diff options
Diffstat (limited to 'drivers/net/ethernet/intel/iavf')
| -rw-r--r-- | drivers/net/ethernet/intel/iavf/Makefile | 7 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/iavf/iavf.h | 90 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/iavf/iavf_common.c | 253 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/iavf/iavf_ethtool.c | 201 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/iavf/iavf_fdir.c | 89 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/iavf/iavf_fdir.h | 13 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/iavf/iavf_main.c | 679 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/iavf/iavf_prototype.h | 10 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/iavf/iavf_ptp.c | 485 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/iavf/iavf_ptp.h | 47 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/iavf/iavf_trace.h | 12 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/iavf/iavf_txrx.c | 932 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/iavf/iavf_txrx.h | 168 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/iavf/iavf_type.h | 329 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/iavf/iavf_types.h | 34 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/iavf/iavf_virtchnl.c | 400 |
16 files changed, 2281 insertions, 1468 deletions
diff --git a/drivers/net/ethernet/intel/iavf/Makefile b/drivers/net/ethernet/intel/iavf/Makefile index 2d154a4e2fd7..e13720a728ff 100644 --- a/drivers/net/ethernet/intel/iavf/Makefile +++ b/drivers/net/ethernet/intel/iavf/Makefile @@ -11,6 +11,7 @@ subdir-ccflags-y += -I$(src) obj-$(CONFIG_IAVF) += iavf.o -iavf-objs := iavf_main.o iavf_ethtool.o iavf_virtchnl.o iavf_fdir.o \ - iavf_adv_rss.o \ - iavf_txrx.o iavf_common.o iavf_adminq.o +iavf-y := iavf_main.o iavf_ethtool.o iavf_virtchnl.o iavf_fdir.o \ + iavf_adv_rss.o iavf_txrx.o iavf_common.o iavf_adminq.o + +iavf-$(CONFIG_PTP_1588_CLOCK) += iavf_ptp.o diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index db8188c7ac4b..9de3e0ba3731 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -33,12 +33,15 @@ #include <net/udp.h> #include <net/tc_act/tc_gact.h> #include <net/tc_act/tc_mirred.h> +#include <net/tc_act/tc_skbedit.h> +#include <net/net_shaper.h> #include "iavf_type.h" #include <linux/avf/virtchnl.h> #include "iavf_txrx.h" #include "iavf_fdir.h" #include "iavf_adv_rss.h" +#include "iavf_types.h" #include <linux/bitmap.h> #define DEFAULT_DEBUG_LEVEL_SHIFT 3 @@ -80,7 +83,7 @@ struct iavf_vsi { #define MAXIMUM_ETHERNET_VLAN_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN) -#define IAVF_RX_DESC(R, i) (&(((union iavf_32byte_rx_desc *)((R)->desc))[i])) +#define IAVF_RX_DESC(R, i) (&(((struct iavf_rx_desc *)((R)->desc))[i])) #define IAVF_TX_DESC(R, i) (&(((struct iavf_tx_desc *)((R)->desc))[i])) #define IAVF_TX_CTXTDESC(R, i) \ (&(((struct iavf_tx_context_desc *)((R)->desc))[i])) @@ -249,6 +252,9 @@ struct iavf_cloud_filter { #define IAVF_RESET_WAIT_DETECTED_COUNT 500 #define IAVF_RESET_WAIT_COMPLETE_COUNT 2000 +#define IAVF_MAX_QOS_TC_NUM 8 +#define IAVF_DEFAULT_QUANTA_SIZE 1024 + /* board specific private data structure */ struct iavf_adapter { struct workqueue_struct *wq; @@ -266,6 +272,7 @@ struct iavf_adapter { /* Lock to protect accesses to MAC and VLAN lists */ spinlock_t mac_vlan_list_lock; char misc_vector_name[IFNAMSIZ + 9]; + u8 rxdid; int num_active_queues; int num_req_queues; @@ -287,7 +294,7 @@ struct iavf_adapter { #define IAVF_FLAG_RESET_PENDING BIT(4) #define IAVF_FLAG_RESET_NEEDED BIT(5) #define IAVF_FLAG_WB_ON_ITR_CAPABLE BIT(6) -#define IAVF_FLAG_LEGACY_RX BIT(15) +/* BIT(15) is free, was IAVF_FLAG_LEGACY_RX */ #define IAVF_FLAG_REINIT_ITR_NEEDED BIT(16) #define IAVF_FLAG_QUEUES_DISABLED BIT(17) #define IAVF_FLAG_SETUP_NETDEV_FEATURES BIT(18) @@ -335,6 +342,20 @@ struct iavf_adapter { #define IAVF_FLAG_AQ_DISABLE_CTAG_VLAN_INSERTION BIT_ULL(36) #define IAVF_FLAG_AQ_ENABLE_STAG_VLAN_INSERTION BIT_ULL(37) #define IAVF_FLAG_AQ_DISABLE_STAG_VLAN_INSERTION BIT_ULL(38) +#define IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW BIT_ULL(39) +#define IAVF_FLAG_AQ_CFG_QUEUES_QUANTA_SIZE BIT_ULL(40) +#define IAVF_FLAG_AQ_GET_QOS_CAPS BIT_ULL(41) +#define IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS BIT_ULL(42) +#define IAVF_FLAG_AQ_GET_PTP_CAPS BIT_ULL(43) +#define IAVF_FLAG_AQ_SEND_PTP_CMD BIT_ULL(44) + + /* AQ messages that must be sent after IAVF_FLAG_AQ_GET_CONFIG, in + * order to negotiated extended capabilities. + */ +#define IAVF_FLAG_AQ_EXTENDED_CAPS \ + (IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS | \ + IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS | \ + IAVF_FLAG_AQ_GET_PTP_CAPS) /* flags for processing extended capability messages during * __IAVF_INIT_EXTENDED_CAPS. Each capability exchange requires @@ -346,10 +367,18 @@ struct iavf_adapter { u64 extended_caps; #define IAVF_EXTENDED_CAP_SEND_VLAN_V2 BIT_ULL(0) #define IAVF_EXTENDED_CAP_RECV_VLAN_V2 BIT_ULL(1) +#define IAVF_EXTENDED_CAP_SEND_RXDID BIT_ULL(2) +#define IAVF_EXTENDED_CAP_RECV_RXDID BIT_ULL(3) +#define IAVF_EXTENDED_CAP_SEND_PTP BIT_ULL(4) +#define IAVF_EXTENDED_CAP_RECV_PTP BIT_ULL(5) #define IAVF_EXTENDED_CAPS \ (IAVF_EXTENDED_CAP_SEND_VLAN_V2 | \ - IAVF_EXTENDED_CAP_RECV_VLAN_V2) + IAVF_EXTENDED_CAP_RECV_VLAN_V2 | \ + IAVF_EXTENDED_CAP_SEND_RXDID | \ + IAVF_EXTENDED_CAP_RECV_RXDID | \ + IAVF_EXTENDED_CAP_SEND_PTP | \ + IAVF_EXTENDED_CAP_RECV_PTP) /* Lock to prevent possible clobbering of * current_netdev_promisc_flags @@ -393,6 +422,8 @@ struct iavf_adapter { VIRTCHNL_VF_OFFLOAD_VLAN_V2) #define CRC_OFFLOAD_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \ VIRTCHNL_VF_OFFLOAD_CRC) +#define TC_U32_SUPPORT(_a) ((_a)->vf_res->vf_cap_flags & \ + VIRTCHNL_VF_OFFLOAD_TC_U32) #define VLAN_V2_FILTERING_ALLOWED(_a) \ (VLAN_V2_ALLOWED((_a)) && \ ((_a)->vlan_v2_caps.filtering.filtering_support.outer || \ @@ -405,14 +436,23 @@ struct iavf_adapter { VIRTCHNL_VF_OFFLOAD_FDIR_PF) #define ADV_RSS_SUPPORT(_a) ((_a)->vf_res->vf_cap_flags & \ VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF) +#define QOS_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \ + VIRTCHNL_VF_OFFLOAD_QOS) +#define IAVF_RXDID_ALLOWED(a) \ + ((a)->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) +#define IAVF_PTP_ALLOWED(a) \ + ((a)->vf_res->vf_cap_flags & VIRTCHNL_VF_CAP_PTP) struct virtchnl_vf_resource *vf_res; /* incl. all VSIs */ struct virtchnl_vsi_resource *vsi_res; /* our LAN VSI */ struct virtchnl_version_info pf_version; #define PF_IS_V11(_a) (((_a)->pf_version.major == 1) && \ ((_a)->pf_version.minor == 1)) struct virtchnl_vlan_caps vlan_v2_caps; + u64 supp_rxdids; + struct iavf_ptp ptp; u16 msg_enable; struct iavf_eth_stats current_stats; + struct virtchnl_qos_cap_list *qos_caps; struct iavf_vsi vsi; u32 aq_wait_count; /* RSS stuff */ @@ -437,6 +477,7 @@ struct iavf_adapter { #define IAVF_MAX_FDIR_FILTERS 128 /* max allowed Flow Director filters */ u16 fdir_active_fltr; + u16 raw_fdir_active_fltr; struct list_head fdir_list_head; spinlock_t fdir_fltr_lock; /* protect the Flow Director filter list */ @@ -444,6 +485,32 @@ struct iavf_adapter { spinlock_t adv_rss_lock; /* protect the RSS management list */ }; +/* Must be called with fdir_fltr_lock lock held */ +static inline bool iavf_fdir_max_reached(struct iavf_adapter *adapter) +{ + return adapter->fdir_active_fltr + adapter->raw_fdir_active_fltr >= + IAVF_MAX_FDIR_FILTERS; +} + +static inline void +iavf_inc_fdir_active_fltr(struct iavf_adapter *adapter, + struct iavf_fdir_fltr *fltr) +{ + if (iavf_is_raw_fdir(fltr)) + adapter->raw_fdir_active_fltr++; + else + adapter->fdir_active_fltr++; +} + +static inline void +iavf_dec_fdir_active_fltr(struct iavf_adapter *adapter, + struct iavf_fdir_fltr *fltr) +{ + if (iavf_is_raw_fdir(fltr)) + adapter->raw_fdir_active_fltr--; + else + adapter->fdir_active_fltr--; +} /* Ethtool Private Flags */ @@ -499,37 +566,33 @@ static inline void iavf_change_state(struct iavf_adapter *adapter, iavf_state_str(adapter->state)); } -int iavf_up(struct iavf_adapter *adapter); void iavf_down(struct iavf_adapter *adapter); int iavf_process_config(struct iavf_adapter *adapter); int iavf_parse_vf_resource_msg(struct iavf_adapter *adapter); void iavf_schedule_reset(struct iavf_adapter *adapter, u64 flags); void iavf_schedule_aq_request(struct iavf_adapter *adapter, u64 flags); void iavf_schedule_finish_config(struct iavf_adapter *adapter); -void iavf_reset(struct iavf_adapter *adapter); void iavf_set_ethtool_ops(struct net_device *netdev); -void iavf_update_stats(struct iavf_adapter *adapter); void iavf_free_all_tx_resources(struct iavf_adapter *adapter); void iavf_free_all_rx_resources(struct iavf_adapter *adapter); -void iavf_napi_add_all(struct iavf_adapter *adapter); -void iavf_napi_del_all(struct iavf_adapter *adapter); - int iavf_send_api_ver(struct iavf_adapter *adapter); int iavf_verify_api_ver(struct iavf_adapter *adapter); int iavf_send_vf_config_msg(struct iavf_adapter *adapter); int iavf_get_vf_config(struct iavf_adapter *adapter); int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter); int iavf_send_vf_offload_vlan_v2_msg(struct iavf_adapter *adapter); +int iavf_send_vf_supported_rxdids_msg(struct iavf_adapter *adapter); +int iavf_get_vf_supported_rxdids(struct iavf_adapter *adapter); +int iavf_send_vf_ptp_caps_msg(struct iavf_adapter *adapter); +int iavf_get_vf_ptp_caps(struct iavf_adapter *adapter); void iavf_set_queue_vlan_tag_loc(struct iavf_adapter *adapter); u16 iavf_get_num_vlans_added(struct iavf_adapter *adapter); void iavf_irq_enable(struct iavf_adapter *adapter, bool flush); void iavf_configure_queues(struct iavf_adapter *adapter); -void iavf_deconfigure_queues(struct iavf_adapter *adapter); void iavf_enable_queues(struct iavf_adapter *adapter); void iavf_disable_queues(struct iavf_adapter *adapter); void iavf_map_queues(struct iavf_adapter *adapter); -int iavf_request_queues(struct iavf_adapter *adapter, int num); void iavf_add_ether_addrs(struct iavf_adapter *adapter); void iavf_del_ether_addrs(struct iavf_adapter *adapter); void iavf_add_vlans(struct iavf_adapter *adapter); @@ -549,8 +612,9 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, enum virtchnl_ops v_opcode, enum iavf_status v_retval, u8 *msg, u16 msglen); int iavf_config_rss(struct iavf_adapter *adapter); -int iavf_lan_add_device(struct iavf_adapter *adapter); -int iavf_lan_del_device(struct iavf_adapter *adapter); +void iavf_cfg_queues_bw(struct iavf_adapter *adapter); +void iavf_cfg_queues_quanta_size(struct iavf_adapter *adapter); +void iavf_get_qos_caps(struct iavf_adapter *adapter); void iavf_enable_channels(struct iavf_adapter *adapter); void iavf_disable_channels(struct iavf_adapter *adapter); void iavf_add_cloud_filter(struct iavf_adapter *adapter); diff --git a/drivers/net/ethernet/intel/iavf/iavf_common.c b/drivers/net/ethernet/intel/iavf/iavf_common.c index 5a25233a89d5..aa751ce3425b 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_common.c +++ b/drivers/net/ethernet/intel/iavf/iavf_common.c @@ -432,259 +432,6 @@ enum iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 vsi_id, return iavf_aq_get_set_rss_key(hw, vsi_id, key, true); } -/* The iavf_ptype_lookup table is used to convert from the 8-bit ptype in the - * hardware to a bit-field that can be used by SW to more easily determine the - * packet type. - * - * Macros are used to shorten the table lines and make this table human - * readable. - * - * We store the PTYPE in the top byte of the bit field - this is just so that - * we can check that the table doesn't have a row missing, as the index into - * the table should be the PTYPE. - * - * Typical work flow: - * - * IF NOT iavf_ptype_lookup[ptype].known - * THEN - * Packet is unknown - * ELSE IF iavf_ptype_lookup[ptype].outer_ip == IAVF_RX_PTYPE_OUTER_IP - * Use the rest of the fields to look at the tunnels, inner protocols, etc - * ELSE - * Use the enum iavf_rx_l2_ptype to decode the packet type - * ENDIF - */ - -/* macro to make the table lines short, use explicit indexing with [PTYPE] */ -#define IAVF_PTT(PTYPE, OUTER_IP, OUTER_IP_VER, OUTER_FRAG, T, TE, TEF, I, PL)\ - [PTYPE] = { \ - 1, \ - IAVF_RX_PTYPE_OUTER_##OUTER_IP, \ - IAVF_RX_PTYPE_OUTER_##OUTER_IP_VER, \ - IAVF_RX_PTYPE_##OUTER_FRAG, \ - IAVF_RX_PTYPE_TUNNEL_##T, \ - IAVF_RX_PTYPE_TUNNEL_END_##TE, \ - IAVF_RX_PTYPE_##TEF, \ - IAVF_RX_PTYPE_INNER_PROT_##I, \ - IAVF_RX_PTYPE_PAYLOAD_LAYER_##PL } - -#define IAVF_PTT_UNUSED_ENTRY(PTYPE) [PTYPE] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 } - -/* shorter macros makes the table fit but are terse */ -#define IAVF_RX_PTYPE_NOF IAVF_RX_PTYPE_NOT_FRAG -#define IAVF_RX_PTYPE_FRG IAVF_RX_PTYPE_FRAG -#define IAVF_RX_PTYPE_INNER_PROT_TS IAVF_RX_PTYPE_INNER_PROT_TIMESYNC - -/* Lookup table mapping the 8-bit HW PTYPE to the bit field for decoding */ -struct iavf_rx_ptype_decoded iavf_ptype_lookup[BIT(8)] = { - /* L2 Packet types */ - IAVF_PTT_UNUSED_ENTRY(0), - IAVF_PTT(1, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - IAVF_PTT(2, L2, NONE, NOF, NONE, NONE, NOF, TS, PAY2), - IAVF_PTT(3, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - IAVF_PTT_UNUSED_ENTRY(4), - IAVF_PTT_UNUSED_ENTRY(5), - IAVF_PTT(6, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - IAVF_PTT(7, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - IAVF_PTT_UNUSED_ENTRY(8), - IAVF_PTT_UNUSED_ENTRY(9), - IAVF_PTT(10, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY2), - IAVF_PTT(11, L2, NONE, NOF, NONE, NONE, NOF, NONE, NONE), - IAVF_PTT(12, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(13, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(14, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(15, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(16, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(17, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(18, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(19, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(20, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(21, L2, NONE, NOF, NONE, NONE, NOF, NONE, PAY3), - - /* Non Tunneled IPv4 */ - IAVF_PTT(22, IP, IPV4, FRG, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(23, IP, IPV4, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(24, IP, IPV4, NOF, NONE, NONE, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(25), - IAVF_PTT(26, IP, IPV4, NOF, NONE, NONE, NOF, TCP, PAY4), - IAVF_PTT(27, IP, IPV4, NOF, NONE, NONE, NOF, SCTP, PAY4), - IAVF_PTT(28, IP, IPV4, NOF, NONE, NONE, NOF, ICMP, PAY4), - - /* IPv4 --> IPv4 */ - IAVF_PTT(29, IP, IPV4, NOF, IP_IP, IPV4, FRG, NONE, PAY3), - IAVF_PTT(30, IP, IPV4, NOF, IP_IP, IPV4, NOF, NONE, PAY3), - IAVF_PTT(31, IP, IPV4, NOF, IP_IP, IPV4, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(32), - IAVF_PTT(33, IP, IPV4, NOF, IP_IP, IPV4, NOF, TCP, PAY4), - IAVF_PTT(34, IP, IPV4, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), - IAVF_PTT(35, IP, IPV4, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), - - /* IPv4 --> IPv6 */ - IAVF_PTT(36, IP, IPV4, NOF, IP_IP, IPV6, FRG, NONE, PAY3), - IAVF_PTT(37, IP, IPV4, NOF, IP_IP, IPV6, NOF, NONE, PAY3), - IAVF_PTT(38, IP, IPV4, NOF, IP_IP, IPV6, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(39), - IAVF_PTT(40, IP, IPV4, NOF, IP_IP, IPV6, NOF, TCP, PAY4), - IAVF_PTT(41, IP, IPV4, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), - IAVF_PTT(42, IP, IPV4, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT */ - IAVF_PTT(43, IP, IPV4, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), - - /* IPv4 --> GRE/NAT --> IPv4 */ - IAVF_PTT(44, IP, IPV4, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), - IAVF_PTT(45, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), - IAVF_PTT(46, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(47), - IAVF_PTT(48, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), - IAVF_PTT(49, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), - IAVF_PTT(50, IP, IPV4, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT --> IPv6 */ - IAVF_PTT(51, IP, IPV4, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), - IAVF_PTT(52, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), - IAVF_PTT(53, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(54), - IAVF_PTT(55, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), - IAVF_PTT(56, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), - IAVF_PTT(57, IP, IPV4, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT --> MAC */ - IAVF_PTT(58, IP, IPV4, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), - - /* IPv4 --> GRE/NAT --> MAC --> IPv4 */ - IAVF_PTT(59, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), - IAVF_PTT(60, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), - IAVF_PTT(61, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(62), - IAVF_PTT(63, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), - IAVF_PTT(64, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), - IAVF_PTT(65, IP, IPV4, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT -> MAC --> IPv6 */ - IAVF_PTT(66, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), - IAVF_PTT(67, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), - IAVF_PTT(68, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(69), - IAVF_PTT(70, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), - IAVF_PTT(71, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), - IAVF_PTT(72, IP, IPV4, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), - - /* IPv4 --> GRE/NAT --> MAC/VLAN */ - IAVF_PTT(73, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), - - /* IPv4 ---> GRE/NAT -> MAC/VLAN --> IPv4 */ - IAVF_PTT(74, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), - IAVF_PTT(75, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), - IAVF_PTT(76, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(77), - IAVF_PTT(78, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), - IAVF_PTT(79, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), - IAVF_PTT(80, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), - - /* IPv4 -> GRE/NAT -> MAC/VLAN --> IPv6 */ - IAVF_PTT(81, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), - IAVF_PTT(82, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), - IAVF_PTT(83, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(84), - IAVF_PTT(85, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), - IAVF_PTT(86, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), - IAVF_PTT(87, IP, IPV4, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), - - /* Non Tunneled IPv6 */ - IAVF_PTT(88, IP, IPV6, FRG, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(89, IP, IPV6, NOF, NONE, NONE, NOF, NONE, PAY3), - IAVF_PTT(90, IP, IPV6, NOF, NONE, NONE, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(91), - IAVF_PTT(92, IP, IPV6, NOF, NONE, NONE, NOF, TCP, PAY4), - IAVF_PTT(93, IP, IPV6, NOF, NONE, NONE, NOF, SCTP, PAY4), - IAVF_PTT(94, IP, IPV6, NOF, NONE, NONE, NOF, ICMP, PAY4), - - /* IPv6 --> IPv4 */ - IAVF_PTT(95, IP, IPV6, NOF, IP_IP, IPV4, FRG, NONE, PAY3), - IAVF_PTT(96, IP, IPV6, NOF, IP_IP, IPV4, NOF, NONE, PAY3), - IAVF_PTT(97, IP, IPV6, NOF, IP_IP, IPV4, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(98), - IAVF_PTT(99, IP, IPV6, NOF, IP_IP, IPV4, NOF, TCP, PAY4), - IAVF_PTT(100, IP, IPV6, NOF, IP_IP, IPV4, NOF, SCTP, PAY4), - IAVF_PTT(101, IP, IPV6, NOF, IP_IP, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> IPv6 */ - IAVF_PTT(102, IP, IPV6, NOF, IP_IP, IPV6, FRG, NONE, PAY3), - IAVF_PTT(103, IP, IPV6, NOF, IP_IP, IPV6, NOF, NONE, PAY3), - IAVF_PTT(104, IP, IPV6, NOF, IP_IP, IPV6, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(105), - IAVF_PTT(106, IP, IPV6, NOF, IP_IP, IPV6, NOF, TCP, PAY4), - IAVF_PTT(107, IP, IPV6, NOF, IP_IP, IPV6, NOF, SCTP, PAY4), - IAVF_PTT(108, IP, IPV6, NOF, IP_IP, IPV6, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT */ - IAVF_PTT(109, IP, IPV6, NOF, IP_GRENAT, NONE, NOF, NONE, PAY3), - - /* IPv6 --> GRE/NAT -> IPv4 */ - IAVF_PTT(110, IP, IPV6, NOF, IP_GRENAT, IPV4, FRG, NONE, PAY3), - IAVF_PTT(111, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, NONE, PAY3), - IAVF_PTT(112, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(113), - IAVF_PTT(114, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, TCP, PAY4), - IAVF_PTT(115, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, SCTP, PAY4), - IAVF_PTT(116, IP, IPV6, NOF, IP_GRENAT, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> IPv6 */ - IAVF_PTT(117, IP, IPV6, NOF, IP_GRENAT, IPV6, FRG, NONE, PAY3), - IAVF_PTT(118, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, NONE, PAY3), - IAVF_PTT(119, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(120), - IAVF_PTT(121, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, TCP, PAY4), - IAVF_PTT(122, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, SCTP, PAY4), - IAVF_PTT(123, IP, IPV6, NOF, IP_GRENAT, IPV6, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC */ - IAVF_PTT(124, IP, IPV6, NOF, IP_GRENAT_MAC, NONE, NOF, NONE, PAY3), - - /* IPv6 --> GRE/NAT -> MAC -> IPv4 */ - IAVF_PTT(125, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, FRG, NONE, PAY3), - IAVF_PTT(126, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, NONE, PAY3), - IAVF_PTT(127, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(128), - IAVF_PTT(129, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, TCP, PAY4), - IAVF_PTT(130, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, SCTP, PAY4), - IAVF_PTT(131, IP, IPV6, NOF, IP_GRENAT_MAC, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC -> IPv6 */ - IAVF_PTT(132, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, FRG, NONE, PAY3), - IAVF_PTT(133, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, NONE, PAY3), - IAVF_PTT(134, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(135), - IAVF_PTT(136, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, TCP, PAY4), - IAVF_PTT(137, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, SCTP, PAY4), - IAVF_PTT(138, IP, IPV6, NOF, IP_GRENAT_MAC, IPV6, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC/VLAN */ - IAVF_PTT(139, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, NONE, NOF, NONE, PAY3), - - /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv4 */ - IAVF_PTT(140, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, FRG, NONE, PAY3), - IAVF_PTT(141, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, NONE, PAY3), - IAVF_PTT(142, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(143), - IAVF_PTT(144, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, TCP, PAY4), - IAVF_PTT(145, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, SCTP, PAY4), - IAVF_PTT(146, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV4, NOF, ICMP, PAY4), - - /* IPv6 --> GRE/NAT -> MAC/VLAN --> IPv6 */ - IAVF_PTT(147, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, FRG, NONE, PAY3), - IAVF_PTT(148, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, NONE, PAY3), - IAVF_PTT(149, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, UDP, PAY4), - IAVF_PTT_UNUSED_ENTRY(150), - IAVF_PTT(151, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, TCP, PAY4), - IAVF_PTT(152, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, SCTP, PAY4), - IAVF_PTT(153, IP, IPV6, NOF, IP_GRENAT_MAC_VLAN, IPV6, NOF, ICMP, PAY4), - - /* unused entries */ - [154 ... 255] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 } -}; - /** * iavf_aq_send_msg_to_pf * @hw: pointer to the hardware structure diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 378c3e9ddf9d..288bb5b2e72e 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -240,29 +240,6 @@ static const struct iavf_stats iavf_gstrings_stats[] = { #define IAVF_QUEUE_STATS_LEN ARRAY_SIZE(iavf_gstrings_queue_stats) -/* For now we have one and only one private flag and it is only defined - * when we have support for the SKIP_CPU_SYNC DMA attribute. Instead - * of leaving all this code sitting around empty we will strip it unless - * our one private flag is actually available. - */ -struct iavf_priv_flags { - char flag_string[ETH_GSTRING_LEN]; - u32 flag; - bool read_only; -}; - -#define IAVF_PRIV_FLAG(_name, _flag, _read_only) { \ - .flag_string = _name, \ - .flag = _flag, \ - .read_only = _read_only, \ -} - -static const struct iavf_priv_flags iavf_gstrings_priv_flags[] = { - IAVF_PRIV_FLAG("legacy-rx", IAVF_FLAG_LEGACY_RX, 0), -}; - -#define IAVF_PRIV_FLAGS_STR_LEN ARRAY_SIZE(iavf_gstrings_priv_flags) - /** * iavf_get_link_ksettings - Get Link Speed and Duplex settings * @netdev: network interface device structure @@ -342,8 +319,6 @@ static int iavf_get_sset_count(struct net_device *netdev, int sset) return IAVF_STATS_LEN + (IAVF_QUEUE_STATS_LEN * 2 * netdev->real_num_tx_queues); - else if (sset == ETH_SS_PRIV_FLAGS) - return IAVF_PRIV_FLAGS_STR_LEN; else return -EINVAL; } @@ -386,21 +361,6 @@ static void iavf_get_ethtool_stats(struct net_device *netdev, } /** - * iavf_get_priv_flag_strings - Get private flag strings - * @netdev: network interface device structure - * @data: buffer for string data - * - * Builds the private flags string table - **/ -static void iavf_get_priv_flag_strings(struct net_device *netdev, u8 *data) -{ - unsigned int i; - - for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) - ethtool_puts(&data, iavf_gstrings_priv_flags[i].flag_string); -} - -/** * iavf_get_stat_strings - Get stat strings * @netdev: network interface device structure * @data: buffer for string data @@ -438,109 +398,12 @@ static void iavf_get_strings(struct net_device *netdev, u32 sset, u8 *data) case ETH_SS_STATS: iavf_get_stat_strings(netdev, data); break; - case ETH_SS_PRIV_FLAGS: - iavf_get_priv_flag_strings(netdev, data); - break; default: break; } } /** - * iavf_get_priv_flags - report device private flags - * @netdev: network interface device structure - * - * The get string set count and the string set should be matched for each - * flag returned. Add new strings for each flag to the iavf_gstrings_priv_flags - * array. - * - * Returns a u32 bitmap of flags. - **/ -static u32 iavf_get_priv_flags(struct net_device *netdev) -{ - struct iavf_adapter *adapter = netdev_priv(netdev); - u32 i, ret_flags = 0; - - for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) { - const struct iavf_priv_flags *priv_flags; - - priv_flags = &iavf_gstrings_priv_flags[i]; - - if (priv_flags->flag & adapter->flags) - ret_flags |= BIT(i); - } - - return ret_flags; -} - -/** - * iavf_set_priv_flags - set private flags - * @netdev: network interface device structure - * @flags: bit flags to be set - **/ -static int iavf_set_priv_flags(struct net_device *netdev, u32 flags) -{ - struct iavf_adapter *adapter = netdev_priv(netdev); - u32 orig_flags, new_flags, changed_flags; - int ret = 0; - u32 i; - - orig_flags = READ_ONCE(adapter->flags); - new_flags = orig_flags; - - for (i = 0; i < IAVF_PRIV_FLAGS_STR_LEN; i++) { - const struct iavf_priv_flags *priv_flags; - - priv_flags = &iavf_gstrings_priv_flags[i]; - - if (flags & BIT(i)) - new_flags |= priv_flags->flag; - else - new_flags &= ~(priv_flags->flag); - - if (priv_flags->read_only && - ((orig_flags ^ new_flags) & ~BIT(i))) - return -EOPNOTSUPP; - } - - /* Before we finalize any flag changes, any checks which we need to - * perform to determine if the new flags will be supported should go - * here... - */ - - /* Compare and exchange the new flags into place. If we failed, that - * is if cmpxchg returns anything but the old value, this means - * something else must have modified the flags variable since we - * copied it. We'll just punt with an error and log something in the - * message buffer. - */ - if (cmpxchg(&adapter->flags, orig_flags, new_flags) != orig_flags) { - dev_warn(&adapter->pdev->dev, - "Unable to update adapter->flags as it was modified by another thread...\n"); - return -EAGAIN; - } - - changed_flags = orig_flags ^ new_flags; - - /* Process any additional changes needed as a result of flag changes. - * The changed_flags value reflects the list of bits that were changed - * in the code above. - */ - - /* issue a reset to force legacy-rx change to take effect */ - if (changed_flags & IAVF_FLAG_LEGACY_RX) { - if (netif_running(netdev)) { - iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); - ret = iavf_wait_for_reset(adapter); - if (ret) - netdev_warn(netdev, "Changing private flags timeout or interrupted waiting for reset"); - } - } - - return ret; -} - -/** * iavf_get_msglevel - Get debug message level * @netdev: network interface device structure * @@ -585,7 +448,6 @@ static void iavf_get_drvinfo(struct net_device *netdev, strscpy(drvinfo->driver, iavf_driver_name, 32); strscpy(drvinfo->fw_version, "N/A", 4); strscpy(drvinfo->bus_info, pci_name(adapter->pdev), 32); - drvinfo->n_priv_flags = IAVF_PRIV_FLAGS_STR_LEN; } /** @@ -1065,7 +927,7 @@ iavf_get_ethtool_fdir_entry(struct iavf_adapter *adapter, spin_lock_bh(&adapter->fdir_fltr_lock); - rule = iavf_find_fdir_fltr_by_loc(adapter, fsp->location); + rule = iavf_find_fdir_fltr(adapter, false, fsp->location); if (!rule) { ret = -EINVAL; goto release_lock; @@ -1210,6 +1072,9 @@ iavf_get_fdir_fltr_ids(struct iavf_adapter *adapter, struct ethtool_rxnfc *cmd, spin_lock_bh(&adapter->fdir_fltr_lock); list_for_each_entry(fltr, &adapter->fdir_list_head, list) { + if (iavf_is_raw_fdir(fltr)) + continue; + if (cnt == cmd->rule_cnt) { val = -EMSGSIZE; goto release_lock; @@ -1401,15 +1266,7 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx return -EINVAL; spin_lock_bh(&adapter->fdir_fltr_lock); - if (adapter->fdir_active_fltr >= IAVF_MAX_FDIR_FILTERS) { - spin_unlock_bh(&adapter->fdir_fltr_lock); - dev_err(&adapter->pdev->dev, - "Unable to add Flow Director filter because VF reached the limit of max allowed filters (%u)\n", - IAVF_MAX_FDIR_FILTERS); - return -ENOSPC; - } - - if (iavf_find_fdir_fltr_by_loc(adapter, fsp->location)) { + if (iavf_find_fdir_fltr(adapter, false, fsp->location)) { dev_err(&adapter->pdev->dev, "Failed to add Flow Director filter, it already exists\n"); spin_unlock_bh(&adapter->fdir_fltr_lock); return -EEXIST; @@ -1429,23 +1286,10 @@ static int iavf_add_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rx } err = iavf_add_fdir_fltr_info(adapter, fsp, fltr); - if (err) - goto ret; - - spin_lock_bh(&adapter->fdir_fltr_lock); - iavf_fdir_list_add_fltr(adapter, fltr); - adapter->fdir_active_fltr++; - - if (adapter->link_up) - fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST; - else - fltr->state = IAVF_FDIR_FLTR_INACTIVE; - spin_unlock_bh(&adapter->fdir_fltr_lock); + if (!err) + err = iavf_fdir_add_fltr(adapter, fltr); - if (adapter->link_up) - iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_FDIR_FILTER); -ret: - if (err && fltr) + if (err) kfree(fltr); mutex_unlock(&adapter->crit_lock); @@ -1462,34 +1306,11 @@ ret: static int iavf_del_fdir_ethtool(struct iavf_adapter *adapter, struct ethtool_rxnfc *cmd) { struct ethtool_rx_flow_spec *fsp = (struct ethtool_rx_flow_spec *)&cmd->fs; - struct iavf_fdir_fltr *fltr = NULL; - int err = 0; if (!(adapter->flags & IAVF_FLAG_FDIR_ENABLED)) return -EOPNOTSUPP; - spin_lock_bh(&adapter->fdir_fltr_lock); - fltr = iavf_find_fdir_fltr_by_loc(adapter, fsp->location); - if (fltr) { - if (fltr->state == IAVF_FDIR_FLTR_ACTIVE) { - fltr->state = IAVF_FDIR_FLTR_DEL_REQUEST; - } else if (fltr->state == IAVF_FDIR_FLTR_INACTIVE) { - list_del(&fltr->list); - kfree(fltr); - adapter->fdir_active_fltr--; - fltr = NULL; - } else { - err = -EBUSY; - } - } else if (adapter->fdir_active_fltr) { - err = -EINVAL; - } - spin_unlock_bh(&adapter->fdir_fltr_lock); - - if (fltr && fltr->state == IAVF_FDIR_FLTR_DEL_REQUEST) - iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_FDIR_FILTER); - - return err; + return iavf_fdir_del_fltr(adapter, false, fsp->location); } /** @@ -1987,7 +1808,7 @@ static int iavf_set_rxfh(struct net_device *netdev, static const struct ethtool_ops iavf_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_USE_ADAPTIVE, - .cap_rss_sym_xor_supported = true, + .supported_input_xfrm = RXH_XFRM_SYM_XOR, .get_drvinfo = iavf_get_drvinfo, .get_link = ethtool_op_get_link, .get_ringparam = iavf_get_ringparam, @@ -1995,8 +1816,6 @@ static const struct ethtool_ops iavf_ethtool_ops = { .get_strings = iavf_get_strings, .get_ethtool_stats = iavf_get_ethtool_stats, .get_sset_count = iavf_get_sset_count, - .get_priv_flags = iavf_get_priv_flags, - .set_priv_flags = iavf_set_priv_flags, .get_msglevel = iavf_get_msglevel, .set_msglevel = iavf_set_msglevel, .get_coalesce = iavf_get_coalesce, diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.c b/drivers/net/ethernet/intel/iavf/iavf_fdir.c index 2d47b0b4640e..a1b3b44cc14a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.c +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.c @@ -796,6 +796,9 @@ bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr * spin_lock_bh(&adapter->fdir_fltr_lock); list_for_each_entry(tmp, &adapter->fdir_list_head, list) { + if (iavf_is_raw_fdir(fltr)) + continue; + if (tmp->flow_type != fltr->flow_type) continue; @@ -815,33 +818,52 @@ bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr * } /** - * iavf_find_fdir_fltr_by_loc - find filter with location + * iavf_find_fdir_fltr - find FDIR filter * @adapter: pointer to the VF adapter structure - * @loc: location to find. + * @is_raw: filter type, is raw (tc u32) or not (ethtool) + * @data: data to ID the filter, type dependent * - * Returns pointer to Flow Director filter if found or null + * Returns: pointer to Flow Director filter if found or NULL. Lock must be held. */ -struct iavf_fdir_fltr *iavf_find_fdir_fltr_by_loc(struct iavf_adapter *adapter, u32 loc) +struct iavf_fdir_fltr *iavf_find_fdir_fltr(struct iavf_adapter *adapter, + bool is_raw, u32 data) { struct iavf_fdir_fltr *rule; - list_for_each_entry(rule, &adapter->fdir_list_head, list) - if (rule->loc == loc) + list_for_each_entry(rule, &adapter->fdir_list_head, list) { + if ((is_raw && rule->cls_u32_handle == data) || + (!is_raw && rule->loc == data)) return rule; + } return NULL; } /** - * iavf_fdir_list_add_fltr - add a new node to the flow director filter list + * iavf_fdir_add_fltr - add a new node to the flow director filter list * @adapter: pointer to the VF adapter structure * @fltr: filter node to add to structure + * + * Return: 0 on success or negative errno on failure. */ -void iavf_fdir_list_add_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr) +int iavf_fdir_add_fltr(struct iavf_adapter *adapter, + struct iavf_fdir_fltr *fltr) { struct iavf_fdir_fltr *rule, *parent = NULL; + spin_lock_bh(&adapter->fdir_fltr_lock); + if (iavf_fdir_max_reached(adapter)) { + spin_unlock_bh(&adapter->fdir_fltr_lock); + dev_err(&adapter->pdev->dev, + "Unable to add Flow Director filter (limit (%u) reached)\n", + IAVF_MAX_FDIR_FILTERS); + return -ENOSPC; + } + list_for_each_entry(rule, &adapter->fdir_list_head, list) { + if (iavf_is_raw_fdir(fltr)) + break; + if (rule->loc >= fltr->loc) break; parent = rule; @@ -851,4 +873,55 @@ void iavf_fdir_list_add_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr list_add(&fltr->list, &parent->list); else list_add(&fltr->list, &adapter->fdir_list_head); + + iavf_inc_fdir_active_fltr(adapter, fltr); + + if (adapter->link_up) + fltr->state = IAVF_FDIR_FLTR_ADD_REQUEST; + else + fltr->state = IAVF_FDIR_FLTR_INACTIVE; + spin_unlock_bh(&adapter->fdir_fltr_lock); + + if (adapter->link_up) + iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_FDIR_FILTER); + + return 0; +} + +/** + * iavf_fdir_del_fltr - delete a flow director filter from the list + * @adapter: pointer to the VF adapter structure + * @is_raw: filter type, is raw (tc u32) or not (ethtool) + * @data: data to ID the filter, type dependent + * + * Return: 0 on success or negative errno on failure. + */ +int iavf_fdir_del_fltr(struct iavf_adapter *adapter, bool is_raw, u32 data) +{ + struct iavf_fdir_fltr *fltr = NULL; + int err = 0; + + spin_lock_bh(&adapter->fdir_fltr_lock); + fltr = iavf_find_fdir_fltr(adapter, is_raw, data); + + if (fltr) { + if (fltr->state == IAVF_FDIR_FLTR_ACTIVE) { + fltr->state = IAVF_FDIR_FLTR_DEL_REQUEST; + } else if (fltr->state == IAVF_FDIR_FLTR_INACTIVE) { + list_del(&fltr->list); + iavf_dec_fdir_active_fltr(adapter, fltr); + kfree(fltr); + fltr = NULL; + } else { + err = -EBUSY; + } + } else if (adapter->fdir_active_fltr) { + err = -EINVAL; + } + + if (fltr && fltr->state == IAVF_FDIR_FLTR_DEL_REQUEST) + iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_FDIR_FILTER); + + spin_unlock_bh(&adapter->fdir_fltr_lock); + return err; } diff --git a/drivers/net/ethernet/intel/iavf/iavf_fdir.h b/drivers/net/ethernet/intel/iavf/iavf_fdir.h index d31bd923ba8c..e84a5351162f 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_fdir.h +++ b/drivers/net/ethernet/intel/iavf/iavf_fdir.h @@ -117,17 +117,26 @@ struct iavf_fdir_fltr { u32 flow_id; + u32 cls_u32_handle; /* for FDIR added via tc u32 */ u32 loc; /* Rule location inside the flow table */ u32 q_index; struct virtchnl_fdir_add vc_add_msg; }; +static inline bool iavf_is_raw_fdir(struct iavf_fdir_fltr *fltr) +{ + return !fltr->vc_add_msg.rule_cfg.proto_hdrs.count; +} + int iavf_validate_fdir_fltr_masks(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); int iavf_fill_fdir_add_msg(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); void iavf_print_fdir_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); bool iavf_fdir_is_dup_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); -void iavf_fdir_list_add_fltr(struct iavf_adapter *adapter, struct iavf_fdir_fltr *fltr); -struct iavf_fdir_fltr *iavf_find_fdir_fltr_by_loc(struct iavf_adapter *adapter, u32 loc); +int iavf_fdir_add_fltr(struct iavf_adapter *adapter, + struct iavf_fdir_fltr *fltr); +int iavf_fdir_del_fltr(struct iavf_adapter *adapter, bool is_raw, u32 data); +struct iavf_fdir_fltr *iavf_find_fdir_fltr(struct iavf_adapter *adapter, + bool is_raw, u32 data); #endif /* _IAVF_FDIR_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 166832a4213a..6d7ba4d67a19 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -1,7 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ +#include <linux/net/intel/libie/rx.h> +#include <net/netdev_lock.h> + #include "iavf.h" +#include "iavf_ptp.h" #include "iavf_prototype.h" /* All iavf tracepoints are defined by the include below, which must * be included exactly once across the whole kernel with @@ -43,8 +47,9 @@ static const struct pci_device_id iavf_pci_tbl[] = { MODULE_DEVICE_TABLE(pci, iavf_pci_tbl); MODULE_ALIAS("i40evf"); -MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION("Intel(R) Ethernet Adaptive Virtual Function Network Driver"); +MODULE_IMPORT_NS("LIBETH"); +MODULE_IMPORT_NS("LIBIE"); MODULE_LICENSE("GPL v2"); static const struct net_device_ops iavf_netdev_ops; @@ -707,6 +712,47 @@ static void iavf_configure_tx(struct iavf_adapter *adapter) } /** + * iavf_select_rx_desc_format - Select Rx descriptor format + * @adapter: adapter private structure + * + * Select what Rx descriptor format based on availability and enabled + * features. + * + * Return: the desired RXDID to select for a given Rx queue, as defined by + * enum virtchnl_rxdid_format. + */ +static u8 iavf_select_rx_desc_format(const struct iavf_adapter *adapter) +{ + u64 rxdids = adapter->supp_rxdids; + + /* If we did not negotiate VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC, we must + * stick with the default value of the legacy 32 byte format. + */ + if (!IAVF_RXDID_ALLOWED(adapter)) + return VIRTCHNL_RXDID_1_32B_BASE; + + /* Rx timestamping requires the use of flexible NIC descriptors */ + if (iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP)) { + if (rxdids & BIT(VIRTCHNL_RXDID_2_FLEX_SQ_NIC)) + return VIRTCHNL_RXDID_2_FLEX_SQ_NIC; + + pci_warn(adapter->pdev, + "Unable to negotiate flexible descriptor format\n"); + } + + /* Warn if the PF does not list support for the default legacy + * descriptor format. This shouldn't happen, as this is the format + * used if VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC is not supported. It is + * likely caused by a bug in the PF implementation failing to indicate + * support for the format. + */ + if (!(rxdids & VIRTCHNL_RXDID_1_32B_BASE_M)) + netdev_warn(adapter->netdev, "PF does not list support for default Rx descriptor format\n"); + + return VIRTCHNL_RXDID_1_32B_BASE; +} + +/** * iavf_configure_rx - Configure Receive Unit after Reset * @adapter: board private structure * @@ -714,39 +760,13 @@ static void iavf_configure_tx(struct iavf_adapter *adapter) **/ static void iavf_configure_rx(struct iavf_adapter *adapter) { - unsigned int rx_buf_len = IAVF_RXBUFFER_2048; struct iavf_hw *hw = &adapter->hw; - int i; - /* Legacy Rx will always default to a 2048 buffer size. */ -#if (PAGE_SIZE < 8192) - if (!