Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 283ac9d..c63656c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -68,6 +68,7 @@
#include <linux/lockdep.h>
#include <linux/nmi.h>
#include <linux/psi.h>
+#include <linux/padata.h>
#include <linux/khugepaged.h>
#include <asm/sections.h>
@@ -75,6 +76,35 @@
#include <asm/div64.h>
#include "internal.h"
#include "shuffle.h"
+#include "page_reporting.h"
+
+/* Free Page Internal flags: for internal, non-pcp variants of free_pages(). */
+typedef int __bitwise fpi_t;
+
+/* No special request */
+#define FPI_NONE ((__force fpi_t)0)
+
+/*
+ * Skip free page reporting notification for the (possibly merged) page.
+ * This does not hinder free page reporting from grabbing the page,
+ * reporting it and marking it "reported" - it only skips notifying
+ * the free page reporting infrastructure about a newly freed page. For
+ * example, used when temporarily pulling a page from a freelist and
+ * putting it back unmodified.
+ */
+#define FPI_SKIP_REPORT_NOTIFY ((__force fpi_t)BIT(0))
+
+/*
+ * Place the (possibly merged) page to the tail of the freelist. Will ignore
+ * page shuffling (relevant code - e.g., memory onlining - is expected to
+ * shuffle the whole zone).
+ *
+ * Note: No code should rely on this flag for correctness - it's purely
+ * to allow for optimizations when handing back either fresh pages
+ * (memory onlining) or untouched pages (page isolation, free page
+ * reporting).
+ */
+#define FPI_TO_TAIL ((__force fpi_t)BIT(1))
/* prevent >1 _updater_ of zone percpu pageset ->high and ->batch fields */
static DEFINE_MUTEX(pcp_batch_high_lock);
@@ -96,7 +126,6 @@
*/
DEFINE_PER_CPU(int, _numa_mem_); /* Kernel "local memory" node */
EXPORT_PER_CPU_SYMBOL(_numa_mem_);
-int _node_numa_mem_[MAX_NUMNODES];
#endif
/* work_structs for global per-cpu drains */
@@ -104,8 +133,8 @@
struct zone *zone;
struct work_struct work;
};
-DEFINE_MUTEX(pcpu_drain_mutex);
-DEFINE_PER_CPU(struct pcpu_drain, pcpu_drain);
+static DEFINE_MUTEX(pcpu_drain_mutex);
+static DEFINE_PER_CPU(struct pcpu_drain, pcpu_drain);
#ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY
volatile unsigned long latent_entropy __latent_entropy;
@@ -155,16 +184,16 @@
int ret;
bool bool_result;
- if (!buf)
- return -EINVAL;
ret = kstrtobool(buf, &bool_result);
+ if (ret)
+ return ret;
if (bool_result && page_poisoning_enabled())
pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, will take precedence over init_on_alloc\n");
if (bool_result)
static_branch_enable(&init_on_alloc);
else
static_branch_disable(&init_on_alloc);
- return ret;
+ return 0;
}
early_param("init_on_alloc", early_init_on_alloc);
@@ -173,16 +202,16 @@
int ret;
bool bool_result;
- if (!buf)
- return -EINVAL;
ret = kstrtobool(buf, &bool_result);
+ if (ret)
+ return ret;
if (bool_result && page_poisoning_enabled())
pr_info("mem auto-init: CONFIG_PAGE_POISONING is on, will take precedence over init_on_free\n");
if (bool_result)
static_branch_enable(&init_on_free);
else
static_branch_disable(&init_on_free);
- return ret;
+ return 0;
}
early_param("init_on_free", early_init_on_free);
@@ -246,7 +275,8 @@
unsigned int pageblock_order __read_mostly;
#endif
-static void __free_pages_ok(struct page *page, unsigned int order);
+static void __free_pages_ok(struct page *page, unsigned int order,
+ fpi_t fpi_flags);
/*
* results with 256, 32 in the lowmem_reserve sysctl:
@@ -303,14 +333,14 @@
#endif
};
-compound_page_dtor * const compound_page_dtors[] = {
- NULL,
- free_compound_page,
+compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS] = {
+ [NULL_COMPOUND_DTOR] = NULL,
+ [COMPOUND_PAGE_DTOR] = free_compound_page,
#ifdef CONFIG_HUGETLB_PAGE
- free_huge_page,
+ [HUGETLB_PAGE_DTOR] = free_huge_page,
#endif
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- free_transhuge_page,
+ [TRANSHUGE_PAGE_DTOR] = free_transhuge_page,
#endif
};
@@ -336,7 +366,6 @@
static unsigned long nr_all_pages __initdata;
static unsigned long dma_reserve __initdata;
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
static unsigned long arch_zone_lowest_possible_pfn[MAX_NR_ZONES] __initdata;
static unsigned long arch_zone_highest_possible_pfn[MAX_NR_ZONES] __initdata;
static unsigned long required_kernelcore __initdata;
@@ -349,7 +378,6 @@
/* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */
int movable_zone;
EXPORT_SYMBOL(movable_zone);
-#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
#if MAX_NUMNODES > 1
unsigned int nr_node_ids __read_mostly = MAX_NUMNODES;
@@ -420,6 +448,8 @@
if (end_pfn < pgdat_end_pfn(NODE_DATA(nid)))
return false;
+ if (NODE_DATA(nid)->first_deferred_pfn != ULONG_MAX)
+ return true;
/*
* We start only with one section of pages, more pages are added as
* needed until the rest of deferred pages are initialized.
@@ -461,25 +491,23 @@
{
#ifdef CONFIG_SPARSEMEM
pfn &= (PAGES_PER_SECTION-1);
- return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
#else
pfn = pfn - round_down(page_zone(page)->zone_start_pfn, pageblock_nr_pages);
- return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
#endif /* CONFIG_SPARSEMEM */
+ return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
}
/**
* get_pfnblock_flags_mask - Return the requested group of flags for the pageblock_nr_pages block of pages
* @page: The page within the block of interest
* @pfn: The target page frame number
- * @end_bitidx: The last bit of interest to retrieve
* @mask: mask of bits that the caller is interested in
*
* Return: pageblock_bits flags
*/
-static __always_inline unsigned long __get_pfnblock_flags_mask(struct page *page,
+static __always_inline
+unsigned long __get_pfnblock_flags_mask(struct page *page,
unsigned long pfn,
- unsigned long end_bitidx,
unsigned long mask)
{
unsigned long *bitmap;
@@ -492,20 +520,18 @@
bitidx &= (BITS_PER_LONG-1);
word = bitmap[word_bitidx];
- bitidx += end_bitidx;
- return (word >> (BITS_PER_LONG - bitidx - 1)) & mask;
+ return (word >> bitidx) & mask;
}
unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long pfn,
- unsigned long end_bitidx,
unsigned long mask)
{
- return __get_pfnblock_flags_mask(page, pfn, end_bitidx, mask);
+ return __get_pfnblock_flags_mask(page, pfn, mask);
}
static __always_inline int get_pfnblock_migratetype(struct page *page, unsigned long pfn)
{
- return __get_pfnblock_flags_mask(page, pfn, PB_migrate_end, MIGRATETYPE_MASK);
+ return __get_pfnblock_flags_mask(page, pfn, MIGRATETYPE_MASK);
}
/**
@@ -513,12 +539,10 @@
* @page: The page within the block of interest
* @flags: The flags to set
* @pfn: The target page frame number
- * @end_bitidx: The last bit of interest
* @mask: mask of bits that the caller is interested in
*/
void set_pfnblock_flags_mask(struct page *page, unsigned long flags,
unsigned long pfn,
- unsigned long end_bitidx,
unsigned long mask)
{
unsigned long *bitmap;
@@ -535,9 +559,8 @@
VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page);
- bitidx += end_bitidx;
- mask <<= (BITS_PER_LONG - bitidx - 1);
- flags <<= (BITS_PER_LONG - bitidx - 1);
+ mask <<= bitidx;
+ flags <<= bitidx;
word = READ_ONCE(bitmap[word_bitidx]);
for (;;) {
@@ -554,8 +577,8 @@
migratetype < MIGRATE_PCPTYPES))
migratetype = MIGRATE_UNMOVABLE;
- set_pageblock_flags_group(page, (unsigned long)migratetype,
- PB_migrate, PB_migrate_end);
+ set_pfnblock_flags_mask(page, (unsigned long)migratetype,
+ page_to_pfn(page), MIGRATETYPE_MASK);
}
#ifdef CONFIG_DEBUG_VM
@@ -610,8 +633,7 @@
}
#endif
-static void bad_page(struct page *page, const char *reason,
- unsigned long bad_flags)
+static void bad_page(struct page *page, const char *reason)
{
static unsigned long resume;
static unsigned long nr_shown;
@@ -640,10 +662,6 @@
pr_alert("BUG: Bad page state in process %s pfn:%05lx\n",
current->comm, page_to_pfn(page));
__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();
@@ -672,7 +690,7 @@
void free_compound_page(struct page *page)
{
mem_cgroup_uncharge(page);
- __free_pages_ok(page, compound_order(page));
+ __free_pages_ok(page, compound_order(page), FPI_NONE);
}
void prep_compound_page(struct page *page, unsigned int order)
@@ -680,8 +698,6 @@
int i;
int nr_pages = 1 << order;
- set_compound_page_dtor(page, COMPOUND_PAGE_DTOR);
- set_compound_order(page, order);
__SetPageHead(page);
for (i = 1; i < nr_pages; i++) {
struct page *p = page + i;
@@ -689,7 +705,12 @@
p->mapping = TAIL_MAPPING;
set_compound_head(p, page);
}
+
+ set_compound_page_dtor(page, COMPOUND_PAGE_DTOR);
+ set_compound_order(page, order);
atomic_set(compound_mapcount_ptr(page), -1);
+ if (hpage_pincount_available(page))
+ atomic_set(compound_pincount_ptr(page), 0);
}
#ifdef CONFIG_DEBUG_PAGEALLOC
@@ -773,7 +794,7 @@
unsigned int order, int migratetype) {}
#endif
-static inline void set_page_order(struct page *page, unsigned int order)
+static inline void set_buddy_order(struct page *page, unsigned int order)
{
set_page_private(page, order);
__SetPageBuddy(page);
@@ -792,32 +813,25 @@
*
* For recording page's order, we use page_private(page).
*/
-static inline int page_is_buddy(struct page *page, struct page *buddy,
+static inline bool page_is_buddy(struct page *page, struct page *buddy,
unsigned int order)
{
- if (page_is_guard(buddy) && page_order(buddy) == order) {
- if (page_zone_id(page) != page_zone_id(buddy))
- return 0;
+ if (!page_is_guard(buddy) && !PageBuddy(buddy))
+ return false;
- VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy);
+ if (buddy_order(buddy) != order)
+ return false;
- return 1;
- }
+ /*
+ * zone check is done late to avoid uselessly calculating
+ * zone/node ids for pages that could never merge.
+ */
+ if (page_zone_id(page) != page_zone_id(buddy))
+ return false;
- if (PageBuddy(buddy) && page_order(buddy) == order) {
- /*
- * zone check is done late to avoid uselessly
- * calculating zone/node ids for pages that could
- * never merge.
- */
- if (page_zone_id(page) != page_zone_id(buddy))
- return 0;
+ VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy);
- VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy);
-
- return 1;
- }
- return 0;
+ return true;
}
#ifdef CONFIG_COMPACTION
@@ -825,11 +839,10 @@
{
struct capture_control *capc = current->capture_control;
- return capc &&
+ return unlikely(capc) &&
!(current->flags & PF_KTHREAD) &&
!capc->page &&
- capc->cc->zone == zone &&
- capc->cc->direct_compaction ? capc : NULL;
+ capc->cc->zone == zone ? capc : NULL;
}
static inline bool
@@ -871,6 +884,82 @@
}
#endif /* CONFIG_COMPACTION */
+/* Used for pages not on another list */
+static inline void add_to_free_list(struct page *page, struct zone *zone,
+ unsigned int order, int migratetype)
+{
+ struct free_area *area = &zone->free_area[order];
+
+ list_add(&page->lru, &area->free_list[migratetype]);
+ area->nr_free++;
+}
+
+/* Used for pages not on another list */
+static inline void add_to_free_list_tail(struct page *page, struct zone *zone,
+ unsigned int order, int migratetype)
+{
+ struct free_area *area = &zone->free_area[order];
+
+ list_add_tail(&page->lru, &area->free_list[migratetype]);
+ area->nr_free++;
+}
+
+/*
+ * Used for pages which are on another list. Move the pages to the tail
+ * of the list - so the moved pages won't immediately be considered for
+ * allocation again (e.g., optimization for memory onlining).
+ */
+static inline void move_to_free_list(struct page *page, struct zone *zone,
+ unsigned int order, int migratetype)
+{
+ struct free_area *area = &zone->free_area[order];
+
+ list_move_tail(&page->lru, &area->free_list[migratetype]);
+}
+
+static inline void del_page_from_free_list(struct page *page, struct zone *zone,
+ unsigned int order)
+{
+ /* clear reported state and update reported page count */
+ if (page_reported(page))
+ __ClearPageReported(page);
+
+ list_del(&page->lru);
+ __ClearPageBuddy(page);
+ set_page_private(page, 0);
+ zone->free_area[order].nr_free--;
+}
+
+/*
+ * If this is not the largest possible page, check if the buddy
+ * of the next-highest order is free. If it is, it's possible
+ * that pages are being freed that will coalesce soon. In case,
+ * that is happening, add the free page to the tail of the list
+ * so it's less likely to be used soon and more likely to be merged
+ * as a higher order page
+ */
+static inline bool
+buddy_merge_likely(unsigned long pfn, unsigned long buddy_pfn,
+ struct page *page, unsigned int order)
+{
+ struct page *higher_page, *higher_buddy;
+ unsigned long combined_pfn;
+
+ if (order >= MAX_ORDER - 2)
+ return false;
+
+ if (!pfn_valid_within(buddy_pfn))
+ return false;
+
+ combined_pfn = buddy_pfn & pfn;
+ higher_page = page + (combined_pfn - pfn);
+ buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1);
+ higher_buddy = higher_page + (buddy_pfn - combined_pfn);
+
+ return pfn_valid_within(buddy_pfn) &&
+ page_is_buddy(higher_page, higher_buddy, order + 1);
+}
+
/*
* Freeing function for a buddy system allocator.
