redonkable
/
alistair23-linux
1
0
Fork 0
Code Releases Activity

cpumask: reduce stack usage in SD_x_INIT initializers 

* Remove empty cpumask_t (and all non-zero/non-null) variables
    in SD_*_INIT macros.  Use memset(0) to clear.  Also, don't
    inline the initializer functions to save on stack space in
    build_sched_domains().

  * Merge change to include/linux/topology.h that uses the new
    node_to_cpumask_ptr function in the nr_cpus_node macro into
    this patch.

Depends on:
	[mm-patch]: asm-generic-add-node_to_cpumask_ptr-macro.patch
	[sched-devel]: sched: add new set_cpus_allowed_ptr function

Cc: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Mike Travis <travis@sgi.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
hifive-unleashed-5.1
Mike Travis 2008-04-04 18:11:11 -07:00 committed by Ingo Molnar
parent c5f59f0833
commit 7c16ec585c
3 changed files with 256 additions and 163 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
include/asm-x86/topology.h
View File

@ -154,10 +154,6 @@ extern unsigned long node_remap_size[];
/* sched_domains SD_NODE_INIT for NUMAQ machines */
#define SD_NODE_INIT (struct sched_domain) { \
.span = CPU_MASK_NONE, \
.parent = NULL, \
.child = NULL, \
.groups = NULL, \
.min_interval = 8, \
.max_interval = 32, \
.busy_factor = 32, \
@ -175,7 +171,6 @@ extern unsigned long node_remap_size[];
| SD_WAKE_BALANCE, \
.last_balance = jiffies, \
.balance_interval = 1, \
.nr_balance_failed = 0, \
}
#ifdef CONFIG_X86_64_ACPI_NUMA

46
include/linux/topology.h
View File

@ -38,16 +38,15 @@
#endif
#ifndef nr_cpus_node
#define nr_cpus_node(node) \
({ \
cpumask_t __tmp__; \
__tmp__ = node_to_cpumask(node); \
cpus_weight(__tmp__); \
#define nr_cpus_node(node) \
({ \
node_to_cpumask_ptr(__tmp__, node); \
cpus_weight(*__tmp__); \
})
#endif
#define for_each_node_with_cpus(node) \
for_each_online_node(node) \
#define for_each_node_with_cpus(node) \
for_each_online_node(node) \
if (nr_cpus_node(node))
void arch_update_cpu_topology(void);
@ -80,7 +79,9 @@ void arch_update_cpu_topology(void);
* by defining their own arch-specific initializer in include/asm/topology.h.
* A definition there will automagically override these default initializers
* and allow arch-specific performance tuning of sched_domains.
* (Only non-zero and non-null fields need be specified.)
*/
#ifdef CONFIG_SCHED_SMT
/* MCD - Do we really need this? It is always on if CONFIG_SCHED_SMT is,
* so can't we drop this in favor of CONFIG_SCHED_SMT?
@ -89,20 +90,10 @@ void arch_update_cpu_topology(void);
/* Common values for SMT siblings */
#ifndef SD_SIBLING_INIT
#define SD_SIBLING_INIT (struct sched_domain) { \
.span = CPU_MASK_NONE, \
.parent = NULL, \
.child = NULL, \
.groups = NULL, \
.min_interval = 1, \
.max_interval = 2, \
.busy_factor = 64, \
.imbalance_pct = 110, \
.cache_nice_tries = 0, \
.busy_idx = 0, \
.idle_idx = 0, \
.newidle_idx = 0, \
.wake_idx = 0, \
.forkexec_idx = 0, \
.flags = SD_LOAD_BALANCE \
| SD_BALANCE_NEWIDLE \
| SD_BALANCE_FORK \
@ -112,7 +103,6 @@ void arch_update_cpu_topology(void);
| SD_SHARE_CPUPOWER, \
.last_balance = jiffies, \
.balance_interval = 1, \
.nr_balance_failed = 0, \
}
#endif
#endif /* CONFIG_SCHED_SMT */
@ -121,18 +111,12 @@ void arch_update_cpu_topology(void);
/* Common values for MC siblings. for now mostly derived from SD_CPU_INIT */
#ifndef SD_MC_INIT
#define SD_MC_INIT (struct sched_domain) { \
.span = CPU_MASK_NONE, \
.parent = NULL, \
.child = NULL, \
.groups = NULL, \
.min_interval = 1, \
.max_interval = 4, \
.busy_factor = 64, \
.imbalance_pct = 125, \
.cache_nice_tries = 1, \
.busy_idx = 2, \
.idle_idx = 0, \
.newidle_idx = 0, \
.wake_idx = 1, \
.forkexec_idx = 1, \
.flags = SD_LOAD_BALANCE \
@ -144,7 +128,6 @@ void arch_update_cpu_topology(void);
| BALANCE_FOR_MC_POWER, \
.last_balance = jiffies, \
.balance_interval = 1, \
.nr_balance_failed = 0, \
}
#endif
#endif /* CONFIG_SCHED_MC */
@ -152,10 +135,6 @@ void arch_update_cpu_topology(void);
/* Common values for CPUs */
#ifndef SD_CPU_INIT
#define SD_CPU_INIT (struct sched_domain) { \
.span = CPU_MASK_NONE, \
