2006-12-13 16:34:23 +08:00
|
|
|
#ifndef _LINUX_SLAB_DEF_H
|
|
|
|
#define _LINUX_SLAB_DEF_H
|
|
|
|
|
reciprocal_divide: update/correction of the algorithm
Jakub Zawadzki noticed that some divisions by reciprocal_divide()
were not correct [1][2], which he could also show with BPF code
after divisions are transformed into reciprocal_value() for runtime
invariance which can be passed to reciprocal_divide() later on;
reverse in BPF dump ended up with a different, off-by-one K in
some situations.
This has been fixed by Eric Dumazet in commit aee636c4809fa5
("bpf: do not use reciprocal divide"). This follow-up patch
improves reciprocal_value() and reciprocal_divide() to work in
all cases by using Granlund and Montgomery method, so that also
future use is safe and without any non-obvious side-effects.
Known problems with the old implementation were that division by 1
always returned 0 and some off-by-ones when the dividend and divisor
where very large. This seemed to not be problematic with its
current users, as far as we can tell. Eric Dumazet checked for
the slab usage, we cannot surely say so in the case of flex_array.
Still, in order to fix that, we propose an extension from the
original implementation from commit 6a2d7a955d8d resp. [3][4],
by using the algorithm proposed in "Division by Invariant Integers
Using Multiplication" [5], Torbjörn Granlund and Peter L.
Montgomery, that is, pseudocode for q = n/d where q, n, d is in
u32 universe:
1) Initialization:
int l = ceil(log_2 d)
uword m' = floor((1<<32)*((1<<l)-d)/d)+1
int sh_1 = min(l,1)
int sh_2 = max(l-1,0)
2) For q = n/d, all uword:
uword t = (n*m')>>32
q = (t+((n-t)>>sh_1))>>sh_2
The assembler implementation from Agner Fog [6] also helped a lot
while implementing. We have tested the implementation on x86_64,
ppc64, i686, s390x; on x86_64/haswell we're still half the latency
compared to normal divide.
Joint work with Daniel Borkmann.
[1] http://www.wireshark.org/~darkjames/reciprocal-buggy.c
[2] http://www.wireshark.org/~darkjames/set-and-dump-filter-k-bug.c
[3] https://gmplib.org/~tege/division-paper.pdf
[4] http://homepage.cs.uiowa.edu/~jones/bcd/divide.html
[5] http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.2556
[6] http://www.agner.org/optimize/asmlib.zip
Reported-by: Jakub Zawadzki <darkjames-ws@darkjames.pl>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Austin S Hemmelgarn <ahferroin7@gmail.com>
Cc: linux-kernel@vger.kernel.org
Cc: Jesse Gross <jesse@nicira.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Andy Gospodarek <andy@greyhouse.net>
Cc: Veaceslav Falico <vfalico@redhat.com>
Cc: Jay Vosburgh <fubar@us.ibm.com>
Cc: Jakub Zawadzki <darkjames-ws@darkjames.pl>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 09:29:41 +08:00
|
|
|
#include <linux/reciprocal_div.h>
|
|
|
|
|
2006-12-13 16:34:23 +08:00
|
|
|
/*
|
|
|
|
* Definitions unique to the original Linux SLAB allocator.
|
2008-05-10 02:32:44 +08:00
|
|
|
*/
|
|
|
|
|
|
|
|
struct kmem_cache {
|
2014-01-21 09:12:42 +08:00
|
|
|
/* 1) Cache tunables. Protected by slab_mutex */
|
2008-05-10 02:32:44 +08:00
|
|
|
unsigned int batchcount;
|
|
|
|
unsigned int limit;
|
|
|
|
unsigned int shared;
|
|
|
|
|
2012-06-13 23:24:57 +08:00
|
|
|
unsigned int size;
|
reciprocal_divide: update/correction of the algorithm
Jakub Zawadzki noticed that some divisions by reciprocal_divide()
were not correct [1][2], which he could also show with BPF code
after divisions are transformed into reciprocal_value() for runtime
invariance which can be passed to reciprocal_divide() later on;
reverse in BPF dump ended up with a different, off-by-one K in
some situations.
