/*
* SPARC64 Huge TLB page support.
*
- * Copyright (C) 2002, 2003 David S. Miller (davem@redhat.com)
+ * Copyright (C) 2002, 2003, 2006 David S. Miller (davem@davemloft.net)
*/
#include <linux/config.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include <asm/cacheflush.h>
+#include <asm/mmu_context.h>
-static pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
+/* Slightly simplified from the non-hugepage variant because by
+ * definition we don't have to worry about any page coloring stuff
+ */
+#define VA_EXCLUDE_START (0x0000080000000000UL - (1UL << 32UL))
+#define VA_EXCLUDE_END (0xfffff80000000000UL + (1UL << 32UL))
+
+static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *filp,
+ unsigned long addr,
+ unsigned long len,
+ unsigned long pgoff,
+ unsigned long flags)
+{
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct * vma;
+ unsigned long task_size = TASK_SIZE;
+ unsigned long start_addr;
+
+ if (test_thread_flag(TIF_32BIT))
+ task_size = STACK_TOP32;
+ if (unlikely(len >= VA_EXCLUDE_START))
+ return -ENOMEM;
+
+ 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;
+ }
+
+ task_size -= len;
+
+full_search:
+ addr = ALIGN(addr, HPAGE_SIZE);
+
+ for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
+ /* At this point: (!vma || addr < vma->vm_end). */
+ if (addr < VA_EXCLUDE_START &&
+ (addr + len) >= VA_EXCLUDE_START) {
+ addr = VA_EXCLUDE_END;
+ vma = find_vma(mm, VA_EXCLUDE_END);
+ }
+ if (unlikely(task_size < addr)) {
+ if (start_addr != TASK_UNMAPPED_BASE) {
+ start_addr = addr = TASK_UNMAPPED_BASE;
+ mm->cached_hole_size = 0;
+ goto full_search;
+ }
+ return -ENOMEM;
+ }
+ if (likely(!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 = ALIGN(vma->vm_end, HPAGE_SIZE);
+ }
+}
+
+static unsigned long
+hugetlb_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;
+ struct mm_struct *mm = current->mm;
+ unsigned long addr = addr0;
+
+ /* This should only ever run for 32-bit processes. */
+ BUG_ON(!test_thread_flag(TIF_32BIT));
+
+ /* check if free_area_cache is useful for us */
+ if (len <= mm->cached_hole_size) {
+ mm->cached_hole_size = 0;
+ mm->free_area_cache = mm->mmap_base;
+ }
+
+ /* either no address requested or can't fit in requested address hole */
+ addr = mm->free_area_cache & HPAGE_MASK;
+
+ /* make sure it can fit in the remaining address space */
+ if (likely(addr > len)) {
+ vma = find_vma(mm, addr-len);
+ if (!vma || addr <= vma->vm_start) {
+ /* remember the address as a hint for next time */
+ return (mm->free_area_cache = addr-len);
+ }
+ }
+
+ if (unlikely(mm->mmap_base < len))
+ goto bottomup;
+
+ addr = (mm->mmap_base-len) & HPAGE_MASK;
+
+ do {
+ /*
+ * Lookup failure means no vma is above this address,
+ * else if new region fits below vma->vm_start,
+ * return with success:
+ */
+ vma = find_vma(mm, addr);
+ if (likely(!vma || addr+len <= vma->vm_start)) {
+ /* remember the address as a hint for next time */
+ return (mm->free_area_cache = addr);
+ }
+
+ /* remember the largest hole we saw so far */
+ if (addr + mm->cached_hole_size < vma->vm_start)
+ mm->cached_hole_size = vma->vm_start - addr;
+
+ /* try just below the current vma->vm_start */
+ addr = (vma->vm_start-len) & HPAGE_MASK;
+ } while (likely(len < vma->vm_start));
+
+bottomup:
+ /*
+ * 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->cached_hole_size = ~0UL;
+ mm->free_area_cache = TASK_UNMAPPED_BASE;
+ addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
+ /*
+ * Restore the topdown base:
+ */
+ mm->free_area_cache = mm->mmap_base;
+ mm->cached_hole_size = ~0UL;
+
+ return addr;
+}
+
+unsigned long
+hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+ unsigned long len, unsigned long pgoff, unsigned long flags)
+{
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma;
+ unsigned long task_size = TASK_SIZE;
+
+ if (test_thread_flag(TIF_32BIT))
+ task_size = STACK_TOP32;
+
+ if (len & ~HPAGE_MASK)
+ return -EINVAL;
+ if (len > task_size)
+ return -ENOMEM;
+
+ if (addr) {
+ addr = ALIGN(addr, HPAGE_SIZE);
+ vma = find_vma(mm, addr);
+ if (task_size - len >= addr &&
+ (!vma || addr + len <= vma->vm_start))
+ return addr;
+ }
+ if (mm->get_unmapped_area == arch_get_unmapped_area)
+ return hugetlb_get_unmapped_area_bottomup(file, addr, len,
+ pgoff, flags);
+ else
+ return hugetlb_get_unmapped_area_topdown(file, addr, len,
+ pgoff, flags);
+}
+
+pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
+ pud_t *pud;
pmd_t *pmd;
pte_t *pte = NULL;
+ /* We must align the address, because our caller will run
+ * set_huge_pte_at() on whatever we return, which writes out
+ * all of the sub-ptes for the hugepage range. So we have
+ * to give it the first such sub-pte.
