Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:
 "Highlights:

   - Gustavo A. R. Silva keeps working on the implicit switch fallthru
     changes.

   - Support 802.11ax High-Efficiency wireless in cfg80211 et al, From
     Luca Coelho.

   - Re-enable ASPM in r8169, from Kai-Heng Feng.

   - Add virtual XFRM interfaces, which avoids all of the limitations of
     existing IPSEC tunnels. From Steffen Klassert.

   - Convert GRO over to use a hash table, so that when we have many
     flows active we don't traverse a long list during accumluation.

   - Many new self tests for routing, TC, tunnels, etc. Too many
     contributors to mention them all, but I'm really happy to keep
     seeing this stuff.

   - Hardware timestamping support for dpaa_eth/fsl-fman from Yangbo Lu.

   - Lots of cleanups and fixes in L2TP code from Guillaume Nault.

   - Add IPSEC offload support to netdevsim, from Shannon Nelson.

   - Add support for slotting with non-uniform distribution to netem
     packet scheduler, from Yousuk Seung.

   - Add UDP GSO support to mlx5e, from Boris Pismenny.

   - Support offloading of Team LAG in NFP, from John Hurley.

   - Allow to configure TX queue selection based upon RX queue, from
     Amritha Nambiar.

   - Support ethtool ring size configuration in aquantia, from Anton
     Mikaev.

   - Support DSCP and flowlabel per-transport in SCTP, from Xin Long.

   - Support list based batching and stack traversal of SKBs, this is
     very exciting work. From Edward Cree.

   - Busyloop optimizations in vhost_net, from Toshiaki Makita.

   - Introduce the ETF qdisc, which allows time based transmissions. IGB
     can offload this in hardware. From Vinicius Costa Gomes.

   - Add parameter support to devlink, from Moshe Shemesh.

   - Several multiplication and division optimizations for BPF JIT in
     nfp driver, from Jiong Wang.

   - Lots of prepatory work to make more of the packet scheduler layer
     lockless, when possible, from Vlad Buslov.

   - Add ACK filter and NAT awareness to sch_cake packet scheduler, from
     Toke Høiland-Jørgensen.

   - Support regions and region snapshots in devlink, from Alex Vesker.

   - Allow to attach XDP programs to both HW and SW at the same time on
     a given device, with initial support in nfp. From Jakub Kicinski.

   - Add TLS RX offload and support in mlx5, from Ilya Lesokhin.

   - Use PHYLIB in r8169 driver, from Heiner Kallweit.

   - All sorts of changes to support Spectrum 2 in mlxsw driver, from
     Ido Schimmel.

   - PTP support in mv88e6xxx DSA driver, from Andrew Lunn.

   - Make TCP_USER_TIMEOUT socket option more accurate, from Jon
     Maxwell.

   - Support for templates in packet scheduler classifier, from Jiri
     Pirko.

   - IPV6 support in RDS, from Ka-Cheong Poon.

   - Native tproxy support in nf_tables, from Máté Eckl.

   - Maintain IP fragment queue in an rbtree, but optimize properly for
     in-order frags. From Peter Oskolkov.

   - Improvde handling of ACKs on hole repairs, from Yuchung Cheng"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1996 commits)
  bpf: test: fix spelling mistake "REUSEEPORT" -> "REUSEPORT"
  hv/netvsc: Fix NULL dereference at single queue mode fallback
  net: filter: mark expected switch fall-through
  xen-netfront: fix warn message as irq device name has '/'
  cxgb4: Add new T5 PCI device ids 0x50af and 0x50b0
  net: dsa: mv88e6xxx: missing unlock on error path
  rds: fix building with IPV6=m
  inet/connection_sock: prefer _THIS_IP_ to current_text_addr
  net: dsa: mv88e6xxx: bitwise vs logical bug
  net: sock_diag: Fix spectre v1 gadget in __sock_diag_cmd()
  ieee802154: hwsim: using right kind of iteration
  net: hns3: Add vlan filter setting by ethtool command -K
  net: hns3: Set tx ring' tc info when netdev is up
  net: hns3: Remove tx ring BD len register in hns3_enet
  net: hns3: Fix desc num set to default when setting channel
  net: hns3: Fix for phy link issue when using marvell phy driver
  net: hns3: Fix for information of phydev lost problem when down/up
  net: hns3: Fix for command format parsing error in hclge_is_all_function_id_zero
  net: hns3: Add support for serdes loopback selftest
  bnxt_en: take coredump_record structure off stack
  ...

