ice: support devlink subfunction
Subsystems (3)
v2 cover ice: support devlink subfunction
Hi,
This is second patchset split from subfunction patchset [1]. Important changes from previous version:
* remove unnecessary checks for devlink port type
* link correct devlink port to subfunction netdev
Follow up patchset with subfunction port representor will be the last patchset for subfunction implementation in ice. It is a little unpleasant to split it like that, because devlink port should be linked with port representor netdev. In this patchset use devlink port without linking it. It will be done correctly in the follow up when subfunction port representor is available.
Currently ice driver does not allow creating more than one networking device per physical function. The only way to have more hardware backed netdev is to use SR-IOV.
Following patchset adds support for devlink port API. For each new pcisf type port, driver allocates new VSI, configures all resources needed, including dynamically MSIX vectors, program rules and registers new netdev.
This series supports only one Tx/Rx queue pair per subfunction.
Example commands:
devlink port add pci/0000:31:00.1 flavour pcisf pfnum 1 sfnum 1000 devlink port function set pci/0000:31:00.1/1 hw_addr 00:00:00:00:03:14 devlink port function set pci/0000:31:00.1/1 state active devlink port function del pci/0000:31:00.1/1
v1 --> v2: [2]
* use correct parameters in ice_devlink_alloc() thanks to Mateusz
[1] https://lore.kernel.org/netdev/[email protected]/
[2] https://lore.kernel.org/netdev/[email protected]/
Piotr Raczynski (7):
ice: add new VSI type for subfunctions
ice: export ice ndo_ops functions
ice: add basic devlink subfunctions support
ice: allocate devlink for subfunction
ice: base subfunction aux driver
ice: implement netdev for subfunction
ice: allow to activate and deactivate subfunction
drivers/net/ethernet/intel/ice/Makefile | 1 + .../net/ethernet/intel/ice/devlink/devlink.c | 44 +- .../net/ethernet/intel/ice/devlink/devlink.h | 1 + .../ethernet/intel/ice/devlink/devlink_port.c | 512 ++++++++++++++++++ .../ethernet/intel/ice/devlink/devlink_port.h | 37 ++ drivers/net/ethernet/intel/ice/ice.h | 12 + drivers/net/ethernet/intel/ice/ice_base.c | 5 +- drivers/net/ethernet/intel/ice/ice_dcb_lib.c | 1 + drivers/net/ethernet/intel/ice/ice_lib.c | 52 +- drivers/net/ethernet/intel/ice/ice_lib.h | 3 + drivers/net/ethernet/intel/ice/ice_main.c | 66 ++- drivers/net/ethernet/intel/ice/ice_sf_eth.c | 317 +++++++++++ drivers/net/ethernet/intel/ice/ice_sf_eth.h | 33 ++ drivers/net/ethernet/intel/ice/ice_type.h | 1 + drivers/net/ethernet/intel/ice/ice_xsk.c | 2 +- 15 files changed, 1040 insertions(+), 47 deletions(-) create mode 100644 drivers/net/ethernet/intel/ice/ice_sf_eth.c create mode 100644 drivers/net/ethernet/intel/ice/ice_sf_eth.h
Signature · 1 line
2.42.0
PATCH v2 1/7 ice: add new VSI type for subfunctions
From: Piotr Raczynski <[email protected]>
Add required plumbing for new VSI type dedicated to devlink subfunctions. Make sure that the vsi is properly configured and destroyed. Also allow loading XDP and AF_XDP sockets.
The first implementation of devlink subfunctions supports only one Tx/Rx queue pair per given subfunction.
--- drivers/net/ethernet/intel/ice/ice_base.c | 5 +++- drivers/net/ethernet/intel/ice/ice_dcb_lib.c | 1 + drivers/net/ethernet/intel/ice/ice_lib.c | 25 ++++++++++++++++++-- drivers/net/ethernet/intel/ice/ice_main.c | 7 ++++-- drivers/net/ethernet/intel/ice/ice_type.h | 1 + drivers/net/ethernet/intel/ice/ice_xsk.c | 2 +- 6 files changed, 35 insertions(+), 6 deletions(-)
drivers/net/ethernet/intel/ice/ice_base.c +4 -1
@@ -330,6 +330,9 @@ ice_setup_tx_ctx(struct ice_tx_ring *ring, struct ice_tlan_ctx *tlan_ctx, u16 pf tlan_ctx->vmvf_num = hw->func_caps.vf_base_id + vsi->vf->vf_id; tlan_ctx->vmvf_type =ICE_TLAN_CTX_VMVF_TYPE_VF ;break ; +case ICE_VSI_SF : + tlan_ctx->vmvf_type =ICE_TLAN_CTX_VMVF_TYPE_VMQ ; +break ;default :return ; }
@@ -526,7 +529,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring) ring->rx_buf_len = ring->vsi->rx_buf_len; -if (ring->vsi->type ==ICE_VSI_PF ) { +if (ring->vsi->type ==ICE_VSI_PF || ring->vsi->type ==ICE_VSI_SF ) {if (!xdp_rxq_info_is_reg (&ring->xdp_rxq)) { err = __xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev, ring->q_index,
drivers/net/ethernet/intel/ice/ice_dcb_lib.c +1 -0
@@ -187,6 +187,7 @@ void ice_vsi_set_dcb_tc_cfg(struct ice_vsi *vsi) vsi->tc_cfg.numtc =ice_dcb_get_num_tc (cfg);break ;case ICE_VSI_CHNL : +case ICE_VSI_SF : vsi->tc_cfg.ena_tc =BIT (ice_get_first_droptc (vsi)); vsi->tc_cfg.numtc =1 ;break ;
