Merge tag 'rds-odp-for-5.5' into rdma.git for-next

From https://git.kernel.org/pub/scm/linux/kernel/git/leon/linux-rdma

Leon Romanovsky says:

====================
Use ODP MRs for kernel ULPs

The following series extends MR creation routines to allow creation of
user MRs through kernel ULPs as a proxy. The immediate use case is to
allow RDS to work over FS-DAX, which requires ODP (on-demand-paging)
MRs to be created and such MRs were not possible to create prior this
series.

The first part of this patchset extends RDMA to have special verb
ib_reg_user_mr(). The common use case that uses this function is a
userspace application that allocates memory for HCA access but the
responsibility to register the memory at the HCA is on an kernel ULP.
This ULP acts as an agent for the userspace application.

The second part provides advise MR functionality for ULPs. This is
integral part of ODP flows and used to trigger pagefaults in advance
to prepare memory before running working set.

The third part is actual user of those in-kernel APIs.
====================

* tag 'rds-odp-for-5.5':
  net/rds: Use prefetch for On-Demand-Paging MR
  net/rds: Handle ODP mr registration/unregistration
  net/rds: Detect need of On-Demand-Paging memory registration
  RDMA/mlx5: Fix handling of IOVA != user_va in ODP paths
  IB/mlx5: Mask out unsupported ODP capabilities for kernel QPs
  RDMA/mlx5: Don't fake udata for kernel path
  IB/mlx5: Add ODP WQE handlers for kernel QPs
  IB/core: Add interface to advise_mr for kernel users
  IB/core: Introduce ib_reg_user_mr
  IB: Allow calls to ib_umem_get from kernel ULPs

Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

3 files changed, 14 insertions, 5 deletions

diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index 753f54e17e0a..e3518fd6b95b 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -69,7 +69,7 @@ static inline size_t ib_umem_num_pages(struct ib_umem *umem)
 
 #ifdef CONFIG_INFINIBAND_USER_MEM
 
-struct ib_umem *ib_umem_get(struct ib_udata *udata, unsigned long addr,
+struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr,
 			    size_t size, int access);
 void ib_umem_release(struct ib_umem *umem);
 int ib_umem_page_count(struct ib_umem *umem);
@@ -83,7 +83,7 @@ unsigned long ib_umem_find_best_pgsz(struct ib_umem *umem,
 
 #include <linux/err.h>
 
-static inline struct ib_umem *ib_umem_get(struct ib_udata *udata,
+static inline struct ib_umem *ib_umem_get(struct ib_device *device,
 					  unsigned long addr, size_t size,
 					  int access)
 {
diff --git a/include/rdma/ib_umem_odp.h b/include/rdma/ib_umem_odp.h
index 81429acc8257..64314ff76612 100644
--- a/include/rdma/ib_umem_odp.h
+++ b/include/rdma/ib_umem_odp.h
@@ -114,9 +114,9 @@ static inline size_t ib_umem_odp_num_pages(struct ib_umem_odp *umem_odp)
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
 
 struct ib_umem_odp *
-ib_umem_odp_get(struct ib_udata *udata, unsigned long addr, size_t size,
+ib_umem_odp_get(struct ib_device *device, unsigned long addr, size_t size,
 		int access, const struct mmu_interval_notifier_ops *ops);
-struct ib_umem_odp *ib_umem_odp_alloc_implicit(struct ib_udata *udata,
+struct ib_umem_odp *ib_umem_odp_alloc_implicit(struct ib_device *device,
 					       int access);
 struct ib_umem_odp *
 ib_umem_odp_alloc_child(struct ib_umem_odp *root_umem, unsigned long addr,
@@ -134,7 +134,7 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 start_offset,
 #else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 
 static inline struct ib_umem_odp *
-ib_umem_odp_get(struct ib_udata *udata, unsigned long addr, size_t size,
+ib_umem_odp_get(struct ib_device *device, unsigned long addr, size_t size,
 		int access, const struct mmu_interval_notifier_ops *ops)
 {
 	return ERR_PTR(-EINVAL);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 6506df9f31ae..1f779fad3a1e 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -4166,6 +4166,15 @@ static inline void ib_dma_free_coherent(struct ib_device *dev,
 	dma_free_coherent(dev->dma_device, size, cpu_addr, dma_handle);
 }
 
+/* ib_reg_user_mr - register a memory region for virtual addresses from kernel
+ * space. This function should be called when 'current' is the owning MM.
+ */
+struct ib_mr *ib_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
+			     u64 virt_addr, int mr_access_flags);
+
+/* ib_advise_mr -  give an advice about an address range in a memory region */
+int ib_advise_mr(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice,
+		 u32 flags, struct ib_sge *sg_list, u32 num_sge);
 /**
  * ib_dereg_mr_user - Deregisters a memory region and removes it from the
  *   HCA translation table.