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.c533
1 files changed, 417 insertions, 116 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 838ca8bb64f7..59de90d5d3a3 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -223,6 +223,19 @@ static char * const zone_names[MAX_NR_ZONES] = {
#endif
};
+char * const migratetype_names[MIGRATE_TYPES] = {
+ "Unmovable",
+ "Movable",
+ "Reclaimable",
+ "HighAtomic",
+#ifdef CONFIG_CMA
+ "CMA",
+#endif
+#ifdef CONFIG_MEMORY_ISOLATION
+ "Isolate",
+#endif
+};
+
compound_page_dtor * const compound_page_dtors[] = {
NULL,
free_compound_page,
@@ -236,6 +249,7 @@ compound_page_dtor * const compound_page_dtors[] = {
int min_free_kbytes = 1024;
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;
@@ -247,6 +261,7 @@ 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;
/* movable_zone is the "real" zone pages in ZONE_MOVABLE are taken from */
int movable_zone;
@@ -293,13 +308,20 @@ static inline bool update_defer_init(pg_data_t *pgdat,
unsigned long pfn, unsigned long zone_end,
unsigned long *nr_initialised)
{
+ unsigned long max_initialise;
+
/* Always populate low zones for address-contrained allocations */
if (zone_end < pgdat_end_pfn(pgdat))
return true;
+ /*
+ * 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_initialise = max(2UL << (30 - PAGE_SHIFT),
+ (pgdat->node_spanned_pages >> 8));
- /* Initialise at least 2G of the highest zone */
(*nr_initialised)++;
- if (*nr_initialised > (2UL << (30 - PAGE_SHIFT)) &&
+ if ((*nr_initialised > max_initialise) &&
(pfn & (PAGES_PER_SECTION - 1)) == 0) {
pgdat->first_deferred_pfn = pfn;
return false;
@@ -416,7 +438,7 @@ static void bad_page(struct page *page, const char *reason,
goto out;
}
if (nr_unshown) {
- printk(KERN_ALERT
+ pr_alert(
"BUG: Bad page state: %lu messages suppressed\n",
nr_unshown);
nr_unshown = 0;
@@ -426,9 +448,14 @@ static void bad_page(struct page *page, const char *reason,
if (nr_shown++ == 0)
resume = jiffies + 60 * HZ;
- printk(KERN_ALERT "BUG: Bad page state in process %s pfn:%05lx\n",
+ pr_alert("BUG: Bad page state in process %s pfn:%05lx\n",
current->comm, page_to_pfn(page));
- dump_page_badflags(page, reason, bad_flags);
+ __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();
dump_stack();
@@ -477,7 +504,9 @@ void prep_compound_page(struct page *page, unsigned int order)
#ifdef CONFIG_DEBUG_PAGEALLOC
unsigned int _debug_guardpage_minorder;
-bool _debug_pagealloc_enabled __read_mostly;
+bool _debug_pagealloc_enabled __read_mostly
+ = IS_ENABLED(CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT);
+EXPORT_SYMBOL(_debug_pagealloc_enabled);
bool _debug_guardpage_enabled __read_mostly;
static int __init early_debug_pagealloc(char *buf)
@@ -488,6 +517,9 @@ static int __init early_debug_pagealloc(char *buf)
if (strcmp(buf, "on") == 0)
_debug_pagealloc_enabled = true;
+ if (strcmp(buf, "off") == 0)
+ _debug_pagealloc_enabled = false;
+
return 0;
}
early_param("debug_pagealloc", early_debug_pagealloc);
@@ -519,11 +551,11 @@ static int __init debug_guardpage_minorder_setup(char *buf)
unsigned long res;
if (kstrtoul(buf, 10, &res) < 0 || res > MAX_ORDER / 2) {
- printk(KERN_ERR "Bad debug_guardpage_minorder value\n");
+ pr_err("Bad debug_guardpage_minorder value\n");
return 0;
}
_debug_guardpage_minorder = res;
- printk(KERN_INFO "Setting debug_guardpage_minorder to %lu\n", res);
+ pr_info("Setting debug_guardpage_minorder to %lu\n", res);
return 0;
}
__setup("debug_guardpage_minorder=", debug_guardpage_minorder_setup);
@@ -660,34 +692,28 @@ static inline void __free_one_page(struct page *page,
unsigned long combined_idx;
unsigned long uninitialized_var(buddy_idx);
struct page *buddy;
- unsigned int max_order = MAX_ORDER;
+ unsigned int max_order;
+
+ max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1);
VM_BUG_ON(!zone_is_initialized(zone));
VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page);
VM_BUG_ON(migratetype == -1);
- if (is_migrate_isolate(migratetype)) {
- /*
- * We restrict max order of merging to prevent merge
- * between freepages on isolate pageblock and normal
- * pageblock. Without this, pageblock isolation
- * could cause incorrect freepage accounting.
