Merge branch 'odp_fixes' into hmm.git

From rdma.git

Jason Gunthorpe says:

====================
This is a collection of general cleanups for ODP to clarify some of the
flows around umem creation and use of the interval tree.
====================

The branch is based on v5.3-rc5 due to dependencies, and is being taken
into hmm.git due to dependencies in the next patches.

* odp_fixes:
  RDMA/mlx5: Use odp instead of mr->umem in pagefault_mr
  RDMA/mlx5: Use ib_umem_start instead of umem.address
  RDMA/core: Make invalidate_range a device operation
  RDMA/odp: Use kvcalloc for the dma_list and page_list
  RDMA/odp: Check for overflow when computing the umem_odp end
  RDMA/odp: Provide ib_umem_odp_release() to undo the allocs
  RDMA/odp: Split creating a umem_odp from ib_umem_get
  RDMA/odp: Make the three ways to create a umem_odp clear
  RMDA/odp: Consolidate umem_odp initialization
  RDMA/odp: Make it clearer when a umem is an implicit ODP umem
  RDMA/odp: Iterate over the whole rbtree directly
  RDMA/odp: Use the common interval tree library instead of generic
  RDMA/mlx5: Fix MR npages calculation for IB_ACCESS_HUGETLB

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

3 files changed, 41 insertions, 24 deletions

diff --git a/include/rdma/ib_umem_odp.h b/include/rdma/ib_umem_odp.h
index 479db5c98ff6..b37c674b7fe6 100644
--- a/include/rdma/ib_umem_odp.h
+++ b/include/rdma/ib_umem_odp.h
@@ -37,11 +37,6 @@
 #include <rdma/ib_verbs.h>
 #include <linux/interval_tree.h>
 
-struct umem_odp_node {
-	u64 __subtree_last;
-	struct rb_node rb;
-};
-
 struct ib_umem_odp {
 	struct ib_umem umem;
 	struct ib_ucontext_per_mm *per_mm;
@@ -72,7 +67,15 @@ struct ib_umem_odp {
 	int npages;
 
 	/* Tree tracking */
-	struct umem_odp_node	interval_tree;
+	struct interval_tree_node interval_tree;
+
+	/*
+	 * An implicit odp umem cannot be DMA mapped, has 0 length, and serves
+	 * only as an anchor for the driver to hold onto the per_mm. FIXME:
+	 * This should be removed and drivers should work with the per_mm
+	 * directly.
+	 */
+	bool is_implicit_odp;
 
 	struct completion	notifier_completion;
 	int			dying;
@@ -88,14 +91,13 @@ static inline struct ib_umem_odp *to_ib_umem_odp(struct ib_umem *umem)
 /* Returns the first page of an ODP umem. */
 static inline unsigned long ib_umem_start(struct ib_umem_odp *umem_odp)
 {
-	return ALIGN_DOWN(umem_odp->umem.address, 1UL << umem_odp->page_shift);
+	return umem_odp->interval_tree.start;
 }
 
 /* Returns the address of the page after the last one of an ODP umem. */
 static inline unsigned long ib_umem_end(struct ib_umem_odp *umem_odp)
 {
-	return ALIGN(umem_odp->umem.address + umem_odp->umem.length,
-		     1UL << umem_odp->page_shift);
+	return umem_odp->interval_tree.last + 1;
 }
 
 static inline size_t ib_umem_odp_num_pages(struct ib_umem_odp *umem_odp)
@@ -136,9 +138,12 @@ struct ib_ucontext_per_mm {
 	struct rcu_head rcu;
 };
 
-int ib_umem_odp_get(struct ib_umem_odp *umem_odp, int access);
-struct ib_umem_odp *ib_alloc_odp_umem(struct ib_umem_odp *root_umem,
-				      unsigned long addr, size_t size);
+struct ib_umem_odp *ib_umem_odp_get(struct ib_udata *udata, unsigned long addr,
+				    size_t size, int access);
+struct ib_umem_odp *ib_umem_odp_alloc_implicit(struct ib_udata *udata,
+					       int access);
+struct ib_umem_odp *ib_umem_odp_alloc_child(struct ib_umem_odp *root_umem,
+					    unsigned long addr, size_t size);
 void ib_umem_odp_release(struct ib_umem_odp *umem_odp);
 
