summaryrefslogtreecommitdiff
path: root/drivers/net/ethernet/intel/ice/ice_main.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/net/ethernet/intel/ice/ice_main.c')
-rw-r--r--drivers/net/ethernet/intel/ice/ice_main.c780
1 files changed, 506 insertions, 274 deletions
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 33a164fa325a..c3a0fb97c5ee 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -13,7 +13,9 @@
#include "ice_fltr.h"
#include "ice_dcb_lib.h"
#include "ice_dcb_nl.h"
-#include "ice_devlink.h"
+#include "devlink/devlink.h"
+#include "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
@@ -34,8 +36,8 @@ static const char ice_copyright[] = "Copyright (c) 2018, Intel Corporation.";
#define ICE_DDP_PKG_PATH "intel/ice/ddp/"
#define ICE_DDP_PKG_FILE ICE_DDP_PKG_PATH "ice.pkg"
-MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>");
MODULE_DESCRIPTION(DRV_SUMMARY);
+MODULE_IMPORT_NS("LIBIE");
MODULE_LICENSE("GPL v2");
MODULE_FIRMWARE(ICE_DDP_PKG_FILE);
@@ -85,7 +87,8 @@ ice_indr_setup_tc_cb(struct net_device *netdev, struct Qdisc *sch,
bool netif_is_ice(const struct net_device *dev)
{
- return dev && (dev->netdev_ops == &ice_netdev_ops);
+ return dev && (dev->netdev_ops == &ice_netdev_ops ||
+ dev->netdev_ops == &ice_netdev_safe_mode_ops);
}
/**
@@ -519,25 +522,6 @@ static void ice_pf_dis_all_vsi(struct ice_pf *pf, bool locked)
}
/**
- * ice_clear_sw_switch_recipes - clear switch recipes
- * @pf: board private structure
- *
- * Mark switch recipes as not created in sw structures. There are cases where
- * rules (especially advanced rules) need to be restored, either re-read from
- * hardware or added again. For example after the reset. 'recp_created' flag
- * prevents from doing that and need to be cleared upfront.
- */
-static void ice_clear_sw_switch_recipes(struct ice_pf *pf)
-{
- struct ice_sw_recipe *recp;
- u8 i;
-
- recp = pf->hw.switch_info->recp_list;
- for (i = 0; i < ICE_MAX_NUM_RECIPES; i++)
- recp[i].recp_created = false;
-}
-
-/**
* ice_prepare_for_reset - prep for reset
* @pf: board private structure
* @reset_type: reset type requested
@@ -558,6 +542,8 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
if (test_bit(ICE_PREPARED_FOR_RESET, pf->state))
return;
+ synchronize_irq(pf->oicr_irq.virq);
+
ice_unplug_aux_dev(pf);
/* Notify VFs of impending reset */
@@ -571,8 +557,9 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
mutex_unlock(&pf->vfs.table_lock);
if (ice_is_eswitch_mode_switchdev(pf)) {
- if (reset_type != ICE_RESET_PFR)
- ice_clear_sw_switch_recipes(pf);
+ rtnl_lock();
+ ice_eswitch_br_fdb_flush(pf->eswitch.br_offloads->bridge);
+ rtnl_unlock();
}
/* release ADQ specific HW and SW resources */
@@ -605,11 +592,15 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
memset(&vsi->mqprio_qopt, 0, sizeof(vsi->mqprio_qopt));
}
}
+
+ if (vsi->netdev)
+ netif_device_detach(vsi->netdev);
skip:
/* clear SW filtering DB */
ice_clear_hw_tbls(hw);
/* disable the VSIs and their queues that are not already DOWN */
+ set_bit(ICE_VSI_REBUILD_PENDING, ice_get_main_vsi(pf)->state);
ice_pf_dis_all_vsi(pf, false);
if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags))
@@ -621,7 +612,7 @@ skip:
if (hw->port_info)
ice_sched_clear_port(hw->port_info);
- ice_shutdown_all_ctrlq(hw);
+ ice_shutdown_all_ctrlq(hw, false);
set_bit(ICE_PREPARED_FOR_RESET, pf->state);
}
@@ -803,6 +794,9 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup)
}
switch (vsi->port_info->phy.link_info.link_speed) {
+ case ICE_AQ_LINK_SPEED_200GB:
+ speed = "200 G";
+ break;
case ICE_AQ_LINK_SPEED_100GB:
speed = "100 G";
break;
@@ -1150,7 +1144,7 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up,
if (link_up == old_link && link_speed == old_link_speed)
return 0;
- ice_ptp_link_change(pf, pf->hw.pf_id, link_up);
+ ice_ptp_link_change(pf, link_up);
if (ice_is_dcb_active(pf)) {
if (test_bit(ICE_FLAG_DCB_ENA, pf->flags))
@@ -1552,12 +1546,20 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
ice_vf_lan_overflow_event(pf, &event);
break;
case ice_mbx_opc_send_msg_to_pf:
- data.num_msg_proc = i;
- data.num_pending_arq = pending;
- data.max_num_msgs_mbx = hw->mailboxq.num_rq_entries;
- data.async_watermark_val = ICE_MBX_OVERFLOW_WATERMARK;
+ if (ice_is_feature_supported(pf, ICE_F_MBX_LIMIT)) {
+ ice_vc_process_vf_msg(pf, &event, NULL);
+ ice_mbx_vf_dec_trig_e830(hw, &event);
+ } else {
+ u16 val = hw->mailboxq.num_rq_entries;
- ice_vc_process_vf_msg(pf, &event, &data);
+ data.max_num_msgs_mbx = val;
+ val = ICE_MBX_OVERFLOW_WATERMARK;
+ data.async_watermark_val = val;
+ data.num_msg_proc = i;
+ data.num_pending_arq = pending;
+
+ ice_vc_process_vf_msg(pf, &event, &data);
+ }
break;
case ice_aqc_opc_fw_logs_event:
ice_get_fwlog_data(pf, &event);
@@ -1565,6 +1567,9 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
case ice_aqc_opc_lldp_set_mib_change:
ice_dcb_process_lldp_set_mib_change(pf, &event);
break;
+ case ice_aqc_opc_get_health_status:
+ ice_process_health_status_event(pf, &event);
+ break;
default:
dev_dbg(dev, "%s Receive Queue unknown event 0x%04x ignored\n",
qtype, opcode);
@@ -1745,6 +1750,39 @@ static void ice_service_timer(struct timer_list *t)
}
/**
+ * ice_mdd_maybe_reset_vf - reset VF after MDD event
+ * @pf: pointer to the PF structure
+ * @vf: pointer to the VF structure
+ * @reset_vf_tx: whether Tx MDD has occurred
+ * @reset_vf_rx: whether Rx MDD has occurred
+ *
+ * Since the queue can get stuck on VF MDD events, the PF can be configured to
+ * automatically reset the VF by enabling the private ethtool flag
+ * mdd-auto-reset-vf.
