[PATCH v1 02/12] mm: remove extra ZONE_DEVICE struct page refcount

[Alex Sierra <alex.sierra@amd.com>]

From: Ralph Campbell <rcampbell@nvidia.com>

ZONE_DEVICE struct pages have an extra reference count that complicates the
code for put_page() and several places in the kernel that need to check the
reference count to see that a page is not being used (gup, compaction,
migration, etc.). Clean up the code so the reference count doesn't need to
be treated specially for ZONE_DEVICE.

Signed-off-by: Ralph Campbell <rcampbell@nvidia.com>
Signed-off-by: Alex Sierra <alex.sierra@amd.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
v2:
AS: merged this patch in linux 5.11 version

v5:
AS: add condition at try_grab_page to check for the zone device type, while
page ref counter is checked less/equal to zero. In case of device zone, pages
ref counter are initialized to zero.

v7:
AS: fix condition at try_grab_page added at v5, is invalid. It supposed
to fix xfstests/generic/413 test, however, there's a known issue on
this test where DAX mapped area DIO to non-DAX expect to fail.
https://patchwork.kernel.org/project/fstests/patch/1489463960-3579-1-git-send-email-xzhou@redhat.com
This condition was removed after rebase over patch series
https://lore.kernel.org/r/20210813044133.1536842-4-jhubbard@nvidia.com
---
 arch/powerpc/kvm/book3s_hv_uvmem.c     |  2 +-
 drivers/gpu/drm/nouveau/nouveau_dmem.c |  2 +-
 fs/dax.c                               |  4 +-
 include/linux/dax.h                    |  2 +-
 include/linux/memremap.h               |  7 +--
 include/linux/mm.h                     | 11 ----
 lib/test_hmm.c                         |  2 +-
 mm/internal.h                          |  8 +++
 mm/memcontrol.c                        |  6 +--
 mm/memremap.c                          | 69 +++++++-------------------
 mm/migrate.c                           |  5 --
 mm/page_alloc.c                        |  3 ++
 mm/swap.c                              | 45 ++---------------
 13 files changed, 46 insertions(+), 120 deletions(-)

diff --git a/arch/powerpc/kvm/book3s_hv_uvmem.c b/arch/powerpc/kvm/book3s_hv_uvmem.c
index 84e5a2dc8be5..acee67710620 100644
--- a/arch/powerpc/kvm/book3s_hv_uvmem.c
+++ b/arch/powerpc/kvm/book3s_hv_uvmem.c
@@ -711,7 +711,7 @@ static struct page *kvmppc_uvmem_get_page(unsigned long gpa, struct kvm *kvm)
 
 	dpage = pfn_to_page(uvmem_pfn);
 	dpage->zone_device_data = pvt;
-	get_page(dpage);
+	init_page_count(dpage);
 	lock_page(dpage);
 	return dpage;
 out_clear:
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index 92987daa5e17..8bc7120e1216 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -324,7 +324,7 @@ nouveau_dmem_page_alloc_locked(struct nouveau_drm *drm)
 			return NULL;
 	}
 
-	get_page(page);
+	init_page_count(page);
 	lock_page(page);
 	return page;
 }
diff --git a/fs/dax.c b/fs/dax.c
index c387d09e3e5a..1166630b7190 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -571,14 +571,14 @@ static void *grab_mapping_entry(struct xa_state *xas,
 
 /**
  * dax_layout_busy_page_range - find first pinned page in @mapping
- * @mapping: address space to scan for a page with ref count > 1
+ * @mapping: address space to scan for a page with ref count > 0
  * @start: Starting offset. Page containing 'start' is included.
  * @end: End offset. Page containing 'end' is included. If 'end' is LLONG_MAX,
  *       pages from 'start' till the end of file are included.
  *
  * DAX requires ZONE_DEVICE mapped pages. These pages are never
  * 'onlined' to the page allocator so they are considered idle when
- * page->count == 1. A filesystem uses this interface to determine if
+ * page->count == 0. A filesystem uses this interface to determine if
  * any page in the mapping is busy, i.e. for DMA, or other
  * get_user_pages() usages.
  *
diff --git a/include/linux/dax.h b/include/linux/dax.h
index 8b5da1d60dbc..05fc982ce153 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -245,7 +245,7 @@ static inline bool dax_mapping(struct address_space *mapping)
 
 static inline bool dax_page_unused(struct page *page)
 {
-	return page_ref_count(page) == 1;
+	return page_ref_count(page) == 0;
 }
 
