The patch titled
mm: add FOLL_MLOCK follow_page flag.
has been added to the -mm tree. Its filename is
mm-add-foll_mlock-follow_page-flag.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://userweb.kernel.org/~akpm/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: mm: add FOLL_MLOCK follow_page flag.
From: Michel Lespinasse <walken@xxxxxxxxxx>
Move the code to mlock pages from __mlock_vma_pages_range() to
follow_page().
This allows __mlock_vma_pages_range() to not have to break down work into
16-page batches.
An additional motivation for doing this within the present patch series is
that it'll make it easier for a later chagne to drop mmap_sem when
blocking on disk (we'd like to be able to resume at the page that was read
from disk instead of at the start of a 16-page batch).
Signed-off-by: Michel Lespinasse <walken@xxxxxxxxxx>
Cc: Hugh Dickins <hughd@xxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Nick Piggin <npiggin@xxxxxxxxx>
Cc: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: David Howells <dhowells@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/mm.h | 1
mm/memory.c | 22 ++++++++++++++
mm/mlock.c | 65 +++----------------------------------------
3 files changed, 28 insertions(+), 60 deletions(-)
diff -puN include/linux/mm.h~mm-add-foll_mlock-follow_page-flag include/linux/mm.h
--- a/include/linux/mm.h~mm-add-foll_mlock-follow_page-flag
+++ a/include/linux/mm.h
@@ -1420,6 +1420,7 @@ struct page *follow_page(struct vm_area_
#define FOLL_DUMP 0x08 /* give error on hole if it would be zero */
#define FOLL_FORCE 0x10 /* get_user_pages read/write w/o permission */
#define FOLL_MINOR 0x20 /* do only minor page faults */
+#define FOLL_MLOCK 0x40 /* mark page as mlocked */
typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
void *data);
diff -puN mm/memory.c~mm-add-foll_mlock-follow_page-flag mm/memory.c
--- a/mm/memory.c~mm-add-foll_mlock-follow_page-flag
+++ a/mm/memory.c
@@ -1310,6 +1310,28 @@ struct page *follow_page(struct vm_area_
*/
mark_page_accessed(page);
}
+ if (flags & FOLL_MLOCK) {
+ /*
+ * The preliminary mapping check is mainly to avoid the
+ * pointless overhead of lock_page on the ZERO_PAGE
+ * which might bounce very badly if there is contention.
+ *
+ * If the page is already locked, we don't need to
+ * handle it now - vmscan will handle it later if and
+ * when it attempts to reclaim the page.
+ */
+ if (page->mapping && trylock_page(page)) {
+ lru_add_drain(); /* push cached pages to LRU */
+ /*
+ * Because we lock page here and migration is
+ * blocked by the pte's page reference, we need
+ * only check for file-cache page truncation.
+ */
+ if (page->mapping)
+ mlock_vma_page(page);
+ unlock_page(page);
+ }
+ }
unlock:
pte_unmap_unlock(ptep, ptl);
out:
diff -puN mm/mlock.c~mm-add-foll_mlock-follow_page-flag mm/mlock.c
--- a/mm/mlock.c~mm-add-foll_mlock-follow_page-flag
+++ a/mm/mlock.c
@@ -159,10 +159,9 @@ static long __mlock_vma_pages_range(stru
{
struct mm_struct *mm = vma->vm_mm;
unsigned long addr = start;
- struct page *pages[16]; /* 16 gives a reasonable batch */
int nr_pages = (end - start) / PAGE_SIZE;
- int ret = 0;
int gup_flags;
+ int ret;
VM_BUG_ON(start & ~PAGE_MASK);
VM_BUG_ON(end & ~PAGE_MASK);
@@ -170,7 +169,7 @@ static long __mlock_vma_pages_range(stru
VM_BUG_ON(end > vma->vm_end);
VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
- gup_flags = FOLL_TOUCH | FOLL_GET;
+ gup_flags = FOLL_TOUCH | FOLL_MLOCK;
/*
* We want to touch writable mappings with a write fault in order
* to break COW, except for shared mappings because these don't COW
@@ -185,63 +184,9 @@ static long __mlock_vma_pages_range(stru
nr_pages--;
}
- while (nr_pages > 0) {
- int i;
-
- cond_resched();
-
- /*
- * get_user_pages makes pages present if we are
- * setting mlock. and this extra reference count will
- * disable migration of this page. However, page may
- * still be truncated out from under us.
- */
- ret = __get_user_pages(current, mm, addr,
- min_t(int, nr_pages, ARRAY_SIZE(pages)),
- 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,
- * or for addresses that map beyond end of a file.
- * We'll mlock the pages if/when they get faulted in.
- */
- if (ret < 0)
- break;
-
- lru_add_drain(); /* push cached pages to LRU */
-
- for (i = 0; i < ret; i++) {
- struct page *page = pages[i];
-
- if (page->mapping) {
- /*
- * That preliminary check is mainly to avoid
- * the pointless overhead of lock_page on the
- * ZERO_PAGE: which might bounce very badly if
- * there is contention. However, we're still
- * dirtying its cacheline with get/put_page:
- * we'll add another __get_user_pages flag to
- * avoid it if that case turns out to matter.
- */
- lock_page(page);
- /*
- * Because we lock page here and migration is
- * blocked by the elevated reference, we need
- * only check for file-cache page truncation.
- */
- if (page->mapping)
- mlock_vma_page(page);
- unlock_page(page);
- }
- put_page(page); /* ref from get_user_pages() */
- }
-
- addr += ret * PAGE_SIZE;
- nr_pages -= ret;
- ret = 0;
- }
-
- return ret; /* 0 or negative error code */
+ ret = __get_user_pages(current, mm, addr, nr_pages, gup_flags,
+ NULL, NULL);
+ return max(ret, 0); /* 0 or negative error code */
}
/*
_
Patches currently in -mm which might be from walken@xxxxxxxxxx are
do_wp_page-remove-the-reuse-flag.patch
do_wp_page-clarify-dirty_page-handling.patch
mlock-avoid-dirtying-pages-and-triggering-writeback.patch
mlock-only-hold-mmap_sem-in-shared-mode-when-faulting-in-pages.patch
mm-add-foll_mlock-follow_page-flag.patch
mm-move-vm_locked-check-to-__mlock_vma_pages_range.patch
rwsem-implement-rwsem_is_contended.patch
mlock-do-not-hold-mmap_sem-for-extended-periods-of-time.patch
x86-rwsem-more-precise-rwsem_is_contended-implementation.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
