* [PATCH rdma-next v1 0/3] ODP support for mlx5 DC QPs
@ 2019-08-04 10:00 Leon Romanovsky
2019-08-04 10:00 ` [PATCH mlx5-next v1 1/3] IB/mlx5: Query ODP capabilities for DC Leon Romanovsky
` (2 more replies)
0 siblings, 3 replies; 6+ messages in thread
From: Leon Romanovsky @ 2019-08-04 10:00 UTC (permalink / raw)
To: Doug Ledford, Jason Gunthorpe
Cc: Leon Romanovsky, RDMA mailing list, Michael Guralnik, Moni Shoua,
Saeed Mahameed, linux-netdev
From: Leon Romanovsky <leonro@mellanox.com>
Changelog
v1:
* Fixed alignment to u64 in mlx5-abi.h (Gal P.)
v0:
* https://lore.kernel.org/linux-rdma/20190801122139.25224-1-leon@kernel.org
---------------------------------------------------------------------------------
From Michael,
The series adds support for on-demand paging for DC transport.
Adding handling of DC WQE parsing upon page faults and exposing
capabilities.
As DC is mlx-only transport, the capabilities are exposed to the user
using the direct-verbs mechanism. Namely through the
mlx5dv_query_device.
Thanks
Thanks
Michael Guralnik (3):
IB/mlx5: Query ODP capabilities for DC
IB/mlx5: Expose ODP for DC capabilities to user
IB/mlx5: Add page fault handler for DC initiator WQE
drivers/infiniband/hw/mlx5/main.c | 6 +++++
drivers/infiniband/hw/mlx5/mlx5_ib.h | 1 +
drivers/infiniband/hw/mlx5/odp.c | 27 ++++++++++++++++++-
.../net/ethernet/mellanox/mlx5/core/main.c | 6 +++++
include/linux/mlx5/mlx5_ifc.h | 4 ++-
include/uapi/rdma/mlx5-abi.h | 3 +++
6 files changed, 45 insertions(+), 2 deletions(-)
--
2.20.1
^ permalink raw reply [flat|nested] 6+ messages in thread* [PATCH mlx5-next v1 1/3] IB/mlx5: Query ODP capabilities for DC 2019-08-04 10:00 [PATCH rdma-next v1 0/3] ODP support for mlx5 DC QPs Leon Romanovsky @ 2019-08-04 10:00 ` Leon Romanovsky 2019-08-05 18:23 ` Saeed Mahameed 2019-08-04 10:00 ` [PATCH rdma-next v1 2/3] IB/mlx5: Expose ODP for DC capabilities to user Leon Romanovsky 2019-08-04 10:00 ` [PATCH rdma-next v1 3/3] IB/mlx5: Add page fault handler for DC initiator WQE Leon Romanovsky 2 siblings, 1 reply; 6+ messages in thread From: Leon Romanovsky @ 2019-08-04 10:00 UTC (permalink / raw) To: Doug Ledford, Jason Gunthorpe Cc: Leon Romanovsky, RDMA mailing list, Michael Guralnik, Moni Shoua, Saeed Mahameed, linux-netdev From: Michael Guralnik <michaelgur@mellanox.com> Set current capabilities of ODP for DC to max capabilities and cache them in mlx5_ib. Signed-off-by: Michael Guralnik <michaelgur@mellanox.com> Reviewed-by: Moni Shoua <monis@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> --- drivers/infiniband/hw/mlx5/mlx5_ib.h | 1 + drivers/infiniband/hw/mlx5/odp.c | 18 ++++++++++++++++++ drivers/net/ethernet/mellanox/mlx5/core/main.c | 6 ++++++ include/linux/mlx5/mlx5_ifc.h | 4 +++- 4 files changed, 28 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h index cb41a7e6255a..f99c71b3c876 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -967,6 +967,7 @@ struct mlx5_ib_dev { struct mutex slow_path_mutex; int fill_delay; struct ib_odp_caps odp_caps; + uint32_t dc_odp_caps; u64 odp_max_size; struct mlx5_ib_pf_eq odp_pf_eq; diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index b0c5de39d186..5e87a5e25574 