+ */
+static void ice_mdd_maybe_reset_vf(struct ice_pf *pf, struct ice_vf *vf,
+ bool reset_vf_tx, bool reset_vf_rx)
+{
+ struct device *dev = ice_pf_to_dev(pf);
+
+ if (!test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags))
+ return;
+
+ /* VF MDD event counters will be cleared by reset, so print the event
+ * prior to reset.
+ */
+ if (reset_vf_tx)
+ ice_print_vf_tx_mdd_event(vf);
+
+ if (reset_vf_rx)
+ ice_print_vf_rx_mdd_event(vf);
+
+ dev_info(dev, "PF-to-VF reset on PF %d VF %d due to MDD event\n",
+ pf->hw.pf_id, vf->vf_id);
+ ice_reset_vf(vf, ICE_VF_RESET_NOTIFY | ICE_VF_RESET_LOCK);
+}
+
+/**
* ice_handle_mdd_event - handle malicious driver detect event
* @pf: pointer to the PF structure
*
@@ -1781,6 +1819,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
if (netif_msg_tx_err(pf))
dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
event, queue, pf_num, vf_num);
+ ice_report_mdd_event(pf, ICE_MDD_SRC_TX_PQM, pf_num, vf_num,
+ event, queue);
wr32(hw, GL_MDET_TX_PQM, 0xffffffff);
}
@@ -1794,6 +1834,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
if (netif_msg_tx_err(pf))
dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
event, queue, pf_num, vf_num);
+ ice_report_mdd_event(pf, ICE_MDD_SRC_TX_TCLAN, pf_num, vf_num,
+ event, queue);
wr32(hw, GL_MDET_TX_TCLAN_BY_MAC(hw), U32_MAX);
}
@@ -1807,6 +1849,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
if (netif_msg_rx_err(pf))
dev_info(dev, "Malicious Driver Detection event %d on RX queue %d PF# %d VF# %d\n",
event, queue, pf_num, vf_num);
+ ice_report_mdd_event(pf, ICE_MDD_SRC_RX, pf_num, vf_num, event,
+ queue);
wr32(hw, GL_MDET_RX, 0xffffffff);
}
@@ -1837,6 +1881,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
*/
mutex_lock(&pf->vfs.table_lock);
ice_for_each_vf(pf, bkt, vf) {
+ bool reset_vf_tx = false, reset_vf_rx = false;
+
reg = rd32(hw, VP_MDET_TX_PQM(vf->vf_id));
if (reg & VP_MDET_TX_PQM_VALID_M) {
wr32(hw, VP_MDET_TX_PQM(vf->vf_id), 0xFFFF);
@@ -1845,6 +1891,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
if (netif_msg_tx_err(pf))
dev_info(dev, "Malicious Driver Detection event TX_PQM detected on VF %d\n",
vf->vf_id);
+
+ reset_vf_tx = true;
}
reg = rd32(hw, VP_MDET_TX_TCLAN(vf->vf_id));
@@ -1855,6 +1903,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
if (netif_msg_tx_err(pf))
dev_info(dev, "Malicious Driver Detection event TX_TCLAN detected on VF %d\n",
vf->vf_id);
+
+ reset_vf_tx = true;
}
reg = rd32(hw, VP_MDET_TX_TDPU(vf->vf_id));
@@ -1865,6 +1915,8 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
if (netif_msg_tx_err(pf))
dev_info(dev, "Malicious Driver Detection event TX_TDPU detected on VF %d\n",
vf->vf_id);
+
+ reset_vf_tx = true;
}
reg = rd32(hw, VP_MDET_RX(vf->vf_id));
@@ -1876,18 +1928,12 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
dev_info(dev, "Malicious Driver Detection event RX detected on VF %d\n",
vf->vf_id);
- /* Since the queue is disabled on VF Rx MDD events, the
- * PF can be configured to reset the VF through ethtool
- * private flag mdd-auto-reset-vf.
- */
- if (test_bit(ICE_FLAG_MDD_AUTO_RESET_VF, pf->flags)) {
- /* VF MDD event counters will be cleared by
- * reset, so print the event prior to reset.
- */
- ice_print_vf_rx_mdd_event(vf);
- ice_reset_vf(vf, ICE_VF_RESET_LOCK);
- }
+ reset_vf_rx = true;
}
+
+ if (reset_vf_tx || reset_vf_rx)
+ ice_mdd_maybe_reset_vf(pf, vf, reset_vf_tx,
+ reset_vf_rx);
}
mutex_unlock(&pf->vfs.table_lock);
@@ -2318,6 +2364,18 @@ static void ice_check_media_subtask(struct ice_pf *pf)
}
}
+static void ice_service_task_recovery_mode(struct work_struct *work)
+{
+ struct ice_pf *pf = container_of(work, struct ice_pf, serv_task);
+
+ set_bit(ICE_ADMINQ_EVENT_PENDING, pf->state);
+ ice_clean_adminq_subtask(pf);
+
+ ice_service_task_complete(pf);
+
+ mod_timer(&pf->serv_tmr, jiffies + msecs_to_jiffies(100));
+}
+
/**
* ice_service_task - manage and run subtasks
* @work: pointer to work_struct contained by the PF struct
@@ -2327,9 +2385,11 @@ static void ice_service_task(struct work_struct *work)
struct ice_pf *pf = container_of(work, struct ice_pf, serv_task);
unsigned long start_time = jiffies;
- /* subtasks */
+ if (pf->health_reporters.tx_hang_buf.tx_ring) {
+ ice_report_tx_hang(pf);
+ pf->health_reporters.tx_hang_buf.tx_ring = NULL;
+ }
- /* process reset requests first */
ice_reset_subtask(pf);
/* bail if a reset/recovery cycle is pending or rebuild failed */
@@ -2570,7 +2630,7 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
}
/* assign the mask for this irq */
- irq_set_affinity_hint(irq_num, &q_vector->affinity_mask);
+ irq_update_affinity_hint(irq_num, &q_vector->affinity_mask);
}
err = ice_set_cpu_rx_rmap(vsi);
@@ -2588,7 +2648,7 @@ free_q_irqs:
irq_num = vsi->q_vectors[vector]->irq.virq;
if (!IS_ENABLED(CONFIG_RFS_ACCEL))
irq_set_affinity_notifier(irq_num, NULL);
- irq_set_affinity_hint(irq_num, NULL);
+ irq_update_affinity_hint(irq_num, NULL);
devm_free_irq(dev, irq_num, &vsi->q_vectors[vector]);
}
return err;
@@ -2670,17 +2730,72 @@ static void ice_vsi_assign_bpf_prog(struct ice_vsi *vsi, struct bpf_prog *prog)
bpf_prog_put(old_prog);
}
+static struct ice_tx_ring *ice_xdp_ring_from_qid(struct ice_vsi *vsi, int qid)
+{
+ struct ice_q_vector *q_vector;
+ struct ice_tx_ring *ring;
+
+ if (static_key_enabled(&ice_xdp_locking_key))
+ return vsi->xdp_rings[qid % vsi->num_xdp_txq];
+
+ q_vector = vsi->rx_rings[qid]->q_vector;
+ ice_for_each_tx_ring(ring, q_vector->tx)
+ if (ice_ring_is_xdp(ring))
+ return ring;
+
+ return NULL;
+}
+
+/**
+ * ice_map_xdp_rings - Map XDP rings to interrupt vectors
+ * @vsi: the VSI with XDP rings being configured
+ *
+ * Map XDP rings to interrupt vectors and perform the configuration steps
+ * dependent on the mapping.