This has been fixed by Eric Dumazet in commit aee636c4809fa5
("bpf: do not use reciprocal divide"). This follow-up patch
improves reciprocal_value() and reciprocal_divide() to work in
all cases by using Granlund and Montgomery method, so that also
future use is safe and without any non-obvious side-effects.
Known problems with the old implementation were that division by 1
always returned 0 and some off-by-ones when the dividend and divisor
where very large. This seemed to not be problematic with its
current users, as far as we can tell. Eric Dumazet checked for
the slab usage, we cannot surely say so in the case of flex_array.
Still, in order to fix that, we propose an extension from the
original implementation from commit 6a2d7a955d8d resp. [3][4],
by using the algorithm proposed in "Division by Invariant Integers
Using Multiplication" [5], Torbjörn Granlund and Peter L.
Montgomery, that is, pseudocode for q = n/d where q, n, d is in
u32 universe:
1) Initialization:
int l = ceil(log_2 d)
uword m' = floor((1<<32)*((1<<l)-d)/d)+1
int sh_1 = min(l,1)
int sh_2 = max(l-1,0)
2) For q = n/d, all uword:
uword t = (n*m')>>32
q = (t+((n-t)>>sh_1))>>sh_2
The assembler implementation from Agner Fog [6] also helped a lot
while implementing. We have tested the implementation on x86_64,
ppc64, i686, s390x; on x86_64/haswell we're still half the latency
compared to normal divide.
Joint work with Daniel Borkmann.
[1] http://www.wireshark.org/~darkjames/reciprocal-buggy.c
[2] http://www.wireshark.org/~darkjames/set-and-dump-filter-k-bug.c
[3] https://gmplib.org/~tege/division-paper.pdf
[4] http://homepage.cs.uiowa.edu/~jones/bcd/divide.html
[5] http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.2556
[6] http://www.agner.org/optimize/asmlib.zip
Reported-by: Jakub Zawadzki <darkjames-ws@darkjames.pl>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Austin S Hemmelgarn <ahferroin7@gmail.com>
Cc: linux-kernel@vger.kernel.org
Cc: Jesse Gross <jesse@nicira.com>
Cc: Jamal Hadi Salim <jhs@mojatatu.com>
Cc: Stephen Hemminger <stephen@networkplumber.org>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Christoph Lameter <cl@linux-foundation.org>
Cc: Andy Gospodarek <andy@greyhouse.net>
Cc: Veaceslav Falico <vfalico@redhat.com>
Cc: Jay Vosburgh <fubar@us.ibm.com>
Cc: Jakub Zawadzki <darkjames-ws@darkjames.pl>
Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2014-01-22 09:29:41 +08:00
|
|
|
struct reciprocal_value reciprocal_buffer_size;
|
2011-07-21 01:04:23 +08:00
|
|
|
/* 2) touched by every alloc & free from the backend */
|
2008-05-10 02:32:44 +08:00
|
|
|
|
|
|
|
unsigned int flags; /* constant flags */
|
|
|
|
unsigned int num; /* # of objs per slab */
|
|
|
|
|
2011-07-21 01:04:23 +08:00
|
|
|
/* 3) cache_grow/shrink */
|
2008-05-10 02:32:44 +08:00
|
|
|
/* order of pgs per slab (2^n) */
|
|
|
|
unsigned int gfporder;
|
|
|
|
|
|
|
|
/* force GFP flags, e.g. GFP_DMA */
|
2012-06-14 20:17:21 +08:00
|
|
|
gfp_t allocflags;
|
