@@ -8,6 +8,9 @@
#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_LONGTERM_BENCHMARK _IOWR('g', 5, struct gup_benchmark)
+#define PIN_BENCHMARK _IOWR('g', 6, struct gup_benchmark)
struct gup_benchmark {
__u64 get_delta_usec;
@@ -19,6 +22,44 @@ struct gup_benchmark {
__u64 expansion[10]; /* For future use */
};
+static void put_back_pages(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_LONGTERM_BENCHMARK:
+ case PIN_BENCHMARK:
+ put_user_pages(pages, nr_pages);
+ break;
+ }
+}
+
+static void verify_dma_pinned(int cmd, struct page **pages,
+ unsigned long nr_pages)
+{
+ int i;
+
+ switch (cmd) {
+ case PIN_FAST_BENCHMARK:
+ case PIN_LONGTERM_BENCHMARK:
+ case PIN_BENCHMARK:
+ for (i = 0; i < nr_pages; i++) {
+ if (WARN(!page_dma_pinned(pages[i]),
+ "pages[%d] is NOT dma-pinned\n", i))
+ break;
+ }
+ break;
+ }
+}
+
static int __gup_benchmark_ioctl(unsigned int cmd,
struct gup_benchmark *gup)
{
@@ -62,6 +103,19 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
nr = get_user_pages(addr, nr, gup->flags & 1, pages + i,
NULL);
break;
+ case PIN_FAST_BENCHMARK:
+ nr = pin_user_pages_fast(addr, nr, gup->flags & 1,
+ pages + i);
+ break;
+ case PIN_LONGTERM_BENCHMARK:
+ nr = pin_longterm_pages(addr, nr,
+ (gup->flags & 1),
+ pages + i, NULL);
+ break;
+ case PIN_BENCHMARK:
+ nr = pin_user_pages(addr, nr, gup->flags & 1, pages + i,
+ NULL);
+ break;
default:
return -1;
}
@@ -72,15 +126,22 @@ 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);
@@ -98,6 +159,9 @@ 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_LONGTERM_BENCHMARK:
+ case PIN_BENCHMARK:
break;
default:
return -EINVAL;
@@ -18,6 +18,15 @@
#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. This is done
+ * by calling pin_user_pages_fast(), pin_longterm_pages(), and pin_user_pages(),
+ * respectively.
+ */
+#define PIN_FAST_BENCHMARK _IOWR('g', 4, struct gup_benchmark)
+#define PIN_LONGTERM_BENCHMARK _IOWR('g', 5, struct gup_benchmark)
+#define PIN_BENCHMARK _IOWR('g', 6, struct gup_benchmark)
+
struct gup_benchmark {
__u64 get_delta_usec;
__u64 put_delta_usec;
@@ -37,8 +46,17 @@ 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:abctTLUuwSH")) != -1) {
switch (opt) {
+ case 'a':
+ cmd = PIN_FAST_BENCHMARK;
+ break;
+ case 'b':
+ cmd = PIN_LONGTERM_BENCHMARK;
+ break;
+ case 'c':
+ cmd = PIN_BENCHMARK;
+ break;
case 'm':
size = atoi(optarg) * MB;
break;
@@ -60,6 +78,9 @@ int main(int argc, char **argv)
case 'U':
cmd = GUP_BENCHMARK;
break;
+ case 'u':
+ cmd = GUP_FAST_BENCHMARK;
+ break;
case 'w':
write = 1;
break;
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(): via the '-c' command line option * pin_longterm_pages(): via the '-b' command line option * pin_user_pages_fast(): via the '-a' 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 three 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_LONGTERM_BENCHMARK : calls pin_longterm_pages() PIN_BENCHMARK : calls pin_user_pages() In between the calls to pin_*() and put_user_pages(), check each page: if page_dma_pinned() returns false, then WARN and return. Do this outside of the benchmark timestamps, so that it doesn't affect reported times. Signed-off-by: John Hubbard <jhubbard@nvidia.com> --- mm/gup_benchmark.c | 74 ++++++++++++++++++++-- tools/testing/selftests/vm/gup_benchmark.c | 23 ++++++- 2 files changed, 91 insertions(+), 6 deletions(-)