Merge tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull HMM updates from Jason Gunthorpe:
 "Improvements and bug fixes for the hmm interface in the kernel:

   - Improve clarity, locking and APIs related to the 'hmm mirror'
     feature merged last cycle. In linux-next we now see AMDGPU and
     nouveau to be using this API.

   - Remove old or transitional hmm APIs. These are hold overs from the
     past with no users, or APIs that existed only to manage cross tree
     conflicts. There are still a few more of these cleanups that didn't
     make the merge window cut off.

   - Improve some core mm APIs:
       - export alloc_pages_vma() for driver use
       - refactor into devm_request_free_mem_region() to manage
         DEVICE_PRIVATE resource reservations
       - refactor duplicative driver code into the core dev_pagemap
         struct

   - Remove hmm wrappers of improved core mm APIs, instead have drivers
     use the simplified API directly

   - Remove DEVICE_PUBLIC

   - Simplify the kconfig flow for the hmm users and core code"

* tag 'for-linus-hmm' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (42 commits)
  mm: don't select MIGRATE_VMA_HELPER from HMM_MIRROR
  mm: remove the HMM config option
  mm: sort out the DEVICE_PRIVATE Kconfig mess
  mm: simplify ZONE_DEVICE page private data
  mm: remove hmm_devmem_add
  mm: remove hmm_vma_alloc_locked_page
  nouveau: use devm_memremap_pages directly
  nouveau: use alloc_page_vma directly
  PCI/P2PDMA: use the dev_pagemap internal refcount
  device-dax: use the dev_pagemap internal refcount
  memremap: provide an optional internal refcount in struct dev_pagemap
  memremap: replace the altmap_valid field with a PGMAP_ALTMAP_VALID flag
  memremap: remove the data field in struct dev_pagemap
  memremap: add a migrate_to_ram method to struct dev_pagemap_ops
  memremap: lift the devmap_enable manipulation into devm_memremap_pages
  memremap: pass a struct dev_pagemap to ->kill and ->cleanup
  memremap: move dev_pagemap callbacks into a separate structure
  memremap: validate the pagemap type passed to devm_memremap_pages
  mm: factor out a devm_request_free_mem_region helper
  mm: export alloc_pages_vma
  ...

3 files changed, 157 insertions, 77 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 8f3e2d97d771..dfa78985a6fd 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -677,7 +677,6 @@ void __mmdrop(struct mm_struct *mm)
 	WARN_ON_ONCE(mm == current->active_mm);
 	mm_free_pgd(mm);
 	destroy_context(mm);
-	hmm_mm_destroy(mm);
 	mmu_notifier_mm_destroy(mm);
 	check_mm(mm);
 	put_user_ns(mm->user_ns);
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 6e1970719dc2..bea6f887adad 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -11,41 +11,39 @@
 #include <linux/types.h>
 #include <linux/wait_bit.h>
 #include <linux/xarray.h>
-#include <linux/hmm.h>
 
 static DEFINE_XARRAY(pgmap_array);
 #define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1)
 #define SECTION_SIZE (1UL << PA_SECTION_SHIFT)
 
-#if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
-vm_fault_t device_private_entry_fault(struct vm_area_struct *vma,
-		       unsigned long addr,
-		       swp_entry_t entry,
-		       unsigned int flags,
-		       pmd_t *pmdp)
+#ifdef CONFIG_DEV_PAGEMAP_OPS
+DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
+EXPORT_SYMBOL(devmap_managed_key);
+static atomic_t devmap_managed_enable;
+
+static void devmap_managed_enable_put(void *data)
 {
-	struct page *page = device_private_entry_to_page(entry);
-	struct hmm_devmem *devmem;
+	if (atomic_dec_and_test(&devmap_managed_enable))
+		static_branch_disable(&devmap_managed_key);
+}
 
-	devmem = container_of(page->pgmap, typeof(*devmem), pagemap);
+static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap)
+{
+	if (!pgmap->ops || !pgmap->ops->page_free) {
+		WARN(1, "Missing page_free method\n");
+		return -EINVAL;
+	}
 
