Merge tag 'mlx5-updates-2024-02-01' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

Saeed Mahameed says:

====================
mlx5-updates-2024-02-01

1) IPSec global stats for xfrm and mlx5
2) XSK memory improvements for non-linear SKBs
3) Software steering debug dump to use seq_file ops
4) Various code clean-ups

* tag 'mlx5-updates-2024-02-01' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux:
  net/mlx5e: XDP, Exclude headroom and tailroom from memory calculations
  net/mlx5e: XSK, Exclude tailroom from non-linear SKBs memory calculations
  net/mlx5: DR, Change SWS usage to debug fs seq_file interface
  net/mlx5: Change missing SyncE capability print to debug
  net/mlx5: Remove initial segmentation duplicate definitions
  net/mlx5: Return specific error code for timeout on wait_fw_init
  net/mlx5: SF, Stop waiting for FW as teardown was called
  net/mlx5: remove fw reporter dump option for non PF
  net/mlx5: remove fw_fatal reporter dump option for non PF
  net/mlx5: Rename mlx5_sf_dev_remove
  Documentation: Fix counter name of mlx5 vnic reporter
  net/mlx5e: Delete obsolete IPsec code
  net/mlx5e: Connect mlx5 IPsec statistics with XFRM core
  xfrm: get global statistics from the offloaded device
  xfrm: generalize xdo_dev_state_update_curlft to allow statistics update
====================

Link: https://lore.kernel.org/r/20240206005527.1353368-1-saeed@kernel.orgSigned-off-by: Jakub Kicinski <kuba@kernel.org>

Documentation/networking/devlink/mlx5.rst

@@ -250,7 +250,7 @@ them in realtime.
 
 Description of the vnic counters:
 
-- total_q_under_processor_handle
+- total_error_queues
         number of queues in an error state due to
         an async error or errored command.
 - send_queue_priority_update_flow
@@ -259,7 +259,8 @@ Description of the vnic counters:
         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
+- 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.

Documentation/networking/xfrm_device.rst

@@ -71,9 +71,9 @@ Callbacks to implement
 	bool	(*xdo_dev_offload_ok) (struct sk_buff *skb,
 				       struct xfrm_state *x);
 	void    (*xdo_dev_state_advance_esn) (struct xfrm_state *x);
+	void    (*xdo_dev_state_update_stats) (struct xfrm_state *x);
 
         /* Solely packet offload callbacks */
-	void    (*xdo_dev_state_update_curlft) (struct xfrm_state *x);
 	int	(*xdo_dev_policy_add) (struct xfrm_policy *x, struct netlink_ext_ack *extack);
 	void	(*xdo_dev_policy_delete) (struct xfrm_policy *x);
 	void	(*xdo_dev_policy_free) (struct xfrm_policy *x);
@@ -191,6 +191,6 @@ xdo_dev_policy_free() on any remaining offloaded states.
 
 Outcome of HW handling packets, the XFRM core can't count hard, soft limits.
 The HW/driver are responsible to perform it and provide accurate data when
-xdo_dev_state_update_curlft() is called. In case of one of these limits
+xdo_dev_state_update_stats() is called. In case of one of these limits
 occuried, the driver needs to call to xfrm_state_check_expire() to make sure
 that XFRM performs rekeying sequence.

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

@@ -210,7 +210,7 @@ static bool is_dpll_supported(struct mlx5_core_dev *dev)
 		return false;
 
 	if (!MLX5_CAP_MCAM_REG2(dev, synce_registers)) {
-		mlx5_core_warn(dev, "Missing SyncE capability\n");
+		mlx5_core_dbg(dev, "Missing SyncE capability\n");
 		return false;
 	}
 

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

@@ -240,11 +240,14 @@ static u32 mlx5e_rx_get_linear_sz_xsk(struct mlx5e_params *params,
 	return xsk->headroom + hw_mtu;
 }
 
-static u32 mlx5e_rx_get_linear_sz_skb(struct mlx5e_params *params, bool xsk)
+static u32 mlx5e_rx_get_linear_sz_skb(struct mlx5e_params *params, bool no_head_tail_room)
 {
-	/* SKBs built on XDP_PASS on XSK RQs don't have headroom. */
-	u16 headroom = xsk ? 0 : mlx5e_get_linear_rq_headroom(params, NULL);
 	u32 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
+	u16 headroom;
+
+	if (no_head_tail_room)
+		return SKB_DATA_ALIGN(hw_mtu);
+	headroom = mlx5e_get_linear_rq_headroom(params, NULL);
 
 	return MLX5_SKB_FRAG_SZ(headroom + hw_mtu);
 }
@@ -254,6 +257,7 @@ static u32 mlx5e_rx_get_linear_stride_sz(struct mlx5_core_dev *mdev,
 					 struct mlx5e_xsk_param *xsk,
 					 bool mpwqe)
 {
+	bool no_head_tail_room;
 	u32 sz;
 
