summaryrefslogtreecommitdiff
path: root/mm/page_alloc.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/page_alloc.c')
-rw-r--r--mm/page_alloc.c172
1 files changed, 117 insertions, 55 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2bcdfbf8c36d..5b7402abc1d6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -238,9 +238,21 @@ compound_page_dtor * const compound_page_dtors[] = {
#endif
};
+/*
+ * Try to keep at least this much lowmem free. Do not allow normal
+ * allocations below this point, only high priority ones. Automatically
+ * tuned according to the amount of memory in the system.
+ */
int min_free_kbytes = 1024;
int user_min_free_kbytes = -1;
+/*
+ * Extra memory for the system to try freeing. Used to temporarily
+ * free memory, to make space for new workloads. Anyone can allocate
+ * down to the min watermarks controlled by min_free_kbytes above.
+ */
+int extra_free_kbytes = 0;
+
static unsigned long __meminitdata nr_kernel_pages;
static unsigned long __meminitdata nr_all_pages;
static unsigned long __meminitdata dma_reserve;
@@ -267,8 +279,37 @@ EXPORT_SYMBOL(nr_online_nodes);
int page_group_by_mobility_disabled __read_mostly;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+
+/*
+ * Determine how many pages need to be initialized durig early boot
+ * (non-deferred initialization).
+ * The value of first_deferred_pfn will be set later, once non-deferred pages
+ * are initialized, but for now set it ULONG_MAX.
+ */
static inline void reset_deferred_meminit(pg_data_t *pgdat)
{
+ phys_addr_t start_addr, end_addr;
+ unsigned long max_pgcnt;
+ unsigned long reserved;
+
+ /*
+ * Initialise at least 2G of a node but also take into account that
+ * two large system hashes that can take up 1GB for 0.25TB/node.
+ */
+ max_pgcnt = max(2UL << (30 - PAGE_SHIFT),
+ (pgdat->node_spanned_pages >> 8));
+
+ /*
+ * Compensate the all the memblock reservations (e.g. crash kernel)
+ * from the initial estimation to make sure we will initialize enough
+ * memory to boot.
+ */
+ start_addr = PFN_PHYS(pgdat->node_start_pfn);
+ end_addr = PFN_PHYS(pgdat->node_start_pfn + max_pgcnt);
+ reserved = memblock_reserved_memory_within(start_addr, end_addr);
+ max_pgcnt += PHYS_PFN(reserved);
+
+ pgdat->static_init_pgcnt = min(max_pgcnt, pgdat->node_spanned_pages);
pgdat->first_deferred_pfn = ULONG_MAX;
}
@@ -302,10 +343,9 @@ static inline bool update_defer_init(pg_data_t *pgdat,
/* Always populate low zones for address-contrained allocations */
if (zone_end < pgdat_end_pfn(pgdat))
return true;
-
/* Initialise at least 2G of the highest zone */
(*nr_initialised)++;
- if (*nr_initialised > (2UL << (30 - PAGE_SHIFT)) &&
+ if ((*nr_initialised > pgdat->static_init_pgcnt) &&
(pfn & (PAGES_PER_SECTION - 1)) == 0) {
pgdat->first_deferred_pfn = pfn;
return false;
@@ -541,6 +581,9 @@ static inline void set_page_guard(struct zone *zone, struct page *page,
return;
page_ext = lookup_page_ext(page);
+ if (unlikely(!page_ext))
+ return;
+
__set_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
INIT_LIST_HEAD(&page->lru);
@@ -558,6 +601,9 @@ static inline void clear_page_guard(struct zone *zone, struct page *page,
return;
page_ext = lookup_page_ext(page);
+ if (unlikely(!page_ext))
+ return;
+
__clear_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags);
set_page_private(page, 0);
@@ -1508,14 +1554,14 @@ int move_freepages(struct zone *zone,
#endif
for (page = start_page; page <= end_page;) {
- /* Make sure we are not inadvertently changing nodes */
- VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);
-
if (!pfn_valid_within(page_to_pfn(page))) {
page++;
continue;
}
+ /* Make sure we are not inadvertently changing nodes */
+ VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page);
+
if (!PageBuddy(page)) {
page++;
continue;
@@ -1729,13 +1775,25 @@ static void unreserve_highatomic_pageblock(const struct alloc_context *ac)
struct page, lru);
/*
- * It should never happen but changes to locking could
- * inadvertently allow a per-cpu drain to add pages
- * to MIGRATE_HIGHATOMIC while unreserving so be safe
- * and watch for underflows.
+ * In page freeing path, migratetype change is racy so
+ * we can counter several free pages in a pageblock
+ * in this loop althoug we changed the pageblock type
+ * from highatomic to ac->migratetype. So we should
+ * adjust the count once.
