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

/*
 * PPC Huge TLB Page Support for Kernel.
 *
 * Copyright (C) 2003 David Gibson, IBM Corporation.
 * Copyright (C) 2011 Becky Bruce, Freescale Semiconductor
 *
 * Based on the IA-32 version:
 * Copyright (C) 2002, Rohit Seth <rohit.seth@intel.com>
 */

#include <linux/mm.h>
#include <linux/io.h>
#include <linux/slab.h>
#include <linux/hugetlb.h>
#include <linux/export.h>
#include <linux/of_fdt.h>
#include <linux/memblock.h>
#include <linux/bootmem.h>
#include <linux/moduleparam.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>
#include <asm/setup.h>

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

unsigned int HPAGE_SHIFT;

/*
 * Tracks gpages after the device tree is scanned and before the
 * huge_boot_pages list is ready.  On non-Freescale implementations, this is
 * just used to track 16G pages and so is a single array.  FSL-based
 * implementations may have more than one gpage size, so we need multiple
 * arrays
 */
#ifdef CONFIG_PPC_FSL_BOOK3E
#define MAX_NUMBER_GPAGES	128
struct psize_gpages {
	u64 gpage_list[MAX_NUMBER_GPAGES];
	unsigned int nr_gpages;
};
static struct psize_gpages gpage_freearray[MMU_PAGE_COUNT];
#else
#define MAX_NUMBER_GPAGES	1024
static u64 gpage_freearray[MAX_NUMBER_GPAGES];
static unsigned nr_gpages;
#endif

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

#ifdef CONFIG_PPC_BOOK3S_64
/*
 * At this point we do the placement change only for BOOK3S 64. This would
 * possibly work on other subarchs.
 */

/*
 * We have PGD_INDEX_SIZ = 12 and PTE_INDEX_SIZE = 8, so that we can have
 * 16GB hugepage pte in PGD and 16MB hugepage pte at PMD;
 */
int pmd_huge(pmd_t pmd)
{
	/*
	 * leaf pte for huge page, bottom two bits != 00
	 */
	return ((pmd_val(pmd) & 0x3) != 0x0);
}

int pud_huge(pud_t pud)
{
	/*
	 * leaf pte for huge page, bottom two bits != 00
	 */
	return ((pud_val(pud) & 0x3) != 0x0);
}

int pgd_huge(pgd_t pgd)
{
	/*
	 * leaf pte for huge page, bottom two bits != 00
	 */
	return ((pgd_val(pgd) & 0x3) != 0x0);
}
#else
int pmd_huge(pmd_t pmd)
{
	return 0;
}

int pud_huge(pud_t pud)
{
	return 0;
}

int pgd_huge(pgd_t pgd)
{
	return 0;
}
#endif

/*
 * We have 4 cases for pgds and pmds:
 * (1) invalid (all zeroes)
 * (2) pointer to next table, as normal; bottom 6 bits == 0
 * (3) leaf pte for huge page, bottom two bits != 00
 * (4) hugepd pointer, bottom two bits == 00, next 4 bits indicate size of table
 */
pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift)
{
	pgd_t *pg;
	pud_t *pu;
	pmd_t *pm;
	pte_t *ret_pte;
	hugepd_t *hpdp = NULL;
	unsigned pdshift = PGDIR_SHIFT;

	if (shift)
		*shift = 0;

	pg = pgdir + pgd_index(ea);

	if (pgd_huge(*pg)) {
		ret_pte = (pte_t *) pg;
		goto out;
	} else if (is_hugepd(pg))
		hpdp = (hugepd_t *)pg;
	else if (!pgd_none(*pg)) {
		pdshift = PUD_SHIFT;
		pu = pud_offset(pg, ea);

		if (pud_huge(*pu)) {
			ret_pte = (pte_t *) pu;
			goto out;
		} else if (is_hugepd(pu))
			hpdp = (hugepd_t *)pu;
		else if (!pud_none(*pu)) {
			pdshift = PMD_SHIFT;
			pm = pmd_offset(pu, ea);

			if (pmd_huge(*pm)) {
				ret_pte = (pte_t *) pm;
				goto out;
			} else if (is_hugepd(pm))
				hpdp = (hugepd_t *)pm;
			else if (!pmd_none(*pm))
				return pte_offset_kernel(pm, ea);
		}
	}
	if (!hpdp)
		return NULL;

	ret_pte = hugepte_offset(hpdp, ea, pdshift);
	pdshift = hugepd_shift(*hpdp);
out:
	if (shift)
		*shift = pdshift;
	return ret_pte;
}
EXPORT_SYMBOL_GPL(find_linux_pte_or_hugepte);

pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
{
	return find_linux_pte_or_hugepte(mm->pgd, addr, NULL);
}

static int __hugepte_alloc(struct mm_struct *mm, hugepd_t *hpdp,
			   unsigned long address, unsigned pdshift, unsigned pshift)
{
	struct kmem_cache *cachep;
	pte_t