drivers/net/ethernet/intel/ice/ice_lib.c +23 -2
@@ -20,6 +20,8 @@ const char *ice_vsi_type_str(enum ice_vsi_type vsi_type)return "ICE_VSI_PF" ;case ICE_VSI_VF :return "ICE_VSI_VF" ; +case ICE_VSI_SF : +return "ICE_VSI_SF" ;case ICE_VSI_CTRL :return "ICE_VSI_CTRL" ;case ICE_VSI_CHNL :
@@ -141,6 +143,7 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi) {switch (vsi->type) {case ICE_VSI_PF : +case ICE_VSI_SF :case ICE_VSI_CTRL :case ICE_VSI_LB :/* a user could change the values of num_[tr]x_desc using
@@ -207,6 +210,12 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi)max_t (int, vsi->alloc_rxq, vsi->alloc_txq));break ; +case ICE_VSI_SF : + vsi->alloc_txq =1 ; + vsi->alloc_rxq =1 ; + vsi->num_q_vectors =1 ; + vsi->irq_dyn_alloc = true; +break ;case ICE_VSI_VF :if (vf->num_req_qs) vf->num_vf_qs = vf->num_req_qs;
@@ -566,6 +575,7 @@ ice_vsi_alloc_def(struct ice_vsi *vsi, struct ice_channel *ch)switch (vsi->type) {case ICE_VSI_PF : +case ICE_VSI_SF :/* Setup default MSIX irq handler for VSI */ vsi->irq_handler = ice_msix_clean_rings;break ;
@@ -894,6 +904,11 @@ static void ice_vsi_set_rss_params(struct ice_vsi *vsi) max_rss_size); vsi->rss_lut_type =ICE_LUT_PF ;break ; +case ICE_VSI_SF : + vsi->rss_table_size =ICE_LUT_VSI_SIZE ; + vsi->rss_size =min_t (u16,num_online_cpus (), max_rss_size); + vsi->rss_lut_type =ICE_LUT_VSI ; +break ;case ICE_VSI_VF :/* VF VSI will get a small RSS table. * For VSI_LUT, LUT size should be set to 64 bytes.
@@ -1141,6 +1156,7 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi) lut_type =ICE_AQ_VSI_Q_OPT_RSS_LUT_PF ;break ;case ICE_VSI_VF : +case ICE_VSI_SF :/* VF VSI will gets a small RSS table which is a VSI LUT type */ lut_type =ICE_AQ_VSI_Q_OPT_RSS_LUT_VSI ;break ;
@@ -1219,6 +1235,7 @@ static int ice_vsi_init(struct ice_vsi *vsi, u32 vsi_flags)case ICE_VSI_PF : ctxt->flags =ICE_AQ_VSI_TYPE_PF ;break ; +case ICE_VSI_SF :case ICE_VSI_CHNL : ctxt->flags =ICE_AQ_VSI_TYPE_VMDQ2 ;break ;
@@ -2100,6 +2117,7 @@ static void ice_set_agg_vsi(struct ice_vsi *vsi)case ICE_VSI_CHNL :case ICE_VSI_LB :case ICE_VSI_PF : +case ICE_VSI_SF : max_agg_nodes =ICE_MAX_PF_AGG_NODES ; agg_node_id_start =ICE_PF_AGG_NODE_ID_START ; agg_node_iter = &pf->pf_agg_node[0 ];
@@ -2271,6 +2289,7 @@ ice_vsi_cfg_def(struct ice_vsi *vsi, struct ice_vsi_cfg_params *params)switch (vsi->type) {case ICE_VSI_CTRL : +case ICE_VSI_SF :case ICE_VSI_PF : ret =ice_vsi_alloc_q_vectors (vsi);if (ret)
@@ -2662,7 +2681,8 @@ int ice_ena_vsi(struct ice_vsi *vsi, bool locked)clear_bit (ICE_VSI_NEEDS_RESTART , vsi->state); -if (vsi->netdev && vsi->type ==ICE_VSI_PF ) { +if (vsi->netdev && (vsi->type ==ICE_VSI_PF || + vsi->type ==ICE_VSI_SF )) {if (netif_running (vsi->netdev)) {if (!locked)rtnl_lock ();
@@ -2691,7 +2711,8 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked)set_bit (ICE_VSI_NEEDS_RESTART , vsi->state); -if (vsi->type ==ICE_VSI_PF && vsi->netdev) { +if (vsi->netdev && (vsi->type ==ICE_VSI_PF || + vsi->type ==ICE_VSI_SF )) {if (netif_running (vsi->netdev)) {if (!locked)rtnl_lock ();
drivers/net/ethernet/intel/ice/ice_main.c +5 -2
@@ -2946,6 +2946,9 @@ int ice_vsi_determine_xdp_res(struct ice_vsi *vsi)if (avail < cpus /2 )return -ENOMEM ; +if (vsi->type ==ICE_VSI_SF ) + avail = vsi->alloc_txq; + vsi->num_xdp_txq =min_t (u16, avail, cpus);if (vsi->num_xdp_txq < cpus)
@@ -3061,8 +3064,8 @@ static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp)struct ice_netdev_priv *np =netdev_priv (dev);struct ice_vsi *vsi = np->vsi; -if (vsi->type !=ICE_VSI_PF ) { -NL_SET_ERR_MSG_MOD (xdp->extack,"XDP can be loaded only on PF VSI" ); +if (vsi->type !=ICE_VSI_PF && vsi->type !=ICE_VSI_SF ) { +NL_SET_ERR_MSG_MOD (xdp->extack,"XDP can be loaded only on PF or SF VSI" );return -EINVAL ; }
drivers/net/ethernet/intel/ice/ice_type.h +1 -0
@@ -150,6 +150,7 @@ enum ice_vsi_type {ICE_VSI_CTRL =3 ,/* equates to ICE_VSI_PF with 1 queue pair */ ICE_VSI_CHNL =4 ,ICE_VSI_LB =6 , + ICE_VSI_SF = 9, }; struct ice_link_status {
drivers/net/ethernet/intel/ice/ice_xsk.c +1 -1
@@ -288,7 +288,7 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid) {int err; -if (vsi->type !=ICE_VSI_PF ) +if (vsi->type !=ICE_VSI_PF && vsi->type !=ICE_VSI_SF )return -EINVAL ; if (qid >= vsi->netdev->real_num_rx_queues ||
Signature · 1 line
2.42.0
PATCH v2 2/7 ice: export ice ndo_ops functions
In reply to Michal SwiatkowskiFrom: Piotr Raczynski <[email protected]>
Make some of the netdevice_ops functions visible from outside for another VSI type created netdev.
