int user_min_free_kbytes = -1;
int watermark_scale_factor = 10;
-static unsigned long __meminitdata nr_kernel_pages;
-static unsigned long __meminitdata nr_all_pages;
-static unsigned long __meminitdata dma_reserve;
+static unsigned long nr_kernel_pages __meminitdata;
+static unsigned long nr_all_pages __meminitdata;
+static unsigned long dma_reserve __meminitdata;
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
-static unsigned long __meminitdata arch_zone_lowest_possible_pfn[MAX_NR_ZONES];
-static unsigned long __meminitdata arch_zone_highest_possible_pfn[MAX_NR_ZONES];
-static unsigned long __initdata required_kernelcore;
-static unsigned long __initdata required_movablecore;
-static unsigned long __meminitdata zone_movable_pfn[MAX_NUMNODES];
-static bool mirrored_kernelcore;
+static unsigned long arch_zone_lowest_possible_pfn[MAX_NR_ZONES] __meminitdata;
+static unsigned long arch_zone_highest_possible_pfn[MAX_NR_ZONES] __meminitdata;
+static unsigned long required_kernelcore __initdata;
+static unsigned long required_kernelcore_percent __initdata;
+static unsigned long required_movablecore __initdata;
+static unsigned long required_movablecore_percent __initdata;
+static unsigned long zone_movable_pfn[MAX_NUMNODES] __meminitdata;
+static bool mirrored_kernelcore __meminitdata;
/* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */
int movable_zone;
int page_group_by_mobility_disabled __read_mostly;
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
-
-/*
- * Determine how many pages need to be initialized during 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;
-}
-
/* Returns true if the struct page for the pfn is uninitialised */
static inline bool __meminit early_page_uninitialised(unsigned long pfn)
{
return true;
}
#else
-static inline void reset_deferred_meminit(pg_data_t *pgdat)
-{
-}
-
static inline bool early_page_uninitialised(unsigned long pfn)
{
return false;
}
#endif /* CONFIG_DEBUG_VM */
+static inline void prefetch_buddy(struct page *page)
+{
+ unsigned long pfn = page_to_pfn(page);
+ unsigned long buddy_pfn = __find_buddy_pfn(pfn, 0);
+ struct page *buddy = page + (buddy_pfn - pfn);
+
+ prefetch(buddy);
+}
+
/*
* Frees a number of pages from the PCP lists
* Assumes all pages on list are in same zone, and of same order.
{
int migratetype = 0;
int batch_free = 0;
+ int prefetch_nr = 0;
bool isolated_pageblocks;
-
- spin_lock(&zone->lock);
- isolated_pageblocks = has_isolate_pageblock(zone);
+ struct page *page, *tmp;
+ LIST_HEAD(head);
while (count) {
- struct page *page;
struct list_head *list;
/*
batch_free = count;
do {
- int mt; /* migratetype of the to-be-freed page */
-
page = list_last_entry(list, struct page, lru);
- /* must delete as __free_one_page list manipulates */
+ /* must delete to avoid corrupting pcp list */
list_del(&page->lru);
-
- mt = get_pcppage_migratetype(page);
- /* MIGRATE_ISOLATE page should not go to pcplists */
- VM_BUG_ON_PAGE(is_migrate_isolate(mt), page);
- /* Pageblock could have been isolated meanwhile */
- if (unlikely(isolated_pageblocks))
- mt = get_pageblock_migratetype(page);
+ pcp->count--;
if (bulkfree_pcp_prepare(page))
continue;
- __free_one_page(page, page_to_pfn(page), zone, 0, mt);
- trace_mm_page_pcpu_drain(page, 0, mt);
+ list_add_tail(&page->lru, &head);
+
+ /*
+ * We are going to put the page back to the global
+ * pool, prefetch its buddy to speed up later access
+ * under zone->lock. It is believed the overhead of
+ * an additional test and calculating buddy_pfn here
+ * can be offset by reduced memory latency later. To
+ * avoid excessive prefetching due to large count, only
+ * prefetch buddy for the first pcp->batch nr of pages.
+ */
+ if (prefetch_nr++ < pcp->batch)
+ prefetch_buddy(page);
} while (--count && --batch_free && !list_empty(list));
}
+
+ spin_lock(&zone->lock);
+ isolated_pageblocks = has_isolate_pageblock(zone);
+
+ /*
+ * Use safe version since after __free_one_page(),
+ * page->lru.next will not point to original list.
