unsigned long address, pmd_t *pmd,
int referenced)
{
- int swapped_in = 0, ret = 0;
+ int swapped_in = 0;
+ vm_fault_t ret = 0;
struct vm_fault vmf = {
.vma = vma,
.address = address,
* collapse_shmem - collapse small tmpfs/shmem pages into huge one.
*
* Basic scheme is simple, details are more complex:
- * - allocate and freeze a new huge page;
+ * - allocate and lock a new huge page;
* - scan over radix tree replacing old pages the new one
* + swap in pages if necessary;
* + fill in gaps;
* - if replacing succeed:
* + copy data over;
* + free old pages;
- * + unfreeze huge page;
+ * + unlock huge page;
* - if replacing failed;
* + put all pages back and unfreeze them;
* + restore gaps in the radix-tree;
- * + free huge page;
+ * + unlock and free huge page;
*/
static void collapse_shmem(struct mm_struct *mm,
struct address_space *mapping, pgoff_t start,
goto out;
}
+ __SetPageLocked(new_page);
+ __SetPageSwapBacked(new_page);
new_page->index = start;
new_page->mapping = mapping;
- __SetPageSwapBacked(new_page);
- __SetPageLocked(new_page);
- BUG_ON(!page_ref_freeze(new_page, 1));
-
/*
- * At this point the new_page is 'frozen' (page_count() is zero), locked
- * and not up-to-date. It's safe to insert it into radix tree, because
- * nobody would be able to map it or use it in other way until we
- * unfreeze it.
+ * At this point the new_page is locked and not up-to-date.
+ * It's safe to insert it into the page cache, because nobody would
+ * be able to map it or use it in another way until we unlock it.
*/
index = start;
int n = min(iter.index, end) - index;
/*
+ * Stop if extent has been hole-punched, and is now completely
+ * empty (the more obvious i_size_read() check would take an
+ * irq-unsafe seqlock on 32-bit).
+ */
+ if (n >= HPAGE_PMD_NR) {
+ result = SCAN_TRUNCATED;
+ goto tree_locked;
+ }
+
+ /*
* Handle holes in the radix tree: charge it from shmem and
* insert relevant subpage of new_page into the radix-tree.
*/
if (n && !shmem_charge(mapping->host, n)) {
result = SCAN_FAIL;
- break;
+ goto tree_locked;
}
- nr_none += n;
for (; index < min(iter.index, end); index++) {
radix_tree_insert(&mapping->i_pages, index,
new_page + (index % HPAGE_PMD_NR));
}
+ nr_none += n;
/* We are done. */
if (index >= end)
result = SCAN_FAIL;
goto tree_unlocked;
}
- xa_lock_irq(&mapping->i_pages);
} else if (trylock_page(page)) {
get_page(page);
+ xa_unlock_irq(&mapping->i_pages);
} else {
result = SCAN_PAGE_LOCK;
- break;
+ goto tree_locked;
}
/*
result = SCAN_TRUNCATED;
goto out_unlock;
}
- xa_unlock_irq(&mapping->i_pages);
if (isolate_lru_page(page)) {
result = SCAN_DEL_PAGE_LRU;
- goto out_isolate_failed;
+ goto out_unlock;
}
if (page_mapped(page))
*/
if (!page_ref_freeze(page, 3)) {
result = SCAN_PAGE_COUNT;
- goto out_lru;
+ xa_unlock_irq(&mapping->i_pages);
+ putback_lru_page(page);
+ goto out_unlock;
}
/*
slot = radix_tree_iter_resume(slot, &iter);
index++;
continue;
-out_lru:
- xa_unlock_irq(&mapping->i_pages);
- putback_lru_page(page);
-out_isolate_failed:
- unlock_page(page);
- put_page(page);
- goto tree_unlocked;
out_unlock:
unlock_page(page);
put_page(page);
- break;
+ goto tree_unlocked;
}
/*
* This code only triggers if there's nothing in radix tree
* beyond 'end'.