*
@@ -898,13 +987,14 @@
static inline void __free_one_page(struct page *page,
unsigned long pfn,
struct zone *zone, unsigned int order,
- int migratetype)
+ int migratetype, fpi_t fpi_flags)
{
- unsigned long combined_pfn;
- unsigned long uninitialized_var(buddy_pfn);
- struct page *buddy;
- unsigned int max_order;
struct capture_control *capc = task_capc(zone);
+ unsigned long buddy_pfn;
+ unsigned long combined_pfn;
+ unsigned int max_order;
+ struct page *buddy;
+ bool to_tail;
max_order = min_t(unsigned int, MAX_ORDER - 1, pageblock_order);
@@ -939,7 +1029,7 @@
if (page_is_guard(buddy))
clear_page_guard(zone, buddy, order, migratetype);
else
- del_page_from_free_area(buddy, &zone->free_area[order]);
+ del_page_from_free_list(buddy, zone, order);
combined_pfn = buddy_pfn & pfn;
page = page + (combined_pfn - pfn);
pfn = combined_pfn;
@@ -971,37 +1061,23 @@
}
done_merging:
- set_page_order(page, order);
+ set_buddy_order(page, order);
- /*
- * If this is not the largest possible page, check if the buddy
- * of the next-highest order is free. If it is, it's possible
- * that pages are being freed that will coalesce soon. In case,
- * that is happening, add the free page to the tail of the list
- * so it's less likely to be used soon and more likely to be merged
- * as a higher order page
- */
- if ((order < MAX_ORDER-2) && pfn_valid_within(buddy_pfn)
- && !is_shuffle_order(order)) {
- struct page *higher_page, *higher_buddy;
- combined_pfn = buddy_pfn & pfn;
- higher_page = page + (combined_pfn - pfn);
- buddy_pfn = __find_buddy_pfn(combined_pfn, order + 1);
- higher_buddy = higher_page + (buddy_pfn - combined_pfn);
- if (pfn_valid_within(buddy_pfn) &&
- page_is_buddy(higher_page, higher_buddy, order + 1)) {
- add_to_free_area_tail(page, &zone->free_area[order],
- migratetype);
- return;
- }
- }
-
- if (is_shuffle_order(order))
- add_to_free_area_random(page, &zone->free_area[order],
- migratetype);
+ if (fpi_flags & FPI_TO_TAIL)
+ to_tail = true;
+ else if (is_shuffle_order(order))
+ to_tail = shuffle_pick_tail();
else
- add_to_free_area(page, &zone->free_area[order], migratetype);
+ to_tail = buddy_merge_likely(pfn, buddy_pfn, page, order);
+ if (to_tail)
+ add_to_free_list_tail(page, zone, order, migratetype);
+ else
+ add_to_free_list(page, zone, order, migratetype);
+
+ /* Notify page reporting subsystem of freed page */
+ if (!(fpi_flags & FPI_SKIP_REPORT_NOTIFY))
+ page_reporting_notify_free(order);
}
/*
@@ -1026,13 +1102,9 @@
return true;
}
-static void free_pages_check_bad(struct page *page)
+static const char *page_bad_reason(struct page *page, unsigned long flags)
{
- const char *bad_reason;
- unsigned long bad_flags;
-
- bad_reason = NULL;
- bad_flags = 0;
+ const char *bad_reason = NULL;
if (unlikely(atomic_read(&page->_mapcount) != -1))
bad_reason = "nonzero mapcount";
@@ -1040,24 +1112,32 @@
bad_reason = "non-NULL mapping";
if (unlikely(page_ref_count(page) != 0))
bad_reason = "nonzero _refcount";
- if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_FREE)) {
- bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set";
- bad_flags = PAGE_FLAGS_CHECK_AT_FREE;
+ if (unlikely(page->flags & flags)) {
+ if (flags == PAGE_FLAGS_CHECK_AT_PREP)
+ bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag(s) set";
+ else
+ bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set";
}
#ifdef CONFIG_MEMCG
if (unlikely(page->mem_cgroup))
bad_reason = "page still charged to cgroup";
#endif
- bad_page(page, bad_reason, bad_flags);
+ return bad_reason;
}
-static inline int free_pages_check(struct page *page)
+static void check_free_page_bad(struct page *page)
+{
+ bad_page(page,
+ page_bad_reason(page, PAGE_FLAGS_CHECK_AT_FREE));
+}
+
+static inline int check_free_page(struct page *page)
{
if (likely(page_expected_state(page, PAGE_FLAGS_CHECK_AT_FREE)))
return 0;
/* Something has gone sideways, find it */
- free_pages_check_bad(page);
+ check_free_page_bad(page);
return 1;
}
@@ -1079,7 +1159,7 @@
case 1:
/* the first tail page: ->mapping may be compound_mapcount() */
if (unlikely(compound_mapcount(page))) {
- bad_page(page, "nonzero compound_mapcount", 0);
+ bad_page(page, "nonzero compound_mapcount");
goto out;
}
break;
@@ -1091,17 +1171,17 @@
break;
default:
if (page->mapping != TAIL_MAPPING) {
- bad_page(page, "corrupted mapping in tail page", 0);
+ bad_page(page, "corrupted mapping in tail page");
goto out;
}
break;
}
if (unlikely(!PageTail(page))) {
- bad_page(page, "PageTail not set", 0);
+ bad_page(page, "PageTail not set");
goto out;
}
if (unlikely(compound_head(page) != head_page)) {
- bad_page(page, "compound_head not consistent", 0);
+ bad_page(page, "compound_head not consistent");
goto out;
}
ret = 0;
@@ -1115,8 +1195,11 @@
{
int i;
+ /* s390's use of memset() could override KASAN redzones. */
+ kasan_disable_current();
for (i = 0; i < numpages; i++)
clear_highpage(page + i);
+ kasan_enable_current();
}
static __always_inline bool free_pages_prepare(struct page *page,
@@ -1128,6 +1211,17 @@
trace_mm_page_free(page, order);
+ if (unlikely(PageHWPoison(page)) && !order) {
+ /*
+ * Do not let hwpoison pages hit pcplists/buddy
+ * Untie memcg state and reset page's owner
+ */
+ if (memcg_kmem_enabled() && PageKmemcg(page))
+ __memcg_kmem_uncharge_page(page, order);
+ reset_page_owner(page, order);
+ return false;
+ }
+
/*
* Check tail pages before head page information is cleared to
* avoid checking PageCompound for order-0 pages.
@@ -1143,7 +1237,7 @@
for (i = 1; i < (1 << order); i++) {
if (compound)
bad += free_tail_pages_check(page, page + i);
- if (unlikely(free_pages_check(page + i))) {
+ if (unlikely(check_free_page(page + i))) {
bad++;
continue;
}
@@ -1153,9 +1247,9 @@
if (PageMappingFlags(page))
page->mapping = NULL;
if (memcg_kmem_enabled() && PageKmemcg(page))
- __memcg_kmem_uncharge(page, order);
+ __memcg_kmem_uncharge_page(page, order);
if (check_free)
- bad += free_pages_check(page);
+ bad += check_free_page(page);
if (bad)
return false;
@@ -1202,7 +1296,7 @@
static bool bulkfree_pcp_prepare(struct page *page)
{
if (debug_pagealloc_enabled_static())
- return free_pages_check(page);
+ return check_free_page(page);
else
return false;
}
@@ -1223,7 +1317,7 @@
static bool bulkfree_pcp_prepare(struct page *page)
{
- return free_pages_check(page);
+ return check_free_page(page);
}
#endif /* CONFIG_DEBUG_VM */
@@ -1323,7 +1417,7 @@
if (unlikely(isolated_pageblocks))
mt = get_pageblock_migratetype(page);
- __free_one_page(page, page_to_pfn(page), zone, 0, mt);
+ __free_one_page(page, page_to_pfn(page), zone, 0, mt, FPI_NONE);
trace_mm_page_pcpu_drain(page, 0, mt);
}
spin_unlock(&zone->lock);
@@ -1332,14 +1426,14 @@
static void free_one_page(struct zone *zone,
struct page *page, unsigned long pfn,
unsigned int order,
- int migratetype)
+ int migratetype, fpi_t fpi_flags)
{
spin_lock(&zone->lock);
if (unlikely(has_isolate_pageblock(zone) ||
is_migrate_isolate(migratetype))) {
migratetype = get_pfnblock_migratetype(page, pfn);
}
- __free_one_page(page, pfn, zone, order, migratetype);
+ __free_one_page(page, pfn, zone, order, migratetype, fpi_flags);
spin_unlock(&zone->lock);
}
@@ -1417,7 +1511,8 @@
}
}
-static void __free_pages_ok(struct page *page, unsigned int order)
+static void __free_pages_ok(struct page *page, unsigned int order,
+ fpi_t fpi_flags)
{
unsigned long flags;
int migratetype;
@@ -1429,7 +1524,8 @@
migratetype = get_pfnblock_migratetype(page, pfn);
local_irq_save(flags);
__count_vm_events(PGFREE, 1 << order);
- free_one_page(page_zone(page), page, pfn, order, migratetype);
+ free_one_page(page_zone(page), page, pfn, order, migratetype,
+ fpi_flags);
local_irq_restore(flags);
}
@@ -1439,6 +1535,11 @@
struct page *p = page;
unsigned int loop;
+ /*
+ * When initializing the memmap, __init_single_page() sets the refcount
+ * of all pages to 1 ("allocated"/"not free"). We have to set the
+ * refcount of all involved pages to 0.
+ */
prefetchw(p);
for (loop = 0; loop < (nr_pages - 1); loop++, p++) {
prefetchw(p + 1);
@@ -1449,15 +1550,43 @@
set_page_count(p, 0);
atomic_long_add(nr_pages, &page_zone(page)->managed_pages);
- set_page_refcounted(page);
- __free_pages(page, order);
+
+ /*
+ * Bypass PCP and place fresh pages right to the tail, primarily
+ * relevant for memory onlining.
+ */
+ __free_pages_ok(page, order, FPI_TO_TAIL);
}
-#if defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) || \
- defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP)
+#ifdef CONFIG_NEED_MULTIPLE_NODES
static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata;
+#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
+
+/*
+ * Required by SPARSEMEM. Given a PFN, return what node the PFN is on.
+ */
+int __meminit __early_pfn_to_nid(unsigned long pfn,
+ struct mminit_pfnnid_cache *state)
+{
+ unsigned long start_pfn, end_pfn;
+ int nid;
+
+ if (state->last_start <= pfn && pfn < state->last_end)
+ return state->last_nid;
+
+ nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn);
+ if (nid != NUMA_NO_NODE) {
+ state->last_start = start_pfn;
+ state->last_end = end_pfn;
+ state->last_nid = nid;
+ }
+
+ return nid;
+}
+#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */
+
int __meminit early_pfn_to_nid(unsigned long pfn)
{
static DEFINE_SPINLOCK(early_pfn_lock);
@@ -1471,27 +1600,7 @@
return nid;
}
-#endif
-
-#ifdef CONFIG_NODES_SPAN_OTHER_NODES
-/* Only safe to use early in boot when initialisation is single-threaded */
-static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
-{
- int nid;
-
- nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache);
- if (nid >= 0 && nid != node)
- return false;
- return true;
-}
-
-#else
-static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
-{
- return true;
-}
-#endif
-
+#endif /* CONFIG_NEED_MULTIPLE_NODES */
void __init memblock_free_pages(struct page *page, unsigned long pfn,
unsigned int order)
@@ -1768,16 +1877,43 @@
return nr_pages;
}
+static void __init
+deferred_init_memmap_chunk(unsigned long start_pfn, unsigned long end_pfn,
+ void *arg)
+{
+ unsigned long spfn, epfn;
+ struct zone *zone = arg;
+ u64 i;
+
+ deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn, start_pfn);
+
+ /*
+ * Initialize and free pages in MAX_ORDER sized increments so that we
+ * can avoid introducing any issues with the buddy allocator.
+ */
+ while (spfn < end_pfn) {
+ deferred_init_maxorder(&i, zone, &spfn, &epfn);
+ cond_resched();
+ }
+}
+
+/* An arch may override for more concurrency. */
+__weak int __init
+deferred_page_init_max_threads(const struct cpumask *node_cpumask)
+{
+ return 1;
+}
+
/* Initialise remaining memory on a node */
static int __init deferred_init_memmap(void *data)
{
pg_data_t *pgdat = data;
const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
- unsigned long spfn = 0, epfn = 0, nr_pages = 0;
+ unsigned long spfn = 0, epfn = 0;
unsigned long first_init_pfn, flags;
unsigned long start = jiffies;
struct zone *zone;
- int zid;
+ int zid, max_threads;
u64 i;
/* Bind memory initialisation thread to a local node if possible */
@@ -1816,21 +1952,30 @@
first_init_pfn))
goto zone_empty;
- /*
- * Initialize and free pages in MAX_ORDER sized increments so
- * that we can avoid introducing any issues with the buddy
- * allocator.
