Merge tag 'mlx5-updates-2023-01-10' of git://git.kernel.org/pub/scm/linux/kernel/git/saeed/linux

mlx5-updates-2023-01-10

1) From Gal: Add debugfs entries for netdev nic driver
   - ktls, flow steering and hairpin info
   - useful for debug and performance analysis
   - e.g hairpin queue attributes, dump ktls tx pool size, etc

2) From Maher: Update shared buffer configuration on PFC commands
   2.1) For every change of buffer's headroom, recalculate the size of shared
       buffer to be equal to "total_buffer_size" - "new_headroom_size".
       The new shared buffer size will be split in ratio of 3:1 between
       lossy and lossless pools, respectively.

   2.2) For each port buffer change, count the number of lossless buffers.
       If there is only one lossless buffer, then set its lossless pool
       usage threshold to be infinite. Otherwise, if there is more than
       one lossless buffer, set a usage threshold for each lossless buffer.

    While at it, add more verbosity to debug prints when handling user
    commands, to assist in future debug.

3) From Tariq: Throttle high rate FW commands

4) From Shay: Properly initialize management PF

5) Various cleanup patches

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

@@ -47,6 +47,25 @@
 #define CREATE_TRACE_POINTS
 #include "diag/cmd_tracepoint.h"
 
+struct mlx5_ifc_mbox_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_mbox_in_bits {
+	u8         opcode[0x10];
+	u8         uid[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x40];
+};
+
 enum {
 	CMD_IF_REV = 5,
 };
@@ -70,6 +89,26 @@ enum {
 	MLX5_CMD_DELIVERY_STAT_CMD_DESCR_ERR		= 0x10,
 };
 
+static u16 in_to_opcode(void *in)
+{
+	return MLX5_GET(mbox_in, in, opcode);
+}
+
+/* Returns true for opcodes that might be triggered very frequently and throttle
+ * the command interface. Limit their command slots usage.
+ */
+static bool mlx5_cmd_is_throttle_opcode(u16 op)
+{
+	switch (op) {
+	case MLX5_CMD_OP_CREATE_GENERAL_OBJECT:
+	case MLX5_CMD_OP_DESTROY_GENERAL_OBJECT:
+	case MLX5_CMD_OP_MODIFY_GENERAL_OBJECT:
+	case MLX5_CMD_OP_QUERY_GENERAL_OBJECT:
+		return true;
+	}
+	return false;
+}
+
 static struct mlx5_cmd_work_ent *
 cmd_alloc_ent(struct mlx5_cmd *cmd, struct mlx5_cmd_msg *in,
 	      struct mlx5_cmd_msg *out, void *uout, int uout_size,
@@ -91,6 +130,7 @@ cmd_alloc_ent(struct mlx5_cmd *cmd, struct mlx5_cmd_msg *in,
 	ent->context	= context;
 	ent->cmd	= cmd;
 	ent->page_queue = page_queue;
+	ent->op         = in_to_opcode(in->first.data);
 	refcount_set(&ent->refcnt, 1);
 
 	return ent;
@@ -752,25 +792,6 @@ static int cmd_status_to_err(u8 status)
 	}
 }
 
-struct mlx5_ifc_mbox_out_bits {
-	u8         status[0x8];
-	u8         reserved_at_8[0x18];
-
-	u8         syndrome[0x20];
-
-	u8         reserved_at_40[0x40];
-};
-
-struct mlx5_ifc_mbox_in_bits {
-	u8         opcode[0x10];
-	u8         uid[0x10];
-
-	u8         reserved_at_20[0x10];
-	u8         op_mod[0x10];
-
-	u8         reserved_at_40[0x40];
-};
-
 void mlx5_cmd_out_err(struct mlx5_core_dev *dev, u16 opcode, u16 op_mod, void *out)
 {
 	u32 syndrome = MLX5_GET(mbox_out, out, syndrome);
@@ -788,7 +809,7 @@ static void cmd_status_print(struct mlx5_core_dev *dev, void *in, void *out)
 	u16 opcode, op_mod;
 	u16 uid;
 
-	opcode = MLX5_GET(mbox_in, in, opcode);
+	opcode = in_to_opcode(in);
 	op_mod = MLX5_GET(mbox_in, in, op_mod);
 	uid    = MLX5_GET(mbox_in, in, uid);
 
@@ -800,7 +821,7 @@ int mlx5_cmd_check(struct mlx5_core_dev *dev, int err, void *in, void *out)
 {
 	/* aborted due to PCI error or via reset flow mlx5_cmd_trigger_completions() */
 	if (err == -ENXIO) {
-		u16 opcode = MLX5_GET(mbox_in, in, opcode);
+		u16 opcode = in_to_opcode(in);
 		u32 syndrome;
 		u8 status;
 
@@ -829,9 +850,9 @@ static void dump_command(struct mlx5_core_dev *dev,
 			 struct mlx5_cmd_work_ent *ent, int input)
 {
 	struct mlx5_cmd_msg *msg = input ? ent->in : ent->out;
-	u16 op = MLX5_GET(mbox_in, ent->lay->in, opcode);
 	struct mlx5_cmd_mailbox *next = msg->next;
 	int n = mlx5_calc_cmd_blocks(msg);
+	u16 op = ent->op;
 	int data_only;
 	u32 offset = 0;
 	int dump_len;
@@ -883,11 +904,6 @@ static void dump_command(struct mlx5_core_dev *dev,
 	mlx5_core_dbg(dev, "cmd[%d]: end dump\n", ent->idx);
 }
 
-static u16 msg_to_opcode(struct mlx5_cmd_msg *in)
-{
-	return MLX5_GET(mbox_in, in->first.data, opcode);
-}
-
 static void mlx5_cmd_comp_handler(struct mlx5_core_dev *dev, u64 vec, bool forced);
 
 static void cb_timeout_handler(struct work_struct *work)
@@ -905,13 +921,13 @@ static void cb_timeout_handler(struct work_struct *work)
 	/* Maybe got handled by eq recover ? */
 	if (!test_bit(MLX5_CMD_ENT_STATE_PENDING_COMP, &ent->state)) {
 		mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) Async, recovered after timeout\n", ent->idx,
-			       mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in));
+			       mlx5_command_str(ent->op), ent->op);
 		goto out; /* phew, already handled */
 	}
 
 	ent->ret = -ETIMEDOUT;
 	mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) Async, timeout. Will cause a leak of a command resource\n",
-		       ent->idx, mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in));
+		       ent->idx, mlx5_command_str(ent->op), ent->op);
 	mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, true);
 
 out:
@@ -985,7 +1001,6 @@ static void cmd_work_handler(struct work_struct *work)
 	ent->lay = lay;
 	memset(lay, 0, sizeof(*lay));
 	memcpy(lay->in, ent->in->first.data, sizeof(lay->in));
-	ent->op = be32_to_cpu(lay->in[0]) >> 16;
 	if (ent->in->next)
 		lay->in_ptr = cpu_to_be64(ent->in->next->dma);
 	lay->inlen = cpu_to_be32(ent->in->len);
@@ -1098,12 +1113,12 @@ static void wait_func_handle_exec_timeout(struct mlx5_core_dev *dev,
 	 */
 	if (wait_for_completion_timeout(&ent->done, timeout)) {
 		mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) recovered after timeout\n", ent->idx,
-			       mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in));
+			       mlx5_command_str(ent->op), ent->op);
 		return;
 	}
 
 	mlx5_core_warn(dev, "cmd[%d]: %s(0x%x) No done completion\n", ent->idx,
-		       mlx5_command_str(msg_to_opcode(ent->in)), msg_to_opcode(ent->in));
+		       mlx5_command_str(ent->op), ent->op);
 
