Re: [PATCH 1/6] powerpc: port 64 bits pgtable_cache to 32 bits

From: Aneesh Kumar K.V
Date: Sun Aug 14 2016 - 10:17:56 EST


Christophe Leroy <christophe.leroy@xxxxxx> writes:

> Today powerpc64 uses a set of pgtable_caches while powerpc32 uses
> standard pages when using 4k pages and a single pgtable_cache
> if using other size pages. In addition powerpc32 uses another cache
> when handling huge pages.
>
> In preparation of implementing huge pages on the 8xx, this patch
> replaces the specific powerpc32 handling by the 64 bits approach.

Why is this needed ? Can you also summarize the page size used and the
hugepage format you are planning to use ? . What are the page sizes
supported by 8xx ? Also is the new code copy of existing powerpc64 4k
page size code ?

>
> Signed-off-by: Christophe Leroy <christophe.leroy@xxxxxx>
> ---
> arch/powerpc/include/asm/book3s/32/pgalloc.h | 44 ++++++--
> arch/powerpc/include/asm/book3s/32/pgtable.h | 43 ++++----
> arch/powerpc/include/asm/book3s/64/pgtable.h | 3 -
> arch/powerpc/include/asm/hugetlb.h | 2 -
> arch/powerpc/include/asm/nohash/32/pgalloc.h | 44 ++++++--
> arch/powerpc/include/asm/nohash/32/pgtable.h | 45 ++++----
> arch/powerpc/include/asm/nohash/64/pgtable.h | 2 -
> arch/powerpc/include/asm/pgtable.h | 2 +
> arch/powerpc/mm/Makefile | 2 +-
> arch/powerpc/mm/hugetlbpage.c | 12 +--
> arch/powerpc/mm/init-common.c | 152 +++++++++++++++++++++++++++
> arch/powerpc/mm/init_32.c | 5 -
> arch/powerpc/mm/init_64.c | 82 ---------------
> arch/powerpc/mm/pgtable_32.c | 37 -------
> 14 files changed, 282 insertions(+), 193 deletions(-)
> create 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 8e21bb4..ab215fd 100644
> --- a/arch/powerpc/include/asm/book3s/32/pgalloc.h
> +++ b/arch/powerpc/include/asm/book3s/32/pgalloc.h
> @@ -2,14 +2,42 @@
> #define _ASM_POWERPC_BOOK3S_32_PGALLOC_H
>
> #include <linux/threads.h>
> +#include <linux/slab.h>
>
> -/* For 32-bit, all levels of page tables are just drawn from get_free_page() */
> -#define MAX_PGTABLE_INDEX_SIZE 0
> +/*
> + * 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
>
> extern void __bad_pte(pmd_t *pmd);
>
> -extern pgd_t *pgd_alloc(struct mm_struct *mm);
> -extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
> +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);
> +}
>
> /*
> * We don't have any real pmd's, and this code never triggers because
> @@ -68,8 +96,12 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
>
> static inline void pgtable_free(void *table, unsigned index_size)
> {
> - BUG_ON(index_size); /* 32-bit doesn't use this */
> - free_page((unsigned long)table);
> + 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 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 38b33dc..83a2159 100644
> --- a/arch/powerpc/include/asm/book3s/32/pgtable.h
> +++ b/arch/powerpc/include/asm/book3s/32/pgtable.h
> @@ -8,6 +8,26 @@
> /* 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 (sizeof(pmd_t) << PTE_INDEX_SIZE)
> +#define PUD_TABLE_SIZE (sizeof(pud_t) << PTE_INDEX_SIZE)
> +#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)
> +
> +/* With 4k base page size, hugepage PTEs go at the PMD level */
> +#define MIN_HUGEPTE_SHIFT PMD_SHIFT
> +
> /*
> * 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
> @@ -19,14 +39,10 @@
> * -Matt
> */
> /* PGDIR_SHIFT determines what a top-level page table entry can map */
> -#define PGDIR_SHIFT (PAGE_SHIFT + PTE_SHIFT)
> +#define PGDIR_SHIFT (PAGE_SHIFT + PTE_INDEX_SIZE)
> #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
> @@ -82,12 +98,8 @@
>
> extern unsigned long ioremap_bot;
>
> -/*
> - * 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))
> +/* Bits to mask out from a PGD to get to the PUD page */
> +#define PGD_MASKED_BITS 0
>
> #define pte_ERROR(e) \
> pr_err("%s:%d: bad pte %llx.\n", __FILE__, __LINE__, \
> @@ -282,15 +294,6 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
> #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 263bf39..3f85d43 100644
> --- a/arch/powerpc/include/asm/book3s/64/pgtable.h
> +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
