#endif
};
+char * const migratetype_names[MIGRATE_TYPES] = {
+ "Unmovable",
+ "Movable",
+ "Reclaimable",
+ "HighAtomic",
+#ifdef CONFIG_CMA
+ "CMA",
+#endif
+#ifdef CONFIG_MEMORY_ISOLATION
+ "Isolate",
+#endif
+};
+
compound_page_dtor * const compound_page_dtors[] = {
NULL,
free_compound_page,
static unsigned long __initdata required_kernelcore;
static unsigned long __initdata required_movablecore;
static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES];
+static bool mirrored_kernelcore;
/* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */
int movable_zone;
goto out;
}
if (nr_unshown) {
- printk(KERN_ALERT
+ pr_alert(
"BUG: Bad page state: %lu messages suppressed\n",
nr_unshown);
nr_unshown = 0;
if (nr_shown++ == 0)
resume = jiffies + 60 * HZ;
- printk(KERN_ALERT "BUG: Bad page state in process %s pfn:%05lx\n",
+ pr_alert("BUG: Bad page state in process %s pfn:%05lx\n",
current->comm, page_to_pfn(page));
- dump_page_badflags(page, reason, bad_flags);
+ __dump_page(page, reason);
+ bad_flags &= page->flags;
+ if (bad_flags)
+ pr_alert("bad because of flags: %#lx(%pGp)\n",
+ bad_flags, &bad_flags);
+ dump_page_owner(page);
print_modules();
dump_stack();
#ifdef CONFIG_DEBUG_PAGEALLOC
unsigned int _debug_guardpage_minorder;
-bool _debug_pagealloc_enabled __read_mostly;
+bool _debug_pagealloc_enabled __read_mostly
+ = IS_ENABLED(CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT);
+EXPORT_SYMBOL(_debug_pagealloc_enabled);
bool _debug_guardpage_enabled __read_mostly;
static int __init early_debug_pagealloc(char *buf)
if (strcmp(buf, "on") == 0)
_debug_pagealloc_enabled = true;
+ if (strcmp(buf, "off") == 0)
+ _debug_pagealloc_enabled = false;
+
return 0;
}
early_param("debug_pagealloc", early_debug_pagealloc);
PAGE_SIZE << order);
}
arch_free_page(page, order);
+ kernel_poison_pages(page, 1 << order, 0);
kernel_map_pages(page, 1 << order, 0);
return true;
return __free_pages_boot_core(page, pfn, order);
}
+/*
+ * Check that the whole (or subset of) a pageblock given by the interval of
+ * [start_pfn, end_pfn) is valid and within the same zone, before scanning it
+ * with the migration of free compaction scanner. The scanners then need to
+ * use only pfn_valid_within() check for arches that allow holes within
+ * pageblocks.
+ *
+ * Return struct page pointer of start_pfn, or NULL if checks were not passed.
+ *
+ * It's possible on some configurations to have a setup like node0 node1 node0
+ * i.e. it's possible that all pages within a zones range of pages do not
+ * belong to a single zone. We assume that a border between node0 and node1
+ * can occur within a single pageblock, but not a node0 node1 node0
+ * interleaving within a single pageblock. It is therefore sufficient to check
+ * the first and last page of a pageblock and avoid checking each individual
+ * page in a pageblock.
