Merge tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull hmm updates from Jason Gunthorpe:
 "This is more cleanup and consolidation of the hmm APIs and the very
  strongly related mmu_notifier interfaces. Many places across the tree
  using these interfaces are touched in the process. Beyond that a
  cleanup to the page walker API and a few memremap related changes
  round out the series:

   - General improvement of hmm_range_fault() and related APIs, more
     documentation, bug fixes from testing, API simplification &
     consolidation, and unused API removal

   - Simplify the hmm related kconfigs to HMM_MIRROR and DEVICE_PRIVATE,
     and make them internal kconfig selects

   - Hoist a lot of code related to mmu notifier attachment out of
     drivers by using a refcount get/put attachment idiom and remove the
     convoluted mmu_notifier_unregister_no_release() and related APIs.

   - General API improvement for the migrate_vma API and revision of its
     only user in nouveau

   - Annotate mmu_notifiers with lockdep and sleeping region debugging

  Two series unrelated to HMM or mmu_notifiers came along due to
  dependencies:

   - Allow pagemap's memremap_pages family of APIs to work without
     providing a struct device

   - Make walk_page_range() and related use a constant structure for
     function pointers"

* tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (75 commits)
  libnvdimm: Enable unit test infrastructure compile checks
  mm, notifier: Catch sleeping/blocking for !blockable
  kernel.h: Add non_block_start/end()
  drm/radeon: guard against calling an unpaired radeon_mn_unregister()
  csky: add missing brackets in a macro for tlb.h
  pagewalk: use lockdep_assert_held for locking validation
  pagewalk: separate function pointers from iterator data
  mm: split out a new pagewalk.h header from mm.h
  mm/mmu_notifiers: annotate with might_sleep()
  mm/mmu_notifiers: prime lockdep
  mm/mmu_notifiers: add a lockdep map for invalidate_range_start/end
  mm/mmu_notifiers: remove the __mmu_notifier_invalidate_range_start/end exports
  mm/hmm: hmm_range_fault() infinite loop
  mm/hmm: hmm_range_fault() NULL pointer bug
  mm/hmm: fix hmm_range_fault()'s handling of swapped out pages
  mm/mmu_notifiers: remove unregister_no_release
  RDMA/odp: remove ib_ucontext from ib_umem
  RDMA/odp: use mmu_notifier_get/put for 'struct ib_ucontext_per_mm'
  RDMA/mlx5: Use odp instead of mr->umem in pagefault_mr
  RDMA/mlx5: Use ib_umem_start instead of umem.address
  ...

3 files changed, 36 insertions, 31 deletions

diff --git a/include/rdma/ib_umem.h b/include/rdma/ib_umem.h
index 1052d0d62be7..a91b2af64ec4 100644
--- a/include/rdma/ib_umem.h
+++ b/include/rdma/ib_umem.h
@@ -42,7 +42,7 @@ struct ib_ucontext;
 struct ib_umem_odp;
 
 struct ib_umem {
-	struct ib_ucontext     *context;
+	struct ib_device       *ibdev;
 	struct mm_struct       *owning_mm;
 	size_t			length;
 	unsigned long		address;
diff --git a/include/rdma/ib_umem_odp.h b/include/rdma/ib_umem_odp.h
index 479db5c98ff6..253df1a1fa54 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)
@@ -120,25 +122,20 @@ static inline size_t ib_umem_odp_num_pages(struct ib_umem_odp *umem_odp)
 #ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
 
 struct ib_ucontext_per_mm {
-	struct ib_ucontext *context;
-	struct mm_struct *mm;
+	struct mmu_notifier mn;
 	struct pid *tgid;
-	bool active;
 
 	struct rb_root_cached umem_tree;
 	/* Protects umem_tree */
 	struct rw_semaphore umem_rwsem;
-
-	struct mmu_notifier mn;
-	unsigned int odp_mrs_count;
-
-	struct list_head ucontext_list;
-	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 +160,17 @@ 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 +191,11 @@ 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 4f225175cb91..f659f4a02aa9 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1417,11 +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;
-
 	struct ib_rdmacg_object	cg_obj;
 	/*
 	 * Implementation details of the RDMA core, don't use in drivers:
@@ -2378,6 +2373,8 @@ 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,