Message-Id: <20200524215739.551568-4-bigeasy@linutronix.de>
Date:   Sun, 24 May 2020 23:57:35 +0200
From:   Sebastian Andrzej Siewior <bigeasy@...utronix.de>
To:     linux-kernel@...r.kernel.org
Cc:     Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...nel.org>,
        Steven Rostedt <rostedt@...dmis.org>,
        Will Deacon <will@...nel.org>,
        Thomas Gleixner <tglx@...utronix.de>,
        "Paul E . McKenney" <paulmck@...nel.org>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        Matthew Wilcox <willy@...radead.org>,
        Andrew Morton <akpm@...ux-foundation.org>, linux-mm@...ck.org,
        Sebastian Andrzej Siewior <bigeasy@...utronix.de>
Subject: [PATCH v2 3/7] mm/swap: Use local_lock for protection

From: Ingo Molnar <mingo@...nel.org>

The various struct pagevec per CPU variables are protected by disabling
either preemption or interrupts across the critical sections. Inside
these sections spinlocks have to be acquired.

These spinlocks are regular spinlock_t types which are converted to
"sleeping" spinlocks on PREEMPT_RT enabled kernels. Obviously sleeping
locks cannot be acquired in preemption or interrupt disabled sections.

local locks provide a trivial way to substitute preempt and interrupt
disable instances. On a non PREEMPT_RT enabled kernel local_lock() maps
to preempt_disable() and local_lock_irq() to local_irq_disable().

Create lru_rotate_pvecs containing the pagevec and the locallock.
Create lru_pvecs containing the remaining pagevecs and the locallock.
Add lru_add_drain_cpu_zone() which is used from compact_zone() to avoid
exporting the pvec structure.

Change the relevant call sites to acquire these locks instead of using
preempt_disable() / get_cpu() / get_cpu_var() and local_irq_disable() /
local_irq_save().

There is neither a functional change nor a change in the generated
binary code for non PREEMPT_RT enabled non-debug kernels.

When lockdep is enabled local locks have lockdep maps embedded. These
allow lockdep to validate the protections, i.e. inappropriate usage of a
preemption only protected sections would result in a lockdep warning
while the same problem would not be noticed with a plain
preempt_disable() based protection.

local locks also improve readability as they provide a named scope for
the protections while preempt/interrupt disable are opaque scopeless.

Finally local locks allow PREEMPT_RT to substitute them with real
locking primitives to ensure the correctness of operation in a fully
preemptible kernel.

[ bigeasy: Adopted to use local_lock ]

Cc: Andrew Morton <akpm@...ux-foundation.org>
Cc: linux-mm@...ck.org
Signed-off-by: Ingo Molnar <mingo@...nel.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
---
 include/linux/swap.h |   1 +
 mm/compaction.c      |   6 +--
 mm/swap.c            | 114 +++++++++++++++++++++++++++++--------------
 3 files changed, 79 insertions(+), 42 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index e1bbf7a16b276..25181d2dd0b9f 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -337,6 +337,7 @@ extern void activate_page(struct page *);
 extern void mark_page_accessed(struct page *);
 extern void lru_add_drain(void);
 extern void lru_add_drain_cpu(int cpu);
+extern void lru_add_drain_cpu_zone(struct zone *zone);
 extern void lru_add_drain_all(void);
 extern void rotate_reclaimable_page(struct page *page);
 extern void deactivate_file_page(struct page *page);
diff --git a/mm/compaction.c b/mm/compaction.c
index 46f0fcc93081e..c9d659e6a02c5 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -2243,15 +2243,11 @@ compact_zone(struct compact_control *cc, struct capture_control *capc)
 		 * would succeed.
 		 */
 		if (cc->order > 0 && last_migrated_pfn) {
-			int cpu;
 			unsigned long current_block_start =
 				block_start_pfn(cc->migrate_pfn, cc->order);
 