 	/* XSK frames are mapped as individual pages, because frames may come in
@@ -262,7 +266,13 @@ static u32 mlx5e_rx_get_linear_stride_sz(struct mlx5_core_dev *mdev,
 	if (xsk)
 		return mpwqe ? 1 << mlx5e_mpwrq_page_shift(mdev, xsk) : PAGE_SIZE;
 
-	sz = roundup_pow_of_two(mlx5e_rx_get_linear_sz_skb(params, false));
+	no_head_tail_room = params->xdp_prog && mpwqe && !mlx5e_rx_is_linear_skb(mdev, params, xsk);
+
+	/* When no_head_tail_room is set, headroom and tailroom are excluded from skb calculations.
+	 * no_head_tail_room should be set in the case of XDP with Striding RQ
+	 * when SKB is not linear. This is because another page is allocated for the linear part.
+	 */
+	sz = roundup_pow_of_two(mlx5e_rx_get_linear_sz_skb(params, no_head_tail_room));
 
 	/* XDP in mlx5e doesn't support multiple packets per page.
 	 * Do not assume sz <= PAGE_SIZE if params->xdp_prog is set.
@@ -289,7 +299,11 @@ bool mlx5e_rx_is_linear_skb(struct mlx5_core_dev *mdev,
 	if (params->packet_merge.type != MLX5E_PACKET_MERGE_NONE)
 		return false;
 
-	/* Both XSK and non-XSK cases allocate an SKB on XDP_PASS. Packet data
+	/* Call mlx5e_rx_get_linear_sz_skb with the no_head_tail_room parameter set
+	 * to exclude headroom and tailroom from calculations.
+	 * no_head_tail_room is true when SKB is built on XDP_PASS on XSK RQs
+	 * since packet data buffers don't have headroom and tailroom resreved for the SKB.
+	 * Both XSK and non-XSK cases allocate an SKB on XDP_PASS. Packet data
 	 * must fit into a CPU page.
 	 */
 	if (mlx5e_rx_get_linear_sz_skb(params, xsk) > PAGE_SIZE)

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

@@ -984,21 +984,41 @@ static void mlx5e_xfrm_advance_esn_state(struct xfrm_state *x)
 	queue_work(sa_entry->ipsec->wq, &work->work);
 }
 
-static void mlx5e_xfrm_update_curlft(struct xfrm_state *x)
+static void mlx5e_xfrm_update_stats(struct xfrm_state *x)
 {
 	struct mlx5e_ipsec_sa_entry *sa_entry = to_ipsec_sa_entry(x);
 	struct mlx5e_ipsec_rule *ipsec_rule = &sa_entry->ipsec_rule;
+	struct net *net = dev_net(x->xso.dev);
 	u64 packets, bytes, lastuse;
 
 	lockdep_assert(lockdep_is_held(&x->lock) ||
-		       lockdep_is_held(&dev_net(x->xso.real_dev)->xfrm.xfrm_cfg_mutex));
+		       lockdep_is_held(&dev_net(x->xso.real_dev)->xfrm.xfrm_cfg_mutex) ||
+		       lockdep_is_held(&dev_net(x->xso.real_dev)->xfrm.xfrm_state_lock));
 
 	if (x->xso.flags & XFRM_DEV_OFFLOAD_FLAG_ACQ)
 		return;
 
+	if (sa_entry->attrs.dir == XFRM_DEV_OFFLOAD_IN) {
+		mlx5_fc_query_cached(ipsec_rule->auth.fc, &bytes, &packets, &lastuse);
+		x->stats.integrity_failed += packets;
+		XFRM_ADD_STATS(net, LINUX_MIB_XFRMINSTATEPROTOERROR, packets);
+
+		mlx5_fc_query_cached(ipsec_rule->trailer.fc, &bytes, &packets, &lastuse);
+		XFRM_ADD_STATS(net, LINUX_MIB_XFRMINHDRERROR, packets);
+	}
+
+	if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET)
+		return;
+
 	mlx5_fc_query_cached(ipsec_rule->fc, &bytes, &packets, &lastuse);
 	x->curlft.packets += packets;
 	x->curlft.bytes += bytes;
+
+	if (sa_entry->attrs.dir == XFRM_DEV_OFFLOAD_IN) {
+		mlx5_fc_query_cached(ipsec_rule->replay.fc, &bytes, &packets, &lastuse);
+		x->stats.replay += packets;
+		XFRM_ADD_STATS(net, LINUX_MIB_XFRMINSTATESEQERROR, packets);
+	}
 }
 
 static int mlx5e_xfrm_validate_policy(struct mlx5_core_dev *mdev,
@@ -1156,7 +1176,7 @@ static const struct xfrmdev_ops mlx5e_ipsec_xfrmdev_ops = {
 	.xdo_dev_offload_ok	= mlx5e_ipsec_offload_ok,
 	.xdo_dev_state_advance_esn = mlx5e_xfrm_advance_esn_state,
 