 #define dax_wait_page(_inode, _page, _wait_cb)				\
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 45a79da89c5f..77ff5fd0685f 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -66,9 +66,10 @@ enum memory_type {
 
 struct dev_pagemap_ops {
 	/*
-	 * Called once the page refcount reaches 1.  (ZONE_DEVICE pages never
-	 * reach 0 refcount unless there is a refcount bug. This allows the
-	 * device driver to implement its own memory management.)
+	 * Called once the page refcount reaches 0. The reference count
+	 * should be reset to one with init_page_count(page) before reusing
+	 * the page. This allows the device driver to implement its own
+	 * memory management.
 	 */
 	void (*page_free)(struct page *page);
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index d8f98d652164..e24c904deeec 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1220,17 +1220,6 @@ static inline void put_page(struct page *page)
 {
 	page = compound_head(page);
 
-	/*
-	 * For devmap managed pages we need to catch refcount transition from
-	 * 2 to 1, when refcount reach one it means the page is free and we
-	 * need to inform the device driver through callback. See
-	 * include/linux/memremap.h and HMM for details.
-	 */
-	if (page_is_devmap_managed(page)) {
-		put_devmap_managed_page(page);
-		return;
-	}
-
 	if (put_page_testzero(page))
 		__put_page(page);
 }
diff --git a/lib/test_hmm.c b/lib/test_hmm.c
index 80a78877bd93..6998f10350ea 100644
--- a/lib/test_hmm.c
+++ b/lib/test_hmm.c
@@ -561,7 +561,7 @@ static struct page *dmirror_devmem_alloc_page(struct dmirror_device *mdevice)
 	}
 
 	dpage->zone_device_data = rpage;
-	get_page(dpage);
+	init_page_count(dpage);
 	lock_page(dpage);
 	return dpage;
 
diff --git a/mm/internal.h b/mm/internal.h
index e8fdb531f887..5438cceca4b9 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -667,4 +667,12 @@ int vmap_pages_range_noflush(unsigned long addr, unsigned long end,
 
 void vunmap_range_noflush(unsigned long start, unsigned long end);
 
+#ifdef CONFIG_DEV_PAGEMAP_OPS
+void free_zone_device_page(struct page *page);
+#else
+static inline void free_zone_device_page(struct page *page)
+{
+}
+#endif
+
 #endif	/* __MM_INTERNAL_H */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 64ada9e650a5..9a6bfb4fd36c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5350,11 +5350,7 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma,
 	 */
 	if (is_device_private_entry(ent)) {
 		page = device_private_entry_to_page(ent);
-		/*
-		 * MEMORY_DEVICE_PRIVATE means ZONE_DEVICE page and which have
-		 * a refcount of 1 when free (unlike normal page)
-		 */
-		if (!page_ref_add_unless(page, 1, 1))
+		if (!get_page_unless_zero(page))
 			return NULL;
 		return page;
 	}
diff --git a/mm/memremap.c b/mm/memremap.c
index 15a074ffb8d7..ab949a571e78 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -12,6 +12,7 @@
 #include <linux/types.h>
 #include <linux/wait_bit.h>
 #include <linux/xarray.h>
+#include "internal.h"
 
 static DEFINE_XARRAY(pgmap_array);
 
@@ -37,32 +38,6 @@ unsigned long memremap_compat_align(void)
 EXPORT_SYMBOL_GPL(memremap_compat_align);
 #endif
 
