summaryrefslogtreecommitdiffstats
path: root/mm/page_alloc.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/page_alloc.c')
-rw-r--r--mm/page_alloc.c507
1 files changed, 385 insertions, 122 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9d666df5ef95..c46b75d14b6f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -43,6 +43,7 @@
#include <linux/vmalloc.h>
#include <linux/vmstat.h>
#include <linux/mempolicy.h>
+#include <linux/memremap.h>
#include <linux/stop_machine.h>
#include <linux/sort.h>
#include <linux/pfn.h>
@@ -114,13 +115,6 @@ static DEFINE_SPINLOCK(managed_page_count_lock);
unsigned long totalram_pages __read_mostly;
unsigned long totalreserve_pages __read_mostly;
unsigned long totalcma_pages __read_mostly;
-/*
- * When calculating the number of globally allowed dirty pages, there
- * is a certain number of per-zone reserves that should not be
- * considered dirtyable memory. This is the sum of those reserves
- * over all existing zones that contribute dirtyable memory.
- */
-unsigned long dirty_balance_reserve __read_mostly;
int percpu_pagelist_fraction;
gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
@@ -229,13 +223,28 @@ static char * const zone_names[MAX_NR_ZONES] = {
#endif
};
-static void free_compound_page(struct page *page);
+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,
#ifdef CONFIG_HUGETLB_PAGE
free_huge_page,
#endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ free_transhuge_page,
+#endif
};
int min_free_kbytes = 1024;
@@ -251,6 +260,7 @@ static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
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;
@@ -420,7 +430,7 @@ static void bad_page(struct page *page, const char *reason,
goto out;
}
if (nr_unshown) {
- printk(KERN_ALERT
+ pr_alert(
"BUG: Bad page state: %lu messages suppressed\n",
nr_unshown);
nr_unshown = 0;
@@ -430,9 +440,14 @@ static void bad_page(struct page *page, const char *reason,
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();
@@ -457,7 +472,7 @@ out:
* This usage means that zero-order pages may not be compound.
*/
-static void free_compound_page(struct page *page)
+void free_compound_page(struct page *page)
{
__free_pages_ok(page, compound_order(page));
}
@@ -473,13 +488,16 @@ void prep_compound_page(struct page *page, unsigned int order)
for (i = 1; i < nr_pages; i++) {
struct page *p = page + i;
set_page_count(p, 0);
+ p->mapping = TAIL_MAPPING;
set_compound_head(p, page);
}
+ atomic_set(compound_mapcount_ptr(page), -1);
}
#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);
bool _debug_guardpage_enabled __read_mostly;
static int __init early_debug_pagealloc(char *buf)
@@ -490,6 +508,9 @@ 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);
@@ -739,7 +760,7 @@ static inline int free_pages_check(struct page *page)
const char *bad_reason = NULL;
unsigned long bad_flags = 0;
- if (unlikely(page_mapcount(page)))
+ if (unlikely(atomic_read(&page->_mapcount) != -1))
bad_reason = "nonzero mapcount";
if (unlikely(page->mapping != NULL))
bad_reason = "non-NULL mapping";
@@ -812,7 +833,7 @@ static void free_pcppages_bulk(struct zone *zone, int count,
do {
int mt; /* migratetype of the to-be-freed page */
- page = list_entry(list->prev, struct page, lru);
+ page = list_last_entry(list, struct page, lru);
/* must delete as __free_one_page list manipulates */
list_del(&page->lru);
@@ -863,6 +884,27 @@ static int free_tail_pages_check(struct page *head_page, struct page *page)
ret = 0;
goto out;
}
+ switch (page - head_page) {
+ case 1:
+ /* the first tail page: ->mapping is compound_mapcount() */
+ if (unlikely(compound_mapcount(page))) {
+ bad_page(page, "nonzero compound_mapcount", 0);
+ goto out;
+ }
+ break;
+ case 2:
+ /*
+ * the second tail page: ->mapping is
+ * page_deferred_list().next -- ignore value.