- */
- max_order = min_t(unsigned int, MAX_ORDER, pageblock_order + 1);
- } else {
+ if (likely(!is_migrate_isolate(migratetype)))
__mod_zone_freepage_state(zone, 1 << order, migratetype);
- }
- page_idx = pfn & ((1 << max_order) - 1);
+ page_idx = pfn & ((1 << MAX_ORDER) - 1);
VM_BUG_ON_PAGE(page_idx & ((1 << order) - 1), page);
VM_BUG_ON_PAGE(bad_range(zone, page), page);
+continue_merging:
while (order < max_order - 1) {
buddy_idx = __find_buddy_index(page_idx, order);
buddy = page + (buddy_idx - page_idx);
if (!page_is_buddy(page, buddy, order))
- break;
+ goto done_merging;
/*
* Our buddy is free or it is CONFIG_DEBUG_PAGEALLOC guard page,
* merge with it and move up one order.
@@ -704,6 +730,32 @@ static inline void __free_one_page(struct page *page,
page_idx = combined_idx;
order++;
}
+ if (max_order < MAX_ORDER) {
+ /* If we are here, it means order is >= pageblock_order.
+ * We want to prevent merge between freepages on isolate
+ * pageblock and normal pageblock. Without this, pageblock
+ * isolation could cause incorrect freepage or CMA accounting.
+ *
+ * We don't want to hit this code for the more frequent
+ * low-order merging.
+ */
+ if (unlikely(has_isolate_pageblock(zone))) {
+ int buddy_mt;
+
+ buddy_idx = __find_buddy_index(page_idx, order);
+ buddy = page + (buddy_idx - page_idx);
+ buddy_mt = get_pageblock_migratetype(buddy);
+
+ if (migratetype != buddy_mt
+ && (is_migrate_isolate(migratetype) ||
+ is_migrate_isolate(buddy_mt)))
+ goto done_merging;
+ }
+ max_order++;
+ goto continue_merging;
+ }
+
+done_merging:
set_page_order(page, order);
/*
@@ -741,7 +793,7 @@ static inline int free_pages_check(struct page *page)
bad_reason = "nonzero mapcount";
if (unlikely(page->mapping != NULL))
bad_reason = "non-NULL mapping";
- if (unlikely(atomic_read(&page->_count) != 0))
+ if (unlikely(page_ref_count(page) != 0))
bad_reason = "nonzero _count";
if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_FREE)) {
bad_reason = "PAGE_FLAGS_CHECK_AT_FREE flag(s) set";
@@ -1002,6 +1054,7 @@ static bool free_pages_prepare(struct page *page, unsigned int order)
PAGE_SIZE << order);
}
arch_free_page(page, order);
+ kernel_poison_pages(page, 1 << order, 0);
kernel_map_pages(page, 1 << order, 0);
return true;
@@ -1104,6 +1157,75 @@ void __init __free_pages_bootmem(struct page *page, unsigned long pfn,
return __free_pages_boot_core(page, pfn, order);
}
+/*
+ * Check that the whole (or subset of) a pageblock given by the interval of
+ * [start_pfn, end_pfn) is valid and within the same zone, before scanning it
+ * with the migration of free compaction scanner. The scanners then need to
+ * use only pfn_valid_within() check for arches that allow holes within
+ * pageblocks.