*/
- if (result == SCAN_SUCCEED && index < end) {
+ if (index < end) {
int n = end - index;
+ /* Stop if extent has been truncated, and is now empty */
+ if (n >= HPAGE_PMD_NR) {
+ result = SCAN_TRUNCATED;
+ goto tree_locked;
+ }
if (!shmem_charge(mapping->host, n)) {
result = SCAN_FAIL;
goto tree_locked;
}
-
for (; index < end; index++) {
radix_tree_insert(&mapping->i_pages, index,
new_page + (index % HPAGE_PMD_NR));
nr_none += n;
}
+ __inc_node_page_state(new_page, NR_SHMEM_THPS);
+ if (nr_none) {
+ struct zone *zone = page_zone(new_page);
+
+ __mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none);
+ __mod_node_page_state(zone->zone_pgdat, NR_SHMEM, nr_none);
+ }
+
tree_locked:
xa_unlock_irq(&mapping->i_pages);
tree_unlocked:
if (result == SCAN_SUCCEED) {
- unsigned long flags;
- struct zone *zone = page_zone(new_page);
-
/*
* Replacing old pages with new one has succeed, now we need to
* copy the content and free old pages.
*/
+ index = start;
list_for_each_entry_safe(page, tmp, &pagelist, lru) {
+ while (index < page->index) {
+ clear_highpage(new_page + (index % HPAGE_PMD_NR));
+ index++;
+ }
copy_highpage(new_page + (page->index % HPAGE_PMD_NR),
page);
list_del(&page->lru);
- unlock_page(page);
- page_ref_unfreeze(page, 1);
page->mapping = NULL;
+ page_ref_unfreeze(page, 1);
ClearPageActive(page);
ClearPageUnevictable(page);
+ unlock_page(page);
put_page(page);
+ index++;
}
-
- local_irq_save(flags);
- __inc_node_page_state(new_page, NR_SHMEM_THPS);
- if (nr_none) {
- __mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none);
- __mod_node_page_state(zone->zone_pgdat, NR_SHMEM, nr_none);
+ while (index < end) {
+ clear_highpage(new_page + (index % HPAGE_PMD_NR));
+ index++;
}
- local_irq_restore(flags);
- /*
- * Remove pte page tables, so we can re-faulti
- * the page as huge.
- */
- retract_page_tables(mapping, start);
-
- /* Everything is ready, let's unfreeze the new_page */
- set_page_dirty(new_page);
SetPageUptodate(new_page);
- page_ref_unfreeze(new_page, HPAGE_PMD_NR);
+ page_ref_add(new_page, HPAGE_PMD_NR - 1);
+ set_page_dirty(new_page);
mem_cgroup_commit_charge(new_page, memcg, false, true);
lru_cache_add_anon(new_page);
- unlock_page(new_page);
+ /*
+ * Remove pte page tables, so we can re-fault the page as huge.
+ */
+ retract_page_tables(mapping, start);
*hpage = NULL;
khugepaged_pages_collapsed++;
} else {
/* Something went wrong: rollback changes to the radix-tree */
- shmem_uncharge(mapping->host, nr_none);
xa_lock_irq(&mapping->i_pages);
+ mapping->nrpages -= nr_none;
+ shmem_uncharge(mapping->host, nr_none);
+
radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) {
if (iter.index >= end)
break;
radix_tree_replace_slot(&mapping->i_pages, slot, page);
slot = radix_tree_iter_resume(slot, &iter);
xa_unlock_irq(&mapping->i_pages);
- putback_lru_page(page);
unlock_page(page);
+ putback_lru_page(page);
xa_lock_irq(&mapping->i_pages);
}
VM_BUG_ON(nr_none);
xa_unlock_irq(&mapping->i_pages);
- /* Unfreeze new_page, caller would take care about freeing it */
- page_ref_unfreeze(new_page, 1);
mem_cgroup_cancel_charge(new_page, memcg, true);
- unlock_page(new_page);
new_page->mapping = NULL;
}
+
+ unlock_page(new_page);
out:
VM_BUG_ON(!list_empty(&pagelist));
/* TODO: tracepoints */