mm: introduce page reference manipulation functions

The success of CMA allocation largely depends on the success of
migration and key factor of it is page reference count.  Until now, page
reference is manipulated by direct calling atomic functions so we cannot
follow up who and where manipulate it.  Then, it is hard to find actual
reason of CMA allocation failure.  CMA allocation should be guaranteed
to succeed so finding offending place is really important.

In this patch, call sites where page reference is manipulated are
converted to introduced wrapper function.  This is preparation step to
add tracepoint to each page reference manipulation function.  With this
facility, we can easily find reason of CMA allocation failure.  There is
no functional change in this patch.

In addition, this patch also converts reference read sites.  It will
help a second step that renames page._count to something else and
prevents later attempt to direct access to it (Suggested by Andrew).

Signed-off-by: Joonsoo Kim <[email protected]>
Acked-by: Michal Nazarewicz <[email protected]>
Acked-by: Vlastimil Babka <[email protected]>
Cc: Minchan Kim <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: "Kirill A. Shutemov" <[email protected]>
Cc: Sergey Senozhatsky <[email protected]>
Cc: Steven Rostedt <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

arch/mips/mm/gup.c

@@ -64,7 +64,7 @@ static inline void get_head_page_multiple(struct page *page, int nr)
 {
 	VM_BUG_ON(page != compound_head(page));
 	VM_BUG_ON(page_count(page) == 0);
-	atomic_add(nr, &page->_count);
+	page_ref_add(page, nr);
 	SetPageReferenced(page);
 }
 

arch/powerpc/mm/mmu_context_hash64.c

@@ -118,8 +118,7 @@ static void destroy_pagetable_page(struct mm_struct *mm)
 	/* drop all the pending references */
 	count = ((unsigned long)pte_frag & ~PAGE_MASK) >> PTE_FRAG_SIZE_SHIFT;
 	/* We allow PTE_FRAG_NR fragments from a PTE page */
-	count = atomic_sub_return(PTE_FRAG_NR - count, &page->_count);
-	if (!count) {
+	if (page_ref_sub_and_test(page, PTE_FRAG_NR - count)) {
 		pgtable_page_dtor(page);
 		free_hot_cold_page(page, 0);
 	}

arch/powerpc/mm/pgtable_64.c

@@ -403,7 +403,7 @@ static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel)
 	 * count.
 	 */
 	if (likely(!mm->context.pte_frag)) {
-		atomic_set(&page->_count, PTE_FRAG_NR);
+		set_page_count(page, PTE_FRAG_NR);
 		mm->context.pte_frag = ret + PTE_FRAG_SIZE;
 	}
 	spin_unlock(&mm->page_table_lock);

arch/powerpc/platforms/512x/mpc512x_shared.c

@@ -188,7 +188,7 @@ static struct fsl_diu_shared_fb __attribute__ ((__aligned__(8))) diu_shared_fb;
 static inline void mpc512x_free_bootmem(struct page *page)
 {
 	BUG_ON(PageTail(page));
-	BUG_ON(atomic_read(&page->_count) > 1);
+	BUG_ON(page_ref_count(page) > 1);
 	free_reserved_page(page);
 }
 

arch/x86/mm/gup.c

@@ -131,7 +131,7 @@ static inline void get_head_page_multiple(struct page *page, int nr)
 {
 	VM_BUG_ON_PAGE(page != compound_head(page), page);
 	VM_BUG_ON_PAGE(page_count(page) == 0, page);
-	atomic_add(nr, &page->_count);
+	page_ref_add(page, nr);
 	SetPageReferenced(page);
 }
 

drivers/block/aoe/aoecmd.c

@@ -875,7 +875,7 @@ bio_pageinc(struct bio *bio)
 		 * compound pages is no longer allowed by the kernel.
 		 */
 		page = compound_head(bv.bv_page);
-		atomic_inc(&page->_count);
+		page_ref_inc(page);
 	}
 }
 
@@ -888,7 +888,7 @@ bio_pagedec(struct bio *bio)
 
 	bio_for_each_segment(bv, bio, iter) {
 		page = compound_head(bv.bv_page);
-		atomic_dec(&page->_count);
+		page_ref_dec(page);
 	}
 }
 

drivers/net/ethernet/freescale/gianfar.c

@@ -2944,7 +2944,7 @@ static bool gfar_add_rx_frag(struct gfar_rx_buff *rxb, u32 lstatus,
 	/* change offset to the other half */
 	rxb->page_offset ^= GFAR_RXB_TRUESIZE;
 