 	ent->ret = -ETIMEDOUT;
 	mlx5_cmd_comp_handler(dev, 1ULL << ent->idx, true);
@@ -1130,12 +1145,10 @@ static int wait_func(struct mlx5_core_dev *dev, struct mlx5_cmd_work_ent *ent)
 
 	if (err == -ETIMEDOUT) {
 		mlx5_core_warn(dev, "%s(0x%x) timeout. Will cause a leak of a command resource\n",
-			       mlx5_command_str(msg_to_opcode(ent->in)),
-			       msg_to_opcode(ent->in));
+			       mlx5_command_str(ent->op), ent->op);
 	} else if (err == -ECANCELED) {
 		mlx5_core_warn(dev, "%s(0x%x) canceled on out of queue timeout.\n",
-			       mlx5_command_str(msg_to_opcode(ent->in)),
-			       msg_to_opcode(ent->in));
+			       mlx5_command_str(ent->op), ent->op);
 	}
 	mlx5_core_dbg(dev, "err %d, delivery status %s(%d)\n",
 		      err, deliv_status_to_str(ent->status), ent->status);
@@ -1169,7 +1182,6 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 	u8 status = 0;
 	int err = 0;
 	s64 ds;
-	u16 op;
 
 	if (callback && page_queue)
 		return -EINVAL;
@@ -1209,9 +1221,8 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 		goto out_free;
 
 	ds = ent->ts2 - ent->ts1;
-	op = MLX5_GET(mbox_in, in->first.data, opcode);
-	if (op < MLX5_CMD_OP_MAX) {
-		stats = &cmd->stats[op];
+	if (ent->op < MLX5_CMD_OP_MAX) {
+		stats = &cmd->stats[ent->op];
 		spin_lock_irq(&stats->lock);
 		stats->sum += ds;
 		++stats->n;
@@ -1219,7 +1230,7 @@ static int mlx5_cmd_invoke(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *in,
 	}
 	mlx5_core_dbg_mask(dev, 1 << MLX5_CMD_TIME,
 			   "fw exec time for %s is %lld nsec\n",
-			   mlx5_command_str(op), ds);
+			   mlx5_command_str(ent->op), ds);
 
 out_free:
 	status = ent->status;
@@ -1816,7 +1827,7 @@ static struct mlx5_cmd_msg *alloc_msg(struct mlx5_core_dev *dev, int in_size,
 
 static int is_manage_pages(void *in)
 {
-	return MLX5_GET(mbox_in, in, opcode) == MLX5_CMD_OP_MANAGE_PAGES;
+	return in_to_opcode(in) == MLX5_CMD_OP_MANAGE_PAGES;
 }
 
 /*  Notes:
@@ -1827,8 +1838,9 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 		    int out_size, mlx5_cmd_cbk_t callback, void *context,
 		    bool force_polling)
 {
-	u16 opcode = MLX5_GET(mbox_in, in, opcode);
 	struct mlx5_cmd_msg *inb, *outb;
+	u16 opcode = in_to_opcode(in);
+	bool throttle_op;
 	int pages_queue;
 	gfp_t gfp;
 	u8 token;
@@ -1837,13 +1849,21 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 	if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, opcode))
 		return -ENXIO;
 
+	throttle_op = mlx5_cmd_is_throttle_opcode(opcode);
+	if (throttle_op) {
+		/* atomic context may not sleep */
+		if (callback)
+			return -EINVAL;
+		down(&dev->cmd.throttle_sem);
+	}
+
 	pages_queue = is_manage_pages(in);
 	gfp = callback ? GFP_ATOMIC : GFP_KERNEL;
 
 	inb = alloc_msg(dev, in_size, gfp);
 	if (IS_ERR(inb)) {
 		err = PTR_ERR(inb);
-		return err;
+		goto out_up;
 	}
 
 	token = alloc_token(&dev->cmd);
@@ -1877,6 +1897,9 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 	mlx5_free_cmd_msg(dev, outb);
 out_in:
 	free_msg(dev, inb);
+out_up:
+	if (throttle_op)
+		up(&dev->cmd.throttle_sem);
 	return err;
 }
 
@@ -1950,8 +1973,8 @@ static int cmd_status_err(struct mlx5_core_dev *dev, int err, u16 opcode, u16 op
 int mlx5_cmd_do(struct mlx5_core_dev *dev, void *in, int in_size, void *out, int out_size)
 {
 	int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, false);
-	u16 opcode = MLX5_GET(mbox_in, in, opcode);
 	u16 op_mod = MLX5_GET(mbox_in, in, op_mod);
+	u16 opcode = in_to_opcode(in);
 
 	return cmd_status_err(dev, err, opcode, op_mod, out);
 }
@@ -1996,8 +2019,8 @@ int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size,
 			  void *out, int out_size)
 {
 	int err = cmd_exec(dev, in, in_size, out, out_size, NULL, NULL, true);
-	u16 opcode = MLX5_GET(mbox_in, in, opcode);
 	u16 op_mod = MLX5_GET(mbox_in, in, op_mod);
+	u16 opcode = in_to_opcode(in);
 
 	err = cmd_status_err(dev, err, opcode, op_mod, out);
 	return mlx5_cmd_check(dev, err, in, out);
@@ -2049,7 +2072,7 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size,
 
 	work->ctx = ctx;
 	work->user_callback = callback;
-	work->opcode = MLX5_GET(mbox_in, in, opcode);
+	work->opcode = in_to_opcode(in);
 	work->op_mod = MLX5_GET(mbox_in, in, op_mod);
 	work->out = out;
 	if (WARN_ON(!atomic_inc_not_zero(&ctx->num_inflight)))
@@ -2226,6 +2249,7 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev)
 
 	sema_init(&cmd->sem, cmd->max_reg_cmds);
 	sema_init(&cmd->pages_sem, 1);
+	sema_init(&cmd->throttle_sem, DIV_ROUND_UP(cmd->max_reg_cmds, 2));
 
 	cmd_h = (u32)((u64)(cmd->dma) >> 32);
 	cmd_l = (u32)(cmd->dma);

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

@@ -59,6 +59,9 @@ bool mlx5_eth_supported(struct mlx5_core_dev *dev)
 	if (!IS_ENABLED(CONFIG_MLX5_CORE_EN))
 		return false;
 
+	if (mlx5_core_is_management_pf(dev))
+		return false;
+
 	if (MLX5_CAP_GEN(dev, port_type) != MLX5_CAP_PORT_TYPE_ETH)
 		return false;
 
@@ -198,6 +201,9 @@ bool mlx5_rdma_supported(struct mlx5_core_dev *dev)
 	if (!IS_ENABLED(CONFIG_MLX5_INFINIBAND))
 		return false;
 
+	if (mlx5_core_is_management_pf(dev))
+		return false;
+
 	if (dev->priv.flags & MLX5_PRIV_FLAGS_DISABLE_IB_ADEV)
 		return false;
 

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

@@ -75,6 +75,10 @@ int mlx5_ec_init(struct mlx5_core_dev *dev)
 	if (!mlx5_core_is_ecpf(dev))
 		return 0;
 
+	/* Management PF don't have a peer PF */
+	if (mlx5_core_is_management_pf(dev))
+		return 0;
+
 	return mlx5_host_pf_init(dev);
 }
 
@@ -85,6 +89,10 @@ void mlx5_ec_cleanup(struct mlx5_core_dev *dev)
 	if (!mlx5_core_is_ecpf(dev))
 		return;
 
+	/* Management PF don't have a peer PF */
+	if (mlx5_core_is_management_pf(dev))
+		return;
+
 	mlx5_host_pf_cleanup(dev);
 
 	err = mlx5_wait_for_pages(dev, &dev->priv.host_pf_pages);

