summaryrefslogtreecommitdiff
path: root/mm/compaction.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-02-23 17:09:35 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2023-02-23 17:09:35 -0800
commit3822a7c40997dc86b1458766a3f146d62393f084 (patch)
tree4473720ecbfaabeedfe58484425be77d0f89f736 /mm/compaction.c
parente4bc15889506723d7b93c053ad4a75cd58248d74 (diff)
parentf9366f4c2a29d14f5992b195e268240c2deb116e (diff)
Merge tag 'mm-stable-2023-02-20-13-37' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton: - Daniel Verkamp has contributed a memfd series ("mm/memfd: add F_SEAL_EXEC") which permits the setting of the memfd execute bit at memfd creation time, with the option of sealing the state of the X bit. - Peter Xu adds a patch series ("mm/hugetlb: Make huge_pte_offset() thread-safe for pmd unshare") which addresses a rare race condition related to PMD unsharing. - Several folioification patch serieses from Matthew Wilcox, Vishal Moola, Sidhartha Kumar and Lorenzo Stoakes - Johannes Weiner has a series ("mm: push down lock_page_memcg()") which does perform some memcg maintenance and cleanup work. - SeongJae Park has added DAMOS filtering to DAMON, with the series "mm/damon/core: implement damos filter". These filters provide users with finer-grained control over DAMOS's actions. SeongJae has also done some DAMON cleanup work. - Kairui Song adds a series ("Clean up and fixes for swap"). - Vernon Yang contributed the series "Clean up and refinement for maple tree". - Yu Zhao has contributed the "mm: multi-gen LRU: memcg LRU" series. It adds to MGLRU an LRU of memcgs, to improve the scalability of global reclaim. - David Hildenbrand has added some userfaultfd cleanup work in the series "mm: uffd-wp + change_protection() cleanups". - Christoph Hellwig has removed the generic_writepages() library function in the series "remove generic_writepages". - Baolin Wang has performed some maintenance on the compaction code in his series "Some small improvements for compaction". - Sidhartha Kumar is doing some maintenance work on struct page in his series "Get rid of tail page fields". - David Hildenbrand contributed some cleanup, bugfixing and generalization of pte management and of pte debugging in his series "mm: support __HAVE_ARCH_PTE_SWP_EXCLUSIVE on all architectures with swap PTEs". - Mel Gorman and Neil Brown have removed the __GFP_ATOMIC allocation flag in the series "Discard __GFP_ATOMIC". - Sergey Senozhatsky has improved zsmalloc's memory utilization with his series "zsmalloc: make zspage chain size configurable". - Joey Gouly has added prctl() support for prohibiting the creation of writeable+executable mappings. The previous BPF-based approach had shortcomings. See "mm: In-kernel support for memory-deny-write-execute (MDWE)". - Waiman Long did some kmemleak cleanup and bugfixing in the series "mm/kmemleak: Simplify kmemleak_cond_resched() & fix UAF". - T.J. Alumbaugh has contributed some MGLRU cleanup work in his series "mm: multi-gen LRU: improve". - Jiaqi Yan has provided some enhancements to our memory error statistics reporting, mainly by presenting the statistics on a per-node basis. See the series "Introduce per NUMA node memory error statistics". - Mel Gorman has a second and hopefully final shot at fixing a CPU-hog regression in compaction via his series "Fix excessive CPU usage during compaction". - Christoph Hellwig does some vmalloc maintenance work in the series "cleanup vfree and vunmap". - Christoph Hellwig has removed block_device_operations.rw_page() in ths series "remove ->rw_page". - We get some maple_tree improvements and cleanups in Liam Howlett's series "VMA tree type safety and remove __vma_adjust()". - Suren Baghdasaryan has done some work on the maintainability of our vm_flags handling in the series "introduce vm_flags modifier functions". - Some pagemap cleanup and generalization work in Mike Rapoport's series "mm, arch: add generic implementation of pfn_valid() for FLATMEM" and "fixups for generic implementation of pfn_valid()" - Baoquan He has done some work to make /proc/vmallocinfo and /proc/kcore better represent the real state of things in his series "mm/vmalloc.c: allow vread() to read out vm_map_ram areas". - Jason Gunthorpe rationalized the GUP system's interface to the rest of the kernel in the series "Simplify the external interface for GUP". - SeongJae Park wishes to migrate people from DAMON's debugfs interface over to its sysfs interface. To support this, we'll temporarily be printing warnings when people use the debugfs interface. See the series "mm/damon: deprecate DAMON debugfs interface". - Andrey Konovalov provided the accurately named "lib/stackdepot: fixes and clean-ups" series. - Huang Ying has provided a dramatic reduction in migration's TLB flush IPI rates with the series "migrate_pages(): batch TLB flushing". - Arnd Bergmann has some objtool fixups in "objtool warning fixes". * tag 'mm-stable-2023-02-20-13-37' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (505 commits) include/linux/migrate.h: remove unneeded externs mm/memory_hotplug: cleanup return value handing in do_migrate_range() mm/uffd: fix comment in handling pte markers mm: change to return bool for isolate_movable_page() mm: hugetlb: change to return bool for isolate_hugetlb() mm: change to return bool for isolate_lru_page() mm: change to return bool for folio_isolate_lru() objtool: add UACCESS exceptions for __tsan_volatile_read/write kmsan: disable ftrace in kmsan core code kasan: mark addr_has_metadata __always_inline mm: memcontrol: rename memcg_kmem_enabled() sh: initialize max_mapnr m68k/nommu: add missing definition of ARCH_PFN_OFFSET mm: percpu: fix incorrect size in pcpu_obj_full_size() maple_tree: reduce stack usage with gcc-9 and earlier mm: page_alloc: call panic() when memoryless node allocation fails mm: multi-gen LRU: avoid futile retries migrate_pages: move THP/hugetlb migration support check to simplify code migrate_pages: batch flushing TLB migrate_pages: share more code between _unmap and _move ...
