numam-dpdk/drivers/net/mlx5/mlx5_trigger.c

528 lines
13 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: BSD-3-Clause
* Copyright 2015 6WIND S.A.
* Copyright 2015 Mellanox Technologies, Ltd
*/
#include <unistd.h>
#include <rte_ether.h>
#include <rte_ethdev_driver.h>
#include <rte_interrupts.h>
#include <rte_alarm.h>
#include "mlx5.h"
#include "mlx5_rxtx.h"
#include "mlx5_utils.h"
/**
* Stop traffic on Tx queues.
*
* @param dev
* Pointer to Ethernet device structure.
*/
static void
mlx5_txq_stop(struct rte_eth_dev *dev)
{
struct mlx5_priv *priv = dev->data->dev_private;
unsigned int i;
for (i = 0; i != priv->txqs_n; ++i)
mlx5_txq_release(dev, i);
}
/**
* Start traffic on Tx queues.
*
* @param dev
* Pointer to Ethernet device structure.
*
* @return
* 0 on success, a negative errno value otherwise and rte_errno is set.
*/
static int
mlx5_txq_start(struct rte_eth_dev *dev)
{
struct mlx5_priv *priv = dev->data->dev_private;
unsigned int i;
int ret;
for (i = 0; i != priv->txqs_n; ++i) {
struct mlx5_txq_ctrl *txq_ctrl = mlx5_txq_get(dev, i);
if (!txq_ctrl)
continue;
if (txq_ctrl->type == MLX5_TXQ_TYPE_HAIRPIN) {
txq_ctrl->obj = mlx5_txq_obj_new
(dev, i, MLX5_TXQ_OBJ_TYPE_DEVX_HAIRPIN);
} else {
txq_alloc_elts(txq_ctrl);
txq_ctrl->obj = mlx5_txq_obj_new
(dev, i, MLX5_TXQ_OBJ_TYPE_IBV);
}
if (!txq_ctrl->obj) {
rte_errno = ENOMEM;
goto error;
}
}
return 0;
error:
ret = rte_errno; /* Save rte_errno before cleanup. */
do {
mlx5_txq_release(dev, i);
} while (i-- != 0);
rte_errno = ret; /* Restore rte_errno. */
return -rte_errno;
}
/**
* Stop traffic on Rx queues.
*
* @param dev
* Pointer to Ethernet device structure.
*/
static void
mlx5_rxq_stop(struct rte_eth_dev *dev)
{
struct mlx5_priv *priv = dev->data->dev_private;
unsigned int i;
for (i = 0; i != priv->rxqs_n; ++i)
mlx5_rxq_release(dev, i);
}
/**
* Start traffic on Rx queues.
*
* @param dev
* Pointer to Ethernet device structure.
*
* @return
* 0 on success, a negative errno value otherwise and rte_errno is set.
*/
static int
mlx5_rxq_start(struct rte_eth_dev *dev)
{
struct mlx5_priv *priv = dev->data->dev_private;
unsigned int i;
int ret = 0;
enum mlx5_rxq_obj_type obj_type = MLX5_RXQ_OBJ_TYPE_IBV;
for (i = 0; i < priv->rxqs_n; ++i) {
if ((*priv->rxqs)[i]->lro) {
obj_type = MLX5_RXQ_OBJ_TYPE_DEVX_RQ;
break;
}
}
/* Allocate/reuse/resize mempool for Multi-Packet RQ. */
if (mlx5_mprq_alloc_mp(dev)) {
/* Should not release Rx queues but return immediately. */
return -rte_errno;
}
for (i = 0; i != priv->rxqs_n; ++i) {
struct mlx5_rxq_ctrl *rxq_ctrl = mlx5_rxq_get(dev, i);
net/mlx5: add new memory region support This is the new design of Memory Region (MR) for mlx PMD, in order to: - Accommodate the new memory hotplug model. - Support non-contiguous Mempool. There are multiple layers for MR search. L0 is to look up the last-hit entry which is pointed by mr_ctrl->mru (Most Recently Used). If L0 misses, L1 is to look up the address in a fixed-sized array by linear search. L0/L1 is in an inline function - mlx5_mr_lookup_cache(). If L1 misses, the bottom-half function is called to look up the address from the bigger local cache of the queue. This is L2 - mlx5_mr_addr2mr_bh() and it is not an inline function. Data structure for L2 is the Binary Tree. If L2 misses, the search falls into the slowest path which takes locks in order to access global device cache (priv->mr.cache) which is also a B-tree and caches the original MR list (priv->mr.mr_list) of the device. Unless the global cache is overflowed, it is all-inclusive of the MR list. This is L3 - mlx5_mr_lookup_dev(). The size of the L3 cache table is limited and can't be expanded on the fly due to deadlock. Refer to the comments in the code for the details - mr_lookup_dev(). If L3 is overflowed, the list will have to be searched directly bypassing the cache although it is slower. If L3 misses, a new MR for the address should be created - mlx5_mr_create(). When it creates a new MR, it tries to register adjacent memsegs as much as possible which are virtually contiguous around the address. This must take two locks - memory_hotplug_lock and priv->mr.rwlock. Due to