Merge tag 'mlx5-fixes-2023-05-24' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5 fixes 2023-05-24

This series includes bug fixes for the mlx5 driver.

* tag 'mlx5-fixes-2023-05-24' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux:
  Documentation: net/mlx5: Wrap notes in admonition blocks
  Documentation: net/mlx5: Add blank line separator before numbered lists
  Documentation: net/mlx5: Use bullet and definition lists for vnic counters description
  Documentation: net/mlx5: Wrap vnic reporter devlink commands in code blocks
  net/mlx5: Fix check for allocation failure in comp_irqs_request_pci()
  net/mlx5: DR, Add missing mutex init/destroy in pattern manager
  net/mlx5e: Move Ethernet driver debugfs to profile init callback
  net/mlx5e: Don't attach netdev profile while handling internal error
  net/mlx5: Fix post parse infra to only parse every action once
  net/mlx5e: Use query_special_contexts cmd only once per mdev
  net/mlx5: fw_tracer, Fix event handling
  net/mlx5: SF, Drain health before removing device
  net/mlx5: Drain health before unregistering devlink
  net/mlx5e: Do not update SBCM when prio2buffer command is invalid
  net/mlx5e: Consider internal buffers size in port buffer calculations
  net/mlx5e: Prevent encap offload when neigh update is running
  net/mlx5e: Extract remaining tunnel encap code to dedicated file
====================

Link: https://lore.kernel.org/r/20230525034847.99268-1-saeed@kernel.orgSigned-off-by: Jakub Kicinski <kuba@kernel.org>

Documentation/networking/device_drivers/ethernet/mellanox/mlx5/devlink.rst

@@ -40,6 +40,7 @@ flow_steering_mode: Device flow steering mode
 ---------------------------------------------
 The flow steering mode parameter controls the flow steering mode of the driver.
 Two modes are supported:
+
 1. 'dmfs' - Device managed flow steering.
 2. 'smfs' - Software/Driver managed flow steering.
 
@@ -99,6 +100,7 @@ between representors and stacked devices.
 By default metadata is enabled on the supported devices in E-switch.
 Metadata is applicable only for E-switch in switchdev mode and
 users may disable it when NONE of the below use cases will be in use:
+
 1. HCA is in Dual/multi-port RoCE mode.
 2. VF/SF representor bonding (Usually used for Live migration)
 3. Stacked devices
@@ -180,7 +182,8 @@ User commands examples:
 
     $ devlink health diagnose pci/0000:82:00.0 reporter tx
 
-NOTE: This command has valid output only when interface is up, otherwise the command has empty output.
+.. note::
+   This command has valid output only when interface is up, otherwise the command has empty output.
 
 - Show number of tx errors indicated, number of recover flows ended successfully,
   is autorecover enabled and graceful period from last recover::
@@ -232,8 +235,9 @@ User commands examples:
 
     $ devlink health dump show pci/0000:82:00.0 reporter fw
 
-NOTE: This command can run only on the PF which has fw tracer ownership,
-running it on other PF or any VF will return "Operation not permitted".
+.. note::
+   This command can run only on the PF which has fw tracer ownership,
+   running it on other PF or any VF will return "Operation not permitted".
 
 fw fatal reporter
 -----------------
@@ -256,7 +260,8 @@ User commands examples:
 
     $ devlink health dump show pci/0000:82:00.1 reporter fw_fatal
 
-NOTE: This command can run only on PF.
+.. note::
+   This command can run only on PF.
 
 vnic reporter
 -------------
@@ -265,28 +270,37 @@ It is responsible for querying the vnic diagnostic counters from fw and displayi
 them in realtime.
 
 Description of the vnic counters:
-total_q_under_processor_handle: number of queues in an error state due to
-an async error or errored command.
-send_queue_priority_update_flow: number of QP/SQ priority/SL update
-events.
-cq_overrun: number of times CQ entered an error state due to an
-overflow.
-async_eq_overrun: number of times an EQ mapped to async events was
-overrun.
-comp_eq_overrun: number of times an EQ mapped to completion events was
-overrun.
-quota_exceeded_command: number of commands issued and failed due to quota
-exceeded.
-invalid_command: number of commands issued and failed dues to any reason
-other than quota exceeded.
-nic_receive_steering_discard: number of packets that completed RX flow
-steering but were discarded due to a mismatch in flow table.
+
+- total_q_under_processor_handle
+        number of queues in an error state due to
+        an async error or errored command.
+- send_queue_priority_update_flow
+        number of QP/SQ priority/SL update events.
+- cq_overrun
+        number of times CQ entered an error state due to an overflow.
+- async_eq_overrun
+        number of times an EQ mapped to async events was overrun.
+        comp_eq_overrun number of times an EQ mapped to completion events was
+        overrun.
+- quota_exceeded_command
+        number of commands issued and failed due to quota exceeded.
+- invalid_command
+        number of commands issued and failed dues to any reason other than quota
+        exceeded.
+- nic_receive_steering_discard
+        number of packets that completed RX flow
+        steering but were discarded due to a mismatch in flow table.
 