(adapter->flags & IAVF_FLAG_LEGACY_RX)) { - struct net_device *netdev = adapter->netdev; + adapter->rxdid = iavf_select_rx_desc_format(adapter); - /* For jumbo frames on systems with 4K pages we have to use - * an order 1 page, so we might as well increase the size - * of our Rx buffer to make better use of the available space - */ - rx_buf_len = IAVF_RXBUFFER_3072; - - /* We use a 1536 buffer size for configurations with - * standard Ethernet mtu. On x86 this gives us enough room - * for shared info and 192 bytes of padding. - */ - if (!IAVF_2K_TOO_SMALL_WITH_PADDING && - (netdev->mtu <= ETH_DATA_LEN)) - rx_buf_len = IAVF_RXBUFFER_1536 - NET_IP_ALIGN; - } -#endif - - for (i = 0; i < adapter->num_active_queues; i++) { + for (u32 i = 0; i < adapter->num_active_queues; i++) { adapter->rx_rings[i].tail = hw->hw_addr + IAVF_QRX_TAIL1(i); - adapter->rx_rings[i].rx_buf_len = rx_buf_len; - - if (adapter->flags & IAVF_FLAG_LEGACY_RX) - clear_ring_build_skb_enabled(&adapter->rx_rings[i]); - else - set_ring_build_skb_enabled(&adapter->rx_rings[i]); + adapter->rx_rings[i].rxdid = adapter->rxdid; } } @@ -800,6 +820,11 @@ iavf_vlan_filter *iavf_add_vlan(struct iavf_adapter *adapter, f->state = IAVF_VLAN_ADD; adapter->num_vlan_filters++; iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_ADD_VLAN_FILTER); + } else if (f->state == IAVF_VLAN_REMOVE) { + /* IAVF_VLAN_REMOVE means that VLAN wasn't yet removed. + * We can safely only change the state here. + */ + f->state = IAVF_VLAN_ACTIVE; } clearout: @@ -820,8 +845,18 @@ static void iavf_del_vlan(struct iavf_adapter *adapter, struct iavf_vlan vlan) f = iavf_find_vlan(adapter, vlan); if (f) { - f->state = IAVF_VLAN_REMOVE; - iavf_schedule_aq_request(adapter, IAVF_FLAG_AQ_DEL_VLAN_FILTER); + /* IAVF_ADD_VLAN means that VLAN wasn't even added yet. + * Remove it from the list. + */ + if (f->state == IAVF_VLAN_ADD) { + list_del(&f->list); + kfree(f); + adapter->num_vlan_filters--; + } else { + f->state = IAVF_VLAN_REMOVE; + iavf_schedule_aq_request(adapter, + IAVF_FLAG_AQ_DEL_VLAN_FILTER); + } } spin_unlock_bh(&adapter->mac_vlan_list_lock); @@ -1207,7 +1242,7 @@ static void iavf_napi_enable_all(struct iavf_adapter *adapter) q_vector = &adapter->q_vectors[q_idx]; napi = &q_vector->napi; - napi_enable(napi); + napi_enable_locked(napi); } } @@ -1223,7 +1258,7 @@ static void iavf_napi_disable_all(struct iavf_adapter *adapter) for (q_idx = 0; q_idx < q_vectors; q_idx++) { q_vector = &adapter->q_vectors[q_idx]; - napi_disable(&q_vector->napi); + napi_disable_locked(&q_vector->napi); } } @@ -1615,7 +1650,6 @@ static int iavf_alloc_queues(struct iavf_adapter *adapter) rx_ring = &adapter->rx_rings[i]; rx_ring->queue_index = i; rx_ring->netdev = adapter->netdev; - rx_ring->dev = &adapter->pdev->dev; rx_ring->count = adapter->rx_desc_count; rx_ring->itr_setting = IAVF_ITR_RX_DEF; } @@ -1828,8 +1862,8 @@ static int iavf_alloc_q_vectors(struct iavf_adapter *adapter) q_vector->v_idx = q_idx; q_vector->reg_idx = q_idx; cpumask_copy(&q_vector->affinity_mask, cpu_possible_mask); - netif_napi_add(adapter->netdev, &q_vector->napi, - iavf_napi_poll); + netif_napi_add_locked(adapter->netdev, &q_vector->napi, + iavf_napi_poll); } return 0; @@ -1855,7 +1889,7 @@ static void iavf_free_q_vectors(struct iavf_adapter *adapter) for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { struct iavf_q_vector *q_vector = &adapter->q_vectors[q_idx]; - netif_napi_del(&q_vector->napi); + netif_napi_del_locked(&q_vector->napi); } kfree(adapter->q_vectors); adapter->q_vectors = NULL; @@ -1996,12 +2030,16 @@ err: static void iavf_finish_config(struct work_struct *work) { struct iavf_adapter *adapter; + bool locks_released = false; int pairs, err; adapter = container_of(work, struct iavf_adapter, finish_config); - /* Always take RTNL first to prevent circular lock dependency */ + /* Always take RTNL first to prevent circular lock dependency; + * The dev->lock is needed to update the queue number + */ rtnl_lock(); + netdev_lock(adapter->netdev); mutex_lock(&adapter->crit_lock); if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES) && @@ -2013,26 +2051,34 @@ static void iavf_finish_config(struct work_struct *work) switch (adapter->state) { case __IAVF_DOWN: + /* Set the real number of queues when reset occurs while + * state == __IAVF_DOWN + */ + pairs = adapter->num_active_queues; + netif_set_real_num_rx_queues(adapter->netdev, pairs); + netif_set_real_num_tx_queues(adapter->netdev, pairs); + if (adapter->netdev->reg_state != NETREG_REGISTERED) { + mutex_unlock(&adapter->crit_lock); + netdev_unlock(adapter->netdev); + locks_released = true; err = register_netdevice(adapter->netdev); if (err) { dev_err(&adapter->pdev->dev, "Unable to register netdev (%d)\n", err); /* go back and try again.*/ + mutex_lock(&adapter->crit_lock); iavf_free_rss(adapter); iavf_free_misc_irq(adapter); iavf_reset_interrupt_capability(adapter); iavf_change_state(adapter, __IAVF_INIT_CONFIG_ADAPTER); + mutex_unlock(&adapter->crit_lock); goto out; } } - - /* Set the real number of queues when reset occurs while - * state == __IAVF_DOWN - */ - fallthrough; + break; case __IAVF_RUNNING: pairs = adapter->num_active_queues; netif_set_real_num_rx_queues(adapter->netdev, pairs); @@ -2044,7 +2090,10 @@ static void iavf_finish_config(struct work_struct *work) } out: - mutex_unlock(&adapter->crit_lock); + if (!locks_released) { + mutex_unlock(&adapter->crit_lock); + netdev_unlock(adapter->netdev); + } rtnl_unlock(); } @@ -2073,6 +2122,10 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter) return iavf_send_vf_config_msg(adapter); if (adapter->aq_required & IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS) return iavf_send_vf_offload_vlan_v2_msg(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS) + return iavf_send_vf_supported_rxdids_msg(adapter); + if (adapter->aq_required & IAVF_FLAG_AQ_GET_PTP_CAPS) + return iavf_send_vf_ptp_caps_msg(adapter); if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_QUEUES) { iavf_disable_queues(adapter); return 0; @@ -2113,6 +2166,21 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter) return 0; } + if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW) { + iavf_cfg_queues_bw(adapter); + return 0; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_GET_QOS_CAPS) { + iavf_get_qos_caps(adapter); + return 0; + } + + if (adapter->aq_required & IAVF_FLAG_AQ_CFG_QUEUES_QUANTA_SIZE) { + iavf_cfg_queues_quanta_size(adapter); + return 0; + } + if (adapter->aq_required & IAVF_FLAG_AQ_CONFIGURE_QUEUES) { iavf_configure_queues(adapter); return 0; @@ -2222,7 +2290,10 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter) iavf_enable_vlan_insertion_v2(adapter, ETH_P_8021AD); return 0; } - + if (adapter->aq_required & IAVF_FLAG_AQ_SEND_PTP_CMD) { + iavf_virtchnl_send_ptp_cmd(adapter); + return IAVF_SUCCESS; + } if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_STATS) { iavf_request_stats(adapter); return 0; @@ -2587,6 +2658,112 @@ err: } /** + * iavf_init_send_supported_rxdids - part of querying for supported RXDID + * formats + * @adapter: board private structure + * + * Function processes send of the request for supported RXDIDs to the PF. + * Must clear IAVF_EXTENDED_CAP_RECV_RXDID if the message is not sent, e.g. + * due to the PF not negotiating VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC. + */ +static void iavf_init_send_supported_rxdids(struct iavf_adapter *adapter) +{ + int ret; + + ret = iavf_send_vf_supported_rxdids_msg(adapter); + if (ret == -EOPNOTSUPP) { + /* PF does not support VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC. In this + * case, we did not send the capability exchange message and + * do not expect a response. + */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_RXDID; + } + + /* We sent the message, so move on to the next step */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_SEND_RXDID; +} + +/** + * iavf_init_recv_supported_rxdids - part of querying for supported RXDID + * formats + * @adapter: board private structure + * + * Function processes receipt of the supported RXDIDs message from the PF. + **/ +static void iavf_init_recv_supported_rxdids(struct iavf_adapter *adapter) +{ + int ret; + + memset(&adapter->supp_rxdids, 0, sizeof(adapter->supp_rxdids)); + + ret = iavf_get_vf_supported_rxdids(adapter); + if (ret) + goto err; + + /* We've processed the PF response to the + * VIRTCHNL_OP_GET_SUPPORTED_RXDIDS message we sent previously. + */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_RXDID; + return; + +err: + /* We didn't receive a reply. Make sure we try sending again when + * __IAVF_INIT_FAILED attempts to recover. + */ + adapter->extended_caps |= IAVF_EXTENDED_CAP_SEND_RXDID; + iavf_change_state(adapter, __IAVF_INIT_FAILED); +} + +/** + * iavf_init_send_ptp_caps - part of querying for extended PTP capabilities + * @adapter: board private structure + * + * Function processes send of the request for 1588 PTP capabilities to the PF. + * Must clear IAVF_EXTENDED_CAP_SEND_PTP if the message is not sent, e.g. + * due to the PF not negotiating VIRTCHNL_VF_PTP_CAP + */ +static void iavf_init_send_ptp_caps(struct iavf_adapter *adapter) +{ + if (iavf_send_vf_ptp_caps_msg(adapter) == -EOPNOTSUPP) { + /* PF does not support VIRTCHNL_VF_PTP_CAP. In this case, we + * did not send the capability exchange message and do not + * expect a response. + */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_PTP; + } + + /* We sent the message, so move on to the next step */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_SEND_PTP; +} + +/** + * iavf_init_recv_ptp_caps - part of querying for supported PTP capabilities + * @adapter: board private structure + * + * Function processes receipt of the PTP capabilities supported on this VF. + **/ +static void iavf_init_recv_ptp_caps(struct iavf_adapter *adapter) +{ + memset(&adapter->ptp.hw_caps, 0, sizeof(adapter->ptp.hw_caps)); + + if (iavf_get_vf_ptp_caps(adapter)) + goto err; + + /* We've processed the PF response to the VIRTCHNL_OP_1588_PTP_GET_CAPS + * message we sent previously. + */ + adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_PTP; + return; + +err: + /* We didn't receive a reply. Make sure we try sending again when + * __IAVF_INIT_FAILED attempts to recover. + */ + adapter->extended_caps |= IAVF_EXTENDED_CAP_SEND_PTP; + iavf_change_state(adapter, __IAVF_INIT_FAILED); +} + +/** * iavf_init_process_extended_caps - Part of driver startup * @adapter: board private structure * @@ -2610,6 +2787,24 @@ static void iavf_init_process_extended_caps(struct iavf_adapter *adapter) return; } + /* Process capability exchange for RXDID formats */ + if (adapter->extended_caps & IAVF_EXTENDED_CAP_SEND_RXDID) { + iavf_init_send_supported_rxdids(adapter); + return; + } else if (adapter->extended_caps & IAVF_EXTENDED_CAP_RECV_RXDID) { + iavf_init_recv_supported_rxdids(adapter); + return; + } + + /* Process capability exchange for PTP features */ + if (adapter->extended_caps & IAVF_EXTENDED_CAP_SEND_PTP) { + iavf_init_send_ptp_caps(adapter); + return; + } else if (adapter->extended_caps & IAVF_EXTENDED_CAP_RECV_PTP) { + iavf_init_recv_ptp_caps(adapter); + return; + } + /* When we reach here, no further extended capabilities exchanges are * necessary, so we finally transition into __IAVF_INIT_CONFIG_ADAPTER */ @@ -2642,9 +2837,8 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) iavf_set_ethtool_ops(netdev); netdev->watchdog_timeo = 5 * HZ; - /* MTU range: 68 - 9710 */ netdev->min_mtu = ETH_MIN_MTU; - netdev->max_mtu = IAVF_MAX_RXBUFFER - IAVF_PACKET_HDR_PAD; + netdev->max_mtu = LIBIE_MAX_MTU; if (!is_valid_ether_addr(adapter->hw.mac.addr)) { dev_info(&pdev->dev, "Invalid MAC address %pM, using random\n", @@ -2699,6 +2893,12 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) /* request initial VLAN offload settings */ iavf_set_vlan_offload_features(adapter, 0, netdev->features); + if (QOS_ALLOWED(adapter)) + adapter->aq_required |= IAVF_FLAG_AQ_GET_QOS_CAPS; + + /* Setup initial PTP configuration */ + iavf_ptp_init(adapter); + iavf_schedule_finish_config(adapter); return; @@ -2720,12 +2920,16 @@ static void iavf_watchdog_task(struct work_struct *work) struct iavf_adapter *adapter = container_of(work, struct iavf_adapter, watchdog_task.work); + struct net_device *netdev = adapter->netdev; struct iavf_hw *hw = &adapter->hw; u32 reg_val; + netdev_lock(netdev); if (!mutex_trylock(&adapter->crit_lock)) { - if (adapter->state == __IAVF_REMOVE) + if (adapter->state == __IAVF_REMOVE) { + netdev_unlock(netdev); return; + } goto restart_watchdog; } @@ -2737,30 +2941,35 @@ static void iavf_watchdog_task(struct work_struct *work) case __IAVF_STARTUP: iavf_startup(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(30)); return; case __IAVF_INIT_VERSION_CHECK: iavf_init_version_check(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(30)); return; case __IAVF_INIT_GET_RESOURCES: iavf_init_get_resources(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(1)); return; case __IAVF_INIT_EXTENDED_CAPS: iavf_init_process_extended_caps(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(1)); return; case __IAVF_INIT_CONFIG_ADAPTER: iavf_init_config_adapter(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(1)); return; @@ -2772,6 +2981,7 @@ static void iavf_watchdog_task(struct work_struct *work) * as it can loop forever */ mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return; } if (++adapter->aq_wait_count > IAVF_AQ_MAX_ERR) { @@ -2780,6 +2990,7 @@ static void iavf_watchdog_task(struct work_struct *work) adapter->flags |= IAVF_FLAG_PF_COMMS_FAILED; iavf_shutdown_adminq(hw); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, (5 * HZ)); return; @@ -2787,6 +2998,7 @@ static void iavf_watchdog_task(struct work_struct *work) /* Try again from failed step*/ iavf_change_state(adapter, adapter->last_state); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, HZ); return; case __IAVF_COMM_FAILED: @@ -2799,6 +3011,7 @@ static void iavf_watchdog_task(struct work_struct *work) iavf_change_state(adapter, __IAVF_INIT_FAILED); adapter->flags &= ~IAVF_FLAG_PF_COMMS_FAILED; mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return; } reg_val = rd32(hw, IAVF_VFGEN_RSTAT) & @@ -2818,12 +3031,14 @@ static void iavf_watchdog_task(struct work_struct *work) adapter->aq_required = 0; adapter->current_op = VIRTCHNL_OP_UNKNOWN; mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(10)); return; case __IAVF_RESETTING: mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, HZ * 2); return; @@ -2854,6 +3069,7 @@ static void iavf_watchdog_task(struct work_struct *work) case __IAVF_REMOVE: default: mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return; } @@ -2865,6 +3081,7 @@ static void iavf_watchdog_task(struct work_struct *work) dev_err(&adapter->pdev->dev, "Hardware reset detected\n"); iavf_schedule_reset(adapter, IAVF_FLAG_RESET_PENDING); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); queue_delayed_work(adapter->wq, &adapter->watchdog_task, HZ * 2); return; @@ -2872,6 +3089,7 @@ static void iavf_watchdog_task(struct work_struct *work) mutex_unlock(&adapter->crit_lock); restart_watchdog: + netdev_unlock(netdev); if (adapter->state >= __IAVF_DOWN) queue_work(adapter->wq, &adapter->adminq_task); if (adapter->aq_required) @@ -2948,6 +3166,30 @@ static void iavf_disable_vf(struct iavf_adapter *adapter) } /** + * iavf_reconfig_qs_bw - Call-back task to handle hardware reset + * @adapter: board private structure + * + * After a reset, the shaper parameters of queues need to be replayed again. + * Since the net_shaper object inside TX rings persists across reset, + * set the update flag for all queues so that the virtchnl message is triggered + * for all queues. + **/ +static void iavf_reconfig_qs_bw(struct iavf_adapter *adapter) +{ + int i, num = 0; + + for (i = 0; i < adapter->num_active_queues; i++) + if (adapter->tx_rings[i].q_shaper.bw_min || + adapter->tx_rings[i].q_shaper.bw_max) { + adapter->tx_rings[i].q_shaper_update = true; + num++; + } + + if (num) + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW; +} + +/** * iavf_reset_task - Call-back task to handle hardware reset * @work: pointer to work_struct * @@ -2973,10 +3215,12 @@ static void iavf_reset_task(struct work_struct *work) /* When device is being removed it doesn't make sense to run the reset * task, just return in such a case. */ + netdev_lock(netdev); if (!mutex_trylock(&adapter->crit_lock)) { if (adapter->state != __IAVF_REMOVE) queue_work(adapter->wq, &adapter->reset_task); + netdev_unlock(netdev); return; } @@ -3024,6 +3268,7 @@ static void iavf_reset_task(struct work_struct *work) reg_val); iavf_disable_vf(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return; /* Do not attempt to reinit. It's dead, Jim. */ } @@ -3079,15 +3324,18 @@ continue_reset: } adapter->aq_required |= IAVF_FLAG_AQ_GET_CONFIG; - /* always set since VIRTCHNL_OP_GET_VF_RESOURCES has not been - * sent/received yet, so VLAN_V2_ALLOWED() cannot is not reliable here, - * however the VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS won't be sent until - * VIRTCHNL_OP_GET_VF_RESOURCES and VIRTCHNL_VF_OFFLOAD_VLAN_V2 have - * been successfully sent and negotiated - */ - adapter->aq_required |= IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS; adapter->aq_required |= IAVF_FLAG_AQ_MAP_VECTORS; + /* Certain capabilities require an extended negotiation process using + * extra messages that must be processed after getting the VF + * configuration. The related checks such as VLAN_V2_ALLOWED() are not + * reliable here, since the configuration has not yet been negotiated. + * + * Always set these flags, since them related VIRTCHNL messages won't + * be sent until after VIRTCHNL_OP_GET_VF_RESOURCES. + */ + adapter->aq_required |= IAVF_FLAG_AQ_EXTENDED_CAPS; + spin_lock_bh(&adapter->mac_vlan_list_lock); /* Delete filter for the current MAC address, it could have @@ -3153,6 +3401,8 @@ continue_reset: iavf_up_complete(adapter); iavf_irq_enable(adapter, true); + + iavf_reconfig_qs_bw(adapter); } else { iavf_change_state(adapter, __IAVF_DOWN); wake_up(&adapter->down_waitqueue); @@ -3162,6 +3412,7 @@ continue_reset: wake_up(&adapter->reset_waitqueue); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return; reset_err: @@ -3172,6 +3423,7 @@ reset_err: iavf_disable_vf(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); } @@ -3785,6 +4037,10 @@ static int iavf_parse_cls_flower(struct iavf_adapter *adapter, flow_rule_match_control(rule, &match); addr_type = match.key->addr_type; + + if (flow_rule_has_control_flags(match.mask->flags, + f->common.extack)) + return -EOPNOTSUPP; } if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { @@ -4038,7 +4294,7 @@ static int iavf_delete_clsflower(struct iavf_adapter *adapter, /** * iavf_setup_tc_cls_flower - flower classifier offloads - * @adapter: board private structure + * @adapter: pointer to iavf adapter structure * @cls_flower: pointer to flow_cls_offload struct with flow info */ static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter, @@ -4057,6 +4313,154 @@ static int iavf_setup_tc_cls_flower(struct iavf_adapter *adapter, } /** + * iavf_add_cls_u32 - Add U32 classifier offloads + * @adapter: pointer to iavf adapter structure + * @cls_u32: pointer to tc_cls_u32_offload struct with flow info + * + * Return: 0 on success or negative errno on failure. + */ +static int iavf_add_cls_u32(struct iavf_adapter *adapter, + struct tc_cls_u32_offload *cls_u32) +{ + struct netlink_ext_ack *extack = cls_u32->common.extack; + struct virtchnl_fdir_rule *rule_cfg; + struct virtchnl_filter_action *vact; + struct virtchnl_proto_hdrs *hdrs; + struct ethhdr *spec_h, *mask_h; + const struct tc_action *act; + struct iavf_fdir_fltr *fltr; + struct tcf_exts *exts; + unsigned int q_index; + int i, status = 0; + int off_base = 0; + + if (cls_u32->knode.link_handle) { + NL_SET_ERR_MSG_MOD(extack, "Linking not supported"); + return -EOPNOTSUPP; + } + + fltr = kzalloc(sizeof(*fltr), GFP_KERNEL); + if (!fltr) + return -ENOMEM; + + rule_cfg = &fltr->vc_add_msg.rule_cfg; + hdrs = &rule_cfg->proto_hdrs; + hdrs->count = 0; + + /* The parser lib at the PF expects the packet starting with MAC hdr */ + switch (ntohs(cls_u32->common.protocol)) { + case ETH_P_802_3: + break; + case ETH_P_IP: + spec_h = (struct ethhdr *)hdrs->raw.spec; + mask_h = (struct ethhdr *)hdrs->raw.mask; + spec_h->h_proto = htons(ETH_P_IP); + mask_h->h_proto = htons(0xFFFF); + off_base += ETH_HLEN; + break; + default: + NL_SET_ERR_MSG_MOD(extack, "Only 802_3 and ip filter protocols are supported"); + status = -EOPNOTSUPP; + goto free_alloc; + } + + for (i = 0; i < cls_u32->knode.sel->nkeys; i++) { + __be32 val, mask; + int off; + + off = off_base + cls_u32->knode.sel->keys[i].off; + val = cls_u32->knode.sel->keys[i].val; + mask = cls_u32->knode.sel->keys[i].mask; + + if (off >= sizeof(hdrs->raw.spec)) { + NL_SET_ERR_MSG_MOD(extack, "Input exceeds maximum allowed."); + status = -EINVAL; + goto free_alloc; + } + + memcpy(&hdrs->raw.spec[off], &val, sizeof(val)); + memcpy(&hdrs->raw.mask[off], &mask, sizeof(mask)); + hdrs->raw.pkt_len = off + sizeof(val); + } + + /* Only one action is allowed */ + rule_cfg->action_set.count = 1; + vact = &rule_cfg->action_set.actions[0]; + exts = cls_u32->knode.exts; + + tcf_exts_for_each_action(i, act, exts) { + /* FDIR queue */ + if (is_tcf_skbedit_rx_queue_mapping(act)) { + q_index = tcf_skbedit_rx_queue_mapping(act); + if (q_index >= adapter->num_active_queues) { + status = -EINVAL; + goto free_alloc; + } + + vact->type = VIRTCHNL_ACTION_QUEUE; + vact->act_conf.queue.index = q_index; + break; + } + + /* Drop */ + if (is_tcf_gact_shot(act)) { + vact->type = VIRTCHNL_ACTION_DROP; + break; + } + + /* Unsupported action */ + NL_SET_ERR_MSG_MOD(extack, "Unsupported action."); + status = -EOPNOTSUPP; + goto free_alloc; + } + + fltr->vc_add_msg.vsi_id = adapter->vsi.id; + fltr->cls_u32_handle = cls_u32->knode.handle; + return iavf_fdir_add_fltr(adapter, fltr); + +free_alloc: + kfree(fltr); + return status; +} + +/** + * iavf_del_cls_u32 - Delete U32 classifier offloads + * @adapter: pointer to iavf adapter structure + * @cls_u32: pointer to tc_cls_u32_offload struct with flow info + * + * Return: 0 on success or negative errno on failure. + */ +static int iavf_del_cls_u32(struct iavf_adapter *adapter, + struct tc_cls_u32_offload *cls_u32) +{ + return iavf_fdir_del_fltr(adapter, true, cls_u32->knode.handle); +} + +/** + * iavf_setup_tc_cls_u32 - U32 filter offloads + * @adapter: pointer to iavf adapter structure + * @cls_u32: pointer to tc_cls_u32_offload struct with flow info + * + * Return: 0 on success or negative errno on failure. + */ +static int iavf_setup_tc_cls_u32(struct iavf_adapter *adapter, + struct tc_cls_u32_offload *cls_u32) +{ + if (!TC_U32_SUPPORT(adapter) || !FDIR_FLTR_SUPPORT(adapter)) + return -EOPNOTSUPP; + + switch (cls_u32->command) { + case TC_CLSU32_NEW_KNODE: + case TC_CLSU32_REPLACE_KNODE: + return iavf_add_cls_u32(adapter, cls_u32); + case TC_CLSU32_DELETE_KNODE: + return iavf_del_cls_u32(adapter, cls_u32); + default: + return -EOPNOTSUPP; + } +} + +/** * iavf_setup_tc_block_cb - block callback for tc * @type: type of offload * @type_data: offload data @@ -4075,6 +4479,8 @@ static int iavf_setup_tc_block_cb(enum tc_setup_type type, void *type_data, switch (type) { case TC_SETUP_CLSFLOWER: return iavf_setup_tc_cls_flower(cb_priv, type_data); + case TC_SETUP_CLSU32: + return iavf_setup_tc_cls_u32(cb_priv, type_data); default: return -EOPNOTSUPP; } @@ -4155,6 +4561,8 @@ static int iavf_open(struct net_device *netdev) struct iavf_adapter *adapter = netdev_priv(netdev); int err; + netdev_assert_locked(netdev); + if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) { dev_err(&adapter->pdev->dev, "Unable to open device due to PF driver failure.