Merge tag 'loongarch-kvm-6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson into HEAD

LoongArch KVM changes for v6.11

1. Add ParaVirt steal time support.
2. Add some VM migration enhancement.
3. Add perf kvm-stat support for loongarch.

12 files changed, 387 insertions, 139 deletions

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 6ad8002b22e1..99a75a59078e 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -409,7 +409,6 @@ struct ice_vsi {
 	struct ice_tc_cfg tc_cfg;
 	struct bpf_prog *xdp_prog;
 	struct ice_tx_ring **xdp_rings;	 /* XDP ring array */
-	unsigned long *af_xdp_zc_qps;	 /* tracks AF_XDP ZC enabled qps */
 	u16 num_xdp_txq;		 /* Used XDP queues */
 	u8 xdp_mapping_mode;		 /* ICE_MAP_MODE_[CONTIG|SCATTER] */
 
@@ -747,6 +746,25 @@ static inline void ice_set_ring_xdp(struct ice_tx_ring *ring)
 }
 
 /**
+ * ice_get_xp_from_qid - get ZC XSK buffer pool bound to a queue ID
+ * @vsi: pointer to VSI
+ * @qid: index of a queue to look at XSK buff pool presence
+ *
+ * Return: A pointer to xsk_buff_pool structure if there is a buffer pool
+ * attached and configured as zero-copy, NULL otherwise.
+ */
+static inline struct xsk_buff_pool *ice_get_xp_from_qid(struct ice_vsi *vsi,
+							u16 qid)
+{
+	struct xsk_buff_pool *pool = xsk_get_pool_from_qid(vsi->netdev, qid);
+
+	if (!ice_is_xdp_ena_vsi(vsi))
+		return NULL;
+
+	return (pool && pool->dev) ? pool : NULL;
+}
+
+/**
  * ice_xsk_pool - get XSK buffer pool bound to a ring
  * @ring: Rx ring to use
  *
@@ -758,10 +776,7 @@ static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring)
 	struct ice_vsi *vsi = ring->vsi;
 	u16 qid = ring->q_index;
 
-	if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps))
-		return NULL;
-
-	return xsk_get_pool_from_qid(vsi->netdev, qid);
+	return ice_get_xp_from_qid(vsi, qid);
 }
 
 /**
@@ -786,12 +801,7 @@ static inline void ice_tx_xsk_pool(struct ice_vsi *vsi, u16 qid)
 	if (!ring)
 		return;
 
-	if (!ice_is_xdp_ena_vsi(vsi) || !test_bit(qid, vsi->af_xdp_zc_qps)) {
-		ring->xsk_pool = NULL;
-		return;
-	}
-
-	ring->xsk_pool = xsk_get_pool_from_qid(vsi->netdev, qid);
+	ring->xsk_pool = ice_get_xp_from_qid(vsi, qid);
 }
 
 /**
@@ -920,9 +930,17 @@ int ice_down(struct ice_vsi *vsi);
 int ice_down_up(struct ice_vsi *vsi);
 int ice_vsi_cfg_lan(struct ice_vsi *vsi);
 struct ice_vsi *ice_lb_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi);
+
+enum ice_xdp_cfg {
+	ICE_XDP_CFG_FULL,	/* Fully apply new config in .ndo_bpf() */
+	ICE_XDP_CFG_PART,	/* Save/use part of config in VSI rebuild */
+};
+
 int ice_vsi_determine_xdp_res(struct ice_vsi *vsi);
-int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog);
-int ice_destroy_xdp_rings(struct ice_vsi *vsi);
+int ice_prepare_xdp_rings(struct ice_vsi *vsi, struct bpf_prog *prog,
+			  enum ice_xdp_cfg cfg_type);
+int ice_destroy_xdp_rings(struct ice_vsi *vsi, enum ice_xdp_cfg cfg_type);
+void ice_map_xdp_rings(struct ice_vsi *vsi);
 int
 ice_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 	     u32 flags);
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 687f6cb2b917..5d396c1a7731 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -842,6 +842,9 @@ void ice_vsi_map_rings_to_vectors(struct ice_vsi *vsi)
 		}
 		rx_rings_rem -= rx_rings_per_v;
 	}
+
+	if (ice_is_xdp_ena_vsi(vsi))
+		ice_map_xdp_rings(vsi);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c
index ce5034ed2b24..f182179529b7 100644
--- a/drivers/net/ethernet/intel/ice/ice_ddp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.c
@@ -1339,6 +1339,7 @@ ice_dwnld_cfg_bufs_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 start,
 
 	for (i = 0; i < count; i++) {
 		bool last = false;
+		int try_cnt = 0;
 		int status;
 
 		bh = (struct ice_buf_hdr *)(bufs + start + i);
@@ -1346,8 +1347,26 @@ ice_dwnld_cfg_bufs_no_lock(struct ice_hw *hw, struct ice_buf *bufs, u32 start,
 		if (indicate_last)
 			last = ice_is_last_download_buffer(bh, i, count);
 
