aboutsummaryrefslogtreecommitdiff
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.c1235
1 files changed, 836 insertions, 399 deletions
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index b40dfe6ae321..1766230abfff 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -1,18 +1,21 @@
// SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) 2018, Intel Corporation. */
+/* Copyright (c) 2018-2023, Intel Corporation. */
/* Intel(R) Ethernet Connection E800 Series Linux Driver */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <generated/utsrelease.h>
+#include <linux/crash_dump.h>
#include "ice.h"
#include "ice_base.h"
#include "ice_lib.h"
#include "ice_fltr.h"
#include "ice_dcb_lib.h"
#include "ice_dcb_nl.h"
-#include "ice_devlink.h"
+#include "devlink/devlink.h"
+#include "devlink/devlink_port.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
* ice driver.
@@ -34,6 +37,7 @@ static const char ice_copyright[] = "Copyright (c) 2018, Intel Corporation.";
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);
@@ -64,6 +68,7 @@ struct device *ice_hw_to_dev(struct ice_hw *hw)
}
static struct workqueue_struct *ice_wq;
+struct workqueue_struct *ice_lag_wq;
static const struct net_device_ops ice_netdev_safe_mode_ops;
static const struct net_device_ops ice_netdev_ops;
@@ -80,7 +85,7 @@ ice_indr_setup_tc_cb(struct net_device *netdev, struct Qdisc *sch,
void *data,
void (*cleanup)(struct flow_block_cb *block_cb));
-bool netif_is_ice(struct net_device *dev)
+bool netif_is_ice(const struct net_device *dev)
{
return dev && (dev->netdev_ops == &ice_netdev_ops);
}
@@ -610,7 +615,7 @@ skip:
ice_pf_dis_all_vsi(pf, false);
if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags))
- ice_ptp_prepare_for_reset(pf);
+ ice_ptp_prepare_for_reset(pf, reset_type);
if (ice_is_feature_supported(pf, ICE_F_GNSS))
ice_gnss_exit(pf);
@@ -635,6 +640,11 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
dev_dbg(dev, "reset_type 0x%x requested\n", reset_type);
+ if (pf->lag && pf->lag->bonded && reset_type == ICE_RESET_PFR) {
+ dev_dbg(dev, "PFR on a bonded interface, promoting to CORER\n");
+ reset_type = ICE_RESET_CORER;
+ }
+
ice_prepare_for_reset(pf, reset_type);
/* trigger the reset */
@@ -718,8 +728,13 @@ static void ice_reset_subtask(struct ice_pf *pf)
}
/* No pending resets to finish processing. Check for new resets */
- if (test_bit(ICE_PFR_REQ, pf->state))
+ if (test_bit(ICE_PFR_REQ, pf->state)) {
reset_type = ICE_RESET_PFR;
+ if (pf->lag && pf->lag->bonded) {
+ dev_dbg(ice_pf_to_dev(pf), "PFR on a bonded interface, promoting to CORER\n");
+ reset_type = ICE_RESET_CORER;
+ }
+ }
if (test_bit(ICE_CORER_REQ, pf->state))
reset_type = ICE_RESET_CORER;
if (test_bit(ICE_GLOBR_REQ, pf->state))
@@ -790,6 +805,9 @@ 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;
@@ -967,7 +985,7 @@ static void ice_set_dflt_mib(struct ice_pf *pf)
* Octets 13 - 20 are TSA values - leave as zeros
*/
buf[5] = 0x64;
- len = (typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S;
+ len = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen);
offset += len + 2;
tlv = (struct ice_lldp_org_tlv *)
((char *)tlv + sizeof(tlv->typelen) + len);
@@ -1001,7 +1019,7 @@ static void ice_set_dflt_mib(struct ice_pf *pf)
/* Octet 1 left as all zeros - PFC disabled */
buf[0] = 0x08;
- len = (typelen & ICE_LLDP_TLV_LEN_M) >> ICE_LLDP_TLV_LEN_S;
+ len = FIELD_GET(ICE_LLDP_TLV_LEN_M, typelen);
offset += len + 2;
if (ice_aq_set_lldp_mib(hw, mib_type, (void *)lldpmib, offset, NULL))
@@ -1239,64 +1257,89 @@ ice_handle_link_event(struct ice_pf *pf, struct ice_rq_event_info *event)
return status;
}
-enum ice_aq_task_state {
- ICE_AQ_TASK_WAITING = 0,
- ICE_AQ_TASK_COMPLETE,
- ICE_AQ_TASK_CANCELED,
-};
+/**
+ * ice_get_fwlog_data - copy the FW log data from ARQ event
+ * @pf: PF that the FW log event is associated with
+ * @event: event structure containing FW log data
+ */
+static void
+ice_get_fwlog_data(struct ice_pf *pf, struct ice_rq_event_info *event)
+{
+ struct ice_fwlog_data *fwlog;
+ struct ice_hw *hw = &pf->hw;
-struct ice_aq_task {
- struct hlist_node entry;
+ fwlog = &hw->fwlog_ring.rings[hw->fwlog_ring.tail];
- u16 opcode;
- struct ice_rq_event_info *event;
- enum ice_aq_task_state state;
-};
+ memset(fwlog->data, 0, PAGE_SIZE);
+ fwlog->data_size = le16_to_cpu(event->desc.datalen);
+
+ memcpy(fwlog->data, event->msg_buf, fwlog->data_size);
+ ice_fwlog_ring_increment(&hw->fwlog_ring.tail, hw->fwlog_ring.size);
+
+ if (ice_fwlog_ring_full(&hw->fwlog_ring)) {
+ /* the rings are full so bump the head to create room */
+ ice_fwlog_ring_increment(&hw->fwlog_ring.head,
+ hw->fwlog_ring.size);
+ }
+}
/**
- * ice_aq_wait_for_event - Wait for an AdminQ event from firmware
+ * ice_aq_prep_for_event - Prepare to wait for an AdminQ event from firmware
* @pf: pointer to the PF private structure
+ * @task: intermediate helper storage and identifier for waiting
* @opcode: the opcode to wait for
- * @timeout: how long to wait, in jiffies
- * @event: storage for the event info
*
- * Waits for a specific AdminQ completion event on the ARQ for a given PF. The
- * current thread will be put to sleep until the specified event occurs or
- * until the given timeout is reached.
+ * Prepares to wait for a specific AdminQ completion event on the ARQ for
+ * a given PF. Actual wait would be done by a call to ice_aq_wait_for_event().
*
- * To obtain only the descriptor contents, pass an event without an allocated
- * msg_buf. If the complete data buffer is desired, allocate the
- * event->msg_buf with enough space ahead of time.
+ * Calls are separated to allow caller registering for event before sending
+ * the command, which mitigates a race between registering and FW responding.
*
- * Returns: zero on success, or a negative error code on failure.
+ * To obtain only the descriptor contents, pass an task->event with null
+ * msg_buf. If the complete data buffer is desired, allocate the
+ * task->event.msg_buf with enough space ahead of time.
*/
-int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout,
- struct ice_rq_event_info *event)
+void ice_aq_prep_for_event(struct ice_pf *pf, struct ice_aq_task *task,
+ u16 opcode)
{
- struct device *dev = ice_pf_to_dev(pf);
- struct ice_aq_task *task;
- unsigned long start;
- long ret;
- int err;
-
- task = kzalloc(sizeof(*task), GFP_KERNEL);
- if (!task)
- return -ENOMEM;
-
INIT_HLIST_NODE(&task->entry);
task->opcode = opcode;
- task->event = event;
task->state = ICE_AQ_TASK_WAITING;
spin_lock_bh(&pf->aq_wait_lock);
hlist_add_head(&task->entry, &pf->aq_wait_list);
spin_unlock_bh(&pf->aq_wait_lock);
+}
- start = jiffies;
+/**
+ * ice_aq_wait_for_event - Wait for an AdminQ event from firmware
+ * @pf: pointer to the PF private structure
+ * @task: ptr prepared by ice_aq_prep_for_event()
+ * @timeout: how long to wait, in jiffies
+ *
+ * Waits for a specific AdminQ completion event on the ARQ for a given PF. The
+ * current thread will be put to sleep until the specified event occurs or
+ * until the given timeout is reached.
