RDMA/odp: Use mmu_interval_notifier_insert()

Replace the internal interval tree based mmu notifier with the new common
mmu_interval_notifier_insert() API. This removes a lot of code and fixes a
deadlock that can be triggered in ODP:

 zap_page_range()
  mmu_notifier_invalidate_range_start()
   [..]
    ib_umem_notifier_invalidate_range_start()
       down_read(&per_mm->umem_rwsem)
  unmap_single_vma()
    [..]
      __split_huge_page_pmd()
        mmu_notifier_invalidate_range_start()
        [..]
           ib_umem_notifier_invalidate_range_start()
              down_read(&per_mm->umem_rwsem)   // DEADLOCK

        mmu_notifier_invalidate_range_end()
           up_read(&per_mm->umem_rwsem)
  mmu_notifier_invalidate_range_end()
     up_read(&per_mm->umem_rwsem)

The umem_rwsem is held across the range_start/end as the ODP algorithm for
invalidate_range_end cannot tolerate changes to the interval
tree. However, due to the nested invalidation regions the second
down_read() can deadlock if there are competing writers. The new core code
provides an alternative scheme to solve this problem.

Fixes: ca748c39ea3f ("RDMA/umem: Get rid of per_mm->notifier_count")
Link: https://lore.kernel.org/r/20191112202231.3856-6-jgg@ziepe.ca
Tested-by: Artemy Kovalyov <artemyko@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

2 files changed, 14 insertions, 56 deletions

diff --git a/include/rdma/ib_umem_odp.h b/include/rdma/ib_umem_odp.h
index 09b0e4494986..81429acc8257 100644
--- a/include/rdma/ib_umem_odp.h
+++ b/include/rdma/ib_umem_odp.h
@@ -35,11 +35,11 @@
 
 #include <rdma/ib_umem.h>
 #include <rdma/ib_verbs.h>
-#include <linux/interval_tree.h>
 
 struct ib_umem_odp {
 	struct ib_umem umem;
-	struct ib_ucontext_per_mm *per_mm;
+	struct mmu_interval_notifier notifier;
+	struct pid *tgid;
 
 	/*
 	 * An array of the pages included in the on-demand paging umem.
@@ -62,13 +62,8 @@ struct ib_umem_odp {
 	struct mutex		umem_mutex;
 	void			*private; /* for the HW driver to use. */
 
-	int notifiers_seq;
-	int notifiers_count;
 	int npages;
 
-	/* Tree tracking */
-	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:
@@ -77,7 +72,6 @@ struct ib_umem_odp {
 	 */
 	bool is_implicit_odp;
 
-	struct completion	notifier_completion;
 	unsigned int		page_shift;
 };
 
@@ -89,13 +83,13 @@ 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 umem_odp->interval_tree.start;
+	return umem_odp->notifier.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 umem_odp->interval_tree.last + 1;
+	return umem_odp->notifier.interval_tree.last + 1;
 }
 
 static inline size_t ib_umem_odp_num_pages(struct ib_umem_odp *umem_odp)
@@ -119,21 +113,15 @@ 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 mmu_notifier mn;
-	struct pid *tgid;
-
-	struct rb_root_cached umem_tree;
-	/* Protects umem_tree */
-	struct rw_semaphore umem_rwsem;
-};
-
-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_get(struct ib_udata *udata, 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,
 					       int access);
-struct ib_umem_odp *ib_umem_odp_alloc_child(struct ib_umem_odp *root_umem,
-					    unsigned long addr, size_t size);
+struct ib_umem_odp *
+ib_umem_odp_alloc_child(struct ib_umem_odp *root_umem, unsigned long addr,
+			size_t size,
+			const struct mmu_interval_notifier_ops *ops);
 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,
@@ -143,39 +131,11 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 start_offset,
 void ib_umem_odp_unmap_dma_pages(struct ib_umem_odp *umem_odp, u64 start_offset,
 				 u64 bound);
 
-typedef int (*umem_call_back)(struct ib_umem_odp *item, u64 start, u64 end,
-			      void *cookie);
-/*
- * Call the callback on each ib_umem in the range. Returns the logical or of
- * the return values of the functions called.
- */
-int rbt_ib_umem_for_each_in_range(struct rb_root_cached *root,
-				  u64 start, u64 end,
-				  umem_call_back cb,
-				  bool blockable, void *cookie);
-
-static inline int ib_umem_mmu_notifier_retry(struct ib_umem_odp *umem_odp,
-					     unsigned long mmu_seq)
-{
-	/*
-	 * This code is strongly based on the KVM code from
-	 * mmu_notifier_retry. Should be called with
-	 * the relevant locks taken (umem_odp->umem_mutex
-	 * and the ucontext umem_mutex semaphore locked for read).
-	 */
-
-	if (unlikely(umem_odp->notifiers_count))
-		return 1;
-	if (umem_odp->notifiers_seq != mmu_seq)
-		return 1;
-	return 0;
-}
-
 #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, int access)
+static inline struct ib_umem_odp *
+ib_umem_odp_get(struct ib_udata *udata, 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 6a47ba85c54c..2c30c859ae0d 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -2422,8 +2422,6 @@ 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,