#include <linux/kmemleak.h>
#include <linux/compaction.h>
#include <trace/events/kmem.h>
-#include <linux/ftrace_event.h>
-#include <linux/memcontrol.h>
#include <linux/prefetch.h>
#include <linux/mm_inline.h>
#include <linux/migrate.h>
* Remove at a later date when no bug reports exist related to
* grouping pages by mobility
*/
- BUG_ON(page_zone(start_page) != page_zone(end_page));
+ VM_BUG_ON(page_zone(start_page) != page_zone(end_page));
#endif
for (page = start_page; page <= end_page;) {
__mod_zone_page_state(zone, NR_ALLOC_BATCH, -(1 << order));
if (atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]) <= 0 &&
- !zone_is_fair_depleted(zone))
- zone_set_flag(zone, ZONE_FAIR_DEPLETED);
+ !test_bit(ZONE_FAIR_DEPLETED, &zone->flags))
+ set_bit(ZONE_FAIR_DEPLETED, &zone->flags);
__count_zone_vm_events(PGALLOC, zone, 1 << order);
zone_statistics(preferred_zone, zone, gfp_flags);
mod_zone_page_state(zone, NR_ALLOC_BATCH,
high_wmark_pages(zone) - low_wmark_pages(zone) -
atomic_long_read(&zone->vm_stat[NR_ALLOC_BATCH]));
- zone_clear_flag(zone, ZONE_FAIR_DEPLETED);
+ clear_bit(ZONE_FAIR_DEPLETED, &zone->flags);
} while (zone++ != preferred_zone);
}
if (alloc_flags & ALLOC_FAIR) {
if (!zone_local(preferred_zone, zone))
break;
- if (zone_is_fair_depleted(zone)) {
+ if (test_bit(ZONE_FAIR_DEPLETED, &zone->flags)) {
nr_fair_skipped++;
continue;
}
zonelist->_zonerefs[pos].zone_idx = 0;
}
+#if defined(CONFIG_64BIT)
+/*
+ * Devices that require DMA32/DMA are relatively rare and do not justify a
+ * penalty to every machine in case the specialised case applies. Default
+ * to Node-ordering on 64-bit NUMA machines
+ */
+static int default_zonelist_order(void)
+{
+ return ZONELIST_ORDER_NODE;
+}
+#else
+/*
+ * On 32-bit, the Normal zone needs to be preserved for allocations accessible
+ * by the kernel. If processes running on node 0 deplete the low memory zone
+ * then reclaim will occur more frequency increasing stalls and potentially
+ * be easier to OOM if a large percentage of the zone is under writeback or
+ * dirty. The problem is significantly worse if CONFIG_HIGHPTE is not set.
+ * Hence, default to zone ordering on 32-bit.
+ */
static int default_zonelist_order(void)
{
- int nid, zone_type;
- unsigned long low_kmem_size, total_size;
- struct zone *z;
- int average_size;
- /*
- * ZONE_DMA and ZONE_DMA32 can be very small area in the system.
- * If they are really small and used heavily, the system can fall
- * into OOM very easily.
- * This function detect ZONE_DMA/DMA32 size and configures zone order.
- */
- /* Is there ZONE_NORMAL ? (ex. ppc has only DMA zone..) */
- low_kmem_size = 0;
- total_size = 0;
- for_each_online_node(nid) {
- for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) {
- z = &NODE_DATA(nid)->node_zones[zone_type];
- if (populated_zone(z)) {
- if (zone_type < ZONE_NORMAL)
- low_kmem_size += z->managed_pages;
- total_size += z->managed_pages;
- } else if (zone_type == ZONE_NORMAL) {
- /*
- * If any node has only lowmem, then node order
- * is preferred to allow kernel allocations
- * locally; otherwise, they can easily infringe
- * on other nodes when there is an abundance of
- * lowmem available to allocate from.
