* 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/smp_lock.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/tlb.h>
-#include <asm/spu.h>
-
-#include <linux/sysctl.h>
-
-#define NUM_LOW_AREAS (0x100000000UL >> SID_SHIFT)
-#define NUM_HIGH_AREAS (PGTABLE_RANGE >> HTLB_AREA_SHIFT)
-#ifdef CONFIG_PPC_64K_PAGES
-#define HUGEPTE_INDEX_SIZE (PMD_SHIFT-HPAGE_SHIFT)
-#else
-#define HUGEPTE_INDEX_SIZE (PUD_SHIFT-HPAGE_SHIFT)
-#endif
-#define PTRS_PER_HUGEPTE (1 << HUGEPTE_INDEX_SIZE)
-#define HUGEPTE_TABLE_SIZE (sizeof(pte_t) << HUGEPTE_INDEX_SIZE)
+#define PAGE_SHIFT_64K 16
+#define PAGE_SHIFT_16M 24
+#define PAGE_SHIFT_16G 34
-#define HUGEPD_SHIFT (HPAGE_SHIFT + HUGEPTE_INDEX_SIZE)
-#define HUGEPD_SIZE (1UL << HUGEPD_SHIFT)
-#define HUGEPD_MASK (~(HUGEPD_SIZE-1))
+#define MAX_NUMBER_GPAGES 1024
-#define huge_pgtable_cache (pgtable_cache[HUGEPTE_CACHE_NUM])
+/* 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;
/* 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;
+static inline int shift_to_mmu_psize(unsigned int shift)
+{
+ int psize;
+
+ for (psize = 0; psize < MMU_PAGE_COUNT; ++psize)
+ if (mmu_psize_defs[psize].shift == shift)
+ return psize;
+ 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();
+}
#define hugepd_none(hpd) ((hpd).pd == 0)
static inline pte_t *hugepd_page(hugepd_t hpd)
{
- BUG_ON(!(hpd.pd & HUGEPD_OK));
- return (pte_t *)(hpd.pd & ~HUGEPD_OK);
+ BUG_ON(!hugepd_ok(hpd));
+ return (pte_t *)((hpd.pd & ~HUGEPD_SHIFT_MASK) | 0xc000000000000000);
}
-static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr)
+static inline unsigned int hugepd_shift(hugepd_t hpd)
{
- unsigned long idx = ((addr >> HPAGE_SHIFT) & (PTRS_PER_HUGEPTE-1));
+ return hpd.pd & HUGEPD_SHIFT_MASK;
+}
+
+static inline pte_t *hugepte_offset(hugepd_t *hpdp, unsigned long addr, unsigned pdshift)
+{
+ unsigned long idx = (addr & ((1UL << pdshift) - 1)) >> hugepd_shift(*hpdp);
pte_t *dir = hugepd_page(*hpdp);
return dir + idx;
}
+pte_t *find_linux_pte_or_hugepte(pgd_t *pgdir, unsigned long ea, unsigned *shift)
+{
+ pgd_t *pg;
+ pud_t *pu;
+ pmd_t *pm;
+ hugepd_t *hpdp = NULL;
+ unsigned pdshift = PGDIR_SHIFT;
+
+ if (shift)
+ *shift = 0;
+
+ pg = pgdir + pgd_index(ea);
+ if (is_hugepd(pg)) {
+ hpdp = (hugepd_t *)pg;
+ } else if (!pgd_none(*pg)) {
+ pdshift = PUD_SHIFT;
+ pu = pud_offset(pg, ea);
+ if (is_hugepd(pu))
+ hpdp = (hugepd_t *)pu;
+ else if (!pud_none(*pu)) {
+ pdshift = PMD_SHIFT;
+ pm = pmd_offset(pu, ea);
+ if (is_hugepd(pm))
+ hpdp = (hugepd_t *)pm;
+ else if (!pmd_none(*pm)) {
+ return pte_offset_map(pm, ea);
+ }
+ }
+ }
+
+ if (!hpdp)
+ return NULL;
+
+ if (shift)
+ *shift = hugepd_shift(*hpdp);
+ return hugepte_offset(hpdp, ea, pdshift);
+}
+
+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 long address, unsigned pdshift, unsigned pshift)
{
- pte_t *new = kmem_cache_alloc(huge_pgtable_cache,
- GFP_KERNEL|__GFP_REPEAT);
+ pte_t *new = kmem_cache_zalloc(PGT_CACHE(pdshift - pshift),
+ GFP_KERNEL|__GFP_REPEAT);
+
+ BUG_ON(pshift > HUGEPD_SHIFT_MASK);
+ BUG_ON((unsigned long)new & HUGEPD_SHIFT_MASK);
if (! new)
return -ENOMEM;
spin_lock(&mm->page_table_lock);
if (!hugepd_none(*hpdp))
- kmem_cache_free(huge_pgtable_cache, new);
+ kmem_cache_free(PGT_CACHE(pdshift - pshift), new);
else
- hpdp->pd = (unsigned long)new | HUGEPD_OK;
+ hpdp->pd = ((unsigned long)new & ~0x8000000000000000) | pshift;
spin_unlock(&mm->page_table_lock);
return 0;
}
-/* Modelled after find_linux_pte() */
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr, unsigned long sz)
{
pgd_t *pg;
pud_t *pu;
+ pmd_t *pm;
+ hugepd_t *hpdp = NULL;
+ unsigned pshift = __ffs(sz);
+ unsigned pdshift = PGDIR_SHIFT;
