Merge: MLX4 driver upgrade - kernel 6.0

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/1778

Description:
============
Hi all,

This MR upgrades mlx4 driver, it includes patches from kernel 5.19 - 6.0

Bugzilla:
=========
Bugzilla: http://bugzilla.redhat.com/2112965

Upstream-status:
================
All patches are accepted upstream to Linus tree.
Each patch commit message describes its origin.

Testing:
========
This patch set passed incremental build testing to verify that it is bisectable.
Sanity tests ran over mlx4 drivers on x86_64 systems (using ConnectX-3),
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).

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: Mohammad Kabat <mkabat@redhat.com>

2bd51c1 (Mohammad Kabat)
   net/mlx4_en: Fix wrong return value on ioctl EEPROM query failure

4d3f47c (Mohammad Kabat)
   RDMA/mlx4: Avoid flush_scheduled_work() usage

4946218 (Mohammad Kabat)
   mlx4: support BIG TCP packets

51c7ac8 (Mohammad Kabat)
   net: mellanox: fix open-coded for_each_set_bit()

 drivers/infiniband/hw/mlx4/cm.c                 | 29 +++++++++++----
 drivers/infiniband/hw/mlx4/main.c               | 10 +++++-
 drivers/infiniband/hw/mlx4/mlx4_ib.h            |  3 ++
 drivers/net/ethernet/mellanox/mlx4/cmd.c        | 23 ++++--------
 drivers/net/ethernet/mellanox/mlx4/en_ethtool.c |  2 +-
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c  |  3 ++
 drivers/net/ethernet/mellanox/mlx4/en_tx.c      | 47 ++++++++++++++++++++-----
 7 files changed, 82 insertions(+), 35 deletions(-)

Approved-by: Kamal Heib <kheib@redhat.com>
Approved-by: Íñigo Huguet <ihuguet@redhat.com>

Signed-off-by: Herton R. Krzesinski <herton@redhat.com>

Author: Herton R. Krzesinski

drivers/infiniband/hw/mlx4/cm.c

@@ -80,6 +80,7 @@ struct cm_req_msg {
 	union ib_gid primary_path_sgid;
 };
 
+static struct workqueue_struct *cm_wq;
 
 static void set_local_comm_id(struct ib_mad *mad, u32 cm_id)
 {
@@ -288,10 +289,10 @@ static void schedule_delayed(struct ib_device *ibdev, struct id_map_entry *id)
 	/*make sure that there is no schedule inside the scheduled work.*/
 	if (!sriov->is_going_down && !id->scheduled_delete) {
 		id->scheduled_delete = 1;
-		schedule_delayed_work(&id->timeout, CM_CLEANUP_CACHE_TIMEOUT);
+		queue_delayed_work(cm_wq, &id->timeout, CM_CLEANUP_CACHE_TIMEOUT);
 	} else if (id->scheduled_delete) {
 		/* Adjust timeout if already scheduled */
-		mod_delayed_work(system_wq, &id->timeout, CM_CLEANUP_CACHE_TIMEOUT);
+		mod_delayed_work(cm_wq, &id->timeout, CM_CLEANUP_CACHE_TIMEOUT);
 	}
 	spin_unlock_irqrestore(&sriov->going_down_lock, flags);
 	spin_unlock(&sriov->id_map_lock);
@@ -370,7 +371,7 @@ static int alloc_rej_tmout(struct mlx4_ib_sriov *sriov, u32 rem_pv_cm_id, int sl
 			ret =  xa_err(item);
 		else
 			/* If a retry, adjust delayed work */
-			mod_delayed_work(system_wq, &item->timeout, CM_CLEANUP_CACHE_TIMEOUT);
+			mod_delayed_work(cm_wq, &item->timeout, CM_CLEANUP_CACHE_TIMEOUT);
 		goto err_or_exists;
 	}
 	xa_unlock(&sriov->xa_rej_tmout);
@@ -393,7 +394,7 @@ static int alloc_rej_tmout(struct mlx4_ib_sriov *sriov, u32 rem_pv_cm_id, int sl
 		return xa_err(old);
 	}
 
