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

/*
 * Copyright (c) 2013, Mellanox Technologies inc.  All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - Redistributions in binary form must reproduce the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */

#include <linux/interrupt.h>
#include <linux/module.h>
#include <linux/mlx5/driver.h>
#include <linux/mlx5/cmd.h>
#include "mlx5_core.h"

enum {
	MLX5_EQE_SIZE		= sizeof(struct mlx5_eqe),
	MLX5_EQE_OWNER_INIT_VAL	= 0x1,
};

enum {
	MLX5_EQ_STATE_ARMED		= 0x9,
	MLX5_EQ_STATE_FIRED		= 0xa,
	MLX5_EQ_STATE_ALWAYS_ARMED	= 0xb,
};

enum {
	MLX5_NUM_SPARE_EQE	= 0x80,
	MLX5_NUM_ASYNC_EQE	= 0x100,
	MLX5_NUM_CMD_EQE	= 32,
};

enum {
	MLX5_EQ_DOORBEL_OFFSET	= 0x40,
};

#define MLX5_ASYNC_EVENT_MASK ((1ull << MLX5_EVENT_TYPE_PATH_MIG)	    | \
			       (1ull << MLX5_EVENT_TYPE_COMM_EST)	    | \
			       (1ull << MLX5_EVENT_TYPE_SQ_DRAINED)	    | \
			       (1ull << MLX5_EVENT_TYPE_CQ_ERROR)	    | \
			       (1ull << MLX5_EVENT_TYPE_WQ_CATAS_ERROR)	    | \
			       (1ull << MLX5_EVENT_TYPE_PATH_MIG_FAILED)    | \
			       (1ull << MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR) | \
			       (1ull << MLX5_EVENT_TYPE_WQ_ACCESS_ERROR)    | \
			       (1ull << MLX5_EVENT_TYPE_PORT_CHANGE)	    | \
			       (1ull << MLX5_EVENT_TYPE_SRQ_CATAS_ERROR)    | \
			       (1ull << MLX5_EVENT_TYPE_SRQ_LAST_WQE)	    | \
			       (1ull << MLX5_EVENT_TYPE_SRQ_RQ_LIMIT))

struct map_eq_in {
	u64	mask;
	u32	reserved;
	u32	unmap_eqn;
};

struct cre_des_eq {
	u8	reserved[15];
	u8	eqn;
};

static int mlx5_cmd_destroy_eq(struct mlx5_core_dev *dev, u8 eqn)
{
	struct mlx5_destroy_eq_mbox_in in;
	struct mlx5_destroy_eq_mbox_out out;
	int err;

	memset(&in, 0, sizeof(in));
	memset(&out, 0, sizeof(out));
	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_DESTROY_EQ);
	in.eqn = eqn;
	err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
	if (!err)
		goto ex;

	if (out.hdr.status)
		err = mlx5_cmd_status_to_err(&out.hdr);

ex:
	return err;
}

static struct mlx5_eqe *get_eqe(struct mlx5_eq *eq, u32 entry)
{
	return mlx5_buf_offset(&eq->buf, entry * MLX5_EQE_SIZE);
}

static struct mlx5_eqe *next_eqe_sw(struct mlx5_eq *eq)
{
	struct mlx5_eqe *eqe = get_eqe(eq, eq->cons_index & (eq->nent - 1));

