The patch titled
Subject: mm: thp: check pmd migration entry in common path
has been added to the -mm tree. Its filename is
mm-thp-check-pmd-migration-entry-in-common-path.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-thp-check-pmd-migration-entry-in-common-path.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-thp-check-pmd-migration-entry-in-common-path.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Zi Yan <zi.yan@xxxxxxxxxxxxxx>
Subject: mm: thp: check pmd migration entry in common path
If one of callers of page migration starts to handle thp, memory
management code start to see pmd migration entry, so we need to prepare
for it before enabling. This patch changes various code point which
checks the status of given pmds in order to prevent race between thp
migration and the pmd-related works.
Signed-off-by: Zi Yan <zi.yan@xxxxxxxxxxxxxx>
Cc: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: Anshuman Khandual <khandual@xxxxxxxxxxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxx>
Cc: David Nellans <dnellans@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/proc/task_mmu.c | 32 ++++++++++-----
include/asm-generic/pgtable.h | 18 ++++++++
include/linux/huge_mm.h | 14 +++++-
mm/gup.c | 22 +++++++++-
mm/huge_memory.c | 65 +++++++++++++++++++++++++++++---
mm/memcontrol.c | 5 ++
mm/memory.c | 12 ++++-
mm/mprotect.c | 4 -
mm/mremap.c | 2
9 files changed, 147 insertions(+), 27 deletions(-)
diff -puN fs/proc/task_mmu.c~mm-thp-check-pmd-migration-entry-in-common-path fs/proc/task_mmu.c
--- a/fs/proc/task_mmu.c~mm-thp-check-pmd-migration-entry-in-common-path
+++ a/fs/proc/task_mmu.c
@@ -596,7 +596,8 @@ static int smaps_pte_range(pmd_t *pmd, u
ptl = pmd_trans_huge_lock(pmd, vma);
if (ptl) {
- smaps_pmd_entry(pmd, addr, walk);
+ if (pmd_present(*pmd))
+ smaps_pmd_entry(pmd, addr, walk);
spin_unlock(ptl);
return 0;
}
@@ -938,6 +939,9 @@ static int clear_refs_pte_range(pmd_t *p
goto out;
}
+ if (!pmd_present(*pmd))
+ goto out;
+
page = pmd_page(*pmd);
/* Clear accessed and referenced bits. */
@@ -1217,27 +1221,33 @@ static int pagemap_pmd_range(pmd_t *pmdp
if (ptl) {
u64 flags = 0, frame = 0;
pmd_t pmd = *pmdp;
+ struct page *page = NULL;
if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(pmd))
flags |= PM_SOFT_DIRTY;
- /*
- * Currently pmd for thp is always present because thp
- * can not be swapped-out, migrated, or HWPOISONed
- * (split in such cases instead.)
- * This if-check is just to prepare for future implementation.
- */
if (pmd_present(pmd)) {
- struct page *page = pmd_page(pmd);
-
- if (page_mapcount(page) == 1)
- flags |= PM_MMAP_EXCLUSIVE;
+ page = pmd_page(pmd);
flags |= PM_PRESENT;
if (pm->show_pfn)
frame = pmd_pfn(pmd) +
((addr & ~PMD_MASK) >> PAGE_SHIFT);
}
+#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
+ else if (is_swap_pmd(pmd)) {
+ swp_entry_t entry = pmd_to_swp_entry(pmd);
+
+ frame = swp_type(entry) |
+ (swp_offset(entry) << MAX_SWAPFILES_SHIFT);
+ flags |= PM_SWAP;
+ VM_BUG_ON(!is_pmd_migration_entry(pmd));
+ page = migration_entry_to_page(entry);
+ }
+#endif
+
+ if (page && page_mapcount(page) == 1)
+ flags |= PM_MMAP_EXCLUSIVE;
for (; addr != end; addr += PAGE_SIZE) {
pagemap_entry_t pme = make_pme(frame, flags);
diff -puN include/asm-generic/pgtable.h~mm-thp-check-pmd-migration-entry-in-common-path include/asm-generic/pgtable.h
--- a/include/asm-generic/pgtable.h~mm-thp-check-pmd-migration-entry-in-common-path
+++ a/include/asm-generic/pgtable.h
@@ -834,7 +834,23 @@ static inline int pmd_none_or_trans_huge
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
barrier();
#endif
- if (pmd_none(pmdval) || pmd_trans_huge(pmdval))
+ /*
+ * !pmd_present() checks for pmd migration entries
+ *
+ * The complete check uses is_pmd_migration_entry() in linux/swapops.h
+ * But using that requires moving current function and pmd_trans_unstable()
+ * to linux/swapops.h to resovle dependency, which is too much code move.
+ *
+ * !pmd_present() is equivalent to is_pmd_migration_entry() currently,
+ * because !pmd_present() pages can only be under migration not swapped
+ * out.