+ *
+ * Returns: zero on success, or a negative error code on failure.
+ */
+int ice_aq_wait_for_event(struct ice_pf *pf, struct ice_aq_task *task,
+ unsigned long timeout)
+{
+ enum ice_aq_task_state *state = &task->state;
+ struct device *dev = ice_pf_to_dev(pf);
+ unsigned long start = jiffies;
+ long ret;
+ int err;
- ret = wait_event_interruptible_timeout(pf->aq_wait_queue, task->state,
+ ret = wait_event_interruptible_timeout(pf->aq_wait_queue,
+ *state != ICE_AQ_TASK_WAITING,
timeout);
- switch (task->state) {
+ switch (*state) {
+ case ICE_AQ_TASK_NOT_PREPARED:
+ WARN(1, "call to %s without ice_aq_prep_for_event()", __func__);
+ err = -EINVAL;
+ break;
case ICE_AQ_TASK_WAITING:
err = ret < 0 ? ret : -ETIMEDOUT;
break;
@@ -1307,7 +1350,7 @@ int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout,
err = ret < 0 ? ret : 0;
break;
default:
- WARN(1, "Unexpected AdminQ wait task state %u", task->state);
+ WARN(1, "Unexpected AdminQ wait task state %u", *state);
err = -EINVAL;
break;
}
@@ -1315,12 +1358,11 @@ int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout,
dev_dbg(dev, "Waited %u msecs (max %u msecs) for firmware response to op 0x%04x\n",
jiffies_to_msecs(jiffies - start),
jiffies_to_msecs(timeout),
- opcode);
+ task->opcode);
spin_lock_bh(&pf->aq_wait_lock);
hlist_del(&task->entry);
spin_unlock_bh(&pf->aq_wait_lock);
- kfree(task);
return err;
}
@@ -1346,23 +1388,26 @@ int ice_aq_wait_for_event(struct ice_pf *pf, u16 opcode, unsigned long timeout,
static void ice_aq_check_events(struct ice_pf *pf, u16 opcode,
struct ice_rq_event_info *event)
{
+ struct ice_rq_event_info *task_ev;
struct ice_aq_task *task;
bool found = false;
spin_lock_bh(&pf->aq_wait_lock);
hlist_for_each_entry(task, &pf->aq_wait_list, entry) {
- if (task->state || task->opcode != opcode)
+ if (task->state != ICE_AQ_TASK_WAITING)
+ continue;
+ if (task->opcode != opcode)
continue;
- memcpy(&task->event->desc, &event->desc, sizeof(event->desc));
- task->event->msg_len = event->msg_len;
+ task_ev = &task->event;
+ memcpy(&task_ev->desc, &event->desc, sizeof(event->desc));
+ task_ev->msg_len = event->msg_len;
/* Only copy the data buffer if a destination was set */
- if (task->event->msg_buf &&
- task->event->buf_len > event->buf_len) {
- memcpy(task->event->msg_buf, event->msg_buf,
+ if (task_ev->msg_buf && task_ev->buf_len >= event->buf_len) {
+ memcpy(task_ev->msg_buf, event->msg_buf,
event->buf_len);
- task->event->buf_len = event->buf_len;
+ task_ev->buf_len = event->buf_len;
}
task->state = ICE_AQ_TASK_COMPLETE;
@@ -1519,8 +1564,8 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
ice_vc_process_vf_msg(pf, &event, &data);
break;
- case ice_aqc_opc_fw_logging:
- ice_output_fw_log(hw, &event.desc, event.msg_buf);
+ case ice_aqc_opc_fw_logs_event:
+ ice_get_fwlog_data(pf, &event);
break;
case ice_aqc_opc_lldp_set_mib_change:
ice_dcb_process_lldp_set_mib_change(pf, &event);
@@ -1609,8 +1654,10 @@ static void ice_clean_sbq_subtask(struct ice_pf *pf)
{
struct ice_hw *hw = &pf->hw;
- /* Nothing to do here if sideband queue is not supported */
- if (!ice_is_sbq_supported(hw)) {
+ /* if mac_type is not generic, sideband is not supported
+ * and there's nothing to do here
+ */
+ if (!ice_is_generic_mac(hw)) {
clear_bit(ICE_SIDEBANDQ_EVENT_PENDING, pf->state);
return;
}
@@ -1703,6 +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
*
@@ -1731,14 +1811,10 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
/* find what triggered an MDD event */
reg = rd32(hw, GL_MDET_TX_PQM);
if (reg & GL_MDET_TX_PQM_VALID_M) {
- u8 pf_num = (reg & GL_MDET_TX_PQM_PF_NUM_M) >>
- GL_MDET_TX_PQM_PF_NUM_S;
- u16 vf_num = (reg & GL_MDET_TX_PQM_VF_NUM_M) >>
- GL_MDET_TX_PQM_VF_NUM_S;
- u8 event = (reg & GL_MDET_TX_PQM_MAL_TYPE_M) >>
- GL_MDET_TX_PQM_MAL_TYPE_S;
- u16 queue = ((reg & GL_MDET_TX_PQM_QNUM_M) >>
- GL_MDET_TX_PQM_QNUM_S);
+ u8 pf_num = FIELD_GET(GL_MDET_TX_PQM_PF_NUM_M, reg);
+ u16 vf_num = FIELD_GET(GL_MDET_TX_PQM_VF_NUM_M, reg);
+ u8 event = FIELD_GET(GL_MDET_TX_PQM_MAL_TYPE_M, reg);
+ u16 queue = FIELD_GET(GL_MDET_TX_PQM_QNUM_M, reg);
if (netif_msg_tx_err(pf))
dev_info(dev, "Malicious Driver Detection event %d on TX queue %d PF# %d VF# %d\n",
@@ -1746,33 +1822,25 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
wr32(hw, GL_MDET_TX_PQM, 0xffffffff);
}
- reg = rd32(hw, GL_MDET_TX_TCLAN);
+ reg = rd32(hw, GL_MDET_TX_TCLAN_BY_MAC(hw));
if (reg & GL_MDET_TX_TCLAN_VALID_M) {
- u8 pf_num = (reg & GL_MDET_TX_TCLAN_PF_NUM_M) >>
- GL_MDET_TX_TCLAN_PF_NUM_S;
- u16 vf_num = (reg & GL_MDET_TX_TCLAN_VF_NUM_M) >>
- GL_MDET_TX_TCLAN_VF_NUM_S;
- u8 event = (reg & GL_MDET_TX_TCLAN_MAL_TYPE_M) >>
- GL_MDET_TX_TCLAN_MAL_TYPE_S;
- u16 queue = ((reg & GL_MDET_TX_TCLAN_QNUM_M) >>
- GL_MDET_TX_TCLAN_QNUM_S);
+ u8 pf_num = FIELD_GET(GL_MDET_TX_TCLAN_PF_NUM_M, reg);
+ u16 vf_num = FIELD_GET(GL_MDET_TX_TCLAN_VF_NUM_M, reg);
+ u8 event = FIELD_GET(GL_MDET_TX_TCLAN_MAL_TYPE_M, reg);
+ u16 queue = FIELD_GET(GL_MDET_TX_TCLAN_QNUM_M, reg);
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);
- wr32(hw, GL_MDET_TX_TCLAN, 0xffffffff);
+ wr32(hw, GL_MDET_TX_TCLAN_BY_MAC(hw), U32_MAX);
}
reg = rd32(hw, GL_MDET_RX);
if (reg & GL_MDET_RX_VALID_M) {
- u8 pf_num = (reg & GL_MDET_RX_PF_NUM_M) >>
- GL_MDET_RX_PF_NUM_S;
- u16 vf_num = (reg & GL_MDET_RX_VF_NUM_M) >>
- GL_MDET_RX_VF_NUM_S;
- u8 event = (reg & GL_MDET_RX_MAL_TYPE_M) >>
- GL_MDET_RX_MAL_TYPE_S;
- u16 queue = ((reg & GL_MDET_RX_QNUM_M) >>
- GL_MDET_RX_QNUM_S);
+ u8 pf_num = FIELD_GET(GL_MDET_RX_PF_NUM_M, reg);
+ u16 vf_num = FIELD_GET(GL_MDET_RX_VF_NUM_M, reg);
+ u8 event = FIELD_GET(GL_MDET_RX_MAL_TYPE_M, reg);