+ *
+ * Return struct page pointer of start_pfn, or NULL if checks were not passed.
+ *
+ * It's possible on some configurations to have a setup like node0 node1 node0
+ * i.e. it's possible that all pages within a zones range of pages do not
+ * belong to a single zone. We assume that a border between node0 and node1
+ * can occur within a single pageblock, but not a node0 node1 node0
+ * interleaving within a single pageblock. It is therefore sufficient to check
+ * the first and last page of a pageblock and avoid checking each individual
+ * page in a pageblock.
+ */
+struct page *__pageblock_pfn_to_page(unsigned long start_pfn,
+ unsigned long end_pfn, struct zone *zone)
+{
+ struct page *start_page;
+ struct page *end_page;
+
+ /* end_pfn is one past the range we are checking */
+ end_pfn--;
+
+ if (!pfn_valid(start_pfn) || !pfn_valid(end_pfn))
+ return NULL;
+
+ start_page = pfn_to_page(start_pfn);
+
+ if (page_zone(start_page) != zone)
+ return NULL;
+
+ end_page = pfn_to_page(end_pfn);
+
+ /* This gives a shorter code than deriving page_zone(end_page) */
+ if (page_zone_id(start_page) != page_zone_id(end_page))
+ return NULL;
+
+ return start_page;
+}
+
+void set_zone_contiguous(struct zone *zone)
+{
+ unsigned long block_start_pfn = zone->zone_start_pfn;
+ unsigned long block_end_pfn;
+
+ block_end_pfn = ALIGN(block_start_pfn + 1, pageblock_nr_pages);
+ for (; block_start_pfn < zone_end_pfn(zone);
+ block_start_pfn = block_end_pfn,
+ block_end_pfn += pageblock_nr_pages) {
+
+ block_end_pfn = min(block_end_pfn, zone_end_pfn(zone));
+
+ if (!__pageblock_pfn_to_page(block_start_pfn,
+ block_end_pfn, zone))
+ return;
+ }
+
+ /* We confirm that there is no hole */
+ zone->contiguous = true;
+}
+
+void clear_zone_contiguous(struct zone *zone)
+{
+ zone->contiguous = false;
+}
+
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
static void __init deferred_free_range(struct page *page,
unsigned long pfn, int nr_pages)
@@ -1254,9 +1376,13 @@ free_range:
pgdat_init_report_one_done();
return 0;
}
+#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
void __init page_alloc_init_late(void)
{
+ struct zone *zone;
+
+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
int nid;
/* There will be num_node_state(N_MEMORY) threads */
@@ -1270,8 +1396,11 @@ void __init page_alloc_init_late(void)
/* Reinit limits that are based on free pages after the kernel is up */
files_maxfiles_init();
+#endif
+
+ for_each_populated_zone(zone)
+ set_zone_contiguous(zone);
}
-#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
#ifdef CONFIG_CMA
/* Free whole pageblock and set its migration type to MIGRATE_CMA. */
@@ -1360,7 +1489,7 @@ static inline int check_new_page(struct page *page)
bad_reason = "nonzero mapcount";
if (unlikely(page->mapping != NULL))
bad_reason = "non-NULL mapping";
- if (unlikely(atomic_read(&page->_count) != 0))
+ if (unlikely(page_ref_count(page) != 0))
bad_reason = "nonzero _count";
if (unlikely(page->flags & __PG_HWPOISON)) {
bad_reason = "HWPoisoned (hardware-corrupted)";
@@ -1381,15 +1510,24 @@ static inline int check_new_page(struct page *page)
return 0;
}
+static inline bool free_pages_prezeroed(bool poisoned)
+{
+ return IS_ENABLED(CONFIG_PAGE_POISONING_ZERO) &&
+ page_poisoning_enabled() && poisoned;
+}
+
static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags,
int alloc_flags)
{
int i;
+ bool poisoned = true;
for (i = 0; i < (1 << order); i++) {
struct page *p = page + i;
if (unlikely(check_new_page(p)))
return 1;
+ if (poisoned)
+ poisoned &= page_is_poisoned(p);
}
set_page_private(page, 0);
@@ -1397,9 +1535,10 @@ static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags,
arch_alloc_page(page, order);
kernel_map_pages(page, 1 << order, 1);
+ kernel_poison_pages(page, 1 << order, 1);
kasan_alloc_pages(page, order);
- if (gfp_flags & __GFP_ZERO)
+ if (!free_pages_prezeroed(poisoned) && (gfp_flags & __GFP_ZERO))
for (i = 0; i < (1 << order); i++)
clear_highpage(page + i);
@@ -2238,19 +2377,11 @@ struct page *buffered_rmqueue(struct zone *preferred_zone,
list_del(&page->lru);
pcp->count--;
} else {
- if (unlikely(gfp_flags & __GFP_NOFAIL)) {
- /*
- * __GFP_NOFAIL is not to be used in new code.