- */
+ max_threads = deferred_page_init_max_threads(cpumask);
+
while (spfn < epfn) {
- nr_pages += deferred_init_maxorder(&i, zone, &spfn, &epfn);
- cond_resched();
+ unsigned long epfn_align = ALIGN(epfn, PAGES_PER_SECTION);
+ struct padata_mt_job job = {
+ .thread_fn = deferred_init_memmap_chunk,
+ .fn_arg = zone,
+ .start = spfn,
+ .size = epfn_align - spfn,
+ .align = PAGES_PER_SECTION,
+ .min_chunk = PAGES_PER_SECTION,
+ .max_threads = max_threads,
+ };
+
+ padata_do_multithreaded(&job);
+ deferred_init_mem_pfn_range_in_zone(&i, zone, &spfn, &epfn,
+ epfn_align);
}
zone_empty:
/* Sanity check that the next zone really is unpopulated */
WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone));
- pr_info("node %d initialised, %lu pages in %ums\n",
- pgdat->node_id, nr_pages, jiffies_to_msecs(jiffies - start));
+ pr_info("node %d deferred pages initialised in %ums\n",
+ pgdat->node_id, jiffies_to_msecs(jiffies - start));
pgdat_init_report_one_done();
return 0;
@@ -2016,13 +2161,11 @@
* -- nyc
*/
static inline void expand(struct zone *zone, struct page *page,
- int low, int high, struct free_area *area,
- int migratetype)
+ int low, int high, int migratetype)
{
unsigned long size = 1 << high;
while (high > low) {
- area--;
high--;
size >>= 1;
VM_BUG_ON_PAGE(bad_range(zone, &page[size]), &page[size]);
@@ -2036,38 +2179,21 @@
if (set_page_guard(zone, &page[size], high, migratetype))
continue;
- add_to_free_area(&page[size], area, migratetype);
- set_page_order(&page[size], high);
+ add_to_free_list(&page[size], zone, high, migratetype);
+ set_buddy_order(&page[size], high);
}
}
static void check_new_page_bad(struct page *page)
{
- const char *bad_reason = NULL;
- unsigned long bad_flags = 0;
-
- if (unlikely(atomic_read(&page->_mapcount) != -1))
- bad_reason = "nonzero mapcount";
- if (unlikely(page->mapping != NULL))
- bad_reason = "non-NULL mapping";
- if (unlikely(page_ref_count(page) != 0))
- bad_reason = "nonzero _refcount";
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";
- bad_flags = PAGE_FLAGS_CHECK_AT_PREP;
- }
-#ifdef CONFIG_MEMCG
- if (unlikely(page->mem_cgroup))
- bad_reason = "page still charged to cgroup";
-#endif
- bad_page(page, bad_reason, bad_flags);
+
+ bad_page(page,
+ page_bad_reason(page, PAGE_FLAGS_CHECK_AT_PREP));
}
/*
@@ -2194,8 +2320,8 @@
page = get_page_from_free_area(area, migratetype);
if (!page)
continue;
- del_page_from_free_area(page, area);
- expand(zone, page, order, current_order, area, migratetype);
+ del_page_from_free_list(page, zone, current_order);
+ expand(zone, page, order, current_order, migratetype);
set_pcppage_migratetype(page, migratetype);
return page;
}
@@ -2208,7 +2334,7 @@
* This array describes the order lists are fallen back to when
* the free lists for the desirable migrate type are depleted
*/
-static int fallbacks[MIGRATE_TYPES][4] = {
+static int fallbacks[MIGRATE_TYPES][3] = {
[MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_TYPES },
[MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_TYPES },
[MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_TYPES },
@@ -2232,7 +2358,7 @@
#endif
/*
- * Move the free pages in a range to the free lists of the requested type.
+ * Move the free pages in a range to the freelist tail of the requested type.
* Note that start_page and end_pages are not aligned on a pageblock
* boundary. If alignment is required, use move_freepages_block()
*/
@@ -2268,8 +2394,8 @@
VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);
VM_BUG_ON_PAGE(page_zone(page) != zone, page);
- order = page_order(page);
- move_to_free_area(page, &zone->free_area[order], migratetype);
+ order = buddy_order(page);
+ move_to_free_list(page, zone, order, migratetype);
page += 1 << order;
pages_moved += 1 << order;
}
@@ -2394,8 +2520,7 @@
static void steal_suitable_fallback(struct zone *zone, struct page *page,
unsigned int alloc_flags, int start_type, bool whole_block)
{
- unsigned int current_order = page_order(page);
- struct free_area *area;
+ unsigned int current_order = buddy_order(page);
int free_pages, movable_pages, alike_pages;
int old_block_type;
@@ -2465,8 +2590,7 @@
return;
single_page:
- area = &zone->free_area[current_order];
- move_to_free_area(page, area, start_type);
+ move_to_free_list(page, zone, current_order, start_type);
}
/*
@@ -2563,7 +2687,7 @@
int order;
bool ret;
- for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->high_zoneidx,
+ for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->highest_zoneidx,
ac->nodemask) {
/*
* Preserve at least one pageblock unless memory pressure
@@ -2722,18 +2846,33 @@
{
struct page *page;
+ if (IS_ENABLED(CONFIG_CMA)) {
+ /*
+ * Balance movable allocations between regular and CMA areas by
+ * allocating from CMA when over half of the zone's free memory
+ * is in the CMA area.
+ */
+ if (alloc_flags & ALLOC_CMA &&
+ zone_page_state(zone, NR_FREE_CMA_PAGES) >
+ zone_page_state(zone, NR_FREE_PAGES) / 2) {
+ page = __rmqueue_cma_fallback(zone, order);
+ if (page)
+ goto out;
+ }
+ }
retry:
page = __rmqueue_smallest(zone, order, migratetype);
if (unlikely(!page)) {
- if (migratetype == MIGRATE_MOVABLE)
+ if (alloc_flags & ALLOC_CMA)
page = __rmqueue_cma_fallback(zone, order);
if (!page && __rmqueue_fallback(zone, order, migratetype,
alloc_flags))
goto retry;
}
-
- trace_mm_page_alloc_zone_locked(page, order, migratetype);
+out:
+ if (page)
+ trace_mm_page_alloc_zone_locked(page, order, migratetype);
return page;
}
@@ -3045,7 +3184,8 @@
*/
if (migratetype >= MIGRATE_PCPTYPES) {
if (unlikely(is_migrate_isolate(migratetype))) {
- free_one_page(zone, page, pfn, 0, migratetype);
+ free_one_page(zone, page, pfn, 0, migratetype,
+ FPI_NONE);
return;
}
migratetype = MIGRATE_MOVABLE;
@@ -3132,12 +3272,12 @@
for (i = 1; i < (1 << order); i++)
set_page_refcounted(page + i);
split_page_owner(page, 1 << order);
+ split_page_memcg(page, 1 << order);
}
EXPORT_SYMBOL_GPL(split_page);
int __isolate_free_page(struct page *page, unsigned int order)
{
- struct free_area *area = &page_zone(page)->free_area[order];
unsigned long watermark;
struct zone *zone;
int mt;
@@ -3163,7 +3303,7 @@
/* Remove page from free list */
- del_page_from_free_area(page, area);
+ del_page_from_free_list(page, zone, order);
/*
* Set the pageblock if the isolated page is at least half of a
@@ -3184,6 +3324,27 @@
return 1UL << order;
}
+/**
+ * __putback_isolated_page - Return a now-isolated page back where we got it
+ * @page: Page that was isolated
+ * @order: Order of the isolated page
+ * @mt: The page's pageblock's migratetype
+ *
+ * This function is meant to return a page pulled from the free lists via
+ * __isolate_free_page back to the free lists they were pulled from.
+ */
+void __putback_isolated_page(struct page *page, unsigned int order, int mt)
+{
+ struct zone *zone = page_zone(page);
+
+ /* zone lock should be held when this function is called */
+ lockdep_assert_held(&zone->lock);
+
+ /* Return isolated page to tail of freelist. */
+ __free_one_page(page, page_to_pfn(page), zone, order, mt,
+ FPI_SKIP_REPORT_NOTIFY | FPI_TO_TAIL);
+}
+
/*
* Update NUMA hit/miss statistics
*
@@ -3271,9 +3432,16 @@
struct page *page;
if (likely(order == 0)) {
- page = rmqueue_pcplist(preferred_zone, zone, gfp_flags,
+ /*
+ * MIGRATE_MOVABLE pcplist could have the pages on CMA area and
+ * we need to skip it when CMA area isn't allowed.
+ */
+ if (!IS_ENABLED(CONFIG_CMA) || alloc_flags & ALLOC_CMA ||
+ migratetype != MIGRATE_MOVABLE) {
+ page = rmqueue_pcplist(preferred_zone, zone, gfp_flags,
migratetype, alloc_flags);
- goto out;
+ goto out;
+ }
}
/*
@@ -3285,7 +3453,13 @@
do {
page = NULL;
- if (alloc_flags & ALLOC_HARDER) {
+ /*
+ * order-0 request can reach here when the pcplist is skipped
+ * due to non-CMA allocation context. HIGHATOMIC area is
+ * reserved for high-order atomic allocation, so order-0
+ * request should skip it.
+ */
+ if (order > 0 && alloc_flags & ALLOC_HARDER) {
page = __rmqueue_smallest(zone, order, MIGRATE_HIGHATOMIC);
if (page)
trace_mm_page_alloc_zone_locked(page, order, migratetype);
@@ -3392,6 +3566,29 @@
}
ALLOW_ERROR_INJECTION(should_fail_alloc_page, TRUE);
+static inline long __zone_watermark_unusable_free(struct zone *z,
+ unsigned int order, unsigned int alloc_flags)
+{
+ const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
+ long unusable_free = (1 << order) - 1;
+
+ /*
+ * If the caller does not have rights to ALLOC_HARDER then subtract
+ * the high-atomic reserves. This will over-estimate the size of the
+ * atomic reserve but it avoids a search.
+ */
+ if (likely(!alloc_harder))
+ unusable_free += z->nr_reserved_highatomic;
+
+#ifdef CONFIG_CMA
+ /* If allocation can't use CMA areas don't use free CMA pages */
+ if (!(alloc_flags & ALLOC_CMA))
+ unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES);
+#endif
+
+ return unusable_free;
+}
+
/*
* Return true if free base pages are above 'mark'. For high-order checks it
* will return true of the order-0 watermark is reached and there is at least
@@ -3399,7 +3596,7 @@
* to check in the allocation paths if no pages are free.
*/
bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
- int classzone_idx, unsigned int alloc_flags,
+ int highest_zoneidx, unsigned int alloc_flags,
long free_pages)
{
long min = mark;
@@ -3407,19 +3604,12 @@
const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
/* free_pages may go negative - that's OK */
- free_pages -= (1 << order) - 1;
+ free_pages -= __zone_watermark_unusable_free(z, order, alloc_flags);
if (alloc_flags & ALLOC_HIGH)
min -= min / 2;
- /*
- * If the caller does not have rights to ALLOC_HARDER then subtract
- * the high-atomic reserves. This will over-estimate the size of the
- * atomic reserve but it avoids a search.
- */
- if (likely(!alloc_harder)) {
- free_pages -= z->nr_reserved_highatomic;
- } else {
+ if (unlikely(alloc_harder)) {
/*
* OOM victims can try even harder than normal ALLOC_HARDER
* users on the grounds that it's definitely going to be in
@@ -3432,19 +3622,12 @@
min -= min / 4;
}
-
-#ifdef CONFIG_CMA
- /* If allocation can't use CMA areas don't use free CMA pages */
- if (!(alloc_flags & ALLOC_CMA))
- free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);
-#endif
-
/*
* Check watermarks for an order-0 allocation request. If these
* are not met, then a high-order request also cannot go ahead
* even if a suitable page happened to be free.
*/
- if (free_pages <= min + z->lowmem_reserve[classzone_idx])
+ if (free_pages <= min + z->lowmem_reserve[highest_zoneidx])
return false;
/* If this is an order-0 request then the watermark is fine */
@@ -3470,44 +3653,41 @@
return true;
}
#endif
- if (alloc_harder &&
- !list_empty(&area->free_list[MIGRATE_HIGHATOMIC]))
+ if (alloc_harder && !free_area_empty(area, MIGRATE_HIGHATOMIC))
return true;
}
return false;
}
bool zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
- int classzone_idx, unsigned int alloc_flags)
+ int highest_zoneidx, unsigned int alloc_flags)
{
- return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
+ return __zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags,
zone_page_state(z, NR_FREE_PAGES));
}
static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
- unsigned long mark, int classzone_idx,
+ unsigned long mark, int highest_zoneidx,
unsigned int alloc_flags, gfp_t gfp_mask)
{
- long free_pages = zone_page_state(z, NR_FREE_PAGES);
- long cma_pages = 0;
+ long free_pages;
-#ifdef CONFIG_CMA
- /* If allocation can't use CMA areas don't use free CMA pages */
- if (!(alloc_flags & ALLOC_CMA))
- cma_pages = zone_page_state(z, NR_FREE_CMA_PAGES);
-#endif
+ free_pages = zone_page_state(z, NR_FREE_PAGES);
/*
* Fast check for order-0 only. If this fails then the reserves
- * need to be calculated. There is a corner case where the check
- * passes but only the high-order atomic reserve are free. If
- * the caller is !atomic then it'll uselessly search the free
- * list. That corner case is then slower but it is harmless.
+ * need to be calculated.
