summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/cma.c83
-rw-r--r--mm/compaction.c4
-rw-r--r--mm/internal.h4
-rw-r--r--mm/kasan/kasan.c66
-rw-r--r--mm/memory_hotplug.c2
-rw-r--r--mm/page_alloc.c99
-rw-r--r--mm/swapfile.c7
7 files changed, 125 insertions, 140 deletions
diff --git a/mm/cma.c b/mm/cma.c
index aa40e6c7b042..5809bbe360d7 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -39,7 +39,6 @@
#include <trace/events/cma.h>
#include "cma.h"
-#include "internal.h"
struct cma cma_areas[MAX_CMA_AREAS];
unsigned cma_area_count;
@@ -110,25 +109,23 @@ static int __init cma_activate_area(struct cma *cma)
if (!cma->bitmap)
return -ENOMEM;
+ WARN_ON_ONCE(!pfn_valid(pfn));
+ zone = page_zone(pfn_to_page(pfn));
+
do {
unsigned j;
base_pfn = pfn;
- if (!pfn_valid(base_pfn))
- goto err;
-
- zone = page_zone(pfn_to_page(base_pfn));
for (j = pageblock_nr_pages; j; --j, pfn++) {
- if (!pfn_valid(pfn))
- goto err;
-
+ WARN_ON_ONCE(!pfn_valid(pfn));
/*
- * In init_cma_reserved_pageblock(), present_pages
- * is adjusted with assumption that all pages in
- * the pageblock come from a single zone.
+ * alloc_contig_range requires the pfn range
+ * specified to be in the same zone. Make this
+ * simple by forcing the entire CMA resv range
+ * to be in the same zone.
*/
if (page_zone(pfn_to_page(pfn)) != zone)
- goto err;
+ goto not_in_zone;
}
init_cma_reserved_pageblock(pfn_to_page(base_pfn));
} while (--i);
@@ -142,7 +139,7 @@ static int __init cma_activate_area(struct cma *cma)
return 0;
-err:
+not_in_zone:
pr_err("CMA area %s could not be activated\n", cma->name);
kfree(cma->bitmap);
cma->count = 0;
@@ -152,41 +149,6 @@ err:
static int __init cma_init_reserved_areas(void)
{
int i;
- struct zone *zone;
- pg_data_t *pgdat;
-
- if (!cma_area_count)
- return 0;
-
- for_each_online_pgdat(pgdat) {
- unsigned long start_pfn = UINT_MAX, end_pfn = 0;
-
- zone = &pgdat->node_zones[ZONE_MOVABLE];
-
- /*
- * In this case, we cannot adjust the zone range
- * since it is now maximum node span and we don't
- * know original zone range.
- */
- if (populated_zone(zone))
- continue;
-
- for (i = 0; i < cma_area_count; i++) {
- if (pfn_to_nid(cma_areas[i].base_pfn) !=
- pgdat->node_id)
- continue;
-
- start_pfn = min(start_pfn, cma_areas[i].base_pfn);
- end_pfn = max(end_pfn, cma_areas[i].base_pfn +
- cma_areas[i].count);
- }
-
- if (!end_pfn)
- continue;
-
- zone->zone_start_pfn = start_pfn;
- zone->spanned_pages = end_pfn - start_pfn;
- }
for (i = 0; i < cma_area_count; i++) {
int ret = cma_activate_area(&cma_areas[i]);
@@ -195,32 +157,9 @@ static int __init cma_init_reserved_areas(void)
return ret;
}
- /*
- * Reserved pages for ZONE_MOVABLE are now activated and
- * this would change ZONE_MOVABLE's managed page counter and
- * the other zones' present counter. We need to re-calculate
- * various zone information that depends on this initialization.
- */
- build_all_zonelists(NULL);
- for_each_populated_zone(zone) {
- if (zone_idx(zone) == ZONE_MOVABLE) {
- zone_pcp_reset(zone);
- setup_zone_pageset(zone);
- } else
- zone_pcp_update(zone);
-
- set_zone_contiguous(zone);
- }
-
- /*
- * We need to re-init per zone wmark by calling
- * init_per_zone_wmark_min() but doesn't call here because it is
- * registered on core_initcall and it will be called later than us.
- */
-
return 0;
}
-pure_initcall(cma_init_reserved_areas);
+core_initcall(cma_init_reserved_areas);
/**
* cma_init_reserved_mem() - create custom contiguous area from reserved memory
diff --git a/mm/compaction.c b/mm/compaction.c
index 028b7210a669..29bd1df18b98 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1450,12 +1450,14 @@ static enum compact_result __compaction_suitable(struct zone *zone, int order,
* if compaction succeeds.