-	atomic_inc(&page->_count);
+	page_ref_inc(page);
 
 	return true;
 }

drivers/net/ethernet/intel/fm10k/fm10k_main.c

@@ -243,7 +243,7 @@ static bool fm10k_can_reuse_rx_page(struct fm10k_rx_buffer *rx_buffer,
 	/* Even if we own the page, we are not allowed to use atomic_set()
 	 * This would break get_page_unless_zero() users.
 	 */
-	atomic_inc(&page->_count);
+	page_ref_inc(page);
 
 	return true;
 }

drivers/net/ethernet/intel/igb/igb_main.c

@@ -6630,7 +6630,7 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
 	/* Even if we own the page, we are not allowed to use atomic_set()
 	 * This would break get_page_unless_zero() users.
 	 */
-	atomic_inc(&page->_count);
+	page_ref_inc(page);
 
 	return true;
 }

drivers/net/ethernet/intel/ixgbe/ixgbe_main.c

@@ -1942,7 +1942,7 @@ static bool ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring,
 	/* Even if we own the page, we are not allowed to use atomic_set()
 	 * This would break get_page_unless_zero() users.
 	 */
-	atomic_inc(&page->_count);
+	page_ref_inc(page);
 
 	return true;
 }

drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c

@@ -837,7 +837,7 @@ static bool ixgbevf_add_rx_frag(struct ixgbevf_ring *rx_ring,
 	/* Even if we own the page, we are not allowed to use atomic_set()
 	 * This would break get_page_unless_zero() users.
 	 */
-	atomic_inc(&page->_count);
+	page_ref_inc(page);
 
 	return true;
 }

drivers/net/ethernet/mellanox/mlx4/en_rx.c

@@ -82,8 +82,7 @@ static int mlx4_alloc_pages(struct mlx4_en_priv *priv,
 	/* Not doing get_page() for each frag is a big win
 	 * on asymetric workloads. Note we can not use atomic_set().
 	 */
-	atomic_add(page_alloc->page_size / frag_info->frag_stride - 1,
-		   &page->_count);
+	page_ref_add(page, page_alloc->page_size / frag_info->frag_stride - 1);
 	return 0;
 }
 
@@ -127,7 +126,7 @@ static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv,
 			dma_unmap_page(priv->ddev, page_alloc[i].dma,
 				page_alloc[i].page_size, PCI_DMA_FROMDEVICE);
 			page = page_alloc[i].page;
-			atomic_set(&page->_count, 1);
+			set_page_count(page, 1);
 			put_page(page);
 		}
 	}
@@ -165,7 +164,7 @@ static int mlx4_en_init_allocator(struct mlx4_en_priv *priv,
 
 		en_dbg(DRV, priv, "  frag %d allocator: - size:%d frags:%d\n",
 		       i, ring->page_alloc[i].page_size,
-		       atomic_read(&ring->page_alloc[i].page->_count));
+		       page_ref_count(ring->page_alloc[i].page));
 	}
 	return 0;
 
@@ -177,7 +176,7 @@ static int mlx4_en_init_allocator(struct mlx4_en_priv *priv,
 		dma_unmap_page(priv->ddev, page_alloc->dma,
 			       page_alloc->page_size, PCI_DMA_FROMDEVICE);
 		page = page_alloc->page;
-		atomic_set(&page->_count, 1);
+		set_page_count(page, 1);
 		put_page(page);
 		page_alloc->page = NULL;
 	}

drivers/net/ethernet/sun/niu.c

@@ -3341,7 +3341,7 @@ static int niu_rbr_add_page(struct niu *np, struct rx_ring_info *rp,
 
 	niu_hash_page(rp, page, addr);
 	if (rp->rbr_blocks_per_page > 1)
-		atomic_add(rp->rbr_blocks_per_page - 1, &page->_count);
+		page_ref_add(page, rp->rbr_blocks_per_page - 1);
 
 	for (i = 0; i < rp->rbr_blocks_per_page; i++) {
 		__le32 *rbr = &rp->rbr[start_index + i];