+ */
+void ice_map_xdp_rings(struct ice_vsi *vsi)
+{
+ int xdp_rings_rem = vsi->num_xdp_txq;
+ int v_idx, q_idx;
+
+ /* follow the logic from ice_vsi_map_rings_to_vectors */
+ ice_for_each_q_vector(vsi, v_idx) {
+ struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
+ int xdp_rings_per_v, q_id, q_base;
+
+ xdp_rings_per_v = DIV_ROUND_UP(xdp_rings_rem,
+ vsi->num_q_vectors - v_idx);
+ q_base = vsi->num_xdp_txq - xdp_rings_rem;
+
+ for (q_id = q_base; q_id < (q_base + xdp_rings_per_v); q_id++) {
+ struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_id];
+
+ xdp_ring->q_vector = q_vector;
+ xdp_ring->next = q_vector->tx.tx_ring;
+ q_vector->tx.tx_ring = xdp_ring;
+ }
+ xdp_rings_rem -= xdp_rings_per_v;
+ }
+
+ ice_for_each_rxq(vsi, q_idx) {
+ vsi->rx_rings[q_idx]->xdp_ring = ice_xdp_ring_from_qid(vsi,
+ q_idx);
+ ice_tx_xsk_pool(vsi, q_idx);
+ }
+}
+
/**
* ice_prepare_xdp_rings - Allocate, configure and setup Tx rings for XDP
* @vsi: VSI to bring up Tx rings used by XDP
* @prog: bpf program that will be assigned to VSI
+ * @cfg_type: create from scratch or restore the existing configuration
*
* Return 0 on success and negative value on error
*/
-int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog)
+int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog,
+ enum ice_xdp_cfg cfg_type)
{
u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
- int xdp_rings_rem = vsi->num_xdp_txq;
struct ice_pf *pf = vsi->back;
struct ice_qs_cfg xdp_qs_cfg = {
.qs_mutex = &pf->avail_q_mutex,
@@ -2693,8 +2808,7 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog)
.mapping_mode = ICE_VSI_MAP_CONTIG
};
struct device *dev;
- int i, v_idx;
- int status;
+ int status, i;
dev = ice_pf_to_dev(pf);
vsi->xdp_rings = devm_kcalloc(dev, vsi->num_xdp_txq,
@@ -2713,49 +2827,15 @@ int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog)
if (ice_xdp_alloc_setup_rings(vsi))
goto clear_xdp_rings;
- /* follow the logic from ice_vsi_map_rings_to_vectors */
- ice_for_each_q_vector(vsi, v_idx) {
- struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
- int xdp_rings_per_v, q_id, q_base;
-
- xdp_rings_per_v = DIV_ROUND_UP(xdp_rings_rem,
- vsi->num_q_vectors - v_idx);
- q_base = vsi->num_xdp_txq - xdp_rings_rem;
-
- for (q_id = q_base; q_id < (q_base + xdp_rings_per_v); q_id++) {
- struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_id];
-
- xdp_ring->q_vector = q_vector;
- xdp_ring->next = q_vector->tx.tx_ring;
- q_vector->tx.tx_ring = xdp_ring;
- }
- xdp_rings_rem -= xdp_rings_per_v;
- }
-
- ice_for_each_rxq(vsi, i) {
- if (static_key_enabled(&ice_xdp_locking_key)) {
- vsi->rx_rings[i]->xdp_ring = vsi->xdp_rings[i % vsi->num_xdp_txq];
- } else {
- struct ice_q_vector *q_vector = vsi->rx_rings[i]->q_vector;
- struct ice_tx_ring *ring;
-
- ice_for_each_tx_ring(ring, q_vector->tx) {
- if (ice_ring_is_xdp(ring)) {
- vsi->rx_rings[i]->xdp_ring = ring;
- break;
- }
- }
- }
- ice_tx_xsk_pool(vsi, i);
- }
-
/* omit the scheduler update if in reset path; XDP queues will be
* taken into account at the end of ice_vsi_rebuild, where
* ice_cfg_vsi_lan is being called
*/
- if (ice_is_reset_in_progress(pf->state))
+ if (cfg_type == ICE_XDP_CFG_PART)
return 0;
+ ice_map_xdp_rings(vsi);
+
/* tell the Tx scheduler that right now we have
* additional queues
*/
@@ -2805,22 +2885,21 @@ err_map_xdp:
/**
* ice_destroy_xdp_rings - undo the configuration made by ice_prepare_xdp_rings
* @vsi: VSI to remove XDP rings
+ * @cfg_type: disable XDP permanently or allow it to be restored later
*
* Detach XDP rings from irq vectors, clean up the PF bitmap and free
* resources
*/
-int ice_destroy_xdp_rings(struct ice_vsi *vsi)
+int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type)
{
u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 };
struct ice_pf *pf = vsi->back;
int i, v_idx;
/* q_vectors are freed in reset path so there's no point in detaching
- * rings; in case of rebuild being triggered not from reset bits
- * in pf->state won't be set, so additionally check first q_vector
- * against NULL
+ * rings
*/
- if (ice_is_reset_in_progress(pf->state) || !vsi->q_vectors[0])
+ if (cfg_type == ICE_XDP_CFG_PART)
goto free_qmap;
ice_for_each_q_vector(vsi, v_idx) {
@@ -2861,7 +2940,7 @@ free_qmap:
if (static_key_enabled(&ice_xdp_locking_key))
static_branch_dec(&ice_xdp_locking_key);
- if (ice_is_reset_in_progress(pf->state) || !vsi->q_vectors[0])
+ if (cfg_type == ICE_XDP_CFG_PART)
return 0;
ice_vsi_assign_bpf_prog(vsi, NULL);
@@ -2890,7 +2969,7 @@ static void ice_vsi_rx_napi_schedule(struct ice_vsi *vsi)
ice_for_each_rxq(vsi, i) {
struct ice_rx_ring *rx_ring = vsi->rx_rings[i];
- if (rx_ring->xsk_pool)
+ if (READ_ONCE(rx_ring->xsk_pool))
napi_schedule(&rx_ring->q_vector->napi);
}
}
@@ -2910,6 +2989,9 @@ 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)
@@ -2941,8 +3023,8 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
struct netlink_ext_ack *extack)
{
unsigned int frame_size = vsi->netdev->mtu + ICE_ETH_PKT_HDR_PAD;
- bool if_running = netif_running(vsi->netdev);
int ret = 0, xdp_ring_err = 0;
+ bool if_running;
if (prog && !prog->aux->xdp_has_frags) {
if (frame_size > ice_max_xdp_frame_size(vsi)) {
@@ -2953,13 +3035,17 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
}
/* hot swap progs and avoid toggling link */
- if (ice_is_xdp_ena_vsi(vsi) == !!prog) {
+ if (ice_is_xdp_ena_vsi(vsi) == !!prog ||
