aboutsummaryrefslogtreecommitdiff
path: root/mm/page_alloc.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/page_alloc.c')
-rw-r--r--mm/page_alloc.c335
1 files changed, 227 insertions, 108 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b37435c274cf..d4205e5e41d1 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -19,6 +19,7 @@
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/swap.h>
+#include <linux/swapops.h>
#include <linux/interrupt.h>
#include <linux/pagemap.h>
#include <linux/jiffies.h>
@@ -63,6 +64,7 @@
#include <linux/sched/rt.h>
#include <linux/sched/mm.h>
#include <linux/page_owner.h>
+#include <linux/page_table_check.h>
#include <linux/kthread.h>
#include <linux/memcontrol.h>
#include <linux/ftrace.h>
@@ -677,10 +679,8 @@ static inline int pindex_to_order(unsigned int pindex)
int order = pindex / MIGRATE_PCPTYPES;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- if (order > PAGE_ALLOC_COSTLY_ORDER) {
+ if (order > PAGE_ALLOC_COSTLY_ORDER)
order = pageblock_order;
- VM_BUG_ON(order != pageblock_order);
- }
#else
VM_BUG_ON(order > PAGE_ALLOC_COSTLY_ORDER);
#endif
@@ -724,27 +724,37 @@ static inline void free_the_page(struct page *page, unsigned int order)
void free_compound_page(struct page *page)
{
- mem_cgroup_uncharge(page);
+ mem_cgroup_uncharge(page_folio(page));
free_the_page(page, compound_order(page));
}
+static void prep_compound_head(struct page *page, unsigned int order)
+{
+ set_compound_page_dtor(page, COMPOUND_PAGE_DTOR);
+ set_compound_order(page, order);
+ atomic_set(compound_mapcount_ptr(page), -1);
+ if (hpage_pincount_available(page))
+ atomic_set(compound_pincount_ptr(page), 0);
+}
+
+static void prep_compound_tail(struct page *head, int tail_idx)
+{
+ struct page *p = head + tail_idx;
+
+ p->mapping = TAIL_MAPPING;
+ set_compound_head(p, head);
+}
+
void prep_compound_page(struct page *page, unsigned int order)
{
int i;
int nr_pages = 1 << order;
__SetPageHead(page);
- for (i = 1; i < nr_pages; i++) {
- struct page *p = page + i;
- p->mapping = TAIL_MAPPING;
- set_compound_head(p, page);
- }
+ for (i = 1; i < nr_pages; i++)
+ prep_compound_tail(page, i);
- set_compound_page_dtor(page, COMPOUND_PAGE_DTOR);
- set_compound_order(page, order);
- atomic_set(compound_mapcount_ptr(page), -1);
- if (hpage_pincount_available(page))
- atomic_set(compound_pincount_ptr(page), 0);
+ prep_compound_head(page, order);
}
#ifdef CONFIG_DEBUG_PAGEALLOC
@@ -1299,6 +1309,7 @@ static __always_inline bool free_pages_prepare(struct page *page,
if (memcg_kmem_enabled() && PageMemcgKmem(page))
__memcg_kmem_uncharge_page(page, order);
reset_page_owner(page, order);
+ page_table_check_free(page, order);
return false;
}
@@ -1312,8 +1323,10 @@ static __always_inline bool free_pages_prepare(struct page *page,
VM_BUG_ON_PAGE(compound && compound_order(page) != order, page);
- if (compound)
+ if (compound) {
ClearPageDoubleMap(page);
+ ClearPageHasHWPoisoned(page);
+ }
for (i = 1; i < (1 << order); i++) {
if (compound)
bad += free_tail_pages_check(page, page + i);
@@ -1336,6 +1349,7 @@ static __always_inline bool free_pages_prepare(struct page *page,
page_cpupid_reset_last(page);
page->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
reset_page_owner(page, order);
+ page_table_check_free(page, order);
if (!PageHighMem(page)) {
debug_check_no_locks_freed(page_address(page),
@@ -1428,14 +1442,8 @@ static inline void prefetch_buddy(struct page *page)
/*
* Frees a number of pages from the PCP lists
- * Assumes all pages on list are in same zone, and of same order.