1 files changed, 213 insertions, 7 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 872014702fc1..d2d59444f562 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -159,9 +159,10 @@ static bool use_prio;
 module_param_named(use_prio, use_prio, bool, 0444);
 MODULE_PARM_DESC(use_prio, "Enable steering by VLAN priority on ETH ports (deprecated)");
 
-int log_mtts_per_seg = ilog2(MLX4_MTT_ENTRY_PER_SEG);
+int log_mtts_per_seg = ilog2(1);
 module_param_named(log_mtts_per_seg, log_mtts_per_seg, int, 0444);
-MODULE_PARM_DESC(log_mtts_per_seg, "Log2 number of MTT entries per segment (1-7)");
+MODULE_PARM_DESC(log_mtts_per_seg, "Log2 number of MTT entries per segment "
+		 "(0-7) (default: 0)");
 
 static int port_type_array[2] = {MLX4_PORT_TYPE_NONE, MLX4_PORT_TYPE_NONE};
 static int arr_argc = 2;
@@ -177,6 +178,131 @@ struct mlx4_port_config {
 
 static atomic_t pf_loading = ATOMIC_INIT(0);
 
+static int mlx4_devlink_ierr_reset_get(struct devlink *devlink, u32 id,
+				       struct devlink_param_gset_ctx *ctx)
+{
+	ctx->val.vbool = !!mlx4_internal_err_reset;
+	return 0;
+}
+
+static int mlx4_devlink_ierr_reset_set(struct devlink *devlink, u32 id,
+				       struct devlink_param_gset_ctx *ctx)
+{
+	mlx4_internal_err_reset = ctx->val.vbool;
+	return 0;
+}
+
+static int mlx4_devlink_crdump_snapshot_get(struct devlink *devlink, u32 id,
+					    struct devlink_param_gset_ctx *ctx)
+{
+	struct mlx4_priv *priv = devlink_priv(devlink);
+	struct mlx4_dev *dev = &priv->dev;
+
+	ctx->val.vbool = dev->persist->crdump.snapshot_enable;
+	return 0;
+}
+
+static int mlx4_devlink_crdump_snapshot_set(struct devlink *devlink, u32 id,
+					    struct devlink_param_gset_ctx *ctx)
+{
+	struct mlx4_priv *priv = devlink_priv(devlink);
+	struct mlx4_dev *dev = &priv->dev;
+
+	dev->persist->crdump.snapshot_enable = ctx->val.vbool;
+	return 0;
+}
+
+static int
+mlx4_devlink_max_macs_validate(struct devlink *devlink, u32 id,
+			       union devlink_param_value val,
+			       struct netlink_ext_ack *extack)
+{
+	u32 value = val.vu32;
+
+	if (value < 1 || value > 128)
+		return -ERANGE;
+
+	if (!is_power_of_2(value)) {
+		NL_SET_ERR_MSG_MOD(extack, "max_macs supported must be power of 2");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+enum mlx4_devlink_param_id {
+	MLX4_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
+	MLX4_DEVLINK_PARAM_ID_ENABLE_64B_CQE_EQE,
+	MLX4_DEVLINK_PARAM_ID_ENABLE_4K_UAR,
+};
+
+static const struct devlink_param mlx4_devlink_params[] = {
+	DEVLINK_PARAM_GENERIC(INT_ERR_RESET,
+			      BIT(DEVLINK_PARAM_CMODE_RUNTIME) |
+			      BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      mlx4_devlink_ierr_reset_get,
+			      mlx4_devlink_ierr_reset_set, NULL),
+	DEVLINK_PARAM_GENERIC(MAX_MACS,
+			      BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, mlx4_devlink_max_macs_validate),
+	DEVLINK_PARAM_GENERIC(REGION_SNAPSHOT,
+			      BIT(DEVLINK_PARAM_CMODE_RUNTIME) |
+			      BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      mlx4_devlink_crdump_snapshot_get,
+			      mlx4_devlink_crdump_snapshot_set, NULL),
+	DEVLINK_PARAM_DRIVER(MLX4_DEVLINK_PARAM_ID_ENABLE_64B_CQE_EQE,
+			     "enable_64b_cqe_eqe", DEVLINK_PARAM_TYPE_BOOL,
+			     BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			     NULL, NULL, NULL),
+	DEVLINK_PARAM_DRIVER(MLX4_DEVLINK_PARAM_ID_ENABLE_4K_UAR,
+			     "enable_4k_uar", DEVLINK_PARAM_TYPE_BOOL,
+			     BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			     NULL, NULL, NULL),
+};
+
+static void mlx4_devlink_set_init_value(struct devlink *devlink, u32 param_id,
+					union devlink_param_value init_val)
+{
+	struct mlx4_priv *priv = devlink_priv(devlink);
+	struct mlx4_dev *dev = &priv->dev;
+	int err;
+
+	err = devlink_param_driverinit_value_set(devlink, param_id, init_val);
+	if (err)
+		mlx4_warn(dev,
+			  "devlink set parameter %u value failed (err = %d)",
+			  param_id, err);
+}
+
+static void mlx4_devlink_set_params_init_values(struct devlink *devlink)
+{
+	union devlink_param_value value;
+
+	value.vbool = !!mlx4_internal_err_reset;
+	mlx4_devlink_set_init_value(devlink,
+				    DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET,
+				    value);
+
+	value.vu32 = 1UL << log_num_mac;
+	mlx4_devlink_set_init_value(devlink,
+				    DEVLINK_PARAM_GENERIC_ID_MAX_MACS, value);
+
+	value.vbool = enable_64b_cqe_eqe;
+	mlx4_devlink_set_init_value(devlink,
+				    MLX4_DEVLINK_PARAM_ID_ENABLE_64B_CQE_EQE,
+				    value);
+
+	value.vbool = enable_4k_uar;
+	mlx4_devlink_set_init_value(devlink,
+				    MLX4_DEVLINK_PARAM_ID_ENABLE_4K_UAR,
+				    value);
+
+	value.vbool = false;
+	mlx4_devlink_set_init_value(devlink,
+				    DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT,
+				    value);
+}
+
 static inline void mlx4_set_num_reserved_uars(struct mlx4_dev *dev,
 					      struct mlx4_dev_cap *dev_cap)
 {
@@ -428,6 +554,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.max_rss_tbl_sz     = dev_cap->max_rss_tbl_sz;
 	dev->caps.wol_port[1]          = dev_cap->wol_port[1];
 	dev->caps.wol_port[2]          = dev_cap->wol_port[2];
+	dev->caps.health_buffer_addrs  = dev_cap->health_buffer_addrs;
 
