* [PATCH rdma-next 0/2] Allocate the per-port Q counter
@ 2018-12-09 10:52 Leon Romanovsky
2018-12-09 10:52 ` [PATCH mlx5-next 1/2] net/mlx5: Add shared Q counter bits Leon Romanovsky
` (3 more replies)
0 siblings, 4 replies; 6+ messages in thread
From: Leon Romanovsky @ 2018-12-09 10:52 UTC (permalink / raw)
To: Doug Ledford, Jason Gunthorpe
Cc: Leon Romanovsky, RDMA mailing list, Yishai Hadas, Saeed Mahameed,
linux-netdev
From: Leon Romanovsky <leonro@mellanox.com>
Hi
See commit message for the patch description.
Thanks
Leon Romanovsky (1):
net/mlx5: Add shared Q counter bits
Yishai Hadas (1):
IB/mlx5: Allocate the per-port Q counter shared when DEVX is supported
drivers/infiniband/hw/mlx5/cmd.c | 17 +++++++++++++++++
drivers/infiniband/hw/mlx5/cmd.h | 2 ++
drivers/infiniband/hw/mlx5/main.c | 10 ++++++++--
include/linux/mlx5/mlx5_ifc.h | 6 +++++-
4 files changed, 32 insertions(+), 3 deletions(-)
^ permalink raw reply [flat|nested] 6+ messages in thread
* [PATCH mlx5-next 1/2] net/mlx5: Add shared Q counter bits
2018-12-09 10:52 [PATCH rdma-next 0/2] Allocate the per-port Q counter Leon Romanovsky
@ 2018-12-09 10:52 ` Leon Romanovsky
2018-12-09 10:52 ` [PATCH rdma-next 2/2] IB/mlx5: Allocate the per-port Q counter shared when DEVX is supported Leon Romanovsky
` (2 subsequent siblings)
3 siblings, 0 replies; 6+ messages in thread
From: Leon Romanovsky @ 2018-12-09 10:52 UTC (permalink / raw)
To: Doug Ledford, Jason Gunthorpe
Cc: Leon Romanovsky, RDMA mailing list, Yishai Hadas, Saeed Mahameed,
linux-netdev
From: Leon Romanovsky <leonro@mellanox.com>
Updated HW specification file with needed bits to allow
sharing of Q counters between DEVX contexts and kernel.
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
include/linux/mlx5/mlx5_ifc.h | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 52393fbcf3b4..15093356a226 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -85,6 +85,10 @@ enum {
MLX5_OBJ_TYPE_UMEM = 0x0005,
};
+enum {
+ MLX5_SHARED_RESOURCE_UID = 0xffff,
+};
+
enum {
MLX5_CMD_OP_QUERY_HCA_CAP = 0x100,
MLX5_CMD_OP_QUERY_ADAPTER = 0x101,
@@ -7464,7 +7468,7 @@ struct mlx5_ifc_alloc_q_counter_out_bits {
struct mlx5_ifc_alloc_q_counter_in_bits {
u8 opcode[0x10];
- u8 reserved_at_10[0x10];
+ u8 uid[0x10];
u8 reserved_at_20[0x10];
u8 op_mod[0x10];
--
2.19.1
^ permalink raw reply related [flat|nested] 6+ messages in thread
* [PATCH rdma-next 2/2] IB/mlx5: Allocate the per-port Q counter shared when DEVX is supported
2018-12-09 10:52 [PATCH rdma-next 0/2] Allocate the per-port Q counter Leon Romanovsky
2018-12-09 10:52 ` [PATCH mlx5-next 1/2] net/mlx5: Add shared Q counter bits Leon Romanovsky
@ 2018-12-09 10:52 ` Leon Romanovsky
2018-12-19 5:11 ` [PATCH rdma-next 0/2] Allocate the per-port Q counter Jason Gunthorpe
2018-12-21 19:12 ` Jason Gunthorpe
3 siblings, 0 replies; 6+ messages in thread
From: Leon Romanovsky @ 2018-12-09 10:52 UTC (permalink / raw)
To: Doug Ledford, Jason Gunthorpe
Cc: Leon Romanovsky, RDMA mailing list, Yishai Hadas, Saeed Mahameed,
linux-netdev
From: Yishai Hadas <yishaih@mellanox.com>
The per-port Q counter is some kernel resource and as such may be used
by few UID(s) upon DEVX usage.