- *
- * All __GFP_NOFAIL callers should be fixed so that they
- * properly detect and handle allocation failures.
- *
- * We most definitely don't want callers attempting to
- * allocate greater than order-1 page units with
- * __GFP_NOFAIL.
- */
- WARN_ON_ONCE(order > 1);
- }
+ /*
+ * We most definitely don't want callers attempting to
+ * allocate greater than order-1 page units with __GFP_NOFAIL.
+ */
+ WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1));
spin_lock_irqsave(&zone->lock, flags);
page = NULL;
@@ -2690,9 +2821,8 @@ void warn_alloc_failed(gfp_t gfp_mask, unsigned int order, const char *fmt, ...)
va_end(args);
}
- pr_warn("%s: page allocation failure: order:%u, mode:0x%x\n",
- current->comm, order, gfp_mask);
-
+ pr_warn("%s: page allocation failure: order:%u, mode:%#x(%pGg)\n",
+ current->comm, order, gfp_mask, &gfp_mask);
dump_stack();
if (!should_suppress_show_mem())
show_mem(filter);
@@ -2748,8 +2878,12 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
* XXX: Page reclaim didn't yield anything,
* and the OOM killer can't be invoked, but
* keep looping as per tradition.
+ *
+ * But do not keep looping if oom_killer_disable()
+ * was already called, for the system is trying to
+ * enter a quiescent state during suspend.
*/
- *did_some_progress = 1;
+ *did_some_progress = !oom_killer_disabled;
goto out;
}
if (pm_suspended_storage())
@@ -3008,14 +3142,6 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
(__GFP_ATOMIC|__GFP_DIRECT_RECLAIM)))
gfp_mask &= ~__GFP_ATOMIC;
- /*
- * If this allocation cannot block and it is for a specific node, then
- * fail early. There's no need to wakeup kswapd or retry for a
- * speculative node-specific allocation.
- */
- if (IS_ENABLED(CONFIG_NUMA) && (gfp_mask & __GFP_THISNODE) && !can_direct_reclaim)
- goto nopage;
-
retry:
if (gfp_mask & __GFP_KSWAPD_RECLAIM)
wake_all_kswapds(order, ac);
@@ -3372,7 +3498,7 @@ refill:
/* Even if we own the page, we do not use atomic_set().
* This would break get_page_unless_zero() users.