 	/* Save uar page shift */
 	if (!mlx4_is_slave(dev)) {
@@ -3711,10 +3838,14 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data,
 		}
 	}
 
-	err = mlx4_catas_init(&priv->dev);
+	err = mlx4_crdump_init(&priv->dev);
 	if (err)
 		goto err_release_regions;
 
+	err = mlx4_catas_init(&priv->dev);
+	if (err)
+		goto err_crdump;
+
 	err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv, 0);
 	if (err)
 		goto err_catas;
@@ -3724,6 +3855,9 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data,
 err_catas:
 	mlx4_catas_end(&priv->dev);
 
+err_crdump:
+	mlx4_crdump_end(&priv->dev);
+
 err_release_regions:
 	pci_release_regions(pdev);
 
@@ -3757,8 +3891,68 @@ static int mlx4_devlink_port_type_set(struct devlink_port *devlink_port,
 	return __set_port_type(info, mlx4_port_type);
 }
 
+static void mlx4_devlink_param_load_driverinit_values(struct devlink *devlink)
+{
+	struct mlx4_priv *priv = devlink_priv(devlink);
+	struct mlx4_dev *dev = &priv->dev;
+	struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
+	union devlink_param_value saved_value;
+	int err;
+
+	err = devlink_param_driverinit_value_get(devlink,
+						 DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET,
+						 &saved_value);
+	if (!err && mlx4_internal_err_reset != saved_value.vbool) {
+		mlx4_internal_err_reset = saved_value.vbool;
+		/* Notify on value changed on runtime configuration mode */
+		devlink_param_value_changed(devlink,
+					    DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET);
+	}
+	err = devlink_param_driverinit_value_get(devlink,
+						 DEVLINK_PARAM_GENERIC_ID_MAX_MACS,
+						 &saved_value);
+	if (!err)
+		log_num_mac = order_base_2(saved_value.vu32);
+	err = devlink_param_driverinit_value_get(devlink,
+						 MLX4_DEVLINK_PARAM_ID_ENABLE_64B_CQE_EQE,
+						 &saved_value);
+	if (!err)
+		enable_64b_cqe_eqe = saved_value.vbool;
+	err = devlink_param_driverinit_value_get(devlink,
+						 MLX4_DEVLINK_PARAM_ID_ENABLE_4K_UAR,
+						 &saved_value);
+	if (!err)
+		enable_4k_uar = saved_value.vbool;
+	err = devlink_param_driverinit_value_get(devlink,
+						 DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT,
+						 &saved_value);
+	if (!err && crdump->snapshot_enable != saved_value.vbool) {
+		crdump->snapshot_enable = saved_value.vbool;
+		devlink_param_value_changed(devlink,
+					    DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT);
+	}
+}
+
+static int mlx4_devlink_reload(struct devlink *devlink,
+			       struct netlink_ext_ack *extack)
+{
+	struct mlx4_priv *priv = devlink_priv(devlink);
+	struct mlx4_dev *dev = &priv->dev;
+	struct mlx4_dev_persistent *persist = dev->persist;
+	int err;
+
+	if (persist->num_vfs)
+		mlx4_warn(persist->dev, "Reload performed on PF, will cause reset on operating Virtual Functions\n");
+	err = mlx4_restart_one(persist->pdev, true, devlink);
+	if (err)
+		mlx4_err(persist->dev, "mlx4_restart_one failed, ret=%d\n", err);
+
+	return err;
+}
+
 static const struct devlink_ops mlx4_devlink_ops = {
 	.port_type_set	= mlx4_devlink_port_type_set,
+	.reload		= mlx4_devlink_reload,
 };
 