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

@@ -247,7 +247,7 @@ struct mlx5e_rx_wqe_ll {
 };
 
 struct mlx5e_rx_wqe_cyc {
-	struct mlx5_wqe_data_seg      data[0];
+	DECLARE_FLEX_ARRAY(struct mlx5_wqe_data_seg, data);
 };
 
 struct mlx5e_umr_wqe {
@@ -968,6 +968,7 @@ struct mlx5e_priv {
 	struct mlx5e_scratchpad    scratchpad;
 	struct mlx5e_htb          *htb;
 	struct mlx5e_mqprio_rl    *mqprio_rl;
+	struct dentry             *dfs_root;
 };
 
 struct mlx5e_rx_handlers {

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

@@ -145,7 +145,8 @@ void mlx5e_destroy_flow_steering(struct mlx5e_flow_steering *fs, bool ntuple,
 
 struct mlx5e_flow_steering *mlx5e_fs_init(const struct mlx5e_profile *profile,
 					  struct mlx5_core_dev *mdev,
-					  bool state_destroy);
+					  bool state_destroy,
+					  struct dentry *dfs_root);
 void mlx5e_fs_cleanup(struct mlx5e_flow_steering *fs);
 struct mlx5e_vlan_table *mlx5e_fs_get_vlan(struct mlx5e_flow_steering *fs);
 void mlx5e_fs_set_tc(struct mlx5e_flow_steering *fs, struct mlx5e_tc_table *tc);
@@ -189,6 +190,8 @@ int mlx5e_fs_vlan_rx_kill_vid(struct mlx5e_flow_steering *fs,
 			      __be16 proto, u16 vid);
 void mlx5e_fs_init_l2_addr(struct mlx5e_flow_steering *fs, struct net_device *netdev);
 
+struct dentry *mlx5e_fs_get_debugfs_root(struct mlx5e_flow_steering *fs);
+
 #define fs_err(fs, fmt, ...) \
 	mlx5_core_err(mlx5e_fs_get_mdev(fs), fmt, ##__VA_ARGS__)
 

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

@@ -287,6 +287,78 @@ int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in)
 	return err;
 }
 
+int mlx5e_port_query_sbpr(struct mlx5_core_dev *mdev, u32 desc, u8 dir,
+			  u8 pool_idx, void *out, int size_out)
+{
+	u32 in[MLX5_ST_SZ_DW(sbpr_reg)] = {};
+
+	MLX5_SET(sbpr_reg, in, desc, desc);
+	MLX5_SET(sbpr_reg, in, dir, dir);
+	MLX5_SET(sbpr_reg, in, pool, pool_idx);
+
+	return mlx5_core_access_reg(mdev, in, sizeof(in), out, size_out, MLX5_REG_SBPR, 0, 0);
+}
+
+int mlx5e_port_set_sbpr(struct mlx5_core_dev *mdev, u32 desc, u8 dir,
+			u8 pool_idx, u32 infi_size, u32 size)
+{
+	u32 out[MLX5_ST_SZ_DW(sbpr_reg)] = {};
+	u32 in[MLX5_ST_SZ_DW(sbpr_reg)] = {};
+
+	MLX5_SET(sbpr_reg, in, desc, desc);
+	MLX5_SET(sbpr_reg, in, dir, dir);
+	MLX5_SET(sbpr_reg, in, pool, pool_idx);
+	MLX5_SET(sbpr_reg, in, infi_size, infi_size);
+	MLX5_SET(sbpr_reg, in, size, size);
+	MLX5_SET(sbpr_reg, in, mode, 1);
+
+	return mlx5_core_access_reg(mdev, in, sizeof(in), out, sizeof(out), MLX5_REG_SBPR, 0, 1);
+}
+
+static int mlx5e_port_query_sbcm(struct mlx5_core_dev *mdev, u32 desc,
+				 u8 pg_buff_idx, u8 dir, void *out,
+				 int size_out)
+{
+	u32 in[MLX5_ST_SZ_DW(sbcm_reg)] = {};
+
+	MLX5_SET(sbcm_reg, in, desc, desc);
+	MLX5_SET(sbcm_reg, in, local_port, 1);
+	MLX5_SET(sbcm_reg, in, pg_buff, pg_buff_idx);
+	MLX5_SET(sbcm_reg, in, dir, dir);
+
+	return mlx5_core_access_reg(mdev, in, sizeof(in), out, size_out, MLX5_REG_SBCM, 0, 0);
+}
+
+int mlx5e_port_set_sbcm(struct mlx5_core_dev *mdev, u32 desc, u8 pg_buff_idx,
+			u8 dir, u8 infi_size, u32 max_buff, u8 pool_idx)
+{
+	u32 out[MLX5_ST_SZ_DW(sbcm_reg)] = {};
+	u32 in[MLX5_ST_SZ_DW(sbcm_reg)] = {};
+	u32 min_buff;
+	int err;
+	u8 exc;
+
+	err = mlx5e_port_query_sbcm(mdev, desc, pg_buff_idx, dir, out,
+				    sizeof(out));
+	if (err)
+		return err;
+
+	exc = MLX5_GET(sbcm_reg, out, exc);
+	min_buff = MLX5_GET(sbcm_reg, out, min_buff);
+
+	MLX5_SET(sbcm_reg, in, desc, desc);
+	MLX5_SET(sbcm_reg, in, local_port, 1);
+	MLX5_SET(sbcm_reg, in, pg_buff, pg_buff_idx);
+	MLX5_SET(sbcm_reg, in, dir, dir);
+	MLX5_SET(sbcm_reg, in, exc, exc);
+	MLX5_SET(sbcm_reg, in, min_buff, min_buff);
+	MLX5_SET(sbcm_reg, in, infi_max, infi_size);
+	MLX5_SET(sbcm_reg, in, max_buff, max_buff);
+	MLX5_SET(sbcm_reg, in, pool, pool_idx);
+
+	return mlx5_core_access_reg(mdev, in, sizeof(in), out, sizeof(out), MLX5_REG_SBCM, 0, 1);
+}
+
 /* buffer[i]: buffer that priority i mapped to */
 int mlx5e_port_query_priority2buffer(struct mlx5_core_dev *mdev, u8 *buffer)
 {

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

@@ -57,6 +57,12 @@ u32 mlx5e_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed,
 bool mlx5e_ptys_ext_supported(struct mlx5_core_dev *mdev);
 int mlx5e_port_query_pbmc(struct mlx5_core_dev *mdev, void *out);
 int mlx5e_port_set_pbmc(struct mlx5_core_dev *mdev, void *in);
+int mlx5e_port_query_sbpr(struct mlx5_core_dev *mdev, u32 desc, u8 dir,
+			  u8 pool_idx, void *out, int size_out);
+int mlx5e_port_set_sbpr(struct mlx5_core_dev *mdev, u32 desc, u8 dir,
+			u8 pool_idx, u32 infi_size, u32 size);
+int mlx5e_port_set_sbcm(struct mlx5_core_dev *mdev, u32 desc, u8 pg_buff_idx,
+			u8 dir, u8 infi_size, u32 max_buff, u8 pool_idx);
 int mlx5e_port_query_priority2buffer(struct mlx5_core_dev *mdev, u8 *buffer);
 int mlx5e_port_set_priority2buffer(struct mlx5_core_dev *mdev, u8 *buffer);
 

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

@@ -73,6 +73,7 @@ int mlx5e_port_query_buffer(struct mlx5e_priv *priv,
 			  port_buffer->buffer[i].lossy);
 	}
 