-	schedule_delayed_work(&item->timeout, CM_CLEANUP_CACHE_TIMEOUT);
+	queue_delayed_work(cm_wq, &item->timeout, CM_CLEANUP_CACHE_TIMEOUT);
 
 	return 0;
 
@@ -500,15 +501,15 @@ static void rej_tmout_xa_cleanup(struct mlx4_ib_sriov *sriov, int slave)
 	xa_lock(&sriov->xa_rej_tmout);
 	xa_for_each(&sriov->xa_rej_tmout, id, item) {
 		if (slave < 0 || slave == item->slave) {
-			mod_delayed_work(system_wq, &item->timeout, 0);
+			mod_delayed_work(cm_wq, &item->timeout, 0);
 			flush_needed = true;
 			++cnt;
 		}
 	}
 	xa_unlock(&sriov->xa_rej_tmout);
 
 	if (flush_needed) {
-		flush_scheduled_work();
+		flush_workqueue(cm_wq);
 		pr_debug("Deleted %d entries in xarray for slave %d during cleanup\n",
 			 cnt, slave);
 	}
@@ -540,7 +541,7 @@ void mlx4_ib_cm_paravirt_clean(struct mlx4_ib_dev *dev, int slave)
 	spin_unlock(&sriov->id_map_lock);
 
 	if (need_flush)
-		flush_scheduled_work(); /* make sure all timers were flushed */
+		flush_workqueue(cm_wq); /* make sure all timers were flushed */
 
 	/* now, remove all leftover entries from databases*/
 	spin_lock(&sriov->id_map_lock);
@@ -587,3 +588,17 @@ void mlx4_ib_cm_paravirt_clean(struct mlx4_ib_dev *dev, int slave)
 
 	rej_tmout_xa_cleanup(sriov, slave);
 }
+
+int mlx4_ib_cm_init(void)
+{
+	cm_wq = alloc_workqueue("mlx4_ib_cm", 0, 0);
+	if (!cm_wq)
+		return -ENOMEM;
+
+	return 0;
+}
+
+void mlx4_ib_cm_destroy(void)
+{
+	destroy_workqueue(cm_wq);
+}

drivers/infiniband/hw/mlx4/main.c

@@ -3307,10 +3307,14 @@ static int __init mlx4_ib_init(void)
 	if (!wq)
 		return -ENOMEM;
 
-	err = mlx4_ib_mcg_init();
+	err = mlx4_ib_cm_init();
 	if (err)
 		goto clean_wq;
 
+	err = mlx4_ib_mcg_init();
+	if (err)
+		goto clean_cm;
+
 	err = mlx4_register_interface(&mlx4_ib_interface);
 	if (err)
 		goto clean_mcg;
@@ -3320,6 +3324,9 @@ static int __init mlx4_ib_init(void)
 clean_mcg:
 	mlx4_ib_mcg_destroy();
 
+clean_cm:
+	mlx4_ib_cm_destroy();
+
 clean_wq:
 	destroy_workqueue(wq);
 	return err;
@@ -3329,6 +3336,7 @@ static void __exit mlx4_ib_cleanup(void)
 {
 	mlx4_unregister_interface(&mlx4_ib_interface);
 	mlx4_ib_mcg_destroy();
+	mlx4_ib_cm_destroy();
 	destroy_workqueue(wq);
 }
 

drivers/infiniband/hw/mlx4/mlx4_ib.h

@@ -937,4 +937,7 @@ mlx4_ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *wq_ind_table)
 int mlx4_ib_umem_calc_optimal_mtt_size(struct ib_umem *umem, u64 start_va,
 				       int *num_of_mtts);
 