+ *
+ * pmd_none() is preseved for future condition checks on pmd migration
+ * entries and not confusing with this function name, although it is
+ * redundant with !pmd_present().
+ */
+ if (pmd_none(pmdval) || pmd_trans_huge(pmdval) ||
+ (IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION) && !pmd_present(pmdval)))
return 1;
if (unlikely(pmd_bad(pmdval))) {
pmd_clear_bad(pmd);
diff -puN include/linux/huge_mm.h~mm-thp-check-pmd-migration-entry-in-common-path include/linux/huge_mm.h
--- a/include/linux/huge_mm.h~mm-thp-check-pmd-migration-entry-in-common-path
+++ a/include/linux/huge_mm.h
@@ -147,7 +147,7 @@ void __split_huge_pmd(struct vm_area_str
#define split_huge_pmd(__vma, __pmd, __address) \
do { \
pmd_t *____pmd = (__pmd); \
- if (pmd_trans_huge(*____pmd) \
+ if (is_swap_pmd(*____pmd) || pmd_trans_huge(*____pmd) \
|| pmd_devmap(*____pmd)) \
__split_huge_pmd(__vma, __pmd, __address, \
false, NULL); \
@@ -178,12 +178,18 @@ extern spinlock_t *__pmd_trans_huge_lock
struct vm_area_struct *vma);
extern spinlock_t *__pud_trans_huge_lock(pud_t *pud,
struct vm_area_struct *vma);
+
+static inline int is_swap_pmd(pmd_t pmd)
+{
+ return !pmd_none(pmd) && !pmd_present(pmd);
+}
+
/* mmap_sem must be held on entry */
static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
struct vm_area_struct *vma)
{
VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma);
- if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd))
+ if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd))
return __pmd_trans_huge_lock(pmd, vma);
else
return NULL;
@@ -299,6 +305,10 @@ static inline void vma_adjust_trans_huge
long adjust_next)
{
}
+static inline int is_swap_pmd(pmd_t pmd)
+{
+ return 0;
+}
static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
struct vm_area_struct *vma)
{
diff -puN mm/gup.c~mm-thp-check-pmd-migration-entry-in-common-path mm/gup.c
--- a/mm/gup.c~mm-thp-check-pmd-migration-entry-in-common-path
+++ a/mm/gup.c
@@ -234,6 +234,16 @@ static struct page *follow_pmd_mask(stru
return page;
return no_page_table(vma, flags);
}
+retry:
+ if (!pmd_present(*pmd)) {
+ if (likely(!(flags & FOLL_MIGRATION)))
+ return no_page_table(vma, flags);
+ VM_BUG_ON(thp_migration_supported() &&
+ !is_pmd_migration_entry(*pmd));
+ if (is_pmd_migration_entry(*pmd))
+ pmd_migration_entry_wait(mm, pmd);
+ goto retry;
+ }
if (pmd_devmap(*pmd)) {
ptl = pmd_lock(mm, pmd);
page = follow_devmap_pmd(vma, address, pmd, flags);
@@ -247,7 +257,15 @@ static struct page *follow_pmd_mask(stru
if ((flags & FOLL_NUMA) && pmd_protnone(*pmd))
return no_page_table(vma, flags);
+retry_locked:
ptl = pmd_lock(mm, pmd);
+ if (unlikely(!pmd_present(*pmd))) {
+ spin_unlock(ptl);
+ if (likely(!(flags & FOLL_MIGRATION)))
+ return no_page_table(vma, flags);
+ pmd_migration_entry_wait(mm, pmd);
+ goto retry_locked;
+ }
if (unlikely(!pmd_trans_huge(*pmd))) {
spin_unlock(ptl);
return follow_page_pte(vma, address, pmd, flags);
@@ -424,7 +442,7 @@ static int get_gate_page(struct mm_struc
pud = pud_offset(p4d, address);
BUG_ON(pud_none(*pud));
pmd = pmd_offset(pud, address);
- if (pmd_none(*pmd))
+ if (!pmd_present(*pmd))
return -EFAULT;
VM_BUG_ON(pmd_trans_huge(*pmd));
pte = pte_offset_map(pmd, address);
@@ -1534,7 +1552,7 @@ static int gup_pmd_range(pud_t pud, unsi
pmd_t pmd = READ_ONCE(*pmdp);
next = pmd_addr_end(addr, end);
- if (pmd_none(pmd))
+ if (!pmd_present(pmd))
