a37fbe666c
The number of times yet another open coded `BITS_TO_LONGS(nbits) * sizeof(long)` can be spotted is huge. Some generic helper is long overdue. Add one, bitmap_size(), but with one detail. BITS_TO_LONGS() uses DIV_ROUND_UP(). The latter works well when both divident and divisor are compile-time constants or when the divisor is not a pow-of-2. When it is however, the compilers sometimes tend to generate suboptimal code (GCC 13): 48 83 c0 3f add $0x3f,%rax 48 c1 e8 06 shr $0x6,%rax 48 8d 14 c5 00 00 00 00 lea 0x0(,%rax,8),%rdx %BITS_PER_LONG is always a pow-2 (either 32 or 64), but GCC still does full division of `nbits + 63` by it and then multiplication by 8. Instead of BITS_TO_LONGS(), use ALIGN() and then divide by 8. GCC: 8d 50 3f lea 0x3f(%rax),%edx c1 ea 03 shr $0x3,%edx 81 e2 f8 ff ff 1f and $0x1ffffff8,%edx Now it shifts `nbits + 63` by 3 positions (IOW performs fast division by 8) and then masks bits[2:0]. bloat-o-meter: add/remove: 0/0 grow/shrink: 20/133 up/down: 156/-773 (-617) Clang does it better and generates the same code before/after starting from -O1, except that with the ALIGN() approach it uses %edx and thus still saves some bytes: add/remove: 0/0 grow/shrink: 9/133 up/down: 18/-538 (-520) Note that we can't expand DIV_ROUND_UP() by adding a check and using this approach there, as it's used in array declarations where expressions are not allowed. Add this helper to tools/ as well. Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com> Acked-by: Yury Norov <yury.norov@gmail.com> Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com> Signed-off-by: David S. Miller <davem@davemloft.net>
103 lines
2.3 KiB
C
103 lines
2.3 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* Copyright IBM Corp. 2007, 2012
|
|
* Author(s): Peter Oberparleiter <peter.oberparleiter@de.ibm.com>
|
|
*/
|
|
|
|
#include <linux/vmalloc.h>
|
|
#include <linux/bitmap.h>
|
|
#include <linux/bitops.h>
|
|
#include "idset.h"
|
|
#include "css.h"
|
|
|
|
struct idset {
|
|
int num_ssid;
|
|
int num_id;
|
|
unsigned long bitmap[];
|
|
};
|
|
|
|
static inline unsigned long idset_bitmap_size(int num_ssid, int num_id)
|
|
{
|
|
return bitmap_size(size_mul(num_ssid, num_id));
|
|
}
|
|
|
|
static struct idset *idset_new(int num_ssid, int num_id)
|
|
{
|
|
struct idset *set;
|
|
|
|
set = vmalloc(sizeof(struct idset) +
|
|
idset_bitmap_size(num_ssid, num_id));
|
|
if (set) {
|
|
set->num_ssid = num_ssid;
|
|
set->num_id = num_id;
|
|
memset(set->bitmap, 0, idset_bitmap_size(num_ssid, num_id));
|
|
}
|
|
return set;
|
|
}
|
|
|
|
void idset_free(struct idset *set)
|
|
{
|
|
vfree(set);
|
|
}
|
|
|
|
void idset_fill(struct idset *set)
|
|
{
|
|
memset(set->bitmap, 0xff,
|
|
idset_bitmap_size(set->num_ssid, set->num_id));
|
|
}
|
|
|
|
static inline void idset_add(struct idset *set, int ssid, int id)
|
|
{
|
|
set_bit(ssid * set->num_id + id, set->bitmap);
|
|
}
|
|
|
|
static inline void idset_del(struct idset *set, int ssid, int id)
|
|
{
|
|
clear_bit(ssid * set->num_id + id, set->bitmap);
|
|
}
|
|
|
|
static inline int idset_contains(struct idset *set, int ssid, int id)
|
|
{
|
|
return test_bit(ssid * set->num_id + id, set->bitmap);
|
|
}
|
|
|
|
struct idset *idset_sch_new(void)
|
|
{
|
|
return idset_new(max_ssid + 1, __MAX_SUBCHANNEL + 1);
|
|
}
|
|
|
|
void idset_sch_add(struct idset *set, struct subchannel_id schid)
|
|
{
|
|
idset_add(set, schid.ssid, schid.sch_no);
|
|
}
|
|
|
|
void idset_sch_del(struct idset *set, struct subchannel_id schid)
|
|
{
|
|
idset_del(set, schid.ssid, schid.sch_no);
|
|
}
|
|
|
|
/* Clear ids starting from @schid up to end of subchannel set. */
|
|
void idset_sch_del_subseq(struct idset *set, struct subchannel_id schid)
|
|
{
|
|
int pos = schid.ssid * set->num_id + schid.sch_no;
|
|
|
|
bitmap_clear(set->bitmap, pos, set->num_id - schid.sch_no);
|
|
}
|
|
|
|
int idset_sch_contains(struct idset *set, struct subchannel_id schid)
|
|
{
|
|
return idset_contains(set, schid.ssid, schid.sch_no);
|
|
}
|
|
|
|
int idset_is_empty(struct idset *set)
|
|
{
|
|
return bitmap_empty(set->bitmap, set->num_ssid * set->num_id);
|
|
}
|
|
|
|
void idset_add_set(struct idset *to, struct idset *from)
|
|
{
|
|
int len = min(to->num_ssid * to->num_id, from->num_ssid * from->num_id);
|
|
|
|
bitmap_or(to->bitmap, to->bitmap, from->bitmap, len);
|
|
}
|