.parent = NULL, \
.child = NULL, \
.groups = NULL, \
.min_interval = 1, \
.max_interval = 4, \
.busy_factor = 64, \
@ -174,16 +153,11 @@ void arch_update_cpu_topology(void);
| BALANCE_FOR_PKG_POWER,\
.last_balance = jiffies, \
.balance_interval = 1, \
.nr_balance_failed = 0, \
}
#endif
/* sched_domains SD_ALLNODES_INIT for NUMA machines */
#define SD_ALLNODES_INIT (struct sched_domain) { \
.span = CPU_MASK_NONE, \
.parent = NULL, \
.child = NULL, \
.groups = NULL, \
.min_interval = 64, \
.max_interval = 64*num_online_cpus(), \
.busy_factor = 128, \
@ -191,14 +165,10 @@ void arch_update_cpu_topology(void);
.cache_nice_tries = 1, \
.busy_idx = 3, \
.idle_idx = 3, \
.newidle_idx = 0, /* unused */ \
.wake_idx = 0, /* unused */ \
.forkexec_idx = 0, /* unused */ \
.flags = SD_LOAD_BALANCE \
| SD_SERIALIZE, \
.last_balance = jiffies, \
.balance_interval = 64, \
.nr_balance_failed = 0, \
}
#ifdef CONFIG_NUMA

368
kernel/sched.c
View File

@ -1869,17 +1869,17 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
* find_idlest_cpu - find the idlest cpu among the cpus in group.
*/
static int
find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu,
cpumask_t *tmp)
{
cpumask_t tmp;
unsigned long load, min_load = ULONG_MAX;
int idlest = -1;
int i;
/* Traverse only the allowed CPUs */
cpus_and(tmp, group->cpumask, p->cpus_allowed);
cpus_and(*tmp, group->cpumask, p->cpus_allowed);
for_each_cpu_mask(i, tmp) {
for_each_cpu_mask(i, *tmp) {
load = weighted_cpuload(i);
if (load < min_load || (load == min_load && i == this_cpu)) {
@ -1918,7 +1918,7 @@ static int sched_balance_self(int cpu, int flag)
}
while (sd) {
cpumask_t span;
cpumask_t span, tmpmask;
struct sched_group *group;
int new_cpu, weight;
@ -1934,7 +1934,7 @@ static int sched_balance_self(int cpu, int flag)
continue;
}
new_cpu = find_idlest_cpu(group, t, cpu);
new_cpu = find_idlest_cpu(group, t, cpu, &tmpmask);
if (new_cpu == -1 || new_cpu == cpu) {
/* Now try balancing at a lower domain level of cpu */
sd = sd->child;
@ -2818,7 +2818,7 @@ static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
static struct sched_group *
find_busiest_group(struct sched_domain *sd, int this_cpu,
unsigned long *imbalance, enum cpu_idle_type idle,
int *sd_idle, cpumask_t *cpus, int *balance)
int *sd_idle, const cpumask_t *cpus, int *balance)
{
struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups;
unsigned long max_load, avg_load, total_load, this_load, total_pwr;
@ -3119,7 +3119,7 @@ ret:
*/
static struct rq *
find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
unsigned long imbalance, cpumask_t *cpus)
unsigned long imbalance, const cpumask_t *cpus)
{
struct rq *busiest = NULL, *rq;
unsigned long max_load = 0;
@ -3158,15 +3158,16 @@ find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
*/
static int load_balance(int this_cpu, struct rq *this_rq,
struct sched_domain *sd, enum cpu_idle_type idle,
int *balance)
int *balance, cpumask_t *cpus)
{
int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
struct sched_group *group;
unsigned long imbalance;
struct rq *busiest;
cpumask_t cpus = CPU_MASK_ALL;
unsigned long flags;
cpus_setall(*cpus);
/*
* When power savings policy is enabled for the parent domain, idle
* sibling can pick up load irrespective of busy siblings. In this case,
@ -3181,7 +3182,7 @@ static int load_balance(int this_cpu, struct rq *this_rq,
redo:
group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle,
&cpus, balance);
cpus, balance);
if (*balance == 0)
goto out_balanced;
@ -3191,7 +3192,7 @@ redo:
goto out_balanced;
}
busiest = find_busiest_queue(group, idle, imbalance, &cpus);
busiest = find_busiest_queue(group, idle, imbalance, cpus);
if (!busiest) {
schedstat_inc(sd, lb_nobusyq[idle]);
goto out_balanced;
@ -3224,8 +3225,8 @@ redo:
/* All tasks on this runqueue were pinned by CPU affinity */
if (unlikely(all_pinned)) {
cpu_clear(cpu_of(busiest), cpus);
if (!cpus_empty(cpus))
cpu_clear(cpu_of(busiest), *cpus);
if (!cpus_empty(*cpus))
goto redo;
goto out_balanced;
}
@ -3310,7 +3311,8 @@ out_one_pinned:
* this_rq is locked.
