summaryrefslogtreecommitdiff
path: root/mm/mmap.c
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 /mm/mmap.c
parent9f6c6fc505560465be0964eb4da1b6ca97bd3951 (diff)
downloadlwn-e0da382c92626ad1d7f4b7527d19b80104d67a83.tar.gz
lwn-e0da382c92626ad1d7f4b7527d19b80104d67a83.zip
[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 'mm/mmap.c')
-rw-r--r--mm/mmap.c102
1 files changed, 21 insertions, 81 deletions
diff --git a/mm/mmap.c b/mm/mmap.c
index a95ebda27446..926d03015471 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -29,6 +29,10 @@
#include <asm/cacheflush.h>
#include <asm/tlb.h>
+static void unmap_region(struct mm_struct *mm,
+ struct vm_area_struct *vma, struct vm_area_struct *prev,
+ unsigned long start, unsigned long end);
+
/*
* WARNING: the debugging will use recursive algorithms so never enable this
* unless you know what you are doing.
@@ -1129,7 +1133,8 @@ unmap_and_free_vma:
fput(file);
/* Undo any partial mapping done by a device driver. */
- zap_page_range(vma, vma->vm_start, vma->vm_end - vma->vm_start, NULL);
+ unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end);
+ charged = 0;
free_vma:
kmem_cache_free(vm_area_cachep, vma);
unacct_error:
@@ -1572,66 +1577,6 @@ find_extend_vma(struct mm_struct * mm, unsigned long addr)
}
#endif
-/*
- * Try to free as many page directory entries as we can,
- * without having to work very hard at actually scanning
- * the page tables themselves.
- *
- * Right now we try to free page tables if we have a nice
- * PGDIR-aligned area that got free'd up. We could be more
- * granular if we want to, but this is fast and simple,
- * and covers the bad cases.
- *
- * "prev", if it exists, points to a vma before the one
- * we just free'd - but there's no telling how much before.
- */
-static void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *prev,
- unsigned long start, unsigned long end)
-{
- unsigned long first = start & PGDIR_MASK;
- unsigned long last = end + PGDIR_SIZE - 1;
- struct mm_struct *mm = tlb->mm;
-
- if (last > MM_VM_SIZE(mm) || last < end)
- last = MM_VM_SIZE(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;
- if (first < FIRST_USER_PGD_NR * PGDIR_SIZE)
- first = FIRST_USER_PGD_NR * PGDIR_SIZE;
- /* No point trying to free anything if we're in the same pte page */
- if ((first & PMD_MASK) < (last & PMD_MASK)) {
- clear_page_range(tlb, first, last);
- flush_tlb_pgtables(mm, first, last);
- }
-}
-
/* Normal function to fix up a mapping
* This function is the default for when an area has no specific
* function. This may be used as part of a more specific routine.
@@ -1674,24 +1619,22 @@ static void unmap_vma_list(struct mm_struct *mm,
* Called with the page table lock held.
*/
static void unmap_region(struct mm_struct *mm,
- struct vm_area_struct *vma,
- struct vm_area_struct *prev,
- unsigned long start,
- unsigned long end)
+ struct vm_area_struct *vma, struct vm_area_struct *prev,
+ unsigned long start, unsigned long end)
{
+ struct vm_area_struct *next = prev? prev->vm_next: mm->mmap;
struct mmu_gather *tlb;
unsigned long nr_accounted = 0;
lru_add_drain();
+ spin_lock(&mm->page_table_lock);
tlb = tlb_gather_mmu(mm, 0);
unmap_vmas(&tlb, mm, vma, start, end, &nr_accounted, NULL);
vm_unacct_memory(nr_accounted);
-
- if (is_hugepage_only_range(mm, start, end - start))
- hugetlb_free_pgtables(tlb, prev, start, end);
- else
- free_pgtables(tlb, prev, start, end);
+ free_pgtables(&tlb, vma, prev? prev->vm_end: 0,
+ next? next->vm_start: 0);
tlb_finish_mmu(tlb, start, end);
+ spin_unlock(&mm->page_table_lock);
}
/*
@@ -1823,9 +1766,7 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
* Remove the vma's, and unmap the actual pages
*/
detach_vmas_to_be_unmapped(mm, mpnt, prev, end);
- spin_lock(&mm->page_table_lock);
unmap_region(mm, mpnt, prev, start, end);
- spin_unlock(&mm->page_table_lock);
/* Fix up all other VM information */
unmap_vma_list(mm, mpnt);
@@ -1957,25 +1898,21 @@ EXPORT_SYMBOL(do_brk);
void exit_mmap(struct mm_struct *mm)
{
struct mmu_gather *tlb;
- struct vm_area_struct *vma;
+ struct vm_area_struct *vma = mm->mmap;
unsigned long nr_accounted = 0;
lru_add_drain();
spin_lock(&mm->page_table_lock);
- tlb = tlb_gather_mmu(mm, 1);
flush_cache_mm(mm);
- /* Use ~0UL here to ensure all VMAs in the mm are unmapped */
- mm->map_count -= unmap_vmas(&tlb, mm, mm->mmap, 0,
- ~0UL, &nr_accounted, NULL);
+ tlb = tlb_gather_mmu(mm, 1);
+ /* Use -1 here to ensure all VMAs in the mm are unmapped */
+ mm->map_count -= unmap_vmas(&tlb, mm, vma, 0, -1, &nr_accounted, NULL);
vm_unacct_memory(nr_accounted);
- BUG_ON(mm->map_count); /* This is just debugging */
- clear_page_range(tlb, FIRST_USER_PGD_NR * PGDIR_SIZE, MM_VM_SIZE(mm));
-
+ free_pgtables(&tlb, vma, 0, 0);
tlb_finish_mmu(tlb, 0, MM_VM_SIZE(mm));
- vma = mm->mmap;
mm->mmap = mm->mmap_cache = NULL;
mm->mm_rb = RB_ROOT;
set_mm_counter(mm, rss, 0);
@@ -1993,6 +1930,9 @@ void exit_mmap(struct mm_struct *mm)
remove_vm_struct(vma);
vma = next;
}
+
+ BUG_ON(mm->map_count); /* This is just debugging */
+ BUG_ON(mm->nr_ptes); /* This is just debugging */
}
/* Insert vm structure into process list sorted by address