path: root/arch/powerpc/mm/hugetlbpage.c

/*
 * PPC64 (POWER4) Huge TLB Page Support for Kernel.
 *
 * Copyright (C) 2003 David Gibson, IBM Corporation.
 *
 * Based on the IA-32 version:
 * Copyright (C) 2002, Rohit Seth <rohit.seth@intel.com>
 */

#include <linux/init.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/err.h>
#include <linux/sysctl.h>
#include <asm/mman.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/mmu_context.h>
#include <asm/machdep.h>
#include <asm/cputable.h>
#include <asm/spu.h>

#define PAGE_SHIFT_64K	16
#define PAGE_SHIFT_16M	24
#define PAGE_SHIFT_16G	34

#define NUM_LOW_AREAS	(0x100000000UL >> SID_SHIFT)
#define NUM_HIGH_AREAS	(PGTABLE_RANGE >> HTLB_AREA_SHIFT)
#define MAX_NUMBER_GPAGES	1024

/* Tracks the 16G pages after the device tree is scanned and before the
 * huge_boot_pages list is ready.  */
static unsigned long gpage_freearray[MAX_NUMBER_GPAGES];
static unsigned nr_gpages;

/* Array of valid huge page sizes - non-zero value(hugepte_shift) is
 * stored for the huge page sizes that are valid.
 */
unsigned int mmu_huge_psizes[MMU_PAGE_COUNT] = { }; /* initialize all to 0 */

#define hugepte_shift			mmu_huge_psizes
#define PTRS_PER_HUGEPTE(psize)		(1 << hugepte_shift[psize])
#define HUGEPTE_TABLE_SIZE(psize)	(sizeof(pte_t) << hugepte_shift[psize])

#define HUGEPD_SHIFT(psize)		(mmu_psize_to_shift(psize) \
						+ hugepte_shift[psize])
#define HUGEPD_SIZE(psize)		(1UL << HUGEPD_SHIFT(psize))
#define HUGEPD_MASK(psize)		(~(HUGEPD_SIZE(psize)-1))

/* Subtract one from array size because we don't need a cache for 4K since
 * is not a huge page size */
#define huge_pgtable_cache(psize)	(pgtable_cache[HUGEPTE_CACHE_NUM \
							+ psize-1])
#define HUGEPTE_CACHE_NAME(psize)	(huge_pgtable_cache_name[psize])

static const char *huge_pgtable_cache_name[MMU_PAGE_COUNT] = {
	"unused_4K", "hugepte_cache_64K", "unused_64K_AP",
	"hugepte_cache_1M", "hugepte_cache_16M", "hugepte_cache_16G"
};

/* Flag to mark huge PD pointers.  This means pmd_bad() and pud_bad()
 * will choke on pointers to hugepte tables, which is handy for
 * catching screwups early. */
#define HUGEPD_OK	0x1

typedef struct { unsigned long pd; } hugepd_t;

#define hugepd_none(hpd)	((hpd).pd == 0)

static inline int shift_to_mmu_psize(unsigned int shift)
{
	switch (shift) {
#ifndef CONFIG_PPC_64K_PAGES
	case PAGE_SHIFT_64K:
	    return MMU_PAGE_64K;
#endif
	case PAGE_SHIFT_16M:
	    return MMU_PAGE_16M;
	case PAGE_SHIFT_16G:
	    return MMU_PAGE_16G;
	}
	return -1;
}

static inline unsigned int mmu_psize_to_shift(unsigned int mmu_psize)
{
	if (mmu_psize_defs[mmu_psize].shift)
		return mmu_psize_defs[mmu_psize].shift;
	BUG();
}

static inline pte_t *hugepd_page(hugepd_t hpd)
{
	BUG_ON(!(hpd.pd & HUGEPD_OK));
	return (pte_t *)(hpd.pd & ~HUGEPD_OK);
}

static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr,
				    struct hstate *hstate)
{
	unsigned int shift = huge_page_shift(hstate);
	int psize = shift_to_mmu_psize(shift);
	unsigned long idx = ((addr >> shift) & (PTRS_PER_HUGEPTE(psize)-1));
	pte_t *dir = hugepd_page(*hpdp);

	return dir + idx;
}

static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
			   unsigned long address, unsigned int psize)
{
	pte_t *new = kmem_cache_zalloc(huge_pgtable_cache(psize),
				      GFP_KERNEL|__GFP_REPEAT);

	if (! new)
		return -ENOMEM;

	spin_lock(&mm->page_table_lock);
	if (!hugepd_none(*hpdp))
		kmem_cache_free(huge_pgtable_cache(psize), new);
	else
		hpdp->pd = (unsigned long)new | HUGEPD_OK;
	spin_unlock(&mm->page_table_lock);
	return 0;
}

/* Base page size affects how we walk hugetlb page tables */
#ifdef CONFIG_PPC_64K_PAGES
#define hpmd_offset(pud, addr, h)	pmd_offset(pud, addr)
#define hpmd_alloc(mm, pud, addr, h)	pmd_alloc(mm, pud, addr)
#else
static inline
pmd_t *hpmd_offset(pud_t *pud, unsigned long addr, struct hstate *hstate)
{
	if (huge_page_shift(hstate) == PAGE_SHIFT_64K)
		return pmd_offset(pud, addr);
	else
		return (pmd_t *) pud;
}
static inline
pmd_t *hpmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long addr,
		  struct hstate *hstate)
{
	if (huge_page_shift(hstate) == PAGE_SHIFT_64K)
		return pmd_alloc(mm, pud, addr);
	else
		return (pmd_t *) pud;
}
#endif

/* Build list of addresses of gigantic pages.  This function is used in early
 * boot before the buddy or bootmem allocator is setup.
 */
void add_gpage(unsigned long addr, unsigned long page_size,
	unsigned long number_of_pages)
{
	if (!addr)
		return;
	while (number_of_pages > 0) {
		gpage_freearray[nr_gpages] = addr;
		nr_gpages++;
		number_of_pages--;
		addr += page_size;
	}
}

/* Moves the gigantic page addresses from the temporary list to the
 * huge_boot_pages list.
 */
int alloc_bootmem_huge_page(struct hstate *hstate)
{
	struct huge_bootmem_page *m;
	if (nr_gpages == 0)
		return 0;
	m = phys_to_virt(gpage_freearray[--nr_gpages]);
	gpage_freearray[nr_gpages] = 0;
	list_add(&m->list, &huge_boot_pages);
	m->hstate = hstate;
	return 1;
}


/* Modelled after find_linux_pte() */
pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
{
	pgd_t *pg;
	pud_t *pu;
	pmd_t *pm;

	unsigned int psize;
	unsigned int shift;
	unsigned long sz;
	struct hstate *hstate;
	psize = get_slice_psize(mm, addr);
	shift = mmu_psize_to_shift(psize);
	sz = ((1UL) << shift);
	hstate = size_to_hstate(sz);

	addr &= hstate->mask;

	pg = pgd_offset(mm, addr);
	if (!pgd_none(*pg)) {
		pu = pud_offset(pg, addr);
		if (!pud_none(*pu)) {
			pm = hpmd_offset(pu, addr, hstate);
			if (!pmd_none(*pm))
				return hugepte_offset((hugepd_t *)pm, addr,
						      hstate);
		}
	}

	return NULL;
}

pte_t *huge_pte_alloc(