*/
- atomic_add(size - 1, &page->_count);
+ page_ref_add(page, size - 1);
/* reset page count bias and offset to start of new frag */
nc->pfmemalloc = page_is_pfmemalloc(page);
@@ -3384,7 +3510,7 @@ refill:
if (unlikely(offset < 0)) {
page = virt_to_page(nc->va);
- if (!atomic_sub_and_test(nc->pagecnt_bias, &page->_count))
+ if (!page_ref_sub_and_test(page, nc->pagecnt_bias))
goto refill;
#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
@@ -3392,7 +3518,7 @@ refill:
size = nc->size;
#endif
/* OK, page count is 0, we can safely set it */
- atomic_set(&page->_count, size);
+ set_page_count(page, size);
/* reset page count bias and offset to start of new frag */
nc->pagecnt_bias = size;
@@ -3603,6 +3729,49 @@ static inline void show_node(struct zone *zone)
printk("Node %d ", zone_to_nid(zone));
}
+long si_mem_available(void)
+{
+ long available;
+ unsigned long pagecache;
+ unsigned long wmark_low = 0;
+ unsigned long pages[NR_LRU_LISTS];
+ struct zone *zone;
+ int lru;
+
+ for (lru = LRU_BASE; lru < NR_LRU_LISTS; lru++)
+ pages[lru] = global_page_state(NR_LRU_BASE + lru);
+
+ for_each_zone(zone)
+ wmark_low += zone->watermark[WMARK_LOW];
+
+ /*
+ * Estimate the amount of memory available for userspace allocations,
+ * without causing swapping.
+ */
+ available = global_page_state(NR_FREE_PAGES) - totalreserve_pages;
+
+ /*
+ * Not all the page cache can be freed, otherwise the system will
+ * start swapping. Assume at least half of the page cache, or the
+ * low watermark worth of cache, needs to stay.
+ */
+ pagecache = pages[LRU_ACTIVE_FILE] + pages[LRU_INACTIVE_FILE];
+ pagecache -= min(pagecache / 2, wmark_low);
+ available += pagecache;
+
+ /*
+ * Part of the reclaimable slab consists of items that are in use,
+ * and cannot be freed. Cap this estimate at the low watermark.
+ */
+ available += global_page_state(NR_SLAB_RECLAIMABLE) -
+ min(global_page_state(NR_SLAB_RECLAIMABLE) / 2, wmark_low);
+
+ if (available < 0)
+ available = 0;
+ return available;
+}
+EXPORT_SYMBOL_GPL(si_mem_available);
+
void si_meminfo(struct sysinfo *val)
{
val->totalram = totalram_pages;
@@ -3935,9 +4104,7 @@ static int __parse_numa_zonelist_order(char *s)
} else if (*s == 'z' || *s == 'Z') {
user_zonelist_order = ZONELIST_ORDER_ZONE;
} else {
- printk(KERN_WARNING
- "Ignoring invalid numa_zonelist_order value: "
- "%s\n", s);
+ pr_warn("Ignoring invalid numa_zonelist_order value: %s\n", s);
return -EINVAL;
}
return 0;
@@ -4401,12 +4568,11 @@ 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
@@ -4491,6 +4657,9 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
pg_data_t *pgdat = NODE_DATA(nid);
unsigned long pfn;
unsigned long nr_initialised = 0;
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+ struct memblock_region *r = NULL, *tmp;
+#endif
if (highest_memmap_pfn < end_pfn - 1)
highest_memmap_pfn = end_pfn - 1;
@@ -4504,20 +4673,51 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone,
for (pfn = start_pfn; pfn < end_pfn; pfn++) {
/*
- * There can be holes in boot-time mem_map[]s
- * handed to this function. They do not
- * exist on hotplugged memory.
+ * There can be holes in boot-time mem_map[]s handed to this
+ * function. They do not exist on hotplugged memory.
+ */
+ if (context != MEMMAP_EARLY)
+ goto not_early;
+
+ if (!early_pfn_valid(pfn))
+ continue;
+ if (!early_pfn_in_nid(pfn, nid))
+ continue;
+ if (!update_defer_init(pgdat, pfn, end_pfn, &nr_initialised))
+ break;
+
+#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
+ /*
+ * If not mirrored_kernelcore and ZONE_MOVABLE exists, range
+ * from zone_movable_pfn[nid] to end of each node should be
+ * ZONE_MOVABLE not ZONE_NORMAL. skip it.