+ test_bit(ICE_VSI_REBUILD_PENDING, vsi->state)) {
ice_vsi_assign_bpf_prog(vsi, prog);
return 0;
}
+ if_running = netif_running(vsi->netdev) &&
+ !test_and_set_bit(ICE_VSI_DOWN, vsi->state);
+
/* need to stop netdev while setting up the program for Rx rings */
- if (if_running && !test_and_set_bit(ICE_VSI_DOWN, vsi->state)) {
+ if (if_running) {
ret = ice_down(vsi);
if (ret) {
NL_SET_ERR_MSG_MOD(extack, "Preparing device for XDP attach failed");
@@ -2972,7 +3058,8 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
if (xdp_ring_err) {
NL_SET_ERR_MSG_MOD(extack, "Not enough Tx resources for XDP");
} else {
- xdp_ring_err = ice_prepare_xdp_rings(vsi, prog);
+ xdp_ring_err = ice_prepare_xdp_rings(vsi, prog,
+ ICE_XDP_CFG_FULL);
if (xdp_ring_err)
NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Tx resources failed");
}
@@ -2983,7 +3070,7 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
NL_SET_ERR_MSG_MOD(extack, "Setting up XDP Rx resources failed");
} else if (ice_is_xdp_ena_vsi(vsi) && !prog) {
xdp_features_clear_redirect_target(vsi->netdev);
- xdp_ring_err = ice_destroy_xdp_rings(vsi);
+ xdp_ring_err = ice_destroy_xdp_rings(vsi, ICE_XDP_CFG_FULL);
if (xdp_ring_err)
NL_SET_ERR_MSG_MOD(extack, "Freeing XDP Tx resources failed");
/* reallocate Rx queues that were used for zero-copy */
@@ -3020,25 +3107,32 @@ 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;
+ int ret;
- 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;
}
+ mutex_lock(&vsi->xdp_state_lock);
+
switch (xdp->command) {
case XDP_SETUP_PROG:
- return ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack);
+ ret = ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack);
+ break;
case XDP_SETUP_XSK_POOL:
- return ice_xsk_pool_setup(vsi, xdp->xsk.pool,
- xdp->xsk.queue_id);
+ ret = ice_xsk_pool_setup(vsi, xdp->xsk.pool, xdp->xsk.queue_id);
+ break;
default:
- return -EINVAL;
+ ret = -EINVAL;
}
+
+ mutex_unlock(&vsi->xdp_state_lock);
+ return ret;
}
/**
@@ -3480,28 +3574,6 @@ skip_req_irq:
}
/**
- * 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
*/
@@ -3534,7 +3606,7 @@ 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);
@@ -3648,7 +3720,7 @@ ice_pf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
struct ice_vsi_cfg_params params = {};
params.type = ICE_VSI_PF;
- params.pi = pi;
+ params.port_info = pi;
params.flags = ICE_VSI_FLAG_INIT;
return ice_vsi_setup(pf, &params);
@@ -3661,7 +3733,7 @@ ice_chnl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi,
struct ice_vsi_cfg_params params = {};
params.type = ICE_VSI_CHNL;
- params.pi = pi;
+ params.port_info = pi;
params.ch = ch;
params.flags = ICE_VSI_FLAG_INIT;
@@ -3682,7 +3754,7 @@ ice_ctrl_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
struct ice_vsi_cfg_params params = {};
params.type = ICE_VSI_CTRL;
- params.pi = pi;
+ params.port_info = pi;
params.flags = ICE_VSI_FLAG_INIT;
return ice_vsi_setup(pf, &params);
@@ -3702,7 +3774,7 @@ ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi)
struct ice_vsi_cfg_params params = {};
params.type = ICE_VSI_LB;
- params.pi = pi;
+ params.port_info = pi;
params.flags = ICE_VSI_FLAG_INIT;
return ice_vsi_setup(pf, &params);
@@ -3716,8 +3788,7 @@ 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;
@@ -3779,8 +3850,7 @@ finish:
*
* 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;
@@ -3949,6 +4019,9 @@ 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);
}
/**
@@ -4040,7 +4113,14 @@ static int ice_init_pf(struct ice_pf *pf)
mutex_init(&pf->vfs.table_lock);
hash_init(pf->vfs.table);
- ice_mbx_init_snapshot(&pf->hw);
+ if (ice_is_feature_supported(pf, ICE_F_MBX_LIMIT))
+ wr32(&pf->hw, E830_MBX_PF_IN_FLIGHT_VF_MSGS_THRESH,
+ ICE_MBX_OVERFLOW_WATERMARK);
+ else
+ ice_mbx_init_snapshot(&pf->hw);
+
+ xa_init(&pf->dyn_ports);
+ xa_init(&pf->sf_nums);
return 0;
}
@@ -4079,7 +4159,7 @@ bool ice_is_wol_supported(struct ice_hw *hw)
int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked)
{
struct ice_pf *pf = vsi->back;
- int err = 0, timeout = 50;
+ int i, err = 0, timeout = 50;
if (!new_rx && !new_tx)
return -EINVAL;
@@ -4098,15 +4178,32 @@ int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked)
/* set for the next time the netdev is started */
if (!netif_running(vsi->netdev)) {
- ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT);
+ err = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT);
+ if (err)
+ goto rebuild_err;
dev_dbg(ice_pf_to_dev(pf), "Link is down, queue count change happens when link is brought up\n");
goto done;
}
ice_vsi_close(vsi);
- ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT);
+ err = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT);
+ if (err)
+ goto rebuild_err;
+
+ ice_for_each_traffic_class(i) {
+ if (vsi->tc_cfg.ena_tc & BIT(i))
+ netdev_set_tc_queue(vsi->netdev,
+ vsi->tc_cfg.tc_info[i].netdev_tc,
+ vsi->tc_cfg.tc_info[i].qcount_tx,
+ vsi->tc_cfg.tc_info[i].qoffset);
+ }
ice_pf_dcb_recfg(pf, locked);
ice_vsi_open(vsi);
+ goto done;
+
+rebuild_err:
+ dev_err(ice_pf_to_dev(pf), "Error during VSI rebuild: %d. Unload and reload the driver.\n",
+ err);
done:
clear_bit(ICE_CFG_BUSY, pf->state);
return err;
@@ -4417,11 +4514,13 @@ static char *ice_get_opt_fw_name(struct ice_pf *pf)
/**
* ice_request_fw - Device initialization routine
* @pf: pointer to the PF instance
+ * @firmware: double pointer to firmware struct
+ *
+ * Return: zero when successful, negative values otherwise.
