aha/lib/cpumask.c

178 lines
4.5 KiB
C
Raw Permalink Normal View History

#include <linux/kernel.h>
#include <linux/bitops.h>
#include <linux/cpumask.h>
#include <linux/module.h>
#include <linux/bootmem.h>
int __first_cpu(const cpumask_t *srcp)
{
return min_t(int, NR_CPUS, find_first_bit(srcp->bits, NR_CPUS));
}
EXPORT_SYMBOL(__first_cpu);
int __next_cpu(int n, const cpumask_t *srcp)
{
return min_t(int, NR_CPUS, find_next_bit(srcp->bits, NR_CPUS, n+1));
}
EXPORT_SYMBOL(__next_cpu);
x86: Add performance variants of cpumask operators * Increase performance for systems with large count NR_CPUS by limiting the range of the cpumask operators that loop over the bits in a cpumask_t variable. This removes a large amount of wasted cpu cycles. * Add performance variants of the cpumask operators: int cpus_weight_nr(mask) Same using nr_cpu_ids instead of NR_CPUS int first_cpu_nr(mask) Number lowest set bit, or nr_cpu_ids int next_cpu_nr(cpu, mask) Next cpu past 'cpu', or nr_cpu_ids for_each_cpu_mask_nr(cpu, mask) for-loop cpu over mask using nr_cpu_ids * Modify following to use performance variants: #define num_online_cpus() cpus_weight_nr(cpu_online_map) #define num_possible_cpus() cpus_weight_nr(cpu_possible_map) #define num_present_cpus() cpus_weight_nr(cpu_present_map) #define for_each_possible_cpu(cpu) for_each_cpu_mask_nr((cpu), ...) #define for_each_online_cpu(cpu) for_each_cpu_mask_nr((cpu), ...) #define for_each_present_cpu(cpu) for_each_cpu_mask_nr((cpu), ...) * Comment added to include/linux/cpumask.h: Note: The alternate operations with the suffix "_nr" are used to limit the range of the loop to nr_cpu_ids instead of NR_CPUS when NR_CPUS > 64 for performance reasons. If NR_CPUS is <= 64 then most assembler bitmask operators execute faster with a constant range, so the operator will continue to use NR_CPUS. Another consideration is that nr_cpu_ids is initialized to NR_CPUS and isn't lowered until the possible cpus are discovered (including any disabled cpus). So early uses will span the entire range of NR_CPUS. (The net effect is that for systems with 64 or less CPU's there are no functional changes.) For inclusion into sched-devel/latest tree. Based on: git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6.git + sched-devel/latest .../mingo/linux-2.6-sched-devel.git Cc: Paul Jackson <pj@sgi.com> Cc: Christoph Lameter <clameter@sgi.com> Reviewed-by: Paul Jackson <pj@sgi.com> Reviewed-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Mike Travis <travis@sgi.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-05-12 19:21:13 +00:00
#if NR_CPUS > 64
int __next_cpu_nr(int n, const cpumask_t *srcp)
{
return min_t(int, nr_cpu_ids,
find_next_bit(srcp->bits, nr_cpu_ids, n+1));
}
EXPORT_SYMBOL(__next_cpu_nr);
#endif
int __any_online_cpu(const cpumask_t *mask)
{
int cpu;
for_each_cpu_mask(cpu, *mask) {
if (cpu_online(cpu))
break;
}
return cpu;
}
EXPORT_SYMBOL(__any_online_cpu);
/**
* cpumask_next_and - get the next cpu in *src1p & *src2p
* @n: the cpu prior to the place to search (ie. return will be > @n)
* @src1p: the first cpumask pointer
* @src2p: the second cpumask pointer
*
* Returns >= nr_cpu_ids if no further cpus set in both.
*/
int cpumask_next_and(int n, const struct cpumask *src1p,
const struct cpumask *src2p)
{
while ((n = cpumask_next(n, src1p)) < nr_cpu_ids)
if (cpumask_test_cpu(n, src2p))
break;
return n;
}
EXPORT_SYMBOL(cpumask_next_and);
/**
* cpumask_any_but - return a "random" in a cpumask, but not this one.
* @mask: the cpumask to search
* @cpu: the cpu to ignore.
*
* Often used to find any cpu but smp_processor_id() in a mask.
* Returns >= nr_cpu_ids if no cpus set.
*/
int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
{
unsigned int i;
cpumask_check(cpu);
for_each_cpu(i, mask)
if (i != cpu)
break;
return i;
}
/* These are not inline because of header tangles. */
#ifdef CONFIG_CPUMASK_OFFSTACK
/**
* alloc_cpumask_var_node - allocate a struct cpumask on a given node
* @mask: pointer to cpumask_var_t where the cpumask is returned
* @flags: GFP_ flags
*
* Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is
* a nop returning a constant 1 (in <linux/cpumask.h>)
* Returns TRUE if memory allocation succeeded, FALSE otherwise.
*
* In addition, mask will be NULL if this fails. Note that gcc is
* usually smart enough to know that mask can never be NULL if
* CONFIG_CPUMASK_OFFSTACK=n, so does code elimination in that case
* too.
*/
bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
{
*mask = kmalloc_node(cpumask_size(), flags, node);
#ifdef CONFIG_DEBUG_PER_CPU_MAPS
if (!*mask) {
printk(KERN_ERR "=> alloc_cpumask_var: failed!\n");
dump_stack();
}
#endif
/* FIXME: Bandaid to save us from old primitives which go to NR_CPUS. */
if (*mask) {
unsigned char *ptr = (unsigned char *)cpumask_bits(*mask);
unsigned int tail;
tail = BITS_TO_LONGS(NR_CPUS - nr_cpumask_bits) * sizeof(long);
memset(ptr + cpumask_size() - tail, 0, tail);
}
return *mask != NULL;
}
EXPORT_SYMBOL(alloc_cpumask_var_node);
bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
{
return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node);
}
EXPORT_SYMBOL(zalloc_cpumask_var_node);
/**
* alloc_cpumask_var - allocate a struct cpumask
* @mask: pointer to cpumask_var_t where the cpumask is returned
* @flags: GFP_ flags
*
* Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is
* a nop returning a constant 1 (in <linux/cpumask.h>).
*
* See alloc_cpumask_var_node.
*/
bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
{
return alloc_cpumask_var_node(mask, flags, numa_node_id());
}
EXPORT_SYMBOL(alloc_cpumask_var);
bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
{
return alloc_cpumask_var(mask, flags | __GFP_ZERO);
}
EXPORT_SYMBOL(zalloc_cpumask_var);
/**
* alloc_bootmem_cpumask_var - allocate a struct cpumask from the bootmem arena.
* @mask: pointer to cpumask_var_t where the cpumask is returned
*
* Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is
* a nop (in <linux/cpumask.h>).
* Either returns an allocated (zero-filled) cpumask, or causes the
* system to panic.
*/
void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask)
{
*mask = alloc_bootmem(cpumask_size());
}
/**
* free_cpumask_var - frees memory allocated for a struct cpumask.
* @mask: cpumask to free
*
* This is safe on a NULL mask.
*/
void free_cpumask_var(cpumask_var_t mask)
{
kfree(mask);
}
EXPORT_SYMBOL(free_cpumask_var);
/**
* free_bootmem_cpumask_var - frees result of alloc_bootmem_cpumask_var
* @mask: cpumask to free
*/
void __init free_bootmem_cpumask_var(cpumask_var_t mask)
{
free_bootmem((unsigned long)mask, cpumask_size());
}
#endif