-		status = ice_aq_download_pkg(hw, bh, ICE_PKG_BUF_SIZE, last,
-					     &offset, &info, NULL);
+		while (1) {
+			status = ice_aq_download_pkg(hw, bh, ICE_PKG_BUF_SIZE,
+						     last, &offset, &info,
+						     NULL);
+			if (hw->adminq.sq_last_status != ICE_AQ_RC_ENOSEC &&
+			    hw->adminq.sq_last_status != ICE_AQ_RC_EBADSIG)
+				break;
+
+			try_cnt++;
+
+			if (try_cnt == 5)
+				break;
+
+			msleep(20);
+		}
+
+		if (try_cnt)
+			dev_dbg(ice_hw_to_dev(hw),
+				"ice_aq_download_pkg number of retries: %d\n",
+				try_cnt);
 
 		/* Save AQ status from download package */
 		if (status) {
diff --git a/drivers/net/ethernet/intel/ice/ice_hwmon.c b/drivers/net/ethernet/intel/ice/ice_hwmon.c
index e4c2c1bff6c0..b7aa6812510a 100644
--- a/drivers/net/ethernet/intel/ice/ice_hwmon.c
+++ b/drivers/net/ethernet/intel/ice/ice_hwmon.c
@@ -96,7 +96,7 @@ static bool ice_is_internal_reading_supported(struct ice_pf *pf)
 
 	unsigned long sensors = pf->hw.dev_caps.supported_sensors;
 
-	return _test_bit(ICE_SENSOR_SUPPORT_E810_INT_TEMP_BIT, &sensors);
+	return test_bit(ICE_SENSOR_SUPPORT_E810_INT_TEMP_BIT, &sensors);
 };
 
 void ice_hwmon_init(struct ice_pf *pf)
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 5371e91f6bbb..7629b0190578 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -114,14 +114,8 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi)
 	if (!vsi->q_vectors)
 		goto err_vectors;
 
-	vsi->af_xdp_zc_qps = bitmap_zalloc(max_t(int, vsi->alloc_txq, vsi->alloc_rxq), GFP_KERNEL);
-	if (!vsi->af_xdp_zc_qps)
-		goto err_zc_qps;
-
 	return 0;
 
-err_zc_qps:
-	devm_kfree(dev, vsi->q_vectors);
 err_vectors:
 	devm_kfree(dev, vsi->rxq_map);
 err_rxq_map:
@@ -309,8 +303,6 @@ static void ice_vsi_free_arrays(struct ice_vsi *vsi)
 
 	dev = ice_pf_to_dev(pf);
 
-	bitmap_free(vsi->af_xdp_zc_qps);
-	vsi->af_xdp_zc_qps = NULL;
 	/* free the ring and vector containers */
 	devm_kfree(dev, vsi->q_vectors);
 	vsi->q_vectors = NULL;
@@ -2282,22 +2274,23 @@ static int ice_vsi_cfg_def(struct ice_vsi *vsi)
 		if (ret)
 			goto unroll_vector_base;
 
-		ice_vsi_map_rings_to_vectors(vsi);
-
-		/* Associate q_vector rings to napi */
-		ice_vsi_set_napi_queues(vsi);
-
-		vsi->stat_offsets_loaded = false;
-
 		if (ice_is_xdp_ena_vsi(vsi)) {
 			ret = ice_vsi_determine_xdp_res(vsi);
 			if (ret)
 				goto unroll_vector_base;
-			ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog);
+			ret = ice_prepare_xdp_rings(vsi, vsi->xdp_prog,
+						    ICE_XDP_CFG_PART);
 			if (ret)
 				goto unroll_vector_base;
 		}
 
