mm: mempolicy: Use _PAGE_NUMA to migrate pages
Note: Based on "mm/mpol: Use special PROT_NONE to migrate pages" but
sufficiently different that the signed-off-bys were dropped
Combine our previous _PAGE_NUMA, mpol_misplaced and migrate_misplaced_page()
pieces into an effective migrate on fault scheme.
Note that (on x86) we rely on PROT_NONE pages being !present and avoid
the TLB flush from try_to_unmap(TTU_MIGRATION). This greatly improves the
page-migration performance.
Based-on-work-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mel Gorman <mgorman@suse.de>
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f5f3763..5723b55 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -18,6 +18,7 @@
#include <linux/freezer.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
+#include <linux/migrate.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
#include "internal.h"
@@ -1019,17 +1020,39 @@
}
/* NUMA hinting page fault entry point for trans huge pmds */
-int do_huge_pmd_numa_page(struct mm_struct *mm, unsigned long addr,
- pmd_t pmd, pmd_t *pmdp)
+int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
+ unsigned long addr, pmd_t pmd, pmd_t *pmdp)
{
- struct page *page;
+ struct page *page = NULL;
unsigned long haddr = addr & HPAGE_PMD_MASK;
+ int target_nid;
spin_lock(&mm->page_table_lock);
if (unlikely(!pmd_same(pmd, *pmdp)))
goto out_unlock;
page = pmd_page(pmd);
+ get_page(page);
+ spin_unlock(&mm->page_table_lock);
+
+ target_nid = mpol_misplaced(page, vma, haddr);
+ if (target_nid == -1)
+ goto clear_pmdnuma;
+
+ /*
+ * Due to lacking code to migrate thp pages, we'll split
+ * (which preserves the special PROT_NONE) and re-take the
+ * fault on the normal pages.
+ */
+ split_huge_page(page);
+ put_page(page);
+ return 0;
+
+clear_pmdnuma:
+ spin_lock(&mm->page_table_lock);
+ if (unlikely(!pmd_same(pmd, *pmdp)))
+ goto out_unlock;
+
pmd = pmd_mknonnuma(pmd);
set_pmd_at(mm, haddr, pmdp, pmd);
VM_BUG_ON(pmd_numa(*pmdp));
@@ -1037,6 +1060,8 @@
out_unlock:
spin_unlock(&mm->page_table_lock);
+ if (page)
+ put_page(page);
return 0;
}
diff --git a/mm/memory.c b/mm/memory.c
index e30616f..d525426 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -57,6 +57,7 @@
#include <linux/swapops.h>
#include <linux/elf.h>
#include <linux/gfp.h>
+#include <linux/migrate.h>
#include <asm/io.h>
#include <asm/pgalloc.h>
@@ -3451,8 +3452,9 @@
int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long addr, pte_t pte, pte_t *ptep, pmd_t *pmd)
{
- struct page *page;
+ struct page *page = NULL;
spinlock_t *ptl;
+ int current_nid, target_nid;
/*
* The "pte" at this point cannot be used safely without
@@ -3465,8 +3467,11 @@
*/
ptl = pte_lockptr(mm, pmd);
spin_lock(ptl);
- if (unlikely(!pte_same(*ptep, pte)))
- goto out_unlock;
+ if (unlikely(!pte_same(*ptep, pte))) {
+ pte_unmap_unlock(ptep, ptl);
+ goto out;
+ }
+
pte = pte_mknonnuma(pte);
set_pte_at(mm, addr, ptep, pte);
update_mmu_cache(vma, addr, ptep);
@@ -3477,8 +3482,25 @@
return 0;
}
-out_unlock:
+ get_page(page);
+ current_nid = page_to_nid(page);
+ target_nid = mpol_misplaced(page, vma, addr);
pte_unmap_unlock(ptep, ptl);
+ if (target_nid == -1) {
+ /*
+ * Account for the fault against the current node if it not
+ * being replaced regardless of where the page is located.
+ */
+ current_nid = numa_node_id();
+ put_page(page);
+ goto out;
+ }
+
+ /* Migrate to the requested node */
+ if (migrate_misplaced_page(page, target_nid))
+ current_nid = target_nid;
+
+out:
return 0;
}
@@ -3655,7 +3677,7 @@
barrier();
if (pmd_trans_huge(orig_pmd)) {
if (pmd_numa(*pmd))
- return do_huge_pmd_numa_page(mm, address,
+ return do_huge_pmd_numa_page(mm, vma, address,
orig_pmd, pmd);
if ((flags & FAULT_FLAG_WRITE) && !pmd_write(orig_pmd)) {