2008-05-10 02:32:44 +08:00
|
|
|
|
|
|
|
size_t colour; /* cache colouring range */
|
|
|
|
unsigned int colour_off; /* colour offset */
|
2013-10-24 09:07:49 +08:00
|
|
|
struct kmem_cache *freelist_cache;
|
|
|
|
unsigned int freelist_size;
|
2008-05-10 02:32:44 +08:00
|
|
|
|
|
|
|
/* constructor func */
|
|
|
|
void (*ctor)(void *obj);
|
|
|
|
|
2011-07-21 01:04:23 +08:00
|
|
|
/* 4) cache creation/removal */
|
2008-05-10 02:32:44 +08:00
|
|
|
const char *name;
|
2012-06-13 23:24:57 +08:00
|
|
|
struct list_head list;
|
|
|
|
int refcount;
|
|
|
|
int object_size;
|
|
|
|
int align;
|
2008-05-10 02:32:44 +08:00
|
|
|
|
2011-07-21 01:04:23 +08:00
|
|
|
/* 5) statistics */
|
2008-05-10 02:32:44 +08:00
|
|
|
#ifdef CONFIG_DEBUG_SLAB
|
|
|
|
unsigned long num_active;
|
|
|
|
unsigned long num_allocations;
|
|
|
|
unsigned long high_mark;
|
|
|
|
unsigned long grown;
|
|
|
|
unsigned long reaped;
|
|
|
|
unsigned long errors;
|
|
|
|
unsigned long max_freeable;
|
|
|
|
unsigned long node_allocs;
|
|
|
|
unsigned long node_frees;
|
|
|
|
unsigned long node_overflow;
|
|
|
|
atomic_t allochit;
|
|
|
|
atomic_t allocmiss;
|
|
|
|
atomic_t freehit;
|
|
|
|
atomic_t freemiss;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* If debugging is enabled, then the allocator can add additional
|
2012-06-13 23:24:57 +08:00
|
|
|
* fields and/or padding to every object. size contains the total
|
2008-05-10 02:32:44 +08:00
|
|
|
* object size including these internal fields, the following two
|
|
|
|
* variables contain the offset to the user object and its size.
|
|
|
|
*/
|
|
|
|
int obj_offset;
|
|
|
|
#endif /* CONFIG_DEBUG_SLAB */
|
2012-12-19 06:22:27 +08:00
|
|
|
#ifdef CONFIG_MEMCG_KMEM
|
|
|
|
struct memcg_cache_params *memcg_params;
|
|
|
|
#endif
|
2008-05-10 02:32:44 +08:00
|
|
|
|
2011-07-21 01:04:23 +08:00
|
|
|
/* 6) per-cpu/per-node data, touched during every alloc/free */
|
2008-05-10 02:32:44 +08:00
|
|
|
/*
|
2011-07-21 01:04:23 +08:00
|
|
|
* We put array[] at the end of kmem_cache, because we want to size
|
|
|
|
* this array to nr_cpu_ids slots instead of NR_CPUS
|
2008-05-10 02:32:44 +08:00
|
|
|
* (see kmem_cache_init())
|
2011-07-21 01:04:23 +08:00
|
|
|
* We still use [NR_CPUS] and not [1] or [0] because cache_cache
|
|
|
|
* is statically defined, so we reserve the max number of cpus.
|
2012-11-29 00:23:01 +08:00
|
|
|
*
|
|
|
|
* We also need to guarantee that the list is able to accomodate a
|
|
|
|
* pointer for each node since "nodelists" uses the remainder of
|
|
|
|
* available pointers.
|
2008-05-10 02:32:44 +08:00
|
|
|
*/
|
2013-01-11 03:14:19 +08:00
|
|
|
struct kmem_cache_node **node;
|
2012-11-29 00:23:01 +08:00
|
|
|
struct array_cache *array[NR_CPUS + MAX_NUMNODES];
|
2008-05-10 02:32:44 +08:00
|
|
|
/*
|
2011-07-21 01:04:23 +08:00
|
|
|
* Do not add fields after array[]
|
2008-05-10 02:32:44 +08:00
|
|
|
*/
|
|
|
|
};
|
|
|
|
|
2006-12-13 16:34:23 +08:00
|
|
|
#endif /* _LINUX_SLAB_DEF_H */
|