On Thu, Dec 20, 2018 at 11:23:13AM +0200, Leon Romanovsky wrote:
> From: Leon Romanovsky <leo...@mellanox.com>
>
> Hi,
>
> As a followup to Jason's request to rethink CONFIG_INFINIBAND_ON_DEMAND_PAGING
> usage, this series cleans mlx5_ib and RDMA/core code and it is based on
> already
> sent but not yet accepted patch https://patchwork.kernel.org/patch/10735547/
>
> It is under extensive testing now, but I wanted to raise awareness as soon
> as possible for the patch "RDMA/core: Don't depend device ODP capabilities
> on kconfig option", which changes behavior for mlx5 devices with
> CONFIG_INFINIBAND_ON_DEMAND_PAGING set to no.
>
> Thanks
>
> Leon Romanovsky (5):
> RDMA: Clean structures from CONFIG_INFINIBAND_ON_DEMAND_PAGING
> RDMA/core: Don't depend device ODP capabilities on kconfig option
> RDMA/mlx5: Introduce and reuse helper to identify ODP MR
> RDMA/mlx5: Embed into the code flow the ODP config option
> RDMA/mlx5: Delete declaration of already removed function
I'm imagining something like this integrated into these patches, what
do you think?
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index c6144df47ea47e..c2615b6bb68841 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -95,6 +95,9 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context,
unsigned long addr,
struct scatterlist *sg, *sg_list_start;
unsigned int gup_flags = FOLL_WRITE;
+ if ((access & IB_ACCESS_ON_DEMAND) && !context->invalidate_range)
+ return ERR_PTR(-EOPNOTSUPP);
+
if (dmasync)
dma_attrs |= DMA_ATTR_WRITE_BARRIER;
diff --git a/drivers/infiniband/core/uverbs_cmd.c
b/drivers/infiniband/core/uverbs_cmd.c
index 4d28db23f53955..241376bae09540 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -236,8 +236,7 @@ static int ib_uverbs_get_context(struct uverbs_attr_bundle
*attrs)
mutex_init(&ucontext->per_mm_list_lock);
INIT_LIST_HEAD(&ucontext->per_mm_list);
- if (!IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING) ||
- !(ib_dev->attrs.device_cap_flags & IB_DEVICE_ON_DEMAND_PAGING))
+ if (!(ib_dev->attrs.device_cap_flags & IB_DEVICE_ON_DEMAND_PAGING))
ucontext->invalidate_range = NULL;
resp.num_comp_vectors = file->device->num_comp_vectors;
@@ -3607,13 +3606,15 @@ static int ib_uverbs_ex_query_device(struct
uverbs_attr_bundle *attrs)
copy_query_dev_fields(ucontext, &resp.base, &attr);
- resp.odp_caps.general_caps = attr.odp_caps.general_caps;
- resp.odp_caps.per_transport_caps.rc_odp_caps =
- attr.odp_caps.per_transport_caps.rc_odp_caps;
- resp.odp_caps.per_transport_caps.uc_odp_caps =
- attr.odp_caps.per_transport_caps.uc_odp_caps;
- resp.odp_caps.per_transport_caps.ud_odp_caps =
- attr.odp_caps.per_transport_caps.ud_odp_caps;
+ if (ib_dev->attrs.device_cap_flags & IB_DEVICE_ON_DEMAND_PAGING) {
+ resp.odp_caps.general_caps = attr.odp_caps.general_caps;
+ resp.odp_caps.per_transport_caps.rc_odp_caps =
+ attr.odp_caps.per_transport_caps.rc_odp_caps;
+ resp.odp_caps.per_transport_caps.uc_odp_caps =
+ attr.odp_caps.per_transport_caps.uc_odp_caps;
+ resp.odp_caps.per_transport_caps.ud_odp_caps =
+ attr.odp_caps.per_transport_caps.ud_odp_caps;
+ }
resp.timestamp_mask = attr.timestamp_mask;
resp.hca_core_clock = attr.hca_core_clock;
diff --git a/drivers/infiniband/hw/mlx5/main.c
b/drivers/infiniband/hw/mlx5/main.c
index ff131e4c874ec5..df8366fb0142d6 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -923,9 +923,11 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
props->hca_core_clock = MLX5_CAP_GEN(mdev, device_frequency_khz);
props->timestamp_mask = 0x7FFFFFFFFFFFFFFFULL;
- if (MLX5_CAP_GEN(mdev, pg))
- props->device_cap_flags |= IB_DEVICE_ON_DEMAND_PAGING;
- props->odp_caps = dev->odp_caps;
+ if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {
+ if (MLX5_CAP_GEN(mdev, pg))
+ props->device_cap_flags |= IB_DEVICE_ON_DEMAND_PAGING;
+ props->odp_caps = dev->odp_caps;
+ }
if (MLX5_CAP_GEN(mdev, cd))
props->device_cap_flags |= IB_DEVICE_CROSS_CHANNEL;
@@ -1761,7 +1763,8 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct
ib_device *ibdev,
if (err)
goto out_sys_pages;
- context->ibucontext.invalidate_range = &mlx5_ib_invalidate_range;
+ if (ibdev->attrs.device_cap_flags & IB_DEVICE_ON_DEMAND_PAGING)
+ context->ibucontext.invalidate_range =
&mlx5_ib_invalidate_range;
if (req.flags & MLX5_IB_ALLOC_UCTX_DEVX) {
err = mlx5_ib_devx_create(dev, true);
diff --git a/drivers/infiniband/hw/mlx5/mem.c b/drivers/infiniband/hw/mlx5/mem.c
index 9f90be296ee0f7..22827ba4b6d8eb 100644
--- a/drivers/infiniband/hw/mlx5/mem.c
+++ b/drivers/infiniband/hw/mlx5/mem.c
@@ -150,7 +150,7 @@ void __mlx5_ib_populate_pas(struct mlx5_ib_dev *dev, struct
ib_umem *umem,
struct scatterlist *sg;
int entry;
- if (umem->is_odp) {
+ if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING) && umem->is_odp) {
WARN_ON(shift != 0);
WARN_ON(access_flags != (MLX5_IB_MTT_READ | MLX5_IB_MTT_WRITE));
diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 65d07c111d42a7..8183e94da5a1ea 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1332,12 +1332,14 @@ struct ib_mr *mlx5_ib_reg_user_mr(struct ib_pd *pd, u64
start, u64 length,
mlx5_ib_dbg(dev, "start 0x%llx, virt_addr 0x%llx, length 0x%llx,
access_flags 0x%x\n",
start, virt_addr, length, access_flags);
- if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING) && !start &&
- length == U64_MAX) {
+ if (!start && length == U64_MAX) {
if (!(access_flags & IB_ACCESS_ON_DEMAND) ||
!(dev->odp_caps.general_caps & IB_ODP_SUPPORT_IMPLICIT))
return ERR_PTR(-EINVAL);
+ if (!IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING))
+ return ERR_PTR(-EOPNOTSUPP);
+
mr = mlx5_ib_alloc_implicit_mr(to_mpd(pd), access_flags);
if (IS_ERR(mr))
return ERR_CAST(mr);
