| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20210422111441.24318-3-mgorman@techsingularity.net>
Date: Thu, 22 Apr 2021 12:14:34 +0100
From: Mel Gorman <mgorman@...hsingularity.net>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: Chuck Lever <chuck.lever@...cle.com>,
Jesper Dangaard Brouer <brouer@...hat.com>,
Thomas Gleixner <tglx@...utronix.de>,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...nel.org>,
Michal Hocko <mhocko@...nel.org>,
Vlastimil Babka <vbabka@...e.cz>,
Linux-MM <linux-mm@...ck.org>,
Linux-RT-Users <linux-rt-users@...r.kernel.org>,
LKML <linux-kernel@...r.kernel.org>,
Mel Gorman <mgorman@...hsingularity.net>
Subject: [PATCH 2/9] mm/page_alloc: Convert per-cpu list protection to local_lock
There is a lack of clarity of what exactly local_irq_save/local_irq_restore
protects in page_alloc.c . It conflates the protection of per-cpu page
allocation structures with per-cpu vmstat deltas.
This patch protects the PCP structure using local_lock which for most
configurations is identical to IRQ enabling/disabling. The scope of the
lock is still wider than it should be but this is decreased later.
It is possible for the local_lock to be embedded safely within struct
per_cpu_pages but it adds complexity to free_unref_page_list.
[lkp@...el.com: Make pagesets static]
Signed-off-by: Mel Gorman <mgorman@...hsingularity.net>
---
include/linux/mmzone.h | 2 ++
mm/page_alloc.c | 50 +++++++++++++++++++++++++++++-------------
2 files changed, 37 insertions(+), 15 deletions(-)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index a4393ac27336..106da8fbc72a 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -20,6 +20,7 @@
#include <linux/atomic.h>
#include <linux/mm_types.h>
#include <linux/page-flags.h>
+#include <linux/local_lock.h>
#include <asm/page.h>
/* Free memory management - zoned buddy allocator. */
@@ -337,6 +338,7 @@ enum zone_watermarks {
#define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost)
#define wmark_pages(z, i) (z->_watermark[i] + z->watermark_boost)
+/* Fields and list protected by pagesets local_lock in page_alloc.c */
struct per_cpu_pages {
int count; /* number of pages in the list */
int high; /* high watermark, emptying needed */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 2d6283cab22d..4e92d43c25f6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -112,6 +112,13 @@ typedef int __bitwise fpi_t;
static DEFINE_MUTEX(pcp_batch_high_lock);
#define MIN_PERCPU_PAGELIST_FRACTION (8)
+struct pagesets {
+ local_lock_t lock;
+};
+static DEFINE_PER_CPU(struct pagesets, pagesets) = {
+ .lock = INIT_LOCAL_LOCK(lock),
+};
+
#ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
DEFINE_PER_CPU(int, numa_node);
EXPORT_PER_CPU_SYMBOL(numa_node);
@@ -1421,6 +1428,10 @@ static void free_pcppages_bulk(struct zone *zone, int count,
} while (--count && --batch_free && !list_empty(list));
}
+ /*
+ * local_lock_irq held so equivalent to spin_lock_irqsave for
+ * both PREEMPT_RT and non-PREEMPT_RT configurations.
+ */
spin_lock(&zone->lock);
isolated_pageblocks = has_isolate_pageblock(zone);
@@ -1541,6 +1552,11 @@ static void __free_pages_ok(struct page *page, unsigned int order,
return;
migratetype = get_pfnblock_migratetype(page, pfn);
+
+ /*
+ * TODO FIX: Disable IRQs before acquiring IRQ-safe zone->lock
+ * and protect vmstat updates.
+ */
local_irq_save(flags);
__count_vm_events(PGFREE, 1 << order);
free_one_page(page_zone(page), page, pfn, order, migratetype,
@@ -2910,6 +2926,10 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
{
int i, allocated = 0;
+ /*
+ * local_lock_irq held so equivalent to spin_lock_irqsave for
+ * both PREEMPT_RT and non-PREEMPT_RT configurations.
