[PATCH 05/10] mm: Convert p[te|md]_mknonnuma and remaining page table manipulations
From: Mel Gorman
Date: Mon Jan 05 2015 - 05:57:17 EST
With PROT_NONE, the traditional page table manipulation functions are
sufficient.
Signed-off-by: Mel Gorman <mgorman@xxxxxxx>
Acked-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Acked-by: Aneesh Kumar <aneesh.kumar@xxxxxxxxxxxxxxxxxx>
Tested-by: Sasha Levin <sasha.levin@xxxxxxxxxx>
---
include/linux/huge_mm.h | 3 +--
mm/huge_memory.c | 33 +++++++--------------------------
mm/memory.c | 10 ++++++----
mm/mempolicy.c | 2 +-
mm/migrate.c | 2 +-
mm/mprotect.c | 2 +-
mm/pgtable-generic.c | 2 --
7 files changed, 17 insertions(+), 37 deletions(-)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index ad9051b..554bbe3 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -31,8 +31,7 @@ extern int move_huge_pmd(struct vm_area_struct *vma,
unsigned long new_addr, unsigned long old_end,
pmd_t *old_pmd, pmd_t *new_pmd);
extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
- unsigned long addr, pgprot_t newprot,
- int prot_numa);
+ unsigned long addr, pgprot_t newprot);
enum transparent_hugepage_flag {
TRANSPARENT_HUGEPAGE_FLAG,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f81fddf..5618e22 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1366,9 +1366,8 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
goto out;
clear_pmdnuma:
BUG_ON(!PageLocked(page));
- pmd = pmd_mknonnuma(pmd);
+ pmd = pmd_modify(pmd, vma->vm_page_prot);
set_pmd_at(mm, haddr, pmdp, pmd);
- VM_BUG_ON(pmd_protnone(*pmdp));
update_mmu_cache_pmd(vma, addr, pmdp);
unlock_page(page);
out_unlock:
@@ -1503,7 +1502,7 @@ out:
* - HPAGE_PMD_NR is protections changed and TLB flush necessary
*/
int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
- unsigned long addr, pgprot_t newprot, int prot_numa)
+ unsigned long addr, pgprot_t newprot)
{
struct mm_struct *mm = vma->vm_mm;
spinlock_t *ptl;
@@ -1512,29 +1511,11 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
pmd_t entry;
ret = 1;
- if (!prot_numa) {
- entry = pmdp_get_and_clear_notify(mm, addr, pmd);
- if (pmd_protnone(entry))
- entry = pmd_mknonnuma(entry);
- entry = pmd_modify(entry, newprot);
- ret = HPAGE_PMD_NR;
- set_pmd_at(mm, addr, pmd, entry);
- BUG_ON(pmd_write(entry));
- } else {
- struct page *page = pmd_page(*pmd);
-
- /*
- * Do not trap faults against the zero page. The
- * read-only data is likely to be read-cached on the
- * local CPU cache and it is less useful to know about
- * local vs remote hits on the zero page.
- */
- if (!is_huge_zero_page(page) &&
- !pmd_protnone(*pmd)) {
- pmdp_set_numa(mm, addr, pmd);
- ret = HPAGE_PMD_NR;
- }
- }
+ entry = pmdp_get_and_clear_notify(mm, addr, pmd);
+ entry = pmd_modify(entry, newprot);
+ ret = HPAGE_PMD_NR;
+ set_pmd_at(mm, addr, pmd, entry);
+ BUG_ON(pmd_write(entry));
spin_unlock(ptl);
}
diff --git a/mm/memory.c b/mm/memory.c
index 47aa715..debe3f4 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3113,9 +3113,9 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
* validation through pte_unmap_same(). It's of NUMA type but
* the pfn may be screwed if the read is non atomic.
*
- * ptep_modify_prot_start is not called as this is clearing
- * the _PAGE_NUMA bit and it is not really expected that there
- * would be concurrent hardware modifications to the PTE.
+ * We can safely just do a "set_pte_at()", because the old
+ * page table entry is not accessible, so there would be no
+ * concurrent hardware modifications to the PTE.
*/
ptl = pte_lockptr(mm, pmd);
spin_lock(ptl);
@@ -3124,7 +3124,9 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
goto out;
}
- pte = pte_mknonnuma(pte);
+ /* Make it present again */
+ pte = pte_modify(pte, vma->vm_page_prot);
+ pte = pte_mkyoung(pte);
set_pte_at(mm, addr, ptep, pte);
update_mmu_cache(vma, addr, ptep);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 0e0961b..4fcbf12 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -627,7 +627,7 @@ unsigned long change_prot_numa(struct vm_area_struct *vma,
{
int nr_updated;
- nr_updated = change_protection(vma, addr, end, vma->vm_page_prot, 0, 1);
+ nr_updated = change_protection(vma, addr, end, PAGE_NONE, 0, 1);
if (nr_updated)
count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated);
diff --git a/mm/migrate.c b/mm/migrate.c
index e6a5ff1..8491bee 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1878,7 +1878,7 @@ out_fail:
out_dropref:
ptl = pmd_lock(mm, pmd);
if (pmd_same(*pmd, entry)) {
- entry = pmd_mknonnuma(entry);
+ entry = pmd_modify(entry, vma->vm_page_prot);
set_pmd_at(mm, mmun_start, pmd, entry);
update_mmu_cache_pmd(vma, address, &entry);
}
diff --git a/mm/mprotect.c b/mm/mprotect.c
index e93ddac..dc65c0f 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -141,7 +141,7 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
split_huge_page_pmd(vma, addr, pmd);
else {
int nr_ptes = change_huge_pmd(vma, pmd, addr,
- newprot, prot_numa);
+ newprot);
if (nr_ptes) {
if (nr_ptes == HPAGE_PMD_NR) {
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 4b8ad76..c25f94b 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -193,8 +193,6 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
pmd_t *pmdp)
{
pmd_t entry = *pmdp;
- if (pmd_protnone(entry))
- entry = pmd_mknonnuma(entry);
set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(entry));
flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
}
--
2.1.2
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/