Diffstat (limited to 'mm/compaction.c')
-rw-r--r--mm/compaction.c101
1 files changed, 59 insertions, 42 deletions
diff --git a/mm/compaction.c b/mm/compaction.c
index 8238e83385a7..5a9501e0ae01 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -122,7 +122,6 @@ bool PageMovable(struct page *page)
return false;
}
-EXPORT_SYMBOL(PageMovable);
void __SetPageMovable(struct page *page, const struct movable_operations *mops)
{
@@ -977,7 +976,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
locked = NULL;
}
- if (!isolate_movable_page(page, mode))
+ if (isolate_movable_page(page, mode))
goto isolate_success;
}
@@ -1102,12 +1101,12 @@ isolate_success_no_list:
/*
* Avoid isolating too much unless this block is being
- * rescanned (e.g. dirty/writeback pages, parallel allocation)
+ * fully scanned (e.g. dirty/writeback pages, parallel allocation)
* or a lock is contended. For contention, isolate quickly to
* potentially remove one source of contention.
*/
if (cc->nr_migratepages >= COMPACT_CLUSTER_MAX &&
- !cc->rescan && !cc->contended) {
+ !cc->finish_pageblock && !cc->contended) {
++low_pfn;
break;
}
@@ -1172,14 +1171,14 @@ isolate_abort:
}
/*
- * Updated the cached scanner pfn once the pageblock has been scanned
+ * Update the cached scanner pfn once the pageblock has been scanned.
* Pages will either be migrated in which case there is no point
* scanning in the near future or migration failed in which case the
* failure reason may persist. The block is marked for skipping if
* there were no pages isolated in the block or if the block is
* rescanned twice in a row.
*/
- if (low_pfn == end_pfn && (!nr_isolated || cc->rescan)) {
+ if (low_pfn == end_pfn && (!nr_isolated || cc->finish_pageblock)) {
if (valid_page && !skip_updated)
set_pageblock_skip(valid_page);
update_cached_migrate(cc, low_pfn);
@@ -1763,6 +1762,13 @@ static unsigned long fast_find_migrateblock(struct compact_control *cc)
return pfn;
/*
+ * If the pageblock should be finished then do not select a different
+ * pageblock.
+ */
+ if (cc->finish_pageblock)
+ return pfn;
+
+ /*
* If the migrate_pfn is not at the start of a zone or the start
* of a pageblock then assume this is a continuation of a previous
* scan restarted due to COMPACT_CLUSTER_MAX.
@@ -2027,6 +2033,8 @@ static unsigned int fragmentation_score_node(pg_data_t *pgdat)
struct zone *zone;
zone = &pgdat->node_zones[zoneid];
+ if (!populated_zone(zone))
+ continue;
score += fragmentation_score_zone_weighted(zone);
}
@@ -2315,9 +2323,6 @@ compact_zone(struct compact_control *cc, struct capture_control *capc)
if (ret == COMPACT_SUCCESS || ret == COMPACT_SKIPPED)
return ret;
- /* huh, compaction_suitable is returning something unexpected */
- VM_BUG_ON(ret != COMPACT_CONTINUE);
-
/*
* Clear pageblock skip if there were failures recently and compaction
* is about to be retried after being deferred.
@@ -2375,19 +2380,20 @@ compact_zone(struct compact_control *cc, struct capture_control *capc)
unsigned long iteration_start_pfn = cc->migrate_pfn;
/*
- * Avoid multiple rescans which can happen if a page cannot be
- * isolated (dirty/writeback in async mode) or if the migrated
- * pages are being allocated before the pageblock is cleared.
- * The first rescan will capture the entire pageblock for
- * migration. If it fails, it'll be marked skip and scanning
- * will proceed as normal.
