@@ -2287,25 +2287,15 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page,
}
}
-/*
- * Unfreeze all the cpu partial slabs.
- *
- * This function must be called with preemption or migration
- * disabled with c local to the cpu.
- */
-static void unfreeze_partials(struct kmem_cache *s,
- struct kmem_cache_cpu *c)
-{
#ifdef CONFIG_SLUB_CPU_PARTIAL
+static void __unfreeze_partials(struct kmem_cache *s, struct page *partial_page)
+{
struct kmem_cache_node *n = NULL, *n2 = NULL;
- struct page *page, *partial_page, *discard_page = NULL;
+ struct page *page, *discard_page = NULL;
unsigned long flags;
local_irq_save(flags);
- partial_page = slub_percpu_partial(c);
- c->partial = NULL;
-
while (partial_page) {
struct page new;
struct page old;
@@ -2360,10 +2350,49 @@ static void unfreeze_partials(struct kmem_cache *s,
discard_slab(s, page);
stat(s, FREE_SLAB);
}
+}
-#endif /* CONFIG_SLUB_CPU_PARTIAL */
+/*
+ * Unfreeze all the cpu partial slabs.
+ *
+ * This function must be called with preemption or migration
+ * disabled.
+ */
+static void unfreeze_partials(struct kmem_cache *s)
+{
+ struct page *partial_page;
+
+ do {
+ partial_page = this_cpu_read(s->cpu_slab->partial);
+
+ } while (partial_page &&
+ this_cpu_cmpxchg(s->cpu_slab->partial, partial_page, NULL)
+ != partial_page);
+
+ if (partial_page)
+ __unfreeze_partials(s, partial_page);
}
+static void unfreeze_partials_cpu(struct kmem_cache *s,
+ struct kmem_cache_cpu *c)
+{
+ struct page *partial_page;
+
+ partial_page = slub_percpu_partial(c);
+ c->partial = NULL;
+
+ if (partial_page)
+ __unfreeze_partials(s, partial_page);
+}
+
+#else /* CONFIG_SLUB_CPU_PARTIAL */
+
+static void unfreeze_partials(struct kmem_cache *s) { }
+static void unfreeze_partials_cpu(struct kmem_cache *s,
+ struct kmem_cache_cpu *c) { }
+
+#endif /* CONFIG_SLUB_CPU_PARTIAL */
+
/*
* Put a page that was just frozen (in __slab_free|get_partial_node) into a
* partial page slot if available.
@@ -2392,7 +2421,7 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
* partial array is full. Move the existing
* set to the per node partial list.
*/
- unfreeze_partials(s, this_cpu_ptr(s->cpu_slab));
+ unfreeze_partials(s);
oldpage = NULL;
pobjects = 0;
pages = 0;
@@ -2427,11 +2456,6 @@ static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
stat(s, CPUSLAB_FLUSH);
}
-/*
- * Flush cpu slab.
- *
- * Called from IPI handler with interrupts disabled.
- */
static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu)
{
struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu);
@@ -2439,14 +2463,23 @@ static inline void __flush_cpu_slab(struct kmem_cache *s, int cpu)
if (c->page)
flush_slab(s, c);
- unfreeze_partials(s, c);
+ unfreeze_partials_cpu(s, c);
}
+/*
+ * Flush cpu slab.
+ *
+ * Called from IPI handler with interrupts disabled.
+ */
static void flush_cpu_slab(void *d)
{
struct kmem_cache *s = d;
+ struct kmem_cache_cpu *c = this_cpu_ptr(s->cpu_slab);
- __flush_cpu_slab(s, smp_processor_id());
+ if (c->page)
+ flush_slab(s, c);
+
+ unfreeze_partials(s);
}
static bool has_cpu_slab(int cpu, void *info)
Instead of relying on disabled irqs for atomicity when detaching the percpu partial list, we can use this_cpu_cmpxchg() and detach without irqs disabled. However, unfreeze_partials() can be also called from another cpu on behalf of a cpu that is being offlined, so we need to restructure the code accordingly: - __unfreeze_partials() is the bulk of unfreeze_partials() that processes the detached percpu partial list - unfreeze_partials() uses this_cpu_cmpxchg() to detach list from current cpu - unfreeze_partials_cpu() is to be called for the offlined cpu so it needs no protection, and is called from __flush_cpu_slab() - flush_cpu_slab() is for the local cpu thus it needs to call unfreeze_partials(). So it can't simply call __flush_cpu_slab(smp_processor_id()) anymore and we have to open-code it Signed-off-by: Vlastimil Babka <vbabka@suse.cz> --- mm/slub.c | 77 +++++++++++++++++++++++++++++++++++++++---------------- 1 file changed, 55 insertions(+), 22 deletions(-)