp_clock = NULL; netdev_err(netdev, "ptp_clock_register failed\n"); + mutex_destroy(&adapter->ptm_lock); } else if (adapter->ptp_clock) { netdev_info(netdev, "PHC added\n"); adapter->ptp_flags |= IGC_PTP_ENABLED; @@ -1162,10 +1213,12 @@ static void igc_ptm_stop(struct igc_adapter *adapter) struct igc_hw *hw = &adapter->hw; u32 ctrl; + mutex_lock(&adapter->ptm_lock); ctrl = rd32(IGC_PTM_CTRL); ctrl &= ~IGC_PTM_CTRL_EN; wr32(IGC_PTM_CTRL, ctrl); + mutex_unlock(&adapter->ptm_lock); } /** @@ -1196,13 +1249,18 @@ void igc_ptp_suspend(struct igc_adapter *adapter) **/ void igc_ptp_stop(struct igc_adapter *adapter) { + if (!(adapter->ptp_flags & IGC_PTP_ENABLED)) + return; + igc_ptp_suspend(adapter); + adapter->ptp_flags &= ~IGC_PTP_ENABLED; if (adapter->ptp_clock) { ptp_clock_unregister(adapter->ptp_clock); netdev_info(adapter->netdev, "PHC removed\n"); adapter->ptp_flags &= ~IGC_PTP_ENABLED; } + mutex_destroy(&adapter->ptm_lock); } /** @@ -1214,13 +1272,18 @@ void igc_ptp_stop(struct igc_adapter *adapter) void igc_ptp_reset(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; - u32 cycle_ctrl, ctrl; + u32 cycle_ctrl, ctrl, stat; unsigned long flags; u32 timadj; + if (!(adapter->ptp_flags & IGC_PTP_ENABLED)) + return; + /* reset the tstamp_config */ igc_ptp_set_timestamp_mode(adapter, &adapter->tstamp_config); + mutex_lock(&adapter->ptm_lock); + spin_lock_irqsave(&adapter->tmreg_lock, flags); switch (adapter->hw.mac.type) { @@ -1249,14 +1312,19 @@ void igc_ptp_reset(struct igc_adapter *adapter) ctrl = IGC_PTM_CTRL_EN | IGC_PTM_CTRL_START_NOW | IGC_PTM_CTRL_SHRT_CYC(IGC_PTM_SHORT_CYC_DEFAULT) | - IGC_PTM_CTRL_PTM_TO(IGC_PTM_TIMEOUT_DEFAULT) | - IGC_PTM_CTRL_TRIG; + IGC_PTM_CTRL_PTM_TO(IGC_PTM_TIMEOUT_DEFAULT); wr32(IGC_PTM_CTRL, ctrl); /* Force the first cycle to run. */ - wr32(IGC_PTM_STAT, IGC_PTM_STAT_VALID); + igc_ptm_trigger(hw); + + if (readx_poll_timeout_atomic(rd32, IGC_PTM_STAT, stat, + stat, IGC_PTM_STAT_SLEEP, + IGC_PTM_STAT_TIMEOUT)) + netdev_err(adapter->netdev, "Timeout reading IGC_PTM_STAT register\n"); + igc_ptm_reset(hw); break; default: /* No work to do. */ @@ -1273,5 +1341,7 @@ void igc_ptp_reset(struct igc_adapter *adapter) out: spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + mutex_unlock(&adapter->ptm_lock); + wrfl(); } diff --git a/drivers/net/ethernet/intel/igc/igc_regs.h b/drivers/net/ethernet/intel/igc/igc_regs.h index d38c87d7e5e8..f343c6bfc6be 100644 --- a/drivers/net/ethernet/intel/igc/igc_regs.h +++ b/drivers/net/ethernet/intel/igc/igc_regs.h @@ -12,6 +12,7 @@ #define IGC_MDIC 0x00020 /* MDI Control - RW */ #define IGC_CONNSW 0x00034 /* Copper/Fiber switch control - RW */ #define IGC_VET 0x00038 /* VLAN Ether Type - RW */ +#define IGC_LEDCTL 0x00E00 /* LED Control - RW */ #define IGC_I225_PHPM 0x00E14 /* I225 PHY Power Management */ #define IGC_GPHY_VERSION 0x0001E /* I225 gPHY Firmware Version */ @@ -221,6 +222,22 @@ #define IGC_FTQF(_n) (0x059E0 + (4 * (_n))) /* 