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
  ...

6 files changed, 62 insertions, 81 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/Kconfig b/drivers/gpu/drm/amd/amdgpu/Kconfig
index f6e5c0282fc1..2e98c016cb47 100644
--- a/drivers/gpu/drm/amd/amdgpu/Kconfig
+++ b/drivers/gpu/drm/amd/amdgpu/Kconfig
@@ -27,7 +27,9 @@ config DRM_AMDGPU_CIK
 config DRM_AMDGPU_USERPTR
 	bool "Always enable userptr write support"
 	depends on DRM_AMDGPU
-	depends on HMM_MIRROR
+	depends on MMU
+	select HMM_MIRROR
+	select MMU_NOTIFIER
 	help
 	  This option selects CONFIG_HMM and CONFIG_HMM_MIRROR if it
 	  isn't already selected to enabled full userptr support.
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 48a2070e72f2..bdf849da32e4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -35,6 +35,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/vga_switcheroo.h>
 #include <drm/drm_probe_helper.h>
+#include <linux/mmu_notifier.h>
 
 #include "amdgpu.h"
 #include "amdgpu_irq.h"
@@ -1469,6 +1470,7 @@ static void __exit amdgpu_exit(void)
 	amdgpu_unregister_atpx_handler();
 	amdgpu_sync_fini();
 	amdgpu_fence_slab_fini();
+	mmu_notifier_synchronize();
 }
 
 module_init(amdgpu_init);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
index f1f8cdd695d3..31d4deb5d294 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
@@ -195,13 +195,14 @@ static void amdgpu_mn_invalidate_node(struct amdgpu_mn_node *node,
  * Block for operations on BOs to finish and mark pages as accessed and
  * potentially dirty.
  */
-static int amdgpu_mn_sync_pagetables_gfx(struct hmm_mirror *mirror,
-			const struct hmm_update *update)
+static int
+amdgpu_mn_sync_pagetables_gfx(struct hmm_mirror *mirror,
+			      const struct mmu_notifier_range *update)
 {
 	struct amdgpu_mn *amn = container_of(mirror, struct amdgpu_mn, mirror);
 	unsigned long start = update->start;
 	unsigned long end = update->end;
-	bool blockable = update->blockable;
+	bool blockable = mmu_notifier_range_blockable(update);
 	struct interval_tree_node *it;
 
 	/* notification is exclusive, but interval is inclusive */
@@ -243,13 +244,14 @@ static int amdgpu_mn_sync_pagetables_gfx(struct hmm_mirror *mirror,
  * necessitates evicting all user-mode queues of the process. The BOs
  * are restorted in amdgpu_mn_invalidate_range_end_hsa.
  */
-static int amdgpu_mn_sync_pagetables_hsa(struct hmm_mirror *mirror,
-			const struct hmm_update *update)
+static int
+amdgpu_mn_sync_pagetables_hsa(struct hmm_mirror *mirror,
+			      const struct mmu_notifier_range *update)
 {
 	struct amdgpu_mn *amn = container_of(mirror, struct amdgpu_mn, mirror);
 	unsigned long start = update->start;
 	unsigned long end = update->end;
-	bool blockable = update->blockable;
+	bool blockable = mmu_notifier_range_blockable(update);
 	struct interval_tree_node *it;
 
 	/* notification is exclusive, but interval is inclusive */
@@ -482,6 +484,5 @@ void amdgpu_hmm_init_range(struct hmm_range *range)
 		range->flags = hmm_range_flags;
 		range->values = hmm_range_values;
 		range->pfn_shift = PAGE_SHIFT;
-		INIT_LIST_HEAD(&range->list);
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 13b144c8f67d..dff41d0a85fe 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -794,7 +794,6 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
 	struct hmm_range *range;
 	unsigned long i;
 	uint64_t *pfns;
-	int retry = 0;
 	int r = 0;
 
 	if (!mm) /* Happens during process shutdown */
@@ -835,10 +834,11 @@ int amdgpu_ttm_tt_get_user_pages(struct amdgpu_bo *bo, struct page **pages)
 				0 : range->flags[HMM_PFN_WRITE];
 	range->pfn_flags_mask = 0;
 	range->pfns = pfns;
-	hmm_range_register(range, mirror, start,
-			   start + ttm->num_pages * PAGE_SIZE, PAGE_SHIFT);
+	range->start = start;
+	range->end = start + ttm->num_pages * PAGE_SIZE;
+
+	hmm_range_register(range, mirror);
 
