mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-24 21:24:00 +08:00
809fa972fd
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 commitaee636c480("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 commit6a2d7a955dresp. [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>
82 lines
2.4 KiB
C
82 lines
2.4 KiB
C
#ifndef _FLEX_ARRAY_H
|
|
#define _FLEX_ARRAY_H
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/reciprocal_div.h>
|
|
#include <asm/page.h>
|
|
|
|
#define FLEX_ARRAY_PART_SIZE PAGE_SIZE
|
|
#define FLEX_ARRAY_BASE_SIZE PAGE_SIZE
|
|
|
|
struct flex_array_part;
|
|
|
|
/*
|
|
* This is meant to replace cases where an array-like
|
|
* structure has gotten too big to fit into kmalloc()
|
|
* and the developer is getting tempted to use
|
|
* vmalloc().
|
|
*/
|
|
|
|
struct flex_array {
|
|
union {
|
|
struct {
|
|
int element_size;
|
|
int total_nr_elements;
|
|
int elems_per_part;
|
|
struct reciprocal_value reciprocal_elems;
|
|
struct flex_array_part *parts[];
|
|
};
|
|
/*
|
|
* This little trick makes sure that
|
|
* sizeof(flex_array) == PAGE_SIZE
|
|
*/
|
|
char padding[FLEX_ARRAY_BASE_SIZE];
|
|
};
|
|
};
|
|
|
|
/* Number of bytes left in base struct flex_array, excluding metadata */
|
|
#define FLEX_ARRAY_BASE_BYTES_LEFT \
|
|
(FLEX_ARRAY_BASE_SIZE - offsetof(struct flex_array, parts))
|
|
|
|
/* Number of pointers in base to struct flex_array_part pages */
|
|
#define FLEX_ARRAY_NR_BASE_PTRS \
|
|
(FLEX_ARRAY_BASE_BYTES_LEFT / sizeof(struct flex_array_part *))
|
|
|
|
/* Number of elements of size that fit in struct flex_array_part */
|
|
#define FLEX_ARRAY_ELEMENTS_PER_PART(size) \
|
|
(FLEX_ARRAY_PART_SIZE / size)
|
|
|
|
/*
|
|
* Defines a statically allocated flex array and ensures its parameters are
|
|
* valid.
|
|
*/
|
|
#define DEFINE_FLEX_ARRAY(__arrayname, __element_size, __total) \
|
|
struct flex_array __arrayname = { { { \
|
|
.element_size = (__element_size), \
|
|
.total_nr_elements = (__total), \
|
|
} } }; \
|
|
static inline void __arrayname##_invalid_parameter(void) \
|
|
{ \
|
|
BUILD_BUG_ON((__total) > FLEX_ARRAY_NR_BASE_PTRS * \
|
|
FLEX_ARRAY_ELEMENTS_PER_PART(__element_size)); \
|
|
}
|
|
|
|
struct flex_array *flex_array_alloc(int element_size, unsigned int total,
|
|
gfp_t flags);
|
|
int flex_array_prealloc(struct flex_array *fa, unsigned int start,
|
|
unsigned int nr_elements, gfp_t flags);
|
|
void flex_array_free(struct flex_array *fa);
|
|
void flex_array_free_parts(struct flex_array *fa);
|
|
int flex_array_put(struct flex_array *fa, unsigned int element_nr, void *src,
|
|
gfp_t flags);
|
|
int flex_array_clear(struct flex_array *fa, unsigned int element_nr);
|
|
void *flex_array_get(struct flex_array *fa, unsigned int element_nr);
|
|
int flex_array_shrink(struct flex_array *fa);
|
|
|
|
#define flex_array_put_ptr(fa, nr, src, gfp) \
|
|
flex_array_put(fa, nr, (void *)&(src), gfp)
|
|
|
|
void *flex_array_get_ptr(struct flex_array *fa, unsigned int element_nr);
|
|
|
|
#endif /* _FLEX_ARRAY_H */
|