+ */
+ addr &= HPAGE_MASK;
+
pgd = pgd_offset(mm, addr);
- if (pgd) {
- pmd = pmd_alloc(mm, pgd, addr);
+ pud = pud_alloc(mm, pgd, addr);
+ if (pud) {
+ pmd = pmd_alloc(mm, pud, addr);
if (pmd)
pte = pte_alloc_map(mm, pmd, addr);
}
return pte;
}
-static pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
+ pud_t *pud;
pmd_t *pmd;
pte_t *pte = NULL;
+ addr &= HPAGE_MASK;
+
pgd = pgd_offset(mm, addr);
- if (pgd) {
- pmd = pmd_offset(pgd, addr);
- if (pmd)
- pte = pte_offset_map(pmd, addr);
+ if (!pgd_none(*pgd)) {
+ pud = pud_offset(pgd, addr);
+ if (!pud_none(*pud)) {
+ pmd = pmd_offset(pud, addr);
+ if (!pmd_none(*pmd))
+ pte = pte_offset_map(pmd, addr);
+ }
}
return pte;
}
-#define mk_pte_huge(entry) do { pte_val(entry) |= _PAGE_SZHUGE; } while (0)
-
-static void set_huge_pte(struct mm_struct *mm, struct vm_area_struct *vma,
- struct page *page, pte_t * page_table, int write_access)
+void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep, pte_t entry)
{
- unsigned long i;
- pte_t entry;
+ int i;
- mm->rss += (HPAGE_SIZE / PAGE_SIZE);
-
- if (write_access)
- entry = pte_mkwrite(pte_mkdirty(mk_pte(page,
- vma->vm_page_prot)));
- else
- entry = pte_wrprotect(mk_pte(page, vma->vm_page_prot));
- entry = pte_mkyoung(entry);
- mk_pte_huge(entry);
+ if (!pte_present(*ptep) && pte_present(entry))
+ mm->context.huge_pte_count++;
for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
- set_pte(page_table, entry);
- page_table++;
-
+ set_pte_at(mm, addr, ptep, entry);
+ ptep++;
+ addr += PAGE_SIZE;
pte_val(entry) += PAGE_SIZE;
}
}
-/*
- * This function checks for proper alignment of input addr and len parameters.
- */
-int is_aligned_hugepage_range(unsigned long addr, unsigned long len)
-{
- if (len & ~HPAGE_MASK)
- return -EINVAL;
- if (addr & ~HPAGE_MASK)
- return -EINVAL;
- return 0;
-}
-
-int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
- struct vm_area_struct *vma)
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+ pte_t *ptep)
{
- pte_t *src_pte, *dst_pte, entry;
- struct page *ptepage;
- unsigned long addr = vma->vm_start;
- unsigned long end = vma->vm_end;
+ pte_t entry;
int i;
- while (addr < end) {
- dst_pte = huge_pte_alloc(dst, addr);
- if (!dst_pte)
- goto nomem;
- src_pte = huge_pte_offset(src, addr);
- BUG_ON(!src_pte || pte_none(*src_pte));
- entry = *src_pte;
- ptepage = pte_page(entry);
- get_page(ptepage);
- for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
- set_pte(dst_pte, entry);
- pte_val(entry) += PAGE_SIZE;
- dst_pte++;
- }
- dst->rss += (HPAGE_SIZE / PAGE_SIZE);
- addr += HPAGE_SIZE;
- }
- return 0;
-
-nomem:
- return -ENOMEM;
-}
-
-int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
- struct page **pages, struct vm_area_struct **vmas,
- unsigned long *position, int *length, int i)
-{
- unsigned long vaddr = *position;
- int remainder = *length;
-
- WARN_ON(!is_vm_hugetlb_page(vma));
-
- while (vaddr < vma->vm_end && remainder) {
- if (pages) {
- pte_t *pte;
- struct page *page;
+ entry = *ptep;
+ if (pte_present(entry))
+ mm->context.huge_pte_count--;
- pte = huge_pte_offset(mm, vaddr);
-
- /* hugetlb should be locked, and hence, prefaulted */
- BUG_ON(!pte || pte_none(*pte));
-
- page = pte_page(*pte);
-
- WARN_ON(!PageCompound(page));
-
- get_page(page);
- pages[i] = page;
- }
-
- if (vmas)
- vmas[i] = vma;
