@@ -332,7 +332,7 @@ __flush_tlb_range (struct vm_area_struct *vma, unsigned long start,
preempt_disable();
#ifdef CONFIG_SMP
- if (mm != current->active_mm || cpumask_weight(mm_cpumask(mm)) != 1) {
+ if (mm != current->active_mm || !cpumask_weight_eq(mm_cpumask(mm), 1)) {
ia64_global_tlb_purge(mm, start, end, nbits);
preempt_enable();
return;
@@ -763,7 +763,7 @@ static void octeon_irq_cpu_offline_ciu(struct irq_data *data)
if (!cpumask_test_cpu(cpu, mask))
return;
- if (cpumask_weight(mask) > 1) {
+ if (cpumask_weight_gt(mask, 1)) {
/*
* It has multi CPU affinity, just remove this CPU
* from the affinity set.
@@ -795,7 +795,7 @@ static int octeon_irq_ciu_set_affinity(struct irq_data *data,
* This removes the need to do locking in the .ack/.eoi
* functions.
*/
- if (cpumask_weight(dest) != 1)
+ if (!cpumask_weight_eq(dest, 1))
return -EINVAL;
if (!enable_one)
@@ -72,7 +72,7 @@ static void crash_kexec_prepare_cpus(void)
*/
pr_emerg("Sending IPI to other cpus...\n");
msecs = 10000;
- while ((cpumask_weight(&cpus_in_crash) < ncpus) && (--msecs > 0)) {
+ while (cpumask_weight_lt(&cpus_in_crash, ncpus) && (--msecs > 0)) {
cpu_relax();
mdelay(1);
}
@@ -1655,7 +1655,7 @@ void start_secondary(void *unused)
if (has_big_cores)
sibling_mask = cpu_smallcore_mask;
- if (cpumask_weight(mask) > cpumask_weight(sibling_mask(cpu)))
+ if (cpumask_weight_gt(mask, cpumask_weight(sibling_mask(cpu))))
shared_caches = true;
}
@@ -483,7 +483,7 @@ static void start_watchdog(void *arg)
wd_smp_lock(&flags);
cpumask_set_cpu(cpu, &wd_cpus_enabled);
- if (cpumask_weight(&wd_cpus_enabled) == 1) {
+ if (cpumask_weight_eq(&wd_cpus_enabled, 1)) {
cpumask_set_cpu(cpu, &wd_smp_cpus_pending);
wd_smp_last_reset_tb = get_tb();
}
@@ -469,7 +469,7 @@ static bool wait_for_other_cpus(int ncpus)
/* We wait for 2s, which is a metric "little while" */
for (timeout = 20000; timeout != 0; --timeout) {
- if (cpumask_weight(&cpus_in_xmon) >= ncpus)
+ if (cpumask_weight_ge(&cpus_in_xmon, ncpus))
return true;
udelay(100);
barrier();
@@ -1338,7 +1338,7 @@ static int cpu_cmd(void)
case 'S':
case 't':
cpumask_copy(&xmon_batch_cpus, &cpus_in_xmon);
- if (cpumask_weight(&xmon_batch_cpus) <= 1) {
+ if (cpumask_weight_le(&xmon_batch_cpus, 1)) {
printf("There are no other cpus in xmon\n");
break;
}
@@ -975,7 +975,7 @@ static int cfset_all_start(struct cfset_request *req)
return -ENOMEM;
cpumask_and(mask, &req->mask, cpu_online_mask);
on_each_cpu_mask(mask, cfset_ioctl_on, &p, 1);
- if (atomic_read(&p.cpus_ack) != cpumask_weight(mask)) {
+ if (!cpumask_weight_eq(mask, atomic_read(&p.cpus_ack))) {
on_each_cpu_mask(mask, cfset_ioctl_off, &p, 1);
rc = -EIO;
debug_sprintf_event(cf_dbg, 4, "%s CPUs missing", __func__);
@@ -1608,7 +1608,7 @@ static void remove_siblinginfo(int cpu)
/*/
* last thread sibling in this cpu core going down
*/
- if (cpumask_weight(topology_sibling_cpumask(cpu)) == 1)
+ if (cpumask_weight_eq(topology_sibling_cpumask(cpu), 1))
cpu_data(sibling).booted_cores--;
}
@@ -1617,7 +1617,7 @@ static void remove_siblinginfo(int cpu)
for_each_cpu(sibling, topology_sibling_cpumask(cpu)) {
cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling));
- if (cpumask_weight(topology_sibling_cpumask(sibling)) == 1)
+ if (cpumask_weight_eq(topology_sibling_cpumask(sibling), 1))
cpu_data(sibling).smt_active = false;
}
@@ -90,7 +90,7 @@ static unsigned int down_and_up_cpus(const struct cpumask *cpus,
* cpu_down() checks the number of online CPUs before the TOS
* resident CPU.