+		ice_vsi_map_rings_to_vectors(vsi);
+
+		/* Associate q_vector rings to napi */
+		ice_vsi_set_napi_queues(vsi);
+
+		vsi->stat_offsets_loaded = false;
+
 		/* ICE_VSI_CTRL does not need RSS so skip RSS processing */
 		if (vsi->type != ICE_VSI_CTRL)
 			/* Do not exit if configuring RSS had an issue, at
@@ -2437,7 +2430,7 @@ void ice_vsi_decfg(struct ice_vsi *vsi)
 		/* return value check can be skipped here, it always returns
 		 * 0 if reset is in progress
 		 */
-		ice_destroy_xdp_rings(vsi);
+		ice_destroy_xdp_rings(vsi, ICE_XDP_CFG_PART);
 
 	ice_vsi_clear_rings(vsi);
 	ice_vsi_free_q_vectors(vsi);
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index f60c022f7960..55a42aad92a5 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -805,6 +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;
@@ -2707,17 +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,
@@ -2730,8 +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,
@@ -2750,49 +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
 	 */
@@ -2842,22 +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) {
@@ -2898,7 +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);
@@ -3009,7 +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");
 		}
@@ -3020,7 +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 */
@@ -4116,7 +4139,7 @@ bool ice_is_wol_supported(struct ice_hw *hw)
 int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked)
 {
 	struct ice_pf *pf = vsi->back;
-	int err = 0, timeout = 50;
+	int i, err = 0, timeout = 50;
 
 	if (!new_rx && !new_tx)
 		return -EINVAL;
@@ -4142,6 +4165,14 @@ int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked)
 
 	ice_vsi_close(vsi);
 	ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT);
+
+	ice_for_each_traffic_class(i) {
+		if (vsi->tc_cfg.ena_tc & BIT(i))
+			netdev_set_tc_queue(vsi->netdev,
+					    vsi->tc_cfg.tc_info[i].netdev_tc,
+					    vsi->tc_cfg.tc_info[i].qcount_tx,
+					    vsi->tc_cfg.tc_info[i].qoffset);
+	}
 	ice_pf_dcb_recfg(pf, locked);
 	ice_vsi_open(vsi);
 done:
@@ -5544,7 +5575,7 @@ static int 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)) {
@@ -5624,6 +5655,11 @@ static int 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;
diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c
index 84eab92dc03c..59e8879ac059 100644
--- a/drivers/net/ethernet/intel/ice/ice_nvm.c
+++ b/drivers/net/ethernet/intel/ice/ice_nvm.c
@@ -374,11 +374,25 @@ ice_read_nvm_module(struct ice_hw *hw, enum ice_bank_select bank, u32 offset, u1
  *
  * Read the specified word from the copy of the Shadow RAM found in the
  * specified NVM module.
+ *
+ * Note that the Shadow RAM copy is always located after the CSS header, and
+ * is aligned to 64-byte (32-word) offsets.
  */
 static int
 ice_read_nvm_sr_copy(struct ice_hw *hw, enum ice_bank_select bank, u32 offset, u16 *data)
 {
-	return ice_read_nvm_module(hw, bank, ICE_NVM_SR_COPY_WORD_OFFSET + offset, data);
+	u32 sr_copy;
+
+	switch (bank) {
+	case ICE_ACTIVE_FLASH_BANK:
+		sr_copy = roundup(hw->flash.banks.active_css_hdr_len, 32);
+		break;
+	case ICE_INACTIVE_FLASH_BANK:
+		sr_copy = roundup(hw->flash.banks.inactive_css_hdr_len, 32);
+		break;
+	}
+
+	return ice_read_nvm_module(hw, bank, sr_copy + offset, data);
 }
 
 /**
@@ -440,8 +454,7 @@ int
 ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len,
 		       u16 module_type)
 {
-	u16 pfa_len, pfa_ptr;
-	u16 next_tlv;
+	u16 pfa_len, pfa_ptr, next_tlv, max_tlv;
 	int status;
 
 	status = ice_read_sr_word(hw, ICE_SR_PFA_PTR, &pfa_ptr);
@@ -454,11 +467,23 @@ ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len,
 		ice_debug(hw, ICE_DBG_INIT, "Failed to read PFA length.\n");
 		return status;
 	}
+
+	/* The Preserved Fields Area contains a sequence of Type-Length-Value
+	 * structures which define its contents. The PFA length includes all
+	 * of the TLVs, plus the initial length word itself, *and* one final
+	 * word at the end after all of the TLVs.
+	 */
+	if (check_add_overflow(pfa_ptr, pfa_len - 1, &max_tlv)) {
+		dev_warn(ice_hw_to_dev(hw), "PFA starts at offset %u. PFA length of %u caused 16-bit arithmetic overflow.\n",
+			 pfa_ptr, pfa_len);
+		return -EINVAL;
+	}
+
 	/* Starting with first TLV after PFA length, iterate through the list
 	 * of TLVs to find the requested one.
 	 */
 	next_tlv = pfa_ptr + 1;
-	while (next_tlv < pfa_ptr + pfa_len) {
+	while (next_tlv < max_tlv) {
 		u16 tlv_sub_module_type;
 		u16 tlv_len;
 