+ */
+ list_for_each_entry_safe(page, tmp, &head, lru) {
+ int mt = get_pcppage_migratetype(page);
+ /* MIGRATE_ISOLATE page should not go to pcplists */
+ VM_BUG_ON_PAGE(is_migrate_isolate(mt), page);
+ /* Pageblock could have been isolated meanwhile */
+ if (unlikely(isolated_pageblocks))
+ mt = get_pageblock_migratetype(page);
+
+ __free_one_page(page, page_to_pfn(page), zone, 0, mt);
+ trace_mm_page_pcpu_drain(page, 0, mt);
+ }
spin_unlock(&zone->lock);
}
}
static void __meminit __init_single_page(struct page *page, unsigned long pfn,
- unsigned long zone, int nid, bool zero)
+ unsigned long zone, int nid)
{
- if (zero)
- mm_zero_struct_page(page);
+ mm_zero_struct_page(page);
set_page_links(page, zone, nid, pfn);
init_page_count(page);
page_mapcount_reset(page);
#endif
}
-static void __meminit __init_single_pfn(unsigned long pfn, unsigned long zone,
- int nid, bool zero)
-{
- return __init_single_page(pfn_to_page(pfn), pfn, zone, nid, zero);
-}
-
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
static void __meminit init_reserved_page(unsigned long pfn)
{
if (pfn >= zone->zone_start_pfn && pfn < zone_end_pfn(zone))
break;
}
- __init_single_pfn(pfn, zid, nid, true);
+ __init_single_page(pfn_to_page(pfn), pfn, zid, nid);
}
#else
static inline void init_reserved_page(unsigned long pfn)
} else if (!(pfn & nr_pgmask)) {
deferred_free_range(pfn - nr_free, nr_free);
nr_free = 1;
- cond_resched();
+ touch_nmi_watchdog();
} else {
nr_free++;
}
continue;
} else if (!page || !(pfn & nr_pgmask)) {
page = pfn_to_page(pfn);
- cond_resched();
+ touch_nmi_watchdog();
} else {
page++;
}
- __init_single_page(page, pfn, zid, nid, true);
+ __init_single_page(page, pfn, zid, nid);
nr_pages++;
}
return (nr_pages);
int nid = pgdat->node_id;
unsigned long start = jiffies;
unsigned long nr_pages = 0;
- unsigned long spfn, epfn;
+ unsigned long spfn, epfn, first_init_pfn, flags;
phys_addr_t spa, epa;
int zid;
struct zone *zone;
- unsigned long first_init_pfn = pgdat->first_deferred_pfn;
const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
u64 i;
+ /* Bind memory initialisation thread to a local node if possible */
+ if (!cpumask_empty(cpumask))
+ set_cpus_allowed_ptr(current, cpumask);
+
+ pgdat_resize_lock(pgdat, &flags);
+ first_init_pfn = pgdat->first_deferred_pfn;
if (first_init_pfn == ULONG_MAX) {
+ pgdat_resize_unlock(pgdat, &flags);
pgdat_init_report_one_done();
return 0;
}
- /* Bind memory initialisation thread to a local node if possible */
- if (!cpumask_empty(cpumask))
- set_cpus_allowed_ptr(current, cpumask);
-
/* Sanity check boundaries */
BUG_ON(pgdat->first_deferred_pfn < pgdat->node_start_pfn);
BUG_ON(pgdat->first_deferred_pfn > pgdat_end_pfn(pgdat));
epfn = min_t(unsigned long, zone_end_pfn(zone), PFN_DOWN(epa));
deferred_free_pages(nid, zid, spfn, epfn);
}
+ pgdat_resize_unlock(pgdat, &flags);
/* Sanity check that the next zone really is unpopulated */
WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone));
pgdat_init_report_one_done();
return 0;
}
+
+/*
+ * During boot we initialize deferred pages on-demand, as needed, but once
+ * page_alloc_init_late() has finished, the deferred pages are all initialized,
+ * and we can permanently disable that path.
