| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <1757499891-596641-6-git-send-email-tariqt@nvidia.com>
Date: Wed, 10 Sep 2025 13:24:46 +0300
From: Tariq Toukan <tariqt@...dia.com>
To: Eric Dumazet <edumazet@...gle.com>, Jakub Kicinski <kuba@...nel.org>,
Paolo Abeni <pabeni@...hat.com>, Andrew Lunn <andrew+netdev@...n.ch>, "David
S. Miller" <davem@...emloft.net>
CC: Jiri Pirko <jiri@...nulli.us>, Jonathan Corbet <corbet@....net>, "Leon
Romanovsky" <leon@...nel.org>, Jason Gunthorpe <jgg@...pe.ca>, Saeed Mahameed
<saeedm@...dia.com>, Tariq Toukan <tariqt@...dia.com>, Mark Bloch
<mbloch@...dia.com>, Alexei Starovoitov <ast@...nel.org>, Daniel Borkmann
<daniel@...earbox.net>, Jesper Dangaard Brouer <hawk@...nel.org>, "John
Fastabend" <john.fastabend@...il.com>, <netdev@...r.kernel.org>,
<linux-doc@...r.kernel.org>, <linux-kernel@...r.kernel.org>,
<linux-rdma@...r.kernel.org>, <bpf@...r.kernel.org>, Gal Pressman
<gal@...dia.com>, Cosmin Ratiu <cratiu@...dia.com>, Dragos Tatulea
<dtatulea@...dia.com>, Jiri Pirko <jiri@...dia.com>
Subject: [PATCH net-next 05/10] net/mlx5e: Prepare for using multiple TX doorbells
From: Cosmin Ratiu <cratiu@...dia.com>
The driver allocates a single doorbell per device and uses
it for all Send Queues (SQs). This can become a bottleneck due to the
high number of concurrent MMIO accesses when ringing the same doorbell
from many channels.
This patch makes the doorbells used by channel queues configurable.
mlx5e_channel_pick_doorbell() is added to select the doorbell to be used
for a given channel, picking the default for now.
When opening a channel, the selected doorbell is saved to the channel
struct and used whenever channel-related queues are created.
Finally, 'uar_page' is added to 'struct mlx5e_create_sq_param' to
control which doorbell to use when allocating an SQ, since that can
happen outside channel context (e.g. for PTP).
Signed-off-by: Cosmin Ratiu <cratiu@...dia.com>
Reviewed-by: Dragos Tatulea <dtatulea@...dia.com>
Signed-off-by: Tariq Toukan <tariqt@...dia.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 1 +
.../ethernet/mellanox/mlx5/core/en/params.h | 1 +
.../net/ethernet/mellanox/mlx5/core/en/ptp.c | 4 +++-
.../net/ethernet/mellanox/mlx5/core/en/ptp.h | 1 +
.../net/ethernet/mellanox/mlx5/core/en_main.c | 18 ++++++++++++++----
5 files changed, 20 insertions(+), 5 deletions(-)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 0dd3bc0f4caa..9c73165653bf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -788,6 +788,7 @@ struct mlx5e_channel {
int vec_ix;
int sd_ix;
int cpu;
+ struct mlx5_sq_bfreg *bfreg;
/* Sync between icosq recovery and XSK enable/disable. */
struct mutex icosq_recovery_lock;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
index e3edf79dde5f..00617c65fe3c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
@@ -51,6 +51,7 @@ struct mlx5e_create_sq_param {
u32 tisn;
u8 tis_lst_sz;
u8 min_inline_mode;
+ u32 uar_page;
};
/* Striding RQ dynamic parameters */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index 7c1d9a9ea464..a392578a063c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -334,7 +334,7 @@ static int mlx5e_ptp_alloc_txqsq(struct mlx5e_ptp *c, int txq_ix,
sq->mdev = mdev;
sq->ch_ix = MLX5E_PTP_CHANNEL_IX;
sq->txq_ix = txq_ix;
- sq->uar_map = mdev->priv.bfreg.map;
+ sq->uar_map = c->bfreg->map;
sq->min_inline_mode = params->tx_min_inline_mode;
sq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
sq->stats = &c->priv->ptp_stats.sq[tc];
@@ -486,6 +486,7 @@ static int mlx5e_ptp_open_txqsq(struct mlx5e_ptp *c, u32 tisn,
csp.wq_ctrl = &txqsq->wq_ctrl;
csp.min_inline_mode = txqsq->min_inline_mode;
csp.ts_cqe_to_dest_cqn = ptpsq->ts_cq.mcq.cqn;
+ csp.uar_page = c->bfreg->index;
err = mlx5e_create_sq_rdy(c->mdev, sqp, &csp, 0, &txqsq->sqn);
if (err)