return 0;
if (unlikely(pmd_trans_huge(pmd) || pmd_huge(pmd))) {
diff -puN mm/huge_memory.c~mm-thp-check-pmd-migration-entry-in-common-path mm/huge_memory.c
--- a/mm/huge_memory.c~mm-thp-check-pmd-migration-entry-in-common-path
+++ a/mm/huge_memory.c
@@ -914,6 +914,23 @@ int copy_huge_pmd(struct mm_struct *dst_
ret = -EAGAIN;
pmd = *src_pmd;
+
+#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
+ if (unlikely(is_swap_pmd(pmd))) {
+ swp_entry_t entry = pmd_to_swp_entry(pmd);
+
+ VM_BUG_ON(!is_pmd_migration_entry(pmd));
+ if (is_write_migration_entry(entry)) {
+ make_migration_entry_read(&entry);
+ pmd = swp_entry_to_pmd(entry);
+ set_pmd_at(src_mm, addr, src_pmd, pmd);
+ }
+ set_pmd_at(dst_mm, addr, dst_pmd, pmd);
+ ret = 0;
+ goto out_unlock;
+ }
+#endif
+
if (unlikely(!pmd_trans_huge(pmd))) {
pte_free(dst_mm, pgtable);
goto out_unlock;
@@ -1556,6 +1573,12 @@ bool madvise_free_huge_pmd(struct mmu_ga
if (is_huge_zero_pmd(orig_pmd))
goto out;
+ if (unlikely(!pmd_present(orig_pmd))) {
+ VM_BUG_ON(thp_migration_supported() &&
+ !is_pmd_migration_entry(orig_pmd));
+ goto out;
+ }
+
page = pmd_page(orig_pmd);
/*
* If other processes are mapping this page, we couldn't discard
@@ -1767,6 +1790,25 @@ int change_huge_pmd(struct vm_area_struc
preserve_write = prot_numa && pmd_write(*pmd);
ret = 1;
+#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
+ if (is_swap_pmd(*pmd)) {
+ swp_entry_t entry = pmd_to_swp_entry(*pmd);
+
+ VM_BUG_ON(!is_pmd_migration_entry(*pmd));
+ if (is_write_migration_entry(entry)) {
+ pmd_t newpmd;
+ /*
+ * A protection check is difficult so
+ * just be safe and disable write
+ */
+ make_migration_entry_read(&entry);
+ newpmd = swp_entry_to_pmd(entry);
+ set_pmd_at(mm, addr, pmd, newpmd);
+ }
+ goto unlock;
+ }
+#endif
+
/*
* Avoid trapping faults against the zero page. The read-only
* data is likely to be read-cached on the local CPU and
@@ -1832,7 +1874,8 @@ spinlock_t *__pmd_trans_huge_lock(pmd_t
{
spinlock_t *ptl;
ptl = pmd_lock(vma->vm_mm, pmd);
- if (likely(pmd_trans_huge(*pmd) || pmd_devmap(*pmd)))
+ if (likely(is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) ||
+ pmd_devmap(*pmd)))
return ptl;
spin_unlock(ptl);
return NULL;
@@ -1950,14 +1993,15 @@ static void __split_huge_pmd_locked(stru
struct page *page;
pgtable_t pgtable;
pmd_t _pmd;
- bool young, write, dirty, soft_dirty;
+ bool young, write, dirty, soft_dirty, pmd_migration = false;
unsigned long addr;
int i;
VM_BUG_ON(haddr & ~HPAGE_PMD_MASK);
VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PMD_SIZE, vma);
- VM_BUG_ON(!pmd_trans_huge(*pmd) && !pmd_devmap(*pmd));
+ VM_BUG_ON(!is_pmd_migration_entry(*pmd) && !pmd_trans_huge(*pmd)
+ && !pmd_devmap(*pmd));
count_vm_event(THP_SPLIT_PMD);
@@ -1982,7 +2026,16 @@ static void __split_huge_pmd_locked(stru
return __split_huge_zero_page_pmd(vma, haddr, pmd);
}
- page = pmd_page(*pmd);
+#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
+ pmd_migration = is_pmd_migration_entry(*pmd);
+ if (pmd_migration) {
+ swp_entry_t entry;
+
+ entry = pmd_to_swp_entry(*pmd);
+ page = pfn_to_page(swp_offset(entry));
+ } else
+#endif
+ page = pmd_page(*pmd);
VM_BUG_ON_PAGE(!page_count(page), page);
page_ref_add(page, HPAGE_PMD_NR - 1);
write = pmd_write(*pmd);
@@ -2001,7 +2054,7 @@ static void __split_huge_pmd_locked(stru
* transferred to avoid any possibility of altering
* permissions across VMAs.
