If the NUMA balancing isn't used to optimize the page placement among
sockets but only among memory types, the hot pages in the fast memory
node couldn't be migrated (promoted) to anywhere. So it's unnecessary
to scan the pages in the fast memory node via changing their PTE/PMD
mapping to be PROT_NONE. So that the page faults could be avoided
too.
In the test, if only the memory tiering NUMA balancing mode is enabled, the
number of the NUMA balancing hint faults for the DRAM node is reduced to
almost 0 with the patch. While the benchmark score doesn't change
visibly.
Signed-off-by: "Huang, Ying" <ying.huang@xxxxxxxxx>
Suggested-by: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: linux-kernel@xxxxxxxxxxxxxxx
Cc: linux-mm@xxxxxxxxx
---
include/linux/node.h | 5 +++++
mm/huge_memory.c | 30 +++++++++++++++++++++---------
mm/mprotect.c | 13 ++++++++++++-
3 files changed, 38 insertions(+), 10 deletions(-)
diff --git a/include/linux/node.h b/include/linux/node.h
index 8e5a29897936..26e96fcc66af 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -181,4 +181,9 @@ static inline void register_hugetlbfs_with_node(node_registration_func_t reg,
#define to_node(device) container_of(device, struct node, dev)
+static inline bool node_is_toptier(int node)
+{
+ return node_state(node, N_CPU);
+}
+
#endif /* _LINUX_NODE_H_ */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index ec2bb93f7431..43bd44499c4f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -33,6 +33,7 @@
#include <linux/oom.h>
#include <linux/numa.h>
#include <linux/page_owner.h>
+#include <linux/sched/sysctl.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
@@ -1822,17 +1823,28 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
}
#endif
- /*
- * Avoid trapping faults against the zero page. The read-only
- * data is likely to be read-cached on the local CPU and
- * local/remote hits to the zero page are not interesting.
- */
- if (prot_numa && is_huge_zero_pmd(*pmd))
- goto unlock;
+ if (prot_numa) {
+ struct page *page;
+ /*
+ * Avoid trapping faults against the zero page. The read-only
+ * data is likely to be read-cached on the local CPU and
+ * local/remote hits to the zero page are not interesting.
+ */
+ if (is_huge_zero_pmd(*pmd))
+ goto unlock;
- if (prot_numa && pmd_protnone(*pmd))
- goto unlock;
+ if (pmd_protnone(*pmd))
+ goto unlock;
+ page = pmd_page(*pmd);
+ /*
+ * Skip scanning top tier node if normal numa
+ * balancing is disabled
+ */
+ if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) &&
+ node_is_toptier(page_to_nid(page)))
+ goto unlock;
+ }
/*
* In case prot_numa, we are under mmap_read_lock(mm). It's critical
* to not clear pmd intermittently to avoid race with MADV_DONTNEED
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 56c02beb6041..b90526237cf4 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -29,6 +29,7 @@
#include <linux/uaccess.h>
#include <linux/mm_inline.h>
#include <linux/pgtable.h>
+#include <linux/sched/sysctl.h>
#include <asm/cacheflush.h>
#include <asm/mmu_context.h>
#include <asm/tlbflush.h>
@@ -83,6 +84,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
*/
if (prot_numa) {
struct page *page;
+ int nid;
/* Avoid TLB flush if possible */
if (pte_protnone(oldpte))
@@ -109,7 +111,16 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
* Don't mess with PTEs if page is already on the node
* a single-threaded process is running on.
*/
- if (target_node == page_to_nid(page))
+ nid = page_to_nid(page);
+ if (target_node == nid)
+ continue;
+
+ /*
+ * Skip scanning top tier node if normal numa
+ * balancing is disabled
+ */
+ if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) &&
+ node_is_toptier(nid))
continue;
}
--
2.29.2