-	.xdo_dev_state_update_curlft = mlx5e_xfrm_update_curlft,
+	.xdo_dev_state_update_stats = mlx5e_xfrm_update_stats,
 	.xdo_dev_policy_add = mlx5e_xfrm_add_policy,
 	.xdo_dev_policy_delete = mlx5e_xfrm_del_policy,
 	.xdo_dev_policy_free = mlx5e_xfrm_free_policy,

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

@@ -137,7 +137,6 @@ struct mlx5e_ipsec_hw_stats {
 struct mlx5e_ipsec_sw_stats {
 	atomic64_t ipsec_rx_drop_sp_alloc;
 	atomic64_t ipsec_rx_drop_sadb_miss;
-	atomic64_t ipsec_rx_drop_syndrome;
 	atomic64_t ipsec_tx_drop_bundle;
 	atomic64_t ipsec_tx_drop_no_state;
 	atomic64_t ipsec_tx_drop_not_ip;

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

@@ -304,12 +304,6 @@ bool mlx5e_ipsec_handle_tx_skb(struct net_device *netdev,
 	return false;
 }
 
-enum {
-	MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_DECRYPTED,
-	MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_AUTH_FAILED,
-	MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_BAD_TRAILER,
-};
-
 void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev,
 				       struct sk_buff *skb,
 				       u32 ipsec_meta_data)
@@ -343,20 +337,7 @@ void mlx5e_ipsec_offload_handle_rx_skb(struct net_device *netdev,
 
 	xo = xfrm_offload(skb);
 	xo->flags = CRYPTO_DONE;
-
-	switch (MLX5_IPSEC_METADATA_SYNDROM(ipsec_meta_data)) {
-	case MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_DECRYPTED:
-		xo->status = CRYPTO_SUCCESS;
-		break;
-	case MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_AUTH_FAILED:
-		xo->status = CRYPTO_TUNNEL_ESP_AUTH_FAILED;
-		break;
-	case MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_BAD_TRAILER:
-		xo->status = CRYPTO_INVALID_PACKET_SYNTAX;
-		break;
-	default:
-		atomic64_inc(&ipsec->sw_stats.ipsec_rx_drop_syndrome);
-	}
+	xo->status = CRYPTO_SUCCESS;
 }
 
 int mlx5_esw_ipsec_rx_make_metadata(struct mlx5e_priv *priv, u32 id, u32 *metadata)
@@ -374,8 +355,6 @@ int mlx5_esw_ipsec_rx_make_metadata(struct mlx5e_priv *priv, u32 id, u32 *metada
 		return err;
 	}
 
-	*metadata = MLX5_IPSEC_METADATA_CREATE(ipsec_obj_id,
-					       MLX5E_IPSEC_OFFLOAD_RX_SYNDROME_DECRYPTED);
-
+	*metadata = ipsec_obj_id;
 	return 0;
 }

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

@@ -43,7 +43,6 @@
 #define MLX5_IPSEC_METADATA_MARKER(metadata)  (((metadata) >> 31) & 0x1)
 #define MLX5_IPSEC_METADATA_SYNDROM(metadata) (((metadata) >> 24) & GENMASK(5, 0))
 #define MLX5_IPSEC_METADATA_HANDLE(metadata)  ((metadata) & GENMASK(23, 0))
-#define MLX5_IPSEC_METADATA_CREATE(id, syndrome) ((id) | ((syndrome) << 24))
 
 struct mlx5e_accel_tx_ipsec_state {
 	struct xfrm_offload *xo;

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

@@ -51,7 +51,6 @@ static const struct counter_desc mlx5e_ipsec_hw_stats_desc[] = {
 static const struct counter_desc mlx5e_ipsec_sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_sw_stats, ipsec_rx_drop_sp_alloc) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_sw_stats, ipsec_rx_drop_sadb_miss) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_sw_stats, ipsec_rx_drop_syndrome) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_sw_stats, ipsec_tx_drop_bundle) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_sw_stats, ipsec_tx_drop_no_state) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_sw_stats, ipsec_tx_drop_not_ip) },

