The patch titled
splitlru: split LRU: munlock rework
has been added to the -mm tree. Its filename is
split-lru-munlock-rework.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 ***
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: splitlru: split LRU: munlock rework
From: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
current munlock processing use to pagewalk.
its cause two problems.
- build error on nommu machine
- runtime error on HIGHPTE machine.
This patch fixes it.
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Cc: Li Zefan <lizf@xxxxxxxxxxxxxx>
Cc: Hugh Dickins <hugh@xxxxxxxxxxx>
Cc: Lee Schermerhorn <Lee.Schermerhorn@xxxxxx>
Acked-by: Rik van Riel <riel@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/mlock.c | 152 +++++++++++----------------------------------------
1 file changed, 35 insertions(+), 117 deletions(-)
diff -puN mm/mlock.c~split-lru-munlock-rework mm/mlock.c
--- a/mm/mlock.c~split-lru-munlock-rework
+++ a/mm/mlock.c
@@ -120,18 +120,33 @@ static void munlock_vma_page(struct page
* vma->vm_mm->mmap_sem must be held for write.
*/
static int __mlock_vma_pages_range(struct vm_area_struct *vma,
- unsigned long start, unsigned long end)
+ unsigned long start, unsigned long end,
+ int mlock)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long addr = start;
struct page *pages[16]; /* 16 gives a reasonable batch */
- int write = !!(vma->vm_flags & VM_WRITE);
int nr_pages = (end - start) / PAGE_SIZE;
int ret;
+ int gup_flags = 0;
+
+ VM_BUG_ON(start & ~PAGE_MASK);
+ VM_BUG_ON(end & ~PAGE_MASK);
+ VM_BUG_ON(start < vma->vm_start);
+ VM_BUG_ON(end > vma->vm_end);
+ VM_BUG_ON((!rwsem_is_locked(&mm->mmap_sem)) &&
+ (atomic_read(&mm->mm_users) != 0));
+
+ /*
+ * mlock: don't page populate if page has PROT_NONE permission.
+ * munlock: the pages always do munlock althrough
+ * its has PROT_NONE permission.
+ */
+ if (!mlock)
+ gup_flags |= GUP_FLAGS_IGNORE_VMA_PERMISSIONS;
- VM_BUG_ON(start & ~PAGE_MASK || end & ~PAGE_MASK);
- VM_BUG_ON(start < vma->vm_start || end > vma->vm_end);
- VM_BUG_ON(!rwsem_is_locked(&vma->vm_mm->mmap_sem));
+ if (vma->vm_flags & VM_WRITE)
+ gup_flags |= GUP_FLAGS_WRITE;
lru_add_drain_all(); /* push cached pages to LRU */
@@ -146,9 +161,9 @@ static int __mlock_vma_pages_range(struc
* disable migration of this page. However, page may
* still be truncated out from under us.
*/
- ret = get_user_pages(current, mm, addr,
+ ret = __get_user_pages(current, mm, addr,
min_t(int, nr_pages, ARRAY_SIZE(pages)),
- write, 0, pages, NULL);
+ gup_flags, pages, NULL);
/*
* This can happen for, e.g., VM_NONLINEAR regions before
* a page has been allocated and mapped at a given offset,
@@ -178,8 +193,12 @@ static int __mlock_vma_pages_range(struc
* by the elevated reference, we need only check for
* page truncation (file-cache only).
*/
- if (page->mapping)
- mlock_vma_page(page);
+ if (page->mapping) {
+ if (mlock)
+ mlock_vma_page(page);
+ else
+ munlock_vma_page(page);
+ }
unlock_page(page);
put_page(page); /* ref from get_user_pages() */
@@ -197,120 +216,19 @@ static int __mlock_vma_pages_range(struc
return 0; /* count entire vma as locked_vm */
}
-/*
- * private structure for munlock page table walk
- */
-struct munlock_page_walk {
- struct vm_area_struct *vma;
- pmd_t *pmd; /* for migration_entry_wait() */
-};
-
-/*
- * munlock normal pages for present ptes
- */
-static int __munlock_pte_handler(pte_t *ptep, unsigned long addr,
- unsigned long end, struct mm_walk *walk)
-{
- struct munlock_page_walk *mpw = walk->private;
- swp_entry_t entry;
- struct page *page;
- pte_t pte;
-
-retry:
- pte = *ptep;
- /*
- * If it's a swap pte, we might be racing with page migration.
