The patch titled
Subject: mm, THP, swap: create PMD swap mapping when unmap the THP
has been added to the -mm tree. Its filename is
mm-thp-swap-create-pmd-swap-mapping-when-unmap-the-thp.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-thp-swap-create-pmd-swap-mapping-when-unmap-the-thp.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-thp-swap-create-pmd-swap-mapping-when-unmap-the-thp.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/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Huang Ying <ying.huang@xxxxxxxxx>
Subject: mm, THP, swap: create PMD swap mapping when unmap the THP
This is the final step of the THP swapin support. When reclaiming a
anonymous THP, after allocating the huge swap cluster and add the THP into
swap cache, the PMD page mapping will be changed to the mapping to the
swap space. Previously, the PMD page mapping will be split before being
changed. In this patch, the unmap code is enhanced not to split the PMD
mapping, but create a PMD swap mapping to replace it instead. So later
when clear the SWAP_HAS_CACHE flag in the last step of swapout, the huge
swap cluster will be kept instead of being split, and when swapin, the
huge swap cluster will be read as a whole into a THP. That is, the THP
will not be split during swapout/swapin. This can eliminate the overhead
of splitting/collapsing, and reduce the page fault count, etc. But more
important, the utilization of THP is improved greatly, that is, much more
THP will be kept when swapping is used, so that we can take full advantage
of THP including its high performance for swapout/swapin.
Link: http://lkml.kernel.org/r/20180622035151.6676-21-ying.huang@xxxxxxxxx
Signed-off-by: "Huang, Ying" <ying.huang@xxxxxxxxx>
Cc: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Shaohua Li <shli@xxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Minchan Kim <minchan@xxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
Cc: Zi Yan <zi.yan@xxxxxxxxxxxxxx>
Cc: Daniel Jordan <daniel.m.jordan@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
diff -puN include/linux/huge_mm.h~mm-thp-swap-create-pmd-swap-mapping-when-unmap-the-thp include/linux/huge_mm.h
--- a/include/linux/huge_mm.h~mm-thp-swap-create-pmd-swap-mapping-when-unmap-the-thp
+++ a/include/linux/huge_mm.h
@@ -404,6 +404,8 @@ static inline gfp_t alloc_hugepage_direc
}
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+struct page_vma_mapped_walk;
+
#ifdef CONFIG_THP_SWAP
extern void __split_huge_swap_pmd(struct vm_area_struct *vma,
unsigned long haddr,
@@ -411,6 +413,8 @@ extern void __split_huge_swap_pmd(struct
extern int split_huge_swap_pmd(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long address, pmd_t orig_pmd);
extern int do_huge_pmd_swap_page(struct vm_fault *vmf, pmd_t orig_pmd);
+extern bool set_pmd_swap_entry(struct page_vma_mapped_walk *pvmw,
+ struct page *page, unsigned long address, pmd_t pmdval);
static inline bool transparent_hugepage_swapin_enabled(
struct vm_area_struct *vma)
@@ -452,6 +456,13 @@ static inline int do_huge_pmd_swap_page(
return 0;
}
+static inline bool set_pmd_swap_entry(struct page_vma_mapped_walk *pvmw,
+ struct page *page, unsigned long address,
+ pmd_t pmdval)
+{
+ return false;
+}
+
static inline bool transparent_hugepage_swapin_enabled(
struct vm_area_struct *vma)
{
diff -puN mm/huge_memory.c~mm-thp-swap-create-pmd-swap-mapping-when-unmap-the-thp mm/huge_memory.c
--- a/mm/huge_memory.c~mm-thp-swap-create-pmd-swap-mapping-when-unmap-the-thp
+++ a/mm/huge_memory.c
@@ -1877,6 +1877,36 @@ split:
count_vm_event(THP_SWPIN_FALLBACK);
goto fallback;
}
+
+bool set_pmd_swap_entry(struct page_vma_mapped_walk *pvmw, struct page *page,
+ unsigned long address, pmd_t pmdval)
+{
+ struct vm_area_struct *vma = pvmw->vma;
+ struct mm_struct *mm = vma->vm_mm;
+ pmd_t swp_pmd;
+ swp_entry_t entry = { .val = page_private(page) };
+
+ if (swap_duplicate(&entry, true) < 0) {
+ set_pmd_at(mm, address, pvmw->pmd, pmdval);
+ return false;
+ }
+ if (list_empty(&mm->mmlist)) {
+ spin_lock(&mmlist_lock);
+ if (list_empty(&mm->mmlist))
+ list_add(&mm->mmlist, &init_mm.mmlist);
+ spin_unlock(&mmlist_lock);
+ }
+ add_mm_counter(mm, MM_ANONPAGES, -HPAGE_PMD_NR);
+ add_mm_counter(mm, MM_SWAPENTS, HPAGE_PMD_NR);
+ swp_pmd = swp_entry_to_pmd(entry);
+ if (pmd_soft_dirty(pmdval))
+ swp_pmd = pmd_swp_mksoft_dirty(swp_pmd);
+ set_pmd_at(mm, address, pvmw->pmd, swp_pmd);
+
+ page_remove_rmap(page, true);
+ put_page(page);
+ return true;
+}
#endif
static inline void zap_deposited_table(struct mm_struct *mm, pmd_t *pmd)
diff -puN mm/rmap.c~mm-thp-swap-create-pmd-swap-mapping-when-unmap-the-thp mm/rmap.c
--- a/mm/rmap.c~mm-thp-swap-create-pmd-swap-mapping-when-unmap-the-thp
+++ a/mm/rmap.c
@@ -1402,12 +1402,51 @@ static bool try_to_unmap_one(struct page
continue;
}
+ address = pvmw.address;
+
+#ifdef CONFIG_THP_SWAP
+ /* PMD-mapped THP swap entry */
+ if (thp_swap_supported() && !pvmw.pte && PageAnon(page)) {
+ pmd_t pmdval;
+
+ VM_BUG_ON_PAGE(PageHuge(page) ||
+ !PageTransCompound(page), page);
+
+ flush_cache_range(vma, address,
+ address + HPAGE_PMD_SIZE);
+ mmu_notifier_invalidate_range_start(mm, address,
+ address + HPAGE_PMD_SIZE);
+ if (should_defer_flush(mm, flags)) {
+ /* check comments for PTE below */
+ pmdval = pmdp_huge_get_and_clear(mm, address,
+ pvmw.pmd);
+ set_tlb_ubc_flush_pending(mm,
+ pmd_dirty(pmdval));
+ } else
+ pmdval = pmdp_huge_clear_flush(vma, address,
+ pvmw.pmd);
+
+ /*
+ * Move the dirty bit to the page. Now the pmd
+ * is gone.
