[PATCH 1/7] Revert "powerpc: port 64 bits pgtable_cache to 32 bits"

Tim Gardner tim.gardner at canonical.com
Fri Mar 24 14:05:34 UTC 2017


BugLink: http://bugs.launchpad.net/bugs/1670247

This reverts commit bbe905e7f8b7622f8e0c289c908a203d5855c696.

Revert because this patch needs a prerequiite for clean application.

Signed-off-by: Tim Gardner <tim.gardner at canonical.com>
---
 arch/powerpc/include/asm/book3s/32/pgalloc.h |  44 ++---------
 arch/powerpc/include/asm/book3s/32/pgtable.h |  40 +++++-----
 arch/powerpc/include/asm/book3s/64/pgtable.h |   3 +
 arch/powerpc/include/asm/nohash/32/pgalloc.h |  44 ++---------
 arch/powerpc/include/asm/nohash/32/pgtable.h |  42 ++++++-----
 arch/powerpc/include/asm/nohash/64/pgtable.h |   2 +
 arch/powerpc/include/asm/pgtable.h           |   2 -
 arch/powerpc/mm/Makefile                     |   3 +-
 arch/powerpc/mm/init-common.c                | 107 ---------------------------
 arch/powerpc/mm/init_64.c                    |  77 +++++++++++++++++++
 arch/powerpc/mm/pgtable_32.c                 |  37 +++++++++
 11 files changed, 174 insertions(+), 227 deletions(-)
 delete mode 100644 arch/powerpc/mm/init-common.c

diff --git a/arch/powerpc/include/asm/book3s/32/pgalloc.h b/arch/powerpc/include/asm/book3s/32/pgalloc.h
index d310546..8e21bb4 100644
--- a/arch/powerpc/include/asm/book3s/32/pgalloc.h
+++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h
@@ -2,42 +2,14 @@
 #define _ASM_POWERPC_BOOK3S_32_PGALLOC_H
 
 #include <linux/threads.h>
-#include <linux/slab.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
+/* 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);
 
-extern struct kmem_cache *pgtable_cache[];
-#define PGT_CACHE(shift) ({				\
-			BUG_ON(!(shift));		\
-			pgtable_cache[(shift) - 1];	\
-		})
-
-static inline pgd_t *pgd_alloc(struct mm_struct *mm)
-{
-	return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), GFP_KERNEL);
-}
-
-static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
-	kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd);
-}
+extern pgd_t *pgd_alloc(struct mm_struct *mm);
+extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
 
 /*
  * We don't have any real pmd's, and this code never triggers because
@@ -96,12 +68,8 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 
 static inline void pgtable_free(void *table, unsigned index_size)
 {
-	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);
-	}
+	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/book3s/32/pgtable.h b/arch/powerpc/include/asm/book3s/32/pgtable.h
index 0122236..dc58980 100644
--- a/arch/powerpc/include/asm/book3s/32/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
@@ -8,23 +8,6 @@
 /* And here we include common definitions */
 #include <asm/pte-common.h>
 
-#define PTE_INDEX_SIZE	PTE_SHIFT
-#define PMD_INDEX_SIZE	0
-#define PUD_INDEX_SIZE	0
-#define PGD_INDEX_SIZE	(32 - PGDIR_SHIFT)
-
-#define PMD_CACHE_INDEX	PMD_INDEX_SIZE
-
-#ifndef __ASSEMBLY__
-#define PTE_TABLE_SIZE	(sizeof(pte_t) << PTE_INDEX_SIZE)
-#define PMD_TABLE_SIZE	0
-#define PUD_TABLE_SIZE	0
-#define PGD_TABLE_SIZE	(sizeof(pgd_t) << PGD_INDEX_SIZE)
-#endif	/* __ASSEMBLY__ */
-
-#define PTRS_PER_PTE	(1 << PTE_INDEX_SIZE)
-#define PTRS_PER_PGD	(1 << PGD_INDEX_SIZE)
-
 /*
  * The normal case is that PTEs are 32-bits and we have a 1-page
  * 1024-entry pgdir pointing to 1-page 1024-entry PTE pages.  -- paulus
@@ -36,10 +19,14 @@
  * -Matt
  */
 /* PGDIR_SHIFT determines what a top-level page table entry can map */
-#define PGDIR_SHIFT	(PAGE_SHIFT + PTE_INDEX_SIZE)
+#define PGDIR_SHIFT	(PAGE_SHIFT + PTE_SHIFT)
 #define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
+#define PTRS_PER_PTE	(1 << PTE_SHIFT)
+#define PTRS_PER_PMD	1
+#define PTRS_PER_PGD	(1 << (32 - PGDIR_SHIFT))
+
 #define USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)
 /*
  * This is the bottom of the PKMAP area with HIGHMEM or an arbitrary
@@ -95,8 +82,12 @@
 
 extern unsigned long ioremap_bot;
 
