Merge tag 'mlx5-fixes-2023-07-05' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5 fixes 2023-07-05

This series provides bug fixes to mlx5 driver.

* tag 'mlx5-fixes-2023-07-05' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux:
  net/mlx5e: RX, Fix page_pool page fragment tracking for XDP
  net/mlx5: Query hca_cap_2 only when supported
  net/mlx5e: TC, CT: Offload ct clear only once
  net/mlx5e: Check for NOT_READY flag state after locking
  net/mlx5: Register a unique thermal zone per device
  net/mlx5e: RX, Fix flush and close release flow of regular rq for legacy rq
  net/mlx5e: fix memory leak in mlx5e_ptp_open
  net/mlx5e: fix memory leak in mlx5e_fs_tt_redirect_any_create
  net/mlx5e: fix double free in mlx5e_destroy_flow_table
====================

Link: https://lore.kernel.org/r/20230705175757.284614-1-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

Author: kuba-moo

drivers/net/ethernet/mellanox/mlx5/core/en/fs_tt_redirect.c

@@ -594,7 +594,7 @@ int mlx5e_fs_tt_redirect_any_create(struct mlx5e_flow_steering *fs)
 
 	err = fs_any_create_table(fs);
 	if (err)
-		return err;
+		goto err_free_any;
 
 	err = fs_any_enable(fs);
 	if (err)
@@ -606,8 +606,8 @@ int mlx5e_fs_tt_redirect_any_create(struct mlx5e_flow_steering *fs)
 
 err_destroy_table:
 	fs_any_destroy_table(fs_any);
-
-	kfree(fs_any);
+err_free_any:
 	mlx5e_fs_set_any(fs, NULL);
+	kfree(fs_any);
 	return err;
 }

drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c

@@ -729,8 +729,10 @@ int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params,
 
 	c = kvzalloc_node(sizeof(*c), GFP_KERNEL, dev_to_node(mlx5_core_dma_dev(mdev)));
 	cparams = kvzalloc(sizeof(*cparams), GFP_KERNEL);
-	if (!c || !cparams)
-		return -ENOMEM;
+	if (!c || !cparams) {
+		err = -ENOMEM;
+		goto err_free;
+	}
 
 	c->priv     = priv;
 	c->mdev     = priv->mdev;

drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c

@@ -1545,7 +1545,8 @@ mlx5_tc_ct_parse_action(struct mlx5_tc_ct_priv *priv,
 
 	attr->ct_attr.ct_action |= act->ct.action; /* So we can have clear + ct */
 	attr->ct_attr.zone = act->ct.zone;
-	attr->ct_attr.nf_ft = act->ct.flow_table;
+	if (!(act->ct.action & TCA_CT_ACT_CLEAR))
+		attr->ct_attr.nf_ft = act->ct.flow_table;
 	attr->ct_attr.act_miss_cookie = act->miss_cookie;
 
 	return 0;
@@ -1990,6 +1991,9 @@ mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_attr *att
 	if (!priv)
 		return -EOPNOTSUPP;
 
+	if (attr->ct_attr.offloaded)
+		return 0;
+
 	if (attr->ct_attr.ct_action & TCA_CT_ACT_CLEAR) {
 		err = mlx5_tc_ct_entry_set_registers(priv, &attr->parse_attr->mod_hdr_acts,
 						     0, 0, 0, 0);
@@ -1999,11 +2003,15 @@ mlx5_tc_ct_flow_offload(struct mlx5_tc_ct_priv *priv, struct mlx5_flow_attr *att
 		attr->action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR;
 	}
 
-	if (!attr->ct_attr.nf_ft) /* means only ct clear action, and not ct_clear,ct() */
+	if (!attr->ct_attr.nf_ft) { /* means only ct clear action, and not ct_clear,ct() */
+		attr->ct_attr.offloaded = true;
 		return 0;
+	}
 
 	mutex_lock(&priv->control_lock);
 	err = __mlx5_tc_ct_flow_offload(priv, attr);
+	if (!err)
+		attr->ct_attr.offloaded = true;
 	mutex_unlock(&priv->control_lock);
 