	return ((eqe->owner & 1) ^ !!(eq->cons_index & eq->nent)) ? NULL : eqe;
}

static const char *eqe_type_str(u8 type)
{
	switch (type) {
	case MLX5_EVENT_TYPE_COMP:
		return "MLX5_EVENT_TYPE_COMP";
	case MLX5_EVENT_TYPE_PATH_MIG:
		return "MLX5_EVENT_TYPE_PATH_MIG";
	case MLX5_EVENT_TYPE_COMM_EST:
		return "MLX5_EVENT_TYPE_COMM_EST";
	case MLX5_EVENT_TYPE_SQ_DRAINED:
		return "MLX5_EVENT_TYPE_SQ_DRAINED";
	case MLX5_EVENT_TYPE_SRQ_LAST_WQE:
		return "MLX5_EVENT_TYPE_SRQ_LAST_WQE";
	case MLX5_EVENT_TYPE_SRQ_RQ_LIMIT:
		return "MLX5_EVENT_TYPE_SRQ_RQ_LIMIT";
	case MLX5_EVENT_TYPE_CQ_ERROR:
		return "MLX5_EVENT_TYPE_CQ_ERROR";
	case MLX5_EVENT_TYPE_WQ_CATAS_ERROR:
		return "MLX5_EVENT_TYPE_WQ_CATAS_ERROR";
	case MLX5_EVENT_TYPE_PATH_MIG_FAILED:
		return "MLX5_EVENT_TYPE_PATH_MIG_FAILED";
	case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
		return "MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR";
	case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
		return "MLX5_EVENT_TYPE_WQ_ACCESS_ERROR";
	case MLX5_EVENT_TYPE_SRQ_CATAS_ERROR:
		return "MLX5_EVENT_TYPE_SRQ_CATAS_ERROR";
	case MLX5_EVENT_TYPE_INTERNAL_ERROR:
		return "MLX5_EVENT_TYPE_INTERNAL_ERROR";
	case MLX5_EVENT_TYPE_PORT_CHANGE:
		return "MLX5_EVENT_TYPE_PORT_CHANGE";
	case MLX5_EVENT_TYPE_GPIO_EVENT:
		return "MLX5_EVENT_TYPE_GPIO_EVENT";
	case MLX5_EVENT_TYPE_REMOTE_CONFIG:
		return "MLX5_EVENT_TYPE_REMOTE_CONFIG";
	case MLX5_EVENT_TYPE_DB_BF_CONGESTION:
		return "MLX5_EVENT_TYPE_DB_BF_CONGESTION";
	case MLX5_EVENT_TYPE_STALL_EVENT:
		return "MLX5_EVENT_TYPE_STALL_EVENT";
	case MLX5_EVENT_TYPE_CMD:
		return "MLX5_EVENT_TYPE_CMD";
	case MLX5_EVENT_TYPE_PAGE_REQUEST:
		return "MLX5_EVENT_TYPE_PAGE_REQUEST";
	default:
		return "Unrecognized event";
	}
}

static enum mlx5_dev_event port_subtype_event(u8 subtype)
{
	switch (subtype) {
	case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
		return MLX5_DEV_EVENT_PORT_DOWN;
	case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
		return MLX5_DEV_EVENT_PORT_UP;
	case MLX5_PORT_CHANGE_SUBTYPE_INITIALIZED:
		return MLX5_DEV_EVENT_PORT_INITIALIZED;
	case MLX5_PORT_CHANGE_SUBTYPE_LID:
		return MLX5_DEV_EVENT_LID_CHANGE;
	case MLX5_PORT_CHANGE_SUBTYPE_PKEY:
		return MLX5_DEV_EVENT_PKEY_CHANGE;
	case MLX5_PORT_CHANGE_SUBTYPE_GUID:
		return MLX5_DEV_EVENT_GUID_CHANGE;
	case MLX5_PORT_CHANGE_SUBTYPE_CLIENT_REREG:
		return MLX5_DEV_EVENT_CLIENT_REREG;
	}
	return -1;
}

static void eq_update_ci(struct mlx5_eq *eq, int arm)
{
	__be32 __iomem *addr = eq->doorbell + (arm ? 0 : 2);
	u32 val = (eq->cons_index & 0xffffff) | (eq->eqn << 24);
	__raw_writel((__force u32) cpu_to_be32(val), addr);
	/* We still want ordering, just not swabbing, so add a barrier */
	mb();
}

static int mlx5_eq_int(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
{
	struct mlx5_eqe *eqe;
	int eqes_found = 0;
	int set_ci = 0;
	u32 cqn;
	u32 rsn;
	u8 port;

