kernel-ark/include/asm-s390/tlb.h
Martin Schwidefsky 2f569afd9c CONFIG_HIGHPTE vs. sub-page page tables.
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>
2008-02-08 09:22:42 -08:00

132 lines
3.6 KiB
C

#ifndef _S390_TLB_H
#define _S390_TLB_H
/*
* TLB flushing on s390 is complicated. The following requirement
* from the principles of operation is the most arduous:
*
* "A valid table entry must not be changed while it is attached
* to any CPU and may be used for translation by that CPU except to
* (1) invalidate the entry by using INVALIDATE PAGE TABLE ENTRY,
* or INVALIDATE DAT TABLE ENTRY, (2) alter bits 56-63 of a page
* table entry, or (3) make a change by means of a COMPARE AND SWAP
* AND PURGE instruction that purges the TLB."
*
* The modification of a pte of an active mm struct therefore is
* a two step process: i) invalidate the pte, ii) store the new pte.
* This is true for the page protection bit as well.
* The only possible optimization is to flush at the beginning of
* a tlb_gather_mmu cycle if the mm_struct is currently not in use.
*
* Pages used for the page tables is a different story. FIXME: more
*/
#include <linux/mm.h>
#include <linux/swap.h>
#include <asm/processor.h>
#include <asm/pgalloc.h>
#include <asm/smp.h>
#include <asm/tlbflush.h>
#ifndef CONFIG_SMP
#define TLB_NR_PTRS 1
#else
#define TLB_NR_PTRS 508
#endif
struct mmu_gather {
struct mm_struct *mm;
unsigned int fullmm;
unsigned int nr_ptes;
unsigned int nr_pmds;
void *array[TLB_NR_PTRS];
};
DECLARE_PER_CPU(struct mmu_gather, mmu_gathers);
static inline struct mmu_gather *tlb_gather_mmu(struct mm_struct *mm,
unsigned int full_mm_flush)
{
struct mmu_gather *tlb = &get_cpu_var(mmu_gathers);
tlb->mm = mm;
tlb->fullmm = full_mm_flush || (num_online_cpus() == 1) ||
(atomic_read(&mm->mm_users) <= 1 && mm == current->active_mm);
tlb->nr_ptes = 0;
tlb->nr_pmds = TLB_NR_PTRS;
if (tlb->fullmm)
__tlb_flush_mm(mm);
return tlb;
}
static inline void tlb_flush_mmu(struct mmu_gather *tlb,
unsigned long start, unsigned long end)
{
if (!tlb->fullmm && (tlb->nr_ptes > 0 || tlb->nr_pmds < TLB_NR_PTRS))
__tlb_flush_mm(tlb->mm);
while (tlb->nr_ptes > 0)
pte_free(tlb->mm, tlb->array[--tlb->nr_ptes]);
while (tlb->nr_pmds < TLB_NR_PTRS)
pmd_free(tlb->mm, (pmd_t *) tlb->array[tlb->nr_pmds++]);
}
static inline void tlb_finish_mmu(struct mmu_gather *tlb,
unsigned long start, unsigned long end)
{
tlb_flush_mmu(tlb, start, end);
/* keep the page table cache within bounds */
check_pgt_cache();
put_cpu_var(mmu_gathers);
}
/*
* Release the page cache reference for a pte removed by
* tlb_ptep_clear_flush. In both flush modes the tlb fo a page cache page
* has already been freed, so just do free_page_and_swap_cache.
*/
static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
{
free_page_and_swap_cache(page);
}
/*
* pte_free_tlb frees a pte table and clears the CRSTE for the
* page table from the tlb.
*/
static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t page)
{
if (!tlb->fullmm) {
tlb->array[tlb->nr_ptes++] = page;
if (tlb->nr_ptes >= tlb->nr_pmds)
tlb_flush_mmu(tlb, 0, 0);
} else
pte_free(tlb->mm, page);
}
/*
* pmd_free_tlb frees a pmd table and clears the CRSTE for the
* segment table entry from the tlb.
*/
static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
{
#ifdef __s390x__
if (!tlb->fullmm) {
tlb->array[--tlb->nr_pmds] = (struct page *) pmd;
if (tlb->nr_ptes >= tlb->nr_pmds)
tlb_flush_mmu(tlb, 0, 0);
} else
pmd_free(tlb->mm, pmd);
#endif
}
#define pud_free_tlb(tlb, pud) do { } while (0)
#define tlb_start_vma(tlb, vma) do { } while (0)
#define tlb_end_vma(tlb, vma) do { } while (0)
#define tlb_remove_tlb_entry(tlb, ptep, addr) do { } while (0)
#define tlb_migrate_finish(mm) do { } while (0)
#endif /* _S390_TLB_H */