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
  ...

3 files changed, 45 insertions, 20 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 53e780748fe3..5a0fd518e04e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1009,7 +1009,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	mm_init_owner(mm, p);
 	RCU_INIT_POINTER(mm->exe_file, NULL);
 	mmu_notifier_mm_init(mm);
-	hmm_mm_init(mm);
 	init_tlb_flush_pending(mm);
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
 	mm->pmd_huge_pte = NULL;
diff --git a/kernel/resource.c b/kernel/resource.c
index 7ea4306503c5..74877e9d90ca 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -1644,19 +1644,8 @@ void resource_list_free(struct list_head *head)
 EXPORT_SYMBOL(resource_list_free);
 
 #ifdef CONFIG_DEVICE_PRIVATE
-/**
- * devm_request_free_mem_region - find free region for device private memory
- *
- * @dev: device struct to bind the resource to
- * @size: size in bytes of the device memory to add
- * @base: resource tree to look in
- *
- * This function tries to find an empty range of physical address big enough to
- * contain the new resource, so that it can later be hotplugged as ZONE_DEVICE
- * memory, which in turn allocates struct pages.
- */
-struct resource *devm_request_free_mem_region(struct device *dev,
-		struct resource *base, unsigned long size)
+static struct resource *__request_free_mem_region(struct device *dev,
+		struct resource *base, unsigned long size, const char *name)
 {
 	resource_size_t end, addr;
 	struct resource *res;
@@ -1670,7 +1659,10 @@ struct resource *devm_request_free_mem_region(struct device *dev,
 				REGION_DISJOINT)
 			continue;
 
-		res = devm_request_mem_region(dev, addr, size, dev_name(dev));
+		if (dev)
+			res = devm_request_mem_region(dev, addr, size, name);
+		else
+			res = request_mem_region(addr, size, name);
 		if (!res)
 			return ERR_PTR(-ENOMEM);
 		res->desc = IORES_DESC_DEVICE_PRIVATE_MEMORY;
@@ -1679,7 +1671,32 @@ struct resource *devm_request_free_mem_region(struct device *dev,
 
 	return ERR_PTR(-ERANGE);
 }
+
+/**
+ * devm_request_free_mem_region - find free region for device private memory
+ *
+ * @dev: device struct to bind the resource to
+ * @size: size in bytes of the device memory to add
+ * @base: resource tree to look in
+ *
+ * This function tries to find an empty range of physical address big enough to
+ * contain the new resource, so that it can later be hotplugged as ZONE_DEVICE
+ * memory, which in turn allocates struct pages.
+ */
+struct resource *devm_request_free_mem_region(struct device *dev,
+		struct resource *base, unsigned long size)
+{
+	return __request_free_mem_region(dev, base, size, dev_name(dev));
+}
 EXPORT_SYMBOL_GPL(devm_request_free_mem_region);
+
+struct resource *request_free_mem_region(struct resource *base,
+		unsigned long size, const char *name)
+{
+	return __request_free_mem_region(NULL, base, size, name);
+}
+EXPORT_SYMBOL_GPL(request_free_mem_region);
+
 #endif /* CONFIG_DEVICE_PRIVATE */
 
 static int __init strict_iomem(char *str)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5e8387bdd09c..f9a1346a5fa9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3871,13 +3871,22 @@ static noinline void __schedule_bug(struct task_struct *prev)
 /*
  * Various schedule()-time debugging checks and statistics:
  */
-static inline void schedule_debug(struct task_struct *prev)
+static inline void schedule_debug(struct task_struct *prev, bool preempt)
 {
 #ifdef CONFIG_SCHED_STACK_END_CHECK
 	if (task_stack_end_corrupted(prev))
 		panic("corrupted stack end detected inside scheduler\n");
 #endif
 
+#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
+	if (!preempt && prev->state && prev->non_block_count) {
+		printk(KERN_ERR "BUG: scheduling in a non-blocking section: %s/%d/%i\n",
+			prev->comm, prev->pid, prev->non_block_count);
+		dump_stack();
+		add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
+	}
+#endif
+
 	if (unlikely(in_atomic_preempt_off())) {
 		__schedule_bug(prev);
 		preempt_count_set(PREEMPT_DISABLED);
@@ -3989,7 +3998,7 @@ static void __sched notrace __schedule(bool preempt)
 	rq = cpu_rq(cpu);
 	prev = rq->curr;
 
-	schedule_debug(prev);
+	schedule_debug(prev, preempt);
 
 	if (sched_feat(HRTICK))
 		hrtick_clear(rq);
@@ -6763,7 +6772,7 @@ void ___might_sleep(const char *file, int line, int preempt_offset)
 	rcu_sleep_check();
 
 	if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
-	     !is_idle_task(current)) ||
+	     !is_idle_task(current) && !current->non_block_count) ||
 	    system_state == SYSTEM_BOOTING || system_state > SYSTEM_RUNNING ||
 	    oops_in_progress)
 		return;
@@ -6779,8 +6788,8 @@ void ___might_sleep(const char *file, int line, int preempt_offset)
 		"BUG: sleeping function called from invalid context at %s:%d\n",
 			file, line);
 	printk(KERN_ERR
-		"in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
-			in_atomic(), irqs_disabled(),
+		"in_atomic(): %d, irqs_disabled(): %d, non_block: %d, pid: %d, name: %s\n",
+			in_atomic(), irqs_disabled(), current->non_block_count,
 			current->pid, current->comm);
 
 	if (task_stack_end_corrupted(current))