Re: [PATCH -V5 06/25] powerpc: Reduce PTE table memory wastage

@@ -233,7 +233,7 @@ typedef struct {
 #endif
 #ifdef CONFIG_PPC_64K_PAGES
 	/* for 4K PTE fragment support */
-	struct page *pgtable_page;
+	void *pte_frag;
 #endif
 } mm_context_t;
 

@@ -511,7 +511,7 @@ typedef struct {
 #endif /* CONFIG_PPC_ICSWX */
 #ifdef CONFIG_PPC_64K_PAGES
 	/* for 4K PTE fragment support */
-	struct page *pgtable_page;
+	void *pte_frag;
 #endif
 } mm_context_t;
 

@@ -149,6 +149,16 @@ static inline void __pte_free_tlb(struct mmu_gather *tlb, pgtable_t table,
 }
 
 #else /* if CONFIG_PPC_64K_PAGES */
+/*
+ * we support 16 fragments per PTE page.
+ */
+#define PTE_FRAG_NR	16
+/*
+ * We use a 2K PTE page fragment and another 2K for storing
+ * real_pte_t hash index
+ */
+#define PTE_FRAG_SIZE_SHIFT  12
+#define PTE_FRAG_SIZE (2 * PTRS_PER_PTE * sizeof(pte_t))
 
 extern pte_t *page_table_alloc(struct mm_struct *, unsigned long, int);
 extern void page_table_free(struct mm_struct *, unsigned long *, int);

@@ -584,7 +584,7 @@ void __init setup_arch(char **cmdline_p)
 	init_mm.end_data = (unsigned long) _edata;
 	init_mm.brk = klimit;
 #ifdef CONFIG_PPC_64K_PAGES
-	init_mm.context.pgtable_page = NULL;
+	init_mm.context.pte_frag = NULL;
 #endif
 	irqstack_early_init();
 	exc_lvl_early_init();

@@ -23,6 +23,7 @@
 #include <linux/slab.h>
 
 #include <asm/mmu_context.h>
+#include <asm/pgalloc.h>
 
 #include "icswx.h"
 

@@ -86,7 +87,7 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 #endif /* CONFIG_PPC_ICSWX */
 
 #ifdef CONFIG_PPC_64K_PAGES
-	mm->context.pgtable_page = NULL;
+	mm->context.pte_frag = NULL;
 #endif
 	return 0;
 }

@@ -103,16 +104,19 @@ EXPORT_SYMBOL_GPL(__destroy_context);
 static void destroy_pagetable_page(struct mm_struct *mm)
 {
 	int count;
+	void *pte_frag;
 	struct page *page;
 
-	page = mm->context.pgtable_page;
-	if (!page)
+	pte_frag = mm->context.pte_frag;
+	if (!pte_frag)
 		return;
 
+	page = virt_to_page(pte_frag);
 	/* drop all the pending references */
-	count = atomic_read(&page->_mapcount) + 1;
-	/* We allow PTE_FRAG_NR(16) fragments from a PTE page */
-	count = atomic_sub_return(16 - count, &page->_count);
+	count = ((unsigned long )pte_frag &
+		 (PAGE_SIZE -1)) >> 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) {
 		pgtable_page_dtor(page);
 		page_mapcount_reset(page);

@@ -352,66 +352,50 @@ struct page *pmd_page(pmd_t pmd)
 }
 
 #ifdef CONFIG_PPC_64K_PAGES
-/*
- * we support 16 fragments per PTE page. This is limited by how many
- * bits we can pack in page->_mapcount. We use the first half for
- * tracking the usage for rcu page table free.
- */
-#define PTE_FRAG_NR	16
-/*
- * We use a 2K PTE page fragment and another 2K for storing
- * real_pte_t hash index
- */
-#define PTE_FRAG_SIZE (2 * PTRS_PER_PTE * sizeof(pte_t))
-
 static pte_t *get_from_cache(struct mm_struct *mm)
 {
-	int index;
-	pte_t *ret = NULL;
-	struct page *page;
+	void *ret = NULL;
 
 	spin_lock(&mm->page_table_lock);
-	page = mm->context.pgtable_page;
-	if (page) {
-		void *p = page_address(page);
-		index = atomic_add_return(1, &page->_mapcount);
-		ret = (pte_t *) (p + (index * PTE_FRAG_SIZE));
+	ret = mm->context.pte_frag;
+	if (ret) {
+		ret += PTE_FRAG_SIZE;
 		/*
 		 * If we have taken up all the fragments mark PTE page NULL
 		 */
-		if (index == PTE_FRAG_NR - 1)
-			mm->context.pgtable_page = NULL;
+		if (((unsigned long )ret & (PAGE_SIZE - 1)) == 0)
+			ret = NULL;
+		mm->context.pte_frag = ret;
 	}
 	spin_unlock(&mm->page_table_lock);
-	return ret;
+	return (pte_t *)ret;
 }
 
 static pte_t *__alloc_for_cache(struct mm_struct *mm, int kernel)
 {
-	pte_t *ret = NULL;
+	void *ret = NULL;
 	struct page *page = alloc_page(GFP_KERNEL | __GFP_NOTRACK |
 				       __GFP_REPEAT | __GFP_ZERO);
 	if (!page)
 		return NULL;
 
+	ret = page_address(page);
 	spin_lock(&mm->page_table_lock);
 	/*
 	 * If we find pgtable_page set, we return
 	 * the allocated page with single fragement
 	 * count.
 	 */
-	if (likely(!mm->context.pgtable_page)) {
+	if (likely(!mm->context.pte_frag)) {
 		atomic_set(&page->_count, PTE_FRAG_NR);
-		atomic_set(&page->_mapcount, 0);
-		mm->context.pgtable_page = page;
+		mm->context.pte_frag = ret + PTE_FRAG_SIZE;
 	}
 	spin_unlock(&mm->page_table_lock);
 
-	ret = (unsigned long *)page_address(page);
 	if (!kernel)
 		pgtable_page_ctor(page);
 
-	return ret;
+	return (pte_t *)ret;
 }
 
 pte_t *page_table_alloc(struct mm_struct *mm, unsigned long vmaddr, int kernel)