2f569afd9c
Background: I've implemented 1K/2K page tables for s390. These sub-page page tables are required to properly support the s390 virtualization instruction with KVM. The SIE instruction requires that the page tables have 256 page table entries (pte) followed by 256 page status table entries (pgste). The pgstes are only required if the process is using the SIE instruction. The pgstes are updated by the hardware and by the hypervisor for a number of reasons, one of them is dirty and reference bit tracking. To avoid wasting memory the standard pte table allocation should return 1K/2K (31/64 bit) and 2K/4K if the process is using SIE. Problem: Page size on s390 is 4K, page table size is 1K or 2K. That means the s390 version for pte_alloc_one cannot return a pointer to a struct page. Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one cannot return a pointer to a pte either, since that would require more than 32 bit for the return value of pte_alloc_one (and the pte * would not be accessible since its not kmapped). Solution: The only solution I found to this dilemma is a new typedef: a pgtable_t. For s390 pgtable_t will be a (pte *) - to be introduced with a later patch. For everybody else it will be a (struct page *). The additional problem with the initialization of the ptl lock and the NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and a destructor pgtable_page_dtor. The page table allocation and free functions need to call these two whenever a page table page is allocated or freed. pmd_populate will get a pgtable_t instead of a struct page pointer. To get the pgtable_t back from a pmd entry that has been installed with pmd_populate a new function pmd_pgtable is added. It replaces the pmd_page call in free_pte_range and apply_to_pte_range. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
166 lines
4.2 KiB
C
166 lines
4.2 KiB
C
#ifndef _ASM_POWERPC_PGALLOC_64_H
|
|
#define _ASM_POWERPC_PGALLOC_64_H
|
|
/*
|
|
* 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.
|
|
*/
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/cpumask.h>
|
|
#include <linux/percpu.h>
|
|
|
|
#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 3 /* from GFP rather than kmem_cache */
|
|
|
|
static inline pgd_t *pgd_alloc(struct mm_struct *mm)
|
|
{
|
|
return kmem_cache_alloc(pgtable_cache[PGD_CACHE_NUM], 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);
|
|
}
|
|
|
|
#ifndef CONFIG_PPC_64K_PAGES
|
|
|
|
#define pgd_populate(MM, PGD, PUD) pgd_set(PGD, PUD)
|
|
|
|
static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr)
|
|
{
|
|
return kmem_cache_alloc(pgtable_cache[PUD_CACHE_NUM],
|
|
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);
|
|
}
|
|
|
|
static inline void pud_populate(struct mm_struct *mm, pud_t *pud, pmd_t *pmd)
|
|
{
|
|
pud_set(pud, (unsigned long)pmd);
|
|
}
|
|
|
|
#define pmd_populate(mm, pmd, pte_page) \
|
|
pmd_populate_kernel(mm, pmd, page_address(pte_page))
|
|
#define pmd_populate_kernel(mm, pmd, pte) pmd_set(pmd, (unsigned long)(pte))
|
|
#define pmd_pgtable(pmd) pmd_page(pmd)
|
|
|
|
|
|
#else /* CONFIG_PPC_64K_PAGES */
|
|
|
|
#define pud_populate(mm, pud, pmd) pud_set(pud, (unsigned long)pmd)
|
|
|
|
static inline void pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd,
|
|
pte_t *pte)
|
|
{
|
|
pmd_set(pmd, (unsigned long)pte);
|
|
}
|
|
|
|
#define pmd_populate(mm, pmd, pte_page) \
|
|
pmd_populate_kernel(mm, pmd, page_address(pte_page))
|
|
#define pmd_pgtable(pmd) pmd_page(pmd)
|
|
|
|
#endif /* CONFIG_PPC_64K_PAGES */
|
|
|
|
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
|
|
{
|
|
return kmem_cache_alloc(pgtable_cache[PMD_CACHE_NUM],
|
|
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);
|
|
}
|
|
|
|
static inline pte_t *pte_alloc_one_kernel(struct mm_struct *mm,
|
|
unsigned long address)
|
|
{
|
|
return (pte_t *)__get_free_page(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO);
|
|
}
|
|
|
|
static inline pgtable_t pte_alloc_one(struct mm_struct *mm,
|
|
unsigned long address)
|
|
{
|
|
struct page *page;
|
|
pte_t *pte;
|
|
|
|
pte = pte_alloc_one_kernel(mm, address);
|
|
if (!pte)
|
|
return NULL;
|
|
page = virt_to_page(pte);
|
|
pgtable_page_ctor(page);
|
|
return page;
|
|
}
|
|
|
|
static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
|
|
{
|
|
free_page((unsigned long)pte);
|
|
}
|
|
|
|
static inline void pte_free(struct mm_struct *mm, pgtable_t ptepage)
|
|
{
|
|
pgtable_page_dtor(ptepage);
|
|
__free_page(ptepage);
|
|
}
|
|
|
|
#define PGF_CACHENUM_MASK 0x3
|
|
|
|
typedef struct pgtable_free {
|
|
unsigned long val;
|
|
} pgtable_free_t;
|
|
|
|
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};
|
|
}
|
|
|
|
static inline void pgtable_free(pgtable_free_t pgf)
|
|
{
|
|
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);
|
|
}
|
|
|
|
extern void pgtable_free_tlb(struct mmu_gather *tlb, pgtable_free_t pgf);
|
|
|
|
#define __pte_free_tlb(tlb,ptepage) \
|
|
do { \
|
|
pgtable_page_dtor(ptepage); \
|
|
pgtable_free_tlb(tlb, pgtable_free_cache(page_address(ptepage), \
|
|
PTE_NONCACHE_NUM, PTE_TABLE_SIZE-1)); \
|
|
} while (0)
|
|
#define __pmd_free_tlb(tlb, pmd) \
|
|
pgtable_free_tlb(tlb, pgtable_free_cache(pmd, \
|
|
PMD_CACHE_NUM, PMD_TABLE_SIZE-1))
|
|
#ifndef CONFIG_PPC_64K_PAGES
|
|
#define __pud_free_tlb(tlb, pud) \
|
|
pgtable_free_tlb(tlb, pgtable_free_cache(pud, \
|
|
PUD_CACHE_NUM, PUD_TABLE_SIZE-1))
|
|
#endif /* CONFIG_PPC_64K_PAGES */
|
|
|
|
#define check_pgt_cache() do { } while (0)
|
|
|
|
#endif /* _ASM_POWERPC_PGALLOC_64_H */
|