summaryrefslogtreecommitdiffstats
path: root/mm/page_alloc.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/page_alloc.c')
-rw-r--r--mm/page_alloc.c344
1 files changed, 195 insertions, 149 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 74af449b1f1..a6b17aa4740 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -48,6 +48,7 @@
#include <linux/page_cgroup.h>
#include <linux/debugobjects.h>
#include <linux/kmemleak.h>
+#include <linux/memory.h>
#include <trace/events/kmem.h>
#include <asm/tlbflush.h>
@@ -555,8 +556,9 @@ static void free_pcppages_bulk(struct zone *zone, int count,
page = list_entry(list->prev, struct page, lru);
/* must delete as __free_one_page list manipulates */
list_del(&page->lru);
- __free_one_page(page, zone, 0, migratetype);
- trace_mm_page_pcpu_drain(page, 0, migratetype);
+ /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */
+ __free_one_page(page, zone, 0, page_private(page));
+ trace_mm_page_pcpu_drain(page, 0, page_private(page));
} while (--count && --batch_free && !list_empty(list));
}
spin_unlock(&zone->lock);
@@ -1007,10 +1009,10 @@ static void drain_pages(unsigned int cpu)
struct per_cpu_pageset *pset;
struct per_cpu_pages *pcp;
- pset = zone_pcp(zone, cpu);
+ local_irq_save(flags);
+ pset = per_cpu_ptr(zone->pageset, cpu);
pcp = &pset->pcp;
- local_irq_save(flags);
free_pcppages_bulk(zone, pcp->count, pcp);
pcp->count = 0;
local_irq_restore(flags);
@@ -1094,7 +1096,6 @@ static void free_hot_cold_page(struct page *page, int cold)
arch_free_page(page, 0);
kernel_map_pages(page, 1, 0);
- pcp = &zone_pcp(zone, get_cpu())->pcp;
migratetype = get_pageblock_migratetype(page);
set_page_private(page, migratetype);
local_irq_save(flags);
@@ -1117,6 +1118,7 @@ static void free_hot_cold_page(struct page *page, int cold)
migratetype = MIGRATE_MOVABLE;
}
+ pcp = &this_cpu_ptr(zone->pageset)->pcp;
if (cold)
list_add_tail(&page->lru, &pcp->lists[migratetype]);
else
@@ -1129,7 +1131,6 @@ static void free_hot_cold_page(struct page *page, int cold)
out:
local_irq_restore(flags);
- put_cpu();
}
void free_hot_page(struct page *page)
@@ -1179,17 +1180,15 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
unsigned long flags;
struct page *page;
int cold = !!(gfp_flags & __GFP_COLD);
- int cpu;
again:
- cpu = get_cpu();
if (likely(order == 0)) {
struct per_cpu_pages *pcp;
struct list_head *list;
- pcp = &zone_pcp(zone, cpu)->pcp;
- list = &pcp->lists[migratetype];
local_irq_save(flags);
+ pcp = &this_cpu_ptr(zone->pageset)->pcp;
+ list = &pcp->lists[migratetype];
if (list_empty(list)) {
pcp->count += rmqueue_bulk(zone, 0,
pcp->batch, list,
@@ -1221,16 +1220,15 @@ again:
}
spin_lock_irqsave(&zone->lock, flags);
page = __rmqueue(zone, order, migratetype);
- __mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << order));
spin_unlock(&zone->lock);
if (!page)
goto failed;
+ __mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << order));
}
__count_zone_vm_events(PGALLOC, zone, 1 << order);
zone_statistics(preferred_zone, zone);
local_irq_restore(flags);
- put_cpu();
VM_BUG_ON(bad_range(zone, page));
if (prep_new_page(page, order, gfp_flags))
@@ -1239,7 +1237,6 @@ again:
failed:
local_irq_restore(flags);
- put_cpu();
return NULL;
}
@@ -2178,7 +2175,7 @@ void show_free_areas(void)
for_each_online_cpu(cpu) {
struct per_cpu_pageset *pageset;
- pageset = zone_pcp(zone, cpu);
+ pageset = per_cpu_ptr(zone->pageset, cpu);
printk("CPU %4d: hi:%5d, btch:%4d usd:%4d\n",
cpu, pageset->pcp.high,