+int mlx4_ib_cm_init(void);
+void mlx4_ib_cm_destroy(void);
+
 #endif /* MLX4_IB_H */

drivers/net/ethernet/mellanox/mlx4/cmd.c

@@ -1994,21 +1994,16 @@ static void mlx4_allocate_port_vpps(struct mlx4_dev *dev, int port)
 
 static int mlx4_master_activate_admin_state(struct mlx4_priv *priv, int slave)
 {
-	int port, err;
+	int p, port, err;
 	struct mlx4_vport_state *vp_admin;
 	struct mlx4_vport_oper_state *vp_oper;
 	struct mlx4_slave_state *slave_state =
 		&priv->mfunc.master.slave_state[slave];
 	struct mlx4_active_ports actv_ports = mlx4_get_active_ports(
 			&priv->dev, slave);
-	int min_port = find_first_bit(actv_ports.ports,
-				      priv->dev.caps.num_ports) + 1;
-	int max_port = min_port - 1 +
-		bitmap_weight(actv_ports.ports, priv->dev.caps.num_ports);
 
-	for (port = min_port; port <= max_port; port++) {
-		if (!test_bit(port - 1, actv_ports.ports))
-			continue;
+	for_each_set_bit(p, actv_ports.ports, priv->dev.caps.num_ports) {
+		port = p + 1;
 		priv->mfunc.master.vf_oper[slave].smi_enabled[port] =
 			priv->mfunc.master.vf_admin[slave].enable_smi[port];
 		vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port];
@@ -2063,19 +2058,13 @@ static int mlx4_master_activate_admin_state(struct mlx4_priv *priv, int slave)
 
 static void mlx4_master_deactivate_admin_state(struct mlx4_priv *priv, int slave)
 {
-	int port;
+	int p, port;
 	struct mlx4_vport_oper_state *vp_oper;
 	struct mlx4_active_ports actv_ports = mlx4_get_active_ports(
 			&priv->dev, slave);
-	int min_port = find_first_bit(actv_ports.ports,
-				      priv->dev.caps.num_ports) + 1;
-	int max_port = min_port - 1 +
-		bitmap_weight(actv_ports.ports, priv->dev.caps.num_ports);
 
-
-	for (port = min_port; port <= max_port; port++) {
-		if (!test_bit(port - 1, actv_ports.ports))
-			continue;
+	for_each_set_bit(p, actv_ports.ports, priv->dev.caps.num_ports) {
+		port = p + 1;
 		priv->mfunc.master.vf_oper[slave].smi_enabled[port] =
 			MLX4_VF_SMI_DISABLED;
 		vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port];

drivers/net/ethernet/mellanox/mlx4/en_ethtool.c

@@ -2110,7 +2110,7 @@ static int mlx4_en_get_module_eeprom(struct net_device *dev,
 			en_err(priv,
 			       "mlx4_get_module_info i(%d) offset(%d) bytes_to_read(%d) - FAILED (0x%x)\n",
 			       i, offset, ee->len - i, ret);
-			return 0;
+			return ret;
 		}
 
 		i += ret;

drivers/net/ethernet/mellanox/mlx4/en_netdev.c

@@ -3417,6 +3417,9 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 	dev->min_mtu = ETH_MIN_MTU;
 	dev->max_mtu = priv->max_mtu;
 
+	/* supports LSOv2 packets. */
+	netif_set_tso_max_size(dev, GSO_MAX_SIZE);
+
 	mdev->pndev[port] = dev;
 	mdev->upper[port] = NULL;
 

drivers/net/ethernet/mellanox/mlx4/en_tx.c

@@ -43,6 +43,7 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/indirect_call_wrapper.h>
+#include <net/ipv6.h>
 
 #include "mlx4_en.h"
 