+	port_buffer->headroom_size = total_used;
 	port_buffer->port_buffer_size =
 		MLX5_GET(pbmc_reg, out, port_buffer_size) * port_buff_cell_sz;
 	port_buffer->spare_buffer_size =
@@ -86,16 +87,204 @@ int mlx5e_port_query_buffer(struct mlx5e_priv *priv,
 	return err;
 }
 
+struct mlx5e_buffer_pool {
+	u32 infi_size;
+	u32 size;
+	u32 buff_occupancy;
+};
+
+static int mlx5e_port_query_pool(struct mlx5_core_dev *mdev,
+				 struct mlx5e_buffer_pool *buffer_pool,
+				 u32 desc, u8 dir, u8 pool_idx)
+{
+	u32 out[MLX5_ST_SZ_DW(sbpr_reg)] = {};
+	int err;
+
+	err = mlx5e_port_query_sbpr(mdev, desc, dir, pool_idx, out,
+				    sizeof(out));
+	if (err)
+		return err;
+
+	buffer_pool->size = MLX5_GET(sbpr_reg, out, size);
+	buffer_pool->infi_size = MLX5_GET(sbpr_reg, out, infi_size);
+	buffer_pool->buff_occupancy = MLX5_GET(sbpr_reg, out, buff_occupancy);
+
+	return err;
+}
+
+enum {
+	MLX5_INGRESS_DIR = 0,
+	MLX5_EGRESS_DIR = 1,
+};
+
+enum {
+	MLX5_LOSSY_POOL = 0,
+	MLX5_LOSSLESS_POOL = 1,
+};
+
+/* No limit on usage of shared buffer pool (max_buff=0) */
+#define MLX5_SB_POOL_NO_THRESHOLD  0
+/* Shared buffer pool usage threshold when calculated
+ * dynamically in alpha units. alpha=13 is equivalent to
+ * HW_alpha of  [(1/128) * 2 ^ (alpha-1)] = 32, where HW_alpha
+ * equates to the following portion of the shared buffer pool:
+ * [32 / (1 + n * 32)] While *n* is the number of buffers
+ * that are using the shared buffer pool.
+ */
+#define MLX5_SB_POOL_THRESHOLD 13
+
+/* Shared buffer class management parameters */
+struct mlx5_sbcm_params {
+	u8 pool_idx;
+	u8 max_buff;
+	u8 infi_size;
+};
+
+static const struct mlx5_sbcm_params sbcm_default = {
+	.pool_idx = MLX5_LOSSY_POOL,
+	.max_buff = MLX5_SB_POOL_NO_THRESHOLD,
+	.infi_size = 0,
+};
+
+static const struct mlx5_sbcm_params sbcm_lossy = {
+	.pool_idx = MLX5_LOSSY_POOL,
+	.max_buff = MLX5_SB_POOL_NO_THRESHOLD,
+	.infi_size = 1,
+};
+
+static const struct mlx5_sbcm_params sbcm_lossless = {
+	.pool_idx = MLX5_LOSSLESS_POOL,
+	.max_buff = MLX5_SB_POOL_THRESHOLD,
+	.infi_size = 0,
+};
+
+static const struct mlx5_sbcm_params sbcm_lossless_no_threshold = {
+	.pool_idx = MLX5_LOSSLESS_POOL,
+	.max_buff = MLX5_SB_POOL_NO_THRESHOLD,
+	.infi_size = 1,
+};
+
+/**
+ * select_sbcm_params() - selects the shared buffer pool configuration
+ *
+ * @buffer: <input> port buffer to retrieve params of
+ * @lossless_buff_count: <input> number of lossless buffers in total
+ *
+ * The selection is based on the following rules:
+ * 1. If buffer size is 0, no shared buffer pool is used.
+ * 2. If buffer is lossy, use lossy shared buffer pool.
+ * 3. If there are more than 1 lossless buffers, use lossless shared buffer pool
+ *    with threshold.
+ * 4. If there is only 1 lossless buffer, use lossless shared buffer pool
+ *    without threshold.
+ *
+ * @return const struct mlx5_sbcm_params* selected values
+ */
+static const struct mlx5_sbcm_params *
+select_sbcm_params(struct mlx5e_bufferx_reg *buffer, u8 lossless_buff_count)
+{
+	if (buffer->size == 0)
+		return &sbcm_default;
+
+	if (buffer->lossy)
+		return &sbcm_lossy;
+
+	if (lossless_buff_count > 1)
+		return &sbcm_lossless;
+
+	return &sbcm_lossless_no_threshold;
+}
+
+static int port_update_pool_cfg(struct mlx5_core_dev *mdev,
+				struct mlx5e_port_buffer *port_buffer)
+{
+	const struct mlx5_sbcm_params *p;
+	u8 lossless_buff_count = 0;
+	int err;
+	int i;
+
+	if (!MLX5_CAP_GEN(mdev, sbcam_reg))
+		return 0;
+
+	for (i = 0; i < MLX5E_MAX_BUFFER; i++)
+		lossless_buff_count += ((port_buffer->buffer[i].size) &&
+				       (!(port_buffer->buffer[i].lossy)));
+
+	for (i = 0; i < MLX5E_MAX_BUFFER; i++) {
+		p = select_sbcm_params(&port_buffer->buffer[i], lossless_buff_count);
+		err = mlx5e_port_set_sbcm(mdev, 0, i,
+					  MLX5_INGRESS_DIR,
+					  p->infi_size,
+					  p->max_buff,
+					  p->pool_idx);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int port_update_shared_buffer(struct mlx5_core_dev *mdev,
+				     u32 current_headroom_size,
+				     u32 new_headroom_size)
+{
+	struct mlx5e_buffer_pool lossless_ipool;
+	struct mlx5e_buffer_pool lossy_epool;
+	u32 lossless_ipool_size;
+	u32 shared_buffer_size;
+	u32 total_buffer_size;
+	u32 lossy_epool_size;
+	int err;
+
+	if (!MLX5_CAP_GEN(mdev, sbcam_reg))
+		return 0;
+
+	err = mlx5e_port_query_pool(mdev, &lossy_epool, 0, MLX5_EGRESS_DIR,
+				    MLX5_LOSSY_POOL);
+	if (err)
+		return err;
+
+	err = mlx5e_port_query_pool(mdev, &lossless_ipool, 0, MLX5_INGRESS_DIR,
+				    MLX5_LOSSLESS_POOL);
+	if (err)
+		return err;
+
+	total_buffer_size = current_headroom_size + lossy_epool.size +
+			    lossless_ipool.size;
+	shared_buffer_size = total_buffer_size - new_headroom_size;
+
+	if (shared_buffer_size < 4) {
+		pr_err("Requested port buffer is too large, not enough space left for shared buffer\n");
+		return -EINVAL;
+	}
+
+	/* Total shared buffer size is split in a ratio of 3:1 between
+	 * lossy and lossless pools respectively.
+	 */
+	lossy_epool_size = (shared_buffer_size / 4) * 3;
+	lossless_ipool_size = shared_buffer_size / 4;
+
+	mlx5e_port_set_sbpr(mdev, 0, MLX5_EGRESS_DIR, MLX5_LOSSY_POOL, 0,
+			    lossy_epool_size);
+	mlx5e_port_set_sbpr(mdev, 0, MLX5_INGRESS_DIR, MLX5_LOSSLESS_POOL, 0,
+			    lossless_ipool_size);
+	return 0;
+}
+
 static int port_set_buffer(struct mlx5e_priv *priv,
 			   struct mlx5e_port_buffer *port_buffer)
 {
 	u16 port_buff_cell_sz = priv->dcbx.port_buff_cell_sz;
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int sz = MLX5_ST_SZ_BYTES(pbmc_reg);
+	u32 new_headroom_size = 0;
+	u32 current_headroom_size;
 	void *in;
 	int err;
 	int i;
 