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

@@ -366,18 +366,18 @@ int mlx5_cmd_fast_teardown_hca(struct mlx5_core_dev *dev)
 		return -EIO;
 	}
 
-	mlx5_set_nic_state(dev, MLX5_NIC_IFC_DISABLED);
+	mlx5_set_nic_state(dev, MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED);
 
 	/* Loop until device state turns to disable */
 	end = jiffies + msecs_to_jiffies(delay_ms);
 	do {
-		if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED)
+		if (mlx5_get_nic_state(dev) == MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED)
 			break;
 
 		cond_resched();
 	} while (!time_after(jiffies, end));
 
-	if (mlx5_get_nic_state(dev) != MLX5_NIC_IFC_DISABLED) {
+	if (mlx5_get_nic_state(dev) != MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED) {
 		dev_err(&dev->pdev->dev, "NIC IFC still %d after %lums.\n",
 			mlx5_get_nic_state(dev), delay_ms);
 		return -EIO;

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

@@ -116,9 +116,9 @@ u32 mlx5_health_check_fatal_sensors(struct mlx5_core_dev *dev)
 		return MLX5_SENSOR_PCI_COMM_ERR;
 	if (pci_channel_offline(dev->pdev))
 		return MLX5_SENSOR_PCI_ERR;
-	if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED)
+	if (mlx5_get_nic_state(dev) == MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED)
 		return MLX5_SENSOR_NIC_DISABLED;
-	if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_SW_RESET)
+	if (mlx5_get_nic_state(dev) == MLX5_INITIAL_SEG_NIC_INTERFACE_SW_RESET)
 		return MLX5_SENSOR_NIC_SW_RESET;
 	if (sensor_fw_synd_rfr(dev))
 		return MLX5_SENSOR_FW_SYND_RFR;
@@ -185,7 +185,7 @@ static bool reset_fw_if_needed(struct mlx5_core_dev *dev)
 	/* Write the NIC interface field to initiate the reset, the command
 	 * interface address also resides here, don't overwrite it.
 	 */
-	mlx5_set_nic_state(dev, MLX5_NIC_IFC_SW_RESET);
+	mlx5_set_nic_state(dev, MLX5_INITIAL_SEG_NIC_INTERFACE_SW_RESET);
 
 	return true;
 }
@@ -246,13 +246,13 @@ void mlx5_error_sw_reset(struct mlx5_core_dev *dev)
 	/* Recover from SW reset */
 	end = jiffies + msecs_to_jiffies(delay_ms);
 	do {
-		if (mlx5_get_nic_state(dev) == MLX5_NIC_IFC_DISABLED)
+		if (mlx5_get_nic_state(dev) == MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED)
 			break;
 
 		msleep(20);
 	} while (!time_after(jiffies, end));
 
-	if (mlx5_get_nic_state(dev) != MLX5_NIC_IFC_DISABLED) {
+	if (mlx5_get_nic_state(dev) != MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED) {
 		dev_err(&dev->pdev->dev, "NIC IFC still %d after %lums.\n",
 			mlx5_get_nic_state(dev), delay_ms);
 	}
@@ -272,26 +272,26 @@ static void mlx5_handle_bad_state(struct mlx5_core_dev *dev)
 	u8 nic_interface = mlx5_get_nic_state(dev);
 
 	switch (nic_interface) {
-	case MLX5_NIC_IFC_FULL:
+	case MLX5_INITIAL_SEG_NIC_INTERFACE_FULL_DRIVER:
 		mlx5_core_warn(dev, "Expected to see disabled NIC but it is full driver\n");
 		break;
 
-	case MLX5_NIC_IFC_DISABLED:
+	case MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED:
 		mlx5_core_warn(dev, "starting teardown\n");
 		break;
 
-	case MLX5_NIC_IFC_NO_DRAM_NIC:
+	case MLX5_INITIAL_SEG_NIC_INTERFACE_NO_DRAM_NIC:
 		mlx5_core_warn(dev, "Expected to see disabled NIC but it is no dram nic\n");
 		break;
 
-	case MLX5_NIC_IFC_SW_RESET:
+	case MLX5_INITIAL_SEG_NIC_INTERFACE_SW_RESET:
 		/* The IFC mode field is 3 bits, so it will read 0x7 in 2 cases:
 		 * 1. PCI has been disabled (ie. PCI-AER, PF driver unloaded
 		 *    and this is a VF), this is not recoverable by SW reset.
 		 *    Logging of this is handled elsewhere.
 		 * 2. FW reset has been issued by another function, driver can
 		 *    be reloaded to recover after the mode switches to
-		 *    MLX5_NIC_IFC_DISABLED.
+		 *    MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED.
 		 */
 		if (dev->priv.health.fatal_error != MLX5_SENSOR_PCI_COMM_ERR)
 			mlx5_core_warn(dev, "NIC SW reset in progress\n");
@@ -555,12 +555,17 @@ static void mlx5_fw_reporter_err_work(struct work_struct *work)
 				      &fw_reporter_ctx);
 }
 
