1 files changed, 91 insertions, 110 deletions

diff --git a/kernel/memremap.c b/kernel/memremap.c
index 5b8600d39931..a856cb5ff192 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -1,47 +1,22 @@
 /* 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>
+#include <linux/hmm.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,
@@ -50,6 +25,9 @@ vm_fault_t device_private_entry_fault(struct vm_area_struct *vma,
 		       pmd_t *pmdp)
 {
 	struct page *page = device_private_entry_to_page(entry);
+	struct hmm_devmem *devmem;
+
+	devmem = container_of(page->pgmap, typeof(*devmem), pagemap);
 
 	/*
 	 * The page_fault() callback must migrate page back to system memory
@@ -65,23 +43,15 @@ vm_fault_t device_private_entry_fault(struct vm_area_struct *vma,
 	 * There is a more in-depth description of what that callback can and
 	 * cannot do, in include/linux/memremap.h
 	 */
-	return page->pgmap->page_fault(vma, addr, page, flags, pmdp);
+	return devmem->page_fault(vma, addr, page, flags, pmdp);
 }
 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();
 }
 
@@ -121,28 +91,33 @@ static void devm_memremap_pages_release(void *data)
 	struct resource *res = &pgmap->res;
 	resource_size_t align_start, align_size;
 	unsigned long pfn;
+	int nid;
 
+	pgmap->kill(pgmap->ref);
 	for_each_device_pfn(pfn, pgmap)
 		put_page(pfn_to_page(pfn));
 
-	if (percpu_ref_tryget_live(pgmap->ref)) {
-		dev_WARN(dev, "%s: page mapping is still live!\n", __func__);
-		percpu_ref_put(pgmap->ref);
-	}
-
 	/* pages are dead and unused, undo the arch mapping */
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
 		- align_start;
 
+	nid = page_to_nid(pfn_to_page(align_start >> PAGE_SHIFT));
+
 	mem_hotplug_begin();
-	arch_remove_memory(align_start, align_size, pgmap->altmap_valid ?
-			&pgmap->altmap : NULL);
-	kasan_remove_zero_shadow(__va(align_start), align_size);
+	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
+		pfn = align_start >> PAGE_SHIFT;
+		__remove_pages(page_zone(pfn_to_page(pfn)), pfn,
+				align_size >> PAGE_SHIFT, NULL);
+	} else {
+		arch_remove_memory(nid, align_start, align_size,
+				pgmap->altmap_valid ? &pgmap->altmap : NULL);
+		kasan_remove_zero_shadow(__va(align_start), align_size);
+	}
 	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__);
 }
@@ -150,7 +125,7 @@ static void devm_memremap_pages_release(void *data)
 /**
  * devm_memremap_pages - remap and provide memmap backing for the given resource
  * @dev: hosting device for @res
- * @pgmap: pointer to a struct dev_pgmap
+ * @pgmap: pointer to a struct dev_pagemap
  *
  * Notes:
  * 1/ At a minimum the res, ref and type members of @pgmap must be initialized
@@ -159,11 +134,8 @@ static void devm_memremap_pages_release(void *data)
  * 2/ The altmap field may optionally be initialized, in which case altmap_valid
  *    must be set to true
  *
- * 3/ pgmap.ref must be 'live' on entry and 'dead' before devm_memunmap_pages()
- *    time (or devm release event). The expected order of events is that ref has
- *    been through percpu_ref_kill() before devm_memremap_pages_release(). The
- *    wait for the completion of all references being dropped and
- *    percpu_ref_exit() must occur after devm_memremap_pages_release().
+ * 3/ pgmap->ref must be 'live' on entry and will be killed at
+ *    devm_memremap_pages_release() time, or if this routine fails.
  *
  * 4/ res is expected to be a host memory range that could feasibly be
  *    treated as a "System RAM" range, i.e. not a device mmio range, but
@@ -175,10 +147,12 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 	struct vmem_altmap *altmap = pgmap->altmap_valid ?
 			&pgmap->altmap : NULL;
 	struct resource *res = &pgmap->res;
-	unsigned long pfn, pgoff, order;
+	struct dev_pagemap *conflict_pgmap;
 	pgprot_t pgprot = PAGE_KERNEL;
 	int error, nid, is_ram;
-	struct dev_pagemap *conflict_pgmap;
+
+	if (!pgmap->ref || !pgmap->kill)
+		return ERR_PTR(-EINVAL);
 