memory_hotplug_lock, there can't be any allocation/free of memory inside. In the free callback of the memory hotplug event, freed space is searched from the MR list and corresponding bits are cleared from the bitmap of MRs. This can fragment a MR and the MR will have multiple search entries in the caches. Once there's a change by the event, the global cache must be rebuilt and all the per-queue caches will be flushed as well. If memory is frequently freed in run-time, that may cause jitter on dataplane processing in the worst case by incurring MR cache flush and rebuild. But, it would be the least probable scenario. To guarantee the most optimal performance, it is highly recommended to use an EAL option - '--socket-mem'. Then, the reserved memory will be pinned and won't be freed dynamically. And it is also recommended to configure per-lcore cache of Mempool. Even though there're many MRs for a device or MRs are highly fragmented, the cache of Mempool will be much helpful to reduce misses on per-queue caches anyway. '--legacy-mem' is also supported. Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
2018-05-09 11:09:04 +00:00
struct rte_mempool *mp;
if (!rxq_ctrl)
continue;
if (rxq_ctrl->type == MLX5_RXQ_TYPE_HAIRPIN) {
rxq_ctrl->obj = mlx5_rxq_obj_new
(dev, i, MLX5_RXQ_OBJ_TYPE_DEVX_HAIRPIN);
if (!rxq_ctrl->obj)
goto error;
continue;
}
net/mlx5: add new memory region support This is the new design of Memory Region (MR) for mlx PMD, in order to: - Accommodate the new memory hotplug model. - Support non-contiguous Mempool. There are multiple layers for MR search. L0 is to look up the last-hit entry which is pointed by mr_ctrl->mru (Most Recently Used). If L0 misses, L1 is to look up the address in a fixed-sized array by linear search. L0/L1 is in an inline function - mlx5_mr_lookup_cache(). If L1 misses, the bottom-half function is called to look up the address from the bigger local cache of the queue. This is L2 - mlx5_mr_addr2mr_bh() and it is not an inline function. Data structure for L2 is the Binary Tree. If L2 misses, the search falls into the slowest path which takes locks in order to access global device cache (priv->mr.cache) which is also a B-tree and caches the original MR list (priv->mr.mr_list) of the device. Unless the global cache is overflowed, it is all-inclusive of the MR list. This is L3 - mlx5_mr_lookup_dev(). The size of the L3 cache table is limited and can't be expanded on the fly due to deadlock. Refer to the comments in the code for the details - mr_lookup_dev(). If L3 is overflowed, the list will have to be searched directly bypassing the cache although it is slower. If L3 misses, a new MR for the address should be created - mlx5_mr_create(). When it creates a new MR, it tries to register adjacent memsegs as much as possible which are virtually contiguous around the address. This must take two locks - memory_hotplug_lock and priv->mr.rwlock. Due to memory_hotplug_lock, there can't be any allocation/free of memory inside. In the free callback of the memory hotplug event, freed space is searched from the MR list and corresponding bits are cleared from the bitmap of MRs. This can fragment a MR and the MR will have multiple search entries in the caches. Once there's a change by the event, the global cache must be rebuilt and all the per-queue caches will be flushed as well. If memory is frequently freed in run-time, that may cause jitter on dataplane processing in the worst case by incurring MR cache flush and rebuild. But, it would be the least probable scenario. To guarantee the most optimal performance, it is highly recommended to use an EAL option - '--socket-mem'. Then, the reserved memory will be pinned and won't be freed dynamically. And it is also recommended to configure per-lcore cache of Mempool. Even though there're many MRs for a device or MRs are highly fragmented, the cache of Mempool will be much helpful to reduce misses on per-queue caches anyway. '--legacy-mem' is also supported. Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
2018-05-09 11:09:04 +00:00
/* Pre-register Rx mempool. */
mp = mlx5_rxq_mprq_enabled(&rxq_ctrl->rxq) ?