- BUG_ON(! in_hugepage_area(mm->context, addr));
-
- addr &= HPAGE_MASK;
+ addr &= ~(sz-1);
pg = pgd_offset(mm, addr);
- if (!pgd_none(*pg)) {
- pu = pud_offset(pg, addr);
- if (!pud_none(*pu)) {
-#ifdef CONFIG_PPC_64K_PAGES
- pmd_t *pm;
- pm = pmd_offset(pu, addr);
- if (!pmd_none(*pm))
- return hugepte_offset((hugepd_t *)pm, addr);
-#else
- return hugepte_offset((hugepd_t *)pu, addr);
-#endif
+ if (pshift >= PUD_SHIFT) {
+ hpdp = (hugepd_t *)pg;
+ } else {
+ pdshift = PUD_SHIFT;
+ pu = pud_alloc(mm, pg, addr);
+ if (pshift >= PMD_SHIFT) {
+ hpdp = (hugepd_t *)pu;
+ } else {
+ pdshift = PMD_SHIFT;
+ pm = pmd_alloc(mm, pu, addr);
+ hpdp = (hugepd_t *)pm;
}
}
- return NULL;
-}
-
-pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
-{
- pgd_t *pg;
- pud_t *pu;
- hugepd_t *hpdp = NULL;
+ if (!hpdp)
+ return NULL;
- BUG_ON(! in_hugepage_area(mm->context, addr));
+ BUG_ON(!hugepd_none(*hpdp) && !hugepd_ok(*hpdp));
- addr &= HPAGE_MASK;
+ if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr, pdshift, pshift))
+ return NULL;
- pg = pgd_offset(mm, addr);
- pu = pud_alloc(mm, pg, addr);
+ return hugepte_offset(hpdp, addr, pdshift);
+}
- if (pu) {
-#ifdef CONFIG_PPC_64K_PAGES
- pmd_t *pm;
- pm = pmd_alloc(mm, pu, addr);
- if (pm)
- hpdp = (hugepd_t *)pm;
-#else
- hpdp = (hugepd_t *)pu;
-#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;
}
+}
- if (! hpdp)
- return NULL;
-
- if (hugepd_none(*hpdp) && __hugepte_alloc(mm, hpdp, addr))
- return NULL;
-
- return hugepte_offset(hpdp, addr);
+/* 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;
}
int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep)
return 0;
}
-static void free_hugepte_range(struct mmu_gather *tlb, hugepd_t *hpdp)
+static void free_hugepd_range(struct mmu_gather *tlb, hugepd_t *hpdp, int pdshift,
+ unsigned long start, unsigned long end,
+ unsigned long floor, unsigned long ceiling)
{
pte_t *hugepte = hugepd_page(*hpdp);
+ unsigned shift = hugepd_shift(*hpdp);
+ unsigned long pdmask = ~((1UL << pdshift) - 1);
+
+ start &= pdmask;
+ if (start < floor)
+ return;
+ if (ceiling) {
+ ceiling &= pdmask;
+ if (! ceiling)
+ return;
+ }
+ if (end - 1 > ceiling - 1)
+ return;
hpdp->pd = 0;
tlb->need_flush = 1;
- pgtable_free_tlb(tlb, pgtable_free_cache(hugepte, HUGEPTE_CACHE_NUM,
- PGF_CACHENUM_MASK));
+ pgtable_free_tlb(tlb, hugepte, pdshift - shift);
}
-#ifdef CONFIG_PPC_64K_PAGES
static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
next = pmd_addr_end(addr, end);
if (pmd_none(*pmd))
continue;
- free_hugepte_range(tlb, (hugepd_t *)pmd);
+ free_hugepd_range(tlb, (hugepd_t *)pmd, PMD_SHIFT,
+ addr, next, floor, ceiling);
} while (pmd++, addr = next, addr != end);
start &= PUD_MASK;
pmd = pmd_offset(pud, start);
pud_clear(pud);
- pmd_free_tlb(tlb, pmd);
+ pmd_free_tlb(tlb, pmd, start);
}
-#endif
static void hugetlb_free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
unsigned long addr, unsigned long end,
pud = pud_offset(pgd, addr);
do {
next = pud_addr_end(addr, end);
-#ifdef CONFIG_PPC_64K_PAGES
- if (pud_none_or_clear_bad(pud))
- continue;
- hugetlb_free_pmd_range(tlb, pud, addr, next, floor, ceiling);
-#else
- if (pud_none(*pud))
- continue;
- free_hugepte_range(tlb, (hugepd_t *)pud);
-#endif
+ if (!is_hugepd(pud)) {
+ if (pud_none_or_clear_bad(pud))
+ continue;
+ hugetlb_free_pmd_range(tlb, pud, addr, next, floor,
+ ceiling);
+ } else {
+ free_hugepd_range(tlb, (hugepd_t *)pud, PUD_SHIFT,
+ addr, next, floor, ceiling);
+ }
} while (pud++, addr = next, addr != end);
start &= PGDIR_MASK;
pud = pud_offset(pgd, start);
pgd_clear(pgd);
- pud_free_tlb(tlb, pud);
+ pud_free_tlb(tlb, pud, start);
}
/*
*
* Must be called with pagetable lock held.