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -353,6 +353,24 @@ void mlx5_ib_internal_fill_odp_caps(struct mlx5_ib_dev *dev) if (MLX5_CAP_ODP(dev->mdev, xrc_odp_caps.srq_receive)) caps->per_transport_caps.xrc_odp_caps |= IB_ODP_SUPPORT_SRQ_RECV; + if (MLX5_CAP_ODP(dev->mdev, dc_odp_caps.send)) + dev->dc_odp_caps |= IB_ODP_SUPPORT_SEND; + + if (MLX5_CAP_ODP(dev->mdev, dc_odp_caps.receive)) + dev->dc_odp_caps |= IB_ODP_SUPPORT_RECV; + + if (MLX5_CAP_ODP(dev->mdev, dc_odp_caps.write)) + dev->dc_odp_caps |= IB_ODP_SUPPORT_WRITE; + + if (MLX5_CAP_ODP(dev->mdev, dc_odp_caps.read)) + dev->dc_odp_caps |= IB_ODP_SUPPORT_READ; + + if (MLX5_CAP_ODP(dev->mdev, dc_odp_caps.atomic)) + dev->dc_odp_caps |= IB_ODP_SUPPORT_ATOMIC; + + if (MLX5_CAP_ODP(dev->mdev, dc_odp_caps.srq_receive)) + dev->dc_odp_caps |= IB_ODP_SUPPORT_SRQ_RECV; + if (MLX5_CAP_GEN(dev->mdev, fixed_buffer_size) && MLX5_CAP_GEN(dev->mdev, null_mkey) && MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset)) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index b15b27a497fc..3995fc6d4d34 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -495,6 +495,12 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev) ODP_CAP_SET_MAX(dev, xrc_odp_caps.write); ODP_CAP_SET_MAX(dev, xrc_odp_caps.read); ODP_CAP_SET_MAX(dev, xrc_odp_caps.atomic); + ODP_CAP_SET_MAX(dev, dc_odp_caps.srq_receive); + ODP_CAP_SET_MAX(dev, dc_odp_caps.send); + ODP_CAP_SET_MAX(dev, dc_odp_caps.receive); + ODP_CAP_SET_MAX(dev, dc_odp_caps.write); + ODP_CAP_SET_MAX(dev, dc_odp_caps.read); + ODP_CAP_SET_MAX(dev, dc_odp_caps.atomic); if (do_set) err = set_caps(dev, set_ctx, set_sz, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index ec571fd7fcf8..5eae8d734435 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -944,7 +944,9 @@ struct mlx5_ifc_odp_cap_bits { struct mlx5_ifc_odp_per_transport_service_cap_bits xrc_odp_caps; - u8 reserved_at_100[0x700]; + struct mlx5_ifc_odp_per_transport_service_cap_bits dc_odp_caps; + + u8 reserved_at_100[0x6E0]; }; struct mlx5_ifc_calc_op { -- 2.20.1 ^ permalink raw reply related [flat|nested] 6+ messages in thread
* Re: [PATCH mlx5-next v1 1/3] IB/mlx5: Query ODP capabilities for DC 2019-08-04 10:00 ` [PATCH mlx5-next v1 1/3] IB/mlx5: Query ODP capabilities for DC Leon Romanovsky @ 2019-08-05 18:23 ` Saeed Mahameed 2019-08-06 7:02 ` Leon Romanovsky 0 siblings, 1 reply; 6+ messages in thread From: Saeed Mahameed @ 2019-08-05 18:23 UTC (permalink / raw) To: Jason Gunthorpe, leon@kernel.org, dledford@redhat.com Cc: Michael Guralnik, Moni Shoua, netdev@vger.kernel.org, Leon Romanovsky, linux-rdma@vger.kernel.org On Sun, 2019-08-04 at 13:00 +0300, Leon Romanovsky wrote: > From: Michael Guralnik <michaelgur@mellanox.com> > > Set current capabilities of ODP for DC to max capabilities and cache > them in mlx5_ib. > > Signed-off-by: Michael Guralnik <michaelgur@mellanox.com> > Reviewed-by: Moni Shoua <monis@mellanox.com> > Signed-off-by: Leon Romanovsky <leonro@mellanox.com> > --- > drivers/infiniband/hw/mlx5/mlx5_ib.h | 1 + > drivers/infiniband/hw/mlx5/odp.c | 18 > ++++++++++++++++++ > drivers/net/ethernet/mellanox/mlx5/core/main.c | 6 ++++++ > include/linux/mlx5/mlx5_ifc.h | 4 +++- Please avoid cross tree changes