+ */
spin_lock(&zone->lock);
for (i = 0; i < count; ++i) {
struct page *page = __rmqueue(zone, order, migratetype,
@@ -2962,12 +2982,12 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
unsigned long flags;
int to_drain, batch;
- local_irq_save(flags);
+ local_lock_irqsave(&pagesets.lock, flags);
batch = READ_ONCE(pcp->batch);
to_drain = min(pcp->count, batch);
if (to_drain > 0)
free_pcppages_bulk(zone, to_drain, pcp);
- local_irq_restore(flags);
+ local_unlock_irqrestore(&pagesets.lock, flags);
}
#endif
@@ -2983,13 +3003,13 @@ static void drain_pages_zone(unsigned int cpu, struct zone *zone)
unsigned long flags;
struct per_cpu_pages *pcp;
- local_irq_save(flags);
+ local_lock_irqsave(&pagesets.lock, flags);
pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
if (pcp->count)
free_pcppages_bulk(zone, pcp->count, pcp);
- local_irq_restore(flags);
+ local_unlock_irqrestore(&pagesets.lock, flags);
}
/*
@@ -3252,9 +3272,9 @@ void free_unref_page(struct page *page)
if (!free_unref_page_prepare(page, pfn))
return;
- local_irq_save(flags);
+ local_lock_irqsave(&pagesets.lock, flags);
free_unref_page_commit(page, pfn);
- local_irq_restore(flags);
+ local_unlock_irqrestore(&pagesets.lock, flags);
}
/*
@@ -3274,7 +3294,7 @@ void free_unref_page_list(struct list_head *list)
set_page_private(page, pfn);
}
- local_irq_save(flags);
+ local_lock_irqsave(&pagesets.lock, flags);
list_for_each_entry_safe(page, next, list, lru) {
unsigned long pfn = page_private(page);
@@ -3287,12 +3307,12 @@ void free_unref_page_list(struct list_head *list)
* a large list of pages to free.
*/
if (++batch_count == SWAP_CLUSTER_MAX) {
- local_irq_restore(flags);
+ local_unlock_irqrestore(&pagesets.lock, flags);
batch_count = 0;
- local_irq_save(flags);
+ local_lock_irqsave(&pagesets.lock, flags);
}
}
- local_irq_restore(flags);
+ local_unlock_irqrestore(&pagesets.lock, flags);
}
/*
@@ -3449,7 +3469,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone,
struct page *page;
unsigned long flags;
- local_irq_save(flags);
+ local_lock_irqsave(&pagesets.lock, flags);
pcp = this_cpu_ptr(zone->per_cpu_pageset);
list = &pcp->lists[migratetype];
page = __rmqueue_pcplist(zone, migratetype, alloc_flags, pcp, list);
@@ -3457,7 +3477,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone,
__count_zid_vm_events(PGALLOC, page_zonenum(page), 1);
zone_statistics(preferred_zone, zone);
}
- local_irq_restore(flags);
+ local_unlock_irqrestore(&pagesets.lock, flags);
return page;
}
@@ -5052,7 +5072,7 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
goto failed;
/* Attempt the batch allocation */
- local_irq_save(flags);
+ local_lock_irqsave(&pagesets.lock, flags);
pcp = this_cpu_ptr(zone->per_cpu_pageset);
pcp_list = &pcp->lists[ac.migratetype];
@@ -5090,12 +5110,12 @@ unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
nr_populated++;
}
- local_irq_restore(flags);
+ local_unlock_irqrestore(&pagesets.lock, flags);
return nr_populated;
failed_irq:
- local_irq_restore(flags);
+ local_unlock_irqrestore(&pagesets.lock, flags);
failed:
page = __alloc_pages(gfp, 0, preferred_nid, nodemask);
--
2.26.2
Powered by blists - more mailing lists