@@ -482,10 +507,13 @@ ice_get_pfa_module_tlv(struct ice_hw *hw, u16 *module_tlv, u16 *module_tlv_len,
 			}
 			return -EINVAL;
 		}
-		/* Check next TLV, i.e. current TLV pointer + length + 2 words
-		 * (for current TLV's type and length)
-		 */
-		next_tlv = next_tlv + tlv_len + 2;
+
+		if (check_add_overflow(next_tlv, 2, &next_tlv) ||
+		    check_add_overflow(next_tlv, tlv_len, &next_tlv)) {
+			dev_warn(ice_hw_to_dev(hw), "TLV of type %u and length 0x%04x caused 16-bit arithmetic overflow. The PFA starts at 0x%04x and has length of 0x%04x\n",
+				 tlv_sub_module_type, tlv_len, pfa_ptr, pfa_len);
+			return -EINVAL;
+		}
 	}
 	/* Module does not exist */
 	return -ENOENT;
@@ -1010,6 +1038,72 @@ static int ice_determine_active_flash_banks(struct ice_hw *hw)
 }
 
 /**
+ * ice_get_nvm_css_hdr_len - Read the CSS header length from the NVM CSS header
+ * @hw: pointer to the HW struct
+ * @bank: whether to read from the active or inactive flash bank
+ * @hdr_len: storage for header length in words
+ *
+ * Read the CSS header length from the NVM CSS header and add the Authentication
+ * header size, and then convert to words.
+ *
+ * Return: zero on success, or a negative error code on failure.
+ */
+static int
+ice_get_nvm_css_hdr_len(struct ice_hw *hw, enum ice_bank_select bank,
+			u32 *hdr_len)
+{
+	u16 hdr_len_l, hdr_len_h;
+	u32 hdr_len_dword;
+	int status;
+
+	status = ice_read_nvm_module(hw, bank, ICE_NVM_CSS_HDR_LEN_L,
+				     &hdr_len_l);
+	if (status)
+		return status;
+
+	status = ice_read_nvm_module(hw, bank, ICE_NVM_CSS_HDR_LEN_H,
+				     &hdr_len_h);
+	if (status)
+		return status;
+
+	/* CSS header length is in DWORD, so convert to words and add
+	 * authentication header size
+	 */
+	hdr_len_dword = hdr_len_h << 16 | hdr_len_l;
+	*hdr_len = (hdr_len_dword * 2) + ICE_NVM_AUTH_HEADER_LEN;
+
+	return 0;
+}
+
+/**
+ * ice_determine_css_hdr_len - Discover CSS header length for the device
+ * @hw: pointer to the HW struct
+ *
+ * Determine the size of the CSS header at the start of the NVM module. This
+ * is useful for locating the Shadow RAM copy in the NVM, as the Shadow RAM is
+ * always located just after the CSS header.
+ *
+ * Return: zero on success, or a negative error code on failure.
+ */
+static int ice_determine_css_hdr_len(struct ice_hw *hw)
+{
+	struct ice_bank_info *banks = &hw->flash.banks;
+	int status;
+
+	status = ice_get_nvm_css_hdr_len(hw, ICE_ACTIVE_FLASH_BANK,
+					 &banks->active_css_hdr_len);
+	if (status)
+		return status;
+
+	status = ice_get_nvm_css_hdr_len(hw, ICE_INACTIVE_FLASH_BANK,
+					 &banks->inactive_css_hdr_len);
+	if (status)
+		return status;
+
+	return 0;
+}
+
+/**
  * ice_init_nvm - initializes NVM setting
  * @hw: pointer to the HW struct
  *
@@ -1055,6 +1149,12 @@ int ice_init_nvm(struct ice_hw *hw)
 		return status;
 	}
 
