Re: [PATCH 1/5] freepgt: free_pgtables use vma list

[Nick Piggin]

Andrew Morton wrote:
> With these six patches the ppc64 is hitting the BUG in exit_mmap():
>
>         BUG_ON(mm->nr_ptes);    /* This is just debugging */
>
> fairly early in boot.

No doubt Hugh will have this fixed before long... but if you
have time to spare, you may just try hitting it on the head
and making it a bit dumber. It might help show where the problem
is.

- don't span multiple vmas
- don't be so smart about avoiding unfreeable regions

I dunno. Maybe it won't help at all. Maybe it will make things
worse :P


Index: linux-2.6/mm/memory.c
===================================================================
--- linux-2.6.orig/mm/memory.c	2005-03-22 23:04:34.000000000 +1100
+++ linux-2.6/mm/memory.c	2005-03-22 23:11:31.000000000 +1100
@@ -110,13 +110,18 @@ void pmd_clear_bad(pmd_t *pmd)
  * Note: this doesn't free the actual pages themselves. That
  * has been handled earlier when unmapping all the memory regions.
  */
-static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd)
+static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
+				unsigned long addr, unsigned long end,
+				unsigned long floor, unsigned long ceiling)
 {
-	struct page *page = pmd_page(*pmd);
-	pmd_clear(pmd);
-	pte_free_tlb(tlb, page);
-	dec_page_state(nr_page_table_pages);
-	tlb->mm->nr_ptes--;
+	if (((addr & PMD_MASK) >= floor)
+			&& (end - 1 <= (ceiling & PMD_MASK) - 1)) {
+		struct page *page = pmd_page(*pmd);
+		pmd_clear(pmd);
+		pte_free_tlb(tlb, page);
+		dec_page_state(nr_page_table_pages);
+		tlb->mm->nr_ptes--;
+	}
 }
 
 static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
@@ -133,7 +138,7 @@ static inline void free_pmd_range(struct
 		next = pmd_addr_end(addr, end);
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
-		free_pte_range(tlb, pmd);
+		free_pte_range(tlb, pmd, addr, end, floor, ceiling);
 	} while (pmd++, addr = next, addr != end);
 
 	start &= PUD_MASK;
@@ -190,18 +195,6 @@ void free_pgd_range(struct mmu_gather **
 	unsigned long next;
 	unsigned long start;
 
-	addr &= PMD_MASK;
-	if (addr < floor) {
-		addr += PMD_SIZE;
-		if (!addr)
-			return;
-	}
-	ceiling &= PMD_MASK;
-	if (end - 1 > ceiling - 1)
-		end -= PMD_SIZE;
-	if (addr > end - 1)
-		return;
-
 	start = addr;
 	pgd = pgd_offset((*tlb)->mm, addr);
 	do {
@@ -226,14 +219,6 @@ void free_pgtables(struct mmu_gather **t
 			hugetlb_free_pgd_range(tlb, addr, vma->vm_end,
 				floor, next? next->vm_start: ceiling);
 		} else {
-			/*
-			 * Optimization: gather nearby vmas into one call down
-			 */
-			while (next && next->vm_start <= vma->vm_end + PMD_SIZE
-			&& !is_hugepage_only_range(next->vm_start, HPAGE_SIZE)){
-				vma = next;
-				next = vma->vm_next;
-			}
 			free_pgd_range(tlb, addr, vma->vm_end,
 				floor, next? next->vm_start: ceiling);
 		}