5-tuple Queue Fltr */ +/* Time sync registers - preemption statistics */ +#define IGC_PRMPTDRCNT 0x04284 /* Good RX Preempted Packets */ +#define IGC_PRMEVNTTCNT 0x04298 /* TX Preemption event counter */ +#define IGC_PRMEVNTRCNT 0x0429C /* RX Preemption event counter */ + + /* Preemption Exception Counter */ + #define IGC_PRMEXCPRCNT 0x42A0 +/* Received out of order packets with SMD-C */ +#define IGC_PRMEXCPRCNT_OOO_SMDC 0x000000FF +/* Received out of order packets with SMD-C and wrong Frame CNT */ +#define IGC_PRMEXCPRCNT_OOO_FRAME_CNT 0x0000FF00 +/* Received out of order packets with SMD-C and wrong Frag CNT */ +#define IGC_PRMEXCPRCNT_OOO_FRAG_CNT 0x00FF0000 +/* Received packets with SMD-S and wrong Frag CNT and Frame CNT */ +#define IGC_PRMEXCPRCNT_MISS_FRAME_FRAG_CNT 0xFF000000 + /* Transmit Scheduling Registers */ #define IGC_TQAVCTRL 0x3570 #define IGC_TXQCTL(_n) (0x3344 + 0x4 * (_n)) @@ -237,6 +254,8 @@ #define IGC_TQAVCC(_n) (0x3004 + ((_n) * 0x40)) #define IGC_TQAVHC(_n) (0x300C + ((_n) * 0x40)) +#define IGC_TXARB 0x3354 /* Tx Arbitration Control TxARB - RW */ + /* System Time Registers */ #define IGC_SYSTIML 0x0B600 /* System time register Low - RO */ #define IGC_SYSTIMH 0x0B604 /* System time register High - RO */ @@ -307,6 +326,16 @@ #define IGC_IPCNFG 0x0E38 /* Internal PHY Configuration */ #define IGC_EEE_SU 0x0E34 /* EEE Setup */ +/* MULTI GBT AN Control Register - reg. 7.32 */ +#define IGC_ANEG_MULTIGBT_AN_CTRL 0x0020 + +/* EEE ANeg Advertisement Register - reg 7.60 and reg 7.62 */ +#define IGC_ANEG_EEE_AB1 0x003c +#define IGC_ANEG_EEE_AB2 0x003e +/* EEE ANeg Link-Partner Advertisement Register - reg 7.61 and reg 7.63 */ +#define IGC_ANEG_EEE_LP_AB1 0x003d +#define IGC_ANEG_EEE_LP_AB2 0x003f + /* LTR registers */ #define IGC_LTRC 0x01A0 /* Latency Tolerance Reporting Control */ #define IGC_LTRMINV 0x5BB0 /* LTR Minimum Value */ diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c index 22cefb1eeedf..f22cc4d4f459 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.c +++ b/drivers/net/ethernet/intel/igc/igc_tsn.c @@ -2,9 +2,143 @@ /* Copyright (c) 2019 Intel Corporation */ #include "igc.h" +#include "igc_base.h" #include "igc_hw.h" #include "igc_tsn.h" +#define MIN_MULTPLIER_TX_MIN_FRAG 0 +#define MAX_MULTPLIER_TX_MIN_FRAG 3 +/* Frag size is based on the Section 8.12.2 of the SW User Manual */ +#define TX_MIN_FRAG_SIZE 64 +#define TX_MAX_FRAG_SIZE (TX_MIN_FRAG_SIZE * \ + (MAX_MULTPLIER_TX_MIN_FRAG + 1)) + +DEFINE_STATIC_KEY_FALSE(igc_fpe_enabled); + +static int igc_fpe_init_smd_frame(struct igc_ring *ring, + struct igc_tx_buffer *buffer, + struct sk_buff *skb) +{ + dma_addr_t dma = dma_map_single(ring->dev, skb->data, skb->len, + DMA_TO_DEVICE); + + if (dma_mapping_error(ring->dev, dma)) { + netdev_err_once(ring->netdev, "Failed to map DMA for TX\n"); + return -ENOMEM; + } + + buffer->skb = skb; + buffer->protocol = 0; + buffer->bytecount = skb->len; + buffer->gso_segs = 