[PATCH] Hugepage consolidation

A lot of the code in arch/*/mm/hugetlbpage.c is quite similar.  This patch
attempts to consolidate a lot of the code across the arch's, putting the
combined version in mm/hugetlb.c.  There are a couple of uglyish hacks in
order to covert all the hugepage archs, but the result is a very large
reduction in the total amount of code.  It also means things like hugepage
lazy allocation could be implemented in one place, instead of six.

Tested, at least a little, on ppc64, i386 and x86_64.

Notes:
	- this patch changes the meaning of set_huge_pte() to be more
	  analagous to set_pte()
	- does SH4 need s special huge_ptep_get_and_clear()??

Acked-by: William Lee Irwin <wli@holomorphy.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

19 files changed, 300 insertions, 850 deletions

diff --git a/arch/i386/mm/hugetlbpage.c b/arch/i386/mm/hugetlbpage.c
index 171fc925e1e4..5aa06001a4bd 100644
--- a/arch/i386/mm/hugetlbpage.c
+++ b/arch/i386/mm/hugetlbpage.c
@@ -18,7 +18,7 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 
-static pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
+pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
 {
         pgd_t *pgd;
         pud_t *pud;
@@ -30,7 +30,7 @@ static pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long addr)
         return (pte_t *) pmd;
 }
 
-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;
@@ -42,21 +42,6 @@ static pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
         return (pte_t *) pmd;
 }
 
-static void set_huge_pte(struct mm_struct *mm, struct vm_area_struct *vma, struct page *page, pte_t * page_table, int write_access)
-{
-        pte_t entry;
-
-        add_mm_counter(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);
-        set_pte(page_table, entry);
-}
-
 /*
  * This function checks for proper alignment of input addr and len parameters.
  */
@@ -69,77 +54,6 @@ int is_aligned_hugepage_range(unsigned long addr, unsigned long len)
         return 0;
 }
 
-int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
-                        struct vm_area_struct *vma)
-{
-        pte_t *src_pte, *dst_pte, entry;
-        struct page *ptepage;
-        unsigned long addr = vma->vm_start;
-        unsigned long end = vma->vm_end;
-
-        while (addr < end) {
-                dst_pte = huge_pte_alloc(dst, addr);
-                if (!dst_pte)
-                        goto nomem;
-                src_pte = huge_pte_offset(src, addr);
-                entry = *src_pte;
-                ptepage = pte_page(entry);
-                get_page(ptepage);
-                set_pte(dst_pte, entry);
-                add_mm_counter(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 vpfn, vaddr = *position;
-        int remainder = *length;
-
-        WARN_ON(!is_vm_hugetlb_page(vma));
-
-        vpfn = vaddr/PAGE_SIZE;
-        while (vaddr < vma->vm_end && remainder) {
-
-                if (pages) {
-                        pte_t *pte;
-                        struct page *page;
-
-                        pte = huge_pte_offset(mm, vaddr);
-
-                        /* hugetlb should be locked, and hence, prefaulted */
-                        WARN_ON(!pte || pte_none(*pte));
-
-                        page = &pte_page(*pte)[vpfn % (HPAGE_SIZE/PAGE_SIZE)];
-
-                        WARN_ON(!PageCompound(page));
-
-                        get_page(page);
-                        pages[i] = page;
-                }
-
-                if (vmas)
-                        vmas[i] = vma;
-
-                vaddr += PAGE_SIZE;
-                ++vpfn;
-                --remainder;
-                ++i;
-        }
-
-        *length = remainder;
-        *position = vaddr;
-
-        return i;
-}
-
 #if 0   /* This is just for testing */
 struct page *
 follow_huge_addr(struct mm_struct *mm, unsigned long address, int write)
@@ -204,83 +118,15 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 }
 #endif
 
-void unmap_hugepage_range(struct vm_area_struct *vma,
-                unsigned long start, unsigned long end)
+void hugetlb_clean_stale_pgtable(pte_t *pte)
 {
-        struct mm_struct *mm = vma->vm_mm;
-        unsigned long address;
-        pte_t pte, *ptep;
+        pmd_t *pmd = (pmd_t *) pte;
         struct page *page;
 
-        BUG_ON(start & (HPAGE_SIZE - 1));
-        BUG_ON(end & (HPAGE_SIZE - 1));
-
-        for (address = start; address < end; address += HPAGE_SIZE) {
-                ptep = huge_pte_offset(mm, address);
-                if (!ptep)
-                        continue;
-                pte = ptep_get_and_clear(mm, address, ptep);
-                if (pte_none(pte))
-                        continue;
-                page = pte_page(pte);
-                put_page(page);
-        }
-        add_mm_counter(mm ,rss, -((end - start) >> PAGE_SHIFT));
-        flush_tlb_range(vma, start, end);
-}
-
-int hugetlb_prefault(struct address_space *mapping, struct vm_area_struct *vma)
-{
-        struct mm_struct *mm = current->mm;
-        unsigned long addr;
-        int ret = 0;
-
+        page = pmd_page(*pmd);
+        pmd_clear(pmd);
+        dec_page_state(nr_page_table_pages);
+        page_cache_release(page);