 	return err;
@@ -2021,7 +2029,7 @@ void
 mlx5_tc_ct_delete_flow(struct mlx5_tc_ct_priv *priv,
 		       struct mlx5_flow_attr *attr)
 {
-	if (!attr->ct_attr.ft) /* no ct action, return */
+	if (!attr->ct_attr.offloaded) /* no ct action, return */
 		return;
 	if (!attr->ct_attr.nf_ft) /* means only ct clear action, and not ct_clear,ct() */
 		return;

drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.h

@@ -29,6 +29,7 @@ struct mlx5_ct_attr {
 	u32 ct_labels_id;
 	u32 act_miss_mapping;
 	u64 act_miss_cookie;
+	bool offloaded;
 	struct mlx5_ct_ft *ft;
 };
 

drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c

@@ -662,8 +662,7 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
 				/* No need to check ((page->pp_magic & ~0x3UL) == PP_SIGNATURE)
 				 * as we know this is a page_pool page.
 				 */
-				page_pool_put_defragged_page(page->pp,
-							     page, -1, true);
+				page_pool_recycle_direct(page->pp, page);
 			} while (++n < num);
 
 			break;

drivers/net/ethernet/mellanox/mlx5/core/en_accel/fs_tcp.c

@@ -190,6 +190,7 @@ static int accel_fs_tcp_create_groups(struct mlx5e_flow_table *ft,
 	in = kvzalloc(inlen, GFP_KERNEL);
 	if  (!in || !ft->g) {
 		kfree(ft->g);
+		ft->g = NULL;
 		kvfree(in);
 		return -ENOMEM;
 	}

drivers/net/ethernet/mellanox/mlx5/core/en_rx.c

@@ -390,10 +390,18 @@ static void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix)
 {
 	struct mlx5e_wqe_frag_info *wi = get_frag(rq, ix);
 
-	if (rq->xsk_pool)
+	if (rq->xsk_pool) {
 		mlx5e_xsk_free_rx_wqe(wi);
-	else
+	} else {
 		mlx5e_free_rx_wqe(rq, wi);
+
+		/* Avoid a second release of the wqe pages: dealloc is called
+		 * for the same missing wqes on regular RQ flush and on regular
+		 * RQ close. This happens when XSK RQs come into play.
+		 */
+		for (int i = 0; i < rq->wqe.info.num_frags; i++, wi++)
+			wi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE);
+	}
 }
 
 static void mlx5e_xsk_free_rx_wqes(struct mlx5e_rq *rq, u16 ix, int wqe_bulk)
@@ -1743,11 +1751,11 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi
 
 	prog = rcu_dereference(rq->xdp_prog);
 	if (prog && mlx5e_xdp_handle(rq, prog, &mxbuf)) {
-		if (test_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
+		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
 			struct mlx5e_wqe_frag_info *pwi;
 
 			for (pwi = head_wi; pwi < wi; pwi++)
-				pwi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE);
+				pwi->frag_page->frags++;
 		}
 		return NULL; /* page/packet was consumed by XDP */
 	}
@@ -1817,12 +1825,8 @@ static void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 			      rq, wi, cqe, cqe_bcnt);
 	if (!skb) {
 		/* probably for XDP */
-		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
-			/* do not return page to cache,
-			 * it will be returned on XDP_TX completion.
-			 */
-			wi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE);
-		}
+		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))
+			wi->frag_page->frags++;
 		goto wq_cyc_pop;
 	}
 
@@ -1868,12 +1872,8 @@ static void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 			      rq, wi, cqe, cqe_bcnt);
 	if (!skb) {
 		/* probably for XDP */
-		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
-			/* do not return page to cache,
-			 * it will be returned on XDP_TX completion.
-			 */
-			wi->flags |= BIT(MLX5E_WQE_FRAG_SKIP_RELEASE);
-		}
+		if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))
+			wi->frag_page->frags++;
 		goto wq_cyc_pop;
 	}
 
@@ -2052,12 +2052,12 @@ mlx5e_skb_from_cqe_mpwrq_nonlinear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *w
 	if (prog) {
 		if (mlx5e_xdp_handle(rq, prog, &mxbuf)) {
 			if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags)) {
-				int i;
+				struct mlx5e_frag_page *pfp;
+
+				for (pfp = head_page; pfp < frag_page; pfp++)
+					pfp->frags++;
 
