From 2c9affe4c102db8031477a0ff10af4803345ff7e Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.com>
Date: Thu, 17 Feb 2022 10:47:58 +0100
Subject: [PATCH] mm/memcg: Revert ("mm/memcg: optimize user context object
stock access")
References: SLE Realtime Extension
Patch-mainline: v5.18-rc1
Git-commit: fead2b869764f89d524b79dc8862e61d5191be55
The optimisation is based on a micro benchmark where local_irq_save() is
more expensive than a preempt_disable(). There is no evidence that it is
visible in a real-world workload and there are CPUs where the opposite is
true (local_irq_save() is cheaper than preempt_disable()).
Based on micro benchmarks, the optimisation makes sense on PREEMPT_NONE
where preempt_disable() is optimized away. There is no improvement with
PREEMPT_DYNAMIC since the preemption counter is always available.
The optimization makes also the PREEMPT_RT integration more complicated
since most of the assumption are not true on PREEMPT_RT.
Revert the optimisation since it complicates the PREEMPT_RT integration
and the improvement is hardly visible.
[ bigeasy: Patch body around Michal's diff ]
Link: https://lore.kernel.org/all/YgOGkXXCrD%2F1k+p4@dhcp22.suse.cz
Link: https://lkml.kernel.org/r/YdX+INO9gQje6d0S@linutronix.de
Signed-off-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: Roman Gushchin <guro@fb.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Mel Gorman <mgorman@suse.de>
---
mm/memcontrol.c | 94 +++++++++++++++++----------------------------------------
1 file changed, 27 insertions(+), 67 deletions(-)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 38af3a5f1b38..c6c19a183de1 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2069,23 +2069,17 @@ void unlock_page_memcg(struct page *page)
}
EXPORT_SYMBOL(unlock_page_memcg);
-struct obj_stock {
+struct memcg_stock_pcp {
+ struct mem_cgroup *cached; /* this never be root cgroup */
+ unsigned int nr_pages;
+
#ifdef CONFIG_MEMCG_KMEM
struct obj_cgroup *cached_objcg;
struct pglist_data *cached_pgdat;
unsigned int nr_bytes;
int nr_slab_reclaimable_b;
int nr_slab_unreclaimable_b;
-#else
- int dummy[0];
#endif
-};
-
-struct memcg_stock_pcp {
- struct mem_cgroup *cached; /* this never be root cgroup */
- unsigned int nr_pages;
- struct obj_stock task_obj;
- struct obj_stock irq_obj;
struct work_struct work;
unsigned long flags;
@@ -2095,12 +2089,12 @@ static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock);
static DEFINE_MUTEX(percpu_charge_mutex);
#ifdef CONFIG_MEMCG_KMEM
-static void drain_obj_stock(struct obj_stock *stock);
+static void drain_obj_stock(struct memcg_stock_pcp *stock);
static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
struct mem_cgroup *root_memcg);
#else
-static inline void drain_obj_stock(struct obj_stock *stock)
+static inline void drain_obj_stock(struct memcg_stock_pcp *stock)
{
}
static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
@@ -2110,41 +2104,6 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
}
#endif
-/*
- * Most kmem_cache_alloc() calls are from user context. The irq disable/enable
- * sequence used in this case to access content from object stock is slow.
- * To optimize for user context access, there are now two object stocks for
- * task context and interrupt context access respectively.
- *
- * The task context object stock can be accessed by disabling preemption only
- * 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.
- */
-static inline struct obj_stock *get_obj_stock(unsigned long *pflags)
-{
- struct memcg_stock_pcp *stock;
-
- if (likely(in_task())) {
- *pflags = 0UL;
- preempt_disable();
- stock = this_cpu_ptr(&memcg_stock);
- return &stock->task_obj;
- }
-
- local_irq_save(*pflags);
- stock = this_cpu_ptr(&memcg_stock);
- return &stock->irq_obj;
-}
-
-static inline void put_obj_stock(unsigned long flags)
-{
- if (likely(in_task()))
- preempt_enable();
- else
- local_irq_restore(flags);
-}
-
/**
* consume_stock: Try to consume stocked charge on this cpu.
