@@ -86,6 +86,7 @@ static DEFINE_XARRAY(memory_blocks);
* Memory groups, indexed by memory group id (mgid).
*/
static DEFINE_XARRAY_FLAGS(memory_groups, XA_FLAGS_ALLOC);
+#define MEMORY_GROUP_MARK_DYNAMIC XA_MARK_1
static BLOCKING_NOTIFIER_HEAD(memory_chain);
@@ -939,6 +940,8 @@ static int memory_group_register(struct memory_group group)
if (ret) {
kfree(new_group);
return ret;
+ } else if (group.is_dynamic) {
+ xa_set_mark(&memory_groups, mgid, MEMORY_GROUP_MARK_DYNAMIC);
}
return mgid;
}
@@ -1044,3 +1047,30 @@ struct memory_group *memory_group_find_by_id(int mgid)
{
return xa_load(&memory_groups, mgid);
}
+
+/*
+ * This is an internal helper only to be used in core memory hotplug code to
+ * walk all dynamic memory groups excluding a given memory group, either
+ * belonging to a specific node, or belonging to any node.
+ */
+int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func,
+ struct memory_group *excluded, void *arg)
+{
+ struct memory_group *group;
+ unsigned long index;
+ int ret = 0;
+
+ xa_for_each_marked(&memory_groups, index, group,
+ MEMORY_GROUP_MARK_DYNAMIC) {
+ if (group == excluded)
+ continue;
+#ifdef CONFIG_NUMA
+ if (nid != NUMA_NO_NODE && group->nid != nid)
+ continue;
+#endif /* CONFIG_NUMA */
+ ret = func(group, arg);
+ if (ret)
+ break;
+ }
+ return ret;
+}
@@ -146,6 +146,9 @@ extern int memory_group_register_static(int nid, unsigned long max_pages);
extern int memory_group_register_dynamic(int nid, unsigned long unit_pages);
extern int memory_group_unregister(int mgid);
struct memory_group *memory_group_find_by_id(int mgid);
+typedef int (*walk_memory_groups_func_t)(struct memory_group *, void *);
+int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func,
+ struct memory_group *excluded, void *arg);
#endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */
#ifdef CONFIG_MEMORY_HOTPLUG
@@ -752,11 +752,44 @@ static void auto_movable_stats_account_zone(struct auto_movable_stats *stats,
#endif /* CONFIG_CMA */
}
}
+struct auto_movable_group_stats {
+ unsigned long movable_pages;
+ unsigned long req_kernel_early_pages;
+};
-static bool auto_movable_can_online_movable(int nid, unsigned long nr_pages)
+static int auto_movable_stats_account_group(struct memory_group *group,
+ void *arg)
+{
+ const int ratio = READ_ONCE(auto_movable_ratio);
+ struct auto_movable_group_stats *stats = arg;
+ long pages;
+
+ /*
+ * We don't support modifying the config while the auto-movable online
+ * policy is already enabled. Just avoid the division by zero below.
+ */
+ if (!ratio)
+ return 0;
+
+ /*
+ * Calculate how many early kernel pages this group requires to
+ * satisfy the configured zone ratio.
+ */
+ pages = group->present_movable_pages * 100 / ratio;
+ pages -= group->present_kernel_pages;
+
+ if (pages > 0)
+ stats->req_kernel_early_pages += pages;
+ stats->movable_pages += group->present_movable_pages;
+ return 0;
+}
+
+static bool auto_movable_can_online_movable(int nid, struct memory_group *group,
+ unsigned long nr_pages)
{
- struct auto_movable_stats stats = {};
unsigned long kernel_early_pages, movable_pages;
+ struct auto_movable_group_stats group_stats = {};
+ struct auto_movable_stats stats = {};
pg_data_t *pgdat = NODE_DATA(nid);
struct zone *zone;
int i;
@@ -777,6 +810,21 @@ static bool auto_movable_can_online_movable(int nid, unsigned long nr_pages)
kernel_early_pages = stats.kernel_early_pages;
movable_pages = stats.movable_pages;
+ /*
+ * Kernel memory inside dynamic memory group allows for more MOVABLE
+ * memory within the same group. Remove the effect of all but the
+ * current group from the stats.