*/
-void hugetlb_free_pgd_range(struct mmu_gather **tlb,
+void hugetlb_free_pgd_range(struct mmu_gather *tlb,
unsigned long addr, unsigned long end,
unsigned long floor, unsigned long ceiling)
{
pgd_t *pgd;
unsigned long next;
- unsigned long start;
/*
- * Comments below take from the normal free_pgd_range(). They
- * apply here too. The tests against HUGEPD_MASK below are
- * essential, because we *don't* test for this at the bottom
- * level. Without them we'll attempt to free a hugepte table
- * when we unmap just part of it, even if there are other
- * active mappings using it.
- *
- * The next few lines have given us lots of grief...
- *
- * Why are we testing HUGEPD* at this top level? Because
- * often there will be no work to do at all, and we'd prefer
- * not to go all the way down to the bottom just to discover
- * that.
- *
- * Why all these "- 1"s? Because 0 represents both the bottom
- * of the address space and the top of it (using -1 for the
- * top wouldn't help much: the masks would do the wrong thing).
- * The rule is that addr 0 and floor 0 refer to the bottom of
- * the address space, but end 0 and ceiling 0 refer to the top
- * Comparisons need to use "end - 1" and "ceiling - 1" (though
- * that end 0 case should be mythical).
+ * Because there are a number of different possible pagetable
+ * layouts for hugepage ranges, we limit knowledge of how
+ * things should be laid out to the allocation path
+ * (huge_pte_alloc(), above). Everything else works out the
+ * structure as it goes from information in the hugepd
+ * pointers. That means that we can't here use the
+ * optimization used in the normal page free_pgd_range(), of
+ * checking whether we're actually covering a large enough
+ * range to have to do anything at the top level of the walk
+ * instead of at the bottom.
*
- * Wherever addr is brought up or ceiling brought down, we
- * must be careful to reject "the opposite 0" before it
- * confuses the subsequent tests. But what about where end is
- * brought down by HUGEPD_SIZE below? no, end can't go down to
- * 0 there.
- *
- * Whereas we round start (addr) and ceiling down, by different
- * masks at different levels, in order to test whether a table
- * now has no other vmas using it, so can be freed, we don't
- * bother to round floor or end up - the tests don't need that.
+ * To make sense of this, you should probably go read the big
+ * block comment at the top of the normal free_pgd_range(),
+ * too.
*/
- addr &= HUGEPD_MASK;
- if (addr < floor) {
- addr += HUGEPD_SIZE;
- if (!addr)
- return;
- }
- if (ceiling) {
- ceiling &= HUGEPD_MASK;
- if (!ceiling)
- return;
- }
- if (end - 1 > ceiling - 1)
- end -= HUGEPD_SIZE;
- if (addr > end - 1)
- return;
-
- start = addr;
- pgd = pgd_offset((*tlb)->mm, addr);
+ pgd = pgd_offset(tlb->mm, addr);
do {
- BUG_ON(! in_hugepage_area((*tlb)->mm->context, addr));
next = pgd_addr_end(addr, end);
- if (pgd_none_or_clear_bad(pgd))
- continue;
- hugetlb_free_pud_range(*tlb, pgd, addr, next, floor, ceiling);
+ if (!is_hugepd(pgd)) {
+ if (pgd_none_or_clear_bad(pgd))
+ continue;
+ hugetlb_free_pud_range(tlb, pgd, addr, next, floor, ceiling);
+ } else {
+ free_hugepd_range(tlb, (hugepd_t *)pgd, PGDIR_SHIFT,
+ addr, next, floor, ceiling);
+ }
} 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 & HPAGE_MASK, 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 slb_flush_info {
- struct mm_struct *mm;
- u16 newareas;
-};
-
-static void flush_low_segments(void *parm)
-{
- struct slb_flush_info *fi = parm;
- unsigned long i;
-
- BUILD_BUG_ON((sizeof(fi->newareas)*8) != NUM_LOW_AREAS);
-
- if (current->active_mm != fi->mm)
- return;
-
- /* Only need to do anything if this CPU is working in the same
- * mm as the one which has changed */
-