rxq_ctrl->rxq.mprq_mp : rxq_ctrl->rxq.mp;
net/mlx5: add new memory region support This is the new design of Memory Region (MR) for mlx PMD, in order to: - Accommodate the new memory hotplug model. - Support non-contiguous Mempool. There are multiple layers for MR search. L0 is to look up the last-hit entry which is pointed by mr_ctrl->mru (Most Recently Used). If L0 misses, L1 is to look up the address in a fixed-sized array by linear search. L0/L1 is in an inline function - mlx5_mr_lookup_cache(). If L1 misses, the bottom-half function is called to look up the address from the bigger local cache of the queue. This is L2 - mlx5_mr_addr2mr_bh() and it is not an inline function. Data structure for L2 is the Binary Tree. If L2 misses, the search falls into the slowest path which takes locks in order to access global device cache (priv->mr.cache) which is also a B-tree and caches the original MR list (priv->mr.mr_list) of the device. Unless the global cache is overflowed, it is all-inclusive of the MR list. This is L3 - mlx5_mr_lookup_dev(). The size of the L3 cache table is limited and can't be expanded on the fly due to deadlock. Refer to the comments in the code for the details - mr_lookup_dev(). If L3 is overflowed, the list will have to be searched directly bypassing the cache although it is slower. If L3 misses, a new MR for the address should be created - mlx5_mr_create(). When it creates a new MR, it tries to register adjacent memsegs as much as possible which are virtually contiguous around the address. This must take two locks - memory_hotplug_lock and priv->mr.rwlock. Due to memory_hotplug_lock, there can't be any allocation/free of memory inside. In the free callback of the memory hotplug event, freed space is searched from the MR list and corresponding bits are cleared from the bitmap of MRs. This can fragment a MR and the MR will have multiple search entries in the caches. Once there's a change by the event, the global cache must be rebuilt and all the per-queue caches will be flushed as well. If memory is frequently freed in run-time, that may cause jitter on dataplane processing in the worst case by incurring MR cache flush and rebuild. But, it would be the least probable scenario. To guarantee the most optimal performance, it is highly recommended to use an EAL option - '--socket-mem'. Then, the reserved memory will be pinned and won't be freed dynamically. And it is also recommended to configure per-lcore cache of Mempool. Even though there're many MRs for a device or MRs are highly fragmented, the cache of Mempool will be much helpful to reduce misses on per-queue caches anyway. '--legacy-mem' is also supported. Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
2018-05-09 11:09:04 +00:00
DRV_LOG(DEBUG,
"port %u Rx queue %u registering"
" mp %s having %u chunks",
dev->data->port_id, rxq_ctrl->rxq.idx,
net/mlx5: add new memory region support This is the new design of Memory Region (MR) for mlx PMD, in order to: - Accommodate the new memory hotplug model. - Support non-contiguous Mempool. There are multiple layers for MR search. L0 is to look up the last-hit entry which is pointed by mr_ctrl->mru (Most Recently Used). If L0 misses, L1 is to look up the address in a fixed-sized array by linear search. L0/L1 is in an inline function - mlx5_mr_lookup_cache(). If L1 misses, the bottom-half function is called to look up the address from the bigger local cache of the queue. This is L2 - mlx5_mr_addr2mr_bh() and it is not an inline function. Data structure for L2 is the Binary Tree. If L2 misses, the search falls into the slowest path which takes locks in order to access global device cache (priv->mr.cache) which is also a B-tree and caches the original MR list (priv->mr.mr_list) of the device. Unless the global cache is overflowed, it is all-inclusive of the MR list. This is L3 - mlx5_mr_lookup_dev(). The size of the L3 cache table is limited and can't be expanded on the fly due to deadlock. Refer to the comments in the code for the details - mr_lookup_dev(). If L3 is overflowed, the list will have to be searched directly bypassing the cache although it is slower. If L3 misses, a new MR for the address should be created - mlx5_mr_create(). When it creates a new MR, it tries to register adjacent memsegs as much as possible which are virtually contiguous around the address. This must take two locks - memory_hotplug_lock and priv->mr.rwlock. Due to memory_hotplug_lock, there can't be any allocation/free of memory inside. In the free callback of the memory hotplug event, freed space is searched from the MR list and corresponding bits are cleared from the bitmap of MRs. This can fragment a MR and the MR will have multiple search entries in the caches. Once there's a change by the event, the global cache must be rebuilt and all the per-queue caches will be flushed as well. If memory is frequently freed in run-time, that may cause jitter on dataplane processing in the worst case by incurring MR cache flush and rebuild. But, it would be the least probable scenario. To guarantee the most optimal performance, it is highly recommended to use an EAL option - '--socket-mem'. Then, the reserved memory will be pinned and won't be freed dynamically. And it is also recommended to configure per-lcore cache of Mempool. Even though there're many MRs for a device or MRs are highly fragmented, the cache of Mempool will be much helpful to reduce misses on per-queue caches anyway. '--legacy-mem' is also supported. Signed-off-by: Yongseok Koh <yskoh@mellanox.com>
2018-05-09 11:09:04 +00:00
mp->name, mp->nb_mem_chunks);
mlx5_mr_update_mp(dev, &rxq_ctrl->rxq.mr_ctrl, mp);
ret = rxq_alloc_elts(rxq_ctrl);
if (ret)
goto error;
rxq_ctrl->obj = mlx5_rxq_obj_new(dev, i, obj_type);
if (!rxq_ctrl->obj)
goto error;
if (obj_type == MLX5_RXQ_OBJ_TYPE_IBV)
rxq_ctrl->wqn = rxq_ctrl->obj->wq->wq_num;
else if (obj_type == MLX5_RXQ_OBJ_TYPE_DEVX_RQ)
rxq_ctrl->wqn = rxq_ctrl->obj->rq->id;
}
return 0;
error:
ret = rte_errno; /* Save rte_errno before cleanup. */
do {
mlx5_rxq_release(dev, i);
} while (i-- != 0);
rte_errno = ret; /* Restore rte_errno. */
return -rte_errno;
}
/**
* Binds Tx queues to Rx queues for hairpin.
*
* Binds Tx queues to the target Rx queues.
*
* @param dev
* Pointer to Ethernet device structure.
*
* @return
* 0 on success, a negative errno value otherwise and rte_errno is set.