+ u16 queue = FIELD_GET(GL_MDET_RX_QNUM_M, reg);
if (netif_msg_rx_err(pf))
dev_info(dev, "Malicious Driver Detection event %d on RX queue %d PF# %d VF# %d\n",
@@ -1788,9 +1856,9 @@ static void ice_handle_mdd_event(struct ice_pf *pf)
dev_info(dev, "Malicious Driver Detection event TX_PQM detected on PF\n");
}
- reg = rd32(hw, PF_MDET_TX_TCLAN);
+ reg = rd32(hw, PF_MDET_TX_TCLAN_BY_MAC(hw));
if (reg & PF_MDET_TX_TCLAN_VALID_M) {
- wr32(hw, PF_MDET_TX_TCLAN, 0xFFFF);
+ wr32(hw, PF_MDET_TX_TCLAN_BY_MAC(hw), 0xffff);
if (netif_msg_tx_err(pf))
dev_info(dev, "Malicious Driver Detection event TX_TCLAN detected on PF\n");
}
@@ -1807,6 +1875,8 @@ 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);
@@ -1815,6 +1885,8 @@ 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));
@@ -1825,6 +1897,8 @@ 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));
@@ -1835,6 +1909,8 @@ 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));
@@ -1846,18 +1922,12 @@ 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);
@@ -2133,7 +2203,7 @@ static int ice_configure_phy(struct ice_vsi *vsi)
/* Ensure we have media as we cannot configure a medialess port */
if (!(phy->link_info.link_info & ICE_AQ_MEDIA_AVAILABLE))
- return -EPERM;
+ return -ENOMEDIUM;
ice_print_topo_conflict(vsi);
@@ -2640,17 +2710,72 @@ 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,
@@ -2663,8 +2788,7 @@ 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,
@@ -2683,49 +2807,15 @@ 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
*/
@@ -2775,22 +2865,21 @@ 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) {
@@ -2831,7 +2920,7 @@ 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);
@@ -2942,7 +3031,8 @@ 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");
}
@@ -2953,7 +3043,7 @@ 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 */
@@ -3018,6 +3108,7 @@ static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp)
static void ice_ena_misc_vector(struct ice_pf *pf)
{
struct ice_hw *hw = &pf->hw;
+ u32 pf_intr_start_offset;
u32 val;
/* Disable anti-spoof detection interrupt to prevent spurious event
@@ -3046,6 +3137,47 @@ static void ice_ena_misc_vector(struct ice_pf *pf)
/* SW_ITR_IDX = 0, but don't change INTENA */
wr32(hw, GLINT_DYN_CTL(pf->oicr_irq.index),
GLINT_DYN_CTL_SW_ITR_INDX_M | GLINT_DYN_CTL_INTENA_MSK_M);
+
+ if (!pf->hw.dev_caps.ts_dev_info.ts_ll_int_read)
+ return;
+ pf_intr_start_offset = rd32(hw, PFINT_ALLOC) & PFINT_ALLOC_FIRST;
+ wr32(hw, GLINT_DYN_CTL(pf->ll_ts_irq.index + pf_intr_start_offset),
+ GLINT_DYN_CTL_SW_ITR_INDX_M | GLINT_DYN_CTL_INTENA_MSK_M);
+}
+
+/**
+ * ice_ll_ts_intr - ll_ts interrupt handler
+ * @irq: interrupt number
+ * @data: pointer to a q_vector
+ */
+static irqreturn_t ice_ll_ts_intr(int __always_unused irq, void *data)
+{
+ struct ice_pf *pf = data;
+ u32 pf_intr_start_offset;
+ struct ice_ptp_tx *tx;
+ unsigned long flags;
+ struct ice_hw *hw;
+ u32 val;
+ u8 idx;
+
+ hw = &pf->hw;
+ tx = &pf->ptp.port.tx;
+ spin_lock_irqsave(&tx->lock, flags);
+ ice_ptp_complete_tx_single_tstamp(tx);
+
+ idx = find_next_bit_wrap(tx->in_use, tx->len,
+ tx->last_ll_ts_idx_read + 1);
+ if (idx != tx->len)
+ ice_ptp_req_tx_single_tstamp(tx, idx);
+ spin_unlock_irqrestore(&tx->lock, flags);
+
+ val = GLINT_DYN_CTL_INTENA_M | GLINT_DYN_CTL_CLEARPBA_M |
+ (ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S);
+ pf_intr_start_offset = rd32(hw, PFINT_ALLOC) & PFINT_ALLOC_FIRST;
+ wr32(hw, GLINT_DYN_CTL(pf->ll_ts_irq.index + pf_intr_start_offset),
+ val);
+
+ return IRQ_HANDLED;
}
/**
@@ -3056,6 +3188,7 @@ static void ice_ena_misc_vector(struct ice_pf *pf)
static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
{
struct ice_pf *pf = (struct ice_pf *)data;
+ irqreturn_t ret = IRQ_HANDLED;
struct ice_hw *hw = &pf->hw;
struct device *dev;
u32 oicr, ena_mask;
@@ -3095,8 +3228,8 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
/* we have a reset warning */
ena_mask &= ~PFINT_OICR_GRST_M;
- reset = (rd32(hw, GLGEN_RSTAT) & GLGEN_RSTAT_RESET_TYPE_M) >>
- GLGEN_RSTAT_RESET_TYPE_S;
+ reset = FIELD_GET(GLGEN_RSTAT_RESET_TYPE_M,
+ rd32(hw, GLGEN_RSTAT));
if (reset == ICE_RESET_CORER)
pf->corer_count++;
@@ -3137,8 +3270,22 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
if (oicr & PFINT_OICR_TSYN_TX_M) {
ena_mask &= ~PFINT_OICR_TSYN_TX_M;
- if (!hw->reset_ongoing)
+ if (ice_pf_state_is_nominal(pf) &&
+ pf->hw.dev_caps.ts_dev_info.ts_ll_int_read) {
+ struct ice_ptp_tx *tx = &pf->ptp.port.tx;
+ unsigned long flags;
+ u8 idx;
+
+ spin_lock_irqsave(&tx->lock, flags);
+ idx = find_next_bit_wrap(tx->in_use, tx->len,
+ tx->last_ll_ts_idx_read + 1);
+ if (idx != tx->len)
+ ice_ptp_req_tx_single_tstamp(tx, idx);
+ spin_unlock_irqrestore(&tx->lock, flags);
+ } else if (ice_ptp_pf_handles_tx_interrupt(pf)) {
set_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread);
+ ret = IRQ_WAKE_THREAD;
+ }
}
if (oicr & PFINT_OICR_TSYN_EVNT_M) {
@@ -3147,14 +3294,14 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
ena_mask &= ~PFINT_OICR_TSYN_EVNT_M;
- if (hw->func_caps.ts_func_info.src_tmr_owned) {
+ if (ice_pf_src_tmr_owned(pf)) {
/* Save EVENTs from GLTSYN register */
pf->ptp.ext_ts_irq |= gltsyn_stat &
(GLTSYN_STAT_EVENT0_M |
GLTSYN_STAT_EVENT1_M |
GLTSYN_STAT_EVENT2_M);
- set_bit(ICE_MISC_THREAD_EXTTS_EVENT, pf->misc_thread);
+ ice_ptp_extts_event(pf);
}
}
@@ -3177,8 +3324,11 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
set_bit(ICE_PFR_REQ, pf->state);
}
}
+ ice_service_task_schedule(pf);
+ if (ret == IRQ_HANDLED)
+ ice_irq_dynamic_ena(hw, NULL, NULL);
- return IRQ_WAKE_THREAD;
+ return ret;
}
/**
