powerpc/mm: Cleanup management of kmem_caches for pagetables

Currently we have a fair bit of rather fiddly code to manage the
various kmem_caches used to store page tables of various levels.  We
generally have two caches holding some combination of PGD, PUD and PMD
tables, plus several more for the special hugepage pagetables.

This patch cleans this all up by taking a different approach.  Rather
than the caches being designated as for PUDs or for hugeptes for 16M
pages, the caches are simply allocated to be a specific size.  Thus
sharing of caches between different types/levels of pagetables happens
naturally.  The pagetable size, where needed, is passed around encoded
in the same way as {PGD,PUD,PMD}_INDEX_SIZE; that is n where the
pagetable contains 2^n pointers.

Signed-off-by: David Gibson <dwg@au1.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

4 files changed, 45 insertions, 56 deletions

diff --git a/arch/powerpc/include/asm/pgalloc-32.h b/arch/powerpc/include/asm/pgalloc-32.h
index c9500d666a1d..580cf73b96e8 100644
--- a/arch/powerpc/include/asm/pgalloc-32.h
+++ b/arch/powerpc/include/asm/pgalloc-32.h
@@ -3,7 +3,8 @@
 
 #include <linux/threads.h>
 
-#define PTE_NONCACHE_NUM	0  /* dummy for now to share code w/ppc64 */
+/* For 32-bit, all levels of page tables are just drawn from get_free_page() */
+#define MAX_PGTABLE_INDEX_SIZE	0
 
 extern void __bad_pte(pmd_t *pmd);
 
@@ -36,11 +37,10 @@ extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
 extern pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr);
 extern pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long addr);
 
-static inline void pgtable_free(pgtable_free_t pgf)
+static inline void pgtable_free(void *table, unsigned index_size)
 {
-	void *p = (void *)(pgf.val & ~PGF_CACHENUM_MASK);
-
-	free_page((unsigned long)p);
+	BUG_ON(index_size); /* 32-bit doesn't use this */
+	free_page((unsigned long)table);
 }
 
 #define check_pgt_cache()	do { } while (0)
diff --git a/arch/powerpc/include/asm/pgalloc-64.h b/arch/powerpc/include/asm/pgalloc-64.h
index e6f069c4f713..5c1cd73dafa8 100644
--- a/arch/powerpc/include/asm/pgalloc-64.h
+++ b/arch/powerpc/include/asm/pgalloc-64.h
@@ -11,27 +11,39 @@
 #include <linux/cpumask.h>
 #include <linux/percpu.h>
 
+/*
+ * Functions that deal with pagetables that could be at any level of
+ * the table need to be passed an "index_size" so they know how to
+ * handle allocation.  For PTE pages (which are linked to a struct
+ * page for now, and drawn from the main get_free_pages() pool), the
+ * allocation size will be (2^index_size * sizeof(pointer)) and
+ * allocations are drawn from the kmem_cache in PGT_CACHE(index_size).
+ *
+ * The maximum index size needs to be big enough to allow any
+ * pagetable sizes we need, but small enough to fit in the low bits of
+ * any page table pointer.  In other words all pagetables, even tiny
+ * ones, must be aligned to allow at least enough low 0 bits to
+ * contain this value.  This value is also used as a mask, so it must
+ * be one less than a power of two.
+ */
+#define MAX_PGTABLE_INDEX_SIZE	0xf
+
 #ifndef CONFIG_PPC_SUBPAGE_PROT
 static inline void subpage_prot_free(pgd_t *pgd) {}
 #endif
 
 extern struct kmem_cache *pgtable_cache[];
-
-#define PGD_CACHE_NUM		0
-#define PUD_CACHE_NUM		1
-#define PMD_CACHE_NUM		1
-#define HUGEPTE_CACHE_NUM	2
-#define PTE_NONCACHE_NUM	7  /* from GFP rather than kmem_cache */
+#define PGT_CACHE(shift) (pgtable_cache[(shift)-1])
 
 static inline pgd_t *pgd_alloc(struct mm_struct *mm)
 {
-	return kmem_cache_alloc(pgtable_cache[PGD_CACHE_NUM], GFP_KERNEL);
+	return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), GFP_KERNEL);
 }
 
 static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 {
 	subpage_prot_free(pgd);
-	kmem_cache_free(pgtable_cache[PGD_CACHE_NUM], pgd);
+	kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd);
 }
 
 #ifndef CONFIG_PPC_64K_PAGES
@@ -40,13 +52,13 @@ static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
 
 static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(pgtable_cache[PUD_CACHE_NUM],
+	return kmem_cache_alloc(PGT_CACHE(PUD_INDEX_SIZE),
 				GFP_KERNEL|__GFP_REPEAT);
 }
 
 static inline void pud_free(struct mm_struct *mm, pud_t *pud)
 {
-	kmem_cache_free(pgtable_cache[PUD_CACHE_NUM], pud);
+	kmem_cache_free(PGT_CACHE(PUD_INDEX_SIZE), pud);
 }
 
 static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
@@ -78,13 +90,13 @@ static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
 
