The patch titled
Subject: mm: don't split THP page when syscall is called
has been added to the -mm tree. Its filename is
mm-dont-split-thp-page-when-syscall-is-called.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-dont-split-thp-page-when-syscall-is-called.patch
echo and later at
echo http://ozlabs.org/~akpm/mmotm/broken-out/mm-dont-split-thp-page-when-syscall-is-called.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: Minchan Kim <minchan@xxxxxxxxxx>
Subject: mm: don't split THP page when syscall is called
We don't need to split THP page when MADV_FREE syscall is called. It
could be done when VM decide really frees it so we could avoid unnecessary
THP split.
Signed-off-by: Minchan Kim <minchan@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/huge_mm.h | 4 ++++
mm/huge_memory.c | 35 +++++++++++++++++++++++++++++++++++
mm/madvise.c | 21 ++++++++++++++++++++-
mm/rmap.c | 8 ++++++--
mm/vmscan.c | 28 ++++++++++++++++++----------
5 files changed, 83 insertions(+), 13 deletions(-)
diff -puN include/linux/huge_mm.h~mm-dont-split-thp-page-when-syscall-is-called include/linux/huge_mm.h
--- a/include/linux/huge_mm.h~mm-dont-split-thp-page-when-syscall-is-called
+++ a/include/linux/huge_mm.h
@@ -19,6 +19,9 @@ extern struct page *follow_trans_huge_pm
unsigned long addr,
pmd_t *pmd,
unsigned int flags);
+extern int madvise_free_huge_pmd(struct mmu_gather *tlb,
+ struct vm_area_struct *vma,
+ pmd_t *pmd, unsigned long addr);
extern int zap_huge_pmd(struct mmu_gather *tlb,
struct vm_area_struct *vma,
pmd_t *pmd, unsigned long addr);
@@ -56,6 +59,7 @@ extern pmd_t *page_check_address_pmd(str
unsigned long address,
enum page_check_address_pmd_flag flag,
spinlock_t **ptl);
+extern int pmd_freeable(pmd_t pmd);
#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
diff -puN mm/huge_memory.c~mm-dont-split-thp-page-when-syscall-is-called mm/huge_memory.c
--- a/mm/huge_memory.c~mm-dont-split-thp-page-when-syscall-is-called
+++ a/mm/huge_memory.c
@@ -1383,6 +1383,36 @@ out:
return 0;
}
+int madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
+ pmd_t *pmd, unsigned long addr)
+
+{
+ spinlock_t *ptl;
+ struct mm_struct *mm = tlb->mm;
+ int ret = 1;
+
+ if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+ struct page *page;
+ pmd_t orig_pmd;
+
+ orig_pmd = pmdp_get_and_clear(mm, addr, pmd);
+
+ /* No hugepage in swapcache */
+ page = pmd_page(orig_pmd);
+ VM_BUG_ON_PAGE(PageSwapCache(page), page);
+
+ orig_pmd = pmd_mkold(orig_pmd);
+ orig_pmd = pmd_mkclean(orig_pmd);
+
+ set_pmd_at(mm, addr, pmd, orig_pmd);
+ tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
+ spin_unlock(ptl);
+ ret = 0;
+ }
+
+ return ret;
+}
+
int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
pmd_t *pmd, unsigned long addr)
{
@@ -1619,6 +1649,11 @@ unlock:
return NULL;
}
+int pmd_freeable(pmd_t pmd)
+{
+ return !pmd_dirty(pmd);
+}
+
static int __split_huge_page_splitting(struct page *page,
struct vm_area_struct *vma,
unsigned long address)
diff -puN mm/madvise.c~mm-dont-split-thp-page-when-syscall-is-called mm/madvise.c
--- a/mm/madvise.c~mm-dont-split-thp-page-when-syscall-is-called
+++ a/mm/madvise.c
@@ -271,8 +271,26 @@ static int madvise_free_pte_range(pmd_t
spinlock_t *ptl;
pte_t *pte, ptent;
struct page *page;
+ unsigned long next;
+
+ next = pmd_addr_end(addr, end);
+ if (pmd_trans_huge(*pmd)) {
+ if (next - addr != HPAGE_PMD_SIZE) {
+#ifdef CONFIG_DEBUG_VM
+ if (!rwsem_is_locked(&mm->mmap_sem)) {
+ pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n",
+ __func__, addr, end,
+ vma->vm_start,
+ vma->vm_end);
+ BUG();
+ }
+#endif
+ split_huge_page_pmd(vma, addr, pmd);
+ } else if (!madvise_free_huge_pmd(tlb, vma, pmd, addr))
+ goto next;
+ /* fall through */
+ }
- split_huge_page_pmd(vma, addr, pmd);
if (pmd_trans_unstable(pmd))
return 0;
@@ -316,6 +334,7 @@ static int madvise_free_pte_range(pmd_t
}
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(pte - 1, ptl);
+next:
cond_resched();
return 0;
}
diff -puN mm/rmap.c~mm-dont-split-thp-page-when-syscall-is-called mm/rmap.c
--- a/mm/rmap.c~mm-dont-split-thp-page-when-syscall-is-called
+++ a/mm/rmap.c
@@ -704,9 +704,13 @@ static int page_referenced_one(struct pa
referenced++;
/*
- * In this implmentation, MADV_FREE doesn't support THP free
+ * Use pmd_freeable instead of raw pmd_dirty because in some
+ * of architecture, pmd_dirty is not defined unless
+ * CONFIG_TRANSPARNTE_HUGE is enabled
*/
- dirty++;
+ if (!pmd_freeable(*pmd))
+ dirty++;
+
spin_unlock(ptl);
} else {
pte_t *pte;
diff -puN mm/vmscan.c~mm-dont-split-thp-page-when-syscall-is-called mm/vmscan.c
--- a/mm/vmscan.c~mm-dont-split-thp-page-when-syscall-is-called
+++ a/mm/vmscan.c
@@ -976,17 +976,25 @@ static unsigned long shrink_page_list(st
* Anonymous process memory has backing store?