*/
- if (cpumask_weight(offlined_cpus) + 1 == nb_available_cpus) {
+ if (cpumask_weight_eq(offlined_cpus, nb_available_cpus - 1)) {
if (ret != -EBUSY) {
pr_err("Unexpected return code %d while trying "
"to power down last online CPU %d\n",
@@ -762,8 +762,8 @@ static void init_vp_index(struct vmbus_channel *channel)
}
alloced_mask = &hv_context.hv_numa_map[numa_node];
- if (cpumask_weight(alloced_mask) ==
- cpumask_weight(cpumask_of_node(numa_node))) {
+ if (cpumask_weight_eq(alloced_mask,
+ cpumask_weight(cpumask_of_node(numa_node)))) {
/*
* We have cycled through all the CPUs in the node;
* reset the alloced map.
@@ -507,7 +507,7 @@ static int _dev_comp_vect_cpu_mask_init(struct hfi1_devdata *dd,
* available CPUs divide it by the number of devices in the
* local NUMA node.
*/
- if (cpumask_weight(&entry->comp_vect_mask) == 1) {
+ if (cpumask_weight_eq(&entry->comp_vect_mask, 1)) {
possible_cpus_comp_vect = 1;
dd_dev_warn(dd,
"Number of kernel receive queues is too large for completion vector affinity to be effective\n");
@@ -593,7 +593,7 @@ int hfi1_dev_affinity_init(struct hfi1_devdata *dd)
{
struct hfi1_affinity_node *entry;
const struct cpumask *local_mask;
- int curr_cpu, possible, i, ret;
+ int curr_cpu, i, ret;
bool new_entry = false;
local_mask = cpumask_of_node(dd->node);
@@ -626,10 +626,9 @@ int hfi1_dev_affinity_init(struct hfi1_devdata *dd)
local_mask);
/* fill in the receive list */
- possible = cpumask_weight(&entry->def_intr.mask);
curr_cpu = cpumask_first(&entry->def_intr.mask);
- if (possible == 1) {
+ if (cpumask_weight_eq(&entry->def_intr.mask, 1)) {
/* only one CPU, everyone will use it */
cpumask_set_cpu(curr_cpu, &entry->rcv_intr.mask);
cpumask_set_cpu(curr_cpu, &entry->general_intr_mask);
@@ -1017,7 +1016,7 @@ int hfi1_get_proc_affinity(int node)
cpu = cpumask_first(proc_mask);
cpumask_set_cpu(cpu, &set->used);
goto done;
- } else if (current->nr_cpus_allowed < cpumask_weight(&set->mask)) {
+ } else if (cpumask_weight_gt(&set->mask, current->nr_cpus_allowed)) {
hfi1_cdbg(PROC, "PID %u %s affinity set to CPU set(s) %*pbl",
current->pid, current->comm,
cpumask_pr_args(proc_mask));
@@ -1151,7 +1151,7 @@ static void assign_ctxt_affinity(struct file *fp, struct qib_devdata *dd)
* reserve a processor for it on the local NUMA node.
*/
if ((weight >= qib_cpulist_count) &&
- (cpumask_weight(local_mask) <= qib_cpulist_count)) {
+ (cpumask_weight_le(local_mask, qib_cpulist_count))) {
for_each_cpu(local_cpu, local_mask)
if (!test_and_set_bit(local_cpu, qib_cpulist)) {
fd->rec_cpu_num = local_cpu;
@@ -3405,7 +3405,7 @@ static void qib_setup_7322_interrupt(struct qib_devdata *dd, int clearpend)
local_mask = cpumask_of_pcibus(dd->pcidev->bus);
firstcpu = cpumask_first(local_mask);
if (firstcpu >= nr_cpu_ids ||
- cpumask_weight(local_mask) == num_online_cpus()) {
+ cpumask_weight_eq(local_mask, num_online_cpus())) {
local_mask = topology_core_cpumask(0);
firstcpu = cpumask_first(local_mask);
}
@@ -12643,7 +12643,7 @@ lpfc_cpuhp_get_eq(struct lpfc_hba *phba, unsigned int cpu,
* gone offline yet, we need >1.
