Merge branch '100GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/tnguy/next-queue

Tony Nguyen says:

====================
100GbE Intel Wired LAN Driver Updates 2021-06-07

This series contains updates to virtchnl header file and ice driver.

Brett adds capability bits to virtchnl to specify whether a primary or
secondary MAC address is being requested and adds the implementation to
ice. He also adds storing of VF MAC address so that it will be preserved
across reboots of VM and refactors VF queue configuration to remove the
expectation that configuration be done all at once.

Krzysztof refactors ice_setup_rx_ctx() to remove configuration not
related to Rx context into a new function, ice_vsi_cfg_rxq().

Liwei Song extends the wait time for the global config timeout.

Salil Mehta refactors code in ice_vsi_set_num_qs() to remove an
unnecessary call when the user has requested specific number of Rx or Tx
queues.

Jesse converts define macros to static inlines for NOP configurations.

Jake adds messaging when devlink fails to read device capabilities and
when pldmfw cannot find the requested firmware. Adds a wait for reset
completion when reporting devlink info and reinitializes NVM during
rebuild to ensure values are current.

Ani adds detection and reporting of modules exceeding supported power
levels and changes an error message to a debug message.

Paul fixes a clang warning for deadcode.DeadStores.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/intel/ice/ice.h

@@ -393,6 +393,7 @@ enum ice_pf_flags {
 	ICE_FLAG_TOTAL_PORT_SHUTDOWN_ENA,
 	ICE_FLAG_NO_MEDIA,
 	ICE_FLAG_FW_LLDP_AGENT,
+	ICE_FLAG_MOD_POWER_UNSUPPORTED,
 	ICE_FLAG_ETHTOOL_CTXT,		/* set when ethtool holds RTNL lock */
 	ICE_FLAG_LEGACY_RX,
 	ICE_FLAG_VF_TRUE_PROMISC_ENA,
@@ -456,6 +457,8 @@ struct ice_pf {
 	struct hlist_head aq_wait_list;
 	wait_queue_head_t aq_wait_queue;
 
+	wait_queue_head_t reset_wait_queue;
+
 	u32 hw_csum_rx_error;
 	u16 oicr_idx;		/* Other interrupt cause MSIX vector index */
 	u16 num_avail_sw_msix;	/* remaining MSIX SW vectors left unclaimed */

drivers/net/ethernet/intel/ice/ice_adminq_cmd.h

@@ -1123,7 +1123,9 @@ struct ice_aqc_get_link_status_data {
 #define ICE_AQ_LINK_TOPO_UNDRUTIL_PRT	BIT(5)
 #define ICE_AQ_LINK_TOPO_UNDRUTIL_MEDIA	BIT(6)
 #define ICE_AQ_LINK_TOPO_UNSUPP_MEDIA	BIT(7)
-	u8 reserved1;
+	u8 link_cfg_err;
+#define ICE_AQ_LINK_MODULE_POWER_UNSUPPORTED	BIT(5)
+#define ICE_AQ_LINK_INVAL_MAX_POWER_LIMIT	BIT(7)
 	u8 link_info;
 #define ICE_AQ_LINK_UP			BIT(0)	/* Link Status */
 #define ICE_AQ_LINK_FAULT		BIT(1)
@@ -1166,7 +1168,7 @@ struct ice_aqc_get_link_status_data {
 #define ICE_AQ_CFG_PACING_TYPE_FIXED	ICE_AQ_CFG_PACING_TYPE_M
 	/* External Device Power Ability */
 	u8 power_desc;
-#define ICE_AQ_PWR_CLASS_M		0x3
+#define ICE_AQ_PWR_CLASS_M		0x3F
 #define ICE_AQ_LINK_PWR_BASET_LOW_HIGH	0
 #define ICE_AQ_LINK_PWR_BASET_HIGH	1
 #define ICE_AQ_LINK_PWR_QSFP_CLASS_1	0

drivers/net/ethernet/intel/ice/ice_arfs.h

@@ -52,12 +52,12 @@ bool
 ice_is_arfs_using_perfect_flow(struct ice_hw *hw,
 			       enum ice_fltr_ptype flow_type);
 #else
-#define ice_sync_arfs_fltrs(pf) do {} while (0)
-#define ice_init_arfs(vsi) do {} while (0)
-#define ice_clear_arfs(vsi) do {} while (0)
-#define ice_remove_arfs(pf) do {} while (0)
-#define ice_free_cpu_rx_rmap(vsi) do {} while (0)
-#define ice_rebuild_arfs(pf) do {} while (0)
+static inline void ice_clear_arfs(struct ice_vsi *vsi) { }
+static inline void ice_free_cpu_rx_rmap(struct ice_vsi *vsi) { }
+static inline void ice_init_arfs(struct ice_vsi *vsi) { }
+static inline void ice_sync_arfs_fltrs(struct ice_pf *pf) { }
+static inline void ice_remove_arfs(struct ice_pf *pf) { }
+static inline void ice_rebuild_arfs(struct ice_pf *pf) { }
 