\n"); return -EIO; @@ -4249,6 +4657,8 @@ static int iavf_close(struct net_device *netdev) u64 aq_to_restore; int status; + netdev_assert_locked(netdev); + mutex_lock(&adapter->crit_lock); if (adapter->state <= __IAVF_DOWN_PENDING) { @@ -4286,6 +4696,7 @@ static int iavf_close(struct net_device *netdev) iavf_free_traffic_irqs(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); /* We explicitly don't free resources here because the hardware is * still active and can DMA into memory. Resources are cleared in @@ -4304,6 +4715,7 @@ static int iavf_close(struct net_device *netdev) if (!status) netdev_warn(netdev, "Device resources not yet released\n"); + netdev_lock(netdev); mutex_lock(&adapter->crit_lock); adapter->aq_required |= aq_to_restore; mutex_unlock(&adapter->crit_lock); @@ -4324,7 +4736,7 @@ static int iavf_change_mtu(struct net_device *netdev, int new_mtu) 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)) { iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); @@ -4357,8 +4769,8 @@ static void iavf_disable_fdir(struct iavf_adapter *adapter) fdir->state == IAVF_FDIR_FLTR_INACTIVE) { /* Delete filters not registered in PF */ list_del(&fdir->list); + iavf_dec_fdir_active_fltr(adapter, fdir); kfree(fdir); - adapter->fdir_active_fltr--; } else if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING || fdir->state == IAVF_FDIR_FLTR_DIS_REQUEST || fdir->state == IAVF_FDIR_FLTR_ACTIVE) { @@ -4768,6 +5180,117 @@ static netdev_features_t iavf_fix_features(struct net_device *netdev, return iavf_fix_strip_features(adapter, features); } +static int iavf_hwstamp_get(struct net_device *netdev, + struct kernel_hwtstamp_config *config) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + *config = adapter->ptp.hwtstamp_config; + + return 0; +} + +static int iavf_hwstamp_set(struct net_device *netdev, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + struct iavf_adapter *adapter = netdev_priv(netdev); + + return iavf_ptp_set_ts_config(adapter, config, extack); +} + +static int +iavf_verify_shaper(struct net_shaper_binding *binding, + const struct net_shaper *shaper, + struct netlink_ext_ack *extack) +{ + struct iavf_adapter *adapter = netdev_priv(binding->netdev); + u64 vf_max; + + if (shaper->handle.scope == NET_SHAPER_SCOPE_QUEUE) { + vf_max = adapter->qos_caps->cap[0].shaper.peak; + if (vf_max && shaper->bw_max > vf_max) { + NL_SET_ERR_MSG_FMT(extack, "Max rate (%llu) of queue %d can't exceed max TX rate of VF (%llu kbps)", + shaper->bw_max, shaper->handle.id, + vf_max); + return -EINVAL; + } + } + return 0; +} + +static int +iavf_shaper_set(struct net_shaper_binding *binding, + const struct net_shaper *shaper, + struct netlink_ext_ack *extack) +{ + struct iavf_adapter *adapter = netdev_priv(binding->netdev); + const struct net_shaper_handle *handle = &shaper->handle; + struct iavf_ring *tx_ring; + int ret = 0; + + mutex_lock(&adapter->crit_lock); + if (handle->id >= adapter->num_active_queues) + goto unlock; + + ret = iavf_verify_shaper(binding, shaper, extack); + if (ret) + goto unlock; + + tx_ring = &adapter->tx_rings[handle->id]; + + tx_ring->q_shaper.bw_min = div_u64(shaper->bw_min, 1000); + tx_ring->q_shaper.bw_max = div_u64(shaper->bw_max, 1000); + tx_ring->q_shaper_update = true; + + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW; + +unlock: + mutex_unlock(&adapter->crit_lock); + return ret; +} + +static int iavf_shaper_del(struct net_shaper_binding *binding, + const struct net_shaper_handle *handle, + struct netlink_ext_ack *extack) +{ + struct iavf_adapter *adapter = netdev_priv(binding->netdev); + struct iavf_ring *tx_ring; + + mutex_lock(&adapter->crit_lock); + if (handle->id >= adapter->num_active_queues) + goto unlock; + + tx_ring = &adapter->tx_rings[handle->id]; + tx_ring->q_shaper.bw_min = 0; + tx_ring->q_shaper.bw_max = 0; + tx_ring->q_shaper_update = true; + + adapter->aq_required |= IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW; + +unlock: + mutex_unlock(&adapter->crit_lock); + return 0; +} + +static void iavf_shaper_cap(struct net_shaper_binding *binding, + enum net_shaper_scope scope, + unsigned long *flags) +{ + if (scope != NET_SHAPER_SCOPE_QUEUE) + return; + + *flags = BIT(NET_SHAPER_A_CAPS_SUPPORT_BW_MIN) | + BIT(NET_SHAPER_A_CAPS_SUPPORT_BW_MAX) | + BIT(NET_SHAPER_A_CAPS_SUPPORT_METRIC_BPS); +} + +static const struct net_shaper_ops iavf_shaper_ops = { + .set = iavf_shaper_set, + .delete = iavf_shaper_del, + .capabilities = iavf_shaper_cap, +}; + static const struct net_device_ops iavf_netdev_ops = { .ndo_open = iavf_open, .ndo_stop = iavf_close, @@ -4783,6 +5306,9 @@ static const struct net_device_ops iavf_netdev_ops = { .ndo_fix_features = iavf_fix_features, .ndo_set_features = iavf_set_features, .ndo_setup_tc = iavf_setup_tc, + .net_shaper_ops = &iavf_shaper_ops, + .ndo_hwtstamp_get = iavf_hwstamp_get, + .ndo_hwtstamp_set = iavf_hwstamp_set, }; /** @@ -4868,9 +5394,11 @@ int iavf_process_config(struct iavf_adapter *adapter) /* get HW VLAN features that can be toggled */ hw_vlan_features = iavf_get_netdev_vlan_hw_features(adapter); - /* Enable cloud filter if ADQ is supported */ - if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) + /* Enable HW TC offload if ADQ or tc U32 is supported */ + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ || + TC_U32_SUPPORT(adapter)) hw_features |= NETIF_F_HW_TC; + if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_USO) hw_features |= NETIF_F_GSO_UDP_L4; @@ -4927,7 +5455,7 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) struct net_device *netdev; struct iavf_adapter *adapter = NULL; struct iavf_hw *hw = NULL; - int err; + int err, len; err = pci_enable_device(pdev); if (err) @@ -4995,6 +5523,13 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) hw->bus.func = PCI_FUNC(pdev->devfn); hw->bus.bus_id = pdev->bus->number; + len = struct_size(adapter->qos_caps, cap, IAVF_MAX_QOS_TC_NUM); + adapter->qos_caps = kzalloc(len, GFP_KERNEL); + if (!adapter->qos_caps) { + err = -ENOMEM; + goto err_alloc_qos_cap; + } + /* set up the locks for the AQ, do this only once in probe * and destroy them only once in remove */ @@ -5028,11 +5563,17 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Setup the wait queue for indicating virtchannel events */ init_waitqueue_head(&adapter->vc_waitqueue); + INIT_LIST_HEAD(&adapter->ptp.aq_cmds); + init_waitqueue_head(&adapter->ptp.phc_time_waitqueue); + mutex_init(&adapter->ptp.aq_cmd_lock); + queue_delayed_work(adapter->wq, &adapter->watchdog_task, msecs_to_jiffies(5 * (pdev->devfn & 0x07))); /* Initialization goes on in the work. Do not add more of it below. */ return 0; +err_alloc_qos_cap: + iounmap(hw->hw_addr); err_ioremap: destroy_workqueue(adapter->wq); err_alloc_wq: @@ -5051,13 +5592,14 @@ err_dma: * * Called when the system (VM) is entering sleep/suspend. **/ -static int __maybe_unused iavf_suspend(struct device *dev_d) +static int iavf_suspend(struct device *dev_d) { struct net_device *netdev = dev_get_drvdata(dev_d); struct iavf_adapter *adapter = netdev_priv(netdev); netif_device_detach(netdev); + netdev_lock(netdev); mutex_lock(&adapter->crit_lock); if (netif_running(netdev)) { @@ -5069,6 +5611,7 @@ static int __maybe_unused iavf_suspend(struct device *dev_d) iavf_reset_interrupt_capability(adapter); mutex_unlock(&adapter->crit_lock); + netdev_unlock(netdev); return 0; } @@ -5079,7 +5622,7 @@ static int __maybe_unused iavf_suspend(struct device *dev_d) * * Called when the system (VM) is resumed from sleep/suspend. **/ -static int __maybe_unused iavf_resume(struct device *dev_d) +static int iavf_resume(struct device *dev_d) { struct pci_dev *pdev = to_pci_dev(dev_d); struct iavf_adapter *adapter; @@ -5167,6 +5710,7 @@ static void iavf_remove(struct pci_dev *pdev) if (netdev->reg_state == NETREG_REGISTERED) unregister_netdev(netdev); + netdev_lock(netdev); mutex_lock(&adapter->crit_lock); dev_info(&adapter->pdev->dev, "Removing device\n"); iavf_change_state(adapter, __IAVF_REMOVE); @@ -5179,6 +5723,8 @@ static void iavf_remove(struct pci_dev *pdev) msleep(50); } + iavf_ptp_release(adapter); + iavf_misc_irq_disable(adapter); /* Shut down all the garbage mashers on the detention level */ cancel_work_sync(&adapter->reset_task); @@ -5203,6 +5749,7 @@ static void iavf_remove(struct pci_dev *pdev) mutex_destroy(&hw->aq.asq_mutex); mutex_unlock(&adapter->crit_lock); mutex_destroy(&adapter->crit_lock); + netdev_unlock(netdev); iounmap(hw->hw_addr); pci_release_regions(pdev); @@ -5266,14 +5813,14 @@ static void iavf_shutdown(struct pci_dev *pdev) pci_set_power_state(pdev, PCI_D3hot); } -static SIMPLE_DEV_PM_OPS(iavf_pm_ops, iavf_suspend, iavf_resume); +static DEFINE_SIMPLE_DEV_PM_OPS(iavf_pm_ops, iavf_suspend, iavf_resume); static struct pci_driver iavf_driver = { .name = iavf_driver_name, .id_table = iavf_pci_tbl, .probe = iavf_probe, .remove = iavf_remove, - .driver.pm = &iavf_pm_ops, + .driver.pm = pm_sleep_ptr(&iavf_pm_ops), .shutdown = iavf_shutdown, }; diff --git a/drivers/net/ethernet/intel/iavf/iavf_prototype.h b/drivers/net/ethernet/intel/iavf/iavf_prototype.h index 4a48e6171405..cac9d1a35a52 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_prototype.h +++ b/drivers/net/ethernet/intel/iavf/iavf_prototype.h @@ -18,7 +18,6 @@ /* adminq functions */ enum iavf_status iavf_init_adminq(struct iavf_hw *hw); enum iavf_status iavf_shutdown_adminq(struct iavf_hw *hw); -void iavf_adminq_init_ring_data(struct iavf_hw *hw); enum iavf_status iavf_clean_arq_element(struct iavf_hw *hw, struct iavf_arq_event_info *e, u16 *events_pending); @@ -33,8 +32,6 @@ bool iavf_asq_done(struct iavf_hw *hw); void iavf_debug_aq(struct iavf_hw *hw, enum iavf_debug_mask mask, void *desc, void *buffer, u16 buf_len); -void iavf_idle_aq(struct iavf_hw *hw); -void iavf_resume_aq(struct iavf_hw *hw); bool iavf_check_asq_alive(struct iavf_hw *hw); enum iavf_status iavf_aq_queue_shutdown(struct iavf_hw *hw, bool unloading); const char *iavf_aq_str(struct iavf_hw *hw, enum iavf_admin_queue_err aq_err); @@ -45,13 +42,6 @@ enum iavf_status iavf_aq_set_rss_lut(struct iavf_hw *hw, u16 seid, enum iavf_status iavf_aq_set_rss_key(struct iavf_hw *hw, u16 seid, struct iavf_aqc_get_set_rss_key_data *key); -extern struct iavf_rx_ptype_decoded iavf_ptype_lookup[]; - -static inline struct iavf_rx_ptype_decoded decode_rx_desc_ptype(u8 ptype) -{ - return iavf_ptype_lookup[ptype]; -} - void iavf_vf_parse_hw_config(struct iavf_hw *hw, struct virtchnl_vf_resource *msg); enum iavf_status iavf_aq_send_msg_to_pf(struct iavf_hw *hw, diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.c b/drivers/net/ethernet/intel/iavf/iavf_ptp.c new file mode 100644 index 000000000000..b4d5eda2e84f --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.c @@ -0,0 +1,485 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2024 Intel Corporation. */ + +#include "iavf.h" +#include "iavf_ptp.h" + +#define iavf_clock_to_adapter(info) \ + container_of_const(info, struct iavf_adapter, ptp.info) + +/** + * iavf_ptp_disable_rx_tstamp - Disable timestamping in Rx rings + * @adapter: private adapter structure + * + * Disable timestamp reporting for all Rx rings. + */ +static void iavf_ptp_disable_rx_tstamp(struct iavf_adapter *adapter) +{ + for (u32 i = 0; i < adapter->num_active_queues; i++) + adapter->rx_rings[i].flags &= ~IAVF_TXRX_FLAGS_HW_TSTAMP; +} + +/** + * iavf_ptp_enable_rx_tstamp - Enable timestamping in Rx rings + * @adapter: private adapter structure + * + * Enable timestamp reporting for all Rx rings. + */ +static void iavf_ptp_enable_rx_tstamp(struct iavf_adapter *adapter) +{ + for (u32 i = 0; i < adapter->num_active_queues; i++) + adapter->rx_rings[i].flags |= IAVF_TXRX_FLAGS_HW_TSTAMP; +} + +/** + * iavf_ptp_set_timestamp_mode - Set device timestamping mode + * @adapter: private adapter structure + * @config: pointer to kernel_hwtstamp_config + * + * Set the timestamping mode requested from the userspace. + * + * Note: this function always translates Rx timestamp requests for any packet + * category into HWTSTAMP_FILTER_ALL. + * + * Return: 0 on success, negative error code otherwise. + */ +static int iavf_ptp_set_timestamp_mode(struct iavf_adapter *adapter, + struct kernel_hwtstamp_config *config) +{ + /* Reserved for future extensions. */ + if (config->flags) + return -EINVAL; + + switch (config->tx_type) { + case HWTSTAMP_TX_OFF: + break; + case HWTSTAMP_TX_ON: + return -EOPNOTSUPP; + default: + return -ERANGE; + } + + if (config->rx_filter == HWTSTAMP_FILTER_NONE) { + iavf_ptp_disable_rx_tstamp(adapter); + return 0; + } else if (config->rx_filter > HWTSTAMP_FILTER_NTP_ALL) { + return -ERANGE; + } else if (!(iavf_ptp_cap_supported(adapter, + VIRTCHNL_1588_PTP_CAP_RX_TSTAMP))) { + return -EOPNOTSUPP; + } + + config->rx_filter = HWTSTAMP_FILTER_ALL; + iavf_ptp_enable_rx_tstamp(adapter); + + return 0; +} + +/** + * iavf_ptp_set_ts_config - Set timestamping configuration + * @adapter: private adapter structure + * @config: pointer to kernel_hwtstamp_config structure + * @extack: pointer to netlink_ext_ack structure + * + * Program the requested timestamping configuration to the device. + * + * Return: 0 on success, negative error code otherwise. + */ +int iavf_ptp_set_ts_config(struct iavf_adapter *adapter, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + int err; + + err = iavf_ptp_set_timestamp_mode(adapter, config); + if (err) + return err; + + /* Save successful settings for future reference */ + adapter->ptp.hwtstamp_config = *config; + + return 0; +} + +/** + * iavf_ptp_cap_supported - Check if a PTP capability is supported + * @adapter: private adapter structure + * @cap: the capability bitmask to check + * + * Return: true if every capability set in cap is also set in the enabled + * capabilities reported by the PF, false otherwise. + */ +bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, u32 cap) +{ + if (!IAVF_PTP_ALLOWED(adapter)) + return false; + + /* Only return true if every bit in cap is set in hw_caps.caps */ + return (adapter->ptp.hw_caps.caps & cap) == cap; +} + +/** + * iavf_allocate_ptp_cmd - Allocate a PTP command message structure + * @v_opcode: the virtchnl opcode + * @msglen: length in bytes of the associated virtchnl structure + * + * Allocates a PTP command message and pre-fills it with the provided message + * length and opcode. + * + * Return: allocated PTP command. + */ +static struct iavf_ptp_aq_cmd *iavf_allocate_ptp_cmd(enum virtchnl_ops v_opcode, + u16 msglen) +{ + struct iavf_ptp_aq_cmd *cmd; + + cmd = kzalloc(struct_size(cmd, msg, msglen), GFP_KERNEL); + if (!cmd) + return NULL; + + cmd->v_opcode = v_opcode; + cmd->msglen = msglen; + + return cmd; +} + +/** + * iavf_queue_ptp_cmd - Queue PTP command for sending over virtchnl + * @adapter: private adapter structure + * @cmd: the command structure to send + * + * Queue the given command structure into the PTP virtchnl command queue tos + * end to the PF. + */ +static void iavf_queue_ptp_cmd(struct iavf_adapter *adapter, + struct iavf_ptp_aq_cmd *cmd) +{ + mutex_lock(&adapter->ptp.aq_cmd_lock); + list_add_tail(&cmd->list, &adapter->ptp.aq_cmds); + mutex_unlock(&adapter->ptp.aq_cmd_lock); + + adapter->aq_required |= IAVF_FLAG_AQ_SEND_PTP_CMD; + mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0); +} + +/** + * iavf_send_phc_read - Send request to read PHC time + * @adapter: private adapter structure + * + * Send a request to obtain the PTP hardware clock time. This allocates the + * VIRTCHNL_OP_1588_PTP_GET_TIME message and queues it up to send to + * indirectly read the PHC time. + * + * This function does not wait for the reply from the PF. + * + * Return: 0 if success, error code otherwise. + */ +static int iavf_send_phc_read(struct iavf_adapter *adapter) +{ + struct iavf_ptp_aq_cmd *cmd; + + if (!adapter->ptp.clock) + return -EOPNOTSUPP; + + cmd = iavf_allocate_ptp_cmd(VIRTCHNL_OP_1588_PTP_GET_TIME, + sizeof(struct virtchnl_phc_time)); + if (!cmd) + return -ENOMEM; + + iavf_queue_ptp_cmd(adapter, cmd); + + return 0; +} + +/** + * iavf_read_phc_indirect - Indirectly read the PHC time via virtchnl + * @adapter: private adapter structure + * @ts: storage for the timestamp value + * @sts: system timestamp values before and after the read + * + * Used when the device does not have direct register access to the PHC time. + * Indirectly reads the time via the VIRTCHNL_OP_1588_PTP_GET_TIME, and waits + * for the reply from the PF. + * + * Based on some simple measurements using ftrace and phc2sys, this clock + * access method has about a ~110 usec latency even when the system is not + * under load. In order to achieve acceptable results when using phc2sys with + * the indirect clock access method, it is recommended to use more + * conservative proportional and integration constants with the P/I servo. + * + * Return: 0 if success, error code otherwise. + */ +static int iavf_read_phc_indirect(struct iavf_adapter *adapter, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + long ret; + int err; + + adapter->ptp.phc_time_ready = false; + + ptp_read_system_prets(sts); + + err = iavf_send_phc_read(adapter); + if (err) + return err; + + ret = wait_event_interruptible_timeout(adapter->ptp.phc_time_waitqueue, + adapter->ptp.phc_time_ready, + HZ); + + ptp_read_system_postts(sts); + + if (ret < 0) + return ret; + else if (!ret) + return -EBUSY; + + *ts = ns_to_timespec64(adapter->ptp.cached_phc_time); + + return 0; +} + +static int iavf_ptp_gettimex64(struct ptp_clock_info *info, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + struct iavf_adapter *adapter = iavf_clock_to_adapter(info); + + if (!adapter->ptp.clock) + return -EOPNOTSUPP; + + return iavf_read_phc_indirect(adapter, ts, sts); +} + +/** + * iavf_ptp_cache_phc_time - Cache PHC time for performing timestamp extension + * @adapter: private adapter structure + * + * Periodically cache the PHC time in order to allow for timestamp extension. + * This is required because the Tx and Rx timestamps only contain 32bits of + * nanoseconds. Timestamp extension allows calculating the corrected 64bit + * timestamp. This algorithm relies on the cached time being within ~1 second + * of the timestamp. + */ +static void iavf_ptp_cache_phc_time(struct iavf_adapter *adapter) +{ + if (!time_is_before_jiffies(adapter->ptp.cached_phc_updated + HZ)) + return; + + /* The response from virtchnl will store the time into + * cached_phc_time. + */ + iavf_send_phc_read(adapter); +} + +/** + * iavf_ptp_do_aux_work - Perform periodic work required for PTP support + * @info: PTP clock info structure + * + * Handler to take care of periodic work required for PTP operation. This + * includes the following tasks: + * + * 1) updating cached_phc_time + * + * cached_phc_time is used by the Tx and Rx timestamp flows in order to + * perform timestamp extension, by carefully comparing the timestamp + * 32bit nanosecond timestamps and determining the corrected 64bit + * timestamp value to report to userspace. This algorithm only works if + * the cached_phc_time is within ~1 second of the Tx or Rx timestamp + * event. This task periodically reads the PHC time and stores it, to + * ensure that timestamp extension operates correctly. + * + * Returns: time in jiffies until the periodic task should be re-scheduled. + */ +static long iavf_ptp_do_aux_work(struct ptp_clock_info *info) +{ + struct iavf_adapter *adapter = iavf_clock_to_adapter(info); + + iavf_ptp_cache_phc_time(adapter); + + /* Check work about twice a second */ + return msecs_to_jiffies(500); +} + +/** + * iavf_ptp_register_clock - Register a new PTP for userspace + * @adapter: private adapter structure + * + * Allocate and register a new PTP clock device if necessary. + * + * Return: 0 if success, error otherwise. + */ +static int iavf_ptp_register_clock(struct iavf_adapter *adapter) +{ + struct ptp_clock_info *ptp_info = &adapter->ptp.info; + struct device *dev = &adapter->pdev->dev; + struct ptp_clock *clock; + + snprintf(ptp_info->name, sizeof(ptp_info->name), "%s-%s-clk", + KBUILD_MODNAME, dev_name(dev)); + ptp_info->owner = THIS_MODULE; + ptp_info->gettimex64 = iavf_ptp_gettimex64; + ptp_info->do_aux_work = iavf_ptp_do_aux_work; + + clock = ptp_clock_register(ptp_info, dev); + if (IS_ERR(clock)) + return PTR_ERR(clock); + + adapter->ptp.clock = clock; + + dev_dbg(&adapter->pdev->dev, "PTP clock %s registered\n", + adapter->ptp.info.name); + + return 0; +} + +/** + * iavf_ptp_init - Initialize PTP support if capability was negotiated + * @adapter: private adapter structure + * + * Initialize PTP functionality, based on the capabilities that the PF has + * enabled for this VF. + */ +void iavf_ptp_init(struct iavf_adapter *adapter) +{ + int err; + + if (!iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_READ_PHC)) { + pci_notice(adapter->pdev, + "Device does not have PTP clock support\n"); + return; + } + + err = iavf_ptp_register_clock(adapter); + if (err) { + pci_err(adapter->pdev, + "Failed to register PTP clock device (%p)\n", + ERR_PTR(err)); + return; + } + + for (int i = 0; i < adapter->num_active_queues; i++) { + struct iavf_ring *rx_ring = &adapter->rx_rings[i]; + + rx_ring->ptp = &adapter->ptp; + } + + ptp_schedule_worker(adapter->ptp.clock, 0); +} + +/** + * iavf_ptp_release - Disable PTP support + * @adapter: private adapter structure + * + * Release all PTP resources that were previously initialized. + */ +void iavf_ptp_release(struct iavf_adapter *adapter) +{ + struct iavf_ptp_aq_cmd *cmd, *tmp; + + if (!adapter->ptp.clock) + return; + + pci_dbg(adapter->pdev, "removing PTP clock %s\n", + adapter->ptp.info.name); + ptp_clock_unregister(adapter->ptp.clock); + adapter->ptp.clock = NULL; + + /* Cancel any remaining uncompleted PTP clock commands */ + mutex_lock(&adapter->ptp.aq_cmd_lock); + list_for_each_entry_safe(cmd, tmp, &adapter->ptp.aq_cmds, list) { + list_del(&cmd->list); + kfree(cmd); + } + adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD; + mutex_unlock(&adapter->ptp.aq_cmd_lock); + + adapter->ptp.hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; + iavf_ptp_disable_rx_tstamp(adapter); +} + +/** + * iavf_ptp_process_caps - Handle change in PTP capabilities + * @adapter: private adapter structure + * + * Handle any state changes necessary due to change in PTP capabilities, such + * as after a device reset or change in configuration from the PF. + */ +void iavf_ptp_process_caps(struct iavf_adapter *adapter) +{ + bool phc = iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_READ_PHC); + + /* Check if the device gained or lost necessary access to support the + * PTP hardware clock. If so, driver must respond appropriately by + * creating or destroying the PTP clock device. + */ + if (adapter->ptp.clock && !phc) + iavf_ptp_release(adapter); + else if (!adapter->ptp.clock && phc) + iavf_ptp_init(adapter); + + /* Check if the device lost access to Rx timestamp incoming packets */ + if (!iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP)) { + adapter->ptp.hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE; + iavf_ptp_disable_rx_tstamp(adapter); + } +} + +/** + * iavf_ptp_extend_32b_timestamp - Convert a 32b nanoseconds timestamp to 64b + * nanoseconds + * @cached_phc_time: recently cached copy of PHC time + * @in_tstamp: Ingress/egress 32b nanoseconds timestamp value + * + * Hardware captures timestamps which contain only 32 bits of nominal + * nanoseconds, as opposed to the 64bit timestamps that the stack expects. + * + * Extend the 32bit nanosecond timestamp using the following algorithm and + * assumptions: + * + * 1) have a recently cached copy of the PHC time + * 2) assume that the in_tstamp was captured 2^31 nanoseconds (~2.1 + * seconds) before or after the PHC time was captured. + * 3) calculate the delta between the cached time and the timestamp + * 4) if the delta is smaller than 2^31 nanoseconds, then the timestamp was + * captured after the PHC time. In this case, the full timestamp is just + * the cached PHC time plus the delta. + * 5) otherwise, if the delta is larger than 2^31 nanoseconds, then the + * timestamp was captured *before* the PHC time, i.e. because the PHC + * cache was updated after the timestamp was captured by hardware. In this + * case, the full timestamp is the cached time minus the inverse delta. + * + * This algorithm works even if the PHC time was updated after a Tx timestamp + * was requested, but before the Tx timestamp event was reported from + * hardware. + * + * This calculation primarily relies on keeping the cached PHC time up to + * date. If the timestamp was captured more than 2^31 nanoseconds after the + * PHC time, it is possible that the lower 32bits of PHC time have + * overflowed more than once, and we might generate an incorrect timestamp. + * + * This is prevented by (a) periodically updating the cached PHC time once + * a second, and (b) discarding any Tx timestamp packet if it has waited for + * a timestamp for more than one second. + * + * Return: extended timestamp (to 64b). + */ +u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time, u32 in_tstamp) +{ + u32 low = lower_32_bits(cached_phc_time); + u32 delta = in_tstamp - low; + u64 ns; + + /* Do not assume that the in_tstamp is always more recent than the + * cached PHC time. If the delta is large, it indicates that the + * in_tstamp was taken in the past, and should be converted + * forward. + */ + if (delta > S32_MAX) + ns = cached_phc_time - (low - in_tstamp); + else + ns = cached_phc_time + delta; + + return ns; +} diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.h b/drivers/net/ethernet/intel/iavf/iavf_ptp.h new file mode 100644 index 000000000000..783b8f287cd9 --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2024 Intel Corporation. */ + +#ifndef _IAVF_PTP_H_ +#define _IAVF_PTP_H_ + +#include "iavf_types.h" + +/* bit indicating whether a 40bit timestamp is valid */ +#define IAVF_PTP_40B_TSTAMP_VALID BIT(24) + +#if IS_ENABLED(CONFIG_PTP_1588_CLOCK) +void iavf_ptp_init(struct iavf_adapter *adapter); +void iavf_ptp_release(struct iavf_adapter *adapter); +void iavf_ptp_process_caps(struct iavf_adapter *adapter); +bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, u32 cap); +void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter); +int iavf_ptp_set_ts_config(struct iavf_adapter *adapter, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack); +u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time, u32 in_tstamp); +#else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ +static inline void iavf_ptp_init(struct iavf_adapter *adapter) { } +static inline void iavf_ptp_release(struct iavf_adapter *adapter) { } +static inline void iavf_ptp_process_caps(struct iavf_adapter *adapter) { } +static inline bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, + u32 cap) +{ + return false; +} + +static inline void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter) { } +static inline int iavf_ptp_set_ts_config(struct iavf_adapter *adapter, + struct kernel_hwtstamp_config *config, + struct netlink_ext_ack *extack) +{ + return -1; +} + +static inline u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time, + u32 in_tstamp) +{ + return 0; +} + +#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ +#endif /* _IAVF_PTP_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_trace.h b/drivers/net/ethernet/intel/iavf/iavf_trace.h index 82fda6f5abf0..c5e4d1823886 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_trace.h +++ b/drivers/net/ethernet/intel/iavf/iavf_trace.h @@ -83,7 +83,7 @@ DECLARE_EVENT_CLASS( __entry->ring = ring; __entry->desc = desc; __entry->buf = buf; - __assign_str(devname, ring->netdev->name); + __assign_str(devname); ), TP_printk( @@ -112,7 +112,7 @@ DECLARE_EVENT_CLASS( iavf_rx_template, TP_PROTO(struct iavf_ring *ring, - union iavf_32byte_rx_desc *desc, + struct iavf_rx_desc *desc, struct sk_buff *skb), TP_ARGS(ring, desc, skb), @@ -128,7 +128,7 @@ DECLARE_EVENT_CLASS( __entry->ring = ring; __entry->desc = desc; __entry->skb = skb; - __assign_str(devname, ring->netdev->name); + __assign_str(devname); ), TP_printk( @@ -140,7 +140,7 @@ DECLARE_EVENT_CLASS( DEFINE_EVENT( iavf_rx_template, iavf_clean_rx_irq, TP_PROTO(struct iavf_ring *ring, - union iavf_32byte_rx_desc *desc, + struct iavf_rx_desc *desc, struct sk_buff *skb), TP_ARGS(ring, desc, skb)); @@ -148,7 +148,7 @@ DEFINE_EVENT( DEFINE_EVENT( iavf_rx_template, iavf_clean_rx_irq_rx, TP_PROTO(struct iavf_ring *ring, - union iavf_32byte_rx_desc *desc, + struct iavf_rx_desc *desc, struct sk_buff *skb), TP_ARGS(ring, desc, skb)); @@ -170,7 +170,7 @@ DECLARE_EVENT_CLASS( TP_fast_assign( __entry->skb = skb; __entry->ring = ring; - __assign_str(devname, ring->netdev->name); + __assign_str(devname); ), TP_printk( diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index b71484c87a84..422312b8b54a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -2,11 +2,32 @@ /* Copyright(c) 2013 - 2018 Intel Corporation. */ #include <linux/bitfield.h> +#include <linux/net/intel/libie/rx.h> #include <linux/prefetch.h> #include "iavf.h" #include "iavf_trace.h" #include "iavf_prototype.h" +#include "iavf_ptp.h" + +/** + * iavf_is_descriptor_done - tests DD bit in Rx descriptor + * @qw1: quad word 1 from descriptor to get Descriptor Done field from + * @flex: is the descriptor flex or legacy + * + * This function tests the descriptor done bit in specified descriptor. Because + * there are two types of descriptors (legacy and flex) the parameter rx_ring + * is used to distinguish. + * + * Return: true or false based on the state of DD bit in Rx descriptor. + */ +static bool iavf_is_descriptor_done(u64 qw1, bool flex) +{ + if (flex) + return FIELD_GET(IAVF_RXD_FLEX_DD_M, qw1); + else + return FIELD_GET(IAVF_RXD_LEGACY_DD_M, qw1); +} static __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size, u32 td_tag) @@ -184,7 +205,7 @@ void iavf_detect_recover_hung(struct iavf_vsi *vsi) * pending work. */ packets = tx_ring->stats.packets & INT_MAX; - if (tx_ring->tx_stats.prev_pkt_ctr == packets) { + if (tx_ring->prev_pkt_ctr == packets) { iavf_force_wb(vsi, tx_ring->q_vector); continue; } @@ -193,7 +214,7 @@ void iavf_detect_recover_hung(struct iavf_vsi *vsi) * to iavf_get_tx_pending() */ smp_rmb(); - tx_ring->tx_stats.prev_pkt_ctr = + tx_ring->prev_pkt_ctr = iavf_get_tx_pending(tx_ring, true) ? packets : -1; } } @@ -319,7 +340,7 @@ static bool iavf_clean_tx_irq(struct iavf_vsi *vsi, ((j / WB_STRIDE) == 0) && (j > 0) && !test_bit(__IAVF_VSI_DOWN, vsi->state) && (IAVF_DESC_UNUSED(tx_ring) != tx_ring->count)) - tx_ring->arm_wb = true; + tx_ring->flags |= IAVF_TXR_FLAGS_ARM_WB; } /* notify netdev of completed buffers */ @@ -674,7 +695,7 @@ int iavf_setup_tx_descriptors(struct iavf_ring *tx_ring) tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; - tx_ring->tx_stats.prev_pkt_ctr = -1; + tx_ring->prev_pkt_ctr = -1; return 0; err: @@ -689,11 +710,8 @@ err: **/ static void iavf_clean_rx_ring(struct iavf_ring *rx_ring) { - unsigned long bi_size; - u16 i; - /* ring already cleared, nothing to do */ - if (!rx_ring->rx_bi) + if (!rx_ring->rx_fqes) return; if (rx_ring->skb) { @@ -701,41 +719,16 @@ static void iavf_clean_rx_ring(struct iavf_ring *rx_ring) rx_ring->skb = NULL; } - /* Free all the Rx ring sk_buffs */ - for (i = 0; i < rx_ring->count; i++) { - struct iavf_rx_buffer *rx_bi = &rx_ring->rx_bi[i]; + /* Free all the Rx ring buffers */ + for (u32 i = rx_ring->next_to_clean; i != rx_ring->next_to_use; ) { + const struct libeth_fqe *rx_fqes = &rx_ring->rx_fqes[i]; - if (!rx_bi->page) - continue; + page_pool_put_full_page(rx_ring->pp, rx_fqes->page, false); - /* Invalidate cache lines that may have been written to by - * device so that we avoid corrupting memory. - */ - dma_sync_single_range_for_cpu(rx_ring->dev, - rx_bi->dma, - rx_bi->page_offset, - rx_ring->rx_buf_len, - DMA_FROM_DEVICE); - - /* free resources associated with mapping */ - dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma, - iavf_rx_pg_size(rx_ring), - DMA_FROM_DEVICE, - IAVF_RX_DMA_ATTR); - - __page_frag_cache_drain(rx_bi->page, rx_bi->pagecnt_bias); - - rx_bi->page = NULL; - rx_bi->page_offset = 0; + if (unlikely(++i == rx_ring->count)) + i = 0; } - bi_size = sizeof(struct iavf_rx_buffer) * rx_ring->count; - memset(rx_ring->rx_bi, 0, bi_size); - - /* Zero out the descriptor ring */ - memset(rx_ring->desc, 0, rx_ring->size); - - rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; } @@ -748,15 +741,22 @@ static void iavf_clean_rx_ring(struct iavf_ring *rx_ring) **/ void iavf_free_rx_resources(struct iavf_ring *rx_ring) { + struct libeth_fq fq = { + .fqes = rx_ring->rx_fqes, + .pp = rx_ring->pp, + }; + iavf_clean_rx_ring(rx_ring); - kfree(rx_ring->rx_bi); - rx_ring->rx_bi = NULL; if (rx_ring->desc) { - dma_free_coherent(rx_ring->dev, rx_ring->size, + dma_free_coherent(rx_ring->pp->p.dev, rx_ring->size, rx_ring->desc, rx_ring->dma); rx_ring->desc = NULL; } + + libeth_rx_fq_destroy(&fq); + rx_ring->rx_fqes = NULL; + rx_ring->pp = NULL; } /** @@ -767,38 +767,46 @@ void iavf_free_rx_resources(struct iavf_ring *rx_ring) **/ int iavf_setup_rx_descriptors(struct iavf_ring *rx_ring) { - struct device *dev = rx_ring->dev; - int bi_size; - - /* warn if we are about to overwrite the pointer */ - WARN_ON(rx_ring->rx_bi); - bi_size = sizeof(struct iavf_rx_buffer) * rx_ring->count; - rx_ring->rx_bi = kzalloc(bi_size, GFP_KERNEL); - if (!rx_ring->rx_bi) - goto err; + struct libeth_fq fq = { + .count = rx_ring->count, + .buf_len = LIBIE_MAX_RX_BUF_LEN, + .nid = NUMA_NO_NODE, + }; + int ret; + + ret = libeth_rx_fq_create(&fq, &rx_ring->q_vector->napi); + if (ret) + return ret; + + rx_ring->pp = fq.pp; + rx_ring->rx_fqes = fq.fqes; + rx_ring->truesize = fq.truesize; + rx_ring->rx_buf_len = fq.buf_len; u64_stats_init(&rx_ring->syncp); /* Round up to nearest 4K */ - rx_ring->size = rx_ring->count * sizeof(union iavf_32byte_rx_desc); + rx_ring->size = rx_ring->count * sizeof(struct iavf_rx_desc); rx_ring->size = ALIGN(rx_ring->size, 4096); - rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size, + rx_ring->desc = dma_alloc_coherent(fq.pp->p.dev, rx_ring->size, &rx_ring->dma, GFP_KERNEL); if (!rx_ring->desc) { - dev_info(dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n", + dev_info(fq.pp->p.dev, "Unable to allocate memory for the Rx descriptor ring, size=%d\n", rx_ring->size); goto err; } - rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; return 0; + err: - kfree(rx_ring->rx_bi); - rx_ring->rx_bi = NULL; + libeth_rx_fq_destroy(&fq); + rx_ring->rx_fqes = NULL; + rx_ring->pp = NULL; + return -ENOMEM; } @@ -811,9 +819,6 @@ static void iavf_release_rx_desc(struct iavf_ring *rx_ring, u32 val) { rx_ring->next_to_use = val; - /* update next to alloc since we have filled the ring */ - rx_ring->next_to_alloc = val; - /* Force memory writes to complete before letting h/w * know there are new descriptors to fetch. (Only * applicable for weak-ordered memory model archs, @@ -824,69 +829,6 @@ static void iavf_release_rx_desc(struct iavf_ring *rx_ring, u32 val) } /** - * iavf_rx_offset - Return expected offset into page to access data - * @rx_ring: Ring we are requesting offset of - * - * Returns the offset value for ring into the data buffer. - */ -static unsigned int iavf_rx_offset(struct iavf_ring *rx_ring) -{ - return ring_uses_build_skb(rx_ring) ? IAVF_SKB_PAD : 0; -} - -/** - * iavf_alloc_mapped_page - recycle or make a new page - * @rx_ring: ring to use - * @bi: rx_buffer struct to modify - * - * Returns true if the page was successfully allocated or - * reused. - **/ -static bool iavf_alloc_mapped_page(struct iavf_ring *rx_ring, - struct iavf_rx_buffer *bi) -{ - struct page *page = bi->page; - dma_addr_t dma; - - /* since we are recycling buffers we should seldom need to alloc */ - if (likely(page)) { - rx_ring->rx_stats.page_reuse_count++; - return true; - } - - /* alloc new page for storage */ - page = dev_alloc_pages(iavf_rx_pg_order(rx_ring)); - if (unlikely(!page)) { - rx_ring->rx_stats.alloc_page_failed++; - return false; - } - - /* map page for use */ - dma = dma_map_page_attrs(rx_ring->dev, page, 0, - iavf_rx_pg_size(rx_ring), - DMA_FROM_DEVICE, - IAVF_RX_DMA_ATTR); - - /* if mapping failed free memory back to system since - * there isn't much point in holding memory we can't use - */ - if (dma_mapping_error(rx_ring->dev, dma)) { - __free_pages(page, iavf_rx_pg_order(rx_ring)); - rx_ring->rx_stats.alloc_page_failed++; - return false; - } - - bi->dma = dma; - bi->page = page; - bi->page_offset = iavf_rx_offset(rx_ring); - - /* initialize pagecnt_bias to 1 representing we fully own page */ - bi->pagecnt_bias = 1; - - return true; -} - -/** * iavf_receive_skb - Send a completed packet up the stack * @rx_ring: rx ring in play * @skb: packet to send up @@ -916,43 +858,42 @@ static void iavf_receive_skb(struct iavf_ring *rx_ring, **/ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count) { + const struct libeth_fq_fp fq = { + .pp = rx_ring->pp, + .fqes = rx_ring->rx_fqes, + .truesize = rx_ring->truesize, + .count = rx_ring->count, + }; u16 ntu = rx_ring->next_to_use; - union iavf_rx_desc *rx_desc; - struct iavf_rx_buffer *bi; + struct iavf_rx_desc *rx_desc; /* do nothing if no valid netdev defined */ if (!rx_ring->netdev || !cleaned_count) return false; rx_desc = IAVF_RX_DESC(rx_ring, ntu); - bi = &rx_ring->rx_bi[ntu]; do { - if (!iavf_alloc_mapped_page(rx_ring, bi)) - goto no_buffers; + dma_addr_t addr; - /* sync the buffer for use by the device */ - dma_sync_single_range_for_device(rx_ring->dev, bi->dma, - bi->page_offset, - rx_ring->rx_buf_len, - DMA_FROM_DEVICE); + addr = libeth_rx_alloc(&fq, ntu); + if (addr == DMA_MAPPING_ERROR) + goto no_buffers; /* Refresh the desc even if buffer_addrs didn't change * because each write-back erases this info. */ - rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset); + rx_desc->qw0 = cpu_to_le64(addr); rx_desc++; - bi++; ntu++; if (unlikely(ntu == rx_ring->count)) { rx_desc = IAVF_RX_DESC(rx_ring, 0); - bi = rx_ring->rx_bi; ntu = 0; } /* clear the status bits for the next_to_use descriptor */ - rx_desc->wb.qword1.status_error_len = 0; + rx_desc->qw1 = 0; cleaned_count--; } while (cleaned_count); @@ -966,6 +907,8 @@ no_buffers: if (rx_ring->next_to_use != ntu) iavf_release_rx_desc(rx_ring, ntu); + rx_ring->rx_stats.alloc_page_failed++; + /* make sure to come back via polling to try again after * allocation failure */ @@ -973,81 +916,46 @@ no_buffers: } /** - * iavf_rx_checksum - Indicate in skb if hw indicated a good cksum + * iavf_rx_csum - Indicate in skb if hw indicated a good checksum * @vsi: the VSI we care about * @skb: skb currently being received and modified - * @rx_desc: the receive descriptor + * @decoded_pt: decoded ptype information + * @csum_bits: decoded Rx descriptor information **/ -static void iavf_rx_checksum(struct iavf_vsi *vsi, - struct sk_buff *skb, - union iavf_rx_desc *rx_desc) +static void iavf_rx_csum(const struct iavf_vsi *vsi, struct sk_buff *skb, + struct libeth_rx_pt decoded_pt, + struct libeth_rx_csum csum_bits) { - struct iavf_rx_ptype_decoded decoded; - u32 rx_error, rx_status; bool ipv4, ipv6; - u8 ptype; - u64 qword; - - qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword); - rx_error = FIELD_GET(IAVF_RXD_QW1_ERROR_MASK, qword); - rx_status = FIELD_GET(IAVF_RXD_QW1_STATUS_MASK, qword); - decoded = decode_rx_desc_ptype(ptype); skb->ip_summed = CHECKSUM_NONE; - skb_checksum_none_assert(skb); - - /* Rx csum enabled and ip headers found? */ - if (!(vsi->netdev->features & NETIF_F_RXCSUM)) - return; - /* did the hardware decode the packet and checksum? */ - if (!(rx_status & BIT(IAVF_RX_DESC_STATUS_L3L4P_SHIFT))) - return; - - /* both known and outer_ip must be set for the below code to work */ - if (!