> @@ -786,9 +786,6 @@ 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/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
> index c5517f4..c201cd6 100644
> --- a/arch/powerpc/include/asm/hugetlb.h
> +++ b/arch/powerpc/include/asm/hugetlb.h
> @@ -5,8 +5,6 @@
> #include <asm/page.h>
> #include <asm-generic/hugetlb.h>
>
> -extern struct kmem_cache *hugepte_cache;
> -
> #ifdef CONFIG_PPC_BOOK3S_64
>
> #include <asm/book3s/64/hugetlb-radix.h>
> diff --git a/arch/powerpc/include/asm/nohash/32/pgalloc.h b/arch/powerpc/include/asm/nohash/32/pgalloc.h
> index 76d6b9e..c2fe85c 100644
> --- a/arch/powerpc/include/asm/nohash/32/pgalloc.h
> +++ b/arch/powerpc/include/asm/nohash/32/pgalloc.h
> @@ -2,14 +2,42 @@
> #define _ASM_POWERPC_PGALLOC_32_H
>
> #include <linux/threads.h>
> +#include <linux/slab.h>
>
> -/* For 32-bit, all levels of page tables are just drawn from get_free_page() */
> -#define MAX_PGTABLE_INDEX_SIZE 0
> +/*
> + * 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
>
> extern void __bad_pte(pmd_t *pmd);
>
> -extern pgd_t *pgd_alloc(struct mm_struct *mm);
> -extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
> +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);
> +}
>
> /*
> * We don't have any real pmd's, and this code never triggers because
> @@ -68,8 +96,12 @@ static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
>
> static inline void pgtable_free(void *table, unsigned index_size)
> {
> - BUG_ON(index_size); /* 32-bit doesn't use this */
> - free_page((unsigned long)table);
> + 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 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 7808475..8a2937d 100644
> --- a/arch/powerpc/include/asm/nohash/32/pgtable.h
> +++ b/arch/powerpc/include/asm/nohash/32/pgtable.h
> @@ -16,6 +16,26 @@ 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 (sizeof(pmd_t) << PTE_INDEX_SIZE)
> +#define PUD_TABLE_SIZE (sizeof(pud_t) << PTE_INDEX_SIZE)
> +#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)
> +
> +/* With 4k base page size, hugepage PTEs go at the PMD level */
> +#define MIN_HUGEPTE_SHIFT PMD_SHIFT
> +
> /*
> * 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
> @@ -27,22 +47,12 @@ 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_SHIFT)
> +#define PGDIR_SHIFT (PAGE_SHIFT + PTE_INDEX_SIZE)
> #define PGDIR_SIZE (1UL << PGDIR_SHIFT)
> #define PGDIR_MASK (~(PGDIR_SIZE-1))
>
> -/*
> - * 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))
> +/* Bits to mask out from a PGD to get to the PUD page */
> +#define PGD_MASKED_BITS 0
>
> #define USER_PTRS_PER_PGD (TASK_SIZE / PGDIR_SIZE)
> #define FIRST_USER_ADDRESS 0UL
> @@ -327,15 +337,6 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
> #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 d4d808c..b0fc9e4 100644
> --- a/arch/powerpc/include/asm/nohash/64/pgtable.h
> +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h
> @@ -357,8 +357,6 @@ static inline void __ptep_set_access_flags(pte_t *ptep, pte_t entry)
> #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 9bd87f2..dd01212 100644
> --- a/arch/powerpc/include/asm/pgtable.h
> +++ b/arch/powerpc/include/asm/pgtable.h
> @@ -78,6 +78,8 @@ 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 f2cea6d..08bb010 100644
> --- a/arch/powerpc/mm/Makefile
> +++ b/arch/powerpc/mm/Makefile
> @@ -7,7 +7,7 @@ subdir-ccflags-$(CONFIG_PPC_WERROR) := -Werror
> ccflags-$(CONFIG_PPC64) := $(NO_MINIMAL_TOC)
>
> obj-y := fault.o mem.o pgtable.o mmap.o \
> - init_$(CONFIG_WORD_SIZE).o \
> + init_$(CONFIG_WORD_SIZE).o init-common.o \
> pgtable_$(CONFIG_WORD_SIZE).o
> obj-$(CONFIG_PPC_MMU_NOHASH) += mmu_context_nohash.o tlb_nohash.o \
> tlb_nohash_low.o
> diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
> index 7372ee1..9164a77 100644
> --- a/arch/powerpc/mm/hugetlbpage.c
> +++ b/arch/powerpc/mm/hugetlbpage.c
> @@ -68,7 +68,7 @@ static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
> #ifdef CONFIG_PPC_FSL_BOOK3E
> int i;
> int num_hugepd = 1 << (pshift - pdshift);
> - cachep = hugepte_cache;
> + cachep = PGT_CACHE(1);
> #else
> cachep = PGT_CACHE(pdshift - pshift);
> #endif