+ */
+ if (pmd_dirty(pmdval))
+ set_page_dirty(page);
+
+ /* Update high watermark before we lower rss */
+ update_hiwater_rss(mm);
+
+ ret = set_pmd_swap_entry(&pvmw, page, address, pmdval);
+ mmu_notifier_invalidate_range_end(mm, address,
+ address + HPAGE_PMD_SIZE);
+ continue;
+ }
+#endif
+
/* Unexpected PMD-mapped THP? */
VM_BUG_ON_PAGE(!pvmw.pte, page);
subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
- address = pvmw.address;
-
if (IS_ENABLED(CONFIG_MIGRATION) &&
(flags & TTU_MIGRATION) &&
diff -puN mm/vmscan.c~mm-thp-swap-create-pmd-swap-mapping-when-unmap-the-thp mm/vmscan.c
--- a/mm/vmscan.c~mm-thp-swap-create-pmd-swap-mapping-when-unmap-the-thp
+++ a/mm/vmscan.c
@@ -1148,11 +1148,7 @@ static unsigned long shrink_page_list(st
* processes. Try to unmap it here.
*/
if (page_mapped(page)) {
- enum ttu_flags flags = ttu_flags | TTU_BATCH_FLUSH;
-
- if (unlikely(PageTransHuge(page)))
- flags |= TTU_SPLIT_HUGE_PMD;
- if (!try_to_unmap(page, flags)) {
+ if (!try_to_unmap(page, ttu_flags | TTU_BATCH_FLUSH)) {
nr_unmap_fail++;
goto activate_locked;
}
_
Patches currently in -mm which might be from ying.huang@xxxxxxxxx are
mm-clear_huge_page-move-order-algorithm-into-a-separate-function.patch
mm-huge-page-copy-target-sub-page-last-when-copy-huge-page.patch
mm-hugetlbfs-rename-address-to-haddr-in-hugetlb_cow.patch
mm-hugetlbfs-pass-fault-address-to-cow-handler.patch
mm-swap-fix-race-between-swapoff-and-some-swap-operations.patch
mm-swap-fix-race-between-swapoff-and-some-swap-operations-v6.patch
mm-fix-race-between-swapoff-and-mincore.patch
mm-thp-swap-enable-pmd-swap-operations-for-config_thp_swap.patch
mm-thp-swap-make-config_thp_swap-depends-on-config_swap.patch
mm-thp-swap-support-pmd-swap-mapping-in-swap_duplicate.patch
mm-thp-swap-support-pmd-swap-mapping-in-swapcache_free_cluster.patch
mm-thp-swap-support-pmd-swap-mapping-in-free_swap_and_cache-swap_free.patch
mm-thp-swap-support-pmd-swap-mapping-when-splitting-huge-pmd.patch
mm-thp-swap-support-pmd-swap-mapping-in-split_swap_cluster.patch
mm-thp-swap-support-to-read-a-huge-swap-cluster-for-swapin-a-thp.patch
mm-thp-swap-swapin-a-thp-as-a-whole.patch
mm-thp-swap-support-to-count-thp-swapin-and-its-fallback.patch
mm-thp-swap-add-sysfs-interface-to-configure-thp-swapin.patch
mm-thp-swap-support-pmd-swap-mapping-in-swapoff.patch
mm-thp-swap-support-pmd-swap-mapping-in-madvise_free.patch
mm-cgroup-thp-swap-support-to-move-swap-account-for-pmd-swap-mapping.patch
mm-thp-swap-support-to-copy-pmd-swap-mapping-when-fork.patch
mm-thp-swap-free-pmd-swap-mapping-when-zap_huge_pmd.patch
mm-thp-swap-support-pmd-swap-mapping-for-madv_willneed.patch
mm-thp-swap-support-pmd-swap-mapping-in-mincore.patch
mm-thp-swap-support-pmd-swap-mapping-in-common-path.patch
mm-thp-swap-create-pmd-swap-mapping-when-unmap-the-thp.patch
mm-thp-avoid-to-split-thp-when-reclaim-madv_free-thp.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