 static inline int ice_set_cpu_rx_rmap(struct ice_vsi __always_unused *vsi)
 {

drivers/net/ethernet/intel/ice/ice_base.c

@@ -319,11 +319,9 @@ static unsigned int ice_rx_offset(struct ice_ring *rx_ring)
  *
  * Configure the Rx descriptor ring in RLAN context.
  */
-int ice_setup_rx_ctx(struct ice_ring *ring)
+static int ice_setup_rx_ctx(struct ice_ring *ring)
 {
-	struct device *dev = ice_pf_to_dev(ring->vsi->back);
 	int chain_len = ICE_MAX_CHAINED_RX_BUFS;
-	u16 num_bufs = ICE_DESC_UNUSED(ring);
 	struct ice_vsi *vsi = ring->vsi;
 	u32 rxdid = ICE_RXDID_FLEX_NIC;
 	struct ice_rlan_ctx rlan_ctx;
@@ -339,48 +337,6 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	/* clear the context structure first */
 	memset(&rlan_ctx, 0, sizeof(rlan_ctx));
 
-	ring->rx_buf_len = vsi->rx_buf_len;
-
-	if (ring->vsi->type == ICE_VSI_PF) {
-		if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
-			/* coverity[check_return] */
-			xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
-					 ring->q_index, ring->q_vector->napi.napi_id);
-
-		ring->xsk_pool = ice_xsk_pool(ring);
-		if (ring->xsk_pool) {
-			xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
-
-			ring->rx_buf_len =
-				xsk_pool_get_rx_frame_size(ring->xsk_pool);
-			/* For AF_XDP ZC, we disallow packets to span on
-			 * multiple buffers, thus letting us skip that
-			 * handling in the fast-path.
-			 */
-			chain_len = 1;
-			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
-							 MEM_TYPE_XSK_BUFF_POOL,
-							 NULL);
-			if (err)
-				return err;
-			xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq);
-
-			dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
-				 ring->q_index);
-		} else {
-			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
-				/* coverity[check_return] */
-				xdp_rxq_info_reg(&ring->xdp_rxq,
-						 ring->netdev,
-						 ring->q_index, ring->q_vector->napi.napi_id);
-
-			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
-							 MEM_TYPE_PAGE_SHARED,
-							 NULL);
-			if (err)
-				return err;
-		}
-	}
 	/* Receive Queue Base Address.
 	 * Indicates the starting address of the descriptor queue defined in
 	 * 128 Byte units.
@@ -415,6 +371,12 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	 */
 	rlan_ctx.showiv = 0;
 
+	/* For AF_XDP ZC, we disallow packets to span on
+	 * multiple buffers, thus letting us skip that
+	 * handling in the fast-path.
+	 */
+	if (ring->xsk_pool)
+		chain_len = 1;
 	/* Max packet size for this queue - must not be set to a larger value
 	 * than 5 x DBUF
 	 */
@@ -438,7 +400,7 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	/* Absolute queue number out of 2K needs to be passed */
 	err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q);
 	if (err) {
-		dev_err(dev, "Failed to set LAN Rx queue context for absolute Rx queue %d error: %d\n",
+		dev_err(ice_pf_to_dev(vsi->back), "Failed to set LAN Rx queue context for absolute Rx queue %d error: %d\n",
 			pf_q, err);
 		return -EIO;
 	}
@@ -458,6 +420,66 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 	ring->tail = hw->hw_addr + QRX_TAIL(pf_q);
 	writel(0, ring->tail);
 