+ */
+struct page *__pageblock_pfn_to_page(unsigned long start_pfn,
+ unsigned long end_pfn, struct zone *zone)
+{
+ struct page *start_page;
+ struct page *end_page;
+
+ /* end_pfn is one past the range we are checking */
+ end_pfn--;
+
+ if (!pfn_valid(start_pfn) || !pfn_valid(end_pfn))
+ return NULL;
+
+ start_page = pfn_to_page(start_pfn);
+
+ if (page_zone(start_page) != zone)
+ return NULL;
+
+ end_page = pfn_to_page(end_pfn);
+
+ /* This gives a shorter code than deriving page_zone(end_page) */
+ if (page_zone_id(start_page) != page_zone_id(end_page))
+ return NULL;
+
+ return start_page;
+}
+
+void set_zone_contiguous(struct zone *zone)
+{
+ unsigned long block_start_pfn = zone->zone_start_pfn;
+ unsigned long block_end_pfn;
+
+ block_end_pfn = ALIGN(block_start_pfn + 1, pageblock_nr_pages);
+ for (; block_start_pfn < zone_end_pfn(zone);
+ block_start_pfn = block_end_pfn,
+ block_end_pfn += pageblock_nr_pages) {
+
+ block_end_pfn = min(block_end_pfn, zone_end_pfn(zone));
+
+ if (!__pageblock_pfn_to_page(block_start_pfn,
+ block_end_pfn, zone))
+ return;
+ }
+
+ /* We confirm that there is no hole */
+ zone->contiguous = true;
+}
+
+void clear_zone_contiguous(struct zone *zone)
+{
+ zone->contiguous = false;
+}
+
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
static void __init deferred_free_range(struct page *page,
unsigned long pfn, int nr_pages)
pgdat_init_report_one_done();
return 0;
}
+#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
void __init page_alloc_init_late(void)
{
+ struct zone *zone;
+
+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
int nid;
/* There will be num_node_state(N_MEMORY) threads */
/* Reinit limits that are based on free pages after the kernel is up */
files_maxfiles_init();
+#endif
+
+ for_each_populated_zone(zone)
+ set_zone_contiguous(zone);
}
-#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
#ifdef CONFIG_CMA
/* Free whole pageblock and set its migration type to MIGRATE_CMA. */
return 0;
}
+static inline bool should_zero(void)
+{
+ return !IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) ||
+ !page_poisoning_enabled();
+}
+
static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags,
int alloc_flags)
{
set_page_refcounted(page);
arch_alloc_page(page, order);
+ kernel_poison_pages(page, 1 << order, 1);
kernel_map_pages(page, 1 << order, 1);
kasan_alloc_pages(page, order);
- if (gfp_flags & __GFP_ZERO)
+ if (should_zero() && gfp_flags & __GFP_ZERO)
for (i = 0; i < (1 << order); i++)
clear_highpage(page + i);
va_end(args);
}
- pr_warn("%s: page allocation failure: order:%u, mode:0x%x\n",
- current->comm, order, gfp_mask);
-
+ pr_warn("%s: page allocation failure: order:%u, mode:%#x(%pGg)\n",
+ current->comm, order, gfp_mask, &gfp_mask);
dump_stack();
if (!should_suppress_show_mem())
show_mem(filter);
* XXX: Page reclaim didn't yield anything,
* and the OOM killer can't be invoked, but
* keep looping as per tradition.
+ *
+ * But do not keep looping if oom_killer_disable()
+ * was already called, for the system is trying to
+ * enter a quiescent state during suspend.
*/
- *did_some_progress = 1;
+ *did_some_progress = !oom_killer_disabled;
goto out;
}
if (pm_suspended_storage())
return (gfp_mask & (GFP_TRANSHUGE | __GFP_KSWAPD_RECLAIM)) == GFP_TRANSHUGE;
}
+/*
+ * Maximum number of reclaim retries without any progress before OOM killer
+ * is consider as the only way to move forward.
+ */
+#define MAX_RECLAIM_RETRIES 16
+
+/*
+ * 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) 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,
+ int no_progress_loops)
+{
+ struct zone *zone;
+ struct zoneref *z;
+
+ /*
+ * Make sure we converge to OOM if we cannot make any progress
+ * several times in the row.
+ */
+ if (no_progress_loops > MAX_RECLAIM_RETRIES)
+ return false;
+
+ /* Do not retry high order allocations unless they are __GFP_REPEAT */
+ if (order > PAGE_ALLOC_COSTLY_ORDER && !(gfp_mask & __GFP_REPEAT))
+ return false;
+
+ /*
+ * Keep reclaiming pages while there is a chance this will lead
+ * somewhere. If none of the target zones can satisfy our allocation
+ * request even if all reclaimable pages are considered then we are
+ * screwed and have to go OOM.
+ */
+ for_each_zone_zonelist_nodemask(zone, z, ac->zonelist,
+ ac->high_zoneidx, ac->nodemask) {
+ unsigned long available;
+ unsigned long reclaimable;
+
+ available = reclaimable = zone_reclaimable_pages(zone);
+ available -= DIV_ROUND_UP(no_progress_loops * available,
+ MAX_RECLAIM_RETRIES);
+ available += zone_page_state_snapshot(zone, NR_FREE_PAGES);
+
+ /*
+ * Would the allocation succeed if we reclaimed the whole
+ * available?