 User commands examples:
-- Diagnose PF/VF vnic counters
+
+- Diagnose PF/VF vnic counters::
+
         $ devlink health diagnose pci/0000:82:00.1 reporter vnic
+
 - Diagnose representor vnic counters (performed by supplying devlink port of the
-  representor, which can be obtained via devlink port command)
+  representor, which can be obtained via devlink port command)::
+
         $ devlink health diagnose pci/0000:82:00.1/65537 reporter vnic
 
-NOTE: This command can run over all interfaces such as PF/VF and representor ports.
+.. note::
+   This command can run over all interfaces such as PF/VF and representor ports.

drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c

@@ -490,7 +490,7 @@ static void poll_trace(struct mlx5_fw_tracer *tracer,
 				(u64)timestamp_low;
 		break;
 	default:
-		if (tracer_event->event_id >= tracer->str_db.first_string_trace ||
+		if (tracer_event->event_id >= tracer->str_db.first_string_trace &&
 		    tracer_event->event_id <= tracer->str_db.first_string_trace +
 					      tracer->str_db.num_string_trace) {
 			tracer_event->type = TRACER_EVENT_TYPE_STRING;

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

@@ -327,6 +327,7 @@ struct mlx5e_params {
 	unsigned int sw_mtu;
 	int hard_mtu;
 	bool ptp_rx;
+	__be32 terminate_lkey_be;
 };
 
 static inline u8 mlx5e_get_dcb_num_tc(struct mlx5e_params *params)

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

@@ -51,7 +51,7 @@ int mlx5e_port_query_buffer(struct mlx5e_priv *priv,
 	if (err)
 		goto out;
 
-	for (i = 0; i < MLX5E_MAX_BUFFER; i++) {
+	for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) {
 		buffer = MLX5_ADDR_OF(pbmc_reg, out, buffer[i]);
 		port_buffer->buffer[i].lossy =
 			MLX5_GET(bufferx_reg, buffer, lossy);
@@ -73,14 +73,24 @@ int mlx5e_port_query_buffer(struct mlx5e_priv *priv,
 			  port_buffer->buffer[i].lossy);
 	}
 
-	port_buffer->headroom_size = total_used;
+	port_buffer->internal_buffers_size = 0;
+	for (i = MLX5E_MAX_NETWORK_BUFFER; i < MLX5E_TOTAL_BUFFERS; i++) {
+		buffer = MLX5_ADDR_OF(pbmc_reg, out, buffer[i]);
+		port_buffer->internal_buffers_size +=
+			MLX5_GET(bufferx_reg, buffer, size) * port_buff_cell_sz;
+	}
+
 	port_buffer->port_buffer_size =
 		MLX5_GET(pbmc_reg, out, port_buffer_size) * port_buff_cell_sz;
-	port_buffer->spare_buffer_size =
-		port_buffer->port_buffer_size - total_used;
-
-	mlx5e_dbg(HW, priv, "total buffer size=%d, spare buffer size=%d\n",
-		  port_buffer->port_buffer_size,
+	port_buffer->headroom_size = total_used;
+	port_buffer->spare_buffer_size = port_buffer->port_buffer_size -
+					 port_buffer->internal_buffers_size -
+					 port_buffer->headroom_size;
+
+	mlx5e_dbg(HW, priv,
+		  "total buffer size=%u, headroom buffer size=%u, internal buffers size=%u, spare buffer size=%u\n",
+		  port_buffer->port_buffer_size, port_buffer->headroom_size,
+		  port_buffer->internal_buffers_size,
 		  port_buffer->spare_buffer_size);
 out:
 	kfree(out);
@@ -206,11 +216,11 @@ static int port_update_pool_cfg(struct mlx5_core_dev *mdev,
 	if (!MLX5_CAP_GEN(mdev, sbcam_reg))
 		return 0;
 
-	for (i = 0; i < MLX5E_MAX_BUFFER; i++)
+	for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++)
 		lossless_buff_count += ((port_buffer->buffer[i].size) &&
 				       (!(port_buffer->buffer[i].lossy)));
 
-	for (i = 0; i < MLX5E_MAX_BUFFER; i++) {
+	for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) {
 		p = select_sbcm_params(&port_buffer->buffer[i], lossless_buff_count);
 		err = mlx5e_port_set_sbcm(mdev, 0, i,
 					  MLX5_INGRESS_DIR,
@@ -293,7 +303,7 @@ static int port_set_buffer(struct mlx5e_priv *priv,
 	if (err)
 		goto out;
 
-	for (i = 0; i < MLX5E_MAX_BUFFER; i++) {
+	for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) {
 		void *buffer = MLX5_ADDR_OF(pbmc_reg, in, buffer[i]);
 		u64 size = port_buffer->buffer[i].size;
 		u64 xoff = port_buffer->buffer[i].xoff;
@@ -351,7 +361,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
 {
 	int i;
 
-	for (i = 0; i < MLX5E_MAX_BUFFER; i++) {
+	for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) {
 		if (port_buffer->buffer[i].lossy) {
 			port_buffer->buffer[i].xoff = 0;
 			port_buffer->buffer[i].xon  = 0;
@@ -408,7 +418,7 @@ static int update_buffer_lossy(struct mlx5_core_dev *mdev,
 	int err;
 	int i;
 
-	for (i = 0; i < MLX5E_MAX_BUFFER; i++) {
+	for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) {
 		prio_count = 0;
 		lossy_count = 0;
 
