The patch titled
Subject: mm/gup_benchmark: use proper FOLL_WRITE flags instead of hard-coding "1"
has been added to the -mm tree. Its filename is
mm-gup_benchmark-use-proper-foll_write-flags-instead-of-hard-coding-1.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-gup_benchmark-use-proper-foll_write-flags-instead-of-hard-coding-1.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-gup_benchmark-use-proper-foll_write-flags-instead-of-hard-coding-1.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: John Hubbard <jhubbard@xxxxxxxxxx>
Subject: mm/gup_benchmark: use proper FOLL_WRITE flags instead of hard-coding "1"
Fix the gup benchmark flags to use the symbolic FOLL_WRITE, instead of a
hard-coded "1" value.
Also, clean up the filtering of gup flags a little, by just doing it once
before issuing any of the get_user_pages*() calls. This makes it harder
to overlook, instead of having little "gup_flags & 1" phrases in the
function calls.
Link: http://lkml.kernel.org/r/20191209225344.99740-22-jhubbard@xxxxxxxxxx
Signed-off-by: John Hubbard <jhubbard@xxxxxxxxxx>
Reviewed-by: Ira Weiny <ira.weiny@xxxxxxxxx>
Cc: Alex Williamson <alex.williamson@xxxxxxxxxx>
Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Aneesh Kumar K.V <aneesh.kumar@xxxxxxxxxxxxx>
Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
Cc: Björn Töpel <bjorn.topel@xxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxx>
Cc: Daniel Vetter <daniel@xxxxxxxx>
Cc: Daniel Vetter <daniel.vetter@xxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Dave Chinner <david@xxxxxxxxxxxxx>
Cc: David Airlie <airlied@xxxxxxxx>
Cc: "David S . Miller" <davem@xxxxxxxxxxxxx>
Cc: Hans Verkuil <hverkuil-cisco@xxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxx>
Cc: Jens Axboe <axboe@xxxxxxxxx>
Cc: Jerome Glisse <jglisse@xxxxxxxxxx>
Cc: Jonathan Corbet <corbet@xxxxxxx>
Cc: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Leon Romanovsky <leonro@xxxxxxxxxxxx>
Cc: Magnus Karlsson <magnus.karlsson@xxxxxxxxx>
Cc: Mauro Carvalho Chehab <mchehab@xxxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Mike Rapoport <rppt@xxxxxxxxxxxxx>
Cc: Paul Mackerras <paulus@xxxxxxxxx>
Cc: Shuah Khan <shuah@xxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/gup_benchmark.c | 9 ++++++---
tools/testing/selftests/vm/gup_benchmark.c | 6 +++++-
2 files changed, 11 insertions(+), 4 deletions(-)
--- a/mm/gup_benchmark.c~mm-gup_benchmark-use-proper-foll_write-flags-instead-of-hard-coding-1
+++ a/mm/gup_benchmark.c
@@ -48,18 +48,21 @@ static int __gup_benchmark_ioctl(unsigne
nr = (next - addr) / PAGE_SIZE;
}
+ /* Filter out most gup flags: only allow a tiny subset here: */
+ gup->flags &= FOLL_WRITE;
+
switch (cmd) {
case GUP_FAST_BENCHMARK:
- nr = get_user_pages_fast(addr, nr, gup->flags & 1,
+ nr = get_user_pages_fast(addr, nr, gup->flags,
pages + i);
break;
case GUP_LONGTERM_BENCHMARK:
nr = get_user_pages(addr, nr,
- (gup->flags & 1) | FOLL_LONGTERM,
+ gup->flags | FOLL_LONGTERM,
pages + i, NULL);
break;
case GUP_BENCHMARK:
- nr = get_user_pages(addr, nr, gup->flags & 1, pages + i,
+ nr = get_user_pages(addr, nr, gup->flags, pages + i,
NULL);
break;
default:
--- a/tools/testing/selftests/vm/gup_benchmark.c~mm-gup_benchmark-use-proper-foll_write-flags-instead-of-hard-coding-1
+++ a/tools/testing/selftests/vm/gup_benchmark.c
@@ -18,6 +18,9 @@
#define GUP_LONGTERM_BENCHMARK _IOWR('g', 2, struct gup_benchmark)
#define GUP_BENCHMARK _IOWR('g', 3, struct gup_benchmark)
+/* Just the flags we need, copied from mm.h: */
+#define FOLL_WRITE 0x01 /* check pte is writable */
+
struct gup_benchmark {
__u64 get_delta_usec;
__u64 put_delta_usec;
@@ -85,7 +88,8 @@ int main(int argc, char **argv)
}
gup.nr_pages_per_call = nr_pages;
- gup.flags = write;
+ if (write)
+ gup.flags |= FOLL_WRITE;
fd = open("/sys/kernel/debug/gup_benchmark", O_RDWR);
if (fd == -1)
_
Patches currently in -mm which might be from jhubbard@xxxxxxxxxx are
mm-gup-factor-out-duplicate-code-from-four-routines.patch
mm-gup-move-try_get_compound_head-to-top-fix-minor-issues.patch
mm-devmap-refactor-1-based-refcounting-for-zone_device-pages.patch
goldish_pipe-rename-local-pin_user_pages-routine.patch
mm-fix-get_user_pages_remotes-handling-of-foll_longterm.patch
vfio-fix-foll_longterm-use-simplify-get_user_pages_remote-call.patch
mm-gup-allow-foll_force-for-get_user_pages_fast.patch
ib-umem-use-get_user_pages_fast-to-pin-dma-pages.patch
mm-gup-introduce-pin_user_pages-and-foll_pin.patch
goldish_pipe-convert-to-pin_user_pages-and-put_user_page.patch
ib-corehwumem-set-foll_pin-via-pin_user_pages-fix-up-odp.patch
mm-process_vm_access-set-foll_pin-via-pin_user_pages_remote.patch
drm-via-set-foll_pin-via-pin_user_pages_fast.patch
fs-io_uring-set-foll_pin-via-pin_user_pages.patch
net-xdp-set-foll_pin-via-pin_user_pages.patch
media-v4l2-core-set-pages-dirty-upon-releasing-dma-buffers.patch
media-v4l2-core-pin_user_pages-foll_pin-and-put_user_page-conversion.patch
vfio-mm-pin_user_pages-foll_pin-and-put_user_page-conversion.patch
powerpc-book3s64-convert-to-pin_user_pages-and-put_user_page.patch
powerpc-book3s64-convert-to-pin_user_pages-and-put_user_page-fix.patch
mm-gup_benchmark-use-proper-foll_write-flags-instead-of-hard-coding-1.patch
mm-tree-wide-rename-put_user_page-to-unpin_user_page.patch
mm-gup-pass-flags-arg-to-__gup_device_-functions.patch
mm-gup-track-foll_pin-pages.patch
mm-gup_benchmark-support-pin_user_pages-and-related-calls.patch
selftests-vm-run_vmtests-invoke-gup_benchmark-with-basic-foll_pin-coverage.patch
