The patch titled
Subject: mm/memcg: disable task obj_stock for PREEMPT_RT
has been added to the -mm tree. Its filename is
mm-memcg-disable-task-obj_stock-for-preempt_rt.patch
This patch should soon appear at
https://ozlabs.org/~akpm/mmots/broken-out/mm-memcg-disable-task-obj_stock-for-preempt_rt.patch
and later at
https://ozlabs.org/~akpm/mmotm/broken-out/mm-memcg-disable-task-obj_stock-for-preempt_rt.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Waiman Long <longman@xxxxxxxxxx>
Subject: mm/memcg: disable task obj_stock for PREEMPT_RT
For PREEMPT_RT kernel, preempt_disable() and local_irq_save() are
typically converted to local_lock() and local_lock_irqsave() respectively.
These two variants of local_lock() are essentially the same. Thus, there
is no performance advantage in choosing one over the other.
As there is no point in maintaining two different sets of obj_stock, it is
simpler and more efficient to just disable task_obj and use only irq_obj
for PREEMPT_RT. However, task_obj will still be there in the
memcg_stock_pcp structure even though it is not used in this
configuration.
Link: https://lkml.kernel.org/r/20210803175519.22298-1-longman@xxxxxxxxxx
Signed-off-by: Waiman Long <longman@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxxxx>
Cc: Vladimir Davydov <vdavydov.dev@xxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Roman Gushchin <guro@xxxxxx>
Cc: Shakeel Butt <shakeelb@xxxxxxxxxx>
Cc: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Cc: Luis Goncalves <lgoncalv@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/memcontrol.c | 18 ++++++++++++++----
1 file changed, 14 insertions(+), 4 deletions(-)
--- a/mm/memcontrol.c~mm-memcg-disable-task-obj_stock-for-preempt_rt
+++ a/mm/memcontrol.c
@@ -2093,12 +2093,22 @@ static bool obj_stock_flush_required(str
* which is cheap in non-preempt kernel. The interrupt context object stock
* can only be accessed after disabling interrupt. User context code can
* access interrupt object stock, but not vice versa.
+ *
+ * For PREEMPT_RT kernel, preempt_disable() and local_irq_save() may have
+ * to be changed to variants of local_lock(). This eliminates the
+ * performance advantage of using preempt_disable(). Fall back to always
+ * use local_irq_save() and use only irq_obj for simplicity.
*/
+static inline bool use_task_obj_stock(void)
+{
+ return !IS_ENABLED(CONFIG_PREEMPT_RT) && likely(in_task());
+}
+
static inline struct obj_stock *get_obj_stock(unsigned long *pflags)
{
struct memcg_stock_pcp *stock;
- if (likely(in_task())) {
+ if (use_task_obj_stock()) {
*pflags = 0UL;
preempt_disable();
stock = this_cpu_ptr(&memcg_stock);
@@ -2112,7 +2122,7 @@ static inline struct obj_stock *get_obj_
static inline void put_obj_stock(unsigned long flags)
{
- if (likely(in_task()))
+ if (use_task_obj_stock())
preempt_enable();
else
local_irq_restore(flags);
@@ -2185,7 +2195,7 @@ static void drain_local_stock(struct wor
stock = this_cpu_ptr(&memcg_stock);
drain_obj_stock(&stock->irq_obj);
- if (in_task())
+ if (use_task_obj_stock())
drain_obj_stock(&stock->task_obj);
drain_stock(stock);
clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
@@ -3163,7 +3173,7 @@ static bool obj_stock_flush_required(str
{
struct mem_cgroup *memcg;
- if (in_task() && stock->task_obj.cached_objcg) {
+ if (use_task_obj_stock() && stock->task_obj.cached_objcg) {
memcg = obj_cgroup_memcg(stock->task_obj.cached_objcg);
if (memcg && mem_cgroup_is_descendant(memcg, root_memcg))
return true;
_
Patches currently in -mm which might be from longman@xxxxxxxxxx are
mm-memcg-fix-incorrect-flushing-of-lruvec-data-in-obj_stock.patch
mm-memcg-disable-task-obj_stock-for-preempt_rt.patch