To enable using it for QP/RQ when DEVX context is used need to allocate
it with a sharing mode indication to let firmware allows its usage.
The UID = 0xffff was chosen to mark it.
Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
---
drivers/infiniband/hw/mlx5/cmd.c | 17 +++++++++++++++++
drivers/infiniband/hw/mlx5/cmd.h | 2 ++
drivers/infiniband/hw/mlx5/main.c | 10 ++++++++--
3 files changed, 27 insertions(+), 2 deletions(-)
diff --git a/drivers/infiniband/hw/mlx5/cmd.c b/drivers/infiniband/hw/mlx5/cmd.c
index ca060a2e2b36..752c60426a1c 100644
--- a/drivers/infiniband/hw/mlx5/cmd.c
+++ b/drivers/infiniband/hw/mlx5/cmd.c
@@ -326,3 +326,20 @@ int mlx5_cmd_xrcd_dealloc(struct mlx5_core_dev *dev, u32 xrcdn, u16 uid)
MLX5_SET(dealloc_xrcd_in, in, uid, uid);
return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
}
+
+int mlx5_cmd_alloc_q_counter(struct mlx5_core_dev *dev, u16 *counter_id,
+ u16 uid)
+{
+ u32 in[MLX5_ST_SZ_DW(alloc_q_counter_in)] = {0};
+ u32 out[MLX5_ST_SZ_DW(alloc_q_counter_out)] = {0};
+ int err;
+
+ MLX5_SET(alloc_q_counter_in, in, opcode, MLX5_CMD_OP_ALLOC_Q_COUNTER);
+ MLX5_SET(alloc_q_counter_in, in, uid, uid);
+
+ err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out));
+ if (!err)
+ *counter_id = MLX5_GET(alloc_q_counter_out, out,
+ counter_set_id);
+ return err;
+}
diff --git a/drivers/infiniband/hw/mlx5/cmd.h b/drivers/infiniband/hw/mlx5/cmd.h
index c03c56455534..1e76dc67a369 100644
--- a/drivers/infiniband/hw/mlx5/cmd.h
+++ b/drivers/infiniband/hw/mlx5/cmd.h
@@ -61,4 +61,6 @@ int mlx5_cmd_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid,
u32 qpn, u16 uid);
int mlx5_cmd_xrcd_alloc(struct mlx5_core_dev *dev, u32 *xrcdn, u16 uid);
int mlx5_cmd_xrcd_dealloc(struct mlx5_core_dev *dev, u32 xrcdn, u16 uid);
+int mlx5_cmd_alloc_q_counter(struct mlx5_core_dev *dev, u16 *counter_id,
+ u16 uid);
#endif /* MLX5_IB_CMD_H */
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 4660f5f1547a..3477fa1b2289 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -5114,6 +5114,10 @@ static int mlx5_ib_alloc_counters(struct mlx5_ib_dev *dev)
{
int err = 0;
int i;
+ bool is_shared;
+
+ is_shared = MLX5_CAP_GEN_64(dev->mdev, general_obj_types) &
+ MLX5_GENERAL_OBJ_TYPES_CAP_UCTX;
for (i = 0; i < dev->num_ports; i++) {
err = __mlx5_ib_alloc_counters(dev, &dev->port[i].cnts);
@@ -5123,8 +5127,10 @@ static int mlx5_ib_alloc_counters(struct mlx5_ib_dev *dev)
mlx5_ib_fill_counters(dev, dev->port[i].cnts.names,
dev->port[i].cnts.offsets);
- err = mlx5_core_alloc_q_counter(dev->mdev,
- &dev->port[i].cnts.set_id);
+ err = mlx5_cmd_alloc_q_counter(dev->mdev,
+ &dev->port[i].cnts.set_id,
+ is_shared ?