*/
- if (!order && (free_pages - cma_pages) > mark + z->lowmem_reserve[classzone_idx])
- return true;
+ if (!order) {
+ long fast_free;
- if (__zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
+ fast_free = free_pages;
+ fast_free -= __zone_watermark_unusable_free(z, 0, alloc_flags);
+ if (fast_free > mark + z->lowmem_reserve[highest_zoneidx])
+ return true;
+ }
+
+ if (__zone_watermark_ok(z, order, mark, highest_zoneidx, alloc_flags,
free_pages))
return true;
/*
@@ -3519,7 +3699,7 @@
if (unlikely(!order && (gfp_mask & __GFP_ATOMIC) && z->watermark_boost
&& ((alloc_flags & ALLOC_WMARK_MASK) == WMARK_MIN))) {
mark = z->_watermark[WMARK_MIN];
- return __zone_watermark_ok(z, order, mark, classzone_idx,
+ return __zone_watermark_ok(z, order, mark, highest_zoneidx,
alloc_flags, free_pages);
}
@@ -3527,14 +3707,14 @@
}
bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
- unsigned long mark, int classzone_idx)
+ unsigned long mark, int highest_zoneidx)
{
long free_pages = zone_page_state(z, NR_FREE_PAGES);
if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark)
free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES);
- return __zone_watermark_ok(z, order, mark, classzone_idx, 0,
+ return __zone_watermark_ok(z, order, mark, highest_zoneidx, 0,
free_pages);
}
@@ -3562,10 +3742,13 @@
static inline unsigned int
alloc_flags_nofragment(struct zone *zone, gfp_t gfp_mask)
{
- unsigned int alloc_flags = 0;
+ unsigned int alloc_flags;
- if (gfp_mask & __GFP_KSWAPD_RECLAIM)
- alloc_flags |= ALLOC_KSWAPD;
+ /*
+ * __GFP_KSWAPD_RECLAIM is assumed to be the same as ALLOC_KSWAPD
+ * to save a branch.
+ */
+ alloc_flags = (__force int) (gfp_mask & __GFP_KSWAPD_RECLAIM);
#ifdef CONFIG_ZONE_DMA32
if (!zone)
@@ -3588,6 +3771,20 @@
return alloc_flags;
}
+static inline unsigned int current_alloc_flags(gfp_t gfp_mask,
+ unsigned int alloc_flags)
+{
+#ifdef CONFIG_CMA
+ unsigned int pflags = current->flags;
+
+ if (!(pflags & PF_MEMALLOC_NOCMA) &&
+ gfp_migratetype(gfp_mask) == MIGRATE_MOVABLE)
+ alloc_flags |= ALLOC_CMA;
+
+#endif
+ return alloc_flags;
+}
+
/*
* get_page_from_freelist goes through the zonelist trying to allocate
* a page.
@@ -3608,8 +3805,8 @@
*/
no_fallback = alloc_flags & ALLOC_NOFRAGMENT;
z = ac->preferred_zoneref;
- for_next_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx,
- ac->nodemask) {
+ for_next_zone_zonelist_nodemask(zone, z, ac->highest_zoneidx,
+ ac->nodemask) {
struct page *page;
unsigned long mark;
@@ -3664,7 +3861,7 @@
mark = wmark_pages(zone, alloc_flags & ALLOC_WMARK_MASK);
if (!zone_watermark_fast(zone, order, mark,
- ac_classzone_idx(ac), alloc_flags,
+ ac->highest_zoneidx, alloc_flags,
gfp_mask)) {
int ret;
@@ -3698,7 +3895,7 @@
default:
/* did we reclaim enough */
if (zone_watermark_ok(zone, order, mark,
- ac_classzone_idx(ac), alloc_flags))
+ ac->highest_zoneidx, alloc_flags))
goto try_this_zone;
continue;
@@ -3767,7 +3964,9 @@
va_list args;
static DEFINE_RATELIMIT_STATE(nopage_rs, 10*HZ, 1);
- if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs))
+ if ((gfp_mask & __GFP_NOWARN) ||
+ !__ratelimit(&nopage_rs) ||
+ ((gfp_mask & __GFP_DMA) && !has_managed_dma()))
return;
va_start(args, fmt);
@@ -3853,11 +4052,13 @@
* success so it is time to admit defeat. We will skip the OOM killer
* because it is very likely that the caller has a more reasonable
* fallback than shooting a random task.
+ *
+ * The OOM killer may not free memory on a specific node.
*/
- if (gfp_mask & __GFP_RETRY_MAYFAIL)
+ if (gfp_mask & (__GFP_RETRY_MAYFAIL | __GFP_THISNODE))
goto out;
/* The OOM killer does not needlessly kill tasks for lowmem */
- if (ac->high_zoneidx < ZONE_NORMAL)
+ if (ac->highest_zoneidx < ZONE_NORMAL)
goto out;
if (pm_suspended_storage())
goto out;
@@ -3871,10 +4072,6 @@
* failures more gracefully we should just bail out here.
*/
- /* The OOM killer may not free memory on a specific node */
- if (gfp_mask & __GFP_THISNODE)
- goto out;
-
/* Exhausted what can be done so it's blame time */
if (out_of_memory(&oc) || WARN_ON_ONCE(gfp_mask & __GFP_NOFAIL)) {
*did_some_progress = 1;
@@ -4060,10 +4257,10 @@
* 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) {
+ for_each_zone_zonelist_nodemask(zone, z, ac->zonelist,
+ ac->highest_zoneidx, ac->nodemask) {
if (zone_watermark_ok(zone, 0, min_wmark_pages(zone),
- ac_classzone_idx(ac), alloc_flags))
+ ac->highest_zoneidx, alloc_flags))
return true;
}
return false;
@@ -4122,13 +4319,12 @@
#endif
/* Perform direct synchronous page reclaim */
-static int
+static unsigned long
__perform_reclaim(gfp_t gfp_mask, unsigned int order,
const struct alloc_context *ac)
{
- int progress;
unsigned int noreclaim_flag;
- unsigned long pflags;
+ unsigned long pflags, progress;
cond_resched();
@@ -4169,7 +4365,7 @@
/*
* If an allocation failed after direct reclaim, it could be because
* pages are pinned on the per-cpu lists or in high alloc reserves.
- * Shrink them them and try again
+ * Shrink them and try again
*/
if (!page && !drained) {
unreserve_highatomic_pageblock(ac, false);
@@ -4187,12 +4383,12 @@
struct zoneref *z;
struct zone *zone;
pg_data_t *last_pgdat = NULL;
- enum zone_type high_zoneidx = ac->high_zoneidx;
+ enum zone_type highest_zoneidx = ac->highest_zoneidx;
- for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, high_zoneidx,
+ for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, highest_zoneidx,
ac->nodemask) {
if (last_pgdat != zone->zone_pgdat)
- wakeup_kswapd(zone, gfp_mask, order, high_zoneidx);
+ wakeup_kswapd(zone, gfp_mask, order, highest_zoneidx);
last_pgdat = zone->zone_pgdat;
}
}
@@ -4202,8 +4398,13 @@
{
unsigned int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
- /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */
+ /*
+ * __GFP_HIGH is assumed to be the same as ALLOC_HIGH
+ * and __GFP_KSWAPD_RECLAIM is assumed to be the same as ALLOC_KSWAPD
+ * to save two branches.
+ */
BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH);
+ BUILD_BUG_ON(__GFP_KSWAPD_RECLAIM != (__force gfp_t) ALLOC_KSWAPD);
/*
* The caller may dip into page reserves a bit more if the caller
@@ -4211,7 +4412,8 @@
* policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will
* set both ALLOC_HARDER (__GFP_ATOMIC) and ALLOC_HIGH (__GFP_HIGH).
*/
- alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH);
+ alloc_flags |= (__force int)
+ (gfp_mask & (__GFP_HIGH | __GFP_KSWAPD_RECLAIM));
if (gfp_mask & __GFP_ATOMIC) {
/*
@@ -4228,13 +4430,8 @@
} else if (unlikely(rt_task(current)) && !in_interrupt())
alloc_flags |= ALLOC_HARDER;
- if (gfp_mask & __GFP_KSWAPD_RECLAIM)
- alloc_flags |= ALLOC_KSWAPD;
+ alloc_flags = current_alloc_flags(gfp_mask, alloc_flags);
-#ifdef CONFIG_CMA
- if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
- alloc_flags |= ALLOC_CMA;
-#endif
return alloc_flags;
}
@@ -4324,8 +4521,8 @@
* 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) {
+ for_each_zone_zonelist_nodemask(zone, z, ac->zonelist,
+ ac->highest_zoneidx, ac->nodemask) {
unsigned long available;
unsigned long reclaimable;
unsigned long min_wmark = min_wmark_pages(zone);
@@ -4339,7 +4536,7 @@
* reclaimable pages?
*/
wmark = __zone_watermark_ok(zone, order, min_wmark,
- ac_classzone_idx(ac), alloc_flags, available);
+ ac->highest_zoneidx, alloc_flags, available);
trace_reclaim_retry_zone(z, order, reclaimable,
available, min_wmark, *no_progress_loops, wmark);
if (wmark) {
@@ -4458,7 +4655,7 @@
* could end up iterating over non-eligible zones endlessly.
*/
ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
- ac->high_zoneidx, ac->nodemask);
+ ac->highest_zoneidx, ac->nodemask);
if (!ac->preferred_zoneref->zone)
goto nopage;
@@ -4493,8 +4690,11 @@
if (page)
goto got_pg;
- if (order >= pageblock_order && (gfp_mask & __GFP_IO) &&
- !(gfp_mask & __GFP_RETRY_MAYFAIL)) {
+ /*
+ * Checks for costly allocations with __GFP_NORETRY, which
+ * includes some THP page fault allocations
+ */
+ if (costly_order && (gfp_mask & __GFP_NORETRY)) {
/*
* If allocating entire pageblock(s) and compaction
* failed because all zones are below low watermarks
@@ -4515,23 +4715,6 @@
if (compact_result == COMPACT_SKIPPED ||
compact_result == COMPACT_DEFERRED)
goto nopage;
- }
-
- /*
- * Checks for costly allocations with __GFP_NORETRY, which
- * includes THP page fault allocations
- */
- if (costly_order && (gfp_mask & __GFP_NORETRY)) {
- /*
- * If compaction is deferred for high-order allocations,
- * it is because sync compaction recently failed. If
- * this is the case and the caller requested a THP
- * allocation, we do not want to heavily disrupt the
- * system, so we fail the allocation instead of entering
- * direct reclaim.
- */
- if (compact_result == COMPACT_DEFERRED)
- goto nopage;
/*
* Looks like reclaim/compaction is worth trying, but
@@ -4549,7 +4732,7 @@
reserve_flags = __gfp_pfmemalloc_flags(gfp_mask);
if (reserve_flags)
- alloc_flags = reserve_flags;
+ alloc_flags = current_alloc_flags(gfp_mask, reserve_flags);
/*
* Reset the nodemask and zonelist iterators if memory policies can be
@@ -4559,7 +4742,7 @@
if (!(alloc_flags & ALLOC_CPUSET) || reserve_flags) {
ac->nodemask = NULL;
ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
- ac->high_zoneidx, ac->nodemask);
+ ac->highest_zoneidx, ac->nodemask);
}
/* Attempt with potentially adjusted zonelist and alloc_flags */
@@ -4626,7 +4809,7 @@
/* Avoid allocations with no watermarks from looping endlessly */
if (tsk_is_oom_victim(current) &&
- (alloc_flags == ALLOC_OOM ||
+ (alloc_flags & ALLOC_OOM ||
(gfp_mask & __GFP_NOMEMALLOC)))
goto nopage;
@@ -4693,14 +4876,18 @@
struct alloc_context *ac, gfp_t *alloc_mask,
unsigned int *alloc_flags)
{
- ac->high_zoneidx = gfp_zone(gfp_mask);
+ ac->highest_zoneidx = gfp_zone(gfp_mask);
ac->zonelist = node_zonelist(preferred_nid, gfp_mask);
ac->nodemask = nodemask;
- ac->migratetype = gfpflags_to_migratetype(gfp_mask);
+ ac->migratetype = gfp_migratetype(gfp_mask);
if (cpusets_enabled()) {
*alloc_mask |= __GFP_HARDWALL;
- if (!ac->nodemask)
+ /*
+ * When we are in the interrupt context, it is irrelevant
+ * to the current task context. It means that any node ok.
+ */
+ if (!in_interrupt() && !ac->nodemask)
ac->nodemask = &cpuset_current_mems_allowed;
else
*alloc_flags |= ALLOC_CPUSET;
@@ -4714,15 +4901,8 @@
if (should_fail_alloc_page(gfp_mask, order))
return false;
- if (IS_ENABLED(CONFIG_CMA) && ac->migratetype == MIGRATE_MOVABLE)
- *alloc_flags |= ALLOC_CMA;
+ *alloc_flags = current_alloc_flags(gfp_mask, *alloc_flags);
- return true;
-}
-
-/* Determine whether to spread dirty pages and what the first usable zone */
-static inline void finalise_ac(gfp_t gfp_mask, struct alloc_context *ac)
-{
/* Dirty zone balancing only done in the fast path */
ac->spread_dirty_pages = (gfp_mask & __GFP_WRITE);
@@ -4732,7 +4912,9 @@
* may get reset for allocations that ignore memory policies.
*/
ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
- ac->high_zoneidx, ac->nodemask);
+ ac->highest_zoneidx, ac->nodemask);
+
+ return true;
}
/*
@@ -4761,8 +4943,6 @@
if (!prepare_alloc_pages(gfp_mask, order, preferred_nid, nodemask, &ac, &alloc_mask, &alloc_flags))
return NULL;
- finalise_ac(gfp_mask, &ac);
-
/*
* Forbid the first pass from falling back to types that fragment
* memory until all local zones are considered.
@@ -4787,14 +4967,13 @@
* Restore the original nodemask if it was potentially replaced with
* &cpuset_current_mems_allowed to optimize the fast-path attempt.
*/
- if (unlikely(ac.nodemask != nodemask))
- ac.nodemask = nodemask;
+ ac.nodemask = nodemask;
page = __alloc_pages_slowpath(alloc_mask, order, &ac);
out:
if (memcg_kmem_enabled() && (gfp_mask & __GFP_ACCOUNT) && page &&
- unlikely(__memcg_kmem_charge(page, gfp_mask, order) != 0)) {
+ unlikely(__memcg_kmem_charge_page(page, gfp_mask, order) != 0)) {
__free_pages(page, order);
page = NULL;
}
@@ -4832,13 +5011,16 @@
if (order == 0) /* Via pcp? */
free_unref_page(page);
else
- __free_pages_ok(page, order);
+ __free_pages_ok(page, order, FPI_NONE);
}
void __free_pages(struct page *page, unsigned int order)
{
if (put_page_testzero(page))
free_the_page(page, order);
+ else if (!PageHead(page))
+ while (order-- > 0)
+ free_the_page(page + (1 << order), order);
}
EXPORT_SYMBOL(__free_pages);
@@ -5100,19 +5282,6 @@
}
EXPORT_SYMBOL_GPL(nr_free_buffer_pages);
-/**
- * nr_free_pagecache_pages - count number of pages beyond high watermark
- *
- * nr_free_pagecache_pages() counts the number of pages which are beyond the
- * high watermark within all zones.