*/
-static void ice_request_fw(struct ice_pf *pf)
+static int ice_request_fw(struct ice_pf *pf, const struct firmware **firmware)
{
char *opt_fw_filename = ice_get_opt_fw_name(pf);
- const struct firmware *firmware = NULL;
struct device *dev = ice_pf_to_dev(pf);
int err = 0;
@@ -4430,29 +4529,120 @@ static void ice_request_fw(struct ice_pf *pf)
* and warning messages for other errors.
*/
if (opt_fw_filename) {
- err = firmware_request_nowarn(&firmware, opt_fw_filename, dev);
- if (err) {
- kfree(opt_fw_filename);
- goto dflt_pkg_load;
- }
-
- /* request for firmware was successful. Download to device */
- ice_load_pkg(firmware, pf);
+ err = firmware_request_nowarn(firmware, opt_fw_filename, dev);
kfree(opt_fw_filename);
- release_firmware(firmware);
- return;
+ if (!err)
+ return err;
+ }
+ err = request_firmware(firmware, ICE_DDP_PKG_FILE, dev);
+ if (err)
+ dev_err(dev, "The DDP package file was not found or could not be read. Entering Safe Mode\n");
+
+ return err;
+}
+
+/**
+ * ice_init_tx_topology - performs Tx topology initialization
+ * @hw: pointer to the hardware structure
+ * @firmware: pointer to firmware structure
+ *
+ * Return: zero when init was successful, negative values otherwise.
+ */
+static int
+ice_init_tx_topology(struct ice_hw *hw, const struct firmware *firmware)
+{
+ u8 num_tx_sched_layers = hw->num_tx_sched_layers;
+ struct ice_pf *pf = hw->back;
+ struct device *dev;
+ int err;
+
+ dev = ice_pf_to_dev(pf);
+ err = ice_cfg_tx_topo(hw, firmware->data, firmware->size);
+ if (!err) {
+ if (hw->num_tx_sched_layers > num_tx_sched_layers)
+ dev_info(dev, "Tx scheduling layers switching feature disabled\n");
+ else
+ dev_info(dev, "Tx scheduling layers switching feature enabled\n");
+ /* if there was a change in topology ice_cfg_tx_topo triggered
+ * a CORER and we need to re-init hw
+ */
+ ice_deinit_hw(hw);
+ err = ice_init_hw(hw);
+
+ return err;
+ } else if (err == -EIO) {
+ dev_info(dev, "DDP package does not support Tx scheduling layers switching feature - please update to the latest DDP package and try again\n");
+ }
+
+ return 0;
+}
+
+/**
+ * ice_init_supported_rxdids - Initialize supported Rx descriptor IDs
+ * @hw: pointer to the hardware structure
+ * @pf: pointer to pf structure
+ *
+ * The pf->supported_rxdids bitmap is used to indicate to VFs which descriptor
+ * formats the PF hardware supports. The exact list of supported RXDIDs
+ * depends on the loaded DDP package. The IDs can be determined by reading the
+ * GLFLXP_RXDID_FLAGS register after the DDP package is loaded.
+ *
+ * Note that the legacy 32-byte RXDID 0 is always supported but is not listed
+ * in the DDP package. The 16-byte legacy descriptor is never supported by
+ * VFs.
+ */
+static void ice_init_supported_rxdids(struct ice_hw *hw, struct ice_pf *pf)
+{
+ pf->supported_rxdids = BIT(ICE_RXDID_LEGACY_1);
+
+ for (int i = ICE_RXDID_FLEX_NIC; i < ICE_FLEX_DESC_RXDID_MAX_NUM; i++) {
+ u32 regval;
+
+ regval = rd32(hw, GLFLXP_RXDID_FLAGS(i, 0));
+ if ((regval >> GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S)
+ & GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M)
+ pf->supported_rxdids |= BIT(i);
}
+}
-dflt_pkg_load:
- err = request_firmware(&firmware, ICE_DDP_PKG_FILE, dev);
+/**
+ * ice_init_ddp_config - DDP related configuration
+ * @hw: pointer to the hardware structure
+ * @pf: pointer to pf structure
+ *
+ * This function loads DDP file from the disk, then initializes Tx
+ * topology. At the end DDP package is loaded on the card.
+ *
+ * Return: zero when init was successful, negative values otherwise.
+ */
+static int ice_init_ddp_config(struct ice_hw *hw, struct ice_pf *pf)
+{
+ struct device *dev = ice_pf_to_dev(pf);
+ const struct firmware *firmware = NULL;
+ int err;
+
+ err = ice_request_fw(pf, &firmware);
if (err) {
- dev_err(dev, "The DDP package file was not found or could not be read. Entering Safe Mode\n");
- return;
+ dev_err(dev, "Fail during requesting FW: %d\n", err);
+ return err;
+ }
+
+ err = ice_init_tx_topology(hw, firmware);
+ if (err) {
+ dev_err(dev, "Fail during initialization of Tx topology: %d\n",
+ err);
+ release_firmware(firmware);
+ return err;
}
- /* request for firmware was successful. Download to device */
+ /* Download firmware to device */
ice_load_pkg(firmware, pf);
release_firmware(firmware);
+
+ /* Initialize the supported Rx descriptor IDs after loading DDP */
+ ice_init_supported_rxdids(hw, pf);
+
+ return 0;
}
/**
@@ -4574,64 +4764,21 @@ static void ice_decfg_netdev(struct ice_vsi *vsi)
vsi->netdev = NULL;
}
-/**
- * ice_wait_for_fw - wait for full FW readiness
- * @hw: pointer to the hardware structure
- * @timeout: milliseconds that can elapse before timing out
- */
-static int ice_wait_for_fw(struct ice_hw *hw, u32 timeout)
-{
- int fw_loading;
- u32 elapsed = 0;
-
- while (elapsed <= timeout) {
- fw_loading = rd32(hw, GL_MNG_FWSM) & GL_MNG_FWSM_FW_LOADING_M;
-
- /* firmware was not yet loaded, we have to wait more */
- if (fw_loading) {
- elapsed += 100;
- msleep(100);
- continue;
- }
- return 0;
- }
-
- return -ETIMEDOUT;
-}
-
int ice_init_dev(struct ice_pf *pf)
{
struct device *dev = ice_pf_to_dev(pf);
struct ice_hw *hw = &pf->hw;
int err;
- err = ice_init_hw(hw);
- if (err) {
- dev_err(dev, "ice_init_hw failed: %d\n", err);
- return err;
- }
-
- /* Some cards require longer initialization times
- * due to necessity of loading FW from an external source.
- * This can take even half a minute.