+ MLX5_SHARED_RESOURCE_UID : 0);
if (err) {
mlx5_ib_warn(dev,
"couldn't allocate queue counter for port %d, err %d\n",
--
2.19.1
^ permalink raw reply related [flat|nested] 6+ messages in thread
* Re: [PATCH rdma-next 0/2] Allocate the per-port Q counter
2018-12-09 10:52 [PATCH rdma-next 0/2] Allocate the per-port Q counter Leon Romanovsky
2018-12-09 10:52 ` [PATCH mlx5-next 1/2] net/mlx5: Add shared Q counter bits Leon Romanovsky
2018-12-09 10:52 ` [PATCH rdma-next 2/2] IB/mlx5: Allocate the per-port Q counter shared when DEVX is supported Leon Romanovsky
@ 2018-12-19 5:11 ` Jason Gunthorpe
2018-12-19 6:08 ` Leon Romanovsky
2018-12-21 19:12 ` Jason Gunthorpe
3 siblings, 1 reply; 6+ messages in thread
From: Jason Gunthorpe @ 2018-12-19 5:11 UTC (permalink / raw)
To: Leon Romanovsky
Cc: Doug Ledford, Leon Romanovsky, RDMA mailing list, Yishai Hadas,
Saeed Mahameed, linux-netdev
On Sun, Dec 09, 2018 at 12:52:34PM +0200, Leon Romanovsky wrote:
> From: Leon Romanovsky <leonro@mellanox.com>
>
> Hi
>
> See commit message for the patch description.
>
> Thanks
>
> Leon Romanovsky (1):
> net/mlx5: Add shared Q counter bits
>
> Yishai Hadas (1):
> IB/mlx5: Allocate the per-port Q counter shared when DEVX is supported
This seems fine, please update the shared branch
Thanks,
Jason
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH rdma-next 0/2] Allocate the per-port Q counter
2018-12-19 5:11 ` [PATCH rdma-next 0/2] Allocate the per-port Q counter Jason Gunthorpe
@ 2018-12-19 6:08 ` Leon Romanovsky
0 siblings, 0 replies; 6+ messages in thread
From: Leon Romanovsky @ 2018-12-19 6:08 UTC (permalink / raw)
To: Jason Gunthorpe
Cc: Doug Ledford, RDMA mailing list, Yishai Hadas, Saeed Mahameed,
linux-netdev
[-- Attachment #1: Type: text/plain, Size: 572 bytes --]
On Tue, Dec 18, 2018 at 10:11:14PM -0700, Jason Gunthorpe wrote:
> On Sun, Dec 09, 2018 at 12:52:34PM +0200, Leon Romanovsky wrote:
> > From: Leon Romanovsky <leonro@mellanox.com>
> >
> > Hi
> >
> > See commit message for the patch description.
> >
> > Thanks
> >
> > Leon Romanovsky (1):
> > net/mlx5: Add shared Q counter bits
> >
> > Yishai Hadas (1):
> > IB/mlx5: Allocate the per-port Q counter shared when DEVX is supported
>
> This seems fine, please update the shared branch
Done,
2acc7957dbc3 net/mlx5: Add shared Q counter bits
Thanks
>
> Thanks,
> Jason
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 801 bytes --]
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH rdma-next 0/2] Allocate the per-port Q counter
2018-12-09 10:52 [PATCH rdma-next 0/2] Allocate the per-port Q counter Leon Romanovsky
` (2 preceding siblings ...)
2018-12-19 5:11 ` [PATCH rdma-next 0/2] Allocate the per-port Q counter Jason Gunthorpe
@ 2018-12-21 19:12 ` Jason Gunthorpe
3 siblings, 0 replies; 6+ messages in thread
From: Jason Gunthorpe @ 2018-12-21 19:12 UTC (permalink / raw)
To: Leon Romanovsky
Cc: Doug Ledford, Leon Romanovsky, RDMA mailing list, Yishai Hadas,
Saeed Mahameed, linux-netdev
On Sun, Dec 09, 2018 at 12:52:34PM +0200, Leon Romanovsky wrote:
> From: Leon Romanovsky <leonro@mellanox.com>
>
> Hi
>
> See commit message for the patch description.
>
> Thanks
>
> Leon Romanovsky (1):
> net/mlx5: Add shared Q counter bits
>
> Yishai Hadas (1):
> IB/mlx5: Allocate the per-port Q counter shared when DEVX is supported
Applied to for-next
Thanks,
Jason
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2018-12-21 19:12 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-12-09 10:52 [PATCH rdma-next 0/2] Allocate the per-port Q counter Leon Romanovsky
2018-12-09 10:52 ` [PATCH mlx5-next 1/2] net/mlx5: Add shared Q counter bits Leon Romanovsky
2018-12-09 10:52 ` [PATCH rdma-next 2/2] IB/mlx5: Allocate the per-port Q counter shared when DEVX is supported Leon Romanovsky
2018-12-19 5:11 ` [PATCH rdma-next 0/2] Allocate the per-port Q counter Jason Gunthorpe
2018-12-19 6:08 ` Leon Romanovsky
2018-12-21 19:12 ` Jason Gunthorpe
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).