(decoded.known && decoded.outer_ip)) + if (unlikely(!csum_bits.l3l4p)) return; - ipv4 = (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP) && - (decoded.outer_ip_ver == IAVF_RX_PTYPE_OUTER_IPV4); - ipv6 = (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP) && - (decoded.outer_ip_ver == IAVF_RX_PTYPE_OUTER_IPV6); + ipv4 = libeth_rx_pt_get_ip_ver(decoded_pt) == LIBETH_RX_PT_OUTER_IPV4; + ipv6 = libeth_rx_pt_get_ip_ver(decoded_pt) == LIBETH_RX_PT_OUTER_IPV6; - if (ipv4 && - (rx_error & (BIT(IAVF_RX_DESC_ERROR_IPE_SHIFT) | - BIT(IAVF_RX_DESC_ERROR_EIPE_SHIFT)))) + if (unlikely(ipv4 && (csum_bits.ipe || csum_bits.eipe))) goto checksum_fail; /* likely incorrect csum if alternate IP extension headers found */ - if (ipv6 && - rx_status & BIT(IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT)) - /* don't increment checksum err here, non-fatal err */ + if (unlikely(ipv6 && csum_bits.ipv6exadd)) return; /* there was some L4 error, count error and punt packet to the stack */ - if (rx_error & BIT(IAVF_RX_DESC_ERROR_L4E_SHIFT)) + if (unlikely(csum_bits.l4e)) goto checksum_fail; /* handle packets that were not able to be checksummed due * to arrival speed, in this case the stack can compute * the csum. */ - if (rx_error & BIT(IAVF_RX_DESC_ERROR_PPRS_SHIFT)) + if (unlikely(csum_bits.pprs)) return; - /* Only report checksum unnecessary for TCP, UDP, or SCTP */ - switch (decoded.inner_prot) { - case IAVF_RX_PTYPE_INNER_PROT_TCP: - case IAVF_RX_PTYPE_INNER_PROT_UDP: - case IAVF_RX_PTYPE_INNER_PROT_SCTP: - skb->ip_summed = CHECKSUM_UNNECESSARY; - fallthrough; - default: - break; - } - + skb->ip_summed = CHECKSUM_UNNECESSARY; return; checksum_fail: @@ -1055,73 +963,196 @@ checksum_fail: } /** - * iavf_ptype_to_htype - get a hash type - * @ptype: the ptype value from the descriptor + * iavf_legacy_rx_csum - Indicate in skb if hw indicated a good checksum + * @vsi: the VSI we care about + * @qw1: quad word 1 + * @decoded_pt: decoded packet type * - * Returns a hash type to be used by skb_set_hash + * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte + * descriptor writeback format. + * + * Return: decoded checksum bits. **/ -static int iavf_ptype_to_htype(u8 ptype) +static struct libeth_rx_csum +iavf_legacy_rx_csum(const struct iavf_vsi *vsi, u64 qw1, + const struct libeth_rx_pt decoded_pt) { - struct iavf_rx_ptype_decoded decoded = decode_rx_desc_ptype(ptype); + struct libeth_rx_csum csum_bits = {}; - if (!decoded.known) - return PKT_HASH_TYPE_NONE; + if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded_pt)) + return csum_bits; - if (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP && - decoded.payload_layer == IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY4) - return PKT_HASH_TYPE_L4; - else if (decoded.outer_ip == IAVF_RX_PTYPE_OUTER_IP && - decoded.payload_layer == IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY3) - return PKT_HASH_TYPE_L3; - else - return PKT_HASH_TYPE_L2; + csum_bits.ipe = FIELD_GET(IAVF_RXD_LEGACY_IPE_M, qw1); + csum_bits.eipe = FIELD_GET(IAVF_RXD_LEGACY_EIPE_M, qw1); + csum_bits.l4e = FIELD_GET(IAVF_RXD_LEGACY_L4E_M, qw1); + csum_bits.pprs = FIELD_GET(IAVF_RXD_LEGACY_PPRS_M, qw1); + csum_bits.l3l4p = FIELD_GET(IAVF_RXD_LEGACY_L3L4P_M, qw1); + csum_bits.ipv6exadd = FIELD_GET(IAVF_RXD_LEGACY_IPV6EXADD_M, qw1); + + return csum_bits; } /** - * iavf_rx_hash - set the hash value in the skb + * iavf_flex_rx_csum - Indicate in skb if hw indicated a good checksum + * @vsi: the VSI we care about + * @qw1: quad word 1 + * @decoded_pt: decoded packet type + * + * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible + * descriptor writeback format. + * + * Return: decoded checksum bits. + **/ +static struct libeth_rx_csum +iavf_flex_rx_csum(const struct iavf_vsi *vsi, u64 qw1, + const struct libeth_rx_pt decoded_pt) +{ + struct libeth_rx_csum csum_bits = {}; + + if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded_pt)) + return csum_bits; + + csum_bits.ipe = FIELD_GET(IAVF_RXD_FLEX_XSUM_IPE_M, qw1); + csum_bits.eipe = FIELD_GET(IAVF_RXD_FLEX_XSUM_EIPE_M, qw1); + csum_bits.l4e = FIELD_GET(IAVF_RXD_FLEX_XSUM_L4E_M, qw1); + csum_bits.eudpe = FIELD_GET(IAVF_RXD_FLEX_XSUM_EUDPE_M, qw1); + csum_bits.l3l4p = FIELD_GET(IAVF_RXD_FLEX_L3L4P_M, qw1); + csum_bits.ipv6exadd = FIELD_GET(IAVF_RXD_FLEX_IPV6EXADD_M, qw1); + csum_bits.nat = FIELD_GET(IAVF_RXD_FLEX_NAT_M, qw1); + + return csum_bits; +} + +/** + * iavf_legacy_rx_hash - set the hash value in the skb * @ring: descriptor ring - * @rx_desc: specific descriptor + * @qw0: quad word 0 + * @qw1: quad word 1 * @skb: skb currently being received and modified - * @rx_ptype: Rx packet type + * @decoded_pt: decoded packet type + * + * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte + * descriptor writeback format. **/ -static void iavf_rx_hash(struct iavf_ring *ring, - union iavf_rx_desc *rx_desc, - struct sk_buff *skb, - u8 rx_ptype) +static void iavf_legacy_rx_hash(const struct iavf_ring *ring, __le64 qw0, + __le64 qw1, struct sk_buff *skb, + const struct libeth_rx_pt decoded_pt) { + const __le64 rss_mask = cpu_to_le64(IAVF_RXD_LEGACY_FLTSTAT_M); u32 hash; - const __le64 rss_mask = - cpu_to_le64((u64)IAVF_RX_DESC_FLTSTAT_RSS_HASH << - IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT); - if (!(ring->netdev->features & NETIF_F_RXHASH)) + if (!libeth_rx_pt_has_hash(ring->netdev, decoded_pt)) return; - if ((rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask) { - hash = le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss); - skb_set_hash(skb, hash, iavf_ptype_to_htype(rx_ptype)); + if ((qw1 & rss_mask) == rss_mask) { + hash = le64_get_bits(qw0, IAVF_RXD_LEGACY_RSS_M); + libeth_rx_pt_set_hash(skb, hash, decoded_pt); } } /** + * iavf_flex_rx_hash - set the hash value in the skb + * @ring: descriptor ring + * @qw1: quad word 1 + * @skb: skb currently being received and modified + * @decoded_pt: decoded packet type + * + * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible + * descriptor writeback format. + **/ +static void iavf_flex_rx_hash(const struct iavf_ring *ring, __le64 qw1, + struct sk_buff *skb, + const struct libeth_rx_pt decoded_pt) +{ + bool rss_valid; + u32 hash; + + if (!libeth_rx_pt_has_hash(ring->netdev, decoded_pt)) + return; + + rss_valid = le64_get_bits(qw1, IAVF_RXD_FLEX_RSS_VALID_M); + if (rss_valid) { + hash = le64_get_bits(qw1, IAVF_RXD_FLEX_RSS_HASH_M); + libeth_rx_pt_set_hash(skb, hash, decoded_pt); + } +} + +/** + * iavf_flex_rx_tstamp - Capture Rx timestamp from the descriptor + * @rx_ring: descriptor ring + * @qw2: quad word 2 of descriptor + * @qw3: quad word 3 of descriptor + * @skb: skb currently being received + * + * Read the Rx timestamp value from the descriptor and pass it to the stack. + * + * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible + * descriptor writeback format. + */ +static void iavf_flex_rx_tstamp(const struct iavf_ring *rx_ring, __le64 qw2, + __le64 qw3, struct sk_buff *skb) +{ + u32 tstamp; + u64 ns; + + /* Skip processing if timestamps aren't enabled */ + if (!(rx_ring->flags & IAVF_TXRX_FLAGS_HW_TSTAMP)) + return; + + /* Check if this Rx descriptor has a valid timestamp */ + if (!le64_get_bits(qw2, IAVF_PTP_40B_TSTAMP_VALID)) + return; + + /* the ts_low field only contains the valid bit and sub-nanosecond + * precision, so we don't need to extract it. + */ + tstamp = le64_get_bits(qw3, IAVF_RXD_FLEX_QW3_TSTAMP_HIGH_M); + + ns = iavf_ptp_extend_32b_timestamp(rx_ring->ptp->cached_phc_time, + tstamp); + + *skb_hwtstamps(skb) = (struct skb_shared_hwtstamps) { + .hwtstamp = ns_to_ktime(ns), + }; +} + +/** * iavf_process_skb_fields - Populate skb header fields from Rx descriptor * @rx_ring: rx descriptor ring packet is being transacted on * @rx_desc: pointer to the EOP Rx descriptor * @skb: pointer to current skb being populated - * @rx_ptype: the packet type decoded by hardware + * @ptype: the packet type decoded by hardware + * @flex: is the descriptor flex or legacy * * This function checks the ring, descriptor, and packet information in * order to populate the hash, checksum, VLAN, protocol, and * other fields within the skb. **/ -static void -iavf_process_skb_fields(struct iavf_ring *rx_ring, - union iavf_rx_desc *rx_desc, struct sk_buff *skb, - u8 rx_ptype) +static void iavf_process_skb_fields(const struct iavf_ring *rx_ring, + const struct iavf_rx_desc *rx_desc, + struct sk_buff *skb, u32 ptype, + bool flex) { - iavf_rx_hash(rx_ring, rx_desc, skb, rx_ptype); - - iavf_rx_checksum(rx_ring->vsi, skb, rx_desc); + struct libeth_rx_csum csum_bits; + struct libeth_rx_pt decoded_pt; + __le64 qw0 = rx_desc->qw0; + __le64 qw1 = rx_desc->qw1; + __le64 qw2 = rx_desc->qw2; + __le64 qw3 = rx_desc->qw3; + + decoded_pt = libie_rx_pt_parse(ptype); + + if (flex) { + iavf_flex_rx_hash(rx_ring, qw1, skb, decoded_pt); + iavf_flex_rx_tstamp(rx_ring, qw2, qw3, skb); + csum_bits = iavf_flex_rx_csum(rx_ring->vsi, le64_to_cpu(qw1), + decoded_pt); + } else { + iavf_legacy_rx_hash(rx_ring, qw0, qw1, skb, decoded_pt); + csum_bits = iavf_legacy_rx_csum(rx_ring->vsi, le64_to_cpu(qw1), + decoded_pt); + } + iavf_rx_csum(rx_ring->vsi, skb, decoded_pt, csum_bits); skb_record_rx_queue(skb, rx_ring->queue_index); @@ -1152,95 +1183,9 @@ static bool iavf_cleanup_headers(struct iavf_ring *rx_ring, struct sk_buff *skb) } /** - * iavf_reuse_rx_page - page flip buffer and store it back on the ring - * @rx_ring: rx descriptor ring to store buffers on - * @old_buff: donor buffer to have page reused - * - * Synchronizes page for reuse by the adapter - **/ -static void iavf_reuse_rx_page(struct iavf_ring *rx_ring, - struct iavf_rx_buffer *old_buff) -{ - struct iavf_rx_buffer *new_buff; - u16 nta = rx_ring->next_to_alloc; - - new_buff = &rx_ring->rx_bi[nta]; - - /* update, and store next to alloc */ - nta++; - rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; - - /* transfer page from old buffer to new buffer */ - new_buff->dma = old_buff->dma; - new_buff->page = old_buff->page; - new_buff->page_offset = old_buff->page_offset; - new_buff->pagecnt_bias = old_buff->pagecnt_bias; -} - -/** - * iavf_can_reuse_rx_page - Determine if this page can be reused by - * the adapter for another receive - * - * @rx_buffer: buffer containing the page - * - * If page is reusable, rx_buffer->page_offset is adjusted to point to - * an unused region in the page. - * - * For small pages, @truesize will be a constant value, half the size - * of the memory at page. We'll attempt to alternate between high and - * low halves of the page, with one half ready for use by the hardware - * and the other half being consumed by the stack. We use the page - * ref count to determine whether the stack has finished consuming the - * portion of this page that was passed up with a previous packet. If - * the page ref count is >1, we'll assume the "other" half page is - * still busy, and this page cannot be reused. - * - * For larger pages, @truesize will be the actual space used by the - * received packet (adjusted upward to an even multiple of the cache - * line size). This will advance through the page by the amount - * actually consumed by the received packets while there is still - * space for a buffer. Each region of larger pages will be used at - * most once, after which the page will not be reused. - * - * In either case, if the page is reusable its refcount is increased. - **/ -static bool iavf_can_reuse_rx_page(struct iavf_rx_buffer *rx_buffer) -{ - unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; - struct page *page = rx_buffer->page; - - /* Is any reuse possible? */ - if (!dev_page_is_reusable(page)) - return false; - -#if (PAGE_SIZE < 8192) - /* if we are only owner of page we can reuse it */ - if (unlikely((page_count(page) - pagecnt_bias) > 1)) - return false; -#else -#define IAVF_LAST_OFFSET \ - (SKB_WITH_OVERHEAD(PAGE_SIZE) - IAVF_RXBUFFER_2048) - if (rx_buffer->page_offset > IAVF_LAST_OFFSET) - return false; -#endif - - /* If we have drained the page fragment pool we need to update - * the pagecnt_bias and page count so that we fully restock the - * number of references the driver holds. - */ - if (unlikely(!pagecnt_bias)) { - page_ref_add(page, USHRT_MAX); - rx_buffer->pagecnt_bias = USHRT_MAX; - } - - return true; -} - -/** * iavf_add_rx_frag - Add contents of Rx buffer to sk_buff - * @rx_ring: rx descriptor ring to transact packets on - * @rx_buffer: buffer containing page to add * @skb: sk_buff to place the data into + * @rx_buffer: buffer containing page to add * @size: packet length from rx_desc * * This function will add the data contained in rx_buffer->page to the skb. @@ -1248,210 +1193,53 @@ static bool iavf_can_reuse_rx_page(struct iavf_rx_buffer *rx_buffer) * * The function will then update the page offset. **/ -static void iavf_add_rx_frag(struct iavf_ring *rx_ring, - struct iavf_rx_buffer *rx_buffer, - struct sk_buff *skb, +static void iavf_add_rx_frag(struct sk_buff *skb, + const struct libeth_fqe *rx_buffer, unsigned int size) { -#if (PAGE_SIZE < 8192) - unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2; -#else - unsigned int truesize = SKB_DATA_ALIGN(size + iavf_rx_offset(rx_ring)); -#endif - - if (!size) - return; + u32 hr = rx_buffer->page->pp->p.offset; skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, - rx_buffer->page_offset, size, truesize); - - /* page is being used so we must update the page offset */ -#if (PAGE_SIZE < 8192) - rx_buffer->page_offset ^= truesize; -#else - rx_buffer->page_offset += truesize; -#endif -} - -/** - * iavf_get_rx_buffer - Fetch Rx buffer and synchronize data for use - * @rx_ring: rx descriptor ring to transact packets on - * @size: size of buffer to add to skb - * - * This function will pull an Rx buffer from the ring and synchronize it - * for use by the CPU. - */ -static struct iavf_rx_buffer *iavf_get_rx_buffer(struct iavf_ring *rx_ring, - const unsigned int size) -{ - struct iavf_rx_buffer *rx_buffer; - - rx_buffer = &rx_ring->rx_bi[rx_ring->next_to_clean]; - prefetchw(rx_buffer->page); - if (!size) - return rx_buffer; - - /* we are reusing so sync this buffer for CPU use */ - dma_sync_single_range_for_cpu(rx_ring->dev, - rx_buffer->dma, - rx_buffer->page_offset, - size, - DMA_FROM_DEVICE); - - /* We have pulled a buffer for use, so decrement pagecnt_bias */ - rx_buffer->pagecnt_bias--; - - return rx_buffer; -} - -/** - * iavf_construct_skb - Allocate skb and populate it - * @rx_ring: rx descriptor ring to transact packets on - * @rx_buffer: rx buffer to pull data from - * @size: size of buffer to add to skb - * - * This function allocates an skb. It then populates it with the page - * data from the current receive descriptor, taking care to set up the - * skb correctly. - */ -static struct sk_buff *iavf_construct_skb(struct iavf_ring *rx_ring, - struct iavf_rx_buffer *rx_buffer, - unsigned int size) -{ - void *va; -#if (PAGE_SIZE < 8192) - unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2; -#else - unsigned int truesize = SKB_DATA_ALIGN(size); -#endif - unsigned int headlen; - struct sk_buff *skb; - - if (!rx_buffer) - return NULL; - /* prefetch first cache line of first page */ - va = page_address(rx_buffer->page) + rx_buffer->page_offset; - net_prefetch(va); - - /* allocate a skb to store the frags */ - skb = __napi_alloc_skb(&rx_ring->q_vector->napi, - IAVF_RX_HDR_SIZE, - GFP_ATOMIC | __GFP_NOWARN); - if (unlikely(!skb)) - return NULL; - - /* Determine available headroom for copy */ - headlen = size; - if (headlen > IAVF_RX_HDR_SIZE) - headlen = eth_get_headlen(skb->dev, va, IAVF_RX_HDR_SIZE); - - /* align pull length to size of long to optimize memcpy performance */ - memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); - - /* update all of the pointers */ - size -= headlen; - if (size) { - skb_add_rx_frag(skb, 0, rx_buffer->page, - rx_buffer->page_offset + headlen, - size, truesize); - - /* buffer is used by skb, update page_offset */ -#if (PAGE_SIZE < 8192) - rx_buffer->page_offset ^= truesize; -#else - rx_buffer->page_offset += truesize; -#endif - } else { - /* buffer is unused, reset bias back to rx_buffer */ - rx_buffer->pagecnt_bias++; - } - - return skb; + rx_buffer->offset + hr, size, rx_buffer->truesize); } /** * iavf_build_skb - Build skb around an existing buffer - * @rx_ring: Rx descriptor ring to transact packets on * @rx_buffer: Rx buffer to pull data from * @size: size of buffer to add to skb * * This function builds an skb around an existing Rx buffer, taking care * to set up the skb correctly and avoid any memcpy overhead. */ -static struct sk_buff *iavf_build_skb(struct iavf_ring *rx_ring, - struct iavf_rx_buffer *rx_buffer, +static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer, unsigned int size) { - void *va; -#if (PAGE_SIZE < 8192) - unsigned int truesize = iavf_rx_pg_size(rx_ring) / 2; -#else - unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + - SKB_DATA_ALIGN(IAVF_SKB_PAD + size); -#endif + u32 hr = rx_buffer->page->pp->p.offset; struct sk_buff *skb; + void *va; - if (!rx_buffer || !size) - return NULL; /* prefetch first cache line of first page */ - va = page_address(rx_buffer->page) + rx_buffer->page_offset; - net_prefetch(va); + va = page_address(rx_buffer->page) + rx_buffer->offset; + net_prefetch(va + hr); /* build an skb around the page buffer */ - skb = napi_build_skb(va - IAVF_SKB_PAD, truesize); + skb = napi_build_skb(va, rx_buffer->truesize); if (unlikely(!skb)) return NULL; + skb_mark_for_recycle(skb); + /* update pointers within the skb to store the data */ - skb_reserve(skb, IAVF_SKB_PAD); + skb_reserve(skb, hr); __skb_put(skb, size); - /* buffer is used by skb, update page_offset */ -#if (PAGE_SIZE < 8192) - rx_buffer->page_offset ^= truesize; -#else - rx_buffer->page_offset += truesize; -#endif - return skb; } /** - * iavf_put_rx_buffer - Clean up used buffer and either recycle or free - * @rx_ring: rx descriptor ring to transact packets on - * @rx_buffer: rx buffer to pull data from - * - * This function will clean up the contents of the rx_buffer. It will - * either recycle the buffer or unmap it and free the associated resources. - */ -static void iavf_put_rx_buffer(struct iavf_ring *rx_ring, - struct iavf_rx_buffer *rx_buffer) -{ - if (!rx_buffer) - return; - - if (iavf_can_reuse_rx_page(rx_buffer)) { - /* hand second half of page back to the ring */ - iavf_reuse_rx_page(rx_ring, rx_buffer); - rx_ring->rx_stats.page_reuse_count++; - } else { - /* we are not reusing the buffer so unmap it */ - dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, - iavf_rx_pg_size(rx_ring), - DMA_FROM_DEVICE, IAVF_RX_DMA_ATTR); - __page_frag_cache_drain(rx_buffer->page, - rx_buffer->pagecnt_bias); - } - - /* clear contents of buffer_info */ - rx_buffer->page = NULL; -} - -/** * iavf_is_non_eop - process handling of non-EOP buffers * @rx_ring: Rx ring being processed - * @rx_desc: Rx descriptor for current buffer - * @skb: Current socket buffer containing buffer in progress + * @fields: Rx descriptor extracted fields * * This function updates next to clean. If the buffer is an EOP buffer * this function exits returning false, otherwise it will place the @@ -1459,8 +1247,7 @@ static void iavf_put_rx_buffer(struct iavf_ring *rx_ring, * that this is in fact a non-EOP buffer. **/ static bool iavf_is_non_eop(struct iavf_ring *rx_ring, - union iavf_rx_desc *rx_desc, - struct sk_buff *skb) + struct libeth_rqe_info fields) { u32 ntc = rx_ring->next_to_clean + 1; @@ -1471,8 +1258,7 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring, prefetch(IAVF_RX_DESC(rx_ring, ntc)); /* if we are the last buffer then there is nothing else to do */ -#define IAVF_RXD_EOF BIT(IAVF_RX_DESC_STATUS_EOF_SHIFT) - if (likely(iavf_test_staterr(rx_desc, IAVF_RXD_EOF))) + if (likely(fields.eop)) return false; rx_ring->rx_stats.non_eop_descs++; @@ -1481,6 +1267,109 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring, } /** + * iavf_extract_legacy_rx_fields - Extract fields from the Rx descriptor + * @rx_ring: rx descriptor ring + * @rx_desc: the descriptor to process + * + * Decode the Rx descriptor and extract relevant information including the + * size, VLAN tag, Rx packet type, end of packet field and RXE field value. + * + * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte + * descriptor writeback format. + * + * Return: fields extracted from the Rx descriptor. + */ +static struct libeth_rqe_info +iavf_extract_legacy_rx_fields(const struct iavf_ring *rx_ring, + const struct iavf_rx_desc *rx_desc) +{ + u64 qw0 = le64_to_cpu(rx_desc->qw0); + u64 qw1 = le64_to_cpu(rx_desc->qw1); + u64 qw2 = le64_to_cpu(rx_desc->qw2); + struct libeth_rqe_info fields; + bool l2tag1p, l2tag2p; + + fields.eop = FIELD_GET(IAVF_RXD_LEGACY_EOP_M, qw1); + fields.len = FIELD_GET(IAVF_RXD_LEGACY_LENGTH_M, qw1); + + if (!fields.eop) + return fields; + + fields.rxe = FIELD_GET(IAVF_RXD_LEGACY_RXE_M, qw1); + fields.ptype = FIELD_GET(IAVF_RXD_LEGACY_PTYPE_M, qw1); + fields.vlan = 0; + + if (rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1) { + l2tag1p = FIELD_GET(IAVF_RXD_LEGACY_L2TAG1P_M, qw1); + if (l2tag1p) + fields.vlan = FIELD_GET(IAVF_RXD_LEGACY_L2TAG1_M, qw0); + } else if (rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2) { + l2tag2p = FIELD_GET(IAVF_RXD_LEGACY_L2TAG2P_M, qw2); + if (l2tag2p) + fields.vlan = FIELD_GET(IAVF_RXD_LEGACY_L2TAG2_M, qw2); + } + + return fields; +} + +/** + * iavf_extract_flex_rx_fields - Extract fields from the Rx descriptor + * @rx_ring: rx descriptor ring + * @rx_desc: the descriptor to process + * + * Decode the Rx descriptor and extract relevant information including the + * size, VLAN tag, Rx packet type, end of packet field and RXE field value. + * + * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible + * descriptor writeback format. + * + * Return: fields extracted from the Rx descriptor. + */ +static struct libeth_rqe_info +iavf_extract_flex_rx_fields(const struct iavf_ring *rx_ring, + const struct iavf_rx_desc *rx_desc) +{ + struct libeth_rqe_info fields = {}; + u64 qw0 = le64_to_cpu(rx_desc->qw0); + u64 qw1 = le64_to_cpu(rx_desc->qw1); + u64 qw2 = le64_to_cpu(rx_desc->qw2); + bool l2tag1p, l2tag2p; + + fields.eop = FIELD_GET(IAVF_RXD_FLEX_EOP_M, qw1); + fields.len = FIELD_GET(IAVF_RXD_FLEX_PKT_LEN_M, qw0); + + if (!fields.eop) + return fields; + + fields.rxe = FIELD_GET(IAVF_RXD_FLEX_RXE_M, qw1); + fields.ptype = FIELD_GET(IAVF_RXD_FLEX_PTYPE_M, qw0); + fields.vlan = 0; + + if (rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1) { + l2tag1p = FIELD_GET(IAVF_RXD_FLEX_L2TAG1P_M, qw1); + if (l2tag1p) + fields.vlan = FIELD_GET(IAVF_RXD_FLEX_L2TAG1_M, qw1); + } else if (rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2) { + l2tag2p = FIELD_GET(IAVF_RXD_FLEX_L2TAG2P_M, qw2); + if (l2tag2p) + fields.vlan = FIELD_GET(IAVF_RXD_FLEX_L2TAG2_2_M, qw2); + } + + return fields; +} + +static struct libeth_rqe_info +iavf_extract_rx_fields(const struct iavf_ring *rx_ring, + const struct iavf_rx_desc *rx_desc, + bool flex) +{ + if (flex) + return iavf_extract_flex_rx_fields(rx_ring, rx_desc); + else + return iavf_extract_legacy_rx_fields(rx_ring, rx_desc); +} + +/** * iavf_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf * @rx_ring: rx descriptor ring to transact