* Try to allocate it some swap space here.
*/
- if (PageAnon(page) && !PageSwapCache(page) && !freeable) {
- if (!(sc->gfp_mask & __GFP_IO))
- goto keep_locked;
- if (!add_to_swap(page, page_list))
- goto activate_locked;
- may_enter_fs = 1;
-
- /* Adding to swap updated mapping */
- mapping = page_mapping(page);
+ if (PageAnon(page) && !PageSwapCache(page)) {
+ if (!freeable) {
+ if (!(sc->gfp_mask & __GFP_IO))
+ goto keep_locked;
+ if (!add_to_swap(page, page_list))
+ goto activate_locked;
+ may_enter_fs = 1;
+ /* Adding to swap updated mapping */
+ mapping = page_mapping(page);
+ } else {
+ if (likely(!PageTransHuge(page)))
+ goto unmap;
+ /* try_to_unmap isn't aware of THP page */
+ if (unlikely(split_huge_page_to_list(page,
+ page_list)))
+ goto keep_locked;
+ }
}
-
+unmap:
/*
* The page is mapped into the page tables of one or more
* processes. Try to unmap it here.
_
Patches currently in -mm which might be from minchan@xxxxxxxxxx are
mm-frontswap-invalidate-expired-data-on-a-dup-store-failure.patch
mm-compaction-pass-classzone_idx-and-alloc_flags-to-watermark-checking.patch
mm-compaction-pass-classzone_idx-and-alloc_flags-to-watermark-checking-fix.patch
mm-compaction-simplify-deferred-compaction.patch
mm-compaction-defer-only-on-compact_complete.patch
mm-compaction-always-update-cached-scanner-positions.patch
mm-compaction-always-update-cached-scanner-positions-fix.patch
mm-compaction-more-focused-lru-and-pcplists-draining.patch
mm-compaction-more-focused-lru-and-pcplists-draining-fix.patch
mm-page_isolation-check-pfn-validity-before-access.patch
mm-page_alloc-store-updated-page-migratetype-to-avoid-misusing-stale-value.patch
mm-page_alloc-store-updated-page-migratetype-to-avoid-misusing-stale-value-fix.patch
mm-support-madvisemadv_free.patch
x86-add-pmd_-for-thp.patch
sparc-add-pmd_-for-thp.patch
powerpc-add-pmd_-for-thp.patch
arm-add-pmd_mkclean-for-thp.patch
arm64-add-pmd_-for-thp.patch
mm-dont-split-thp-page-when-syscall-is-called.patch
zsmalloc-merge-size_class-to-reduce-fragmentation.patch
zram-remove-bio-parameter-from-zram_bvec_rw.patch
zram-change-parameter-from-vaild_io_request.patch
zram-implement-rw_page-operation-of-zram.patch
zram-implement-rw_page-operation-of-zram-fix.patch
zram-implement-rw_page-operation-of-zram-fix-2.patch
zram-implement-rw_page-operation-of-zram-fix-2-cleanup.patch
zram-implement-rw_page-operation-of-zram-fix-3.patch
zsmalloc-fix-zs_init-cpu-notifier-error-handling.patch
zsmalloc-fix-zs_init-cpu-notifier-error-handling-fix-2.patch
zsmalloc-fix-zs_init-cpu-notifier-error-handling-fix.patch
zsmalloc-correct-fragile-_atomic-use.patch
mm-zram-correct-zram_zero-flag-bit-position.patch
mm-zswap-add-__init-to-some-functions-in-zswap.patch
debugging-keep-track-of-page-owners.patch
page-owners-correct-page-order-when-to-free-page.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
