The patch titled
Subject: mm/gup_benchmark: support pin_user_pages() and related calls
has been added to the -mm tree. Its filename is
mm-gup_benchmark-support-pin_user_pages-and-related-calls.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-gup_benchmark-support-pin_user_pages-and-related-calls.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-gup_benchmark-support-pin_user_pages-and-related-calls.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: support pin_user_pages() and related calls
Up until now, gup_benchmark supported testing of the following kernel
functions:
* get_user_pages(): via the '-U' command line option
* get_user_pages_longterm(): via the '-L' command line option
* get_user_pages_fast(): as the default (no options required)
Add test coverage for the new corresponding pin_*() functions:
* pin_user_pages_fast(): via the '-a' command line option
* pin_user_pages(): via the '-b' command line option
Also, add an option for clarity: '-u' for what is now (still) the default
choice: get_user_pages_fast().
Also, for the commands that set FOLL_PIN, verify that the pages really are
dma-pinned, via the new is_dma_pinned() routine. Those commands are:
PIN_FAST_BENCHMARK : calls pin_user_pages_fast()
PIN_BENCHMARK : calls pin_user_pages()
In between the calls to pin_*() and unpin_user_pages(), check each page:
if page_maybe_dma_pinned() returns false, then WARN and return.
Do this outside of the benchmark timestamps, so that it doesn't affect
reported times.
Link: http://lkml.kernel.org/r/20200211001536.1027652-10-jhubbard@xxxxxxxxxx
Signed-off-by: John Hubbard <jhubbard@xxxxxxxxxx>
Reviewed-by: Ira Weiny <ira.weiny@xxxxxxxxx>
Acked-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: Jérôme Glisse <jglisse@xxxxxxxxxx>
Cc: "Matthew Wilcox (Oracle)" <willy@xxxxxxxxxxxxx>
Cc: Al Viro <viro@xxxxxxxxxxxxxxxxxx>
Cc: Christoph Hellwig <hch@xxxxxxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Dave Chinner <david@xxxxxxxxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxx>
Cc: Jonathan Corbet <corbet@xxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Cc: Shuah Khan <shuah@xxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/gup_benchmark.c | 71 +++++++++++++++++--
tools/testing/selftests/vm/gup_benchmark.c | 15 +++-
2 files changed, 80 insertions(+), 6 deletions(-)
--- a/mm/gup_benchmark.c~mm-gup_benchmark-support-pin_user_pages-and-related-calls
+++ a/mm/gup_benchmark.c
@@ -8,6 +8,8 @@
#define GUP_FAST_BENCHMARK _IOWR('g', 1, struct gup_benchmark)
#define GUP_LONGTERM_BENCHMARK _IOWR('g', 2, struct gup_benchmark)
#define GUP_BENCHMARK _IOWR('g', 3, struct gup_benchmark)
+#define PIN_FAST_BENCHMARK _IOWR('g', 4, struct gup_benchmark)
+#define PIN_BENCHMARK _IOWR('g', 5, struct gup_benchmark)
struct gup_benchmark {
__u64 get_delta_usec;
@@ -19,6 +21,48 @@ struct gup_benchmark {
__u64 expansion[10]; /* For future use */
};
+static void put_back_pages(unsigned int cmd, struct page **pages,
+ unsigned long nr_pages)
+{
+ unsigned long i;
+
+ switch (cmd) {
+ case GUP_FAST_BENCHMARK:
+ case GUP_LONGTERM_BENCHMARK:
+ case GUP_BENCHMARK:
+ for (i = 0; i < nr_pages; i++)
+ put_page(pages[i]);
+ break;
+
+ case PIN_FAST_BENCHMARK:
+ case PIN_BENCHMARK:
+ unpin_user_pages(pages, nr_pages);
+ break;
+ }
+}
+
+static void verify_dma_pinned(unsigned int cmd, struct page **pages,
+ unsigned long nr_pages)
+{