@@ -3194,12 +3344,7 @@ static irqreturn_t ice_misc_intr_thread_fn(int __always_unused irq, void *data)
hw = &pf->hw;
if (ice_is_reset_in_progress(pf->state))
- return IRQ_HANDLED;
-
- ice_service_task_schedule(pf);
-
- if (test_and_clear_bit(ICE_MISC_THREAD_EXTTS_EVENT, pf->misc_thread))
- ice_ptp_extts_event(pf);
+ goto skip_irq;
if (test_and_clear_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread)) {
/* Process outstanding Tx timestamps. If there is more work,
@@ -3211,6 +3356,7 @@ static irqreturn_t ice_misc_intr_thread_fn(int __always_unused irq, void *data)
}
}
+skip_irq:
ice_irq_dynamic_ena(hw, NULL, NULL);
return IRQ_HANDLED;
@@ -3241,6 +3387,20 @@ static void ice_dis_ctrlq_interrupts(struct ice_hw *hw)
}
/**
+ * ice_free_irq_msix_ll_ts- Unroll ll_ts vector setup
+ * @pf: board private structure
+ */
+static void ice_free_irq_msix_ll_ts(struct ice_pf *pf)
+{
+ int irq_num = pf->ll_ts_irq.virq;
+
+ synchronize_irq(irq_num);
+ devm_free_irq(ice_pf_to_dev(pf), irq_num, pf);
+
+ ice_free_irq(pf, pf->ll_ts_irq);
+}
+
+/**
* ice_free_irq_msix_misc - Unroll misc vector setup
* @pf: board private structure
*/
@@ -3259,6 +3419,8 @@ static void ice_free_irq_msix_misc(struct ice_pf *pf)
devm_free_irq(ice_pf_to_dev(pf), misc_irq_num, pf);
ice_free_irq(pf, pf->oicr_irq);
+ if (pf->hw.dev_caps.ts_dev_info.ts_ll_int_read)
+ ice_free_irq_msix_ll_ts(pf);
}
/**
@@ -3284,10 +3446,12 @@ static void ice_ena_ctrlq_interrupts(struct ice_hw *hw, u16 reg_idx)
PFINT_MBX_CTL_CAUSE_ENA_M);
wr32(hw, PFINT_MBX_CTL, val);
- /* This enables Sideband queue Interrupt causes */
- val = ((reg_idx & PFINT_SB_CTL_MSIX_INDX_M) |
- PFINT_SB_CTL_CAUSE_ENA_M);
- wr32(hw, PFINT_SB_CTL, val);
+ if (!hw->dev_caps.ts_dev_info.ts_ll_int_read) {
+ /* enable Sideband queue Interrupt causes */
+ val = ((reg_idx & PFINT_SB_CTL_MSIX_INDX_M) |
+ PFINT_SB_CTL_CAUSE_ENA_M);
+ wr32(hw, PFINT_SB_CTL, val);
+ }
ice_flush(hw);
}
@@ -3304,13 +3468,17 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)
{
struct device *dev = ice_pf_to_dev(pf);
struct ice_hw *hw = &pf->hw;
- struct msi_map oicr_irq;
+ u32 pf_intr_start_offset;
+ struct msi_map irq;
int err = 0;
if (!pf->int_name[0])
snprintf(pf->int_name, sizeof(pf->int_name) - 1, "%s-%s:misc",
dev_driver_string(dev), dev_name(dev));
+ if (!pf->int_name_ll_ts[0])
+ snprintf(pf->int_name_ll_ts, sizeof(pf->int_name_ll_ts) - 1,
+ "%s-%s:ll_ts", dev_driver_string(dev), dev_name(dev));
/* Do not request IRQ but do enable OICR interrupt since settings are
* lost during reset. Note that this function is called only during
* rebuild path and not while reset is in progress.
@@ -3319,11 +3487,11 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)
goto skip_req_irq;
/* reserve one vector in irq_tracker for misc interrupts */
- oicr_irq = ice_alloc_irq(pf, false);
- if (oicr_irq.index < 0)
- return oicr_irq.index;
+ irq = ice_alloc_irq(pf, false);
+ if (irq.index < 0)
+ return irq.index;
- pf->oicr_irq = oicr_irq;
+ pf->oicr_irq = irq;
err = devm_request_threaded_irq(dev, pf->oicr_irq.virq, ice_misc_intr,
ice_misc_intr_thread_fn, 0,
pf->int_name, pf);
@@ -3334,10 +3502,34 @@ static int ice_req_irq_msix_misc(struct ice_pf *pf)
return err;
}
+ /* reserve one vector in irq_tracker for ll_ts interrupt */
+ if (!pf->hw.dev_caps.ts_dev_info.ts_ll_int_read)
+ goto skip_req_irq;
+
+ irq = ice_alloc_irq(pf, false);
+ if (irq.index < 0)
+ return irq.index;
+
+ pf->ll_ts_irq = irq;
+ err = devm_request_irq(dev, pf->ll_ts_irq.virq, ice_ll_ts_intr, 0,
+ pf->int_name_ll_ts, pf);
+ if (err) {
+ dev_err(dev, "devm_request_irq for %s failed: %d\n",
+ pf->int_name_ll_ts, err);
+ ice_free_irq(pf, pf->ll_ts_irq);
+ return err;
+ }
+
skip_req_irq:
ice_ena_misc_vector(pf);
ice_ena_ctrlq_interrupts(hw, pf->oicr_irq.index);
+ /* This enables LL TS interrupt */
+ pf_intr_start_offset = rd32(hw, PFINT_ALLOC) & PFINT_ALLOC_FIRST;
+ if (pf->hw.dev_caps.ts_dev_info.ts_ll_int_read)
+ wr32(hw, PFINT_SB_CTL,
+ ((pf->ll_ts_irq.index + pf_intr_start_offset) &
+ PFINT_SB_CTL_MSIX_INDX_M) | PFINT_SB_CTL_CAUSE_ENA_M);
wr32(hw, GLINT_ITR(ICE_RX_ITR, pf->oicr_irq.index),
ITR_REG_ALIGN(ICE_ITR_8K) >> ICE_ITR_GRAN_S);
@@ -3362,9 +3554,11 @@ static void ice_napi_add(struct ice_vsi *vsi)
if (!vsi->netdev)
return;
- ice_for_each_q_vector(vsi, v_idx)
+ 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);
+ }
}
/**
@@ -3384,6 +3578,7 @@ static void ice_set_ops(struct ice_vsi *vsi)
netdev->netdev_ops = &ice_netdev_ops;
netdev->udp_tunnel_nic_info = &pf->hw.udp_tunnel_nic;
+ netdev->xdp_metadata_ops = &ice_xdp_md_ops;
ice_set_ethtool_ops(netdev);
if (vsi->type != ICE_VSI_PF)
@@ -3392,6 +3587,7 @@ static void ice_set_ops(struct ice_vsi *vsi)
netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
NETDEV_XDP_ACT_XSK_ZEROCOPY |
NETDEV_XDP_ACT_RX_SG;
+ netdev->xdp_zc_max_segs = ICE_MAX_BUF_TXD;
}
/**
@@ -3512,7 +3708,7 @@ 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);
@@ -3525,7 +3721,7 @@ 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;
@@ -3546,7 +3742,7 @@ 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);
@@ -3566,7 +3762,7 @@ 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);
@@ -3794,6 +3990,7 @@ u16 ice_get_avail_rxq_count(struct ice_pf *pf)
static void ice_deinit_pf(struct ice_pf *pf)
{
ice_service_task_stop(pf);
+ mutex_destroy(&pf->lag_mutex);
mutex_destroy(&pf->adev_mutex);
mutex_destroy(&pf->sw_mutex);
mutex_destroy(&pf->tc_mutex);
@@ -3856,7 +4053,8 @@ static void ice_set_pf_caps(struct ice_pf *pf)
}
clear_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags);
- if (func_caps->common_cap.ieee_1588)
+ if (func_caps->common_cap.ieee_1588 &&