@@ -634,19 +635,28 @@ static int get_real_size(const struct sk_buff *skb,
 			 struct net_device *dev,
 			 int *lso_header_size,
 			 bool *inline_ok,
-			 void **pfrag)
+			 void **pfrag,
+			 int *hopbyhop)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	int real_size;
 
 	if (shinfo->gso_size) {
 		*inline_ok = false;
-		if (skb->encapsulation)
+		*hopbyhop = 0;
+		if (skb->encapsulation) {
 			*lso_header_size = skb_inner_tcp_all_headers(skb);
-		else
+		} else {
+			/* Detects large IPV6 TCP packets and prepares for removal of
+			 * HBH header that has been pushed by ip6_xmit(),
+			 * mainly so that tcpdump can dissect them.
+			 */
+			if (ipv6_has_hopopt_jumbo(skb))
+				*hopbyhop = sizeof(struct hop_jumbo_hdr);
 			*lso_header_size = skb_tcp_all_headers(skb);
+		}
 		real_size = CTRL_SIZE + shinfo->nr_frags * DS_SIZE +
-			ALIGN(*lso_header_size + 4, DS_SIZE);
+			ALIGN(*lso_header_size - *hopbyhop + 4, DS_SIZE);
 		if (unlikely(*lso_header_size != skb_headlen(skb))) {
 			/* We add a segment for the skb linear buffer only if
 			 * it contains data */
@@ -873,6 +883,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	int desc_size;
 	int real_size;
 	u32 index, bf_index;
+	struct ipv6hdr *h6;
 	__be32 op_own;
 	int lso_header_size;
 	void *fragptr = NULL;
@@ -881,6 +892,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 	bool stop_queue;
 	bool inline_ok;
 	u8 data_offset;
+	int hopbyhop;
 	bool bf_ok;
 
 	tx_ind = skb_get_queue_mapping(skb);
@@ -890,7 +902,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto tx_drop;
 
 	real_size = get_real_size(skb, shinfo, dev, &lso_header_size,
-				  &inline_ok, &fragptr);
+				  &inline_ok, &fragptr, &hopbyhop);
 	if (unlikely(!real_size))
 		goto tx_drop_count;
 
@@ -943,7 +955,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 		data = &tx_desc->data;
 		data_offset = offsetof(struct mlx4_en_tx_desc, data);
 	} else {
-		int lso_align = ALIGN(lso_header_size + 4, DS_SIZE);
+		int lso_align = ALIGN(lso_header_size - hopbyhop + 4, DS_SIZE);
 
 		data = (void *)&tx_desc->lso + lso_align;
 		data_offset = offsetof(struct mlx4_en_tx_desc, lso) + lso_align;
@@ -1008,14 +1020,31 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev)
 			((ring->prod & ring->size) ?
 				cpu_to_be32(MLX4_EN_BIT_DESC_OWN) : 0);
 
+		lso_header_size -= hopbyhop;
 		/* Fill in the LSO prefix */
 		tx_desc->lso.mss_hdr_size = cpu_to_be32(
 			shinfo->gso_size << 16 | lso_header_size);
 
-		/* Copy headers;
-		 * note that we already verified that it is linear */
-		memcpy(tx_desc->lso.header, skb->data, lso_header_size);
 
+		if (unlikely(hopbyhop)) {
+			/* remove the HBH header.
+			 * Layout: [Ethernet header][IPv6 header][HBH][TCP header]
+			 */
+			memcpy(tx_desc->lso.header, skb->data, ETH_HLEN + sizeof(*h6));
+			h6 = (struct ipv6hdr *)((char *)tx_desc->lso.header + ETH_HLEN);
+			h6->nexthdr = IPPROTO_TCP;
+			/* Copy the TCP header after the IPv6 one */
+			memcpy(h6 + 1,
+			       skb->data + ETH_HLEN + sizeof(*h6) +
+					sizeof(struct hop_jumbo_hdr),
+			       tcp_hdrlen(skb));
+			/* Leave ipv6 payload_len set to 0, as LSO v2 specs request. */
+		} else {
+			/* Copy headers;
+			 * note that we already verified that it is linear
+			 */
+			memcpy(tx_desc->lso.header, skb->data, lso_header_size);
+		}
 		ring->tso_packets++;
 
 		i = shinfo->gso_segs;