	while ((eqe = next_eqe_sw(eq))) {
		/*
		 * Make sure we read EQ entry contents after we've
		 * checked the ownership bit.
		 */
		rmb();

		mlx5_core_dbg(eq->dev, "eqn %d, eqe type %s\n",
			      eq->eqn, eqe_type_str(eqe->type));
		switch (eqe->type) {
		case MLX5_EVENT_TYPE_COMP:
			cqn = be32_to_cpu(eqe->data.comp.cqn) & 0xffffff;
			mlx5_cq_completion(dev, cqn);
			break;

		case MLX5_EVENT_TYPE_PATH_MIG:
		case MLX5_EVENT_TYPE_COMM_EST:
		case MLX5_EVENT_TYPE_SQ_DRAINED:
		case MLX5_EVENT_TYPE_SRQ_LAST_WQE:
		case MLX5_EVENT_TYPE_WQ_CATAS_ERROR:
		case MLX5_EVENT_TYPE_PATH_MIG_FAILED:
		case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
		case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
			rsn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
			mlx5_core_dbg(dev, "event %s(%d) arrived\n",
				      eqe_type_str(eqe->type), eqe->type);
			mlx5_rsc_event(dev, rsn, eqe->type);
			break;

		case MLX5_EVENT_TYPE_SRQ_RQ_LIMIT:
		case MLX5_EVENT_TYPE_SRQ_CATAS_ERROR:
			rsn = be32_to_cpu(eqe->data.qp_srq.qp_srq_n) & 0xffffff;
			mlx5_core_dbg(dev, "SRQ event %s(%d): srqn 0x%x\n",
				      eqe_type_str(eqe->type), eqe->type, rsn);
			mlx5_srq_event(dev, rsn, eqe->type);
			break;

		case MLX5_EVENT_TYPE_CMD:
			mlx5_cmd_comp_handler(dev, be32_to_cpu(eqe->data.cmd.vector));
			break;

		case MLX5_EVENT_TYPE_PORT_CHANGE:
			port = (eqe->data.port.port >> 4) & 0xf;
			switch (eqe->sub_type) {
			case MLX5_PORT_CHANGE_SUBTYPE_DOWN:
			case MLX5_PORT_CHANGE_SUBTYPE_ACTIVE:
			case MLX5_PORT_CHANGE_SUBTYPE_LID:
			case MLX5_PORT_CHANGE_SUBTYPE_PKEY:
			case MLX5_PORT_CHANGE_SUBTYPE_GUID:
			case MLX5_PORT_CHANGE_SUBTYPE_CLIENT_REREG:
			case MLX5_PORT_CHANGE_SUBTYPE_INITIALIZED:
				if (dev->event)
					dev->event(dev, port_subtype_event(eqe->sub_type),
						   (unsigned long)port);
				break;
			default:
				mlx5_core_warn(dev, "Port event with unrecognized subtype: port %d, sub_type %d\n",
					       port, eqe->sub_type);
			}
			break;
		case MLX5_EVENT_TYPE_CQ_ERROR:
			cqn = be32_to_cpu(eqe->data.cq_err.cqn) & 0xffffff;
			mlx5_core_warn(dev, "CQ error on CQN 0x%x, syndrom 0x%x\n",
				       cqn, eqe->data.cq_err.syndrome);
			mlx5_cq_event(dev, cqn, eqe->type);
			break;

		case MLX5_EVENT_TYPE_PAGE_REQUEST:
			{
				u16 func_id = be16_to_cpu(eqe->data.req_pages.func_id);
				s32 npages = be32_to_cpu(eqe->data.req_pages.num_pages);

				mlx5_core_dbg(dev, "page request for func 0x%x, npages %d\n",
					      func_id, npages);
				mlx5_core_req_pages_handler(dev, func_id, npages);
			}
			break;


		default:
			mlx5_core_warn(dev, "Unhandled event 0x%x on EQ 0x%x\n",
				       eqe->type, eq->eqn);
			break;
		}

