mirror of
https://github.com/FEX-Emu/linux.git
synced 2024-12-25 19:07:46 +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>
150 lines
4.0 KiB
C
150 lines
4.0 KiB
C
#ifndef _ASM_PGALLOC_H
|
|
#define _ASM_PGALLOC_H
|
|
|
|
#include <linux/gfp.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/threads.h>
|
|
#include <asm/processor.h>
|
|
#include <asm/fixmap.h>
|
|
|
|
#include <asm/cache.h>
|
|
|
|
/* Allocate the top level pgd (page directory)
|
|
*
|
|
* Here (for 64 bit kernels) we implement a Hybrid L2/L3 scheme: we
|
|
* allocate the first pmd adjacent to the pgd. This means that we can
|
|
* subtract a constant offset to get to it. The pmd and pgd sizes are
|
|
* arranged so that a single pmd covers 4GB (giving a full 64-bit
|
|
* process access to 8TB) so our lookups are effectively L2 for the
|
|
* first 4GB of the kernel (i.e. for all ILP32 processes and all the
|
|
* kernel for machines with under 4GB of memory) */
|
|
static inline pgd_t *pgd_alloc(struct mm_struct *mm)
|
|
{
|
|
pgd_t *pgd = (pgd_t *)__get_free_pages(GFP_KERNEL,
|
|
PGD_ALLOC_ORDER);
|
|
pgd_t *actual_pgd = pgd;
|
|
|
|
if (likely(pgd != NULL)) {
|
|
memset(pgd, 0, PAGE_SIZE<<PGD_ALLOC_ORDER);
|
|
#ifdef CONFIG_64BIT
|
|
actual_pgd += PTRS_PER_PGD;
|
|
/* Populate first pmd with allocated memory. We mark it
|
|
* with PxD_FLAG_ATTACHED as a signal to the system that this
|
|
* pmd entry may not be cleared. */
|
|
__pgd_val_set(*actual_pgd, (PxD_FLAG_PRESENT |
|
|
PxD_FLAG_VALID |
|
|
PxD_FLAG_ATTACHED)
|
|
+ (__u32)(__pa((unsigned long)pgd) >> PxD_VALUE_SHIFT));
|
|
/* The first pmd entry also is marked with _PAGE_GATEWAY as
|
|
* a signal that this pmd may not be freed */
|
|
__pgd_val_set(*pgd, PxD_FLAG_ATTACHED);
|
|
#endif
|
|
}
|
|
return actual_pgd;
|
|
}
|
|
|
|
static inline void pgd_free(struct mm_struct *mm, pgd_t *pgd)
|
|
{
|
|
#ifdef CONFIG_64BIT
|
|
pgd -= PTRS_PER_PGD;
|
|
#endif
|
|
free_pages((unsigned long)pgd, PGD_ALLOC_ORDER);
|
|
}
|
|
|
|
#if PT_NLEVELS == 3
|
|
|
|
/* Three Level Page Table Support for pmd's */
|
|
|
|
static inline void pgd_populate(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmd)
|
|
{
|
|
__pgd_val_set(*pgd, (PxD_FLAG_PRESENT | PxD_FLAG_VALID) +
|
|
(__u32)(__pa((unsigned long)pmd) >> PxD_VALUE_SHIFT));
|
|
}
|
|
|
|
static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long address)
|
|
{
|
|
pmd_t *pmd = (pmd_t *)__get_free_pages(GFP_KERNEL|__GFP_REPEAT,
|
|
PMD_ORDER);
|
|
if (pmd)
|
|
memset(pmd, 0, PAGE_SIZE<<PMD_ORDER);
|
|
return pmd;
|
|
}
|
|
|
|
static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
|
|
{
|
|
#ifdef CONFIG_64BIT
|
|
if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
|
|
/* This is the permanent pmd attached to the pgd;
|
|
* cannot free it */
|
|
return;
|
|
#endif
|
|
free_pages((unsigned long)pmd, PMD_ORDER);
|
|
}
|
|
|
|
#else
|
|
|
|
/* Two Level Page Table Support for pmd's */
|
|
|
|
/*
|
|
* allocating and freeing a pmd is trivial: the 1-entry pmd is
|
|
* inside the pgd, so has no extra memory associated with it.
|
|
*/
|
|
|
|
#define pmd_alloc_one(mm, addr) ({ BUG(); ((pmd_t *)2); })
|
|
#define pmd_free(mm, x) do { } while (0)
|
|
#define pgd_populate(mm, pmd, pte) BUG()
|
|
|
|
#endif
|
|
|
|
static inline void
|
|
pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmd, pte_t *pte)
|
|
{
|
|
#ifdef CONFIG_64BIT
|
|
/* preserve the gateway marker if this is the beginning of
|
|
* the permanent pmd */
|
|
if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
|
|
__pmd_val_set(*pmd, (PxD_FLAG_PRESENT |
|
|
PxD_FLAG_VALID |
|
|
PxD_FLAG_ATTACHED)
|
|
+ (__u32)(__pa((unsigned long)pte) >> PxD_VALUE_SHIFT));
|
|
else
|
|
#endif
|
|
__pmd_val_set(*pmd, (PxD_FLAG_PRESENT | PxD_FLAG_VALID)
|
|
+ (__u32)(__pa((unsigned long)pte) >> PxD_VALUE_SHIFT));
|
|
}
|
|
|
|
#define pmd_populate(mm, pmd, pte_page) \
|
|
pmd_populate_kernel(mm, pmd, page_address(pte_page))
|
|
#define pmd_pgtable(pmd) pmd_page(pmd)
|
|
|
|
static inline pgtable_t
|
|
pte_alloc_one(struct mm_struct *mm, unsigned long address)
|
|
{
|
|
struct page *page = alloc_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
|
|
if (page)
|
|
pgtable_page_ctor(page);
|
|
return page;
|
|
}
|
|
|
|
static inline pte_t *
|
|
pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr)
|
|
{
|
|
pte_t *pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT|__GFP_ZERO);
|
|
return pte;
|
|
}
|
|
|
|
static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
|
|
{
|
|
free_page((unsigned long)pte);
|
|
}
|
|
|
|
static inline void pte_free_kernel(struct mm_struct *mm, struct page *pte)
|
|
{
|
|
pgtable_page_dtor(pte);
|
|
pte_free_kernel(page_address((pte));
|
|
}
|
|
|
|
#define check_pgt_cache() do { } while (0)
|
|
|
|
#endif
|