*/
- if (context == MEMMAP_EARLY) {
- if (!early_pfn_valid(pfn))
+ if (!mirrored_kernelcore && zone_movable_pfn[nid])
+ if (zone == ZONE_NORMAL && pfn >= zone_movable_pfn[nid])
continue;
- if (!early_pfn_in_nid(pfn, nid))
+
+ /*
+ * Check given memblock attribute by firmware which can affect
+ * kernel memory layout. If zone==ZONE_MOVABLE but memory is
+ * mirrored, it's an overlapped memmap init. skip it.
+ */
+ if (mirrored_kernelcore && zone == ZONE_MOVABLE) {
+ if (!r || pfn >= memblock_region_memory_end_pfn(r)) {
+ for_each_memblock(memory, tmp)
+ if (pfn < memblock_region_memory_end_pfn(tmp))
+ break;
+ r = tmp;
+ }
+ if (pfn >= memblock_region_memory_base_pfn(r) &&
+ memblock_is_mirror(r)) {
+ /* already initialized as NORMAL */
+ pfn = memblock_region_memory_end_pfn(r);
continue;
- if (!update_defer_init(pgdat, pfn, end_pfn,
- &nr_initialised))
- break;
+ }
}
+#endif
+not_early:
/*
* Mark the block movable so that blocks are reserved for
* movable at startup. This will force kernel allocations
@@ -4934,11 +5134,6 @@ static void __meminit adjust_zone_range_for_zone_movable(int nid,
*zone_end_pfn = min(node_end_pfn,
arch_zone_highest_possible_pfn[movable_zone]);
- /* Adjust for ZONE_MOVABLE starting within this range */
- } else if (*zone_start_pfn < zone_movable_pfn[nid] &&
- *zone_end_pfn > zone_movable_pfn[nid]) {
- *zone_end_pfn = zone_movable_pfn[nid];
-
/* Check if this whole range is within ZONE_MOVABLE */
} else if (*zone_start_pfn >= zone_movable_pfn[nid])
*zone_start_pfn = *zone_end_pfn;
@@ -4953,31 +5148,31 @@ static unsigned long __meminit 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 *ignored)
{
- unsigned long zone_start_pfn, zone_end_pfn;
-
/* When hotadd a new node from cpu_up(), the node should be empty */
if (!node_start_pfn && !node_end_pfn)
return 0;
/* Get the start and end of the zone */
- zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type];
- zone_end_pfn = arch_zone_highest_possible_pfn[zone_type];
+ *zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type];
+ *zone_end_pfn = arch_zone_highest_possible_pfn[zone_type];
adjust_zone_range_for_zone_movable(nid, zone_type,
node_start_pfn, node_end_pfn,
- &zone_start_pfn, &zone_end_pfn);
+ zone_start_pfn, zone_end_pfn);
/* Check that this node has pages within the zone's required range */
- if (zone_end_pfn < node_start_pfn || zone_start_pfn > node_end_pfn)
+ if (*zone_end_pfn < node_start_pfn || *zone_start_pfn > node_end_pfn)
return 0;
/* Move the zone boundaries inside the node if necessary */
- zone_end_pfn = min(zone_end_pfn, node_end_pfn);
- zone_start_pfn = max(zone_start_pfn, node_start_pfn);
+ *zone_end_pfn = min(*zone_end_pfn, node_end_pfn);
+ *zone_start_pfn = max(*zone_start_pfn, node_start_pfn);
/* Return the spanned pages */
- return zone_end_pfn - zone_start_pfn;
+ return *zone_end_pfn - *zone_start_pfn;
}
/*
@@ -5023,6 +5218,7 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid,
unsigned long zone_low = arch_zone_lowest_possible_pfn[zone_type];
unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type];
unsigned long zone_start_pfn, zone_end_pfn;
+ unsigned long nr_absent;
/* When hotadd a new node from cpu_up(), the node should be empty */
if (!node_start_pfn && !node_end_pfn)
@@ -5034,7 +5230,39 @@ static unsigned long __meminit zone_absent_pages_in_node(int nid,
adjust_zone_range_for_zone_movable(nid, zone_type,
node_start_pfn, node_end_pfn,
&zone_start_pfn, &zone_end_pfn);
- return __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn);
+ nr_absent = __absent_pages_in_range(nid, zone_start_pfn, zone_end_pfn);
+
+ /*
+ * ZONE_MOVABLE handling.
