[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>

1 files changed, 24 insertions, 171 deletions

diff --git a/arch/sparc64/mm/hugetlbpage.c b/arch/sparc64/mm/hugetlbpage.c
index 5a1f831..625cbb3 100644
--- a/arch/sparc64/mm/hugetlbpage.c
+++ b/arch/sparc64/mm/hugetlbpage.c
@@ -22,7 +22,7 @@
 #include <asm/cacheflush.h>
 #include <asm/mmu_context.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;
@@ -41,7 +41,7 @@ static pte_t *huge_pte_alloc(struct mm_struct *mm, unsigned long 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;
@@ -62,30 +62,34 @@ static pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr)
 
 #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,
-			 unsigned long addr,
-			 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;
+
+	for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
+		set_pte_at(mm, addr, ptep, entry);
+		ptep++;
+		addr += PAGE_SIZE;
+		pte_val(entry) += PAGE_SIZE;
+	}
+}
 
-	add_mm_counter(mm, rss, HPAGE_SIZE / PAGE_SIZE);
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep)
+{
+	pte_t entry;
+	int i;
 
-	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);
+	entry = *ptep;
 
 	for (i = 0; i < (1 << HUGETLB_PAGE_ORDER); i++) {
-		set_pte_at(mm, addr, page_table, entry);
-		page_table++;
+		pte_clear(mm, addr, ptep);
 		addr += PAGE_SIZE;
-
-		pte_val(entry) += PAGE_SIZE;
+		ptep++;
 	}
+
+	return entry;
 }
 
 /*
@@ -100,79 +104,6 @@ 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;
-	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_at(dst, addr, dst_pte, entry);
-			pte_val(entry) += PAGE_SIZE;
-			dst_pte++;
-			addr += PAGE_SIZE;
-		}
-		add_mm_counter(dst, rss, HPAGE_SIZE / PAGE_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;
-
-			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;
-	}
-
-	*length = remainder;
-	*position = vaddr;
-
-	return i;
-}
-
 struct page *follow_huge_addr(struct mm_struct *mm,
 			      unsigned long address, int write)
 {
@@ -190,34 +121,6 @@ struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 	return NULL;
 }
 
-void unmap_hugepage_range(struct vm_area_struct *vma,
-			  unsigned long start, unsigned long end)
-{
-	struct mm_struct *mm = vma->vm_mm;
-	unsigned long address;
-	pte_t *pte;
-	struct page *page;
-	int i;
-
-	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(mm, address+(i*PAGE_SIZE), pte);
-			pte++;
-		}
-	}
-	add_mm_counter(mm, rss, -((end - start) >> PAGE_SHIFT));
-	flush_tlb_range(vma, start, end);
-}
-
 static void context_reload(void *__data)
 {
 	struct mm_struct *mm = __data;
@@ -226,12 +129,8 @@ static void context_reload(void *__data)
 		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;
-
 	/* On UltraSPARC-III+ and later, configure the second half of
 	 * the Data-TLB for huge pages.
 	 */
@@ -261,50 +160,4 @@ int hugetlb_prefault(struct address_space *mapping, struct vm_area_struct *vma)
 		}
 		spin_unlock(&ctx_alloc_lock);
 	}
-
-	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);
-			if (! ret) {
-				unlock_page(page);
-			} else {
-				hugetlb_put_quota(mapping);
-				free_huge_page(page);
-				goto out;
-			}
-		}
-		set_huge_pte(mm, vma, addr, page, pte, vma->vm_flags & VM_WRITE);
-	}
-out:
-	spin_unlock(&mm->page_table_lock);
-	return ret;
 }