Can you explain the usage of PGT_CACHE(1) ?

> @@ -411,7 +411,7 @@ static void hugepd_free_rcu_callback(struct rcu_head *head)
> unsigned int i;
>
> for (i = 0; i < batch->index; i++)
> - kmem_cache_free(hugepte_cache, batch->ptes[i]);
> + kmem_cache_free(PGT_CACHE(1), batch->ptes[i]);
>
> free_page((unsigned long)batch);
> }
> @@ -425,7 +425,7 @@ static void hugepd_free(struct mmu_gather *tlb, void *hugepte)
> if (atomic_read(&tlb->mm->mm_users) < 2 ||
> cpumask_equal(mm_cpumask(tlb->mm),
> cpumask_of(smp_processor_id()))) {
> - kmem_cache_free(hugepte_cache, hugepte);
> + kmem_cache_free(PGT_CACHE(1), hugepte);
> put_cpu_var(hugepd_freelist_cur);
> return;
> }
> @@ -792,7 +792,6 @@ static int __init hugepage_setup_sz(char *str)
> __setup("hugepagesz=", hugepage_setup_sz);
>
> #ifdef CONFIG_PPC_FSL_BOOK3E
> -struct kmem_cache *hugepte_cache;
> static int __init hugetlbpage_init(void)
> {
> int psize;
> @@ -815,9 +814,8 @@ static int __init hugetlbpage_init(void)
> * Create a kmem cache for hugeptes. The bottom bits in the pte have
> * size information encoded in them, so align them to allow this
> */
> - hugepte_cache = kmem_cache_create("hugepte-cache", sizeof(pte_t),
> - HUGEPD_SHIFT_MASK + 1, 0, NULL);
> - if (hugepte_cache == NULL)
> + pgtable_cache_add(1, NULL);
> + if (!PGT_CACHE(1))
> panic("%s: Unable to create kmem cache for hugeptes\n",
> __func__);
>
> diff --git a/arch/powerpc/mm/init-common.c b/arch/powerpc/mm/init-common.c
> new file mode 100644
> index 0000000..2632eab
> --- /dev/null
> +++ b/arch/powerpc/mm/init-common.c
> @@ -0,0 +1,152 @@
> +/*
> + * PowerPC version
> + * Copyright (C) 1995-1996 Gary Thomas (gdt@xxxxxxxxxxxx)
> + *
> + * Modifications by Paul Mackerras (PowerMac) (paulus@xxxxxxxxxxxxx)
> + * and Cort Dougan (PReP) (cort@xxxxxxxxxx)
> + * Copyright (C) 1996 Paul Mackerras
> + *
> + * Derived from "arch/i386/mm/init.c"
> + * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
> + *
> + * Dave Engebretsen <engebret@xxxxxxxxxx>
> + * 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/signal.h>
> +#include <linux/sched.h>
> +#include <linux/kernel.h>
> +#include <linux/errno.h>
> +#include <linux/string.h>
> +#include <linux/types.h>
> +#include <linux/mman.h>
> +#include <linux/mm.h>