-
- vaddr += PAGE_SIZE;
- --remainder;
- ++i;
+ for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
+ pte_clear(mm, addr, ptep);
+ addr += PAGE_SIZE;
+ ptep++;
}
- *length = remainder;
- *position = vaddr;
-
- return i;
+ return entry;
}
struct page *follow_huge_addr(struct mm_struct *mm,
return NULL;
}
-void unmap_hugepage_range(struct vm_area_struct *vma,
- unsigned long start, unsigned long end)
+static void context_reload(void *__data)
{
- struct mm_struct *mm = vma->vm_mm;
- unsigned long address;
- pte_t *pte;
- struct page *page;
- int i;
+ struct mm_struct *mm = __data;
- BUG_ON(start & (HPAGE_SIZE - 1));
- BUG_ON(end & (HPAGE_SIZE - 1));
-
- for (address = start; address < end; address += HPAGE_SIZE) {
- pte = huge_pte_offset(mm, address);
- BUG_ON(!pte);
- if (pte_none(*pte))
- continue;
- page = pte_page(*pte);
- put_page(page);
- for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
- pte_clear(pte);
- pte++;
- }
- }
- mm->rss -= (end - start) >> PAGE_SHIFT;
- flush_tlb_range(vma, start, end);
+ if (mm == current->mm)
+ load_secondary_context(mm);
}
-int hugetlb_prefault(struct address_space *mapping, struct vm_area_struct *vma)
+void hugetlb_prefault_arch_hook(struct mm_struct *mm)
{
- struct mm_struct *mm = current->mm;
- unsigned long addr;
- int ret = 0;
-
- BUG_ON(vma->vm_start & ~HPAGE_MASK);
- BUG_ON(vma->vm_end & ~HPAGE_MASK);
-
- spin_lock(&mm->page_table_lock);
- for (addr = vma->vm_start; addr < vma->vm_end; addr += HPAGE_SIZE) {
- unsigned long idx;
- pte_t *pte = huge_pte_alloc(mm, addr);
- struct page *page;
-
- if (!pte) {
- ret = -ENOMEM;
- goto out;
- }
- if (!pte_none(*pte))
- continue;
-
- idx = ((addr - vma->vm_start) >> HPAGE_SHIFT)
- + (vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT));
- page = find_get_page(mapping, idx);
- if (!page) {
- /* charge the fs quota first */
- if (hugetlb_get_quota(mapping)) {
- ret = -ENOMEM;
- goto out;
- }
- page = alloc_huge_page();
- if (!page) {
- hugetlb_put_quota(mapping);
- ret = -ENOMEM;
- goto out;
- }
- ret = add_to_page_cache(page, mapping, idx, GFP_ATOMIC);
- unlock_page(page);
- if (ret) {
- hugetlb_put_quota(mapping);
- free_huge_page(page);
- goto out;
- }
+ struct tsb_config *tp = &mm->context.tsb_block[MM_TSB_HUGE];
+
+ if (likely(tp->tsb != NULL))
+ return;
+
+ tsb_grow(mm, MM_TSB_HUGE, 0);
+ tsb_context_switch(mm);
+ smp_tsb_sync(mm);
+
+ /* On UltraSPARC-III+ and later, configure the second half of
+ * the Data-TLB for huge pages.
+ */
+ if (tlb_type == cheetah_plus) {
+ unsigned long ctx;
+
+ spin_lock(&ctx_alloc_lock);
+ ctx = mm->context.sparc64_ctx_val;
+ ctx &= ~CTX_PGSZ_MASK;
+ ctx |= CTX_PGSZ_BASE << CTX_PGSZ0_SHIFT;
+ ctx |= CTX_PGSZ_HUGE << CTX_PGSZ1_SHIFT;
+
+ if (ctx != mm->context.sparc64_ctx_val) {
+ /* When changing the page size fields, we
+ * must perform a context flush so that no
+ * stale entries match. This flush must
+ * occur with the original context register
+ * settings.
+ */
+ do_flush_tlb_mm(mm);
+
+ /* Reload the context register of all processors
+ * also executing in this address space.
+ */
+ mm->context.sparc64_ctx_val = ctx;
+ on_each_cpu(context_reload, mm, 0, 0);
}
- set_huge_pte(mm, vma, page, pte, vma->vm_flags & VM_WRITE);
+ spin_unlock(&ctx_alloc_lock);
}
-out:
- spin_unlock(&mm->page_table_lock);
- return ret;
}