ice: Create and register virtual bus for RDMA
Subsystems (2)
Tony Nguyen
maintainerPATCH v4 1/6 ice: Create and register virtual bus for RDMA
From: Dave Ertman <[email protected]>
The RDMA block does not have its own PCI function, instead it must utilize the ice driver to gain access to the PCI device. Create a virtual bus device so the irdma driver can register a virtual bus driver to bind to it and receive device data. The device data contains all of the relevant information that the irdma peer will need to access this PF's IIDC API callbacks.
Note the header file iidc.h is located under include/linux/net/intel as this is a unified header file to be used by all consumers of the IIDC interface.
--- MAINTAINERS | 1 + drivers/net/ethernet/intel/Kconfig | 1 + drivers/net/ethernet/intel/ice/Makefile | 1 + drivers/net/ethernet/intel/ice/ice.h | 13 + .../net/ethernet/intel/ice/ice_adminq_cmd.h | 1 + drivers/net/ethernet/intel/ice/ice_common.c | 18 +- drivers/net/ethernet/intel/ice/ice_dcb_lib.c | 31 ++ drivers/net/ethernet/intel/ice/ice_dcb_lib.h | 3 + .../net/ethernet/intel/ice/ice_hw_autogen.h | 1 + drivers/net/ethernet/intel/ice/ice_idc.c | 400 ++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_idc_int.h | 67 +++ drivers/net/ethernet/intel/ice/ice_lib.c | 11 + drivers/net/ethernet/intel/ice/ice_lib.h | 2 + drivers/net/ethernet/intel/ice/ice_main.c | 56 ++- drivers/net/ethernet/intel/ice/ice_type.h | 1 + include/linux/net/intel/iidc.h | 337 +++++++++++++++ 16 files changed, 941 insertions(+), 3 deletions(-) create mode 100644 drivers/net/ethernet/intel/ice/ice_idc.c create mode 100644 drivers/net/ethernet/intel/ice/ice_idc_int.h create mode 100644 include/linux/net/intel/iidc.h
MAINTAINERS +1 -0
@@ -8427,6 +8427,7 @@ F: Documentation/networking/device_drivers/intel/ice.rst F: drivers/net/ethernet/intel/ F: drivers/net/ethernet/intel/*/ F: include/linux/avf/virtchnl.h +F: include/linux/net/intel/iidc.h INTEL FRAMEBUFFER DRIVER (excluding 810 and 815) M: Maik Broemme <[email protected]>
drivers/net/ethernet/intel/Kconfig +1 -0
@@ -294,6 +294,7 @@ config ICE tristate "Intel(R) Ethernet Connection E800 Series Support" default n depends on PCI_MSI + select VIRTUAL_BUS ---help--- This driver supports Intel(R) Ethernet Connection E800 Series of devices. For more information on how to identify your adapter, go
drivers/net/ethernet/intel/ice/Makefile +1 -0
@@ -19,6 +19,7 @@ ice-y := ice_main.o \ ice_txrx.o \ ice_flex_pipe.o \ ice_flow.o \ + ice_idc.o \ ice_ethtool.o ice-$(CONFIG_PCI_IOV) += ice_virtchnl_pf.o ice_sriov.o ice-$(CONFIG_DCB) += ice_dcb.o ice_dcb_nl.o ice_dcb_lib.o
drivers/net/ethernet/intel/ice/ice.h +13 -0
@@ -33,6 +33,7 @@#include <linux/if_bridge.h> #include <linux/ctype.h> #include <linux/bpf.h> +#include <linux/virtual_bus.h> #include <linux/avf/virtchnl.h> #include <net/ipv6.h> #include <net/xdp_sock.h>
@@ -47,6 +48,7 @@#include "ice_switch.h" #include "ice_common.h" #include "ice_sched.h" +#include "ice_idc_int.h" #include "ice_virtchnl_pf.h" #include "ice_sriov.h" #include "ice_xsk.h"
@@ -75,6 +77,8 @@ extern const char ice_drv_ver[];#define ICE_MAX_LG_RSS_QS 256#define ICE_RES_VALID_BIT 0x8000#define ICE_RES_MISC_VEC_ID (ICE_RES_VALID_BIT - 1) +#define ICE_RDMA_NUM_VECS 4 +#define ICE_RES_RDMA_VEC_ID (ICE_RES_MISC_VEC_ID - 1)#define ICE_INVAL_Q_INDEX 0xffff#define ICE_INVAL_VFID 256
@@ -333,11 +337,13 @@ struct ice_q_vector {enum ice_pf_flags {ICE_FLAG_FLTR_SYNC , +ICE_FLAG_IWARP_ENA ,ICE_FLAG_RSS_ENA ,ICE_FLAG_SRIOV_ENA ,ICE_FLAG_SRIOV_CAPABLE ,ICE_FLAG_DCB_CAPABLE ,ICE_FLAG_DCB_ENA , +ICE_FLAG_PEER_ENA ,ICE_FLAG_ADV_FEATURES ,ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA ,ICE_FLAG_NO_MEDIA ,
@@ -382,6 +388,8 @@ struct ice_pf {struct mutex sw_mutex;/* lock for protecting VSI alloc flow */ struct mutex tc_mutex;/* lock to protect TC changes */ u32 msg_enable; +u32 num_rdma_msix;/* Total MSIX vectors for RDMA driver */ +u32 rdma_base_vector;u32 hw_csum_rx_error;u32 oicr_idx;/* Other interrupt cause MSIX vector index */ u32 num_avail_sw_msix;/* remaining MSIX SW vectors left unclaimed */
@@ -408,6 +416,7 @@ struct ice_pf {unsigned long tx_timeout_last_recovery;u32 tx_timeout_recovery_level;char int_name[ICE_INT_NAME_STR_LEN ]; +struct ice_peer_dev_int **peers;u32 sw_int_count; };
@@ -521,6 +530,10 @@ int ice_get_rss(struct ice_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size);void ice_fill_rss_lut (u8 *lut,u16 rss_table_size,u16 rss_size);int ice_schedule_reset (struct ice_pf *pf,enum ice_reset_req reset);void ice_print_link_msg (struct ice_vsi *vsi,bool isup); +int ice_init_peer_devices (struct ice_pf *pf); +int +ice_for_each_peer (struct ice_pf *pf,void *data, +int (*fn)(struct ice_peer_dev_int *,void *));int ice_open (struct net_device *netdev);int ice_stop (struct net_device *netdev);
drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +1 -0
@@ -108,6 +108,7 @@ struct ice_aqc_list_caps_elem {#define ICE_AQC_CAPS_TXQS 0x0042#define ICE_AQC_CAPS_MSIX 0x0043#define ICE_AQC_CAPS_MAX_MTU 0x0047 +#define ICE_AQC_CAPS_IWARP 0x0051u8 major_ver;u8 minor_ver;
drivers/net/ethernet/intel/ice/ice_common.c +17 -1
@@ -848,7 +848,8 @@ enum ice_status ice_check_reset(struct ice_hw *hw) GLNVM_ULD_POR_DONE_1_M |\ GLNVM_ULD_PCIER_DONE_2_M) - uld_mask =ICE_RESET_DONE_MASK ; + uld_mask =ICE_RESET_DONE_MASK | (hw->func_caps.common_cap.iwarp ? +GLNVM_ULD_PE_DONE_M :0 );/* Device is Active; check Global Reset processes are done */ for (cnt =0 ; cnt <ICE_PF_RESET_WAIT_COUNT ; cnt++) {
@@ -1767,6 +1768,11 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count,"%s: msix_vector_first_id = %d\n" , prefix, caps->msix_vector_first_id);break ; +case ICE_AQC_CAPS_IWARP : + caps->iwarp = (number ==1 ); +ice_debug (hw,ICE_DBG_INIT , +"%s: iwarp = %d\n" , prefix, caps->iwarp); +break ;case ICE_AQC_CAPS_MAX_MTU : caps->max_mtu = number; ice_debug(hw, ICE_DBG_INIT, "%s: max_mtu = %d\n",
@@ -1790,6 +1796,16 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count,ice_debug (hw,ICE_DBG_INIT ,"%s: maxtc = %d (based on #ports)\n" , prefix, caps->maxtc); +if (caps->iwarp) { +ice_debug (hw,ICE_DBG_INIT ,"%s: forcing RDMA off\n" , + prefix); + caps->iwarp =0 ; + } + +/* print message only when processing device capabilities */ +if (dev_p) +dev_info (ice_hw_to_dev (hw), +"RDMA functionality is not available with the current device configuration.\n" ); } }
drivers/net/ethernet/intel/ice/ice_dcb_lib.c +31 -0
