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
  ...

1 files changed, 19 insertions, 101 deletions

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 7f04754c7f2b..72120061b7d4 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -166,8 +166,6 @@ static inline int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 #define MIGRATE_PFN_MIGRATE	(1UL << 1)
 #define MIGRATE_PFN_LOCKED	(1UL << 2)
 #define MIGRATE_PFN_WRITE	(1UL << 3)
-#define MIGRATE_PFN_DEVICE	(1UL << 4)
-#define MIGRATE_PFN_ERROR	(1UL << 5)
 #define MIGRATE_PFN_SHIFT	6
 
 static inline struct page *migrate_pfn_to_page(unsigned long mpfn)
@@ -182,107 +180,27 @@ static inline unsigned long migrate_pfn(unsigned long pfn)
 	return (pfn << MIGRATE_PFN_SHIFT) | MIGRATE_PFN_VALID;
 }
 
-/*
- * struct migrate_vma_ops - migrate operation callback
- *
- * @alloc_and_copy: alloc destination memory and copy source memory to it
- * @finalize_and_map: allow caller to map the successfully migrated pages
- *
- *
- * The alloc_and_copy() callback happens once all source pages have been locked,
- * unmapped and checked (checked whether pinned or not). All pages that can be
- * migrated will have an entry in the src array set with the pfn value of the
- * page and with the MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE flag set (other
- * flags might be set but should be ignored by the callback).
- *
- * The alloc_and_copy() callback can then allocate destination memory and copy
- * source memory to it for all those entries (ie with MIGRATE_PFN_VALID and
- * MIGRATE_PFN_MIGRATE flag set). Once these are allocated and copied, the
- * callback must update each corresponding entry in the dst array with the pfn
- * value of the destination page and with the MIGRATE_PFN_VALID and
- * MIGRATE_PFN_LOCKED flags set (destination pages must have their struct pages
- * locked, via lock_page()).
- *
- * At this point the alloc_and_copy() callback is done and returns.
- *
- * Note that the callback does not have to migrate all the pages that are
- * marked with MIGRATE_PFN_MIGRATE flag in src array unless this is a migration
- * from device memory to system memory (ie the MIGRATE_PFN_DEVICE flag is also
- * set in the src array entry). If the device driver cannot migrate a device
- * page back to system memory, then it must set the corresponding dst array
- * entry to MIGRATE_PFN_ERROR. This will trigger a SIGBUS if CPU tries to
- * access any of the virtual addresses originally backed by this page. Because
- * a SIGBUS is such a severe result for the userspace process, the device
- * driver should avoid setting MIGRATE_PFN_ERROR unless it is really in an
- * unrecoverable state.
- *
- * For empty entry inside CPU page table (pte_none() or pmd_none() is true) we
- * do set MIGRATE_PFN_MIGRATE flag inside the corresponding source array thus
- * allowing device driver to allocate device memory for those unback virtual
- * address. For this the device driver simply have to allocate device memory
- * and properly set the destination entry like for regular migration. Note that
- * this can still fails and thus inside the device driver must check if the
- * migration was successful for those entry inside the finalize_and_map()
- * callback just like for regular migration.
- *
- * THE alloc_and_copy() CALLBACK MUST NOT CHANGE ANY OF THE SRC ARRAY ENTRIES
- * OR BAD THINGS WILL HAPPEN !
- *
- *
- * The finalize_and_map() callback happens after struct page migration from
- * source to destination (destination struct pages are the struct pages for the
- * memory allocated by the alloc_and_copy() callback).  Migration can fail, and
- * thus the finalize_and_map() allows the driver to inspect which pages were
- * successfully migrated, and which were not. Successfully migrated pages will
- * have the MIGRATE_PFN_MIGRATE flag set for their src array entry.
- *
- * It is safe to update device page table from within the finalize_and_map()
- * callback because both destination and source page are still locked, and the
- * mmap_sem is held in read mode (hence no one can unmap the range being
- * migrated).
- *
- * Once callback is done cleaning up things and updating its page table (if it
- * chose to do so, this is not an obligation) then it returns. At this point,
- * the HMM core will finish up the final steps, and the migration is complete.
- *
- * THE finalize_and_map() CALLBACK MUST NOT CHANGE ANY OF THE SRC OR DST ARRAY
- * ENTRIES OR BAD THINGS WILL HAPPEN !
- */
-struct migrate_vma_ops {
-	void (*alloc_and_copy)(struct vm_area_struct *vma,
-			       const unsigned long *src,
-			       unsigned long *dst,
-			       unsigned long start,
-			       unsigned long end,
-			       void *private);
-	void (*finalize_and_map)(struct vm_area_struct *vma,
-				 const unsigned long *src,
-				 const unsigned long *dst,
-				 unsigned long start,
-				 unsigned long end,
-				 void *private);
+struct migrate_vma {
+	struct vm_area_struct	*vma;
+	/*
+	 * Both src and dst array must be big enough for
+	 * (end - start) >> PAGE_SHIFT entries.
+	 *
+	 * The src array must not be modified by the caller after
+	 * migrate_vma_setup(), and must not change the dst array after
+	 * migrate_vma_pages() returns.
+	 */
+	unsigned long		*dst;
+	unsigned long		*src;
+	unsigned long		cpages;
+	unsigned long		npages;
+	unsigned long		start;
+	unsigned long		end;
 };
 
-#if defined(CONFIG_MIGRATE_VMA_HELPER)
-int migrate_vma(const struct migrate_vma_ops *ops,
-		struct vm_area_struct *vma,
-		unsigned long start,
-		unsigned long end,
-		unsigned long *src,
-		unsigned long *dst,
-		void *private);
-#else
-static inline int migrate_vma(const struct migrate_vma_ops *ops,
-			      struct vm_area_struct *vma,
-			      unsigned long start,
-			      unsigned long end,
-			      unsigned long *src,
-			      unsigned long *dst,
-			      void *private)
-{
-	return -EINVAL;
-}
-#endif /* IS_ENABLED(CONFIG_MIGRATE_VMA_HELPER) */
+int migrate_vma_setup(struct migrate_vma *args);
+void migrate_vma_pages(struct migrate_vma *migrate);
+void migrate_vma_finalize(struct migrate_vma *migrate);
 
 #endif /* CONFIG_MIGRATION */