+ */
+ if (__zone_watermark_ok(zone, order, min_wmark_pages(zone),
+ ac->high_zoneidx, alloc_flags, available)) {
+ unsigned long writeback;
+ unsigned long dirty;
+
+ writeback = zone_page_state_snapshot(zone, NR_WRITEBACK);
+ dirty = zone_page_state_snapshot(zone, NR_FILE_DIRTY);
+
+ /*
+ * If we didn't make any progress and have a lot of
+ * dirty + writeback pages then we should wait for
+ * an IO to complete to slow down the reclaim and
+ * prevent from pre mature OOM
+ */
+ if (!did_some_progress && 2*(writeback + dirty) > reclaimable) {
+ congestion_wait(BLK_RW_ASYNC, HZ/10);
+ return true;
+ }
+
+ /*
+ * Memory allocation/reclaim might be called from a WQ
+ * context and the current implementation of the WQ
+ * concurrency control doesn't recognize that
+ * a particular WQ is congested if the worker thread is
+ * looping without ever sleeping. Therefore we have to
+ * do a short sleep here rather than calling
+ * cond_resched().
+ */
+ if (current->flags & PF_WQ_WORKER)
+ schedule_timeout(1);
+ else
+ cond_resched();
+
+ return true;
+ }
+ }
+
+ return false;
+}
+
static inline struct page *
__alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
struct alloc_context *ac)
bool can_direct_reclaim = gfp_mask & __GFP_DIRECT_RECLAIM;
struct page *page = NULL;
int alloc_flags;
- unsigned long pages_reclaimed = 0;
unsigned long did_some_progress;
enum migrate_mode migration_mode = MIGRATE_ASYNC;
bool deferred_compaction = false;
int contended_compaction = COMPACT_CONTENDED_NONE;
+ int no_progress_loops = 0;
/*
* In the slowpath, we sanity check order to avoid ever trying to
if (gfp_mask & __GFP_NORETRY)
goto noretry;
- /* Keep reclaiming pages as long as there is reasonable progress */
- pages_reclaimed += did_some_progress;
- if ((did_some_progress && order <= PAGE_ALLOC_COSTLY_ORDER) ||
- ((gfp_mask & __GFP_REPEAT) && pages_reclaimed < (1 << order))) {
- /* Wait for some write requests to complete then retry */
- wait_iff_congested(ac->preferred_zone, BLK_RW_ASYNC, HZ/50);
+ /*
+ * Costly allocations might have made a progress but this doesn't mean
+ * their order will become available due to high fragmentation so do
+ * not reset the no progress counter for them
+ */
+ if (did_some_progress && order <= PAGE_ALLOC_COSTLY_ORDER)
+ no_progress_loops = 0;
+ else
+ no_progress_loops++;
+
+ if (should_reclaim_retry(gfp_mask, order, ac, alloc_flags,
+ did_some_progress > 0, no_progress_loops))
goto retry;
- }
/* Reclaim has failed us, start killing things */
page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress);
goto got_pg;
/* Retry as long as the OOM killer is making progress */
- if (did_some_progress)
+ if (did_some_progress) {
+ no_progress_loops = 0;
goto retry;
+ }
noretry:
/*
pg_data_t *pgdat = NODE_DATA(nid);
unsigned long pfn;
unsigned long nr_initialised = 0;
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+ struct memblock_region *r = NULL, *tmp;
+#endif
if (highest_memmap_pfn < end_pfn - 1)
highest_memmap_pfn = end_pfn - 1;
for (pfn = start_pfn; pfn < end_pfn; pfn++) {
/*
- * There can be holes in boot-time mem_map[]s
- * handed to this function. They do not
- * exist on hotplugged memory.
+ * There can be holes in boot-time mem_map[]s handed to this
+ * function. They do not exist on hotplugged memory.
*/
- if (context == MEMMAP_EARLY) {
- if (!early_pfn_valid(pfn))
+ if (context != MEMMAP_EARLY)
+ goto not_early;
+
+ if (!early_pfn_valid(pfn))
+ continue;
+ if (!early_pfn_in_nid(pfn, nid))
+ continue;
+ if (!update_defer_init(pgdat, pfn, end_pfn, &nr_initialised))
+ break;
+
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+ /*
+ * If not mirrored_kernelcore and ZONE_MOVABLE exists, range
+ * from zone_movable_pfn[nid] to end of each node should be
+ * ZONE_MOVABLE not ZONE_NORMAL. skip it.
+ */
+ if (!mirrored_kernelcore && zone_movable_pfn[nid])
+ if (zone == ZONE_NORMAL && pfn >= zone_movable_pfn[nid])
continue;
- if (!early_pfn_in_nid(pfn, nid))
+
+ /*
+ * Check given memblock attribute by firmware which can affect
+ * kernel memory layout. If zone==ZONE_MOVABLE but memory is
+ * mirrored, it's an overlapped memmap init. skip it.