		++eq->cons_index;
		eqes_found = 1;
		++set_ci;

		/* The HCA will think the queue has overflowed if we
		 * don't tell it we've been processing events.  We
		 * create our EQs with MLX5_NUM_SPARE_EQE extra
		 * entries, so we must update our consumer index at
		 * least that often.
		 */
		if (unlikely(set_ci >= MLX5_NUM_SPARE_EQE)) {
			eq_update_ci(eq, 0);
			set_ci = 0;
		}
	}

	eq_update_ci(eq, 1);

	return eqes_found;
}

static irqreturn_t mlx5_msix_handler(int irq, void *eq_ptr)
{
	struct mlx5_eq *eq = eq_ptr;
	struct mlx5_core_dev *dev = eq->dev;

	mlx5_eq_int(dev, eq);

	/* MSI-X vectors always belong to us */
	return IRQ_HANDLED;
}

static void init_eq_buf(struct mlx5_eq *eq)
{
	struct mlx5_eqe *eqe;
	int i;

	for (i = 0; i < eq->nent; i++) {
		eqe = get_eqe(eq, i);
		eqe->owner = MLX5_EQE_OWNER_INIT_VAL;
	}
}

int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
		       int nent, u64 mask, const char *name, struct mlx5_uar *uar)
{
	struct mlx5_eq_table *table = &dev->priv.eq_table;
	struct mlx5_create_eq_mbox_in *in;
	struct mlx5_create_eq_mbox_out out;
	int err;
	int inlen;

	eq->nent = roundup_pow_of_two(nent + MLX5_NUM_SPARE_EQE);
	err = mlx5_buf_alloc(dev, eq->nent * MLX5_EQE_SIZE, 2 * PAGE_SIZE,
			     &eq->buf);
	if (err)
		return err;

	init_eq_buf(eq);

	inlen = sizeof(*in) + sizeof(in->pas[0]) * eq->buf.npages;
	in = mlx5_vzalloc(inlen);
	if (!in) {
		err = -ENOMEM;
		goto err_buf;
	}
	memset(&out, 0, sizeof(out));

	mlx5_fill_page_array(&eq->buf, in->pas);

	in->hdr.opcode = cpu_to_be16(MLX5_CMD_OP_CREATE_EQ);
	in->ctx.log_sz_usr_page = cpu_to_be32(ilog2(eq->nent) << 24 | uar->index);
	in->ctx.intr = vecidx;
	in->ctx.log_page_size = eq->buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT;
	in->events_mask = cpu_to_be64(mask);

	err = mlx5_cmd_exec(dev, in, inlen, &out, sizeof(out));
	if (err)
		goto err_in;

	if (out.hdr.status) {
		err = mlx5_cmd_status_to_err(&out.hdr);
		goto err_in;
	}

	snprintf(eq->name, MLX5_MAX_EQ_NAME, "%s@pci:%s",
		 name, pci_name(dev->pdev));
	eq->eqn = out.eq_number;
	err = request_irq(table->msix_arr[vecidx].vector, mlx5_msix_handler, 0,
			  eq->name, eq);
	if (err)
		goto err_eq;

	eq->irqn = vecidx;
	eq->dev = dev;
	eq->doorbell = uar->map + MLX5_EQ_DOORBEL_OFFSET;

	err = mlx5_debug_eq_add(dev, eq);
	if (err)
		goto err_irq;