+ */
+ break;
+ default:
+ if (page->mapping != TAIL_MAPPING) {
+ bad_page(page, "corrupted mapping in tail page", 0);
+ goto out;
+ }
+ break;
+ }
if (unlikely(!PageTail(page))) {
bad_page(page, "PageTail not set", 0);
goto out;
@@ -873,6 +915,7 @@ static int free_tail_pages_check(struct page *head_page, struct page *page)
}
ret = 0;
out:
+ page->mapping = NULL;
clear_compound_head(page);
return ret;
}
@@ -982,6 +1025,7 @@ static bool free_pages_prepare(struct page *page, unsigned int order)
PAGE_SIZE << order);
}
arch_free_page(page, order);
+ kernel_poison_pages(page, 1 << order, 0);
kernel_map_pages(page, 1 << order, 0);
return true;
@@ -1084,6 +1128,75 @@ void __init __free_pages_bootmem(struct page *page, unsigned long pfn,
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)
@@ -1234,9 +1347,13 @@ free_range:
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 */
@@ -1250,8 +1367,11 @@ void __init page_alloc_init_late(void)
/* 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. */
@@ -1336,7 +1456,7 @@ static inline int check_new_page(struct page *page)
const char *bad_reason = NULL;
unsigned long bad_flags = 0;
- if (unlikely(page_mapcount(page)))
+ if (unlikely(atomic_read(&page->_mapcount) != -1))
bad_reason = "nonzero mapcount";
if (unlikely(page->mapping != NULL))
bad_reason = "non-NULL mapping";
@@ -1361,15 +1481,24 @@ static inline int check_new_page(struct page *page)
return 0;
}
+static inline bool free_pages_prezeroed(bool poisoned)
+{
+ return IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) &&
+ page_poisoning_enabled() && poisoned;
+}
+
static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags,
int alloc_flags)
{
int i;
+ bool poisoned = true;
for (i = 0; i < (1 << order); i++) {
struct page *p = page + i;
if (unlikely(check_new_page(p)))
return 1;
+ if (poisoned)
+ poisoned &= page_is_poisoned(p);
}
set_page_private(page, 0);
@@ -1377,9 +1506,10 @@ static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags,
arch_alloc_page(page, order);
kernel_map_pages(page, 1 << order, 1);
+ kernel_poison_pages(page, 1 << order, 1);
kasan_alloc_pages(page, order);
- if (gfp_flags & __GFP_ZERO)
+ if (!free_pages_prezeroed(poisoned) && (gfp_flags & __GFP_ZERO))
for (i = 0; i < (1 << order); i++)
clear_highpage(page + i);
@@ -1417,11 +1547,10 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order,
/* Find a page of the appropriate size in the preferred list */
for (current_order = order; current_order < MAX_ORDER; ++current_order) {
area = &(zone->free_area[current_order]);
- if (list_empty(&area->free_list[migratetype]))
- continue;
-
- page = list_entry(area->free_list[migratetype].next,
+ page = list_first_entry_or_null(&area->free_list[migratetype],
struct page, lru);
+ if (!page)
+ continue;
list_del(&page->lru);
rmv_page_order(page);
area->nr_free--;
@@ -1700,12 +1829,12 @@ static void unreserve_highatomic_pageblock(const struct alloc_context *ac)
for (order = 0; order < MAX_ORDER; order++) {
struct free_area *area = &(zone->free_area[order]);
- if (list_empty(&area->free_list[MIGRATE_HIGHATOMIC]))
+ page = list_first_entry_or_null(
+ &area->free_list[MIGRATE_HIGHATOMIC],
+ struct page, lru);
+ if (!page)
continue;
- page = list_entry(area->free_list[MIGRATE_HIGHATOMIC].next,
- struct page, lru);
-
/*
* It should never happen but changes to locking could
* inadvertently allow a per-cpu drain to add pages
@@ -1753,7 +1882,7 @@ __rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype)
if (fallback_mt == -1)
continue;
- page = list_entry(area->free_list[fallback_mt].next,
+ page = list_first_entry(&area->free_list[fallback_mt],
struct page, lru);
if (can_steal)
steal_suitable_fallback(zone, page, start_migratetype);
@@ -1788,7 +1917,7 @@ __rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype)
* Call me with the zone->lock already held.