--- drivers/net/ethernet/intel/ice/ice.h | 8 +++++ drivers/net/ethernet/intel/ice/ice_lib.c | 22 ++++++++++++++ drivers/net/ethernet/intel/ice/ice_lib.h | 1 + drivers/net/ethernet/intel/ice/ice_main.c | 37 ++++------------------- 4 files changed, 37 insertions(+), 31 deletions(-)
drivers/net/ethernet/intel/ice/ice.h +8 -0
@@ -982,6 +982,14 @@ void ice_unload(struct ice_pf *pf);void ice_adv_lnk_speed_maps_init (void );int ice_init_dev (struct ice_pf *pf);void ice_deinit_dev (struct ice_pf *pf); +int ice_change_mtu (struct net_device *netdev,int new_mtu); +void ice_tx_timeout (struct net_device *netdev,unsigned int txqueue); +int ice_xdp (struct net_device *dev,struct netdev_bpf *xdp); +void ice_set_netdev_features (struct net_device *netdev); +int ice_vlan_rx_add_vid (struct net_device *netdev,__be16 proto,u16 vid); +int ice_vlan_rx_kill_vid (struct net_device *netdev,__be16 proto,u16 vid); +void ice_get_stats64 (struct net_device *netdev, +struct rtnl_link_stats64 *stats);/** * ice_set_rdma_cap - enable RDMA support
drivers/net/ethernet/intel/ice/ice_lib.c +22 -0
@@ -2846,6 +2846,28 @@ void ice_vsi_set_napi_queues(struct ice_vsi *vsi)ice_q_vector_set_napi_queues (vsi->q_vectors[i]); } +/** +* ice_napi_add - register NAPI handler for the VSI +* @vsi: VSI for which NAPI handler is to be registered +* +* This function is only called in the driver's load path. Registering the NAPI +* handler is done in ice_vsi_alloc_q_vector() for all other cases (i.e. resume, +* reset/rebuild, etc.) +*/ +void ice_napi_add (struct ice_vsi *vsi) +{ +int v_idx; + +if (!vsi->netdev) +return ; + +ice_for_each_q_vector (vsi, v_idx) { +netif_napi_add (vsi->netdev, &vsi->q_vectors[v_idx]->napi, + ice_napi_poll); +__ice_q_vector_set_napi_queues (vsi->q_vectors[v_idx], false); + } +} +/** * ice_vsi_release - Delete a VSI and free its resources * @vsi: the VSI being removed
drivers/net/ethernet/intel/ice/ice_lib.h +1 -0
@@ -90,6 +90,7 @@ void __ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked);void ice_q_vector_set_napi_queues (struct ice_q_vector *q_vector);void ice_vsi_set_napi_queues (struct ice_vsi *vsi); +void ice_napi_add (struct ice_vsi *vsi);int ice_vsi_release (struct ice_vsi *vsi);
drivers/net/ethernet/intel/ice/ice_main.c +6 -31
@@ -3059,7 +3059,7 @@ static int ice_xdp_safe_mode(struct net_device __always_unused *dev,* @dev: netdevice * @xdp: XDP command */ -static int ice_xdp (struct net_device *dev,struct netdev_bpf *xdp) +int ice_xdp (struct net_device *dev,struct netdev_bpf *xdp) {struct ice_netdev_priv *np =netdev_priv (dev);struct ice_vsi *vsi = np->vsi;
@@ -3518,28 +3518,6 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)return 0 ; } -/** -* ice_napi_add - register NAPI handler for the VSI -* @vsi: VSI for which NAPI handler is to be registered -* -* This function is only called in the driver's load path. Registering the NAPI -* handler is done in ice_vsi_alloc_q_vector() for all other cases (i.e. resume, -* reset/rebuild, etc.) -*/ -static void ice_napi_add (struct ice_vsi *vsi) -{ -int v_idx; - -if (!vsi->netdev) -return ; - -ice_for_each_q_vector (vsi, v_idx) { -netif_napi_add (vsi->netdev, &vsi->q_vectors[v_idx]->napi, - ice_napi_poll); -__ice_q_vector_set_napi_queues (vsi->q_vectors[v_idx], false); - } -} -/** * ice_set_ops - set netdev and ethtools ops for the given netdev * @vsi: the VSI associated with the new netdev
@@ -3573,7 +3551,7 @@ static void ice_set_ops(struct ice_vsi *vsi)* ice_set_netdev_features - set features for the given netdev * @netdev: netdev instance */ -static void ice_set_netdev_features (struct net_device *netdev) +void ice_set_netdev_features (struct net_device *netdev) {struct ice_pf *pf =ice_netdev_to_pf (netdev);bool is_dvm_ena =ice_is_dvm_ena (&pf->hw);
@@ -3755,8 +3733,7 @@ ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)* * net_device_ops implementation for adding VLAN IDs */ -static int -ice_vlan_rx_add_vid (struct net_device *netdev,__be16 proto,u16 vid) +int ice_vlan_rx_add_vid (struct net_device *netdev,__be16 proto,u16 vid) {struct ice_netdev_priv *np =netdev_priv (netdev);struct ice_vsi_vlan_ops *vlan_ops;