+ unsigned long i;
+ struct page *page;
+
+ switch (cmd) {
+ case PIN_FAST_BENCHMARK:
+ case PIN_BENCHMARK:
+ for (i = 0; i < nr_pages; i++) {
+ page = pages[i];
+ if (WARN(!page_maybe_dma_pinned(page),
+ "pages[%lu] is NOT dma-pinned\n", i)) {
+
+ dump_page(page, "gup_benchmark failure");
+ break;
+ }
+ }
+ break;
+ }
+}
+
static int __gup_benchmark_ioctl(unsigned int cmd,
struct gup_benchmark *gup)
{
@@ -66,6 +110,14 @@ static int __gup_benchmark_ioctl(unsigne
nr = get_user_pages(addr, nr, gup->flags, pages + i,
NULL);
break;
+ case PIN_FAST_BENCHMARK:
+ nr = pin_user_pages_fast(addr, nr, gup->flags,
+ pages + i);
+ break;
+ case PIN_BENCHMARK:
+ nr = pin_user_pages(addr, nr, gup->flags, pages + i,
+ NULL);
+ break;
default:
kvfree(pages);
ret = -EINVAL;
@@ -78,15 +130,22 @@ static int __gup_benchmark_ioctl(unsigne
}
end_time = ktime_get();
+ /* Shifting the meaning of nr_pages: now it is actual number pinned: */
+ nr_pages = i;
+
gup->get_delta_usec = ktime_us_delta(end_time, start_time);
gup->size = addr - gup->addr;
+ /*
+ * Take an un-benchmark-timed moment to verify DMA pinned
+ * state: print a warning if any non-dma-pinned pages are found:
+ */
+ verify_dma_pinned(cmd, pages, nr_pages);
+
start_time = ktime_get();
- for (i = 0; i < nr_pages; i++) {
- if (!pages[i])
- break;
- put_page(pages[i]);
- }
+
+ put_back_pages(cmd, pages, nr_pages);
+
end_time = ktime_get();
gup->put_delta_usec = ktime_us_delta(end_time, start_time);
@@ -105,6 +164,8 @@ static long gup_benchmark_ioctl(struct f
case GUP_FAST_BENCHMARK:
case GUP_LONGTERM_BENCHMARK:
case GUP_BENCHMARK:
+ case PIN_FAST_BENCHMARK:
+ case PIN_BENCHMARK:
break;
default:
return -EINVAL;
--- a/tools/testing/selftests/vm/gup_benchmark.c~mm-gup_benchmark-support-pin_user_pages-and-related-calls
+++ a/tools/testing/selftests/vm/gup_benchmark.c
@@ -18,6 +18,10 @@
#define GUP_LONGTERM_BENCHMARK _IOWR('g', 2, struct gup_benchmark)
#define GUP_BENCHMARK _IOWR('g', 3, struct gup_benchmark)
+/* Similar to above, but use FOLL_PIN instead of FOLL_GET. */
+#define PIN_FAST_BENCHMARK _IOWR('g', 4, struct gup_benchmark)
+#define PIN_BENCHMARK _IOWR('g', 5, struct gup_benchmark)
+
/* Just the flags we need, copied from mm.h: */
#define FOLL_WRITE 0x01 /* check pte is writable */
@@ -40,8 +44,14 @@ int main(int argc, char **argv)
char *file = "/dev/zero";
char *p;
- while ((opt = getopt(argc, argv, "m:r:n:f:tTLUwSH")) != -1) {
+ while ((opt = getopt(argc, argv, "m:r:n:f:abtTLUuwSH")) != -1) {
switch (opt) {
+ case 'a':
+ cmd = PIN_FAST_BENCHMARK;
+ break;
+ case 'b':
+ cmd = PIN_BENCHMARK;
+ break;
case 'm':
size = atoi(optarg) * MB;
break;
@@ -63,6 +73,9 @@ int main(int argc, char **argv)
case 'U':
cmd = GUP_BENCHMARK;
break;
+ case 'u':
+ cmd = GUP_FAST_BENCHMARK;
+ break;
case 'w':
write = 1;
break;
_
Patches currently in -mm which might be from jhubbard@xxxxxxxxxx are
mm-gup-split-get_user_pages_remote-into-two-routines.patch
mm-gup-pass-a-flags-arg-to-__gup_device_-functions.patch
mm-introduce-page_ref_sub_return.patch
mm-gup-pass-gup-flags-to-two-more-routines.patch
mm-gup-require-foll_get-for-get_user_pages_fast.patch
mm-gup-track-foll_pin-pages.patch
mm-gup-page-hpage_pinned_refcount-exact-pin-counts-for-huge-pages.patch
mm-gup-proc-vmstat-pin_user_pages-foll_pin-reporting.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
mm-dump_page-additional-diagnostics-for-huge-pinned-pages.patch