+	status = ice_determine_css_hdr_len(hw);
+	if (status) {
+		ice_debug(hw, ICE_DBG_NVM, "Failed to determine Shadow RAM copy offsets.\n");
+		return status;
+	}
+
 	status = ice_get_nvm_ver_info(hw, ICE_ACTIVE_FLASH_BANK, &flash->nvm);
 	if (status) {
 		ice_debug(hw, ICE_DBG_INIT, "Failed to read NVM info.\n");
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 0f17fc1181d2..fefaf52fd677 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -1559,6 +1559,10 @@ void ice_ptp_extts_event(struct ice_pf *pf)
 	u8 chan, tmr_idx;
 	u32 hi, lo;
 
+	/* Don't process timestamp events if PTP is not ready */
+	if (pf->ptp.state != ICE_PTP_READY)
+		return;
+
 	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
 	/* Event time is captured by one of the two matched registers
 	 *      GLTSYN_EVNT_L: 32 LSB of sampled time event
@@ -1584,27 +1588,33 @@ void ice_ptp_extts_event(struct ice_pf *pf)
 /**
  * ice_ptp_cfg_extts - Configure EXTTS pin and channel
  * @pf: Board private structure
- * @ena: true to enable; false to disable
  * @chan: GPIO channel (0-3)
- * @gpio_pin: GPIO pin
- * @extts_flags: request flags from the ptp_extts_request.flags
+ * @config: desired EXTTS configuration.
+ * @store: If set to true, the values will be stored
+ *
+ * Configure an external timestamp event on the requested channel.
+ *
+ * Return: 0 on success, -EOPNOTUSPP on unsupported flags
  */
-static int
-ice_ptp_cfg_extts(struct ice_pf *pf, bool ena, unsigned int chan, u32 gpio_pin,
-		  unsigned int extts_flags)
+static int ice_ptp_cfg_extts(struct ice_pf *pf, unsigned int chan,
+			     struct ice_extts_channel *config, bool store)
 {
 	u32 func, aux_reg, gpio_reg, irq_reg;
 	struct ice_hw *hw = &pf->hw;
 	u8 tmr_idx;
 
-	if (chan > (unsigned int)pf->ptp.info.n_ext_ts)
-		return -EINVAL;
+	/* Reject requests with unsupported flags */
+	if (config->flags & ~(PTP_ENABLE_FEATURE |
+			      PTP_RISING_EDGE |
+			      PTP_FALLING_EDGE |
+			      PTP_STRICT_FLAGS))
+		return -EOPNOTSUPP;
 
 	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
 
 	irq_reg = rd32(hw, PFINT_OICR_ENA);
 
-	if (ena) {
+	if (config->ena) {
 		/* Enable the interrupt */
 		irq_reg |= PFINT_OICR_TSYN_EVNT_M;
 		aux_reg = GLTSYN_AUX_IN_0_INT_ENA_M;
@@ -1613,9 +1623,9 @@ ice_ptp_cfg_extts(struct ice_pf *pf, bool ena, unsigned int chan, u32 gpio_pin,
 #define GLTSYN_AUX_IN_0_EVNTLVL_FALLING_EDGE	BIT(1)
 
 		/* set event level to requested edge */
-		if (extts_flags & PTP_FALLING_EDGE)
+		if (config->flags & PTP_FALLING_EDGE)
 			aux_reg |= GLTSYN_AUX_IN_0_EVNTLVL_FALLING_EDGE;
-		if (extts_flags & PTP_RISING_EDGE)
+		if (config->flags & PTP_RISING_EDGE)
 			aux_reg |= GLTSYN_AUX_IN_0_EVNTLVL_RISING_EDGE;
 
 		/* Write GPIO CTL reg.
@@ -1636,12 +1646,52 @@ ice_ptp_cfg_extts(struct ice_pf *pf, bool ena, unsigned int chan, u32 gpio_pin,
 
 	wr32(hw, PFINT_OICR_ENA, irq_reg);
 	wr32(hw, GLTSYN_AUX_IN(chan, tmr_idx), aux_reg);
-	wr32(hw, GLGEN_GPIO_CTL(gpio_pin), gpio_reg);
+	wr32(hw, GLGEN_GPIO_CTL(config->gpio_pin), gpio_reg);
+
+	if (store)
+		memcpy(&pf->ptp.extts_channels[chan], config, sizeof(*config));
 
