static unsigned long nr_shown;
static unsigned long nr_unshown;
- /* Don't complain about poisoned pages */
- if (PageHWPoison(page)) {
- page_mapcount_reset(page); /* remove PageBuddy */
- return;
- }
-
/*
* Allow a burst of 60 reports, then keep quiet for that minute;
* or allow a steady drip of one report per second.
{
if (!buf)
return -EINVAL;
-
- if (strcmp(buf, "on") == 0)
- _debug_pagealloc_enabled = true;
-
- if (strcmp(buf, "off") == 0)
- _debug_pagealloc_enabled = false;
-
- return 0;
+ return kstrtobool(buf, &_debug_pagealloc_enabled);
}
early_param("debug_pagealloc", early_debug_pagealloc);
trace_mm_page_free(page, order);
kmemcheck_free_shadow(page, order);
- kasan_free_pages(page, order);
/*
* Check tail pages before head page information is cleared to
arch_free_page(page, order);
kernel_poison_pages(page, 1 << order, 0);
kernel_map_pages(page, 1 << order, 0);
+ kasan_free_pages(page, order);
return true;
}
* marks the pages PageReserved. The remaining valid pages are later
* sent to the buddy page allocator.
*/
-void __meminit reserve_bootmem_region(unsigned long start, unsigned long end)
+void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end)
{
unsigned long start_pfn = PFN_DOWN(start);
unsigned long end_pfn = PFN_UP(end);
if (unlikely(page->flags & __PG_HWPOISON)) {
bad_reason = "HWPoisoned (hardware-corrupted)";
bad_flags = __PG_HWPOISON;
+ /* Don't complain about hwpoisoned pages */
+ page_mapcount_reset(page); /* remove PageBuddy */
+ return;
}
if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_PREP)) {
bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set";
* one free page of a suitable size. Checking now avoids taking the zone lock
* to check in the allocation paths if no pages are free.
*/
-static bool __zone_watermark_ok(struct zone *z, unsigned int order,
- unsigned long mark, int classzone_idx,
- unsigned int alloc_flags,
- long free_pages)
+bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
+ int classzone_idx, unsigned int alloc_flags,
+ long free_pages)
{
long min = mark;
int o;
return page;
}
+
+/*
+ * Maximum number of compaction retries wit a progress before OOM
+ * killer is consider as the only way to move forward.
+ */
+#define MAX_COMPACT_RETRIES 16
+
#ifdef CONFIG_COMPACTION
/* Try memory compaction for high-order allocations before reclaim */
static struct page *
return NULL;
}
+
+static inline bool
+should_compact_retry(struct alloc_context *ac, int order, int alloc_flags,
+ enum compact_result compact_result, enum migrate_mode *migrate_mode,
+ int compaction_retries)
+{
+ int max_retries = MAX_COMPACT_RETRIES;
+
+ if (!order)
+ return false;
+
+ /*
+ * compaction considers all the zone as desperately out of memory
+ * so it doesn't really make much sense to retry except when the
+ * failure could be caused by weak migration mode.
+ */
+ if (compaction_failed(compact_result)) {
+ if (*migrate_mode == MIGRATE_ASYNC) {
+ *migrate_mode = MIGRATE_SYNC_LIGHT;
+ return true;
+ }
+ return false;
+ }
+
+ /*
+ * make sure the compaction wasn't deferred or didn't bail out early
+ * due to locks contention before we declare that we should give up.
+ * But do not retry if the given zonelist is not suitable for
+ * compaction.
+ */
+ if (compaction_withdrawn(compact_result))
+ return compaction_zonelist_suitable(ac, order, alloc_flags);
+
+ /*
+ * !costly requests are much more important than __GFP_REPEAT
+ * costly ones because they are de facto nofail and invoke OOM
+ * killer to move on while costly can fail and users are ready
+ * to cope with that. 1/4 retries is rather arbitrary but we
+ * would need much more detailed feedback from compaction to
+ * make a better decision.
+ */
+ if (order > PAGE_ALLOC_COSTLY_ORDER)
+ max_retries /= 4;
+ if (compaction_retries <= max_retries)
+ return true;
+
+ return false;
+}
#else
static inline struct page *
__alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
unsigned int alloc_flags, const struct alloc_context *ac,
enum migrate_mode mode, enum compact_result *compact_result)
{
+ *compact_result = COMPACT_SKIPPED;
return NULL;
}
+
+static inline bool
+should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_flags,
+ enum compact_result compact_result,
+ enum migrate_mode *migrate_mode,
+ int compaction_retries)
+{
+ struct zone *zone;
+ struct zoneref *z;
+
+ if (!order || order > PAGE_ALLOC_COSTLY_ORDER)
+ return false;
+
+ /*
+ * There are setups with compaction disabled which would prefer to loop
+ * inside the allocator rather than hit the oom killer prematurely.