+	return 0;
+}
+
+/**
+ * ice_vsi_cfg_rxq - Configure an Rx queue
+ * @ring: the ring being configured
+ *
+ * Return 0 on success and a negative value on error.
+ */
+int ice_vsi_cfg_rxq(struct ice_ring *ring)
+{
+	struct device *dev = ice_pf_to_dev(ring->vsi->back);
+	u16 num_bufs = ICE_DESC_UNUSED(ring);
+	int err;
+
+	ring->rx_buf_len = ring->vsi->rx_buf_len;
+
+	if (ring->vsi->type == ICE_VSI_PF) {
+		if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
+			/* coverity[check_return] */
+			xdp_rxq_info_reg(&ring->xdp_rxq, ring->netdev,
+					 ring->q_index, ring->q_vector->napi.napi_id);
+
+		ring->xsk_pool = ice_xsk_pool(ring);
+		if (ring->xsk_pool) {
+			xdp_rxq_info_unreg_mem_model(&ring->xdp_rxq);
+
+			ring->rx_buf_len =
+				xsk_pool_get_rx_frame_size(ring->xsk_pool);
+			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+							 MEM_TYPE_XSK_BUFF_POOL,
+							 NULL);
+			if (err)
+				return err;
+			xsk_pool_set_rxq_info(ring->xsk_pool, &ring->xdp_rxq);
+
+			dev_info(dev, "Registered XDP mem model MEM_TYPE_XSK_BUFF_POOL on Rx ring %d\n",
+				 ring->q_index);
+		} else {
+			if (!xdp_rxq_info_is_reg(&ring->xdp_rxq))
+				/* coverity[check_return] */
+				xdp_rxq_info_reg(&ring->xdp_rxq,
+						 ring->netdev,
+						 ring->q_index, ring->q_vector->napi.napi_id);
+
+			err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq,
+							 MEM_TYPE_PAGE_SHARED,
+							 NULL);
+			if (err)
+				return err;
+		}
+	}
+
+	err = ice_setup_rx_ctx(ring);
+	if (err) {
+		dev_err(dev, "ice_setup_rx_ctx failed for RxQ %d, err %d\n",
+			ring->q_index, err);
+		return err;
+	}
+
 	if (ring->xsk_pool) {
 		bool ok;
 
@@ -470,9 +492,13 @@ int ice_setup_rx_ctx(struct ice_ring *ring)
 		}
 
 		ok = ice_alloc_rx_bufs_zc(ring, num_bufs);
-		if (!ok)
+		if (!ok) {
+			u16 pf_q = ring->vsi->rxq_map[ring->q_index];
+
 			dev_info(dev, "Failed to allocate some buffers on XSK buffer pool enabled Rx ring %d (pf_q %d)\n",
 				 ring->q_index, pf_q);
+		}
+
 		return 0;
 	}
 

drivers/net/ethernet/intel/ice/ice_base.h

@@ -6,7 +6,7 @@
 
 #include "ice.h"
 
-int ice_setup_rx_ctx(struct ice_ring *ring);
+int ice_vsi_cfg_rxq(struct ice_ring *ring);
 int __ice_vsi_get_qs(struct ice_qs_cfg *qs_cfg);
 int
 ice_vsi_ctrl_one_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx, bool wait);

drivers/net/ethernet/intel/ice/ice_common.c

@@ -425,6 +425,7 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
 	li->phy_type_high = le64_to_cpu(link_data.phy_type_high);
 	*hw_media_type = ice_get_media_type(pi);
 	li->link_info = link_data.link_info;
+	li->link_cfg_err = link_data.link_cfg_err;
 	li->an_info = link_data.an_info;
 	li->ext_info = link_data.ext_info;
 	li->max_frame_size = le16_to_cpu(link_data.max_frame_size);
@@ -455,6 +456,7 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
 		  (unsigned long long)li->phy_type_high);
 	ice_debug(hw, ICE_DBG_LINK, "	media_type = 0x%x\n", *hw_media_type);
 	ice_debug(hw, ICE_DBG_LINK, "	link_info = 0x%x\n", li->link_info);
+	ice_debug(hw, ICE_DBG_LINK, "	link_cfg_err = 0x%x\n", li->link_cfg_err);
 	ice_debug(hw, ICE_DBG_LINK, "	an_info = 0x%x\n", li->an_info);
 	ice_debug(hw, ICE_DBG_LINK, "	ext_info = 0x%x\n", li->ext_info);
 	ice_debug(hw, ICE_DBG_LINK, "	fec_info = 0x%x\n", li->fec_info);

drivers/net/ethernet/intel/ice/ice_dcb_lib.h

@@ -60,7 +60,7 @@ static inline bool ice_is_dcb_active(struct ice_pf *pf)
 		test_bit(ICE_FLAG_DCB_ENA, pf->flags));
 }
 #else
-#define ice_dcb_rebuild(pf) do {} while (0)
+static inline void ice_dcb_rebuild(struct ice_pf *pf) { }
 
 static inline u8 ice_dcb_get_ena_tc(struct ice_dcbx_cfg __always_unused *dcbcfg)
 {
@@ -113,11 +113,12 @@ ice_is_pfc_causing_hung_q(struct ice_pf __always_unused *pf,
 	return false;
 }
 