 			if (last_migrated_pfn < current_block_start) {
-				cpu = get_cpu();
-				lru_add_drain_cpu(cpu);
-				drain_local_pages(cc->zone);
-				put_cpu();
+				lru_add_drain_cpu_zone(cc->zone);
 				/* No more flushing until we migrate again */
 				last_migrated_pfn = 0;
 			}
diff --git a/mm/swap.c b/mm/swap.c
index bf9a79fed62d7..4f965292044ca 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -35,6 +35,7 @@
 #include <linux/uio.h>
 #include <linux/hugetlb.h>
 #include <linux/page_idle.h>
+#include <linux/locallock.h>
 
 #include "internal.h"
 
@@ -44,14 +45,29 @@
 /* How many pages do we try to swap or page in/out together? */
 int page_cluster;
 
-static DEFINE_PER_CPU(struct pagevec, lru_add_pvec);
-static DEFINE_PER_CPU(struct pagevec, lru_rotate_pvecs);
-static DEFINE_PER_CPU(struct pagevec, lru_deactivate_file_pvecs);
-static DEFINE_PER_CPU(struct pagevec, lru_deactivate_pvecs);
-static DEFINE_PER_CPU(struct pagevec, lru_lazyfree_pvecs);
+/* Protecting lru_rotate_pvecs */
+struct lru_rotate_pvecs {
+	struct local_lock lock;
+	struct pagevec pvec;
+};
+static DEFINE_PER_CPU(struct lru_rotate_pvecs, lru_rotate_pvecs) = {
+	.lock = INIT_LOCAL_LOCK(lock),
+};
+
+/* Protecting the following struct pagevec */
+struct lru_pvecs {
+	struct local_lock lock;
+	struct pagevec lru_add_pvec;
+	struct pagevec lru_deactivate_file_pvecs;
+	struct pagevec lru_deactivate_pvecs;
+	struct pagevec lru_lazyfree_pvecs;
 #ifdef CONFIG_SMP
-static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs);
+	struct pagevec activate_page_pvecs;
 #endif
+};
+static DEFINE_PER_CPU(struct lru_pvecs, lru_pvecs) = {
+	.lock = INIT_LOCAL_LOCK(lock),
+};
 
 /*
  * This path almost never happens for VM activity - pages are normally
@@ -254,11 +270,11 @@ void rotate_reclaimable_page(struct page *page)
 		unsigned long flags;
 
 		get_page(page);
-		local_irq_save(flags);
-		pvec = this_cpu_ptr(&lru_rotate_pvecs);
+		local_lock_irqsave(&lru_rotate_pvecs.lock, flags);
+		pvec = this_cpu_ptr(&lru_rotate_pvecs.pvec);
 		if (!pagevec_add(pvec, page) || PageCompound(page))
 			pagevec_move_tail(pvec);
-		local_irq_restore(flags);
+		local_unlock_irqrestore(&lru_rotate_pvecs.lock, flags);
 	}
 }
 
@@ -293,7 +309,7 @@ static void __activate_page(struct page *page, struct lruvec *lruvec,
 #ifdef CONFIG_SMP
 static void activate_page_drain(int cpu)
 {
-	struct pagevec *pvec = &per_cpu(activate_page_pvecs, cpu);
+	struct pagevec *pvec = &per_cpu(lru_pvecs.activate_page_pvecs, cpu);
 
 	if (pagevec_count(pvec))
 		pagevec_lru_move_fn(pvec, __activate_page, NULL);
@@ -301,19 +317,21 @@ static void activate_page_drain(int cpu)
 
 static bool need_activate_page_drain(int cpu)
 {
-	return pagevec_count(&per_cpu(activate_page_pvecs, cpu)) != 0;
+	return pagevec_count(&per_cpu(lru_pvecs.activate_page_pvecs, cpu)) != 0;
 }
 
 void activate_page(struct page *page)
 {
 	page = compound_head(page);
 	if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) {
-		struct pagevec *pvec = &get_cpu_var(activate_page_pvecs);
+		struct pagevec *pvec;
 