- */
- if (ice_is_pf_c827(hw)) {
- err = ice_wait_for_fw(hw, 30000);
- if (err) {
- dev_err(dev, "ice_wait_for_fw timed out");
- return err;
- }
- }
-
ice_init_feature_support(pf);
- ice_request_fw(pf);
+ err = ice_init_ddp_config(hw, pf);
- /* if ice_request_fw fails, ICE_FLAG_ADV_FEATURES bit won't be
+ /* if ice_init_ddp_config fails, ICE_FLAG_ADV_FEATURES bit won't be
* set in pf->state, which will cause ice_is_safe_mode to return
* true
*/
- if (ice_is_safe_mode(pf)) {
+ if (err || ice_is_safe_mode(pf)) {
/* we already got function/device capabilities but these don't
* reflect what the driver needs to do in safe mode. Instead of
* adding conditional logic everywhere to ignore these
@@ -4643,7 +4790,7 @@ int ice_init_dev(struct ice_pf *pf)
err = ice_init_pf(pf);
if (err) {
dev_err(dev, "ice_init_pf failed: %d\n", err);
- goto err_init_pf;
+ return err;
}
pf->hw.udp_tunnel_nic.set_port = ice_udp_tunnel_set_port;
@@ -4667,7 +4814,7 @@ int ice_init_dev(struct ice_pf *pf)
if (err) {
dev_err(dev, "ice_init_interrupt_scheme failed: %d\n", err);
err = -EIO;
- goto err_init_interrupt_scheme;
+ goto unroll_pf_init;
}
/* In case of MSIX we are going to setup the misc vector right here
@@ -4678,17 +4825,15 @@ int ice_init_dev(struct ice_pf *pf)
err = ice_req_irq_msix_misc(pf);
if (err) {
dev_err(dev, "setup of misc vector failed: %d\n", err);
- goto err_req_irq_msix_misc;
+ goto unroll_irq_scheme_init;
}
return 0;
-err_req_irq_msix_misc:
+unroll_irq_scheme_init:
ice_clear_interrupt_scheme(pf);
-err_init_interrupt_scheme:
+unroll_pf_init:
ice_deinit_pf(pf);
-err_init_pf:
- ice_deinit_hw(hw);
return err;
}
@@ -4920,6 +5065,7 @@ static int ice_init_devlink(struct ice_pf *pf)
return err;
ice_devlink_init_regions(pf);
+ ice_health_init(pf);
ice_devlink_register(pf);
return 0;
@@ -4928,6 +5074,7 @@ static int ice_init_devlink(struct ice_pf *pf)
static void ice_deinit_devlink(struct ice_pf *pf)
{
ice_devlink_unregister(pf);
+ ice_health_deinit(pf);
ice_devlink_destroy_regions(pf);
ice_devlink_unregister_params(pf);
}
@@ -5082,6 +5229,36 @@ void ice_unload(struct ice_pf *pf)
ice_decfg_netdev(vsi);
}
+static int ice_probe_recovery_mode(struct ice_pf *pf)
+{
+ struct device *dev = ice_pf_to_dev(pf);
+ int err;
+
+ dev_err(dev, "Firmware recovery mode detected. Limiting functionality. Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode\n");
+
+ INIT_HLIST_HEAD(&pf->aq_wait_list);
+ spin_lock_init(&pf->aq_wait_lock);
+ init_waitqueue_head(&pf->aq_wait_queue);
+
+ timer_setup(&pf->serv_tmr, ice_service_timer, 0);
+ pf->serv_tmr_period = HZ;
+ INIT_WORK(&pf->serv_task, ice_service_task_recovery_mode);
+ clear_bit(ICE_SERVICE_SCHED, pf->state);
+ err = ice_create_all_ctrlq(&pf->hw);
+ if (err)
+ return err;
+
+ scoped_guard(devl, priv_to_devlink(pf)) {
+ err = ice_init_devlink(pf);
+ if (err)
+ return err;
+ }
+
+ ice_service_task_restart(pf);
+
+ return 0;
+}
+
/**
* ice_probe - Device initialization routine
* @pdev: PCI device information struct
@@ -5093,6 +5270,7 @@ static int
ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
{
struct device *dev = &pdev->dev;
+ struct ice_adapter *adapter;
struct ice_pf *pf;
struct ice_hw *hw;
int err;
@@ -5144,7 +5322,6 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
}
pci_set_master(pdev);
-
pf->pdev = pdev;
pci_set_drvdata(pdev, pf);
set_bit(ICE_DOWN, pf->state);
@@ -5173,30 +5350,47 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
hw->debug_mask = debug;
#endif
+ if (ice_is_recovery_mode(hw))
+ return ice_probe_recovery_mode(pf);
+
+ err = ice_init_hw(hw);
+ if (err) {
+ dev_err(dev, "ice_init_hw failed: %d\n", err);
+ return err;
+ }
+
+ adapter = ice_adapter_get(pdev);
+ if (IS_ERR(adapter)) {
+ err = PTR_ERR(adapter);
+ goto unroll_hw_init;
+ }
+ pf->adapter = adapter;
+
err = ice_init(pf);
if (err)
- goto err_init;
+ goto unroll_adapter;
devl_lock(priv_to_devlink(pf));
err = ice_load(pf);
- devl_unlock(priv_to_devlink(pf));
if (err)
- goto err_load;
+ goto unroll_init;
err = ice_init_devlink(pf);
if (err)
- goto err_init_devlink;
+ goto unroll_load;
+ devl_unlock(priv_to_devlink(pf));
return 0;
-err_init_devlink:
- devl_lock(priv_to_devlink(pf));
+unroll_load:
ice_unload(pf);
+unroll_init:
devl_unlock(priv_to_devlink(pf));
-err_load:
ice_deinit(pf);
-err_init:
- pci_disable_device(pdev);
+unroll_adapter:
+ ice_adapter_put(pdev);
+unroll_hw_init:
+ ice_deinit_hw(hw);
return err;
}
@@ -5276,6 +5470,14 @@ static void ice_remove(struct pci_dev *pdev)
msleep(100);
}
+ if (ice_is_recovery_mode(&pf->hw)) {
+ ice_service_task_stop(pf);
+ scoped_guard(devl, priv_to_devlink(pf)) {
+ ice_deinit_devlink(pf);
+ }
+ return;
+ }
+
if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) {
set_bit(ICE_VF_RESETS_DISABLED, pf->state);
ice_free_vfs(pf);
@@ -5290,9 +5492,10 @@ static void ice_remove(struct pci_dev *pdev)
if (!ice_is_safe_mode(pf))
ice_remove_arfs(pf);
+ devl_lock(priv_to_devlink(pf));
+ ice_dealloc_all_dynamic_ports(pf);
ice_deinit_devlink(pf);
- devl_lock(priv_to_devlink(pf));
ice_unload(pf);
devl_unlock(priv_to_devlink(pf));
@@ -5302,7 +5505,7 @@ static void ice_remove(struct pci_dev *pdev)
ice_setup_mc_magic_wake(pf);
ice_set_wake(pf);
- pci_disable_device(pdev);
+ ice_adapter_put(pdev);
}
/**
@@ -5321,7 +5524,6 @@ static void ice_shutdown(struct pci_dev *pdev)
}
}
-#ifdef CONFIG_PM
/**
* ice_prepare_for_shutdown - prep for PCI shutdown
* @pf: board private structure
@@ -5346,7 +5548,7 @@ static void ice_prepare_for_shutdown(struct ice_pf *pf)
if (pf->vsi[v])
pf->vsi[v]->vsi_num = 0;
- ice_shutdown_all_ctrlq(hw);
+ ice_shutdown_all_ctrlq(hw, true);
}
/**
@@ -5383,7 +5585,9 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf)
if (ret)
goto err_reinit;
ice_vsi_map_rings_to_vectors(pf->vsi[v]);
+ rtnl_lock();
ice_vsi_set_napi_queues(pf->vsi[v]);
+ rtnl_unlock();
}
ret = ice_req_irq_msix_misc(pf);
@@ -5397,8 +5601,12 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf)
err_reinit:
while (v--)
- if (pf->vsi[v])
+ if (pf->vsi[v]) {
+ rtnl_lock();
+ ice_vsi_clear_napi_queues(pf->vsi[v]);
+ rtnl_unlock();
ice_vsi_free_q_vectors(pf->vsi[v]);
+ }
return ret;
}
@@ -5410,7 +5618,7 @@ err_reinit:
* Power Management callback to quiesce the device and prepare
* for D3 transition.