@@ -763,6 +763,37 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_ring *tx_ring,return 0 ; } +/** +* ice_setup_dcb_qos_info - Setup DCB QoS information +* @pf: ptr to ice_pf +* @qos_info: QoS param instance +*/ +void ice_setup_dcb_qos_info (struct ice_pf *pf,struct iidc_qos_params *qos_info) +{ +struct ice_dcbx_cfg *dcbx_cfg; +u32 up2tc; +int i; + + dcbx_cfg = &pf->hw.port_info->local_dcbx_cfg; + up2tc =rd32 (&pf->hw,PRTDCB_TUP2TC ); + qos_info->num_apps = dcbx_cfg->numapps; + + qos_info->num_tc =ice_dcb_get_num_tc (dcbx_cfg); + +for (i =0 ; i <IIDC_MAX_USER_PRIORITY ; i++) + qos_info->up2tc[i] = (up2tc >> (i *3 )) &0x7 ; + +for (i =0 ; i <IEEE_8021QAZ_MAX_TCS ; i++) + qos_info->tc_info[i].rel_bw = + dcbx_cfg->etscfg.tcbwtable[i]; + +for (i =0 ; i < qos_info->num_apps; i++) { + qos_info->apps[i].priority = dcbx_cfg->app[i].priority; + qos_info->apps[i].prot_id = dcbx_cfg->app[i].prot_id; + qos_info->apps[i].selector = dcbx_cfg->app[i].selector; + } +} +/** * ice_dcb_process_lldp_set_mib_change - Process MIB change * @pf: ptr to ice_pf
drivers/net/ethernet/intel/ice/ice_dcb_lib.h +3 -0
@@ -29,6 +29,8 @@ int ice_tx_prepare_vlan_flags_dcb(struct ice_ring *tx_ring, struct ice_tx_buf *first);void +ice_setup_dcb_qos_info (struct ice_pf *pf,struct iidc_qos_params *qos_info); +void ice_dcb_process_lldp_set_mib_change (struct ice_pf *pf,struct ice_rq_event_info *event);void ice_vsi_cfg_netdev_tc (struct ice_vsi *vsi,u8 ena_tc);
@@ -82,6 +84,7 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_ring __always_unused *tx_ring,#define ice_update_dcb_stats (pf) do {} while (0)#define ice_pf_dcb_recfg (pf) do {} while (0)#define ice_vsi_cfg_dcb_rings (vsi) do {} while (0) +#define ice_setup_dcb_qos_info (pf, qos_info) do {} while (0)#define ice_dcb_process_lldp_set_mib_change (pf, event) do {} while (0)#define ice_set_cgd_num (tlan_ctx, ring) do {} while (0)#define ice_vsi_cfg_netdev_tc (vsi, ena_tc) do {} while (0)
drivers/net/ethernet/intel/ice/ice_hw_autogen.h +1 -0
@@ -58,6 +58,7 @@#define PRTDCB_GENS 0x00083020#define PRTDCB_GENS_DCBX_STATUS_S 0#define PRTDCB_GENS_DCBX_STATUS_M ICE_M(0x7, 0) +#define PRTDCB_TUP2TC 0x001D26C0#define GL_PREEXT_L2_PMASK0 (_i) (0x0020F0FC + ((_i) * 4))#define GL_PREEXT_L2_PMASK1 (_i) (0x0020F108 + ((_i) * 4))#define GLFLXP_RXDID_FLX_WRD_0 (_i) (0x0045c800 + ((_i) * 4))
drivers/net/ethernet/intel/ice/ice_idc.c new file +400 -0
400 lines not on this page · raw message
drivers/net/ethernet/intel/ice/ice_idc_int.h new file +67 -0
67 lines not on this page · raw message
drivers/net/ethernet/intel/ice/ice_lib.c +11 -0
@@ -504,6 +504,17 @@ bool ice_is_safe_mode(struct ice_pf *pf)return !test_bit (ICE_FLAG_ADV_FEATURES , pf->flags); } +/** +* ice_is_peer_ena +* @pf: pointer to the PF struct +* +* returns true if peer devices/drivers are supported, false otherwise +*/ +bool ice_is_peer_ena (struct ice_pf *pf) +{ +return test_bit (ICE_FLAG_PEER_ENA , pf->flags); +} +/** * ice_vsi_clean_rss_flow_fld - Delete RSS configuration * @vsi: the VSI being cleaned up
drivers/net/ethernet/intel/ice/ice_lib.h +2 -0
@@ -104,6 +104,8 @@ ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set);bool ice_is_safe_mode (struct ice_pf *pf); +bool ice_is_peer_ena (struct ice_pf *pf); +bool ice_is_dflt_vsi_in_use (struct ice_sw *sw);bool ice_is_vsi_dflt_vsi (struct ice_sw *sw,struct ice_vsi *vsi);
drivers/net/ethernet/intel/ice/ice_main.c +54 -2
106 lines not on this page · raw message
drivers/net/ethernet/intel/ice/ice_type.h +1 -0
@@ -189,6 +189,7 @@ struct ice_hw_common_caps {u8 rss_table_entry_width;/* RSS Entry width in bits */ u8 dcb; +u8 iwarp; };/* Function specific capabilities */
include/linux/net/intel/iidc.h new file +337 -0
337 lines not on this page · raw message
Signature · 1 line
2.20.1
Tony Nguyen
maintainerPATCH v4 2/6 ice: Complete RDMA peer registration
From: Dave Ertman <[email protected]>
Ensure that the peer supports the minimal set of operations required for operation and, if so, open the connection to the peer.
--- drivers/net/ethernet/intel/ice/ice_idc.c | 288 ++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_idc_int.h | 36 +++ drivers/net/ethernet/intel/ice/ice_lib.c | 33 ++ drivers/net/ethernet/intel/ice/ice_lib.h | 2 + drivers/net/ethernet/intel/ice/ice_main.c | 18 +- drivers/net/ethernet/intel/ice/ice_switch.c | 23 ++ drivers/net/ethernet/intel/ice/ice_switch.h | 2 + .../net/ethernet/intel/ice/ice_virtchnl_pf.c | 25 -- 8 files changed, 401 insertions(+), 26 deletions(-)
drivers/net/ethernet/intel/ice/ice_idc.c +288 -0
@@ -145,6 +145,78 @@ ice_peer_state_change(struct ice_peer_dev_int *peer_dev, long new_state,mutex_unlock (&peer_dev->peer_dev_state_mutex); } +/** +* ice_peer_close - close a peer device +* @peer_dev_int: device to close +* @data: pointer to opaque data +* +* This function will also set the state bit for the peer to CLOSED. This +* function is meant to be called from a ice_for_each_peer(). +*/ +int ice_peer_close (struct ice_peer_dev_int *peer_dev_int,void *data) +{ +enum iidc_close_reason reason = *(enum iidc_close_reason *)(data); +struct iidc_peer_dev *peer_dev; +struct ice_pf *pf; +int i; + + peer_dev = &peer_dev_int->peer_dev; +/* return 0 so ice_for_each_peer will continue closing other peers */ +if (!ice_validate_peer_dev (peer_dev)) +return 0 ; + pf =pci_get_drvdata (peer_dev->pdev); + +if (test_bit (__ICE_DOWN, pf->state) || +test_bit (__ICE_SUSPENDED, pf->state) || +test_bit (__ICE_NEEDS_RESTART, pf->state)) +return 0 ; + +mutex_lock (&peer_dev_int->peer_dev_state_mutex); + +/* no peer driver, already closed, closing or opening nothing to do */ +if (test_bit (ICE_PEER_DEV_STATE_CLOSED , peer_dev_int->state) || +test_bit (ICE_PEER_DEV_STATE_CLOSING , peer_dev_int->state) || +test_bit (ICE_PEER_DEV_STATE_OPENING , peer_dev_int->state) || +test_bit (ICE_PEER_DEV_STATE_REMOVED , peer_dev_int->state)) + goto peer_close_out; + +/* Set the peer state to CLOSING */ +ice_peer_state_change (peer_dev_int,ICE_PEER_DEV_STATE_CLOSING , true); + +for (i =0 ; i <IIDC_EVENT_NBITS ; i++) +bitmap_zero (peer_dev_int->current_events[i].type, +IIDC_EVENT_NBITS ); + +if (peer_dev->peer_ops && peer_dev->peer_ops->close) + peer_dev->peer_ops->close (peer_dev, reason); + +/* Set the peer state to CLOSED */ +ice_peer_state_change (peer_dev_int,ICE_PEER_DEV_STATE_CLOSED , true); + +peer_close_out: +mutex_unlock (&peer_dev_int->peer_dev_state_mutex); + +return 0 ; +} + +/** +* ice_peer_update_vsi - update the pf_vsi info in peer_dev struct +* @peer_dev_int: pointer to peer dev internal struct +* @data: opaque pointer - VSI to be updated +*/ +int ice_peer_update_vsi (struct ice_peer_dev_int *peer_dev_int,void *data) +{ +struct ice_vsi *vsi = (struct ice_vsi *)data; +struct iidc_peer_dev *peer_dev; + + peer_dev = &peer_dev_int->peer_dev; +if (!peer_dev) +return 0 ; + + peer_dev->pf_vsi_num = vsi->vsi_num; +return 0 ; +} +/** * ice_for_each_peer - iterate across and call function for each peer dev * @pf: pointer to private board struct