-				for (i = 0; i < sinfo->nr_frags; i++)
-					/* non-atomic */
-					__set_bit(page_idx + i, wi->skip_release_bitmap);
-				return NULL;
+				wi->linear_page.frags++;
 			}
 			mlx5e_page_release_fragmented(rq, &wi->linear_page);
 			return NULL; /* page/packet was consumed by XDP */
@@ -2155,7 +2155,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 				 cqe_bcnt, &mxbuf);
 		if (mlx5e_xdp_handle(rq, prog, &mxbuf)) {
 			if (__test_and_clear_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags))
-				__set_bit(page_idx, wi->skip_release_bitmap); /* non-atomic */
+				frag_page->frags++;
 			return NULL; /* page/packet was consumed by XDP */
 		}
 

drivers/net/ethernet/mellanox/mlx5/core/en_tc.c

@@ -1639,7 +1639,8 @@ static void remove_unready_flow(struct mlx5e_tc_flow *flow)
 	uplink_priv = &rpriv->uplink_priv;
 
 	mutex_lock(&uplink_priv->unready_flows_lock);
-	unready_flow_del(flow);
+	if (flow_flag_test(flow, NOT_READY))
+		unready_flow_del(flow);
 	mutex_unlock(&uplink_priv->unready_flows_lock);
 }
 
@@ -1932,8 +1933,7 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv,
 	esw_attr = attr->esw_attr;
 	mlx5e_put_flow_tunnel_id(flow);
 
-	if (flow_flag_test(flow, NOT_READY))
-		remove_unready_flow(flow);
+	remove_unready_flow(flow);
 
 	if (mlx5e_is_offloaded_flow(flow)) {
 		if (flow_flag_test(flow, SLOW))

drivers/net/ethernet/mellanox/mlx5/core/eswitch.c

@@ -807,6 +807,9 @@ static int mlx5_esw_vport_caps_get(struct mlx5_eswitch *esw, struct mlx5_vport *
 	hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
 	vport->info.roce_enabled = MLX5_GET(cmd_hca_cap, hca_caps, roce);
 
+	if (!MLX5_CAP_GEN_MAX(esw->dev, hca_cap_2))
+		goto out_free;
+
 	memset(query_ctx, 0, query_out_sz);
 	err = mlx5_vport_get_other_func_cap(esw->dev, vport->vport, query_ctx,
 					    MLX5_CAP_GENERAL_2);

drivers/net/ethernet/mellanox/mlx5/core/thermal.c

@@ -68,14 +68,19 @@ static struct thermal_zone_device_ops mlx5_thermal_ops = {
 
 int mlx5_thermal_init(struct mlx5_core_dev *mdev)
 {
+	char data[THERMAL_NAME_LENGTH];
 	struct mlx5_thermal *thermal;
-	struct thermal_zone_device *tzd;
-	const char *data = "mlx5";
+	int err;
 
-	tzd = thermal_zone_get_zone_by_name(data);
-	if (!IS_ERR(tzd))
+	if (!mlx5_core_is_pf(mdev) && !mlx5_core_is_ecpf(mdev))
 		return 0;
 
+	err = snprintf(data, sizeof(data), "mlx5_%s", dev_name(mdev->device));
+	if (err < 0 || err >= sizeof(data)) {
+		mlx5_core_err(mdev, "Failed to setup thermal zone name, %d\n", err);
+		return -EINVAL;
+	}
+
 	thermal = kzalloc(sizeof(*thermal), GFP_KERNEL);
 	if (!thermal)
 		return -ENOMEM;
@@ -89,10 +94,10 @@ int mlx5_thermal_init(struct mlx5_core_dev *mdev)
 								 &mlx5_thermal_ops,
 								 NULL, 0, MLX5_THERMAL_POLL_INT_MSEC);
 	if (IS_ERR(thermal->tzdev)) {
-		dev_err(mdev->device, "Failed to register thermal zone device (%s) %ld\n",
-			data, PTR_ERR(thermal->tzdev));
+		err = PTR_ERR(thermal->tzdev);
+		mlx5_core_err(mdev, "Failed to register thermal zone device (%s) %d\n", data, err);
 		kfree(thermal);
-		return -EINVAL;
+		return err;
 	}
 
 	mdev->thermal = thermal;