packets on * @budget: Total limit on number of packets to process @@ -1494,18 +1383,17 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring, **/ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget) { + bool flex = rx_ring->rxdid == VIRTCHNL_RXDID_2_FLEX_SQ_NIC; unsigned int total_rx_bytes = 0, total_rx_packets = 0; struct sk_buff *skb = rx_ring->skb; u16 cleaned_count = IAVF_DESC_UNUSED(rx_ring); bool failure = false; while (likely(total_rx_packets < (unsigned int)budget)) { - struct iavf_rx_buffer *rx_buffer; - union iavf_rx_desc *rx_desc; - unsigned int size; - u16 vlan_tag = 0; - u8 rx_ptype; - u64 qword; + struct libeth_rqe_info fields; + struct libeth_fqe *rx_buffer; + struct iavf_rx_desc *rx_desc; + u64 qw1; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= IAVF_RX_BUFFER_WRITE) { @@ -1516,55 +1404,50 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget) rx_desc = IAVF_RX_DESC(rx_ring, rx_ring->next_to_clean); - /* status_error_len will always be zero for unused descriptors - * because it's cleared in cleanup, and overlaps with hdr_addr - * which is always zero because packet split isn't used, if the - * hardware wrote DD then the length will be non-zero - */ - qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - /* This memory barrier is needed to keep us from reading * any other fields out of the rx_desc until we have * verified the descriptor has been written back. */ dma_rmb(); -#define IAVF_RXD_DD BIT(IAVF_RX_DESC_STATUS_DD_SHIFT) - if (!iavf_test_staterr(rx_desc, IAVF_RXD_DD)) + + qw1 = le64_to_cpu(rx_desc->qw1); + /* If DD field (descriptor done) is unset then other fields are + * not valid + */ + if (!iavf_is_descriptor_done(qw1, flex)) break; - size = FIELD_GET(IAVF_RXD_QW1_LENGTH_PBUF_MASK, qword); + fields = iavf_extract_rx_fields(rx_ring, rx_desc, flex); iavf_trace(clean_rx_irq, rx_ring, rx_desc, skb); - rx_buffer = iavf_get_rx_buffer(rx_ring, size); + + rx_buffer = &rx_ring->rx_fqes[rx_ring->next_to_clean]; + if (!libeth_rx_sync_for_cpu(rx_buffer, fields.len)) + goto skip_data; /* retrieve a buffer from the ring */ if (skb) - iavf_add_rx_frag(rx_ring, rx_buffer, skb, size); - else if (ring_uses_build_skb(rx_ring)) - skb = iavf_build_skb(rx_ring, rx_buffer, size); + iavf_add_rx_frag(skb, rx_buffer, fields.len); else - skb = iavf_construct_skb(rx_ring, rx_buffer, size); + skb = iavf_build_skb(rx_buffer, fields.len); /* exit if we failed to retrieve a buffer */ if (!skb) { rx_ring->rx_stats.alloc_buff_failed++; - if (rx_buffer && size) - rx_buffer->pagecnt_bias++; break; } - iavf_put_rx_buffer(rx_ring, rx_buffer); +skip_data: cleaned_count++; - if (iavf_is_non_eop(rx_ring, rx_desc, skb)) + if (iavf_is_non_eop(rx_ring, fields) || unlikely(!skb)) continue; - /* ERR_MASK will only have valid bits if EOP set, and - * what we are doing here is actually checking - * IAVF_RX_DESC_ERROR_RXE_SHIFT, since it is the zeroth bit in - * the error field + /* RXE field in descriptor is an indication of the MAC errors + * (like CRC, alignment, oversize etc). If it is set then iavf + * should finish. */ - if (unlikely(iavf_test_staterr(rx_desc, BIT(IAVF_RXD_QW1_ERROR_SHIFT)))) { + if (unlikely(fields.rxe)) { dev_kfree_skb_any(skb); skb = NULL; continue; @@ -1578,22 +1461,11 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget) /* probably a little skewed due to removing CRC */ total_rx_bytes += skb->len; - qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len); - rx_ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword); - /* populate checksum, VLAN, and protocol */ - iavf_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); - - if (qword & BIT(IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT) && - rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1) - vlan_tag = le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1); - if (rx_desc->wb.qword2.ext_status & - cpu_to_le16(BIT(IAVF_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT)) && - rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2) - vlan_tag = le16_to_cpu(rx_desc->wb.qword2.l2tag2_2); + iavf_process_skb_fields(rx_ring, rx_desc, skb, fields.ptype, flex); iavf_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb); - iavf_receive_skb(rx_ring, skb, vlan_tag); + iavf_receive_skb(rx_ring, skb, fields.vlan); skb = NULL; /* update budget accounting */ @@ -1743,8 +1615,8 @@ int iavf_napi_poll(struct napi_struct *napi, int budget) clean_complete = false; continue; } - arm_wb |= ring->arm_wb; - ring->arm_wb = false; + arm_wb |= !!(ring->flags & IAVF_TXR_FLAGS_ARM_WB); + ring->flags &= ~IAVF_TXR_FLAGS_ARM_WB; } /* Handle case where we are called by netpoll with a budget of 0 */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h index 10ba36602c0c..79ad554f2d53 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h @@ -80,96 +80,6 @@ enum iavf_dyn_idx_t { BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \ BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP)) -/* Supported Rx Buffer Sizes (a multiple of 128) */ -#define IAVF_RXBUFFER_256 256 -#define IAVF_RXBUFFER_1536 1536 /* 128B aligned standard Ethernet frame */ -#define IAVF_RXBUFFER_2048 2048 -#define IAVF_RXBUFFER_3072 3072 /* Used for large frames w/ padding */ -#define IAVF_MAX_RXBUFFER 9728 /* largest size for single descriptor */ - -/* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we - * reserve 2 more, and skb_shared_info adds an additional 384 bytes more, - * this adds up to 512 bytes of extra data meaning the smallest allocation - * we could have is 1K. - * i.e. RXBUFFER_256 --> 960 byte skb (size-1024 slab) - * i.e. RXBUFFER_512 --> 1216 byte skb (size-2048 slab) - */ -#define IAVF_RX_HDR_SIZE IAVF_RXBUFFER_256 -#define IAVF_PACKET_HDR_PAD (ETH_HLEN + ETH_FCS_LEN + (VLAN_HLEN * 2)) -#define iavf_rx_desc iavf_32byte_rx_desc - -#define IAVF_RX_DMA_ATTR \ - (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) - -/* Attempt to maximize the headroom available for incoming frames. We - * use a 2K buffer for receives and need 1536/1534 to store the data for - * the frame. This leaves us with 512 bytes of room. From that we need - * to deduct the space needed for the shared info and the padding needed - * to IP align the frame. - * - * Note: For cache line sizes 256 or larger this value is going to end - * up negative. In these cases we should fall back to the legacy - * receive path. - */ -#if (PAGE_SIZE < 8192) -#define IAVF_2K_TOO_SMALL_WITH_PADDING \ -((NET_SKB_PAD + IAVF_RXBUFFER_1536) > SKB_WITH_OVERHEAD(IAVF_RXBUFFER_2048)) - -static inline int iavf_compute_pad(int rx_buf_len) -{ - int page_size, pad_size; - - page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2); - pad_size = SKB_WITH_OVERHEAD(page_size) - rx_buf_len; - - return pad_size; -} - -static inline int iavf_skb_pad(void) -{ - int rx_buf_len; - - /* If a 2K buffer cannot handle a standard Ethernet frame then - * optimize padding for a 3K buffer instead of a 1.5K buffer. - * - * For a 3K buffer we need to add enough padding to allow for - * tailroom due to NET_IP_ALIGN possibly shifting us out of - * cache-line alignment. - */ - if (IAVF_2K_TOO_SMALL_WITH_PADDING) - rx_buf_len = IAVF_RXBUFFER_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN); - else - rx_buf_len = IAVF_RXBUFFER_1536; - - /* if needed make room for NET_IP_ALIGN */ - rx_buf_len -= NET_IP_ALIGN; - - return iavf_compute_pad(rx_buf_len); -} - -#define IAVF_SKB_PAD iavf_skb_pad() -#else -#define IAVF_2K_TOO_SMALL_WITH_PADDING false -#define IAVF_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) -#endif - -/** - * iavf_test_staterr - tests bits in Rx descriptor status and error fields - * @rx_desc: pointer to receive descriptor (in le64 format) - * @stat_err_bits: value to mask - * - * This function does some fast chicanery in order to return the - * value of the mask which is really only used for boolean tests. - * The status_error_len doesn't need to be shifted because it begins - * at offset zero. - */ -static inline bool iavf_test_staterr(union iavf_rx_desc *rx_desc, - const u64 stat_err_bits) -{ - return !!(rx_desc->wb.qword1.status_error_len & - cpu_to_le64(stat_err_bits)); -} - /* How many Rx Buffers do we bundle into one write to the hardware ? */ #define IAVF_RX_INCREMENT(r, i) \ do { \ @@ -271,17 +181,6 @@ struct iavf_tx_buffer { u32 tx_flags; }; -struct iavf_rx_buffer { - dma_addr_t dma; - struct page *page; -#if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536) - __u32 page_offset; -#else - __u16 page_offset; -#endif - __u16 pagecnt_bias; -}; - struct iavf_queue_stats { u64 packets; u64 bytes; @@ -293,7 +192,6 @@ struct iavf_tx_queue_stats { u64 tx_done_old; u64 tx_linearize; u64 tx_force_wb; - int prev_pkt_ctr; u64 tx_lost_interrupt; }; @@ -301,14 +199,6 @@ struct iavf_rx_queue_stats { u64 non_eop_descs; u64 alloc_page_failed; u64 alloc_buff_failed; - u64 page_reuse_count; - u64 realloc_count; -}; - -enum iavf_ring_state_t { - __IAVF_TX_FDIR_INIT_DONE, - __IAVF_TX_XPS_INIT_DONE, - __IAVF_RING_STATE_NBITS /* must be last */ }; /* some useful defines for virtchannel interface, which @@ -326,16 +216,19 @@ enum iavf_ring_state_t { struct iavf_ring { struct iavf_ring *next; /* pointer to next ring in q_vector */ void *desc; /* Descriptor ring memory */ - struct device *dev; /* Used for DMA mapping */ + union { + struct page_pool *pp; /* Used on Rx for buffer management */ + struct device *dev; /* Used on Tx for DMA mapping */ + }; struct net_device *netdev; /* netdev ring maps to */ union { + struct libeth_fqe *rx_fqes; struct iavf_tx_buffer *tx_bi; - struct iavf_rx_buffer *rx_bi; }; - DECLARE_BITMAP(state, __IAVF_RING_STATE_NBITS); - u16 queue_index; /* Queue number of ring */ - u8 dcb_tc; /* Traffic class of ring */ u8 __iomem *tail; + u32 truesize; + + u16 queue_index; /* Queue number of ring */ /* high bit set means dynamic, use accessors routines to read/write. * hardware only supports 2us resolution for the ITR registers. @@ -345,26 +238,21 @@ struct iavf_ring { u16 itr_setting; u16 count; /* Number of descriptors */ - u16 reg_idx; /* HW register index of the ring */ - u16 rx_buf_len; /* used in interrupt processing */ u16 next_to_use; u16 next_to_clean; - u8 atr_sample_rate; - u8 atr_count; - - bool ring_active; /* is ring online or not */ - bool arm_wb; /* do something to arm write back */ - u8 packet_stride; + u16 rxdid; /* Rx descriptor format */ u16 flags; #define IAVF_TXR_FLAGS_WB_ON_ITR BIT(0) -#define IAVF_RXR_FLAGS_BUILD_SKB_ENABLED BIT(1) +#define IAVF_TXR_FLAGS_ARM_WB BIT(1) +/* BIT(2) is free */ #define IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1 BIT(3) #define IAVF_TXR_FLAGS_VLAN_TAG_LOC_L2TAG2 BIT(4) #define IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2 BIT(5) +#define IAVF_TXRX_FLAGS_HW_TSTAMP BIT(6) /* stats structs */ struct iavf_queue_stats stats; @@ -374,6 +262,7 @@ struct iavf_ring { struct iavf_rx_queue_stats rx_stats; }; + int prev_pkt_ctr; /* For Tx stall detection */ unsigned int size; /* length of descriptor ring in bytes */ dma_addr_t dma; /* physical address of ring */ @@ -381,7 +270,6 @@ struct iavf_ring { struct iavf_q_vector *q_vector; /* Backreference to associated vector */ struct rcu_head rcu; /* to avoid race on free */ - u16 next_to_alloc; struct sk_buff *skb; /* When iavf_clean_rx_ring_irq() must * return before it sees the EOP for * the current packet, we save that skb @@ -390,22 +278,13 @@ struct iavf_ring { * iavf_clean_rx_ring_irq() is called * for this ring. */ -} ____cacheline_internodealigned_in_smp; - -static inline bool ring_uses_build_skb(struct iavf_ring *ring) -{ - return !!(ring->flags & IAVF_RXR_FLAGS_BUILD_SKB_ENABLED); -} -static inline void set_ring_build_skb_enabled(struct iavf_ring *ring) -{ - ring->flags |= IAVF_RXR_FLAGS_BUILD_SKB_ENABLED; -} + struct iavf_ptp *ptp; -static inline void clear_ring_build_skb_enabled(struct iavf_ring *ring) -{ - ring->flags &= ~IAVF_RXR_FLAGS_BUILD_SKB_ENABLED; -} + u32 rx_buf_len; + struct net_shaper q_shaper; + bool q_shaper_update; +} ____cacheline_internodealigned_in_smp; #define IAVF_ITR_ADAPTIVE_MIN_INC 0x0002 #define IAVF_ITR_ADAPTIVE_MIN_USECS 0x0002 @@ -428,17 +307,6 @@ struct iavf_ring_container { #define iavf_for_each_ring(pos, head) \ for (pos = (head).ring; pos != NULL; pos = pos->next) -static inline unsigned int iavf_rx_pg_order(struct iavf_ring *ring) -{ -#if (PAGE_SIZE < 8192) - if (ring->rx_buf_len > (PAGE_SIZE / 2)) - return 1; -#endif - return 0; -} - -#define iavf_rx_pg_size(_ring) (PAGE_SIZE << iavf_rx_pg_order(_ring)) - bool iavf_alloc_rx_buffers(struct iavf_ring *rxr, u16 cleaned_count); netdev_tx_t iavf_xmit_frame(struct sk_buff *skb, struct net_device *netdev); int iavf_setup_tx_descriptors(struct iavf_ring *tx_ring); diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h index 2b6a207fa441..f9e1319620f4 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_type.h +++ b/drivers/net/ethernet/intel/iavf/iavf_type.h @@ -10,8 +10,6 @@ #include "iavf_adminq.h" #include "iavf_devids.h" -#define IAVF_RXQ_CTX_DBUFF_SHIFT 7 - /* IAVF_MASK is a macro used on 32 bit registers */ #define IAVF_MASK(mask, shift) ((u32)(mask) << (shift)) @@ -180,110 +178,116 @@ struct iavf_hw { char err_str[16]; }; -/* RX Descriptors */ -union iavf_16byte_rx_desc { - struct { - __le64 pkt_addr; /* Packet buffer address */ - __le64 hdr_addr; /* Header buffer address */ - } read; - struct { - struct { - struct { - union { - __le16 mirroring_status; - __le16 fcoe_ctx_id; - } mirr_fcoe; - __le16 l2tag1; - } lo_dword; - union { - __le32 rss; /* RSS Hash */ - __le32 fd_id; /* Flow director filter id */ - __le32 fcoe_param; /* FCoE DDP Context id */ - } hi_dword; - } qword0; - struct { - /* ext status/error/pktype/length */ - __le64 status_error_len; - } qword1; - } wb; /* writeback */ -}; - -union iavf_32byte_rx_desc { - struct { - __le64 pkt_addr; /* Packet buffer address */ - __le64 hdr_addr; /* Header buffer address */ - /* bit 0 of hdr_buffer_addr is DD bit */ - __le64 rsvd1; - __le64 rsvd2; - } read; - struct { - struct { - struct { - union { - __le16 mirroring_status; - __le16 fcoe_ctx_id; - } mirr_fcoe; - __le16 l2tag1; - } lo_dword; - union { - __le32 rss; /* RSS Hash */ - __le32 fcoe_param; /* FCoE DDP Context id */ - /* Flow director filter id in case of - * Programming status desc WB - */ - __le32 fd_id; - } hi_dword; - } qword0; - struct { - /* status/error/pktype/length */ - __le64 status_error_len; - } qword1; - struct { - __le16 ext_status; /* extended status */ - __le16 rsvd; - __le16 l2tag2_1; - __le16 l2tag2_2; - } qword2; - struct { - union { - __le32 flex_bytes_lo; - __le32 pe_status; - } lo_dword; - union { - __le32 flex_bytes_hi; - __le32 fd_id; - } hi_dword; - } qword3; - } wb; /* writeback */ -}; - -enum iavf_rx_desc_status_bits { - /* Note: These are predefined bit offsets */ - IAVF_RX_DESC_STATUS_DD_SHIFT = 0, - IAVF_RX_DESC_STATUS_EOF_SHIFT = 1, - IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT = 2, - IAVF_RX_DESC_STATUS_L3L4P_SHIFT = 3, - IAVF_RX_DESC_STATUS_CRCP_SHIFT = 4, - IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT = 5, /* 2 BITS */ - IAVF_RX_DESC_STATUS_TSYNVALID_SHIFT = 7, - /* Note: Bit 8 is reserved in X710 and XL710 */ - IAVF_RX_DESC_STATUS_EXT_UDP_0_SHIFT = 8, - IAVF_RX_DESC_STATUS_UMBCAST_SHIFT = 9, /* 2 BITS */ - IAVF_RX_DESC_STATUS_FLM_SHIFT = 11, - IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT = 12, /* 2 BITS */ - IAVF_RX_DESC_STATUS_LPBK_SHIFT = 14, - IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT = 15, - IAVF_RX_DESC_STATUS_RESERVED_SHIFT = 16, /* 2 BITS */ - /* Note: For non-tunnel packets INT_UDP_0 is the right status for - * UDP header - */ - IAVF_RX_DESC_STATUS_INT_UDP_0_SHIFT = 18, - IAVF_RX_DESC_STATUS_LAST /* this entry must be last!!! */ -}; - -#define IAVF_RXD_QW1_STATUS_SHIFT 0 -#define IAVF_RXD_QW1_STATUS_MASK ((BIT(IAVF_RX_DESC_STATUS_LAST) - 1) \ - << IAVF_RXD_QW1_STATUS_SHIFT) +/** + * struct iavf_rx_desc - Receive descriptor (both legacy and flexible) + * @qw0: quad word 0 fields: + * Legacy: Descriptor Type; Mirror ID; L2TAG1P (S-TAG); Filter Status + * Flex: Descriptor Type; Mirror ID; UMBCAST; Packet Type; Flexible Flags + * Section 0; Packet Length; Header Length; Split Header Flag; + * Flexible Flags section 1 / Extended Status + * @qw1: quad word 1 fields: + * Legacy: Status Field; Error Field; Packet Type; Packet Length (packet, + * header, Split Header Flag) + * Flex: Status / Error 0 Field; L2TAG1P (S-TAG); Flexible Metadata + * Container #0; Flexible Metadata Container #1 + * @qw2: quad word 2 fields: + * Legacy: Extended Status; 1st L2TAG2P (C-TAG); 2nd L2TAG2P (C-TAG) + * Flex: Status / Error 1 Field; Flexible Flags section 2; Timestamp Low; + * 1st L2TAG2 (C-TAG); 2nd L2TAG2 (C-TAG) + * @qw3: quad word 3 fields: + * Legacy: FD Filter ID / Flexible Bytes + * Flex: Flexible Metadata Container #2; Flexible Metadata Container #3; + * Flexible Metadata Container #4 / Timestamp High 0; Flexible + * Metadata Container #5 / Timestamp High 1; + */ +struct iavf_rx_desc { + aligned_le64 qw0; +/* The hash signature (RSS) */ +#define IAVF_RXD_LEGACY_RSS_M GENMASK_ULL(63, 32) +/* Stripped C-TAG VLAN from the receive packet */ +#define IAVF_RXD_LEGACY_L2TAG1_M GENMASK_ULL(33, 16) +/* Packet type */ +#define IAVF_RXD_FLEX_PTYPE_M GENMASK_ULL(25, 16) +/* Packet length */ +#define IAVF_RXD_FLEX_PKT_LEN_M GENMASK_ULL(45, 32) + + aligned_le64 qw1; +/* Descriptor done indication flag. */ +#define IAVF_RXD_LEGACY_DD_M BIT(0) +/* End of packet. Set to 1 if this descriptor is the last one of the packet */ +#define IAVF_RXD_LEGACY_EOP_M BIT(1) +/* L2 TAG 1 presence indication */ +#define IAVF_RXD_LEGACY_L2TAG1P_M BIT(2) +/* Detectable L3 and L4 integrity check is processed by the HW */ +#define IAVF_RXD_LEGACY_L3L4P_M BIT(3) +/* Set when an IPv6 packet contains a Destination Options Header or a Routing + * Header. + */ +#define IAVF_RXD_LEGACY_IPV6EXADD_M BIT(15) +/* Receive MAC Errors: CRC; Alignment; Oversize; Undersizes; Length error */ +#define IAVF_RXD_LEGACY_RXE_M BIT(19) +/* Checksum reports: + * - IPE: IP checksum error + * - L4E: L4 integrity error + * - EIPE: External IP header (tunneled packets) + */ +#define IAVF_RXD_LEGACY_IPE_M BIT(22) +#define IAVF_RXD_LEGACY_L4E_M BIT(23) +#define IAVF_RXD_LEGACY_EIPE_M BIT(24) +/* Set for packets that skip checksum calculation in pre-parser */ +#define IAVF_RXD_LEGACY_PPRS_M BIT(26) +/* Indicates the content in the Filter Status field */ +#define IAVF_RXD_LEGACY_FLTSTAT_M GENMASK_ULL(13, 12) +/* Packet type */ +#define IAVF_RXD_LEGACY_PTYPE_M GENMASK_ULL(37, 30) +/* Packet length */ +#define IAVF_RXD_LEGACY_LENGTH_M GENMASK_ULL(51, 38) +/* Descriptor done indication flag */ +#define IAVF_RXD_FLEX_DD_M BIT(0) +/* End of packet. Set to 1 if this descriptor is the last one of the packet */ +#define IAVF_RXD_FLEX_EOP_M BIT(1) +/* Detectable L3 and L4 integrity check is processed by the HW */ +#define IAVF_RXD_FLEX_L3L4P_M BIT(3) +/* Checksum reports: + * - IPE: IP checksum error + * - L4E: L4 integrity error + * - EIPE: External IP header (tunneled packets) + * - EUDPE: External UDP checksum error (tunneled packets) + */ +#define IAVF_RXD_FLEX_XSUM_IPE_M BIT(4) +#define IAVF_RXD_FLEX_XSUM_L4E_M BIT(5) +#define IAVF_RXD_FLEX_XSUM_EIPE_M BIT(6) +#define IAVF_RXD_FLEX_XSUM_EUDPE_M BIT(7) +/* Set when an IPv6 packet contains a Destination Options Header or a Routing + * Header. + */ +#define IAVF_RXD_FLEX_IPV6EXADD_M BIT(9) +/* Receive MAC Errors: CRC; Alignment; Oversize; Undersizes; Length error */ +#define IAVF_RXD_FLEX_RXE_M BIT(10) +/* Indicates that the RSS/HASH result is valid */ +#define IAVF_RXD_FLEX_RSS_VALID_M BIT(12) +/* L2 TAG 1 presence indication */ +#define IAVF_RXD_FLEX_L2TAG1P_M BIT(13) +/* Stripped L2 Tag from the receive packet */ +#define IAVF_RXD_FLEX_L2TAG1_M GENMASK_ULL(31, 16) +/* The hash signature (RSS) */ +#define IAVF_RXD_FLEX_RSS_HASH_M GENMASK_ULL(63, 32) + + aligned_le64 qw2; +/* L2 Tag 2 Presence */ +#define IAVF_RXD_LEGACY_L2TAG2P_M BIT(0) +/* Stripped S-TAG VLAN from the receive packet */ +#define IAVF_RXD_LEGACY_L2TAG2_M GENMASK_ULL(63, 32) +/* Stripped S-TAG VLAN from the receive packet */ +#define IAVF_RXD_FLEX_L2TAG2_2_M GENMASK_ULL(63, 48) +/* The packet is a UDP tunneled packet */ +#define IAVF_RXD_FLEX_NAT_M BIT(4) +/* L2 Tag 2 Presence */ +#define IAVF_RXD_FLEX_L2TAG2P_M BIT(11) + aligned_le64 qw3; +#define IAVF_RXD_FLEX_QW3_TSTAMP_HIGH_M GENMASK_ULL(63, 32) +} __aligned(4 * sizeof(__le64)); +static_assert(sizeof(struct iavf_rx_desc) == 32); #define IAVF_RXD_QW1_STATUS_TSYNINDX_SHIFT IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT #define IAVF_RXD_QW1_STATUS_TSYNINDX_MASK (0x3UL << \ @@ -300,22 +304,6 @@ enum iavf_rx_desc_fltstat_values { IAVF_RX_DESC_FLTSTAT_RSS_HASH = 3, }; -#define IAVF_RXD_QW1_ERROR_SHIFT 19 -#define IAVF_RXD_QW1_ERROR_MASK (0xFFUL << IAVF_RXD_QW1_ERROR_SHIFT) - -enum iavf_rx_desc_error_bits { - /* Note: These are predefined bit offsets */ - IAVF_RX_DESC_ERROR_RXE_SHIFT = 0, - IAVF_RX_DESC_ERROR_RECIPE_SHIFT = 1, - IAVF_RX_DESC_ERROR_HBO_SHIFT = 2, - IAVF_RX_DESC_ERROR_L3L4E_SHIFT = 3, /* 3 BITS */ - IAVF_RX_DESC_ERROR_IPE_SHIFT = 3, - IAVF_RX_DESC_ERROR_L4E_SHIFT = 4, - IAVF_RX_DESC_ERROR_EIPE_SHIFT = 5, - IAVF_RX_DESC_ERROR_OVERSIZE_SHIFT = 6, - IAVF_RX_DESC_ERROR_PPRS_SHIFT = 7 -}; - enum iavf_rx_desc_error_l3l4e_fcoe_masks { IAVF_RX_DESC_ERROR_L3L4E_NONE = 0, IAVF_RX_DESC_ERROR_L3L4E_PROT = 1, @@ -324,101 +312,6 @@ enum iavf_rx_desc_error_l3l4e_fcoe_masks { IAVF_RX_DESC_ERROR_L3L4E_DMAC_WARN = 4 }; -#define IAVF_RXD_QW1_PTYPE_SHIFT 30 -#define IAVF_RXD_QW1_PTYPE_MASK (0xFFULL << IAVF_RXD_QW1_PTYPE_SHIFT) - -/* Packet type non-ip values */ -enum iavf_rx_l2_ptype { - IAVF_RX_PTYPE_L2_RESERVED = 0, - IAVF_RX_PTYPE_L2_MAC_PAY2 = 1, - IAVF_RX_PTYPE_L2_TIMESYNC_PAY2 = 2, - IAVF_RX_PTYPE_L2_FIP_PAY2 = 3, - IAVF_RX_PTYPE_L2_OUI_PAY2 = 4, - IAVF_RX_PTYPE_L2_MACCNTRL_PAY2 = 5, - IAVF_RX_PTYPE_L2_LLDP_PAY2 = 6, - IAVF_RX_PTYPE_L2_ECP_PAY2 = 7, - IAVF_RX_PTYPE_L2_EVB_PAY2 = 8, - IAVF_RX_PTYPE_L2_QCN_PAY2 = 9, - IAVF_RX_PTYPE_L2_EAPOL_PAY2 = 10, - IAVF_RX_PTYPE_L2_ARP = 11, - IAVF_RX_PTYPE_L2_FCOE_PAY3 = 12, - IAVF_RX_PTYPE_L2_FCOE_FCDATA_PAY3 = 13, - IAVF_RX_PTYPE_L2_FCOE_FCRDY_PAY3 = 14, - IAVF_RX_PTYPE_L2_FCOE_FCRSP_PAY3 = 15, - IAVF_RX_PTYPE_L2_FCOE_FCOTHER_PA = 16, - IAVF_RX_PTYPE_L2_FCOE_VFT_PAY3 = 17, - IAVF_RX_PTYPE_L2_FCOE_VFT_FCDATA = 18, - IAVF_RX_PTYPE_L2_FCOE_VFT_FCRDY = 19, - IAVF_RX_PTYPE_L2_FCOE_VFT_FCRSP = 20, - IAVF_RX_PTYPE_L2_FCOE_VFT_FCOTHER = 21, - IAVF_RX_PTYPE_GRENAT4_MAC_PAY3 = 58, - IAVF_RX_PTYPE_GRENAT4_MACVLAN_IPV6_ICMP_PAY4 = 87, - IAVF_RX_PTYPE_GRENAT6_MAC_PAY3 = 124, - IAVF_RX_PTYPE_GRENAT6_MACVLAN_IPV6_ICMP_PAY4 = 153 -}; - -struct iavf_rx_ptype_decoded { - u32 known:1; - u32 outer_ip:1; - u32 outer_ip_ver:1; - u32 outer_frag:1; - u32 tunnel_type:3; - u32 tunnel_end_prot:2; - u32 tunnel_end_frag:1; - u32 inner_prot:4; - u32 payload_layer:3; -}; - -enum iavf_rx_ptype_outer_ip { - IAVF_RX_PTYPE_OUTER_L2 = 0, - IAVF_RX_PTYPE_OUTER_IP = 1 -}; - -enum iavf_rx_ptype_outer_ip_ver { - IAVF_RX_PTYPE_OUTER_NONE = 0, - IAVF_RX_PTYPE_OUTER_IPV4 = 0, - IAVF_RX_PTYPE_OUTER_IPV6 = 1 -}; - -enum iavf_rx_ptype_outer_fragmented { - IAVF_RX_PTYPE_NOT_FRAG = 0, - IAVF_RX_PTYPE_FRAG = 1 -}; - -enum iavf_rx_ptype_tunnel_type { - IAVF_RX_PTYPE_TUNNEL_NONE = 0, - IAVF_RX_PTYPE_TUNNEL_IP_IP = 1, - IAVF_RX_PTYPE_TUNNEL_IP_GRENAT = 2, - IAVF_RX_PTYPE_TUNNEL_IP_GRENAT_MAC = 3, - IAVF_RX_PTYPE_TUNNEL_IP_GRENAT_MAC_VLAN = 4, -}; - -enum iavf_rx_ptype_tunnel_end_prot { - IAVF_RX_PTYPE_TUNNEL_END_NONE = 0, - IAVF_RX_PTYPE_TUNNEL_END_IPV4 = 1, - IAVF_RX_PTYPE_TUNNEL_END_IPV6 = 2, -}; - -enum iavf_rx_ptype_inner_prot { - IAVF_RX_PTYPE_INNER_PROT_NONE = 0, - IAVF_RX_PTYPE_INNER_PROT_UDP = 1, - IAVF_RX_PTYPE_INNER_PROT_TCP = 2, - IAVF_RX_PTYPE_INNER_PROT_SCTP = 3, - IAVF_RX_PTYPE_INNER_PROT_ICMP = 4, - IAVF_RX_PTYPE_INNER_PROT_TIMESYNC = 5 -}; - -enum iavf_rx_ptype_payload_layer { - IAVF_RX_PTYPE_PAYLOAD_LAYER_NONE = 0, - IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY2 = 1, - IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY3 = 2, - IAVF_RX_PTYPE_PAYLOAD_LAYER_PAY4 = 3, -}; - -#define IAVF_RXD_QW1_LENGTH_PBUF_SHIFT 38 -#define IAVF_RXD_QW1_LENGTH_PBUF_MASK (0x3FFFULL << \ - IAVF_RXD_QW1_LENGTH_PBUF_SHIFT) - #define IAVF_RXD_QW1_LENGTH_HBUF_SHIFT 52 #define IAVF_RXD_QW1_LENGTH_HBUF_MASK (0x7FFULL << \ IAVF_RXD_QW1_LENGTH_HBUF_SHIFT) @@ -437,6 +330,8 @@ enum iavf_rx_desc_ext_status_bits { IAVF_RX_DESC_EXT_STATUS_PELONGB_SHIFT = 11, }; +#define IAVF_RX_DESC_EXT_STATUS_L2TAG2P_M BIT(IAVF_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT) + enum iavf_rx_desc_pe_status_bits { /* Note: These are predefined bit offsets */ IAVF_RX_DESC_PE_STATUS_QPID_SHIFT = 0, /* 18 BITS */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_types.h b/drivers/net/ethernet/intel/iavf/iavf_types.h new file mode 100644 index 000000000000..a095855122bf --- /dev/null +++ b/drivers/net/ethernet/intel/iavf/iavf_types.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2024 Intel Corporation. */ + +#ifndef _IAVF_TYPES_H_ +#define _IAVF_TYPES_H_ + +#include "iavf_types.h" + +#include <linux/avf/virtchnl.h> +#include <linux/ptp_clock_kernel.h> + +/* structure used to queue PTP commands for processing */ +struct iavf_ptp_aq_cmd { + struct list_head list; + enum virtchnl_ops v_opcode:16; + u16 msglen; + u8 msg[] __counted_by(msglen); +}; + +struct iavf_ptp { + wait_queue_head_t phc_time_waitqueue; + struct virtchnl_ptp_caps hw_caps; + struct ptp_clock_info info; + struct ptp_clock *clock; + struct list_head aq_cmds; + u64 cached_phc_time; + unsigned long cached_phc_updated; + /* Lock protecting access to the AQ command list */ + struct mutex aq_cmd_lock; + struct kernel_hwtstamp_config hwtstamp_config; + bool phc_time_ready:1; +}; + +#endif /* _IAVF_TYPES_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 22f2df7c460b..a6f0e5990be2 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -1,7 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ +#include <linux/net/intel/libie/rx.h> + #include "iavf.h" +#include "iavf_ptp.h" #include "iavf_prototype.h" /** @@ -140,15 +143,19 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter) VIRTCHNL_VF_OFFLOAD_WB_ON_ITR | VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2 | VIRTCHNL_VF_OFFLOAD_ENCAP | + VIRTCHNL_VF_OFFLOAD_TC_U32 | VIRTCHNL_VF_OFFLOAD_VLAN_V2 | + VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC | VIRTCHNL_VF_OFFLOAD_CRC | VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM | VIRTCHNL_VF_OFFLOAD_REQ_QUEUES | + VIRTCHNL_VF_CAP_PTP | VIRTCHNL_VF_OFFLOAD_ADQ | VIRTCHNL_VF_OFFLOAD_USO | VIRTCHNL_VF_OFFLOAD_FDIR_PF | VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF | - VIRTCHNL_VF_CAP_ADV_LINK_SPEED; + VIRTCHNL_VF_CAP_ADV_LINK_SPEED | + VIRTCHNL_VF_OFFLOAD_QOS; adapter->current_op = VIRTCHNL_OP_GET_VF_RESOURCES; adapter->aq_required &= ~IAVF_FLAG_AQ_GET_CONFIG; @@ -173,6 +180,54 @@ int iavf_send_vf_offload_vlan_v2_msg(struct iavf_adapter *adapter) NULL, 0); } +int iavf_send_vf_supported_rxdids_msg(struct iavf_adapter *adapter) +{ + adapter->aq_required &= ~IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS; + + if (!IAVF_RXDID_ALLOWED(adapter)) + return -EOPNOTSUPP; + + adapter->current_op = VIRTCHNL_OP_GET_SUPPORTED_RXDIDS; + + return iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_SUPPORTED_RXDIDS, + NULL, 0); +} + +/** + * iavf_send_vf_ptp_caps_msg - Send request for PTP capabilities + * @adapter: private adapter structure + * + * Send the VIRTCHNL_OP_1588_PTP_GET_CAPS command to the PF to request the PTP + * capabilities available to this device. This includes the following + * potential access: + * + * * READ_PHC - access to read the PTP hardware clock time + * * RX_TSTAMP - access to request Rx timestamps on all received packets + * + * The PF will reply with the same opcode a filled out copy of the + * virtchnl_ptp_caps structure which defines the specifics of which features + * are accessible to this device. + * + * Return: 0 if success, error code otherwise. + */ +int iavf_send_vf_ptp_caps_msg(struct iavf_adapter *adapter) +{ + struct virtchnl_ptp_caps hw_caps = { + .caps = VIRTCHNL_1588_PTP_CAP_READ_PHC | + VIRTCHNL_1588_PTP_CAP_RX_TSTAMP + }; + + adapter->aq_required &= ~IAVF_FLAG_AQ_GET_PTP_CAPS; + + if (!IAVF_PTP_ALLOWED(adapter)) + return -EOPNOTSUPP; + + adapter->current_op = VIRTCHNL_OP_1588_PTP_GET_CAPS; + + return iavf_send_pf_msg(adapter, VIRTCHNL_OP_1588_PTP_GET_CAPS, + (u8 *)&hw_caps, sizeof(hw_caps)); +} + /** * iavf_validate_num_queues * @adapter: adapter structure @@ -259,6 +314,40 @@ int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter) return err; } +int iavf_get_vf_supported_rxdids(struct iavf_adapter *adapter) +{ + struct iavf_arq_event_info event; + u64 rxdids; + int err; + + event.msg_buf = (u8 *)&rxdids; + event.buf_len = sizeof(rxdids); + + err = iavf_poll_virtchnl_msg(&adapter->hw, &event, + VIRTCHNL_OP_GET_SUPPORTED_RXDIDS); + if (!err) + adapter->supp_rxdids = rxdids; + + return err; +} + +int iavf_get_vf_ptp_caps(struct iavf_adapter *adapter) +{ + struct virtchnl_ptp_caps caps = {}; + struct iavf_arq_event_info event; + int err; + + event.msg_buf = (u8 *)∩︀ + event.buf_len = sizeof(caps); + + err = iavf_poll_virtchnl_msg(&adapter->hw, &event, + VIRTCHNL_OP_1588_PTP_GET_CAPS); + if (!err) + adapter->ptp.hw_caps = caps; + + return err; +} + /** * iavf_configure_queues * @adapter: adapter structure @@ -268,13 +357,14 @@ int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter) void iavf_configure_queues(struct iavf_adapter *adapter) { struct virtchnl_vsi_queue_config_info *vqci; - int i, max_frame = adapter->vf_res->max_mtu; int pairs = adapter->num_active_queues; struct virtchnl_queue_pair_info *vqpi; + u32 i, max_frame; + u8 rx_flags = 0; size_t len; - if (max_frame > IAVF_MAX_RXBUFFER || !max_frame) - max_frame = IAVF_MAX_RXBUFFER; + max_frame = LIBIE_MAX_RX_FRM_LEN(adapter->rx_rings->pp->p.offset); + max_frame = min_not_zero(adapter->vf_res->max_mtu, max_frame); if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { /* bail because we already have a command pending */ @@ -288,10 +378,8 @@ void iavf_configure_queues(struct iavf_adapter *adapter) if (!vqci) return; - /* Limit maximum frame size when jumbo frames is not enabled */ - if (!(adapter->flags & IAVF_FLAG_LEGACY_RX) && - (adapter->netdev->mtu <= ETH_DATA_LEN)) - max_frame = IAVF_RXBUFFER_1536 - NET_IP_ALIGN; + if (iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP)) + rx_flags |= VIRTCHNL_PTP_RX_TSTAMP; vqci->vsi_id = adapter->vsi_res->vsi_id; vqci->num_queue_pairs = pairs; @@ -309,12 +397,13 @@ void iavf_configure_queues(struct iavf_adapter *adapter) vqpi->rxq.ring_len = adapter->rx_rings[i].count; vqpi->rxq.dma_ring_addr = adapter->rx_rings[i].dma; vqpi->rxq.max_pkt_size = max_frame; - vqpi->rxq.databuffer_size = - ALIGN(adapter->rx_rings[i].rx_buf_len, - BIT_ULL(IAVF_RXQ_CTX_DBUFF_SHIFT)); + vqpi->rxq.databuffer_size = adapter->rx_rings[i].rx_buf_len; + if (IAVF_RXDID_ALLOWED(adapter)) + vqpi->rxq.rxdid = adapter->rxdid; if (CRC_OFFLOAD_ALLOWED(adapter)) vqpi->rxq.crc_disable = !!(adapter->netdev->features & NETIF_F_RXFCS); + vqpi->rxq.flags = rx_flags; vqpi++; } @@ -1405,6 +1494,67 @@ void iavf_disable_vlan_insertion_v2(struct iavf_adapter *adapter, u16 tpid) VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2); } +#if IS_ENABLED(CONFIG_PTP_1588_CLOCK) +/** + * iavf_virtchnl_send_ptp_cmd - Send one queued PTP command + * @adapter: adapter private structure + * + * De-queue one PTP command request and send the command message to the PF. + * Clear IAVF_FLAG_AQ_SEND_PTP_CMD if no more messages are left to send. + */ +void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter) +{ + struct iavf_ptp_aq_cmd *cmd; + int err; + + if (!adapter->ptp.clock) { + /* This shouldn't be possible to hit, since no messages should + * be queued if PTP is not initialized. + */ + pci_err(adapter->pdev, "PTP is not initialized\n"); + adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD; + return; + } + + mutex_lock(&adapter->ptp.aq_cmd_lock); + cmd = list_first_entry_or_null(&adapter->ptp.aq_cmds, + struct iavf_ptp_aq_cmd, list); + if (!cmd) { + /* no further PTP messages to send */ + adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD; + goto out_unlock; + } + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + pci_err(adapter->pdev, + "Cannot send PTP command %d, command %d pending\n", + cmd->v_opcode, adapter->current_op); + goto out_unlock; + } + + err = iavf_send_pf_msg(adapter, cmd->v_opcode, cmd->msg, cmd->msglen); + if (!err) { + /* Command was sent without errors, so we can remove it from + * the list and discard it. + */ + list_del(&cmd->list); + kfree(cmd); + } else { + /* We failed to send the command, try again next cycle */ + pci_err(adapter->pdev, "Failed to send PTP command %d\n", + cmd->v_opcode); + } + + if (list_empty(&adapter->ptp.aq_cmds)) + /* no further PTP messages to send */ + adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD; + +out_unlock: + mutex_unlock(&adapter->ptp.aq_cmd_lock); +} +#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */ + /** * iavf_print_link_message - print link up or down * @adapter: adapter structure @@ -1512,6 +1662,130 @@ iavf_set_adapter_link_speed_from_vpe(struct iavf_adapter *adapter, } /** + * iavf_get_qos_caps - get qos caps support + * @adapter: iavf adapter struct instance + * + * This function requests PF for Supported QoS Caps. + */ +void iavf_get_qos_caps(struct iavf_adapter *adapter) +{ + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, + "Cannot get qos caps, command %d pending\n", + adapter->current_op); + return; + } + + adapter->current_op = VIRTCHNL_OP_GET_QOS_CAPS; + adapter->aq_required &= ~IAVF_FLAG_AQ_GET_QOS_CAPS; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_QOS_CAPS, NULL, 0); +} + +/** + * iavf_set_quanta_size - set quanta size of queue chunk + * @adapter: iavf adapter struct instance + * @quanta_size: quanta size in bytes + * @queue_index: starting index of queue chunk + * @num_queues: number of queues in the queue chunk + * + * This function requests PF to set quanta size of queue chunk + * starting at queue_index. + */ +static void +iavf_set_quanta_size(struct iavf_adapter *adapter, u16 quanta_size, + u16 queue_index, u16 num_queues) +{ + struct virtchnl_quanta_cfg quanta_cfg; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, + "Cannot set queue quanta size, command %d pending\n", + adapter->current_op); + return; + } + + adapter->current_op = VIRTCHNL_OP_CONFIG_QUANTA; + quanta_cfg.quanta_size = quanta_size; + quanta_cfg.queue_select.type = VIRTCHNL_QUEUE_TYPE_TX; + quanta_cfg.queue_select.start_queue_id = queue_index; + quanta_cfg.queue_select.num_queues = num_queues; + adapter->aq_required &= ~IAVF_FLAG_AQ_CFG_QUEUES_QUANTA_SIZE; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_QUANTA, + (u8 *)&quanta_cfg, sizeof(quanta_cfg)); +} + +/** + * iavf_cfg_queues_quanta_size - configure quanta size of queues + * @adapter: adapter structure + * + * Request that the PF configure quanta size of allocated queues. + **/ +void iavf_cfg_queues_quanta_size(struct iavf_adapter *adapter) +{ + int quanta_size = IAVF_DEFAULT_QUANTA_SIZE; + + /* Set Queue Quanta Size to default */ + iavf_set_quanta_size(adapter, quanta_size, 0, + adapter->num_active_queues); +} + +/** + * iavf_cfg_queues_bw - configure bandwidth of allocated queues + * @adapter: iavf adapter structure instance + * + * This function requests PF to configure queue bandwidth of allocated queues + */ +void iavf_cfg_queues_bw(struct iavf_adapter *adapter) +{ + struct virtchnl_queues_bw_cfg *qs_bw_cfg; + struct net_shaper *q_shaper; + int qs_to_update = 0; + int i, inx = 0; + size_t len; + + if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) { + /* bail because we already have a command pending */ + dev_err(&adapter->pdev->dev, + "Cannot set tc queue bw, command %d pending\n", + adapter->current_op); + return; + } + + for (i = 0; i < adapter->num_active_queues; i++) { + if (adapter->tx_rings[i].q_shaper_update) + qs_to_update++; + } + len = struct_size(qs_bw_cfg, cfg, qs_to_update); + qs_bw_cfg = kzalloc(len, GFP_KERNEL); + if (!qs_bw_cfg) + return; + + qs_bw_cfg->vsi_id = adapter->vsi.id; + qs_bw_cfg->num_queues = qs_to_update; + + for (i = 0; i < adapter->num_active_queues; i++) { + struct iavf_ring *tx_ring = &adapter->tx_rings[i]; + + q_shaper = &tx_ring->q_shaper; + if (tx_ring->q_shaper_update) { + qs_bw_cfg->cfg[inx].queue_id = i; + qs_bw_cfg->cfg[inx].shaper.peak = q_shaper->bw_max; + qs_bw_cfg->cfg[inx].shaper.committed = q_shaper->bw_min; + qs_bw_cfg->cfg[inx].tc = 0; + inx++; + } + } + + adapter->current_op = VIRTCHNL_OP_CONFIG_QUEUE_BW; + adapter->aq_required &= ~IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW; + iavf_send_pf_msg(adapter, VIRTCHNL_OP_CONFIG_QUEUE_BW, + (u8 *)qs_bw_cfg, len); + kfree(qs_bw_cfg); +} + +/** * iavf_enable_channels * @adapter: adapter structure * @@ -1966,8 +2240,8 @@ static void iavf_activate_fdir_filters(struct iavf_adapter *adapter) * list on PF is already cleared after a reset */ list_del(&f->list); + iavf_dec_fdir_active_fltr(adapter, f); kfree(f); - adapter->fdir_active_fltr--; } } spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -1977,6 +2251,37 @@ static void iavf_activate_fdir_filters(struct iavf_adapter *adapter) } /** + * iavf_virtchnl_ptp_get_time - Respond to VIRTCHNL_OP_1588_PTP_GET_TIME + * @adapter: private adapter structure + * @data: the message from the PF + * @len: length of the message from the PF + * + * Handle the VIRTCHNL_OP_1588_PTP_GET_TIME message from the PF. This message + * is sent by the PF in response to the same op as a request from the VF. + * Extract the 64bit nanoseconds time from the message and store it in + * cached_phc_time. Then, notify any thread that is waiting for the update via + * the wait queue. + */ +static void iavf_virtchnl_ptp_get_time(struct iavf_adapter *adapter, + void *data, u16 len) +{ + struct virtchnl_phc_time *msg = data; + + if (len != sizeof(*msg)) { + dev_err_once(&adapter->pdev->dev, + "Invalid VIRTCHNL_OP_1588_PTP_GET_TIME from PF. Got size %u, expected %zu\n", + len, sizeof(*msg)); + return; + } + + adapter->ptp.cached_phc_time = msg->time; + adapter->ptp.cached_phc_updated = jiffies; + adapter->ptp.phc_time_ready = true; + + wake_up(&adapter->ptp.phc_time_waitqueue); +} + +/** * iavf_virtchnl_completion * @adapter: adapter structure * @v_opcode: opcode sent by PF @@ -2140,8 +2445,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, dev_err(&adapter->pdev->dev, "%s\n", msg); list_del(&fdir->list); + iavf_dec_fdir_active_fltr(adapter, fdir); kfree(fdir); - adapter->fdir_active_fltr--; } } spin_unlock_bh(&adapter->fdir_fltr_lock); @@ -2231,6 +2536,18 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC; break; + case VIRTCHNL_OP_GET_QOS_CAPS: + dev_warn(&adapter->pdev->dev, "Failed to Get Qos CAPs, error %s\n", + iavf_stat_str(&adapter->hw, v_retval)); + break; + case VIRTCHNL_OP_CONFIG_QUANTA: + dev_warn(&adapter->pdev->dev, "Failed to Config Quanta, error %s\n", + iavf_stat_str(&adapter->hw, v_retval)); + break; + case VIRTCHNL_OP_CONFIG_QUEUE_BW: + dev_warn(&adapter->pdev->dev, "Failed to Config Queue BW, error %s\n", + iavf_stat_str(&adapter->hw, v_retval)); + break; default: dev_err(&adapter->pdev->dev, "PF returned error %d (%s) to our request %d\n", v_retval, iavf_stat_str(&adapter->hw, v_retval), @@ -2376,6 +2693,25 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, aq_required; } break; + case VIRTCHNL_OP_GET_SUPPORTED_RXDIDS: + if (msglen != sizeof(u64)) + return; + + adapter->supp_rxdids = *(u64 *)msg; + + break; + case VIRTCHNL_OP_1588_PTP_GET_CAPS: + if (msglen != sizeof(adapter->ptp.hw_caps)) + return; + + adapter->ptp.hw_caps = *(struct virtchnl_ptp_caps *)msg; + + /* process any state change needed due to new capabilities */ + iavf_ptp_process_caps(adapter); + break; + case VIRTCHNL_OP_1588_PTP_GET_TIME: + iavf_virtchnl_ptp_get_time(adapter, msg, msglen); + break; case VIRTCHNL_OP_ENABLE_QUEUES: /* enable transmits */ iavf_irq_enable(adapter, true); @@ -2456,8 +2792,12 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, list) { if (fdir->state == IAVF_FDIR_FLTR_ADD_PENDING) { if (add_fltr->status == VIRTCHNL_FDIR_SUCCESS) { - dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is added\n", - fdir->loc); + if (!iavf_is_raw_fdir(fdir)) + dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is added\n", + fdir->loc); + else + dev_info(&adapter->pdev->dev, "Flow Director filter (raw) for TC handle %x is added\n", + TC_U32_USERHTID(fdir->cls_u32_handle)); fdir->state = IAVF_FDIR_FLTR_ACTIVE; fdir->flow_id = add_fltr->flow_id; } else { @@ -2465,8 +2805,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, add_fltr->status); iavf_print_fdir_fltr(adapter, fdir); list_del(&fdir->list); + iavf_dec_fdir_active_fltr(adapter, fdir); kfree(fdir); - adapter->fdir_active_fltr--; } } } @@ -2484,11 +2824,15 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, if (del_fltr->status == VIRTCHNL_FDIR_SUCCESS || del_fltr->status == VIRTCHNL_FDIR_FAILURE_RULE_NONEXIST) { - dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is deleted\n", - fdir->loc); + if (!iavf_is_raw_fdir(fdir)) + dev_info(&adapter->pdev->dev, "Flow Director filter with location %u is deleted\n", + fdir->loc); + else + dev_info(&adapter->pdev->dev, "Flow Director filter (raw) for TC handle %x is deleted\n", + TC_U32_USERHTID(fdir->cls_u32_handle)); list_del(&fdir->list); + iavf_dec_fdir_active_fltr(adapter, fdir); kfree(fdir); - adapter->fdir_active_fltr--; } else { fdir->state = IAVF_FDIR_FLTR_ACTIVE; dev_info(&adapter->pdev->dev, "Failed to delete Flow Director filter with status: %d\n", @@ -2565,6 +2909,24 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, if (!v_retval) iavf_netdev_features_vlan_strip_set(netdev, false); break; + case VIRTCHNL_OP_GET_QOS_CAPS: { + u16 len = struct_size(adapter->qos_caps, cap, + IAVF_MAX_QOS_TC_NUM); + + memcpy(adapter->qos_caps, msg, min(msglen, len)); + + adapter->aq_required |= IAVF_FLAG_AQ_CFG_QUEUES_QUANTA_SIZE; + } + break; + case VIRTCHNL_OP_CONFIG_QUANTA: + break; + case VIRTCHNL_OP_CONFIG_QUEUE_BW: { + int i; + /* shaper configuration is successful for all queues */ + for (i = 0; i < adapter->num_active_queues; i++) + adapter->tx_rings[i].q_shaper_update = false; + } + break; default: if (adapter->current_op && (v_opcode != adapter->current_op)) dev_warn(&adapter->pdev->dev, "Expected response %d from PF, received %d\n", |