2017-11-18 02:31:22 +03:00
# 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)
2018-10-27 01:09:56 +03:00
# define GUP_LONGTERM_BENCHMARK _IOWR('g', 2, struct gup_benchmark)
# define GUP_BENCHMARK _IOWR('g', 3, struct gup_benchmark)
2017-11-18 02:31:22 +03:00
struct gup_benchmark {
2018-10-27 01:09:52 +03:00
__u64 get_delta_usec ;
__u64 put_delta_usec ;
2017-11-18 02:31:22 +03:00
__u64 addr ;
__u64 size ;
__u32 nr_pages_per_call ;
__u32 flags ;
2018-10-27 01:09:52 +03:00
__u64 expansion [ 10 ] ; /* For future use */
2017-11-18 02:31:22 +03:00
} ;
static int __gup_benchmark_ioctl ( unsigned int cmd ,
struct gup_benchmark * gup )
{
ktime_t start_time , end_time ;
2018-10-06 01:51:44 +03:00
unsigned long i , nr_pages , addr , next ;
int nr ;
2017-11-18 02:31:22 +03:00
struct page * * pages ;
2020-01-05 00:00:12 +03:00
int ret = 0 ;
2017-11-18 02:31:22 +03:00
2018-10-31 01:04:32 +03:00
if ( gup - > size > ULONG_MAX )
return - EINVAL ;
2017-11-18 02:31:22 +03:00
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 00:04:48 +03:00
pages = kvcalloc ( nr_pages , sizeof ( void * ) , GFP_KERNEL ) ;
2017-11-18 02:31:22 +03:00
if ( ! pages )
return - ENOMEM ;
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 ;
}
2018-10-27 01:09:56 +03:00
switch ( cmd ) {
case GUP_FAST_BENCHMARK :
nr = get_user_pages_fast ( addr , nr , gup - > flags & 1 ,
pages + i ) ;
break ;
case GUP_LONGTERM_BENCHMARK :
mm/gup: replace get_user_pages_longterm() with FOLL_LONGTERM
Pach series "Add FOLL_LONGTERM to GUP fast and use it".
HFI1, qib, and mthca, use get_user_pages_fast() due to its performance
advantages. These pages can be held for a significant time. But
get_user_pages_fast() does not protect against mapping FS DAX pages.
Introduce FOLL_LONGTERM and use this flag in get_user_pages_fast() which
retains the performance while also adding the FS DAX checks. XDP has also
shown interest in using this functionality.[1]
In addition we change get_user_pages() to use the new FOLL_LONGTERM flag
and remove the specialized get_user_pages_longterm call.
[1] https://lkml.org/lkml/2019/3/19/939
"longterm" is a relative thing and at this point is probably a misnomer.
This is really flagging a pin which is going to be given to hardware and
can't move. I've thought of a couple of alternative names but I think we
have to settle on if we are going to use FL_LAYOUT or something else to
solve the "longterm" problem. Then I think we can change the flag to a
better name.
Secondly, it depends on how often you are registering memory. I have
spoken with some RDMA users who consider MR in the performance path...
For the overall application performance. I don't have the numbers as the
tests for HFI1 were done a long time ago. But there was a significant
advantage. Some of which is probably due to the fact that you don't have
to hold mmap_sem.
Finally, architecturally I think it would be good for everyone to use
*_fast. There are patches submitted to the RDMA list which would allow
the use of *_fast (they reworking the use of mmap_sem) and as soon as they
are accepted I'll submit a patch to convert the RDMA core as well. Also
to this point others are looking to use *_fast.
As an aside, Jasons pointed out in my previous submission that *_fast and
*_unlocked look very much the same. I agree and I think further cleanup
will be coming. But I'm focused on getting the final solution for DAX at
the moment.
This patch (of 7):
This patch starts a series which aims to support FOLL_LONGTERM in
get_user_pages_fast(). Some callers who would like to do a longterm (user
controlled pin) of pages with the fast variant of GUP for performance
purposes.
Rather than have a separate get_user_pages_longterm() call, introduce
FOLL_LONGTERM and change the longterm callers to use it.
This patch does not change any functionality. In the short term
"longterm" or user controlled pins are unsafe for Filesystems and FS DAX
in particular has been blocked. However, callers of get_user_pages_fast()
were not "protected".
FOLL_LONGTERM can _only_ be supported with get_user_pages[_fast]() as it
requires vmas to determine if DAX is in use.
NOTE: In merging with the CMA changes we opt to change the
get_user_pages() call in check_and_migrate_cma_pages() to a call of
__get_user_pages_locked() on the newly migrated pages. This makes the
code read better in that we are calling __get_user_pages_locked() on the
pages before and after a potential migration.