- *
- * Return: number of pages beyond high watermark within all zones.
- */
-unsigned long nr_free_pagecache_pages(void)
-{
- return nr_free_zone_pages(gfp_zone(GFP_HIGHUSER_MOVABLE));
-}
-
static inline void show_node(struct zone *zone)
{
if (IS_ENABLED(CONFIG_NUMA))
@@ -5155,8 +5324,8 @@
* items that are in use, and cannot be freed. Cap this estimate at the
* low watermark.
*/
- reclaimable = global_node_page_state(NR_SLAB_RECLAIMABLE) +
- global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE);
+ reclaimable = global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B) +
+ global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE);
available += reclaimable - min(reclaimable / 2, wmark_low);
if (available < 0)
@@ -5286,7 +5455,7 @@
printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n"
" active_file:%lu inactive_file:%lu isolated_file:%lu\n"
- " unevictable:%lu dirty:%lu writeback:%lu unstable:%lu\n"
+ " unevictable:%lu dirty:%lu writeback:%lu\n"
" slab_reclaimable:%lu slab_unreclaimable:%lu\n"
" mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n"
" free:%lu free_pcp:%lu free_cma:%lu\n",
@@ -5299,9 +5468,8 @@
global_node_page_state(NR_UNEVICTABLE),
global_node_page_state(NR_FILE_DIRTY),
global_node_page_state(NR_WRITEBACK),
- global_node_page_state(NR_UNSTABLE_NFS),
- global_node_page_state(NR_SLAB_RECLAIMABLE),
- global_node_page_state(NR_SLAB_UNRECLAIMABLE),
+ global_node_page_state_pages(NR_SLAB_RECLAIMABLE_B),
+ global_node_page_state_pages(NR_SLAB_UNRECLAIMABLE_B),
global_node_page_state(NR_FILE_MAPPED),
global_node_page_state(NR_SHMEM),
global_zone_page_state(NR_PAGETABLE),
@@ -5332,7 +5500,10 @@
" anon_thp: %lukB"
#endif
" writeback_tmp:%lukB"
- " unstable:%lukB"
+ " kernel_stack:%lukB"
+#ifdef CONFIG_SHADOW_CALL_STACK
+ " shadow_call_stack:%lukB"
+#endif
" all_unreclaimable? %s"
"\n",
pgdat->node_id,
@@ -5354,7 +5525,10 @@
K(node_page_state(pgdat, NR_ANON_THPS) * HPAGE_PMD_NR),
#endif
K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
- K(node_page_state(pgdat, NR_UNSTABLE_NFS)),
+ node_page_state(pgdat, NR_KERNEL_STACK_KB),
+#ifdef CONFIG_SHADOW_CALL_STACK
+ node_page_state(pgdat, NR_KERNEL_SCS_KB),
+#endif
pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ?
"yes" : "no");
}
@@ -5376,6 +5550,7 @@
" min:%lukB"
" low:%lukB"
" high:%lukB"
+ " reserved_highatomic:%luKB"
" active_anon:%lukB"
" inactive_anon:%lukB"
" active_file:%lukB"
@@ -5385,7 +5560,6 @@
" present:%lukB"
" managed:%lukB"
" mlocked:%lukB"
- " kernel_stack:%lukB"
" pagetables:%lukB"
" bounce:%lukB"
" free_pcp:%lukB"
@@ -5397,6 +5571,7 @@
K(min_wmark_pages(zone)),
K(low_wmark_pages(zone)),
K(high_wmark_pages(zone)),
+ K(zone->nr_reserved_highatomic),
K(zone_page_state(zone, NR_ZONE_ACTIVE_ANON)),
K(zone_page_state(zone, NR_ZONE_INACTIVE_ANON)),
K(zone_page_state(zone, NR_ZONE_ACTIVE_FILE)),
@@ -5406,7 +5581,6 @@
K(zone->present_pages),
K(zone_managed_pages(zone)),
K(zone_page_state(zone, NR_MLOCK)),
- zone_page_state(zone, NR_KERNEL_STACK_KB),
K(zone_page_state(zone, NR_PAGETABLE)),
K(zone_page_state(zone, NR_BOUNCE)),
K(free_pcp),
@@ -5505,36 +5679,17 @@
return 0;
}
-static __init int setup_numa_zonelist_order(char *s)
-{
- if (!s)
- return 0;
-
- return __parse_numa_zonelist_order(s);
-}
-early_param("numa_zonelist_order", setup_numa_zonelist_order);
-
char numa_zonelist_order[] = "Node";
/*
* sysctl handler for numa_zonelist_order
*/
int numa_zonelist_order_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *length,
- loff_t *ppos)
+ void *buffer, size_t *length, loff_t *ppos)
{
- char *str;
- int ret;
-
- if (!write)
- return proc_dostring(table, write, buffer, length, ppos);
- str = memdup_user_nul(buffer, 16);
- if (IS_ERR(str))
- return PTR_ERR(str);
-
- ret = __parse_numa_zonelist_order(str);
- kfree(str);
- return ret;
+ if (write)
+ return __parse_numa_zonelist_order(buffer);
+ return proc_dostring(table, write, buffer, length, ppos);
}
@@ -5561,7 +5716,6 @@
int n, val;
int min_val = INT_MAX;
int best_node = NUMA_NO_NODE;
- const struct cpumask *tmp = cpumask_of_node(0);
/* Use the local node if we haven't already */
if (!node_isset(node, *used_node_mask)) {
@@ -5582,8 +5736,7 @@
val += (n < node);
/* Give preference to headless and unused nodes */
- tmp = cpumask_of_node(n);
- if (!cpumask_empty(tmp))
+ if (!cpumask_empty(cpumask_of_node(n)))
val += PENALTY_FOR_NODE_WITH_CPUS;
/* Slight preference for less loaded node */
@@ -5654,14 +5807,13 @@
{
static int node_order[MAX_NUMNODES];
int node, load, nr_nodes = 0;
- nodemask_t used_mask;
+ nodemask_t used_mask = NODE_MASK_NONE;
int local_node, prev_node;
/* NUMA-aware ordering of nodes */
local_node = pgdat->node_id;
load = nr_online_nodes;
prev_node = local_node;
- nodes_clear(used_mask);
memset(node_order, 0, sizeof(node_order));
while ((node = find_next_best_node(local_node, &used_mask)) >= 0) {
@@ -5841,13 +5993,16 @@
*/
void __ref build_all_zonelists(pg_data_t *pgdat)
{
+ unsigned long vm_total_pages;
+
if (system_state == SYSTEM_BOOTING) {
build_all_zonelists_init();
} else {
__build_all_zonelists(pgdat);
/* cpuset refresh routine should be here */
}
- vm_total_pages = nr_free_pagecache_pages();
+ /* Get the number of free pages beyond high watermark in all zones. */
+ vm_total_pages = nr_free_zone_pages(gfp_zone(GFP_HIGHUSER_MOVABLE));
/*
* Disable grouping by mobility if the number of pages in the
* system is too low to allow the mechanism to work. It would be
@@ -5873,12 +6028,11 @@
static bool __meminit
overlap_memmap_init(unsigned long zone, unsigned long *pfn)
{
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
static struct memblock_region *r;
if (mirrored_kernelcore && zone == ZONE_MOVABLE) {
if (!r || *pfn >= memblock_region_memory_end_pfn(r)) {
- for_each_memblock(memory, r) {
+ for_each_mem_region(r) {
if (*pfn < memblock_region_memory_end_pfn(r))
break;
}
@@ -5889,7 +6043,6 @@
return true;
}
}
-#endif
return false;
}
@@ -5897,10 +6050,15 @@
* Initially all pages are reserved - free ones are freed
* up by memblock_free_all() once the early boot process is
* done. Non-atomic initialization, single-pass.
+ *
+ * All aligned pageblocks are initialized to the specified migratetype
+ * (usually MIGRATE_MOVABLE). Besides setting the migratetype, no related
+ * zone stats (e.g., nr_isolate_pageblock) are touched.
*/
void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
- unsigned long start_pfn, enum meminit_context context,
- struct vmem_altmap *altmap)
+ unsigned long start_pfn, unsigned long zone_end_pfn,
+ enum meminit_context context,
+ struct vmem_altmap *altmap, int migratetype)
{
unsigned long pfn, end_pfn = start_pfn + size;
struct page *page;
@@ -5926,19 +6084,15 @@
}
#endif
- for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+ for (pfn = start_pfn; pfn < end_pfn; ) {
/*
* There can be holes in boot-time mem_map[]s handed to this
* function. They do not exist on hotplugged memory.
*/
if (context == MEMINIT_EARLY) {
- if (!early_pfn_valid(pfn))
- continue;
- if (!early_pfn_in_nid(pfn, nid))
- continue;
if (overlap_memmap_init(zone, &pfn))
continue;
- if (defer_init(nid, pfn, end_pfn))
+ if (defer_init(nid, pfn, zone_end_pfn))
break;
}
@@ -5948,31 +6102,25 @@
__SetPageReserved(page);
/*
- * Mark the block movable so that blocks are reserved for
- * movable at startup. This will force kernel allocations
- * to reserve their blocks rather than leaking throughout
- * the address space during boot when many long-lived
- * kernel allocations are made.
- *
- * bitmap is created for zone's valid pfn range. but memmap
- * can be created for invalid pages (for alignment)
- * check here not to call set_pageblock_migratetype() against
- * pfn out of zone.
+ * Usually, we want to mark the pageblock MIGRATE_MOVABLE,
+ * such that unmovable allocations won't be scattered all
+ * over the place during system boot.
*/
- if (!(pfn & (pageblock_nr_pages - 1))) {
- set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+ if (IS_ALIGNED(pfn, pageblock_nr_pages)) {
+ set_pageblock_migratetype(page, migratetype);
cond_resched();
}
+ pfn++;
}
}
#ifdef CONFIG_ZONE_DEVICE
void __ref memmap_init_zone_device(struct zone *zone,
unsigned long start_pfn,
- unsigned long size,
+ unsigned long nr_pages,
struct dev_pagemap *pgmap)
{
- unsigned long pfn, end_pfn = start_pfn + size;
+ unsigned long pfn, end_pfn = start_pfn + nr_pages;
struct pglist_data *pgdat = zone->zone_pgdat;
struct vmem_altmap *altmap = pgmap_altmap(pgmap);
unsigned long zone_idx = zone_idx(zone);
@@ -5983,13 +6131,13 @@
return;
/*
- * The call to memmap_init_zone should have already taken care
+ * The call to memmap_init should have already taken care
* of the pages reserved for the memmap, so we can just jump to
* the end of that region and start processing the device pages.
*/
if (altmap) {
start_pfn = altmap->base_pfn + vmem_altmap_offset(altmap);
- size = end_pfn - start_pfn;
+ nr_pages = end_pfn - start_pfn;
}
for (pfn = start_pfn; pfn < end_pfn; pfn++) {
@@ -6021,22 +6169,17 @@
* the address space during boot when many long-lived
* kernel allocations are made.
*
- * bitmap is created for zone's valid pfn range. but memmap
- * can be created for invalid pages (for alignment)
- * check here not to call set_pageblock_migratetype() against
- * pfn out of zone.
- *
* Please note that MEMINIT_HOTPLUG path doesn't clear memmap
* because this is done early in section_activate()
*/
- if (!(pfn & (pageblock_nr_pages - 1))) {
+ if (IS_ALIGNED(pfn, pageblock_nr_pages)) {
set_pageblock_migratetype(page, MIGRATE_MOVABLE);
cond_resched();
}
}
pr_info("%s initialised %lu pages in %ums\n", __func__,
- size, jiffies_to_msecs(jiffies - start));
+ nr_pages, jiffies_to_msecs(jiffies - start));
}
#endif
@@ -6049,10 +6192,125 @@
}
}
-void __meminit __weak memmap_init(unsigned long size, int nid,
- unsigned long zone, unsigned long start_pfn)
+#if !defined(CONFIG_FLAT_NODE_MEM_MAP)
+/*
+ * Only struct pages that correspond to ranges defined by memblock.memory
+ * are zeroed and initialized by going through __init_single_page() during
+ * memmap_init_zone_range().
+ *
+ * But, there could be struct pages that correspond to holes in
+ * memblock.memory. This can happen because of the following reasons:
+ * - physical memory bank size is not necessarily the exact multiple of the
+ * arbitrary section size
+ * - early reserved memory may not be listed in memblock.memory
+ * - memory layouts defined with memmap= kernel parameter may not align
+ * nicely with memmap sections
+ *
+ * Explicitly initialize those struct pages so that:
+ * - PG_Reserved is set
+ * - zone and node links point to zone and node that span the page if the
+ * hole is in the middle of a zone
+ * - zone and node links point to adjacent zone/node if the hole falls on
+ * the zone boundary; the pages in such holes will be prepended to the
+ * zone/node above the hole except for the trailing pages in the last
+ * section that will be appended to the zone/node below.