+ * Let's give them a good hope and keep retrying while the order-0
+ * watermarks are OK.
+ */
+ for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx,
+ ac->nodemask) {
+ if (zone_watermark_ok(zone, 0, min_wmark_pages(zone),
+ ac_classzone_idx(ac), alloc_flags))
+ return true;
+ }
+ return false;
+}
#endif /* CONFIG_COMPACTION */
/* Perform direct synchronous page reclaim */
* Checks whether it makes sense to retry the reclaim to make a forward progress
* for the given allocation request.
* The reclaim feedback represented by did_some_progress (any progress during
- * the last reclaim round), pages_reclaimed (cumulative number of reclaimed
- * pages) and no_progress_loops (number of reclaim rounds without any progress
- * in a row) is considered as well as the reclaimable pages on the applicable
- * zone list (with a backoff mechanism which is a function of no_progress_loops).
+ * the last reclaim round) and no_progress_loops (number of reclaim rounds without
+ * any progress in a row) is considered as well as the reclaimable pages on the
+ * applicable zone list (with a backoff mechanism which is a function of
+ * no_progress_loops).
*
* Returns true if a retry is viable or false to enter the oom path.
*/
static inline bool
should_reclaim_retry(gfp_t gfp_mask, unsigned order,
struct alloc_context *ac, int alloc_flags,
- bool did_some_progress, unsigned long pages_reclaimed,
- int no_progress_loops)
+ bool did_some_progress, int no_progress_loops)
{
struct zone *zone;
struct zoneref *z;
if (no_progress_loops > MAX_RECLAIM_RETRIES)
return false;
- if (order > PAGE_ALLOC_COSTLY_ORDER) {
- if (pages_reclaimed >= (1<<order))
- return false;
-
- if (did_some_progress)
- return true;
- }
-
/*
* Keep reclaiming pages while there is a chance this will lead somewhere.
* If none of the target zones can satisfy our allocation request even
bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM;
struct page *page = NULL;
unsigned int alloc_flags;
- unsigned long pages_reclaimed = 0;
unsigned long did_some_progress;
enum migrate_mode migration_mode = MIGRATE_ASYNC;
enum compact_result compact_result;
+ int compaction_retries = 0;
int no_progress_loops = 0;
/*
goto nopage;
}
- /*
- * It can become very expensive to allocate transparent hugepages at
- * fault, so use asynchronous memory compaction for THP unless it is
- * khugepaged trying to collapse.
- */
- if (!is_thp_gfp_mask(gfp_mask) || (current->flags & PF_KTHREAD))
- migration_mode = MIGRATE_SYNC_LIGHT;
+ if (order && compaction_made_progress(compact_result))
+ compaction_retries++;
/* Try direct reclaim and then allocating */
page = __alloc_pages_direct_reclaim(gfp_mask, order, alloc_flags, ac,
if (order > PAGE_ALLOC_COSTLY_ORDER && !(gfp_mask & __GFP_REPEAT))
goto noretry;
- if (did_some_progress) {
+ /*
+ * Costly allocations might have made a progress but this doesn't mean
+ * their order will become available due to high fragmentation so
+ * always increment the no progress counter for them
+ */
+ if (did_some_progress && order <= PAGE_ALLOC_COSTLY_ORDER)
no_progress_loops = 0;
- pages_reclaimed += did_some_progress;
- } else {
+ else
no_progress_loops++;
- }
if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags,
- did_some_progress > 0, pages_reclaimed,
- no_progress_loops))
+ did_some_progress > 0, no_progress_loops))
+ goto retry;
+
+ /*
+ * It doesn't make any sense to retry for the compaction if the order-0
+ * reclaim is not able to make any progress because the current
+ * implementation of the compaction depends on the sufficient amount
+ * of free memory (see __compaction_suitable)
+ */
+ if (did_some_progress > 0 &&
+ should_compact_retry(ac, order, alloc_flags,
+ compact_result, &migration_mode,
+ compaction_retries))
goto retry;
/* Reclaim has failed us, start killing things */
noretry:
/*
- * High-order allocations do not necessarily loop after
- * direct reclaim and reclaim/compaction depends on compaction
- * being called after reclaim so call directly if necessary
+ * High-order allocations do not necessarily loop after direct reclaim
+ * and reclaim/compaction depends on compaction being called after
+ * reclaim so call directly if necessary.
+ * It can become very expensive to allocate transparent hugepages at
+ * fault, so use asynchronous memory compaction for THP unless it is
+ * khugepaged trying to collapse. All other requests should tolerate
+ * at least light sync migration.
*/
+ if (is_thp_gfp_mask(gfp_mask) && !(current->flags & PF_KTHREAD))
+ migration_mode = MIGRATE_ASYNC;
+ else
+ migration_mode = MIGRATE_SYNC_LIGHT;
page = __alloc_pages_direct_compact(gfp_mask, order, alloc_flags,
ac, migration_mode,
&compact_result);