*/
static int
mlx5_hairpin_bind(struct rte_eth_dev *dev)
{
struct mlx5_priv *priv = dev->data->dev_private;
struct mlx5_devx_modify_sq_attr sq_attr = { 0 };
struct mlx5_devx_modify_rq_attr rq_attr = { 0 };
struct mlx5_txq_ctrl *txq_ctrl;
struct mlx5_rxq_ctrl *rxq_ctrl;
struct mlx5_devx_obj *sq;
struct mlx5_devx_obj *rq;
unsigned int i;
int ret = 0;
for (i = 0; i != priv->txqs_n; ++i) {
txq_ctrl = mlx5_txq_get(dev, i);
if (!txq_ctrl)
continue;
if (txq_ctrl->type != MLX5_TXQ_TYPE_HAIRPIN) {
mlx5_txq_release(dev, i);
continue;
}
if (!txq_ctrl->obj) {
rte_errno = ENOMEM;
DRV_LOG(ERR, "port %u no txq object found: %d",
dev->data->port_id, i);
mlx5_txq_release(dev, i);
return -rte_errno;
}
sq = txq_ctrl->obj->sq;
rxq_ctrl = mlx5_rxq_get(dev,
txq_ctrl->hairpin_conf.peers[0].queue);
if (!rxq_ctrl) {
mlx5_txq_release(dev, i);
rte_errno = EINVAL;
DRV_LOG(ERR, "port %u no rxq object found: %d",
dev->data->port_id,
txq_ctrl->hairpin_conf.peers[0].queue);
return -rte_errno;
}
if (rxq_ctrl->type != MLX5_RXQ_TYPE_HAIRPIN ||
rxq_ctrl->hairpin_conf.peers[0].queue != i) {
rte_errno = ENOMEM;
DRV_LOG(ERR, "port %u Tx queue %d can't be binded to "
"Rx queue %d", dev->data->port_id,
i, txq_ctrl->hairpin_conf.peers[0].queue);
goto error;
}
rq = rxq_ctrl->obj->rq;
if (!rq) {
rte_errno = ENOMEM;
DRV_LOG(ERR, "port %u hairpin no matching rxq: %d",
dev->data->port_id,
txq_ctrl->hairpin_conf.peers[0].queue);
goto error;
}
sq_attr.state = MLX5_SQC_STATE_RDY;
sq_attr.sq_state = MLX5_SQC_STATE_RST;
sq_attr.hairpin_peer_rq = rq->id;
sq_attr.hairpin_peer_vhca = priv->config.hca_attr.vhca_id;
ret = mlx5_devx_cmd_modify_sq(sq, &sq_attr);
if (ret)
goto error;
rq_attr.state = MLX5_SQC_STATE_RDY;
rq_attr.rq_state = MLX5_SQC_STATE_RST;
rq_attr.hairpin_peer_sq = sq->id;
rq_attr.hairpin_peer_vhca = priv->config.hca_attr.vhca_id;
ret = mlx5_devx_cmd_modify_rq(rq, &rq_attr);
if (ret)
goto error;
mlx5_txq_release(dev, i);
mlx5_rxq_release(dev, txq_ctrl->hairpin_conf.peers[0].queue);
}
return 0;
error:
mlx5_txq_release(dev, i);
mlx5_rxq_release(dev, txq_ctrl->hairpin_conf.peers[0].queue);
return -rte_errno;
}
/**
* DPDK callback to start the device.
*
* Simulate device start by attaching all configured flows.
*
* @param dev
* Pointer to Ethernet device structure.
*
* @return
* 0 on success, a negative errno value otherwise and rte_errno is set.
*/
int
mlx5_dev_start(struct rte_eth_dev *dev)
{
struct mlx5_priv *priv = dev->data->dev_private;
int ret;
DRV_LOG(DEBUG, "port %u starting device", dev->data->port_id);
ret = mlx5_txq_start(dev);
if (ret) {
DRV_LOG(ERR, "port %u Tx queue allocation failed: %s",
dev->data->port_id, strerror(rte_errno));
return -rte_errno;
}
ret = mlx5_rxq_start(dev);
if (ret) {
DRV_LOG(ERR, "port %u Rx queue allocation failed: %s",
dev->data->port_id, strerror(rte_errno));
mlx5_txq_stop(dev);
return -rte_errno;
}
ret = mlx5_hairpin_bind(dev);
if (ret) {
DRV_LOG(ERR, "port %u hairpin binding failed: %s",
dev->data->port_id, strerror(rte_errno));
mlx5_txq_stop(dev);
return -rte_errno;
}
dev->data->dev_started = 1;
ret = mlx5_rx_intr_vec_enable(dev);
if (ret) {
DRV_LOG(ERR, "port %u Rx interrupt vector creation failed",
dev->data->port_id);
net/mlx5: fix Rx interrupts management This commit addresses various issues that may lead to undefined behavior when configuring Rx interrupts. While failure to create a Rx queue completion channel in rxq_ctrl_setup() prevents that queue from being created, existing queues still have theirs. Since the error handler disables dev_conf.intr_conf.rxq as well, subsequent calls to rxq_ctrl_setup() create Rx queues without interrupts. This leads to a scenario where not all Rx queues support interrupts; missing checks on the presence of completion channels may crash the application. Considering that the PMD is not supposed to disable user-provided configuration parameters (dev_conf.intr_conf.rxq), and that these can change for subsequent rxq_ctrl_setup() calls anyway, properly supporting a mixed mode where not all Rx queues have interrupts enabled is a better approach. To do so with a minimum set of changes, priv_intr_efd_enable() and priv_create_intr_vec() are first refactored as a single priv_rx_intr_vec_enable() function (same for their "disable" counterparts). Since they had to be used together, there was no point in keeping them separate. Remaining changes: - Always clean up before reconfiguring interrupts to avoid memory leaks. - Always clean up when closing the device. - Use malloc()/free() instead of their rte_*() counterparts since there is no need to store the vector in huge pages-backed memory. - Allow more Rx queues than the size of the event file descriptor array as long as Rx interrupts are not requested on all of them. - Properly clean up interrupt handle when disabling Rx interrupts (nb_efd and intr_vec reset to 0). - Check completion channel presence while toggling Rx interrupts on a given queue. Fixes: 3c7d44af252a ("net/mlx5: support user space Rx interrupt event") Cc: stable@dpdk.org Signed-off-by: Adrien Mazarguil <adrien.mazarguil@6wind.com>
