linux_dsm_epyc7002/drivers/net/ethernet/mellanox/mlx4/en_cq.c
Or Gerlitz 08ff32352d mlx4: 64-byte CQE/EQE support
ConnectX-3 devices can use either 64- or 32-byte completion queue
entries (CQEs) and event queue entries (EQEs).  Using 64-byte
EQEs/CQEs performs better because each entry is aligned to a complete
cacheline.  This patch queries the HCA's capabilities, and if it
supports 64-byte CQEs and EQES the driver will configure the HW to
work in 64-byte mode.

The 32-byte vs 64-byte mode is global per HCA and not per CQ or EQ.

Since this mode is global, userspace (libmlx4) must be updated to work
with the configured CQE size, and guests using SR-IOV virtual
functions need to know both EQE and CQE size.

In case one of the 64-byte CQE/EQE capabilities is activated, the
patch makes sure that older guest drivers that use the QUERY_DEV_FUNC
command (e.g as done in mlx4_core of Linux 3.3..3.6) will notice that
they need an update to be able to work with the PPF. This is done by
changing the returned pf_context_behaviour not to be zero any more. In
case none of these capabilities is activated that value remains zero
and older guest drivers can run OK.

The SRIOV related flow is as follows

1. the PPF does the detection of the new capabilities using
   QUERY_DEV_CAP command.

2. the PPF activates the new capabilities using INIT_HCA.

3. the VF detects if the PPF activated the capabilities using
   QUERY_HCA, and if this is the case activates them for itself too.

Note that the VF detects that it must be aware to the new PF behaviour
using QUERY_FUNC_CAP.  Steps 1 and 2 apply also for native mode.

User space notification is done through a new field introduced in
struct mlx4_ib_ucontext which holds device capabilities for which user
space must take action. This changes the binary interface so the ABI
towards libmlx4 exposed through uverbs is bumped from 3 to 4 but only
when **needed** i.e. only when the driver does use 64-byte CQEs or
future device capabilities which must be in sync by user space. This
practice allows to work with unmodified libmlx4 on older devices (e.g
A0, B0) which don't support 64-byte CQEs.

In order to keep existing systems functional when they update to a
newer kernel that contains these changes in VF and userspace ABI, a
module parameter enable_64b_cqe_eqe must be set to enable 64-byte
mode; the default is currently false.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>
2012-11-26 10:19:17 -08:00

181 lines
4.8 KiB
C

/*
* Copyright (c) 2007 Mellanox Technologies. 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/mlx4/cq.h>
#include <linux/mlx4/qp.h>
#include <linux/mlx4/cmd.h>
#include "mlx4_en.h"
static void mlx4_en_cq_event(struct mlx4_cq *cq, enum mlx4_event event)
{
return;
}
int mlx4_en_create_cq(struct mlx4_en_priv *priv,
struct mlx4_en_cq *cq,
int entries, int ring, enum cq_type mode)
{
struct mlx4_en_dev *mdev = priv->mdev;
int err;
cq->size = entries;
cq->buf_size = cq->size * mdev->dev->caps.cqe_size;
cq->ring = ring;
cq->is_tx = mode;
spin_lock_init(&cq->lock);
err = mlx4_alloc_hwq_res(mdev->dev, &cq->wqres,
cq->buf_size, 2 * PAGE_SIZE);
if (err)
return err;
err = mlx4_en_map_buffer(&cq->wqres.buf);
if (err)
mlx4_free_hwq_res(mdev->dev, &cq->wqres, cq->buf_size);
else
cq->buf = (struct mlx4_cqe *) cq->wqres.buf.direct.buf;
return err;
}
int mlx4_en_activate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq,
int cq_idx)
{
struct mlx4_en_dev *mdev = priv->mdev;
int err = 0;
char name[25];
struct cpu_rmap *rmap =
#ifdef CONFIG_RFS_ACCEL
priv->dev->rx_cpu_rmap;
#else
NULL;
#endif
cq->dev = mdev->pndev[priv->port];
cq->mcq.set_ci_db = cq->wqres.db.db;
cq->mcq.arm_db = cq->wqres.db.db + 1;
*cq->mcq.set_ci_db = 0;
*cq->mcq.arm_db = 0;
memset(cq->buf, 0, cq->buf_size);
if (cq->is_tx == RX) {
if (mdev->dev->caps.comp_pool) {
if (!cq->vector) {
sprintf(name, "%s-%d", priv->dev->name,
cq->ring);
/* Set IRQ for specific name (per ring) */
if (mlx4_assign_eq(mdev->dev, name, rmap,
&cq->vector)) {
cq->vector = (cq->ring + 1 + priv->port)
% mdev->dev->caps.num_comp_vectors;
mlx4_warn(mdev, "Failed Assigning an EQ to "
"%s ,Falling back to legacy EQ's\n",
name);
}
}
} else {
cq->vector = (cq->ring + 1 + priv->port) %
mdev->dev->caps.num_comp_vectors;
}
} else {
/* For TX we use the same irq per
ring we assigned for the RX */
struct mlx4_en_cq *rx_cq;
cq_idx = cq_idx % priv->rx_ring_num;
rx_cq = &priv->rx_cq[cq_idx];
cq->vector = rx_cq->vector;
}
if (!cq->is_tx)
cq->size = priv->rx_ring[cq->ring].actual_size;
err = mlx4_cq_alloc(mdev->dev, cq->size, &cq->wqres.mtt, &mdev->priv_uar,
cq->wqres.db.dma, &cq->mcq, cq->vector, 0);
if (err)
return err;
cq->mcq.comp = cq->is_tx ? mlx4_en_tx_irq : mlx4_en_rx_irq;
cq->mcq.event = mlx4_en_cq_event;
if (!cq->is_tx) {
netif_napi_add(cq->dev, &cq->napi, mlx4_en_poll_rx_cq, 64);
napi_enable(&cq->napi);
}
return 0;
}
void mlx4_en_destroy_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
{
struct mlx4_en_dev *mdev = priv->mdev;
mlx4_en_unmap_buffer(&cq->wqres.buf);
mlx4_free_hwq_res(mdev->dev, &cq->wqres, cq->buf_size);
if (priv->mdev->dev->caps.comp_pool && cq->vector)
mlx4_release_eq(priv->mdev->dev, cq->vector);
cq->vector = 0;
cq->buf_size = 0;
cq->buf = NULL;
}
void mlx4_en_deactivate_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
{
if (!cq->is_tx) {
napi_disable(&cq->napi);
netif_napi_del(&cq->napi);
}
mlx4_cq_free(priv->mdev->dev, &cq->mcq);
}
/* Set rx cq moderation parameters */
int mlx4_en_set_cq_moder(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
{
return mlx4_cq_modify(priv->mdev->dev, &cq->mcq,
cq->moder_cnt, cq->moder_time);
}
int mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq)
{
mlx4_cq_arm(&cq->mcq, MLX4_CQ_DB_REQ_NOT, priv->mdev->uar_map,
&priv->mdev->uar_lock);
return 0;
}