> +#include <linux/swap.h>
> +#include <linux/stddef.h>
> +#include <linux/vmalloc.h>
> +#include <linux/init.h>
> +#include <linux/delay.h>
> +#include <linux/highmem.h>
> +#include <linux/idr.h>
> +#include <linux/nodemask.h>
> +#include <linux/module.h>
> +#include <linux/poison.h>
> +#include <linux/memblock.h>
> +#include <linux/hugetlb.h>
> +#include <linux/slab.h>
> +
> +#include <asm/pgalloc.h>
> +#include <asm/page.h>
> +#include <asm/prom.h>
> +#include <asm/rtas.h>
> +#include <asm/io.h>
> +#include <asm/mmu_context.h>
> +#include <asm/pgtable.h>
> +#include <asm/mmu.h>
> +#include <asm/uaccess.h>
> +#include <asm/smp.h>
> +#include <asm/machdep.h>
> +#include <asm/tlb.h>
> +#include <asm/eeh.h>
> +#include <asm/processor.h>
> +#include <asm/mmzone.h>
> +#include <asm/cputable.h>
> +#include <asm/sections.h>
> +#include <asm/iommu.h>
> +#include <asm/vdso.h>
> +
> +#include "mmu_decl.h"
> +
> +phys_addr_t memstart_addr = (phys_addr_t)~0ull;
> +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);
> +
> + 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_32.c b/arch/powerpc/mm/init_32.c
> index 448685f..79c24d4 100644
> --- a/arch/powerpc/mm/init_32.c
> +++ b/arch/powerpc/mm/init_32.c
> @@ -59,11 +59,6 @@
> phys_addr_t total_memory;
> phys_addr_t total_lowmem;
>
> -phys_addr_t memstart_addr = (phys_addr_t)~0ull;
> -EXPORT_SYMBOL(memstart_addr);
> -phys_addr_t kernstart_addr;
> -EXPORT_SYMBOL(kernstart_addr);
> -
> #ifdef CONFIG_RELOCATABLE
> /* Used in __va()/__pa() */
> long long virt_phys_offset;
> diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
> index 16ada1e..4acd546 100644
> --- a/arch/powerpc/mm/init_64.c
> +++ b/arch/powerpc/mm/init_64.c
> @@ -75,88 +75,6 @@
> #endif
> #endif /* CONFIG_PPC_STD_MMU_64 */
>
> -phys_addr_t memstart_addr = ~0;
> -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 0ae0572..a65c0b4 100644
> --- a/arch/powerpc/mm/pgtable_32.c
> +++ b/arch/powerpc/mm/pgtable_32.c
> @@ -42,43 +42,6 @@ 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;
> --
> 2.1.0

I still didn't quiet follow why we are replacing

- hugepte_cache = kmem_cache_create("hugepte-cache", sizeof(pte_t),
- HUGEPD_SHIFT_MASK + 1, 0, NULL);
+ pgtable_cache_add(1, NULL);

-aneesh