Merge: mlx5: Add driver fixes up to v6.10

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/4625

Hi all,

This MR includes updates for the mlx5 drivers. It has backports of fixes up to kernel v6.10.

JIRA: https://issues.redhat.com/browse/RHEL-45365

All patches are accepted upstream in Linus' tree. Each patch commit message describes its origin.

This patch set passed incremental build testing to verify that it is bisectable.
Sanity tests ran over mlx5 drivers on x86_64 systems (using ConnectX-4/5/6),
including the following:
 
Ethernet:
- IPv4 traffic (ICMP, TCP, UDP).
- IPv6 traffic (ICMP, TCP, UDP).
 
VLAN:
- IPv4 traffic (ICMP, TCP, UDP).
- IPv6 traffic (ICMP, TCP, UDP).
 
RoCE:
- RDMA (ibv_*_pingpong).
- RDMACM (examples that comes with librdmacm packages).
 
Infiniband:
- RDMA (ibv_*_pingpong).
- RDMACM (examples that comes with librdmacm packages).
 
IPoIB:
- IPv4 traffic (ICMP, TCP, UDP).
- IPv6 traffic (ICMP, TCP, UDP).
 
PKey:
- IPv4 traffic (ICMP, TCP, UDP).
- IPv6 traffic (ICMP, TCP, UDP).
 
ASAP2/OVS:
- Various sanity tests covering OVS offloads.
 
NFSoRDMA:
- Discover, mount and write.
 
iSER:
- Discover, login and mount.
 
SRP:
- Verify srp_daemon service is up and system can discover SRP targets.

Signed-off-by: Benjamin Poirier <bpoirier@redhat.com>

Approved-by: Kamal Heib <kheib@redhat.com>
Approved-by: Michal Schmidt <mschmidt@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Lucas Zampieri <lzampier@redhat.com>

Author: zampierilucas

drivers/infiniband/hw/mlx5/main.c

@@ -3760,10 +3760,10 @@ static int mlx5_ib_stage_init_init(struct mlx5_ib_dev *dev)
 	spin_lock_init(&dev->dm.lock);
 	dev->dm.dev = mdev;
 	return 0;
-err:
-	mlx5r_macsec_dealloc_gids(dev);
 err_mp:
 	mlx5_ib_cleanup_multiport_master(dev);
+err:
+	mlx5r_macsec_dealloc_gids(dev);
 	return err;
 }
 

drivers/infiniband/hw/mlx5/mlx5_ib.h

@@ -639,9 +639,10 @@ struct mlx5_ib_mkey {
 	unsigned int ndescs;
 	struct wait_queue_head wait;
 	refcount_t usecount;
-	/* User Mkey must hold either a rb_key or a cache_ent. */
+	/* Cacheable user Mkey must hold either a rb_key or a cache_ent. */
 	struct mlx5r_cache_rb_key rb_key;
 	struct mlx5_cache_ent *cache_ent;
+	u8 cacheable : 1;
 };
 
 #define MLX5_IB_MTT_PRESENT (MLX5_IB_MTT_READ | MLX5_IB_MTT_WRITE)

drivers/infiniband/hw/mlx5/mr.c

@@ -246,6 +246,7 @@ static void set_cache_mkc(struct mlx5_cache_ent *ent, void *mkc)
 	MLX5_SET(mkc, mkc, access_mode_1_0, ent->rb_key.access_mode & 0x3);
 	MLX5_SET(mkc, mkc, access_mode_4_2,
 		(ent->rb_key.access_mode >> 2) & 0x7);
+	MLX5_SET(mkc, mkc, ma_translation_mode, !!ent->rb_key.ats);
 
 	MLX5_SET(mkc, mkc, translations_octword_size,
 		 get_mkc_octo_size(ent->rb_key.access_mode,
@@ -641,10 +642,8 @@ static int mlx5_cache_ent_insert(struct mlx5_mkey_cache *cache,
 			new = &((*new)->rb_left);
 		if (cmp < 0)
 			new = &((*new)->rb_right);
-		if (cmp == 0) {
-			mutex_unlock(&cache->rb_lock);
+		if (cmp == 0)
 			return -EEXIST;
-		}
 	}
 
 	/* Add new node and rebalance tree. */
@@ -719,6 +718,8 @@ static struct mlx5_ib_mr *_mlx5_mr_cache_alloc(struct mlx5_ib_dev *dev,
 	}
 	mr->mmkey.cache_ent = ent;
 	mr->mmkey.type = MLX5_MKEY_MR;
+	mr->mmkey.rb_key = ent->rb_key;
+	mr->mmkey.cacheable = true;
 	init_waitqueue_head(&mr->mmkey.wait);
 	return mr;
 }
@@ -1158,6 +1159,7 @@ static struct mlx5_ib_mr *alloc_cacheable_mr(struct ib_pd *pd,
 		if (IS_ERR(mr))
 			return mr;
 		mr->mmkey.rb_key = rb_key;
+		mr->mmkey.cacheable = true;
 		return mr;
 	}
 
