summaryrefslogtreecommitdiffstats
path: root/mm/memory.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/memory.c
parent9f6c6fc505560465be0964eb4da1b6ca97bd3951 (diff)
downloadop-kernel-dev-e0da382c92626ad1d7f4b7527d19b80104d67a83.zip
op-kernel-dev-e0da382c92626ad1d7f4b7527d19b80104d67a83.tar.gz
[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/memory.c')
-rw-r--r--mm/memory.c152
1 files changed, 115 insertions, 37 deletions
diff --git a/mm/memory.c b/mm/memory.c
index fb6e5deb..fee5dc8 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -110,87 +110,165 @@ 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 inline void clear_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
- unsigned long addr, unsigned long end)
+static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd)
{
- if (!((addr | end) & ~PMD_MASK)) {
- /* Only free fully aligned ranges */
- struct page *page = pmd_page(*pmd);
- pmd_clear(pmd);
- dec_page_state(nr_page_table_pages);
- tlb->mm->nr_ptes--;
- pte_free_tlb(tlb, page);
- }
+ 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 clear_pmd_range(struct mmu_gather *tlb, pud_t *pud,
- unsigned long addr, unsigned long end)
+static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
+ unsigned long addr, unsigned long end,
+ unsigned long floor, unsigned long ceiling)
{
pmd_t *pmd;
unsigned long next;
- pmd_t *empty_pmd = NULL;
+ unsigned long start;
+ start = addr;
pmd = pmd_offset(pud, addr);
-
- /* Only free fully aligned ranges */
- if (!((addr | end) & ~PUD_MASK))
- empty_pmd = pmd;
do {
next = pmd_addr_end(addr, end);
if (pmd_none_or_clear_bad(pmd))
continue;
- clear_pte_range(tlb, pmd, addr, next);
+ free_pte_range(tlb, pmd);
} while (pmd++, addr = next, addr != end);
- if (empty_pmd) {
- pud_clear(pud);
- pmd_free_tlb(tlb, empty_pmd);
+ start &= PUD_MASK;
+ if (start < floor)
+ return;
+ if (ceiling) {
+ ceiling &= PUD_MASK;
+ if (!ceiling)
+ return;
}
+ if (end - 1 > ceiling - 1)
+ return;
+
+ pmd = pmd_offset(pud, start);
+ pud_clear(pud);
+ pmd_free_tlb(tlb, pmd);
}
-static inline void clear_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
- unsigned long addr, unsigned long end)
+static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
+ unsigned long addr, unsigned long end,
+ unsigned long floor, unsigned long ceiling)
{
pud_t *pud;
unsigned long next;
- pud_t *empty_pud = NULL;
+ unsigned long start;
+ start = addr;
pud = pud_offset(pgd, addr);
-
- /* Only free fully aligned ranges */
- if (!((addr | end) & ~PGDIR_MASK))
- empty_pud = pud;
do {
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
continue;
- clear_pmd_range(tlb, pud, addr, next);
+ free_pmd_range(tlb, pud, addr, next, floor, ceiling);
} while (pud++, addr = next, addr != end);
- if (empty_pud) {
- pgd_clear(pgd);
- pud_free_tlb(tlb, empty_pud);
+ start &= PGDIR_MASK;
+ if (start < floor)
+ return;
+ if (ceiling) {
+ ceiling &= PGDIR_MASK;
+ if (!ceiling)
+ return;
}
+ if (end - 1 > ceiling - 1)
+ return;
+
+ pud = pud_offset(pgd, start);
+ pgd_clear(pgd);
+ pud_free_tlb(tlb, pud);
}
/*
- * This function clears user-level page tables of a process.
- * Unlike other pagetable walks, some memory layouts might give end 0.
+ * This function frees user-level page tables of a process.
+ *
* Must be called with pagetable lock held.
*/
-void clear_page_range(struct mmu_gather *tlb,
- unsigned long addr, unsigned long end)
+static inline void free_pgd_range(struct mmu_gather *tlb,
+ unsigned long addr, unsigned long end,
+ unsigned long floor, unsigned long ceiling)
{
pgd_t *pgd;
unsigned long next;
+ unsigned long start;
+ /*
+ * The next few lines have given us lots of grief...
+ *
+ * Why are we testing PMD* at this top level? Because often
+ * there will be no work to do at all, and we'd prefer not to
+ * go all the way down to the bottom just to discover that.
+ *
+ * Why all these "- 1"s? Because 0 represents both the bottom
+ * of the address space and the top of it (using -1 for the
+ * top wouldn't help much: the masks would do the wrong thing).
+ * The rule is that addr 0 and floor 0 refer to the bottom of
+ * the address space, but end 0 and ceiling 0 refer to the top
+ * Comparisons need to use "end - 1" and "ceiling - 1" (though
+ * that end 0 case should be mythical).
+ *
+ * Wherever addr is brought up or ceiling brought down, we must
+ * be careful to reject "the opposite 0" before it confuses the
+ * subsequent tests. But what about where end is brought down
+ * by PMD_SIZE below? no, end can't go down to 0 there.
+ *
+ * Whereas we round start (addr) and ceiling down, by different
+ * masks at different levels, in order to test whether a table
+ * now has no other vmas using it, so can be freed, we don't
+ * bother to round floor or end up - the tests don't need that.
+ */
+
+ addr &= PMD_MASK;
+ if (addr < floor) {
+ addr += PMD_SIZE;
+ if (!addr)
+ return;
+ }
+ if (ceiling) {
+ ceiling &= PMD_MASK;
+ if (!ceiling)
+ return;
+ }
+ if (end - 1 > ceiling - 1)
+ end -= PMD_SIZE;
+ if (addr > end - 1)
+ return;
+
+ start = addr;
pgd = pgd_offset(tlb->mm, addr);
do {
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
- clear_pud_range(tlb, pgd, addr, next);
+ free_pud_range(tlb, pgd, addr, next, floor, ceiling);
} while (pgd++, addr = next, addr != end);
+
+ if (!tlb_is_full_mm(tlb))
+ flush_tlb_pgtables(tlb->mm, start, end);
+}
+
+void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *vma,
+ unsigned long floor, unsigned long ceiling)
+{
+ while (vma) {
+ struct vm_area_struct *next = vma->vm_next;
+ unsigned long addr = vma->vm_start;
+
+ /* Optimization: gather nearby vmas into a single call down */
+ while (next && next->vm_start <= vma->vm_end + PMD_SIZE) {
+ vma = next;
+ next = vma->vm_next;
+ }
+ free_pgd_range(*tlb, addr, vma->vm_end,
+ floor, next? next->vm_start: ceiling);
+ vma = next;
+ }
}
pte_t fastcall * pte_alloc_map(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
OpenPOWER on IntegriCloud