diff mbox series

[v2,01/10] mm/memcg: Revert ("mm/memcg: optimize user context object stock access")

Message ID 20220808125602.97747-2-goliath@infraroot.at
State New
Headers show
Series Backport MEMCG changes from v5.17 | expand

Commit Message

David Oberhollenzer Aug. 8, 2022, 12:55 p.m. UTC 
From: Michal Hocko <mhocko@suse.com>

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>
[do: backported to v5.15]
Signed-off-by: David Oberhollenzer <goliath@infraroot.at>
---
 mm/memcontrol.c | 94 ++++++++++++++-----------------------------------
 1 file changed, 27 insertions(+), 67 deletions(-)
diff mbox series

Patch

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 971546bb99e0..a07e068989b4 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2102,23 +2102,17 @@  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;
@@ -2128,12 +2122,12 @@  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,
@@ -2144,41 +2138,6 @@  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.
  * @nr_pages: how many pages to charge.
@@ -2245,9 +2204,7 @@  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);
 
@@ -3084,10 +3041,13 @@  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
@@ -3138,26 +3098,29 @@  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;
 
@@ -3213,13 +3176,8 @@  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;
 	}
@@ -3230,10 +3188,13 @@  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);
@@ -3249,7 +3210,7 @@  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);
@@ -6874,7 +6835,6 @@  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);
 
@@ -6883,7 +6843,7 @@  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
@@ -6911,7 +6871,7 @@  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;