-#ifdef CONFIG_DEV_PAGEMAP_OPS
-DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
-EXPORT_SYMBOL(devmap_managed_key);
-
-static void devmap_managed_enable_put(struct dev_pagemap *pgmap)
-{
-	if (pgmap->type == MEMORY_DEVICE_PRIVATE ||
-	    pgmap->type == MEMORY_DEVICE_FS_DAX)
-		static_branch_dec(&devmap_managed_key);
-}
-
-static void devmap_managed_enable_get(struct dev_pagemap *pgmap)
-{
-	if (pgmap->type == MEMORY_DEVICE_PRIVATE ||
-	    pgmap->type == MEMORY_DEVICE_FS_DAX)
-		static_branch_inc(&devmap_managed_key);
-}
-#else
-static void devmap_managed_enable_get(struct dev_pagemap *pgmap)
-{
-}
-static void devmap_managed_enable_put(struct dev_pagemap *pgmap)
-{
-}
-#endif /* CONFIG_DEV_PAGEMAP_OPS */
-
 static void pgmap_array_delete(struct range *range)
 {
 	xa_store_range(&pgmap_array, PHYS_PFN(range->start), PHYS_PFN(range->end),
@@ -102,16 +77,6 @@ static unsigned long pfn_end(struct dev_pagemap *pgmap, int range_id)
 	return (range->start + range_len(range)) >> PAGE_SHIFT;
 }
 
-static unsigned long pfn_next(unsigned long pfn)
-{
-	if (pfn % 1024 == 0)
-		cond_resched();
-	return pfn + 1;
-}
-
-#define for_each_device_pfn(pfn, map, i) \
-	for (pfn = pfn_first(map, i); pfn < pfn_end(map, i); pfn = pfn_next(pfn))
-
 static void dev_pagemap_kill(struct dev_pagemap *pgmap)
 {
 	if (pgmap->ops && pgmap->ops->kill)
@@ -167,20 +132,18 @@ static void pageunmap_range(struct dev_pagemap *pgmap, int range_id)
 
 void memunmap_pages(struct dev_pagemap *pgmap)
 {
-	unsigned long pfn;
 	int i;
 
 	dev_pagemap_kill(pgmap);
 	for (i = 0; i < pgmap->nr_range; i++)
-		for_each_device_pfn(pfn, pgmap, i)
-			put_page(pfn_to_page(pfn));
+		percpu_ref_put_many(pgmap->ref, pfn_end(pgmap, i) -
+						pfn_first(pgmap, i));
 	dev_pagemap_cleanup(pgmap);
 
 	for (i = 0; i < pgmap->nr_range; i++)
 		pageunmap_range(pgmap, i);
 
 	WARN_ONCE(pgmap->altmap.alloc, "failed to free all reserved pages\n");
-	devmap_managed_enable_put(pgmap);
 }
 EXPORT_SYMBOL_GPL(memunmap_pages);
 
@@ -382,8 +345,6 @@ void *memremap_pages(struct dev_pagemap *pgmap, int nid)
 		}
 	}
 
-	devmap_managed_enable_get(pgmap);
-
 	/*
 	 * Clear the pgmap nr_range as it will be incremented for each
 	 * successfully processed range. This communicates how many
@@ -498,16 +459,9 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 EXPORT_SYMBOL_GPL(get_dev_pagemap);
 
 #ifdef CONFIG_DEV_PAGEMAP_OPS
-void free_devmap_managed_page(struct page *page)
+static void free_device_page(struct page *page)
 {
-	/* notify page idle for dax */
-	if (!is_device_private_page(page)) {
-		wake_up_var(&page->_refcount);
-		return;
-	}
-
 	__ClearPageWaiters(page);
-
 	mem_cgroup_uncharge(page);
 