@@ -432,11 +442,11 @@ static int update_buffer_lossy(struct mlx5_core_dev *mdev,
 	}
 
 	if (changed) {
-		err = port_update_pool_cfg(mdev, port_buffer);
+		err = update_xoff_threshold(port_buffer, xoff, max_mtu, port_buff_cell_sz);
 		if (err)
 			return err;
 
-		err = update_xoff_threshold(port_buffer, xoff, max_mtu, port_buff_cell_sz);
+		err = port_update_pool_cfg(mdev, port_buffer);
 		if (err)
 			return err;
 
@@ -515,7 +525,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 
 	if (change & MLX5E_PORT_BUFFER_PRIO2BUFFER) {
 		update_prio2buffer = true;
-		for (i = 0; i < MLX5E_MAX_BUFFER; i++)
+		for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++)
 			mlx5e_dbg(HW, priv, "%s: requested to map prio[%d] to buffer %d\n",
 				  __func__, i, prio2buffer[i]);
 
@@ -530,7 +540,7 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 	}
 
 	if (change & MLX5E_PORT_BUFFER_SIZE) {
-		for (i = 0; i < MLX5E_MAX_BUFFER; i++) {
+		for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) {
 			mlx5e_dbg(HW, priv, "%s: buffer[%d]=%d\n", __func__, i, buffer_size[i]);
 			if (!port_buffer.buffer[i].lossy && !buffer_size[i]) {
 				mlx5e_dbg(HW, priv, "%s: lossless buffer[%d] size cannot be zero\n",
@@ -544,7 +554,9 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 
 		mlx5e_dbg(HW, priv, "%s: total buffer requested=%d\n", __func__, total_used);
 
-		if (total_used > port_buffer.port_buffer_size)
+		if (total_used > port_buffer.headroom_size &&
+		    (total_used - port_buffer.headroom_size) >
+			    port_buffer.spare_buffer_size)
 			return -EINVAL;
 
 		update_buffer = true;

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

@@ -35,7 +35,8 @@
 #include "en.h"
 #include "port.h"
 
-#define MLX5E_MAX_BUFFER 8
+#define MLX5E_MAX_NETWORK_BUFFER 8
+#define MLX5E_TOTAL_BUFFERS 10
 #define MLX5E_DEFAULT_CABLE_LEN 7 /* 7 meters */
 
 #define MLX5_BUFFER_SUPPORTED(mdev) (MLX5_CAP_GEN(mdev, pcam_reg) && \
@@ -60,8 +61,9 @@ struct mlx5e_bufferx_reg {
 struct mlx5e_port_buffer {
 	u32                       port_buffer_size;
 	u32                       spare_buffer_size;
-	u32                       headroom_size;
-	struct mlx5e_bufferx_reg  buffer[MLX5E_MAX_BUFFER];
+	u32                       headroom_size;	  /* Buffers 0-7 */
+	u32                       internal_buffers_size;  /* Buffers 8-9 */
+	struct mlx5e_bufferx_reg  buffer[MLX5E_MAX_NETWORK_BUFFER];
 };
 
 int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,

drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.c

@@ -84,7 +84,7 @@ mlx5e_tc_act_init_parse_state(struct mlx5e_tc_act_parse_state *parse_state,
 
 int
 mlx5e_tc_act_post_parse(struct mlx5e_tc_act_parse_state *parse_state,
-			struct flow_action *flow_action,
+			struct flow_action *flow_action, int from, int to,
 			struct mlx5_flow_attr *attr,
 			enum mlx5_flow_namespace_type ns_type)
 {
@@ -96,6 +96,11 @@ mlx5e_tc_act_post_parse(struct mlx5e_tc_act_parse_state *parse_state,
 	priv = parse_state->flow->priv;
 
 	flow_action_for_each(i, act, flow_action) {
+		if (i < from)
+			continue;
+		else if (i > to)
+			break;
+
 		tc_act = mlx5e_tc_act_get(act->id, ns_type);
 		if (!tc_act || !tc_act->post_parse)
 			continue;

drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h

@@ -112,7 +112,7 @@ mlx5e_tc_act_init_parse_state(struct mlx5e_tc_act_parse_state *parse_state,
 
 int
 mlx5e_tc_act_post_parse(struct mlx5e_tc_act_parse_state *parse_state,
-			struct flow_action *flow_action,
+			struct flow_action *flow_action, int from, int to,
 			struct mlx5_flow_attr *attr,
 			enum mlx5_flow_namespace_type ns_type);
 

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

@@ -492,6 +492,19 @@ void mlx5e_encap_put(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e)
 	mlx5e_encap_dealloc(priv, e);
 }
 
+static void mlx5e_encap_put_locked(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e)
+{
+	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
+
+	lockdep_assert_held(&esw->offloads.encap_tbl_lock);
+
+	if (!refcount_dec_and_test(&e->refcnt))
+		return;
+	list_del(&e->route_list);
+	hash_del_rcu(&e->encap_hlist);
+	mlx5e_encap_dealloc(priv, e);
+}
+
 static void mlx5e_decap_put(struct mlx5e_priv *priv, struct mlx5e_decap_entry *d)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
@@ -816,6 +829,8 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv,
 	uintptr_t hash_key;
 	int err = 0;
 