-#define ice_update_dcb_stats(pf) do {} while (0)
-#define ice_pf_dcb_recfg(pf) do {} while (0)
-#define ice_vsi_cfg_dcb_rings(vsi) do {} while (0)
-#define ice_dcb_process_lldp_set_mib_change(pf, event) do {} while (0)
-#define ice_set_cgd_num(tlan_ctx, ring) do {} while (0)
-#define ice_vsi_cfg_netdev_tc(vsi, ena_tc) do {} while (0)
+static inline void ice_pf_dcb_recfg(struct ice_pf *pf) { }
+static inline void ice_vsi_cfg_dcb_rings(struct ice_vsi *vsi) { }
+static inline void ice_update_dcb_stats(struct ice_pf *pf) { }
+static inline void
+ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, struct ice_rq_event_info *event) { }
+static inline void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc) { }
+static inline void ice_set_cgd_num(struct ice_tlan_ctx *tlan_ctx, struct ice_ring *ring) { }
 #endif /* CONFIG_DCB */
 #endif /* _ICE_DCB_LIB_H_ */

drivers/net/ethernet/intel/ice/ice_dcb_nl.h

@@ -11,9 +11,10 @@ void
 ice_dcbnl_flush_apps(struct ice_pf *pf, struct ice_dcbx_cfg *old_cfg,
 		     struct ice_dcbx_cfg *new_cfg);
 #else
-#define ice_dcbnl_setup(vsi) do {} while (0)
-#define ice_dcbnl_set_all(vsi) do {} while (0)
-#define ice_dcbnl_flush_apps(pf, old_cfg, new_cfg) do {} while (0)
+static inline void ice_dcbnl_setup(struct ice_vsi *vsi) { }
+static inline void ice_dcbnl_set_all(struct ice_vsi *vsi) { }
+static inline void
+ice_dcbnl_flush_apps(struct ice_pf *pf, struct ice_dcbx_cfg *old_cfg,
+		     struct ice_dcbx_cfg *new_cfg) { }
 #endif /* CONFIG_DCB */
-
 #endif /* _ICE_DCB_NL_H_ */

drivers/net/ethernet/intel/ice/ice_devlink.c

@@ -276,6 +276,12 @@ static int ice_devlink_info_get(struct devlink *devlink,
 	size_t i;
 	int err;
 
+	err = ice_wait_for_reset(pf, 10 * HZ);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Device is busy resetting");
+		return err;
+	}
+
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
 	if (!ctx)
 		return -ENOMEM;
@@ -283,6 +289,9 @@ static int ice_devlink_info_get(struct devlink *devlink,
 	/* discover capabilities first */
 	status = ice_discover_dev_caps(hw, &ctx->dev_caps);
 	if (status) {
+		dev_dbg(dev, "Failed to discover device capabilities, status %s aq_err %s\n",
+			ice_stat_str(status), ice_aq_str(hw->adminq.sq_last_status));
+		NL_SET_ERR_MSG_MOD(extack, "Unable to discover device capabilities");
 		err = -EIO;
 		goto out_free_ctx;
 	}

drivers/net/ethernet/intel/ice/ice_ethtool.c

@@ -3462,13 +3462,9 @@ static int
 ice_get_rc_coalesce(struct ethtool_coalesce *ec, enum ice_container_type c_type,
 		    struct ice_ring_container *rc)
 {
-	struct ice_pf *pf;
-
 	if (!rc->ring)
 		return -EINVAL;
 
-	pf = rc->ring->vsi->back;
-
 	switch (c_type) {
 	case ICE_RX_CONTAINER:
 		ec->use_adaptive_rx_coalesce = ITR_IS_DYNAMIC(rc);
@@ -3480,7 +3476,7 @@ ice_get_rc_coalesce(struct ethtool_coalesce *ec, enum ice_container_type c_type,
 		ec->tx_coalesce_usecs = rc->itr_setting;
 		break;
 	default:
-		dev_dbg(ice_pf_to_dev(pf), "Invalid c_type %d\n", c_type);
+		dev_dbg(ice_pf_to_dev(rc->ring->vsi->back), "Invalid c_type %d\n", c_type);
 		return -EINVAL;
 	}
 

drivers/net/ethernet/intel/ice/ice_fw_update.c

@@ -702,6 +702,16 @@ int ice_flash_pldm_image(struct ice_pf *pf, const struct firmware *fw,
 	}
 
 	err = pldmfw_flash_image(&priv.context, fw);
+	if (err == -ENOENT) {
+		dev_err(dev, "Firmware image has no record matching this device\n");
+		NL_SET_ERR_MSG_MOD(extack, "Firmware image has no record matching this device");
+	} else if (err) {
+		/* Do not set a generic extended ACK message here. A more
+		 * specific message may already have been set by one of our
+		 * ops.
+		 */
+		dev_err(dev, "Failed to flash PLDM image, err %d", err);
+	}
 
 	ice_release_nvm(hw);
 

drivers/net/ethernet/intel/ice/ice_lib.c

@@ -169,12 +169,13 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id)
 