fs/nilfs2/page.c

@@ -180,7 +180,7 @@ void nilfs_page_bug(struct page *page)
 
 	printk(KERN_CRIT "NILFS_PAGE_BUG(%p): cnt=%d index#=%llu flags=0x%lx "
 	       "mapping=%p ino=%lu\n",
-	       page, atomic_read(&page->_count),
+	       page, page_ref_count(page),
 	       (unsigned long long)page->index, page->flags, m, ino);
 
 	if (page_has_buffers(page)) {

include/linux/mm.h

@@ -22,6 +22,7 @@
 #include <linux/resource.h>
 #include <linux/page_ext.h>
 #include <linux/err.h>
+#include <linux/page_ref.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -386,8 +387,8 @@ static inline int pmd_devmap(pmd_t pmd)
  */
 static inline int put_page_testzero(struct page *page)
 {
-	VM_BUG_ON_PAGE(atomic_read(&page->_count) == 0, page);
-	return atomic_dec_and_test(&page->_count);
+	VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
+	return page_ref_dec_and_test(page);
 }
 
 /*
@@ -398,7 +399,7 @@ static inline int put_page_testzero(struct page *page)
  */
 static inline int get_page_unless_zero(struct page *page)
 {
-	return atomic_inc_not_zero(&page->_count);
+	return page_ref_add_unless(page, 1, 0);
 }
 
 extern int page_is_ram(unsigned long pfn);
@@ -486,27 +487,13 @@ static inline int total_mapcount(struct page *page)
 }
 #endif
 
-static inline int page_count(struct page *page)
-{
-	return atomic_read(&compound_head(page)->_count);
-}
-
 static inline struct page *virt_to_head_page(const void *x)
 {
 	struct page *page = virt_to_page(x);
 
 	return compound_head(page);
 }
 
-/*
- * Setup the page count before being freed into the page allocator for
- * the first time (boot or memory hotplug)
- */
-static inline void init_page_count(struct page *page)
-{
-	atomic_set(&page->_count, 1);
-}
-
 void __put_page(struct page *page);
 
 void put_pages_list(struct list_head *pages);
@@ -716,8 +703,8 @@ static inline void get_page(struct page *page)
 	 * Getting a normal page or the head of a compound page
 	 * requires to already have an elevated page->_count.
 	 */
-	VM_BUG_ON_PAGE(atomic_read(&page->_count) <= 0, page);
-	atomic_inc(&page->_count);
+	VM_BUG_ON_PAGE(page_ref_count(page) <= 0, page);
+	page_ref_inc(page);
 
 	if (unlikely(is_zone_device_page(page)))
 		get_zone_device_page(page);

include/linux/page_ref.h

@@ -0,0 +1,85 @@
+#ifndef _LINUX_PAGE_REF_H
+#define _LINUX_PAGE_REF_H
+
+#include <linux/atomic.h>
+#include <linux/mm_types.h>
+#include <linux/page-flags.h>
+
+static inline int page_ref_count(struct page *page)
+{
+	return atomic_read(&page->_count);
+}
+
+static inline int page_count(struct page *page)
+{
+	return atomic_read(&compound_head(page)->_count);
+}
+
+static inline void set_page_count(struct page *page, int v)
+{
+	atomic_set(&page->_count, v);
+}
+
+/*
+ * Setup the page count before being freed into the page allocator for
+ * the first time (boot or memory hotplug)
+ */
+static inline void init_page_count(struct page *page)
+{
+	set_page_count(page, 1);
+}
+
+static inline void page_ref_add(struct page *page, int nr)
+{
+	atomic_add(nr, &page->_count);
+}
+
+static inline void page_ref_sub(struct page *page, int nr)
+{
+	atomic_sub(nr, &page->_count);
+}
+
+static inline void page_ref_inc(struct page *page)
+{
+	atomic_inc(&page->_count);
+}
+
+static inline void page_ref_dec(struct page *page)
+{
+	atomic_dec(&page->_count);
+}
+
+static inline int page_ref_sub_and_test(struct page *page, int nr)
+{
+	return atomic_sub_and_test(nr, &page->_count);
+}
+
+static inline int page_ref_dec_and_test(struct page *page)
+{
+	return atomic_dec_and_test(&page->_count);
+}
+
+static inline int page_ref_dec_return(struct page *page)
+{
+	return atomic_dec_return(&page->_count);
+}
+
+static inline int page_ref_add_unless(struct page *page, int nr, int u)
+{
+	return atomic_add_unless(&page->_count, nr, u);
+}
+
+static inline int page_ref_freeze(struct page *page, int count)
+{
+	return likely(atomic_cmpxchg(&page->_count, count, 0) == count);
+}
+
+static inline void page_ref_unfreeze(struct page *page, int count)
+{
+	VM_BUG_ON_PAGE(page_count(page) != 0, page);
+	VM_BUG_ON(count == 0);
+
+	atomic_set(&page->_count, count);
+}
+
+#endif