-/* Bits to mask out from a PGD to get to the PUD page */
-#define PGD_MASKED_BITS		0
+/*
+ * entries per page directory level: our page-table tree is two-level, so
+ * we don't really have any PMD directory.
+ */
+#define PTE_TABLE_SIZE	(sizeof(pte_t) << PTE_SHIFT)
+#define PGD_TABLE_SIZE	(sizeof(pgd_t) << (32 - PGDIR_SHIFT))
 
 #define pte_ERROR(e) \
 	pr_err("%s:%d: bad pte %llx.\n", __FILE__, __LINE__, \
@@ -293,6 +284,15 @@ static inline void __ptep_set_access_flags(struct mm_struct *mm,
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) >> 3 })
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val << 3 })
 
+#ifndef CONFIG_PPC_4K_PAGES
+void pgtable_cache_init(void);
+#else
+/*
+ * No page table caches to initialise
+ */
+#define pgtable_cache_init()	do { } while (0)
+#endif
+
 extern int get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep,
 		      pmd_t **pmdp);
 
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index 8f9d5a6..6b2a58f 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -817,6 +817,9 @@ extern struct page *pgd_page(pgd_t pgd);
 #define pgd_ERROR(e) \
 	pr_err("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
 
+void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
+void pgtable_cache_init(void);
+
 static inline int map_kernel_page(unsigned long ea, unsigned long pa,
 				  unsigned long flags)
 {
diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h
index 6331392..76d6b9e 100644
--- a/arch/powerpc/include/asm/nohash/32/pgalloc.h
+++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h
@@ -2,42 +2,14 @@
 #define _ASM_POWERPC_PGALLOC_32_H
 
 #include <linux/threads.h>
-#include <linux/slab.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
+/* 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);
 
-extern struct kmem_cache *pgtable_cache[];
-#define PGT_CACHE(shift) ({				\
-			BUG_ON(!(shift));		\
-			pgtable_cache[(shift) - 1];	\
-		})
-
-static inline pgd_t *pgd_alloc(struct mm_struct *mm)
-{
-	return kmem_cache_alloc(PGT_CACHE(PGD_INDEX_SIZE), GFP_KERNEL);
-}
-
-static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
-	kmem_cache_free(PGT_CACHE(PGD_INDEX_SIZE), pgd);
-}
+extern pgd_t *pgd_alloc(struct mm_struct *mm);
+extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
 
 /*
  * We don't have any real pmd's, and this code never triggers because
@@ -96,12 +68,8 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
 
 static inline void pgtable_free(void *table, unsigned index_size)
 {
-	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);
-	}
+	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/nohash/32/pgtable.h b/arch/powerpc/include/asm/nohash/32/pgtable.h
index ba9921b..65073fb 100644
--- a/arch/powerpc/include/asm/nohash/32/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
@@ -16,23 +16,6 @@ extern int icache_44x_need_flush;
 
 #endif /* __ASSEMBLY__ */
 
-#define PTE_INDEX_SIZE	PTE_SHIFT
-#define PMD_INDEX_SIZE	0
-#define PUD_INDEX_SIZE	0
-#define PGD_INDEX_SIZE	(32 - PGDIR_SHIFT)
-
-#define PMD_CACHE_INDEX	PMD_INDEX_SIZE
-
-#ifndef __ASSEMBLY__
-#define PTE_TABLE_SIZE	(sizeof(pte_t) << PTE_INDEX_SIZE)
-#define PMD_TABLE_SIZE	0
-#define PUD_TABLE_SIZE	0
-#define PGD_TABLE_SIZE	(sizeof(pgd_t) << PGD_INDEX_SIZE)
-#endif	/* __ASSEMBLY__ */
-
-#define PTRS_PER_PTE	(1 << PTE_INDEX_SIZE)
-#define PTRS_PER_PGD	(1 << PGD_INDEX_SIZE)
-
 /*
  * The normal case is that PTEs are 32-bits and we have a 1-page
  * 1024-entry pgdir pointing to 1-page 1024-entry PTE pages.  -- paulus
@@ -44,12 +27,22 @@ extern int icache_44x_need_flush;
  * -Matt
  */
 /* PGDIR_SHIFT determines what a top-level page table entry can map */
-#define PGDIR_SHIFT	(PAGE_SHIFT + PTE_INDEX_SIZE)
+#define PGDIR_SHIFT	(PAGE_SHIFT + PTE_SHIFT)
 #define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 
-/* Bits to mask out from a PGD to get to the PUD page */
-#define PGD_MASKED_BITS		0
+/*
+ * entries per page directory level: our page-table tree is two-level, so
+ * we don't really have any PMD directory.
+ */
+#ifndef __ASSEMBLY__
+#define PTE_TABLE_SIZE	(sizeof(pte_t) << PTE_SHIFT)
+#define PGD_TABLE_SIZE	(sizeof(pgd_t) << (32 - PGDIR_SHIFT))
+#endif	/* __ASSEMBLY__ */
+
+#define PTRS_PER_PTE	(1 << PTE_SHIFT)
+#define PTRS_PER_PMD	1
+#define PTRS_PER_PGD	(1 << (32 - PGDIR_SHIFT))
 