+	lockdep_assert_held(&esw->offloads.encap_tbl_lock);
+
 	parse_attr = attr->parse_attr;
 	tun_info = parse_attr->tun_info[out_index];
 	mpls_info = &parse_attr->mpls_info[out_index];
@@ -829,7 +844,6 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv,
 
 	hash_key = hash_encap_info(&key);
 
-	mutex_lock(&esw->offloads.encap_tbl_lock);
 	e = mlx5e_encap_get(priv, &key, hash_key);
 
 	/* must verify if encap is valid or not */
@@ -840,15 +854,6 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv,
 			goto out_err;
 		}
 
-		mutex_unlock(&esw->offloads.encap_tbl_lock);
-		wait_for_completion(&e->res_ready);
-
-		/* Protect against concurrent neigh update. */
-		mutex_lock(&esw->offloads.encap_tbl_lock);
-		if (e->compl_result < 0) {
-			err = -EREMOTEIO;
-			goto out_err;
-		}
 		goto attach_flow;
 	}
 
@@ -877,15 +882,12 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv,
 	INIT_LIST_HEAD(&e->flows);
 	hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key);
 	tbl_time_before = mlx5e_route_tbl_get_last_update(priv);
-	mutex_unlock(&esw->offloads.encap_tbl_lock);
 
 	if (family == AF_INET)
 		err = mlx5e_tc_tun_create_header_ipv4(priv, mirred_dev, e);
 	else if (family == AF_INET6)
 		err = mlx5e_tc_tun_create_header_ipv6(priv, mirred_dev, e);
 
-	/* Protect against concurrent neigh update. */
-	mutex_lock(&esw->offloads.encap_tbl_lock);
 	complete_all(&e->res_ready);
 	if (err) {
 		e->compl_result = err;
@@ -920,18 +922,15 @@ int mlx5e_attach_encap(struct mlx5e_priv *priv,
 	} else {
 		flow_flag_set(flow, SLOW);
 	}
-	mutex_unlock(&esw->offloads.encap_tbl_lock);
 
 	return err;
 
 out_err:
-	mutex_unlock(&esw->offloads.encap_tbl_lock);
 	if (e)
-		mlx5e_encap_put(priv, e);
+		mlx5e_encap_put_locked(priv, e);
 	return err;
 
 out_err_init:
-	mutex_unlock(&esw->offloads.encap_tbl_lock);
 	kfree(tun_info);
 	kfree(e);
 	return err;
@@ -1016,6 +1015,93 @@ int mlx5e_attach_decap(struct mlx5e_priv *priv,
 	return err;
 }
 
+int mlx5e_tc_tun_encap_dests_set(struct mlx5e_priv *priv,
+				 struct mlx5e_tc_flow *flow,
+				 struct mlx5_flow_attr *attr,
+				 struct netlink_ext_ack *extack,
+				 bool *vf_tun)
+{
+	struct mlx5e_tc_flow_parse_attr *parse_attr;
+	struct mlx5_esw_flow_attr *esw_attr;
+	struct net_device *encap_dev = NULL;
+	struct mlx5e_rep_priv *rpriv;
+	struct mlx5e_priv *out_priv;
+	struct mlx5_eswitch *esw;
+	int out_index;
+	int err = 0;
+
+	if (!mlx5e_is_eswitch_flow(flow))
+		return 0;
+
+	parse_attr = attr->parse_attr;
+	esw_attr = attr->esw_attr;
+	*vf_tun = false;
+
+	esw = priv->mdev->priv.eswitch;
+	mutex_lock(&esw->offloads.encap_tbl_lock);
+	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) {
+		struct net_device *out_dev;
+		int mirred_ifindex;
+
+		if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP))
+			continue;
+
+		mirred_ifindex = parse_attr->mirred_ifindex[out_index];
+		out_dev = dev_get_by_index(dev_net(priv->netdev), mirred_ifindex);
+		if (!out_dev) {
+			NL_SET_ERR_MSG_MOD(extack, "Requested mirred device not found");
+			err = -ENODEV;
+			goto out;
+		}
+		err = mlx5e_attach_encap(priv, flow, attr, out_dev, out_index,
+					 extack, &encap_dev);
+		dev_put(out_dev);
+		if (err)
+			goto out;
+
+		if (esw_attr->dests[out_index].flags &
+		    MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE &&
+		    !esw_attr->dest_int_port)
+			*vf_tun = true;
+
+		out_priv = netdev_priv(encap_dev);
+		rpriv = out_priv->ppriv;
+		esw_attr->dests[out_index].rep = rpriv->rep;
+		esw_attr->dests[out_index].mdev = out_priv->mdev;
+	}
+
+	if (*vf_tun && esw_attr->out_count > 1) {
+		NL_SET_ERR_MSG_MOD(extack, "VF tunnel encap with mirroring is not supported");
+		err = -EOPNOTSUPP;
+		goto out;
+	}
+
+out:
+	mutex_unlock(&esw->offloads.encap_tbl_lock);
+	return err;
+}
+
+void mlx5e_tc_tun_encap_dests_unset(struct mlx5e_priv *priv,
+				    struct mlx5e_tc_flow *flow,
+				    struct mlx5_flow_attr *attr)
+{
+	struct mlx5_esw_flow_attr *esw_attr;
+	int out_index;
+
+	if (!mlx5e_is_eswitch_flow(flow))
+		return;
+
+	esw_attr = attr->esw_attr;
+
+	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) {
+		if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP))
+			continue;
+
+		mlx5e_detach_encap(flow->priv, flow, attr, out_index);
+		kfree(attr->parse_attr->tun_info[out_index]);
+	}
+}
+
 static int cmp_route_info(struct mlx5e_route_key *a,
 			  struct mlx5e_route_key *b)
 {