2017-06-14 11:49:17 +00:00
goto error;
}
mlx5_stats_init(dev);
net/mlx5: fix link status behavior This behavior is mixed between what should be handled by the application and what is under PMD responsibility. According to DPDK API: - link_update() should only query the link status [1] - link_set_{up,down}() should only set the link to the according status [1] - dev_{start,stop}() should enable/disable traffic reception/emission [2] On this PMD, the link status is retrieved from the net device associated owned by the Linux Kernel, it does not means that even when this interface is down, the PMD cannot send/receive traffic from the NIC those two information are unrelated, until the physical port is active and has a link, the PMD can receive/send traffic on the wire. According to DPDK API, calling the rte_eth_dev_start() even when the Linux interface link is down is then possible and allowed, as the traffic will flow between the DPDK application and the Physical port. This also means that a synchronization between the Linux interface and the DPDK application remains under the DPDK application responsibility. To handle such synchronization the application should behave as the following scheme, to start: rte_eth_get_link(port_id, &link); if (link.link_status == ETH_DOWN) rte_eth_dev_set_link_up(port_id); rte_eth_dev_start(port_id); Taking in account the possible returned values for each function. and to stop: rte_eth_dev_stop(port_id); rte_eth_dev_set_link_down(port_id); The application should also set the LSC interrupt callbacks to catch and behave accordingly when the administrator set the Linux device down/up. The same callbacks are called when the link on the medium falls/raise. [1] https://dpdk.org/browse/dpdk/tree/lib/librte_ether/rte_ethdev_core.h [2] https://dpdk.org/browse/dpdk/tree/lib/librte_ether/rte_ethdev.h#n1677 Fixes: c7bf62255edf ("net/mlx5: fix handling link status event") Fixes: e313ef4c2fe8 ("net/mlx5: fix link state on device start") Cc: stable@dpdk.org Signed-off-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com> Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com> Acked-by: Yongseok Koh <yskoh@mellanox.com>
2018-03-12 13:43:18 +00:00
ret = mlx5_traffic_enable(dev);
if (ret) {
net/mlx5: fix link status behavior This behavior is mixed between what should be handled by the application and what is under PMD responsibility. According to DPDK API: - link_update() should only query the link status [1] - link_set_{up,down}() should only set the link to the according status [1] - dev_{start,stop}() should enable/disable traffic reception/emission [2] On this PMD, the link status is retrieved from the net device associated owned by the Linux Kernel, it does not means that even when this interface is down, the PMD cannot send/receive traffic from the NIC those two information are unrelated, until the physical port is active and has a link, the PMD can receive/send traffic on the wire. According to DPDK API, calling the rte_eth_dev_start() even when the Linux interface link is down is then possible and allowed, as the traffic will flow between the DPDK application and the Physical port. This also means that a synchronization between the Linux interface and the DPDK application remains under the DPDK application responsibility. To handle such synchronization the application should behave as the following scheme, to start: rte_eth_get_link(port_id, &link); if (link.link_status == ETH_DOWN) rte_eth_dev_set_link_up(port_id); rte_eth_dev_start(port_id); Taking in account the possible returned values for each function. and to stop: rte_eth_dev_stop(port_id); rte_eth_dev_set_link_down(port_id); The application should also set the LSC interrupt callbacks to catch and behave accordingly when the administrator set the Linux device down/up. The same callbacks are called when the link on the medium falls/raise. [1] https://dpdk.org/browse/dpdk/tree/lib/librte_ether/rte_ethdev_core.h [2] https://dpdk.org/browse/dpdk/tree/lib/librte_ether/rte_ethdev.h#n1677 Fixes: c7bf62255edf ("net/mlx5: fix handling link status event") Fixes: e313ef4c2fe8 ("net/mlx5: fix link state on device start") Cc: stable@dpdk.org Signed-off-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com> Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com> Acked-by: Yongseok Koh <yskoh@mellanox.com>
2018-03-12 13:43:18 +00:00
DRV_LOG(DEBUG, "port %u failed to set defaults flows",
dev->data->port_id);
goto error;
}
