The patch titled
SLUB: Fixes to kmem_cache_shrink()
has been removed from the -mm tree. Its filename was
slub-free-slabs-and-sort-partial-slab-lists-in-kmem_cache_shrink-fixes-to-kmem_cache_shrink.patch
This patch was dropped because it was folded into slub-free-slabs-and-sort-partial-slab-lists-in-kmem_cache_shrink.patch
------------------------------------------------------
Subject: SLUB: Fixes to kmem_cache_shrink()
From: Christoph Lameter <clameter@xxxxxxx>
1. Reclaim all empty slabs even if we are below MIN_PARTIAL partial slabs.
The point here is to recover all possible memory.
2. Fix race condition vs. slab_free. If we want to free a slab then
we need to acquire the slab lock since slab_free may have freed
an object and is waiting to acquire the lock to remove the slab.
We do a trylock. If its unsuccessful then we are racing with
slab_free. Simply keep the empty slab on the partial lists.
slab_free will remove the slab as soon as we drop the list_lock.
3. #2 may have the result that we end up with empty slabs on the
slabs_by_inuse array. So make sure that we also splice in the
zeroeth element.
Signed-off-by: Christoph Lameter <clameter@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/slub.c | 19 +++++++++++++------
1 files changed, 13 insertions(+), 6 deletions(-)
diff -puN mm/slub.c~slub-free-slabs-and-sort-partial-slab-lists-in-kmem_cache_shrink-fixes-to-kmem_cache_shrink mm/slub.c
--- a/mm/slub.c~slub-free-slabs-and-sort-partial-slab-lists-in-kmem_cache_shrink-fixes-to-kmem_cache_shrink
+++ a/mm/slub.c
@@ -2237,7 +2237,7 @@ int kmem_cache_shrink(struct kmem_cache
for_each_online_node(node) {
n = get_node(s, node);
- if (n->nr_partial <= MIN_PARTIAL)
+ if (!n->nr_partial)
continue;
for (i = 0; i < s->objects; i++)
@@ -2254,14 +2254,21 @@ int kmem_cache_shrink(struct kmem_cache
* the upper limit.
*/
list_for_each_entry_safe(page, t, &n->partial, lru) {
- if (!page->inuse) {
+ if (!page->inuse && slab_trylock(page)) {
+ /*
+ * Must hold slab lock here because slab_free
+ * may have freed the last object and be
+ * waiting to release the slab.
+ */
list_del(&page->lru);
n->nr_partial--;
+ slab_unlock(page);
discard_slab(s, page);
- } else
- if (n->nr_partial > MAX_PARTIAL)
- list_move(&page->lru,
+ } else {
+ if (n->nr_partial > MAX_PARTIAL)
+ list_move(&page->lru,
slabs_by_inuse + page->inuse);
+ }
}
if (n->nr_partial <= MAX_PARTIAL)
@@ -2271,7 +2278,7 @@ int kmem_cache_shrink(struct kmem_cache
* Rebuild the partial list with the slabs filled up
* most first and the least used slabs at the end.
*/
- for (i = s->objects - 1; i > 0; i--)
+ for (i = s->objects - 1; i >= 0; i--)
list_splice(slabs_by_inuse + i, n->partial.prev);
out:
_
Patches currently in -mm which might be from clameter@xxxxxxx are
extend-print_symbol-capability.patch
slab-introduce-krealloc.patch
ia64-sn-xpc-convert-to-use-kthread-api-fix.patch
ia64-sn-xpc-convert-to-use-kthread-api-fix-2.patch
add-apply_to_page_range-which-applies-a-function-to-a-pte-range.patch
add-apply_to_page_range-which-applies-a-function-to-a-pte-range-fix.patch
safer-nr_node_ids-and-nr_node_ids-determination-and-initial.patch
use-zvc-counters-to-establish-exact-size-of-dirtyable-pages.patch
slab-ensure-cache_alloc_refill-terminates.patch
smaps-extract-pmd-walker-from-smaps-code.patch
smaps-add-pages-referenced-count-to-smaps.patch
smaps-add-clear_refs-file-to-clear-reference.patch
slab-use-num_possible_cpus-in-enable_cpucache.patch
i386-use-page-allocator-to-allocate-thread_info-structure.patch
slub-core.patch
make-page-private-usable-in-compound-pages-v1.patch
optimize-compound_head-by-avoiding-a-shared-page.patch
add-virt_to_head_page-and-consolidate-code-in-slab-and-slub.patch
slub-fix-object-tracking.patch
slub-enable-tracking-of-full-slabs.patch
slub-validation-of-slabs-metadata-and-guard-zones.patch
slub-add-min_partial.patch
slub-add-ability-to-list-alloc--free-callers-per-slab.patch
slub-free-slabs-and-sort-partial-slab-lists-in-kmem_cache_shrink.patch
slub-free-slabs-and-sort-partial-slab-lists-in-kmem_cache_shrink-fixes-to-kmem_cache_shrink.patch
slub-remove-object-activities-out-of-checking-functions.patch
slub-remove-object-activities-out-of-checking-functions-printk-cleanup-diagnostic-functions.patch
slub-user-documentation.patch
slub-user-documentation-fix.patch
slub-add-slabinfo-tool.patch
slub-add-slabinfo-tool-update-slabinfoc.patch
slub-major-slabinfo-update.patch
slub-slabinfo-remove-hackname.patch
slub-slabinfo-more-statistic-fixes-and-handling-fixes.patch
slub-exploit-page-mobility-to-increase-allocation-order.patch
slub-mm-only-make-slub-the-default-slab-allocator.patch
quicklists-for-page-table-pages.patch
quicklists-for-page-table-pages-avoid-useless-virt_to_page-conversion.patch
quicklists-for-page-table-pages-avoid-useless-virt_to_page-conversion-fix.patch
quicklist-support-for-ia64.patch
quicklist-support-for-x86_64.patch
quicklist-support-for-sparc64.patch
slab-allocators-remove-obsolete-slab_must_hwcache_align.patch
kmem_cache-simplify-slab-cache-creation.patch
slab-allocators-remove-slab_debug_initial-flag.patch
slab-allocators-remove-slab_debug_initial-flag-locks-fix.patch
slab-allocators-remove-multiple-alignment-specifications.patch
slab-allocators-remove-slab_ctor_atomic.patch
fault-injection-fix-failslab-with-config_numa.patch
mm-fix-handling-of-panic_on_oom-when-cpusets-are-in-use.patch
slub-i386-support.patch
slab-shutdown-cache_reaper-when-cpu-goes-down.patch
mm-implement-swap-prefetching.patch
revoke-core-code-slab-allocators-remove-slab_debug_initial-flag-revoke.patch
vmstat-use-our-own-timer-events.patch
readahead-state-based-method-aging-accounting.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
