The patch titled
Subject: userfaultfd: non-cooperative: add madvise() event for MADV_FREE request
has been added to the -mm tree. Its filename is
userfaultfd-non-cooperative-add-madvise-event-for-madv_free-request.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/userfaultfd-non-cooperative-add-madvise-event-for-madv_free-request.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/userfaultfd-non-cooperative-add-madvise-event-for-madv_free-request.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: Mike Rapoport <rppt@xxxxxxxxxxxxxxxxxx>
Subject: userfaultfd: non-cooperative: add madvise() event for MADV_FREE request
MADV_FREE is identical to MADV_DONTNEED from the point of view of uffd
monitor. The monitor has to stop handling #PF events in the range being
freed. We are reusing userfaultfd_remove callback along with the logic
required to re-get and re-validate the VMA which may change or disappear
because userfaultfd_remove releases mmap_sem.
Link: http://lkml.kernel.org/r/1497876311-18615-1-git-send-email-rppt@xxxxxxxxxxxxxxxxxx
Signed-off-by: Mike Rapoport <rppt@xxxxxxxxxxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Hillf Danton <hillf.zj@xxxxxxxxxxxxxxx>
Cc: Pavel Emelyanov <xemul@xxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/madvise.c | 42 ++++++++++++++++++++++--------------------
1 file changed, 22 insertions(+), 20 deletions(-)
diff -puN mm/madvise.c~userfaultfd-non-cooperative-add-madvise-event-for-madv_free-request mm/madvise.c
--- a/mm/madvise.c~userfaultfd-non-cooperative-add-madvise-event-for-madv_free-request
+++ a/mm/madvise.c
@@ -451,9 +451,6 @@ static int madvise_free_single_vma(struc
struct mm_struct *mm = vma->vm_mm;
struct mmu_gather tlb;
- if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP))
- return -EINVAL;
-
/* MADV_FREE works for only anon vma at the moment */
if (!vma_is_anonymous(vma))
return -EINVAL;
@@ -477,14 +474,6 @@ static int madvise_free_single_vma(struc
return 0;
}
-static long madvise_free(struct vm_area_struct *vma,
- struct vm_area_struct **prev,
- unsigned long start, unsigned long end)
-{
- *prev = vma;
- return madvise_free_single_vma(vma, start, end);
-}
-
/*
* Application no longer needs these pages. If the pages are dirty,
* it's OK to just throw them away. The app will be more careful about
@@ -504,9 +493,17 @@ static long madvise_free(struct vm_area_
* An interface that causes the system to free clean pages and flush
* dirty pages is already available as msync(MS_INVALIDATE).
*/
-static long madvise_dontneed(struct vm_area_struct *vma,
- struct vm_area_struct **prev,
- unsigned long start, unsigned long end)
+static long madvise_dontneed_single_vma(struct vm_area_struct *vma,
+ unsigned long start, unsigned long end)
+{
+ zap_page_range(vma, start, end - start);
+ return 0;
+}
+
+static long madvise_dontneed_free(struct vm_area_struct *vma,
+ struct vm_area_struct **prev,
+ unsigned long start, unsigned long end,
+ int behavior)
{
*prev = vma;
if (!can_madv_dontneed_vma(vma))
@@ -526,7 +523,8 @@ static long madvise_dontneed(struct vm_a
* is also < vma->vm_end. If start <
* vma->vm_start it means an hole materialized
* in the user address space within the
- * virtual range passed to MADV_DONTNEED.
+ * virtual range passed to MADV_DONTNEED
+ * or MADV_FREE.
*/
return -ENOMEM;
}
@@ -537,7 +535,7 @@ static long madvise_dontneed(struct vm_a
* Don't fail if end > vma->vm_end. If the old
* vma was splitted while the mmap_sem was
* released the effect of the concurrent
- * operation may not cause MADV_DONTNEED to
+ * operation may not cause madvise() to
* have an undefined result. There may be an
* adjacent next vma that we'll walk
* next. userfaultfd_remove() will generate an
@@ -549,8 +547,13 @@ static long madvise_dontneed(struct vm_a
}
VM_WARN_ON(start >= end);
}
- zap_page_range(vma, start, end - start);
- return 0;
+
+ if (behavior == MADV_DONTNEED)
+ return madvise_dontneed_single_vma(vma, start, end);
+ else if (behavior == MADV_FREE)
+ return madvise_free_single_vma(vma, start, end);
+ else
+ return -EINVAL;
}
/*
@@ -656,9 +659,8 @@ madvise_vma(struct vm_area_struct *vma,
case MADV_WILLNEED:
return madvise_willneed(vma, prev, start, end);
case MADV_FREE:
- return madvise_free(vma, prev, start, end);
case MADV_DONTNEED:
- return madvise_dontneed(vma, prev, start, end);
+ return madvise_dontneed_free(vma, prev, start, end, behavior);
default:
return madvise_behavior(vma, prev, start, end, behavior);
}
_
Patches currently in -mm which might be from rppt@xxxxxxxxxxxxxxxxxx are
exit-dont-include-unused-userfaultfd_kh.patch
userfaultfd-drop-dead-code.patch
userfaultfd-non-cooperative-add-madvise-event-for-madv_free-request.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
