mm/gup_benchmark: rename to mm/gup_test

Patch series "selftests/vm: gup_test, hmm-tests, assorted improvements", v3.

Summary: This series provides two main things, and a number of smaller
supporting goodies.  The two main points are:

1) Add a new sub-test to gup_test, which in turn is a renamed version
   of gup_benchmark.  This sub-test allows nicer testing of dump_pages(),
   at least on user-space pages.

   For quite a while, I was doing a quick hack to gup_test.c whenever I
   wanted to try out changes to dump_page().  Then Matthew Wilcox asked me
   what I meant when I said "I used my dump_page() unit test", and I
   realized that it might be nice to check in a polished up version of
   that.

   Details about how it works and how to use it are in the commit
   description for patch #6 ("selftests/vm: gup_test: introduce the
   dump_pages() sub-test").

2) Fixes a limitation of hmm-tests: these tests are incredibly useful,
   but only if people actually build and run them.  And it turns out that
   libhugetlbfs is a little too effective at throwing a wrench in the
   works, there.  So I've added a little configuration check that removes
   just two of the 21 hmm-tests, if libhugetlbfs is not available.

   Further details in the commit description of patch #8
   ("selftests/vm: hmm-tests: remove the libhugetlbfs dependency").

Other smaller things that this series does:

a) Remove code duplication by creating gup_test.h.

b) Clear up the sub-test organization, and their invocation within
   run_vmtests.sh.

c) Other minor assorted improvements.

[1] v2 is here:
https://lore.kernel.org/linux-doc/20200929212747.251804-1-jhubbard@nvidia.com/

[2] https://lore.kernel.org/r/CAHk-=wgh-TMPHLY3jueHX7Y2fWh3D+nMBqVS__AZm6-oorquWA@mail.gmail.com

This patch (of 9):

Rename nearly every "gup_benchmark" reference and file name to "gup_test".
The one exception is for the actual gup benchmark test itself.

The current code already does a *little* bit more than benchmarking, and
definitely covers more than get_user_pages_fast().  More importantly,
however, subsequent patches are about to add some functionality that is
non-benchmark related.

Closely related changes:

* Kconfig: in addition to renaming the options from GUP_BENCHMARK to
  GUP_TEST, update the help text to reflect that it's no longer a
  benchmark-only test.

Link: https://lkml.kernel.org/r/20201026064021.3545418-1-jhubbard@nvidia.com
Link: https://lkml.kernel.org/r/20201026064021.3545418-2-jhubbard@nvidia.com
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Jérôme Glisse <jglisse@redhat.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 210 insertions, 0 deletions

diff --git a/mm/gup_test.c b/mm/gup_test.c
new file mode 100644
index 000000000000..59472ea6aa39
--- /dev/null
+++ b/mm/gup_test.c
@@ -0,0 +1,210 @@
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/ktime.h>
+#include <linux/debugfs.h>
+
+#define GUP_FAST_BENCHMARK	_IOWR('g', 1, struct gup_test)
+#define GUP_BENCHMARK		_IOWR('g', 2, struct gup_test)
+#define PIN_FAST_BENCHMARK	_IOWR('g', 3, struct gup_test)
+#define PIN_BENCHMARK		_IOWR('g', 4, struct gup_test)
+#define PIN_LONGTERM_BENCHMARK	_IOWR('g', 5, struct gup_test)
+
+struct gup_test {
+	__u64 get_delta_usec;
+	__u64 put_delta_usec;
+	__u64 addr;
+	__u64 size;
+	__u32 nr_pages_per_call;
+	__u32 flags;
+	__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_BENCHMARK:
+		for (i = 0; i < nr_pages; i++)
+			put_page(pages[i]);
+		break;
+
+	case PIN_FAST_BENCHMARK:
+	case PIN_BENCHMARK:
+	case PIN_LONGTERM_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:
+	case PIN_LONGTERM_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_test failure");
+				break;
+			}
+		}
+		break;
+	}
+}
+
+static int __gup_test_ioctl(unsigned int cmd,
+		struct gup_test *gup)
+{
+	ktime_t start_time, end_time;
+	unsigned long i, nr_pages, addr, next;
+	int nr;
+	struct page **pages;
+	int ret = 0;
+	bool needs_mmap_lock =
+		cmd != GUP_FAST_BENCHMARK && cmd != PIN_FAST_BENCHMARK;
+
+	if (gup->size > ULONG_MAX)
+		return -EINVAL;
+
+	nr_pages = gup->size / PAGE_SIZE;
+	pages = kvcalloc(nr_pages, sizeof(void *), GFP_KERNEL);
+	if (!pages)
+		return -ENOMEM;
+
+	if (needs_mmap_lock && mmap_read_lock_killable(current->mm)) {
+		ret = -EINTR;
+		goto free_pages;
+	}
+
+	i = 0;
+	nr = gup->nr_pages_per_call;
+	start_time = ktime_get();
+	for (addr = gup->addr; addr < gup->addr + gup->size; addr = next) {
+		if (nr != gup->nr_pages_per_call)
+			break;
+
+		next = addr + nr * PAGE_SIZE;
+		if (next > gup->addr + gup->size) {
+			next = gup->addr + gup->size;
+			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,
+						 pages + i);
+			break;
+		case GUP_BENCHMARK:
+			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;
+		case PIN_LONGTERM_BENCHMARK:
+			nr = pin_user_pages(addr, nr,
+					    gup->flags | FOLL_LONGTERM,
+					    pages + i, NULL);
+			break;
+		default:
+			ret = -EINVAL;
+			goto unlock;
+		}
+
+		if (nr <= 0)
+			break;
+		i += nr;
+	}
+	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();
+
+	put_back_pages(cmd, pages, nr_pages);
+
+	end_time = ktime_get();
+	gup->put_delta_usec = ktime_us_delta(end_time, start_time);
+
+unlock:
+	if (needs_mmap_lock)
+		mmap_read_unlock(current->mm);
+free_pages:
+	kvfree(pages);
+	return ret;
+}
+
+static long gup_test_ioctl(struct file *filep, unsigned int cmd,
+		unsigned long arg)
+{
+	struct gup_test gup;
+	int ret;
+
+	switch (cmd) {
+	case GUP_FAST_BENCHMARK:
+	case GUP_BENCHMARK:
+	case PIN_FAST_BENCHMARK:
+	case PIN_BENCHMARK:
+	case PIN_LONGTERM_BENCHMARK:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (copy_from_user(&gup, (void __user *)arg, sizeof(gup)))
+		return -EFAULT;
+
+	ret = __gup_test_ioctl(cmd, &gup);
+	if (ret)
+		return ret;
+
+	if (copy_to_user((void __user *)arg, &gup, sizeof(gup)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static const struct file_operations gup_test_fops = {
+	.open = nonseekable_open,
+	.unlocked_ioctl = gup_test_ioctl,
+};
+
+static int gup_test_init(void)
+{
+	debugfs_create_file_unsafe("gup_test", 0600, NULL, NULL,
+				   &gup_test_fops);
+
+	return 0;
+}
+
+late_initcall(gup_test_init);