+		local_lock(&lru_pvecs.lock);
+		pvec = this_cpu_ptr(&lru_pvecs.activate_page_pvecs);
 		get_page(page);
 		if (!pagevec_add(pvec, page) || PageCompound(page))
 			pagevec_lru_move_fn(pvec, __activate_page, NULL);
-		put_cpu_var(activate_page_pvecs);
+		local_unlock(&lru_pvecs.lock);
 	}
 }
 
@@ -335,9 +353,12 @@ void activate_page(struct page *page)
 
 static void __lru_cache_activate_page(struct page *page)
 {
-	struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
+	struct pagevec *pvec;
 	int i;
 
+	local_lock(&lru_pvecs.lock);
+	pvec = this_cpu_ptr(&lru_pvecs.lru_add_pvec);
+
 	/*
 	 * Search backwards on the optimistic assumption that the page being
 	 * activated has just been added to this pagevec. Note that only
@@ -357,7 +378,7 @@ static void __lru_cache_activate_page(struct page *page)
 		}
 	}
 
-	put_cpu_var(lru_add_pvec);
+	local_unlock(&lru_pvecs.lock);
 }
 
 /*
@@ -404,12 +425,14 @@ EXPORT_SYMBOL(mark_page_accessed);
 
 static void __lru_cache_add(struct page *page)
 {
-	struct pagevec *pvec = &get_cpu_var(lru_add_pvec);
+	struct pagevec *pvec;
 
+	local_lock(&lru_pvecs.lock);
+	pvec = this_cpu_ptr(&lru_pvecs.lru_add_pvec);
 	get_page(page);
 	if (!pagevec_add(pvec, page) || PageCompound(page))
 		__pagevec_lru_add(pvec);
-	put_cpu_var(lru_add_pvec);
+	local_unlock(&lru_pvecs.lock);
 }
 
 /**
@@ -593,30 +616,30 @@ static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec,
  */
 void lru_add_drain_cpu(int cpu)
 {
-	struct pagevec *pvec = &per_cpu(lru_add_pvec, cpu);
+	struct pagevec *pvec = &per_cpu(lru_pvecs.lru_add_pvec, cpu);
 
 	if (pagevec_count(pvec))
 		__pagevec_lru_add(pvec);
 
-	pvec = &per_cpu(lru_rotate_pvecs, cpu);
+	pvec = &per_cpu(lru_rotate_pvecs.pvec, cpu);
 	if (pagevec_count(pvec)) {
 		unsigned long flags;
 
 		/* No harm done if a racing interrupt already did this */
-		local_irq_save(flags);
+		local_lock_irqsave(&lru_rotate_pvecs.lock, flags);
 		pagevec_move_tail(pvec);
-		local_irq_restore(flags);
+		local_unlock_irqrestore(&lru_rotate_pvecs.lock, flags);
 	}
 
-	pvec = &per_cpu(lru_deactivate_file_pvecs, cpu);
+	pvec = &per_cpu(lru_pvecs.lru_deactivate_file_pvecs, cpu);
 	if (pagevec_count(pvec))
 		pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL);
 
-	pvec = &per_cpu(lru_deactivate_pvecs, cpu);
+	pvec = &per_cpu(lru_pvecs.lru_deactivate_pvecs, cpu);
 	if (pagevec_count(pvec))
 		pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
 
-	pvec = &per_cpu(lru_lazyfree_pvecs, cpu);
+	pvec = &per_cpu(lru_pvecs.lru_lazyfree_pvecs, cpu);
 	if (pagevec_count(pvec))
 		pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL);
 