 	/*
@@ -534,4 +488,19 @@ void free_devmap_managed_page(struct page *page)
 	page->mapping = NULL;
 	page->pgmap->ops->page_free(page);
 }
+
+void free_zone_device_page(struct page *page)
+{
+	switch (page->pgmap->type) {
+	case MEMORY_DEVICE_PRIVATE:
+		free_device_page(page);
+		return;
+	case MEMORY_DEVICE_FS_DAX:
+		/* notify page idle */
+		wake_up_var(&page->_refcount);
+		return;
+	default:
+		return;
+	}
+}
 #endif /* CONFIG_DEV_PAGEMAP_OPS */
diff --git a/mm/migrate.c b/mm/migrate.c
index 41ff2c9896c4..e3a10e2a1bb3 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -350,11 +350,6 @@ static int expected_page_refs(struct address_space *mapping, struct page *page)
 {
 	int expected_count = 1;
 
-	/*
-	 * Device private pages have an extra refcount as they are
-	 * ZONE_DEVICE pages.
-	 */
-	expected_count += is_device_private_page(page);
 	if (mapping)
 		expected_count += thp_nr_pages(page) + page_has_private(page);
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ef2265f86b91..1ef1f733af5b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6414,6 +6414,9 @@ void __ref memmap_init_zone_device(struct zone *zone,
 
 		__init_single_page(page, pfn, zone_idx, nid);
 
+		/* ZONE_DEVICE pages start with a zero reference count. */
+		set_page_count(page, 0);
+
 		/*
 		 * Mark page reserved as it will need to wait for onlining
 		 * phase for it to be fully associated with a zone.
diff --git a/mm/swap.c b/mm/swap.c
index dfb48cf9c2c9..9e821f1951c5 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -114,12 +114,11 @@ static void __put_compound_page(struct page *page)
 void __put_page(struct page *page)
 {
 	if (is_zone_device_page(page)) {
-		put_dev_pagemap(page->pgmap);
-
 		/*
 		 * The page belongs to the device that created pgmap. Do
 		 * not return it to page allocator.
 		 */
+		free_zone_device_page(page);
 		return;
 	}
 
@@ -917,29 +916,18 @@ void release_pages(struct page **pages, int nr)
 		if (is_huge_zero_page(page))
 			continue;
 
+		if (!put_page_testzero(page))
+			continue;
+
 		if (is_zone_device_page(page)) {
 			if (lruvec) {
 				unlock_page_lruvec_irqrestore(lruvec, flags);
 				lruvec = NULL;
 			}
-			/*
-			 * ZONE_DEVICE pages that return 'false' from
-			 * page_is_devmap_managed() do not require special
-			 * processing, and instead, expect a call to
-			 * put_page_testzero().
-			 */
-			if (page_is_devmap_managed(page)) {
-				put_devmap_managed_page(page);
-				continue;
-			}
-			if (put_page_testzero(page))
-				put_dev_pagemap(page->pgmap);
+			free_zone_device_page(page);
 			continue;
 		}
 
-		if (!put_page_testzero(page))
-			continue;
-
 		if (PageCompound(page)) {
 			if (lruvec) {
 				unlock_page_lruvec_irqrestore(lruvec, flags);
@@ -1143,26 +1131,3 @@ void __init swap_setup(void)
 	 * _really_ don't want to cluster much more
 	 */
 }
-
-#ifdef CONFIG_DEV_PAGEMAP_OPS
-void put_devmap_managed_page(struct page *page)
-{
-	int count;
-
-	if (WARN_ON_ONCE(!page_is_devmap_managed(page)))
-		return;
-
-	count = page_ref_dec_return(page);
-
-	/*
-	 * devmap page refcounts are 1-based, rather than 0-based: if
-	 * refcount is 1, then the page is free and the refcount is
-	 * stable because nobody holds a reference on the page.
-	 */
-	if (count == 1)
-		free_devmap_managed_page(page);
-	else if (!count)
-		__put_page(page);
-}
-EXPORT_SYMBOL(put_devmap_managed_page);
-#endif
-- 
2.32.0