mirror of
https://github.com/torvalds/linux.git
synced 2024-12-27 13:22:23 +00:00
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>
160 lines
4.0 KiB
C
160 lines
4.0 KiB
C
/* pgalloc.c: page directory & page table allocation
|
|
*
|
|
* Copyright (C) 2004 Red Hat, Inc. All Rights Reserved.
|
|
* Written by David Howells (dhowells@redhat.com)
|
|
*
|
|
* 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/sched.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/quicklist.h>
|
|
#include <asm/pgalloc.h>
|
|
#include <asm/page.h>
|
|
#include <asm/cacheflush.h>
|
|
|
|
pgd_t swapper_pg_dir[PTRS_PER_PGD] __attribute__((aligned(PAGE_SIZE)));
|
|
|
|
pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address)
|
|
{
|
|
pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
|
|
if (pte)
|
|
clear_page(pte);
|
|
return pte;
|
|
}
|
|
|
|
pgtable_t pte_alloc_one(struct mm_struct *mm, unsigned long address)
|
|
{
|
|
struct page *page;
|
|
|
|
#ifdef CONFIG_HIGHPTE
|
|
page = alloc_pages(GFP_KERNEL|__GFP_HIGHMEM|__GFP_REPEAT, 0);
|
|
#else
|
|
page = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
|
|
#endif
|
|
if (page) {
|
|
clear_highpage(page);
|
|
pgtable_page_ctor(page);
|
|
flush_dcache_page(page);
|
|
}
|
|
return page;
|
|
}
|
|
|
|
void __set_pmd(pmd_t *pmdptr, unsigned long pmd)
|
|
{
|
|
unsigned long *__ste_p = pmdptr->ste;
|
|
int loop;
|
|
|
|
if (!pmd) {
|
|
memset(__ste_p, 0, PME_SIZE);
|
|
}
|
|
else {
|
|
BUG_ON(pmd & (0x3f00 | xAMPRx_SS | 0xe));
|
|
|
|
for (loop = PME_SIZE; loop > 0; loop -= 4) {
|
|
*__ste_p++ = pmd;
|
|
pmd += __frv_PT_SIZE;
|
|
}
|
|
}
|
|
|
|
frv_dcache_writeback((unsigned long) pmdptr, (unsigned long) (pmdptr + 1));
|
|
}
|
|
|
|
/*
|
|
* List of all pgd's needed for non-PAE so it can invalidate entries
|
|
* in both cached and uncached pgd's; not needed for PAE since the
|
|
* kernel pmd is shared. If PAE were not to share the pmd a similar
|
|
* tactic would be needed. This is essentially codepath-based locking
|
|
* against pageattr.c; it is the unique case in which a valid change
|
|
* of kernel pagetables can't be lazily synchronized by vmalloc faults.
|
|
* vmalloc faults work because attached pagetables are never freed.
|
|
* If the locking proves to be non-performant, a ticketing scheme with
|
|
* checks at dup_mmap(), exec(), and other mmlist addition points
|
|
* could be used. The locking scheme was chosen on the basis of
|
|
* manfred's recommendations and having no core impact whatsoever.
|
|
* -- wli
|
|
*/
|
|
DEFINE_SPINLOCK(pgd_lock);
|
|
struct page *pgd_list;
|
|
|
|
static inline void pgd_list_add(pgd_t *pgd)
|
|
{
|
|
struct page *page = virt_to_page(pgd);
|
|
page->index = (unsigned long) pgd_list;
|
|
if (pgd_list)
|
|
set_page_private(pgd_list, (unsigned long) &page->index);
|
|
pgd_list = page;
|
|
set_page_private(page, (unsigned long)&pgd_list);
|
|
}
|
|
|
|
static inline void pgd_list_del(pgd_t *pgd)
|
|
{
|
|
struct page *next, **pprev, *page = virt_to_page(pgd);
|
|
next = (struct page *) page->index;
|
|
pprev = (struct page **) page_private(page);
|
|
*pprev = next;
|
|
if (next)
|
|
set_page_private(next, (unsigned long) pprev);
|
|
}
|
|
|
|
void pgd_ctor(void *pgd)
|
|
{
|
|
unsigned long flags;
|
|
|
|
if (PTRS_PER_PMD == 1)
|
|
spin_lock_irqsave(&pgd_lock, flags);
|
|
|
|
memcpy((pgd_t *) pgd + USER_PGDS_IN_LAST_PML4,
|
|
swapper_pg_dir + USER_PGDS_IN_LAST_PML4,
|
|
(PTRS_PER_PGD - USER_PGDS_IN_LAST_PML4) * sizeof(pgd_t));
|
|
|
|
if (PTRS_PER_PMD > 1)
|
|
return;
|
|
|
|
pgd_list_add(pgd);
|
|
spin_unlock_irqrestore(&pgd_lock, flags);
|
|
memset(pgd, 0, USER_PGDS_IN_LAST_PML4 * sizeof(pgd_t));
|
|
}
|
|
|
|
/* never called when PTRS_PER_PMD > 1 */
|
|
void pgd_dtor(void *pgd)
|
|
{
|
|
unsigned long flags; /* can be called from interrupt context */
|
|
|
|
spin_lock_irqsave(&pgd_lock, flags);
|
|
pgd_list_del(pgd);
|
|
spin_unlock_irqrestore(&pgd_lock, flags);
|
|
}
|
|
|
|
pgd_t *pgd_alloc(struct mm_struct *mm)
|
|
{
|
|
pgd_t *pgd;
|
|
|
|
pgd = quicklist_alloc(0, GFP_KERNEL, pgd_ctor);
|
|
if (!pgd)
|
|
return pgd;
|
|
|
|
return pgd;
|
|
}
|
|
|
|
void pgd_free(struct mm_struct *mm, pgd_t *pgd)
|
|
{
|
|
/* in the non-PAE case, clear_page_tables() clears user pgd entries */
|
|
quicklist_free(0, pgd_dtor, pgd);
|
|
}
|
|
|
|
void __init pgtable_cache_init(void)
|
|
{
|
|
}
|
|
|
|
void check_pgt_cache(void)
|
|
{
|
|
quicklist_trim(0, pgd_dtor, 25, 16);
|
|
}
|
|
|