 	return 0;
 }
 
 /**
+ * ice_ptp_disable_all_extts - Disable all EXTTS channels
+ * @pf: Board private structure
+ */
+static void ice_ptp_disable_all_extts(struct ice_pf *pf)
+{
+	struct ice_extts_channel extts_cfg = {};
+	int i;
+
+	for (i = 0; i < pf->ptp.info.n_ext_ts; i++) {
+		if (pf->ptp.extts_channels[i].ena) {
+			extts_cfg.gpio_pin = pf->ptp.extts_channels[i].gpio_pin;
+			extts_cfg.ena = false;
+			ice_ptp_cfg_extts(pf, i, &extts_cfg, false);
+		}
+	}
+
+	synchronize_irq(pf->oicr_irq.virq);
+}
+
+/**
+ * ice_ptp_enable_all_extts - Enable all EXTTS channels
+ * @pf: Board private structure
+ *
+ * Called during reset to restore user configuration.
+ */
+static void ice_ptp_enable_all_extts(struct ice_pf *pf)
+{
+	int i;
+
+	for (i = 0; i < pf->ptp.info.n_ext_ts; i++) {
+		if (pf->ptp.extts_channels[i].ena)
+			ice_ptp_cfg_extts(pf, i, &pf->ptp.extts_channels[i],
+					  false);
+	}
+}
+
+/**
  * ice_ptp_cfg_clkout - Configure clock to generate periodic wave
  * @pf: Board private structure
  * @chan: GPIO channel (0-3)
@@ -1659,6 +1709,9 @@ static int ice_ptp_cfg_clkout(struct ice_pf *pf, unsigned int chan,
 	u32 func, val, gpio_pin;
 	u8 tmr_idx;
 
+	if (config && config->flags & ~PTP_PEROUT_PHASE)
+		return -EOPNOTSUPP;
+
 	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
 
 	/* 0. Reset mode & out_en in AUX_OUT */
@@ -1795,17 +1848,18 @@ ice_ptp_gpio_enable_e810(struct ptp_clock_info *info,
 			 struct ptp_clock_request *rq, int on)
 {
 	struct ice_pf *pf = ptp_info_to_pf(info);
-	struct ice_perout_channel clk_cfg = {0};
 	bool sma_pres = false;
 	unsigned int chan;
 	u32 gpio_pin;
-	int err;
 
 	if (ice_is_feature_supported(pf, ICE_F_SMA_CTRL))
 		sma_pres = true;
 
 	switch (rq->type) {
 	case PTP_CLK_REQ_PEROUT:
+	{
+		struct ice_perout_channel clk_cfg = {};
+
 		chan = rq->perout.index;
 		if (sma_pres) {
 			if (chan == ice_pin_desc_e810t[SMA1].chan)
@@ -1825,15 +1879,19 @@ ice_ptp_gpio_enable_e810(struct ptp_clock_info *info,
 			clk_cfg.gpio_pin = chan;
 		}
 
+		clk_cfg.flags = rq->perout.flags;
 		clk_cfg.period = ((rq->perout.period.sec * NSEC_PER_SEC) +
 				   rq->perout.period.nsec);
 		clk_cfg.start_time = ((rq->perout.start.sec * NSEC_PER_SEC) +
 				       rq->perout.start.nsec);
 		clk_cfg.ena = !!on;
 
-		err = ice_ptp_cfg_clkout(pf, chan, &clk_cfg, true);
-		break;
+		return ice_ptp_cfg_clkout(pf, chan, &clk_cfg, true);
+	}
 	case PTP_CLK_REQ_EXTTS:
+	{
+		struct ice_extts_channel extts_cfg = {};
+
 		chan = rq->extts.index;
 		if (sma_pres) {
 			if (chan < ice_pin_desc_e810t[SMA2].chan)
@@ -1849,14 +1907,15 @@ ice_ptp_gpio_enable_e810(struct ptp_clock_info *info,
 			gpio_pin = chan;
 		}
 
-		err = ice_ptp_cfg_extts(pf, !!on, chan, gpio_pin,
-					rq->extts.flags);
-		break;
+		extts_cfg.flags = rq->extts.flags;
+		extts_cfg.gpio_pin = gpio_pin;
+		extts_cfg.ena = !!on;
+
+		return ice_ptp_cfg_extts(pf, chan, &extts_cfg, true);
+	}
 	default:
 		return -EOPNOTSUPP;
 	}
-
-	return err;
 }
 