 int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 start_offset,
@@ -163,8 +168,17 @@ int rbt_ib_umem_for_each_in_range(struct rb_root_cached *root,
  * Find first region intersecting with address range.
  * Return NULL if not found
  */
-struct ib_umem_odp *rbt_ib_umem_lookup(struct rb_root_cached *root,
-				       u64 addr, u64 length);
+static inline struct ib_umem_odp *
+rbt_ib_umem_lookup(struct rb_root_cached *root, u64 addr, u64 length)
+{
+	struct interval_tree_node *node;
+
+	node = interval_tree_iter_first(root, addr, addr + length - 1);
+	if (!node)
+		return NULL;
+	return container_of(node, struct ib_umem_odp, interval_tree);
+
+}
 
 static inline int ib_umem_mmu_notifier_retry(struct ib_umem_odp *umem_odp,
 					     unsigned long mmu_seq)
@@ -185,9 +199,11 @@ static inline int ib_umem_mmu_notifier_retry(struct ib_umem_odp *umem_odp,
 
 #else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 
-static inline int ib_umem_odp_get(struct ib_umem_odp *umem_odp, int access)
+static inline struct ib_umem_odp *ib_umem_odp_get(struct ib_udata *udata,
+						  unsigned long addr,
+						  size_t size, int access)
 {
-	return -EINVAL;
+	return ERR_PTR(-EINVAL);
 }
 
 static inline void ib_umem_odp_release(struct ib_umem_odp *umem_odp) {}
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index c5f8a9f17063..c2b39dda44cc 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1417,8 +1417,6 @@ struct ib_ucontext {
 
 	bool cleanup_retryable;
 
-	void (*invalidate_range)(struct ib_umem_odp *umem_odp,
-				 unsigned long start, unsigned long end);
 	struct mutex per_mm_list_lock;
 	struct list_head per_mm_list;
 
@@ -2378,6 +2376,8 @@ struct ib_device_ops {
 			    u64 iova);
 	int (*unmap_fmr)(struct list_head *fmr_list);
 	int (*dealloc_fmr)(struct ib_fmr *fmr);
+	void (*invalidate_range)(struct ib_umem_odp *umem_odp,
+				 unsigned long start, unsigned long end);
 	int (*attach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid);
 	int (*detach_mcast)(struct ib_qp *qp, union ib_gid *gid, u16 lid);
 	struct ib_xrcd *(*alloc_xrcd)(struct ib_device *device,
@@ -2647,7 +2647,9 @@ struct ib_client {
 			const union ib_gid *gid,
 			const struct sockaddr *addr,
 			void *client_data);
-	struct list_head list;
+
+	refcount_t uses;
+	struct completion uses_zero;
 	u32 client_id;
 
 	/* kverbs are not required by the client */
diff --git a/include/rdma/rdmavt_qp.h b/include/rdma/rdmavt_qp.h
index 0eeea520a853..e06c77d76463 100644
--- a/include/rdma/rdmavt_qp.h
+++ b/include/rdma/rdmavt_qp.h
@@ -608,7 +608,7 @@ static inline void rvt_qp_wqe_reserve(
 /**
  * rvt_qp_wqe_unreserve - clean reserved operation
  * @qp - the rvt qp
- * @wqe - the send wqe
+ * @flags - send wqe flags
  *
  * This decrements the reserve use count.
  *
@@ -620,11 +620,9 @@ static inline void rvt_qp_wqe_reserve(
  * the compiler does not juggle the order of the s_last
  * ring index and the decrementing of s_reserved_used.
  */
-static inline void rvt_qp_wqe_unreserve(
-	struct rvt_qp *qp,
-	struct rvt_swqe *wqe)
+static inline void rvt_qp_wqe_unreserve(struct rvt_qp *qp, int flags)
 {
-	if (unlikely(wqe->wr.send_flags & RVT_SEND_RESERVE_USED)) {
+	if (unlikely(flags & RVT_SEND_RESERVE_USED)) {
 		atomic_dec(&qp->s_reserved_used);
 		/* insure no compiler re-order up to s_last change */
 		smp_mb__after_atomic();
@@ -853,6 +851,7 @@ rvt_qp_complete_swqe(struct rvt_qp *qp,
 	u32 byte_len, last;
 	int flags = wqe->wr.send_flags;
 
+	rvt_qp_wqe_unreserve(qp, flags);
 	rvt_put_qp_swqe(qp, wqe);
 
 	need_completion =