+ */
+static void __init init_unavailable_range(unsigned long spfn,
+ unsigned long epfn,
+ int zone, int node)
{
- memmap_init_zone(size, nid, zone, start_pfn, MEMINIT_EARLY, NULL);
+ unsigned long pfn;
+ u64 pgcnt = 0;
+
+ for (pfn = spfn; pfn < epfn; pfn++) {
+ if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) {
+ pfn = ALIGN_DOWN(pfn, pageblock_nr_pages)
+ + pageblock_nr_pages - 1;
+ continue;
+ }
+ __init_single_page(pfn_to_page(pfn), pfn, zone, node);
+ __SetPageReserved(pfn_to_page(pfn));
+ pgcnt++;
+ }
+
+ if (pgcnt)
+ pr_info("On node %d, zone %s: %lld pages in unavailable ranges",
+ node, zone_names[zone], pgcnt);
+}
+#else
+static inline void init_unavailable_range(unsigned long spfn,
+ unsigned long epfn,
+ int zone, int node)
+{
+}
+#endif
+
+static void __init memmap_init_zone_range(struct zone *zone,
+ unsigned long start_pfn,
+ unsigned long end_pfn,
+ unsigned long *hole_pfn)
+{
+ unsigned long zone_start_pfn = zone->zone_start_pfn;
+ unsigned long zone_end_pfn = zone_start_pfn + zone->spanned_pages;
+ int nid = zone_to_nid(zone), zone_id = zone_idx(zone);
+
+ start_pfn = clamp(start_pfn, zone_start_pfn, zone_end_pfn);
+ end_pfn = clamp(end_pfn, zone_start_pfn, zone_end_pfn);
+
+ if (start_pfn >= end_pfn)
+ return;
+
+ memmap_init_zone(end_pfn - start_pfn, nid, zone_id, start_pfn,
+ zone_end_pfn, MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
+
+ if (*hole_pfn < start_pfn)
+ init_unavailable_range(*hole_pfn, start_pfn, zone_id, nid);
+
+ *hole_pfn = end_pfn;
+}
+
+void __init __weak memmap_init(void)
+{
+ unsigned long start_pfn, end_pfn;
+ unsigned long hole_pfn = 0;
+ int i, j, zone_id, nid;
+
+ for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) {
+ struct pglist_data *node = NODE_DATA(nid);
+
+ for (j = 0; j < MAX_NR_ZONES; j++) {
+ struct zone *zone = node->node_zones + j;
+
+ if (!populated_zone(zone))
+ continue;
+
+ memmap_init_zone_range(zone, start_pfn, end_pfn,
+ &hole_pfn);
+ zone_id = j;
+ }
+ }
+
+#ifdef CONFIG_SPARSEMEM
+ /*
+ * Initialize the memory map for hole in the range [memory_end,
+ * section_end].
+ * Append the pages in this hole to the highest zone in the last
+ * node.
+ * The call to init_unavailable_range() is outside the ifdef to
+ * silence the compiler warining about zone_id set but not used;
+ * for FLATMEM it is a nop anyway
+ */
+ end_pfn = round_up(end_pfn, PAGES_PER_SECTION);
+ if (hole_pfn < end_pfn)
+#endif
+ init_unavailable_range(hole_pfn, end_pfn, zone_id, nid);
+}
+
+/* A stub for backwards compatibility with custom implementatin on IA-64 */
+void __meminit __weak arch_memmap_init(unsigned long size, int nid,
+ unsigned long zone,
+ unsigned long range_start_pfn)
+{
}
static int zone_batchsize(struct zone *zone)
@@ -6111,7 +6369,7 @@
* locking.
*
* Any new users of pcp->batch and pcp->high should ensure they can cope with
- * those fields changing asynchronously (acording the the above rule).
+ * those fields changing asynchronously (acording to the above rule).
*
* mutex_is_locked(&pcp_batch_high_lock) required when calling this function
* outside of boot time (or some other assurance that no concurrent updaters
@@ -6204,10 +6462,25 @@
{
struct pglist_data *pgdat;
struct zone *zone;
+ int __maybe_unused cpu;
for_each_populated_zone(zone)
setup_zone_pageset(zone);
+#ifdef CONFIG_NUMA
+ /*
+ * Unpopulated zones continue using the boot pagesets.
+ * The numa stats for these pagesets need to be reset.
+ * Otherwise, they will end up skewing the stats of
+ * the nodes these zones are associated with.
+ */
+ for_each_possible_cpu(cpu) {
+ struct per_cpu_pageset *pcp = &per_cpu(boot_pageset, cpu);
+ memset(pcp->vm_numa_stat_diff, 0,
+ sizeof(pcp->vm_numa_stat_diff));
+ }
+#endif
+
for_each_online_pgdat(pgdat)
pgdat->per_cpu_nodestats =
alloc_percpu(struct per_cpu_nodestat);
@@ -6250,73 +6523,6 @@
zone->initialized = 1;
}
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
-#ifndef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
-
-/*
- * Required by SPARSEMEM. Given a PFN, return what node the PFN is on.
- */
-int __meminit __early_pfn_to_nid(unsigned long pfn,
- struct mminit_pfnnid_cache *state)
-{
- unsigned long start_pfn, end_pfn;
- int nid;
-
- if (state->last_start <= pfn && pfn < state->last_end)
- return state->last_nid;
-
- nid = memblock_search_pfn_nid(pfn, &start_pfn, &end_pfn);
- if (nid != NUMA_NO_NODE) {
- state->last_start = start_pfn;
- state->last_end = end_pfn;
- state->last_nid = nid;
- }
-
- return nid;
-}
-#endif /* CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID */
-
-/**
- * free_bootmem_with_active_regions - Call memblock_free_early_nid for each active range
- * @nid: The node to free memory on. If MAX_NUMNODES, all nodes are freed.
- * @max_low_pfn: The highest PFN that will be passed to memblock_free_early_nid
- *
- * If an architecture guarantees that all ranges registered contain no holes
- * and may be freed, this this function may be used instead of calling
- * memblock_free_early_nid() manually.
- */
-void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn)
-{
- unsigned long start_pfn, end_pfn;
- int i, this_nid;
-
- for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, &this_nid) {
- start_pfn = min(start_pfn, max_low_pfn);
- end_pfn = min(end_pfn, max_low_pfn);
-
- if (start_pfn < end_pfn)
- memblock_free_early_nid(PFN_PHYS(start_pfn),
- (end_pfn - start_pfn) << PAGE_SHIFT,
- this_nid);
- }
-}
-
-/**
- * sparse_memory_present_with_active_regions - Call memory_present for each active range
- * @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used.
- *
- * If an architecture guarantees that all ranges registered contain no holes and may
- * be freed, this function may be used instead of calling memory_present() manually.
- */
-void __init sparse_memory_present_with_active_regions(int nid)
-{
- unsigned long start_pfn, end_pfn;
- int i, this_nid;
-
- for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, &this_nid)
- memory_present(this_nid, start_pfn, end_pfn);
-}
-
/**
* get_pfn_range_for_nid - Return the start and end page frames for a node
* @nid: The nid to return the range for. If MAX_NUMNODES, the min and max PFN are returned.
@@ -6413,8 +6619,7 @@
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_end_pfn)
{
unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type];
unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type];
@@ -6478,8 +6683,7 @@
static unsigned long __init zone_absent_pages_in_node(int nid,
unsigned long zone_type,
unsigned long node_start_pfn,
- unsigned long node_end_pfn,
- unsigned long *ignored)
+ unsigned long node_end_pfn)
{
unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type];
unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type];
@@ -6507,7 +6711,7 @@
unsigned long start_pfn, end_pfn;
struct memblock_region *r;
- for_each_memblock(memory, r) {
+ for_each_mem_region(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),
@@ -6526,45 +6730,9 @@
return nr_absent;
}
-#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
-static inline unsigned long __init 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];
-}
-
-static inline unsigned long __init zone_absent_pages_in_node(int nid,
- unsigned long zone_type,
- unsigned long node_start_pfn,
- unsigned long node_end_pfn,
- unsigned long *zholes_size)
-{
- if (!zholes_size)
- return 0;
-
- return zholes_size[zone_type];
-}
-
-#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
-
static void __init calculate_node_totalpages(struct pglist_data *pgdat,
unsigned long node_start_pfn,
- unsigned long node_end_pfn,
- unsigned long *zones_size,
- unsigned long *zholes_size)
+ unsigned long node_end_pfn)
{
unsigned long realtotalpages = 0, totalpages = 0;
enum zone_type i;
@@ -6572,17 +6740,21 @@
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 spanned, absent;
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);
+ spanned = zone_spanned_pages_in_node(pgdat->node_id, i,
+ node_start_pfn,
+ node_end_pfn,
+ &zone_start_pfn,
+ &zone_end_pfn);
+ absent = zone_absent_pages_in_node(pgdat->node_id, i,
+ node_start_pfn,
+ node_end_pfn);
+
+ size = spanned;
+ real_size = size - absent;
+
if (size)
zone->zone_start_pfn = zone_start_pfn;
else
@@ -6733,7 +6905,7 @@
pgdat_page_ext_init(pgdat);
spin_lock_init(&pgdat->lru_lock);
- lruvec_init(node_lruvec(pgdat));
+ lruvec_init(&pgdat->__lruvec);
}
static void __meminit zone_init_internals(struct zone *zone, enum zone_type idx, int nid,
@@ -6837,7 +7009,7 @@
set_pageblock_order();
setup_usemap(pgdat, zone, zone_start_pfn, size);
init_currently_empty_zone(zone, zone_start_pfn, size);
- memmap_init(size, nid, j, zone_start_pfn);
+ arch_memmap_init(size, nid, j, zone_start_pfn);
}
}
@@ -6882,10 +7054,8 @@
*/
if (pgdat == NODE_DATA(0)) {
mem_map = NODE_DATA(0)->node_mem_map;
-#if defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP) || defined(CONFIG_FLATMEM)
if (page_to_pfn(mem_map) != pgdat->node_start_pfn)
mem_map -= offset;
-#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
}
#endif
}
@@ -6902,30 +7072,25 @@
static inline void pgdat_set_deferred_range(pg_data_t *pgdat) {}
#endif
-void __init free_area_init_node(int nid, unsigned long *zones_size,
- unsigned long node_start_pfn,
- unsigned long *zholes_size)
+static void __init free_area_init_node(int nid)
{
pg_data_t *pgdat = NODE_DATA(nid);
unsigned long start_pfn = 0;
unsigned long end_pfn = 0;
/* pg_data_t should be reset to zero when it's allocated */
- WARN_ON(pgdat->nr_zones || pgdat->kswapd_classzone_idx);
+ WARN_ON(pgdat->nr_zones || pgdat->kswapd_highest_zoneidx);
+
+ get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
pgdat->node_id = nid;
- pgdat->node_start_pfn = node_start_pfn;
+ pgdat->node_start_pfn = start_pfn;
pgdat->per_cpu_nodestats = NULL;
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
- get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
+
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);
+ calculate_node_totalpages(pgdat, start_pfn, end_pfn);
alloc_node_mem_map(pgdat);
pgdat_set_deferred_range(pgdat);
@@ -6933,80 +7098,11 @@
free_area_init_core(pgdat);
}
-#if !defined(CONFIG_FLAT_NODE_MEM_MAP)
-/*
- * Zero all valid struct pages in range [spfn, epfn), return number of struct
- * pages zeroed
- */
-static u64 zero_pfn_range(unsigned long spfn, unsigned long epfn)
+void __init free_area_init_memoryless_node(int nid)
{
- unsigned long pfn;
- u64 pgcnt = 0;
-
- for (pfn = spfn; pfn < epfn; pfn++) {
- if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) {
- pfn = ALIGN_DOWN(pfn, pageblock_nr_pages)
- + pageblock_nr_pages - 1;
- continue;
- }
- mm_zero_struct_page(pfn_to_page(pfn));
- pgcnt++;
- }
-
- return pgcnt;
+ free_area_init_node(nid);
}
-/*
- * Only struct pages that are backed by physical memory are zeroed and
- * initialized by going through __init_single_page(). But, there are some
- * struct pages which are reserved in memblock allocator and their fields
- * may be accessed (for example page_to_pfn() on some configuration accesses
- * flags). We must explicitly zero those struct pages.
- *
- * This function also addresses a similar issue where struct pages are left
- * uninitialized because the physical address range is not covered by
- * memblock.memory or memblock.reserved. That could happen when memblock
- * layout is manually configured via memmap=, or when the highest physical
- * address (max_pfn) does not end on a section boundary.
- */
-void __init zero_resv_unavail(void)
-{
- phys_addr_t start, end;
- u64 i, pgcnt;
- phys_addr_t next = 0;
-
- /*
- * Loop through unavailable ranges not covered by memblock.memory.
- */
- pgcnt = 0;
- for_each_mem_range(i, &memblock.memory, NULL,
- NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) {
- if (next < start)
- pgcnt += zero_pfn_range(PFN_DOWN(next), PFN_UP(start));
- next = end;
- }
-
- /*
- * Early sections always have a fully populated memmap for the whole
- * section - see pfn_valid(). If the last section has holes at the
- * end and that section is marked "online", the memmap will be
- * considered initialized. Make sure that memmap has a well defined
- * state.
- */
- pgcnt += zero_pfn_range(PFN_DOWN(next),
- round_up(max_pfn, PAGES_PER_SECTION));
-
- /*
- * Struct pages that do not have backing memory. This could be because
- * firmware is using some of this memory, or for some other reasons.
- */
- if (pgcnt)
- pr_info("Zeroed struct page in unavailable ranges: %lld pages", pgcnt);
-}
-#endif /* !CONFIG_FLAT_NODE_MEM_MAP */
-
-#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
-
#if MAX_NUMNODES > 1
/*
* Figure out the number of possible node ids.
@@ -7070,24 +7166,6 @@
return ~accl_mask + 1;
}
-/* Find the lowest pfn for a node */
-static unsigned long __init find_min_pfn_for_node(int nid)
-{
- unsigned long min_pfn = ULONG_MAX;
- unsigned long start_pfn;
- int i;
-
- for_each_mem_pfn_range(i, nid, &start_pfn, NULL, NULL)
- min_pfn = min(min_pfn, start_pfn);
-
- if (min_pfn == ULONG_MAX) {
- pr_warn("Could not find start_pfn for node %d\n", nid);
- return 0;
- }
-
- return min_pfn;
-}
-
/**
* find_min_pfn_with_active_regions - Find the minimum PFN registered
*
@@ -7096,7 +7174,7 @@
*/
unsigned long __init find_min_pfn_with_active_regions(void)
{
- return find_min_pfn_for_node(MAX_NUMNODES);
+ return PHYS_PFN(memblock_start_of_DRAM());
}
/*
@@ -7145,11 +7223,11 @@
* options.
