From: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
To: dev@dpdk.org
Cc: matan@mellanox.com, rasland@mellanox.com
Subject: [dpdk-dev] [PATCH 01/12] net/mlx5: move backing PCI device to private context
Date: Wed, 25 Sep 2019 07:53:24 +0000 [thread overview]
Message-ID: <1569398015-6027-2-git-send-email-viacheslavo@mellanox.com> (raw)
In-Reply-To: <1569398015-6027-1-git-send-email-viacheslavo@mellanox.com>
Now all devices created over the same multiport IB device
have shared context containing the backing PCI device field.
For the VF LAG configurations it becomes possible the
representors might be connected to VF created over different
PFs. In this case representors have the different backing
PCI devices and mentioned field should be moved to device
private area.
Signed-off-by: Viacheslav Ovsiienko <viacheslavo@mellanox.com>
---
drivers/net/mlx5/mlx5.c | 4 ++--
drivers/net/mlx5/mlx5.h | 2 +-
drivers/net/mlx5/mlx5_txq.c | 2 +-
3 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c
index 5088a97..b4096a4 100644
--- a/drivers/net/mlx5/mlx5.c
+++ b/drivers/net/mlx5/mlx5.c
@@ -373,7 +373,6 @@ struct mlx5_dev_spawn_data {
sizeof(sh->ibdev_name));
strncpy(sh->ibdev_path, sh->ctx->device->ibdev_path,
sizeof(sh->ibdev_path));
- sh->pci_dev = spawn->pci_dev;
pthread_mutex_init(&sh->intr_mutex, NULL);
/*
* Setting port_id to max unallowed value means
@@ -406,7 +405,7 @@ struct mlx5_dev_spawn_data {
*/
err = mlx5_mr_btree_init(&sh->mr.cache,
MLX5_MR_BTREE_CACHE_N * 2,
- sh->pci_dev->device.numa_node);
+ spawn->pci_dev->device.numa_node);
if (err) {
err = rte_errno;
goto error;
@@ -1756,6 +1755,7 @@ struct mlx5_dev_spawn_data {
}
priv->sh = sh;
priv->ibv_port = spawn->ibv_port;
+ priv->pci_dev = spawn->pci_dev;
priv->mtu = RTE_ETHER_MTU;
#ifndef RTE_ARCH_64
/* Initialize UAR access locks for 32bit implementations. */
diff --git a/drivers/net/mlx5/mlx5.h b/drivers/net/mlx5/mlx5.h
index 5482eb7..f45d627 100644
--- a/drivers/net/mlx5/mlx5.h
+++ b/drivers/net/mlx5/mlx5.h
@@ -547,7 +547,6 @@ struct mlx5_ibv_shared {
char ibdev_name[IBV_SYSFS_NAME_MAX]; /* IB device name. */
char ibdev_path[IBV_SYSFS_PATH_MAX]; /* IB device path for secondary */
struct ibv_device_attr_ex device_attr; /* Device properties. */
- struct rte_pci_device *pci_dev; /* Backend PCI device. */
LIST_ENTRY(mlx5_ibv_shared) mem_event_cb;
/**< Called by memory event callback. */
struct {
@@ -606,6 +605,7 @@ struct mlx5_priv {
struct rte_eth_dev_data *dev_data; /* Pointer to device data. */
struct mlx5_ibv_shared *sh; /* Shared IB device context. */
uint32_t ibv_port; /* IB device port number. */
+ struct rte_pci_device *pci_dev; /* Backend PCI device. */
struct rte_ether_addr mac[MLX5_MAX_MAC_ADDRESSES]; /* MAC addresses. */
BITFIELD_DECLARE(mac_own, uint64_t, MLX5_MAX_MAC_ADDRESSES);
/* Bit-field of MAC addresses owned by the PMD. */
diff --git a/drivers/net/mlx5/mlx5_txq.c b/drivers/net/mlx5/mlx5_txq.c
index 2b7d6c0..d9fd143 100644
--- a/drivers/net/mlx5/mlx5_txq.c
+++ b/drivers/net/mlx5/mlx5_txq.c
@@ -728,7 +728,7 @@ struct mlx5_txq_ibv *
if (config->txqs_inline == MLX5_ARG_UNSET)
txqs_inline =
#if defined(RTE_ARCH_ARM64)
- (priv->sh->pci_dev->id.device_id ==
+ (priv->pci_dev->id.device_id ==
PCI_DEVICE_ID_MELLANOX_CONNECTX5BF) ?
MLX5_INLINE_MAX_TXQS_BLUEFIELD :
#endif
--
1.8.3.1
next prev parent reply other threads:[~2019-09-25 7:53 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-09-25 7:53 [dpdk-dev] [PATCH 00/12] net/mlx5: add bonding configuration support Viacheslav Ovsiienko
2019-09-25 7:53 ` Viacheslav Ovsiienko [this message]
2019-09-25 7:53 ` [dpdk-dev] [PATCH 02/12] net/mlx5: update PCI address retrieving routine Viacheslav Ovsiienko
2019-09-25 7:53 ` [dpdk-dev] [PATCH 03/12] net/mlx5: allocate device list explicitly Viacheslav Ovsiienko
2019-09-25 7:53 ` [dpdk-dev] [PATCH 04/12] net/mlx5: add VF LAG mode bonding device recognition Viacheslav Ovsiienko
2019-09-30 10:34 ` Ferruh Yigit
2019-10-01 9:02 ` Slava Ovsiienko
2019-09-25 7:53 ` [dpdk-dev] [PATCH 05/12] net/mlx5: generate bonding device name Viacheslav Ovsiienko
2019-09-25 7:53 ` [dpdk-dev] [PATCH 06/12] net/mlx5: check the kernel support for VF LAG bonding Viacheslav Ovsiienko
2019-09-25 7:53 ` [dpdk-dev] [PATCH 07/12] net/mlx5: query vport index match mode and parameters Viacheslav Ovsiienko
2019-09-25 7:53 ` [dpdk-dev] [PATCH 08/12] net/mlx5: elaborate E-Switch port parameters query Viacheslav Ovsiienko
2019-09-25 7:53 ` [dpdk-dev] [PATCH 09/12] net/mlx5: update source and destination vport translations Viacheslav Ovsiienko
2019-09-25 7:53 ` [dpdk-dev] [PATCH 10/12] net/mlx5: extend switch domain searching range Viacheslav Ovsiienko
2019-09-25 7:53 ` [dpdk-dev] [PATCH 11/12] net/mlx5: update switch port ID in bonding configuration Viacheslav Ovsiienko
2019-09-25 7:53 ` [dpdk-dev] [PATCH 12/12] net/mlx5: check sibling device configurations mismatch Viacheslav Ovsiienko
2019-09-25 10:29 ` [dpdk-dev] [PATCH 00/12] net/mlx5: add bonding configuration support Matan Azrad
2019-09-29 11:47 ` Raslan Darawsheh
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1569398015-6027-2-git-send-email-viacheslavo@mellanox.com \
--to=viacheslavo@mellanox.com \
--cc=dev@dpdk.org \
--cc=matan@mellanox.com \
--cc=rasland@mellanox.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).