@@ -3818,8 +3795,7 @@ ice_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid)* * net_device_ops implementation for removing VLAN IDs */ -static int -ice_vlan_rx_kill_vid (struct net_device *netdev,__be16 proto,u16 vid) +int ice_vlan_rx_kill_vid (struct net_device *netdev,__be16 proto,u16 vid) {struct ice_netdev_priv *np =netdev_priv (netdev);struct ice_vsi_vlan_ops *vlan_ops;
@@ -7052,7 +7028,6 @@ void ice_update_pf_stats(struct ice_pf *pf)* @netdev: network interface device structure * @stats: main device statistics structure */ -static void ice_get_stats64 (struct net_device *netdev,struct rtnl_link_stats64 *stats) {struct ice_netdev_priv *np =netdev_priv (netdev);
@@ -7725,7 +7700,7 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)* * Returns 0 on success, negative on failure */ -static int ice_change_mtu (struct net_device *netdev,int new_mtu) +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;
@@ -8149,7 +8124,7 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,* @netdev: network interface device structure * @txqueue: Tx queue */ -static void ice_tx_timeout (struct net_device *netdev,unsigned int txqueue) +void ice_tx_timeout (struct net_device *netdev,unsigned int txqueue) {struct ice_netdev_priv *np =netdev_priv (netdev);struct ice_tx_ring *tx_ring =NULL ;
Signature · 1 line
2.42.0
PATCH v2 3/7 ice: add basic devlink subfunctions support
In reply to Michal SwiatkowskiFrom: Piotr Raczynski <[email protected]>
Implement devlink port handlers responsible for ethernet type devlink subfunctions. Create subfunction devlink port and setup all resources needed for a subfunction netdev to operate. Configure new VSI for each new subfunction, initialize and configure interrupts and Tx/Rx resources. Set correct MAC filters and create new netdev.
For now, subfunction is limited to only one Tx/Rx queue pair.
Only allocate new subfunction VSI with devlink port new command. This makes sure that real resources are configured only when a new subfunction gets activated. Allocate and free subfunction MSIX interrupt vectors using new API calls with pci_msix_alloc_irq_at and pci_msix_free_irq.
Support both automatic and manual subfunction numbers. If no subfunction number is provided, use xa_alloc to pick a number automatically. This will find the first free index and use that as the number. This reduces burden on users in the simple case where a specific number is not required. It may also be slightly faster to check that a number exists since xarray lookup should be faster than a linear scan of the dyn_ports xarray.
--- .../net/ethernet/intel/ice/devlink/devlink.c | 3 + .../ethernet/intel/ice/devlink/devlink_port.c | 454 ++++++++++++++++++ .../ethernet/intel/ice/devlink/devlink_port.h | 30 ++ drivers/net/ethernet/intel/ice/ice.h | 4 + drivers/net/ethernet/intel/ice/ice_lib.c | 5 +- drivers/net/ethernet/intel/ice/ice_lib.h | 2 + drivers/net/ethernet/intel/ice/ice_main.c | 12 +- 7 files changed, 506 insertions(+), 4 deletions(-)
drivers/net/ethernet/intel/ice/devlink/devlink.c +3 -0
@@ -6,6 +6,7 @@#include "ice.h" #include "ice_lib.h" #include "devlink.h" +#include "devlink_port.h" #include "ice_eswitch.h" #include "ice_fw_update.h" #include "ice_dcb_lib.h"
@@ -1281,6 +1282,8 @@ static const struct devlink_ops ice_devlink_ops = { .rate_leaf_parent_set = ice_devlink_set_parent, .rate_node_parent_set = ice_devlink_set_parent, + + .port_new = ice_devlink_port_new, }; static int
drivers/net/ethernet/intel/ice/devlink/devlink_port.c +454 -0
463 lines not on this page · raw message
drivers/net/ethernet/intel/ice/devlink/devlink_port.h +30 -0
@@ -4,9 +4,39 @@#ifndef _DEVLINK_PORT_H_#define _DEVLINK_PORT_H_ +#include "../ice.h" + +/** +* struct ice_dynamic_port - Track dynamically added devlink port instance +* @hw_addr: the HW address for this port +* @active: true if the port has been activated +* @devlink_port: the associated devlink port structure +* @pf: pointer to the PF private structure +* @vsi: the VSI associated with this port +* +* An instance of a dynamically added devlink port. Each port flavour +*/ +struct ice_dynamic_port { +u8 hw_addr[ETH_ALEN ]; +u8 active :1 ; +struct devlink_port devlink_port; +struct ice_pf *pf; +struct ice_vsi *vsi; +}; + +void ice_dealloc_all_dynamic_ports (struct ice_pf *pf); +int ice_devlink_create_pf_port (struct ice_pf *pf);void ice_devlink_destroy_pf_port (struct ice_pf *pf);int ice_devlink_create_vf_port (struct ice_vf *vf);void ice_devlink_destroy_vf_port (struct ice_vf *vf); +#define ice_devlink_port_to_dyn (p) \ + container_of(port, struct ice_dynamic_port, devlink_port) + +int +ice_devlink_port_new (struct devlink *devlink, +const struct devlink_port_new_attrs *new_attr, +struct netlink_ext_ack *extack, +struct devlink_port **devlink_port);#endif /* _DEVLINK_PORT_H_ */
