forked from luck/tmp_suning_uos_patched
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>
96 lines
2.6 KiB
C
96 lines
2.6 KiB
C
#ifndef _I386_PGALLOC_H
|
|
#define _I386_PGALLOC_H
|
|
|
|
#include <linux/threads.h>
|
|
#include <linux/mm.h> /* for struct page */
|
|
#include <linux/pagemap.h>
|
|
#include <asm/tlb.h>
|
|
#include <asm-generic/tlb.h>
|
|
|
|
#ifdef CONFIG_PARAVIRT
|
|
#include <asm/paravirt.h>
|
|
#else
|
|
#define paravirt_alloc_pt(mm, pfn) do { } while (0)
|
|
#define paravirt_alloc_pd(mm, pfn) do { } while (0)
|
|
#define paravirt_alloc_pd_clone(pfn, clonepfn, start, count) do { } while (0)
|
|
#define paravirt_release_pt(pfn) do { } while (0)
|
|
#define paravirt_release_pd(pfn) do { } while (0)
|
|
#endif
|
|
|
|
static inline void pmd_populate_kernel(struct mm_struct *mm,
|
|
pmd_t *pmd, pte_t *pte)
|
|
{
|
|
paravirt_alloc_pt(mm, __pa(pte) >> PAGE_SHIFT);
|
|
set_pmd(pmd, __pmd(__pa(pte) | _PAGE_TABLE));
|
|
}
|
|
|
|
static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd, struct page *pte)
|
|
{
|
|
unsigned long pfn = page_to_pfn(pte);
|
|
|
|
paravirt_alloc_pt(mm, pfn);
|
|
set_pmd(pmd, __pmd(((pteval_t)pfn << PAGE_SHIFT) | _PAGE_TABLE));
|
|
}
|
|
#define pmd_pgtable(pmd) pmd_page(pmd)
|
|
|
|
/*
|
|
* Allocate and free page tables.
|
|
*/
|
|
extern pgd_t *pgd_alloc(struct mm_struct *);
|
|
extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
|
|
|
|
extern pte_t *pte_alloc_one_kernel(struct mm_struct *, unsigned long);
|
|
extern pgtable_t pte_alloc_one(struct mm_struct *, unsigned long);
|
|
|
|
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 pte)
|
|
{
|
|
pgtable_page_dtor(pte);
|
|
__free_page(pte);
|
|
}
|
|
|
|
|
|
extern void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte);
|
|
|
|
#ifdef CONFIG_X86_PAE
|
|
/*
|
|
* In the PAE case we free the pmds as part of the pgd.
|
|
*/
|
|
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
|
|
{
|
|
return (pmd_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
|
|
}
|
|
|
|
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
|
|
{
|
|
BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
|
|
free_page((unsigned long)pmd);
|
|
}
|
|
|
|
extern void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd);
|
|
|
|
static inline void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
|
|
{
|
|
paravirt_alloc_pd(mm, __pa(pmd) >> PAGE_SHIFT);
|
|
|
|
/* Note: almost everything apart from _PAGE_PRESENT is
|
|
reserved at the pmd (PDPT) level. */
|
|
set_pud(pudp, __pud(__pa(pmd) | _PAGE_PRESENT));
|
|
|
|
/*
|
|
* According to Intel App note "TLBs, Paging-Structure Caches,
|
|
* and Their Invalidation", April 2007, document 317080-001,
|
|
* section 8.1: in PAE mode we explicitly have to flush the
|
|
* TLB via cr3 if the top-level pgd is changed...
|
|
*/
|
|
if (mm == current->active_mm)
|
|
write_cr3(read_cr3());
|
|
}
|
|
#endif /* CONFIG_X86_PAE */
|
|
|
|
#endif /* _I386_PGALLOC_H */
|