*/
static int
load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd,
cpumask_t *cpus)
{
struct sched_group *group;
struct rq *busiest = NULL;
@ -3318,7 +3320,8 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
int ld_moved = 0;
int sd_idle = 0;
int all_pinned = 0;
cpumask_t cpus = CPU_MASK_ALL;
cpus_setall(*cpus);
/*
* When power savings policy is enabled for the parent domain, idle
@ -3333,14 +3336,13 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
schedstat_inc(sd, lb_count[CPU_NEWLY_IDLE]);
redo:
group = find_busiest_group(sd, this_cpu, &imbalance, CPU_NEWLY_IDLE,
&sd_idle, &cpus, NULL);
&sd_idle, cpus, NULL);
if (!group) {
schedstat_inc(sd, lb_nobusyg[CPU_NEWLY_IDLE]);
goto out_balanced;
}
busiest = find_busiest_queue(group, CPU_NEWLY_IDLE, imbalance,
&cpus);
busiest = find_busiest_queue(group, CPU_NEWLY_IDLE, imbalance, cpus);
if (!busiest) {
schedstat_inc(sd, lb_nobusyq[CPU_NEWLY_IDLE]);
goto out_balanced;
@ -3362,8 +3364,8 @@ redo:
spin_unlock(&busiest->lock);
if (unlikely(all_pinned)) {
cpu_clear(cpu_of(busiest), cpus);
if (!cpus_empty(cpus))
cpu_clear(cpu_of(busiest), *cpus);
if (!cpus_empty(*cpus))
goto redo;
}
}
@ -3397,6 +3399,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
struct sched_domain *sd;
int pulled_task = -1;
unsigned long next_balance = jiffies + HZ;
cpumask_t tmpmask;
for_each_domain(this_cpu, sd) {
unsigned long interval;
@ -3406,8 +3409,8 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
if (sd->flags & SD_BALANCE_NEWIDLE)
/* If we've pulled tasks over stop searching: */
pulled_task = load_balance_newidle(this_cpu,
this_rq, sd);
pulled_task = load_balance_newidle(this_cpu, this_rq,
sd, &tmpmask);
interval = msecs_to_jiffies(sd->balance_interval);
if (time_after(next_balance, sd->last_balance + interval))
@ -3566,6 +3569,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
/* Earliest time when we have to do rebalance again */
unsigned long next_balance = jiffies + 60*HZ;
int update_next_balance = 0;
cpumask_t tmp;
for_each_domain(cpu, sd) {
if (!(sd->flags & SD_LOAD_BALANCE))
@ -3589,7 +3593,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
}
if (time_after_eq(jiffies, sd->last_balance + interval)) {
if (load_balance(cpu, rq, sd, idle, &balance)) {
if (load_balance(cpu, rq, sd, idle, &balance, &tmp)) {
/*
* We've pulled tasks over so either we're no
* longer idle, or one of our SMT siblings is
@ -4945,7 +4949,7 @@ long sched_setaffinity(pid_t pid, const cpumask_t *in_mask)
cpuset_cpus_allowed(p, &cpus_allowed);
cpus_and(new_mask, new_mask, cpus_allowed);
again:
retval = set_cpus_allowed(p, new_mask);
retval = set_cpus_allowed_ptr(p, &new_mask);
if (!retval) {
cpuset_cpus_allowed(p, &cpus_allowed);
@ -5700,7 +5704,7 @@ static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
*/
static void migrate_nr_uninterruptible(struct rq *rq_src)
{
struct rq *rq_dest = cpu_rq(any_online_cpu(CPU_MASK_ALL));
struct rq *rq_dest = cpu_rq(any_online_cpu(*CPU_MASK_ALL_PTR));
unsigned long flags;
local_irq_save(flags);
@ -6118,14 +6122,14 @@ EXPORT_SYMBOL(nr_cpu_ids);
#ifdef CONFIG_SCHED_DEBUG
static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level)
static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
cpumask_t *groupmask)
{
struct sched_group *group = sd->groups;
cpumask_t groupmask;
char str[256];
cpulist_scnprintf(str, sizeof(str), sd->span);
cpus_clear(groupmask);
cpus_clear(*groupmask);
printk(KERN_DEBUG "%*s domain %d: ", level, "", level);