 static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
@@ -3792,14 +3986,21 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	ret = devlink_register(devlink, &pdev->dev);
 	if (ret)
 		goto err_persist_free;
-
-	ret =  __mlx4_init_one(pdev, id->driver_data, priv);
+	ret = devlink_params_register(devlink, mlx4_devlink_params,
+				      ARRAY_SIZE(mlx4_devlink_params));
 	if (ret)
 		goto err_devlink_unregister;
+	mlx4_devlink_set_params_init_values(devlink);
+	ret =  __mlx4_init_one(pdev, id->driver_data, priv);
+	if (ret)
+		goto err_params_unregister;
 
 	pci_save_state(pdev);
 	return 0;
 
+err_params_unregister:
+	devlink_params_unregister(devlink, mlx4_devlink_params,
+				  ARRAY_SIZE(mlx4_devlink_params));
 err_devlink_unregister:
 	devlink_unregister(devlink);
 err_persist_free:
@@ -3929,6 +4130,7 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 	else
 		mlx4_info(dev, "%s: interface is down\n", __func__);
 	mlx4_catas_end(dev);
+	mlx4_crdump_end(dev);
 	if (dev->flags & MLX4_FLAG_SRIOV && !active_vfs) {
 		mlx4_warn(dev, "Disabling SR-IOV\n");
 		pci_disable_sriov(pdev);
@@ -3936,6 +4138,8 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 
 	pci_release_regions(pdev);
 	mlx4_pci_disable_device(dev);
+	devlink_params_unregister(devlink, mlx4_devlink_params,
+				  ARRAY_SIZE(mlx4_devlink_params));
 	devlink_unregister(devlink);
 	kfree(dev->persist);
 	devlink_free(devlink);
@@ -3960,7 +4164,7 @@ static int restore_current_port_types(struct mlx4_dev *dev,
 	return err;
 }
 
-int mlx4_restart_one(struct pci_dev *pdev)
+int mlx4_restart_one(struct pci_dev *pdev, bool reload, struct devlink *devlink)
 {
 	struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);
 	struct mlx4_dev	 *dev  = persist->dev;
@@ -3973,6 +4177,8 @@ int mlx4_restart_one(struct pci_dev *pdev)
 	memcpy(nvfs, dev->persist->nvfs, sizeof(dev->persist->nvfs));
 
 	mlx4_unload_one(pdev);
+	if (reload)
+		mlx4_devlink_param_load_driverinit_values(devlink);
 	err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv, 1);
 	if (err) {
 		mlx4_err(dev, "%s: ERROR: mlx4_load_one failed, pci_name=%s, err=%d\n",
@@ -4205,7 +4411,7 @@ static int __init mlx4_verify_params(void)
 	if (use_prio != 0)
 		pr_warn("mlx4_core: use_prio - obsolete module param, ignored\n");
 
-	if ((log_mtts_per_seg < 1) || (log_mtts_per_seg > 7)) {
+	if ((log_mtts_per_seg < 0) || (log_mtts_per_seg > 7)) {
 		pr_warn("mlx4_core: bad log_mtts_per_seg: %d\n",
 			log_mtts_per_seg);
 		return -1;