* 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/io.h>
#include <linux/slab.h>
-#include <linux/err.h>
-#include <linux/sysctl.h>
-#include <asm/mman.h>
+#include <linux/hugetlb.h>
+#include <asm/pgtable.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
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.
- */
-static unsigned int mmu_huge_psizes[MMU_PAGE_COUNT] = { }; /* initialize all to 0 */
-
/* 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. */
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;
- }
+ int psize;
+
+ for (psize = 0; psize < MMU_PAGE_COUNT; ++psize)
+ if (mmu_psize_defs[psize].shift == shift)
+ return psize;
return -1;
}
} while (pgd++, addr = next, addr != end);
}
-void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep, pte_t pte)
-{
- if (pte_present(*ptep)) {
- /* We open-code pte_clear because we need to pass the right
- * argument to hpte_need_flush (huge / !huge). Might not be
- * necessary anymore if we make hpte_need_flush() get the
- * page size from the slices
- */
- pte_update(mm, addr, ptep, ~0UL, 1);
- }
- *ptep = __pte(pte_val(pte) & ~_PAGE_HPTEFLAGS);
-}
-
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
- pte_t *ptep)
-{
- unsigned long old = pte_update(mm, addr, ptep, ~0UL, 1);
- return __pte(old);
-}
-
struct page *
follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
{
return 1;
}
+static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
+ unsigned long sz)
+{
+ unsigned long __boundary = (addr + sz) & ~(sz-1);
+ return (__boundary - 1 < end - 1) ? __boundary : end;
+}
+
int gup_hugepd(hugepd_t *hugepd, unsigned pdshift,
unsigned long addr, unsigned long end,
int write, struct page **pages, int *nr)
{
pte_t *ptep;
unsigned long sz = 1UL << hugepd_shift(*hugepd);
+ unsigned long next;
ptep = hugepte_offset(hugepd, addr, pdshift);
do {
+ next = hugepte_addr_end(addr, end, sz);
if (!gup_hugepte(ptep, sz, addr, end, write, pages, nr))
return 0;
- } while (ptep++, addr += sz, addr != end);
+ } while (ptep++, addr = next, addr != end);
return 1;
}
struct hstate *hstate = hstate_file(file);
int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate));
- if (!mmu_huge_psizes[mmu_psize])
- return -EINVAL;
return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1, 0);
}
return 1UL << mmu_psize_to_shift(psize);
}
-/*
- * Called by asm hashtable.S for doing lazy icache flush
- */
-static unsigned int hash_huge_page_do_lazy_icache(unsigned long rflags,
- pte_t pte, int trap, unsigned long sz)
-{
- struct page *page;
- int i;
-
- if (!pfn_valid(pte_pfn(pte)))
- return rflags;
-
- page = pte_page(pte);
-
- /* page is dirty */
- if (!test_bit(PG_arch_1, &page->flags) && !PageReserved(page)) {
- if (trap == 0x400) {
- for (i = 0; i < (sz / PAGE_SIZE); i++)
- __flush_dcache_icache(page_address(page+i));
- set_bit(PG_arch_1, &page->flags);
- } else {
- rflags |= HPTE_R_N;
- }
- }
- return rflags;
-}
-
-int __hash_page_huge(unsigned long ea, unsigned long access, unsigned long vsid,
- pte_t *ptep, unsigned long trap, int local, int ssize,
- unsigned int shift, unsigned int mmu_psize)
+static int __init add_huge_page_size(unsigned long long size)
{
- unsigned long old_pte, new_pte;
- unsigned long va, rflags, pa, sz;
- long slot;
- int err = 1;
-
- BUG_ON(shift != mmu_psize_defs[mmu_psize].shift);
-
- /* Search the Linux page table for a match with va */
- va = hpt_va(ea, vsid, ssize);
-
- /*
- * Check the user's access rights to the page. If access should be
- * prevented then send the problem up to do_page_fault.
- */
- if (unlikely(access & ~pte_val(*ptep)))
- goto out;
- /*
- * At this point, we have a pte (old_pte) which can be used to build
- * or update an HPTE. There are 2 cases:
- *
- * 1. There is a valid (present) pte with no associated HPTE (this is
- * the most common case)
- * 2. There is a valid (present) pte with an associated HPTE. The
- * current values of the pp bits in the HPTE prevent access
- * because we are doing software DIRTY bit management and the
- * page is currently not DIRTY.