+	current_headroom_size = port_buffer->headroom_size;
+
 	in = kzalloc(sz, GFP_KERNEL);
 	if (!in)
 		return -ENOMEM;
@@ -110,6 +299,7 @@ static int port_set_buffer(struct mlx5e_priv *priv,
 		u64 xoff = port_buffer->buffer[i].xoff;
 		u64 xon = port_buffer->buffer[i].xon;
 
+		new_headroom_size += size;
 		do_div(size, port_buff_cell_sz);
 		do_div(xoff, port_buff_cell_sz);
 		do_div(xon, port_buff_cell_sz);
@@ -119,6 +309,17 @@ static int port_set_buffer(struct mlx5e_priv *priv,
 		MLX5_SET(bufferx_reg, buffer, xon_threshold, xon);
 	}
 
+	new_headroom_size /= port_buff_cell_sz;
+	current_headroom_size /= port_buff_cell_sz;
+	err = port_update_shared_buffer(priv->mdev, current_headroom_size,
+					new_headroom_size);
+	if (err)
+		return err;
+
+	err = port_update_pool_cfg(priv->mdev, port_buffer);
+	if (err)
+		return err;
+
 	err = mlx5e_port_set_pbmc(mdev, in);
 out:
 	kfree(in);
@@ -174,6 +375,7 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
 
 /**
  *	update_buffer_lossy	- Update buffer configuration based on pfc
+ *	@mdev: port function core device
  *	@max_mtu: netdev's max_mtu
  *	@pfc_en: <input> current pfc configuration
  *	@buffer: <input> current prio to buffer mapping
@@ -192,7 +394,8 @@ static int update_xoff_threshold(struct mlx5e_port_buffer *port_buffer,
  *	@return: 0 if no error,
  *	sets change to true if buffer configuration was modified.
  */
-static int update_buffer_lossy(unsigned int max_mtu,
+static int update_buffer_lossy(struct mlx5_core_dev *mdev,
+			       unsigned int max_mtu,
 			       u8 pfc_en, u8 *buffer, u32 xoff, u16 port_buff_cell_sz,
 			       struct mlx5e_port_buffer *port_buffer,
 			       bool *change)
@@ -229,6 +432,10 @@ static int update_buffer_lossy(unsigned int max_mtu,
 	}
 
 	if (changed) {
+		err = port_update_pool_cfg(mdev, port_buffer);
+		if (err)
+			return err;
+
 		err = update_xoff_threshold(port_buffer, xoff, max_mtu, port_buff_cell_sz);
 		if (err)
 			return err;
@@ -293,23 +500,30 @@ int mlx5e_port_manual_buffer_config(struct mlx5e_priv *priv,
 	}
 
 	if (change & MLX5E_PORT_BUFFER_PFC) {
+		mlx5e_dbg(HW, priv, "%s: requested PFC per priority bitmask: 0x%x\n",
+			  __func__, pfc->pfc_en);
 		err = mlx5e_port_query_priority2buffer(priv->mdev, buffer);
 		if (err)
 			return err;
 
-		err = update_buffer_lossy(max_mtu, pfc->pfc_en, buffer, xoff, port_buff_cell_sz,
-					  &port_buffer, &update_buffer);
+		err = update_buffer_lossy(priv->mdev, max_mtu, pfc->pfc_en, buffer, xoff,
+					  port_buff_cell_sz, &port_buffer,
+					  &update_buffer);
 		if (err)
 			return err;
 	}
 
 	if (change & MLX5E_PORT_BUFFER_PRIO2BUFFER) {
 		update_prio2buffer = true;
+		for (i = 0; i < MLX5E_MAX_BUFFER; i++)
+			mlx5e_dbg(HW, priv, "%s: requested to map prio[%d] to buffer %d\n",
+				  __func__, i, prio2buffer[i]);
+
 		err = fill_pfc_en(priv->mdev, &curr_pfc_en);
 		if (err)
 			return err;
 
-		err = update_buffer_lossy(max_mtu, curr_pfc_en, prio2buffer, xoff,
+		err = update_buffer_lossy(priv->mdev, max_mtu, curr_pfc_en, prio2buffer, xoff,
 					  port_buff_cell_sz, &port_buffer, &update_buffer);
 		if (err)
 			return err;

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

@@ -60,6 +60,7 @@ 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];
 };
 

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

@@ -28,7 +28,7 @@ struct mlx5e_flow_meter_aso_obj {
 	int base_id;
 	int total_meters;
 
-	unsigned long meters_map[0]; /* must be at the end of this struct */
+	unsigned long meters_map[]; /* must be at the end of this struct */
 };
 
 struct mlx5e_flow_meters {

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

@@ -365,7 +365,7 @@ void mlx5e_accel_fs_tcp_destroy(struct mlx5e_flow_steering *fs)
 	for (i = 0; i < ACCEL_FS_TCP_NUM_TYPES; i++)
 		accel_fs_tcp_destroy_table(fs, i);
 
-	kvfree(accel_tcp);
+	kfree(accel_tcp);
 	mlx5e_fs_set_accel_tcp(fs, NULL);
 }
 
@@ -377,7 +377,7 @@ int mlx5e_accel_fs_tcp_create(struct mlx5e_flow_steering *fs)
 	if (!MLX5_CAP_FLOWTABLE_NIC_RX(mlx5e_fs_get_mdev(fs), ft_field_support.outer_ip_version))
 		return -EOPNOTSUPP;
 
-	accel_tcp = kvzalloc(sizeof(*accel_tcp), GFP_KERNEL);
+	accel_tcp = kzalloc(sizeof(*accel_tcp), GFP_KERNEL);
 	if (!accel_tcp)
 		return -ENOMEM;
 	mlx5e_fs_set_accel_tcp(fs, accel_tcp);
@@ -397,7 +397,7 @@ int mlx5e_accel_fs_tcp_create(struct mlx5e_flow_steering *fs)
 err_destroy_tables:
 	while (--i >= 0)
 		accel_fs_tcp_destroy_table(fs, i);
-	kvfree(accel_tcp);
+	kfree(accel_tcp);
 	mlx5e_fs_set_accel_tcp(fs, NULL);
 	return err;
 }

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

 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 // Copyright (c) 2019 Mellanox Technologies.
 
+#include <linux/debugfs.h>
 #include "en.h"
 #include "lib/mlx5.h"
 #include "en_accel/ktls.h"
@@ -177,6 +178,15 @@ void mlx5e_ktls_cleanup_rx(struct mlx5e_priv *priv)
 	destroy_workqueue(priv->tls->rx_wq);
 }
 
+static void mlx5e_tls_debugfs_init(struct mlx5e_tls *tls,
+				   struct dentry *dfs_root)
+{
+	if (IS_ERR_OR_NULL(dfs_root))
+		return;
+
+	tls->debugfs.dfs = debugfs_create_dir("tls", dfs_root);
+}
+
 int mlx5e_ktls_init(struct mlx5e_priv *priv)
 {
 	struct mlx5e_tls *tls;
@@ -189,11 +199,23 @@ int mlx5e_ktls_init(struct mlx5e_priv *priv)
 		return -ENOMEM;
 
 	priv->tls = tls;
+	priv->tls->mdev = priv->mdev;
+
+	mlx5e_tls_debugfs_init(tls, priv->dfs_root);
+
 	return 0;
 }
 
 void mlx5e_ktls_cleanup(struct mlx5e_priv *priv)
 {
+	struct mlx5e_tls *tls = priv->tls;
+
+	if (!mlx5e_is_ktls_device(priv->mdev))
+		return;
+
+	debugfs_remove_recursive(tls->debugfs.dfs);
+	tls->debugfs.dfs = NULL;
+
 	kfree(priv->tls);
 	priv->tls = NULL;
 }

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

@@ -4,6 +4,7 @@
 #ifndef __MLX5E_KTLS_H__
 #define __MLX5E_KTLS_H__
 
+#include <linux/debugfs.h>
 #include <linux/tls.h>
 #include <net/tls.h>
 #include "en.h"
@@ -72,10 +73,17 @@ struct mlx5e_tls_sw_stats {
 	atomic64_t rx_tls_del;
 };
 
+struct mlx5e_tls_debugfs {
+	struct dentry *dfs;
+	struct dentry *dfs_tx;
+};
+
 struct mlx5e_tls {
+	struct mlx5_core_dev *mdev;
 	struct mlx5e_tls_sw_stats sw_stats;
 	struct workqueue_struct *rx_wq;
 	struct mlx5e_tls_tx_pool *tx_pool;
+	struct mlx5e_tls_debugfs debugfs;
 };
 
 int mlx5e_ktls_init(struct mlx5e_priv *priv);

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

 // SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
 // Copyright (c) 2019 Mellanox Technologies.
 