- /* update the paca copy of the context struct */
- get_paca()->context = current->active_mm->context;
-
- asm volatile("isync" : : : "memory");
- for (i = 0; i < NUM_LOW_AREAS; i++) {
- if (! (fi->newareas & (1U << i)))
- continue;
- asm volatile("slbie %0"
- : : "r" ((i << SID_SHIFT) | SLBIE_C));
- }
- asm volatile("isync" : : : "memory");
-}
-
-static void flush_high_segments(void *parm)
-{
- struct slb_flush_info *fi = parm;
- unsigned long i, j;
-
-
- BUILD_BUG_ON((sizeof(fi->newareas)*8) != NUM_HIGH_AREAS);
-
- if (current->active_mm != fi->mm)
- return;
-
- /* Only need to do anything if this CPU is working in the same
- * mm as the one which has changed */
-
- /* update the paca copy of the context struct */
- get_paca()->context = current->active_mm->context;
-
- asm volatile("isync" : : : "memory");
- for (i = 0; i < NUM_HIGH_AREAS; i++) {
- if (! (fi->newareas & (1U << i)))
- continue;
- for (j = 0; j < (1UL << (HTLB_AREA_SHIFT-SID_SHIFT)); j++)
- asm volatile("slbie %0"
- :: "r" (((i << HTLB_AREA_SHIFT)
- + (j << SID_SHIFT)) | SLBIE_C));
- }
- asm volatile("isync" : : : "memory");
-}
-
-static int prepare_low_area_for_htlb(struct mm_struct *mm, unsigned long area)
-{
- unsigned long start = area << SID_SHIFT;
- unsigned long end = (area+1) << SID_SHIFT;
- struct vm_area_struct *vma;
-
- BUG_ON(area >= NUM_LOW_AREAS);
-
- /* Check no VMAs are in the region */
- vma = find_vma(mm, start);
- if (vma && (vma->vm_start < end))
- return -EBUSY;
-
- return 0;
-}
-
-static int prepare_high_area_for_htlb(struct mm_struct *mm, unsigned long area)
-{
- unsigned long start = area << HTLB_AREA_SHIFT;
- unsigned long end = (area+1) << HTLB_AREA_SHIFT;
- struct vm_area_struct *vma;
-
- BUG_ON(area >= NUM_HIGH_AREAS);
-
- /* Hack, so that each addresses is controlled by exactly one
- * of the high or low area bitmaps, the first high area starts
- * at 4GB, not 0 */
- if (start == 0)
- start = 0x100000000UL;
-
- /* Check no VMAs are in the region */
- vma = find_vma(mm, start);
- if (vma && (vma->vm_start < end))
- return -EBUSY;
-
- return 0;
-}
-
-static int open_low_hpage_areas(struct mm_struct *mm, u16 newareas)
-{
- unsigned long i;
- struct slb_flush_info fi;
-
- BUILD_BUG_ON((sizeof(newareas)*8) != NUM_LOW_AREAS);
- BUILD_BUG_ON((sizeof(mm->context.low_htlb_areas)*8) != NUM_LOW_AREAS);
-
- newareas &= ~(mm->context.low_htlb_areas);
- if (! newareas)
- return 0; /* The segments we want are already open */
-
- for (i = 0; i < NUM_LOW_AREAS; i++)
- if ((1 << i) & newareas)
- if (prepare_low_area_for_htlb(mm, i) != 0)
- return -EBUSY;
-
- mm->context.low_htlb_areas |= newareas;
-
- /* the context change must make it to memory before the flush,
- * so that further SLB misses do the right thing. */
- mb();
-
- fi.mm = mm;
- fi.newareas = newareas;
- on_each_cpu(flush_low_segments, &fi, 0, 1);
-
- return 0;
-}
-
-static int open_high_hpage_areas(struct mm_struct *mm, u16 newareas)
-{
- struct slb_flush_info fi;
- unsigned long i;
-
- BUILD_BUG_ON((sizeof(newareas)*8) != NUM_HIGH_AREAS);
- BUILD_BUG_ON((sizeof(mm->context.high_htlb_areas)*8)
- != NUM_HIGH_AREAS);
-
- newareas &= ~(mm->context.high_htlb_areas);
- if (! newareas)
- return 0; /* The areas we want are already open */
-
- for (i = 0; i < NUM_HIGH_AREAS; i++)
- if ((1 << i) & newareas)
- if (prepare_high_area_for_htlb(mm, i) != 0)
- return -EBUSY;
-
- mm->context.high_htlb_areas |= newareas;
-
- /* the context change must make it to memory before the flush,
- * so that further SLB misses do the right thing. */
- mb();
-
- fi.mm = mm;
- fi.newareas = newareas;
- on_each_cpu(flush_high_segments, &fi, 0, 1);
-
- return 0;
-}
-
-int prepare_hugepage_range(unsigned long addr, unsigned long len, pgoff_t pgoff)
-{
- int err = 0;
-
- if (pgoff & (~HPAGE_MASK >> PAGE_SHIFT))
- return -EINVAL;