 	switch (vsi->type) {
 	case ICE_VSI_PF:
-		vsi->alloc_txq = min3(pf->num_lan_msix,
-				      ice_get_avail_txq_count(pf),
-				      (u16)num_online_cpus());
 		if (vsi->req_txq) {
 			vsi->alloc_txq = vsi->req_txq;
 			vsi->num_txq = vsi->req_txq;
+		} else {
+			vsi->alloc_txq = min3(pf->num_lan_msix,
+					      ice_get_avail_txq_count(pf),
+					      (u16)num_online_cpus());
 		}
 
 		pf->num_lan_tx = vsi->alloc_txq;
@@ -183,12 +184,13 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id)
 		if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) {
 			vsi->alloc_rxq = 1;
 		} else {
-			vsi->alloc_rxq = min3(pf->num_lan_msix,
-					      ice_get_avail_rxq_count(pf),
-					      (u16)num_online_cpus());
 			if (vsi->req_rxq) {
 				vsi->alloc_rxq = vsi->req_rxq;
 				vsi->num_rxq = vsi->req_rxq;
+			} else {
+				vsi->alloc_rxq = min3(pf->num_lan_msix,
+						      ice_get_avail_rxq_count(pf),
+						      (u16)num_online_cpus());
 			}
 		}
 
@@ -1693,6 +1695,33 @@ ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio)
 	wr32(hw, QRXFLXP_CNTXT(pf_q), regval);
 }
 
+int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx)
+{
+	if (q_idx >= vsi->num_rxq)
+		return -EINVAL;
+
+	return ice_vsi_cfg_rxq(vsi->rx_rings[q_idx]);
+}
+
+int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_ring **tx_rings, u16 q_idx)
+{
+	struct ice_aqc_add_tx_qgrp *qg_buf;
+	int err;
+
+	if (q_idx >= vsi->alloc_txq || !tx_rings || !tx_rings[q_idx])
+		return -EINVAL;
+
+	qg_buf = kzalloc(struct_size(qg_buf, txqs, 1), GFP_KERNEL);
+	if (!qg_buf)
+		return -ENOMEM;
+
+	qg_buf->num_txqs = 1;
+
+	err = ice_vsi_cfg_txq(vsi, tx_rings[q_idx], qg_buf);
+	kfree(qg_buf);
+	return err;
+}
+
 /**
  * ice_vsi_cfg_rxqs - Configure the VSI for Rx
  * @vsi: the VSI being configured
@@ -1710,15 +1739,11 @@ int ice_vsi_cfg_rxqs(struct ice_vsi *vsi)
 	ice_vsi_cfg_frame_size(vsi);
 setup_rings:
 	/* set up individual rings */
-	for (i = 0; i < vsi->num_rxq; i++) {
-		int err;
+	ice_for_each_rxq(vsi, i) {
+		int err = ice_vsi_cfg_rxq(vsi->rx_rings[i]);
 
-		err = ice_setup_rx_ctx(vsi->rx_rings[i]);
-		if (err) {
-			dev_err(ice_pf_to_dev(vsi->back), "ice_setup_rx_ctx failed for RxQ %d, err %d\n",
-				i, err);
+		if (err)
 			return err;
-		}
 	}
 
 	return 0;
@@ -2226,7 +2251,7 @@ void ice_cfg_sw_lldp(struct ice_vsi *vsi, bool tx, bool create)
 	}
 
 	if (status)
-		dev_err(dev, "Fail %s %s LLDP rule on VSI %i error: %s\n",
+		dev_dbg(dev, "Fail %s %s LLDP rule on VSI %i error: %s\n",
 			create ? "adding" : "removing", tx ? "TX" : "RX",
 			vsi->vsi_num, ice_stat_str(status));
 }
@@ -3205,6 +3230,34 @@ bool ice_is_reset_in_progress(unsigned long *state)
 	       test_bit(ICE_GLOBR_REQ, state);
 }
 
+/**
+ * ice_wait_for_reset - Wait for driver to finish reset and rebuild
+ * @pf: pointer to the PF structure
+ * @timeout: length of time to wait, in jiffies
+ *
+ * Wait (sleep) for a short time until the driver finishes cleaning up from
+ * a device reset. The caller must be able to sleep. Use this to delay
+ * operations that could fail while the driver is cleaning up after a device
+ * reset.
+ *
+ * Returns 0 on success, -EBUSY if the reset is not finished within the
+ * timeout, and -ERESTARTSYS if the thread was interrupted.
+ */
+int ice_wait_for_reset(struct ice_pf *pf, unsigned long timeout)
+{
+	long ret;
+
+	ret = wait_event_interruptible_timeout(pf->reset_wait_queue,
+					       !ice_is_reset_in_progress(pf->state),
+					       timeout);
+	if (ret < 0)
+		return ret;
+	else if (!ret)
+		return -EBUSY;
+	else
+		return 0;
+}
+
 #ifdef CONFIG_DCB
 /**
  * ice_vsi_update_q_map - update our copy of the VSI info with new queue map

drivers/net/ethernet/intel/ice/ice_lib.h

@@ -12,6 +12,10 @@ bool ice_pf_state_is_nominal(struct ice_pf *pf);
 
 void ice_update_eth_stats(struct ice_vsi *vsi);
 
