From: John Hubbard <jhubbard@nvidia.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: "Al Viro" <viro@zeniv.linux.org.uk>,
"Christoph Hellwig" <hch@infradead.org>,
"Dan Williams" <dan.j.williams@intel.com>,
"Dave Chinner" <david@fromorbit.com>,
"Ira Weiny" <ira.weiny@intel.com>, "Jan Kara" <jack@suse.cz>,
"Jason Gunthorpe" <jgg@ziepe.ca>,
"Jonathan Corbet" <corbet@lwn.net>,
"Jérôme Glisse" <jglisse@redhat.com>,
"Kirill A . Shutemov" <kirill@shutemov.name>,
"Michal Hocko" <mhocko@suse.com>,
"Mike Kravetz" <mike.kravetz@oracle.com>,
"Shuah Khan" <shuah@kernel.org>,
"Vlastimil Babka" <vbabka@suse.cz>,
"Matthew Wilcox" <willy@infradead.org>,
linux-doc@vger.kernel.org, linux-fsdevel@vger.kernel.org,
linux-kselftest@vger.kernel.org, linux-rdma@vger.kernel.org,
linux-mm@kvack.org, LKML <linux-kernel@vger.kernel.org>,
"John Hubbard" <jhubbard@nvidia.com>
Subject: [PATCH v3 11/12] mm/gup_benchmark: support pin_user_pages() and related calls
Date: Fri, 31 Jan 2020 19:40:28 -0800 [thread overview]
Message-ID: <20200201034029.4063170-12-jhubbard@nvidia.com> (raw)
In-Reply-To: <20200201034029.4063170-1-jhubbard@nvidia.com>
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.
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
---
mm/gup_benchmark.c | 71 ++++++++++++++++++++--
tools/testing/selftests/vm/gup_benchmark.c | 15 ++++-
2 files changed, 80 insertions(+), 6 deletions(-)
diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c
index 8dba38e79a9f..447628d0131f 100644
--- a/mm/gup_benchmark.c
+++ b/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)
+{
+ int 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)
+{
+ int 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[%d] 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(unsigned int cmd,
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(unsigned int cmd,
}
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 file *filep, unsigned int cmd,
case GUP_FAST_BENCHMARK:
case GUP_LONGTERM_BENCHMARK:
case GUP_BENCHMARK:
+ case PIN_FAST_BENCHMARK:
+ case PIN_BENCHMARK:
break;
default:
return -EINVAL;
diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
index 389327e9b30a..43b4dfe161a2 100644
--- a/tools/testing/selftests/vm/gup_benchmark.c
+++ b/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;
--
2.25.0
next prev parent reply other threads:[~2020-02-01 3:41 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-02-01 3:40 [PATCH v3 00/12] mm/gup: track FOLL_PIN pages John Hubbard
2020-02-01 3:40 ` [PATCH v3 01/12] mm: dump_page(): better diagnostics for compound pages John Hubbard
2020-02-03 13:16 ` Kirill A. Shutemov
2020-02-03 19:51 ` John Hubbard
2020-02-01 3:40 ` [PATCH v3 02/12] mm/gup: split get_user_pages_remote() into two routines John Hubbard
2020-02-03 13:17 ` Kirill A. Shutemov
2020-02-03 14:20 ` Jan Kara
2020-02-03 21:09 ` John Hubbard
2020-02-01 3:40 ` [PATCH v3 03/12] mm/gup: pass a flags arg to __gup_device_* functions John Hubbard
2020-02-03 13:19 ` Kirill A. Shutemov
2020-02-03 19:56 ` John Hubbard
2020-02-01 3:40 ` [PATCH v3 04/12] mm: introduce page_ref_sub_return() John Hubbard
2020-02-03 13:23 ` Kirill A. Shutemov
2020-02-03 20:03 ` John Hubbard
2020-02-01 3:40 ` [PATCH v3 05/12] mm/gup: pass gup flags to two more routines John Hubbard
2020-02-03 13:24 ` Kirill A. Shutemov
2020-02-03 14:18 ` Jan Kara
2020-02-01 3:40 ` [PATCH v3 06/12] mm/gup: require FOLL_GET for get_user_pages_fast() John Hubbard
2020-02-03 13:26 ` Kirill A. Shutemov
2020-02-03 14:18 ` Jan Kara
2020-02-01 3:40 ` [PATCH v3 07/12] mm/gup: track FOLL_PIN pages John Hubbard
2020-02-03 13:40 ` Kirill A. Shutemov
2020-02-03 21:01 ` John Hubbard
2020-02-03 14:29 ` Jan Kara
2020-02-01 3:40 ` [PATCH v3 08/12] mm/gup: page->hpage_pinned_refcount: exact pin counts for huge pages John Hubbard
2020-02-03 13:45 ` Kirill A. Shutemov
2020-02-03 14:43 ` Jan Kara
2020-02-01 3:40 ` [PATCH v3 09/12] mm: dump_page(): better diagnostics for huge pinned pages John Hubbard
2020-02-03 13:46 ` Kirill A. Shutemov
2020-02-03 14:44 ` Jan Kara
2020-02-01 3:40 ` [PATCH v3 10/12] mm/gup: /proc/vmstat: pin_user_pages (FOLL_PIN) reporting John Hubbard
2020-02-03 13:53 ` Kirill A. Shutemov
2020-02-03 21:04 ` John Hubbard
2020-02-03 21:30 ` Kirill A. Shutemov
2020-02-03 21:34 ` John Hubbard
2020-02-03 23:16 ` John Hubbard
2020-02-03 23:43 ` John Hubbard
2020-02-01 3:40 ` John Hubbard [this message]
2020-02-03 13:58 ` [PATCH v3 11/12] mm/gup_benchmark: support pin_user_pages() and related calls Kirill A. Shutemov
2020-02-03 21:17 ` John Hubbard
2020-02-03 21:55 ` Kirill A. Shutemov
2020-02-03 22:07 ` John Hubbard
2020-02-01 3:40 ` [PATCH v3 12/12] selftests/vm: run_vmtests: invoke gup_benchmark with basic FOLL_PIN coverage John Hubbard
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200201034029.4063170-12-jhubbard@nvidia.com \
--to=jhubbard@nvidia.com \
--cc=akpm@linux-foundation.org \
--cc=corbet@lwn.net \
--cc=dan.j.williams@intel.com \
--cc=david@fromorbit.com \
--cc=hch@infradead.org \
--cc=ira.weiny@intel.com \
--cc=jack@suse.cz \
--cc=jgg@ziepe.ca \
--cc=jglisse@redhat.com \
--cc=kirill@shutemov.name \
--cc=linux-doc@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-kselftest@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-rdma@vger.kernel.org \
--cc=mhocko@suse.com \
--cc=mike.kravetz@oracle.com \
--cc=shuah@kernel.org \
--cc=vbabka@suse.cz \
--cc=viro@zeniv.linux.org.uk \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).