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
@@ -202,34 +176,19 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 	is_ram = region_intersects(align_start, align_size,
 		IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
 
-	if (is_ram == REGION_MIXED) {
-		WARN_ONCE(1, "%s attempted on mixed region %pr\n",
-				__func__, res);
-		return ERR_PTR(-ENXIO);
+	if (is_ram != REGION_DISJOINT) {
+		WARN_ONCE(1, "%s attempted on %s region %pr\n", __func__,
+				is_ram == REGION_MIXED ? "mixed" : "ram", res);
+		error = -ENXIO;
+		goto err_array;
 	}
 
-	if (is_ram == REGION_INTERSECTS)
-		return __va(res->start);
-
-	if (!pgmap->ref)
-		return ERR_PTR(-EINVAL);
-
 	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)
@@ -241,36 +200,57 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 		goto err_pfn_remap;
 
 	mem_hotplug_begin();
-	error = kasan_add_zero_shadow(__va(align_start), align_size);
-	if (error) {
-		mem_hotplug_done();
-		goto err_kasan;
+
+	/*
+	 * For device private memory we call add_pages() as we only need to
+	 * allocate and initialize struct page for the device memory. More-
+	 * over the device memory is un-accessible thus we do not want to
+	 * create a linear mapping for the memory like arch_add_memory()
+	 * would do.
+	 *
+	 * For all other device memory types, which are accessible by
+	 * the CPU, we do want the linear mapping and thus use
+	 * arch_add_memory().
+	 */
+	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
+		error = add_pages(nid, align_start >> PAGE_SHIFT,
+				align_size >> PAGE_SHIFT, NULL, false);
+	} else {
+		error = kasan_add_zero_shadow(__va(align_start), align_size);
+		if (error) {
+			mem_hotplug_done();
+			goto err_kasan;
+		}
+
+		error = arch_add_memory(nid, align_start, align_size, altmap,
+				false);
+	}
+
+	if (!error) {
+		struct zone *zone;
+
+		zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
+		move_pfn_range_to_zone(zone, align_start >> PAGE_SHIFT,
+				align_size >> PAGE_SHIFT, altmap);
 	}
 
-	error = arch_add_memory(nid, align_start, align_size, altmap, false);
-	if (!error)
-		move_pfn_range_to_zone(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
-					align_start >> PAGE_SHIFT,
-					align_size >> PAGE_SHIFT, altmap);
 	mem_hotplug_done();
 	if (error)
 		goto err_add_memory;
 
-	for_each_device_pfn(pfn, pgmap) {
-		struct page *page = pfn_to_page(pfn);
-
-		/*
-		 * ZONE_DEVICE pages union ->lru with a ->pgmap back
-		 * pointer.  It is a bug if a ZONE_DEVICE page is ever
-		 * freed or placed on a driver-private list.  Seed the
-		 * storage with LIST_POISON* values.
-		 */
-		list_del(&page->lru);
-		page->pgmap = pgmap;
-		percpu_ref_get(pgmap->ref);
-	}
+	/*
+	 * Initialization of the pages has been deferred until now in order
+	 * to allow us to do the work while not holding the hotplug lock.
+	 */
+	memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE],
+				align_start >> PAGE_SHIFT,
+				align_size >> PAGE_SHIFT, pgmap);
+	percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap));
 
-	devm_add_action(dev, devm_memremap_pages_release, pgmap);
+	error = devm_add_action_or_reset(dev, devm_memremap_pages_release,
+			pgmap);
+	if (error)
+		return ERR_PTR(error);
 
 	return __va(res->start);
 
@@ -279,11 +259,12 @@ 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:
+	pgmap->kill(pgmap->ref);
 	return ERR_PTR(error);
 }
-EXPORT_SYMBOL(devm_memremap_pages);
+EXPORT_SYMBOL_GPL(devm_memremap_pages);
 
 unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
 {
@@ -320,7 +301,7 @@ 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();