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return kmem_cache_alloc(pgtable_cache[PMD_CACHE_NUM],
+	return kmem_cache_alloc(PGT_CACHE(PMD_INDEX_SIZE),
 				GFP_KERNEL|__GFP_REPEAT);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
-	kmem_cache_free(pgtable_cache[PMD_CACHE_NUM], pmd);
+	kmem_cache_free(PGT_CACHE(PMD_INDEX_SIZE), pmd);
 }
 
 static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
@@ -107,24 +119,22 @@ static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
 	return page;
 }
 
-static inline void pgtable_free(pgtable_free_t pgf)
+static inline void pgtable_free(void *table, unsigned index_size)
 {
-	void *p = (void *)(pgf.val & ~PGF_CACHENUM_MASK);
-	int cachenum = pgf.val & PGF_CACHENUM_MASK;
-
-	if (cachenum == PTE_NONCACHE_NUM)
-		free_page((unsigned long)p);
-	else
-		kmem_cache_free(pgtable_cache[cachenum], p);
+	if (!index_size)
+		free_page((unsigned long)table);
+	else {
+		BUG_ON(index_size > MAX_PGTABLE_INDEX_SIZE);
+		kmem_cache_free(PGT_CACHE(index_size), table);
+	}
 }
 
-#define __pmd_free_tlb(tlb, pmd,addr)		      \
-	pgtable_free_tlb(tlb, pgtable_free_cache(pmd, \
-		PMD_CACHE_NUM, PMD_TABLE_SIZE-1))
+#define __pmd_free_tlb(tlb, pmd, addr)		      \
+	pgtable_free_tlb(tlb, pmd, PMD_INDEX_SIZE)
 #ifndef CONFIG_PPC_64K_PAGES
 #define __pud_free_tlb(tlb, pud, addr)		      \
-	pgtable_free_tlb(tlb, pgtable_free_cache(pud, \
-		PUD_CACHE_NUM, PUD_TABLE_SIZE-1))
+	pgtable_free_tlb(tlb, pud, PUD_INDEX_SIZE)
+
 #endif /* CONFIG_PPC_64K_PAGES */
 
 #define check_pgt_cache()	do { } while (0)
diff --git a/arch/powerpc/include/asm/pgalloc.h b/arch/powerpc/include/asm/pgalloc.h
index f2e812de7c3c..abe8532bd14e 100644
--- a/arch/powerpc/include/asm/pgalloc.h
+++ b/arch/powerpc/include/asm/pgalloc.h
@@ -24,25 +24,6 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 	__free_page(ptepage);
 }
 
-typedef struct pgtable_free {
-	unsigned long val;
-} pgtable_free_t;
-
-/* This needs to be big enough to allow for MMU_PAGE_COUNT + 2 to be stored
- * and small enough to fit in the low bits of any naturally aligned page
- * table cache entry. Arbitrarily set to 0x1f, that should give us some
- * room to grow
- */
-#define PGF_CACHENUM_MASK	0x1f
-
-static inline pgtable_free_t pgtable_free_cache(void *p, int cachenum,
-						unsigned long mask)
-{
-	BUG_ON(cachenum > PGF_CACHENUM_MASK);
-
-	return (pgtable_free_t){.val = ((unsigned long) p & ~mask) | cachenum};
-}
-
 #ifdef CONFIG_PPC64
 #include <asm/pgalloc-64.h>
 #else
@@ -50,12 +31,12 @@ static inline pgtable_free_t pgtable_free_cache(void *p, int cachenum,
 #endif
 
 #ifdef CONFIG_SMP
-extern void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf);
+extern void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift);
 extern void pte_free_finish(void);
 #else /* CONFIG_SMP */
-static inline void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf)
+static inline void pgtable_free_tlb(struct mmu_gather *tlb, void *table, unsigned shift)
 {
-	pgtable_free(pgf);
+	pgtable_free(table, shift);
 }
 static inline void pte_free_finish(void) { }
 #endif /* !CONFIG_SMP */
@@ -63,12 +44,9 @@ static inline void pte_free_finish(void) { }
 static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *ptepage,
 				  unsigned long address)
 {
-	pgtable_free_t pgf = pgtable_free_cache(page_address(ptepage),
-						PTE_NONCACHE_NUM,
-						PTE_TABLE_SIZE-1);
 	tlb_flush_pgtable(tlb, address);
 	pgtable_page_dtor(ptepage);
-	pgtable_free_tlb(tlb, pgf);
+	pgtable_free_tlb(tlb, page_address(ptepage), 0);
 }
 
 #endif /* __KERNEL__ */
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index 806abe7a3fa5..8697d6555090 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -354,6 +354,7 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
 #define pgoff_to_pte(off)	((pte_t) {((off) << PTE_RPN_SHIFT)|_PAGE_FILE})
 #define PTE_FILE_MAX_BITS	(BITS_PER_LONG - PTE_RPN_SHIFT)
 
+void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
 void pgtable_cache_init(void);
 
 /*