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

@@ -30,6 +30,15 @@ int mlx5e_attach_decap_route(struct mlx5e_priv *priv,
 void mlx5e_detach_decap_route(struct mlx5e_priv *priv,
 			      struct mlx5e_tc_flow *flow);
 
+int mlx5e_tc_tun_encap_dests_set(struct mlx5e_priv *priv,
+				 struct mlx5e_tc_flow *flow,
+				 struct mlx5_flow_attr *attr,
+				 struct netlink_ext_ack *extack,
+				 bool *vf_tun);
+void mlx5e_tc_tun_encap_dests_unset(struct mlx5e_priv *priv,
+				    struct mlx5e_tc_flow *flow,
+				    struct mlx5_flow_attr *attr);
+
 struct ip_tunnel_info *mlx5e_dup_tun_info(const struct ip_tunnel_info *tun_info);
 
 int mlx5e_tc_set_attr_rx_tun(struct mlx5e_tc_flow *flow,

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

@@ -926,9 +926,10 @@ static int mlx5e_dcbnl_getbuffer(struct net_device *dev,
 	if (err)
 		return err;
 
-	for (i = 0; i < MLX5E_MAX_BUFFER; i++)
+	for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++)
 		dcb_buffer->buffer_size[i] = port_buffer.buffer[i].size;
-	dcb_buffer->total_size = port_buffer.port_buffer_size;
+	dcb_buffer->total_size = port_buffer.port_buffer_size -
+				 port_buffer.internal_buffers_size;
 
 	return 0;
 }
@@ -970,7 +971,7 @@ static int mlx5e_dcbnl_setbuffer(struct net_device *dev,
 	if (err)
 		return err;
 
-	for (i = 0; i < MLX5E_MAX_BUFFER; i++) {
+	for (i = 0; i < MLX5E_MAX_NETWORK_BUFFER; i++) {
 		if (port_buffer.buffer[i].size != dcb_buffer->buffer_size[i]) {
 			changed |= MLX5E_PORT_BUFFER_SIZE;
 			buffer_size = dcb_buffer->buffer_size;

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

@@ -727,26 +727,6 @@ static void mlx5e_rq_free_shampo(struct mlx5e_rq *rq)
 	mlx5e_rq_shampo_hd_free(rq);
 }
 
-static __be32 mlx5e_get_terminate_scatter_list_mkey(struct mlx5_core_dev *dev)
-{
-	u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {};
-	u32 in[MLX5_ST_SZ_DW(query_special_contexts_in)] = {};
-	int res;
-
-	if (!MLX5_CAP_GEN(dev, terminate_scatter_list_mkey))
-		return MLX5_TERMINATE_SCATTER_LIST_LKEY;
-
-	MLX5_SET(query_special_contexts_in, in, opcode,
-		 MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS);
-	res = mlx5_cmd_exec_inout(dev, query_special_contexts, in, out);
-	if (res)
-		return MLX5_TERMINATE_SCATTER_LIST_LKEY;
-
-	res = MLX5_GET(query_special_contexts_out, out,
-		       terminate_scatter_list_mkey);
-	return cpu_to_be32(res);
-}
-
 static int mlx5e_alloc_rq(struct mlx5e_params *params,
 			  struct mlx5e_xsk_param *xsk,
 			  struct mlx5e_rq_param *rqp,
@@ -908,7 +888,7 @@ static int mlx5e_alloc_rq(struct mlx5e_params *params,
 			/* check if num_frags is not a pow of two */
 			if (rq->wqe.info.num_frags < (1 << rq->wqe.info.log_num_frags)) {
 				wqe->data[f].byte_count = 0;
-				wqe->data[f].lkey = mlx5e_get_terminate_scatter_list_mkey(mdev);
+				wqe->data[f].lkey = params->terminate_lkey_be;
 				wqe->data[f].addr = 0;
 			}
 		}
@@ -5007,6 +4987,8 @@ void mlx5e_build_nic_params(struct mlx5e_priv *priv, struct mlx5e_xsk *xsk, u16
 	/* RQ */
 	mlx5e_build_rq_params(mdev, params);
 
+	params->terminate_lkey_be = mlx5_core_get_terminate_scatter_list_mkey(mdev);
+
 	params->packet_merge.timeout = mlx5e_choose_lro_timeout(mdev, MLX5E_DEFAULT_LRO_TIMEOUT);
 
 	/* CQ moderation params */
@@ -5279,12 +5261,16 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
 
 	mlx5e_timestamp_init(priv);
 
+	priv->dfs_root = debugfs_create_dir("nic",
+					    mlx5_debugfs_get_dev_root(mdev));
+
 	fs = mlx5e_fs_init(priv->profile, mdev,
 			   !test_bit(MLX5E_STATE_DESTROYING, &priv->state),
 			   priv->dfs_root);
 	if (!fs) {
 		err = -ENOMEM;
 		mlx5_core_err(mdev, "FS initialization failed, %d\n", err);
+		debugfs_remove_recursive(priv->dfs_root);
 		return err;
 	}
 	priv->fs = fs;
@@ -5305,6 +5291,7 @@ static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
 	mlx5e_health_destroy_reporters(priv);
 	mlx5e_ktls_cleanup(priv);
 	mlx5e_fs_cleanup(priv->fs);
+	debugfs_remove_recursive(priv->dfs_root);
 	priv->fs = NULL;
 }
 