+ * Assumes all pages on list are in same zone.
* count is the number of pages to free.
- *
- * If the zone was previously in an "all pages pinned" state then look to
- * see if this freeing clears that state.
- *
- * And clear the zone's pages_scanned counter, to hold off the "all pages are
- * pinned" detection logic.
*/
static void free_pcppages_bulk(struct zone *zone, int count,
struct per_cpu_pages *pcp)
@@ -1589,7 +1597,7 @@ static void __meminit init_reserved_page(unsigned long pfn)
for (zid = 0; zid < MAX_NR_ZONES; zid++) {
struct zone *zone = &pgdat->node_zones[zid];
- if (pfn >= zone->zone_start_pfn && pfn < zone_end_pfn(zone))
+ if (zone_spans_pfn(zone, pfn))
break;
}
__init_single_page(pfn_to_page(pfn), pfn, zid, nid);
@@ -2416,6 +2424,7 @@ inline void post_alloc_hook(struct page *page, unsigned int order,
}
set_page_owner(page, order, gfp_flags);
+ page_table_check_alloc(page, order);
}
static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags,
@@ -3147,9 +3156,9 @@ static void drain_local_pages_wq(struct work_struct *work)
* cpu which is alright but we also have to make sure to not move to
* a different one.
*/
- preempt_disable();
+ migrate_disable();
drain_local_pages(drain->zone);
- preempt_enable();
+ migrate_enable();
}
/*
@@ -3966,6 +3975,8 @@ bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
}
#ifdef CONFIG_NUMA
+int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE;
+
static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
{
return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <=
@@ -4208,7 +4219,9 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...)
va_list args;
static DEFINE_RATELIMIT_STATE(nopage_rs, 10*HZ, 1);
- if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs))
+ if ((gfp_mask & __GFP_NOWARN) ||
+ !__ratelimit(&nopage_rs) ||
+ ((gfp_mask & __GFP_DMA) && !has_managed_dma()))
return;
va_start(args, fmt);
@@ -4795,30 +4808,11 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order,
trace_reclaim_retry_zone(z, order, reclaimable,
available, min_wmark, *no_progress_loops, wmark);
if (wmark) {
- /*
- * If we didn't make any progress and have a lot of
- * dirty + writeback pages then we should wait for
- * an IO to complete to slow down the reclaim and
- * prevent from pre mature OOM
- */
- if (!did_some_progress) {
- unsigned long write_pending;
-
- write_pending = zone_page_state_snapshot(zone,
- NR_ZONE_WRITE_PENDING);
-
- if (2 * write_pending > reclaimable) {
- congestion_wait(BLK_RW_ASYNC, HZ/10);
- return true;
- }
- }
-
ret = true;
- goto out;
+ break;
}
}
-out:
/*
* Memory allocation/reclaim might be called from a WQ context and the
* current implementation of the WQ concurrency control doesn't
@@ -4914,6 +4908,19 @@ retry_cpuset:
if (!ac->preferred_zoneref->zone)
goto nopage;
+ /*
+ * Check for insane configurations where the cpuset doesn't contain
+ * any suitable zone to satisfy the request - e.g. non-movable
+ * GFP_HIGHUSER allocations from MOVABLE nodes only.
