summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
authorHugh Dickins <hugh@veritas.com>2005-04-19 13:29:15 -0700
committerLinus Torvalds <torvalds@ppc970.osdl.org.(none)>2005-04-19 13:29:15 -0700
commite0da382c92626ad1d7f4b7527d19b80104d67a83 (patch)
treeb3f455518c286ee14cb2755ced8808487bca7911 /arch
parent9f6c6fc505560465be0964eb4da1b6ca97bd3951 (diff)
[PATCH] freepgt: free_pgtables use vma list
Recent woes with some arches needing their own pgd_addr_end macro; and 4-level clear_page_range regression since 2.6.10's clear_page_tables; and its long-standing well-known inefficiency in searching throughout the higher-level page tables for those few entries to clear and free: all can be blamed on ignoring the list of vmas when we free page tables. Replace exit_mmap's clear_page_range of the total user address space by free_pgtables operating on the mm's vma list; unmap_region use it in the same way, giving floor and ceiling beyond which it may not free tables. This brings lmbench fork/exec/sh numbers back to 2.6.10 (unless preempt is enabled, in which case latency fixes spoil unmap_vmas throughput). Beware: the do_mmap_pgoff driver failure case must now use unmap_region instead of zap_page_range, since a page table might have been allocated, and can only be freed while it is touched by some vma. Move free_pgtables from mmap.c to memory.c, where its lower levels are adapted from the clear_page_range levels. (Most of free_pgtables' old code was actually for a non-existent case, prev not properly set up, dating from before hch gave us split_vma.) Pass mmu_gather** in the public interfaces, since we might want to add latency lockdrops later; but no attempt to do so yet, going by vma should itself reduce latency. But what if is_hugepage_only_range? Those ia64 and ppc64 cases need careful examination: put that off until a later patch of the series. What of x86_64's 32bit vdso page __map_syscall32 maps outside any vma? And the range to sparc64's flush_tlb_pgtables? It's less clear to me now that we need to do more than is done here - every PMD_SIZE ever occupied will be flushed, do we really have to flush every PGDIR_SIZE ever partially occupied? A shame to complicate it unnecessarily. Special thanks to David Miller for time spent repairing my ceilings. Signed-off-by: Hugh Dickins <hugh@veritas.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
Diffstat (limited to 'arch')
-rw-r--r--arch/i386/mm/pgtable.c2
-rw-r--r--arch/ia64/mm/hugetlbpage.c37
2 files changed, 3 insertions, 36 deletions
diff --git a/arch/i386/mm/pgtable.c b/arch/i386/mm/pgtable.c
index 0742d54f8bb0..dd81479ff88a 100644
--- a/arch/i386/mm/pgtable.c
+++ b/arch/i386/mm/pgtable.c
@@ -255,6 +255,6 @@ void pgd_free(pgd_t *pgd)
if (PTRS_PER_PMD > 1)
for (i = 0; i < USER_PTRS_PER_PGD; ++i)
kmem_cache_free(pmd_cache, (void *)__va(pgd_val(pgd[i])-1));
- /* in the non-PAE case, clear_page_range() clears user pgd entries */
+ /* in the non-PAE case, free_pgtables() clears user pgd entries */
kmem_cache_free(pgd_cache, pgd);
}
diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c
index 40ad8328ffd5..626258ae9742 100644
--- a/arch/ia64/mm/hugetlbpage.c
+++ b/arch/ia64/mm/hugetlbpage.c
@@ -187,45 +187,12 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int wri
}
/*
- * Same as generic free_pgtables(), except constant PGDIR_* and pgd_offset
- * are hugetlb region specific.
+ * Do nothing, until we've worked out what to do! To allow build, we
+ * must remove reference to clear_page_range since it no longer exists.
*/
void hugetlb_free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *prev,
unsigned long start, unsigned long end)
{
- unsigned long first = start & HUGETLB_PGDIR_MASK;
- unsigned long last = end + HUGETLB_PGDIR_SIZE - 1;
- struct mm_struct *mm = tlb->mm;
-
- if (!prev) {
- prev = mm->mmap;
- if (!prev)
- goto no_mmaps;
- if (prev->vm_end > start) {
- if (last > prev->vm_start)
- last = prev->vm_start;
- goto no_mmaps;
- }
- }
- for (;;) {
- struct vm_area_struct *next = prev->vm_next;
-
- if (next) {
- if (next->vm_start < start) {
- prev = next;
- continue;
- }
- if (last > next->vm_start)
- last = next->vm_start;
- }
- if (prev->vm_end > first)
- first = prev->vm_end;
- break;
- }
-no_mmaps:
- if (last < first) /* for arches with discontiguous pgd indices */
- return;
- clear_page_range(tlb, first, last);
}
void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)