+ * Treat pages to be ZONE_MOVABLE in ZONE_NORMAL as absent pages
+ * and vice versa.
+ */
+ if (zone_movable_pfn[nid]) {
+ if (mirrored_kernelcore) {
+ unsigned long start_pfn, end_pfn;
+ struct memblock_region *r;
+
+ for_each_memblock(memory, 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),
+ zone_start_pfn, zone_end_pfn);
+
+ if (zone_type == ZONE_MOVABLE &&
+ memblock_is_mirror(r))
+ nr_absent += end_pfn - start_pfn;
+
+ if (zone_type == ZONE_NORMAL &&
+ !memblock_is_mirror(r))
+ nr_absent += end_pfn - start_pfn;
+ }
+ } else {
+ if (zone_type == ZONE_NORMAL)
+ nr_absent += node_end_pfn - zone_movable_pfn[nid];
+ }
+ }
+
+ return nr_absent;
}
#else /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
@@ -5042,8 +5270,18 @@ static inline unsigned long __meminit 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];
}
@@ -5072,15 +5310,22 @@ static void __meminit calculate_node_totalpages(struct pglist_data *pgdat,
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 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);
+ if (size)
+ zone->zone_start_pfn = zone_start_pfn;
+ else
+ zone->zone_start_pfn = 0;
zone->spanned_pages = size;
zone->present_pages = real_size;
@@ -5201,7 +5446,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
{
enum zone_type j;
int nid = pgdat->node_id;
- unsigned long zone_start_pfn = pgdat->node_start_pfn;
int ret;
pgdat_resize_init(pgdat);
@@ -5217,11 +5461,15 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
#endif
init_waitqueue_head(&pgdat->kswapd_wait);
init_waitqueue_head(&pgdat->pfmemalloc_wait);
+#ifdef CONFIG_COMPACTION
+ init_waitqueue_head(&pgdat->kcompactd_wait);
+#endif
pgdat_page_ext_init(pgdat);
for (j = 0; j < MAX_NR_ZONES; j++) {
struct zone *zone = pgdat->node_zones + j;
unsigned long size, realsize, freesize, memmap_pages;
+ unsigned long zone_start_pfn = zone->zone_start_pfn;
size = zone->spanned_pages;
realsize = freesize = zone->present_pages;
@@ -5240,8 +5488,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
" %s zone: %lu pages used for memmap\n",
zone_names[j], memmap_pages);
} else
- printk(KERN_WARNING
- " %s zone: %lu pages exceeds freesize %lu\n",
+ pr_warn(" %s zone: %lu pages exceeds freesize %lu\n",
zone_names[j], memmap_pages, freesize);
}
@@ -5290,7 +5537,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
ret = init_currently_empty_zone(zone, zone_start_pfn, size);
BUG_ON(ret);
memmap_init(size, nid, j, zone_start_pfn);
- zone_start_pfn += size;
}
}
@@ -5358,6 +5604,8 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size,
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);
@@ -5448,8 +5696,7 @@ static unsigned long __init find_min_pfn_for_node(int nid)
min_pfn = min(min_pfn, start_pfn);
if (min_pfn == ULONG_MAX) {
- printk(KERN_WARNING
- "Could not find start_pfn for node %d\n", nid);
+ pr_warn("Could not find start_pfn for node %d\n", nid);
return 0;
}
@@ -5529,6 +5776,36 @@ static void __init find_zone_movable_pfns_for_nodes(void)
}
/*
+ * If kernelcore=mirror is specified, ignore movablecore option
+ */
+ if (mirrored_kernelcore) {
+ bool mem_below_4gb_not_mirrored = false;
+
+ for_each_memblock(memory, r) {
+ if (memblock_is_mirror(r))
+ continue;
+
+ nid = r->nid;
+
+ usable_startpfn = memblock_region_memory_base_pfn(r);
+
+ if (usable_startpfn < 0x100000) {
+ mem_below_4gb_not_mirrored = true;
+ continue;
+ }
+
+ zone_movable_pfn[nid] = zone_movable_pfn[nid] ?