+ */
+static DEFINE_STATIC_KEY_TRUE(deferred_pages);
+
+/*
+ * If this zone has deferred pages, try to grow it by initializing enough
+ * deferred pages to satisfy the allocation specified by order, rounded up to
+ * the nearest PAGES_PER_SECTION boundary. So we're adding memory in increments
+ * of SECTION_SIZE bytes by initializing struct pages in increments of
+ * PAGES_PER_SECTION * sizeof(struct page) bytes.
+ *
+ * Return true when zone was grown, otherwise return false. We return true even
+ * when we grow less than requested, to let the caller decide if there are
+ * enough pages to satisfy the allocation.
+ *
+ * Note: We use noinline because this function is needed only during boot, and
+ * it is called from a __ref function _deferred_grow_zone. This way we are
+ * making sure that it is not inlined into permanent text section.
+ */
+static noinline bool __init
+deferred_grow_zone(struct zone *zone, unsigned int order)
+{
+ int zid = zone_idx(zone);
+ int nid = zone_to_nid(zone);
+ pg_data_t *pgdat = NODE_DATA(nid);
+ unsigned long nr_pages_needed = ALIGN(1 << order, PAGES_PER_SECTION);
+ unsigned long nr_pages = 0;
+ unsigned long first_init_pfn, spfn, epfn, t, flags;
+ unsigned long first_deferred_pfn = pgdat->first_deferred_pfn;
+ phys_addr_t spa, epa;
+ u64 i;
+
+ /* Only the last zone may have deferred pages */
+ if (zone_end_pfn(zone) != pgdat_end_pfn(pgdat))
+ return false;
+
+ pgdat_resize_lock(pgdat, &flags);
+
+ /*
+ * If deferred pages have been initialized while we were waiting for
+ * the lock, return true, as the zone was grown. The caller will retry
+ * this zone. We won't return to this function since the caller also
+ * has this static branch.
+ */
+ if (!static_branch_unlikely(&deferred_pages)) {
+ pgdat_resize_unlock(pgdat, &flags);
+ return true;
+ }
+
+ /*
+ * If someone grew this zone while we were waiting for spinlock, return
+ * true, as there might be enough pages already.
+ */
+ if (first_deferred_pfn != pgdat->first_deferred_pfn) {
+ pgdat_resize_unlock(pgdat, &flags);
+ return true;
+ }
+
+ first_init_pfn = max(zone->zone_start_pfn, first_deferred_pfn);
+
+ if (first_init_pfn >= pgdat_end_pfn(pgdat)) {
+ pgdat_resize_unlock(pgdat, &flags);
+ return false;
+ }
+
+ for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) {
+ spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa));
+ epfn = min_t(unsigned long, zone_end_pfn(zone), PFN_DOWN(epa));
+
+ while (spfn < epfn && nr_pages < nr_pages_needed) {
+ t = ALIGN(spfn + PAGES_PER_SECTION, PAGES_PER_SECTION);
+ first_deferred_pfn = min(t, epfn);
+ nr_pages += deferred_init_pages(nid, zid, spfn,
+ first_deferred_pfn);
+ spfn = first_deferred_pfn;
+ }
+
+ if (nr_pages >= nr_pages_needed)
+ break;
+ }
+
+ for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) {
+ spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa));
+ epfn = min_t(unsigned long, first_deferred_pfn, PFN_DOWN(epa));
+ deferred_free_pages(nid, zid, spfn, epfn);
+
+ if (first_deferred_pfn == epfn)
+ break;
+ }
+ pgdat->first_deferred_pfn = first_deferred_pfn;
+ pgdat_resize_unlock(pgdat, &flags);
+
+ return nr_pages > 0;
+}
+
+/*
+ * deferred_grow_zone() is __init, but it is called from
+ * get_page_from_freelist() during early boot until deferred_pages permanently
+ * disables this call. This is why we have refdata wrapper to avoid warning,
+ * and to ensure that the function body gets unloaded.
+ */
+static bool __ref
+_deferred_grow_zone(struct zone *zone, unsigned int order)
+{
+ return deferred_grow_zone(zone, order);
+}
+
#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
void __init page_alloc_init_late(void)
/* Block until all are initialised */
wait_for_completion(&pgdat_init_all_done_comp);
+ /*
+ * We initialized the rest of the deferred pages. Permanently disable
+ * on-demand struct page initialization.