-	/*
-	 * The page_fault() callback must migrate page back to system memory
-	 * so that CPU can access it. This might fail for various reasons
-	 * (device issue, device was unsafely unplugged, ...). When such
-	 * error conditions happen, the callback must return VM_FAULT_SIGBUS.
-	 *
-	 * Note that because memory cgroup charges are accounted to the device
-	 * memory, this should never fail because of memory restrictions (but
-	 * allocation of regular system page might still fail because we are
-	 * out of memory).
-	 *
-	 * There is a more in-depth description of what that callback can and
-	 * cannot do, in include/linux/memremap.h
-	 */
-	return devmem->page_fault(vma, addr, page, flags, pmdp);
+	if (atomic_inc_return(&devmap_managed_enable) == 1)
+		static_branch_enable(&devmap_managed_key);
+	return devm_add_action_or_reset(dev, devmap_managed_enable_put, NULL);
 }
-#endif /* CONFIG_DEVICE_PRIVATE */
+#else
+static int devmap_managed_enable_get(struct device *dev, struct dev_pagemap *pgmap)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_DEV_PAGEMAP_OPS */
 
 static void pgmap_array_delete(struct resource *res)
 {
@@ -56,14 +54,8 @@ static void pgmap_array_delete(struct resource *res)
 
 static unsigned long pfn_first(struct dev_pagemap *pgmap)
 {
-	const struct resource *res = &pgmap->res;
-	struct vmem_altmap *altmap = &pgmap->altmap;
-	unsigned long pfn;
-
-	pfn = res->start >> PAGE_SHIFT;
-	if (pgmap->altmap_valid)
-		pfn += vmem_altmap_offset(altmap);
-	return pfn;
+	return (pgmap->res.start >> PAGE_SHIFT) +
+		vmem_altmap_offset(pgmap_altmap(pgmap));
 }
 
 static unsigned long pfn_end(struct dev_pagemap *pgmap)
@@ -83,6 +75,24 @@ static unsigned long pfn_next(unsigned long pfn)
 #define for_each_device_pfn(pfn, map) \
 	for (pfn = pfn_first(map); pfn < pfn_end(map); pfn = pfn_next(pfn))
 
+static void dev_pagemap_kill(struct dev_pagemap *pgmap)
+{
+	if (pgmap->ops && pgmap->ops->kill)
+		pgmap->ops->kill(pgmap);
+	else
+		percpu_ref_kill(pgmap->ref);
+}
+
+static void dev_pagemap_cleanup(struct dev_pagemap *pgmap)
+{
+	if (pgmap->ops && pgmap->ops->cleanup) {
+		pgmap->ops->cleanup(pgmap);
+	} else {
+		wait_for_completion(&pgmap->done);
+		percpu_ref_exit(pgmap->ref);
+	}
+}
+
 static void devm_memremap_pages_release(void *data)
 {
 	struct dev_pagemap *pgmap = data;
@@ -92,10 +102,10 @@ static void devm_memremap_pages_release(void *data)
 	unsigned long pfn;
 	int nid;
 
-	pgmap->kill(pgmap->ref);
+	dev_pagemap_kill(pgmap);
 	for_each_device_pfn(pfn, pgmap)
 		put_page(pfn_to_page(pfn));
-	pgmap->cleanup(pgmap->ref);
+	dev_pagemap_cleanup(pgmap);
 
 	/* pages are dead and unused, undo the arch mapping */
 	align_start = res->start & ~(SECTION_SIZE - 1);
@@ -111,7 +121,7 @@ static void devm_memremap_pages_release(void *data)
 				align_size >> PAGE_SHIFT, NULL);
 	} else {
 		arch_remove_memory(nid, align_start, align_size,
-				pgmap->altmap_valid ? &pgmap->altmap : NULL);
+				pgmap_altmap(pgmap));
 		kasan_remove_zero_shadow(__va(align_start), align_size);
 	}
 	mem_hotplug_done();
@@ -122,20 +132,29 @@ static void devm_memremap_pages_release(void *data)
 		      "%s: failed to free all reserved pages\n", __func__);
 }
 