- */
- if (unlikely(!pte_present(pte))) {
- if (!is_swap_pte(pte))
- goto out;
- entry = pte_to_swp_entry(pte);
- if (is_migration_entry(entry)) {
- migration_entry_wait(mpw->vma->vm_mm, mpw->pmd, addr);
- goto retry;
- }
- goto out;
- }
-
- page = vm_normal_page(mpw->vma, addr, pte);
- if (!page)
- goto out;
-
- lock_page(page);
- if (!page->mapping) {
- unlock_page(page);
- goto retry;
- }
- munlock_vma_page(page);
- unlock_page(page);
-
-out:
- return 0;
-}
-
-/*
- * Save pmd for pte handler for waiting on migration entries
- */
-static int __munlock_pmd_handler(pmd_t *pmd, unsigned long addr,
- unsigned long end, struct mm_walk *walk)
-{
- struct munlock_page_walk *mpw = walk->private;
-
- mpw->pmd = pmd;
- return 0;
-}
-
-
-/*
- * munlock a range of pages in the vma using standard page table walk.
- *
- * vma->vm_mm->mmap_sem must be held for write.
- */
-static void __munlock_vma_pages_range(struct vm_area_struct *vma,
- unsigned long start, unsigned long end)
-{
- struct mm_struct *mm = vma->vm_mm;
- struct munlock_page_walk mpw = {
- .vma = vma,
- };
- struct mm_walk munlock_page_walk = {
- .pmd_entry = __munlock_pmd_handler,
- .pte_entry = __munlock_pte_handler,
- .private = &mpw,
- .mm = mm,
- };
-
- VM_BUG_ON(start & ~PAGE_MASK || end & ~PAGE_MASK);
- VM_BUG_ON((!rwsem_is_locked(&mm->mmap_sem)) &&
- (atomic_read(&mm->mm_users) != 0));
- VM_BUG_ON(start < vma->vm_start);
- VM_BUG_ON(end > vma->vm_end);
-
- lru_add_drain_all(); /* push cached pages to LRU */
- walk_page_range(start, end, &munlock_page_walk);
- lru_add_drain_all(); /* to update stats */
-}
-
#else /* CONFIG_UNEVICTABLE_LRU */
/*
* Just make pages present if VM_LOCKED. No-op if unlocking.
*/
static int __mlock_vma_pages_range(struct vm_area_struct *vma,
- unsigned long start, unsigned long end)
+ unsigned long start, unsigned long end,
+ int mlock)
{
- if (vma->vm_flags & VM_LOCKED)
+ if (mlock && (vma->vm_flags & VM_LOCKED))
make_pages_present(start, end);
return 0;
}
-
-/*
- * munlock a range of pages in the vma -- no-op.
- */
-static void __munlock_vma_pages_range(struct vm_area_struct *vma,
- unsigned long start, unsigned long end)
-{
-}
#endif /* CONFIG_UNEVICTABLE_LRU */
/*
@@ -333,7 +251,7 @@ int mlock_vma_pages_range(struct vm_area
is_vm_hugetlb_page(vma) ||
vma == get_gate_vma(current))) {
downgrade_write(&mm->mmap_sem);
- nr_pages = __mlock_vma_pages_range(vma, start, end);
+ nr_pages = __mlock_vma_pages_range(vma, start, end, 1);
up_read(&mm->mmap_sem);
/* vma can change or disappear */
@@ -368,7 +286,7 @@ void munlock_vma_pages_range(struct vm_a
unsigned long start, unsigned long end)
{
vma->vm_flags &= ~VM_LOCKED;
- __munlock_vma_pages_range(vma, start, end);
+ __mlock_vma_pages_range(vma, start, end, 0);
}
/*
@@ -445,7 +363,7 @@ success:
*/
downgrade_write(&mm->mmap_sem);
- ret = __mlock_vma_pages_range(vma, start, end);
+ ret = __mlock_vma_pages_range(vma, start, end, 1);
if (ret > 0) {
mm->locked_vm -= ret;
ret = 0;
@@ -471,7 +389,7 @@ success:
* while. Should we downgrade the semaphore for both lock
* AND unlock ?