@@ -5851,8 +5838,8 @@ void mlx5e_detach_netdev(struct mlx5e_priv *priv)
 }
 
 static int
-mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mdev,
-			    const struct mlx5e_profile *new_profile, void *new_ppriv)
+mlx5e_netdev_init_profile(struct net_device *netdev, struct mlx5_core_dev *mdev,
+			  const struct mlx5e_profile *new_profile, void *new_ppriv)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	int err;
@@ -5868,6 +5855,25 @@ mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mde
 	err = new_profile->init(priv->mdev, priv->netdev);
 	if (err)
 		goto priv_cleanup;
+
+	return 0;
+
+priv_cleanup:
+	mlx5e_priv_cleanup(priv);
+	return err;
+}
+
+static int
+mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mdev,
+			    const struct mlx5e_profile *new_profile, void *new_ppriv)
+{
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	int err;
+
+	err = mlx5e_netdev_init_profile(netdev, mdev, new_profile, new_ppriv);
+	if (err)
+		return err;
+
 	err = mlx5e_attach_netdev(priv);
 	if (err)
 		goto profile_cleanup;
@@ -5875,7 +5881,6 @@ mlx5e_netdev_attach_profile(struct net_device *netdev, struct mlx5_core_dev *mde
 
 profile_cleanup:
 	new_profile->cleanup(priv);
-priv_cleanup:
 	mlx5e_priv_cleanup(priv);
 	return err;
 }
@@ -5894,6 +5899,12 @@ int mlx5e_netdev_change_profile(struct mlx5e_priv *priv,
 	priv->profile->cleanup(priv);
 	mlx5e_priv_cleanup(priv);
 
+	if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR) {
+		mlx5e_netdev_init_profile(netdev, mdev, new_profile, new_ppriv);
+		set_bit(MLX5E_STATE_DESTROYING, &priv->state);
+		return -EIO;
+	}
+
 	err = mlx5e_netdev_attach_profile(netdev, mdev, new_profile, new_ppriv);
 	if (err) { /* roll back to original profile */
 		netdev_warn(netdev, "%s: new profile init failed, %d\n", __func__, err);
@@ -5955,8 +5966,11 @@ static int mlx5e_suspend(struct auxiliary_device *adev, pm_message_t state)
 	struct net_device *netdev = priv->netdev;
 	struct mlx5_core_dev *mdev = priv->mdev;
 
-	if (!netif_device_present(netdev))
+	if (!netif_device_present(netdev)) {
+		if (test_bit(MLX5E_STATE_DESTROYING, &priv->state))
+			mlx5e_destroy_mdev_resources(mdev);
 		return -ENODEV;
+	}
 
 	mlx5e_detach_netdev(priv);
 	mlx5e_destroy_mdev_resources(mdev);
@@ -6002,9 +6016,6 @@ static int mlx5e_probe(struct auxiliary_device *adev,
 	priv->profile = profile;
 	priv->ppriv = NULL;
 
-	priv->dfs_root = debugfs_create_dir("nic",
-					    mlx5_debugfs_get_dev_root(priv->mdev));
-
 	err = profile->init(mdev, netdev);
 	if (err) {
 		mlx5_core_err(mdev, "mlx5e_nic_profile init failed, %d\n", err);
@@ -6033,7 +6044,6 @@ static int mlx5e_probe(struct auxiliary_device *adev,
 err_profile_cleanup:
 	profile->cleanup(priv);
 err_destroy_netdev:
-	debugfs_remove_recursive(priv->dfs_root);
 	mlx5e_destroy_netdev(priv);
 err_devlink_port_unregister:
 	mlx5e_devlink_port_unregister(mlx5e_dev);
@@ -6053,7 +6063,6 @@ static void mlx5e_remove(struct auxiliary_device *adev)
 	unregister_netdev(priv->netdev);
 	mlx5e_suspend(adev, state);
 	priv->profile->cleanup(priv);
-	debugfs_remove_recursive(priv->dfs_root);
 	mlx5e_destroy_netdev(priv);
 	mlx5e_devlink_port_unregister(mlx5e_dev);
 	mlx5e_destroy_devlink(mlx5e_dev);

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

@@ -30,6 +30,7 @@
  * SOFTWARE.
  */
 
+#include <linux/debugfs.h>
 #include <linux/mlx5/fs.h>
 #include <net/switchdev.h>
 #include <net/pkt_cls.h>
@@ -812,11 +813,15 @@ static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev,
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
+	priv->dfs_root = debugfs_create_dir("nic",
+					    mlx5_debugfs_get_dev_root(mdev));
+
 	priv->fs = mlx5e_fs_init(priv->profile, mdev,
 				 !test_bit(MLX5E_STATE_DESTROYING, &priv->state),
 				 priv->dfs_root);
 	if (!priv->fs) {
 		netdev_err(priv->netdev, "FS allocation failed\n");
+		debugfs_remove_recursive(priv->dfs_root);
 		return -ENOMEM;
 	}
 