* @memcg: memcg to consume from.
@@ -2211,9 +2170,7 @@ static void drain_local_stock(struct work_struct *dummy)
local_irq_save(flags);
stock = this_cpu_ptr(&memcg_stock);
- drain_obj_stock(&stock->irq_obj);
- if (in_task())
- drain_obj_stock(&stock->task_obj);
+ drain_obj_stock(stock);
drain_stock(stock);
clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags);
@@ -3077,10 +3034,13 @@ void __memcg_kmem_uncharge_page(struct page *page, int order)
void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
enum node_stat_item idx, int nr)
{
+ struct memcg_stock_pcp *stock;
unsigned long flags;
- struct obj_stock *stock = get_obj_stock(&flags);
int *bytes;
+ local_irq_save(flags);
+ stock = this_cpu_ptr(&memcg_stock);
+
/*
* Save vmstat data in stock and skip vmstat array update unless
* accumulating over a page of vmstat data or when pgdat or idx
@@ -3131,26 +3091,29 @@ void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
if (nr)
mod_objcg_mlstate(objcg, pgdat, idx, nr);
- put_obj_stock(flags);
+ local_irq_restore(flags);
}
static bool consume_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes)
{
+ struct memcg_stock_pcp *stock;
unsigned long flags;
- struct obj_stock *stock = get_obj_stock(&flags);
bool ret = false;
+ local_irq_save(flags);
+
+ stock = this_cpu_ptr(&memcg_stock);
if (objcg == stock->cached_objcg && stock->nr_bytes >= nr_bytes) {
stock->nr_bytes -= nr_bytes;
ret = true;
}
- put_obj_stock(flags);
+ local_irq_restore(flags);
return ret;
}
-static void drain_obj_stock(struct obj_stock *stock)
+static void drain_obj_stock(struct memcg_stock_pcp *stock)
{
struct obj_cgroup *old = stock->cached_objcg;
@@ -3206,13 +3169,8 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
{
struct mem_cgroup *memcg;
- if (in_task() && 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;
- }
- if (stock->irq_obj.cached_objcg) {
- memcg = obj_cgroup_memcg(stock->irq_obj.cached_objcg);
+ if (stock->cached_objcg) {
+ memcg = obj_cgroup_memcg(stock->cached_objcg);
if (memcg && mem_cgroup_is_descendant(memcg, root_memcg))
return true;
}
@@ -3223,10 +3181,13 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock,
static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes,
bool allow_uncharge)
{
+ struct memcg_stock_pcp *stock;
unsigned long flags;
- struct obj_stock *stock = get_obj_stock(&flags);
unsigned int nr_pages = 0;
+ local_irq_save(flags);
+
+ stock = this_cpu_ptr(&memcg_stock);
if (stock->cached_objcg != objcg) { /* reset if necessary */
drain_obj_stock(stock);
obj_cgroup_get(objcg);
@@ -3242,7 +3203,7 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes,
stock->nr_bytes &= (PAGE_SIZE - 1);
}
- put_obj_stock(flags);
+ local_irq_restore(flags);
if (nr_pages)
obj_cgroup_uncharge_pages(objcg, nr_pages);
@@ -6835,7 +6796,6 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
unsigned long nr_pages;
struct mem_cgroup *memcg;
struct obj_cgroup *objcg;
- bool use_objcg = PageMemcgKmem(page);
VM_BUG_ON_PAGE(PageLRU(page), page);
@@ -6844,7 +6804,7 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
* page memcg or objcg at this point, we have fully
* exclusive access to the page.
*/
- if (use_objcg) {
+ if (PageMemcgKmem(page)) {
objcg = __page_objcg(page);
/*
* This get matches the put at the end of the function and
@@ -6872,7 +6832,7 @@ static void uncharge_page(struct page *page, struct uncharge_gather *ug)
nr_pages = compound_nr(page);
- if (use_objcg) {
+ if (PageMemcgKmem(page)) {
ug->nr_memory += nr_pages;
ug->nr_kmem += nr_pages;