[PATCH 03 of 11] invalidate_page outside PT lock

From: Andrea Arcangeli
Date: Wed May 07 2008 - 10:39:40 EST


# HG changeset patch
# User Andrea Arcangeli <andrea@xxxxxxxxxxxx>
# Date 1210115129 -7200
# Node ID d60d200565abde6a8ed45271e53cde9c5c75b426
# Parent c5badbefeee07518d9d1acca13e94c981420317c
invalidate_page outside PT lock

Moves all mmu notifier methods outside the PT lock (first and not last
step to make them sleep capable).

Signed-off-by: Andrea Arcangeli <andrea@xxxxxxxxxxxx>

diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -210,35 +210,6 @@ static inline void mmu_notifier_mm_destr
__mmu_notifier_mm_destroy(mm);
}

-/*
- * These two macros will sometime replace ptep_clear_flush.
- * ptep_clear_flush is impleemnted as macro itself, so this also is
- * implemented as a macro until ptep_clear_flush will converted to an
- * inline function, to diminish the risk of compilation failure. The
- * invalidate_page method over time can be moved outside the PT lock
- * and these two macros can be later removed.
- */
-#define ptep_clear_flush_notify(__vma, __address, __ptep) \
-({ \
- pte_t __pte; \
- struct vm_area_struct *___vma = __vma; \
- unsigned long ___address = __address; \
- __pte = ptep_clear_flush(___vma, ___address, __ptep); \
- mmu_notifier_invalidate_page(___vma->vm_mm, ___address); \
- __pte; \
-})
-
-#define ptep_clear_flush_young_notify(__vma, __address, __ptep) \
-({ \
- int __young; \
- struct vm_area_struct *___vma = __vma; \
- unsigned long ___address = __address; \
- __young = ptep_clear_flush_young(___vma, ___address, __ptep); \
- __young |= mmu_notifier_clear_flush_young(___vma->vm_mm, \
- ___address); \
- __young; \
-})
-
#else /* CONFIG_MMU_NOTIFIER */

static inline void mmu_notifier_release(struct mm_struct *mm)
@@ -274,9 +245,6 @@ static inline void mmu_notifier_mm_destr
{
}

-#define ptep_clear_flush_young_notify ptep_clear_flush_young
-#define ptep_clear_flush_notify ptep_clear_flush
-
#endif /* CONFIG_MMU_NOTIFIER */

#endif /* _LINUX_MMU_NOTIFIER_H */
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -188,11 +188,13 @@ __xip_unmap (struct address_space * mapp
if (pte) {
/* Nuke the page table entry. */
flush_cache_page(vma, address, pte_pfn(*pte));
- pteval = ptep_clear_flush_notify(vma, address, pte);
+ pteval = ptep_clear_flush(vma, address, pte);
page_remove_rmap(page, vma);
dec_mm_counter(mm, file_rss);
BUG_ON(pte_dirty(pteval));
pte_unmap_unlock(pte, ptl);
+ /* must invalidate_page _before_ freeing the page */
+ mmu_notifier_invalidate_page(mm, address);
page_cache_release(page);
}
}
diff --git a/mm/memory.c b/mm/memory.c
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1714,9 +1714,10 @@ static int do_wp_page(struct mm_struct *
*/
page_table = pte_offset_map_lock(mm, pmd, address,
&ptl);
- page_cache_release(old_page);
+ new_page = NULL;
if (!pte_same(*page_table, orig_pte))
goto unlock;
+ page_cache_release(old_page);

page_mkwrite = 1;
}
@@ -1732,6 +1733,7 @@ static int do_wp_page(struct mm_struct *
if (ptep_set_access_flags(vma, address, page_table, entry,1))
update_mmu_cache(vma, address, entry);
ret |= VM_FAULT_WRITE;
+ old_page = new_page = NULL;
goto unlock;
}

@@ -1776,7 +1778,7 @@ gotten:
* seen in the presence of one thread doing SMC and another
* thread doing COW.
*/
- ptep_clear_flush_notify(vma, address, page_table);
+ ptep_clear_flush(vma, address, page_table);
set_pte_at(mm, address, page_table, entry);
update_mmu_cache(vma, address, entry);
lru_cache_add_active(new_page);
@@ -1788,12 +1790,18 @@ gotten:
} else
mem_cgroup_uncharge_page(new_page);