net/mlx5: fix link status behavior This behavior is mixed between what should be handled by the application and what is under PMD responsibility. According to DPDK API: - link_update() should only query the link status [1] - link_set_{up,down}() should only set the link to the according status [1] - dev_{start,stop}() should enable/disable traffic reception/emission [2] On this PMD, the link status is retrieved from the net device associated owned by the Linux Kernel, it does not means that even when this interface is down, the PMD cannot send/receive traffic from the NIC those two information are unrelated, until the physical port is active and has a link, the PMD can receive/send traffic on the wire. According to DPDK API, calling the rte_eth_dev_start() even when the Linux interface link is down is then possible and allowed, as the traffic will flow between the DPDK application and the Physical port. This also means that a synchronization between the Linux interface and the DPDK application remains under the DPDK application responsibility. To handle such synchronization the application should behave as the following scheme, to start: rte_eth_get_link(port_id, &link); if (link.link_status == ETH_DOWN) rte_eth_dev_set_link_up(port_id); rte_eth_dev_start(port_id); Taking in account the possible returned values for each function. and to stop: rte_eth_dev_stop(port_id); rte_eth_dev_set_link_down(port_id); The application should also set the LSC interrupt callbacks to catch and behave accordingly when the administrator set the Linux device down/up. The same callbacks are called when the link on the medium falls/raise. [1] https://dpdk.org/browse/dpdk/tree/lib/librte_ether/rte_ethdev_core.h [2] https://dpdk.org/browse/dpdk/tree/lib/librte_ether/rte_ethdev.h#n1677 Fixes: c7bf62255edf ("net/mlx5: fix handling link status event") Fixes: e313ef4c2fe8 ("net/mlx5: fix link state on device start") Cc: stable@dpdk.org Signed-off-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com> Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com> Acked-by: Yongseok Koh <yskoh@mellanox.com>
2018-03-12 13:43:18 +00:00
ret = mlx5_flow_start(dev, &priv->flows);
if (ret) {
DRV_LOG(DEBUG, "port %u failed to set flows",
dev->data->port_id);
goto error;
}
rte_wmb();
net/mlx5: fix link status behavior This behavior is mixed between what should be handled by the application and what is under PMD responsibility. According to DPDK API: - link_update() should only query the link status [1] - link_set_{up,down}() should only set the link to the according status [1] - dev_{start,stop}() should enable/disable traffic reception/emission [2] On this PMD, the link status is retrieved from the net device associated owned by the Linux Kernel, it does not means that even when this interface is down, the PMD cannot send/receive traffic from the NIC those two information are unrelated, until the physical port is active and has a link, the PMD can receive/send traffic on the wire. According to DPDK API, calling the rte_eth_dev_start() even when the Linux interface link is down is then possible and allowed, as the traffic will flow between the DPDK application and the Physical port. This also means that a synchronization between the Linux interface and the DPDK application remains under the DPDK application responsibility. To handle such synchronization the application should behave as the following scheme, to start: rte_eth_get_link(port_id, &link); if (link.link_status == ETH_DOWN) rte_eth_dev_set_link_up(port_id); rte_eth_dev_start(port_id); Taking in account the possible returned values for each function. and to stop: rte_eth_dev_stop(port_id); rte_eth_dev_set_link_down(port_id); The application should also set the LSC interrupt callbacks to catch and behave accordingly when the administrator set the Linux device down/up. The same callbacks are called when the link on the medium falls/raise. [1] https://dpdk.org/browse/dpdk/tree/lib/librte_ether/rte_ethdev_core.h [2] https://dpdk.org/browse/dpdk/tree/lib/librte_ether/rte_ethdev.h#n1677 Fixes: c7bf62255edf ("net/mlx5: fix handling link status event") Fixes: e313ef4c2fe8 ("net/mlx5: fix link state on device start") Cc: stable@dpdk.org Signed-off-by: Nelio Laranjeiro <nelio.laranjeiro@6wind.com> Acked-by: Adrien Mazarguil <adrien.mazarguil@6wind.com> Acked-by: Yongseok Koh <yskoh@mellanox.com>
2018-03-12 13:43:18 +00:00
dev->tx_pkt_burst = mlx5_select_tx_function(dev);
dev->rx_pkt_burst = mlx5_select_rx_function(dev);
/* Enable datapath on secondary process. */
mlx5_mp_req_start_rxtx(dev);
mlx5_dev_interrupt_handler_install(dev);
return 0;
error:
ret = rte_errno; /* Save rte_errno before cleanup. */
/* Rollback. */
dev->data->dev_started = 0;
mlx5_flow_stop(dev, &priv->flows);
mlx5_traffic_disable(dev);
mlx5_txq_stop(dev);
mlx5_rxq_stop(dev);
rte_errno = ret; /* Restore rte_errno. */
return -rte_errno;
}
/**
* DPDK callback to stop the device.
*
* Simulate device stop by detaching all configured flows.
*
* @param dev
* Pointer to Ethernet device structure.