*/
static struct page *__rmqueue(struct zone *zone, unsigned int order,
- int migratetype, gfp_t gfp_flags)
+ int migratetype)
{
struct page *page;
@@ -1818,7 +1947,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
spin_lock(&zone->lock);
for (i = 0; i < count; ++i) {
- struct page *page = __rmqueue(zone, order, migratetype, 0);
+ struct page *page = __rmqueue(zone, order, migratetype);
if (unlikely(page == NULL))
break;
@@ -1988,7 +2117,7 @@ void mark_free_pages(struct zone *zone)
unsigned long pfn, max_zone_pfn;
unsigned long flags;
unsigned int order, t;
- struct list_head *curr;
+ struct page *page;
if (zone_is_empty(zone))
return;
@@ -1998,17 +2127,17 @@ void mark_free_pages(struct zone *zone)
max_zone_pfn = zone_end_pfn(zone);
for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++)
if (pfn_valid(pfn)) {
- struct page *page = pfn_to_page(pfn);
-
+ page = pfn_to_page(pfn);
if (!swsusp_page_is_forbidden(page))
swsusp_unset_page_free(page);
}
for_each_migratetype_order(order, t) {
- list_for_each(curr, &zone->free_area[order].free_list[t]) {
+ list_for_each_entry(page,
+ &zone->free_area[order].free_list[t], lru) {
unsigned long i;
- pfn = page_to_pfn(list_entry(curr, struct page, lru));
+ pfn = page_to_pfn(page);
for (i = 0; i < (1UL << order); i++)
swsusp_set_page_free(pfn_to_page(pfn + i));
}
@@ -2212,9 +2341,9 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
}
if (cold)
- page = list_entry(list->prev, struct page, lru);
+ page = list_last_entry(list, struct page, lru);
else
- page = list_entry(list->next, struct page, lru);
+ page = list_first_entry(list, struct page, lru);
list_del(&page->lru);
pcp->count--;
@@ -2241,7 +2370,7 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
trace_mm_page_alloc_zone_locked(page, order, migratetype);
}
if (!page)
- page = __rmqueue(zone, order, migratetype, gfp_flags);
+ page = __rmqueue(zone, order, migratetype);
spin_unlock(&zone->lock);
if (!page)
goto failed;
@@ -2671,9 +2800,8 @@ void warn_alloc_failed(gfp_t gfp_mask, unsigned int order, const char *fmt, ...)
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);
@@ -2740,8 +2868,21 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
goto out;
}
/* Exhausted what can be done so it's blamo time */
- if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL))
+ if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) {
*did_some_progress = 1;
+
+ if (gfp_mask & __GFP_NOFAIL) {
+ page = get_page_from_freelist(gfp_mask, order,
+ ALLOC_NO_WATERMARKS|ALLOC_CPUSET, ac);
+ /*
+ * fallback to ignore cpuset restriction if our nodes
+ * are depleted
+ */
+ if (!page)
+ page = get_page_from_freelist(gfp_mask, order,
+ ALLOC_NO_WATERMARKS, ac);
+ }
+ }
out:
mutex_unlock(&oom_lock);
return page;
@@ -2876,28 +3017,6 @@ retry:
return page;
}
-/*
- * This is called in the allocator slow-path if the allocation request is of
- * sufficient urgency to ignore watermarks and take other desperate measures
- */
-static inline struct page *
-__alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order,
- const struct alloc_context *ac)
-{
- struct page *page;
-
- do {
- page = get_page_from_freelist(gfp_mask, order,
- ALLOC_NO_WATERMARKS, ac);
-
- if (!page && gfp_mask & __GFP_NOFAIL)
- wait_iff_congested(ac->preferred_zone, BLK_RW_ASYNC,
- HZ/50);
- } while (!page && (gfp_mask & __GFP_NOFAIL));
-
- return page;
-}
-
static void wake_all_kswapds(unsigned int order, const struct alloc_context *ac)
{
struct zoneref *z;
@@ -3042,28 +3161,36 @@ retry:
* allocations are system rather than user orientated
*/
ac->zonelist = node_zonelist(numa_node_id(), gfp_mask);
-
- page = __alloc_pages_high_priority(gfp_mask, order, ac);
-
- if (page) {
+ page = get_page_from_freelist(gfp_mask, order,
+ ALLOC_NO_WATERMARKS, ac);
+ if (page)
goto got_pg;
- }
}
/* Caller is not willing to reclaim, we can't balance anything */
if (!can_direct_reclaim) {
/*
- * All existing users of the deprecated __GFP_NOFAIL are
- * blockable, so warn of any new users that actually allow this
- * type of allocation to fail.