 #define USER_PTRS_PER_PGD	(TASK_SIZE / PGDIR_SIZE)
 #define FIRST_USER_ADDRESS	0UL
@@ -336,6 +329,15 @@ static inline void __ptep_set_access_flags(struct mm_struct *mm,
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val(pte) >> 3 })
 #define __swp_entry_to_pte(x)		((pte_t) { (x).val << 3 })
 
+#ifndef CONFIG_PPC_4K_PAGES
+void pgtable_cache_init(void);
+#else
+/*
+ * No page table caches to initialise
+ */
+#define pgtable_cache_init()	do { } while (0)
+#endif
+
 extern int get_pteptr(struct mm_struct *mm, unsigned long addr, pte_t **ptep,
 		      pmd_t **pmdp);
 
diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h
index ac96526..ea1c012 100644
--- a/arch/powerpc/include/asm/nohash/64/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
@@ -359,6 +359,8 @@ static inline void __ptep_set_access_flags(struct mm_struct *mm,
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val((pte)) })
 #define __swp_entry_to_pte(x)		__pte((x).val)
 
+void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
+void pgtable_cache_init(void);
 extern int map_kernel_page(unsigned long ea, unsigned long pa,
 			   unsigned long flags);
 extern int __meminit vmemmap_create_mapping(unsigned long start,
diff --git a/arch/powerpc/include/asm/pgtable.h b/arch/powerpc/include/asm/pgtable.h
index dd01212..9bd87f2 100644
--- a/arch/powerpc/include/asm/pgtable.h
+++ b/arch/powerpc/include/asm/pgtable.h
@@ -78,8 +78,6 @@ static inline pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea,
 
 unsigned long vmalloc_to_phys(void *vmalloc_addr);
 
-void pgtable_cache_add(unsigned shift, void (*ctor)(void *));
-void pgtable_cache_init(void);
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_PGTABLE_H */
diff --git a/arch/powerpc/mm/Makefile b/arch/powerpc/mm/Makefile
index 6f7961d..f2cea6d 100644
--- a/arch/powerpc/mm/Makefile
+++ b/arch/powerpc/mm/Makefile
@@ -8,8 +8,7 @@ ccflags-$(CONFIG_PPC64)	:= $(NO_MINIMAL_TOC)
 
