memory tiering: skip to scan fast memory

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.

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: "Huang, Ying" <[email protected]>
Suggested-by: Dave Hansen <[email protected]>
Tested-by: Baolin Wang <[email protected]>
Reviewed-by: Baolin Wang <[email protected]>
Acked-by: Johannes Weiner <[email protected]>
Reviewed-by: Oscar Salvador <[email protected]>
Reviewed-by: Yang Shi <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Rik van Riel <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Zi Yan <[email protected]>
Cc: Wei Xu <[email protected]>
Cc: Shakeel Butt <[email protected]>
Cc: zhongjiang-ali <[email protected]>
Cc: Feng Tang <[email protected]>
Cc: Randy Dunlap <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

2 files changed, 33 insertions, 10 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 9c52b3661f71..88c83c84325c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -34,6 +34,7 @@
 #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>
@@ -1766,17 +1767,28 @@ 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 2887644fd150..b69ce7a7b2b7 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;
 			}