+ */
+ if (cpusets_insane_config() && (gfp_mask & __GFP_HARDWALL)) {
+ struct zoneref *z = first_zones_zonelist(ac->zonelist,
+ ac->highest_zoneidx,
+ &cpuset_current_mems_allowed);
+ if (!z->zone)
+ goto nopage;
+ }
+
if (alloc_flags & ALLOC_KSWAPD)
wake_all_kswapds(order, gfp_mask, ac);
@@ -5223,6 +5230,10 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
if (unlikely(page_array && nr_pages - nr_populated == 0))
goto out;
+ /* Bulk allocator does not support memcg accounting. */
+ if (memcg_kmem_enabled() && (gfp & __GFP_ACCOUNT))
+ goto failed;
+
/* Use the single page allocator for one page. */
if (nr_pages - nr_populated == 1)
goto failed;
@@ -5400,6 +5411,18 @@ out:
}
EXPORT_SYMBOL(__alloc_pages);
+struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid,
+ nodemask_t *nodemask)
+{
+ struct page *page = __alloc_pages(gfp | __GFP_COMP, order,
+ preferred_nid, nodemask);
+
+ if (page && order > 1)
+ prep_transhuge_page(page);
+ return (struct folio *)page;
+}
+EXPORT_SYMBOL(__folio_alloc);
+
/*
* Common helper functions. Never use with __GFP_HIGHMEM because the returned
* address cannot represent highmem pages. Use alloc_pages and then kmap if
@@ -5612,8 +5635,8 @@ void *alloc_pages_exact(size_t size, gfp_t gfp_mask)
unsigned int order = get_order(size);
unsigned long addr;
- if (WARN_ON_ONCE(gfp_mask & __GFP_COMP))
- gfp_mask &= ~__GFP_COMP;
+ if (WARN_ON_ONCE(gfp_mask & (__GFP_COMP | __GFP_HIGHMEM)))
+ gfp_mask &= ~(__GFP_COMP | __GFP_HIGHMEM);
addr = __get_free_pages(gfp_mask, order);
return make_alloc_exact(addr, order, size);
@@ -5637,8 +5660,8 @@ void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask)
unsigned int order = get_order(size);
struct page *p;
- if (WARN_ON_ONCE(gfp_mask & __GFP_COMP))
- gfp_mask &= ~__GFP_COMP;
+ if (WARN_ON_ONCE(gfp_mask & (__GFP_COMP | __GFP_HIGHMEM)))
+ gfp_mask &= ~(__GFP_COMP | __GFP_HIGHMEM);
p = alloc_pages_node(nid, gfp_mask, order);
if (!p)
@@ -5980,6 +6003,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
printk(KERN_CONT
"%s"
" free:%lukB"
+ " boost:%lukB"
" min:%lukB"
" low:%lukB"
" high:%lukB"
@@ -6000,6 +6024,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
"\n",
zone->name,
K(zone_page_state(zone, NR_FREE_PAGES)),
+ K(zone->watermark_boost),
K(min_wmark_pages(zone)),
K(low_wmark_pages(zone)),
K(high_wmark_pages(zone)),
@@ -6255,7 +6280,7 @@ static void build_zonelists(pg_data_t *pgdat)
*/
if (node_distance(local_node, node) !=
node_distance(local_node, prev_node))
- node_load[node] = load;
+ node_load[node] += load;
node_order[nr_nodes++] = node;
prev_node = node;
@@ -6264,6 +6289,10 @@ static void build_zonelists(pg_data_t *pgdat)
build_zonelists_in_node_order(pgdat, node_order, nr_nodes);
build_thisnode_zonelists(pgdat);
+ pr_info("Fallback order for Node %d: ", local_node);
+ for (node = 0; node < nr_nodes; node++)
+ pr_cont("%d ", node_order[node]);
+ pr_cont("\n");
}
#ifdef CONFIG_HAVE_MEMORYLESS_NODES
@@ -6550,6 +6579,75 @@ void __meminit memmap_init_range(unsigned long size, int nid, unsigned long zone
}
#ifdef CONFIG_ZONE_DEVICE
+static void __ref __init_zone_device_page(struct page *page, unsigned long pfn,
+ unsigned long zone_idx, int nid,
+ struct dev_pagemap *pgmap)
+{
+
+ __init_single_page(page, pfn, zone_idx, nid);
+
+ /*
+ * Mark page reserved as it will need to wait for onlining
+ * phase for it to be fully associated with a zone.