+ */
+ if (mirrored_kernelcore && zone == ZONE_MOVABLE) {
+ if (!r || pfn >= memblock_region_memory_end_pfn(r)) {
+ for_each_memblock(memory, tmp)
+ if (pfn < memblock_region_memory_end_pfn(tmp))
+ break;
+ r = tmp;
+ }
+ if (pfn >= memblock_region_memory_base_pfn(r) &&
+ memblock_is_mirror(r)) {
+ /* already initialized as NORMAL */
+ pfn = memblock_region_memory_end_pfn(r);
continue;
- if (!update_defer_init(pgdat, pfn, end_pfn,
- &nr_initialised))
- break;
+ }
}
+#endif
+not_early:
/*
* Mark the block movable so that blocks are reserved for
* movable at startup. This will force kernel allocations
*zone_end_pfn = min(node_end_pfn,
arch_zone_highest_possible_pfn[movable_zone]);
- /* Adjust for ZONE_MOVABLE starting within this range */
- } else if (*zone_start_pfn < zone_movable_pfn[nid] &&
- *zone_end_pfn > zone_movable_pfn[nid]) {
- *zone_end_pfn = zone_movable_pfn[nid];
-
/* Check if this whole range is within ZONE_MOVABLE */
} else if (*zone_start_pfn >= zone_movable_pfn[nid])
*zone_start_pfn = *zone_end_pfn;
unsigned long zone_type,
unsigned long node_start_pfn,
unsigned long node_end_pfn,
+ unsigned long *zone_start_pfn,
+ unsigned long *zone_end_pfn,
unsigned long *ignored)
{
- unsigned long zone_start_pfn, zone_end_pfn;
-
/* When hotadd a new node from cpu_up(), the node should be empty */
if (!node_start_pfn && !node_end_pfn)
return 0;
/* Get the start and end of the zone */
- zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type];
- zone_end_pfn = arch_zone_highest_possible_pfn[zone_type];
+ *zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type];
+ *zone_end_pfn = arch_zone_highest_possible_pfn[zone_type];
adjust_zone_range_for_zone_movable(nid, zone_type,
node_start_pfn, node_end_pfn,
- &zone_start_pfn, &zone_end_pfn);
+ zone_start_pfn, zone_end_pfn);
/* Check that this node has pages within the zone's required range */
- if (zone_end_pfn < node_start_pfn || zone_start_pfn > node_end_pfn)
+ if (*zone_end_pfn < node_start_pfn || *zone_start_pfn > node_end_pfn)
return 0;
/* Move the zone boundaries inside the node if necessary */
- zone_end_pfn = min(zone_end_pfn, node_end_pfn);
- zone_start_pfn = max(zone_start_pfn, node_start_pfn);
+ *zone_end_pfn = min(*zone_end_pfn, node_end_pfn);
+ *zone_start_pfn = max(*zone_start_pfn, node_start_pfn);
/* Return the spanned pages */
- return zone_end_pfn - zone_start_pfn;
+ return *zone_end_pfn - *zone_start_pfn;
}
/*
unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type];
unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type];
unsigned long zone_start_pfn, zone_end_pfn;
+ unsigned long nr_absent;
/* When hotadd a new node from cpu_up(), the node should be empty */
if (!node_start_pfn && !node_end_pfn)
adjust_zone_range_for_zone_movable(nid, zone_type,
node_start_pfn, node_end_pfn,
&zone_start_pfn, &zone_end_pfn);
- return __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn);
+ nr_absent = __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn);
+
+ /*
+ * ZONE_MOVABLE handling.
+ * Treat pages to be ZONE_MOVABLE in ZONE_NORMAL as absent pages
+ * and vice versa.