include/linux/pagemap.h

@@ -165,7 +165,7 @@ static inline int page_cache_get_speculative(struct page *page)
 	 * SMP requires.
 	 */
 	VM_BUG_ON_PAGE(page_count(page) == 0, page);
-	atomic_inc(&page->_count);
+	page_ref_inc(page);
 
 #else
 	if (unlikely(!get_page_unless_zero(page))) {
@@ -194,30 +194,17 @@ static inline int page_cache_add_speculative(struct page *page, int count)
 	VM_BUG_ON(!in_atomic());
 # endif
 	VM_BUG_ON_PAGE(page_count(page) == 0, page);
-	atomic_add(count, &page->_count);
+	page_ref_add(page, count);
 
 #else
-	if (unlikely(!atomic_add_unless(&page->_count, count, 0)))
+	if (unlikely(!page_ref_add_unless(page, count, 0)))
 		return 0;
 #endif
 	VM_BUG_ON_PAGE(PageCompound(page) && page != compound_head(page), page);
 
 	return 1;
 }
 
-static inline int page_freeze_refs(struct page *page, int count)
-{
-	return likely(atomic_cmpxchg(&page->_count, count, 0) == count);
-}
-
-static inline void page_unfreeze_refs(struct page *page, int count)
-{
-	VM_BUG_ON_PAGE(page_count(page) != 0, page);
-	VM_BUG_ON(count == 0);
-
-	atomic_set(&page->_count, count);
-}
-
 #ifdef CONFIG_NUMA
 extern struct page *__page_cache_alloc(gfp_t gfp);
 #else

mm/debug.c

@@ -43,7 +43,7 @@ const struct trace_print_flags vmaflag_names[] = {
 void __dump_page(struct page *page, const char *reason)
 {
 	pr_emerg("page:%p count:%d mapcount:%d mapping:%p index:%#lx",
-		  page, atomic_read(&page->_count), page_mapcount(page),
+		  page, page_ref_count(page), page_mapcount(page),
 		  page->mapping, page->index);
 	if (PageCompound(page))
 		pr_cont(" compound_mapcount: %d", compound_mapcount(page));

mm/huge_memory.c

@@ -2888,7 +2888,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 
 	page = pmd_page(*pmd);
 	VM_BUG_ON_PAGE(!page_count(page), page);
-	atomic_add(HPAGE_PMD_NR - 1, &page->_count);
+	page_ref_add(page, HPAGE_PMD_NR - 1);
 	write = pmd_write(*pmd);
 	young = pmd_young(*pmd);
 	dirty = pmd_dirty(*pmd);
@@ -3257,7 +3257,7 @@ static void __split_huge_page_tail(struct page *head, int tail,
 	struct page *page_tail = head + tail;
 
 	VM_BUG_ON_PAGE(atomic_read(&page_tail->_mapcount) != -1, page_tail);
-	VM_BUG_ON_PAGE(atomic_read(&page_tail->_count) != 0, page_tail);
+	VM_BUG_ON_PAGE(page_ref_count(page_tail) != 0, page_tail);
 
 	/*
 	 * tail_page->_count is zero and not changing from under us. But
@@ -3270,7 +3270,7 @@ static void __split_huge_page_tail(struct page *head, int tail,
 	 * atomic_set() here would be safe on all archs (and not only on x86),
 	 * it's safer to use atomic_inc().
 	 */
-	atomic_inc(&page_tail->_count);
+	page_ref_inc(page_tail);
 
 	page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
 	page_tail->flags |= (head->flags &