*/
- __munlock_vma_pages_range(vma, start, end);
+ __mlock_vma_pages_range(vma, start, end, 0);
}
out:
_
Patches currently in -mm which might be from kosaki.motohiro@xxxxxxxxxxxxxx are
adapt-drivers-base-topologyc-to-new-sysfs-api.patch
ahci-use-correct-type-for-cpu-flags.patch
page-allocator-inlnie-some-__alloc_pages-wrappers.patch
page-allocator-inlnie-some-__alloc_pages-wrappers-fix.patch
mm-hugetlbc-fix-duplicate-variable.patch
page-flags-record-page-flag-overlays-explicitly.patch
slub-record-page-flag-overlays-explicitly.patch
slob-record-page-flag-overlays-explicitly.patch
mm-create-sys-kernel-mm-fix.patch
mm-make-config_migration-available-w-o-config_numa-fix.patch
pm-schedule-sysrq-poweroff-on-boot-cpu-fix.patch
call_usermodehelper-increase-reliability.patch
cgroup-list_for_each-cleanup-v2.patch
cgroup-anotate-two-variables-with-__read_mostly.patch
devcgroup-code-cleanup-fix-fix.patch
memcg-remove-refcnt-from-page_cgroup-fix-memcg-fix-mem_cgroup_end_migration-race.patch
memcg-remove-refcnt-from-page_cgroup-memcg-fix-shmem_unuse_inode-charging.patch
memcg-clean-up-checking-of-the-disabled-flag.patch
memcg-clean-up-checking-of-the-disabled-flag-memcg-further-checking-of-disabled-flag.patch
per-task-delay-accounting-update-document-and-getdelaysc-for-memory-reclaim.patch
full-conversion-to-early_initcall-interface-remove-old-interface-fix-fix.patch
full-conversion-to-early_initcall-interface-remove-old-interface-fix-fix-fix.patch
relay-add-buffer-only-channels-useful-for-early-logging-fix.patch
mm-speculative-page-references-fix-migration_entry_wait-for-speculative-page-cache.patch
vmscan-use-an-indexed-array-for-lru-variables.patch
swap-use-an-array-for-the-lru-pagevecs.patch
define-page_file_cache-function-fix-splitlru-shmem_getpage-setpageswapbacked-sooner.patch
vmscan-split-lru-lists-into-anon-file-sets-collect-lru-meminfo-statistics-from-correct-offset.patch
vmscan-split-lru-lists-into-anon-file-sets-prevent-incorrect-oom-under-split_lru.patch
vmscan-split-lru-lists-into-anon-file-sets-split_lru-fix-pagevec_move_tail-doesnt-treat-unevictable-page.patch
vmscan-split-lru-lists-into-anon-file-sets-splitlru-memcg-swapbacked-pages-active.patch
vmscan-split-lru-lists-into-anon-file-sets-splitlru-bdi_cap_swap_backed.patch
vmscan-second-chance-replacement-for-anonymous-pages.patch
vmscan-second-chance-replacement-for-anonymous-pages-fix.patch
unevictable-lru-infrastructure.patch
unevictable-lru-infrastructure-fix.patch
unevictable-lru-infrastructure-remove-redundant-page-mapping-check.patch
unevictable-lru-infrastructure-putback_lru_page-unevictable-page-handling-rework.patch
unevictable-lru-infrastructure-kill-unnecessary-lock_page-in-vmscanc.patch
unevictable-lru-infrastructure-revert-migration-change-of-unevictable-lru-infrastructure.patch
unevictable-lru-page-statistics.patch
unevictable-lru-page-statistics-fix-printk-in-show_free_areas.patch
unevictable-lru-page-statistics-units-fix.patch
shm_locked-pages-are-unevictable.patch
shm_locked-pages-are-unevictable-revert-shm-change-of-shm_locked-pages-are-unevictable-patch.patch
mlock-mlocked-pages-are-unevictable.patch
mlock-mlocked-pages-are-unevictable-fix.patch
mlock-mlocked-pages-are-unevictable-fix-fix.patch
mlock-mlocked-pages-are-unevictable-fix-3.patch
mlock-mlocked-pages-are-unevictable-fix-fix-munlock-page-table-walk-now-requires-mm.patch
mlock-mlocked-pages-are-unevictable-restore-patch-failure-hunk-of-mlock-mlocked-pages-are-unevictablepatch.patch
mlock-mlocked-pages-are-unevictable-fix-truncate-race-and-sevaral-comments.patch
mmap-handle-mlocked-pages-during-map-remap-unmap.patch
mmap-handle-mlocked-pages-during-map-remap-unmap-cleanup.patch
fix-double-unlock_page-in-2626-rc5-mm3-kernel-bug-at-mm-filemapc-575.patch
introduce-__get_user_pages.patch
split-lru-munlock-rework.patch
revert-to-unevictable-lru-infrastructure-kconfig-fixpatch.patch
vmstat-mlocked-pages-statistics.patch
vmstat-mlocked-pages-statistics-fix-incorrect-mlocked-field-of-proc-meminfo.patch
vmstat-mlocked-pages-statistics-fix.patch
swap-cull-unevictable-pages-in-fault-path-fix.patch
vmstat-unevictable-and-mlocked-pages-vm-events.patch
restore-patch-failure-of-vmstat-unevictable-and-mlocked-pages-vm-eventspatch.patch
vmscan-unevictable-lru-scan-sysctl.patch
vmscan-unevictable-lru-scan-sysctl-nommu-fix.patch
vmscan-unevictable-lru-scan-sysctl-add-sys_device-parameter.patch
vmscam-kill-unused-lru-functions.patch
mm-more-likely-reclaim-madv_sequential-mappings.patch
make-mm-memoryc-print_bad_pte-static.patch
mm-swapfilec-make-code-static.patch
make-mm-rmapc-anon_vma_cachep-static.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