+ !(pf->hw.mac_type == ICE_MAC_E830))
set_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags);
pf->max_pf_txqs = func_caps->common_cap.num_txq;
@@ -3874,6 +4072,7 @@ static int ice_init_pf(struct ice_pf *pf)
mutex_init(&pf->sw_mutex);
mutex_init(&pf->tc_mutex);
mutex_init(&pf->adev_mutex);
+ mutex_init(&pf->lag_mutex);
INIT_HLIST_HEAD(&pf->aq_wait_list);
spin_lock_init(&pf->aq_wait_lock);
@@ -4278,11 +4477,13 @@ 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;
@@ -4291,29 +4492,95 @@ 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;
+ u8 *buf_copy;
+ int err;
+
+ dev = ice_pf_to_dev(pf);
+ /* ice_cfg_tx_topo buf argument is not a constant,
+ * so we have to make a copy
+ */
+ buf_copy = kmemdup(firmware->data, firmware->size, GFP_KERNEL);
+
+ err = ice_cfg_tx_topo(hw, buf_copy, 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_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, "Fail during requesting FW: %d\n", err);
+ return err;
}
-dflt_pkg_load:
- err = request_firmware(&firmware, ICE_DDP_PKG_FILE, dev);
+ err = ice_init_tx_topology(hw, 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 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);
+
+ return 0;
}
/**
@@ -4344,6 +4611,19 @@ static void ice_print_wake_reason(struct ice_pf *pf)
}
/**
+ * ice_pf_fwlog_update_module - update 1 module
+ * @pf: pointer to the PF struct
+ * @log_level: log_level to use for the @module
+ * @module: module to update
+ */
+void ice_pf_fwlog_update_module(struct ice_pf *pf, int log_level, int module)
+{
+ struct ice_hw *hw = &pf->hw;
+
+ hw->fwlog_cfg.module_entries[module].log_level = log_level;
+}
+
+/**
* ice_register_netdev - register netdev
* @vsi: pointer to the VSI struct
*/
@@ -4422,91 +4702,32 @@ static void ice_decfg_netdev(struct ice_vsi *vsi)
vsi->netdev = NULL;
}
-static int ice_start_eth(struct ice_vsi *vsi)
-{
- int err;
-
- err = ice_init_mac_fltr(vsi->back);
- if (err)
- return err;
-
- err = ice_vsi_open(vsi);
- if (err)
- ice_fltr_remove_all(vsi);
-
- return err;
-}
-
-static void ice_stop_eth(struct ice_vsi *vsi)
-{
- ice_fltr_remove_all(vsi);
- ice_vsi_close(vsi);
-}
-
-static int ice_init_eth(struct ice_pf *pf)
+/**
+ * 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)
{
- struct ice_vsi *vsi = ice_get_main_vsi(pf);
- int err;
-
- if (!vsi)
- return -EINVAL;
-
- /* init channel list */
- INIT_LIST_HEAD(&vsi->ch_list);
+ int fw_loading;
+ u32 elapsed = 0;
- err = ice_cfg_netdev(vsi);
- if (err)
- return err;
- /* Setup DCB netlink interface */
- ice_dcbnl_setup(vsi);
+ while (elapsed <= timeout) {
+ fw_loading = rd32(hw, GL_MNG_FWSM) & GL_MNG_FWSM_FW_LOADING_M;
- err = ice_init_mac_fltr(pf);
- if (err)
- goto err_init_mac_fltr;
-
- err = ice_devlink_create_pf_port(pf);
- if (err)
- goto err_devlink_create_pf_port;
-
- SET_NETDEV_DEVLINK_PORT(vsi->netdev, &pf->devlink_port);
-
- err = ice_register_netdev(vsi);
- if (err)
- goto err_register_netdev;
-
- err = ice_tc_indir_block_register(vsi);
- if (err)
- goto err_tc_indir_block_register;
-
- ice_napi_add(vsi);
-
- return 0;
-
-err_tc_indir_block_register:
- ice_unregister_netdev(vsi);
-err_register_netdev:
- ice_devlink_destroy_pf_port(pf);
-err_devlink_create_pf_port:
-err_init_mac_fltr:
- ice_decfg_netdev(vsi);
- return err;
-}
-
-static void ice_deinit_eth(struct ice_pf *pf)
-{
- struct ice_vsi *vsi = ice_get_main_vsi(pf);
-
- if (!vsi)
- return;
+ /* firmware was not yet loaded, we have to wait more */
+ if (fw_loading) {
+ elapsed += 100;
+ msleep(100);
+ continue;
+ }
+ return 0;
+ }
- ice_vsi_close(vsi);
- ice_unregister_netdev(vsi);
- ice_devlink_destroy_pf_port(pf);
- ice_tc_indir_block_unregister(vsi);
- ice_decfg_netdev(vsi);
+ return -ETIMEDOUT;
}
-static int ice_init_dev(struct ice_pf *pf)
+int ice_init_dev(struct ice_pf *pf)
{
struct device *dev = ice_pf_to_dev(pf);
struct ice_hw *hw = &pf->hw;
@@ -4518,11 +4739,25 @@ static int ice_init_dev(struct ice_pf *pf)
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 (err)
+ return err;
- /* 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
*/
@@ -4587,7 +4822,7 @@ err_init_pf:
return err;
}
-static void ice_deinit_dev(struct ice_pf *pf)
+void ice_deinit_dev(struct ice_pf *pf)
{
ice_free_irq_msix_misc(pf);
ice_deinit_pf(pf);
@@ -4613,6 +4848,10 @@ static void ice_init_features(struct ice_pf *pf)
if (ice_is_feature_supported(pf, ICE_F_GNSS))
ice_gnss_init(pf);
+ if (ice_is_feature_supported(pf, ICE_F_CGU) ||
+ ice_is_feature_supported(pf, ICE_F_PHY_RCLK))
+ ice_dpll_init(pf);
+
/* Note: Flow director init failure is non-fatal to load */
if (ice_init_fdir(pf))
dev_err(dev, "could not initialize flow director\n");
@@ -4627,10 +4866,15 @@ static void ice_init_features(struct ice_pf *pf)
if (ice_init_lag(pf))
dev_warn(dev, "Failed to init link aggregation support\n");
+
+ ice_hwmon_init(pf);
}
static void ice_deinit_features(struct ice_pf *pf)
{
+ if (ice_is_safe_mode(pf))
+ return;
+
ice_deinit_lag(pf);
if (test_bit(ICE_FLAG_DCB_CAPABLE, pf->flags))
ice_cfg_lldp_mib_change(&pf->hw, false);
@@ -4639,6 +4883,10 @@ static void ice_deinit_features(struct ice_pf *pf)
ice_gnss_exit(pf);
if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags))
ice_ptp_release(pf);
+ if (test_bit(ICE_FLAG_DPLL, pf->flags))
+ ice_dpll_deinit(pf);
+ if (pf->eswitch_mode == DEVLINK_ESWITCH_MODE_SWITCHDEV)
+ xa_destroy(&pf->eswitch.reprs);
}
static void ice_init_wakeup(struct ice_pf *pf)
@@ -4879,31 +5127,47 @@ static void ice_deinit(struct ice_pf *pf)
/**
* ice_load - load pf by init hw and starting VSI
* @pf: pointer to the pf instance
+ *
+ * This function has to be called under devl_lock.
