1 << PG_reclaim |
1 << PG_slab |
1 << PG_swapcache |
- 1 << PG_writeback |
- 1 << PG_reserved );
+ 1 << PG_writeback );
set_page_count(page, 0);
reset_page_mapcount(page);
page->mapping = NULL;
add_taint(TAINT_BAD_PAGE);
}
-#ifndef CONFIG_HUGETLB_PAGE
-#define prep_compound_page(page, order) do { } while (0)
-#define destroy_compound_page(page, order) do { } while (0)
-#else
/*
* Higher-order pages are called "compound pages". They are structured thusly:
*
ClearPageCompound(p);
}
}
-#endif /* CONFIG_HUGETLB_PAGE */
/*
* function for dealing with page's order in buddy system.
zone->free_area[order].nr_free++;
}
-static inline void free_pages_check(const char *function, struct page *page)
+static inline int free_pages_check(const char *function, struct page *page)
{
- if ( page_mapcount(page) ||
- page->mapping != NULL ||
- page_count(page) != 0 ||
+ if (unlikely(page_mapcount(page) |
+ (page->mapping != NULL) |
+ (page_count(page) != 0) |
(page->flags & (
1 << PG_lru |
1 << PG_private |
1 << PG_slab |
1 << PG_swapcache |
1 << PG_writeback |
- 1 << PG_reserved )))
+ 1 << PG_reserved ))))
bad_page(function, page);
if (PageDirty(page))
__ClearPageDirty(page);
+ /*
+ * For now, we report if PG_reserved was found set, but do not
+ * clear it, and do not free the page. But we shall soon need
+ * to do more, for when the ZERO_PAGE count wraps negative.
+ */
+ return PageReserved(page);
}
/*
free_pages_bulk(struct zone *zone, int count,
struct list_head *list, unsigned int order)
{
- unsigned long flags;
struct page *page = NULL;
int ret = 0;
- spin_lock_irqsave(&zone->lock, flags);
+ spin_lock(&zone->lock);
zone->all_unreclaimable = 0;
zone->pages_scanned = 0;
while (!list_empty(list) && count--) {
__free_pages_bulk(page, zone, order);
ret++;
}
- spin_unlock_irqrestore(&zone->lock, flags);
+ spin_unlock(&zone->lock);
return ret;
}
void __free_pages_ok(struct page *page, unsigned int order)
{
+ unsigned long flags;
LIST_HEAD(list);
int i;
+ int reserved = 0;
arch_free_page(page, order);
- mod_page_state(pgfree, 1 << order);
-
#ifndef CONFIG_MMU
if (order > 0)
for (i = 1 ; i < (1 << order) ; ++i)
#endif
for (i = 0 ; i < (1 << order) ; ++i)
- free_pages_check(__FUNCTION__, page + i);
+ reserved += free_pages_check(__FUNCTION__, page + i);
+ if (reserved)
+ return;
+
list_add(&page->lru, &list);
+ mod_page_state(pgfree, 1 << order);
kernel_map_pages(page, 1<<order, 0);
+ local_irq_save(flags);
free_pages_bulk(page_zone(page), 1, &list, order);
+ local_irq_restore(flags);
}
return page;
}
-void set_page_refs(struct page *page, int order)
-{
-#ifdef CONFIG_MMU
- set_page_count(page, 1);
-#else
- int i;
-
- /*
- * We need to reference all the pages for this order, otherwise if
- * anyone accesses one of the pages with (get/put) it will be freed.
- * - eg: access_process_vm()
- */
- for (i = 0; i < (1 << order); i++)
- set_page_count(page + i, 1);
-#endif /* CONFIG_MMU */
-}
-
/*
* This page is about to be returned from the page allocator
*/
-static void prep_new_page(struct page *page, int order)
+static int prep_new_page(struct page *page, int order)
{
- if ( page_mapcount(page) ||
- page->mapping != NULL ||
- page_count(page) != 0 ||
+ if (unlikely(page_mapcount(page) |
+ (page->mapping != NULL) |
+ (page_count(page) != 0) |
(page->flags & (
1 << PG_lru |
1 << PG_private |
1 << PG_slab |
1 << PG_swapcache |
1 << PG_writeback |
- 1 << PG_reserved )))
+ 1 << PG_reserved ))))
bad_page(__FUNCTION__, page);
+ /*
+ * For now, we report if PG_reserved was found set, but do not
+ * clear it, and do not allocate the page: as a safety net.