- if (len & ~HPAGE_MASK)
- return -EINVAL;
- if (addr & ~HPAGE_MASK)
- return -EINVAL;
-
- if (addr < 0x100000000UL)
- err = open_low_hpage_areas(current->mm,
- LOW_ESID_MASK(addr, len));
- if ((addr + len) > 0x100000000UL)
- err = open_high_hpage_areas(current->mm,
- HTLB_AREA_MASK(addr, len));
-#ifdef CONFIG_SPE_BASE
- spu_flush_all_slbs(current->mm);
-#endif
- if (err) {
- printk(KERN_DEBUG "prepare_hugepage_range(%lx, %lx)"
- " failed (lowmask: 0x%04hx, highmask: 0x%04hx)\n",
- addr, len,
- LOW_ESID_MASK(addr, len), HTLB_AREA_MASK(addr, len));
- return err;
- }
-
- return 0;
-}
-
struct page *
follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
{
pte_t *ptep;
struct page *page;
+ unsigned shift;
+ unsigned long mask;
- if (! in_hugepage_area(mm->context, address))
+ ptep = find_linux_pte_or_hugepte(mm->pgd, address, &shift);
+
+ /* Verify it is a huge page else bail. */
+ if (!ptep || !shift)
return ERR_PTR(-EINVAL);
- ptep = huge_pte_offset(mm, address);
+ mask = (1UL << shift) - 1;
page = pte_page(*ptep);
if (page)
- page += (address % HPAGE_SIZE) / PAGE_SIZE;
+ page += (address & mask) / PAGE_SIZE;
return page;
}
return 0;
}
+int pud_huge(pud_t pud)
+{
+ return 0;
+}
+
struct page *
follow_huge_pmd(struct mm_struct *mm, unsigned long address,
pmd_t *pmd, int write)
return NULL;
}
-/* Because we have an exclusive hugepage region which lies within the
- * normal user address space, we have to take special measures to make
- * non-huge mmap()s evade the hugepage reserved regions. */
-unsigned long arch_get_unmapped_area(struct file *filp, unsigned long addr,
- unsigned long len, unsigned long pgoff,
- unsigned long flags)
+static noinline int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
+ unsigned long end, int write, struct page **pages, int *nr)
{
- struct mm_struct *mm = current->mm;
- struct vm_area_struct *vma;
- unsigned long start_addr;
-
- if (len > TASK_SIZE)
- return -ENOMEM;
-
- if (addr) {
- addr = PAGE_ALIGN(addr);
- vma = find_vma(mm, addr);
- if (((TASK_SIZE - len) >= addr)
- && (!vma || (addr+len) <= vma->vm_start)
- && !is_hugepage_only_range(mm, addr,len))
- return addr;
- }
- if (len > mm->cached_hole_size) {
- start_addr = addr = mm->free_area_cache;
- } else {
- start_addr = addr = TASK_UNMAPPED_BASE;
- mm->cached_hole_size = 0;
- }
-
-full_search:
- vma = find_vma(mm, addr);
- while (TASK_SIZE - len >= addr) {
- BUG_ON(vma && (addr >= vma->vm_end));
+ unsigned long mask;
+ unsigned long pte_end;
+ struct page *head, *page;
+ pte_t pte;
+ int refs;
- if (touches_hugepage_low_range(mm, addr, len)) {
- addr = ALIGN(addr+1, 1<<SID_SHIFT);
- vma = find_vma(mm, addr);
- continue;
- }
- if (touches_hugepage_high_range(mm, addr, len)) {
- addr = ALIGN(addr+1, 1UL<<HTLB_AREA_SHIFT);
- vma = find_vma(mm, addr);
- continue;
- }
- if (!vma || addr + len <= vma->vm_start) {
- /*
- * Remember the place where we stopped the search:
- */
- mm->free_area_cache = addr + len;
- return addr;
- }
- if (addr + mm->cached_hole_size < vma->vm_start)
- mm->cached_hole_size = vma->vm_start - addr;
- addr = vma->vm_end;
- vma = vma->vm_next;
- }
+ pte_end = (addr + sz) & ~(sz-1);
+ if (pte_end < end)
+ end = pte_end;
- /* Make sure we didn't miss any holes */
- if (start_addr != TASK_UNMAPPED_BASE) {
- start_addr = addr = TASK_UNMAPPED_BASE;
- mm->cached_hole_size = 0;
- goto full_search;
- }
- return -ENOMEM;
-}
+ pte = *ptep;
+ mask = _PAGE_PRESENT | _PAGE_USER;
+ if (write)
+ mask |= _PAGE_RW;
-/*
- * This mmap-allocator allocates new areas top-down from below the
- * stack's low limit (the base):
- *
- * Because we have an exclusive hugepage region which lies within the
- * normal user address space, we have to take special measures to make
- * non-huge mmap()s evade the hugepage reserved regions.