+ */
+ walk_dynamic_memory_groups(nid, auto_movable_stats_account_group,
+ group, &group_stats);
+ if (kernel_early_pages <= group_stats.req_kernel_early_pages)
+ return false;
+ kernel_early_pages -= group_stats.req_kernel_early_pages;
+ movable_pages -= group_stats.movable_pages;
+
+ if (group && group->is_dynamic)
+ kernel_early_pages += group->present_kernel_pages;
+
/*
* Test if we could online the given number of pages to ZONE_MOVABLE
* and still stay in the configured ratio.
@@ -834,6 +882,10 @@ static struct zone *default_kernel_zone_for_pfn(int nid, unsigned long start_pfn
* with unmovable allocations). While there are corner cases where it might
* still work, it is barely relevant in practice.
*
+ * Exceptions are dynamic memory groups, which allow for more MOVABLE
+ * memory within the same memory group -- because in that case, there is
+ * coordination within the single memory device managed by a single driver.
+ *
* We rely on "present pages" instead of "managed pages", as the latter is
* highly unreliable and dynamic in virtualized environments, and does not
* consider boot time allocations. For example, memory ballooning adjusts the
@@ -899,12 +951,12 @@ static struct zone *auto_movable_zone_for_pfn(int nid,
* nobody interferes, all will be MOVABLE if possible.
*/
nr_pages = max_pages - online_pages;
- if (!auto_movable_can_online_movable(NUMA_NO_NODE, nr_pages))
+ if (!auto_movable_can_online_movable(NUMA_NO_NODE, group, nr_pages))
goto kernel_zone;
#ifdef CONFIG_NUMA
if (auto_movable_numa_aware &&
- !auto_movable_can_online_movable(nid, nr_pages))
+ !auto_movable_can_online_movable(nid, group, nr_pages))
goto kernel_zone;
#endif /* CONFIG_NUMA */
Currently, the "auto-movable" online policy does not allow for hotplugged KERNEL (ZONE_NORMAL) memory to increase the amount of MOVABLE memory we can have, primarily, because there is no coordiantion across memory devices and we don't want to create zone-imbalances accidentially when unplugging memory. However, within a single memory device it's different. Let's allow for KERNEL memory within a dynamic memory group to allow for more MOVABLE within the same memory group. The only thing we have to take care of is that the managing driver avoids zone imbalances by unplugging MOVABLE memory first, otherwise there can be corner cases where unplug of memory could result in (accidential) zone imbalances. virtio-mem is the only user of dynamic memory groups and recently added support for prioritizing unplug of ZONE_MOVABLE over ZONE_NORMAL, so we don't need a new toggle to enable it for dynamic memory groups. We limit this handling to dynamic memory groups, because: * We want to keep the runtime overhead for collecting stats when onlining a single memory block small. We tend to have only a handful of dynamic memory groups, but we can have quite some static memory groups (e.g., 256 DIMMs). * It doesn't make too much sense for static memory groups, as we try onlining all applicable memory blocks either completely to ZONE_MOVABLE or not. In ordinary operation, we won't have a mixture of zones within a static memory group. When adding memory to a dynamic memory group, we'll first online memory to ZONE_MOVABLE as long as early KERNEL memory allows for it. Then, we'll online the next unit(s) to ZONE_NORMAL, until we can online the next unit(s) to ZONE_MOVABLE. For a simple virtio-mem device with a MOVABLE:KERNEL ratio of 3:1, it will result in a layout like: [M][M][M][M][M][M][M][M][N][M][M][M][N][M][M][M]... ^ movable memory due to early kernel memory ^ allows for more movable memory ... ^-----^ ... here ^ allows for more movable memory ... ^-----^ ... here While the created layout is sub-optimal when it comes to contiguous zones, it gives us the maximum flexibility when dynamically growing/shrinking a device; we can grow small VMs really big in small steps, and still shrink reliably to e.g., 1/4 of the maximum VM size in this example, removing full memory blocks along with meta data more reliably. Mark dynamic memory groups in the xarray such that we can efficiently iterate over them when collecting stats. In usual setups, we have one virtio-mem device per NUMA node, and usually only a small number of NUMA nodes. Note: for now, there seems to be no compelling reason to make this behavior configurable. Signed-off-by: David Hildenbrand <david@redhat.com> --- drivers/base/memory.c | 30 +++++++++++++++++++++ include/linux/memory.h | 3 +++ mm/memory_hotplug.c | 60 +++++++++++++++++++++++++++++++++++++++--- 3 files changed, 89 insertions(+), 4 deletions(-)