-retry:
 	/*
 	 * Just wait for range to be valid, safe to ignore return value as we
 	 * will use the return value of hmm_range_fault() below under the
@@ -847,24 +847,12 @@ retry:
 	hmm_range_wait_until_valid(range, HMM_RANGE_DEFAULT_TIMEOUT);
 
 	down_read(&mm->mmap_sem);
-
-	r = hmm_range_fault(range, true);
-	if (unlikely(r < 0)) {
-		if (likely(r == -EAGAIN)) {
-			/*
-			 * return -EAGAIN, mmap_sem is dropped
-			 */
-			if (retry++ < MAX_RETRY_HMM_RANGE_FAULT)
-				goto retry;
-			else
-				pr_err("Retry hmm fault too many times\n");
-		}
-
-		goto out_up_read;
-	}
-
+	r = hmm_range_fault(range, 0);
 	up_read(&mm->mmap_sem);
 
+	if (unlikely(r < 0))
+		goto out_free_pfns;
+
 	for (i = 0; i < ttm->num_pages; i++) {
 		pages[i] = hmm_device_entry_to_page(range, pfns[i]);
 		if (unlikely(!pages[i])) {
@@ -880,9 +868,6 @@ retry:
 
 	return 0;
 
-out_up_read:
-	if (likely(r != -EAGAIN))
-		up_read(&mm->mmap_sem);
 out_free_pfns:
 	hmm_range_unregister(range);
 	kvfree(pfns);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 3bb75d11a662..c89326125d71 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -687,9 +687,6 @@ struct kfd_process {
 	/* We want to receive a notification when the mm_struct is destroyed */
 	struct mmu_notifier mmu_notifier;
 
-	/* Use for delayed freeing of kfd_process structure */
-	struct rcu_head	rcu;
-
 	unsigned int pasid;
 	unsigned int doorbell_index;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 0c6ac043ae3c..40e3fc0c6942 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -62,8 +62,8 @@ static struct workqueue_struct *kfd_restore_wq;
 
 static struct kfd_process *find_process(const struct task_struct *thread);
 static void kfd_process_ref_release(struct kref *ref);
-static struct kfd_process *create_process(const struct task_struct *thread,
-					struct file *filep);
+static struct kfd_process *create_process(const struct task_struct *thread);
+static int kfd_process_init_cwsr_apu(struct kfd_process *p, struct file *filep);
 
 static void evict_process_worker(struct work_struct *work);
 static void restore_process_worker(struct work_struct *work);
@@ -289,7 +289,15 @@ struct kfd_process *kfd_create_process(struct file *filep)
 	if (process) {
 		pr_debug("Process already found\n");
 	} else {
-		process = create_process(thread, filep);
+		process = create_process(thread);
+		if (IS_ERR(process))
+			goto out;
+
+		ret = kfd_process_init_cwsr_apu(process, filep);
+		if (ret) {
+			process = ERR_PTR(ret);
+			goto out;
+		}
 
 		if (!procfs.kobj)
 			goto out;
@@ -478,11 +486,9 @@ static void kfd_process_ref_release(struct kref *ref)
 	queue_work(kfd_process_wq, &p->release_work);
 }
 
-static void kfd_process_destroy_delayed(struct rcu_head *rcu)
+static void kfd_process_free_notifier(struct mmu_notifier *mn)
 {
-	struct kfd_process *p = container_of(rcu, struct kfd_process, rcu);
-
-	kfd_unref_process(p);
+	kfd_unref_process(container_of(mn, struct kfd_process, mmu_notifier));
 }
 
 static void kfd_process_notifier_release(struct mmu_notifier *mn,
@@ -534,12 +540,12 @@ static void kfd_process_notifier_release(struct mmu_notifier *mn,
 
 	mutex_unlock(&p->mutex);
 