* For costly orders, we require low watermark instead of min for
* compaction to proceed to increase its chances.
+ * ALLOC_CMA is used, as pages in CMA pageblocks are considered
+ * suitable migration targets
*/
watermark = (order > PAGE_ALLOC_COSTLY_ORDER) ?
low_wmark_pages(zone) : min_wmark_pages(zone);
watermark += compact_gap(order);
if (!__zone_watermark_ok(zone, 0, watermark, classzone_idx,
- 0, wmark_target))
+ ALLOC_CMA, wmark_target))
return COMPACT_SKIPPED;
return COMPACT_CONTINUE;
diff --git a/mm/internal.h b/mm/internal.h
index 62d8c34e63d5..502d14189794 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -168,9 +168,6 @@ extern void post_alloc_hook(struct page *page, unsigned int order,
gfp_t gfp_flags);
extern int user_min_free_kbytes;
-extern void set_zone_contiguous(struct zone *zone);
-extern void clear_zone_contiguous(struct zone *zone);
-
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
/*
@@ -498,6 +495,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone,
#define ALLOC_HARDER 0x10 /* try to alloc harder */
#define ALLOC_HIGH 0x20 /* __GFP_HIGH set */
#define ALLOC_CPUSET 0x40 /* check for correct cpuset */
+#define ALLOC_CMA 0x80 /* allow allocations from CMA areas */
enum ttu_flags;
struct tlbflush_unmap_batch;
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index bc0e68f7dc75..f185455b3406 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -792,6 +792,40 @@ DEFINE_ASAN_SET_SHADOW(f5);
DEFINE_ASAN_SET_SHADOW(f8);
#ifdef CONFIG_MEMORY_HOTPLUG
+static bool shadow_mapped(unsigned long addr)
+{
+ pgd_t *pgd = pgd_offset_k(addr);
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ if (pgd_none(*pgd))
+ return false;
+ p4d = p4d_offset(pgd, addr);
+ if (p4d_none(*p4d))
+ return false;
+ pud = pud_offset(p4d, addr);
+ if (pud_none(*pud))
+ return false;
+
+ /*
+ * We can't use pud_large() or pud_huge(), the first one is
+ * arch-specific, the last one depends on HUGETLB_PAGE. So let's abuse
+ * pud_bad(), if pud is bad then it's bad because it's huge.
+ */
+ if (pud_bad(*pud))
+ return true;
+ pmd = pmd_offset(pud, addr);
+ if (pmd_none(*pmd))
+ return false;
+
+ if (pmd_bad(*pmd))
+ return true;
+ pte = pte_offset_kernel(pmd, addr);
+ return !pte_none(*pte);
+}
+
static int __meminit kasan_mem_notifier(struct notifier_block *nb,
unsigned long action, void *data)
{
@@ -813,6 +847,14 @@ static int __meminit kasan_mem_notifier(struct notifier_block *nb,
case MEM_GOING_ONLINE: {
void *ret;
+ /*
+ * If shadow is mapped already than it must have been mapped
+ * during the boot. This could happen if we onlining previously
+ * offlined memory.
+ */
+ if (shadow_mapped(shadow_start))
+ return NOTIFY_OK;
+
ret = __vmalloc_node_range(shadow_size, PAGE_SIZE, shadow_start,
shadow_end, GFP_KERNEL,
PAGE_KERNEL, VM_NO_GUARD,
@@ -824,8 +866,26 @@ static int __meminit kasan_mem_notifier(struct notifier_block *nb,
kmemleak_ignore(ret);
return NOTIFY_OK;
}
- case MEM_OFFLINE:
- vfree((void *)shadow_start);
+ case MEM_CANCEL_ONLINE:
+ case MEM_OFFLINE: {
+ struct vm_struct *vm;
+
+ /*
+ * shadow_start was either mapped during boot by kasan_init()
+ * or during memory online by __vmalloc_node_range().
+ * In the latter case we can use vfree() to free shadow.
+ * Non-NULL result of the find_vm_area() will tell us if
+ * that was the second case.
+ *
+ * Currently it's not possible to free shadow mapped
+ * during boot by kasan_init(). It's because the code
+ * to do that hasn't been written yet. So we'll just
+ * leak the memory.
+ */
+ vm = find_vm_area((void *)shadow_start);
+ if (vm)
+ vfree((void *)shadow_start);
+ }
}
return NOTIFY_OK;
@@ -838,5 +898,5 @@ static int __init kasan_memhotplug_init(void)
return 0;
}
-module_init(kasan_memhotplug_init);
+core_initcall(kasan_memhotplug_init);
#endif
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index f74826cdceea..25982467800b 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1158,7 +1158,7 @@ int __ref add_memory_resource(int nid, struct resource *res, bool online)
* nodes have to go through register_node.