+ * Avoid multiple rescans of the same pageblock which can
+ * happen if a page cannot be isolated (dirty/writeback in
+ * async mode) or if the migrated pages are being allocated
+ * before the pageblock is cleared. The first rescan will
+ * capture the entire pageblock for migration. If it fails,
+ * it'll be marked skip and scanning will proceed as normal.
*/
- cc->rescan = false;
+ cc->finish_pageblock = false;
if (pageblock_start_pfn(last_migrated_pfn) ==
pageblock_start_pfn(iteration_start_pfn)) {
- cc->rescan = true;
+ cc->finish_pageblock = true;
}
+rescan:
switch (isolate_migratepages(cc)) {
case ISOLATE_ABORT:
ret = COMPACT_CONTENDED;
@@ -2430,18 +2436,37 @@ compact_zone(struct compact_control *cc, struct capture_control *capc)
goto out;
}
/*
- * We failed to migrate at least one page in the current
- * order-aligned block, so skip the rest of it.
+ * If an ASYNC or SYNC_LIGHT fails to migrate a page
+ * within the current order-aligned block, scan the
+ * remainder of the pageblock. This will mark the
+ * pageblock "skip" to avoid rescanning in the near
+ * future. This will isolate more pages than necessary
+ * for the request but avoid loops due to
+ * fast_find_migrateblock revisiting blocks that were
+ * recently partially scanned.
*/
- if (cc->direct_compaction &&
- (cc->mode == MIGRATE_ASYNC)) {
- cc->migrate_pfn = block_end_pfn(
- cc->migrate_pfn - 1, cc->order);
- /* Draining pcplists is useless in this case */
- last_migrated_pfn = 0;
+ if (cc->direct_compaction && !cc->finish_pageblock &&
+ (cc->mode < MIGRATE_SYNC)) {
+ cc->finish_pageblock = true;
+
+ /*
+ * Draining pcplists does not help THP if
+ * any page failed to migrate. Even after
+ * drain, the pageblock will not be free.
+ */
+ if (cc->order == COMPACTION_HPAGE_ORDER)
+ last_migrated_pfn = 0;
+
+ goto rescan;
}
}
+ /* Stop if a page has been captured */
+ if (capc && capc->page) {
+ ret = COMPACT_SUCCESS;
+ break;
+ }
+
check_drain:
/*
* Has the migration scanner moved away from the previous
@@ -2460,12 +2485,6 @@ check_drain:
last_migrated_pfn = 0;
}
}
-
- /* Stop if a page has been captured */
- if (capc && capc->page) {
- ret = COMPACT_SUCCESS;
- break;
- }
}
out:
@@ -2493,6 +2512,9 @@ out:
trace_mm_compaction_end(cc, start_pfn, end_pfn, sync, ret);
+ VM_BUG_ON(!list_empty(&cc->freepages));
+ VM_BUG_ON(!list_empty(&cc->migratepages));
+
return ret;
}
@@ -2531,9 +2553,6 @@ static enum compact_result compact_zone_order(struct zone *zone, int order,
ret = compact_zone(&cc, &capc);
- VM_BUG_ON(!list_empty(&cc.freepages));
- VM_BUG_ON(!list_empty(&cc.migratepages));
-
/*
* Make sure we hide capture control first before we read the captured
* page pointer, otherwise an interrupt could free and capture a page
@@ -2665,8 +2684,10 @@ static void proactive_compact_node(pg_data_t *pgdat)
compact_zone(&cc, NULL);
- VM_BUG_ON(!list_empty(&cc.freepages));
- VM_BUG_ON(!list_empty(&cc.migratepages));
+ count_compact_events(KCOMPACTD_MIGRATE_SCANNED,
+ cc.total_migrate_scanned);
+ count_compact_events(KCOMPACTD_FREE_SCANNED,
+ cc.total_free_scanned);
}
}
@@ -2694,9 +2715,6 @@ static void compact_node(int nid)
cc.zone = zone;
compact_zone(&cc, NULL);
-
- VM_BUG_ON(!list_empty(&cc.freepages));
- VM_BUG_ON(!list_empty(&cc.migratepages));
}
}
@@ -2736,6 +2754,8 @@ int compaction_proactiveness_sysctl_handler(struct ctl_table *table, int write,
continue;
pgdat->proactive_compact_trigger = true;
+ trace_mm_compaction_wakeup_kcompactd(pgdat->node_id, -1,
+ pgdat->nr_zones - 1);
wake_up_interruptible(&pgdat->kcompactd_wait);
}
}
@@ -2873,9 +2893,6 @@ static void kcompactd_do_work(pg_data_t *pgdat)
cc.total_migrate_scanned);
count_compact_events(KCOMPACTD_FREE_SCANNED,
cc.total_free_scanned);
-
- VM_BUG_ON(!list_empty(&cc.freepages));
- VM_BUG_ON(!list_empty(&cc.migratepages));
}
/*