@@ -641,11 +664,14 @@ void deactivate_file_page(struct page *page)
 		return;
 
 	if (likely(get_page_unless_zero(page))) {
-		struct pagevec *pvec = &get_cpu_var(lru_deactivate_file_pvecs);
+		struct pagevec *pvec;
+
+		local_lock(&lru_pvecs.lock);
+		pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate_file_pvecs);
 
 		if (!pagevec_add(pvec, page) || PageCompound(page))
 			pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL);
-		put_cpu_var(lru_deactivate_file_pvecs);
+		local_unlock(&lru_pvecs.lock);
 	}
 }
 
@@ -660,12 +686,14 @@ void deactivate_file_page(struct page *page)
 void deactivate_page(struct page *page)
 {
 	if (PageLRU(page) && PageActive(page) && !PageUnevictable(page)) {
-		struct pagevec *pvec = &get_cpu_var(lru_deactivate_pvecs);
+		struct pagevec *pvec;
 
+		local_lock(&lru_pvecs.lock);
+		pvec = this_cpu_ptr(&lru_pvecs.lru_deactivate_pvecs);
 		get_page(page);
 		if (!pagevec_add(pvec, page) || PageCompound(page))
 			pagevec_lru_move_fn(pvec, lru_deactivate_fn, NULL);
-		put_cpu_var(lru_deactivate_pvecs);
+		local_unlock(&lru_pvecs.lock);
 	}
 }
 
@@ -680,21 +708,33 @@ void mark_page_lazyfree(struct page *page)
 {
 	if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) &&
 	    !PageSwapCache(page) && !PageUnevictable(page)) {
-		struct pagevec *pvec = &get_cpu_var(lru_lazyfree_pvecs);
+		struct pagevec *pvec;
 
+		local_lock(&lru_pvecs.lock);
+		pvec = this_cpu_ptr(&lru_pvecs.lru_lazyfree_pvecs);
 		get_page(page);
 		if (!pagevec_add(pvec, page) || PageCompound(page))
 			pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL);
-		put_cpu_var(lru_lazyfree_pvecs);
+		local_unlock(&lru_pvecs.lock);
 	}
 }
 
 void lru_add_drain(void)
 {
-	lru_add_drain_cpu(get_cpu());
-	put_cpu();
+	local_lock(&lru_pvecs.lock);
+	lru_add_drain_cpu(smp_processor_id());
+	local_unlock(&lru_pvecs.lock);
 }
 
+void lru_add_drain_cpu_zone(struct zone *zone)
+{
+	local_lock(&lru_pvecs.lock);
+	lru_add_drain_cpu(smp_processor_id());
+	drain_local_pages(zone);
+	local_unlock(&lru_pvecs.lock);
+}
+
+
 #ifdef CONFIG_SMP
 
 static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
@@ -743,11 +783,11 @@ void lru_add_drain_all(void)
 	for_each_online_cpu(cpu) {
 		struct work_struct *work = &per_cpu(lru_add_drain_work, cpu);
 
-		if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) ||
-		    pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) ||
-		    pagevec_count(&per_cpu(lru_deactivate_file_pvecs, cpu)) ||
-		    pagevec_count(&per_cpu(lru_deactivate_pvecs, cpu)) ||
-		    pagevec_count(&per_cpu(lru_lazyfree_pvecs, cpu)) ||
+		if (pagevec_count(&per_cpu(lru_pvecs.lru_add_pvec, cpu)) ||
+		    pagevec_count(&per_cpu(lru_rotate_pvecs.pvec, cpu)) ||
+		    pagevec_count(&per_cpu(lru_pvecs.lru_deactivate_file_pvecs, cpu)) ||
+		    pagevec_count(&per_cpu(lru_pvecs.lru_deactivate_pvecs, cpu)) ||
+		    pagevec_count(&per_cpu(lru_pvecs.lru_lazyfree_pvecs, cpu)) ||
 		    need_activate_page_drain(cpu)) {
 			INIT_WORK(work, lru_add_drain_per_cpu);
 			queue_work_on(cpu, mm_percpu_wq, work);
-- 
2.27.0.rc0

Powered by blists - more mailing lists