After page A on source node is migrated to page B on target node, hinting
fault is recorded on the target node for B. On the source node there is
another record for A, since a two-stage filter is used when migrating pages.
Page A is no longer used after migration, so we have to erase its record.
Signed-off-by: Hillf Danton <dhillf@xxxxxxxxx>
---
--- a/include/linux/sched.h Sat Sep 14 16:57:32 2013
+++ b/include/linux/sched.h Sat Sep 14 17:22:20 2013
@@ -1440,12 +1440,13 @@ struct task_struct {
#define TNF_NO_GROUP 0x02
#ifdef CONFIG_NUMA_BALANCING
-extern void task_numa_fault(int last_node, int node, int pages, int flags);
+extern void task_numa_fault(int last_cpupid, int src_node,
+ int dst_node, int pages, int flags);
extern pid_t task_numa_group_id(struct task_struct *p);
extern void set_numabalancing_state(bool enabled);
#else
-static inline void task_numa_fault(int last_node, int node, int pages,
- int flags)
+static inline void task_numa_fault(int last_cpupid, int src_node,
+ int dst_node, int pages, int flags)
{
}
static inline pid_t task_numa_group_id(struct task_struct *p)
--- a/kernel/sched/fair.c Wed Sep 11 18:33:00 2013
+++ b/kernel/sched/fair.c Sat Sep 14 17:57:16 2013
@@ -1493,7 +1493,8 @@ void task_numa_free(struct task_struct *
/*
* Got a PROT_NONE fault for a page on @node.
*/
-void task_numa_fault(int last_cpupid, int node, int pages, int flags)
+void task_numa_fault(int last_cpupid, int src_node, int dst_node,
+ int pages, int flags)
{
struct task_struct *p = current;
bool migrated = flags & TNF_MIGRATED;
@@ -1559,7 +1560,15 @@ void task_numa_fault(int last_cpupid, in
if (migrated)
p->numa_pages_migrated += pages;
- p->numa_faults_buffer[task_faults_idx(node, priv)] += pages;
+ p->numa_faults_buffer[task_faults_idx(dst_node, priv)] += pages;
+
+ if (migrated) {
+ /* extract numa-hint faults from src node */
+ int idx = task_faults_idx(src_node, priv);
+
+ if (p->numa_faults[idx] >= pages)
+ p->numa_faults[idx] -= pages;
+ }
}
static void reset_ptenuma_scan(struct task_struct *p)
--- a/mm/huge_memory.c Sat Sep 14 16:54:28 2013
+++ b/mm/huge_memory.c Sat Sep 14 17:46:54 2013
@@ -1295,6 +1295,7 @@ int do_huge_pmd_numa_page(struct mm_stru
unsigned long haddr = addr & HPAGE_PMD_MASK;
int page_nid = -1, this_nid = numa_node_id();
int target_nid, last_cpupid = -1;
+ int src_nid;
bool page_locked;
bool migrated = false;
int flags = 0;
@@ -1306,6 +1307,7 @@ int do_huge_pmd_numa_page(struct mm_stru
page = pmd_page(pmd);
BUG_ON(is_huge_zero_page(page));
page_nid = page_to_nid(page);
+ src_nid = page_nid;
last_cpupid = page_cpupid_last(page);
count_vm_numa_event(NUMA_HINT_FAULTS);
if (page_nid == this_nid)
@@ -1388,7 +1390,7 @@ out:
page_unlock_anon_vma_read(anon_vma);
if (page_nid != -1)
- task_numa_fault(last_cpupid, page_nid, HPAGE_PMD_NR, flags);
+ task_numa_fault(last_cpupid, src_nid, page_nid, HPAGE_PMD_NR, flags);
return 0;
}
--- a/mm/memory.c Sat Sep 14 16:54:52 2013
+++ b/mm/memory.c Sat Sep 14 17:52:02 2013
@@ -3555,6 +3555,7 @@ int do_numa_page(struct mm_struct *mm, s
struct page *page = NULL;
spinlock_t *ptl;
int page_nid = -1;
+ int src_nid;
int last_cpupid;
int target_nid;
bool migrated = false;
@@ -3597,6 +3598,7 @@ int do_numa_page(struct mm_struct *mm, s
last_cpupid = page_cpupid_last(page);
page_nid = page_to_nid(page);
+ src_nid = page_nid;
target_nid = numa_migrate_prep(page, vma, addr, page_nid);
pte_unmap_unlock(ptep, ptl);
if (target_nid == -1) {
@@ -3613,7 +3615,7 @@ int do_numa_page(struct mm_struct *mm, s
out:
if (page_nid != -1)
- task_numa_fault(last_cpupid, page_nid, 1, flags);
+ task_numa_fault(last_cpupid, src_nid, page_nid, 1, flags);
return 0;
}
@@ -3652,6 +3654,7 @@ static int do_pmd_numa_page(struct mm_st
pte_t pteval = *pte;
struct page *page;
int page_nid = -1;
+ int src_nid;
int target_nid;
bool migrated = false;
int flags = 0;
@@ -3684,6 +3687,7 @@ static int do_pmd_numa_page(struct mm_st
last_cpupid = page_cpupid_last(page);
page_nid = page_to_nid(page);
+ src_nid = page_nid;
target_nid = numa_migrate_prep(page, vma, addr, page_nid);
pte_unmap_unlock(pte, ptl);
if (target_nid != -1) {
@@ -3697,7 +3701,7 @@ static int do_pmd_numa_page(struct mm_st
}
if (page_nid != -1)
- task_numa_fault(last_cpupid, page_nid, 1, flags);
+ task_numa_fault(last_cpupid, src_nid, page_nid, 1, flags);
pte = pte_offset_map_lock(mm, pmdp, addr, &ptl);
}
--?韬{.n?壏?檩jg??a旃??迻)钋?韰骅w+h櫒璀?ｙ/i?⒏?婃⒎?湼Щ 烚m?? ?)钋?痂燐^櫒?觥櫒ザ?v夗﨣趓O璁?f?i?⒏?