*/
int ice_load(struct ice_pf *pf)
{
- struct ice_vsi_cfg_params params = {};
struct ice_vsi *vsi;
int err;
- err = ice_init_dev(pf);
+ devl_assert_locked(priv_to_devlink(pf));
+
+ vsi = ice_get_main_vsi(pf);
+
+ /* init channel list */
+ INIT_LIST_HEAD(&vsi->ch_list);
+
+ err = ice_cfg_netdev(vsi);
if (err)
return err;
- vsi = ice_get_main_vsi(pf);
+ /* Setup DCB netlink interface */
+ ice_dcbnl_setup(vsi);
- params = ice_vsi_to_params(vsi);
- params.flags = ICE_VSI_FLAG_INIT;
+ err = ice_init_mac_fltr(pf);
+ if (err)
+ goto err_init_mac_fltr;
- rtnl_lock();
- err = ice_vsi_cfg(vsi, &params);
+ err = ice_devlink_create_pf_port(pf);
if (err)
- goto err_vsi_cfg;
+ goto err_devlink_create_pf_port;
+
+ SET_NETDEV_DEVLINK_PORT(vsi->netdev, &pf->devlink_port);
- err = ice_start_eth(ice_get_main_vsi(pf));
+ err = ice_register_netdev(vsi);
+ if (err)
+ goto err_register_netdev;
+
+ err = ice_tc_indir_block_register(vsi);
if (err)
- goto err_start_eth;
- rtnl_unlock();
+ goto err_tc_indir_block_register;
+
+ ice_napi_add(vsi);
err = ice_init_rdma(pf);
if (err)
@@ -4917,29 +5181,35 @@ int ice_load(struct ice_pf *pf)
return 0;
err_init_rdma:
- ice_vsi_close(ice_get_main_vsi(pf));
- rtnl_lock();
-err_start_eth:
- ice_vsi_decfg(ice_get_main_vsi(pf));
-err_vsi_cfg:
- rtnl_unlock();
- ice_deinit_dev(pf);
+ ice_tc_indir_block_unregister(vsi);
+err_tc_indir_block_register:
+ ice_unregister_netdev(vsi);
+err_register_netdev:
+ ice_devlink_destroy_pf_port(pf);
+err_devlink_create_pf_port:
+err_init_mac_fltr:
+ ice_decfg_netdev(vsi);
return err;
}
/**
* ice_unload - unload pf by stopping VSI and deinit hw
* @pf: pointer to the pf instance
+ *
+ * This function has to be called under devl_lock.
*/
void ice_unload(struct ice_pf *pf)
{
+ struct ice_vsi *vsi = ice_get_main_vsi(pf);
+
+ devl_assert_locked(priv_to_devlink(pf));
+
ice_deinit_features(pf);
ice_deinit_rdma(pf);
- rtnl_lock();
- ice_stop_eth(ice_get_main_vsi(pf));
- ice_vsi_decfg(ice_get_main_vsi(pf));
- rtnl_unlock();
- ice_deinit_dev(pf);
+ ice_tc_indir_block_unregister(vsi);
+ ice_unregister_netdev(vsi);
+ ice_devlink_destroy_pf_port(pf);
+ ice_decfg_netdev(vsi);
}
/**
@@ -4953,6 +5223,7 @@ 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;
@@ -4962,6 +5233,20 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
return -EINVAL;
}
+ /* when under a kdump kernel initiate a reset before enabling the
+ * device in order to clear out any pending DMA transactions. These
+ * transactions can cause some systems to machine check when doing
+ * the pcim_enable_device() below.
+ */
+ if (is_kdump_kernel()) {
+ pci_save_state(pdev);
+ pci_clear_master(pdev);
+ err = pcie_flr(pdev);
+ if (err)
+ return err;
+ pci_restore_state(pdev);
+ }
+
/* this driver uses devres, see
* Documentation/driver-api/driver-model/devres.rst
*/
@@ -4991,7 +5276,12 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
pci_set_master(pdev);
+ adapter = ice_adapter_get(pdev);
+ if (IS_ERR(adapter))
+ return PTR_ERR(adapter);
+
pf->pdev = pdev;
+ pf->adapter = adapter;
pci_set_drvdata(pdev, pf);
set_bit(ICE_DOWN, pf->state);
/* Disable service task until DOWN bit is cleared */
@@ -5023,29 +5313,25 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
if (err)
goto err_init;
- err = ice_init_eth(pf);
- if (err)
- goto err_init_eth;
-
- err = ice_init_rdma(pf);
+ devl_lock(priv_to_devlink(pf));
+ err = ice_load(pf);
if (err)
- goto err_init_rdma;
+ goto err_load;
err = ice_init_devlink(pf);
if (err)
goto err_init_devlink;
-
- ice_init_features(pf);
+ devl_unlock(priv_to_devlink(pf));
return 0;
err_init_devlink:
- ice_deinit_rdma(pf);
-err_init_rdma:
- ice_deinit_eth(pf);
-err_init_eth:
+ ice_unload(pf);
+err_load:
+ devl_unlock(priv_to_devlink(pf));
ice_deinit(pf);
err_init:
+ ice_adapter_put(pdev);
pci_disable_device(pdev);
return err;
}
@@ -5131,23 +5417,28 @@ static void ice_remove(struct pci_dev *pdev)
ice_free_vfs(pf);
}
+ ice_hwmon_exit(pf);
+
ice_service_task_stop(pf);
ice_aq_cancel_waiting_tasks(pf);
set_bit(ICE_DOWN, pf->state);
if (!ice_is_safe_mode(pf))
ice_remove_arfs(pf);
- ice_deinit_features(pf);
+
+ devl_lock(priv_to_devlink(pf));
ice_deinit_devlink(pf);
- ice_deinit_rdma(pf);
- ice_deinit_eth(pf);
- ice_deinit(pf);
+ ice_unload(pf);
+ devl_unlock(priv_to_devlink(pf));
+
+ ice_deinit(pf);
ice_vsi_release_all(pf);
ice_setup_mc_magic_wake(pf);
ice_set_wake(pf);
+ ice_adapter_put(pdev);
pci_disable_device(pdev);
}
@@ -5167,7 +5458,6 @@ static void ice_shutdown(struct pci_dev *pdev)
}
}
-#ifdef CONFIG_PM
/**
* ice_prepare_for_shutdown - prep for PCI shutdown
* @pf: board private structure
@@ -5229,6 +5519,7 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf)
if (ret)
goto err_reinit;
ice_vsi_map_rings_to_vectors(pf->vsi[v]);
+ ice_vsi_set_napi_queues(pf->vsi[v]);
}
ret = ice_req_irq_msix_misc(pf);
@@ -5255,7 +5546,7 @@ 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;
@@ -5276,7 +5567,7 @@ 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)) {
@@ -5322,7 +5613,7 @@ 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;
@@ -5356,6 +5647,11 @@ 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;
@@ -5373,7 +5669,6 @@ 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
@@ -5465,7 +5760,7 @@ static void ice_pci_err_resume(struct pci_dev *pdev)
return;
}
- ice_restore_all_vfs_msi_state(pdev);
+ ice_restore_all_vfs_msi_state(pf);
ice_do_reset(pf, ICE_RESET_PFR);
ice_service_task_restart(pf);
@@ -5508,38 +5803,52 @@ static void ice_pci_err_reset_done(struct pci_dev *pdev)
* Class, Class Mask, private data (not used) }
*/
static const struct pci_device_id ice_pci_tbl[] = {
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_BACKPLANE), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_QSFP), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_SFP), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_BACKPLANE), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_QSFP), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_SFP), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_BACKPLANE), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_QSFP), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_SFP), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_10G_BASE_T), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_SGMII), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_BACKPLANE), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_QSFP), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_SFP), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_10G_BASE_T), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_SGMII), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_BACKPLANE), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_SFP), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_10G_BASE_T), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_SGMII), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_BACKPLANE), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_SFP), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_10G_BASE_T), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_1GBE), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_QSFP), 0 },
- { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822_SI_DFLT), 0 },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_BACKPLANE) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_QSFP) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_SFP) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_BACKPLANE) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_QSFP) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E810_XXV_SFP) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_BACKPLANE) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_QSFP) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_SFP) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_10G_BASE_T) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823C_SGMII) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_BACKPLANE) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_QSFP) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_SFP) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_10G_BASE_T) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822C_SGMII) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_BACKPLANE) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_SFP) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_10G_BASE_T) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822L_SGMII) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_BACKPLANE) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_SFP) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_10G_BASE_T) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_1GBE) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E823L_QSFP) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E822_SI_DFLT) },