+ */
+ static_branch_disable(&deferred_pages);
+
/* Reinit limits that are based on free pages after the kernel is up */
files_maxfiles_init();
#endif
local_irq_save(flags);
batch = READ_ONCE(pcp->batch);
to_drain = min(pcp->count, batch);
- if (to_drain > 0) {
+ if (to_drain > 0)
free_pcppages_bulk(zone, to_drain, pcp);
- pcp->count -= to_drain;
- }
local_irq_restore(flags);
}
#endif
pset = per_cpu_ptr(zone->pageset, cpu);
pcp = &pset->pcp;
- if (pcp->count) {
+ if (pcp->count)
free_pcppages_bulk(zone, pcp->count, pcp);
- pcp->count = 0;
- }
local_irq_restore(flags);
}
if (pcp->count >= pcp->high) {
unsigned long batch = READ_ONCE(pcp->batch);
free_pcppages_bulk(zone, batch, pcp);
- pcp->count -= batch;
}
}
ac_classzone_idx(ac), alloc_flags)) {
int ret;
+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+ /*
+ * Watermark failed for this zone, but see if we can
+ * grow this zone if it contains deferred pages.
+ */
+ if (static_branch_unlikely(&deferred_pages)) {
+ if (_deferred_grow_zone(zone, order))
+ goto try_this_zone;
+ }
+#endif
/* Checked here to keep the fast path fast */
BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK);
if (alloc_flags & ALLOC_NO_WATERMARKS)
reserve_highatomic_pageblock(page, zone, order);
return page;
+ } else {
+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+ /* Try again if zone has deferred pages */
+ if (static_branch_unlikely(&deferred_pages)) {
+ if (_deferred_grow_zone(zone, order))
+ goto try_this_zone;
+ }
+#endif
}
}
return page;
}
-static void wake_all_kswapds(unsigned int order, const struct alloc_context *ac)
+static void wake_all_kswapds(unsigned int order, gfp_t gfp_mask,
+ const struct alloc_context *ac)
{
struct zoneref *z;
struct zone *zone;
pg_data_t *last_pgdat = NULL;
+ enum zone_type high_zoneidx = ac->high_zoneidx;
- for_each_zone_zonelist_nodemask(zone, z, ac->zonelist,
- ac->high_zoneidx, ac->nodemask) {
+ for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, high_zoneidx,
+ ac->nodemask) {
if (last_pgdat != zone->zone_pgdat)
- wakeup_kswapd(zone, order, ac->high_zoneidx);
+ wakeup_kswapd(zone, gfp_mask, order, high_zoneidx);
last_pgdat = zone->zone_pgdat;
}
}
goto nopage;
if (gfp_mask & __GFP_KSWAPD_RECLAIM)
- wake_all_kswapds(order, ac);
+ wake_all_kswapds(order, gfp_mask, ac);
/*
* The adjusted alloc_flags might result in immediate success, so try
retry:
/* Ensure kswapd doesn't accidentally go to sleep as long as we loop */
if (gfp_mask & __GFP_KSWAPD_RECLAIM)
- wake_all_kswapds(order, ac);
+ wake_all_kswapds(order, gfp_mask, ac);
reserve_flags = __gfp_pfmemalloc_flags(gfp_mask);
if (reserve_flags)
pg_data_t *pgdat = NODE_DATA(nid);
unsigned long pfn;
unsigned long nr_initialised = 0;
+ struct page *page;
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
struct memblock_region *r = NULL, *tmp;
#endif
#endif
not_early:
+ page = pfn_to_page(pfn);
+ __init_single_page(page, pfn, zone, nid);
+ if (context == MEMMAP_HOTPLUG)
+ SetPageReserved(page);
+
/*
* Mark the block movable so that blocks are reserved for
* movable at startup. This will force kernel allocations
* because this is done early in sparse_add_one_section
*/
if (!(pfn & (pageblock_nr_pages - 1))) {
- struct page *page = pfn_to_page(pfn);
-
- __init_single_page(page, pfn, zone, nid,
- context != MEMMAP_HOTPLUG);
set_pageblock_migratetype(page, MIGRATE_MOVABLE);
cond_resched();
- } else {
- __init_single_pfn(pfn, zone, nid,
- context != MEMMAP_HOTPLUG);
}
}
}
end = pgdat_end_pfn(pgdat);
end = ALIGN(end, MAX_ORDER_NR_PAGES);
size = (end - start) * sizeof(struct page);
- map = alloc_remap(pgdat->node_id, size);
- if (!map)
- map = memblock_virt_alloc_node_nopanic(size,
- pgdat->node_id);
+ map = memblock_virt_alloc_node_nopanic(size, pgdat->node_id);
pgdat->node_mem_map = map + offset;
}
pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n",
alloc_node_mem_map(pgdat);
- reset_deferred_meminit(pgdat);
+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+ /*
+ * We start only with one section of pages, more pages are added as
+ * needed until the rest of deferred pages are initialized.