*/
if (movable_node_is_enabled()) {
- for_each_memblock(memory, r) {
+ for_each_mem_region(r) {
if (!memblock_is_hotpluggable(r))
continue;
- nid = r->nid;
+ nid = memblock_get_region_node(r);
usable_startpfn = PFN_DOWN(r->base);
zone_movable_pfn[nid] = zone_movable_pfn[nid] ?
@@ -7166,11 +7244,11 @@
if (mirrored_kernelcore) {
bool mem_below_4gb_not_mirrored = false;
- for_each_memblock(memory, r) {
+ for_each_mem_region(r) {
if (memblock_is_mirror(r))
continue;
- nid = r->nid;
+ nid = memblock_get_region_node(r);
usable_startpfn = memblock_region_memory_base_pfn(r);
@@ -7185,7 +7263,7 @@
}
if (mem_below_4gb_not_mirrored)
- pr_warn("This configuration results in unmirrored kernel memory.");
+ pr_warn("This configuration results in unmirrored kernel memory.\n");
goto out2;
}
@@ -7350,8 +7428,17 @@
}
}
+/*
+ * Some architecturs, e.g. ARC may have ZONE_HIGHMEM below ZONE_NORMAL. For
+ * such cases we allow max_zone_pfn sorted in the descending order
+ */
+bool __weak arch_has_descending_max_zone_pfns(void)
+{
+ return false;
+}
+
/**
- * free_area_init_nodes - Initialise all pg_data_t and zone data
+ * free_area_init - Initialise all pg_data_t and zone data
* @max_zone_pfn: an array of max PFNs for each zone
*
* This will call free_area_init_node() for each active node in the system.
@@ -7363,10 +7450,11 @@
* starts where the previous one ended. For example, ZONE_DMA32 starts
* at arch_max_dma_pfn.
*/
-void __init free_area_init_nodes(unsigned long *max_zone_pfn)
+void __init free_area_init(unsigned long *max_zone_pfn)
{
unsigned long start_pfn, end_pfn;
- int i, nid;
+ int i, nid, zone;
+ bool descending;
/* Record where the zone boundaries are */
memset(arch_zone_lowest_possible_pfn, 0,
@@ -7375,14 +7463,20 @@
sizeof(arch_zone_highest_possible_pfn));
start_pfn = find_min_pfn_with_active_regions();
+ descending = arch_has_descending_max_zone_pfns();
for (i = 0; i < MAX_NR_ZONES; i++) {
- if (i == ZONE_MOVABLE)
+ if (descending)
+ zone = MAX_NR_ZONES - i - 1;
+ else
+ zone = i;
+
+ if (zone == ZONE_MOVABLE)
continue;
- end_pfn = max(max_zone_pfn[i], start_pfn);
- arch_zone_lowest_possible_pfn[i] = start_pfn;
- arch_zone_highest_possible_pfn[i] = end_pfn;
+ end_pfn = max(max_zone_pfn[zone], start_pfn);
+ arch_zone_lowest_possible_pfn[zone] = start_pfn;
+ arch_zone_highest_possible_pfn[zone] = end_pfn;
start_pfn = end_pfn;
}
@@ -7432,17 +7526,17 @@
/* Initialise every node */
mminit_verify_pageflags_layout();
setup_nr_node_ids();
- zero_resv_unavail();
for_each_online_node(nid) {
pg_data_t *pgdat = NODE_DATA(nid);
- free_area_init_node(nid, NULL,
- find_min_pfn_for_node(nid), NULL);
+ free_area_init_node(nid);
/* Any memory on that node */
if (pgdat->node_present_pages)
node_set_state(nid, N_MEMORY);
check_for_memory(pgdat, nid);
}
+
+ memmap_init();
}
static int __init cmdline_parse_core(char *p, unsigned long *core,
@@ -7501,8 +7595,6 @@
early_param("kernelcore", cmdline_parse_kernelcore);
early_param("movablecore", cmdline_parse_movablecore);
-#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
-
void adjust_managed_page_count(struct page *page, long count)
{
atomic_long_add(count, &page_zone(page)->managed_pages);
@@ -7625,13 +7717,6 @@
dma_reserve = new_dma_reserve;
}
-void __init free_area_init(unsigned long *zones_size)
-{
- zero_resv_unavail();
- free_area_init_node(0, zones_size,
- __pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL);
-}
-
static int page_alloc_cpu_dead(unsigned int cpu)
{
@@ -7733,30 +7818,24 @@
static void setup_per_zone_lowmem_reserve(void)
{
struct pglist_data *pgdat;
- enum zone_type j, idx;
+ enum zone_type i, j;
for_each_online_pgdat(pgdat) {
- for (j = 0; j < MAX_NR_ZONES; j++) {
- struct zone *zone = pgdat->node_zones + j;
- unsigned long managed_pages = zone_managed_pages(zone);
+ for (i = 0; i < MAX_NR_ZONES - 1; i++) {
+ struct zone *zone = &pgdat->node_zones[i];
+ int ratio = sysctl_lowmem_reserve_ratio[i];
+ bool clear = !ratio || !zone_managed_pages(zone);
+ unsigned long managed_pages = 0;
- zone->lowmem_reserve[j] = 0;
+ for (j = i + 1; j < MAX_NR_ZONES; j++) {
+ struct zone *upper_zone = &pgdat->node_zones[j];
- idx = j;
- while (idx) {
- struct zone *lower_zone;
+ managed_pages += zone_managed_pages(upper_zone);
- idx--;
- lower_zone = pgdat->node_zones + idx;
-
- if (sysctl_lowmem_reserve_ratio[idx] < 1) {
- sysctl_lowmem_reserve_ratio[idx] = 0;
- lower_zone->lowmem_reserve[j] = 0;
- } else {
- lower_zone->lowmem_reserve[j] =
- managed_pages / sysctl_lowmem_reserve_ratio[idx];
- }
- managed_pages += zone_managed_pages(lower_zone);
+ if (clear)
+ zone->lowmem_reserve[j] = 0;
+ else
+ zone->lowmem_reserve[j] = managed_pages / ratio;
}
}
}
@@ -7816,9 +7895,9 @@
mult_frac(zone_managed_pages(zone),
watermark_scale_factor, 10000));
+ zone->watermark_boost = 0;
zone->_watermark[WMARK_LOW] = min_wmark_pages(zone) + tmp;
zone->_watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp * 2;
- zone->watermark_boost = 0;
spin_unlock_irqrestore(&zone->lock, flags);
}
@@ -7847,7 +7926,7 @@
* Initialise min_free_kbytes.
*
* For small machines we want it small (128k min). For large machines
- * we want it large (64MB max). But it is not linear, because network
+ * we want it large (256MB max). But it is not linear, because network
* bandwidth does not increase linearly with machine size. We use
*
* min_free_kbytes = 4 * sqrt(lowmem_kbytes), for better accuracy:
@@ -7879,8 +7958,8 @@
min_free_kbytes = new_min_free_kbytes;
if (min_free_kbytes < 128)
min_free_kbytes = 128;
- if (min_free_kbytes > 65536)
- min_free_kbytes = 65536;
+ if (min_free_kbytes > 262144)
+ min_free_kbytes = 262144;
} else {
pr_warn("min_free_kbytes is not updated to %d because user defined value %d is preferred\n",
new_min_free_kbytes, user_min_free_kbytes);
@@ -7906,7 +7985,7 @@
* changes.
*/
int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *length, loff_t *ppos)
+ void *buffer, size_t *length, loff_t *ppos)
{
int rc;
@@ -7921,20 +8000,8 @@
return 0;
}
-int watermark_boost_factor_sysctl_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *length, loff_t *ppos)
-{
- int rc;
-
- rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
- if (rc)
- return rc;
-
- return 0;
-}
-
int watermark_scale_factor_sysctl_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *length, loff_t *ppos)
+ void *buffer, size_t *length, loff_t *ppos)
{
int rc;
@@ -7964,7 +8031,7 @@
int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *length, loff_t *ppos)
+ void *buffer, size_t *length, loff_t *ppos)
{
int rc;
@@ -7991,7 +8058,7 @@
}
int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *length, loff_t *ppos)
+ void *buffer, size_t *length, loff_t *ppos)
{
int rc;
@@ -8015,20 +8082,37 @@
* if in function of the boot time zone sizes.
*/
int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *length, loff_t *ppos)
+ void *buffer, size_t *length, loff_t *ppos)
{
+ int i;
+
proc_dointvec_minmax(table, write, buffer, length, ppos);
+
+ for (i = 0; i < MAX_NR_ZONES; i++) {
+ if (sysctl_lowmem_reserve_ratio[i] < 1)
+ sysctl_lowmem_reserve_ratio[i] = 0;
+ }
+
setup_per_zone_lowmem_reserve();
return 0;
}
+static void __zone_pcp_update(struct zone *zone)
+{
+ unsigned int cpu;
+
+ for_each_possible_cpu(cpu)
+ pageset_set_high_and_batch(zone,
+ per_cpu_ptr(zone->pageset, cpu));
+}
+
/*
* percpu_pagelist_fraction - changes the pcp->high for each zone on each
* cpu. It is the fraction of total pages in each zone that a hot per cpu
* pagelist can have before it gets flushed back to buddy allocator.
*/
int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *length, loff_t *ppos)
+ void *buffer, size_t *length, loff_t *ppos)
{
struct zone *zone;
int old_percpu_pagelist_fraction;
@@ -8053,13 +8137,8 @@
if (percpu_pagelist_fraction == old_percpu_pagelist_fraction)
goto out;
- for_each_populated_zone(zone) {
- unsigned int cpu;
-
- for_each_possible_cpu(cpu)
- pageset_set_high_and_batch(zone,
- per_cpu_ptr(zone->pageset, cpu));
- }
+ for_each_populated_zone(zone)
+ __zone_pcp_update(zone);
out:
mutex_unlock(&pcp_batch_high_lock);
return ret;
@@ -8177,7 +8256,7 @@
table = memblock_alloc_raw(size,
SMP_CACHE_BYTES);
} else if (get_order(size) >= MAX_ORDER || hashdist) {
- table = __vmalloc(size, gfp_flags, PAGE_KERNEL);
+ table = __vmalloc(size, gfp_flags);
virt = true;
} else {
/*
@@ -8207,28 +8286,23 @@
/*
* This function checks whether pageblock includes unmovable pages or not.
- * If @count is not zero, it is okay to include less @count unmovable pages
*
* PageLRU check without isolation or lru_lock could race so that
* MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable
* check without lock_page also may miss some movable non-lru pages at
* race condition. So you can't expect this function should be exact.
+ *
+ * Returns a page without holding a reference. If the caller wants to
+ * dereference that page (e.g., dumping), it has to make sure that it
+ * cannot get removed (e.g., via memory unplug) concurrently.
+ *
*/
-bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
- int migratetype, int flags)
+struct page *has_unmovable_pages(struct zone *zone, struct page *page,
+ int migratetype, int flags)
{
- unsigned long found;
unsigned long iter = 0;
unsigned long pfn = page_to_pfn(page);
- const char *reason = "unmovable page";
-
- /*
- * TODO we could make this much more efficient by not checking every
- * page in the range if we know all of them are in MOVABLE_ZONE and
- * that the movable zone guarantees that pages are migratable but
- * the later is not the case right now unfortunatelly. E.g. movablecore
- * can still lead to having bootmem allocations in zone_movable.
- */
+ unsigned long offset = pfn % pageblock_nr_pages;
if (is_migrate_cma_page(page)) {
/*
@@ -8237,22 +8311,25 @@
* so consider them movable here.
*/
if (is_migrate_cma(migratetype))
- return false;
+ return NULL;
- reason = "CMA page";
- goto unmovable;
+ return page;
}
- for (found = 0; iter < pageblock_nr_pages; iter++) {
- unsigned long check = pfn + iter;
-
- if (!pfn_valid_within(check))
+ for (; iter < pageblock_nr_pages - offset; iter++) {
+ if (!pfn_valid_within(pfn + iter))
continue;
- page = pfn_to_page(check);
+ page = pfn_to_page(pfn + iter);
+ /*
+ * Both, bootmem allocations and memory holes are marked
+ * PG_reserved and are unmovable. We can even have unmovable
+ * allocations inside ZONE_MOVABLE, for example when
+ * specifying "movablecore".
+ */
if (PageReserved(page))
- goto unmovable;
+ return page;
/*
* If the zone is movable and we have ruled out all reserved
@@ -8264,15 +8341,20 @@
/*
* Hugepages are not in LRU lists, but they're movable.
+ * THPs are on the LRU, but need to be counted as #small pages.
* We need not scan over tail pages because we don't
* handle each tail page individually in migration.
*/
- if (PageHuge(page)) {
+ if (PageHuge(page) || PageTransCompound(page)) {
struct page *head = compound_head(page);
unsigned int skip_pages;
- if (!hugepage_migration_supported(page_hstate(head)))
- goto unmovable;
+ if (PageHuge(page)) {
+ if (!hugepage_migration_supported(page_hstate(head)))
+ return page;
+ } else if (!PageLRU(head) && !__PageMovable(head)) {
+ return page;
+ }
skip_pages = compound_nr(head) - (page - head);
iter += skip_pages - 1;
@@ -8287,7 +8369,7 @@
*/
if (!page_ref_count(page)) {
if (PageBuddy(page))
- iter += (1 << page_order(page)) - 1;
+ iter += (1 << buddy_order(page)) - 1;
continue;
}
@@ -8295,36 +8377,33 @@
* The HWPoisoned page may be not in buddy system, and
* page_count() is not 0.