drivers/net/ethernet/intel/ice/ice.h +4 -0
@@ -649,6 +649,9 @@ struct ice_pf {struct ice_eswitch eswitch;struct ice_esw_br_port *br_port; +struct xarray dyn_ports; +struct xarray sf_nums; +#define ICE_INVALID_AGG_NODE_ID 0#define ICE_PF_AGG_NODE_ID_START 1#define ICE_MAX_PF_AGG_NODES 32
@@ -905,6 +908,7 @@ int ice_vsi_open(struct ice_vsi *vsi);void ice_set_ethtool_ops (struct net_device *netdev);void ice_set_ethtool_repr_ops (struct net_device *netdev);void ice_set_ethtool_safe_mode_ops (struct net_device *netdev); +void ice_set_ethtool_sf_ops (struct net_device *netdev);u16 ice_get_avail_txq_count (struct ice_pf *pf);u16 ice_get_avail_rxq_count (struct ice_pf *pf);int ice_vsi_recfg_qs (struct ice_vsi *vsi,int new_rx,int new_tx,bool locked);
drivers/net/ethernet/intel/ice/ice_lib.c +3 -2
@@ -7,6 +7,7 @@#include "ice_lib.h" #include "ice_fltr.h" #include "ice_dcb_lib.h" +#include "ice_type.h" #include "ice_vsi_vlan_ops.h" /**
@@ -440,7 +441,7 @@ static int ice_vsi_alloc_ring_stats(struct ice_vsi *vsi)* This deallocates the VSI's queue resources, removes it from the PF's * VSI array if necessary, and deallocates the VSI */ -static void ice_vsi_free (struct ice_vsi *vsi) +void ice_vsi_free (struct ice_vsi *vsi) {struct ice_pf *pf =NULL ;struct device *dev;
@@ -612,7 +613,7 @@ ice_vsi_alloc_def(struct ice_vsi *vsi, struct ice_channel *ch)* * returns a pointer to a VSI on success, NULL on failure. */ -static struct ice_vsi *ice_vsi_alloc (struct ice_pf *pf) +struct ice_vsi *ice_vsi_alloc (struct ice_pf *pf) {struct device *dev =ice_pf_to_dev (pf);struct ice_vsi *vsi =NULL ;
drivers/net/ethernet/intel/ice/ice_lib.h +2 -0
@@ -103,6 +103,8 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked);int ice_vsi_rebuild (struct ice_vsi *vsi,u32 vsi_flags);int ice_vsi_cfg (struct ice_vsi *vsi,struct ice_vsi_cfg_params *params); +struct ice_vsi *ice_vsi_alloc (struct ice_pf *pf); +void ice_vsi_free (struct ice_vsi *vsi);bool ice_is_reset_in_progress (unsigned long *state);int ice_wait_for_reset (struct ice_pf *pf,unsigned long timeout);
drivers/net/ethernet/intel/ice/ice_main.c +10 -2
@@ -3964,6 +3964,9 @@ static void ice_deinit_pf(struct ice_pf *pf)if (pf->ptp.clock)ptp_clock_unregister (pf->ptp.clock); + +xa_destroy (&pf->dyn_ports); +xa_destroy (&pf->sf_nums); }/**
@@ -4057,6 +4060,9 @@ static int ice_init_pf(struct ice_pf *pf)hash_init (pf->vfs.table);ice_mbx_init_snapshot (&pf->hw); +xa_init (&pf->dyn_ports); +xa_init (&pf->sf_nums); +return 0 ; }
@@ -5376,6 +5382,7 @@ static void ice_remove(struct pci_dev *pdev)ice_remove_arfs (pf);devl_lock (priv_to_devlink (pf)); +ice_dealloc_all_dynamic_ports (pf);ice_deinit_devlink (pf);ice_unload (pf);
@@ -6670,7 +6677,8 @@ static int ice_up_complete(struct ice_vsi *vsi)if (vsi->port_info && (vsi->port_info->phy.link_info.link_info &ICE_AQ_LINK_UP ) && - vsi->netdev && vsi->type ==ICE_VSI_PF ) { + ((vsi->netdev && vsi->type ==ICE_VSI_PF ) || + (vsi->netdev && vsi->type ==ICE_VSI_SF ))) {ice_print_link_msg (vsi, true);netif_tx_start_all_queues (vsi->netdev);netif_carrier_on (vsi->netdev);
@@ -7368,7 +7376,7 @@ int ice_vsi_open(struct ice_vsi *vsi)ice_vsi_cfg_netdev_tc (vsi, vsi->tc_cfg.ena_tc); -if (vsi->type ==ICE_VSI_PF ) { +if (vsi->type ==ICE_VSI_PF || vsi->type ==ICE_VSI_SF ) {/* Notify the stack of the actual queue counts. */ err =netif_set_real_num_tx_queues (vsi->netdev, vsi->num_txq);if (err)
Signature · 1 line
2.42.0
PATCH v2 4/7 ice: allocate devlink for subfunction
In reply to Michal SwiatkowskiFrom: Piotr Raczynski <[email protected]>
Make devlink allocation function generic to use it for PF and for SF.
