Prefetch ptes a line ahead. Worth 25% on ia64 when doing big forks.

Index: linux-2.6/include/asm-generic/pgtable.h
===================================================================
--- linux-2.6.orig/include/asm-generic/pgtable.h
+++ linux-2.6/include/asm-generic/pgtable.h
@@ -196,6 +196,33 @@ static inline void ptep_set_wrprotect(st
 })
 #endif
 
+#ifndef __HAVE_ARCH_PTE_PREFETCH
+#define PTES_PER_LINE (L1_CACHE_BYTES / sizeof(pte_t))
+#define PTE_LINE_MASK (~(PTES_PER_LINE - 1))
+#define ADDR_PER_LINE (PTES_PER_LINE << PAGE_SHIFT)
+#define ADDR_LINE_MASK (~(ADDR_PER_LINE - 1))
+
+#define pte_prefetch(pte, addr, end)					\
+({									\
+	unsigned long __nextline = ((addr) + ADDR_PER_LINE) & ADDR_LINE_MASK; \
+	if (__nextline < (end))						\
+		prefetch(pte + PTES_PER_LINE);				\
+})
+
+#define pte_prefetch_start(pte, addr, end)				\
+({									\
+ 	prefetch(pte);							\
+ 	pte_prefetch(pte, addr, end);					\
+})
+
+#define pte_prefetch_next(pte, addr, end)				\
+({									\
+	unsigned long __addr = (addr);					\
+	if (!(__addr & ~ADDR_LINE_MASK)) /* We hit a new cacheline */	\
+		pte_prefetch(pte, __addr, end);				\
+})
+#endif
+
 #ifndef __ASSEMBLY__
 /*
  * When walking page tables, we usually want to skip any p?d_none entries;
Index: linux-2.6/mm/memory.c
===================================================================
--- linux-2.6.orig/mm/memory.c
+++ linux-2.6/mm/memory.c
@@ -437,6 +437,8 @@ again:
 	if (!dst_pte)
 		return -ENOMEM;
 	src_pte = pte_offset_map_nested(src_pmd, addr);
+	pte_prefetch_start(src_pte, addr, end);
+
 	src_ptl = pte_lockptr(src_mm, src_pmd);
 	spin_lock(src_ptl);
 
@@ -458,7 +460,8 @@ again:
 		}
 		copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, vma, addr, rss);
 		progress += 8;
-	} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
+	} while (dst_pte++, src_pte++, addr += PAGE_SIZE,
+			pte_prefetch_next(src_pte, addr, end), addr != end);
 
 	spin_unlock(src_ptl);
 	pte_unmap_nested(src_pte - 1);
@@ -561,6 +564,7 @@ static void zap_pte_range(struct mmu_gat
 	int anon_rss = 0;
 
 	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+	pte_prefetch_start(pte, addr, end);
 	do {
 		pte_t ptent = *pte;
 		if (pte_none(ptent))
@@ -624,7 +628,8 @@ static void zap_pte_range(struct mmu_gat
 		if (!pte_file(ptent))
 			free_swap_and_cache(pte_to_swp_entry(ptent));
 		pte_clear_full(mm, addr, pte, tlb->fullmm);
-	} while (pte++, addr += PAGE_SIZE, addr != end);
+	} while (pte++, addr += PAGE_SIZE,
+			pte_prefetch_next(pte, addr, end), addr != end);
 
 	add_mm_rss(mm, file_rss, anon_rss);
 	pte_unmap_unlock(pte - 1, ptl);