The patch titled
Subject: mm, THP, swap: support PMD swap mapping in swapoff
has been added to the -mm tree. Its filename is
mm-thp-swap-support-pmd-swap-mapping-in-swapoff.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-thp-swap-support-pmd-swap-mapping-in-swapoff.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-thp-swap-support-pmd-swap-mapping-in-swapoff.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: support PMD swap mapping in swapoff
During swapoff, for a huge swap cluster, we need to allocate a THP, read
its contents into the THP and unuse the PMD and PTE swap mappings to it.
If failed to allocate a THP, the huge swap cluster will be split.
During unuse, if it is found that the swap cluster mapped by a PMD swap
mapping is split already, we will split the PMD swap mapping and unuse the
PTEs.
Link: http://lkml.kernel.org/r/20180622035151.6676-13-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/asm-generic/pgtable.h~mm-thp-swap-support-pmd-swap-mapping-in-swapoff include/asm-generic/pgtable.h
--- a/include/asm-generic/pgtable.h~mm-thp-swap-support-pmd-swap-mapping-in-swapoff
+++ a/include/asm-generic/pgtable.h
@@ -931,22 +931,13 @@ static inline int pmd_none_or_trans_huge
barrier();
#endif
/*
- * !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
+ * pmd_none() is preseved for future condition checks on pmd swap
* 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)))
+ ((IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION) ||
+ IS_ENABLED(CONFIG_THP_SWAP)) && !pmd_present(pmdval)))
return 1;
if (unlikely(pmd_bad(pmdval))) {
pmd_clear_bad(pmd);
diff -puN include/linux/huge_mm.h~mm-thp-swap-support-pmd-swap-mapping-in-swapoff include/linux/huge_mm.h
--- a/include/linux/huge_mm.h~mm-thp-swap-support-pmd-swap-mapping-in-swapoff
+++ a/include/linux/huge_mm.h
@@ -405,6 +405,8 @@ static inline gfp_t alloc_hugepage_direc
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
#ifdef CONFIG_THP_SWAP
+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);
static inline bool transparent_hugepage_swapin_enabled(
@@ -430,6 +432,12 @@ static inline bool transparent_hugepage_
return false;
}
#else /* CONFIG_THP_SWAP */
+static inline int split_huge_swap_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+ unsigned long address, pmd_t orig_pmd)
+{
+ return 0;
+}
+
static inline int do_huge_pmd_swap_page(struct vm_fault *vmf, pmd_t orig_pmd)
{
return 0;
diff -puN mm/huge_memory.c~mm-thp-swap-support-pmd-swap-mapping-in-swapoff mm/huge_memory.c
--- a/mm/huge_memory.c~mm-thp-swap-support-pmd-swap-mapping-in-swapoff
+++ a/mm/huge_memory.c
@@ -1664,8 +1664,8 @@ static void __split_huge_swap_pmd(struct
pmd_populate(mm, pmd, pgtable);
}
-static int split_huge_swap_pmd(struct vm_area_struct *vma, pmd_t *pmd,
- unsigned long address, pmd_t orig_pmd)
+int split_huge_swap_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+ unsigned long address, pmd_t orig_pmd)
{
struct mm_struct *mm = vma->vm_mm;
spinlock_t *ptl;
diff -puN mm/swapfile.c~mm-thp-swap-support-pmd-swap-mapping-in-swapoff mm/swapfile.c
--- a/mm/swapfile.c~mm-thp-swap-support-pmd-swap-mapping-in-swapoff
+++ a/mm/swapfile.c
@@ -1933,6 +1933,11 @@ static inline int pte_same_as_swp(pte_t
return pte_same(pte_swp_clear_soft_dirty(pte), swp_pte);
}
+static inline int pmd_same_as_swp(pmd_t pmd, pmd_t swp_pmd)
+{
+ return pmd_same(pmd_swp_clear_soft_dirty(pmd), swp_pmd);
+}
+
/*
* No need to decide whether this PTE shares the swap entry with others,
* just let do_wp_page work it out if a write is requested later - to
@@ -1994,6 +1999,57 @@ out_nolock:
return ret;
}
+#ifdef CONFIG_THP_SWAP
+static int unuse_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+ unsigned long addr, swp_entry_t entry, struct page *page)
+{
+ struct mem_cgroup *memcg;
+ struct swap_info_struct *si;
+ spinlock_t *ptl;
+ int ret = 1;
+
+ if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL,
+ &memcg, true)) {
+ ret = -ENOMEM;
+ goto out_nolock;
+ }
+
+ ptl = pmd_lock(vma->vm_mm, pmd);
+ if (unlikely(!pmd_same_as_swp(*pmd, swp_entry_to_pmd(entry)))) {
+ mem_cgroup_cancel_charge(page, memcg, true);
+ ret = 0;
+ goto out;
+ }
+
+ add_mm_counter(vma->vm_mm, MM_SWAPENTS, -HPAGE_PMD_NR);
+ add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
+ get_page(page);
+ set_pmd_at(vma->vm_mm, addr, pmd,
+ pmd_mkold(mk_huge_pmd(page, vma->vm_page_prot)));
+ page_add_anon_rmap(page, vma, addr, true);
+ mem_cgroup_commit_charge(page, memcg, true, true);
+ si = _swap_info_get(entry);
+ if (si)
+ swap_free_cluster(si, entry);
+ /*
+ * Move the page to the active list so it is not
+ * immediately swapped out again after swapon.