@@ -2401,13 +2398,14 @@ int numa_zonelist_order_handler(ctl_table *table, int write,
{
char saved_string[NUMA_ZONELIST_ORDER_LEN];
int ret;
+ static DEFINE_MUTEX(zl_order_mutex);
+ mutex_lock(&zl_order_mutex);
if (write)
- strncpy(saved_string, (char*)table->data,
- NUMA_ZONELIST_ORDER_LEN);
+ strcpy(saved_string, (char*)table->data);
ret = proc_dostring(table, write, buffer, length, ppos);
if (ret)
- return ret;
+ goto out;
if (write) {
int oldval = user_zonelist_order;
if (__parse_numa_zonelist_order((char*)table->data)) {
@@ -2420,7 +2418,9 @@ int numa_zonelist_order_handler(ctl_table *table, int write,
} else if (oldval != user_zonelist_order)
build_all_zonelists();
}
- return 0;
+out:
+ mutex_unlock(&zl_order_mutex);
+ return ret;
}
@@ -2740,10 +2740,29 @@ static void build_zonelist_cache(pg_data_t *pgdat)
#endif /* CONFIG_NUMA */
+/*
+ * Boot pageset table. One per cpu which is going to be used for all
+ * zones and all nodes. The parameters will be set in such a way
+ * that an item put on a list will immediately be handed over to
+ * the buddy list. This is safe since pageset manipulation is done
+ * with interrupts disabled.
+ *
+ * The boot_pagesets must be kept even after bootup is complete for
+ * unused processors and/or zones. They do play a role for bootstrapping
+ * hotplugged processors.
+ *
+ * zoneinfo_show() and maybe other functions do
+ * not check if the processor is online before following the pageset pointer.
+ * Other parts of the kernel may not check if the zone is available.
+ */
+static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch);
+static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset);
+
/* return values int ....just for stop_machine() */
static int __build_all_zonelists(void *dummy)
{
int nid;
+ int cpu;
#ifdef CONFIG_NUMA
memset(node_load, 0, sizeof(node_load));
@@ -2754,6 +2773,23 @@ static int __build_all_zonelists(void *dummy)
build_zonelists(pgdat);
build_zonelist_cache(pgdat);
}
+
+ /*
+ * Initialize the boot_pagesets that are going to be used
+ * for bootstrapping processors. The real pagesets for
+ * each zone will be allocated later when the per cpu
+ * allocator is available.
+ *
+ * boot_pagesets are used also for bootstrapping offline
+ * cpus if the system is already booted because the pagesets
+ * are needed to initialize allocators on a specific cpu too.
+ * F.e. the percpu allocator needs the page allocator which
+ * needs the percpu allocator in order to allocate its pagesets
+ * (a chicken-egg dilemma).
+ */
+ for_each_possible_cpu(cpu)
+ setup_pageset(&per_cpu(boot_pageset, cpu), 0);
+
return 0;
}
@@ -3091,121 +3127,33 @@ static void setup_pagelist_highmark(struct per_cpu_pageset *p,
pcp->batch = PAGE_SHIFT * 8;
}
-
-#ifdef CONFIG_NUMA
-/*
- * Boot pageset table. One per cpu which is going to be used for all
- * zones and all nodes. The parameters will be set in such a way
- * that an item put on a list will immediately be handed over to
- * the buddy list. This is safe since pageset manipulation is done
- * with interrupts disabled.
- *
- * Some NUMA counter updates may also be caught by the boot pagesets.
- *
- * The boot_pagesets must be kept even after bootup is complete for
- * unused processors and/or zones. They do play a role for bootstrapping
- * hotplugged processors.
- *
- * zoneinfo_show() and maybe other functions do
- * not check if the processor is online before following the pageset pointer.
- * Other parts of the kernel may not check if the zone is available.