	/* EQs are created in ARMED state
	 */
	eq_update_ci(eq, 1);

	mlx5_vfree(in);
	return 0;

err_irq:
	free_irq(table->msix_arr[vecidx].vector, eq);

err_eq:
	mlx5_cmd_destroy_eq(dev, eq->eqn);

err_in:
	mlx5_vfree(in);

err_buf:
	mlx5_buf_free(dev, &eq->buf);
	return err;
}
EXPORT_SYMBOL_GPL(mlx5_create_map_eq);

int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
{
	struct mlx5_eq_table *table = &dev->priv.eq_table;
	int err;

	mlx5_debug_eq_remove(dev, eq);
	free_irq(table->msix_arr[eq->irqn].vector, eq);
	err = mlx5_cmd_destroy_eq(dev, eq->eqn);
	if (err)
		mlx5_core_warn(dev, "failed to destroy a previously created eq: eqn %d\n",
			       eq->eqn);
	synchronize_irq(table->msix_arr[eq->irqn].vector);
	mlx5_buf_free(dev, &eq->buf);

	return err;
}
EXPORT_SYMBOL_GPL(mlx5_destroy_unmap_eq);

int mlx5_eq_init(struct mlx5_core_dev *dev)
{
	int err;

	spin_lock_init(&dev->priv.eq_table.lock);

	err = mlx5_eq_debugfs_init(dev);

	return err;
}


void mlx5_eq_cleanup(struct mlx5_core_dev *dev)
{
	mlx5_eq_debugfs_cleanup(dev);
}

int mlx5_start_eqs(struct mlx5_core_dev *dev)
{
	struct mlx5_eq_table *table = &dev->priv.eq_table;
	int err;

	err = mlx5_create_map_eq(dev, &table->cmd_eq, MLX5_EQ_VEC_CMD,
				 MLX5_NUM_CMD_EQE, 1ull << MLX5_EVENT_TYPE_CMD,
				 "mlx5_cmd_eq", &dev->priv.uuari.uars[0]);
	if (err) {
		mlx5_core_warn(dev, "failed to create cmd EQ %d\n", err);
		return err;
	}

	mlx5_cmd_use_events(dev);

	err = mlx5_create_map_eq(dev, &table->async_eq, MLX5_EQ_VEC_ASYNC,
				 MLX5_NUM_ASYNC_EQE, MLX5_ASYNC_EVENT_MASK,
				 "mlx5_async_eq", &dev->priv.uuari.uars[0]);
	if (err) {
		mlx5_core_warn(dev, "failed to create async EQ %d\n", err);
		goto err1;
	}

	err = mlx5_create_map_eq(dev, &table->pages_eq,
				 MLX5_EQ_VEC_PAGES,
				 dev->caps.gen.max_vf + 1,
				 1 << MLX5_EVENT_TYPE_PAGE_REQUEST, "mlx5_pages_eq",
				 &dev->priv.uuari.uars[0]);
	if (err) {
		mlx5_core_warn(dev, "failed to create pages EQ %d\n", err);
		goto err2;
	}

	return err;

err2:
	mlx5_destroy_unmap_eq(dev, &table->async_eq);

err1:
	mlx5_cmd_use_polling(dev);
	mlx5_destroy_unmap_eq(dev, &table->cmd_eq);
	return err;
}

int mlx5_stop_eqs(struct mlx5_core_dev *dev)
{
	struct mlx5_eq_table *table = &dev->priv.eq_table;
	int err;

	err = mlx5_destroy_unmap_eq(dev, &table->pages_eq);
	if (err)
		return err;

	mlx5_destroy_unmap_eq(dev, &table->async_eq);
	mlx5_cmd_use_polling(dev);

	err = mlx5_destroy_unmap_eq(dev, &table->cmd_eq);
	if (err)
		mlx5_cmd_use_events(dev);

	return err;
}

int mlx5_core_eq_query(struct mlx5_core_dev *dev, struct mlx5_eq *eq,
		       struct mlx5_query_eq_mbox_out *out, int outlen)
{
	struct mlx5_query_eq_mbox_in in;
	int err;

	memset(&in, 0, sizeof(in));
	memset(out, 0, outlen);
	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_QUERY_EQ);
	in.eqn = eq->eqn;
	err = mlx5_cmd_exec(dev, &in, sizeof(in), out, outlen);
	if (err)
		return err;

	if (out->hdr.status)
		err = mlx5_cmd_status_to_err(&out->hdr);

	return err;
}
EXPORT_SYMBOL_GPL(mlx5_core_eq_query);