*/
- if (freeze) {
+ if (freeze || pmd_migration) {
swp_entry_t swp_entry;
swp_entry = make_migration_entry(page + i, write);
entry = swp_entry_to_pte(swp_entry);
@@ -2100,7 +2153,7 @@ void __split_huge_pmd(struct vm_area_str
page = pmd_page(*pmd);
if (PageMlocked(page))
clear_page_mlock(page);
- } else if (!pmd_devmap(*pmd))
+ } else if (!(pmd_devmap(*pmd) || is_pmd_migration_entry(*pmd)))
goto out;
__split_huge_pmd_locked(vma, pmd, haddr, freeze);
out:
diff -puN mm/memcontrol.c~mm-thp-check-pmd-migration-entry-in-common-path mm/memcontrol.c
--- a/mm/memcontrol.c~mm-thp-check-pmd-migration-entry-in-common-path
+++ a/mm/memcontrol.c
@@ -4638,6 +4638,11 @@ static enum mc_target_type get_mctgt_typ
struct page *page = NULL;
enum mc_target_type ret = MC_TARGET_NONE;
+ if (unlikely(is_swap_pmd(pmd))) {
+ VM_BUG_ON(thp_migration_supported() &&
+ !is_pmd_migration_entry(pmd));
+ return ret;
+ }
page = pmd_page(pmd);
VM_BUG_ON_PAGE(!page || !PageHead(page), page);
if (!(mc.flags & MOVE_ANON))
diff -puN mm/memory.c~mm-thp-check-pmd-migration-entry-in-common-path mm/memory.c
--- a/mm/memory.c~mm-thp-check-pmd-migration-entry-in-common-path
+++ a/mm/memory.c
@@ -1036,7 +1036,8 @@ static inline int copy_pmd_range(struct
src_pmd = pmd_offset(src_pud, addr);
do {
next = pmd_addr_end(addr, end);
- if (pmd_trans_huge(*src_pmd) || pmd_devmap(*src_pmd)) {
+ if (is_swap_pmd(*src_pmd) || pmd_trans_huge(*src_pmd)
+ || pmd_devmap(*src_pmd)) {
int err;
VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, vma);
err = copy_huge_pmd(dst_mm, src_mm,
@@ -1296,7 +1297,7 @@ static inline unsigned long zap_pmd_rang
pmd = pmd_offset(pud, addr);
do {
next = pmd_addr_end(addr, end);
- if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
+ if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
if (next - addr != HPAGE_PMD_SIZE) {
VM_BUG_ON_VMA(vma_is_anonymous(vma) &&
!rwsem_is_locked(&tlb->mm->mmap_sem), vma);
@@ -3804,6 +3805,13 @@ static int __handle_mm_fault(struct vm_a
pmd_t orig_pmd = *vmf.pmd;
barrier();
+ if (unlikely(is_swap_pmd(orig_pmd))) {
+ VM_BUG_ON(thp_migration_supported() &&
+ !is_pmd_migration_entry(orig_pmd));
+ if (is_pmd_migration_entry(orig_pmd))
+ pmd_migration_entry_wait(mm, vmf.pmd);
+ return 0;
+ }
if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) {
if (pmd_protnone(orig_pmd) && vma_is_accessible(vma))
return do_huge_pmd_numa_page(&vmf, orig_pmd);
diff -puN mm/mprotect.c~mm-thp-check-pmd-migration-entry-in-common-path mm/mprotect.c
--- a/mm/mprotect.c~mm-thp-check-pmd-migration-entry-in-common-path
+++ a/mm/mprotect.c
@@ -148,7 +148,7 @@ static inline unsigned long change_pmd_r
unsigned long this_pages;
next = pmd_addr_end(addr, end);
- if (!pmd_trans_huge(*pmd) && !pmd_devmap(*pmd)
+ if (!is_swap_pmd(*pmd) && !pmd_trans_huge(*pmd) && !pmd_devmap(*pmd)
&& pmd_none_or_clear_bad(pmd))
continue;
@@ -158,7 +158,7 @@ static inline unsigned long change_pmd_r
mmu_notifier_invalidate_range_start(mm, mni_start, end);
}
- if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
+ if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
if (next - addr != HPAGE_PMD_SIZE) {
__split_huge_pmd(vma, pmd, addr, false, NULL);
} else {
diff -puN mm/mremap.c~mm-thp-check-pmd-migration-entry-in-common-path mm/mremap.c
--- a/mm/mremap.c~mm-thp-check-pmd-migration-entry-in-common-path
+++ a/mm/mremap.c
@@ -222,7 +222,7 @@ unsigned long move_page_tables(struct vm
new_pmd = alloc_new_pmd(vma->vm_mm, vma, new_addr);
if (!new_pmd)
break;
- if (pmd_trans_huge(*old_pmd)) {
+ if (is_swap_pmd(*old_pmd) || pmd_trans_huge(*old_pmd)) {
if (extent == HPAGE_PMD_SIZE) {
bool moved;
/* See comment in move_ptes() */
_
Patches currently in -mm which might be from zi.yan@xxxxxxxxxxxxxx are
mm-thp-enable-thp-migration-in-generic-path.patch
mm-thp-check-pmd-migration-entry-in-common-path.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