@@ -175,6 +247,89 @@ ice_for_each_peer(struct ice_pf *pf, void *data,return 0 ; } +/** +* ice_finish_init_peer_device - complete peer device initialization +* @peer_dev_int: ptr to peer device internal struct +* @data: ptr to opaque data +* +* This function completes remaining initialization of peer_devices +*/ +int +ice_finish_init_peer_device (struct ice_peer_dev_int *peer_dev_int, +void __always_unused *data) +{ +struct iidc_peer_dev *peer_dev; +struct iidc_peer_drv *peer_drv; +struct device *dev; +struct ice_pf *pf; +int ret =0 ; + + peer_dev = &peer_dev_int->peer_dev; +/* peer_dev will not always be populated at the time of this check */ +if (!ice_validate_peer_dev (peer_dev)) +return ret; + + peer_drv = peer_dev->peer_drv; + pf =pci_get_drvdata (peer_dev->pdev); + dev =ice_pf_to_dev (pf); +/* There will be several assessments of the peer_dev's state in this +* chunk of logic. We need to hold the peer_dev_int's state mutex +* for the entire part so that the flow progresses without another +* context changing things mid-flow +*/ +mutex_lock (&peer_dev_int->peer_dev_state_mutex); + +if (!peer_dev->peer_ops) { +dev_err (dev,"peer_ops not defined on peer dev\n" ); + goto init_unlock; + } + +if (!peer_dev->peer_ops->open) { +dev_err (dev,"peer_ops:open not defined on peer dev\n" ); + goto init_unlock; + } + +if (!peer_dev->peer_ops->close) { +dev_err (dev,"peer_ops:close not defined on peer dev\n" ); + goto init_unlock; + } + +/* Peer driver expected to set driver_id during registration */ +if (!peer_drv->driver_id) { +dev_err (dev,"Peer driver did not set driver_id\n" ); + goto init_unlock; + } + +if ((test_bit (ICE_PEER_DEV_STATE_CLOSED , peer_dev_int->state) || +test_bit (ICE_PEER_DEV_STATE_PROBED , peer_dev_int->state)) && +ice_pf_state_is_nominal (pf)) { +/* If the RTNL is locked, we defer opening the peer +* until the next time this function is called by the +* service task. +*/ +if (rtnl_is_locked ()) + goto init_unlock; +ice_peer_state_change (peer_dev_int,ICE_PEER_DEV_STATE_OPENING , + true); + ret = peer_dev->peer_ops->open (peer_dev); +if (ret) { +dev_err (dev,"Peer %d failed to open\n" , + peer_dev->peer_dev_id); +ice_peer_state_change (peer_dev_int, +ICE_PEER_DEV_STATE_PROBED , true); + goto init_unlock; + } + +ice_peer_state_change (peer_dev_int,ICE_PEER_DEV_STATE_OPENED , + true); + } + +init_unlock: +mutex_unlock (&peer_dev_int->peer_dev_state_mutex); + +return ret; +} +/** * ice_unreg_peer_device - unregister specified device * @peer_dev_int: ptr to peer device internal
@@ -199,6 +354,9 @@ ice_unreg_peer_device(struct ice_peer_dev_int *peer_dev_int,if (peer_dev_int->ice_peer_wq) {if (peer_dev_int->peer_prep_task.func)cancel_work_sync (&peer_dev_int->peer_prep_task); + +if (peer_dev_int->peer_close_task.func) +cancel_work_sync (&peer_dev_int->peer_close_task);destroy_workqueue (peer_dev_int->ice_peer_wq); }
@@ -229,6 +387,134 @@ ice_unroll_peer(struct ice_peer_dev_int *peer_dev_int,return 0 ; } +/** +* ice_peer_unregister - request to unregister peer +* @peer_dev: peer device +* +* This function triggers close/remove on peer_dev allowing peer +* to unregister. +*/ +static int ice_peer_unregister (struct iidc_peer_dev *peer_dev) +{ +enum iidc_close_reason reason =IIDC_REASON_PEER_DEV_UNINIT ; +struct ice_peer_dev_int *peer_dev_int; +struct ice_pf *pf; +int ret; + +if (!ice_validate_peer_dev (peer_dev)) +return -EINVAL ; + + pf =pci_get_drvdata (peer_dev->pdev); +if (ice_is_reset_in_progress (pf->state)) +return -EBUSY ; + + peer_dev_int =peer_to_ice_dev_int (peer_dev); + + ret =ice_peer_close (peer_dev_int, &reason); +if (ret) +return ret; + + peer_dev->peer_ops =NULL ; + +ice_peer_state_change (peer_dev_int,ICE_PEER_DEV_STATE_REMOVED , false); + +return 0 ; +} + +/** +* ice_peer_register - Called by peer to open communication with LAN +* @peer_dev: ptr to peer device +* +* registering peer is expected to populate the ice_peerdrv->name field +* before calling this function. +*/ +static int ice_peer_register (struct iidc_peer_dev *peer_dev) +{ +struct ice_peer_drv_int *peer_drv_int; +struct ice_peer_dev_int *peer_dev_int; +struct iidc_peer_drv *peer_drv; + +if (!peer_dev) { +pr_err ("Failed to reg peer dev: peer_dev ptr NULL\n" ); +return -EINVAL ; + } + +if (!peer_dev->pdev) { +pr_err ("Failed to reg peer dev: peer dev pdev NULL\n" ); +return -EINVAL ; + } + +if (!peer_dev->peer_ops || !peer_dev->ops) { +pr_err ("Failed to reg peer dev: peer dev peer_ops/ops NULL\n" ); +return -EINVAL ; + } + + peer_drv = peer_dev->peer_drv; +if (!peer_drv) { +pr_err ("Failed to reg peer dev: peer drv NULL\n" ); +return -EINVAL ; + } + + peer_dev_int =peer_to_ice_dev_int (peer_dev); + peer_drv_int = peer_dev_int->peer_drv_int; +if (!peer_drv_int) { +pr_err ("Failed to match peer_drv_int to peer_dev\n" ); +return -EINVAL ; + } + + peer_drv_int->peer_drv = peer_drv; + +ice_peer_state_change (peer_dev_int,ICE_PEER_DEV_STATE_PROBED , false); + +return 0 ; +} + +/** +* ice_peer_update_vsi_filter - update main VSI filters for RDMA +* @peer_dev: pointer to RDMA peer device +* @filter: selection of filters to enable or disable +* @enable: bool whether to enable or disable filters +*/ +static int +ice_peer_update_vsi_filter (struct iidc_peer_dev *peer_dev, +enum iidc_rdma_filter __always_unused filter, +bool enable) +{ +struct ice_vsi *vsi; +struct ice_pf *pf; +int ret; + +if (!ice_validate_peer_dev (peer_dev)) +return -EINVAL ; + + pf =pci_get_drvdata (peer_dev->pdev); + + vsi =ice_get_main_vsi (pf); +if (!vsi) +return -EINVAL ; + + ret =ice_cfg_iwarp_fltr (&pf->hw, vsi->idx, enable); + +if (ret) { +dev_err (ice_pf_to_dev (pf),"Failed to %sable iWARP filtering\n" , + enable ?"en" :"dis" ); + }else { +if (enable) + vsi->info.q_opt_flags |=ICE_AQ_VSI_Q_OPT_PE_FLTR_EN ; +else + vsi->info.q_opt_flags &= ~ICE_AQ_VSI_Q_OPT_PE_FLTR_EN ; + } + +return ret; +} + +/* Initialize the ice_ops struct, which is used in 'ice_init_peer_devices' */ +static const struct iidc_ops ops = { + .peer_register = ice_peer_register, + .peer_unregister = ice_peer_unregister, + .update_vsi_filter = ice_peer_update_vsi_filter, +}; +/** * ice_reserve_peer_qvector - Reserve vector resources for peer drivers * @pf: board private structure to initialize
@@ -363,6 +649,8 @@ int ice_init_peer_devices(struct ice_pf *pf)/* for DCB, override the qos_info defaults. */ ice_setup_dcb_qos_info (pf, qos_info); +/* Initialize ice_ops */ + peer_dev->ops = &ops;/* make sure peer specific resources such as msix_count and * msix_entries are initialized
drivers/net/ethernet/intel/ice/ice_idc_int.h +36 -0
