linux/tools/testing/selftests/vm/gup_test.c

195 lines
4.0 KiB
C
Raw Normal View History

#include <fcntl.h>
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <sys/ioctl.h>
#include <sys/mman.h>
#include <sys/stat.h>
#include <sys/types.h>
2020-12-15 03:05:08 +00:00
#include "../../../../mm/gup_test.h"
#define MB (1UL << 20)
#define PAGE_SIZE sysconf(_SC_PAGESIZE)
/* Just the flags we need, copied from mm.h: */
#define FOLL_WRITE 0x01 /* check pte is writable */
static char *cmd_to_str(unsigned long cmd)
{
switch (cmd) {
case GUP_FAST_BENCHMARK:
return "GUP_FAST_BENCHMARK";
case PIN_FAST_BENCHMARK:
return "PIN_FAST_BENCHMARK";
case PIN_LONGTERM_BENCHMARK:
return "PIN_LONGTERM_BENCHMARK";
case GUP_BASIC_TEST:
return "GUP_BASIC_TEST";
case PIN_BASIC_TEST:
return "PIN_BASIC_TEST";
selftests/vm: gup_test: introduce the dump_pages() sub-test For quite a while, I was doing a quick hack to gup_test.c (previously, gup_benchmark.c) whenever I wanted to try out my changes to dump_page(). This makes that hack unnecessary, and instead allows anyone to easily get the same coverage from a user space program. That saves a lot of time because you don't have to change the kernel, in order to test different pages and options. The new sub-test takes advantage of the existing gup_test infrastructure, which already provides a simple user space program, some allocated user space pages, an ioctl call, pinning of those pages (via either get_user_pages or pin_user_pages) and a corresponding kernel-side test invocation. There's not much more required, mainly just a couple of inputs from the user. In fact, the new test re-uses the existing command line options in order to get various helpful combinations (THP or normal, _fast or slow gup, gup vs. pup, and more). New command line options are: which pages to dump, and what type of "get/pin" to use. In order to figure out which pages to dump, the logic is: * If the user doesn't specify anything, the page 0 (the first page in the address range that the program sets up for testing) is dumped. * Or, the user can type up to 8 page indices anywhere on the command line. If you type more than 8, then it uses the first 8 and ignores the remaining items. For example: ./gup_test -ct -F 1 0 19 0x1000 Meaning: -c: dump pages sub-test -t: use THP pages -F 1: use pin_user_pages() instead of get_user_pages() 0 19 0x1000: dump pages 0, 19, and 4096 Link: https://lkml.kernel.org/r/20201026064021.3545418-7-jhubbard@nvidia.com Signed-off-by: John Hubbard <jhubbard@nvidia.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> 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>
2020-12-15 03:05:21 +00:00
case DUMP_USER_PAGES_TEST:
return "DUMP_USER_PAGES_TEST";
}
return "Unknown command";
}
int main(int argc, char **argv)
{
selftests/vm: gup_test: introduce the dump_pages() sub-test For quite a while, I was doing a quick hack to gup_test.c (previously, gup_benchmark.c) whenever I wanted to try out my changes to dump_page(). This makes that hack unnecessary, and instead allows anyone to easily get the same coverage from a user space program. That saves a lot of time because you don't have to change the kernel, in order to test different pages and options. The new sub-test takes advantage of the existing gup_test infrastructure, which already provides a simple user space program, some allocated user space pages, an ioctl call, pinning of those pages (via either get_user_pages or pin_user_pages) and a corresponding kernel-side test invocation. There's not much more required, mainly just a couple of inputs from the user. In fact, the new test re-uses the existing command line options in order to get various helpful combinations (THP or normal, _fast or slow gup, gup vs. pup, and more). New command line options are: which pages to dump, and what type of "get/pin" to use. In order to figure out which pages to dump, the logic is: * If the user doesn't specify anything, the page 0 (the first page in the address range that the program sets up for testing) is dumped. * Or, the user can type up to 8 page indices anywhere on the command line. If you type more than 8, then it uses the first 8 and ignores the remaining items. For example: ./gup_test -ct -F 1 0 19 0x1000 Meaning: -c: dump pages sub-test -t: use THP pages -F 1: use pin_user_pages() instead of get_user_pages() 0 19 0x1000: dump pages 0, 19, and 4096 Link: https://lkml.kernel.org/r/20201026064021.3545418-7-jhubbard@nvidia.com Signed-off-by: John Hubbard <jhubbard@nvidia.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> 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>
2020-12-15 03:05:21 +00:00
struct gup_test gup = { 0 };
unsigned long size = 128 * MB;
int i, fd, filed, opt, nr_pages = 1, thp = -1, repeats = 1, write = 0;