+ */
+ if (PageReserved(page))
+ return 1;
+
page->flags &= ~(1 << PG_uptodate | 1 << PG_error |
1 << PG_referenced | 1 << PG_arch_1 |
1 << PG_checked | 1 << PG_mappedtodisk);
set_page_private(page, 0);
set_page_refs(page, order);
kernel_map_pages(page, 1 << order, 1);
+ return 0;
}
/*
static int rmqueue_bulk(struct zone *zone, unsigned int order,
unsigned long count, struct list_head *list)
{
- unsigned long flags;
int i;
int allocated = 0;
struct page *page;
- spin_lock_irqsave(&zone->lock, flags);
+ spin_lock(&zone->lock);
for (i = 0; i < count; ++i) {
page = __rmqueue(zone, order);
if (page == NULL)
allocated++;
list_add_tail(&page->lru, list);
}
- spin_unlock_irqrestore(&zone->lock, flags);
+ spin_unlock(&zone->lock);
return allocated;
}
#if defined(CONFIG_PM) || defined(CONFIG_HOTPLUG_CPU)
static void __drain_pages(unsigned int cpu)
{
+ unsigned long flags;
struct zone *zone;
int i;
struct per_cpu_pages *pcp;
pcp = &pset->pcp[i];
+ local_irq_save(flags);
pcp->count -= free_pages_bulk(zone, pcp->count,
&pcp->list, 0);
+ local_irq_restore(flags);
}
}
}
arch_free_page(page, 0);
- kernel_map_pages(page, 1, 0);
- inc_page_state(pgfree);
if (PageAnon(page))
page->mapping = NULL;
- free_pages_check(__FUNCTION__, page);
+ if (free_pages_check(__FUNCTION__, page))
+ return;
+
+ inc_page_state(pgfree);
+ kernel_map_pages(page, 1, 0);
+
pcp = &zone_pcp(zone, get_cpu())->pcp[cold];
local_irq_save(flags);
list_add(&page->lru, &pcp->list);
buffered_rmqueue(struct zone *zone, int order, gfp_t gfp_flags)
{
unsigned long flags;
- struct page *page = NULL;
+ struct page *page;
int cold = !!(gfp_flags & __GFP_COLD);
+again:
if (order == 0) {
struct per_cpu_pages *pcp;
+ page = NULL;
pcp = &zone_pcp(zone, get_cpu())->pcp[cold];
local_irq_save(flags);
if (pcp->count <= pcp->low)
pcp->count += rmqueue_bulk(zone, 0,
pcp->batch, &pcp->list);
- if (pcp->count) {
+ if (likely(pcp->count)) {
page = list_entry(pcp->list.next, struct page, lru);
list_del(&page->lru);
pcp->count--;
if (page != NULL) {
BUG_ON(bad_range(zone, page));
mod_page_state_zone(zone, pgalloc, 1 << order);
- prep_new_page(page, order);
+ if (prep_new_page(page, order))
+ goto again;
if (gfp_flags & __GFP_ZERO)
prep_zero_page(page, order, gfp_flags);
}
#define ALLOC_NO_WATERMARKS 0x01 /* don't check watermarks at all */
-#define ALLOC_HARDER 0x02 /* try to alloc harder */
-#define ALLOC_HIGH 0x04 /* __GFP_HIGH set */
-#define ALLOC_CPUSET 0x08 /* check for correct cpuset */
+#define ALLOC_WMARK_MIN 0x02 /* use pages_min watermark */
+#define ALLOC_WMARK_LOW 0x04 /* use pages_low watermark */
+#define ALLOC_WMARK_HIGH 0x08 /* use pages_high watermark */
+#define ALLOC_HARDER 0x10 /* try to alloc harder */
+#define ALLOC_HIGH 0x20 /* __GFP_HIGH set */
+#define ALLOC_CPUSET 0x40 /* check for correct cpuset */
/*
* Return 1 if free pages are above 'mark'. This takes into account the order
continue;