- */
-unsigned long
-arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
- const unsigned long len, const unsigned long pgoff,
- const unsigned long flags)
-{
- struct vm_area_struct *vma, *prev_vma;
- struct mm_struct *mm = current->mm;
- unsigned long base = mm->mmap_base, addr = addr0;
- unsigned long largest_hole = mm->cached_hole_size;
- int first_time = 1;
-
- /* requested length too big for entire address space */
- if (len > TASK_SIZE)
- return -ENOMEM;
+ if ((pte_val(pte) & mask) != mask)
+ return 0;
- /* dont allow allocations above current base */
- if (mm->free_area_cache > base)
- mm->free_area_cache = base;
-
- /* requesting a specific address */
- if (addr) {
- addr = PAGE_ALIGN(addr);
- vma = find_vma(mm, addr);
- if (TASK_SIZE - len >= addr &&
- (!vma || addr + len <= vma->vm_start)
- && !is_hugepage_only_range(mm, addr,len))
- return addr;
- }
+ /* hugepages are never "special" */
+ VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
- if (len <= largest_hole) {
- largest_hole = 0;
- mm->free_area_cache = base;
- }
-try_again:
- /* make sure it can fit in the remaining address space */
- if (mm->free_area_cache < len)
- goto fail;
+ refs = 0;
+ head = pte_page(pte);
- /* either no address requested or cant fit in requested address hole */
- addr = (mm->free_area_cache - len) & PAGE_MASK;
+ page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
do {
-hugepage_recheck:
- if (touches_hugepage_low_range(mm, addr, len)) {
- addr = (addr & ((~0) << SID_SHIFT)) - len;
- goto hugepage_recheck;
- } else if (touches_hugepage_high_range(mm, addr, len)) {
- addr = (addr & ((~0UL) << HTLB_AREA_SHIFT)) - len;
- goto hugepage_recheck;
- }
+ VM_BUG_ON(compound_head(page) != head);
+ pages[*nr] = page;
+ (*nr)++;
+ page++;
+ refs++;
+ } while (addr += PAGE_SIZE, addr != end);
+
+ if (!page_cache_add_speculative(head, refs)) {
+ *nr -= refs;
+ return 0;
+ }
- /*
- * Lookup failure means no vma is above this address,
- * i.e. return with success:
- */
- if (!(vma = find_vma_prev(mm, addr, &prev_vma)))
- return addr;
-
- /*
- * new region fits between prev_vma->vm_end and
- * vma->vm_start, use it:
- */
- if (addr+len <= vma->vm_start &&
- (!prev_vma || (addr >= prev_vma->vm_end))) {
- /* remember the address as a hint for next time */
- mm->cached_hole_size = largest_hole;
- return (mm->free_area_cache = addr);
- } else {
- /* pull free_area_cache down to the first hole */
- if (mm->free_area_cache == vma->vm_end) {
- mm->free_area_cache = vma->vm_start;
- mm->cached_hole_size = largest_hole;
- }
+ if (unlikely(pte_val(pte) != pte_val(*ptep))) {
+ /* Could be optimized better */
+ while (*nr) {
+ put_page(page);
+ (*nr)--;
}
-
- /* remember the largest hole we saw so far */
- if (addr + largest_hole < vma->vm_start)
- largest_hole = vma->vm_start - addr;
-
- /* try just below the current vma->vm_start */
- addr = vma->vm_start-len;
- } while (len <= vma->vm_start);
-
-fail:
- /*
- * if hint left us with no space for the requested
- * mapping then try again:
- */
- if (first_time) {
- mm->free_area_cache = base;
- largest_hole = 0;
- first_time = 0;
- goto try_again;
}
- /*
- * A failed mmap() very likely causes application failure,
- * so fall back to the bottom-up function here. This scenario
- * can happen with large stack limits and large mmap()
- * allocations.
- */
- mm->free_area_cache = TASK_UNMAPPED_BASE;
- mm->cached_hole_size = ~0UL;
- addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
- /*
- * Restore the topdown base:
- */
- mm->free_area_cache = base;
- mm->cached_hole_size = ~0UL;
- return addr;
+ return 1;
}
-static int htlb_check_hinted_area(unsigned long addr, unsigned long len)
+static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
+ unsigned long sz)
{
- struct vm_area_struct *vma;
-
- vma = find_vma(current->mm, addr);
- if (TASK_SIZE - len >= addr &&
- (!vma || ((addr + len) <= vma->vm_start)))
- return 0;
-
- return -ENOMEM;
+ unsigned long __boundary = (addr + sz) & ~(sz-1);
+ return (__boundary - 1 < end - 1) ? __boundary : end;
}
-static unsigned long htlb_get_low_area(unsigned long len, u16 segmask)
+int gup_hugepd(hugepd_t *hugepd, unsigned pdshift,
+ unsigned long addr, unsigned long end,
+ int write, struct page **pages, int *nr)
{
- unsigned long addr = 0;
- struct vm_area_struct *vma;
-
- vma = find_vma(current->mm, addr);
- while (addr + len <= 0x100000000UL) {