@ -6169,13 +6173,13 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level)
break;
}
if (cpus_intersects(groupmask, group->cpumask)) {
if (cpus_intersects(*groupmask, group->cpumask)) {
printk(KERN_CONT "\n");
printk(KERN_ERR "ERROR: repeated CPUs\n");
break;
}
cpus_or(groupmask, groupmask, group->cpumask);
cpus_or(*groupmask, *groupmask, group->cpumask);
cpulist_scnprintf(str, sizeof(str), group->cpumask);
printk(KERN_CONT " %s", str);
@ -6184,10 +6188,10 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level)
} while (group != sd->groups);
printk(KERN_CONT "\n");
if (!cpus_equal(sd->span, groupmask))
if (!cpus_equal(sd->span, *groupmask))
printk(KERN_ERR "ERROR: groups don't span domain->span\n");
if (sd->parent && !cpus_subset(groupmask, sd->parent->span))
if (sd->parent && !cpus_subset(*groupmask, sd->parent->span))
printk(KERN_ERR "ERROR: parent span is not a superset "
"of domain->span\n");
return 0;
@ -6195,6 +6199,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level)
static void sched_domain_debug(struct sched_domain *sd, int cpu)
{
cpumask_t *groupmask;
int level = 0;
if (!sd) {
@ -6204,14 +6209,21 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu)
printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu);
groupmask = kmalloc(sizeof(cpumask_t), GFP_KERNEL);
if (!groupmask) {
printk(KERN_DEBUG "Cannot load-balance (out of memory)\n");
return;
}
for (;;) {
if (sched_domain_debug_one(sd, cpu, level))
if (sched_domain_debug_one(sd, cpu, level, groupmask))
break;
level++;
sd = sd->parent;
if (!sd)
break;
}
kfree(groupmask);
}
#else
# define sched_domain_debug(sd, cpu) do { } while (0)
@ -6399,30 +6411,33 @@ __setup("isolcpus=", isolated_cpu_setup);
* and ->cpu_power to 0.
*/
static void
init_sched_build_groups(cpumask_t span, const cpumask_t *cpu_map,
init_sched_build_groups(const cpumask_t *span, const cpumask_t *cpu_map,
int (*group_fn)(int cpu, const cpumask_t *cpu_map,
struct sched_group **sg))
struct sched_group **sg,
cpumask_t *tmpmask),
cpumask_t *covered, cpumask_t *tmpmask)
{
struct sched_group *first = NULL, *last = NULL;
cpumask_t covered = CPU_MASK_NONE;
int i;
for_each_cpu_mask(i, span) {
cpus_clear(*covered);
for_each_cpu_mask(i, *span) {
struct sched_group *sg;
int group = group_fn(i, cpu_map, &sg);
int group = group_fn(i, cpu_map, &sg, tmpmask);
int j;
if (cpu_isset(i, covered))
if (cpu_isset(i, *covered))
continue;
sg->cpumask = CPU_MASK_NONE;
cpus_clear(sg->cpumask);
sg->__cpu_power = 0;
for_each_cpu_mask(j, span) {
if (group_fn(j, cpu_map, NULL) != group)
for_each_cpu_mask(j, *span) {
if (group_fn(j, cpu_map, NULL, tmpmask) != group)
continue;
cpu_set(j, covered);
cpu_set(j, *covered);
cpu_set(j, sg->cpumask);
}
if (!first)
@ -6520,7 +6535,8 @@ static DEFINE_PER_CPU(struct sched_domain, cpu_domains);
static DEFINE_PER_CPU(struct sched_group, sched_group_cpus);
static int
cpu_to_cpu_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg)
cpu_to_cpu_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg,
cpumask_t *unused)
{
if (sg)
*sg = &per_cpu(sched_group_cpus, cpu);
@ -6538,19 +6554,22 @@ static DEFINE_PER_CPU(struct sched_group, sched_group_core);
#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)
static int
cpu_to_core_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg)
cpu_to_core_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg,
cpumask_t *mask)
{
int group;
cpumask_t mask = per_cpu(cpu_sibling_map, cpu);
cpus_and(mask, mask, *cpu_map);
group = first_cpu(mask);
*mask = per_cpu(cpu_sibling_map, cpu);