- if (new_page)
+unlock:
+ pte_unmap_unlock(page_table, ptl);
+
+ if (new_page) {
+ if (new_page == old_page)
+ /* cow happened, notify before releasing old_page */
+ mmu_notifier_invalidate_page(mm, address);
page_cache_release(new_page);
+ }
if (old_page)
page_cache_release(old_page);
-unlock:
- pte_unmap_unlock(page_table, ptl);
+
if (dirty_page) {
if (vma->vm_file)
file_update_time(vma->vm_file);
diff --git a/mm/rmap.c b/mm/rmap.c
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -275,7 +275,7 @@ static int page_referenced_one(struct pa
unsigned long address;
pte_t *pte;
spinlock_t *ptl;
- int referenced = 0;
+ int referenced = 0, clear_flush_young = 0;

address = vma_address(page, vma);
if (address == -EFAULT)
@@ -288,8 +288,11 @@ static int page_referenced_one(struct pa
if (vma->vm_flags & VM_LOCKED) {
referenced++;
*mapcount = 1; /* break early from loop */
- } else if (ptep_clear_flush_young_notify(vma, address, pte))
- referenced++;
+ } else {
+ clear_flush_young = 1;
+ if (ptep_clear_flush_young(vma, address, pte))
+ referenced++;
+ }

/* Pretend the page is referenced if the task has the
swap token and is in the middle of a page fault. */
@@ -299,6 +302,10 @@ static int page_referenced_one(struct pa

(*mapcount)--;
pte_unmap_unlock(pte, ptl);
+
+ if (clear_flush_young)
+ referenced += mmu_notifier_clear_flush_young(mm, address);
+
out:
return referenced;
}
@@ -458,7 +465,7 @@ static int page_mkclean_one(struct page
pte_t entry;

flush_cache_page(vma, address, pte_pfn(*pte));
- entry = ptep_clear_flush_notify(vma, address, pte);
+ entry = ptep_clear_flush(vma, address, pte);
entry = pte_wrprotect(entry);
entry = pte_mkclean(entry);
set_pte_at(mm, address, pte, entry);
@@ -466,6 +473,10 @@ static int page_mkclean_one(struct page
}

pte_unmap_unlock(pte, ptl);
+
+ if (ret)
+ mmu_notifier_invalidate_page(mm, address);
+
out:
return ret;
}
@@ -717,15 +728,14 @@ static int try_to_unmap_one(struct page
* If it's recently referenced (perhaps page_referenced
* skipped over this mm) then we should reactivate it.
*/
- if (!migration && ((vma->vm_flags & VM_LOCKED) ||
- (ptep_clear_flush_young_notify(vma, address, pte)))) {
+ if (!migration && (vma->vm_flags & VM_LOCKED)) {
ret = SWAP_FAIL;
goto out_unmap;
}

/* Nuke the page table entry. */
flush_cache_page(vma, address, page_to_pfn(page));
- pteval = ptep_clear_flush_notify(vma, address, pte);
+ pteval = ptep_clear_flush(vma, address, pte);

/* Move the dirty bit to the physical page now the pte is gone. */
if (pte_dirty(pteval))
@@ -780,6 +790,8 @@ static int try_to_unmap_one(struct page

out_unmap:
pte_unmap_unlock(pte, ptl);
+ if (ret != SWAP_FAIL)
+ mmu_notifier_invalidate_page(mm, address);
out:
return ret;
}
@@ -818,7 +830,7 @@ static void try_to_unmap_cluster(unsigne
spinlock_t *ptl;
struct page *page;
unsigned long address;
- unsigned long end;
+ unsigned long start, end;

address = (vma->vm_start + cursor) & CLUSTER_MASK;
end = address + CLUSTER_SIZE;
@@ -839,6 +851,8 @@ static void try_to_unmap_cluster(unsigne
if (!pmd_present(*pmd))
return;

+ start = address;
+ mmu_notifier_invalidate_range_start(mm, start, end);
pte = pte_offset_map_lock(mm, pmd, address, &ptl);

/* Update high watermark before we lower rss */
@@ -850,12 +864,12 @@ static void try_to_unmap_cluster(unsigne
page = vm_normal_page(vma, address, *pte);
BUG_ON(!page || PageAnon(page));

- if (ptep_clear_flush_young_notify(vma, address, pte))
+ if (ptep_clear_flush_young(vma, address, pte))
continue;

/* Nuke the page table entry. */
flush_cache_page(vma, address, pte_pfn(*pte));
- pteval = ptep_clear_flush_notify(vma, address, pte);
+ pteval = ptep_clear_flush(vma, address, pte);

/* If nonlinear, store the file page offset in the pte. */
if (page->index != linear_page_index(vma, address))
@@ -871,6 +885,7 @@ static void try_to_unmap_cluster(unsigne
(*mapcount)--;
}
pte_unmap_unlock(pte - 1, ptl);
+ mmu_notifier_invalidate_range_end(mm, start, end);
}

static int try_to_unmap_anon(struct page *page, int migration)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/