+ */
+ pgdat->static_init_pgcnt = min_t(unsigned long, PAGES_PER_SECTION,
+ pgdat->node_spanned_pages);
+ pgdat->first_deferred_pfn = ULONG_MAX;
+#endif
free_area_init_core(pgdat);
}
}
/*
- * If movablecore=nn[KMG] was specified, calculate what size of
+ * If kernelcore=nn% or movablecore=nn% was specified, calculate the
+ * amount of necessary memory.
+ */
+ if (required_kernelcore_percent)
+ required_kernelcore = (totalpages * 100 * required_kernelcore_percent) /
+ 10000UL;
+ if (required_movablecore_percent)
+ required_movablecore = (totalpages * 100 * required_movablecore_percent) /
+ 10000UL;
+
+ /*
+ * If movablecore= was specified, calculate what size of
* kernelcore that corresponds so that memory usable for
* any allocation type is evenly spread. If both kernelcore
* and movablecore are specified, then the value of kernelcore
zero_resv_unavail();
}
-static int __init cmdline_parse_core(char *p, unsigned long *core)
+static int __init cmdline_parse_core(char *p, unsigned long *core,
+ unsigned long *percent)
{
unsigned long long coremem;
+ char *endptr;
+
if (!p)
return -EINVAL;
- coremem = memparse(p, &p);
- *core = coremem >> PAGE_SHIFT;
+ /* Value may be a percentage of total memory, otherwise bytes */
+ coremem = simple_strtoull(p, &endptr, 0);
+ if (*endptr == '%') {
+ /* Paranoid check for percent values greater than 100 */
+ WARN_ON(coremem > 100);
- /* Paranoid check that UL is enough for the coremem value */
- WARN_ON((coremem >> PAGE_SHIFT) > ULONG_MAX);
+ *percent = coremem;
+ } else {
+ coremem = memparse(p, &p);
+ /* Paranoid check that UL is enough for the coremem value */
+ WARN_ON((coremem >> PAGE_SHIFT) > ULONG_MAX);
+ *core = coremem >> PAGE_SHIFT;
+ *percent = 0UL;
+ }
return 0;
}
return 0;
}
- return cmdline_parse_core(p, &required_kernelcore);
+ return cmdline_parse_core(p, &required_kernelcore,
+ &required_kernelcore_percent);
}
/*
*/
static int __init cmdline_parse_movablecore(char *p)
{
- return cmdline_parse_core(p, &required_movablecore);
+ return cmdline_parse_core(p, &required_movablecore,
+ &required_movablecore_percent);
}
early_param("kernelcore", cmdline_parse_kernelcore);
cc->nr_migratepages -= nr_reclaimed;
ret = migrate_pages(&cc->migratepages, alloc_migrate_target,
- NULL, 0, cc->mode, MR_CMA);
+ NULL, 0, cc->mode, MR_CONTIG_RANGE);
}
if (ret < 0) {
putback_movable_pages(&cc->migratepages);
* @gfp_mask: GFP mask to use during compaction
*
* The PFN range does not have to be pageblock or MAX_ORDER_NR_PAGES
- * aligned, however it's the caller's responsibility to guarantee that
- * we are the only thread that changes migrate type of pageblocks the
- * pages fall in.
+ * aligned. The PFN range must belong to a single zone.
*
- * The PFN range must belong to a single zone.
+ * The first thing this routine does is attempt to MIGRATE_ISOLATE all
+ * pageblocks in the range. Once isolated, the pageblocks should not
+ * be modified by others.
*
* Returns zero on success or negative error code. On success all
* pages which PFN is in [start, end) are allocated for the caller and
projects / linux-2.6-microblaze.git / blobdiff