* TODO clean up this mess.
*/
- ret = link_mem_sections(nid, start_pfn, nr_pages);
+ ret = link_mem_sections(nid, start_pfn, nr_pages, false);
register_fail:
/*
* If sysfs file of new node can't create, cpu on the node
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 905db9d7962f..22320ea27489 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1743,38 +1743,16 @@ void __init page_alloc_init_late(void)
}
#ifdef CONFIG_CMA
-static void __init adjust_present_page_count(struct page *page, long count)
-{
- struct zone *zone = page_zone(page);
-
- /* We don't need to hold a lock since it is boot-up process */
- zone->present_pages += count;
-}
-
/* Free whole pageblock and set its migration type to MIGRATE_CMA. */
void __init init_cma_reserved_pageblock(struct page *page)
{
unsigned i = pageblock_nr_pages;
- unsigned long pfn = page_to_pfn(page);
struct page *p = page;
- int nid = page_to_nid(page);
-
- /*
- * ZONE_MOVABLE will steal present pages from other zones by
- * changing page links so page_zone() is changed. Before that,
- * we need to adjust previous zone's page count first.
- */
- adjust_present_page_count(page, -pageblock_nr_pages);
do {
__ClearPageReserved(p);
set_page_count(p, 0);
-
- /* Steal pages from other zones */
- set_page_links(p, ZONE_MOVABLE, nid, pfn);
- } while (++p, ++pfn, --i);
-
- adjust_present_page_count(page, pageblock_nr_pages);
+ } while (++p, --i);
set_pageblock_migratetype(page, MIGRATE_CMA);
@@ -2889,7 +2867,7 @@ int __isolate_free_page(struct page *page, unsigned int order)
* exists.
*/
watermark = min_wmark_pages(zone) + (1UL << order);
- if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
+ if (!zone_watermark_ok(zone, 0, watermark, 0, ALLOC_CMA))
return 0;
__mod_zone_freepage_state(zone, -(1UL << order), mt);
@@ -3165,6 +3143,12 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
}
+#ifdef CONFIG_CMA
+ /* If allocation can't use CMA areas don't use free CMA pages */
+ if (!(alloc_flags & ALLOC_CMA))
+ free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);
+#endif
+
/*
* Check watermarks for an order-0 allocation request. If these
* are not met, then a high-order request also cannot go ahead
@@ -3191,8 +3175,10 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
}
#ifdef CONFIG_CMA
- if (!list_empty(&area->free_list[MIGRATE_CMA]))
+ if ((alloc_flags & ALLOC_CMA) &&
+ !list_empty(&area->free_list[MIGRATE_CMA])) {
return true;
+ }
#endif
if (alloc_harder &&
!list_empty(&area->free_list[MIGRATE_HIGHATOMIC]))
@@ -3212,6 +3198,13 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
unsigned long mark, int classzone_idx, unsigned int alloc_flags)
{
long free_pages = zone_page_state(z, NR_FREE_PAGES);
+ long cma_pages = 0;
+
+#ifdef CONFIG_CMA
+ /* If allocation can't use CMA areas don't use free CMA pages */
+ if (!(alloc_flags & ALLOC_CMA))
+ cma_pages = zone_page_state(z, NR_FREE_CMA_PAGES);
+#endif
/*
* Fast check for order-0 only. If this fails then the reserves
@@ -3220,7 +3213,7 @@ static inline bool zone_watermark_fast(struct zone *z, unsigned int order,
* the caller is !atomic then it'll uselessly search the free
* list. That corner case is then slower but it is harmless.