+static void dev_pagemap_percpu_release(struct percpu_ref *ref)
+{
+	struct dev_pagemap *pgmap =
+		container_of(ref, struct dev_pagemap, internal_ref);
+
+	complete(&pgmap->done);
+}
+
 /**
  * devm_memremap_pages - remap and provide memmap backing for the given resource
  * @dev: hosting device for @res
  * @pgmap: pointer to a struct dev_pagemap
  *
  * Notes:
- * 1/ At a minimum the res, ref and type members of @pgmap must be initialized
+ * 1/ At a minimum the res and type members of @pgmap must be initialized
  *    by the caller before passing it to this function
  *
- * 2/ The altmap field may optionally be initialized, in which case altmap_valid
- *    must be set to true
+ * 2/ The altmap field may optionally be initialized, in which case
+ *    PGMAP_ALTMAP_VALID must be set in pgmap->flags.
  *
- * 3/ pgmap->ref must be 'live' on entry and will be killed and reaped
- *    at devm_memremap_pages_release() time, or if this routine fails.
+ * 3/ The ref field may optionally be provided, in which pgmap->ref must be
+ *    'live' on entry and will be killed and reaped 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
@@ -144,22 +163,66 @@ static void devm_memremap_pages_release(void *data)
 void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 {
 	resource_size_t align_start, align_size, align_end;
-	struct vmem_altmap *altmap = pgmap->altmap_valid ?
-			&pgmap->altmap : NULL;
 	struct resource *res = &pgmap->res;
 	struct dev_pagemap *conflict_pgmap;
 	struct mhp_restrictions restrictions = {
 		/*
 		 * We do not want any optional features only our own memmap
 		*/
-		.altmap = altmap,
+		.altmap = pgmap_altmap(pgmap),
 	};
 	pgprot_t pgprot = PAGE_KERNEL;
 	int error, nid, is_ram;
+	bool need_devmap_managed = true;
+
+	switch (pgmap->type) {
+	case MEMORY_DEVICE_PRIVATE:
+		if (!IS_ENABLED(CONFIG_DEVICE_PRIVATE)) {
+			WARN(1, "Device private memory not supported\n");
+			return ERR_PTR(-EINVAL);
+		}
+		if (!pgmap->ops || !pgmap->ops->migrate_to_ram) {
+			WARN(1, "Missing migrate_to_ram method\n");
+			return ERR_PTR(-EINVAL);
+		}
+		break;
+	case MEMORY_DEVICE_FS_DAX:
+		if (!IS_ENABLED(CONFIG_ZONE_DEVICE) ||
+		    IS_ENABLED(CONFIG_FS_DAX_LIMITED)) {
+			WARN(1, "File system DAX not supported\n");
+			return ERR_PTR(-EINVAL);
+		}
+		break;
+	case MEMORY_DEVICE_DEVDAX:
+	case MEMORY_DEVICE_PCI_P2PDMA:
+		need_devmap_managed = false;
+		break;
+	default:
+		WARN(1, "Invalid pgmap type %d\n", pgmap->type);
+		break;
+	}
+
+	if (!pgmap->ref) {
+		if (pgmap->ops && (pgmap->ops->kill || pgmap->ops->cleanup))
+			return ERR_PTR(-EINVAL);
+
+		init_completion(&pgmap->done);
+		error = percpu_ref_init(&pgmap->internal_ref,
+				dev_pagemap_percpu_release, 0, GFP_KERNEL);
+		if (error)
+			return ERR_PTR(error);
+		pgmap->ref = &pgmap->internal_ref;
+	} else {
+		if (!pgmap->ops || !pgmap->ops->kill || !pgmap->ops->cleanup) {
+			WARN(1, "Missing reference count teardown definition\n");
+			return ERR_PTR(-EINVAL);
+		}
+	}
 