+#include <linux/debugfs.h>
 #include "en_accel/ktls.h"
 #include "en_accel/ktls_txrx.h"
 #include "en_accel/ktls_utils.h"
@@ -886,8 +887,24 @@ bool mlx5e_ktls_handle_tx_skb(struct net_device *netdev, struct mlx5e_txqsq *sq,
 	return false;
 }
 
+static void mlx5e_tls_tx_debugfs_init(struct mlx5e_tls *tls,
+				      struct dentry *dfs_root)
+{
+	if (IS_ERR_OR_NULL(dfs_root))
+		return;
+
+	tls->debugfs.dfs_tx = debugfs_create_dir("tx", dfs_root);
+	if (!tls->debugfs.dfs_tx)
+		return;
+
+	debugfs_create_size_t("pool_size", 0400, tls->debugfs.dfs_tx,
+			      &tls->tx_pool->size);
+}
+
 int mlx5e_ktls_init_tx(struct mlx5e_priv *priv)
 {
+	struct mlx5e_tls *tls = priv->tls;
+
 	if (!mlx5e_is_ktls_tx(priv->mdev))
 		return 0;
 
@@ -895,6 +912,8 @@ int mlx5e_ktls_init_tx(struct mlx5e_priv *priv)
 	if (!priv->tls->tx_pool)
 		return -ENOMEM;
 
+	mlx5e_tls_tx_debugfs_init(tls, tls->debugfs.dfs);
+
 	return 0;
 }
 
@@ -903,6 +922,9 @@ void mlx5e_ktls_cleanup_tx(struct mlx5e_priv *priv)
 	if (!mlx5e_is_ktls_tx(priv->mdev))
 		return;
 
+	debugfs_remove_recursive(priv->tls->debugfs.dfs_tx);
+	priv->tls->debugfs.dfs_tx = NULL;
+
 	mlx5e_tls_tx_pool_cleanup(priv->tls->tx_pool);
 	priv->tls->tx_pool = NULL;
 }

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

@@ -30,6 +30,7 @@
  * SOFTWARE.
  */
 
+#include <linux/debugfs.h>
 #include <linux/list.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
@@ -67,6 +68,7 @@ struct mlx5e_flow_steering {
 	struct mlx5e_fs_udp            *udp;
 	struct mlx5e_fs_any            *any;
 	struct mlx5e_ptp_fs            *ptp_fs;
+	struct dentry                  *dfs_root;
 };
 
 static int mlx5e_add_l2_flow_rule(struct mlx5e_flow_steering *fs,
@@ -104,6 +106,11 @@ static inline int mlx5e_hash_l2(const u8 *addr)
 	return addr[5];
 }
 
+struct dentry *mlx5e_fs_get_debugfs_root(struct mlx5e_flow_steering *fs)
+{
+	return fs->dfs_root;
+}
+
 static void mlx5e_add_l2_to_hash(struct hlist_head *hash, const u8 *addr)
 {
 	struct mlx5e_l2_hash_node *hn;
@@ -1429,9 +1436,19 @@ static int mlx5e_fs_ethtool_alloc(struct mlx5e_flow_steering *fs)
 static void mlx5e_fs_ethtool_free(struct mlx5e_flow_steering *fs) { }
 #endif
 
+static void mlx5e_fs_debugfs_init(struct mlx5e_flow_steering *fs,
+				  struct dentry *dfs_root)
+{
+	if (IS_ERR_OR_NULL(dfs_root))
+		return;
+
+	fs->dfs_root = debugfs_create_dir("fs", dfs_root);
+}
+
 struct mlx5e_flow_steering *mlx5e_fs_init(const struct mlx5e_profile *profile,
 					  struct mlx5_core_dev *mdev,
-					  bool state_destroy)
+					  bool state_destroy,
+					  struct dentry *dfs_root)
 {
 	struct mlx5e_flow_steering *fs;
 	int err;
@@ -1458,6 +1475,8 @@ struct mlx5e_flow_steering *mlx5e_fs_init(const struct mlx5e_profile *profile,
 	if (err)
 		goto err_free_tc;
 
+	mlx5e_fs_debugfs_init(fs, dfs_root);
+
 	return fs;
 err_free_tc:
 	mlx5e_fs_tc_free(fs);
@@ -1471,6 +1490,7 @@ struct mlx5e_flow_steering *mlx5e_fs_init(const struct mlx5e_profile *profile,
 
 void mlx5e_fs_cleanup(struct mlx5e_flow_steering *fs)
 {
+	debugfs_remove_recursive(fs->dfs_root);
 	mlx5e_fs_ethtool_free(fs);
 	mlx5e_fs_tc_free(fs);
 	mlx5e_fs_vlan_free(fs);

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

@@ -35,6 +35,7 @@
 #include <net/vxlan.h>
 #include <net/geneve.h>
 #include <linux/bpf.h>
+#include <linux/debugfs.h>
 #include <linux/if_bridge.h>
 #include <linux/filter.h>
 #include <net/page_pool.h>
@@ -5230,7 +5231,8 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev,
 	mlx5e_timestamp_init(priv);
 
 	fs = mlx5e_fs_init(priv->profile, mdev,
-			   !test_bit(MLX5E_STATE_DESTROYING, &priv->state));
+			   !test_bit(MLX5E_STATE_DESTROYING, &priv->state),
+			   priv->dfs_root);
 	if (!fs) {
 		err = -ENOMEM;
 		mlx5_core_err(mdev, "FS initialization failed, %d\n", err);
@@ -5931,6 +5933,9 @@ 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 = mlx5e_devlink_port_register(priv);
 	if (err) {
 		mlx5_core_err(mdev, "mlx5e_devlink_port_register failed, %d\n", err);
@@ -5968,6 +5973,7 @@ static int mlx5e_probe(struct auxiliary_device *adev,
 err_devlink_cleanup:
 	mlx5e_devlink_port_unregister(priv);
 err_destroy_netdev:
+	debugfs_remove_recursive(priv->dfs_root);
 	mlx5e_destroy_netdev(priv);
 	return err;
 }
@@ -5982,6 +5988,7 @@ static void mlx5e_remove(struct auxiliary_device *adev)
 	mlx5e_suspend(adev, state);
 	priv->profile->cleanup(priv);
 	mlx5e_devlink_port_unregister(priv);
+	debugfs_remove_recursive(priv->dfs_root);
 	mlx5e_destroy_netdev(priv);
 }
 