*/
void
mlx5_dev_stop(struct rte_eth_dev *dev)
{
struct mlx5_priv *priv = dev->data->dev_private;
dev->data->dev_started = 0;
/* Prevent crashes when queues are still in use. */
dev->rx_pkt_burst = removed_rx_burst;
dev->tx_pkt_burst = removed_tx_burst;
rte_wmb();
/* Disable datapath on secondary process. */
mlx5_mp_req_stop_rxtx(dev);
usleep(1000 * priv->rxqs_n);
DRV_LOG(DEBUG, "port %u stopping device", dev->data->port_id);
mlx5_flow_stop(dev, &priv->flows);
mlx5_traffic_disable(dev);
mlx5_rx_intr_vec_disable(dev);
mlx5_dev_interrupt_handler_uninstall(dev);
mlx5_txq_stop(dev);
mlx5_rxq_stop(dev);
}
/**
* Enable traffic flows configured by control plane
*
* @param dev
* Pointer to Ethernet device private data.
* @param dev
* Pointer to Ethernet device structure.
*
* @return
* 0 on success, a negative errno value otherwise and rte_errno is set.
*/
int
mlx5_traffic_enable(struct rte_eth_dev *dev)
{
struct mlx5_priv *priv = dev->data->dev_private;
struct rte_flow_item_eth bcast = {
.dst.addr_bytes = "\xff\xff\xff\xff\xff\xff",
};
struct rte_flow_item_eth ipv6_multi_spec = {
.dst.addr_bytes = "\x33\x33\x00\x00\x00\x00",
};
struct rte_flow_item_eth ipv6_multi_mask = {
.dst.addr_bytes = "\xff\xff\x00\x00\x00\x00",
};
struct rte_flow_item_eth unicast = {
.src.addr_bytes = "\x00\x00\x00\x00\x00\x00",
};
struct rte_flow_item_eth unicast_mask = {
.dst.addr_bytes = "\xff\xff\xff\xff\xff\xff",
};
const unsigned int vlan_filter_n = priv->vlan_filter_n;
const struct rte_ether_addr cmp = {
.addr_bytes = "\x00\x00\x00\x00\x00\x00",
};
unsigned int i;
unsigned int j;
int ret;
if (priv->config.dv_esw_en && !priv->config.vf)
if (!mlx5_flow_create_esw_table_zero_flow(dev))
goto error;
if (priv->isolated)
return 0;
if (dev->data->promiscuous) {
struct rte_flow_item_eth promisc = {
.dst.addr_bytes = "\x00\x00\x00\x00\x00\x00",
.src.addr_bytes = "\x00\x00\x00\x00\x00\x00",
.type = 0,
};
ret = mlx5_ctrl_flow(dev, &promisc, &promisc);
if (ret)
goto error;
}
if (dev->data->all_multicast) {
struct rte_flow_item_eth multicast = {
.dst.addr_bytes = "\x01\x00\x00\x00\x00\x00",
.src.addr_bytes = "\x00\x00\x00\x00\x00\x00",
.type = 0,
};
ret = mlx5_ctrl_flow(dev, &multicast, &multicast);
if (ret)
goto error;
} else {
/* Add broadcast/multicast flows. */
for (i = 0; i != vlan_filter_n; ++i) {
uint16_t vlan = priv->vlan_filter[i];
struct rte_flow_item_vlan vlan_spec = {
.tci = rte_cpu_to_be_16(vlan),
};
struct rte_flow_item_vlan vlan_mask =
rte_flow_item_vlan_mask;
ret = mlx5_ctrl_flow_vlan(dev, &bcast, &bcast,
&vlan_spec, &vlan_mask);
if (ret)
goto error;
ret = mlx5_ctrl_flow_vlan(dev, &ipv6_multi_spec,
&ipv6_multi_mask,
&vlan_spec, &vlan_mask);
if (ret)
goto error;
}
if (!vlan_filter_n) {
ret = mlx5_ctrl_flow(dev, &bcast, &bcast);
if (ret)
goto error;
ret = mlx5_ctrl_flow(dev, &ipv6_multi_spec,
&ipv6_multi_mask);
if (ret)
goto error;
}
}
/* Add MAC address flows. */
for (i = 0; i != MLX5_MAX_MAC_ADDRESSES; ++i) {
struct rte_ether_addr *mac = &dev->data->mac_addrs[i];
if (!memcmp(mac, &cmp, sizeof(*mac)))
continue;
memcpy(&unicast.dst.addr_bytes,
mac->addr_bytes,