+int ice_vsi_cfg_single_rxq(struct ice_vsi *vsi, u16 q_idx);
+
+int ice_vsi_cfg_single_txq(struct ice_vsi *vsi, struct ice_ring **tx_rings, u16 q_idx);
+
 int ice_vsi_cfg_rxqs(struct ice_vsi *vsi);
 
 int ice_vsi_cfg_lan_txqs(struct ice_vsi *vsi);
@@ -73,6 +77,7 @@ ice_get_res(struct ice_pf *pf, struct ice_res_tracker *res, u16 needed, u16 id);
 int ice_vsi_rebuild(struct ice_vsi *vsi, bool init_vsi);
 
 bool ice_is_reset_in_progress(unsigned long *state);
+int ice_wait_for_reset(struct ice_pf *pf, unsigned long timeout);
 
 void
 ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio);

drivers/net/ethernet/intel/ice/ice_main.c

@@ -503,6 +503,7 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
 		clear_bit(ICE_PFR_REQ, pf->state);
 		clear_bit(ICE_CORER_REQ, pf->state);
 		clear_bit(ICE_GLOBR_REQ, pf->state);
+		wake_up(&pf->reset_wait_queue);
 		return;
 	}
 
@@ -515,6 +516,7 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
 		ice_rebuild(pf, reset_type);
 		clear_bit(ICE_PREPARED_FOR_RESET, pf->state);
 		clear_bit(ICE_PFR_REQ, pf->state);
+		wake_up(&pf->reset_wait_queue);
 		ice_reset_all_vfs(pf, true);
 	}
 }
@@ -565,6 +567,7 @@ static void ice_reset_subtask(struct ice_pf *pf)
 			clear_bit(ICE_PFR_REQ, pf->state);
 			clear_bit(ICE_CORER_REQ, pf->state);
 			clear_bit(ICE_GLOBR_REQ, pf->state);
+			wake_up(&pf->reset_wait_queue);
 			ice_reset_all_vfs(pf, true);
 		}
 
@@ -861,6 +864,38 @@ static void ice_set_dflt_mib(struct ice_pf *pf)
 	kfree(lldpmib);
 }
 
+/**
+ * ice_check_module_power
+ * @pf: pointer to PF struct
+ * @link_cfg_err: bitmap from the link info structure
+ *
+ * check module power level returned by a previous call to aq_get_link_info
+ * and print error messages if module power level is not supported
+ */
+static void ice_check_module_power(struct ice_pf *pf, u8 link_cfg_err)
+{
+	/* if module power level is supported, clear the flag */
+	if (!(link_cfg_err & (ICE_AQ_LINK_INVAL_MAX_POWER_LIMIT |
+			      ICE_AQ_LINK_MODULE_POWER_UNSUPPORTED))) {
+		clear_bit(ICE_FLAG_MOD_POWER_UNSUPPORTED, pf->flags);
+		return;
+	}
+
+	/* if ICE_FLAG_MOD_POWER_UNSUPPORTED was previously set and the
+	 * above block didn't clear this bit, there's nothing to do
+	 */
+	if (test_bit(ICE_FLAG_MOD_POWER_UNSUPPORTED, pf->flags))
+		return;
+
+	if (link_cfg_err & ICE_AQ_LINK_INVAL_MAX_POWER_LIMIT) {
+		dev_err(ice_pf_to_dev(pf), "The installed module is incompatible with the device's NVM image. Cannot start link\n");
+		set_bit(ICE_FLAG_MOD_POWER_UNSUPPORTED, pf->flags);
+	} else if (link_cfg_err & ICE_AQ_LINK_MODULE_POWER_UNSUPPORTED) {
+		dev_err(ice_pf_to_dev(pf), "The module's power requirements exceed the device's power supply. Cannot start link\n");
+		set_bit(ICE_FLAG_MOD_POWER_UNSUPPORTED, pf->flags);
+	}
+}
+
 /**
  * ice_link_event - process the link event
  * @pf: PF that the link event is associated with
@@ -896,6 +931,8 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up,
 			pi->lport, ice_stat_str(status),
 			ice_aq_str(pi->hw->adminq.sq_last_status));
 