if (!(alloc_flags & ALLOC_NO_WATERMARKS)) {
- if (!zone_watermark_ok(*z, order, (*z)->pages_low,
+ unsigned long mark;
+ if (alloc_flags & ALLOC_WMARK_MIN)
+ mark = (*z)->pages_min;
+ else if (alloc_flags & ALLOC_WMARK_LOW)
+ mark = (*z)->pages_low;
+ else
+ mark = (*z)->pages_high;
+ if (!zone_watermark_ok(*z, order, mark,
classzone_idx, alloc_flags))
continue;
}
might_sleep_if(wait);
+restart:
z = zonelist->zones; /* the list of zones suitable for gfp_mask */
if (unlikely(*z == NULL)) {
/* Should this ever happen?? */
return NULL;
}
-restart:
+
page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
- zonelist, ALLOC_CPUSET);
+ zonelist, ALLOC_WMARK_LOW|ALLOC_CPUSET);
if (page)
goto got_pg;
- do
+ do {
wakeup_kswapd(*z, order);
- while (*(++z));
+ } while (*(++z));
/*
* OK, we're below the kswapd watermark and have kicked background
* cannot run direct reclaim, or if the caller has realtime scheduling
* policy.
*/
- alloc_flags = 0;
+ alloc_flags = ALLOC_WMARK_MIN;
if ((unlikely(rt_task(p)) && !in_interrupt()) || !wait)
alloc_flags |= ALLOC_HARDER;
if (gfp_mask & __GFP_HIGH)
alloc_flags |= ALLOC_HIGH;
- if (wait)
- alloc_flags |= ALLOC_CPUSET;
+ alloc_flags |= ALLOC_CPUSET;
/*
* Go through the zonelist again. Let __GFP_HIGH and allocations
nofail_alloc:
/* go through the zonelist yet again, ignoring mins */
page = get_page_from_freelist(gfp_mask, order,
- zonelist, ALLOC_NO_WATERMARKS|ALLOC_CPUSET);
+ zonelist, ALLOC_NO_WATERMARKS);
if (page)
goto got_pg;
if (gfp_mask & __GFP_NOFAIL) {
* under heavy pressure.
*/
page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
- zonelist, ALLOC_CPUSET);
+ zonelist, ALLOC_WMARK_HIGH|ALLOC_CPUSET);
if (page)
goto got_pg;
for (pfn = start_pfn; pfn < end_pfn; pfn++, page++) {
if (!early_pfn_valid(pfn))
continue;
- if (!early_pfn_in_nid(pfn, nid))
- continue;
page = pfn_to_page(pfn);
set_page_links(page, zone, nid, pfn);
set_page_count(page, 1);
batch = 1;
/*
- * We will be trying to allcoate bigger chunks of contiguous
- * memory of the order of fls(batch). This should result in
- * better cache coloring.
+ * Clamp the batch to a 2^n - 1 value. Having a power
+ * of 2 value was found to be more likely to have
+ * suboptimal cache aliasing properties in some cases.
*
- * A sanity check also to ensure that batch is still in limits.
+ * For example if 2 tasks are alternately allocating
+ * batches of pages, one task can end up with a lot
+ * of pages of one half of the possible page colors
+ * and the other with pages of the other colors.
*/
- batch = (1 << fls(batch + batch/2));
-
- if (fls(batch) >= (PAGE_SHIFT + MAX_ORDER - 2))
- batch = PAGE_SHIFT + ((MAX_ORDER - 1 - PAGE_SHIFT)/2);
+ batch = (1 << (fls(batch + batch/2)-1)) - 1;
return batch;
}
static struct notifier_block pageset_notifier =
{ &pageset_cpuup_callback, NULL, 0 };
-void __init setup_per_cpu_pageset()
+void __init setup_per_cpu_pageset(void)
{
int err;