+ *
+ * We can use the non-atomic __set_bit operation for setting
+ * the flag as we are still initializing the pages.
+ */
+ __SetPageReserved(page);
+
+ /*
+ * ZONE_DEVICE pages union ->lru with a ->pgmap back pointer
+ * and zone_device_data. It is a bug if a ZONE_DEVICE page is
+ * ever freed or placed on a driver-private list.
+ */
+ page->pgmap = pgmap;
+ page->zone_device_data = NULL;
+
+ /*
+ * Mark the block movable so that blocks are reserved for
+ * movable at startup. This will force kernel allocations
+ * to reserve their blocks rather than leaking throughout
+ * the address space during boot when many long-lived
+ * kernel allocations are made.
+ *
+ * Please note that MEMINIT_HOTPLUG path doesn't clear memmap
+ * because this is done early in section_activate()
+ */
+ if (IS_ALIGNED(pfn, pageblock_nr_pages)) {
+ set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+ cond_resched();
+ }
+}
+
+static void __ref memmap_init_compound(struct page *head,
+ unsigned long head_pfn,
+ unsigned long zone_idx, int nid,
+ struct dev_pagemap *pgmap,
+ unsigned long nr_pages)
+{
+ unsigned long pfn, end_pfn = head_pfn + nr_pages;
+ unsigned int order = pgmap->vmemmap_shift;
+
+ __SetPageHead(head);
+ for (pfn = head_pfn + 1; pfn < end_pfn; pfn++) {
+ struct page *page = pfn_to_page(pfn);
+
+ __init_zone_device_page(page, pfn, zone_idx, nid, pgmap);
+ prep_compound_tail(head, pfn - head_pfn);
+ set_page_count(page, 0);
+
+ /*
+ * The first tail page stores compound_mapcount_ptr() and
+ * compound_order() and the second tail page stores
+ * compound_pincount_ptr(). Call prep_compound_head() after
+ * the first and second tail pages have been initialized to
+ * not have the data overwritten.
+ */
+ if (pfn == head_pfn + 2)
+ prep_compound_head(head, order);
+ }
+}
+
void __ref memmap_init_zone_device(struct zone *zone,
unsigned long start_pfn,
unsigned long nr_pages,
@@ -6558,6 +6656,7 @@ void __ref memmap_init_zone_device(struct zone *zone,
unsigned long pfn, end_pfn = start_pfn + nr_pages;
struct pglist_data *pgdat = zone->zone_pgdat;
struct vmem_altmap *altmap = pgmap_altmap(pgmap);
+ unsigned int pfns_per_compound = pgmap_vmemmap_nr(pgmap);
unsigned long zone_idx = zone_idx(zone);
unsigned long start = jiffies;
int nid = pgdat->node_id;
@@ -6575,42 +6674,16 @@ void __ref memmap_init_zone_device(struct zone *zone,
nr_pages = end_pfn - start_pfn;
}
- for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+ for (pfn = start_pfn; pfn < end_pfn; pfn += pfns_per_compound) {
struct page *page = pfn_to_page(pfn);
- __init_single_page(page, pfn, zone_idx, nid);
+ __init_zone_device_page(page, pfn, zone_idx, nid, pgmap);
- /*
- * Mark page reserved as it will need to wait for onlining
- * phase for it to be fully associated with a zone.
- *
- * We can use the non-atomic __set_bit operation for setting
- * the flag as we are still initializing the pages.
- */
- __SetPageReserved(page);
-
- /*
- * ZONE_DEVICE pages union ->lru with a ->pgmap back pointer
- * and zone_device_data. It is a bug if a ZONE_DEVICE page is
- * ever freed or placed on a driver-private list.
- */
- page->pgmap = pgmap;
- page->zone_device_data = NULL;
+ if (pfns_per_compound == 1)
+ continue;
- /*
- * Mark the block movable so that blocks are reserved for
- * movable at startup. This will force kernel allocations
- * to reserve their blocks rather than leaking throughout
- * the address space during boot when many long-lived
- * kernel allocations are made.