 /**
@@ -1869,26 +1928,32 @@ static int ice_ptp_gpio_enable_e823(struct ptp_clock_info *info,
 				    struct ptp_clock_request *rq, int on)
 {
 	struct ice_pf *pf = ptp_info_to_pf(info);
-	struct ice_perout_channel clk_cfg = {0};
-	int err;
 
 	switch (rq->type) {
 	case PTP_CLK_REQ_PPS:
+	{
+		struct ice_perout_channel clk_cfg = {};
+
+		clk_cfg.flags = rq->perout.flags;
 		clk_cfg.gpio_pin = PPS_PIN_INDEX;
 		clk_cfg.period = NSEC_PER_SEC;
 		clk_cfg.ena = !!on;
 
-		err = ice_ptp_cfg_clkout(pf, PPS_CLK_GEN_CHAN, &clk_cfg, true);
-		break;
+		return ice_ptp_cfg_clkout(pf, PPS_CLK_GEN_CHAN, &clk_cfg, true);
+	}
 	case PTP_CLK_REQ_EXTTS:
-		err = ice_ptp_cfg_extts(pf, !!on, rq->extts.index,
-					TIME_SYNC_PIN_INDEX, rq->extts.flags);
-		break;
+	{
+		struct ice_extts_channel extts_cfg = {};
+
+		extts_cfg.flags = rq->extts.flags;
+		extts_cfg.gpio_pin = TIME_SYNC_PIN_INDEX;
+		extts_cfg.ena = !!on;
+
+		return ice_ptp_cfg_extts(pf, rq->extts.index, &extts_cfg, true);
+	}
 	default:
 		return -EOPNOTSUPP;
 	}
-
-	return err;
 }
 
 /**
@@ -2720,6 +2785,10 @@ static int ice_ptp_rebuild_owner(struct ice_pf *pf)
 		ice_ptp_restart_all_phy(pf);
 	}
 
+	/* Re-enable all periodic outputs and external timestamp events */
+	ice_ptp_enable_all_clkout(pf);
+	ice_ptp_enable_all_extts(pf);
+
 	return 0;
 }
 
@@ -3275,6 +3344,8 @@ void ice_ptp_release(struct ice_pf *pf)
 
 	ice_ptp_release_tx_tracker(pf, &pf->ptp.port.tx);
 
+	ice_ptp_disable_all_extts(pf);
+
 	kthread_cancel_delayed_work_sync(&pf->ptp.work);
 
 	ice_ptp_port_phy_stop(&pf->ptp.port);
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h
index 3af20025043a..e2af9749061c 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.h
@@ -29,10 +29,17 @@ enum ice_ptp_pin_e810t {
 struct ice_perout_channel {
 	bool ena;
 	u32 gpio_pin;
+	u32 flags;
 	u64 period;
 	u64 start_time;
 };
 