- BUG_ON(vma && (addr >= vma->vm_end)); /* invariant */
-
- if (! __within_hugepage_low_range(addr, len, segmask)) {
- addr = ALIGN(addr+1, 1<<SID_SHIFT);
- vma = find_vma(current->mm, addr);
- continue;
- }
+ pte_t *ptep;
+ unsigned long sz = 1UL << hugepd_shift(*hugepd);
+ unsigned long next;
- if (!vma || (addr + len) <= vma->vm_start)
- return addr;
- addr = ALIGN(vma->vm_end, HPAGE_SIZE);
- /* Depending on segmask this might not be a confirmed
- * hugepage region, so the ALIGN could have skipped
- * some VMAs */
- vma = find_vma(current->mm, addr);
- }
+ 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 = next, addr != end);
- return -ENOMEM;
+ return 1;
}
-static unsigned long htlb_get_high_area(unsigned long len, u16 areamask)
+unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+ unsigned long len, unsigned long pgoff,
+ unsigned long flags)
{
- unsigned long addr = 0x100000000UL;
- struct vm_area_struct *vma;
-
- vma = find_vma(current->mm, addr);
- while (addr + len <= TASK_SIZE_USER64) {
- BUG_ON(vma && (addr >= vma->vm_end)); /* invariant */
+ struct hstate *hstate = hstate_file(file);
+ int mmu_psize = shift_to_mmu_psize(huge_page_shift(hstate));
- if (! __within_hugepage_high_range(addr, len, areamask)) {
- addr = ALIGN(addr+1, 1UL<<HTLB_AREA_SHIFT);
- vma = find_vma(current->mm, addr);
- continue;
- }
+ return slice_get_unmapped_area(addr, len, flags, mmu_psize, 1, 0);
+}
- if (!vma || (addr + len) <= vma->vm_start)
- return addr;
- addr = ALIGN(vma->vm_end, HPAGE_SIZE);
- /* Depending on segmask this might not be a confirmed
- * hugepage region, so the ALIGN could have skipped
- * some VMAs */
- vma = find_vma(current->mm, addr);
- }
+unsigned long vma_mmu_pagesize(struct vm_area_struct *vma)
+{
+ unsigned int psize = get_slice_psize(vma->vm_mm, vma->vm_start);
- return -ENOMEM;
+ return 1UL << mmu_psize_to_shift(psize);
}
-unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
- unsigned long len, unsigned long pgoff,
- unsigned long flags)
+static int __init add_huge_page_size(unsigned long long size)
{
- int lastshift;
- u16 areamask, curareas;
+ int shift = __ffs(size);
+ int mmu_psize;
- if (HPAGE_SHIFT == 0)
- return -EINVAL;
- if (len & ~HPAGE_MASK)
+ /* 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;
- if (len > TASK_SIZE)
- return -ENOMEM;
- if (!cpu_has_feature(CPU_FTR_16M_PAGE))
+ if ((mmu_psize = shift_to_mmu_psize(shift)) < 0)
return -EINVAL;
- /* Paranoia, caller should have dealt with this */
- BUG_ON((addr + len) < addr);
+#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.
+ */
+ if (shift == PAGE_SHIFT_64K)
+ return -EINVAL;
+#endif /* CONFIG_SPU_FS_64K_LS */
- if (test_thread_flag(TIF_32BIT)) {
- curareas = current->mm->context.low_htlb_areas;
+ BUG_ON(mmu_psize_defs[mmu_psize].shift != shift);
- /* First see if we can use the hint address */
- if (addr && (htlb_check_hinted_area(addr, len) == 0)) {
- areamask = LOW_ESID_MASK(addr, len);
- if (open_low_hpage_areas(current->mm, areamask) == 0)
- return addr;
- }
+ /* Return if huge page size has already been setup */
+ if (size_to_hstate(size))
+ return 0;
- /* Next see if we can map in the existing low areas */
- addr = htlb_get_low_area(len, curareas);
- if (addr != -ENOMEM)
- return addr;
-
- /* Finally go looking for areas to open */
- lastshift = 0;
- for (areamask = LOW_ESID_MASK(0x100000000UL-len, len);
- ! lastshift; areamask >>=1) {
- if (areamask & 1)
- lastshift = 1;
-
- addr = htlb_get_low_area(len, curareas | areamask);
- if ((addr != -ENOMEM)
- && open_low_hpage_areas(current->mm, areamask) == 0)
- return addr;
- }
- } else {
- curareas = current->mm->context.high_htlb_areas;
-
- /* First see if we can use the hint address */
- /* We discourage 64-bit processes from doing hugepage
- * mappings below 4GB (must use MAP_FIXED) */
- if ((addr >= 0x100000000UL)
- && (htlb_check_hinted_area(addr, len) == 0)) {
- areamask = HTLB_AREA_MASK(addr, len);
- if (open_high_hpage_areas(current->mm, areamask) == 0)
- return addr;
- }
+ hugetlb_add_hstate(shift - PAGE_SHIFT);
- /* Next see if we can map in the existing high areas */
- addr = htlb_get_high_area(len, curareas);
- if (addr != -ENOMEM)
- return addr;
-
- /* Finally go looking for areas to open */
- lastshift = 0;
- for (areamask = HTLB_AREA_MASK(TASK_SIZE_USER64-len, len);
- ! lastshift; areamask >>=1) {
- if (areamask & 1)
- lastshift = 1;
-