*/
- zone->nr_reserved_highatomic -= min(pageblock_nr_pages,
- zone->nr_reserved_highatomic);
+ if (get_pageblock_migratetype(page) ==
+ MIGRATE_HIGHATOMIC) {
+ /*
+ * It should never happen but changes to
+ * locking could inadvertently allow a per-cpu
+ * drain to add pages to MIGRATE_HIGHATOMIC
+ * while unreserving so be safe and watch for
+ * underflows.
+ */
+ zone->nr_reserved_highatomic -= min(
+ pageblock_nr_pages,
+ zone->nr_reserved_highatomic);
+ }
/*
* Convert to ac->migratetype and avoid the normal
@@ -2422,9 +2480,6 @@ static bool __zone_watermark_ok(struct zone *z, unsigned int order,
if (!area->nr_free)
continue;
- if (alloc_harder)
- return true;
-
for (mt = 0; mt < MIGRATE_PCPTYPES; mt++) {
if (!list_empty(&area->free_list[mt]))
return true;
@@ -2436,6 +2491,9 @@ static bool __zone_watermark_ok(struct zone *z, unsigned int order,
return true;
}
#endif
+ if (alloc_harder &&
+ !list_empty(&area->free_list[MIGRATE_HIGHATOMIC]))
+ return true;
}
return false;
}
@@ -2467,7 +2525,7 @@ static bool zone_local(struct zone *local_zone, struct zone *zone)
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{
- return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <
+ return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <=
RECLAIM_DISTANCE;
}
#else /* CONFIG_NUMA */
@@ -3063,8 +3121,6 @@ retry:
* the allocation is high priority and these type of
* allocations are system rather than user orientated
*/
- ac->zonelist = node_zonelist(numa_node_id(), gfp_mask);
-
page = __alloc_pages_high_priority(gfp_mask, order, ac);
if (page) {
@@ -3939,8 +3995,7 @@ static int __parse_numa_zonelist_order(char *s)
user_zonelist_order = ZONELIST_ORDER_ZONE;
} else {
printk(KERN_WARNING
- "Ignoring invalid numa_zonelist_order value: "
- "%s\n", s);
+ "Ignoring invalid numa_zonelist_order value: %s\n", s);
return -EINVAL;
}
return 0;
@@ -4405,12 +4460,11 @@ void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone)
else
page_group_by_mobility_disabled = 0;
- pr_info("Built %i zonelists in %s order, mobility grouping %s. "
- "Total pages: %ld\n",
- nr_online_nodes,
- zonelist_order_name[current_zonelist_order],
- page_group_by_mobility_disabled ? "off" : "on",
- vm_total_pages);
+ pr_info("Built %i zonelists in %s order, mobility grouping %s. Total pages: %ld\n",
+ nr_online_nodes,
+ zonelist_order_name[current_zonelist_order],
+ page_group_by_mobility_disabled ? "off" : "on",
+ vm_total_pages);
#ifdef CONFIG_NUMA
pr_info("Policy zone: %s\n", zone_names[policy_zone]);
#endif
@@ -5343,7 +5397,6 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
/* pg_data_t should be reset to zero when it's allocated */
WARN_ON(pgdat->nr_zones || pgdat->classzone_idx);
- reset_deferred_meminit(pgdat);
pgdat->node_id = nid;
pgdat->node_start_pfn = node_start_pfn;
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
@@ -5362,6 +5415,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
(unsigned long)pgdat->node_mem_map);
#endif
+ reset_deferred_meminit(pgdat);
free_area_init_core(pgdat);
}
@@ -5696,15 +5750,18 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
sizeof(arch_zone_lowest_possible_pfn));
memset(arch_zone_highest_possible_pfn, 0,
sizeof(arch_zone_highest_possible_pfn));
- arch_zone_lowest_possible_pfn[0] = find_min_pfn_with_active_regions();
- arch_zone_highest_possible_pfn[0] = max_zone_pfn[0];
- for (i = 1; i < MAX_NR_ZONES; i++) {
+
+ start_pfn = find_min_pfn_with_active_regions();
+
+ for (i = 0; i < MAX_NR_ZONES; i++) {
if (i == ZONE_MOVABLE)
continue;
- arch_zone_lowest_possible_pfn[i] =
- arch_zone_highest_possible_pfn[i-1];
- arch_zone_highest_possible_pfn[i] =
- max(max_zone_pfn[i], arch_zone_lowest_possible_pfn[i]);
+
+ 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;