cpus_and(*mask, *mask, *cpu_map);
group = first_cpu(*mask);
if (sg)
*sg = &per_cpu(sched_group_core, group);
return group;
}
#elif defined(CONFIG_SCHED_MC)
static int
cpu_to_core_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg)
cpu_to_core_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg,
cpumask_t *unused)
{
if (sg)
*sg = &per_cpu(sched_group_core, cpu);
@ -6562,17 +6581,18 @@ static DEFINE_PER_CPU(struct sched_domain, phys_domains);
static DEFINE_PER_CPU(struct sched_group, sched_group_phys);
static int
cpu_to_phys_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg)
cpu_to_phys_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg,
cpumask_t *mask)
{
int group;
#ifdef CONFIG_SCHED_MC
cpumask_t mask = cpu_coregroup_map(cpu);
cpus_and(mask, mask, *cpu_map);
group = first_cpu(mask);
*mask = cpu_coregroup_map(cpu);
cpus_and(*mask, *mask, *cpu_map);
group = first_cpu(*mask);
#elif defined(CONFIG_SCHED_SMT)
cpumask_t mask = per_cpu(cpu_sibling_map, cpu);
cpus_and(mask, mask, *cpu_map);
group = first_cpu(mask);
*mask = per_cpu(cpu_sibling_map, cpu);
cpus_and(*mask, *mask, *cpu_map);
group = first_cpu(*mask);
#else
group = cpu;
#endif
@ -6594,13 +6614,13 @@ static DEFINE_PER_CPU(struct sched_domain, allnodes_domains);
static DEFINE_PER_CPU(struct sched_group, sched_group_allnodes);
static int cpu_to_allnodes_group(int cpu, const cpumask_t *cpu_map,
struct sched_group **sg)
struct sched_group **sg, cpumask_t *nodemask)
{
cpumask_t nodemask = node_to_cpumask(cpu_to_node(cpu));
int group;
cpus_and(nodemask, nodemask, *cpu_map);
group = first_cpu(nodemask);
*nodemask = node_to_cpumask(cpu_to_node(cpu));
cpus_and(*nodemask, *nodemask, *cpu_map);
group = first_cpu(*nodemask);
if (sg)
*sg = &per_cpu(sched_group_allnodes, group);
@ -6636,7 +6656,7 @@ static void init_numa_sched_groups_power(struct sched_group *group_head)
#ifdef CONFIG_NUMA
/* Free memory allocated for various sched_group structures */
static void free_sched_groups(const cpumask_t *cpu_map)
static void free_sched_groups(const cpumask_t *cpu_map, cpumask_t *nodemask)
{
int cpu, i;
@ -6648,11 +6668,11 @@ static void free_sched_groups(const cpumask_t *cpu_map)
continue;
for (i = 0; i < MAX_NUMNODES; i++) {
cpumask_t nodemask = node_to_cpumask(i);
struct sched_group *oldsg, *sg = sched_group_nodes[i];
cpus_and(nodemask, nodemask, *cpu_map);
if (cpus_empty(nodemask))
*nodemask = node_to_cpumask(i);
cpus_and(*nodemask, *nodemask, *cpu_map);
if (cpus_empty(*nodemask))
continue;
if (sg == NULL)
@ -6670,7 +6690,7 @@ next_sg:
}
}
#else
static void free_sched_groups(const cpumask_t *cpu_map)
static void free_sched_groups(const cpumask_t *cpu_map, cpumask_t *nodemask)
{
}
#endif
@ -6727,6 +6747,65 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd)
} while (group != child->groups);
}
/*
* Initializers for schedule domains
* Non-inlined to reduce accumulated stack pressure in build_sched_domains()
*/
#define SD_INIT(sd, type) sd_init_##type(sd)
#define SD_INIT_FUNC(type) \
static noinline void sd_init_##type(struct sched_domain *sd) \
{ \
memset(sd, 0, sizeof(*sd)); \
*sd = SD_##type##_INIT; \
}
SD_INIT_FUNC(CPU)
#ifdef CONFIG_NUMA
SD_INIT_FUNC(ALLNODES)
SD_INIT_FUNC(NODE)
#endif
#ifdef CONFIG_SCHED_SMT
SD_INIT_FUNC(SIBLING)
#endif
#ifdef CONFIG_SCHED_MC
SD_INIT_FUNC(MC)
#endif
/*
* To minimize stack usage kmalloc room for cpumasks and share the
* space as the usage in build_sched_domains() dictates. Used only
* if the amount of space is significant.