+ * All existing users of the __GFP_NOFAIL are blockable, so warn
+ * of any new users that actually allow this type of allocation
+ * to fail.
*/
WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL);
goto nopage;
}
/* Avoid recursion of direct reclaim */
- if (current->flags & PF_MEMALLOC)
+ if (current->flags & PF_MEMALLOC) {
+ /*
+ * __GFP_NOFAIL request from this context is rather bizarre
+ * because we cannot reclaim anything and only can loop waiting
+ * for somebody to do a work for us.
+ */
+ if (WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) {
+ cond_resched();
+ goto retry;
+ }
goto nopage;
+ }
/* Avoid allocations with no watermarks from looping endlessly */
if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL))
@@ -3402,7 +3529,8 @@ EXPORT_SYMBOL(__free_page_frag);
/*
* alloc_kmem_pages charges newly allocated pages to the kmem resource counter
- * of the current memory cgroup.
+ * of the current memory cgroup if __GFP_ACCOUNT is set, other than that it is
+ * equivalent to alloc_pages.
*
* It should be used when the caller would like to use kmalloc, but since the
* allocation is large, it has to fall back to the page allocator.
@@ -4147,8 +4275,7 @@ static void set_zonelist_order(void)
static void build_zonelists(pg_data_t *pgdat)
{
- int j, node, load;
- enum zone_type i;
+ int i, node, load;
nodemask_t used_mask;
int local_node, prev_node;
struct zonelist *zonelist;
@@ -4168,7 +4295,7 @@ static void build_zonelists(pg_data_t *pgdat)
nodes_clear(used_mask);
memset(node_order, 0, sizeof(node_order));
- j = 0;
+ i = 0;
while ((node = find_next_best_node(local_node, &used_mask)) >= 0) {
/*
@@ -4185,12 +4312,12 @@ static void build_zonelists(pg_data_t *pgdat)
if (order == ZONELIST_ORDER_NODE)
build_zonelists_in_node_order(pgdat, node);
else
- node_order[j++] = node; /* remember order */
+ node_order[i++] = node; /* remember order */
}
if (order == ZONELIST_ORDER_ZONE) {
/* calculate node order -- i.e., DMA last! */
- build_zonelists_in_zone_order(pgdat, j);
+ build_zonelists_in_zone_order(pgdat, i);
}
build_thisnode_zonelists(pgdat);
@@ -4468,32 +4595,72 @@ static inline unsigned long wait_table_bits(unsigned long size)
void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
unsigned long start_pfn, enum memmap_context context)
{
- pg_data_t *pgdat = NODE_DATA(nid);
+ struct vmem_altmap *altmap = to_vmem_altmap(__pfn_to_phys(start_pfn));
unsigned long end_pfn = start_pfn + size;
+ pg_data_t *pgdat = NODE_DATA(nid);
unsigned long pfn;
- struct zone *z;
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;
- z = &pgdat->node_zones[zone];
+ /*
+ * Honor reservation requested by the driver for this ZONE_DEVICE
+ * memory
+ */
+ if (altmap && start_pfn == altmap->base_pfn)
+ start_pfn += altmap->reserve;
+
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
@@ -4910,11 +5077,6 @@ static void __meminit adjust_zone_range_for_zone_movable(int nid,
*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;
@@ -4929,31 +5091,31 @@ static unsigned long __meminit zone_spanned_pages_in_node(int nid,
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;
}
/*
@@ -4999,6 +5161,7 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid,
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)
@@ -5010,7 +5173,39 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid,
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 */
@@ -5018,8 +5213,18 @@ static inline unsigned long __meminit zone_spanned_pages_in_node(int nid,
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];
}