+ { PCI_VDEVICE(INTEL, ICE_DEV_ID_E825C_BACKPLANE), },
+ { 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_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 */
- { 0, }
+ {}
};
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,
@@ -5554,11 +5863,11 @@ 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,
+ .sriov_set_msix_vec_count = ice_sriov_set_msix_vec_count,
.err_handler = &ice_pci_err_handler
};
@@ -5570,23 +5879,40 @@ static struct pci_driver ice_driver = {
*/
static int __init ice_module_init(void)
{
- int status;
+ int status = -ENOMEM;
pr_info("%s\n", ice_driver_string);
pr_info("%s\n", ice_copyright);
+ ice_adv_lnk_speed_maps_init();
+
ice_wq = alloc_workqueue("%s", 0, 0, KBUILD_MODNAME);
if (!ice_wq) {
pr_err("Failed to create workqueue\n");
- return -ENOMEM;
+ return status;
}
+ ice_lag_wq = alloc_ordered_workqueue("ice_lag_wq", 0);
+ if (!ice_lag_wq) {
+ pr_err("Failed to create LAG workqueue\n");
+ goto err_dest_wq;
+ }
+
+ ice_debugfs_init();
+
status = pci_register_driver(&ice_driver);
if (status) {
pr_err("failed to register PCI driver, err %d\n", status);
- destroy_workqueue(ice_wq);
+ goto err_dest_lag_wq;
}
+ return 0;
+
+err_dest_lag_wq:
+ destroy_workqueue(ice_lag_wq);
+ ice_debugfs_exit();
+err_dest_wq:
+ destroy_workqueue(ice_wq);
return status;
}
module_init(ice_module_init);
@@ -5600,7 +5926,9 @@ module_init(ice_module_init);
static void __exit ice_module_exit(void)
{
pci_unregister_driver(&ice_driver);
+ ice_debugfs_exit();
destroy_workqueue(ice_wq);
+ destroy_workqueue(ice_lag_wq);
pr_info("module unloaded\n");
}
module_exit(ice_module_exit);
@@ -5703,7 +6031,7 @@ static void ice_set_rx_mode(struct net_device *netdev)
struct ice_netdev_priv *np = netdev_priv(netdev);
struct ice_vsi *vsi = np->vsi;
- if (!vsi)
+ if (!vsi || ice_is_switchdev_running(vsi->back))
return;
/* Set the flags to synchronize filters
@@ -5943,6 +6271,23 @@ ice_fix_features(struct net_device *netdev, netdev_features_t features)
}
/**
+ * ice_set_rx_rings_vlan_proto - update rings with new stripped VLAN proto
+ * @vsi: PF's VSI
+ * @vlan_ethertype: VLAN ethertype (802.1Q or 802.1ad) in network byte order
+ *
+ * Store current stripped VLAN proto in ring packet context,
+ * so it can be accessed more efficiently by packet processing code.
+ */
+static void
+ice_set_rx_rings_vlan_proto(struct ice_vsi *vsi, __be16 vlan_ethertype)
+{
+ u16 i;
+
+ ice_for_each_alloc_rxq(vsi, i)
+ vsi->rx_rings[i]->pkt_ctx.vlan_proto = vlan_ethertype;
+}
+
+/**
* ice_set_vlan_offload_features - set VLAN offload features for the PF VSI
* @vsi: PF's VSI
* @features: features used to determine VLAN offload settings
@@ -5984,6 +6329,9 @@ ice_set_vlan_offload_features(struct ice_vsi *vsi, netdev_features_t features)
if (strip_err || insert_err)
return -EIO;
+ ice_set_rx_rings_vlan_proto(vsi, enable_stripping ?
+ htons(vlan_ethertype) : 0);
+
return 0;
}
@@ -6255,7 +6603,7 @@ static void ice_tx_dim_work(struct work_struct *work)
u16 itr;
dim = container_of(work, struct dim, work);
- rc = (struct ice_ring_container *)dim->priv;
+ rc = dim->priv;
WARN_ON(dim->profile_ix >= ARRAY_SIZE(tx_profile));
@@ -6275,7 +6623,7 @@ static void ice_rx_dim_work(struct work_struct *work)
u16 itr;
dim = container_of(work, struct dim, work);
- rc = (struct ice_ring_container *)dim->priv;
+ rc = dim->priv;
WARN_ON(dim->profile_ix >= ARRAY_SIZE(rx_profile));
@@ -6474,6 +6822,7 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi)
{
struct rtnl_link_stats64 *net_stats, *stats_prev;
struct rtnl_link_stats64 *vsi_stats;
+ struct ice_pf *pf = vsi->back;
u64 pkts, bytes;
int i;
@@ -6519,21 +6868,18 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi)
net_stats = &vsi->net_stats;
stats_prev = &vsi->net_stats_prev;
- /* clear prev counters after reset */
- if (vsi_stats->tx_packets < stats_prev->tx_packets ||
- vsi_stats->rx_packets < stats_prev->rx_packets) {
- stats_prev->tx_packets = 0;
- stats_prev->tx_bytes = 0;
- stats_prev->rx_packets = 0;
- stats_prev->rx_bytes = 0;
+ /* Update netdev counters, but keep in mind that values could start at
+ * random value after PF reset. And as we increase the reported stat by
+ * diff of Prev-Cur, we need to be sure that Prev is valid. If it's not,
+ * let's skip this round.
+ */
+ if (likely(pf->stat_prev_loaded)) {
+ net_stats->tx_packets += vsi_stats->tx_packets - stats_prev->tx_packets;
+ net_stats->tx_bytes += vsi_stats->tx_bytes - stats_prev->tx_bytes;
+ net_stats->rx_packets += vsi_stats->rx_packets - stats_prev->rx_packets;
+ net_stats->rx_bytes += vsi_stats->rx_bytes - stats_prev->rx_bytes;
}
- /* update netdev counters */
- net_stats->tx_packets += vsi_stats->tx_packets - stats_prev->tx_packets;
- net_stats->tx_bytes += vsi_stats->tx_bytes - stats_prev->tx_bytes;
- net_stats->rx_packets += vsi_stats->rx_packets - stats_prev->rx_packets;
- net_stats->rx_bytes += vsi_stats->rx_bytes - stats_prev->rx_bytes;
-
stats_prev->tx_packets = vsi_stats->tx_packets;
stats_prev->tx_bytes = vsi_stats->tx_bytes;
stats_prev->rx_packets = vsi_stats->rx_packets;
@@ -6572,13 +6918,11 @@ void ice_update_vsi_stats(struct ice_vsi *vsi)
cur_ns->rx_crc_errors = pf->stats.crc_errors;
cur_ns->rx_errors = pf->stats.crc_errors +
pf->stats.illegal_bytes +
- pf->stats.rx_len_errors +
pf->stats.rx_undersize +
pf->hw_csum_rx_error +
pf->stats.rx_jabber +
pf->stats.rx_fragments +
pf->stats.rx_oversize;
- cur_ns->rx_length_errors = pf->stats.rx_len_errors;
/* record drops from the port level */
cur_ns->rx_missed_errors = pf->stats.eth.rx_discards;
}
@@ -6718,9 +7062,6 @@ void ice_update_pf_stats(struct ice_pf *pf)
&prev_ps->mac_remote_faults,
&cur_ps->mac_remote_faults);
- ice_stat_update32(hw, GLPRT_RLEC(port), pf->stat_prev_loaded,
- &prev_ps->rx_len_errors, &cur_ps->rx_len_errors);
-
ice_stat_update32(hw, GLPRT_RUC(port), pf->stat_prev_loaded,
&prev_ps->rx_undersize, &cur_ps->rx_undersize);
@@ -6803,6 +7144,50 @@ static void ice_napi_disable_all(struct ice_vsi *vsi)
}
/**
+ * ice_vsi_dis_irq - Mask off queue interrupt generation on the VSI
+ * @vsi: the VSI being un-configured
+ */
+static void ice_vsi_dis_irq(struct ice_vsi *vsi)
+{
+ struct ice_pf *pf = vsi->back;
+ struct ice_hw *hw = &pf->hw;
+ u32 val;
+ int i;
+
+ /* disable interrupt causation from each Rx queue; Tx queues are
+ * handled in ice_vsi_stop_tx_ring()
+ */
+ if (vsi->rx_rings) {
+ ice_for_each_rxq(vsi, i) {
+ if (vsi->rx_rings[i]) {
+ u16 reg;
+
+ reg = vsi->rx_rings[i]->reg_idx;
+ val = rd32(hw, QINT_RQCTL(reg));
+ val &= ~QINT_RQCTL_CAUSE_ENA_M;
+ wr32(hw, QINT_RQCTL(reg), val);
+ }
+ }
+ }
+
+ /* disable each interrupt */
+ ice_for_each_q_vector(vsi, i) {
+ if (!vsi->q_vectors[i])
+ continue;
+ wr32(hw, GLINT_DYN_CTL(vsi->q_vectors[i]->reg_idx), 0);
+ }
+
+ ice_flush(hw);
+
+ /* don't call synchronize_irq() for VF's from the host */
+ if (vsi->type == ICE_VSI_VF)
+ return;
+
+ ice_for_each_q_vector(vsi, i)
+ synchronize_irq(vsi->q_vectors[i]->irq.virq);
+}
+
+/**
* ice_down - Shutdown the connection
* @vsi: The VSI being stopped
*
@@ -6814,13 +7199,11 @@ 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);
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);
@@ -7291,7 +7674,7 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
* fail.
