2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-27 06:34:11 +08:00
linux-next/lib/cpumask.c
Alex Belits 1abdfe706a lib: Restrict cpumask_local_spread to houskeeping CPUs
The current implementation of cpumask_local_spread() does not respect the
isolated CPUs, i.e., even if a CPU has been isolated for Real-Time task,
it will return it to the caller for pinning of its IRQ threads. Having
these unwanted IRQ threads on an isolated CPU adds up to a latency
overhead.

Restrict the CPUs that are returned for spreading IRQs only to the
available housekeeping CPUs.

Signed-off-by: Alex Belits <abelits@marvell.com>
Signed-off-by: Nitesh Narayan Lal <nitesh@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200625223443.2684-2-nitesh@redhat.com
2020-07-08 11:39:01 +02:00

270 lines
6.8 KiB
C

// SPDX-License-Identifier: GPL-2.0
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/bitops.h>
#include <linux/cpumask.h>
#include <linux/export.h>
#include <linux/memblock.h>
#include <linux/numa.h>
#include <linux/sched/isolation.h>
/**
* cpumask_next - get the next cpu in a cpumask
* @n: the cpu prior to the place to search (ie. return will be > @n)
* @srcp: the cpumask pointer
*
* Returns >= nr_cpu_ids if no further cpus set.
*/
unsigned int cpumask_next(int n, const struct cpumask *srcp)
{
/* -1 is a legal arg here. */
if (n != -1)
cpumask_check(n);
return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1);
}
EXPORT_SYMBOL(cpumask_next);
/**
* 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)
{
/* -1 is a legal arg here. */
if (n != -1)
cpumask_check(n);
return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p),
nr_cpumask_bits, n + 1);
}
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;
}
EXPORT_SYMBOL(cpumask_any_but);
/**
* cpumask_next_wrap - helper to implement for_each_cpu_wrap
* @n: the cpu prior to the place to search
* @mask: the cpumask pointer
* @start: the start point of the iteration
* @wrap: assume @n crossing @start terminates the iteration
*
* Returns >= nr_cpu_ids on completion
*
* Note: the @wrap argument is required for the start condition when
* we cannot assume @start is set in @mask.
*/
int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
{
int next;
again:
next = cpumask_next(n, mask);
if (wrap && n < start && next >= start) {
return nr_cpumask_bits;
} else if (next >= nr_cpumask_bits) {
wrap = true;
n = -1;
goto again;
}
return next;
}
EXPORT_SYMBOL(cpumask_next_wrap);
/* 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
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_NO_NODE);
}
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 = memblock_alloc(cpumask_size(), SMP_CACHE_BYTES);
if (!*mask)
panic("%s: Failed to allocate %u bytes\n", __func__,
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)
{
memblock_free_early(__pa(mask), cpumask_size());
}
#endif
/**
* cpumask_local_spread - select the i'th cpu with local numa cpu's first
* @i: index number
* @node: local numa_node
*
* This function selects an online CPU according to a numa aware policy;
* local cpus are returned first, followed by non-local ones, then it
* wraps around.
*
* It's not very efficient, but useful for setup.
*/
unsigned int cpumask_local_spread(unsigned int i, int node)
{
int cpu, hk_flags;
const struct cpumask *mask;
hk_flags = HK_FLAG_DOMAIN | HK_FLAG_MANAGED_IRQ;
mask = housekeeping_cpumask(hk_flags);
/* Wrap: we always want a cpu. */
i %= cpumask_weight(mask);
if (node == NUMA_NO_NODE) {
for_each_cpu(cpu, mask) {
if (i-- == 0)
return cpu;
}
} else {
/* NUMA first. */
for_each_cpu_and(cpu, cpumask_of_node(node), mask) {
if (i-- == 0)
return cpu;
}
for_each_cpu(cpu, mask) {
/* Skip NUMA nodes, done above. */
if (cpumask_test_cpu(cpu, cpumask_of_node(node)))
continue;
if (i-- == 0)
return cpu;
}
}
BUG();
}
EXPORT_SYMBOL(cpumask_local_spread);
static DEFINE_PER_CPU(int, distribute_cpu_mask_prev);
/**
* Returns an arbitrary cpu within srcp1 & srcp2.
*
* Iterated calls using the same srcp1 and srcp2 will be distributed within
* their intersection.
*
* Returns >= nr_cpu_ids if the intersection is empty.
*/
int cpumask_any_and_distribute(const struct cpumask *src1p,
const struct cpumask *src2p)
{
int next, prev;
/* NOTE: our first selection will skip 0. */
prev = __this_cpu_read(distribute_cpu_mask_prev);
next = cpumask_next_and(prev, src1p, src2p);
if (next >= nr_cpu_ids)
next = cpumask_first_and(src1p, src2p);
if (next < nr_cpu_ids)
__this_cpu_write(distribute_cpu_mask_prev, next);
return next;
}
EXPORT_SYMBOL(cpumask_any_and_distribute);