Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "More mm/ work, plenty more to come

  Subsystems affected by this patch series: slub, memcg, gup, kasan,
  pagealloc, hugetlb, vmscan, tools, mempolicy, memblock, hugetlbfs,
  thp, mmap, kconfig"

* akpm: (131 commits)
  arm64: mm: use ARCH_HAS_DEBUG_WX instead of arch defined
  x86: mm: use ARCH_HAS_DEBUG_WX instead of arch defined
  riscv: support DEBUG_WX
  mm: add DEBUG_WX support
  drivers/base/memory.c: cache memory blocks in xarray to accelerate lookup
  mm/thp: rename pmd_mknotpresent() as pmd_mkinvalid()
  powerpc/mm: drop platform defined pmd_mknotpresent()
  mm: thp: don't need to drain lru cache when splitting and mlocking THP
  hugetlbfs: get unmapped area below TASK_UNMAPPED_BASE for hugetlbfs
  sparc32: register memory occupied by kernel as memblock.memory
  include/linux/memblock.h: fix minor typo and unclear comment
  mm, mempolicy: fix up gup usage in lookup_node
  tools/vm/page_owner_sort.c: filter out unneeded line
  mm: swap: memcg: fix memcg stats for huge pages
  mm: swap: fix vmstats for huge pages
  mm: vmscan: limit the range of LRU type balancing
  mm: vmscan: reclaim writepage is IO cost
  mm: vmscan: determine anon/file pressure balance at the reclaim root
  mm: balance LRU lists based on relative thrashing
  mm: only count actual rotations as LRU reclaim cost
  ...

2 files changed, 45 insertions, 21 deletions

diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index dbec3a05590a..2b09b68b9f78 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -21,6 +21,7 @@
 #include <linux/mm.h>
 #include <linux/stat.h>
 #include <linux/slab.h>
+#include <linux/xarray.h>
 
 #include <linux/atomic.h>
 #include <linux/uaccess.h>
@@ -74,6 +75,13 @@ static struct bus_type memory_subsys = {
 	.offline = memory_subsys_offline,
 };
 
+/*
+ * Memory blocks are cached in a local radix tree to avoid
+ * a costly linear search for the corresponding device on
+ * the subsystem bus.
+ */
+static DEFINE_XARRAY(memory_blocks);
+
 static BLOCKING_NOTIFIER_HEAD(memory_chain);
 
 int register_memory_notifier(struct notifier_block *nb)
@@ -489,22 +497,23 @@ int __weak arch_get_memory_phys_device(unsigned long start_pfn)
 	return 0;
 }
 
-/* A reference for the returned memory block device is acquired. */
+/*
+ * A reference for the returned memory block device is acquired.
+ *
+ * Called under device_hotplug_lock.
+ */
 static struct memory_block *find_memory_block_by_id(unsigned long block_id)
 {
-	struct device *dev;
+	struct memory_block *mem;
 
-	dev = subsys_find_device_by_id(&memory_subsys, block_id, NULL);
-	return dev ? to_memory_block(dev) : NULL;
+	mem = xa_load(&memory_blocks, block_id);
+	if (mem)
+		get_device(&mem->dev);
+	return mem;
 }
 
 /*
- * For now, we have a linear search to go find the appropriate
- * memory_block corresponding to a particular phys_index. If
- * this gets to be a real problem, we can always use a radix
- * tree or something here.
- *
- * This could be made generic for all device subsystems.
+ * Called under device_hotplug_lock.
  */
 struct memory_block *find_memory_block(struct mem_section *section)
 {
@@ -548,9 +557,16 @@ int register_memory(struct memory_block *memory)
 	memory->dev.offline = memory->state == MEM_OFFLINE;
 
 	ret = device_register(&memory->dev);
-	if (ret)
+	if (ret) {
 		put_device(&memory->dev);
-
+		return ret;
+	}
+	ret = xa_err(xa_store(&memory_blocks, memory->dev.id, memory,
+			      GFP_KERNEL));
+	if (ret) {
+		put_device(&memory->dev);
+		device_unregister(&memory->dev);
+	}
 	return ret;
 }
 
@@ -604,6 +620,8 @@ static void unregister_memory(struct memory_block *memory)
 	if (WARN_ON_ONCE(memory->dev.bus != &memory_subsys))
 		return;
 
+	WARN_ON(xa_erase(&memory_blocks, memory->dev.id) == NULL);
+
 	/* drop the ref. we got via find_memory_block() */
 	put_device(&memory->dev);
 	device_unregister(&memory->dev);
@@ -750,6 +768,8 @@ void __init memory_dev_init(void)
  *
  * In case func() returns an error, walking is aborted and the error is
  * returned.
+ *
+ * Called under device_hotplug_lock.
  */
 int walk_memory_blocks(unsigned long start, unsigned long size,
 		       void *arg, walk_memory_blocks_func_t func)
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
index f80cf6ac20c5..33776b3f3fa5 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_userptr.c
@@ -471,7 +471,7 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 					down_read(&mm->mmap_sem);
 					locked = 1;
 				}
-				ret = get_user_pages_remote
+				ret = pin_user_pages_remote
 					(work->task, mm,
 					 obj->userptr.ptr + pinned * PAGE_SIZE,
 					 npages - pinned,
@@ -507,7 +507,7 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 	}
 	mutex_unlock(&obj->mm.lock);
 
-	release_pages(pvec, pinned);
+	unpin_user_pages(pvec, pinned);
 	kvfree(pvec);
 
 	i915_gem_object_put(obj);
@@ -564,6 +564,7 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 	struct sg_table *pages;
 	bool active;
 	int pinned;
+	unsigned int gup_flags = 0;
 
 	/* If userspace should engineer that these pages are replaced in
 	 * the vma between us binding this page into the GTT and completion
@@ -606,11 +607,14 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 		 *
 		 * We may or may not care.
 		 */
-		if (pvec) /* defer to worker if malloc fails */
-			pinned = __get_user_pages_fast(obj->userptr.ptr,
-						       num_pages,
-						       !i915_gem_object_is_readonly(obj),
-						       pvec);
+		if (pvec) {
+			/* defer to worker if malloc fails */
+			if (!i915_gem_object_is_readonly(obj))
+				gup_flags |= FOLL_WRITE;
+			pinned = pin_user_pages_fast_only(obj->userptr.ptr,
+							  num_pages, gup_flags,
+							  pvec);
+		}
 	}
 
 	active = false;
@@ -628,7 +632,7 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 		__i915_gem_userptr_set_active(obj, true);
 
 	if (IS_ERR(pages))
-		release_pages(pvec, pinned);
+		unpin_user_pages(pvec, pinned);
 	kvfree(pvec);
 
 	return PTR_ERR_OR_ZERO(pages);
@@ -683,7 +687,7 @@ i915_gem_userptr_put_pages(struct drm_i915_gem_object *obj,
 		}
 
 		mark_page_accessed(page);
-		put_page(page);
+		unpin_user_page(page);
 	}
 	obj->mm.dirty = false;