- */
-
-
- do {
- old_pte = pte_val(*ptep);
- if (old_pte & _PAGE_BUSY)
- goto out;
- new_pte = old_pte | _PAGE_BUSY | _PAGE_ACCESSED;
- } while(old_pte != __cmpxchg_u64((unsigned long *)ptep,
- old_pte, new_pte));
-
- rflags = 0x2 | (!(new_pte & _PAGE_RW));
- /* _PAGE_EXEC -> HW_NO_EXEC since it's inverted */
- rflags |= ((new_pte & _PAGE_EXEC) ? 0 : HPTE_R_N);
- sz = ((1UL) << shift);
- if (!cpu_has_feature(CPU_FTR_COHERENT_ICACHE))
- /* No CPU has hugepages but lacks no execute, so we
- * don't need to worry about that case */
- rflags = hash_huge_page_do_lazy_icache(rflags, __pte(old_pte),
- trap, sz);
-
- /* Check if pte already has an hpte (case 2) */
- if (unlikely(old_pte & _PAGE_HASHPTE)) {
- /* There MIGHT be an HPTE for this pte */
- unsigned long hash, slot;
-
- hash = hpt_hash(va, shift, ssize);
- if (old_pte & _PAGE_F_SECOND)
- hash = ~hash;
- slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
- slot += (old_pte & _PAGE_F_GIX) >> 12;
-
- if (ppc_md.hpte_updatepp(slot, rflags, va, mmu_psize,
- ssize, local) == -1)
- old_pte &= ~_PAGE_HPTEFLAGS;
- }
-
- if (likely(!(old_pte & _PAGE_HASHPTE))) {
- unsigned long hash = hpt_hash(va, shift, ssize);
- unsigned long hpte_group;
-
- pa = pte_pfn(__pte(old_pte)) << PAGE_SHIFT;
-
-repeat:
- hpte_group = ((hash & htab_hash_mask) *
- HPTES_PER_GROUP) & ~0x7UL;
-
- /* clear HPTE slot informations in new PTE */
-#ifdef CONFIG_PPC_64K_PAGES
- new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HPTE_SUB0;
-#else
- new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE;
-#endif
- /* Add in WIMG bits */
- rflags |= (new_pte & (_PAGE_WRITETHRU | _PAGE_NO_CACHE |
- _PAGE_COHERENT | _PAGE_GUARDED));
-
- /* Insert into the hash table, primary slot */
- slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags, 0,
- mmu_psize, ssize);
-
- /* Primary is full, try the secondary */
- if (unlikely(slot == -1)) {
- hpte_group = ((~hash & htab_hash_mask) *
- HPTES_PER_GROUP) & ~0x7UL;
- slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags,
- HPTE_V_SECONDARY,
- mmu_psize, ssize);
- if (slot == -1) {
- if (mftb() & 0x1)
- hpte_group = ((hash & htab_hash_mask) *
- HPTES_PER_GROUP)&~0x7UL;
-
- ppc_md.hpte_remove(hpte_group);
- goto repeat;
- }
- }
+ int shift = __ffs(size);
+ int mmu_psize;
- if (unlikely(slot == -2))
- panic("hash_huge_page: pte_insert failed\n");
+ /* Check that it is a page size supported by the hardware and
+ * that it fits within pagetable and slice limits. */
+ if (!is_power_of_2(size)
+ || (shift > SLICE_HIGH_SHIFT) || (shift <= PAGE_SHIFT))
+ return -EINVAL;
- new_pte |= (slot << 12) & (_PAGE_F_SECOND | _PAGE_F_GIX);
- }
+ if ((mmu_psize = shift_to_mmu_psize(shift)) < 0)
+ return -EINVAL;
- /*
- * No need to use ldarx/stdcx here
+#ifdef CONFIG_SPU_FS_64K_LS
+ /* Disable support for 64K huge pages when 64K SPU local store
+ * support is enabled as the current implementation conflicts.
