On 8/15/20 5:20 AM, Barry Song wrote:
> According to Documentation/core-api/pin_user_pages.rst, FOLL_PIN is a
> prerequisite to FOLL_LONGTERM. Another way of saying that is,
> FOLL_LONGTERM is a specific case, more restrictive case of FOLL_PIN.
>
> Almost all kernel modules are using pin_user_pages() with FOLL_LONGTERM,
> mm/gup_benchmark.c seems to the only exception in which FOLL_PIN is not
> a prerequisite to FOLL_LONGTERM.
>
> Cc: John Hubbard <[email protected]>
> Cc: Jan Kara <[email protected]>
> Cc: Jérôme Glisse <[email protected]>
> Cc: "Matthew Wilcox (Oracle)" <[email protected]>
> Cc: Al Viro <[email protected]>
> Cc: Christoph Hellwig <[email protected]>
> Cc: Dan Williams <[email protected]>
> Cc: Dave Chinner <[email protected]>
> Cc: Jason Gunthorpe <[email protected]>
> Cc: Jonathan Corbet <[email protected]>
> Cc: Michal Hocko <[email protected]>
> Cc: Mike Kravetz <[email protected]>
> Cc: Shuah Khan <[email protected]>
> Cc: Vlastimil Babka <[email protected]>
> Signed-off-by: Barry Song <[email protected]>
> ---
> mm/gup_benchmark.c | 23 +++++++++++-----------
> tools/testing/selftests/vm/gup_benchmark.c | 14 ++++++-------
> 2 files changed, 19 insertions(+), 18 deletions(-)
DKIM-Signature: v a a-sha256; claxed/relaxed; d idia.com; s;
t97543403; bh MgR68sU/7ylDBje1zIHeASZNXztqkMbZmncLAvXTg h PGP-Universal:Subject:To:CC:References:From:Message-ID:Date:
User-Agent:MIME-Version:In-Reply-To:X-Originating-IP:
X-ClientProxiedBy:Content-Type:Content-Language:
Content-Transfer-Encoding;
b UpDUC+nMHrjfAF7P2cj7wZXrE8nzUsgwO7si5v+/Uys92+nacgh1CLHbW1syXHM
mxt5KwyRUBdpZW65ued56n+Kneao+1VTejBHXumUtHN/VFk/cnr8boa1CWU2tWn/d+
ZXY2/sej9jXBl/ejghwFJnTlKl6oX+UY4N8l1MeEYBX/YJBGfR9bA69elnQmBvuHNd
CTdEa3mZ4wcaK+Pgpxyb/z1NhveEAQlAzkfs7llvB8Cgk0q7Ta0jObqzjtwI9n5kow
IHZsPJRmIxe05DO4LI8DKO7Etb/GyrCXklwOGW9LuB6suRsLSlSri85gc0dSAhuTkK
vqEWLfitNguIA
Reviewed-by: John Hubbard <[email protected]>
thanks,
--
John Hubbard
NVIDIA
>
> diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c
> index be690fa66a46..464cae1fa3ea 100644
> --- a/mm/gup_benchmark.c
> +++ b/mm/gup_benchmark.c
> @@ -6,10 +6,10 @@
> #include <linux/debugfs.h>
>
> #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)
> +#define GUP_BENCHMARK _IOWR('g', 2, struct gup_benchmark)
> +#define PIN_FAST_BENCHMARK _IOWR('g', 3, struct gup_benchmark)
> +#define PIN_BENCHMARK _IOWR('g', 4, struct gup_benchmark)
> +#define PIN_LONGTERM_BENCHMARK _IOWR('g', 5, struct gup_benchmark)
>
> struct gup_benchmark {
> __u64 get_delta_usec;
> @@ -28,7 +28,6 @@ static void put_back_pages(unsigned int cmd, struct page **pages,
>
> switch (cmd) {
> case GUP_FAST_BENCHMARK:
> - case GUP_LONGTERM_BENCHMARK:
> case GUP_BENCHMARK:
> for (i = 0; i < nr_pages; i++)
> put_page(pages[i]);
> @@ -36,6 +35,7 @@ static void put_back_pages(unsigned int cmd, struct page **pages,
>
> case PIN_FAST_BENCHMARK:
> case PIN_BENCHMARK:
> + case PIN_LONGTERM_BENCHMARK:
> unpin_user_pages(pages, nr_pages);
> break;
> }
> @@ -50,6 +50,7 @@ static void verify_dma_pinned(unsigned int cmd, struct page **pages,
> 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),
> @@ -101,11 +102,6 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
> nr = get_user_pages_fast(addr, nr, gup->flags,
> pages + i);
> break;
> - case GUP_LONGTERM_BENCHMARK:
> - nr = get_user_pages(addr, nr,
> - gup->flags | FOLL_LONGTERM,
> - pages + i, NULL);
> - break;
> case GUP_BENCHMARK:
> nr = get_user_pages(addr, nr, gup->flags, pages + i,
> NULL);
> @@ -118,6 +114,11 @@ static int __gup_benchmark_ioctl(unsigned int cmd,
> 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:
> kvfree(pages);
> ret = -EINVAL;
> @@ -162,10 +163,10 @@ static long gup_benchmark_ioctl(struct file *filep, unsigned int cmd,
>
> switch (cmd) {
> case GUP_FAST_BENCHMARK:
> - case GUP_LONGTERM_BENCHMARK:
> case GUP_BENCHMARK:
> case PIN_FAST_BENCHMARK:
> case PIN_BENCHMARK:
> + case PIN_LONGTERM_BENCHMARK:
> break;
> default:
> return -EINVAL;
> diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c
> index 43b4dfe161a2..31f8bb086907 100644
> --- a/tools/testing/selftests/vm/gup_benchmark.c
> +++ b/tools/testing/selftests/vm/gup_benchmark.c
> @@ -15,12 +15,12 @@
> #define PAGE_SIZE sysconf(_SC_PAGESIZE)
>
> #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 GUP_BENCHMARK _IOWR('g', 2, 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)
> +#define PIN_FAST_BENCHMARK _IOWR('g', 3, struct gup_benchmark)
> +#define PIN_BENCHMARK _IOWR('g', 4, struct gup_benchmark)
> +#define PIN_LONGTERM_BENCHMARK _IOWR('g', 5, struct gup_benchmark)
>
> /* Just the flags we need, copied from mm.h: */
> #define FOLL_WRITE 0x01 /* check pte is writable */
> @@ -52,6 +52,9 @@ int main(int argc, char **argv)
> case 'b':
> cmd = PIN_BENCHMARK;
> break;
> + case 'L':
> + cmd = PIN_LONGTERM_BENCHMARK;
> + break;
> case 'm':
> size = atoi(optarg) * MB;
> break;
> @@ -67,9 +70,6 @@ int main(int argc, char **argv)
> case 'T':
> thp = 0;
> break;
> - case 'L':
> - cmd = GUP_LONGTERM_BENCHMARK;
> - break;
> case 'U':
> cmd = GUP_BENCHMARK;
> break;
>