- *
- * Please note that MEMINIT_HOTPLUG path doesn't clear memmap
- * because this is done early in section_activate()
- */
- if (IS_ALIGNED(pfn, pageblock_nr_pages)) {
- set_pageblock_migratetype(page, MIGRATE_MOVABLE);
- cond_resched();
- }
+ memmap_init_compound(page, pfn, zone_idx, nid, pgmap,
+ pfns_per_compound);
}
pr_info("%s initialised %lu pages in %ums\n", __func__,
@@ -7389,6 +7462,8 @@ static void pgdat_init_kcompactd(struct pglist_data *pgdat) {}
static void __meminit pgdat_init_internals(struct pglist_data *pgdat)
{
+ int i;
+
pgdat_resize_init(pgdat);
pgdat_init_split_queue(pgdat);
@@ -7397,6 +7472,9 @@ static void __meminit pgdat_init_internals(struct pglist_data *pgdat)
init_waitqueue_head(&pgdat->kswapd_wait);
init_waitqueue_head(&pgdat->pfmemalloc_wait);
+ for (i = 0; i < NR_VMSCAN_THROTTLE; i++)
+ init_waitqueue_head(&pgdat->reclaim_wait[i]);
+
pgdat_page_ext_init(pgdat);
lruvec_init(&pgdat->__lruvec);
}
@@ -8126,8 +8204,7 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char
}
if (pages && s)
- pr_info("Freeing %s memory: %ldK\n",
- s, pages << (PAGE_SHIFT - 10));
+ pr_info("Freeing %s memory: %ldK\n", s, K(pages));
return pages;
}
@@ -8154,7 +8231,7 @@ void __init mem_init_print_info(void)
*/
#define adj_init_size(start, end, size, pos, adj) \
do { \
- if (start <= pos && pos < end && size > adj) \
+ if (&start[0] <= &pos[0] && &pos[0] < &end[0] && size > adj) \
size -= adj; \
} while (0)
@@ -8172,14 +8249,13 @@ void __init mem_init_print_info(void)
", %luK highmem"
#endif
")\n",
- nr_free_pages() << (PAGE_SHIFT - 10),
- physpages << (PAGE_SHIFT - 10),
+ K(nr_free_pages()), K(physpages),
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)
+ K(physpages - totalram_pages() - totalcma_pages),
+ K(totalcma_pages)
#ifdef CONFIG_HIGHMEM
- , totalhigh_pages() << (PAGE_SHIFT - 10)
+ , K(totalhigh_pages())
#endif
);
}
@@ -8452,7 +8528,7 @@ void setup_per_zone_wmarks(void)
* 8192MB: 11584k
* 16384MB: 16384k
*/
-int __meminit init_per_zone_wmark_min(void)
+void calculate_min_free_kbytes(void)
{
unsigned long lowmem_kbytes;
int new_min_free_kbytes;
@@ -8460,16 +8536,17 @@ int __meminit init_per_zone_wmark_min(void)
lowmem_kbytes = nr_free_buffer_pages() * (PAGE_SIZE >> 10);
new_min_free_kbytes = int_sqrt(lowmem_kbytes * 16);
- if (new_min_free_kbytes > user_min_free_kbytes) {
- min_free_kbytes = new_min_free_kbytes;
- if (min_free_kbytes < 128)
- min_free_kbytes = 128;
- if (min_free_kbytes > 262144)
- min_free_kbytes = 262144;
- } else {
+ if (new_min_free_kbytes > user_min_free_kbytes)
+ min_free_kbytes = clamp(new_min_free_kbytes, 128, 262144);
+ else
pr_warn("min_free_kbytes is not updated to %d because user defined value %d is preferred\n",
new_min_free_kbytes, user_min_free_kbytes);
- }
+
+}
+
+int __meminit init_per_zone_wmark_min(void)
+{
+ calculate_min_free_kbytes();
setup_per_zone_wmarks();
refresh_zone_stat_thresholds();
setup_per_zone_lowmem_reserve();
@@ -8756,7 +8833,8 @@ void *__init alloc_large_system_hash(const char *tablename,
} else if (get_order(size) >= MAX_ORDER || hashdist) {
table = __vmalloc(size, gfp_flags);
virt = true;
- huge = is_vm_area_hugepages(table);
+ if (table)
+ huge = is_vm_area_hugepages(table);
} else {
/*
* If bucketsize is not a power-of-two, we may free
@@ -9197,8 +9275,8 @@ static bool zone_spans_last_pfn(const struct zone *zone,
* for allocation requests which can not be fulfilled with the buddy allocator.