*/
struct allmasks {
cpumask_t tmpmask; /* make this one first */
union {
cpumask_t nodemask;
cpumask_t this_sibling_map;
cpumask_t this_core_map;
};
cpumask_t send_covered;
#ifdef CONFIG_NUMA
cpumask_t domainspan;
cpumask_t covered;
cpumask_t notcovered;
#endif
};
#if NR_CPUS > 128
#define SCHED_CPUMASK_ALLOC 1
#define SCHED_CPUMASK_FREE(v) kfree(v)
#define SCHED_CPUMASK_DECLARE(v) struct allmasks *v
#else
#define SCHED_CPUMASK_ALLOC 0
#define SCHED_CPUMASK_FREE(v)
#define SCHED_CPUMASK_DECLARE(v) struct allmasks _v, *v = &_v
#endif
#define SCHED_CPUMASK_VAR(v, a) cpumask_t *v = (cpumask_t *) \
((unsigned long)(a) + offsetof(struct allmasks, v))
/*
* Build sched domains for a given set of cpus and attach the sched domains
* to the individual cpus
@ -6735,6 +6814,8 @@ static int build_sched_domains(const cpumask_t *cpu_map)
{
int i;
struct root_domain *rd;
SCHED_CPUMASK_DECLARE(allmasks);
cpumask_t *tmpmask;
#ifdef CONFIG_NUMA
struct sched_group **sched_group_nodes = NULL;
int sd_allnodes = 0;
@ -6748,38 +6829,60 @@ static int build_sched_domains(const cpumask_t *cpu_map)
printk(KERN_WARNING "Can not alloc sched group node list\n");
return -ENOMEM;
}
sched_group_nodes_bycpu[first_cpu(*cpu_map)] = sched_group_nodes;
#endif
rd = alloc_rootdomain();
if (!rd) {
printk(KERN_WARNING "Cannot alloc root domain\n");
#ifdef CONFIG_NUMA
kfree(sched_group_nodes);
#endif
return -ENOMEM;
}
#if SCHED_CPUMASK_ALLOC
/* get space for all scratch cpumask variables */
allmasks = kmalloc(sizeof(*allmasks), GFP_KERNEL);
if (!allmasks) {
printk(KERN_WARNING "Cannot alloc cpumask array\n");
kfree(rd);
#ifdef CONFIG_NUMA
kfree(sched_group_nodes);
#endif
return -ENOMEM;
}
#endif
tmpmask = (cpumask_t *)allmasks;
#ifdef CONFIG_NUMA
sched_group_nodes_bycpu[first_cpu(*cpu_map)] = sched_group_nodes;
#endif
/*
* Set up domains for cpus specified by the cpu_map.
*/
for_each_cpu_mask(i, *cpu_map) {
struct sched_domain *sd = NULL, *p;
cpumask_t nodemask = node_to_cpumask(cpu_to_node(i));
SCHED_CPUMASK_VAR(nodemask, allmasks);
cpus_and(nodemask, nodemask, *cpu_map);
*nodemask = node_to_cpumask(cpu_to_node(i));
cpus_and(*nodemask, *nodemask, *cpu_map);
#ifdef CONFIG_NUMA
if (cpus_weight(*cpu_map) >
SD_NODES_PER_DOMAIN*cpus_weight(nodemask)) {
SD_NODES_PER_DOMAIN*cpus_weight(*nodemask)) {
sd = &per_cpu(allnodes_domains, i);
*sd = SD_ALLNODES_INIT;
SD_INIT(sd, ALLNODES);
sd->span = *cpu_map;
cpu_to_allnodes_group(i, cpu_map, &sd->groups);
cpu_to_allnodes_group(i, cpu_map, &sd->groups, tmpmask);
p = sd;
sd_allnodes = 1;
} else
p = NULL;
sd = &per_cpu(node_domains, i);
*sd = SD_NODE_INIT;
SD_INIT(sd, NODE);
sd->span = sched_domain_node_span(cpu_to_node(i));
sd->parent = p;
if (p)
@ -6789,94 +6892,114 @@ static int build_sched_domains(const cpumask_t *cpu_map)
p = sd;
sd = &per_cpu(phys_domains, i);
*sd = SD_CPU_INIT;
sd->span = nodemask;
SD_INIT(sd, CPU);
sd->span = *nodemask;
sd->parent = p;
if (p)
p->child = sd;
cpu_to_phys_group(i, cpu_map, &sd->groups);
cpu_to_phys_group(i, cpu_map, &sd->groups, tmpmask);
#ifdef CONFIG_SCHED_MC
p = sd;
sd = &per_cpu(core_domains, i);
*sd = SD_MC_INIT;
SD_INIT(sd, MC);
sd->span = cpu_coregroup_map(i);
