Merge branch 'xarray' of git://git.infradead.org/users/willy/linux-dax

Pull XArray conversion from Matthew Wilcox:
 "The XArray provides an improved interface to the radix tree data
  structure, providing locking as part of the API, specifying GFP flags
  at allocation time, eliminating preloading, less re-walking the tree,
  more efficient iterations and not exposing RCU-protected pointers to
  its users.

  This patch set

   1. Introduces the XArray implementation

   2. Converts the pagecache to use it

   3. Converts memremap to use it

  The page cache is the most complex and important user of the radix
  tree, so converting it was most important. Converting the memremap
  code removes the only other user of the multiorder code, which allows
  us to remove the radix tree code that supported it.

  I have 40+ followup patches to convert many other users of the radix
  tree over to the XArray, but I'd like to get this part in first. The
  other conversions haven't been in linux-next and aren't suitable for
  applying yet, but you can see them in the xarray-conv branch if you're
  interested"

* 'xarray' of git://git.infradead.org/users/willy/linux-dax: (90 commits)
  radix tree: Remove multiorder support
  radix tree test: Convert multiorder tests to XArray
  radix tree tests: Convert item_delete_rcu to XArray
  radix tree tests: Convert item_kill_tree to XArray
  radix tree tests: Move item_insert_order
  radix tree test suite: Remove multiorder benchmarking
  radix tree test suite: Remove __item_insert
  memremap: Convert to XArray
  xarray: Add range store functionality
  xarray: Move multiorder_check to in-kernel tests
  xarray: Move multiorder_shrink to kernel tests
  xarray: Move multiorder account test in-kernel
  radix tree test suite: Convert iteration test to XArray
  radix tree test suite: Convert tag_tagged_items to XArray
  radix tree: Remove radix_tree_clear_tags
  radix tree: Remove radix_tree_maybe_preload_order
  radix tree: Remove split/join code
  radix tree: Remove radix_tree_update_node_t
  page cache: Finish XArray conversion
  dax: Convert page fault handlers to XArray
  ...

1 files changed, 15 insertions, 60 deletions

diff --git a/kernel/memremap.c b/kernel/memremap.c
index 620fc4d2559a..9eced2cc9f94 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -1,47 +1,21 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright(c) 2015 Intel Corporation. All rights reserved. */
-#include <linux/radix-tree.h>
 #include <linux/device.h>
-#include <linux/types.h>
-#include <linux/pfn_t.h>
 #include <linux/io.h>
 #include <linux/kasan.h>
-#include <linux/mm.h>
 #include <linux/memory_hotplug.h>
+#include <linux/mm.h>
+#include <linux/pfn_t.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/types.h>
 #include <linux/wait_bit.h>
+#include <linux/xarray.h>
 
-static DEFINE_MUTEX(pgmap_lock);
-static RADIX_TREE(pgmap_radix, GFP_KERNEL);
+static DEFINE_XARRAY(pgmap_array);
 #define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
 #define SECTION_SIZE (1UL << PA_SECTION_SHIFT)
 
-static unsigned long order_at(struct resource *res, unsigned long pgoff)
-{
-	unsigned long phys_pgoff = PHYS_PFN(res->start) + pgoff;
-	unsigned long nr_pages, mask;
-
-	nr_pages = PHYS_PFN(resource_size(res));
-	if (nr_pages == pgoff)
-		return ULONG_MAX;
-
-	/*
-	 * What is the largest aligned power-of-2 range available from
-	 * this resource pgoff to the end of the resource range,
-	 * considering the alignment of the current pgoff?
-	 */
-	mask = phys_pgoff | rounddown_pow_of_two(nr_pages - pgoff);
-	if (!mask)
-		return ULONG_MAX;
-
-	return find_first_bit(&mask, BITS_PER_LONG);
-}
-
-#define foreach_order_pgoff(res, order, pgoff) \
-	for (pgoff = 0, order = order_at((res), pgoff); order < ULONG_MAX; \
-			pgoff += 1UL << order, order = order_at((res), pgoff))
-
 #if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
 vm_fault_t device_private_entry_fault(struct vm_area_struct *vma,
 		       unsigned long addr,
@@ -70,18 +44,10 @@ vm_fault_t device_private_entry_fault(struct vm_area_struct *vma,
 EXPORT_SYMBOL(device_private_entry_fault);
 #endif /* CONFIG_DEVICE_PRIVATE */
 
-static void pgmap_radix_release(struct resource *res, unsigned long end_pgoff)
+static void pgmap_array_delete(struct resource *res)
 {
-	unsigned long pgoff, order;
-
-	mutex_lock(&pgmap_lock);
-	foreach_order_pgoff(res, order, pgoff) {
-		if (pgoff >= end_pgoff)
-			break;
-		radix_tree_delete(&pgmap_radix, PHYS_PFN(res->start) + pgoff);
-	}
-	mutex_unlock(&pgmap_lock);
-
+	xa_store_range(&pgmap_array, PHYS_PFN(res->start), PHYS_PFN(res->end),
+			NULL, GFP_KERNEL);
 	synchronize_rcu();
 }
 
@@ -142,7 +108,7 @@ static void devm_memremap_pages_release(void *data)
 	mem_hotplug_done();
 
 	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
-	pgmap_radix_release(res, -1);
+	pgmap_array_delete(res);
 	dev_WARN_ONCE(dev, pgmap->altmap.alloc,
 		      "%s: failed to free all reserved pages\n", __func__);
 }
@@ -177,7 +143,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 	struct resource *res = &pgmap->res;
 	struct dev_pagemap *conflict_pgmap;
 	pgprot_t pgprot = PAGE_KERNEL;
-	unsigned long pgoff, order;
 	int error, nid, is_ram;
 
 	align_start = res->start & ~(SECTION_SIZE - 1);
@@ -216,20 +181,10 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 
 	pgmap->dev = dev;
 
-	mutex_lock(&pgmap_lock);
-	error = 0;
-
-	foreach_order_pgoff(res, order, pgoff) {
-		error = __radix_tree_insert(&pgmap_radix,
-				PHYS_PFN(res->start) + pgoff, order, pgmap);
-		if (error) {
-			dev_err(dev, "%s: failed: %d\n", __func__, error);
-			break;
-		}
-	}
-	mutex_unlock(&pgmap_lock);
+	error = xa_err(xa_store_range(&pgmap_array, PHYS_PFN(res->start),
+				PHYS_PFN(res->end), pgmap, GFP_KERNEL));
 	if (error)
-		goto err_radix;
+		goto err_array;
 
 	nid = dev_to_node(dev);
 	if (nid < 0)
@@ -274,8 +229,8 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
  err_kasan:
 	untrack_pfn(NULL, PHYS_PFN(align_start), align_size);
  err_pfn_remap:
- err_radix:
-	pgmap_radix_release(res, pgoff);
+	pgmap_array_delete(res);
+ err_array:
 	return ERR_PTR(error);
 }
 EXPORT_SYMBOL(devm_memremap_pages);
@@ -315,7 +270,7 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 
 	/* fall back to slow path lookup */
 	rcu_read_lock();
-	pgmap = radix_tree_lookup(&pgmap_radix, PHYS_PFN(phys));
+	pgmap = xa_load(&pgmap_array, PHYS_PFN(phys));
 	if (pgmap && !percpu_ref_tryget_live(pgmap->ref))
 		pgmap = NULL;
 	rcu_read_unlock();