@@ -62,6 +62,42 @@ struct ice_peer_dev_int {enum iidc_close_reason rst_type; }; +int ice_peer_update_vsi (struct ice_peer_dev_int *peer_dev_int,void *data);int ice_unroll_peer (struct ice_peer_dev_int *peer_dev_int,void *data);int ice_unreg_peer_device (struct ice_peer_dev_int *peer_dev_int,void *data); +int ice_peer_close (struct ice_peer_dev_int *peer_dev_int,void *data); +int +ice_finish_init_peer_device (struct ice_peer_dev_int *peer_dev_int,void *data); + +static inline struct +ice_peer_dev_int *peer_to_ice_dev_int (struct iidc_peer_dev *peer_dev) +{ + return container_of(peer_dev, struct ice_peer_dev_int, peer_dev); +} + +static inline bool ice_validate_peer_dev (struct iidc_peer_dev *peer_dev) +{ +struct ice_peer_dev_int *peer_dev_int; +struct ice_pf *pf; + +if (!peer_dev || !peer_dev->pdev) +return false; + +if (!peer_dev->peer_ops) +return false; + + pf =pci_get_drvdata (peer_dev->pdev); +if (!pf) +return false; + + peer_dev_int =peer_to_ice_dev_int (peer_dev); +if (!peer_dev_int) +return false; + +if (test_bit (ICE_PEER_DEV_STATE_REMOVED , peer_dev_int->state) || +test_bit (ICE_PEER_DEV_STATE_INIT , peer_dev_int->state)) +return false; + +return true; +}#endif /* !_ICE_IDC_INT_H_ */
drivers/net/ethernet/intel/ice/ice_lib.c +33 -0
@@ -1379,6 +1379,30 @@ ice_add_mac_to_list(struct ice_vsi *vsi, struct list_head *add_list,return 0 ; } +/** +* ice_pf_state_is_nominal - checks the PF for nominal state +* @pf: pointer to PF to check +* +* Check the PF's state for a collection of bits that would indicate +* the PF is in a state that would inhibit normal operation for +* driver functionality. +* +* Returns true if PF is in a nominal state, false otherwise +*/ +bool ice_pf_state_is_nominal (struct ice_pf *pf) +{ + DECLARE_BITMAP(check_bits, __ICE_STATE_NBITS) = { 0 }; + +if (!pf) +return false; + +bitmap_set (check_bits,0 , __ICE_STATE_NOMINAL_CHECK_BITS); +if (bitmap_intersects (pf->state, check_bits, __ICE_STATE_NBITS)) +return false; + +return true; +} +/** * ice_update_eth_stats - Update VSI-specific ethernet statistics counters * @vsi: the VSI to be updated
@@ -2390,6 +2414,15 @@ void ice_vsi_free_rx_rings(struct ice_vsi *vsi)*/ void ice_vsi_close (struct ice_vsi *vsi) { +enum iidc_close_reason reason =IIDC_REASON_INTERFACE_DOWN ; + +if (!ice_is_safe_mode (vsi->back) && vsi->type ==ICE_VSI_PF ) { +int ret =ice_for_each_peer (vsi->back, &reason, ice_peer_close); + +if (ret) +dev_dbg (ice_pf_to_dev (vsi->back),"Peer device did not implement close function\n" ); + } +if (!test_and_set_bit (__ICE_DOWN, vsi->state))ice_down (vsi);
drivers/net/ethernet/intel/ice/ice_lib.h +2 -0
@@ -14,6 +14,8 @@ ice_add_mac_to_list(struct ice_vsi *vsi, struct list_head *add_list,void ice_free_fltr_list (struct device *dev,struct list_head *h); +bool ice_pf_state_is_nominal (struct ice_pf *pf); +void ice_update_eth_stats (struct ice_vsi *vsi);int ice_vsi_cfg_rxqs (struct ice_vsi *vsi);
drivers/net/ethernet/intel/ice/ice_main.c +17 -1
@@ -1490,6 +1490,9 @@ static void ice_service_task(struct work_struct *work)return ; } +/* Invoke remaining initialization of peer devices */ +ice_for_each_peer (pf,NULL , ice_finish_init_peer_device); +ice_process_vflr_event (pf);ice_clean_mailboxq_subtask (pf);
@@ -3447,6 +3450,7 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)static void ice_remove (struct pci_dev *pdev) {struct ice_pf *pf =pci_get_drvdata (pdev); +enum iidc_close_reason reason;int i;if (!pf)
@@ -3463,8 +3467,12 @@ static void ice_remove(struct pci_dev *pdev)ice_free_vfs (pf); } -set_bit (__ICE_DOWN, pf->state);ice_service_task_stop (pf); +if (ice_is_peer_ena (pf)) { + reason =IIDC_REASON_INTERFACE_DOWN ; +ice_for_each_peer (pf, &reason, ice_peer_close); + } +set_bit (__ICE_DOWN, pf->state);ice_vsi_release_all (pf);if (ice_is_peer_ena (pf)) {
@@ -4777,7 +4785,15 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)dev_err (dev,"PF VSI rebuild failed: %d\n" , err); goto err_vsi_rebuild; } +if (ice_is_peer_ena (pf)) { +struct ice_vsi *vsi =ice_get_main_vsi (pf); +if (!vsi) { +dev_err (dev,"No PF_VSI to update peer\n" ); + goto err_vsi_rebuild; + } +ice_for_each_peer (pf, vsi, ice_peer_update_vsi); + }if (test_bit (ICE_FLAG_SRIOV_ENA , pf->flags)) { err =ice_vsi_rebuild_by_type (pf,ICE_VSI_VF );if (err) {
drivers/net/ethernet/intel/ice/ice_switch.c +23 -0
@@ -430,6 +430,29 @@ ice_update_vsi(struct ice_hw *hw, u16 vsi_handle, struct ice_vsi_ctx *vsi_ctx,return ice_aq_update_vsi (hw, vsi_ctx, cd); } +/** +* ice_cfg_iwarp_fltr - enable/disable iWARP filtering on VSI +* @hw: pointer to HW struct +* @vsi_handle: VSI SW index +* @enable: boolean for enable/disable +*/ +enum ice_status +ice_cfg_iwarp_fltr (struct ice_hw *hw,u16 vsi_handle,bool enable) +{ +struct ice_vsi_ctx *ctx; + + ctx =ice_get_vsi_ctx (hw, vsi_handle); +if (!ctx) +return ICE_ERR_DOES_NOT_EXIST ; + +if (enable) + ctx->info.q_opt_flags |=ICE_AQ_VSI_Q_OPT_PE_FLTR_EN ; +else + ctx->info.q_opt_flags &= ~ICE_AQ_VSI_Q_OPT_PE_FLTR_EN ; + +return ice_update_vsi (hw, vsi_handle, ctx,NULL ); +} +/** * ice_aq_alloc_free_vsi_list * @hw: pointer to the HW struct
drivers/net/ethernet/intel/ice/ice_switch.h +2 -0
@@ -220,6 +220,8 @@ void ice_remove_vsi_fltr(struct ice_hw *hw, u16 vsi_handle);enum ice_status ice_add_vlan (struct ice_hw *hw,struct list_head *m_list);enum ice_status ice_remove_vlan (struct ice_hw *hw,struct list_head *v_list); +enum ice_status +ice_cfg_iwarp_fltr (struct ice_hw *hw,u16 vsi_handle,bool enable);/* Promisc/defport setup for VSIs */ enum ice_status
drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +0 -25
@@ -1375,31 +1375,6 @@ static int ice_alloc_vfs(struct ice_pf *pf, u16 num_alloc_vfs)return ret; } -/** -* ice_pf_state_is_nominal - checks the PF for nominal state -* @pf: pointer to PF to check -* -* Check the PF's state for a collection of bits that would indicate -* the PF is in a state that would inhibit normal operation for -* driver functionality. -* -* Returns true if PF is in a nominal state. -* Returns false otherwise -*/ -static bool ice_pf_state_is_nominal (struct ice_pf *pf) -{ - DECLARE_BITMAP(check_bits, __ICE_STATE_NBITS) = { 0 }; - -if (!pf) -return false; - -bitmap_set (check_bits,0 , __ICE_STATE_NOMINAL_CHECK_BITS); -if (bitmap_intersects (pf->state, check_bits, __ICE_STATE_NBITS)) -return false; - -return true; -} -/** * ice_pci_sriov_ena - Enable or change number of VFs * @pf: pointer to the PF structure
Signature · 1 line
2.20.1
Bowers
PATCH v4 2/6 ice: Complete RDMA peer registration
Quoted 15 lines
-----Original Message-----
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at osuosl.org] On Behalf Of Tony Nguyen
Sent: Monday, March 2, 2020 3:31 PM
To: intel-wired-lan at lists.osuosl.org
Subject: [Intel-wired-lan] [PATCH S34 v4 2/6] ice: Complete RDMA peer registrationFrom: Dave Ertman <[email protected]>
Ensure that the peer supports the minimal set of operations required for operation and, if so, open the connection to the peer.