Add function for SF devlink port creation. It will be used in next patch.
--- .../net/ethernet/intel/ice/devlink/devlink.c | 41 ++++++++++++--- .../net/ethernet/intel/ice/devlink/devlink.h | 1 + .../ethernet/intel/ice/devlink/devlink_port.c | 51 +++++++++++++++++++ .../ethernet/intel/ice/devlink/devlink_port.h | 3 ++ 4 files changed, 90 insertions(+), 6 deletions(-)
drivers/net/ethernet/intel/ice/devlink/devlink.c +35 -6
@@ -10,6 +10,7 @@#include "ice_eswitch.h" #include "ice_fw_update.h" #include "ice_dcb_lib.h" +#include "ice_sf_eth.h" /* context for devlink info version reporting */ struct ice_info_ctx {
@@ -1286,6 +1287,8 @@ static const struct devlink_ops ice_devlink_ops = { .port_new = ice_devlink_port_new, }; +static const struct devlink_ops ice_sf_devlink_ops; +static int ice_devlink_enable_roce_get (struct devlink *devlink,u32 id,struct devlink_param_gset_ctx *ctx)
@@ -1417,18 +1420,21 @@ static void ice_devlink_free(void *devlink_ptr) }/** -* ice_allocate_pf - Allocate devlink and return PF structure pointer +* ice_devlink_alloc - Allocate devlink and return devlink priv pointer * @dev: the device to allocate for +* @priv_size: size of the priv memory +* @ops: pointer to devlink ops for this device * -* Allocate a devlink instance for this device and return the private area as -* the PF structure. The devlink memory is kept track of through devres by -* adding an action to remove it when unwinding. +* Allocate a devlink instance for this device and return the private pointer +* The devlink memory is kept track of through devres by adding an action to +* remove it when unwinding. */ -struct ice_pf *ice_allocate_pf (struct device *dev) +static void *ice_devlink_alloc (struct device *dev,size_t priv_size, +const struct devlink_ops *ops) {struct devlink *devlink; - devlink =devlink_alloc (&ice_devlink_ops,sizeof (struct ice_pf ), dev); + devlink =devlink_alloc (ops, priv_size, dev);if (!devlink)return NULL ;
@@ -1439,6 +1445,29 @@ struct ice_pf *ice_allocate_pf(struct device *dev)return devlink_priv (devlink); } +/** +* ice_allocate_pf - Allocate devlink and return PF structure pointer +* @dev: the device to allocate for +* +* Allocate a devlink instance for PF. +*/ +struct ice_pf *ice_allocate_pf (struct device *dev) +{ +return ice_devlink_alloc (dev,sizeof (struct ice_pf ), &ice_devlink_ops); +} + +/** +* ice_allocate_sf - Allocate devlink and return SF structure pointer +* @dev: the device to allocate for +* +* Allocate a devlink instance for SF. +*/ +struct ice_sf_priv *ice_allocate_sf (struct device *dev) +{ +return ice_devlink_alloc (dev,sizeof (struct ice_sf_priv ), + &ice_sf_devlink_ops); +} +/** * ice_devlink_register - Register devlink interface for this PF * @pf: the PF to register the devlink for.
drivers/net/ethernet/intel/ice/devlink/devlink.h +1 -0
@@ -5,6 +5,7 @@#define _ICE_DEVLINK_H_struct ice_pf *ice_allocate_pf (struct device *dev); +struct ice_sf_priv *ice_allocate_sf (struct device *dev);void ice_devlink_register (struct ice_pf *pf);void ice_devlink_unregister (struct ice_pf *pf);
drivers/net/ethernet/intel/ice/devlink/devlink_port.c +51 -0
57 lines not on this page · raw message
drivers/net/ethernet/intel/ice/devlink/devlink_port.h +3 -0
@@ -5,6 +5,7 @@#define _DEVLINK_PORT_H_#include "../ice.h" +#include "ice_sf_eth.h" /** * struct ice_dynamic_port - Track dynamically added devlink port instance
@@ -30,6 +31,8 @@ int ice_devlink_create_pf_port(struct ice_pf *pf);void ice_devlink_destroy_pf_port (struct ice_pf *pf);int ice_devlink_create_vf_port (struct ice_vf *vf);void ice_devlink_destroy_vf_port (struct ice_vf *vf); +int ice_devlink_create_sf_dev_port (struct ice_sf_dev *sf_dev); +void ice_devlink_destroy_sf_dev_port (struct ice_sf_dev *sf_dev);#define ice_devlink_port_to_dyn (p) \ container_of(port, struct ice_dynamic_port, devlink_port)
Signature · 1 line
2.42.0
PATCH v2 5/7 ice: base subfunction aux driver
In reply to Michal SwiatkowskiFrom: Piotr Raczynski <[email protected]>
Implement subfunction driver. It is probe when subfunction port is activated.