+struct ice_extts_channel {
+	bool ena;
+	u32 gpio_pin;
+	u32 flags;
+};
+
 /* The ice hardware captures Tx hardware timestamps in the PHY. The timestamp
  * is stored in a buffer of registers. Depending on the specific hardware,
  * this buffer might be shared across multiple PHY ports.
@@ -226,6 +233,7 @@ enum ice_ptp_state {
  * @ext_ts_irq: the external timestamp IRQ in use
  * @kworker: kwork thread for handling periodic work
  * @perout_channels: periodic output data
+ * @extts_channels: channels for external timestamps
  * @info: structure defining PTP hardware capabilities
  * @clock: pointer to registered PTP clock device
  * @tstamp_config: hardware timestamping configuration
@@ -249,6 +257,7 @@ struct ice_ptp {
 	u8 ext_ts_irq;
 	struct kthread_worker *kworker;
 	struct ice_perout_channel perout_channels[GLTSYN_TGT_H_IDX_MAX];
+	struct ice_extts_channel extts_channels[GLTSYN_TGT_H_IDX_MAX];
 	struct ptp_clock_info info;
 	struct ptp_clock *clock;
 	struct hwtstamp_config tstamp_config;
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 94d6670d0901..1191031b2a43 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -1899,7 +1899,8 @@ ice_aq_alloc_free_vsi_list(struct ice_hw *hw, u16 *vsi_list_id,
 	    lkup_type == ICE_SW_LKUP_ETHERTYPE_MAC ||
 	    lkup_type == ICE_SW_LKUP_PROMISC ||
 	    lkup_type == ICE_SW_LKUP_PROMISC_VLAN ||
-	    lkup_type == ICE_SW_LKUP_DFLT) {
+	    lkup_type == ICE_SW_LKUP_DFLT ||
+	    lkup_type == ICE_SW_LKUP_LAST) {
 		sw_buf->res_type = cpu_to_le16(ICE_AQC_RES_TYPE_VSI_LIST_REP);
 	} else if (lkup_type == ICE_SW_LKUP_VLAN) {
 		if (opc == ice_aqc_opc_alloc_res)
@@ -2922,7 +2923,8 @@ ice_update_vsi_list_rule(struct ice_hw *hw, u16 *vsi_handle_arr, u16 num_vsi,
 	    lkup_type == ICE_SW_LKUP_ETHERTYPE_MAC ||
 	    lkup_type == ICE_SW_LKUP_PROMISC ||
 	    lkup_type == ICE_SW_LKUP_PROMISC_VLAN ||
-	    lkup_type == ICE_SW_LKUP_DFLT)
+	    lkup_type == ICE_SW_LKUP_DFLT ||
+	    lkup_type == ICE_SW_LKUP_LAST)
 		rule_type = remove ? ICE_AQC_SW_RULES_T_VSI_LIST_CLEAR :
 			ICE_AQC_SW_RULES_T_VSI_LIST_SET;
 	else if (lkup_type == ICE_SW_LKUP_VLAN)
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index f0796a93f428..eef397e5baa0 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -482,6 +482,8 @@ struct ice_bank_info {
 	u32 orom_size;				/* Size of OROM bank */
 	u32 netlist_ptr;			/* Pointer to 1st Netlist bank */
 	u32 netlist_size;			/* Size of Netlist bank */
+	u32 active_css_hdr_len;			/* Active CSS header length */
+	u32 inactive_css_hdr_len;		/* Inactive CSS header length */
 	enum ice_flash_bank nvm_bank;		/* Active NVM bank */
 	enum ice_flash_bank orom_bank;		/* Active OROM bank */
 	enum ice_flash_bank netlist_bank;	/* Active Netlist bank */
@@ -1087,17 +1089,13 @@ struct ice_aq_get_set_rss_lut_params {
 #define ICE_SR_SECTOR_SIZE_IN_WORDS	0x800
 
 /* CSS Header words */
+#define ICE_NVM_CSS_HDR_LEN_L			0x02
+#define ICE_NVM_CSS_HDR_LEN_H			0x03
 #define ICE_NVM_CSS_SREV_L			0x14
 #define ICE_NVM_CSS_SREV_H			0x15
 
-/* Length of CSS header section in words */
-#define ICE_CSS_HEADER_LENGTH			330
-
-/* Offset of Shadow RAM copy in the NVM bank area. */
-#define ICE_NVM_SR_COPY_WORD_OFFSET		roundup(ICE_CSS_HEADER_LENGTH, 32)
-
-/* Size in bytes of Option ROM trailer */
-#define ICE_NVM_OROM_TRAILER_LENGTH		(2 * ICE_CSS_HEADER_LENGTH)
+/* Length of Authentication header section in words */
+#define ICE_NVM_AUTH_HEADER_LEN			0x08
 
 /* The Link Topology Netlist section is stored as a series of words. It is
  * stored in the NVM as a TLV, with the first two words containing the type
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 7541f223bf4f..a65955eb23c0 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -269,7 +269,6 @@ static int ice_xsk_pool_disable(struct ice_vsi *vsi, u16 qid)
 	if (!pool)
 		return -EINVAL;
 
-	clear_bit(qid, vsi->af_xdp_zc_qps);
 	xsk_pool_dma_unmap(pool, ICE_RX_DMA_ATTR);
 
 	return 0;
@@ -300,8 +299,6 @@ ice_xsk_pool_enable(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
 	if (err)
 		return err;
 
-	set_bit(qid, vsi->af_xdp_zc_qps);
-
 	return 0;
 }
 
@@ -349,11 +346,13 @@ ice_realloc_rx_xdp_bufs(struct ice_rx_ring *rx_ring, bool pool_present)
 int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc)
 {
 	struct ice_rx_ring *rx_ring;
-	unsigned long q;
+	uint i;
+
+	ice_for_each_rxq(vsi, i) {
+		rx_ring = vsi->rx_rings[i];
+		if (!rx_ring->xsk_pool)
+			continue;
 
-	for_each_set_bit(q, vsi->af_xdp_zc_qps,
-			 max_t(int, vsi->alloc_txq, vsi->alloc_rxq)) {
-		rx_ring = vsi->rx_rings[q];
 		if (ice_realloc_rx_xdp_bufs(rx_ring, zc))
 			return -ENOMEM;
 	}