*
* The allocated memory is always aligned to a page boundary. If nr_pages is a
- * power of two then the alignment is guaranteed to be to the given nr_pages
- * (e.g. 1GB request would be aligned to 1GB).
+ * power of two, then allocated range is also guaranteed to be aligned to same
+ * nr_pages (e.g. 1GB request would be aligned to 1GB).
*
* Allocated pages can be freed with free_contig_range() or by manually calling
* __free_page() on each allocated page.
@@ -9353,21 +9431,21 @@ void __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
}
#endif
+/*
+ * This function returns a stable result only if called under zone lock.
+ */
bool is_free_buddy_page(struct page *page)
{
- struct zone *zone = page_zone(page);
unsigned long pfn = page_to_pfn(page);
- unsigned long flags;
unsigned int order;
- spin_lock_irqsave(&zone->lock, flags);
for (order = 0; order < MAX_ORDER; order++) {
struct page *page_head = page - (pfn & ((1 << order) - 1));
- if (PageBuddy(page_head) && buddy_order(page_head) >= order)
+ if (PageBuddy(page_head) &&
+ buddy_order_unsafe(page_head) >= order)
break;
}
- spin_unlock_irqrestore(&zone->lock, flags);
return order < MAX_ORDER;
}
@@ -9431,6 +9509,7 @@ bool take_page_off_buddy(struct page *page)
del_page_from_free_list(page_head, zone, page_order);
break_down_buddy_pages(zone, page_head, page, 0,
page_order, migratetype);
+ SetPageHWPoisonTakenOff(page);
if (!is_migrate_isolate(migratetype))
__mod_zone_freepage_state(zone, -1, migratetype);
ret = true;
@@ -9442,4 +9521,44 @@ bool take_page_off_buddy(struct page *page)
spin_unlock_irqrestore(&zone->lock, flags);
return ret;
}
+
+/*
+ * Cancel takeoff done by take_page_off_buddy().
+ */
+bool put_page_back_buddy(struct page *page)
+{
+ struct zone *zone = page_zone(page);
+ unsigned long pfn = page_to_pfn(page);
+ unsigned long flags;
+ int migratetype = get_pfnblock_migratetype(page, pfn);
+ bool ret = false;
+
+ spin_lock_irqsave(&zone->lock, flags);
+ if (put_page_testzero(page)) {
+ ClearPageHWPoisonTakenOff(page);
+ __free_one_page(page, pfn, zone, 0, migratetype, FPI_NONE);
+ if (TestClearPageHWPoison(page)) {
+ num_poisoned_pages_dec();
+ ret = true;
+ }
+ }
+ spin_unlock_irqrestore(&zone->lock, flags);
+
+ return ret;
+}
#endif
+
+#ifdef CONFIG_ZONE_DMA
+bool has_managed_dma(void)
+{
+ struct pglist_data *pgdat;
+
+ for_each_online_pgdat(pgdat) {
+ struct zone *zone = &pgdat->node_zones[ZONE_DMA];
+
+ if (managed_zone(zone))
+ return true;
+ }
+ return false;
+}
+#endif /* CONFIG_ZONE_DMA */