*/
- if ((flags & SKIP_HWPOISON) && PageHWPoison(page))
+ if ((flags & MEMORY_OFFLINE) && PageHWPoison(page))
continue;
- if (__PageMovable(page))
+ /*
+ * We treat all PageOffline() pages as movable when offlining
+ * to give drivers a chance to decrement their reference count
+ * in MEM_GOING_OFFLINE in order to indicate that these pages
+ * can be offlined as there are no direct references anymore.
+ * For actually unmovable PageOffline() where the driver does
+ * not support this, we will fail later when trying to actually
+ * move these pages that still have a reference count > 0.
+ * (false negatives in this function only)
+ */
+ if ((flags & MEMORY_OFFLINE) && PageOffline(page))
continue;
- if (!PageLRU(page))
- found++;
+ if (__PageMovable(page) || PageLRU(page))
+ continue;
+
/*
* If there are RECLAIMABLE pages, we need to check
* it. But now, memory offline itself doesn't call
* shrink_node_slabs() and it still to be fixed.
*/
- /*
- * If the page is not RAM, page_count()should be 0.
- * we don't need more check. This is an _used_ not-movable page.
- *
- * The problematic thing here is PG_reserved pages. PG_reserved
- * is set to both of a memory hole page and a _used_ kernel
- * page at boot.
- */
- if (found > count)
- goto unmovable;
+ return page;
}
- return false;
-unmovable:
- WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE);
- if (flags & REPORT_FAILURE)
- dump_page(pfn_to_page(pfn + iter), reason);
- return true;
+ return NULL;
}
#ifdef CONFIG_CONTIG_ALLOC
@@ -8345,10 +8424,14 @@
unsigned long start, unsigned long end)
{
/* This function is based on compact_zone() from compaction.c. */
- unsigned long nr_reclaimed;
+ unsigned int nr_reclaimed;
unsigned long pfn = start;
unsigned int tries = 0;
int ret = 0;
+ struct migration_target_control mtc = {
+ .nid = zone_to_nid(cc->zone),
+ .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL,
+ };
migrate_prep();
@@ -8375,8 +8458,8 @@
&cc->migratepages);
cc->nr_migratepages -= nr_reclaimed;
- ret = migrate_pages(&cc->migratepages, alloc_migrate_target,
- NULL, 0, cc->mode, MR_CONTIG_RANGE);
+ ret = migrate_pages(&cc->migratepages, alloc_migration_target,
+ NULL, (unsigned long)&mtc, cc->mode, MR_CONTIG_RANGE);
}
if (ret < 0) {
putback_movable_pages(&cc->migratepages);
@@ -8421,6 +8504,7 @@
.ignore_skip_hint = true,
.no_set_skip_hint = true,
.gfp_mask = current_gfp_context(gfp_mask),
+ .alloc_contig = true,
};
INIT_LIST_HEAD(&cc.migratepages);
@@ -8450,7 +8534,7 @@
ret = start_isolate_page_range(pfn_max_align_down(start),
pfn_max_align_up(end), migratetype, 0);
- if (ret < 0)
+ if (ret)
return ret;
/*
@@ -8498,7 +8582,7 @@
}
if (outer_start != start) {
- order = page_order(pfn_to_page(outer_start));
+ order = buddy_order(pfn_to_page(outer_start));
/*
* outer_start page could be small order buddy page and
@@ -8511,7 +8595,7 @@
}
/* Make sure the range is really isolated. */
- if (test_pages_isolated(outer_start, end, false)) {
+ if (test_pages_isolated(outer_start, end, 0)) {
pr_info_ratelimited("%s: [%lx, %lx) PFNs busy\n",
__func__, outer_start, end);
ret = -EBUSY;
@@ -8536,6 +8620,108 @@
pfn_max_align_up(end), migratetype);
return ret;
}
+EXPORT_SYMBOL(alloc_contig_range);
+
+static int __alloc_contig_pages(unsigned long start_pfn,
+ unsigned long nr_pages, gfp_t gfp_mask)
+{
+ unsigned long end_pfn = start_pfn + nr_pages;
+
+ return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE,
+ gfp_mask);
+}
+
+static bool pfn_range_valid_contig(struct zone *z, unsigned long start_pfn,
+ unsigned long nr_pages)
+{
+ unsigned long i, end_pfn = start_pfn + nr_pages;
+ struct page *page;
+
+ for (i = start_pfn; i < end_pfn; i++) {
+ page = pfn_to_online_page(i);
+ if (!page)
+ return false;
+
+ if (page_zone(page) != z)
+ return false;
+
+ if (PageReserved(page))
+ return false;
+
+ if (page_count(page) > 0)
+ return false;
+
+ if (PageHuge(page))
+ return false;
+ }
+ return true;
+}
+
+static bool zone_spans_last_pfn(const struct zone *zone,
+ unsigned long start_pfn, unsigned long nr_pages)
+{
+ unsigned long last_pfn = start_pfn + nr_pages - 1;
+
+ return zone_spans_pfn(zone, last_pfn);
+}
+
+/**
+ * alloc_contig_pages() -- tries to find and allocate contiguous range of pages
+ * @nr_pages: Number of contiguous pages to allocate
+ * @gfp_mask: GFP mask to limit search and used during compaction
+ * @nid: Target node
+ * @nodemask: Mask for other possible nodes
+ *
+ * This routine is a wrapper around alloc_contig_range(). It scans over zones
+ * on an applicable zonelist to find a contiguous pfn range which can then be
+ * tried for allocation with alloc_contig_range(). This routine is intended
+ * for allocation requests which can not be fulfilled with the buddy allocator.
+ *
+ * The allocated memory is always aligned to a page boundary. If nr_pages is a
+ * power of two then the alignment is guaranteed to be to the given nr_pages
+ * (e.g. 1GB request would be aligned to 1GB).
+ *
+ * Allocated pages can be freed with free_contig_range() or by manually calling
+ * __free_page() on each allocated page.
+ *
+ * Return: pointer to contiguous pages on success, or NULL if not successful.
+ */
+struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask,
+ int nid, nodemask_t *nodemask)
+{
+ unsigned long ret, pfn, flags;
+ struct zonelist *zonelist;
+ struct zone *zone;
+ struct zoneref *z;
+
+ zonelist = node_zonelist(nid, gfp_mask);
+ for_each_zone_zonelist_nodemask(zone, z, zonelist,
+ gfp_zone(gfp_mask), nodemask) {
+ spin_lock_irqsave(&zone->lock, flags);
+
+ pfn = ALIGN(zone->zone_start_pfn, nr_pages);
+ while (zone_spans_last_pfn(zone, pfn, nr_pages)) {
+ if (pfn_range_valid_contig(zone, pfn, nr_pages)) {
+ /*
+ * We release the zone lock here because
+ * alloc_contig_range() will also lock the zone
+ * at some point. If there's an allocation
+ * spinning on this lock, it may win the race
+ * and cause alloc_contig_range() to fail...
+ */
+ spin_unlock_irqrestore(&zone->lock, flags);
+ ret = __alloc_contig_pages(pfn, nr_pages,
+ gfp_mask);
+ if (!ret)
+ return pfn_to_page(pfn);
+ spin_lock_irqsave(&zone->lock, flags);
+ }
+ pfn += nr_pages;
+ }
+ spin_unlock_irqrestore(&zone->lock, flags);
+ }
+ return NULL;
+}
#endif /* CONFIG_CONTIG_ALLOC */
void free_contig_range(unsigned long pfn, unsigned int nr_pages)
@@ -8550,6 +8736,7 @@
}
WARN(count != 0, "%d pages are still in use!\n", count);
}
+EXPORT_SYMBOL(free_contig_range);
/*
* The zone indicated has a new number of managed_pages; batch sizes and percpu
@@ -8557,11 +8744,8 @@
*/
void __meminit zone_pcp_update(struct zone *zone)
{
- unsigned cpu;
mutex_lock(&pcp_batch_high_lock);
- for_each_possible_cpu(cpu)
- pageset_set_high_and_batch(zone,
- per_cpu_ptr(zone->pageset, cpu));
+ __zone_pcp_update(zone);
mutex_unlock(&pcp_batch_high_lock);
}
@@ -8586,35 +8770,21 @@
#ifdef CONFIG_MEMORY_HOTREMOVE
/*
- * All pages in the range must be in a single zone and isolated
- * before calling this.
+ * All pages in the range must be in a single zone, must not contain holes,
+ * must span full sections, and must be isolated before calling this function.
*/
-unsigned long
-__offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
+void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
{
+ unsigned long pfn = start_pfn;
struct page *page;
struct zone *zone;
- unsigned int order, i;
- unsigned long pfn;
+ unsigned int order;
unsigned long flags;
- unsigned long offlined_pages = 0;
-
- /* find the first valid pfn */
- for (pfn = start_pfn; pfn < end_pfn; pfn++)
- if (pfn_valid(pfn))
- break;
- if (pfn == end_pfn)
- return offlined_pages;
offline_mem_sections(pfn, end_pfn);
zone = page_zone(pfn_to_page(pfn));
spin_lock_irqsave(&zone->lock, flags);
- pfn = start_pfn;
while (pfn < end_pfn) {
- if (!pfn_valid(pfn)) {
- pfn++;
- continue;
- }
page = pfn_to_page(pfn);
/*
* The HWPoisoned page may be not in buddy system, and
@@ -8622,27 +8792,26 @@
*/
if (unlikely(!PageBuddy(page) && PageHWPoison(page))) {
pfn++;
- SetPageReserved(page);
- offlined_pages++;
+ continue;
+ }
+ /*
+ * At this point all remaining PageOffline() pages have a
+ * reference count of 0 and can simply be skipped.
+ */
+ if (PageOffline(page)) {
+ BUG_ON(page_count(page));
+ BUG_ON(PageBuddy(page));
+ pfn++;
continue;
}
BUG_ON(page_count(page));
BUG_ON(!PageBuddy(page));
- order = page_order(page);
- offlined_pages += 1 << order;
-#ifdef CONFIG_DEBUG_VM
- pr_info("remove from free list %lx %d %lx\n",
- pfn, 1 << order, end_pfn);
-#endif
- del_page_from_free_area(page, &zone->free_area[order]);
- for (i = 0; i < (1 << order); i++)
- SetPageReserved((page+i));
+ order = buddy_order(page);
+ del_page_from_free_list(page, zone, order);
pfn += (1 << order);
}
spin_unlock_irqrestore(&zone->lock, flags);
-
- return offlined_pages;
}
#endif
@@ -8657,7 +8826,7 @@
for (order = 0; order < MAX_ORDER; order++) {
struct page *page_head = page - (pfn & ((1 << order) - 1));
- if (PageBuddy(page_head) && page_order(page_head) >= order)
+ if (PageBuddy(page_head) && buddy_order(page_head) >= order)
break;
}
spin_unlock_irqrestore(&zone->lock, flags);
@@ -8667,30 +8836,87 @@
#ifdef CONFIG_MEMORY_FAILURE
/*
- * Set PG_hwpoison flag if a given page is confirmed to be a free page. This
- * test is performed under the zone lock to prevent a race against page
- * allocation.
+ * Break down a higher-order page in sub-pages, and keep our target out of
+ * buddy allocator.
*/
-bool set_hwpoison_free_buddy_page(struct page *page)
+static void break_down_buddy_pages(struct zone *zone, struct page *page,
+ struct page *target, int low, int high,
+ int migratetype)
+{
+ unsigned long size = 1 << high;
+ struct page *current_buddy, *next_page;
+
+ while (high > low) {
+ high--;
+ size >>= 1;
+
+ if (target >= &page[size]) {
+ next_page = page + size;
+ current_buddy = page;
+ } else {
+ next_page = page;
+ current_buddy = page + size;
+ }
+
+ if (set_page_guard(zone, current_buddy, high, migratetype))
+ continue;
+
+ if (current_buddy != target) {
+ add_to_free_list(current_buddy, zone, high, migratetype);
+ set_buddy_order(current_buddy, high);
+ page = next_page;
+ }
+ }
+}
+
+/*
+ * Take a page that will be marked as poisoned off the buddy allocator.
+ */
+bool take_page_off_buddy(struct page *page)
{
struct zone *zone = page_zone(page);
unsigned long pfn = page_to_pfn(page);
unsigned long flags;
unsigned int order;
- bool hwpoisoned = false;
+ bool ret = false;
spin_lock_irqsave(&zone->lock, flags);
for (order = 0; order < MAX_ORDER; order++) {
struct page *page_head = page - (pfn & ((1 << order) - 1));
+ int page_order = buddy_order(page_head);
- if (PageBuddy(page_head) && page_order(page_head) >= order) {
- if (!TestSetPageHWPoison(page))
- hwpoisoned = true;
+ if (PageBuddy(page_head) && page_order >= order) {
+ unsigned long pfn_head = page_to_pfn(page_head);
+ int migratetype = get_pfnblock_migratetype(page_head,
+ pfn_head);
+
+ del_page_from_free_list(page_head, zone, page_order);
+ break_down_buddy_pages(zone, page_head, page, 0,
+ page_order, migratetype);
+ if (!is_migrate_isolate(migratetype))
+ __mod_zone_freepage_state(zone, -1, migratetype);
+ ret = true;
break;
}
+ if (page_count(page_head) > 0)
+ break;
}
spin_unlock_irqrestore(&zone->lock, flags);
-
- return hwpoisoned;
+ return ret;
}
#endif
+
+#ifdef CONFIG_ZONE_DMA
+bool has_managed_dma(void)
+{
+ struct pglist_data *pgdat;
+
+ for_each_online_pgdat(pgdat) {
+ struct zone *zone = &pgdat->node_zones[ZONE_DMA];
+
+ if (managed_zone(zone))
+ return true;
+ }
+ return false;
+}
+#endif /* CONFIG_ZONE_DMA */