 obj-y				:= fault.o mem.o pgtable.o mmap.o \
 				   init_$(CONFIG_WORD_SIZE).o \
-				   pgtable_$(CONFIG_WORD_SIZE).o \
-				   init-common.o
+				   pgtable_$(CONFIG_WORD_SIZE).o
 obj-$(CONFIG_PPC_MMU_NOHASH)	+= mmu_context_nohash.o tlb_nohash.o \
 				   tlb_nohash_low.o
 obj-$(CONFIG_PPC_BOOK3E)	+= tlb_low_$(CONFIG_WORD_SIZE)e.o
diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c
deleted file mode 100644
index a175cd8..0000000
--- a/arch/powerpc/mm/init-common.c
+++ /dev/null
@@ -1,107 +0,0 @@
-/*
- *  PowerPC version
- *    Copyright (C) 1995-1996 Gary Thomas (gdt at linuxppc.org)
- *
- *  Modifications by Paul Mackerras (PowerMac) (paulus at cs.anu.edu.au)
- *  and Cort Dougan (PReP) (cort at cs.nmt.edu)
- *    Copyright (C) 1996 Paul Mackerras
- *
- *  Derived from "arch/i386/mm/init.c"
- *    Copyright (C) 1991, 1992, 1993, 1994  Linus Torvalds
- *
- *  Dave Engebretsen <engebret at us.ibm.com>
- *      Rework for PPC64 port.
- *
- *  This program is free software; you can redistribute it and/or
- *  modify it under the terms of the GNU General Public License
- *  as published by the Free Software Foundation; either version
- *  2 of the License, or (at your option) any later version.
- *
- */
-
-#undef DEBUG
-
-#include <linux/string.h>
-#include <asm/pgalloc.h>
-#include <asm/pgtable.h>
-
-static void pgd_ctor(void *addr)
-{
-	memset(addr, 0, PGD_TABLE_SIZE);
-}
-
-static void pud_ctor(void *addr)
-{
-	memset(addr, 0, PUD_TABLE_SIZE);
-}
-
-static void pmd_ctor(void *addr)
-{
-	memset(addr, 0, PMD_TABLE_SIZE);
-}
-
-struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE];
-
-/*
- * Create a kmem_cache() for pagetables.  This is not used for PTE
- * pages - they're linked to struct page, come from the normal free
- * pages pool and have a different entry size (see real_pte_t) to
- * everything else.  Caches created by this function are used for all
- * the higher level pagetables, and for hugepage pagetables.
- */
-void pgtable_cache_add(unsigned shift, void (*ctor)(void *))
-{
-	char *name;
-	unsigned long table_size = sizeof(void *) << shift;
-	unsigned long align = table_size;
-
-	/* When batching pgtable pointers for RCU freeing, we store
-	 * the index size in the low bits.  Table alignment must be
-	 * big enough to fit it.
-	 *
-	 * Likewise, hugeapge pagetable pointers contain a (different)
-	 * shift value in the low bits.  All tables must be aligned so
-	 * as to leave enough 0 bits in the address to contain it. */
-	unsigned long minalign = max(MAX_PGTABLE_INDEX_SIZE + 1,
-				     HUGEPD_SHIFT_MASK + 1);
-	struct kmem_cache *new;
-
-	/* It would be nice if this was a BUILD_BUG_ON(), but at the
-	 * moment, gcc doesn't seem to recognize is_power_of_2 as a
-	 * constant expression, so so much for that. */
-	BUG_ON(!is_power_of_2(minalign));
-	BUG_ON((shift < 1) || (shift > MAX_PGTABLE_INDEX_SIZE));
-
-	if (PGT_CACHE(shift))
-		return; /* Already have a cache of this size */
-
-	align = max_t(unsigned long, align, minalign);
-	name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift);
-	new = kmem_cache_create(name, table_size, align, 0, ctor);
-	kfree(name);
-	pgtable_cache[shift - 1] = new;
-	pr_debug("Allocated pgtable cache for order %d\n", shift);
-}
-
-
-void pgtable_cache_init(void)
-{
-	pgtable_cache_add(PGD_INDEX_SIZE, pgd_ctor);
-
-	if (PMD_INDEX_SIZE && !PGT_CACHE(PMD_INDEX_SIZE))
-		pgtable_cache_add(PMD_CACHE_INDEX, pmd_ctor);
-	/*
-	 * In all current configs, when the PUD index exists it's the
-	 * same size as either the pgd or pmd index except with THP enabled
-	 * on book3s 64
-	 */
-	if (PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE))
-		pgtable_cache_add(PUD_INDEX_SIZE, pud_ctor);
-
-	if (!PGT_CACHE(PGD_INDEX_SIZE))
-		panic("Couldn't allocate pgd cache");
-	if (PMD_INDEX_SIZE && !PGT_CACHE(PMD_INDEX_SIZE))
-		panic("Couldn't allocate pmd pgtable caches");
-	if (PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE))
-		panic("Couldn't allocate pud pgtable caches");
-}
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index b639792..4d5ce3e 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -82,6 +82,83 @@ EXPORT_SYMBOL_GPL(memstart_addr);
 phys_addr_t kernstart_addr;
 EXPORT_SYMBOL_GPL(kernstart_addr);
 