*/
-static int __maybe_unused ice_suspend(struct device *dev)
+static int ice_suspend(struct device *dev)
{
struct pci_dev *pdev = to_pci_dev(dev);
struct ice_pf *pf;
@@ -5431,7 +5639,7 @@ static int __maybe_unused ice_suspend(struct device *dev)
*/
disabled = ice_service_task_stop(pf);
- ice_unplug_aux_dev(pf);
+ ice_deinit_rdma(pf);
/* Already suspended?, then there is nothing to do */
if (test_and_set_bit(ICE_SUSPENDED, pf->state)) {
@@ -5463,6 +5671,9 @@ static int __maybe_unused ice_suspend(struct device *dev)
ice_for_each_vsi(pf, v) {
if (!pf->vsi[v])
continue;
+ rtnl_lock();
+ ice_vsi_clear_napi_queues(pf->vsi[v]);
+ rtnl_unlock();
ice_vsi_free_q_vectors(pf->vsi[v]);
}
ice_clear_interrupt_scheme(pf);
@@ -5477,7 +5688,7 @@ static int __maybe_unused ice_suspend(struct device *dev)
* ice_resume - PM callback for waking up from D3
* @dev: generic device information structure
*/
-static int __maybe_unused ice_resume(struct device *dev)
+static int ice_resume(struct device *dev)
{
struct pci_dev *pdev = to_pci_dev(dev);
enum ice_reset_req reset_type;
@@ -5511,6 +5722,11 @@ static int __maybe_unused ice_resume(struct device *dev)
if (ret)
dev_err(dev, "Cannot restore interrupt scheme: %d\n", ret);
+ ret = ice_init_rdma(pf);
+ if (ret)
+ dev_err(dev, "Reinitialize RDMA during resume failed: %d\n",
+ ret);
+
clear_bit(ICE_DOWN, pf->state);
/* Now perform PF reset and rebuild */
reset_type = ICE_RESET_PFR;
@@ -5528,7 +5744,6 @@ static int __maybe_unused ice_resume(struct device *dev)
return 0;
}
-#endif /* CONFIG_PM */
/**
* ice_pci_err_detected - warning that PCI error has been detected
@@ -5693,16 +5908,22 @@ static const struct pci_device_id ice_pci_tbl[] = {
{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E825C_QSFP), },
{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E825C_SFP), },
{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E825C_SGMII), },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_BACKPLANE) },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_QSFP56) },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_SFP) },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_SFP_DD) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830CC_BACKPLANE) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830CC_QSFP56) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830CC_SFP) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830CC_SFP_DD) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830C_BACKPLANE), },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_XXV_BACKPLANE), },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830C_QSFP), },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_XXV_QSFP), },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830C_SFP), },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E830_XXV_SFP), },
/* required last entry */
{}
};
MODULE_DEVICE_TABLE(pci, ice_pci_tbl);
-static __maybe_unused SIMPLE_DEV_PM_OPS(ice_pm_ops, ice_suspend, ice_resume);
+static DEFINE_SIMPLE_DEV_PM_OPS(ice_pm_ops, ice_suspend, ice_resume);
static const struct pci_error_handlers ice_pci_err_handler = {
.error_detected = ice_pci_err_detected,
@@ -5717,9 +5938,7 @@ static struct pci_driver ice_driver = {
.id_table = ice_pci_tbl,
.probe = ice_probe,
.remove = ice_remove,
-#ifdef CONFIG_PM
- .driver.pm = &ice_pm_ops,
-#endif /* CONFIG_PM */
+ .driver.pm = pm_sleep_ptr(&ice_pm_ops),
.shutdown = ice_shutdown,
.sriov_configure = ice_sriov_configure,
.sriov_get_vf_total_msix = ice_sriov_get_vf_total_msix,
@@ -5742,7 +5961,7 @@ static int __init ice_module_init(void)
ice_adv_lnk_speed_maps_init();
- ice_wq = alloc_workqueue("%s", 0, 0, KBUILD_MODNAME);
+ ice_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, KBUILD_MODNAME);
if (!ice_wq) {
pr_err("Failed to create workqueue\n");
return status;
@@ -5762,8 +5981,16 @@ 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();
@@ -5781,6 +6008,7 @@ 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);
@@ -5958,12 +6186,14 @@ ice_set_tx_maxrate(struct net_device *netdev, int queue_index, u32 maxrate)
* @addr: the MAC address entry being added
* @vid: VLAN ID
* @flags: instructions from stack about fdb operation
+ * @notified: whether notification was emitted
* @extack: netlink extended ack
*/
static int
ice_fdb_add(struct ndmsg *ndm, struct nlattr __always_unused *tb[],
struct net_device *dev, const unsigned char *addr, u16 vid,
- u16 flags, struct netlink_ext_ack __always_unused *extack)
+ u16 flags, bool *notified,
+ struct netlink_ext_ack __always_unused *extack)
{
int err;
@@ -5997,12 +6227,14 @@ ice_fdb_add(struct ndmsg *ndm, struct nlattr __always_unused *tb[],
* @dev: the net device pointer
* @addr: the MAC address entry being added
* @vid: VLAN ID
+ * @notified: whether notification was emitted
* @extack: netlink extended ack
*/
static int
ice_fdb_del(struct ndmsg *ndm, __always_unused struct nlattr *tb[],
struct net_device *dev, const unsigned char *addr,
- __always_unused u16 vid, struct netlink_ext_ack *extack)
+ __always_unused u16 vid, bool *notified,
+ struct netlink_ext_ack *extack)
{
int err;
@@ -6206,10 +6438,12 @@ ice_set_vlan_filtering_features(struct ice_vsi *vsi, netdev_features_t features)
int err = 0;
/* support Single VLAN Mode (SVM) and Double VLAN Mode (DVM) by checking
- * if either bit is set
+ * if either bit is set. In switchdev mode Rx filtering should never be
+ * enabled.