-static const struct devlink_health_reporter_ops mlx5_fw_reporter_ops = {
+static const struct devlink_health_reporter_ops mlx5_fw_reporter_pf_ops = {
 		.name = "fw",
 		.diagnose = mlx5_fw_reporter_diagnose,
 		.dump = mlx5_fw_reporter_dump,
 };
 
+static const struct devlink_health_reporter_ops mlx5_fw_reporter_ops = {
+		.name = "fw",
+		.diagnose = mlx5_fw_reporter_diagnose,
+};
+
 static int
 mlx5_fw_fatal_reporter_recover(struct devlink_health_reporter *reporter,
 			       void *priv_ctx,
@@ -646,12 +651,17 @@ static void mlx5_fw_fatal_reporter_err_work(struct work_struct *work)
 	}
 }
 
-static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_ops = {
+static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_pf_ops = {
 		.name = "fw_fatal",
 		.recover = mlx5_fw_fatal_reporter_recover,
 		.dump = mlx5_fw_fatal_reporter_dump,
 };
 
+static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_ops = {
+		.name = "fw_fatal",
+		.recover = mlx5_fw_fatal_reporter_recover,
+};
+
 #define MLX5_FW_REPORTER_ECPF_GRACEFUL_PERIOD 180000
 #define MLX5_FW_REPORTER_PF_GRACEFUL_PERIOD 60000
 #define MLX5_FW_REPORTER_VF_GRACEFUL_PERIOD 30000
@@ -659,10 +669,14 @@ static const struct devlink_health_reporter_ops mlx5_fw_fatal_reporter_ops = {
 
 void mlx5_fw_reporters_create(struct mlx5_core_dev *dev)
 {
+	const struct devlink_health_reporter_ops *fw_fatal_ops;
 	struct mlx5_core_health *health = &dev->priv.health;
+	const struct devlink_health_reporter_ops *fw_ops;
 	struct devlink *devlink = priv_to_devlink(dev);
 	u64 grace_period;
 
+	fw_fatal_ops = &mlx5_fw_fatal_reporter_pf_ops;
+	fw_ops = &mlx5_fw_reporter_pf_ops;
 	if (mlx5_core_is_ecpf(dev)) {
 		grace_period = MLX5_FW_REPORTER_ECPF_GRACEFUL_PERIOD;
 	} else if (mlx5_core_is_pf(dev)) {
@@ -670,18 +684,19 @@ void mlx5_fw_reporters_create(struct mlx5_core_dev *dev)
 	} else {
 		/* VF or SF */
 		grace_period = MLX5_FW_REPORTER_DEFAULT_GRACEFUL_PERIOD;
+		fw_fatal_ops = &mlx5_fw_fatal_reporter_ops;
+		fw_ops = &mlx5_fw_reporter_ops;
 	}
 
 	health->fw_reporter =
-		devl_health_reporter_create(devlink, &mlx5_fw_reporter_ops,
-					    0, dev);
+		devl_health_reporter_create(devlink, fw_ops, 0, dev);
 	if (IS_ERR(health->fw_reporter))
 		mlx5_core_warn(dev, "Failed to create fw reporter, err = %ld\n",
 			       PTR_ERR(health->fw_reporter));
 
 	health->fw_fatal_reporter =
 		devl_health_reporter_create(devlink,
-					    &mlx5_fw_fatal_reporter_ops,
+					    fw_fatal_ops,
 					    grace_period,
 					    dev);
 	if (IS_ERR(health->fw_fatal_reporter))

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

@@ -187,31 +187,36 @@ static struct mlx5_profile profile[] = {
 };
 
 static int wait_fw_init(struct mlx5_core_dev *dev, u32 max_wait_mili,
-			u32 warn_time_mili)
+			u32 warn_time_mili, const char *init_state)
 {
 	unsigned long warn = jiffies + msecs_to_jiffies(warn_time_mili);
 	unsigned long end = jiffies + msecs_to_jiffies(max_wait_mili);
 	u32 fw_initializing;
-	int err = 0;
 
