mm/hmm/test: use the new migration invalidation

Use the new MMU_NOTIFY_MIGRATE event to skip MMU invalidations of device
private memory and handle the invalidation in the driver as part of
migrating device private memory.

Link: https://lore.kernel.org/r/20200723223004.9586-6-rcampbell@nvidia.com
Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

Author: Ralph Campbell

lib/test_hmm.c

@@ -214,6 +214,14 @@ static bool dmirror_interval_invalidate(struct mmu_interval_notifier *mni,
 {
 	struct dmirror *dmirror = container_of(mni, struct dmirror, notifier);
 
+	/*
+	 * Ignore invalidation callbacks for device private pages since
+	 * the invalidation is handled as part of the migration process.
+	 */
+	if (range->event == MMU_NOTIFY_MIGRATE &&
+	    range->migrate_pgmap_owner == dmirror->mdevice)
+		return true;
+
 	if (mmu_notifier_range_blockable(range))
 		mutex_lock(&dmirror->mutex);
 	else if (!mutex_trylock(&dmirror->mutex))
@@ -693,7 +701,7 @@ static int dmirror_migrate(struct dmirror *dmirror,
 		args.dst = dst_pfns;
 		args.start = addr;
 		args.end = next;
-		args.pgmap_owner = NULL;
+		args.pgmap_owner = dmirror->mdevice;
 		args.flags = MIGRATE_VMA_SELECT_SYSTEM;
 		ret = migrate_vma_setup(&args);
 		if (ret)
@@ -983,7 +991,7 @@ static void dmirror_devmem_free(struct page *page)
 }
 
 static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args,
-						struct dmirror_device *mdevice)
+						      struct dmirror *dmirror)
 {
 	const unsigned long *src = args->src;
 	unsigned long *dst = args->dst;
@@ -1005,6 +1013,7 @@ static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args,
 			continue;
 
 		lock_page(dpage);
+		xa_erase(&dmirror->pt, addr >> PAGE_SHIFT);
 		copy_highpage(dpage, spage);
 		*dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED;
 		if (*src & MIGRATE_PFN_WRITE)
@@ -1013,15 +1022,6 @@ static vm_fault_t dmirror_devmem_fault_alloc_and_copy(struct migrate_vma *args,
 	return 0;
 }
 
-static void dmirror_devmem_fault_finalize_and_map(struct migrate_vma *args,
-						  struct dmirror *dmirror)
-{
-	/* Invalidate the device's page table mapping. */
-	mutex_lock(&dmirror->mutex);
-	dmirror_do_update(dmirror, args->start, args->end);
-	mutex_unlock(&dmirror->mutex);
-}
-
 static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf)
 {
 	struct migrate_vma args;
@@ -1051,11 +1051,15 @@ static vm_fault_t dmirror_devmem_fault(struct vm_fault *vmf)
 	if (migrate_vma_setup(&args))
 		return VM_FAULT_SIGBUS;
 
-	ret = dmirror_devmem_fault_alloc_and_copy(&args, dmirror->mdevice);
+	ret = dmirror_devmem_fault_alloc_and_copy(&args, dmirror);
 	if (ret)
 		return ret;
 	migrate_vma_pages(&args);
-	dmirror_devmem_fault_finalize_and_map(&args, dmirror);
+	/*
+	 * No device finalize step is needed since
+	 * dmirror_devmem_fault_alloc_and_copy() will have already
+	 * invalidated the device page table.
+	 */
 	migrate_vma_finalize(&args);
 	return 0;
 }

tools/testing/selftests/vm/hmm-tests.c

@@ -881,8 +881,9 @@ TEST_F(hmm, migrate)
 }
 
 /*
- * Migrate anonymous memory to device private memory and fault it back to system
- * memory.
+ * Migrate anonymous memory to device private memory and fault some of it back
+ * to system memory, then try migrating the resulting mix of system and device
+ * private memory to the device.
  */
 TEST_F(hmm, migrate_fault)
 {
@@ -924,8 +925,17 @@ TEST_F(hmm, migrate_fault)
 	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
 		ASSERT_EQ(ptr[i], i);
 
-	/* Fault pages back to system memory and check them. */
-	for (i = 0, ptr = buffer->ptr; i < size / sizeof(*ptr); ++i)
+	/* Fault half the pages back to system memory and check them. */
+	for (i = 0, ptr = buffer->ptr; i < size / (2 * sizeof(*ptr)); ++i)
+		ASSERT_EQ(ptr[i], i);
+
+	/* Migrate memory to the device again. */
+	ret = hmm_dmirror_cmd(self->fd, HMM_DMIRROR_MIGRATE, buffer, npages);
+	ASSERT_EQ(ret, 0);
+	ASSERT_EQ(buffer->cpages, npages);
+
+	/* Check what the device read. */
+	for (i = 0, ptr = buffer->mirror; i < size / sizeof(*ptr); ++i)
 		ASSERT_EQ(ptr[i], i);
 
 	hmm_buffer_free(buffer);