+ min(usable_startpfn, zone_movable_pfn[nid]) :
+ usable_startpfn;
+ }
+
+ if (mem_below_4gb_not_mirrored)
+ pr_warn("This configuration results in unmirrored kernel memory.");
+
+ goto out2;
+ }
+
+ /*
* If movablecore=nn[KMG] was specified, calculate what size of
* kernelcore that corresponds so that memory usable for
* any allocation type is evenly spread. If both kernelcore
@@ -5788,6 +6065,12 @@ static int __init cmdline_parse_core(char *p, unsigned long *core)
*/
static int __init cmdline_parse_kernelcore(char *p)
{
+ /* parse kernelcore=mirror */
+ if (parse_option_str(p, "mirror")) {
+ mirrored_kernelcore = true;
+ return 0;
+ }
+
return cmdline_parse_core(p, &required_kernelcore);
}
@@ -5885,22 +6168,21 @@ 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 : "");
}
/**
@@ -6075,8 +6357,17 @@ static void __setup_per_zone_wmarks(void)
zone->watermark[WMARK_MIN] = tmp;
}
- zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + (tmp >> 2);
- zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
+ /*
+ * Set the kswapd watermarks distance according to the
+ * scale factor in proportion to available memory, but
+ * ensure a minimum size on small systems.
+ */
+ tmp = max_t(u64, tmp >> 2,
+ mult_frac(zone->managed_pages,
+ watermark_scale_factor, 10000));
+
+ zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + tmp;
+ zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + tmp * 2;
__mod_zone_page_state(zone, NR_ALLOC_BATCH,
high_wmark_pages(zone) - low_wmark_pages(zone) -
@@ -6217,6 +6508,21 @@ int min_free_kbytes_sysctl_handler(struct ctl_table *table, int write,
return 0;
}
+int watermark_scale_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;
+
+ if (write)
+ setup_per_zone_wmarks();
+
+ return 0;
+}
+
#ifdef CONFIG_NUMA
int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *length, loff_t *ppos)
@@ -6408,11 +6714,8 @@ void *__init alloc_large_system_hash(const char *tablename,
if (!table)
panic("Failed to allocate %s hash table\n", tablename);
- printk(KERN_INFO "%s hash table entries: %ld (order: %d, %lu bytes)\n",
- tablename,
- (1UL << log2qty),
- ilog2(size) - PAGE_SHIFT,
- size);
+ pr_info("%s hash table entries: %ld (order: %d, %lu bytes)\n",
+ tablename, 1UL << log2qty, ilog2(size) - PAGE_SHIFT, size);
if (_hash_shift)
*_hash_shift = log2qty;
@@ -6563,7 +6866,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
* This check already skips compound tails of THP
* because their page->_count is zero at all time.
*/
- if (!atomic_read(&page->_count)) {
+ if (!page_ref_count(page)) {
if (PageBuddy(page))
iter += (1 << page_order(page)) - 1;
continue;
@@ -6913,8 +7216,8 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
BUG_ON(!PageBuddy(page));
order = page_order(page);
#ifdef CONFIG_DEBUG_VM
- printk(KERN_INFO "remove from free list %lx %d %lx\n",
- pfn, 1 << order, end_pfn);
+ pr_info("remove from free list %lx %d %lx\n",
+ pfn, 1 << order, end_pfn);
#endif
list_del(&page->lru);
rmv_page_order(page);
@@ -6927,7 +7230,6 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
}
#endif
-#ifdef CONFIG_MEMORY_FAILURE
bool is_free_buddy_page(struct page *page)
{
struct zone *zone = page_zone(page);
@@ -6946,4 +7248,3 @@ bool is_free_buddy_page(struct page *page)
return order < MAX_ORDER;
}
-#endif
generated by cgit v1.2.3 (git 2.39.0) at 2025-11-04 07:36:12 +0300