- */
-static struct per_cpu_pageset boot_pageset[NR_CPUS];
-
/*
- * Dynamically allocate memory for the
- * per cpu pageset array in struct zone.
+ * Allocate per cpu pagesets and initialize them.
+ * Before this call only boot pagesets were available.
+ * Boot pagesets will no longer be used by this processorr
+ * after setup_per_cpu_pageset().
*/
-static int __cpuinit process_zones(int cpu)
+void __init setup_per_cpu_pageset(void)
{
- struct zone *zone, *dzone;
- int node = cpu_to_node(cpu);
-
- node_set_state(node, N_CPU); /* this node has a cpu */
+ struct zone *zone;
+ int cpu;
for_each_populated_zone(zone) {
- zone_pcp(zone, cpu) = kmalloc_node(sizeof(struct per_cpu_pageset),
- GFP_KERNEL, node);
- if (!zone_pcp(zone, cpu))
- goto bad;
+ zone->pageset = alloc_percpu(struct per_cpu_pageset);
- setup_pageset(zone_pcp(zone, cpu), zone_batchsize(zone));
+ for_each_possible_cpu(cpu) {
+ struct per_cpu_pageset *pcp = per_cpu_ptr(zone->pageset, cpu);
- if (percpu_pagelist_fraction)
- setup_pagelist_highmark(zone_pcp(zone, cpu),
- (zone->present_pages / percpu_pagelist_fraction));
- }
+ setup_pageset(pcp, zone_batchsize(zone));
- return 0;
-bad:
- for_each_zone(dzone) {
- if (!populated_zone(dzone))
- continue;
- if (dzone == zone)
- break;
- kfree(zone_pcp(dzone, cpu));
- zone_pcp(dzone, cpu) = &boot_pageset[cpu];
- }
- return -ENOMEM;
-}
-
-static inline void free_zone_pagesets(int cpu)
-{
- struct zone *zone;
-
- for_each_zone(zone) {
- struct per_cpu_pageset *pset = zone_pcp(zone, cpu);
-
- /* Free per_cpu_pageset if it is slab allocated */
- if (pset != &boot_pageset[cpu])
- kfree(pset);
- zone_pcp(zone, cpu) = &boot_pageset[cpu];
+ if (percpu_pagelist_fraction)
+ setup_pagelist_highmark(pcp,
+ (zone->present_pages /
+ percpu_pagelist_fraction));
+ }
}
}
-static int __cpuinit pageset_cpuup_callback(struct notifier_block *nfb,
- unsigned long action,
- void *hcpu)
-{
- int cpu = (long)hcpu;
- int ret = NOTIFY_OK;
-
- switch (action) {
- case CPU_UP_PREPARE:
- case CPU_UP_PREPARE_FROZEN:
- if (process_zones(cpu))
- ret = NOTIFY_BAD;
- break;
- case CPU_UP_CANCELED:
- case CPU_UP_CANCELED_FROZEN:
- case CPU_DEAD:
- case CPU_DEAD_FROZEN:
- free_zone_pagesets(cpu);
- break;
- default:
- break;
- }
- return ret;
-}
-
-static struct notifier_block __cpuinitdata pageset_notifier =
- { &pageset_cpuup_callback, NULL, 0 };
-
-void __init setup_per_cpu_pageset(void)
-{
- int err;
-
- /* Initialize per_cpu_pageset for cpu 0.
- * A cpuup callback will do this for every cpu
- * as it comes online
- */
- err = process_zones(smp_processor_id());
- BUG_ON(err);
- register_cpu_notifier(&pageset_notifier);
-}
-
-#endif
-
static noinline __init_refok
int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
{
@@ -3259,7 +3207,7 @@ static int __zone_pcp_update(void *data)
struct per_cpu_pageset *pset;
struct per_cpu_pages *pcp;
- pset = zone_pcp(zone, cpu);
+ pset = per_cpu_ptr(zone->pageset, cpu);
pcp = &pset->pcp;
local_irq_save(flags);
@@ -3277,21 +3225,17 @@ void zone_pcp_update(struct zone *zone)
static __meminit void zone_pcp_init(struct zone *zone)
{
- int cpu;
- unsigned long batch = zone_batchsize(zone);
+ /*
+ * per cpu subsystem is not up at this point. The following code
+ * relies on the ability of the linker to provide the
+ * offset of a (static) per cpu variable into the per cpu area.