*/
- *ptep = __pte(new_pte & ~_PAGE_BUSY);
+ if (shift == PAGE_SHIFT_64K)
+ return -EINVAL;
+#endif /* CONFIG_SPU_FS_64K_LS */
- err = 0;
+ BUG_ON(mmu_psize_defs[mmu_psize].shift != shift);
- out:
- return err;
-}
-
-static void __init set_huge_psize(int psize)
-{
- unsigned pdshift;
+ /* Return if huge page size has already been setup */
+ if (size_to_hstate(size))
+ return 0;
- /* Check that it is a page size supported by the hardware and
- * that it fits within pagetable limits. */
- if (mmu_psize_defs[psize].shift &&
- mmu_psize_defs[psize].shift < SID_SHIFT_1T &&
- (mmu_psize_defs[psize].shift > MIN_HUGEPTE_SHIFT ||
- mmu_psize_defs[psize].shift == PAGE_SHIFT_64K ||
- mmu_psize_defs[psize].shift == PAGE_SHIFT_16G)) {
- /* Return if huge page size has already been setup or is the
- * same as the base page size. */
- if (mmu_huge_psizes[psize] ||
- mmu_psize_defs[psize].shift == PAGE_SHIFT)
- return;
- hugetlb_add_hstate(mmu_psize_defs[psize].shift - PAGE_SHIFT);
+ hugetlb_add_hstate(shift - PAGE_SHIFT);
- if (mmu_psize_defs[psize].shift < PMD_SHIFT)
- pdshift = PMD_SHIFT;
- else if (mmu_psize_defs[psize].shift < PUD_SHIFT)
- pdshift = PUD_SHIFT;
- else
- pdshift = PGDIR_SHIFT;
- mmu_huge_psizes[psize] = pdshift - mmu_psize_defs[psize].shift;
- }
+ return 0;
}
static int __init hugepage_setup_sz(char *str)
{
unsigned long long size;
- int mmu_psize;
- int shift;
size = memparse(str, &str);
- shift = __ffs(size);
- mmu_psize = shift_to_mmu_psize(shift);
- if (mmu_psize >= 0 && mmu_psize_defs[mmu_psize].shift)
- set_huge_psize(mmu_psize);
- else
+ if (add_huge_page_size(size) != 0)
printk(KERN_WARNING "Invalid huge page size specified(%llu)\n", size);
return 1;
if (!cpu_has_feature(CPU_FTR_16M_PAGE))
return -ENODEV;
- /* Add supported huge page sizes. Need to change
- * HUGE_MAX_HSTATE if the number of supported huge page sizes
- * changes.
- */
- set_huge_psize(MMU_PAGE_16M);
- set_huge_psize(MMU_PAGE_16G);
+ for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
+ unsigned shift;
+ unsigned pdshift;
- /* Temporarily disable support for 64K huge pages when 64K SPU local
- * store support is enabled as the current implementation conflicts.
- */
-#ifndef CONFIG_SPU_FS_64K_LS
- set_huge_psize(MMU_PAGE_64K);
-#endif
+ if (!mmu_psize_defs[psize].shift)
+ continue;
- for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
- if (mmu_huge_psizes[psize]) {
- pgtable_cache_add(mmu_huge_psizes[psize], NULL);
- if (!PGT_CACHE(mmu_huge_psizes[psize]))
- panic("hugetlbpage_init(): could not create "
- "pgtable cache for %d bit pagesize\n",
- mmu_psize_to_shift(psize));
- }
+ shift = mmu_psize_to_shift(psize);
+
+ if (add_huge_page_size(1ULL << shift) < 0)
+ continue;
+
+ if (shift < PMD_SHIFT)
+ pdshift = PMD_SHIFT;
+ else if (shift < PUD_SHIFT)
+ pdshift = PUD_SHIFT;
+ else
+ pdshift = PGDIR_SHIFT;
+
+ pgtable_cache_add(pdshift - shift, NULL);
+ if (!PGT_CACHE(pdshift - shift))
+ panic("hugetlbpage_init(): could not create "
+ "pgtable cache for %d bit pagesize\n", shift);
}
+ /* Set default large page size. Currently, we pick 16M or 1M
+ * depending on what is available
+ */
+ if (mmu_psize_defs[MMU_PAGE_16M].shift)
+ HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_16M].shift;
+ else if (mmu_psize_defs[MMU_PAGE_1M].shift)
+ HPAGE_SHIFT = mmu_psize_defs[MMU_PAGE_1M].shift;
+
return 0;
}
module_init(hugetlbpage_init);
+
+void flush_dcache_icache_hugepage(struct page *page)
+{
+ int i;
+
+ BUG_ON(!PageCompound(page));
+
+ for (i = 0; i < (1UL << compound_order(page)); i++)
+ __flush_dcache_icache(page_address(page+i));
+}