+
+ start_pfn = end_pfn;
}
arch_zone_lowest_possible_pfn[ZONE_MOVABLE] = 0;
arch_zone_highest_possible_pfn[ZONE_MOVABLE] = 0;
@@ -5825,8 +5882,8 @@ unsigned long free_reserved_area(void *start, void *end, int poison, char *s)
}
if (pages && s)
- pr_info("Freeing %s memory: %ldK (%p - %p)\n",
- s, pages << (PAGE_SHIFT - 10), start, end);
+ pr_info("Freeing %s memory: %ldK\n",
+ s, pages << (PAGE_SHIFT - 10));
return pages;
}
@@ -5878,22 +5935,21 @@ void __init mem_init_print_info(const char *str)
#undef adj_init_size
- pr_info("Memory: %luK/%luK available "
- "(%luK kernel code, %luK rwdata, %luK rodata, "
- "%luK init, %luK bss, %luK reserved, %luK cma-reserved"
+ pr_info("Memory: %luK/%luK available (%luK kernel code, %luK rwdata, %luK rodata, %luK init, %luK bss, %luK reserved, %luK cma-reserved"
#ifdef CONFIG_HIGHMEM
- ", %luK highmem"
+ ", %luK highmem"
#endif
- "%s%s)\n",
- nr_free_pages() << (PAGE_SHIFT-10), physpages << (PAGE_SHIFT-10),
- codesize >> 10, datasize >> 10, rosize >> 10,
- (init_data_size + init_code_size) >> 10, bss_size >> 10,
- (physpages - totalram_pages - totalcma_pages) << (PAGE_SHIFT-10),
- totalcma_pages << (PAGE_SHIFT-10),
+ "%s%s)\n",
+ nr_free_pages() << (PAGE_SHIFT - 10),
+ physpages << (PAGE_SHIFT - 10),
+ codesize >> 10, datasize >> 10, rosize >> 10,
+ (init_data_size + init_code_size) >> 10, bss_size >> 10,
+ (physpages - totalram_pages - totalcma_pages) << (PAGE_SHIFT - 10),
+ totalcma_pages << (PAGE_SHIFT - 10),
#ifdef CONFIG_HIGHMEM
- totalhigh_pages << (PAGE_SHIFT-10),
+ totalhigh_pages << (PAGE_SHIFT - 10),
#endif
- str ? ", " : "", str ? str : "");
+ str ? ", " : "", str ? str : "");
}
/**
@@ -6037,6 +6093,7 @@ static void setup_per_zone_lowmem_reserve(void)
static void __setup_per_zone_wmarks(void)
{
unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
+ unsigned long pages_low = extra_free_kbytes >> (PAGE_SHIFT - 10);
unsigned long lowmem_pages = 0;
struct zone *zone;
unsigned long flags;
@@ -6048,11 +6105,14 @@ static void __setup_per_zone_wmarks(void)
}
for_each_zone(zone) {
- u64 tmp;
+ u64 min, low;
spin_lock_irqsave(&zone->lock, flags);
- tmp = (u64)pages_min * zone->managed_pages;
- do_div(tmp, lowmem_pages);
+ min = (u64)pages_min * zone->managed_pages;
+ do_div(min, lowmem_pages);
+ low = (u64)pages_low * zone->managed_pages;
+ do_div(low, vm_total_pages);
+
if (is_highmem(zone)) {
/*
* __GFP_HIGH and PF_MEMALLOC allocations usually don't
@@ -6073,11 +6133,13 @@ static void __setup_per_zone_wmarks(void)
* If it's a lowmem zone, reserve a number of pages
* proportionate to the zone's size.
*/
- zone->watermark[WMARK_MIN] = tmp;
+ zone->watermark[WMARK_MIN] = min;
}
- zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + (tmp >> 2);
- zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
+ zone->watermark[WMARK_LOW] = min_wmark_pages(zone) +
+ low + (min >> 2);
+ zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) +
+ low + (min >> 1);
__mod_zone_page_state(zone, NR_ALLOC_BATCH,
high_wmark_pages(zone) - low_wmark_pages(zone) -
@@ -6200,7 +6262,7 @@ core_initcall(init_per_zone_wmark_min)
/*
* min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so
* that we can call two helper functions whenever min_free_kbytes
- * changes.
+ * or extra_free_kbytes changes.
*/
int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
@@ -6782,7 +6844,7 @@ int alloc_contig_range(unsigned long start, unsigned long end,
/* Make sure the range is really isolated. */
if (test_pages_isolated(outer_start, end, false)) {
- pr_info("%s: [%lx, %lx) PFNs busy\n",
+ pr_info_ratelimited("%s: [%lx, %lx) PFNs busy\n",
__func__, outer_start, end);
ret = -EBUSY;
goto done;
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-24 19:54:10 +0000