@@ -900,6 +901,7 @@ int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params,
c->num_tc = mlx5e_get_dcb_num_tc(params);
c->stats = &priv->ptp_stats.ch;
c->lag_port = lag_port;
+ c->bfreg = &mdev->priv.bfreg;
err = mlx5e_ptp_set_state(c, params);
if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
index 883c044852f1..1b3c9648220b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
@@ -66,6 +66,7 @@ struct mlx5e_ptp {
struct mlx5_core_dev *mdev;
struct hwtstamp_config *tstamp;
DECLARE_BITMAP(state, MLX5E_PTP_STATE_NUM_STATES);
+ struct mlx5_sq_bfreg *bfreg;
};
static inline bool mlx5e_use_ptpsq(struct sk_buff *skb)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 02a538ec2ecb..0425f0e3d3a0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1532,7 +1532,7 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
sq->pdev = c->pdev;
sq->mkey_be = c->mkey_be;
sq->channel = c;
- sq->uar_map = mdev->priv.bfreg.map;
+ sq->uar_map = c->bfreg->map;
sq->min_inline_mode = params->tx_min_inline_mode;
sq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu) - ETH_FCS_LEN;
sq->xsk_pool = xsk_pool;
@@ -1617,7 +1617,7 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
int err;
sq->channel = c;
- sq->uar_map = mdev->priv.bfreg.map;
+ sq->uar_map = c->bfreg->map;
sq->reserved_room = param->stop_room;
param->wq.db_numa_node = cpu_to_node(c->cpu);
@@ -1702,7 +1702,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
sq->priv = c->priv;
sq->ch_ix = c->ix;
sq->txq_ix = txq_ix;
- sq->uar_map = mdev->priv.bfreg.map;
+ sq->uar_map = c->bfreg->map;
sq->min_inline_mode = params->tx_min_inline_mode;
sq->hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
sq->max_sq_mpw_wqebbs = mlx5e_get_max_sq_aligned_wqebbs(mdev);
@@ -1778,7 +1778,7 @@ static int mlx5e_create_sq(struct mlx5_core_dev *mdev,
MLX5_SET(sqc, sqc, flush_in_error_en, 1);
MLX5_SET(wq, wq, wq_type, MLX5_WQ_TYPE_CYCLIC);
- MLX5_SET(wq, wq, uar_page, mdev->priv.bfreg.index);
+ MLX5_SET(wq, wq, uar_page, csp->uar_page);
MLX5_SET(wq, wq, log_wq_pg_sz, csp->wq_ctrl->buf.page_shift -
MLX5_ADAPTER_PAGE_SHIFT);
MLX5_SET64(wq, wq, dbr_addr, csp->wq_ctrl->db.dma);
@@ -1882,6 +1882,7 @@ int mlx5e_open_txqsq(struct mlx5e_channel *c, u32 tisn, int txq_ix,
csp.cqn = sq->cq.mcq.cqn;
csp.wq_ctrl = &sq->wq_ctrl;
csp.min_inline_mode = sq->min_inline_mode;
+ csp.uar_page = c->bfreg->index;
err = mlx5e_create_sq_rdy(c->mdev, param, &csp, qos_queue_group_id, &sq->sqn);
if (err)
goto err_free_txqsq;
@@ -2052,6 +2053,7 @@ static int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params
csp.cqn = sq->cq.mcq.cqn;
csp.wq_ctrl = &sq->wq_ctrl;
csp.min_inline_mode = params->tx_min_inline_mode;
+ csp.uar_page = c->bfreg->index;
err = mlx5e_create_sq_rdy(c->mdev, param, &csp, 0, &sq->sqn);
if (err)
goto err_free_icosq;
@@ -2112,6 +2114,7 @@ int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params,
csp.cqn = sq->cq.mcq.cqn;
csp.wq_ctrl = &sq->wq_ctrl;
csp.min_inline_mode = sq->min_inline_mode;
+ csp.uar_page = c->bfreg->index;
set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
err = mlx5e_create_sq_rdy(c->mdev, param, &csp, 0, &sq->sqn);
@@ -2740,6 +2743,11 @@ void mlx5e_trigger_napi_sched(struct napi_struct *napi)
local_bh_enable();
}
+static void mlx5e_channel_pick_doorbell(struct mlx5e_channel *c)
+{
+ c->bfreg = &c->mdev->priv.bfreg;
+}
+
static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
struct mlx5e_params *params,
struct xsk_buff_pool *xsk_pool,
@@ -2794,6 +2802,8 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
c->aff_mask = irq_get_effective_affinity_mask(irq);
c->lag_port = mlx5e_enumerate_lag_port(mdev, ix);
+ mlx5e_channel_pick_doorbell(c);
+
netif_napi_add_config_locked(netdev, &c->napi, mlx5e_napi_poll, ix);
netif_napi_set_irq_locked(&c->napi, irq);
--
2.31.1
Powered by blists - more mailing lists