cpus_and(sd->span, sd->span, *cpu_map);
sd->parent = p;
p->child = sd;
cpu_to_core_group(i, cpu_map, &sd->groups);
cpu_to_core_group(i, cpu_map, &sd->groups, tmpmask);
#endif
#ifdef CONFIG_SCHED_SMT
p = sd;
sd = &per_cpu(cpu_domains, i);
*sd = SD_SIBLING_INIT;
SD_INIT(sd, SIBLING);
sd->span = per_cpu(cpu_sibling_map, i);
cpus_and(sd->span, sd->span, *cpu_map);
sd->parent = p;
p->child = sd;
cpu_to_cpu_group(i, cpu_map, &sd->groups);
cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask);
#endif
}
#ifdef CONFIG_SCHED_SMT
/* Set up CPU (sibling) groups */
for_each_cpu_mask(i, *cpu_map) {
cpumask_t this_sibling_map = per_cpu(cpu_sibling_map, i);
cpus_and(this_sibling_map, this_sibling_map, *cpu_map);
if (i != first_cpu(this_sibling_map))
SCHED_CPUMASK_VAR(this_sibling_map, allmasks);
SCHED_CPUMASK_VAR(send_covered, allmasks);
*this_sibling_map = per_cpu(cpu_sibling_map, i);
cpus_and(*this_sibling_map, *this_sibling_map, *cpu_map);
if (i != first_cpu(*this_sibling_map))
continue;
init_sched_build_groups(this_sibling_map, cpu_map,
&cpu_to_cpu_group);
&cpu_to_cpu_group,
send_covered, tmpmask);
}
#endif
#ifdef CONFIG_SCHED_MC
/* Set up multi-core groups */
for_each_cpu_mask(i, *cpu_map) {
cpumask_t this_core_map = cpu_coregroup_map(i);
cpus_and(this_core_map, this_core_map, *cpu_map);
if (i != first_cpu(this_core_map))
SCHED_CPUMASK_VAR(this_core_map, allmasks);
SCHED_CPUMASK_VAR(send_covered, allmasks);
*this_core_map = cpu_coregroup_map(i);
cpus_and(*this_core_map, *this_core_map, *cpu_map);
if (i != first_cpu(*this_core_map))
continue;
init_sched_build_groups(this_core_map, cpu_map,
&cpu_to_core_group);
&cpu_to_core_group,
send_covered, tmpmask);
}
#endif
/* Set up physical groups */
for (i = 0; i < MAX_NUMNODES; i++) {
cpumask_t nodemask = node_to_cpumask(i);
SCHED_CPUMASK_VAR(nodemask, allmasks);
SCHED_CPUMASK_VAR(send_covered, allmasks);
cpus_and(nodemask, nodemask, *cpu_map);
if (cpus_empty(nodemask))
*nodemask = node_to_cpumask(i);
cpus_and(*nodemask, *nodemask, *cpu_map);
if (cpus_empty(*nodemask))
continue;
init_sched_build_groups(nodemask, cpu_map, &cpu_to_phys_group);
init_sched_build_groups(nodemask, cpu_map,
&cpu_to_phys_group,
send_covered, tmpmask);
}
#ifdef CONFIG_NUMA
/* Set up node groups */
if (sd_allnodes)
init_sched_build_groups(*cpu_map, cpu_map,
&cpu_to_allnodes_group);
if (sd_allnodes) {
SCHED_CPUMASK_VAR(send_covered, allmasks);
init_sched_build_groups(cpu_map, cpu_map,
&cpu_to_allnodes_group,
send_covered, tmpmask);
}
for (i = 0; i < MAX_NUMNODES; i++) {
/* Set up node groups */
struct sched_group *sg, *prev;
cpumask_t nodemask = node_to_cpumask(i);
cpumask_t domainspan;
cpumask_t covered = CPU_MASK_NONE;
SCHED_CPUMASK_VAR(nodemask, allmasks);
SCHED_CPUMASK_VAR(domainspan, allmasks);
SCHED_CPUMASK_VAR(covered, allmasks);
int j;
cpus_and(nodemask, nodemask, *cpu_map);
if (cpus_empty(nodemask)) {
*nodemask = node_to_cpumask(i);
cpus_clear(*covered);
cpus_and(*nodemask, *nodemask, *cpu_map);
if (cpus_empty(*nodemask)) {
sched_group_nodes[i] = NULL;
continue;
}
domainspan = sched_domain_node_span(i);
cpus_and(domainspan, domainspan, *cpu_map);
*domainspan = sched_domain_node_span(i);