 	do {
 		fw_initializing = ioread32be(&dev->iseg->initializing);
 		if (!(fw_initializing >> 31))
 			break;
-		if (time_after(jiffies, end) ||
-		    test_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state)) {
-			err = -EBUSY;
-			break;
+		if (time_after(jiffies, end)) {
+			mlx5_core_err(dev, "Firmware over %u MS in %s state, aborting\n",
+				      max_wait_mili, init_state);
+			return -ETIMEDOUT;
+		}
+		if (test_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state)) {
+			mlx5_core_warn(dev, "device is being removed, stop waiting for FW %s\n",
+				       init_state);
+			return -ENODEV;
 		}
 		if (warn_time_mili && time_after(jiffies, warn)) {
-			mlx5_core_warn(dev, "Waiting for FW initialization, timeout abort in %ds (0x%x)\n",
-				       jiffies_to_msecs(end - warn) / 1000, fw_initializing);
+			mlx5_core_warn(dev, "Waiting for FW %s, timeout abort in %ds (0x%x)\n",
+				       init_state, jiffies_to_msecs(end - warn) / 1000,
+				       fw_initializing);
 			warn = jiffies + msecs_to_jiffies(warn_time_mili);
 		}
 		msleep(mlx5_tout_ms(dev, FW_PRE_INIT_WAIT));
 	} while (true);
 
-	return err;
+	return 0;
 }
 
 static void mlx5_set_driver_version(struct mlx5_core_dev *dev)
@@ -1151,12 +1156,10 @@ static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeou
 	/* wait for firmware to accept initialization segments configurations
 	 */
 	err = wait_fw_init(dev, timeout,
-			   mlx5_tout_ms(dev, FW_PRE_INIT_WARN_MESSAGE_INTERVAL));
-	if (err) {
-		mlx5_core_err(dev, "Firmware over %llu MS in pre-initializing state, aborting\n",
-			      timeout);
+			   mlx5_tout_ms(dev, FW_PRE_INIT_WARN_MESSAGE_INTERVAL),
+			   "pre-initializing");
+	if (err)
 		return err;
-	}
 
 	err = mlx5_cmd_enable(dev);
 	if (err) {
@@ -1166,12 +1169,9 @@ static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeou
 
 	mlx5_tout_query_iseg(dev);
 
-	err = wait_fw_init(dev, mlx5_tout_ms(dev, FW_INIT), 0);
-	if (err) {
-		mlx5_core_err(dev, "Firmware over %llu MS in initializing state, aborting\n",
-			      mlx5_tout_ms(dev, FW_INIT));
+	err = wait_fw_init(dev, mlx5_tout_ms(dev, FW_INIT), 0, "initializing");
+	if (err)
 		goto err_cmd_cleanup;
-	}
 
 	dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev);
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_UP);

drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h

@@ -312,13 +312,6 @@ static inline int mlx5_rescan_drivers(struct mlx5_core_dev *dev)
 	return ret;
 }
 
-enum {
-	MLX5_NIC_IFC_FULL		= 0,
-	MLX5_NIC_IFC_DISABLED		= 1,
-	MLX5_NIC_IFC_NO_DRAM_NIC	= 2,
-	MLX5_NIC_IFC_SW_RESET		= 7
-};
-
 u8 mlx5_get_nic_state(struct mlx5_core_dev *dev);
 void mlx5_set_nic_state(struct mlx5_core_dev *dev, u8 state);
 

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

@@ -74,7 +74,8 @@ static void mlx5_sf_dev_release(struct device *device)
 	kfree(sf_dev);
 }
 
-static void mlx5_sf_dev_remove(struct mlx5_core_dev *dev, struct mlx5_sf_dev *sf_dev)
+static void mlx5_sf_dev_remove_aux(struct mlx5_core_dev *dev,
+				   struct mlx5_sf_dev *sf_dev)
 {
 	int id;
 
@@ -138,7 +139,7 @@ static void mlx5_sf_dev_add(struct mlx5_core_dev *dev, u16 sf_index, u16 fn_id,
 	return;
 
 xa_err:
-	mlx5_sf_dev_remove(dev, sf_dev);
+	mlx5_sf_dev_remove_aux(dev, sf_dev);
 add_err:
 	mlx5_core_err(dev, "SF DEV: fail device add for index=%d sfnum=%d err=%d\n",
 		      sf_index, sfnum, err);
@@ -149,7 +150,7 @@ static void mlx5_sf_dev_del(struct mlx5_core_dev *dev, struct mlx5_sf_dev *sf_de
 	struct mlx5_sf_dev_table *table = dev->priv.sf_dev_table;
 
 	xa_erase(&table->devices, sf_index);
-	mlx5_sf_dev_remove(dev, sf_dev);
+	mlx5_sf_dev_remove_aux(dev, sf_dev);
 }
 
 static int
@@ -367,7 +368,7 @@ static void mlx5_sf_dev_destroy_all(struct mlx5_sf_dev_table *table)
 
 	xa_for_each(&table->devices, index, sf_dev) {
 		xa_erase(&table->devices, index);
-		mlx5_sf_dev_remove(table->dev, sf_dev);
+		mlx5_sf_dev_remove_aux(table->dev, sf_dev);
 	}
 }
 