-	mmu_notifier_unregister_no_release(&p->mmu_notifier, mm);
-	mmu_notifier_call_srcu(&p->rcu, &kfd_process_destroy_delayed);
+	mmu_notifier_put(&p->mmu_notifier);
 }
 
 static const struct mmu_notifier_ops kfd_process_mmu_notifier_ops = {
 	.release = kfd_process_notifier_release,
+	.free_notifier = kfd_process_free_notifier,
 };
 
 static int kfd_process_init_cwsr_apu(struct kfd_process *p, struct file *filep)
@@ -609,81 +615,69 @@ static int kfd_process_device_init_cwsr_dgpu(struct kfd_process_device *pdd)
 	return 0;
 }
 
-static struct kfd_process *create_process(const struct task_struct *thread,
-					struct file *filep)
+/*
+ * On return the kfd_process is fully operational and will be freed when the
+ * mm is released
+ */
+static struct kfd_process *create_process(const struct task_struct *thread)
 {
 	struct kfd_process *process;
 	int err = -ENOMEM;
 
 	process = kzalloc(sizeof(*process), GFP_KERNEL);
-
 	if (!process)
 		goto err_alloc_process;
 
-	process->pasid = kfd_pasid_alloc();
-	if (process->pasid == 0)
-		goto err_alloc_pasid;
-
-	if (kfd_alloc_process_doorbells(process) < 0)
-		goto err_alloc_doorbells;
-
 	kref_init(&process->ref);
-
 	mutex_init(&process->mutex);
-
 	process->mm = thread->mm;
-
-	/* register notifier */
-	process->mmu_notifier.ops = &kfd_process_mmu_notifier_ops;
-	err = mmu_notifier_register(&process->mmu_notifier, process->mm);
-	if (err)
-		goto err_mmu_notifier;
-
-	hash_add_rcu(kfd_processes_table, &process->kfd_processes,
-			(uintptr_t)process->mm);
-
 	process->lead_thread = thread->group_leader;
-	get_task_struct(process->lead_thread);
-
 	INIT_LIST_HEAD(&process->per_device_data);
-
+	INIT_DELAYED_WORK(&process->eviction_work, evict_process_worker);
+	INIT_DELAYED_WORK(&process->restore_work, restore_process_worker);
+	process->last_restore_timestamp = get_jiffies_64();
 	kfd_event_init_process(process);
+	process->is_32bit_user_mode = in_compat_syscall();
+
+	process->pasid = kfd_pasid_alloc();
+	if (process->pasid == 0)
+		goto err_alloc_pasid;
+
+	if (kfd_alloc_process_doorbells(process) < 0)
+		goto err_alloc_doorbells;
 
 	err = pqm_init(&process->pqm, process);
 	if (err != 0)
 		goto err_process_pqm_init;
 
 	/* init process apertures*/
-	process->is_32bit_user_mode = in_compat_syscall();
 	err = kfd_init_apertures(process);
 	if (err != 0)
 		goto err_init_apertures;
 
-	INIT_DELAYED_WORK(&process->eviction_work, evict_process_worker);
-	INIT_DELAYED_WORK(&process->restore_work, restore_process_worker);
-	process->last_restore_timestamp = get_jiffies_64();
-
-	err = kfd_process_init_cwsr_apu(process, filep);
+	/* Must be last, have to use release destruction after this */
+	process->mmu_notifier.ops = &kfd_process_mmu_notifier_ops;
+	err = mmu_notifier_register(&process->mmu_notifier, process->mm);
 	if (err)
-		goto err_init_cwsr;
+		goto err_register_notifier;
+
+	get_task_struct(process->lead_thread);
+	hash_add_rcu(kfd_processes_table, &process->kfd_processes,
+			(uintptr_t)process->mm);
 
 	return process;
 
-err_init_cwsr:
+err_register_notifier:
 	kfd_process_free_outstanding_kfd_bos(process);
 	kfd_process_destroy_pdds(process);
 err_init_apertures:
 	pqm_uninit(&process->pqm);
 err_process_pqm_init:
-	hash_del_rcu(&process->kfd_processes);
-	synchronize_rcu();
-	mmu_notifier_unregister_no_release(&process->mmu_notifier, process->mm);
-err_mmu_notifier:
-	mutex_destroy(&process->mutex);
 	kfd_free_process_doorbells(process);
 err_alloc_doorbells:
 	kfd_pasid_free(process->pasid);
 err_alloc_pasid:
+	mutex_destroy(&process->mutex);
 	kfree(process);
 err_alloc_process:
 	return ERR_PTR(err);