+ */
+ activate_page(page);
+out:
+ spin_unlock(ptl);
+out_nolock:
+ return ret;
+}
+#else
+static inline int unuse_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+ unsigned long addr, swp_entry_t entry,
+ struct page *page)
+{
+ return 0;
+}
+#endif
+
static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
unsigned long addr, unsigned long end,
swp_entry_t entry, struct page *page)
@@ -2034,7 +2090,7 @@ static inline int unuse_pmd_range(struct
unsigned long addr, unsigned long end,
swp_entry_t entry, struct page *page)
{
- pmd_t *pmd;
+ pmd_t swp_pmd = swp_entry_to_pmd(entry), *pmd, orig_pmd;
unsigned long next;
int ret;
@@ -2042,6 +2098,24 @@ static inline int unuse_pmd_range(struct
do {
cond_resched();
next = pmd_addr_end(addr, end);
+ orig_pmd = *pmd;
+ if (thp_swap_supported() && is_swap_pmd(orig_pmd)) {
+ if (likely(!pmd_same_as_swp(orig_pmd, swp_pmd)))
+ continue;
+ /* Huge cluster has been split already */
+ if (!PageTransCompound(page)) {
+ ret = split_huge_swap_pmd(vma, pmd,
+ addr, orig_pmd);
+ if (ret)
+ return ret;
+ ret = unuse_pte_range(vma, pmd, addr,
+ next, entry, page);
+ } else
+ ret = unuse_pmd(vma, pmd, addr, entry, page);
+ if (ret)
+ return ret;
+ continue;
+ }
if (pmd_none_or_trans_huge_or_clear_bad(pmd))
continue;
ret = unuse_pte_range(vma, pmd, addr, next, entry, page);
@@ -2206,6 +2280,7 @@ int try_to_unuse(unsigned int type, bool
* to prevent compiler doing
* something odd.
*/
+ struct swap_cluster_info *ci = NULL;
unsigned char swcount;
struct page *page;
swp_entry_t entry;
@@ -2235,6 +2310,7 @@ int try_to_unuse(unsigned int type, bool
* there are races when an instance of an entry might be missed.
*/
while ((i = find_next_to_unuse(si, i, frontswap)) != 0) {
+retry:
if (signal_pending(current)) {
retval = -EINTR;
break;
@@ -2246,6 +2322,8 @@ int try_to_unuse(unsigned int type, bool
* page and read the swap into it.
*/
swap_map = &si->swap_map[i];
+ if (si->cluster_info)
+ ci = si->cluster_info + i / SWAPFILE_CLUSTER;
entry = swp_entry(type, i);
page = read_swap_cache_async(entry,
GFP_HIGHUSER_MOVABLE, NULL, 0, false);
@@ -2266,6 +2344,12 @@ int try_to_unuse(unsigned int type, bool
*/
if (!swcount || swcount == SWAP_MAP_BAD)
continue;
+ /* Split huge cluster if failed to allocate huge page */
+ if (thp_swap_supported() && cluster_is_huge(ci)) {
+ retval = split_swap_cluster(entry, false);
+ if (!retval || retval == -EEXIST)
+ goto retry;
+ }
retval = -ENOMEM;
break;
}
_
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