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

@@ -95,24 +95,29 @@ static int mlx5_sf_dev_probe(struct auxiliary_device *adev, const struct auxilia
 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);
+	struct mlx5_core_dev *mdev = sf_dev->mdev;
+	struct devlink *devlink;
 
-	mlx5_drain_health_wq(sf_dev->mdev);
+	devlink = priv_to_devlink(mdev);
+	set_bit(MLX5_BREAK_FW_WAIT, &mdev->intf_state);
+	mlx5_drain_health_wq(mdev);
 	devlink_unregister(devlink);
-	if (mlx5_dev_is_lightweight(sf_dev->mdev))
-		mlx5_uninit_one_light(sf_dev->mdev);
+	if (mlx5_dev_is_lightweight(mdev))
+		mlx5_uninit_one_light(mdev);
 	else
-		mlx5_uninit_one(sf_dev->mdev);
-	iounmap(sf_dev->mdev->iseg);
-	mlx5_mdev_uninit(sf_dev->mdev);
+		mlx5_uninit_one(mdev);
+	iounmap(mdev->iseg);
+	mlx5_mdev_uninit(mdev);
 	mlx5_devlink_free(devlink);
 }
 
 static void mlx5_sf_dev_shutdown(struct auxiliary_device *adev)
 {
 	struct mlx5_sf_dev *sf_dev = container_of(adev, struct mlx5_sf_dev, adev);
+	struct mlx5_core_dev *mdev = sf_dev->mdev;
 
-	mlx5_unload_one(sf_dev->mdev, false);
+	set_bit(MLX5_BREAK_FW_WAIT, &mdev->intf_state);
+	mlx5_unload_one(mdev, false);
 }
 
 static const struct auxiliary_device_id mlx5_sf_dev_id_table[] = {

drivers/net/ethernet/mellanox/mlx5/core/steering/dr_dbg.h

 /* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
 /* Copyright (c) 2021, NVIDIA CORPORATION & AFFILIATES. All rights reserved. */
 
+#define MLX5DR_DEBUG_DUMP_BUFF_SIZE (64 * 1024 * 1024)
+#define MLX5DR_DEBUG_DUMP_BUFF_LENGTH 512
+
+enum {
+	MLX5DR_DEBUG_DUMP_STATE_FREE,
+	MLX5DR_DEBUG_DUMP_STATE_IN_PROGRESS,
+};
+
+struct mlx5dr_dbg_dump_buff {
+	char *buff;
+	u32 index;
+	struct list_head node;
+};
+
+struct mlx5dr_dbg_dump_data {
+	struct list_head buff_list;
+};
+
 struct mlx5dr_dbg_dump_info {
 	struct mutex dbg_mutex; /* protect dbg lists */
 	struct dentry *steering_debugfs;
 	struct dentry *fdb_debugfs;
+	struct mlx5dr_dbg_dump_data *dump_data;
+	atomic_t state;
 };
 
 void mlx5dr_dbg_init_dump(struct mlx5dr_domain *dmn);

include/linux/mlx5/mlx5_ifc.h

@@ -10661,6 +10661,7 @@ enum {
 	MLX5_INITIAL_SEG_NIC_INTERFACE_FULL_DRIVER  = 0x0,
 	MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED     = 0x1,
 	MLX5_INITIAL_SEG_NIC_INTERFACE_NO_DRAM_NIC  = 0x2,
+	MLX5_INITIAL_SEG_NIC_INTERFACE_SW_RESET     = 0x7,
 };
 
 enum {

include/linux/netdevice.h

@@ -1062,7 +1062,7 @@ struct xfrmdev_ops {
 	bool	(*xdo_dev_offload_ok) (struct sk_buff *skb,
 				       struct xfrm_state *x);
 	void	(*xdo_dev_state_advance_esn) (struct xfrm_state *x);
-	void	(*xdo_dev_state_update_curlft) (struct xfrm_state *x);
+	void	(*xdo_dev_state_update_stats) (struct xfrm_state *x);
 	int	(*xdo_dev_policy_add) (struct xfrm_policy *x, struct netlink_ext_ack *extack);
 	void	(*xdo_dev_policy_delete) (struct xfrm_policy *x);
 	void	(*xdo_dev_policy_free) (struct xfrm_policy *x);

include/net/xfrm.h

@@ -51,8 +51,10 @@
 
 #ifdef CONFIG_XFRM_STATISTICS
 #define XFRM_INC_STATS(net, field)	SNMP_INC_STATS((net)->mib.xfrm_statistics, field)
+#define XFRM_ADD_STATS(net, field, val) SNMP_ADD_STATS((net)->mib.xfrm_statistics, field, val)
 #else
 #define XFRM_INC_STATS(net, field)	((void)(net))
+#define XFRM_ADD_STATS(net, field, val) ((void)(net))
 #endif
 