when you can.. Here you do can avoid it, so please separate to two stage patches, mlx5_ifc and core, then mlx5_ib. > 4 files changed, 28 insertions(+), 1 deletion(-) > > diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h > b/drivers/infiniband/hw/mlx5/mlx5_ib.h > index cb41a7e6255a..f99c71b3c876 100644 > --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h > +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h > @@ -967,6 +967,7 @@ struct mlx5_ib_dev { > struct mutex slow_path_mutex; > int fill_delay; > struct ib_odp_caps odp_caps; > + uint32_t dc_odp_caps; > u64 odp_max_size; > struct mlx5_ib_pf_eq odp_pf_eq; > > diff --git a/drivers/infiniband/hw/mlx5/odp.c > b/drivers/infiniband/hw/mlx5/odp.c > index b0c5de39d186..5e87a5e25574 100644 > --- a/drivers/infiniband/hw/mlx5/odp.c > +++ b/drivers/infiniband/hw/mlx5/odp.c > @@ -353,6 +353,24 @@ void mlx5_ib_internal_fill_odp_caps(struct > mlx5_ib_dev *dev) > if (MLX5_CAP_ODP(dev->mdev, xrc_odp_caps.srq_receive)) > caps->per_transport_caps.xrc_odp_caps |= > IB_ODP_SUPPORT_SRQ_RECV; > > + if (MLX5_CAP_ODP(dev->mdev, dc_odp_caps.send)) > + dev->dc_odp_caps |= IB_ODP_SUPPORT_SEND; > + > + if (MLX5_CAP_ODP(dev->mdev, dc_odp_caps.receive)) > + dev->dc_odp_caps |= IB_ODP_SUPPORT_RECV; > + > + if (MLX5_CAP_ODP(dev->mdev, dc_odp_caps.write)) > + dev->dc_odp_caps |= IB_ODP_SUPPORT_WRITE; > + > + if (MLX5_CAP_ODP(dev->mdev, dc_odp_caps.read)) > + dev->dc_odp_caps |= IB_ODP_SUPPORT_READ; > + > + if (MLX5_CAP_ODP(dev->mdev, dc_odp_caps.atomic)) > + dev->dc_odp_caps |= IB_ODP_SUPPORT_ATOMIC; > + > + if (MLX5_CAP_ODP(dev->mdev, dc_odp_caps.srq_receive)) > + dev->dc_odp_caps |= IB_ODP_SUPPORT_SRQ_RECV; > + > if (MLX5_CAP_GEN(dev->mdev, fixed_buffer_size) && > MLX5_CAP_GEN(dev->mdev, null_mkey) && > MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset)) > diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c > b/drivers/net/ethernet/mellanox/mlx5/core/main.c > index b15b27a497fc..3995fc6d4d34 100644 > --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c > +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c > @@ -495,6 +495,12 @@ static int handle_hca_cap_odp(struct > mlx5_core_dev *dev) > ODP_CAP_SET_MAX(dev, xrc_odp_caps.write); > ODP_CAP_SET_MAX(dev, xrc_odp_caps.read); > ODP_CAP_SET_MAX(dev, xrc_odp_caps.atomic); > + ODP_CAP_SET_MAX(dev, dc_odp_caps.srq_receive); > + ODP_CAP_SET_MAX(dev, dc_odp_caps.send); > + ODP_CAP_SET_MAX(dev, dc_odp_caps.receive); > + ODP_CAP_SET_MAX(dev, dc_odp_caps.write); > + ODP_CAP_SET_MAX(dev, dc_odp_caps.read); > + ODP_CAP_SET_MAX(dev, dc_odp_caps.atomic); > > if (do_set) > err = set_caps(dev, set_ctx, set_sz, > diff --git a/include/linux/mlx5/mlx5_ifc.h > b/include/linux/mlx5/mlx5_ifc.h > index ec571fd7fcf8..5eae8d734435 100644 > --- a/include/linux/mlx5/mlx5_ifc.h > +++ b/include/linux/mlx5/mlx5_ifc.h > @@ -944,7 +944,9 @@ struct mlx5_ifc_odp_cap_bits { > > struct mlx5_ifc_odp_per_transport_service_cap_bits > xrc_odp_caps; > > - u8 reserved_at_100[0x700]; > + struct mlx5_ifc_odp_per_transport_service_cap_bits dc_odp_caps; > + > + u8 reserved_at_100[0x6E0]; reserved_at_100 should move 20 bit forward. i.e reserved_at_120 ^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH mlx5-next v1 1/3] IB/mlx5: Query ODP capabilities for DC 2019-08-05 18:23 ` Saeed Mahameed @ 2019-08-06 7:02 ` Leon Romanovsky 0 siblings, 0 replies; 6+ messages in thread From: Leon Romanovsky @ 2019-08-06 7:02 UTC (permalink / raw) To: Saeed Mahameed Cc: Jason Gunthorpe, dledford@redhat.com, Michael Guralnik, Moni Shoua, netdev@vger.kernel.org, linux-rdma@vger.kernel.org On Mon, Aug 05, 2019 at 06:23:04PM +0000, Saeed Mahameed wrote: > On Sun, 2019-08-04 at 13:00 +0300, Leon Romanovsky wrote: > > From: Michael Guralnik <michaelgur@mellanox.com> > > > > Set current capabilities of ODP for DC to max capabilities and cache > > them in mlx5_ib. > > > > Signed-off-by: Michael Guralnik <michaelgur@mellanox.com> > > Reviewed-by: Moni Shoua <monis@mellanox.com> > > Signed-off-by: Leon Romanovsky <leonro@mellanox.com> > > --- > > drivers/infiniband/hw/mlx5/mlx5_ib.h | 1 + > > drivers/infiniband/hw/mlx5/odp.c | 18 > > ++++++++++++++++++ > > drivers/net/ethernet/mellanox/mlx5/core/main.c | 6 ++++++ > > include/linux/mlx5/mlx5_ifc.h | 4 +++- > > Please avoid cross tree changes when you can.. > Here you do can avoid it, so please separate to two stage patches, > mlx5_ifc and core, then mlx5_ib. > > > > 4 files changed, 28 insertions(+), 1 deletion(-) > > > > diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h > > b/drivers/infiniband/hw/mlx5/mlx5_ib.h > > index cb41a7e6255a..f99c71b3c876 100644 > > --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h > > +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h > > @@ -967,6 +967,7 @@ struct mlx5_ib_dev { > > struct mutex slow_path_mutex; > > int fill_delay; > > struct ib_odp_caps odp_caps; > > + uint32_t dc_odp_caps; > > u64 odp_max_size; > > struct mlx5_ib_pf_eq odp_pf_eq; > > > > diff --git a/drivers/infiniband/hw/mlx5/odp.c > > b/drivers/infiniband/hw/mlx5/odp.c > > index b0c5de39d186..5e87a5e25574 100644 > > --- a/drivers/infiniband/hw/mlx5/odp.c > > +++ b/drivers/infiniband/hw/mlx5/odp.c > > @@ -353,6 +353,24 @@ void mlx5_ib_internal_fill_odp_caps(struct > > mlx5_ib_dev *dev) > > if (MLX5_CAP_ODP(dev->mdev, xrc_odp_caps.srq_receive)) > > caps->per_transport_caps.xrc_odp_caps |= > > IB_ODP_SUPPORT_SRQ_RECV; > > > > + if (MLX5_CAP_ODP(dev->mdev, dc_odp_caps.send)) > > + dev->dc_odp_caps |= IB_ODP_SUPPORT_SEND; > > + > > + if (MLX5_CAP_ODP(dev->mdev, dc_odp_caps.receive)) > > + dev->dc_odp_caps |= IB_ODP_SUPPORT_RECV; > > + > > + if (MLX5_CAP_ODP(dev->mdev, dc_odp_caps.write)) > > + dev->dc_odp_caps |= IB_ODP_SUPPORT_WRITE; > > + > > + if (MLX5_CAP_ODP(dev->mdev, dc_odp_caps.read)) > > + dev->dc_odp_caps |= IB_ODP_SUPPORT_READ; > > + > > + if (MLX5_CAP_ODP(dev->mdev, dc_odp_caps.atomic)) > > + dev->dc_odp_caps |= IB_ODP_SUPPORT_ATOMIC; > > + > > + if (MLX5_CAP_ODP(dev->mdev, dc_odp_caps.srq_receive)) > > + dev->dc_odp_caps |= IB_ODP_SUPPORT_SRQ_RECV; > > + > > if (MLX5_CAP_GEN(dev->mdev, fixed_buffer_size) && > > MLX5_CAP_GEN(dev->mdev, null_mkey) && > > MLX5_CAP_GEN(dev->mdev, umr_extended_translation_offset)) > > diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c > > b/drivers/net/ethernet/mellanox/mlx5/core/main.c > > index b15b27a497fc..3995fc6d4d34 100644 > > --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c > > +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c > > @@ -495,6 +495,12 @@ static int handle_hca_cap_odp(struct > > mlx5_core_dev *dev) > > ODP_CAP_SET_MAX(dev, xrc_odp_caps.write); > > ODP_CAP_SET_MAX(dev, xrc_odp_caps.read); > > ODP_CAP_SET_MAX(dev, xrc_odp_caps.atomic); > > + ODP_CAP_SET_MAX(dev, dc_odp_caps.srq_receive); > > + ODP_CAP_SET_MAX(dev, dc_odp_caps.send); > > + ODP_CAP_SET_MAX(dev, dc_odp_caps.receive); > > + ODP_CAP_SET_MAX(dev, dc_odp_caps.write); > > + ODP_CAP_SET_MAX(dev, dc_odp_caps.read); > > + ODP_CAP_SET_MAX(dev, dc_odp_caps.atomic); > > > > if (do_set) > > err = set_caps(dev, set_ctx, set_sz, > > diff --git a/include/linux/mlx5/mlx5_ifc.h > > b/include/linux/mlx5/mlx5_ifc.h > > index ec571fd7fcf8..5eae8d734435 100644 > > --- a/include/linux/mlx5/mlx5_ifc.h > > +++ b/include/linux/mlx5/mlx5_ifc.h > > @@ -944,7 +944,9 @@ struct mlx5_ifc_odp_cap_bits { > > > > struct mlx5_ifc_odp_per_transport_service_cap_bits > > xrc_odp_caps; > > > > - u8 reserved_at_100[0x700]; > > + struct mlx5_ifc_odp_per_transport_service_cap_bits dc_odp_caps; > > + > > + u8 reserved_at_100[0x6E0]; > > reserved_at_100 should move 20 bit forward. i.e reserved_at_120 Thanks for pointing it, I'm sending new version now. > > ^ permalink raw reply [flat|nested] 6+ messages in thread
* [PATCH rdma-next v1 2/3] IB/mlx5: Expose ODP for DC capabilities to user 2019-08-04 10:00 [PATCH rdma-next v1 0/3] ODP support for mlx5 DC QPs Leon Romanovsky 2019-08-04 10:00 ` [PATCH mlx5-next v1 1/3] IB/mlx5: Query ODP capabilities for DC Leon Romanovsky @ 2019-08-04 10:00 ` Leon Romanovsky 2019-08-04 10:00 ` [PATCH rdma-next v1 3/3] IB/mlx5: Add page fault handler for DC initiator WQE Leon Romanovsky 2 siblings, 0 replies; 6+ messages in thread From: Leon Romanovsky @ 2019-08-04 10:00 UTC (permalink / raw) To: Doug Ledford, Jason Gunthorpe Cc: Leon Romanovsky, RDMA mailing list, Michael Guralnik, Moni Shoua, Saeed Mahameed, linux-netdev From: Michael Guralnik <michaelgur@mellanox.com> Return ODP capabilities for DC to user in alloc_context. Signed-off-by: Michael Guralnik <michaelgur@mellanox.com> Reviewed-by: Moni Shoua <monis@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> --- drivers/infiniband/hw/mlx5/main.c | 6 ++++++ include/uapi/rdma/mlx5-abi.h | 3 +++ 2 files changed, 9 insertions(+) diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 4a3d700cd783..a53e0dc7c17f 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -1954,6 +1954,12 @@ static int mlx5_ib_alloc_ucontext(struct ib_ucontext *uctx, resp.response_length += sizeof(resp.dump_fill_mkey); } + if (field_avail(typeof(resp), dc_odp_caps, udata->outlen)) { + resp.dc_odp_caps = dev->dc_odp_caps; + resp.comp_mask |= MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_DC_ODP_CAPS; + resp.response_length += sizeof(resp.dc_odp_caps); + } + err = ib_copy_to_udata(udata, &resp, resp.response_length); if (err) goto out_mdev; diff --git a/include/uapi/rdma/mlx5-abi.h b/include/uapi/rdma/mlx5-abi.h index 624f5b53eb1f..7cab806d7fa7 100644 --- a/include/uapi/rdma/mlx5-abi.h +++ b/include/uapi/rdma/mlx5-abi.h @@ -98,6 +98,7 @@ struct mlx5_ib_alloc_ucontext_req_v2 { enum mlx5_ib_alloc_ucontext_resp_mask { MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_CORE_CLOCK_OFFSET = 1UL << 0, MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_DUMP_FILL_MKEY = 1UL << 1, + MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_DC_ODP_CAPS = 1UL << 2, }; enum mlx5_user_cmds_supp_uhw { @@ -147,6 +148,8 @@ struct mlx5_ib_alloc_ucontext_resp { __u32 num_uars_per_page; __u32 num_dyn_bfregs; __u32 dump_fill_mkey; + __u32 dc_odp_caps; + __u32 reserved; }; struct mlx5_ib_alloc_pd_resp { -- 2.20.1 ^ permalink raw reply related [flat|nested] 6+ messages in thread
* [PATCH rdma-next v1 3/3] IB/mlx5: Add page fault handler for DC initiator WQE 2019-08-04 10:00 [PATCH rdma-next v1 0/3] ODP support for mlx5 DC QPs Leon Romanovsky 2019-08-04 10:00 ` [PATCH mlx5-next v1 1/3] IB/mlx5: Query ODP capabilities for DC Leon Romanovsky 2019-08-04 10:00 ` [PATCH rdma-next v1 2/3] IB/mlx5: Expose ODP for DC capabilities to user Leon Romanovsky @ 2019-08-04 10:00 ` Leon Romanovsky 2 siblings, 0 replies; 6+ messages in thread From: Leon Romanovsky @ 2019-08-04 10:00 UTC (permalink / raw) To: Doug Ledford, Jason Gunthorpe Cc: Leon Romanovsky, RDMA mailing list, Michael Guralnik, Moni Shoua, Saeed Mahameed, linux-netdev From: Michael Guralnik <michaelgur@mellanox.com> Parsing DC initiator WQEs upon page fault requires skipping an address vector segment, as in UD WQEs. Signed-off-by: Michael Guralnik <michaelgur@mellanox.com> Reviewed-by: Moni Shoua <monis@mellanox.com> Signed-off-by: Leon Romanovsky <leonro@mellanox.com> --- drivers/infiniband/hw/mlx5/odp.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 5e87a5e25574..6f1de5edbe8e 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -1065,6 +1065,12 @@ static int mlx5_ib_mr_initiator_pfault_handler( case IB_QPT_UD: transport_caps = dev->odp_caps.per_transport_caps.ud_odp_caps; break; + case IB_QPT_DRIVER: + if (qp->qp_sub_type == MLX5_IB_QPT_DCI) { + transport_caps = dev->dc_odp_caps; + break; + } + /* fall through */ default: mlx5_ib_err(dev, "ODP fault on QP of an unsupported transport 0x%x\n", qp->ibqp.qp_type); @@ -1078,7 +1084,8 @@ static int mlx5_ib_mr_initiator_pfault_handler( return -EFAULT; } - if (qp->ibqp.qp_type == IB_QPT_UD) { + if (qp->ibqp.qp_type == IB_QPT_UD || + qp->qp_sub_type == MLX5_IB_QPT_DCI) { av = *wqe; if (av->dqp_dct & cpu_to_be32(MLX5_EXTENDED_UD_AV)) *wqe += sizeof(struct mlx5_av); -- 2.20.1 ^ permalink raw reply related [flat|nested] 6+ messages in thread
end of thread, other threads:[~2019-08-06 7:02 UTC | newest] Thread overview: 6+ messages (download: mbox.gz follow: Atom feed -- links below jump to the message on this page -- 2019-08-04 10:00 [PATCH rdma-next v1 0/3] ODP support for mlx5 DC QPs Leon Romanovsky 2019-08-04 10:00 ` [PATCH mlx5-next v1 1/3] IB/mlx5: Query ODP capabilities for DC Leon Romanovsky 2019-08-05 18:23 ` Saeed Mahameed 2019-08-06 7:02 ` Leon Romanovsky 2019-08-04 10:00 ` [PATCH rdma-next v1 2/3] IB/mlx5: Expose ODP for DC capabilities to user Leon Romanovsky 2019-08-04 10:00 ` [PATCH rdma-next v1 3/3] IB/mlx5: Add page fault handler for DC initiator WQE Leon Romanovsky
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).