@@ -5048,15 +5253,22 @@ static void __meminit calculate_node_totalpages(struct pglist_data *pgdat,
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;
@@ -5177,7 +5389,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
{
enum zone_type j;
int nid = pgdat->node_id;
- unsigned long zone_start_pfn = pgdat->node_start_pfn;
int ret;
pgdat_resize_init(pgdat);
@@ -5186,6 +5397,11 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
pgdat->numabalancing_migrate_nr_pages = 0;
pgdat->numabalancing_migrate_next_window = jiffies;
#endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+ spin_lock_init(&pgdat->split_queue_lock);
+ INIT_LIST_HEAD(&pgdat->split_queue);
+ pgdat->split_queue_len = 0;
+#endif
init_waitqueue_head(&pgdat->kswapd_wait);
init_waitqueue_head(&pgdat->pfmemalloc_wait);
pgdat_page_ext_init(pgdat);
@@ -5193,6 +5409,7 @@ static void __paginginit free_area_init_core(struct pglist_data *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;
@@ -5261,7 +5478,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
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;
}
}
@@ -5329,6 +5545,8 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_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);
@@ -5500,6 +5718,36 @@ static void __init find_zone_movable_pfns_for_nodes(void)
}
/*
+ * 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
* any allocation type is evenly spread. If both kernelcore
@@ -5759,6 +6007,12 @@ static int __init cmdline_parse_core(char *p, unsigned long *core)
*/
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);
}
@@ -5956,20 +6210,12 @@ static void calculate_totalreserve_pages(void)
if (max > zone->managed_pages)
max = zone->managed_pages;
+
+ zone->totalreserve_pages = max;
+
reserve_pages += max;
- /*
- * Lowmem reserves are not available to
- * GFP_HIGHUSER page cache allocations and
- * kswapd tries to balance zones to their high
- * watermark. As a result, neither should be
- * regarded as dirtyable memory, to prevent a
- * situation where reclaim has to clean pages
- * in order to balance the zones.
- */
- zone->dirty_balance_reserve = max;
}
}
- dirty_balance_reserve = reserve_pages;
totalreserve_pages = reserve_pages;
}
@@ -6599,7 +6845,7 @@ bool is_pageblock_removable_nolock(struct page *page)
return !has_unmovable_pages(zone, page, 0, true);
}
-#ifdef CONFIG_CMA
+#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
static unsigned long pfn_max_align_down(unsigned long pfn)
{
@@ -6724,8 +6970,12 @@ int alloc_contig_range(unsigned long start, unsigned long end,
if (ret)
return ret;
+ /*
+ * In case of -EBUSY, we'd like to know which page causes problem.
+ * So, just fall through. We will check it in test_pages_isolated().
+ */
ret = __alloc_contig_migrate_range(&cc, start, end);
- if (ret)
+ if (ret && ret != -EBUSY)
goto done;
/*
@@ -6752,12 +7002,25 @@ int alloc_contig_range(unsigned long start, unsigned long end,
outer_start = start;
while (!PageBuddy(pfn_to_page(outer_start))) {
if (++order >= MAX_ORDER) {
- ret = -EBUSY;
- goto done;
+ outer_start = start;
+ break;
}
outer_start &= ~0UL << order;
}
+ if (outer_start != start) {
+ order = page_order(pfn_to_page(outer_start));
+
+ /*
+ * outer_start page could be small order buddy page and
+ * it doesn't include start page. Adjust outer_start
+ * in this case to report failed page properly
+ * on tracepoint in test_pages_isolated()
+ */
+ if (outer_start + (1UL << order) <= start)
+ outer_start = start;
+ }
+
/* Make sure the range is really isolated. */
if (test_pages_isolated(outer_start, end, false)) {
pr_info("%s: [%lx, %lx) PFNs busy\n",
OpenPOWER on IntegriCloud