VSI is already created. During the probe VSI is being configured. MAC unicast and broadcast filter is added to allow traffic to pass.
--- drivers/net/ethernet/intel/ice/Makefile | 1 + drivers/net/ethernet/intel/ice/ice_main.c | 10 ++ drivers/net/ethernet/intel/ice/ice_sf_eth.c | 130 ++++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_sf_eth.h | 30 +++++ 4 files changed, 171 insertions(+) create mode 100644 drivers/net/ethernet/intel/ice/ice_sf_eth.c create mode 100644 drivers/net/ethernet/intel/ice/ice_sf_eth.h
drivers/net/ethernet/intel/ice/Makefile +1 -0
@@ -31,6 +31,7 @@ ice-y := ice_main.o \ ice_idc.o \ devlink/devlink.o \ devlink/devlink_port.o \ + ice_sf_eth.o \ ice_ddp.o \ ice_fw_update.o \ ice_lag.o \
drivers/net/ethernet/intel/ice/ice_main.c +10 -0
@@ -15,6 +15,7 @@#include "ice_dcb_nl.h" #include "devlink/devlink.h" #include "devlink/devlink_port.h" +#include "ice_sf_eth.h" #include "ice_hwmon.h" /* Including ice_trace.h with CREATE_TRACE_POINTS defined will generate the * ice tracepoint functions. This must be done exactly once across the
@@ -5857,8 +5858,16 @@ static int __init ice_module_init(void) goto err_dest_lag_wq; } + status =ice_sf_driver_register (); +if (status) { +pr_err ("Failed to register SF driver, err %d\n" , status); + goto err_sf_driver; + } +return 0 ; +err_sf_driver: +pci_unregister_driver (&ice_driver); err_dest_lag_wq:destroy_workqueue (ice_lag_wq);ice_debugfs_exit ();
@@ -5876,6 +5885,7 @@ module_init(ice_module_init);*/ static void __exit ice_module_exit(void) { +ice_sf_driver_unregister ();pci_unregister_driver (&ice_driver);ice_debugfs_exit ();destroy_workqueue (ice_wq);
drivers/net/ethernet/intel/ice/ice_sf_eth.c new file +130 -0
130 lines not on this page · raw message
drivers/net/ethernet/intel/ice/ice_sf_eth.h new file +30 -0
@@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2024, Intel Corporation. */ + +#ifndef _ICE_SF_ETH_H_ +#define _ICE_SF_ETH_H_ + +#include <linux/auxiliary_bus.h> +#include "ice.h" + +struct ice_sf_dev { +struct auxiliary_device adev; +struct ice_dynamic_port *dyn_port; +struct ice_sf_priv *priv; +}; + +struct ice_sf_priv { +struct ice_sf_dev *dev; +struct devlink_port devlink_port; +}; + +static inline struct +ice_sf_dev *ice_adev_to_sf_dev (struct auxiliary_device *adev) +{ + return container_of(adev, struct ice_sf_dev, adev); +} + +int ice_sf_driver_register (void ); +void ice_sf_driver_unregister (void ); + +#endif /* _ICE_SF_ETH_H_ */
Signature · 1 line
2.42.0
PATCH v2 6/7 ice: implement netdev for subfunction
In reply to Michal SwiatkowskiFrom: Piotr Raczynski <[email protected]>
Configure netdevice for subfunction usecase. Mostly it is reusing ops from the PF netdevice.
SF netdev is linked to devlink port registered after SF activation.
--- drivers/net/ethernet/intel/ice/ice_sf_eth.c | 85 ++++++++++++++++++++- 1 file changed, 84 insertions(+), 1 deletion(-)
drivers/net/ethernet/intel/ice/ice_sf_eth.c +84 -1
@@ -2,11 +2,85 @@/* Copyright (c) 2024, Intel Corporation. */ #include "ice.h" #include "ice_lib.h" +#include "ice_txrx.h" #include "ice_fltr.h" #include "ice_sf_eth.h" #include "devlink/devlink_port.h" #include "devlink/devlink.h" +static const struct net_device_ops ice_sf_netdev_ops = { + .ndo_open = ice_open, + .ndo_stop = ice_stop, + .ndo_start_xmit = ice_start_xmit, + .ndo_vlan_rx_add_vid = ice_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = ice_vlan_rx_kill_vid, + .ndo_change_mtu = ice_change_mtu, + .ndo_get_stats64 = ice_get_stats64, + .ndo_tx_timeout = ice_tx_timeout, + .ndo_bpf = ice_xdp, + .ndo_xdp_xmit = ice_xdp_xmit, + .ndo_xsk_wakeup = ice_xsk_wakeup, +}; + +/** +* ice_sf_cfg_netdev - Allocate, configure and register a netdev +* @dyn_port: subfunction associated with configured netdev +* @devlink_port: subfunction devlink port to be linked with netdev +* +* Returns 0 on success, negative value on failure +*/ +static int ice_sf_cfg_netdev (struct ice_dynamic_port *dyn_port, +struct devlink_port *devlink_port) +{ +struct ice_vsi *vsi = dyn_port->vsi; +struct ice_netdev_priv *np; +struct net_device *netdev; +int err; + + netdev =alloc_etherdev_mqs (sizeof (*np), vsi->alloc_txq, + vsi->alloc_rxq); +if (!netdev) +return -ENOMEM ; + +SET_NETDEV_DEV (netdev, &vsi->back->pdev->dev); +set_bit (ICE_VSI_NETDEV_ALLOCD , vsi->state); + vsi->netdev = netdev; + np =netdev_priv (netdev); + np->vsi = vsi; + +ice_set_netdev_features (netdev); + + netdev->xdp_features =NETDEV_XDP_ACT_BASIC |NETDEV_XDP_ACT_REDIRECT | +NETDEV_XDP_ACT_XSK_ZEROCOPY | +NETDEV_XDP_ACT_RX_SG ; + +eth_hw_addr_set (netdev, dyn_port->hw_addr); +ether_addr_copy (netdev->perm_addr, dyn_port->hw_addr); + netdev->netdev_ops = &ice_sf_netdev_ops; +SET_NETDEV_DEVLINK_PORT (netdev, devlink_port); + + err =register_netdev (netdev); +if (err) { +free_netdev (netdev); + vsi->netdev =NULL ; +return -ENOMEM ; + } +set_bit (ICE_VSI_NETDEV_REGISTERED , vsi->state); +netif_carrier_off (netdev); +netif_tx_stop_all_queues (netdev); + +return 0 ; +} + +static void ice_sf_decfg_netdev (struct ice_vsi *vsi) +{ +unregister_netdev (vsi->netdev); +clear_bit (ICE_VSI_NETDEV_REGISTERED , vsi->state); +free_netdev (vsi->netdev); + vsi->netdev =NULL ; +clear_bit (ICE_VSI_NETDEV_ALLOCD , vsi->state); +} +/** * ice_sf_dev_probe - subfunction driver probe function * @adev: pointer to the auxiliary device
@@ -55,18 +129,26 @@ static int ice_sf_dev_probe(struct auxiliary_device *adev, goto err_vsi_decfg; } + err =ice_sf_cfg_netdev (dyn_port, &sf_dev->priv->devlink_port); +if (err) { +dev_err (dev,"Subfunction netdev config failed" ); + goto err_devlink_destroy; + } + err =ice_fltr_add_mac_and_broadcast (vsi, vsi->netdev->dev_addr,ICE_FWD_TO_VSI );if (err) {dev_err (dev,"can't add MAC filters %pM for VSI %d\n" , vsi->netdev->dev_addr, vsi->idx); - goto err_devlink_destroy; + goto err_netdev_decfg; }ice_napi_add (vsi);return err; +err_netdev_decfg: +ice_sf_decfg_netdev (vsi); err_devlink_destroy:ice_devlink_destroy_sf_dev_port (sf_dev); err_vsi_decfg:
@@ -89,6 +171,7 @@ static void ice_sf_dev_remove(struct auxiliary_device *adev)ice_vsi_close (vsi); +ice_sf_decfg_netdev (vsi);ice_devlink_destroy_sf_dev_port (sf_dev);devlink_unregister (devlink);devlink_free (devlink);
Signature · 1 line
2.42.0
PATCH v2 7/7 ice: allow to activate and deactivate subfunction
In reply to Michal SwiatkowskiFrom: Piotr Raczynski <[email protected]>
Use previously implemented SF aux driver. It is probe during SF activation and remove after deactivation.
--- .../ethernet/intel/ice/devlink/devlink_port.c | 7 ++ .../ethernet/intel/ice/devlink/devlink_port.h | 4 + drivers/net/ethernet/intel/ice/ice_sf_eth.c | 104 ++++++++++++++++++ drivers/net/ethernet/intel/ice/ice_sf_eth.h | 3 + 4 files changed, 118 insertions(+)
drivers/net/ethernet/intel/ice/devlink/devlink_port.c +7 -0
@@ -496,6 +496,12 @@ static int ice_activate_dynamic_port(struct ice_dynamic_port *dyn_port, struct netlink_ext_ack *extack) { + int err; + + err =ice_sf_eth_activate (dyn_port, extack); +if (err) +return err; + dyn_port->active = true;return 0 ;
@@ -509,6 +515,7 @@ ice_activate_dynamic_port(struct ice_dynamic_port *dyn_port,*/ static void ice_deactivate_dynamic_port (struct ice_dynamic_port *dyn_port) { +ice_sf_eth_deactivate (dyn_port); dyn_port->active = false; }
drivers/net/ethernet/intel/ice/devlink/devlink_port.h +4 -0
@@ -23,6 +23,10 @@ struct ice_dynamic_port {struct devlink_port devlink_port;struct ice_pf *pf;struct ice_vsi *vsi; +/* Flavour-specific implementation data */ +union { +struct ice_sf_dev *sf_dev; + }; };void ice_dealloc_all_dynamic_ports (struct ice_pf *pf);
drivers/net/ethernet/intel/ice/ice_sf_eth.c +104 -0
113 lines not on this page · raw message
drivers/net/ethernet/intel/ice/ice_sf_eth.h +3 -0
@@ -27,4 +27,7 @@ ice_sf_dev *ice_adev_to_sf_dev(struct auxiliary_device *adev)int ice_sf_driver_register (void );void ice_sf_driver_unregister (void ); +int ice_sf_eth_activate (struct ice_dynamic_port *dyn_port, +struct netlink_ext_ack *extack); +void ice_sf_eth_deactivate (struct ice_dynamic_port *dyn_port);#endif /* _ICE_SF_ETH_H_ */
Signature · 1 line
2.42.0