- */
- return ZONELIST_ORDER_NODE;
- }
- }
- }
- if (!low_kmem_size || /* there are no DMA area. */
- low_kmem_size > total_size/2) /* DMA/DMA32 is big. */
- return ZONELIST_ORDER_NODE;
- /*
- * look into each node's config.
- * If there is a node whose DMA/DMA32 memory is very big area on
- * local memory, NODE_ORDER may be suitable.
- */
- average_size = total_size /
- (nodes_weight(node_states[N_MEMORY]) + 1);
- for_each_online_node(nid) {
- low_kmem_size = 0;
- total_size = 0;
- for (zone_type = 0; zone_type < MAX_NR_ZONES; zone_type++) {
- z = &NODE_DATA(nid)->node_zones[zone_type];
- if (populated_zone(z)) {
- if (zone_type < ZONE_NORMAL)
- low_kmem_size += z->present_pages;
- total_size += z->present_pages;
- }
- }
- if (low_kmem_size &&
- total_size > average_size && /* ignore small node */
- low_kmem_size > total_size * 70/100)
- return ZONELIST_ORDER_NODE;
- }
return ZONELIST_ORDER_ZONE;
}
+#endif /* CONFIG_64BIT */
static void set_zonelist_order(void)
{
pgdat->node_start_pfn = node_start_pfn;
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
get_pfn_range_for_nid(nid, &start_pfn, &end_pfn);
+ printk(KERN_INFO "Initmem setup node %d [mem %#010Lx-%#010Lx]\n", nid,
+ (u64) start_pfn << PAGE_SHIFT, (u64) (end_pfn << PAGE_SHIFT) - 1);
#endif
calculate_node_totalpages(pgdat, start_pfn, end_pfn,
zones_size, zholes_size);
return order < MAX_ORDER;
}
#endif
-
-static const struct trace_print_flags pageflag_names[] = {
- {1UL << PG_locked, "locked" },
- {1UL << PG_error, "error" },
- {1UL << PG_referenced, "referenced" },
- {1UL << PG_uptodate, "uptodate" },
- {1UL << PG_dirty, "dirty" },
- {1UL << PG_lru, "lru" },
- {1UL << PG_active, "active" },
- {1UL << PG_slab, "slab" },
- {1UL << PG_owner_priv_1, "owner_priv_1" },
- {1UL << PG_arch_1, "arch_1" },
- {1UL << PG_reserved, "reserved" },
- {1UL << PG_private, "private" },
- {1UL << PG_private_2, "private_2" },
- {1UL << PG_writeback, "writeback" },
-#ifdef CONFIG_PAGEFLAGS_EXTENDED
- {1UL << PG_head, "head" },
- {1UL << PG_tail, "tail" },
-#else
- {1UL << PG_compound, "compound" },
-#endif
- {1UL << PG_swapcache, "swapcache" },
- {1UL << PG_mappedtodisk, "mappedtodisk" },
- {1UL << PG_reclaim, "reclaim" },
- {1UL << PG_swapbacked, "swapbacked" },
- {1UL << PG_unevictable, "unevictable" },
-#ifdef CONFIG_MMU
- {1UL << PG_mlocked, "mlocked" },
-#endif
-#ifdef CONFIG_ARCH_USES_PG_UNCACHED
- {1UL << PG_uncached, "uncached" },
-#endif
-#ifdef CONFIG_MEMORY_FAILURE
- {1UL << PG_hwpoison, "hwpoison" },
-#endif
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- {1UL << PG_compound_lock, "compound_lock" },
-#endif
-};
-
-static void dump_flags(unsigned long flags,
- const struct trace_print_flags *names, int count)
-{
- const char *delim = "";
- unsigned long mask;
- int i;
-
- printk(KERN_ALERT "flags: %#lx(", flags);
-
- /* remove zone id */
- flags &= (1UL << NR_PAGEFLAGS) - 1;