*/
if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags))
- ice_ptp_reset(pf);
+ ice_ptp_rebuild(pf, reset_type);
if (ice_is_feature_supported(pf, ICE_F_GNSS))
ice_gnss_init(pf);
@@ -7303,15 +7686,7 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
goto err_vsi_rebuild;
}
- /* configure PTP timestamping after VSI rebuild */
- if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags))
- ice_ptp_cfg_timestamp(pf, false);
-
- err = ice_vsi_rebuild_by_type(pf, ICE_VSI_SWITCHDEV_CTRL);
- if (err) {
- dev_err(dev, "Switchdev CTRL VSI rebuild failed: %d\n", err);
- goto err_vsi_rebuild;
- }
+ ice_eswitch_rebuild(pf);
if (reset_type == ICE_RESET_PFR) {
err = ice_rebuild_channels(pf);
@@ -7356,6 +7731,11 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
clear_bit(ICE_RESET_FAILED, pf->state);
ice_plug_aux_dev(pf);
+ if (ice_is_feature_supported(pf, ICE_F_SRIOV_LAG))
+ ice_lag_rebuild(pf);
+
+ /* Restore timestamp mode settings after VSI rebuild */
+ ice_ptp_restore_timestamp_mode(pf);
return;
err_vsi_rebuild:
@@ -7424,7 +7804,7 @@ 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;
@@ -7605,6 +7985,59 @@ int ice_get_rss_key(struct ice_vsi *vsi, u8 *seed)
}
/**
+ * ice_set_rss_hfunc - Set RSS HASH function
+ * @vsi: Pointer to VSI structure
+ * @hfunc: hash function (ICE_AQ_VSI_Q_OPT_RSS_*)
+ *
+ * Returns 0 on success, negative on failure
+ */
+int ice_set_rss_hfunc(struct ice_vsi *vsi, u8 hfunc)
+{
+ struct ice_hw *hw = &vsi->back->hw;
+ struct ice_vsi_ctx *ctx;
+ bool symm;
+ int err;
+
+ if (hfunc == vsi->rss_hfunc)
+ return 0;
+
+ if (hfunc != ICE_AQ_VSI_Q_OPT_RSS_HASH_TPLZ &&
+ hfunc != ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ)
+ return -EOPNOTSUPP;
+
+ ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ ctx->info.valid_sections = cpu_to_le16(ICE_AQ_VSI_PROP_Q_OPT_VALID);
+ ctx->info.q_opt_rss = vsi->info.q_opt_rss;
+ ctx->info.q_opt_rss &= ~ICE_AQ_VSI_Q_OPT_RSS_HASH_M;
+ ctx->info.q_opt_rss |=
+ FIELD_PREP(ICE_AQ_VSI_Q_OPT_RSS_HASH_M, hfunc);
+ ctx->info.q_opt_tc = vsi->info.q_opt_tc;
+ ctx->info.q_opt_flags = vsi->info.q_opt_rss;
+
+ err = ice_update_vsi(hw, vsi->idx, ctx, NULL);
+ if (err) {
+ dev_err(ice_pf_to_dev(vsi->back), "Failed to configure RSS hash for VSI %d, error %d\n",
+ vsi->vsi_num, err);
+ } else {
+ vsi->info.q_opt_rss = ctx->info.q_opt_rss;
+ vsi->rss_hfunc = hfunc;
+ netdev_info(vsi->netdev, "Hash function set to: %sToeplitz\n",
+ hfunc == ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ ?
+ "Symmetric " : "");
+ }
+ kfree(ctx);
+ if (err)
+ return err;
+
+ /* Fix the symmetry setting for all existing RSS configurations */
+ symm = !!(hfunc == ICE_AQ_VSI_Q_OPT_RSS_HASH_SYM_TPLZ);
+ return ice_set_rss_cfg_symm(hw, vsi, symm);
+}
+
+/**
* ice_bridge_getlink - Get the hardware bridge mode
* @skb: skb buff
* @pid: process ID
@@ -7701,13 +8134,12 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh,
pf_sw = pf->first_sw;
/* find the attribute in the netlink message */
br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC);
+ 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 */
@@ -7790,8 +8222,8 @@ static void ice_tx_timeout(struct net_device *netdev, unsigned int txqueue)
struct ice_hw *hw = &pf->hw;
u32 head, val = 0;
- head = (rd32(hw, QTX_COMM_HEAD(vsi->txq_map[txqueue])) &
- QTX_COMM_HEAD_HEAD_M) >> QTX_COMM_HEAD_HEAD_S;
+ 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));
@@ -8039,13 +8471,12 @@ static int ice_add_vsi_to_fdir(struct ice_pf *pf, struct ice_vsi *vsi)
for (tun = 0; tun < ICE_FD_HW_SEG_MAX; tun++) {
enum ice_flow_priority prio;
- u64 prof_id;
/* add this VSI to FDir profile for this flow */
prio = ICE_FLOW_PRIO_NORMAL;
prof = hw->fdir_prof[flow];
- prof_id = flow + tun * ICE_FLTR_PTYPE_MAX;
- status = ice_flow_add_entry(hw, ICE_BLK_FD, prof_id,
+ status = ice_flow_add_entry(hw, ICE_BLK_FD,
+ prof->prof_id[tun],
prof->vsi_h[0], vsi->idx,
prio, prof->fdir_seg[tun],
&entry_h);
@@ -9088,8 +9519,14 @@ int ice_stop(struct net_device *netdev)
int link_err = ice_force_phys_link_state(vsi, false);
if (link_err) {
- netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n",
- vsi->vsi_num, link_err);
+ if (link_err == -ENOMEDIUM)
+ netdev_info(vsi->netdev, "Skipping link reconfig - no media attached, VSI %d\n",
+ vsi->vsi_num);
+ else
+ netdev_err(vsi->netdev, "Failed to set physical link down, VSI %d error %d\n",
+ vsi->vsi_num, link_err);
+
+ ice_vsi_close(vsi);
return -EIO;
}
}
Powered by cgit, Gruvboxed by Blaster4385.