+ */
+ zone->pageset = &boot_pageset;
- for (cpu = 0; cpu < NR_CPUS; cpu++) {
-#ifdef CONFIG_NUMA
- /* Early boot. Slab allocator not functional yet */
- zone_pcp(zone, cpu) = &boot_pageset[cpu];
- setup_pageset(&boot_pageset[cpu],0);
-#else
- setup_pageset(zone_pcp(zone,cpu), batch);
-#endif
- }
if (zone->present_pages)
- printk(KERN_DEBUG " %s zone: %lu pages, LIFO batch:%lu\n",
- zone->name, zone->present_pages, batch);
+ printk(KERN_DEBUG " %s zone: %lu pages, LIFO batch:%u\n",
+ zone->name, zone->present_pages,
+ zone_batchsize(zone));
}
__meminit int init_currently_empty_zone(struct zone *zone,
@@ -3430,6 +3374,61 @@ void __init free_bootmem_with_active_regions(int nid,
}
}
+int __init add_from_early_node_map(struct range *range, int az,
+ int nr_range, int nid)
+{
+ int i;
+ u64 start, end;
+
+ /* need to go over early_node_map to find out good range for node */
+ for_each_active_range_index_in_nid(i, nid) {
+ start = early_node_map[i].start_pfn;
+ end = early_node_map[i].end_pfn;
+ nr_range = add_range(range, az, nr_range, start, end);
+ }
+ return nr_range;
+}
+
+#ifdef CONFIG_NO_BOOTMEM
+void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
+ u64 goal, u64 limit)
+{
+ int i;
+ void *ptr;
+
+ /* need to go over early_node_map to find out good range for node */
+ for_each_active_range_index_in_nid(i, nid) {
+ u64 addr;
+ u64 ei_start, ei_last;
+
+ ei_last = early_node_map[i].end_pfn;
+ ei_last <<= PAGE_SHIFT;
+ ei_start = early_node_map[i].start_pfn;
+ ei_start <<= PAGE_SHIFT;
+ addr = find_early_area(ei_start, ei_last,
+ goal, limit, size, align);
+
+ if (addr == -1ULL)
+ continue;
+
+#if 0
+ printk(KERN_DEBUG "alloc (nid=%d %llx - %llx) (%llx - %llx) %llx %llx => %llx\n",
+ nid,
+ ei_start, ei_last, goal, limit, size,
+ align, addr);
+#endif
+
+ ptr = phys_to_virt(addr);
+ memset(ptr, 0, size);
+ reserve_early_without_check(addr, addr + size, "BOOTMEM");
+ return ptr;
+ }
+
+ return NULL;
+}
+#endif
+
+
void __init work_with_active_regions(int nid, work_fn_t work_fn, void *data)
{
int i;
@@ -3579,7 +3578,7 @@ static unsigned long __meminit zone_spanned_pages_in_node(int nid,
* Return the number of holes in a range on a node. If nid is MAX_NUMNODES,
* then all holes in the requested range will be accounted for.