+ */
+ if (zone_movable_pfn[nid]) {
+ if (mirrored_kernelcore) {
+ unsigned long start_pfn, end_pfn;
+ struct memblock_region *r;
+
+ for_each_memblock(memory, r) {
+ start_pfn = clamp(memblock_region_memory_base_pfn(r),
+ zone_start_pfn, zone_end_pfn);
+ end_pfn = clamp(memblock_region_memory_end_pfn(r),
+ zone_start_pfn, zone_end_pfn);
+
+ if (zone_type == ZONE_MOVABLE &&
+ memblock_is_mirror(r))
+ nr_absent += end_pfn - start_pfn;
+
+ if (zone_type == ZONE_NORMAL &&
+ !memblock_is_mirror(r))
+ nr_absent += end_pfn - start_pfn;
+ }
+ } else {
+ if (zone_type == ZONE_NORMAL)
+ nr_absent += node_end_pfn - zone_movable_pfn[nid];
+ }
+ }
+
+ return nr_absent;
}
#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
unsigned long zone_type,
unsigned long node_start_pfn,
unsigned long node_end_pfn,
+ unsigned long *zone_start_pfn,
+ unsigned long *zone_end_pfn,
unsigned long *zones_size)
{
+ unsigned int zone;
+
+ *zone_start_pfn = node_start_pfn;
+ for (zone = 0; zone < zone_type; zone++)
+ *zone_start_pfn += zones_size[zone];
+
+ *zone_end_pfn = *zone_start_pfn + zones_size[zone_type];
+
return zones_size[zone_type];
}
for (i = 0; i < MAX_NR_ZONES; i++) {
struct zone *zone = pgdat->node_zones + i;
+ unsigned long zone_start_pfn, zone_end_pfn;
unsigned long size, real_size;
size = zone_spanned_pages_in_node(pgdat->node_id, i,
node_start_pfn,
node_end_pfn,
+ &zone_start_pfn,
+ &zone_end_pfn,
zones_size);
real_size = size - zone_absent_pages_in_node(pgdat->node_id, i,
node_start_pfn, node_end_pfn,
zholes_size);
+ if (size)
+ zone->zone_start_pfn = zone_start_pfn;
+ else
+ zone->zone_start_pfn = 0;
zone->spanned_pages = size;
zone->present_pages = real_size;
{
enum zone_type j;
int nid = pgdat->node_id;
- unsigned long zone_start_pfn = pgdat->node_start_pfn;
int ret;
pgdat_resize_init(pgdat);
#endif
init_waitqueue_head(&pgdat->kswapd_wait);
init_waitqueue_head(&pgdat->pfmemalloc_wait);
+#ifdef CONFIG_COMPACTION
+ init_waitqueue_head(&pgdat->kcompactd_wait);
+#endif
pgdat_page_ext_init(pgdat);
for (j = 0; j < MAX_NR_ZONES; j++) {
struct zone *zone = pgdat->node_zones + j;
unsigned long size, realsize, freesize, memmap_pages;
+ unsigned long zone_start_pfn = zone->zone_start_pfn;
size = zone->spanned_pages;
realsize = freesize = zone->present_pages;
ret = init_currently_empty_zone(zone, zone_start_pfn, size);
BUG_ON(ret);
memmap_init(size, nid, j, zone_start_pfn);
- zone_start_pfn += size;
}
}
pr_info("Initmem setup node %d [mem %#018Lx-%#018Lx]\n", nid,
(u64)start_pfn << PAGE_SHIFT,
end_pfn ? ((u64)end_pfn << PAGE_SHIFT) - 1 : 0);
+#else
+ start_pfn = node_start_pfn;
#endif
calculate_node_totalpages(pgdat, start_pfn, end_pfn,
zones_size, zholes_size);
goto out2;
}
+ /*
+ * If kernelcore=mirror is specified, ignore movablecore option
+ */
+ if (mirrored_kernelcore) {
+ bool mem_below_4gb_not_mirrored = false;
+
+ for_each_memblock(memory, r) {
+ if (memblock_is_mirror(r))
+ continue;
+
+ nid = r->nid;
+
+ usable_startpfn = memblock_region_memory_base_pfn(r);
+
+ if (usable_startpfn < 0x100000) {
+ mem_below_4gb_not_mirrored = true;
+ continue;
+ }
+
+ zone_movable_pfn[nid] = zone_movable_pfn[nid] ?
+ min(usable_startpfn, zone_movable_pfn[nid]) :
+ usable_startpfn;
+ }
+
+ if (mem_below_4gb_not_mirrored)
+ pr_warn("This configuration results in unmirrored kernel memory.");
+
+ goto out2;
+ }
+
/*
* If movablecore=nn[KMG] was specified, calculate what size of
* kernelcore that corresponds so that memory usable for
*/
static int __init cmdline_parse_kernelcore(char *p)
{
+ /* parse kernelcore=mirror */
+ if (parse_option_str(p, "mirror")) {
+ mirrored_kernelcore = true;
+ return 0;
+ }
+
return cmdline_parse_core(p, &required_kernelcore);
}
}
#endif
-#ifdef CONFIG_MEMORY_FAILURE
bool is_free_buddy_page(struct page *page)
{
struct zone *zone = page_zone(page);
return order < MAX_ORDER;
}
-#endif