cpus_and(*domainspan, *domainspan, *cpu_map);
sg = kmalloc_node(sizeof(struct sched_group), GFP_KERNEL, i);
if (!sg) {
@ -6885,31 +7008,31 @@ static int build_sched_domains(const cpumask_t *cpu_map)
goto error;
}
sched_group_nodes[i] = sg;
for_each_cpu_mask(j, nodemask) {
for_each_cpu_mask(j, *nodemask) {
struct sched_domain *sd;
sd = &per_cpu(node_domains, j);
sd->groups = sg;
}
sg->__cpu_power = 0;
sg->cpumask = nodemask;
sg->cpumask = *nodemask;
sg->next = sg;
cpus_or(covered, covered, nodemask);
cpus_or(*covered, *covered, *nodemask);
prev = sg;
for (j = 0; j < MAX_NUMNODES; j++) {
cpumask_t tmp, notcovered;
SCHED_CPUMASK_VAR(notcovered, allmasks);
int n = (i + j) % MAX_NUMNODES;
node_to_cpumask_ptr(pnodemask, n);
cpus_complement(notcovered, covered);
cpus_and(tmp, notcovered, *cpu_map);
cpus_and(tmp, tmp, domainspan);
if (cpus_empty(tmp))
cpus_complement(*notcovered, *covered);
cpus_and(*tmpmask, *notcovered, *cpu_map);
cpus_and(*tmpmask, *tmpmask, *domainspan);
if (cpus_empty(*tmpmask))
break;
cpus_and(tmp, tmp, *pnodemask);
if (cpus_empty(tmp))
cpus_and(*tmpmask, *tmpmask, *pnodemask);
if (cpus_empty(*tmpmask))
continue;
sg = kmalloc_node(sizeof(struct sched_group),
@ -6920,9 +7043,9 @@ static int build_sched_domains(const cpumask_t *cpu_map)
goto error;
}
sg->__cpu_power = 0;
sg->cpumask = tmp;
sg->cpumask = *tmpmask;
sg->next = prev->next;
cpus_or(covered, covered, tmp);
cpus_or(*covered, *covered, *tmpmask);
prev->next = sg;
prev = sg;
}
@ -6958,7 +7081,8 @@ static int build_sched_domains(const cpumask_t *cpu_map)
if (sd_allnodes) {
struct sched_group *sg;
cpu_to_allnodes_group(first_cpu(*cpu_map), cpu_map, &sg);
cpu_to_allnodes_group(first_cpu(*cpu_map), cpu_map, &sg,
tmpmask);
init_numa_sched_groups_power(sg);
}
#endif
@ -6976,11 +7100,13 @@ static int build_sched_domains(const cpumask_t *cpu_map)
cpu_attach_domain(sd, rd, i);
}
SCHED_CPUMASK_FREE((void *)allmasks);
return 0;
#ifdef CONFIG_NUMA
error:
free_sched_groups(cpu_map);
free_sched_groups(cpu_map, tmpmask);
SCHED_CPUMASK_FREE((void *)allmasks);
return -ENOMEM;
#endif
}
@ -7020,9 +7146,10 @@ static int arch_init_sched_domains(const cpumask_t *cpu_map)
return err;
}
static void arch_destroy_sched_domains(const cpumask_t *cpu_map)
static void arch_destroy_sched_domains(const cpumask_t *cpu_map,
cpumask_t *tmpmask)
{
free_sched_groups(cpu_map);
free_sched_groups(cpu_map, tmpmask);
}
/*
@ -7031,6 +7158,7 @@ static void arch_destroy_sched_domains(const cpumask_t *cpu_map)
*/
static void detach_destroy_domains(const cpumask_t *cpu_map)
{
cpumask_t tmpmask;
int i;
unregister_sched_domain_sysctl();
@ -7038,7 +7166,7 @@ static void detach_destroy_domains(const cpumask_t *cpu_map)
for_each_cpu_mask(i, *cpu_map)
cpu_attach_domain(NULL, &def_root_domain, i);
synchronize_sched();
arch_destroy_sched_domains(cpu_map);
arch_destroy_sched_domains(cpu_map, &tmpmask);
}
/*
@ -7246,7 +7374,7 @@ void __init sched_init_smp(void)
hotcpu_notifier(update_sched_domains, 0);
/* Move init over to a non-isolated CPU */
if (set_cpus_allowed(current, non_isolated_cpus) < 0)
if (set_cpus_allowed_ptr(current, &non_isolated_cpus) < 0)
BUG();
sched_init_granularity();
}