@@ -1570,7 +1572,8 @@ static bool can_use_umr_rereg_access(struct mlx5_ib_dev *dev,
 	unsigned int diffs = current_access_flags ^ target_access_flags;
 
 	if (diffs & ~(IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE |
-		      IB_ACCESS_REMOTE_READ | IB_ACCESS_RELAXED_ORDERING))
+		      IB_ACCESS_REMOTE_READ | IB_ACCESS_RELAXED_ORDERING |
+		      IB_ACCESS_REMOTE_ATOMIC))
 		return false;
 	return mlx5r_umr_can_reconfig(dev, current_access_flags,
 				      target_access_flags);
@@ -1835,6 +1838,23 @@ static int cache_ent_find_and_store(struct mlx5_ib_dev *dev,
 	return ret;
 }
 
+static int mlx5_revoke_mr(struct mlx5_ib_mr *mr)
+{
+	struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device);
+	struct mlx5_cache_ent *ent = mr->mmkey.cache_ent;
+
+	if (mr->mmkey.cacheable && !mlx5r_umr_revoke_mr(mr) && !cache_ent_find_and_store(dev, mr))
+		return 0;
+
+	if (ent) {
+		spin_lock_irq(&ent->mkeys_queue.lock);
+		ent->in_use--;
+		mr->mmkey.cache_ent = NULL;
+		spin_unlock_irq(&ent->mkeys_queue.lock);
+	}
+	return destroy_mkey(dev, mr);
+}
+
 int mlx5_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
 {
 	struct mlx5_ib_mr *mr = to_mmr(ibmr);
@@ -1880,16 +1900,9 @@ int mlx5_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
 	}
 
 	/* Stop DMA */
-	if (mr->umem && mlx5r_umr_can_load_pas(dev, mr->umem->length))
-		if (mlx5r_umr_revoke_mr(mr) ||
-		    cache_ent_find_and_store(dev, mr))
-			mr->mmkey.cache_ent = NULL;
-
-	if (!mr->mmkey.cache_ent) {
-		rc = destroy_mkey(to_mdev(mr->ibmr.device), mr);
-		if (rc)
-			return rc;
-	}
+	rc = mlx5_revoke_mr(mr);
+	if (rc)
+		return rc;
 
 	if (mr->umem) {
 		bool is_odp = is_odp_mr(mr);

drivers/infiniband/hw/mlx5/srq.c

@@ -199,17 +199,20 @@ int mlx5_ib_create_srq(struct ib_srq *ib_srq,
 	int err;
 	struct mlx5_srq_attr in = {};
 	__u32 max_srq_wqes = 1 << MLX5_CAP_GEN(dev->mdev, log_max_srq_sz);
+	__u32 max_sge_sz =  MLX5_CAP_GEN(dev->mdev, max_wqe_sz_rq) /
+			    sizeof(struct mlx5_wqe_data_seg);
 
 	if (init_attr->srq_type != IB_SRQT_BASIC &&
 	    init_attr->srq_type != IB_SRQT_XRC &&
 	    init_attr->srq_type != IB_SRQT_TM)
 		return -EOPNOTSUPP;
 
-	/* Sanity check SRQ size before proceeding */
-	if (init_attr->attr.max_wr >= max_srq_wqes) {
-		mlx5_ib_dbg(dev, "max_wr %d, cap %d\n",
-			    init_attr->attr.max_wr,
-			    max_srq_wqes);
+	/* Sanity check SRQ and sge size before proceeding */
+	if (init_attr->attr.max_wr >= max_srq_wqes ||
+	    init_attr->attr.max_sge > max_sge_sz) {
+		mlx5_ib_dbg(dev, "max_wr %d,wr_cap %d,max_sge %d, sge_cap:%d\n",
+			    init_attr->attr.max_wr, max_srq_wqes,
+			    init_attr->attr.max_sge, max_sge_sz);
 		return -EINVAL;
 	}
 

drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c

@@ -28,8 +28,10 @@ bool mlx5e_validate_xsk_param(struct mlx5e_params *params,
 			      struct mlx5e_xsk_param *xsk,
 			      struct mlx5_core_dev *mdev)
 {
-	/* AF_XDP doesn't support frames larger than PAGE_SIZE. */
-	if (xsk->chunk_size > PAGE_SIZE || xsk->chunk_size < MLX5E_MIN_XSK_CHUNK_SIZE) {
+	/* AF_XDP doesn't support frames larger than PAGE_SIZE,
+	 * and xsk->chunk_size is limited to 65535 bytes.
+	 */
+	if ((size_t)xsk->chunk_size > PAGE_SIZE || xsk->chunk_size < MLX5E_MIN_XSK_CHUNK_SIZE) {
 		mlx5_core_err(mdev, "XSK chunk size %u out of bounds [%u, %lu]\n", xsk->chunk_size,
 			      MLX5E_MIN_XSK_CHUNK_SIZE, PAGE_SIZE);
 		return false;

drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h

@@ -102,8 +102,14 @@ static inline void
 mlx5e_udp_gso_handle_tx_skb(struct sk_buff *skb)
 {
 	int payload_len = skb_shinfo(skb)->gso_size + sizeof(struct udphdr);
+	struct udphdr *udphdr;
 
-	udp_hdr(skb)->len = htons(payload_len);
+	if (skb->encapsulation)
+		udphdr = (struct udphdr *)skb_inner_transport_header(skb);
+	else
+		udphdr = udp_hdr(skb);
+
+	udphdr->len = htons(payload_len);
 }
 
 struct mlx5e_accel_tx_state {

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

@@ -750,8 +750,7 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 err_fs_ft:
 	if (rx->allow_tunnel_mode)
 		mlx5_eswitch_unblock_encap(mdev);
-	mlx5_del_flow_rules(rx->status.rule);
-	mlx5_modify_header_dealloc(mdev, rx->status.modify_hdr);
+	mlx5_ipsec_rx_status_destroy(ipsec, rx);
 err_add:
 	mlx5_destroy_flow_table(rx->ft.status);
 err_fs_ft_status:

drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h

@@ -98,18 +98,11 @@ mlx5e_ipsec_feature_check(struct sk_buff *skb, netdev_features_t features)
 		if (!x || !x->xso.offload_handle)
 			goto out_disable;
 
-		if (xo->inner_ipproto) {
-			/* Cannot support tunnel packet over IPsec tunnel mode
-			 * because we cannot offload three IP header csum
-			 */
-			if (x->props.mode == XFRM_MODE_TUNNEL)
-				goto out_disable;
-
-			/* Only support UDP or TCP L4 checksum */
-			if (xo->inner_ipproto != IPPROTO_UDP &&
-			    xo->inner_ipproto != IPPROTO_TCP)
-				goto out_disable;
-		}
+		/* Only support UDP or TCP L4 checksum */
+		if (xo->inner_ipproto &&
+		    xo->inner_ipproto != IPPROTO_UDP &&
+		    xo->inner_ipproto != IPPROTO_TCP)
+			goto out_disable;
 
 		return features;
 

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

@@ -3769,7 +3769,7 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 		mlx5e_fold_sw_stats64(priv, stats);
 	}
 
-	stats->rx_dropped = priv->stats.qcnt.rx_out_of_buffer;
+	stats->rx_missed_errors = priv->stats.qcnt.rx_out_of_buffer;
 
 	stats->rx_length_errors =
 		PPORT_802_3_GET(pstats, a_in_range_length_errors) +
@@ -4717,7 +4717,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
 
 		/* Verify if UDP port is being offloaded by HW */
 		if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, port))
-			return features;
+			return vxlan_features_check(skb, features);
 
 #if IS_ENABLED(CONFIG_GENEVE)
 		/* Support Geneve offload for default UDP port */
@@ -4743,7 +4743,6 @@ netdev_features_t mlx5e_features_check(struct sk_buff *skb,
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
 	features = vlan_features_check(skb, features);
-	features = vxlan_features_check(skb, features);
 
 	/* Validate if the tunneled packet is being offloaded by HW */
 	if (skb->encapsulation &&
@@ -5702,6 +5701,11 @@ void mlx5e_priv_cleanup(struct mlx5e_priv *priv)
 		kfree(priv->htb_qos_sq_stats[i]);
 	kvfree(priv->htb_qos_sq_stats);
 
+	if (priv->mqprio_rl) {
+		mlx5e_mqprio_rl_cleanup(priv->mqprio_rl);
+		mlx5e_mqprio_rl_free(priv->mqprio_rl);
+	}
+
 	memset(priv, 0, sizeof(*priv));
 }
 

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

@@ -153,7 +153,11 @@ mlx5e_tx_get_gso_ihs(struct mlx5e_txqsq *sq, struct sk_buff *skb, int *hopbyhop)
 
 	*hopbyhop = 0;
 	if (skb->encapsulation) {
-		ihs = skb_inner_tcp_all_headers(skb);
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
+			ihs = skb_inner_transport_offset(skb) +
+			      sizeof(struct udphdr);
+		else
+			ihs = skb_inner_tcp_all_headers(skb);
 		stats->tso_inner_packets++;
 		stats->tso_inner_bytes += skb->len - ihs;
 	} else {