As a side affect some of the interfaces are cleaned up but this is not the
primary purpose of the series.
In review[1] it was asked:
<quote>
> This I don't get - if you do lock down long term mappings performance
> of the actual get_user_pages call shouldn't matter to start with.
>
> What do I miss?
A couple of points.
First "longterm" is a relative thing and at this point is probably a
misnomer. This is really flagging a pin which is going to be given to
hardware and can't move. I've thought of a couple of alternative names
but I think we have to settle on if we are going to use FL_LAYOUT or
something else to solve the "longterm" problem. Then I think we can
change the flag to a better name.
Second, It depends on how often you are registering memory. I have spoken
with some RDMA users who consider MR in the performance path... For the
overall application performance. I don't have the numbers as the tests
for HFI1 were done a long time ago. But there was a significant
advantage. Some of which is probably due to the fact that you don't have
to hold mmap_sem.
Finally, architecturally I think it would be good for everyone to use
*_fast. There are patches submitted to the RDMA list which would allow
the use of *_fast (they reworking the use of mmap_sem) and as soon as they
are accepted I'll submit a patch to convert the RDMA core as well. Also
to this point others are looking to use *_fast.
As an asside, Jasons pointed out in my previous submission that *_fast and
*_unlocked look very much the same. I agree and I think further cleanup
will be coming. But I'm focused on getting the final solution for DAX at
the moment.
</quote>
[1] https://lore.kernel.org/lkml/20190220180255.GA12020@iweiny-DESK2.sc.intel.com/T/#md6abad2569f3bf6c1f03686c8097ab6563e94965
[ira.weiny@intel.com: v3]
Link: http://lkml.kernel.org/r/20190328084422.29911-2-ira.weiny@intel.com
Link: http://lkml.kernel.org/r/20190328084422.29911-2-ira.weiny@intel.com
Link: http://lkml.kernel.org/r/20190317183438.2057-2-ira.weiny@intel.com
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Rich Felker <dalias@libc.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Mike Marshall <hubcap@omnibond.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-05-14 03:17:03 +03:00
nr = get_user_pages ( addr , nr ,
( gup - > flags & 1 ) | FOLL_LONGTERM ,
pages + i , NULL ) ;
2018-10-27 01:09:56 +03:00
break ;
case GUP_BENCHMARK :
nr = get_user_pages ( addr , nr , gup - > flags & 1 , pages + i ,
NULL ) ;
break ;
default :
2020-01-05 00:00:12 +03:00
kvfree ( pages ) ;
ret = - EINVAL ;
goto out ;
2018-10-27 01:09:56 +03:00
}
2018-04-14 01:35:16 +03:00
if ( nr < = 0 )
break ;
2017-11-18 02:31:22 +03:00
i + = nr ;
}
end_time = ktime_get ( ) ;
2018-10-27 01:09:52 +03:00
gup - > get_delta_usec = ktime_us_delta ( end_time , start_time ) ;
2017-11-18 02:31:22 +03:00
gup - > size = addr - gup - > addr ;
2018-10-27 01:09:52 +03:00
start_time = ktime_get ( ) ;
2017-11-18 02:31:22 +03:00
for ( i = 0 ; i < nr_pages ; i + + ) {
if ( ! pages [ i ] )
break ;
put_page ( pages [ i ] ) ;
}
2018-10-27 01:09:52 +03:00
end_time = ktime_get ( ) ;
gup - > put_delta_usec = ktime_us_delta ( end_time , start_time ) ;
2017-11-18 02:31:22 +03:00
kvfree ( pages ) ;
2020-01-05 00:00:12 +03:00
out :
return ret ;
2017-11-18 02:31:22 +03:00
}
static long gup_benchmark_ioctl ( struct file * filep , unsigned int cmd ,
unsigned long arg )
{
struct gup_benchmark gup ;
int ret ;
2018-10-27 01:09:56 +03:00
switch ( cmd ) {
case GUP_FAST_BENCHMARK :
case GUP_LONGTERM_BENCHMARK :
case GUP_BENCHMARK :
break ;
default :
2017-11-18 02:31:22 +03:00
return - EINVAL ;
2018-10-27 01:09:56 +03:00
}
2017-11-18 02:31:22 +03:00
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 )
{
2019-03-06 02:46:09 +03:00
debugfs_create_file_unsafe ( " gup_benchmark " , 0600 , NULL , NULL ,
& gup_benchmark_fops ) ;
2017-11-18 02:31:22 +03:00
return 0 ;
}
late_initcall ( gup_benchmark_init ) ;