- addr = htlb_get_high_area(len, curareas | areamask);
- if ((addr != -ENOMEM)
- && open_high_hpage_areas(current->mm, areamask) == 0)
- return addr;
- }
- }
- printk(KERN_DEBUG "hugetlb_get_unmapped_area() unable to open"
- " enough areas\n");
- return -ENOMEM;
+ return 0;
}
-/*
- * 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)
+static int __init hugepage_setup_sz(char *str)
{
- struct page *page;
- int i;
+ unsigned long long size;
- if (!pfn_valid(pte_pfn(pte)))
- return rflags;
+ size = memparse(str, &str);
- page = pte_page(pte);
+ if (add_huge_page_size(size) != 0)
+ printk(KERN_WARNING "Invalid huge page size specified(%llu)\n", size);
- /* page is dirty */
- if (!test_bit(PG_arch_1, &page->flags) && !PageReserved(page)) {
- if (trap == 0x400) {
- for (i = 0; i < (HPAGE_SIZE / PAGE_SIZE); i++)
- __flush_dcache_icache(page_address(page+i));
- set_bit(PG_arch_1, &page->flags);
- } else {
- rflags |= HPTE_R_N;
- }
- }
- return rflags;
+ return 1;
}
+__setup("hugepagesz=", hugepage_setup_sz);
-int hash_huge_page(struct mm_struct *mm, unsigned long access,
- unsigned long ea, unsigned long vsid, int local,
- unsigned long trap)
+static int __init hugetlbpage_init(void)
{
- pte_t *ptep;
- unsigned long old_pte, new_pte;
- unsigned long va, rflags, pa;
- long slot;
- int err = 1;
-
- ptep = huge_pte_offset(mm, ea);
-
- /* Search the Linux page table for a match with va */
- va = (vsid << 28) | (ea & 0x0fffffff);
-
- /*
- * If no pte found or not present, send the problem up to
- * do_page_fault
- */
- if (unlikely(!ptep || pte_none(*ptep)))
- goto out;
+ int psize;
- /*
- * 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.
- */
+ if (!cpu_has_feature(CPU_FTR_16M_PAGE))
+ return -ENODEV;
+ for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
+ unsigned shift;
+ unsigned pdshift;
- do {
- old_pte = pte_val(*ptep);
- if (old_pte & _PAGE_BUSY)
- goto out;
- new_pte = old_pte | _PAGE_BUSY |
- _PAGE_ACCESSED | _PAGE_HASHPTE;
- } 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);
- 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);
-
- /* 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, HPAGE_SHIFT);
- 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_huge_psize,
- local) == -1)
- old_pte &= ~_PAGE_HPTEFLAGS;
- }
+ if (!mmu_psize_defs[psize].shift)
+ continue;
- if (likely(!(old_pte & _PAGE_HASHPTE))) {
- unsigned long hash = hpt_hash(va, HPAGE_SHIFT);
- 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 */
- new_pte = (new_pte & ~_PAGE_HPTEFLAGS) | _PAGE_HASHPTE;
-
- /* Add in WIMG bits */
- /* XXX We should store these in the pte */
- /* --BenH: I think they are ... */
- rflags |= _PAGE_COHERENT;
-
- /* Insert into the hash table, primary slot */
- slot = ppc_md.hpte_insert(hpte_group, va, pa, rflags, 0,
- mmu_huge_psize);
-
- /* 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_huge_psize);
- if (slot == -1) {
- if (mftb() & 0x1)
- hpte_group = ((hash & htab_hash_mask) *
- HPTES_PER_GROUP)&~0x7UL;
-
- ppc_md.hpte_remove(hpte_group);
- goto repeat;
- }
- }
+ shift = mmu_psize_to_shift(psize);
- if (unlikely(slot == -2))
- panic("hash_huge_page: pte_insert failed\n");
+ if (add_huge_page_size(1ULL << shift) < 0)
+ continue;
- new_pte |= (slot << 12) & (_PAGE_F_SECOND | _PAGE_F_GIX);
+ 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);
}
- /*
- * No need to use ldarx/stdcx here
+ /* Set default large page size. Currently, we pick 16M or 1M
+ * depending on what is available
*/
- *ptep = __pte(new_pte & ~_PAGE_BUSY);
+ 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;
- err = 0;
-
- out:
- return err;
+ return 0;
}
-static void zero_ctor(void *addr, struct kmem_cache *cache, unsigned long flags)
-{
- memset(addr, 0, kmem_cache_size(cache));
-}
+module_init(hugetlbpage_init);
-static int __init hugetlbpage_init(void)
+void flush_dcache_icache_hugepage(struct page *page)
{
- if (!cpu_has_feature(CPU_FTR_16M_PAGE))
- return -ENODEV;
+ int i;
- huge_pgtable_cache = kmem_cache_create("hugepte_cache",
- HUGEPTE_TABLE_SIZE,
- HUGEPTE_TABLE_SIZE,
- SLAB_HWCACHE_ALIGN |
- SLAB_MUST_HWCACHE_ALIGN,
- zero_ctor, NULL);
- if (! huge_pgtable_cache)
- panic("hugetlbpage_init(): could not create hugepte cache\n");
+ BUG_ON(!PageCompound(page));
- return 0;
+ for (i = 0; i < (1UL << compound_order(page)); i++)
+ __flush_dcache_icache(page_address(page+i));
}
-
-module_init(hugetlbpage_init);