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

@@ -788,8 +788,10 @@ static int mlx5e_init_rep(struct mlx5_core_dev *mdev,
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
-	priv->fs = mlx5e_fs_init(priv->profile, mdev,
-				 !test_bit(MLX5E_STATE_DESTROYING, &priv->state));
+	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");
 		return -ENOMEM;
@@ -807,7 +809,8 @@ static int mlx5e_init_ul_rep(struct mlx5_core_dev *mdev,
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 
 	priv->fs = mlx5e_fs_init(priv->profile, mdev,
-				 !test_bit(MLX5E_STATE_DESTROYING, &priv->state));
+				 !test_bit(MLX5E_STATE_DESTROYING, &priv->state),
+				 priv->dfs_root);
 	if (!priv->fs) {
 		netdev_err(priv->netdev, "FS allocation failed\n");
 		return -ENOMEM;

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

@@ -71,6 +71,12 @@
 #define MLX5E_TC_TABLE_NUM_GROUPS 4
 #define MLX5E_TC_TABLE_MAX_GROUP_SIZE BIT(18)
 
+struct mlx5e_hairpin_params {
+	struct mlx5_core_dev *mdev;
+	u32 num_queues;
+	u32 queue_size;
+};
+
 struct mlx5e_tc_table {
 	/* Protects the dynamic assignment of the t parameter
 	 * which is the nic tc root table.
@@ -93,6 +99,8 @@ struct mlx5e_tc_table {
 
 	struct mlx5_tc_ct_priv         *ct;
 	struct mapping_ctx             *mapping;
+	struct mlx5e_hairpin_params    hairpin_params;
+	struct dentry                  *dfs_root;
 };
 
 struct mlx5e_tc_attr_to_reg_mapping mlx5e_tc_attr_to_reg_mappings[] = {
@@ -1016,6 +1024,138 @@ static int mlx5e_hairpin_get_prio(struct mlx5e_priv *priv,
 	return 0;
 }
 
+static int debugfs_hairpin_queues_set(void *data, u64 val)
+{
+	struct mlx5e_hairpin_params *hp = data;
+
+	if (!val) {
+		mlx5_core_err(hp->mdev,
+			      "Number of hairpin queues must be > 0\n");
+		return -EINVAL;
+	}
+
+	hp->num_queues = val;
+
+	return 0;
+}
+
+static int debugfs_hairpin_queues_get(void *data, u64 *val)
+{
+	struct mlx5e_hairpin_params *hp = data;
+
+	*val = hp->num_queues;
+
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(fops_hairpin_queues, debugfs_hairpin_queues_get,
+			 debugfs_hairpin_queues_set, "%llu\n");
+
+static int debugfs_hairpin_queue_size_set(void *data, u64 val)
+{
+	struct mlx5e_hairpin_params *hp = data;
+
+	if (val > BIT(MLX5_CAP_GEN(hp->mdev, log_max_hairpin_num_packets))) {
+		mlx5_core_err(hp->mdev,
+			      "Invalid hairpin queue size, must be <= %lu\n",
+			      BIT(MLX5_CAP_GEN(hp->mdev,
+					       log_max_hairpin_num_packets)));
+		return -EINVAL;
+	}
+
+	hp->queue_size = roundup_pow_of_two(val);
+
+	return 0;
+}
+
+static int debugfs_hairpin_queue_size_get(void *data, u64 *val)
+{
+	struct mlx5e_hairpin_params *hp = data;
+
+	*val = hp->queue_size;
+
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(fops_hairpin_queue_size,
+			 debugfs_hairpin_queue_size_get,
+			 debugfs_hairpin_queue_size_set, "%llu\n");
+
+static int debugfs_hairpin_num_active_get(void *data, u64 *val)
+{
+	struct mlx5e_tc_table *tc = data;
+	struct mlx5e_hairpin_entry *hpe;
+	u32 cnt = 0;
+	u32 bkt;
+
+	mutex_lock(&tc->hairpin_tbl_lock);
+	hash_for_each(tc->hairpin_tbl, bkt, hpe, hairpin_hlist)
+		cnt++;
+	mutex_unlock(&tc->hairpin_tbl_lock);
+
+	*val = cnt;
+
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE(fops_hairpin_num_active,
+			 debugfs_hairpin_num_active_get, NULL, "%llu\n");
+
+static int debugfs_hairpin_table_dump_show(struct seq_file *file, void *priv)
+
+{
+	struct mlx5e_tc_table *tc = file->private;
+	struct mlx5e_hairpin_entry *hpe;
+	u32 bkt;
+
+	mutex_lock(&tc->hairpin_tbl_lock);
+	hash_for_each(tc->hairpin_tbl, bkt, hpe, hairpin_hlist)
+		seq_printf(file, "Hairpin peer_vhca_id %u prio %u refcnt %u\n",
+			   hpe->peer_vhca_id, hpe->prio,
+			   refcount_read(&hpe->refcnt));
+	mutex_unlock(&tc->hairpin_tbl_lock);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(debugfs_hairpin_table_dump);
+
+static void mlx5e_tc_debugfs_init(struct mlx5e_tc_table *tc,
+				  struct dentry *dfs_root)
+{
+	if (IS_ERR_OR_NULL(dfs_root))
+		return;
+
+	tc->dfs_root = debugfs_create_dir("tc", dfs_root);
+	if (!tc->dfs_root)
+		return;
+
+	debugfs_create_file("hairpin_num_queues", 0644, tc->dfs_root,
+			    &tc->hairpin_params, &fops_hairpin_queues);
+	debugfs_create_file("hairpin_queue_size", 0644, tc->dfs_root,
+			    &tc->hairpin_params, &fops_hairpin_queue_size);
+	debugfs_create_file("hairpin_num_active", 0444, tc->dfs_root, tc,
+			    &fops_hairpin_num_active);
+	debugfs_create_file("hairpin_table_dump", 0444, tc->dfs_root, tc,
+			    &debugfs_hairpin_table_dump_fops);
+}
+
+static void
+mlx5e_hairpin_params_init(struct mlx5e_hairpin_params *hairpin_params,
+			  struct mlx5_core_dev *mdev)
+{
+	u64 link_speed64;
+	u32 link_speed;
+
+	hairpin_params->mdev = mdev;
+	/* set hairpin pair per each 50Gbs share of the link */
+	mlx5e_port_max_linkspeed(mdev, &link_speed);
+	link_speed = max_t(u32, link_speed, 50000);
+	link_speed64 = link_speed;
+	do_div(link_speed64, 50000);
+	hairpin_params->num_queues = link_speed64;
+
+	hairpin_params->queue_size =
+		BIT(min_t(u32, 16 - MLX5_MPWRQ_MIN_LOG_STRIDE_SZ(mdev),
+			  MLX5_CAP_GEN(mdev, log_max_hairpin_num_packets)));
+}
+
 static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv,
 				  struct mlx5e_tc_flow *flow,
 				  struct mlx5e_tc_flow_parse_attr *parse_attr,
@@ -1027,8 +1167,6 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv,
 	struct mlx5_core_dev *peer_mdev;
 	struct mlx5e_hairpin_entry *hpe;
 	struct mlx5e_hairpin *hp;
-	u64 link_speed64;
-	u32 link_speed;
 	u8 match_prio;
 	u16 peer_id;
 	int err;
@@ -1081,21 +1219,16 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv,
 		 hash_hairpin_info(peer_id, match_prio));
 	mutex_unlock(&tc->hairpin_tbl_lock);
 