-	if (!pgmap->ref || !pgmap->kill || !pgmap->cleanup) {
-		WARN(1, "Missing reference count teardown definition\n");
-		return ERR_PTR(-EINVAL);
+	if (need_devmap_managed) {
+		error = devmap_managed_enable_get(dev, pgmap);
+		if (error)
+			return ERR_PTR(error);
 	}
 
 	align_start = res->start & ~(SECTION_SIZE - 1);
@@ -241,7 +304,7 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 
 		zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
 		move_pfn_range_to_zone(zone, align_start >> PAGE_SHIFT,
-				align_size >> PAGE_SHIFT, altmap);
+				align_size >> PAGE_SHIFT, pgmap_altmap(pgmap));
 	}
 
 	mem_hotplug_done();
@@ -271,9 +334,8 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
  err_pfn_remap:
 	pgmap_array_delete(res);
  err_array:
-	pgmap->kill(pgmap->ref);
-	pgmap->cleanup(pgmap->ref);
-
+	dev_pagemap_kill(pgmap);
+	dev_pagemap_cleanup(pgmap);
 	return ERR_PTR(error);
 }
 EXPORT_SYMBOL_GPL(devm_memremap_pages);
@@ -287,7 +349,9 @@ EXPORT_SYMBOL_GPL(devm_memunmap_pages);
 unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
 {
 	/* number of pfns from base where pfn_to_page() is valid */
-	return altmap->reserve + altmap->free;
+	if (altmap)
+		return altmap->reserve + altmap->free;
+	return 0;
 }
 
 void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns)
@@ -329,28 +393,6 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 EXPORT_SYMBOL_GPL(get_dev_pagemap);
 
 #ifdef CONFIG_DEV_PAGEMAP_OPS
-DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
-EXPORT_SYMBOL(devmap_managed_key);
-static atomic_t devmap_enable;
-
-/*
- * Toggle the static key for ->page_free() callbacks when dev_pagemap
- * pages go idle.
- */
-void dev_pagemap_get_ops(void)
-{
-	if (atomic_inc_return(&devmap_enable) == 1)
-		static_branch_enable(&devmap_managed_key);
-}
-EXPORT_SYMBOL_GPL(dev_pagemap_get_ops);
-
-void dev_pagemap_put_ops(void)
-{
-	if (atomic_dec_and_test(&devmap_enable))
-		static_branch_disable(&devmap_managed_key);
-}
-EXPORT_SYMBOL_GPL(dev_pagemap_put_ops);
-
 void __put_devmap_managed_page(struct page *page)
 {
 	int count = page_ref_dec_return(page);
@@ -366,7 +408,7 @@ void __put_devmap_managed_page(struct page *page)
 
 		mem_cgroup_uncharge(page);
 
-		page->pgmap->page_free(page, page->pgmap->data);
+		page->pgmap->ops->page_free(page);
 	} else if (!count)
 		__put_page(page);
 }
diff --git a/kernel/resource.c b/kernel/resource.c
index 158f04ec1d4f..d22423e85cf8 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -1628,6 +1628,45 @@ 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)
+{
+	resource_size_t end, addr;
+	struct resource *res;
+
+	size = ALIGN(size, 1UL << PA_SECTION_SHIFT);
+	end = min_t(unsigned long, base->end, (1UL << MAX_PHYSMEM_BITS) - 1);
+	addr = end - size + 1UL;
+
+	for (; addr > size && addr >= base->start; addr -= size) {
+		if (region_intersects(addr, size, 0, IORES_DESC_NONE) !=
+				REGION_DISJOINT)
+			continue;
+
+		res = devm_request_mem_region(dev, addr, size, dev_name(dev));
+		if (!res)
+			return ERR_PTR(-ENOMEM);
+		res->desc = IORES_DESC_DEVICE_PRIVATE_MEMORY;
+		return res;
+	}
+
+	return ERR_PTR(-ERANGE);
+}
+EXPORT_SYMBOL_GPL(devm_request_free_mem_region);
+#endif /* CONFIG_DEVICE_PRIVATE */
+
 static int __init strict_iomem(char *str)
 {
 	if (strstr(str, "relaxed"))