1; + buffer->time_stamp = jiffies; + dma_unmap_len_set(buffer, len, skb->len); + dma_unmap_addr_set(buffer, dma, dma); + + return 0; +} + +static int igc_fpe_init_tx_descriptor(struct igc_ring *ring, + struct sk_buff *skb, + enum igc_txd_popts_type type) +{ + u32 cmd_type, olinfo_status = 0; + struct igc_tx_buffer *buffer; + union igc_adv_tx_desc *desc; + int err; + + if (!igc_desc_unused(ring)) + return -EBUSY; + + buffer = &ring->tx_buffer_info[ring->next_to_use]; + err = igc_fpe_init_smd_frame(ring, buffer, skb); + if (err) + return err; + + cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT | + IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD | + buffer->bytecount; + + olinfo_status |= FIELD_PREP(IGC_ADVTXD_PAYLEN_MASK, buffer->bytecount); + + switch (type) { + case SMD_V: + case SMD_R: + olinfo_status |= FIELD_PREP(IGC_TXD_POPTS_SMD_MASK, type); + break; + } + + desc = IGC_TX_DESC(ring, ring->next_to_use); + desc->read.cmd_type_len = cpu_to_le32(cmd_type); + desc->read.olinfo_status = cpu_to_le32(olinfo_status); + desc->read.buffer_addr = cpu_to_le64(dma_unmap_addr(buffer, dma)); + + netdev_tx_sent_queue(txring_txq(ring), skb->len); + + buffer->next_to_watch = desc; + ring->next_to_use = (ring->next_to_use + 1) % ring->count; + + return 0; +} + +static int igc_fpe_xmit_smd_frame(struct igc_adapter *adapter, + enum igc_txd_popts_type type) +{ + int cpu = smp_processor_id(); + struct netdev_queue *nq; + struct igc_ring *ring; + struct sk_buff *skb; + int err; + + ring = igc_get_tx_ring(adapter, cpu); + nq = txring_txq(ring); + + skb = alloc_skb(SMD_FRAME_SIZE, GFP_ATOMIC); + if (!skb) + return -ENOMEM; + + skb_put_zero(skb, SMD_FRAME_SIZE); + + __netif_tx_lock(nq, cpu); + + err = igc_fpe_init_tx_descriptor(ring, skb, type); + igc_flush_tx_descriptors(ring); + + __netif_tx_unlock(nq); + + return err; +} + +static void igc_fpe_send_mpacket(struct ethtool_mmsv *mmsv, + enum ethtool_mpacket type) +{ + struct igc_fpe_t *fpe = container_of(mmsv, struct igc_fpe_t, mmsv); + struct igc_adapter *adapter; + int err; + + adapter = container_of(fpe, struct igc_adapter, fpe); + + if (type == ETHTOOL_MPACKET_VERIFY) { + err = igc_fpe_xmit_smd_frame(adapter, SMD_V); + if (err && net_ratelimit()) + netdev_err(adapter->netdev, "Error sending SMD-V\n"); + } else if (type == ETHTOOL_MPACKET_RESPONSE) { + err = igc_fpe_xmit_smd_frame(adapter, SMD_R); + if (err && net_ratelimit()) + netdev_err(adapter->netdev, "Error sending SMD-R frame\n"); + } +} + +static const struct ethtool_mmsv_ops igc_mmsv_ops = { + .send_mpacket = igc_fpe_send_mpacket, +}; + +void igc_fpe_init(struct igc_adapter *adapter) +{ + adapter->fpe.tx_min_frag_size = TX_MIN_FRAG_SIZE; + ethtool_mmsv_init(&adapter->fpe.mmsv, adapter->netdev, &igc_mmsv_ops); +} + static bool is_any_launchtime(struct igc_adapter *adapter) { int i; @@ -37,24 +171,33 @@ static unsigned int igc_tsn_new_flags(struct igc_adapter *adapter) { unsigned int new_flags = adapter->flags & ~IGC_FLAG_TSN_ANY_ENABLED; - if (adapter->taprio_offload_enable) - new_flags |= IGC_FLAG_TSN_QBV_ENABLED; - if (is_any_launchtime(adapter)) + if (adapter->taprio_offload_enable || is_any_launchtime(adapter) || + adapter->strict_priority_enable) new_flags |= IGC_FLAG_TSN_QBV_ENABLED; if (is_cbs_enabled(adapter)) new_flags |= IGC_FLAG_TSN_QAV_ENABLED; + if (adapter->fpe.mmsv.pmac_enabled) + new_flags |= IGC_FLAG_TSN_PREEMPT_ENABLED; + return new_flags; } +static bool igc_tsn_is_tx_mode_in_tsn(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + + return !!(rd32(IGC_TQAVCTRL) & IGC_TQAVCTRL_TRANSMIT_MODE_TSN); +} + void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; u16 txoffset; - if (!is_any_launchtime(adapter)) + if (!igc_tsn_is_tx_mode_in_tsn(adapter)) return; switch (adapter->link_speed) { @@ -78,22 +221,89 @@ void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter) wr32(IGC_GTXOFFSET, txoffset); } +static void igc_tsn_restore_retx_default(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 retxctl; + + retxctl = rd32(IGC_RETX_CTL) & IGC_RETX_CTL_WATERMARK_MASK; + wr32(IGC_RETX_CTL, retxctl); +} + +bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + + return (rd32(IGC_BASET_H) || rd32(IGC_BASET_L)) && + adapter->taprio_offload_enable; +} + +static void igc_tsn_tx_arb(struct igc_adapter *adapter, u16 *queue_per_tc) +{ + struct igc_hw *hw = &adapter->hw; + u32 txarb; + + txarb = rd32(IGC_TXARB); + + txarb &= ~(IGC_TXARB_TXQ_PRIO_0_MASK | + IGC_TXARB_TXQ_PRIO_1_MASK | + IGC_TXARB_TXQ_PRIO_2_MASK | + IGC_TXARB_TXQ_PRIO_3_MASK); + + txarb |= IGC_TXARB_TXQ_PRIO_0(queue_per_tc[3]); + txarb |= IGC_TXARB_TXQ_PRIO_1(queue_per_tc[2]); + txarb |= IGC_TXARB_TXQ_PRIO_2(queue_per_tc[1]); + txarb |= IGC_TXARB_TXQ_PRIO_3(queue_per_tc[0]); + + wr32(IGC_TXARB, txarb); +} + +/** + * igc_tsn_set_rxpbsize - Set the receive packet buffer size + * @adapter: Pointer to the igc_adapter structure + * @rxpbs_exp_bmc_be: Value to set the receive packet buffer size, including + * express buffer, BMC buffer, and Best Effort buffer + * + * The IGC_RXPBS register value may include allocations for the Express buffer, + * BMC buffer, Best Effort buffer, and the timestamp descriptor buffer + * (IGC_RXPBS_CFG_TS_EN). + */ +static void igc_tsn_set_rxpbsize(struct igc_adapter *adapter, + u32 rxpbs_exp_bmc_be) +{ + struct igc_hw *hw = &adapter->hw; + u32 rxpbs = rd32(IGC_RXPBS); + + rxpbs &= ~(IGC_RXPBSIZE_EXP_MASK | IGC_BMC2OSPBSIZE_MASK | + IGC_RXPBSIZE_BE_MASK); + rxpbs |= rxpbs_exp_bmc_be; + + wr32(IGC_RXPBS, rxpbs); +} + /* Returns the TSN specific registers to their default values after * the adapter is reset. */ static int igc_tsn_disable_offload(struct igc_adapter *adapter) { + u16 queue_per_tc[4] = { 3, 2, 1, 0 }; struct igc_hw *hw = &adapter->hw; u32 tqavctrl; int i; wr32(IGC_GTXOFFSET, 0); - wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT); + wr32(IGC_TXPBS, IGC_TXPBSIZE_DEFAULT); wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_DEFAULT); + igc_tsn_set_rxpbsize(adapter, IGC_RXPBSIZE_EXP_BMC_DEFAULT); + + if (igc_is_device_id_i226(hw)) + igc_tsn_restore_retx_default(adapter); + tqavctrl = rd32(IGC_TQAVCTRL); tqavctrl &= ~(IGC_TQAVCTRL_TRANSMIT_MODE_TSN | - IGC_TQAVCTRL_ENHANCED_QAV | IGC_TQAVCTRL_FUTSCDDIS); + IGC_TQAVCTRL_ENHANCED_QAV | IGC_TQAVCTRL_FUTSCDDIS | + IGC_TQAVCTRL_PREEMPT_ENA | IGC_TQAVCTRL_MIN_FRAG_MASK); wr32(IGC_TQAVCTRL, tqavctrl); @@ -106,23 +316,82 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter) wr32(IGC_QBVCYCLET_S, 0); wr32(IGC_QBVCYCLET, NSEC_PER_SEC); + /* Restore the default Tx arbitration: Priority 0 has the highest + * priority and is assigned to queue 0 and so on and so forth. + */ + igc_tsn_tx_arb(adapter, queue_per_tc); + adapter->flags &= ~IGC_FLAG_TSN_QBV_ENABLED; return 0; } +/* To partially fix i226 HW errata, reduce MAC internal buffering from 192 Bytes + * to 88 Bytes by setting RETX_CTL register using the recommendation from: + * a) Ethernet Controller I225/I226 Specification Update Rev 2.1 + * Item 9: TSN: Packet Transmission Might Cross the Qbv Window + * b) I225/6 SW User Manual Rev 1.2.4: Section 8.11.5 Retry Buffer Control + */ +static void igc_tsn_set_retx_qbvfullthreshold(struct igc_adapter *adapter) +{ + struct igc_hw *hw = &adapter->hw; + u32 retxctl, watermark; + + retxctl = rd32(IGC_RETX_CTL); + watermark = retxctl & IGC_RETX_CTL_WATERMARK_MASK; + /* Set QBVFULLTH value using watermark and set QBVFULLEN */ + retxctl |= (watermark << IGC_RETX_CTL_QBVFULLTH_SHIFT) | + IGC_RETX_CTL_QBVFULLEN; + wr32(IGC_RETX_CTL, retxctl); +} + +static u8 igc_fpe_get_frag_size_mult(const struct igc_fpe_t *fpe) +{ + u8 mult = (fpe->tx_min_frag_size / TX_MIN_FRAG_SIZE) - 1; + + return clamp_t(u8, mult, MIN_MULTPLIER_TX_MIN_FRAG, + MAX_MULTPLIER_TX_MIN_FRAG); +} + +u32 igc_fpe_get_supported_frag_size(u32 frag_size) +{ + const u32 supported_sizes[] = {64, 128, 192, 256}; + + /* Find the smallest supported size that is >= frag_size */ + for (int i = 0; i < ARRAY_SIZE(supported_sizes); i++) { + if (frag_size <= supported_sizes[i]) + return supported_sizes[i]; + } + + /* Should not happen */ + return TX_MAX_FRAG_SIZE; +} + static int igc_tsn_enable_offload(struct igc_adapter *adapter) { struct igc_hw *hw = &adapter->hw; u32 tqavctrl, baset_l, baset_h; u32 sec, nsec, cycle; ktime_t base_time, systim; + u32 frag_size_mult; int i; wr32(IGC_TSAUXC, 0); wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_TSN); wr32(IGC_TXPBS, IGC_TXPBSIZE_TSN); + igc_tsn_set_rxpbsize(adapter, IGC_RXPBSIZE_EXP_BMC_BE_TSN); + + if (igc_is_device_id_i226(hw)) + igc_tsn_set_retx_qbvfullthreshold(adapter); + + if (adapter->strict_priority_enable) { + /* Configure queue priorities according to the user provided + * mapping. + */ + igc_tsn_tx_arb(adapter, adapter->queue_per_tc); + } + for (i = 0; i < adapter->num_tx_queues; i++) { struct igc_ring *ring = adapter->tx_ring[i]; u32 txqctl = 0; @@ -245,10 +514,16 @@ skip_cbs: wr32(IGC_TXQCTL(i), txqctl); } - tqavctrl = rd32(IGC_TQAVCTRL) & ~IGC_TQAVCTRL_FUTSCDDIS; - + tqavctrl = rd32(IGC_TQAVCTRL) & ~(IGC_TQAVCTRL_FUTSCDDIS | + IGC_TQAVCTRL_PREEMPT_ENA | IGC_TQAVCTRL_MIN_FRAG_MASK); tqavctrl |= IGC_TQAVCTRL_TRANSMIT_MODE_TSN | IGC_TQAVCTRL_ENHANCED_QAV; + if (adapter->fpe.mmsv.pmac_enabled) + tqavctrl |= IGC_TQAVCTRL_PREEMPT_ENA; + + frag_size_mult = igc_fpe_get_frag_size_mult(&adapter->fpe); + tqavctrl |= FIELD_PREP(IGC_TQAVCTRL_MIN_FRAG_MASK, frag_size_mult); + adapter->qbv_count++; cycle = adapter->cycle_time; @@ -262,14 +537,6 @@ skip_cbs: s64 n = div64_s64(ktime_sub_ns(systim, base_time), cycle); base_time = ktime_add_ns(base_time, (n + 1) * cycle); - - /* Increase the counter if scheduling into the past while - * Gate Control List (GCL) is running. - */ - if ((rd32(IGC_BASET_H) || rd32(IGC_BASET_L)) && - (adapter->tc_setup_type == TC_SETUP_QDISC_TAPRIO) && - (adapter->qbv_count > 1)) - adapter->qbv_config_change_errors++; } else { if (igc_is_device_id_i226(hw)) { ktime_t adjust_time, expires_time; @@ -317,6 +584,14 @@ int igc_tsn_reset(struct igc_adapter *adapter) unsigned int new_flags; int err = 0; + if (adapter->fpe.mmsv.pmac_enabled) { + err = igc_enable_empty_addr_recv(adapter); + if (err && net_ratelimit()) + netdev_err(adapter->netdev, "Error adding empty address to MAC filter\n"); + } else { + igc_disable_empty_addr_recv(adapter); + } + new_flags = igc_tsn_new_flags(adapter); if (!(new_flags & IGC_FLAG_TSN_ANY_ENABLED)) @@ -331,15 +606,22 @@ int igc_tsn_reset(struct igc_adapter *adapter) return err; } -int igc_tsn_offload_apply(struct igc_adapter *adapter) +static bool igc_tsn_will_tx_mode_change(struct igc_adapter *adapter) { - struct igc_hw *hw = &adapter->hw; + bool any_tsn_enabled = !!(igc_tsn_new_flags(adapter) & + IGC_FLAG_TSN_ANY_ENABLED); - /* Per I225/6 HW Design Section 7.5.2.1, transmit mode - * cannot be changed dynamically. Require reset the adapter. + return (any_tsn_enabled && !igc_tsn_is_tx_mode_in_tsn(adapter)) || + (!any_tsn_enabled && igc_tsn_is_tx_mode_in_tsn(adapter)); +} + +int igc_tsn_offload_apply(struct igc_adapter *adapter) +{ + /* Per I225/6 HW Design Section 7.5.2.1 guideline, if tx mode change + * from legacy->tsn or tsn->legacy, then reset adapter is needed. */ if (netif_running(adapter->netdev) && - (igc_is_device_id_i225(hw) || !adapter->qbv_count)) { + igc_tsn_will_tx_mode_change(adapter)) { schedule_work(&adapter->reset_task); return 0; } diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.h b/drivers/net/ethernet/intel/igc/igc_tsn.h index b53e6af560b7..c2a77229207b 100644 --- a/drivers/net/ethernet/intel/igc/igc_tsn.h +++ b/drivers/net/ethernet/intel/igc/igc_tsn.h @@ -4,8 +4,61 @@ #ifndef _IGC_TSN_H_ #define _IGC_TSN_H_ +#define IGC_RX_MIN_FRAG_SIZE 60 +#define SMD_FRAME_SIZE 60 + +enum igc_txd_popts_type { + SMD_V = 0x01, + SMD_R = 