*/
-static unsigned long __meminit __absent_pages_in_range(int nid,
+unsigned long __meminit __absent_pages_in_range(int nid,
unsigned long range_start_pfn,
unsigned long range_end_pfn)
{
@@ -3994,7 +3993,7 @@ void __init add_active_range(unsigned int nid, unsigned long start_pfn,
}
/* Merge backward if suitable */
- if (start_pfn < early_node_map[i].end_pfn &&
+ if (start_pfn < early_node_map[i].start_pfn &&
end_pfn >= early_node_map[i].start_pfn) {
early_node_map[i].start_pfn = start_pfn;
return;
@@ -4108,7 +4107,7 @@ static int __init cmp_node_active_region(const void *a, const void *b)
}
/* sort the node_map by start_pfn */
-static void __init sort_node_map(void)
+void __init sort_node_map(void)
{
sort(early_node_map, (size_t)nr_nodemap_entries,
sizeof(struct node_active_region),
@@ -4462,7 +4461,11 @@ void __init set_dma_reserve(unsigned long new_dma_reserve)
}
#ifndef CONFIG_NEED_MULTIPLE_NODES
-struct pglist_data __refdata contig_page_data = { .bdata = &bootmem_node_data[0] };
+struct pglist_data __refdata contig_page_data = {
+#ifndef CONFIG_NO_BOOTMEM
+ .bdata = &bootmem_node_data[0]
+#endif
+ };
EXPORT_SYMBOL(contig_page_data);
#endif
@@ -4805,10 +4808,11 @@ int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
if (!write || (ret == -EINVAL))
return ret;
for_each_populated_zone(zone) {
- for_each_online_cpu(cpu) {
+ for_each_possible_cpu(cpu) {
unsigned long high;
high = zone->present_pages / percpu_pagelist_fraction;
- setup_pagelist_highmark(zone_pcp(zone, cpu), high);
+ setup_pagelist_highmark(
+ per_cpu_ptr(zone->pageset, cpu), high);
}
}
return 0;
@@ -5008,23 +5012,65 @@ void set_pageblock_flags_group(struct page *page, unsigned long flags,
int set_migratetype_isolate(struct page *page)
{
struct zone *zone;
- unsigned long flags;
+ struct page *curr_page;
+ unsigned long flags, pfn, iter;
+ unsigned long immobile = 0;
+ struct memory_isolate_notify arg;
+ int notifier_ret;
int ret = -EBUSY;
int zone_idx;
zone = page_zone(page);
zone_idx = zone_idx(zone);
+
spin_lock_irqsave(&zone->lock, flags);
+ if (get_pageblock_migratetype(page) == MIGRATE_MOVABLE ||
+ zone_idx == ZONE_MOVABLE) {
+ ret = 0;
+ goto out;
+ }
+
+ pfn = page_to_pfn(page);
+ arg.start_pfn = pfn;
+ arg.nr_pages = pageblock_nr_pages;
+ arg.pages_found = 0;
+
/*
- * In future, more migrate types will be able to be isolation target.
+ * It may be possible to isolate a pageblock even if the
+ * migratetype is not MIGRATE_MOVABLE. The memory isolation
+ * notifier chain is used by balloon drivers to return the
+ * number of pages in a range that are held by the balloon
+ * driver to shrink memory. If all the pages are accounted for
+ * by balloons, are free, or on the LRU, isolation can continue.
+ * Later, for example, when memory hotplug notifier runs, these
+ * pages reported as "can be isolated" should be isolated(freed)
+ * by the balloon driver through the memory notifier chain.
*/
- if (get_pageblock_migratetype(page) != MIGRATE_MOVABLE &&
- zone_idx != ZONE_MOVABLE)
+ notifier_ret = memory_isolate_notify(MEM_ISOLATE_COUNT, &arg);
+ notifier_ret = notifier_to_errno(notifier_ret);
+ if (notifier_ret || !arg.pages_found)
goto out;
- set_pageblock_migratetype(page, MIGRATE_ISOLATE);
- move_freepages_block(zone, page, MIGRATE_ISOLATE);
- ret = 0;
+
+ for (iter = pfn; iter < (pfn + pageblock_nr_pages); iter++) {
+ if (!pfn_valid_within(pfn))
+ continue;
+
+ curr_page = pfn_to_page(iter);
+ if (!page_count(curr_page) || PageLRU(curr_page))
+ continue;
+
+ immobile++;
+ }
+
+ if (arg.pages_found == immobile)
+ ret = 0;
+
out:
+ if (!ret) {
+ set_pageblock_migratetype(page, MIGRATE_ISOLATE);
+ move_freepages_block(zone, page, MIGRATE_ISOLATE);
+ }
+
spin_unlock_irqrestore(&zone->lock, flags);
if (!ret)
drain_all_pages();
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-01-08 03:51:57 +0000