kernel_optimize_test/mm/gup_benchmark.c

211 lines
4.5 KiB
C
Raw Permalink Normal View History

#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_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;
__u64 put_delta_usec;
__u64 addr;
__u64 size;
__u32 nr_pages_per_call;
__u32 flags;
__u64 expansion[10]; /* For future use */
};
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 12:05:41 +08:00
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:
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 12:05:41 +08:00
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:
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 12:05:41 +08:00
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_benchmark failure");
break;
}
}
break;
}
}
static int __gup_benchmark_ioctl(unsigned int cmd,
struct gup_benchmark *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;
treewide: kvzalloc() -> kvcalloc() The kvzalloc() function has a 2-factor argument form, kvcalloc(). This patch replaces cases of: kvzalloc(a * b, gfp) with: kvcalloc(a * b, gfp) as well as handling cases of: kvzalloc(a * b * c, gfp) with: kvzalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kvcalloc(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kvzalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kvzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kvzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kvzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kvzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kvzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kvzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kvzalloc( - sizeof(u8) * COUNT + COUNT , ...) | kvzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kvzalloc( - sizeof(char) * COUNT + COUNT , ...) | kvzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kvzalloc + kvcalloc ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kvzalloc + kvcalloc ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kvzalloc + kvcalloc ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kvzalloc + kvcalloc ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kvzalloc + kvcalloc ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kvzalloc + kvcalloc ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kvzalloc + kvcalloc ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kvzalloc + kvcalloc ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kvzalloc + kvcalloc ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kvzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kvzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kvzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kvzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kvzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kvzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kvzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kvzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kvzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kvzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kvzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kvzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kvzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kvzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kvzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kvzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kvzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kvzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kvzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kvzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kvzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kvzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kvzalloc(C1 * C2 * C3, ...) | kvzalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kvzalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kvzalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kvzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kvzalloc(sizeof(THING) * C2, ...) | kvzalloc(sizeof(TYPE) * C2, ...) | kvzalloc(C1 * C2 * C3, ...) | kvzalloc(C1 * C2, ...) | - kvzalloc + kvcalloc ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kvzalloc + kvcalloc ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kvzalloc + kvcalloc ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kvzalloc + kvcalloc ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kvzalloc + kvcalloc ( - (E1) * E2 + E1, E2 , ...) | - kvzalloc + kvcalloc ( - (E1) * (E2) + E1, E2 , ...) | - kvzalloc + kvcalloc ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 05:04:48 +08:00
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;
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 12:05:41 +08:00
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();
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 12:05:41 +08:00
/* 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;
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 12:05:41 +08:00
/*
* 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();
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 12:05:41 +08:00
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_benchmark_ioctl(struct file *filep, unsigned int cmd,
unsigned long arg)
{
struct gup_benchmark gup;
int ret;
switch (cmd) {
case GUP_FAST_BENCHMARK:
case GUP_BENCHMARK:
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 12:05:41 +08:00
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_benchmark_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_benchmark_fops = {
.open = nonseekable_open,
.unlocked_ioctl = gup_benchmark_ioctl,
};
static int gup_benchmark_init(void)
{
debugfs_create_file_unsafe("gup_benchmark", 0600, NULL, NULL,
&gup_benchmark_fops);
return 0;
}
late_initcall(gup_benchmark_init);