unsigned long cmd = GUP_FAST_BENCHMARK;
int flags = MAP_PRIVATE;
char *file = "/dev/zero";
char *p;
selftests/vm: gup_test: introduce the dump_pages() sub-test For quite a while, I was doing a quick hack to gup_test.c (previously, gup_benchmark.c) whenever I wanted to try out my changes to dump_page(). This makes that hack unnecessary, and instead allows anyone to easily get the same coverage from a user space program. That saves a lot of time because you don't have to change the kernel, in order to test different pages and options. The new sub-test takes advantage of the existing gup_test infrastructure, which already provides a simple user space program, some allocated user space pages, an ioctl call, pinning of those pages (via either get_user_pages or pin_user_pages) and a corresponding kernel-side test invocation. There's not much more required, mainly just a couple of inputs from the user. In fact, the new test re-uses the existing command line options in order to get various helpful combinations (THP or normal, _fast or slow gup, gup vs. pup, and more). New command line options are: which pages to dump, and what type of "get/pin" to use. In order to figure out which pages to dump, the logic is: * If the user doesn't specify anything, the page 0 (the first page in the address range that the program sets up for testing) is dumped. * Or, the user can type up to 8 page indices anywhere on the command line. If you type more than 8, then it uses the first 8 and ignores the remaining items. For example: ./gup_test -ct -F 1 0 19 0x1000 Meaning: -c: dump pages sub-test -t: use THP pages -F 1: use pin_user_pages() instead of get_user_pages() 0 19 0x1000: dump pages 0, 19, and 4096 Link: https://lkml.kernel.org/r/20201026064021.3545418-7-jhubbard@nvidia.com Signed-off-by: John Hubbard <jhubbard@nvidia.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> 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>
2020-12-15 03:05:21 +00:00
while ((opt = getopt(argc, argv, "m:r:n:F:f:abctTLUuwSH")) != -1) {
switch (opt) {
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. Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Link: http://lkml.kernel.org/r/20200211001536.1027652-10-jhubbard@nvidia.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-02 04:05:41 +00:00
case 'a':
cmd = PIN_FAST_BENCHMARK;
break;
case 'b':
cmd = PIN_BASIC_TEST;
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. Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Link: http://lkml.kernel.org/r/20200211001536.1027652-10-jhubbard@nvidia.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-02 04:05:41 +00:00
break;
case 'L':
cmd = PIN_LONGTERM_BENCHMARK;
break;
selftests/vm: gup_test: introduce the dump_pages() sub-test For quite a while, I was doing a quick hack to gup_test.c (previously, gup_benchmark.c) whenever I wanted to try out my changes to dump_page(). This makes that hack unnecessary, and instead allows anyone to easily get the same coverage from a user space program. That saves a lot of time because you don't have to change the kernel, in order to test different pages and options. The new sub-test takes advantage of the existing gup_test infrastructure, which already provides a simple user space program, some allocated user space pages, an ioctl call, pinning of those pages (via either get_user_pages or pin_user_pages) and a corresponding kernel-side test invocation. There's not much more required, mainly just a couple of inputs from the user. In fact, the new test re-uses the existing command line options in order to get various helpful combinations (THP or normal, _fast or slow gup, gup vs. pup, and more). New command line options are: which pages to dump, and what type of "get/pin" to use. In order to figure out which pages to dump, the logic is: * If the user doesn't specify anything, the page 0 (the first page in the address range that the program sets up for testing) is dumped. * Or, the user can type up to 8 page indices anywhere on the command line. If you type more than 8, then it uses the first 8 and ignores the remaining items. For example: ./gup_test -ct -F 1 0 19 0x1000 Meaning: -c: dump pages sub-test -t: use THP pages -F 1: use pin_user_pages() instead of get_user_pages() 0 19 0x1000: dump pages 0, 19, and 4096 Link: https://lkml.kernel.org/r/20201026064021.3545418-7-jhubbard@nvidia.com Signed-off-by: John Hubbard <jhubbard@nvidia.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> 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>
2020-12-15 03:05:21 +00:00
case 'c':
cmd = DUMP_USER_PAGES_TEST;
/*
* Dump page 0 (index 1). May be overridden later, by
* user's non-option arguments.
*
* .which_pages is zero-based, so that zero can mean "do
* nothing".