-	params.log_data_size = clamp_t(u8, 16,
+	params.log_num_packets = ilog2(tc->hairpin_params.queue_size);
+	params.log_data_size =
+		clamp_t(u32,
+			params.log_num_packets +
+				MLX5_MPWRQ_MIN_LOG_STRIDE_SZ(priv->mdev),
 			MLX5_CAP_GEN(priv->mdev, log_min_hairpin_wq_data_sz),
 			MLX5_CAP_GEN(priv->mdev, log_max_hairpin_wq_data_sz));
-	params.log_num_packets = params.log_data_size -
-				 MLX5_MPWRQ_MIN_LOG_STRIDE_SZ(priv->mdev);
-	params.log_num_packets = min_t(u8, params.log_num_packets,
-				       MLX5_CAP_GEN(priv->mdev, log_max_hairpin_num_packets));
 
 	params.q_counter = priv->q_counter;
-	/* set hairpin pair per each 50Gbs share of the link */
-	mlx5e_port_max_linkspeed(priv->mdev, &link_speed);
-	link_speed = max_t(u32, link_speed, 50000);
-	link_speed64 = link_speed;
-	do_div(link_speed64, 50000);
-	params.num_channels = link_speed64;
+	params.num_channels = tc->hairpin_params.num_queues;
 
 	hp = mlx5e_hairpin_create(priv, &params, peer_ifindex);
 	hpe->hp = hp;
@@ -5217,6 +5350,8 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
 	tc->ct = mlx5_tc_ct_init(priv, tc->chains, &tc->mod_hdr,
 				 MLX5_FLOW_NAMESPACE_KERNEL, tc->post_act);
 
+	mlx5e_hairpin_params_init(&tc->hairpin_params, dev);
+
 	tc->netdevice_nb.notifier_call = mlx5e_tc_netdev_event;
 	err = register_netdevice_notifier_dev_net(priv->netdev,
 						  &tc->netdevice_nb,
@@ -5227,6 +5362,8 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv)
 		goto err_reg;
 	}
 
+	mlx5e_tc_debugfs_init(tc, mlx5e_fs_get_debugfs_root(priv->fs));
+
 	return 0;
 
 err_reg:
@@ -5255,6 +5392,8 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv)
 {
 	struct mlx5e_tc_table *tc = mlx5e_fs_get_tc(priv->fs);
 
+	debugfs_remove_recursive(tc->dfs_root);
+
 	if (tc->netdevice_nb.notifier_call)
 		unregister_netdevice_notifier_dev_net(priv->netdev,
 						      &tc->netdevice_nb,

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

@@ -1488,7 +1488,7 @@ int mlx5_esw_sf_max_hpf_functions(struct mlx5_core_dev *dev, u16 *max_sfs, u16 *
 	void *hca_caps;
 	int err;
 
-	if (!mlx5_core_is_ecpf(dev)) {
+	if (!mlx5_core_is_ecpf(dev) || mlx5_core_is_management_pf(dev)) {
 		*max_sfs = 0;
 		return 0;
 	}

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

@@ -374,7 +374,8 @@ static int mlx5i_init_rx(struct mlx5e_priv *priv)
 	int err;
 
 	priv->fs = mlx5e_fs_init(priv->profile, mdev,
-				 !test_bit(MLX5E_STATE_DESTROYING, &priv->state));
+				 !test_bit(MLX5E_STATE_DESTROYING, &priv->state),
+				 priv->dfs_root);
 	if (!priv->fs) {
 		netdev_err(priv->netdev, "FS allocation failed\n");
 		return -ENOMEM;

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

@@ -724,7 +724,6 @@ int mlx5dr_send_postsend_action(struct mlx5dr_domain *dmn,
 				struct mlx5dr_action *action)
 {
 	struct postsend_info send_info = {};
-	int ret;
 
 	send_info.write.addr = (uintptr_t)action->rewrite->data;
 	send_info.write.length = action->rewrite->num_of_actions *
@@ -734,9 +733,7 @@ int mlx5dr_send_postsend_action(struct mlx5dr_domain *dmn,
 		mlx5dr_icm_pool_get_chunk_mr_addr(action->rewrite->chunk);
 	send_info.rkey = mlx5dr_icm_pool_get_chunk_rkey(action->rewrite->chunk);
 
-	ret = dr_postsend_icm_data(dmn, &send_info);
-
-	return ret;
+	return dr_postsend_icm_data(dmn, &send_info);
 }
 
 static int dr_modify_qp_rst2init(struct mlx5_core_dev *mdev,

include/linux/mlx5/driver.h

@@ -100,6 +100,8 @@ enum {
 };
 
 enum {
+	MLX5_REG_SBPR            = 0xb001,
+	MLX5_REG_SBCM            = 0xb002,
 	MLX5_REG_QPTS            = 0x4002,
 	MLX5_REG_QETCR		 = 0x4005,
 	MLX5_REG_QTCT		 = 0x400a,
@@ -308,6 +310,7 @@ struct mlx5_cmd {
 	struct workqueue_struct *wq;
 	struct semaphore sem;
 	struct semaphore pages_sem;
+	struct semaphore throttle_sem;
 	int	mode;
 	u16     allowed_opcode;
 	struct mlx5_cmd_work_ent *ent_arr[MLX5_MAX_COMMANDS];
@@ -1200,6 +1203,11 @@ static inline bool mlx5_core_is_vf(const struct mlx5_core_dev *dev)
 	return dev->coredev_type == MLX5_COREDEV_VF;
 }
 
+static inline bool mlx5_core_is_management_pf(const struct mlx5_core_dev *dev)
+{
+	return MLX5_CAP_GEN(dev, num_ports) == 1 && !MLX5_CAP_GEN(dev, native_port_num);
+}
+
 static inline bool mlx5_core_is_ecpf(const struct mlx5_core_dev *dev)
 {
 	return dev->caps.embedded_cpu;

include/linux/mlx5/mlx5_ifc.h

@@ -11000,6 +11000,67 @@ struct mlx5_ifc_pbmc_reg_bits {
 	u8         reserved_at_2e0[0x80];
 };
 
+struct mlx5_ifc_sbpr_reg_bits {
+	u8         desc[0x1];
+	u8         snap[0x1];
+	u8         reserved_at_2[0x4];
+	u8         dir[0x2];
+	u8         reserved_at_8[0x14];
+	u8         pool[0x4];
+
+	u8         infi_size[0x1];
+	u8         reserved_at_21[0x7];
+	u8         size[0x18];
+
+	u8         reserved_at_40[0x1c];
+	u8         mode[0x4];
+
+	u8         reserved_at_60[0x8];
+	u8         buff_occupancy[0x18];
+
+	u8         clr[0x1];
+	u8         reserved_at_81[0x7];
+	u8         max_buff_occupancy[0x18];
+
+	u8         reserved_at_a0[0x8];
+	u8         ext_buff_occupancy[0x18];
+};
+
+struct mlx5_ifc_sbcm_reg_bits {
+	u8         desc[0x1];
+	u8         snap[0x1];
+	u8         reserved_at_2[0x6];
+	u8         local_port[0x8];
+	u8         pnat[0x2];
+	u8         pg_buff[0x6];
+	u8         reserved_at_18[0x6];
+	u8         dir[0x2];
+
+	u8         reserved_at_20[0x1f];
+	u8         exc[0x1];
+
+	u8         reserved_at_40[0x40];
+
+	u8         reserved_at_80[0x8];
+	u8         buff_occupancy[0x18];
+
+	u8         clr[0x1];
+	u8         reserved_at_a1[0x7];
+	u8         max_buff_occupancy[0x18];
+
+	u8         reserved_at_c0[0x8];
+	u8         min_buff[0x18];
+
+	u8         infi_max[0x1];
+	u8         reserved_at_e1[0x7];
+	u8         max_buff[0x18];
+
+	u8         reserved_at_100[0x20];
+
+	u8         reserved_at_120[0x1c];
+	u8         pool[0x4];
+};
+
 struct mlx5_ifc_qtct_reg_bits {
 	u8         reserved_at_0[0x8];
 	u8         port_number[0x8];