Hi Jesper,
Thanks for taking care of the drop RQ.
In general, mlx5 part looks ok to me.
Find a few comments below. Mostly pointing out some typos.
On 13/12/2017 1:19 PM, Jesper Dangaard Brouer wrote:
The mlx5 driver have a special drop-RQ queue (one per interface) that
simply drops all incoming traffic. It helps driver keep other HW
objects (flow steering) alive upon down/up operations. It is
temporarily pointed by flow steering objects during the interface
setup, and when interface is down. It lacks many fields that are set
in a regular RQ (for example its state is never switched to
MLX5_RQC_STATE_RDY). (Thanks to Tariq Toukan for explaination).
typo: explanation
The XDP RX-queue info API is extended with a queue-type, and mlx5 uses
this kind of drop/sink-type (RXQ_TYPE_SINK) for this kind of sink queue.
Driver hook points for xdp_rxq_info:
* init+reg: mlx5e_alloc_rq()
* init+reg: mlx5e_alloc_drop_rq()
* unreg : mlx5e_free_rq()
Tested on actual hardware with samples/bpf program
Cc: Saeed Mahameed <sae...@mellanox.com>
Cc: Matan Barak <mat...@mellanox.com>
Cc: Tariq Toukan <tar...@mellanox.com>
Signed-off-by: Jesper Dangaard Brouer <bro...@redhat.com>
---
drivers/net/ethernet/mellanox/mlx5/core/en.h | 4 ++++
drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 14 +++++++++++++
drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 1 +
include/net/xdp.h | 23 +++++++++++++++++++++
net/core/xdp.c | 6 +++++
5 files changed, 48 insertions(+)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h
b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index c0872b3284cb..fe10a042783b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -46,6 +46,7 @@
#include <linux/mlx5/transobj.h>
#include <linux/rhashtable.h>
#include <net/switchdev.h>
+#include <net/xdp.h>
#include "wq.h"
#include "mlx5_core.h"
#include "en_stats.h"
@@ -568,6 +569,9 @@ struct mlx5e_rq {
u32 rqn;
struct mlx5_core_dev *mdev;
struct mlx5_core_mkey umr_mkey;
+
+ /* XDP read-mostly */
+ struct xdp_rxq_info xdp_rxq;
} ____cacheline_aligned_in_smp;
struct mlx5e_channel {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 0f5c012de52e..ea44b5f25e11 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -582,6 +582,12 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
rq->ix = c->ix;
rq->mdev = mdev;
+ /* XDP RX-queue info */
+ xdp_rxq_info_init(&rq->xdp_rxq);
+ rq->xdp_rxq.dev = rq->netdev;
+ rq->xdp_rxq.queue_index = rq->ix;
+ xdp_rxq_info_reg(&rq->xdp_rxq);
+
You don't set type here. This is ok as long as the following hold:
1) RXQ_TYPE_DEFAULT is zero
2) xdp_rxq is zalloc'ed.
rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL;
if (IS_ERR(rq->xdp_prog)) {
err = PTR_ERR(rq->xdp_prog);
@@ -695,6 +701,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
err_rq_wq_destroy:
if (rq->xdp_prog)
bpf_prog_put(rq->xdp_prog);
+ xdp_rxq_info_unreg(&rq->xdp_rxq);
mlx5_wq_destroy(&rq->wq_ctrl);
return err;
@@ -707,6 +714,8 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq)
if (rq->xdp_prog)
bpf_prog_put(rq->xdp_prog);
+ xdp_rxq_info_unreg(&rq->xdp_rxq);
+
switch (rq->wq_type) {
case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
mlx5e_rq_free_mpwqe_info(rq);
@@ -2768,6 +2777,11 @@ static int mlx5e_alloc_drop_rq(struct mlx5_core_dev
*mdev,
if (err)
return err;
+ /* XDP RX-queue info for "Drop-RQ", packets never reach XDP */
+ xdp_rxq_info_init(&rq->xdp_rxq);
+ xdp_rxq_info_type(&rq->xdp_rxq, RXQ_TYPE_SINK);
+ xdp_rxq_info_reg(&rq->xdp_rxq);
+
rq->mdev = mdev;
return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 5b499c7a698f..7b38480811d4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -812,6 +812,7 @@ static inline int mlx5e_xdp_handle(struct mlx5e_rq *rq,
xdp_set_data_meta_invalid(&xdp);
xdp.data_end = xdp.data + *len;
xdp.data_hard_start = va;
+ xdp.rxq = &rq->xdp_rxq;
act = bpf_prog_run_xdp(prog, &xdp);
switch (act) {
diff --git a/include/net/xdp.h b/include/net/xdp.h
index e4acd198fd60..5be560d943e1 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -36,10 +36,33 @@ struct xdp_rxq_info {
struct net_device *dev;
u32 queue_index;
u32 reg_state;
+ u32 qtype;
} ____cacheline_aligned; /* perf critical, avoid false-sharing */
void xdp_rxq_info_init(struct xdp_rxq_info *xdp_rxq);
void xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq);
void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq);
+/**
+ * DOC: XDP RX-queue type
+ *
+ * The XDP RX-queue info can have associated a type.
+ *
+ * @RXQ_TYPE_DEFAULT: default no specifik queue type need to be specified
typo: specific
+ *
+ * @RXQ_TYPE_SINK: indicate a fake queue that never reach XDP RX
+ * code. Some drivers have a need to maintain a lower layer
+ * RX-queue as a sink queue, while reconfiguring other RX-queues.
+ */
+#define RXQ_TYPE_DEFAULT 0
+#define RXQ_TYPE_SINK 1
+#define RXQ_TYPE_MAX RXQ_TYPE_SINK
Definitions of incremental numbers, enum might be best here, you can
give them some enum type and use it in xdp_rxq_info->qtype.
+
+static inline
+void xdp_rxq_info_type(struct xdp_rxq_info *xdp_rxq, u32 qtype)
+{
+ BUILD_BUG_ON(qtype > RXQ_TYPE_MAX);
+ xdp_rxq->qtype = qtype;
+}
+
#endif /* __LINUX_NET_XDP_H__ */
diff --git a/net/core/xdp.c b/net/core/xdp.c
index a9d2dd7b1ede..2a111f5987f6 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -32,8 +32,14 @@ EXPORT_SYMBOL_GPL(xdp_rxq_info_init);
void xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq)
{
+ if (xdp_rxq->qtype == RXQ_TYPE_SINK)
+ goto skip_content_check;
+
+ /* Check information setup by driver code */
WARN(!xdp_rxq->dev, "Missing net_device from driver");
WARN(xdp_rxq->queue_index == U32_MAX, "Miss queue_index from driver");
+
+skip_content_check:
WARN(!(xdp_rxq->reg_state == REG_STATE_NEW),"API violation, miss init");
xdp_rxq->reg_state = REG_STATE_REGISTRED;
typo: REGISTERED (introduced in a previous patch)
}