0x02, +}; + +DECLARE_STATIC_KEY_FALSE(igc_fpe_enabled); + +void igc_fpe_init(struct igc_adapter *adapter); +u32 igc_fpe_get_supported_frag_size(u32 frag_size); int igc_tsn_offload_apply(struct igc_adapter *adapter); int igc_tsn_reset(struct igc_adapter *adapter); void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter); +bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter); + +static inline bool igc_fpe_is_pmac_enabled(struct igc_adapter *adapter) +{ + return static_branch_unlikely(&igc_fpe_enabled) && + adapter->fpe.mmsv.pmac_enabled; +} + +static inline bool igc_fpe_handle_mpacket(struct igc_adapter *adapter, + union igc_adv_rx_desc *rx_desc, + unsigned int size, void *pktbuf) +{ + u32 status_error = le32_to_cpu(rx_desc->wb.upper.status_error); + int smd; + + smd = FIELD_GET(IGC_RXDADV_STAT_SMD_TYPE_MASK, status_error); + if (smd != IGC_RXD_STAT_SMD_TYPE_V && smd != IGC_RXD_STAT_SMD_TYPE_R) + return false; + + if (size == SMD_FRAME_SIZE && mem_is_zero(pktbuf, SMD_FRAME_SIZE)) { + struct ethtool_mmsv *mmsv = &adapter->fpe.mmsv; + enum ethtool_mmsv_event event; + + if (smd == IGC_RXD_STAT_SMD_TYPE_V) + event = ETHTOOL_MMSV_LP_SENT_VERIFY_MPACKET; + else + event = ETHTOOL_MMSV_LP_SENT_RESPONSE_MPACKET; + + ethtool_mmsv_event_handle(mmsv, event); + } + + return true; +} + +static inline bool igc_fpe_transmitted_smd_v(union igc_adv_tx_desc *tx_desc) +{ + u32 olinfo_status = le32_to_cpu(tx_desc->read.olinfo_status); + u8 smd = FIELD_GET(IGC_TXD_POPTS_SMD_MASK, olinfo_status); + + return smd == SMD_V; +} #endif /* _IGC_BASE_H */ diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.c b/drivers/net/ethernet/intel/igc/igc_xdp.c index e27af72aada8..9eb47b4beb06 100644 --- a/drivers/net/ethernet/intel/igc/igc_xdp.c +++ b/drivers/net/ethernet/intel/igc/igc_xdp.c @@ -13,6 +13,8 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, struct net_device *dev = adapter->netdev; bool if_running = netif_running(dev); struct bpf_prog *old_prog; + bool need_update; + unsigned int i; if (dev->mtu > ETH_DATA_LEN) { /* For now, the driver doesn't support XDP functionality with @@ -22,8 +24,14 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, return -EOPNOTSUPP; } - if (if_running) - igc_close(dev); + need_update = !!adapter->xdp_prog != !!prog; + if (if_running && need_update) { + for (i = 0; i < adapter->num_rx_queues; i++) { + igc_disable_rx_ring(adapter->rx_ring[i]); + igc_disable_tx_ring(adapter->tx_ring[i]); + napi_disable(&adapter->rx_ring[i]->q_vector->napi); + } + } old_prog = xchg(&adapter->xdp_prog, prog); if (old_prog) @@ -34,8 +42,13 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog, else xdp_features_clear_redirect_target(dev); - if (if_running) - igc_open(dev); + if (if_running && need_update) { + for (i = 0; i < adapter->num_rx_queues; i++) { + napi_enable(&adapter->rx_ring[i]->q_vector->napi); + igc_enable_tx_ring(adapter->tx_ring[i]); + igc_enable_rx_ring(adapter->rx_ring[i]); + } + } return 0; } |