Signed-off-by Dave Ertman <[email protected]>Signed-off-by Tony Nguyen <[email protected]>
Quoted 10 lines
--- drivers/net/ethernet/intel/ice/ice_idc.c | 288 ++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_idc_int.h | 36 +++ drivers/net/ethernet/intel/ice/ice_lib.c | 33 ++ drivers/net/ethernet/intel/ice/ice_lib.h | 2 + drivers/net/ethernet/intel/ice/ice_main.c | 18 +- drivers/net/ethernet/intel/ice/ice_switch.c | 23 ++ drivers/net/ethernet/intel/ice/ice_switch.h | 2 + .../net/ethernet/intel/ice/ice_virtchnl_pf.c | 25 -- 8 files changed, 401 insertions(+), 26 deletions(-)
Tony Nguyen
maintainerPATCH v4 3/6 ice: Support resource allocation requests
In reply to Tony NguyenFrom: Dave Ertman <[email protected]>
Enable the peer device to request queue sets from the PF.
--- drivers/net/ethernet/intel/ice/ice.h | 1 + .../net/ethernet/intel/ice/ice_adminq_cmd.h | 32 +++ drivers/net/ethernet/intel/ice/ice_common.c | 188 ++++++++++++++ drivers/net/ethernet/intel/ice/ice_common.h | 9 + drivers/net/ethernet/intel/ice/ice_idc.c | 244 ++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_sched.c | 69 ++++- drivers/net/ethernet/intel/ice/ice_switch.c | 4 + drivers/net/ethernet/intel/ice/ice_switch.h | 2 + drivers/net/ethernet/intel/ice/ice_type.h | 3 + 9 files changed, 547 insertions(+), 5 deletions(-)
drivers/net/ethernet/intel/ice/ice.h +1 -0
@@ -300,6 +300,7 @@ struct ice_vsi {u16 req_rxq;/* User requested Rx queues */ u16 num_rx_desc;u16 num_tx_desc; +u16 qset_handle[ICE_MAX_TRAFFIC_CLASS ];struct ice_tc_cfg tc_cfg;struct bpf_prog *xdp_prog;struct ice_ring **xdp_rings;/* XDP ring array */
drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +32 -0
@@ -1533,6 +1533,36 @@ struct ice_aqc_dis_txq {struct ice_aqc_dis_txq_item qgrps[1 ]; }; +/* Add Tx RDMA Queue Set (indirect 0x0C33) */ +struct ice_aqc_add_rdma_qset { +u8 num_qset_grps; +u8 reserved[7 ]; +__le32 addr_high; +__le32 addr_low; +}; + +/* This is the descriptor of each qset entry for the Add Tx RDMA Queue Set +* command (0x0C33). Only used within struct ice_aqc_add_rdma_qset. +*/ +struct ice_aqc_add_tx_rdma_qset_entry { +__le16 tx_qset_id; +u8 rsvd[2 ]; +__le32 qset_teid; +struct ice_aqc_txsched_elem info; +}; + +/* The format of the command buffer for Add Tx RDMA Queue Set(0x0C33) +* is an array of the following structs. Please note that the length of +* each struct ice_aqc_add_rdma_qset is variable due to the variable +* number of queues in each group! +*/ +struct ice_aqc_add_rdma_qset_data { +__le32 parent_teid; +__le16 num_qsets; +u8 rsvd[2 ]; +struct ice_aqc_add_tx_rdma_qset_entry rdma_qsets[1 ]; +}; +/* Configure Firmware Logging Command (indirect 0xFF09) * Logging Information Read Response (indirect 0xFF10) * Note: The 0xFF10 command has no input parameters.
@@ -1729,6 +1759,7 @@ struct ice_aq_desc {struct ice_aqc_get_set_rss_key get_set_rss_key;struct ice_aqc_add_txqs add_txqs;struct ice_aqc_dis_txqs dis_txqs; +struct ice_aqc_add_rdma_qset add_rdma_qset;struct ice_aqc_add_get_update_free_vsi vsi_cmd;struct ice_aqc_add_update_free_vsi_resp add_update_free_vsi_res;struct ice_aqc_fw_logging fw_logging;
@@ -1863,6 +1894,7 @@ enum ice_adminq_opc {/* Tx queue handling commands/events */ ice_aqc_opc_add_txqs =0x0C30 , ice_aqc_opc_dis_txqs =0x0C31 , + ice_aqc_opc_add_rdma_qset =0x0C33 ,/* package commands */ ice_aqc_opc_download_pkg = 0x0C40,
drivers/net/ethernet/intel/ice/ice_common.c +188 -0
200 lines not on this page · raw message
drivers/net/ethernet/intel/ice/ice_common.h +9 -0
@@ -131,6 +131,15 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr, bool write, struct ice_sq_cd *cd);enum ice_status +ice_cfg_vsi_rdma (struct ice_port_info *pi,u16 vsi_handle,u8 tc_bitmap, +u16 *max_rdmaqs); +enum ice_status +ice_ena_vsi_rdma_qset (struct ice_port_info *pi,u16 vsi_handle,u8 tc, +u16 *rdma_qset,u16 num_qsets,u32 *qset_teid); +enum ice_status +ice_dis_vsi_rdma_qset (struct ice_port_info *pi,u16 count,u32 *qset_teid, +u16 *q_id); +enum ice_status ice_dis_vsi_txq(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u8 num_queues, u16 *q_handle, u16 *q_ids, u32 *q_teids, enum ice_disq_rst_src rst_src, u16 vmvf_num,
drivers/net/ethernet/intel/ice/ice_idc.c +244 -0
256 lines not on this page · raw message
drivers/net/ethernet/intel/ice/ice_sched.c +64 -5
102 lines not on this page · raw message
drivers/net/ethernet/intel/ice/ice_switch.c +4 -0
@@ -310,6 +310,10 @@ static void ice_clear_vsi_q_ctx(struct ice_hw *hw, u16 vsi_handle)devm_kfree (ice_hw_to_dev (hw), vsi->lan_q_ctx[i]); vsi->lan_q_ctx[i] =NULL ; } +if (vsi->rdma_q_ctx[i]) { +devm_kfree (ice_hw_to_dev (hw), vsi->rdma_q_ctx[i]); + vsi->rdma_q_ctx[i] =NULL ; + } } }
drivers/net/ethernet/intel/ice/ice_switch.h +2 -0
@@ -26,6 +26,8 @@ struct ice_vsi_ctx {u8 vf_num;u16 num_lan_q_entries[ICE_MAX_TRAFFIC_CLASS ];struct ice_q_ctx *lan_q_ctx[ICE_MAX_TRAFFIC_CLASS ]; +u16 num_rdma_q_entries[ICE_MAX_TRAFFIC_CLASS ]; +struct ice_q_ctx *rdma_q_ctx[ICE_MAX_TRAFFIC_CLASS ]; };enum ice_sw_fwd_act_type {
drivers/net/ethernet/intel/ice/ice_type.h +3 -0
@@ -45,6 +45,7 @@ static inline u32 ice_round_to_num(u32 N, u32 R)#define ICE_DBG_FLOW BIT_ULL(9)#define ICE_DBG_SW BIT_ULL(13)#define ICE_DBG_SCHED BIT_ULL(14) +#define ICE_DBG_RDMA BIT_ULL(15)#define ICE_DBG_PKG BIT_ULL(16)#define ICE_DBG_RES BIT_ULL(17)#define ICE_DBG_AQ_MSG BIT_ULL(24)
@@ -273,6 +274,7 @@ struct ice_sched_node {u8 tc_num;u8 owner;#define ICE_SCHED_NODE_OWNER_LAN 0 +#define ICE_SCHED_NODE_OWNER_RDMA 2 };/* Access Macros for Tx Sched Elements data */
@@ -344,6 +346,7 @@ struct ice_sched_vsi_info {struct ice_sched_node *ag_node[ICE_MAX_TRAFFIC_CLASS ];struct list_head list_entry;u16 max_lanq[ICE_MAX_TRAFFIC_CLASS ]; +u16 max_rdmaq[ICE_MAX_TRAFFIC_CLASS ]; };/* driver defines the policy */
Signature · 1 line
2.20.1
Bowers
PATCH v4 3/6 ice: Support resource allocation requests
Quoted 14 lines
-----Original Message-----
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at osuosl.org] On Behalf Of Tony Nguyen
Sent: Monday, March 2, 2020 3:31 PM
To: intel-wired-lan at lists.osuosl.org
Subject: [Intel-wired-lan] [PATCH S34 v4 3/6] ice: Support resource allocation requestsFrom: Dave Ertman <[email protected]>
Enable the peer device to request queue sets from the PF.
