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 also be
modified at runtime by other drivers, such as Xen balloon,
virtio_balloon etc. For those cases, memory hotplug lock is a little
too heavy, so introduce a dedicated lock to protect totalram_pages
and zone->managed_pages.
Now we have a simplified locking rules totalram_pages and
zone->managed_pages as:
1) no locking for read accesses because they are unsigned long.
2) no locking for write accesses at boot time in single-threaded context.
3) serialize write accesses at runtime by acquiring the dedicated
managed_page_count_lock.
Also adjust zone->managed_pages when freeing reserved pages into the
buddy system, to keep totalram_pages and zone->managed_pages in
consistence.
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 | 12 ++++++++++++
3 files changed, 24 insertions(+), 8 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index a56bcaa..bfe3686 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1309,6 +1309,7 @@ extern void free_initmem(void);
*/
extern unsigned long free_reserved_area(void *start, void *end,
int poison, char *s);
+
#ifdef CONFIG_HIGHMEM
/*
* Free a highmem page into the buddy system, adjusting totalhigh_pages
@@ -1317,10 +1318,7 @@ extern unsigned long free_reserved_area(void *start, void *end,
extern void free_highmem_page(struct page *page);
#endif
-static inline void adjust_managed_page_count(struct page *page, long count)
-{
- totalram_pages += count;
-}
+extern void adjust_managed_page_count(struct page *page, long count);
/* Free the reserved page into the buddy system, so it gets managed. */
static inline void __free_reserved_page(struct page *page)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 131989a..178f166 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. Idealy 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 9b50e6a..924c099 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -103,6 +103,9 @@ 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;
/*
@@ -5231,6 +5234,15 @@ early_param("movablecore", cmdline_parse_movablecore);
#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
+void adjust_managed_page_count(struct page *page, long count)
+{
+ spin_lock(&managed_page_count_lock);
+ page_zone(page)->managed_pages += count;
+ totalram_pages += count;
+ spin_unlock(&managed_page_count_lock);
+}
+EXPORT_SYMBOL(adjust_managed_page_count);
+
unsigned long free_reserved_area(void *start, void *end, int poison, char *s)
{
void *pos;
--
1.8.1.2
--
To unsubscribe from this list: send the line "unsubscribe linux-arch" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