@@ -829,6 +834,7 @@ static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev,
 static void mlx5e_cleanup_rep(struct mlx5e_priv *priv)
 {
 	mlx5e_fs_cleanup(priv->fs);
+	debugfs_remove_recursive(priv->dfs_root);
 	priv->fs = NULL;
 }
 

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

@@ -1699,91 +1699,6 @@ int mlx5e_tc_query_route_vport(struct net_device *out_dev, struct net_device *ro
 	return mlx5_eswitch_vhca_id_to_vport(esw, vhca_id, vport);
 }
 
-static int
-set_encap_dests(struct mlx5e_priv *priv,
-		struct mlx5e_tc_flow *flow,
-		struct mlx5_flow_attr *attr,
-		struct netlink_ext_ack *extack,
-		bool *vf_tun)
-{
-	struct mlx5e_tc_flow_parse_attr *parse_attr;
-	struct mlx5_esw_flow_attr *esw_attr;
-	struct net_device *encap_dev = NULL;
-	struct mlx5e_rep_priv *rpriv;
-	struct mlx5e_priv *out_priv;
-	int out_index;
-	int err = 0;
-
-	if (!mlx5e_is_eswitch_flow(flow))
-		return 0;
-
-	parse_attr = attr->parse_attr;
-	esw_attr = attr->esw_attr;
-	*vf_tun = false;
-
-	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) {
-		struct net_device *out_dev;
-		int mirred_ifindex;
-
-		if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP))
-			continue;
-
-		mirred_ifindex = parse_attr->mirred_ifindex[out_index];
-		out_dev = dev_get_by_index(dev_net(priv->netdev), mirred_ifindex);
-		if (!out_dev) {
-			NL_SET_ERR_MSG_MOD(extack, "Requested mirred device not found");
-			err = -ENODEV;
-			goto out;
-		}
-		err = mlx5e_attach_encap(priv, flow, attr, out_dev, out_index,
-					 extack, &encap_dev);
-		dev_put(out_dev);
-		if (err)
-			goto out;
-
-		if (esw_attr->dests[out_index].flags &
-		    MLX5_ESW_DEST_CHAIN_WITH_SRC_PORT_CHANGE &&
-		    !esw_attr->dest_int_port)
-			*vf_tun = true;
-
-		out_priv = netdev_priv(encap_dev);
-		rpriv = out_priv->ppriv;
-		esw_attr->dests[out_index].rep = rpriv->rep;
-		esw_attr->dests[out_index].mdev = out_priv->mdev;
-	}
-
-	if (*vf_tun && esw_attr->out_count > 1) {
-		NL_SET_ERR_MSG_MOD(extack, "VF tunnel encap with mirroring is not supported");
-		err = -EOPNOTSUPP;
-		goto out;
-	}
-
-out:
-	return err;
-}
-
-static void
-clean_encap_dests(struct mlx5e_priv *priv,
-		  struct mlx5e_tc_flow *flow,
-		  struct mlx5_flow_attr *attr)
-{
-	struct mlx5_esw_flow_attr *esw_attr;
-	int out_index;
-
-	if (!mlx5e_is_eswitch_flow(flow))
-		return;
-
-	esw_attr = attr->esw_attr;
-
-	for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) {
-		if (!(esw_attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP))
-			continue;
-
-		mlx5e_detach_encap(priv, flow, attr, out_index);
-		kfree(attr->parse_attr->tun_info[out_index]);
-	}
-}
-
 static int
 verify_attr_actions(u32 actions, struct netlink_ext_ack *extack)
 {
@@ -1820,7 +1735,7 @@ post_process_attr(struct mlx5e_tc_flow *flow,
 	if (err)
 		goto err_out;
 
-	err = set_encap_dests(flow->priv, flow, attr, extack, &vf_tun);
+	err = mlx5e_tc_tun_encap_dests_set(flow->priv, flow, attr, extack, &vf_tun);
 	if (err)
 		goto err_out;
 
@@ -3944,8 +3859,8 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state,
 	struct mlx5_flow_attr *prev_attr;
 	struct flow_action_entry *act;
 	struct mlx5e_tc_act *tc_act;
+	int err, i, i_split = 0;
 	bool is_missable;
-	int err, i;
 
 	ns_type = mlx5e_get_flow_namespace(flow);
 	list_add(&attr->list, &flow->attrs);
@@ -3986,7 +3901,8 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state,
 		    i < flow_action->num_entries - 1)) {
 			is_missable = tc_act->is_missable ? tc_act->is_missable(act) : false;
 
-			err = mlx5e_tc_act_post_parse(parse_state, flow_action, attr, ns_type);
+			err = mlx5e_tc_act_post_parse(parse_state, flow_action, i_split, i, attr,
+						      ns_type);
 			if (err)
 				goto out_free_post_acts;
 
@@ -3996,6 +3912,7 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state,
 				goto out_free_post_acts;
 			}
 
+			i_split = i + 1;
 			list_add(&attr->list, &flow->attrs);
 		}
 
@@ -4010,7 +3927,7 @@ parse_tc_actions(struct mlx5e_tc_act_parse_state *parse_state,
 		}
 	}
 
-	err = mlx5e_tc_act_post_parse(parse_state, flow_action, attr, ns_type);
+	err = mlx5e_tc_act_post_parse(parse_state, flow_action, i_split, i, attr, ns_type);
 	if (err)
 		goto out_free_post_acts;
 