Signed-off-by Dave Ertman <[email protected]>Signed-off-by Tony Nguyen <[email protected]>
Quoted 11 lines
--- drivers/net/ethernet/intel/ice/ice.h | 1 + .../net/ethernet/intel/ice/ice_adminq_cmd.h | 32 +++ drivers/net/ethernet/intel/ice/ice_common.c | 188 ++++++++++++++ drivers/net/ethernet/intel/ice/ice_common.h | 9 + drivers/net/ethernet/intel/ice/ice_idc.c | 244 ++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_sched.c | 69 ++++- drivers/net/ethernet/intel/ice/ice_switch.c | 4 + drivers/net/ethernet/intel/ice/ice_switch.h | 2 + drivers/net/ethernet/intel/ice/ice_type.h | 3 + 9 files changed, 547 insertions(+), 5 deletions(-)
Tony Nguyen
maintainerPATCH v4 4/6 ice: Enable event notifications
In reply to Tony NguyenFrom: Dave Ertman <[email protected]>
Enable registration of notifications. Peer devices can register to be notified of certain events as well as notify the driver of its state changes.
--- drivers/net/ethernet/intel/ice/ice_dcb_lib.c | 37 ++++ drivers/net/ethernet/intel/ice/ice_idc.c | 221 +++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_idc_int.h | 1 + drivers/net/ethernet/intel/ice/ice_main.c | 27 ++- 4 files changed, 280 insertions(+), 6 deletions(-)
drivers/net/ethernet/intel/ice/ice_dcb_lib.c +37 -0
@@ -168,6 +168,30 @@ void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi) } } +/** +* ice_peer_prep_tc_change - Pre-notify RDMA Peer in blocking call of TC change +* @peer_dev_int: ptr to peer device internal struct +* @data: ptr to opaque data +*/ +static int +ice_peer_prep_tc_change (struct ice_peer_dev_int *peer_dev_int, +void __always_unused *data) +{ +struct iidc_peer_dev *peer_dev; + + peer_dev = &peer_dev_int->peer_dev; +if (!ice_validate_peer_dev (peer_dev)) +return 0 ; + +if (!test_bit (ICE_PEER_DEV_STATE_OPENED , peer_dev_int->state)) +return 0 ; + +if (peer_dev->peer_ops && peer_dev->peer_ops->prep_tc_change) + peer_dev->peer_ops->prep_tc_change (peer_dev); + +return 0 ; +} +/** * ice_dcb_bwchk - check if ETS bandwidth input parameters are correct * @pf: pointer to the PF struct
@@ -248,6 +272,9 @@ int ice_pf_dcb_cfg(struct ice_pf *pf, struct ice_dcbx_cfg *new_cfg, bool locked)return -ENOMEM ;dev_info (dev,"Commit DCB Configuration to the hardware\n" ); +/* Notify capable peers about impending change to TCs */ +ice_for_each_peer (pf,NULL , ice_peer_prep_tc_change); + pf_vsi =ice_get_main_vsi (pf);if (!pf_vsi) {dev_dbg (dev,"PF VSI doesn't exist\n" );
@@ -580,6 +607,7 @@ static int ice_dcb_noncontig_cfg(struct ice_pf *pf)void ice_pf_dcb_recfg (struct ice_pf *pf) {struct ice_dcbx_cfg *dcbcfg = &pf->hw.port_info->local_dcbx_cfg; +struct iidc_event *event;u8 tc_map =0 ;int v, ret;
@@ -615,6 +643,15 @@ void ice_pf_dcb_recfg(struct ice_pf *pf)if (vsi->type ==ICE_VSI_PF )ice_dcbnl_set_all (vsi); } + event =kzalloc (sizeof (*event),GFP_KERNEL ); +if (!event) +return ; + +set_bit (IIDC_EVENT_TC_CHANGE , event->type); + event->reporter =NULL ; +ice_setup_dcb_qos_info (pf, &event->info.port_qos); +ice_for_each_peer (pf, event, ice_peer_check_for_reg); +kfree (event); }/**
drivers/net/ethernet/intel/ice/ice_idc.c +221 -0
245 lines not on this page · raw message
drivers/net/ethernet/intel/ice/ice_idc_int.h +1 -0
@@ -66,6 +66,7 @@ int ice_peer_update_vsi(struct ice_peer_dev_int *peer_dev_int, void *data);int ice_unroll_peer (struct ice_peer_dev_int *peer_dev_int,void *data);int ice_unreg_peer_device (struct ice_peer_dev_int *peer_dev_int,void *data);int ice_peer_close (struct ice_peer_dev_int *peer_dev_int,void *data); +int ice_peer_check_for_reg (struct ice_peer_dev_int *peer_dev_int,void *data);int ice_finish_init_peer_device (struct ice_peer_dev_int *peer_dev_int,void *data);
drivers/net/ethernet/intel/ice/ice_main.c +21 -6
@@ -4854,7 +4854,9 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu)struct ice_netdev_priv *np =netdev_priv (netdev);struct ice_vsi *vsi = np->vsi;struct ice_pf *pf = vsi->back; +struct iidc_event *event;u8 count =0 ; +int err =0 ;if (new_mtu == netdev->mtu) {netdev_warn (netdev,"MTU is already %u\n" , netdev->mtu);
@@ -4896,27 +4898,40 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu)return -EBUSY ; } + event =kzalloc (sizeof (*event),GFP_KERNEL ); +if (!event) +return -ENOMEM ; + netdev->mtu = new_mtu;/* if VSI is up, bring it down and then back up */ if (!test_and_set_bit (__ICE_DOWN, vsi->state)) { -int err; - err =ice_down (vsi);if (err) { -netdev_err (netdev,"change MTU if_up err %d\n" , err); -return err; +netdev_err (netdev,"change MTU if_down err %d\n" , err); + goto free_event; } err =ice_up (vsi);if (err) {netdev_err (netdev,"change MTU if_up err %d\n" , err); -return err; + goto free_event; } } +if (ice_is_safe_mode (pf)) + goto out; + +set_bit (IIDC_EVENT_MTU_CHANGE , event->type); + event->reporter =NULL ; + event->info.mtu = new_mtu; +ice_for_each_peer (pf, event, ice_peer_check_for_reg); + +out:netdev_dbg (netdev,"changed MTU to %d\n" , new_mtu); -return 0 ; +free_event: +kfree (event); +return err; }/**
Signature · 1 line
2.20.1
Bowers
PATCH v4 4/6 ice: Enable event notifications
Quoted 12 lines
-----Original Message-----
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at osuosl.org] On Behalf Of Tony Nguyen
Sent: Monday, March 2, 2020 3:31 PM
To: intel-wired-lan at lists.osuosl.org
Subject: [Intel-wired-lan] [PATCH S34 v4 4/6] ice: Enable event notificationsFrom: Dave Ertman <[email protected]>
Enable registration of notifications. Peer devices can register to be notified of certain events as well as notify the driver of its state changes.
Quoted 8 lines
Signed-off-by Dave Ertman <[email protected]>Signed-off-by Tony Nguyen <[email protected]>--- drivers/net/ethernet/intel/ice/ice_dcb_lib.c | 37 ++++ drivers/net/ethernet/intel/ice/ice_idc.c | 221 +++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_idc_int.h | 1 + drivers/net/ethernet/intel/ice/ice_main.c | 27 ++- 4 files changed, 280 insertions(+), 6 deletions(-)
Tony Nguyen
maintainerPATCH v4 5/6 ice: Allow reset operations
In reply to Tony NguyenFrom: Dave Ertman <[email protected]>
Enable the PF to notify peers when it's going to reset so that peer devices can prepare accordingly. Also enable the peer devices to request the PF to reset.
Implement ice_peer_is_vsi_ready() so the peer device can determine when the VSI is ready for operations following a reset.