+	ice_check_module_power(pf, pi->phy.link_info.link_cfg_err);
+
 	/* Check if the link state is up after updating link info, and treat
 	 * this event as an UP event since the link is actually UP now.
 	 */
@@ -2010,6 +2047,8 @@ static void ice_check_media_subtask(struct ice_pf *pf)
 	if (err)
 		return;
 
+	ice_check_module_power(pf, pi->phy.link_info.link_cfg_err);
+
 	if (pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) {
 		if (!test_bit(ICE_PHY_INIT_COMPLETE, pf->state))
 			ice_init_phy_user_cfg(pi);
@@ -3343,6 +3382,8 @@ static int ice_init_pf(struct ice_pf *pf)
 	spin_lock_init(&pf->aq_wait_lock);
 	init_waitqueue_head(&pf->aq_wait_queue);
 
+	init_waitqueue_head(&pf->reset_wait_queue);
+
 	/* setup service timer and periodic service task */
 	timer_setup(&pf->serv_tmr, ice_service_timer, 0);
 	pf->serv_tmr_period = HZ;
@@ -4264,6 +4305,8 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent)
 
 	ice_init_link_dflt_override(pf->hw.port_info);
 
+	ice_check_module_power(pf, pf->hw.port_info->phy.link_info.link_cfg_err);
+
 	/* if media available, initialize PHY settings */
 	if (pf->hw.port_info->phy.link_info.link_info &
 	    ICE_AQ_MEDIA_AVAILABLE) {
@@ -6213,6 +6256,12 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 
 	ice_clear_pxe_mode(hw);
 
+	ret = ice_init_nvm(hw);
+	if (ret) {
+		dev_err(dev, "ice_init_nvm failed %s\n", ice_stat_str(ret));
+		goto err_init_ctrlq;
+	}
+
 	ret = ice_get_caps(hw);
 	if (ret) {
 		dev_err(dev, "ice_get_caps failed %s\n", ice_stat_str(ret));
@@ -6918,6 +6967,8 @@ int ice_open_internal(struct net_device *netdev)
 		return -EIO;
 	}
 
+	ice_check_module_power(pf, pi->phy.link_info.link_cfg_err);
+
 	/* Set PHY if there is media, otherwise, turn off PHY */
 	if (pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) {
 		clear_bit(ICE_FLAG_NO_MEDIA, pf->flags);

drivers/net/ethernet/intel/ice/ice_type.h

@@ -64,7 +64,7 @@ enum ice_aq_res_ids {
 /* FW update timeout definitions are in milliseconds */
 #define ICE_NVM_TIMEOUT			180000
 #define ICE_CHANGE_LOCK_TIMEOUT		1000
-#define ICE_GLOBAL_CFG_LOCK_TIMEOUT	3000
+#define ICE_GLOBAL_CFG_LOCK_TIMEOUT	5000
 
 enum ice_aq_res_access_type {
 	ICE_RES_READ = 1,
@@ -147,6 +147,7 @@ struct ice_link_status {
 	u16 max_frame_size;
 	u16 link_speed;
 	u16 req_speeds;
+	u8 link_cfg_err;
 	u8 lse_ena;	/* Link Status Event notification */
 	u8 link_info;
 	u8 an_info;

drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h

@@ -58,6 +58,11 @@ enum ice_virtchnl_cap {
 	ICE_VIRTCHNL_VF_CAP_PRIVILEGE,
 };
 