@@ -4324,7 +4241,7 @@ mlx5_free_flow_attr_actions(struct mlx5e_tc_flow *flow, struct mlx5_flow_attr *a
 	if (attr->post_act_handle)
 		mlx5e_tc_post_act_del(get_post_action(flow->priv), attr->post_act_handle);
 
-	clean_encap_dests(flow->priv, flow, attr);
+	mlx5e_tc_tun_encap_dests_unset(flow->priv, flow, attr);
 
 	if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT)
 		mlx5_fc_destroy(counter_dev, attr->counter);

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

@@ -824,7 +824,7 @@ static int comp_irqs_request_pci(struct mlx5_core_dev *dev)
 	ncomp_eqs = table->num_comp_eqs;
 	cpus = kcalloc(ncomp_eqs, sizeof(*cpus), GFP_KERNEL);
 	if (!cpus)
-		ret = -ENOMEM;
+		return -ENOMEM;
 
 	i = 0;
 	rcu_read_lock();

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

@@ -1802,15 +1802,16 @@ static void remove_one(struct pci_dev *pdev)
 	struct devlink *devlink = priv_to_devlink(dev);
 
 	set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state);
-	/* mlx5_drain_fw_reset() is using devlink APIs. Hence, we must drain
-	 * fw_reset before unregistering the devlink.
+	/* mlx5_drain_fw_reset() and mlx5_drain_health_wq() are using
+	 * devlink notify APIs.
+	 * Hence, we must drain them before unregistering the devlink.
 	 */
 	mlx5_drain_fw_reset(dev);
+	mlx5_drain_health_wq(dev);
 	devlink_unregister(devlink);
 	mlx5_sriov_disable(pdev);
 	mlx5_thermal_uninit(dev);
 	mlx5_crdump_disable(dev);
-	mlx5_drain_health_wq(dev);
 	mlx5_uninit_one(dev);
 	mlx5_pci_close(dev);
 	mlx5_mdev_uninit(dev);

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

@@ -32,6 +32,7 @@
 
 #include <linux/kernel.h>
 #include <linux/mlx5/driver.h>
+#include <linux/mlx5/qp.h>
 #include "mlx5_core.h"
 
 int mlx5_core_create_mkey(struct mlx5_core_dev *dev, u32 *mkey, u32 *in,
@@ -122,3 +123,23 @@ int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num)
 	return mlx5_cmd_exec_in(dev, destroy_psv, in);
 }
 EXPORT_SYMBOL(mlx5_core_destroy_psv);
+
+__be32 mlx5_core_get_terminate_scatter_list_mkey(struct mlx5_core_dev *dev)
+{
+	u32 out[MLX5_ST_SZ_DW(query_special_contexts_out)] = {};
+	u32 in[MLX5_ST_SZ_DW(query_special_contexts_in)] = {};
+	u32 mkey;
+
+	if (!MLX5_CAP_GEN(dev, terminate_scatter_list_mkey))
+		return MLX5_TERMINATE_SCATTER_LIST_LKEY;
+
+	MLX5_SET(query_special_contexts_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS);
+	if (mlx5_cmd_exec_inout(dev, query_special_contexts, in, out))
+		return MLX5_TERMINATE_SCATTER_LIST_LKEY;
+
+	mkey = MLX5_GET(query_special_contexts_out, out,
+			terminate_scatter_list_mkey);
+	return cpu_to_be32(mkey);
+}
+EXPORT_SYMBOL(mlx5_core_get_terminate_scatter_list_mkey);

drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c

@@ -63,6 +63,7 @@ static void mlx5_sf_dev_remove(struct auxiliary_device *adev)
 	struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev);
 	struct devlink *devlink = priv_to_devlink(sf_dev->mdev);
 
+	mlx5_drain_health_wq(sf_dev->mdev);
 	devlink_unregister(devlink);
 	mlx5_uninit_one(sf_dev->mdev);
 	iounmap(sf_dev->mdev->iseg);

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ptrn.c

@@ -213,6 +213,8 @@ struct mlx5dr_ptrn_mgr *mlx5dr_ptrn_mgr_create(struct mlx5dr_domain *dmn)
 	}
 
 	INIT_LIST_HEAD(&mgr->ptrn_list);
+	mutex_init(&mgr->modify_hdr_mutex);
+
 	return mgr;
 
 free_mgr:
@@ -237,5 +239,6 @@ void mlx5dr_ptrn_mgr_destroy(struct mlx5dr_ptrn_mgr *mgr)
 	}
 
 	mlx5dr_icm_pool_destroy(mgr->ptrn_icm_pool);
+	mutex_destroy(&mgr->modify_hdr_mutex);
 	kfree(mgr);
 }

include/linux/mlx5/driver.h

@@ -1093,6 +1093,7 @@ void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev);
 int mlx5_core_create_psv(struct mlx5_core_dev *dev, u32 pdn,
 			 int npsvs, u32 *sig_index);
 int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num);
+__be32 mlx5_core_get_terminate_scatter_list_mkey(struct mlx5_core_dev *dev);
 void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common);
 int mlx5_query_odp_caps(struct mlx5_core_dev *dev,
 			struct mlx5_odp_caps *odp_caps);