*/
gup.which_pages[0] = 1;
break;
case 'F':
/* strtol, so you can pass flags in hex form */
gup.flags = strtol(optarg, 0, 0);
break;
case 'm':
size = atoi(optarg) * MB;
break;
case 'r':
repeats = atoi(optarg);
break;
case 'n':
nr_pages = atoi(optarg);
break;
case 't':
thp = 1;
break;
case 'T':
thp = 0;
break;
case 'U':
cmd = GUP_BASIC_TEST;
break;
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. Signed-off-by: John Hubbard <jhubbard@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Reviewed-by: Ira Weiny <ira.weiny@intel.com> Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Christoph Hellwig <hch@infradead.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Jason Gunthorpe <jgg@ziepe.ca> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Shuah Khan <shuah@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Link: http://lkml.kernel.org/r/20200211001536.1027652-10-jhubbard@nvidia.com Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-04-02 04:05:41 +00:00
case 'u':
cmd = GUP_FAST_BENCHMARK;
break;
case 'w':
write = 1;
break;
case 'f':
file = optarg;
break;
case 'S':
flags &= ~MAP_PRIVATE;
flags |= MAP_SHARED;
break;
case 'H':
flags |= (MAP_HUGETLB | MAP_ANONYMOUS);
break;
default:
return -1;
}
}
selftests/vm: gup_test: introduce the dump_pages() sub-test For quite a while, I was doing a quick hack to gup_test.c (previously, gup_benchmark.c) whenever I wanted to try out my changes to dump_page(). This makes that hack unnecessary, and instead allows anyone to easily get the same coverage from a user space program. That saves a lot of time because you don't have to change the kernel, in order to test different pages and options. The new sub-test takes advantage of the existing gup_test infrastructure, which already provides a simple user space program, some allocated user space pages, an ioctl call, pinning of those pages (via either get_user_pages or pin_user_pages) and a corresponding kernel-side test invocation. There's not much more required, mainly just a couple of inputs from the user. In fact, the new test re-uses the existing command line options in order to get various helpful combinations (THP or normal, _fast or slow gup, gup vs. pup, and more). New command line options are: which pages to dump, and what type of "get/pin" to use. In order to figure out which pages to dump, the logic is: * If the user doesn't specify anything, the page 0 (the first page in the address range that the program sets up for testing) is dumped. * Or, the user can type up to 8 page indices anywhere on the command line. If you type more than 8, then it uses the first 8 and ignores the remaining items. For example: ./gup_test -ct -F 1 0 19 0x1000 Meaning: -c: dump pages sub-test -t: use THP pages -F 1: use pin_user_pages() instead of get_user_pages() 0 19 0x1000: dump pages 0, 19, and 4096 Link: https://lkml.kernel.org/r/20201026064021.3545418-7-jhubbard@nvidia.com Signed-off-by: John Hubbard <jhubbard@nvidia.com> Cc: Jérôme Glisse <jglisse@redhat.com> Cc: Jonathan Corbet <corbet@lwn.net> 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>
2020-12-15 03:05:21 +00:00
if (optind < argc) {
int extra_arg_count = 0;
/*
* For example:
*
* ./gup_test -c 0 1 0x1001
*
* ...to dump pages 0, 1, and 4097
*/
while ((optind < argc) &&
(extra_arg_count < GUP_TEST_MAX_PAGES_TO_DUMP)) {
/*
* Do the 1-based indexing here, so that the user can
* use normal 0-based indexing on the command line.
*/
long page_index = strtol(argv[optind], 0, 0) + 1;
gup.which_pages[extra_arg_count] = page_index;
extra_arg_count++;
optind++;
}
}
filed = open(file, O_RDWR|O_CREAT);
if (filed < 0) {
perror("open");
exit(filed);
}
gup.nr_pages_per_call = nr_pages;
if (write)
gup.flags |= FOLL_WRITE;
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>
2020-12-15 03:05:05 +00:00
fd = open("/sys/kernel/debug/gup_test", O_RDWR);
if (fd == -1) {
perror("open");
exit(1);
}
p = mmap(NULL, size, PROT_READ | PROT_WRITE, flags, filed, 0);
if (p == MAP_FAILED) {
perror("mmap");
exit(1);
}
gup.addr = (unsigned long)p;
if (thp == 1)
madvise(p, size, MADV_HUGEPAGE);
else if (thp == 0)
madvise(p, size, MADV_NOHUGEPAGE);
for (; (unsigned long)p < gup.addr + size; p += PAGE_SIZE)
p[0] = 0;
/* Only report timing information on the *_BENCHMARK commands: */
if ((cmd == PIN_FAST_BENCHMARK) || (cmd == GUP_FAST_BENCHMARK) ||
(cmd == PIN_LONGTERM_BENCHMARK)) {
for (i = 0; i < repeats; i++) {
gup.size = size;
if (ioctl(fd, cmd, &gup))
perror("ioctl"), exit(1);
printf("%s: Time: get:%lld put:%lld us",
cmd_to_str(cmd), gup.get_delta_usec,
gup.put_delta_usec);
if (gup.size != size)
printf(", truncated (size: %lld)", gup.size);
printf("\n");
}
} else {
gup.size = size;
if (ioctl(fd, cmd, &gup)) {
perror("ioctl");
exit(1);
}
printf("%s: done\n", cmd_to_str(cmd));
if (gup.size != size)
printf("Truncated (size: %lld)\n", gup.size);
}
return 0;
}