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

Pull hmm updates from Jason Gunthorpe:
 "Ralph has been working on nouveau's use of hmm_range_fault() and
  migrate_vma() which resulted in this small series. It adds reporting
  of the page table order from hmm_range_fault() and some optimization
  of migrate_vma():

   - Report the size of the page table mapping out of hmm_range_fault().

     This makes it easier to establish a large/huge/etc mapping in the
     device's page table.

   - Allow devices to ignore the invalidations during migration in cases
     where the migration is not going to change pages.

     For instance migrating pages to a device does not require the
     device to invalidate pages already in the device.

   - Update nouveau and hmm_tests to use the above"

* tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
  mm/hmm/test: use the new migration invalidation
  nouveau/svm: use the new migration invalidation
  mm/notifier: add migration invalidation type
  mm/migrate: add a flags parameter to migrate_vma
  nouveau: fix storing invalid ptes
  nouveau/hmm: support mapping large sysmem pages
  nouveau: fix mapping 2MB sysmem pages
  nouveau/hmm: fault one page at a time
  mm/hmm: add tests for hmm_pfn_to_map_order()
  mm/hmm: provide the page mapping order in hmm_range_fault()

3 files changed, 40 insertions, 6 deletions

diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index f4a09ed223ac..866a0fa104c4 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -37,16 +37,17 @@
  *                     will fail. Must be combined with HMM_PFN_REQ_FAULT.
  */
 enum hmm_pfn_flags {
-	/* Output flags */
+	/* Output fields and flags */
 	HMM_PFN_VALID = 1UL << (BITS_PER_LONG - 1),
 	HMM_PFN_WRITE = 1UL << (BITS_PER_LONG - 2),
 	HMM_PFN_ERROR = 1UL << (BITS_PER_LONG - 3),
+	HMM_PFN_ORDER_SHIFT = (BITS_PER_LONG - 8),
 
 	/* Input flags */
 	HMM_PFN_REQ_FAULT = HMM_PFN_VALID,
 	HMM_PFN_REQ_WRITE = HMM_PFN_WRITE,
 
-	HMM_PFN_FLAGS = HMM_PFN_VALID | HMM_PFN_WRITE | HMM_PFN_ERROR,
+	HMM_PFN_FLAGS = 0xFFUL << HMM_PFN_ORDER_SHIFT,
 };
 
 /*
@@ -62,6 +63,25 @@ static inline struct page *hmm_pfn_to_page(unsigned long hmm_pfn)
 }
 
 /*
+ * hmm_pfn_to_map_order() - return the CPU mapping size order
+ *
+ * This is optionally useful to optimize processing of the pfn result
+ * array. It indicates that the page starts at the order aligned VA and is
+ * 1<<order bytes long.  Every pfn within an high order page will have the
+ * same pfn flags, both access protections and the map_order.  The caller must
+ * be careful with edge cases as the start and end VA of the given page may
+ * extend past the range used with hmm_range_fault().
+ *
+ * This must be called under the caller 'user_lock' after a successful
+ * mmu_interval_read_begin(). The caller must have tested for HMM_PFN_VALID
+ * already.
+ */
+static inline unsigned int hmm_pfn_to_map_order(unsigned long hmm_pfn)
+{
+	return (hmm_pfn >> HMM_PFN_ORDER_SHIFT) & 0x1F;
+}
+
+/*
  * struct hmm_range - track invalidation lock on virtual address range
  *
  * @notifier: a mmu_interval_notifier that includes the start/end
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 3e546cbf03dd..540998d9810b 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -180,6 +180,11 @@ static inline unsigned long migrate_pfn(unsigned long pfn)
 	return (pfn << MIGRATE_PFN_SHIFT) | MIGRATE_PFN_VALID;
 }
 
+enum migrate_vma_direction {
+	MIGRATE_VMA_SELECT_SYSTEM = 1 << 0,
+	MIGRATE_VMA_SELECT_DEVICE_PRIVATE = 1 << 1,
+};
+
 struct migrate_vma {
 	struct vm_area_struct	*vma;
 	/*
@@ -199,11 +204,14 @@ struct migrate_vma {
 
 	/*
 	 * Set to the owner value also stored in page->pgmap->owner for
-	 * migrating out of device private memory.  If set only device
-	 * private pages with this owner are migrated.  If not set
-	 * device private pages are not migrated at all.
+	 * migrating out of device private memory. The flags also need to
+	 * be set to MIGRATE_VMA_SELECT_DEVICE_PRIVATE.
+	 * The caller should always set this field when using mmu notifier
+	 * callbacks to avoid device MMU invalidations for device private
+	 * pages that are not being migrated.
 	 */
-	void			*src_owner;
+	void			*pgmap_owner;
+	unsigned long		flags;
 };
 
 int migrate_vma_setup(struct migrate_vma *args);
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index fc68f3570e19..c6f0708195cd 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -38,6 +38,10 @@ struct mmu_interval_notifier;
  *
  * @MMU_NOTIFY_RELEASE: used during mmu_interval_notifier invalidate to signal
  * that the mm refcount is zero and the range is no longer accessible.
+ *
+ * @MMU_NOTIFY_MIGRATE: used during migrate_vma_collect() invalidate to signal
+ * a device driver to possibly ignore the invalidation if the
+ * migrate_pgmap_owner field matches the driver's device private pgmap owner.
  */
 enum mmu_notifier_event {
 	MMU_NOTIFY_UNMAP = 0,
@@ -46,6 +50,7 @@ enum mmu_notifier_event {
 	MMU_NOTIFY_PROTECTION_PAGE,
 	MMU_NOTIFY_SOFT_DIRTY,
 	MMU_NOTIFY_RELEASE,
+	MMU_NOTIFY_MIGRATE,
 };
 
 #define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0)
@@ -264,6 +269,7 @@ struct mmu_notifier_range {
 	unsigned long end;
 	unsigned flags;
 	enum mmu_notifier_event event;
+	void *migrate_pgmap_owner;
 };
 
 static inline int mm_has_notifiers(struct mm_struct *mm)