*/
- if (features &
- (NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER))
+ if ((features &
+ (NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_STAG_FILTER)) &&
+ !ice_is_eswitch_mode_switchdev(vsi->back))
err = vlan_ops->ena_rx_filtering(vsi);
else
err = vlan_ops->dis_rx_filtering(vsi);
@@ -6357,8 +6591,7 @@ ice_set_features(struct net_device *netdev, netdev_features_t features)
if (changed & NETIF_F_HW_TC) {
bool ena = !!(features & NETIF_F_HW_TC);
- ena ? set_bit(ICE_FLAG_CLS_FLOWER, pf->flags) :
- clear_bit(ICE_FLAG_CLS_FLOWER, pf->flags);
+ assign_bit(ICE_FLAG_CLS_FLOWER, pf->flags, ena);
}
if (changed & NETIF_F_LOOPBACK)
@@ -6582,11 +6815,12 @@ 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->type == ICE_VSI_SF)))) {
ice_print_link_msg(vsi, true);
netif_tx_start_all_queues(vsi->netdev);
netif_carrier_on(vsi->netdev);
- ice_ptp_link_change(pf, pf->hw.pf_id, true);
+ ice_ptp_link_change(pf, true);
}
/* Perform an initial read of the statistics registers now to
@@ -6940,7 +7174,6 @@ 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);
@@ -7055,13 +7288,11 @@ int ice_down(struct ice_vsi *vsi)
WARN_ON(!test_bit(ICE_VSI_DOWN, vsi->state));
- if (vsi->netdev && vsi->type == ICE_VSI_PF) {
+ if (vsi->netdev) {
vlan_err = ice_vsi_del_vlan_zero(vsi);
- ice_ptp_link_change(vsi->back, vsi->back->hw.pf_id, false);
+ ice_ptp_link_change(vsi->back, false);
netif_carrier_off(vsi->netdev);
netif_tx_disable(vsi->netdev);
- } else if (vsi->type == ICE_VSI_SWITCHDEV_CTRL) {
- ice_eswitch_stop_all_tx_queues(vsi->back);
}
ice_vsi_dis_irq(vsi);
@@ -7070,7 +7301,7 @@ int ice_down(struct ice_vsi *vsi)
if (tx_err)
netdev_err(vsi->netdev, "Failed stop Tx rings, VSI %d error %d\n",
vsi->vsi_num, tx_err);
- if (!tx_err && ice_is_xdp_ena_vsi(vsi)) {
+ if (!tx_err && vsi->xdp_rings) {
tx_err = ice_vsi_stop_xdp_tx_rings(vsi);
if (tx_err)
netdev_err(vsi->netdev, "Failed stop XDP rings, VSI %d error %d\n",
@@ -7087,7 +7318,7 @@ int ice_down(struct ice_vsi *vsi)
ice_for_each_txq(vsi, i)
ice_clean_tx_ring(vsi->tx_rings[i]);
- if (ice_is_xdp_ena_vsi(vsi))
+ if (vsi->xdp_rings)
ice_for_each_xdp_txq(vsi, i)
ice_clean_tx_ring(vsi->xdp_rings[i]);
@@ -7283,7 +7514,7 @@ 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)
@@ -7292,6 +7523,8 @@ int ice_vsi_open(struct ice_vsi *vsi)
err = netif_set_real_num_rx_queues(vsi->netdev, vsi->num_rxq);
if (err)
goto err_set_qs;
+
+ ice_vsi_set_napi_queues(vsi);
}
err = ice_up_complete(vsi);
@@ -7429,6 +7662,7 @@ static void ice_update_pf_netdev_link(struct ice_pf *pf)
*/
static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
{
+ struct ice_vsi *vsi = ice_get_main_vsi(pf);
struct device *dev = ice_pf_to_dev(pf);
struct ice_hw *hw = &pf->hw;
bool dvm;
@@ -7544,12 +7778,6 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
goto err_vsi_rebuild;
}
- err = ice_eswitch_rebuild(pf);
- if (err) {
- dev_err(dev, "Switchdev rebuild failed: %d\n", err);
- goto err_vsi_rebuild;
- }
-
if (reset_type == ICE_RESET_PFR) {
err = ice_rebuild_channels(pf);
if (err) {
@@ -7577,6 +7805,9 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
ice_rebuild_arfs(pf);
}
+ if (vsi && vsi->netdev)
+ netif_device_attach(vsi->netdev);
+
ice_update_pf_netdev_link(pf);
/* tell the firmware we are up */
@@ -7592,6 +7823,8 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
/* if we get here, reset flow is successful */
clear_bit(ICE_RESET_FAILED, pf->state);
+ ice_health_clear(pf);
+
ice_plug_aux_dev(pf);
if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG))
ice_lag_rebuild(pf);
@@ -7604,7 +7837,7 @@ err_vsi_rebuild:
err_sched_init_port:
ice_sched_cleanup_all(hw);
err_init_ctrlq:
- ice_shutdown_all_ctrlq(hw);
+ ice_shutdown_all_ctrlq(hw, false);
set_bit(ICE_RESET_FAILED, pf->state);
clear_recovery:
/* set this bit in PF state to control service task scheduling */
@@ -7619,7 +7852,7 @@ clear_recovery:
*
* 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;
@@ -7666,7 +7899,7 @@ static int ice_change_mtu(struct net_device *netdev, int new_mtu)
return -EBUSY;
}
- netdev->mtu = (unsigned int)new_mtu;
+ WRITE_ONCE(netdev->mtu, (unsigned int)new_mtu);
err = ice_down_up(vsi);
if (err)
return err;
@@ -7999,12 +8232,9 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
if (!br_spec)
return -EINVAL;
- nla_for_each_nested(attr, br_spec, rem) {
- __u16 mode;
+ nla_for_each_nested_type(attr, IFLA_BRIDGE_MODE, br_spec, rem) {
+ __u16 mode = nla_get_u16(attr);
- if (nla_type(attr) != IFLA_BRIDGE_MODE)
- continue;
- mode = nla_get_u16(attr);
if (mode != BRIDGE_MODE_VEPA && mode != BRIDGE_MODE_VEB)
return -EINVAL;
/* Continue if bridge mode is not being flipped */
@@ -8046,7 +8276,7 @@ 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;
@@ -8085,16 +8315,18 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue)
if (tx_ring) {
struct ice_hw *hw = &pf->hw;
- u32 head, val = 0;
+ u32 head, intr = 0;
head = FIELD_GET(QTX_COMM_HEAD_HEAD_M,
rd32(hw, QTX_COMM_HEAD(vsi->txq_map[txqueue])));
/* Read interrupt register */
- val = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->reg_idx));
+ intr = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->reg_idx));
netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %u, NTC: 0x%x, HW_HEAD: 0x%x, NTU: 0x%x, INT: 0x%x\n",
vsi->vsi_num, txqueue, tx_ring->next_to_clean,
- head, tx_ring->next_to_use, val);
+ head, tx_ring->next_to_use, intr);
+
+ ice_prep_tx_hang_report(pf, tx_ring, vsi->vsi_num, head, intr);
}
pf->tx_timeout_last_recovery = jiffies;
generated by cgit (git 2.34.1) at 2025-03-22 11:49:13 +0000