--- drivers/net/ethernet/intel/ice/ice_idc.c | 140 +++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_idc_int.h | 1 + drivers/net/ethernet/intel/ice/ice_lib.c | 6 + drivers/net/ethernet/intel/ice/ice_main.c | 3 + 4 files changed, 150 insertions(+)
drivers/net/ethernet/intel/ice/ice_idc.c +140 -0
@@ -217,6 +217,40 @@ int ice_peer_update_vsi(struct ice_peer_dev_int *peer_dev_int, void *data)return 0 ; } +/** +* ice_close_peer_for_reset - queue work to close peer for reset +* @peer_dev_int: pointer peer dev internal struct +* @data: pointer to opaque data used for reset type +*/ +int ice_close_peer_for_reset (struct ice_peer_dev_int *peer_dev_int,void *data) +{ +struct iidc_peer_dev *peer_dev; +enum ice_reset_req reset; + + peer_dev = &peer_dev_int->peer_dev; +if (!ice_validate_peer_dev (peer_dev)) +return 0 ; + + reset = *(enum ice_reset_req *)data; + +switch (reset) { +case ICE_RESET_GLOBR : + peer_dev_int->rst_type =IIDC_REASON_GLOBR_REQ ; +break ; +case ICE_RESET_CORER : + peer_dev_int->rst_type =IIDC_REASON_CORER_REQ ; +break ; +case ICE_RESET_PFR : + peer_dev_int->rst_type =IIDC_REASON_PFR_REQ ; +break ; +default : +/* reset type is invalid */ +return 1 ; + } +queue_work (peer_dev_int->ice_peer_wq, &peer_dev_int->peer_close_task); +return 0 ; +} +/** * ice_check_peer_drv_for_events - check peer_drv for events to report * @peer_dev: peer device to report to
@@ -929,6 +963,74 @@ static int ice_peer_register(struct iidc_peer_dev *peer_dev)return 0 ; } +/** +* ice_peer_request_reset - accept request from peer to perform a reset +* @peer_dev: peer device that is request a reset +* @reset_type: type of reset the peer is requesting +*/ +static int +ice_peer_request_reset (struct iidc_peer_dev *peer_dev, +enum iidc_peer_reset_type reset_type) +{ +enum ice_reset_req reset; +struct ice_pf *pf; + +if (!ice_validate_peer_dev (peer_dev)) +return -EINVAL ; + + pf =pci_get_drvdata (peer_dev->pdev); + +switch (reset_type) { +case IIDC_PEER_PFR : + reset =ICE_RESET_PFR ; +break ; +case IIDC_PEER_CORER : + reset =ICE_RESET_CORER ; +break ; +case IIDC_PEER_GLOBR : + reset =ICE_RESET_GLOBR ; +break ; +default : +dev_err (ice_pf_to_dev (pf),"incorrect reset request from peer\n" ); +return -EINVAL ; + } + +return ice_schedule_reset (pf, reset); +} + +/** +* ice_peer_is_vsi_ready - query if VSI in nominal state +* @peer_dev: pointer to iidc_peer_dev struct +*/ +static int ice_peer_is_vsi_ready (struct iidc_peer_dev *peer_dev) +{ + DECLARE_BITMAP(check_bits, __ICE_STATE_NBITS) = { 0 }; +struct ice_netdev_priv *np; +struct ice_vsi *vsi; + +/* If the peer_dev or associated values are not valid, then return +* 0 as there is no ready port associated with the values passed in +* as parameters. +*/ + +if (!ice_validate_peer_dev (peer_dev)) +return 0 ; + +if (!peer_dev->netdev) +return 0 ; + + np =netdev_priv (peer_dev->netdev); + vsi = np->vsi; +if (!vsi) +return 0 ; + +bitmap_set (check_bits,0 , __ICE_STATE_NOMINAL_CHECK_BITS); +if (bitmap_intersects (vsi->state, check_bits, __ICE_STATE_NBITS)) +return 0 ; + +return 1 ; +} +/** * ice_peer_update_vsi_filter - update main VSI filters for RDMA * @peer_dev: pointer to RDMA peer device
@@ -972,9 +1074,11 @@ ice_peer_update_vsi_filter(struct iidc_peer_dev *peer_dev,static const struct iidc_ops ops = { .alloc_res = ice_peer_alloc_res, .free_res = ice_peer_free_res, + .is_vsi_ready = ice_peer_is_vsi_ready, .reg_for_notification = ice_peer_reg_for_notif, .unreg_for_notification = ice_peer_unreg_for_notif, .notify_state_change = ice_peer_report_state_change, + .request_reset = ice_peer_request_reset, .peer_register = ice_peer_register, .peer_unregister = ice_peer_unregister, .update_vsi_filter = ice_peer_update_vsi_filter,
@@ -999,6 +1103,41 @@ static int ice_reserve_peer_qvector(struct ice_pf *pf)return 0 ; } +/** +* ice_peer_close_task - call peer's close asynchronously +* @work: pointer to work_struct contained by the peer_dev_int struct +* +* This method (asynchronous) of calling a peer's close function is +* meant to be used in the reset path. +*/ +static void ice_peer_close_task (struct work_struct *work) +{ +struct ice_peer_dev_int *peer_dev_int; +struct iidc_peer_dev *peer_dev; + + peer_dev_int = container_of(work, struct ice_peer_dev_int, + peer_close_task); + + peer_dev = &peer_dev_int->peer_dev; +if (!peer_dev || !peer_dev->peer_ops) +return ; + +/* If this peer_dev is going to close, we do not want any state changes +* to happen until after we successfully finish or abort the close. +* Grab the peer_dev_state_mutex to protect this flow +*/ +mutex_lock (&peer_dev_int->peer_dev_state_mutex); + +ice_peer_state_change (peer_dev_int,ICE_PEER_DEV_STATE_CLOSING , true); + +if (peer_dev->peer_ops->close) + peer_dev->peer_ops->close (peer_dev, peer_dev_int->rst_type); + +ice_peer_state_change (peer_dev_int,ICE_PEER_DEV_STATE_CLOSED , true); + +mutex_unlock (&peer_dev_int->peer_dev_state_mutex); +} +/** * ice_peer_vdev_release - function to map to virtbus_devices release callback * @vdev: pointer to virtbus_device to free
@@ -1097,6 +1236,7 @@ int ice_init_peer_devices(struct ice_pf *pf)kfree (vbo);return -ENOMEM ; } +INIT_WORK (&peer_dev_int->peer_close_task, ice_peer_close_task); peer_dev->pdev = pdev; qos_info = &peer_dev->initial_qos_info;
drivers/net/ethernet/intel/ice/ice_idc_int.h +1 -0
@@ -63,6 +63,7 @@ struct ice_peer_dev_int { };int ice_peer_update_vsi (struct ice_peer_dev_int *peer_dev_int,void *data); +int ice_close_peer_for_reset (struct ice_peer_dev_int *peer_dev_int,void *data);int ice_unroll_peer (struct ice_peer_dev_int *peer_dev_int,void *data);int ice_unreg_peer_device (struct ice_peer_dev_int *peer_dev_int,void *data);int ice_peer_close (struct ice_peer_dev_int *peer_dev_int,void *data);
drivers/net/ethernet/intel/ice/ice_lib.c +6 -0
@@ -2416,6 +2416,12 @@ void ice_vsi_close(struct ice_vsi *vsi) {enum iidc_close_reason reason =IIDC_REASON_INTERFACE_DOWN ; +if (test_bit (__ICE_CORER_REQ, vsi->back->state)) + reason =IIDC_REASON_CORER_REQ ; +if (test_bit (__ICE_GLOBR_REQ, vsi->back->state)) + reason =IIDC_REASON_GLOBR_REQ ; +if (test_bit (__ICE_PFR_REQ, vsi->back->state)) + reason =IIDC_REASON_PFR_REQ ;if (!ice_is_safe_mode (vsi->back) && vsi->type ==ICE_VSI_PF ) {int ret =ice_for_each_peer (vsi->back, &reason, ice_peer_close);
drivers/net/ethernet/intel/ice/ice_main.c +3 -0
@@ -558,6 +558,9 @@ static void ice_reset_subtask(struct ice_pf *pf)/* return if no valid reset type requested */ if (reset_type ==ICE_RESET_INVAL )return ; +if (ice_is_peer_ena (pf)) +ice_for_each_peer (pf, &reset_type, + ice_close_peer_for_reset);ice_prepare_for_reset (pf);/* make sure we are ready to rebuild */
Signature · 1 line
2.20.1
Bowers
PATCH v4 5/6 ice: Allow reset operations
Quoted 16 lines
-----Original Message-----
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at osuosl.org] On Behalf Of Tony Nguyen
Sent: Monday, March 2, 2020 3:31 PM
To: intel-wired-lan at lists.osuosl.org
Subject: [Intel-wired-lan] [PATCH S34 v4 5/6] ice: Allow reset operationsFrom: Dave Ertman <[email protected]>
Enable the PF to notify peers when it's going to reset so that peer devices can prepare accordingly. Also enable the peer devices to request the PF to reset.
Implement
ice_peer_is_vsi_ready()so the peer device can determine when the VSI is ready for operations following a reset.
Quoted 8 lines
Signed-off-by Dave Ertman <[email protected]>Signed-off-by Tony Nguyen <[email protected]>--- drivers/net/ethernet/intel/ice/ice_idc.c | 140 +++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_idc_int.h | 1 + drivers/net/ethernet/intel/ice/ice_lib.c | 6 + drivers/net/ethernet/intel/ice/ice_main.c | 3 + 4 files changed, 150 insertions(+)
Tony Nguyen
maintainerPATCH v4 6/6 ice: Pass through communications to VF
In reply to Tony NguyenFrom: Dave Ertman <[email protected]>
Allow for forwarding of RDMA and VF virt channel messages. The driver will forward messages from the RDMA driver to the VF via the vc_send operation and invoke the peer's vc_receive() call when receiving a virt channel message destined for the peer driver.
