Currently lock_memory_hotplug()/unlock_memory_hotplug() are used to
protect totalram_pages and zone->managed_pages. Other than the memory
hotplug driver, totalram_pages and zone->managed_pages may be modified
by Xen balloon, virtio_balloon etc at runtime. For those case, memory
hotplug lock is a little too heavy, so introduce a dedicated lock to
protect them.
Now the locking rules for totalram_pages and zone->managed_pages have
been simpilied as:
1) no locking for read accesses because they are unsigned long.
2) no locking for write access at boot time in single-threaded context.
3) serialize write accesses at run time by managed_page_count_lock.
Also adjust zone->managed_pages when dealing with reserved pages.
Signed-off-by: Jiang Liu <jiang.liu@xxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Michel Lespinasse <walken@xxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: linux-mm@xxxxxxxxx (open list:MEMORY MANAGEMENT)
Cc: linux-kernel@xxxxxxxxxxxxxxx (open list)
---
include/linux/mm.h | 6 +-----
include/linux/mmzone.h | 14 ++++++++++----
mm/page_alloc.c | 19 +++++++++++++++++++
3 files changed, 30 insertions(+), 9 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 4d1509b..f9cc7f0 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1299,14 +1299,10 @@ extern void free_initmem(void);
#ifdef CONFIG_HIGHMEM
extern void free_highmem_page(struct page *page);
#endif
+extern void adjust_managed_page_count(struct page *page, long count);
extern unsigned long free_reserved_area(unsigned long start, unsigned long end,
int poison, char *s);
-static inline void adjust_managed_page_count(struct page *page, long count)
-{
- totalram_pages += count;
-}
-
static inline void __free_reserved_page(struct page *page)
{
ClearPageReserved(page);
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index ede2749..bc58fef 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -474,10 +474,16 @@ struct zone {
* frequently read in proximity to zone->lock. It's good to
* give them a chance of being in the same cacheline.
*
- * Write access to present_pages and managed_pages at runtime should
- * be protected by lock_memory_hotplug()/unlock_memory_hotplug().
- * Any reader who can't tolerant drift of present_pages and
- * managed_pages should hold memory hotplug lock to get a stable value.
+ * Write access to present_pages at runtime should be protected by
+ * lock_memory_hotplug()/unlock_memory_hotplug(). Any reader who can't
+ * tolerant drift of present_pages should hold memory hotplug lock to
+ * get a stable value.
+ *
+ * Read access to managed_pages should be safe because it's unsigned
+ * long. Write access to zone->managed_pages and totalram_pages are
+ * protected by managed_page_count_lock at runtime. Basically only
+ * adjust_managed_page_count() should be used instead of directly
+ * touching zone->managed_pages and totalram_pages.
*/
unsigned long spanned_pages;
unsigned long present_pages;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8106aa5..2692931 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -99,6 +99,9 @@ nodemask_t node_states[NR_NODE_STATES] __read_mostly = {
};
EXPORT_SYMBOL(node_states);
+/* Protect totalram_pages and zone->managed_pages */
+static DEFINE_SPINLOCK(managed_page_count_lock);
+
unsigned long totalram_pages __read_mostly;
unsigned long totalreserve_pages __read_mostly;
/*
@@ -5113,6 +5116,22 @@ early_param("movablecore", cmdline_parse_movablecore);
#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
+void adjust_managed_page_count(struct page *page, long count)
+{
+ bool lock = (system_state != SYSTEM_BOOTING);
+
+ /* No need to acquire the lock during boot */
+ if (lock)
+ spin_lock(&managed_page_count_lock);
+
+ page_zone(page)->managed_pages += count;
+ totalram_pages += count;
+
+ if (lock)
+ spin_unlock(&managed_page_count_lock);
+}
+EXPORT_SYMBOL(adjust_managed_page_count);
+
unsigned long free_reserved_area(unsigned long start, unsigned long end,
int poison, char *s)
{
--
1.7.9.5
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>