 
@@ -1577,22 +1579,20 @@ struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id,
 struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi,
 					      unsigned short family);
 int xfrm_state_check_expire(struct xfrm_state *x);
+void xfrm_state_update_stats(struct net *net);
 #ifdef CONFIG_XFRM_OFFLOAD
-static inline void xfrm_dev_state_update_curlft(struct xfrm_state *x)
+static inline void xfrm_dev_state_update_stats(struct xfrm_state *x)
 {
 	struct xfrm_dev_offload *xdo = &x->xso;
 	struct net_device *dev = xdo->dev;
 
-	if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET)
-		return;
-
 	if (dev && dev->xfrmdev_ops &&
-	    dev->xfrmdev_ops->xdo_dev_state_update_curlft)
-		dev->xfrmdev_ops->xdo_dev_state_update_curlft(x);
+	    dev->xfrmdev_ops->xdo_dev_state_update_stats)
+		dev->xfrmdev_ops->xdo_dev_state_update_stats(x);
 
 }
 #else
-static inline void xfrm_dev_state_update_curlft(struct xfrm_state *x) {}
+static inline void xfrm_dev_state_update_stats(struct xfrm_state *x) {}
 #endif
 void xfrm_state_insert(struct xfrm_state *x);
 int xfrm_state_add(struct xfrm_state *x);

net/xfrm/xfrm_proc.c

@@ -52,6 +52,7 @@ static int xfrm_statistics_seq_show(struct seq_file *seq, void *v)
 
 	memset(buff, 0, sizeof(unsigned long) * LINUX_MIB_XFRMMAX);
 
+	xfrm_state_update_stats(net);
 	snmp_get_cpu_field_batch(buff, xfrm_mib_list,
 				 net->mib.xfrm_statistics);
 	for (i = 0; xfrm_mib_list[i].name; i++)

net/xfrm/xfrm_state.c

@@ -570,7 +570,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
 	int err = 0;
 
 	spin_lock(&x->lock);
-	xfrm_dev_state_update_curlft(x);
+	xfrm_dev_state_update_stats(x);
 
 	if (x->km.state == XFRM_STATE_DEAD)
 		goto out;
@@ -1935,7 +1935,7 @@ EXPORT_SYMBOL(xfrm_state_update);
 
 int xfrm_state_check_expire(struct xfrm_state *x)
 {
-	xfrm_dev_state_update_curlft(x);
+	xfrm_dev_state_update_stats(x);
 
 	if (!READ_ONCE(x->curlft.use_time))
 		WRITE_ONCE(x->curlft.use_time, ktime_get_real_seconds());
@@ -1957,6 +1957,19 @@ int xfrm_state_check_expire(struct xfrm_state *x)
 }
 EXPORT_SYMBOL(xfrm_state_check_expire);
 
+void xfrm_state_update_stats(struct net *net)
+{
+	struct xfrm_state *x;
+	int i;
+
+	spin_lock_bh(&net->xfrm.xfrm_state_lock);
+	for (i = 0; i <= net->xfrm.state_hmask; i++) {
+		hlist_for_each_entry(x, net->xfrm.state_bydst + i, bydst)
+			xfrm_dev_state_update_stats(x);
+	}
+	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+}
+
 struct xfrm_state *
 xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi,
 		  u8 proto, unsigned short family)

net/xfrm/xfrm_user.c

@@ -902,7 +902,7 @@ static void copy_to_user_state(struct xfrm_state *x, struct xfrm_usersa_info *p)
 	memcpy(&p->sel, &x->sel, sizeof(p->sel));
 	memcpy(&p->lft, &x->lft, sizeof(p->lft));
 	if (x->xso.dev)
-		xfrm_dev_state_update_curlft(x);
+		xfrm_dev_state_update_stats(x);
 	memcpy(&p->curlft, &x->curlft, sizeof(p->curlft));
 	put_unaligned(x->stats.replay_window, &p->stats.replay_window);
 	put_unaligned(x->stats.replay, &p->stats.replay);