+struct ice_time_mac {
+	unsigned long time_modified;
+	u8 addr[ETH_ALEN];
+};
+
 /* VF MDD events print structure */
 struct ice_mdd_vf_events {
 	u16 count;			/* total count of Rx|Tx events */
@@ -78,7 +83,9 @@ struct ice_vf {
 	struct ice_sw *vf_sw_id;	/* switch ID the VF VSIs connect to */
 	struct virtchnl_version_info vf_ver;
 	u32 driver_caps;		/* reported by VF driver */
-	struct virtchnl_ether_addr dflt_lan_addr;
+	struct virtchnl_ether_addr dev_lan_addr;
+	struct virtchnl_ether_addr hw_lan_addr;
+	struct ice_time_mac legacy_last_added_umac;
 	DECLARE_BITMAP(txq_ena, ICE_MAX_RSS_QS_PER_VF);
 	DECLARE_BITMAP(rxq_ena, ICE_MAX_RSS_QS_PER_VF);
 	u16 port_vlan_info;		/* Port VLAN ID and QoS */
@@ -151,16 +158,18 @@ ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode,
 		      enum virtchnl_status_code v_retval, u8 *msg, u16 msglen);
 bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id);
 #else /* CONFIG_PCI_IOV */
-#define ice_process_vflr_event(pf) do {} while (0)
-#define ice_free_vfs(pf) do {} while (0)
-#define ice_vc_process_vf_msg(pf, event) do {} while (0)
-#define ice_vc_notify_link_state(pf) do {} while (0)
-#define ice_vc_notify_reset(pf) do {} while (0)
-#define ice_set_vf_state_qs_dis(vf) do {} while (0)
-#define ice_vf_lan_overflow_event(pf, event) do {} while (0)
-#define ice_print_vfs_mdd_events(pf) do {} while (0)
-#define ice_print_vf_rx_mdd_event(vf) do {} while (0)
-#define ice_restore_all_vfs_msi_state(pdev) do {} while (0)
+static inline void ice_process_vflr_event(struct ice_pf *pf) { }
+static inline void ice_free_vfs(struct ice_pf *pf) { }
+static inline
+void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) { }
+static inline void ice_vc_notify_link_state(struct ice_pf *pf) { }
+static inline void ice_vc_notify_reset(struct ice_pf *pf) { }
+static inline void ice_set_vf_state_qs_dis(struct ice_vf *vf) { }
+static inline
+void ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event) { }
+static inline void ice_print_vfs_mdd_events(struct ice_pf *pf) { }
+static inline void ice_print_vf_rx_mdd_event(struct ice_vf *vf) { }
+static inline void ice_restore_all_vfs_msi_state(struct pci_dev *pdev) { }
 
 static inline bool
 ice_is_malicious_vf(struct ice_pf __always_unused *pf,

drivers/net/ethernet/intel/ice/ice_xsk.c

@@ -236,7 +236,7 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
 		xdp_ring->xsk_pool = ice_xsk_pool(xdp_ring);
 	}
 
-	err = ice_setup_rx_ctx(rx_ring);
+	err = ice_vsi_cfg_rxq(rx_ring);
 	if (err)
 		goto free_buf;
 

drivers/net/ethernet/intel/ice/ice_xsk.h

@@ -60,7 +60,7 @@ ice_xsk_wakeup(struct net_device __always_unused *netdev,
 	return -EOPNOTSUPP;
 }
 
-#define ice_xsk_clean_rx_ring(rx_ring) do {} while (0)
-#define ice_xsk_clean_xdp_ring(xdp_ring) do {} while (0)
+static inline void ice_xsk_clean_rx_ring(struct ice_ring *rx_ring) { }
+static inline void ice_xsk_clean_xdp_ring(struct ice_ring *xdp_ring) { }
 #endif /* CONFIG_XDP_SOCKETS */
 #endif /* !_ICE_XSK_H_ */

include/linux/avf/virtchnl.h

@@ -412,9 +412,36 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_queue_select);
  * PF removes the filters and returns status.
  */
 
+/* VIRTCHNL_ETHER_ADDR_LEGACY
+ * Prior to adding the @type member to virtchnl_ether_addr, there were 2 pad
+ * bytes. Moving forward all VF drivers should not set type to
+ * VIRTCHNL_ETHER_ADDR_LEGACY. This is only here to not break previous/legacy
+ * behavior. The control plane function (i.e. PF) can use a best effort method
+ * of tracking the primary/device unicast in this case, but there is no
+ * guarantee and functionality depends on the implementation of the PF.
+ */
+
+/* VIRTCHNL_ETHER_ADDR_PRIMARY
+ * All VF drivers should set @type to VIRTCHNL_ETHER_ADDR_PRIMARY for the
+ * primary/device unicast MAC address filter for VIRTCHNL_OP_ADD_ETH_ADDR and
+ * VIRTCHNL_OP_DEL_ETH_ADDR. This allows for the underlying control plane
+ * function (i.e. PF) to accurately track and use this MAC address for
+ * displaying on the host and for VM/function reset.
+ */
+
+/* VIRTCHNL_ETHER_ADDR_EXTRA
+ * All VF drivers should set @type to VIRTCHNL_ETHER_ADDR_EXTRA for any extra
+ * unicast and/or multicast filters that are being added/deleted via
+ * VIRTCHNL_OP_DEL_ETH_ADDR/VIRTCHNL_OP_ADD_ETH_ADDR respectively.
+ */
 struct virtchnl_ether_addr {
 	u8 addr[ETH_ALEN];
-	u8 pad[2];
+	u8 type;
+#define VIRTCHNL_ETHER_ADDR_LEGACY	0
+#define VIRTCHNL_ETHER_ADDR_PRIMARY	1
+#define VIRTCHNL_ETHER_ADDR_EXTRA	2
+#define VIRTCHNL_ETHER_ADDR_TYPE_MASK	3 /* first two bits of type are valid */
+	u8 pad;
 };
 
 VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_ether_addr);