*/
- if (!order && free_pages > mark + z->lowmem_reserve[classzone_idx])
+ if (!order && (free_pages - cma_pages) > mark + z->lowmem_reserve[classzone_idx])
return true;
return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
@@ -3856,6 +3849,10 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
} else if (unlikely(rt_task(current)) && !in_interrupt())
alloc_flags |= ALLOC_HARDER;
+#ifdef CONFIG_CMA
+ if (gfpflags_to_migratetype(gfp_mask) == MIGRATE_MOVABLE)
+ alloc_flags |= ALLOC_CMA;
+#endif
return alloc_flags;
}
@@ -4322,6 +4319,9 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
if (should_fail_alloc_page(gfp_mask, order))
return false;
+ if (IS_ENABLED(CONFIG_CMA) && ac->migratetype == MIGRATE_MOVABLE)
+ *alloc_flags |= ALLOC_CMA;
+
return true;
}
@@ -6204,7 +6204,6 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
{
enum zone_type j;
int nid = pgdat->node_id;
- unsigned long node_end_pfn = 0;
pgdat_resize_init(pgdat);
#ifdef CONFIG_NUMA_BALANCING
@@ -6232,13 +6231,9 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
struct zone *zone = pgdat->node_zones + j;
unsigned long size, realsize, freesize, memmap_pages;
unsigned long zone_start_pfn = zone->zone_start_pfn;
- unsigned long movable_size = 0;
size = zone->spanned_pages;
realsize = freesize = zone->present_pages;
- if (zone_end_pfn(zone) > node_end_pfn)
- node_end_pfn = zone_end_pfn(zone);
-
/*
* Adjust freesize so that it accounts for how much memory
@@ -6287,30 +6282,12 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
zone_seqlock_init(zone);
zone_pcp_init(zone);
- /*
- * The size of the CMA area is unknown now so we need to
- * prepare the memory for the usemap at maximum.
- */
- if (IS_ENABLED(CONFIG_CMA) && j == ZONE_MOVABLE &&
- pgdat->node_spanned_pages) {
- movable_size = node_end_pfn - pgdat->node_start_pfn;
- }
-
- if (!size && !movable_size)
+ if (!size)
continue;
set_pageblock_order();
- if (movable_size) {
- zone->zone_start_pfn = pgdat->node_start_pfn;
- zone->spanned_pages = movable_size;
- setup_usemap(pgdat, zone,
- pgdat->node_start_pfn, movable_size);
- init_currently_empty_zone(zone,
- pgdat->node_start_pfn, movable_size);
- } else {
- setup_usemap(pgdat, zone, zone_start_pfn, size);
- init_currently_empty_zone(zone, zone_start_pfn, size);
- }
+ setup_usemap(pgdat, zone, zone_start_pfn, size);
+ init_currently_empty_zone(zone, zone_start_pfn, size);
memmap_init(size, nid, j, zone_start_pfn);
}
}
@@ -7621,11 +7598,12 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
unsigned long pfn, iter, found;
/*
- * For avoiding noise data, lru_add_drain_all() should be called
- * If ZONE_MOVABLE, the zone never contains unmovable pages
+ * TODO we could make this much more efficient by not checking every
+ * page in the range if we know all of them are in MOVABLE_ZONE and
+ * that the movable zone guarantees that pages are migratable but
+ * the later is not the case right now unfortunatelly. E.g. movablecore
+ * can still lead to having bootmem allocations in zone_movable.
*/
- if (zone_idx(zone) == ZONE_MOVABLE)
- return false;
/*
* CMA allocations (alloc_contig_range) really need to mark isolate
@@ -7646,7 +7624,7 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
page = pfn_to_page(check);
if (PageReserved(page))
- return true;
+ goto unmovable;
/*
* Hugepages are not in LRU lists, but they're movable.
@@ -7696,9 +7674,12 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
* page at boot.
*/
if (found > count)
- return true;
+ goto unmovable;
}
return false;
+unmovable:
+ WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE);
+ return true;
}
bool is_pageblock_removable_nolock(struct page *page)
@@ -7951,7 +7932,7 @@ void free_contig_range(unsigned long pfn, unsigned nr_pages)
}
#endif
-#if defined CONFIG_MEMORY_HOTPLUG || defined CONFIG_CMA
+#ifdef CONFIG_MEMORY_HOTPLUG
/*
* The zone indicated has a new number of managed_pages; batch sizes and percpu
* page high values need to be recalulated.
diff --git a/mm/swapfile.c b/mm/swapfile.c
index cc2cf04d9018..78a015fcec3b 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3112,6 +3112,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
unsigned long *frontswap_map = NULL;
struct page *page = NULL;
struct inode *inode = NULL;
+ bool inced_nr_rotate_swap = false;
if (swap_flags & ~SWAP_FLAGS_VALID)
return -EINVAL;
@@ -3215,8 +3216,10 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
cluster = per_cpu_ptr(p->percpu_cluster, cpu);
cluster_set_null(&cluster->index);
}
- } else
+ } else {
atomic_inc(&nr_rotate_swap);
+ inced_nr_rotate_swap = true;
+ }
error = swap_cgroup_swapon(p->type, maxpages);
if (error)
@@ -3307,6 +3310,8 @@ bad_swap:
vfree(swap_map);
kvfree(cluster_info);
kvfree(frontswap_map);
+ if (inced_nr_rotate_swap)
+ atomic_dec(&nr_rotate_swap);
if (swap_file) {
if (inode && S_ISREG(inode->i_mode)) {
inode_unlock(inode);