net: add rte prefix to ether defines Add 'RTE_' prefix to defines: - rename ETHER_ADDR_LEN as RTE_ETHER_ADDR_LEN. - rename ETHER_TYPE_LEN as RTE_ETHER_TYPE_LEN. - rename ETHER_CRC_LEN as RTE_ETHER_CRC_LEN. - rename ETHER_HDR_LEN as RTE_ETHER_HDR_LEN. - rename ETHER_MIN_LEN as RTE_ETHER_MIN_LEN. - rename ETHER_MAX_LEN as RTE_ETHER_MAX_LEN. - rename ETHER_MTU as RTE_ETHER_MTU. - rename ETHER_MAX_VLAN_FRAME_LEN as RTE_ETHER_MAX_VLAN_FRAME_LEN. - rename ETHER_MAX_VLAN_ID as RTE_ETHER_MAX_VLAN_ID. - rename ETHER_MAX_JUMBO_FRAME_LEN as RTE_ETHER_MAX_JUMBO_FRAME_LEN. - rename ETHER_MIN_MTU as RTE_ETHER_MIN_MTU. - rename ETHER_LOCAL_ADMIN_ADDR as RTE_ETHER_LOCAL_ADMIN_ADDR. - rename ETHER_GROUP_ADDR as RTE_ETHER_GROUP_ADDR. - rename ETHER_TYPE_IPv4 as RTE_ETHER_TYPE_IPv4. - rename ETHER_TYPE_IPv6 as RTE_ETHER_TYPE_IPv6. - rename ETHER_TYPE_ARP as RTE_ETHER_TYPE_ARP. - rename ETHER_TYPE_VLAN as RTE_ETHER_TYPE_VLAN. - rename ETHER_TYPE_RARP as RTE_ETHER_TYPE_RARP. - rename ETHER_TYPE_QINQ as RTE_ETHER_TYPE_QINQ. - rename ETHER_TYPE_ETAG as RTE_ETHER_TYPE_ETAG. - rename ETHER_TYPE_1588 as RTE_ETHER_TYPE_1588. - rename ETHER_TYPE_SLOW as RTE_ETHER_TYPE_SLOW. - rename ETHER_TYPE_TEB as RTE_ETHER_TYPE_TEB. - rename ETHER_TYPE_LLDP as RTE_ETHER_TYPE_LLDP. - rename ETHER_TYPE_MPLS as RTE_ETHER_TYPE_MPLS. - rename ETHER_TYPE_MPLSM as RTE_ETHER_TYPE_MPLSM. - rename ETHER_VXLAN_HLEN as RTE_ETHER_VXLAN_HLEN. - rename ETHER_ADDR_FMT_SIZE as RTE_ETHER_ADDR_FMT_SIZE. - rename VXLAN_GPE_TYPE_IPV4 as RTE_VXLAN_GPE_TYPE_IPV4. - rename VXLAN_GPE_TYPE_IPV6 as RTE_VXLAN_GPE_TYPE_IPV6. - rename VXLAN_GPE_TYPE_ETH as RTE_VXLAN_GPE_TYPE_ETH. - rename VXLAN_GPE_TYPE_NSH as RTE_VXLAN_GPE_TYPE_NSH. - rename VXLAN_GPE_TYPE_MPLS as RTE_VXLAN_GPE_TYPE_MPLS. - rename VXLAN_GPE_TYPE_GBP as RTE_VXLAN_GPE_TYPE_GBP. - rename VXLAN_GPE_TYPE_VBNG as RTE_VXLAN_GPE_TYPE_VBNG. - rename ETHER_VXLAN_GPE_HLEN as RTE_ETHER_VXLAN_GPE_HLEN. Do not update the command line library to avoid adding a dependency to librte_net. Signed-off-by: Olivier Matz <olivier.matz@6wind.com> Reviewed-by: Stephen Hemminger <stephen@networkplumber.org> Reviewed-by: Maxime Coquelin <maxime.coquelin@redhat.com> Reviewed-by: Ferruh Yigit <ferruh.yigit@intel.com>
2019-05-21 16:13:05 +00:00
RTE_ETHER_ADDR_LEN);
for (j = 0; j != vlan_filter_n; ++j) {
uint16_t vlan = priv->vlan_filter[j];
struct rte_flow_item_vlan vlan_spec = {
.tci = rte_cpu_to_be_16(vlan),
};
struct rte_flow_item_vlan vlan_mask =
rte_flow_item_vlan_mask;
ret = mlx5_ctrl_flow_vlan(dev, &unicast,
&unicast_mask,
&vlan_spec,
&vlan_mask);
if (ret)
goto error;
}
if (!vlan_filter_n) {
ret = mlx5_ctrl_flow(dev, &unicast, &unicast_mask);
if (ret)
goto error;
}
}
return 0;
error:
ret = rte_errno; /* Save rte_errno before cleanup. */
mlx5_flow_list_flush(dev, &priv->ctrl_flows);
rte_errno = ret; /* Restore rte_errno. */
return -rte_errno;
}
/**
* Disable traffic flows configured by control plane
*
* @param dev
* Pointer to Ethernet device private data.
*/
void
mlx5_traffic_disable(struct rte_eth_dev *dev)
{
struct mlx5_priv *priv = dev->data->dev_private;
mlx5_flow_list_flush(dev, &priv->ctrl_flows);
}
/**
* Restart traffic flows configured by control plane
*
* @param dev
* Pointer to Ethernet device private data.
*
* @return
* 0 on success, a negative errno value otherwise and rte_errno is set.
*/
int
mlx5_traffic_restart(struct rte_eth_dev *dev)
{
if (dev->data->dev_started) {
mlx5_traffic_disable(dev);
return mlx5_traffic_enable(dev);
}
return 0;
}