-
- for (i = 0; i < count && flags; i++) {
-
- mask = names[i].mask;
- if ((flags & mask) != mask)
- continue;
-
- flags &= ~mask;
- printk("%s%s", delim, names[i].name);
- delim = "|";
- }
-
- /* check for left over flags */
- if (flags)
- printk("%s%#lx", delim, flags);
-
- printk(")\n");
-}
-
-void dump_page_badflags(struct page *page, const char *reason,
- unsigned long badflags)
-{
- printk(KERN_ALERT
- "page:%p count:%d mapcount:%d mapping:%p index:%#lx\n",
- page, atomic_read(&page->_count), page_mapcount(page),
- page->mapping, page->index);
- BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS);
- dump_flags(page->flags, pageflag_names, ARRAY_SIZE(pageflag_names));
- if (reason)
- pr_alert("page dumped because: %s\n", reason);
- if (page->flags & badflags) {
- pr_alert("bad because of flags:\n");
- dump_flags(page->flags & badflags,
- pageflag_names, ARRAY_SIZE(pageflag_names));
- }
- mem_cgroup_print_bad_page(page);
-}
-
-void dump_page(struct page *page, const char *reason)
-{
- dump_page_badflags(page, reason, 0);
-}
-EXPORT_SYMBOL(dump_page);
-
-#ifdef CONFIG_DEBUG_VM
-
-static const struct trace_print_flags vmaflags_names[] = {
- {VM_READ, "read" },
- {VM_WRITE, "write" },
- {VM_EXEC, "exec" },
- {VM_SHARED, "shared" },
- {VM_MAYREAD, "mayread" },
- {VM_MAYWRITE, "maywrite" },
- {VM_MAYEXEC, "mayexec" },
- {VM_MAYSHARE, "mayshare" },
- {VM_GROWSDOWN, "growsdown" },
- {VM_PFNMAP, "pfnmap" },
- {VM_DENYWRITE, "denywrite" },
- {VM_LOCKED, "locked" },
- {VM_IO, "io" },
- {VM_SEQ_READ, "seqread" },
- {VM_RAND_READ, "randread" },
- {VM_DONTCOPY, "dontcopy" },
- {VM_DONTEXPAND, "dontexpand" },
- {VM_ACCOUNT, "account" },
- {VM_NORESERVE, "noreserve" },
- {VM_HUGETLB, "hugetlb" },
- {VM_NONLINEAR, "nonlinear" },
-#if defined(CONFIG_X86)
- {VM_PAT, "pat" },
-#elif defined(CONFIG_PPC)
- {VM_SAO, "sao" },
-#elif defined(CONFIG_PARISC) || defined(CONFIG_METAG) || defined(CONFIG_IA64)
- {VM_GROWSUP, "growsup" },
-#elif !defined(CONFIG_MMU)
- {VM_MAPPED_COPY, "mappedcopy" },
-#else
- {VM_ARCH_1, "arch_1" },
-#endif
- {VM_DONTDUMP, "dontdump" },
-#ifdef CONFIG_MEM_SOFT_DIRTY
- {VM_SOFTDIRTY, "softdirty" },
-#endif
- {VM_MIXEDMAP, "mixedmap" },
- {VM_HUGEPAGE, "hugepage" },
- {VM_NOHUGEPAGE, "nohugepage" },
- {VM_MERGEABLE, "mergeable" },
-};
-
-void dump_vma(const struct vm_area_struct *vma)
-{
- printk(KERN_ALERT
- "vma %p start %p end %p\n"
- "next %p prev %p mm %p\n"
- "prot %lx anon_vma %p vm_ops %p\n"
- "pgoff %lx file %p private_data %p\n",
- vma, (void *)vma->vm_start, (void *)vma->vm_end, vma->vm_next,
- vma->vm_prev, vma->vm_mm,
- (unsigned long)pgprot_val(vma->vm_page_prot),
- vma->anon_vma, vma->vm_ops, vma->vm_pgoff,
- vma->vm_file, vma->vm_private_data);
- dump_flags(vma->vm_flags, vmaflags_names, ARRAY_SIZE(vmaflags_names));
-}
-EXPORT_SYMBOL(dump_vma);
-
-#endif /* CONFIG_DEBUG_VM */