--- drivers/net/ethernet/intel/ice/ice.h | 1 + drivers/net/ethernet/intel/ice/ice_idc.c | 34 +++++++++++++++++++ .../net/ethernet/intel/ice/ice_virtchnl_pf.c | 34 +++++++++++++++++++ 3 files changed, 69 insertions(+)
drivers/net/ethernet/intel/ice/ice.h +1 -0
@@ -391,6 +391,7 @@ struct ice_pf {u32 msg_enable;u32 num_rdma_msix;/* Total MSIX vectors for RDMA driver */ u32 rdma_base_vector; +struct iidc_peer_dev *rdma_peer;u32 hw_csum_rx_error;u32 oicr_idx;/* Other interrupt cause MSIX vector index */ u32 num_avail_sw_msix;/* remaining MSIX SW vectors left unclaimed */
drivers/net/ethernet/intel/ice/ice_idc.c +34 -0
@@ -1070,6 +1070,38 @@ ice_peer_update_vsi_filter(struct iidc_peer_dev *peer_dev,return ret; } +/** +* ice_peer_vc_send - send a virt channel message from RDMA peer +* @peer_dev: pointer to RDMA peer dev +* @vf_id: the absolute VF ID of recipient of message +* @msg: pointer to message contents +* @len: len of message +*/ +static int +ice_peer_vc_send (struct iidc_peer_dev *peer_dev,u32 vf_id,u8 *msg,u16 len) +{ +struct ice_pf *pf; +int err; + +if (!ice_validate_peer_dev (peer_dev)) +return -EINVAL ; +if (!msg || !len) +return -ENOMEM ; + + pf =pci_get_drvdata (peer_dev->pdev); +if (vf_id >= pf->num_alloc_vfs || len >ICE_AQ_MAX_BUF_LEN ) +return -EINVAL ; + +/* VIRTCHNL_OP_IWARP is being used for RoCEv2 msg also */ + err =ice_aq_send_msg_to_vf (&pf->hw, vf_id,VIRTCHNL_OP_IWARP ,0 , msg, + len,NULL ); +if (err) +dev_err (ice_pf_to_dev (pf),"Unable to send RDMA msg to VF, error %d\n" , + err); + +return err; +} +/* Initialize the ice_ops struct, which is used in 'ice_init_peer_devices' */ static const struct iidc_ops ops = { .alloc_res = ice_peer_alloc_res,
@@ -1082,6 +1114,7 @@ static const struct iidc_ops ops = { .peer_register = ice_peer_register, .peer_unregister = ice_peer_unregister, .update_vsi_filter = ice_peer_update_vsi_filter, + .vc_send = ice_peer_vc_send, };/**
@@ -1263,6 +1296,7 @@ int ice_init_peer_devices(struct ice_pf *pf)switch (ice_peers[i].id) {case IIDC_PEER_RDMA_ID :if (test_bit (ICE_FLAG_IWARP_ENA , pf->flags)) { + pf->rdma_peer = peer_dev; peer_dev->msix_count = pf->num_rdma_msix; entry = &pf->msix_entries[pf->rdma_base_vector]; }
drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +34 -0
@@ -3169,6 +3169,37 @@ static int ice_vc_dis_vlan_stripping(struct ice_vf *vf) v_ret, NULL, 0); } +/** +* ice_vc_rdma_msg - send msg to RDMA PF from VF +* @vf: pointer to VF info +* @msg: pointer to msg buffer +* @len: length of the message +* +* This function is called indirectly from the AQ clean function. +*/ +static int ice_vc_rdma_msg (struct ice_vf *vf,u8 *msg,u16 len) +{ +struct iidc_peer_dev *rdma_peer; +int ret; + + rdma_peer = vf->pf->rdma_peer; +if (!rdma_peer) { +pr_err ("Invalid RDMA peer attempted to send message to peer\n" ); +return -EIO ; + } + +if (!rdma_peer->peer_ops || !rdma_peer->peer_ops->vc_receive) { +pr_err ("Incomplete RMDA peer attempting to send msg\n" ); +return -EINVAL ; + } + + ret = rdma_peer->peer_ops->vc_receive (rdma_peer, vf->vf_id, msg, len); +if (ret) +pr_err ("Failed to send message to RDMA peer, error %d\n" , ret); + +return ret; +} +/** * ice_vf_init_vlan_stripping - enable/disable VLAN stripping on initialization * @vf: VF to enable/disable VLAN stripping for on initialization
@@ -3303,6 +3334,9 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event)case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING : err =ice_vc_dis_vlan_stripping (vf);break ; +case VIRTCHNL_OP_IWARP : + err =ice_vc_rdma_msg (vf, msg, msglen); +break ;case VIRTCHNL_OP_UNKNOWN :default : dev_err(dev, "Unsupported opcode %d from VF %d\n", v_opcode,
Signature · 1 line
2.20.1
Bowers
PATCH v4 6/6 ice: Pass through communications to VF
Quoted 15 lines
-----Original Message-----
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at osuosl.org] On Behalf Of Tony Nguyen
Sent: Monday, March 2, 2020 3:31 PM
To: intel-wired-lan at lists.osuosl.org
Subject: [Intel-wired-lan] [PATCH S34 v4 6/6] ice: Pass through communications to VFFrom: Dave Ertman <[email protected]>
Allow for forwarding of RDMA and VF virt channel messages. The driver will forward messages from the RDMA driver to the VF via the
vc_sendoperation and invoke the peer'svc_receive()call when receiving a virt channel message destined for the peer driver.
Quoted 7 lines
Signed-off-by Dave Ertman <[email protected]>Signed-off-by Tony Nguyen <[email protected]>--- drivers/net/ethernet/intel/ice/ice.h | 1 + drivers/net/ethernet/intel/ice/ice_idc.c | 34 +++++++++++++++++++ .../net/ethernet/intel/ice/ice_virtchnl_pf.c | 34 +++++++++++++++++++ 3 files changed, 69 insertions(+)
Bowers
PATCH v4 1/6 ice: Create and register virtual bus for RDMA
In reply to Tony NguyenQuoted 34 lines
-----Original Message-----
From: Intel-wired-lan [mailto:intel-wired-lan-bounces at osuosl.org] On Behalf Of Tony Nguyen
Sent: Monday, March 2, 2020 3:31 PM
To: intel-wired-lan at lists.osuosl.org
Subject: [Intel-wired-lan] [PATCH S34 v4 1/6] ice: Create and register virtual bus for RDMAFrom: Dave Ertman <[email protected]>
The RDMA block does not have its own PCI function, instead it must utilize the ice driver to gain access to the PCI device. Create a virtual bus device so the irdma driver can register a virtual bus driver to bind to it and receive device data. The device data contains all of the relevant information that the irdma peer will need to access this PF's IIDC API callbacks.
Note the header file
iidc.his located underinclude/linux/net/intelas this is a unified header file to be used by all consumers of the IIDC interface.Signed-off-by Dave Ertman <[email protected]>Signed-off-by Tony Nguyen <[email protected]>--- MAINTAINERS | 1 + drivers/net/ethernet/intel/Kconfig | 1 + drivers/net/ethernet/intel/ice/Makefile | 1 + drivers/net/ethernet/intel/ice/ice.h | 13 + .../net/ethernet/intel/ice/ice_adminq_cmd.h | 1 + drivers/net/ethernet/intel/ice/ice_common.c | 18 +- drivers/net/ethernet/intel/ice/ice_dcb_lib.c | 31 ++ drivers/net/ethernet/intel/ice/ice_dcb_lib.h | 3 + .../net/ethernet/intel/ice/ice_hw_autogen.h | 1 + drivers/net/ethernet/intel/ice/ice_idc.c | 400 ++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_idc_int.h | 67 +++ drivers/net/ethernet/intel/ice/ice_lib.c | 11 +
Quoted 8 lines
drivers/net/ethernet/intel/ice/ice_lib.h | 2 + drivers/net/ethernet/intel/ice/ice_main.c | 56 ++- drivers/net/ethernet/intel/ice/ice_type.h | 1 + include/linux/net/intel/iidc.h | 337 +++++++++++++++ 16 files changed, 941 insertions(+), 3 deletions(-) create mode 100644 drivers/net/ethernet/intel/ice/ice_idc.c create mode 100644 drivers/net/ethernet/intel/ice/ice_idc_int.h create mode 100644 include/linux/net/intel/iidc.h