+static void pgd_ctor(void *addr)
+{
+	memset(addr, 0, PGD_TABLE_SIZE);
+}
+
+static void pud_ctor(void *addr)
+{
+	memset(addr, 0, PUD_TABLE_SIZE);
+}
+
+static void pmd_ctor(void *addr)
+{
+	memset(addr, 0, PMD_TABLE_SIZE);
+}
+
+struct kmem_cache *pgtable_cache[MAX_PGTABLE_INDEX_SIZE];
+
+/*
+ * Create a kmem_cache() for pagetables.  This is not used for PTE
+ * pages - they're linked to struct page, come from the normal free
+ * pages pool and have a different entry size (see real_pte_t) to
+ * everything else.  Caches created by this function are used for all
+ * the higher level pagetables, and for hugepage pagetables.
+ */
+void pgtable_cache_add(unsigned shift, void (*ctor)(void *))
+{
+	char *name;
+	unsigned long table_size = sizeof(void *) << shift;
+	unsigned long align = table_size;
+
+	/* When batching pgtable pointers for RCU freeing, we store
+	 * the index size in the low bits.  Table alignment must be
+	 * big enough to fit it.
+	 *
+	 * Likewise, hugeapge pagetable pointers contain a (different)
+	 * shift value in the low bits.  All tables must be aligned so
+	 * as to leave enough 0 bits in the address to contain it. */
+	unsigned long minalign = max(MAX_PGTABLE_INDEX_SIZE + 1,
+				     HUGEPD_SHIFT_MASK + 1);
+	struct kmem_cache *new;
+
+	/* It would be nice if this was a BUILD_BUG_ON(), but at the
+	 * moment, gcc doesn't seem to recognize is_power_of_2 as a
+	 * constant expression, so so much for that. */
+	BUG_ON(!is_power_of_2(minalign));
+	BUG_ON((shift < 1) || (shift > MAX_PGTABLE_INDEX_SIZE));
+
+	if (PGT_CACHE(shift))
+		return; /* Already have a cache of this size */
+
+	align = max_t(unsigned long, align, minalign);
+	name = kasprintf(GFP_KERNEL, "pgtable-2^%d", shift);
+	new = kmem_cache_create(name, table_size, align, 0, ctor);
+	kfree(name);
+	pgtable_cache[shift - 1] = new;
+	pr_debug("Allocated pgtable cache for order %d\n", shift);
+}
+
+
+void pgtable_cache_init(void)
+{
+	pgtable_cache_add(PGD_INDEX_SIZE, pgd_ctor);
+	pgtable_cache_add(PMD_CACHE_INDEX, pmd_ctor);
+	/*
+	 * In all current configs, when the PUD index exists it's the
+	 * same size as either the pgd or pmd index except with THP enabled
+	 * on book3s 64
+	 */
+	if (PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE))
+		pgtable_cache_add(PUD_INDEX_SIZE, pud_ctor);
+
+	if (!PGT_CACHE(PGD_INDEX_SIZE) || !PGT_CACHE(PMD_CACHE_INDEX))
+		panic("Couldn't allocate pgtable caches");
+	if (PUD_INDEX_SIZE && !PGT_CACHE(PUD_INDEX_SIZE))
+		panic("Couldn't allocate pud pgtable caches");
+}
+
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 /*
  * Given an address within the vmemmap, determine the pfn of the page that
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index a65c0b4..0ae0572 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -42,6 +42,43 @@ EXPORT_SYMBOL(ioremap_bot);	/* aka VMALLOC_END */
 
 extern char etext[], _stext[], _sinittext[], _einittext[];
 
+#define PGDIR_ORDER	(32 + PGD_T_LOG2 - PGDIR_SHIFT)
+
+#ifndef CONFIG_PPC_4K_PAGES
+static struct kmem_cache *pgtable_cache;
+
+void pgtable_cache_init(void)
+{
+	pgtable_cache = kmem_cache_create("PGDIR cache", 1 << PGDIR_ORDER,
+					  1 << PGDIR_ORDER, 0, NULL);
+	if (pgtable_cache == NULL)
+		panic("Couldn't allocate pgtable caches");
+}
+#endif
+
+pgd_t *pgd_alloc(struct mm_struct *mm)
+{
+	pgd_t *ret;
+
+	/* pgdir take page or two with 4K pages and a page fraction otherwise */
+#ifndef CONFIG_PPC_4K_PAGES
+	ret = kmem_cache_alloc(pgtable_cache, GFP_KERNEL | __GFP_ZERO);
+#else
+	ret = (pgd_t *)__get_free_pages(GFP_KERNEL|__GFP_ZERO,
+			PGDIR_ORDER - PAGE_SHIFT);
+#endif
+	return ret;
+}
+
+void pgd_free(struct mm_struct *mm, pgd_t *pgd)
+{
+#ifndef CONFIG_PPC_4K_PAGES
+	kmem_cache_free(pgtable_cache, (void *)pgd);
+#else
+	free_pages((unsigned long)pgd, PGDIR_ORDER - PAGE_SHIFT);
+#endif
+}
+
 __ref pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
 {
 	pte_t *pte;
-- 
2.7.4





More information about the kernel-team mailing list