*/
cpumask_and(tmp, maskp, cpu_online_mask);
- if (cpumask_weight(tmp) > 1)
+ if (cpumask_weight_gt(tmp, 1))
continue;
/* Now that we have an irq to shutdown, get the eq
@@ -561,7 +561,7 @@ int qman_test_stash(void)
{
int err;
- if (cpumask_weight(cpu_online_mask) < 2) {
+ if (cpumask_weight_lt(cpu_online_mask, 2)) {
pr_info("%s(): skip - only 1 CPU\n", __func__);
return 0;
}
@@ -575,6 +575,56 @@ static inline unsigned int cpumask_weight(const struct cpumask *srcp)
return bitmap_weight(cpumask_bits(srcp), nr_cpumask_bits);
}
+/**
+ * cpumask_weight_eq - Check if # of bits in *srcp is equal to a given number
+ * @srcp: the cpumask to count bits (< nr_cpu_ids) in.
+ * @num: the number to check.
+ */
+static inline bool cpumask_weight_eq(const struct cpumask *srcp, unsigned int num)
+{
+ return bitmap_weight_eq(cpumask_bits(srcp), nr_cpumask_bits, num);
+}
+
+/**
+ * cpumask_weight_gt - Check if # of bits in *srcp is greater than a given number
+ * @srcp: the cpumask to count bits (< nr_cpu_ids) in.
+ * @num: the number to check.
+ */
+static inline bool cpumask_weight_gt(const struct cpumask *srcp, int num)
+{
+ return bitmap_weight_gt(cpumask_bits(srcp), nr_cpumask_bits, num);
+}
+
+/**
+ * cpumask_weight_ge - Check if # of bits in *srcp is greater than or equal to a given number
+ * @srcp: the cpumask to count bits (< nr_cpu_ids) in.
+ * @num: the number to check.
+ */
+static inline bool cpumask_weight_ge(const struct cpumask *srcp, int num)
+{
+ return bitmap_weight_ge(cpumask_bits(srcp), nr_cpumask_bits, num);
+}
+
+/**
+ * cpumask_weight_lt - Check if # of bits in *srcp is less than a given number
+ * @srcp: the cpumask to count bits (< nr_cpu_ids) in.
+ * @num: the number to check.
+ */
+static inline bool cpumask_weight_lt(const struct cpumask *srcp, int num)
+{
+ return bitmap_weight_lt(cpumask_bits(srcp), nr_cpumask_bits, num);
+}
+
+/**
+ * cpumask_weight_le - Check if # of bits in *srcp is less than or equal to a given number
+ * @srcp: the cpumask to count bits (< nr_cpu_ids) in.
+ * @num: the number to check.
+ */
+static inline bool cpumask_weight_le(const struct cpumask *srcp, int num)
+{
+ return bitmap_weight_le(cpumask_bits(srcp), nr_cpumask_bits, num);
+}
+
/**
* cpumask_shift_right - *dstp = *srcp >> n
* @dstp: the cpumask result
@@ -6006,7 +6006,7 @@ static void sched_core_cpu_starting(unsigned int cpu)
WARN_ON_ONCE(rq->core != rq);
/* if we're the first, we'll be our own leader */
- if (cpumask_weight(smt_mask) == 1)
+ if (cpumask_weight_eq(smt_mask, 1))
goto unlock;
/* find the leader */
@@ -6047,7 +6047,7 @@ static void sched_core_cpu_deactivate(unsigned int cpu)
sched_core_lock(cpu, &flags);
/* if we're the last man standing, nothing to do */
- if (cpumask_weight(smt_mask) == 1) {
+ if (cpumask_weight_eq(smt_mask, 1)) {
WARN_ON_ONCE(rq->core != rq);
goto unlock;
}
@@ -9053,7 +9053,7 @@ int sched_cpu_activate(unsigned int cpu)
/*
* When going up, increment the number of cores with SMT present.
*/
- if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
+ if (cpumask_weight_eq(cpu_smt_mask(cpu), 2))
static_branch_inc_cpuslocked(&sched_smt_present);
#endif
set_cpu_active(cpu, true);
@@ -9128,7 +9128,7 @@ int sched_cpu_deactivate(unsigned int cpu)
/*
* When going down, decrement the number of cores with SMT present.
*/
- if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
+ if (cpumask_weight_eq(cpu_smt_mask(cpu), 2))
static_branch_dec_cpuslocked(&sched_smt_present);
sched_core_cpu_deactivate(cpu);
@@ -169,7 +169,7 @@ static const unsigned int SD_DEGENERATE_GROUPS_MASK =
static int sd_degenerate(struct sched_domain *sd)
{
- if (cpumask_weight(sched_domain_span(sd)) == 1)
+ if (cpumask_weight_eq(sched_domain_span(sd), 1))
return 1;
/* Following flags need at least 2 groups */
@@ -648,7 +648,7 @@ void tick_cleanup_dead_cpu(int cpu)
*/
list_for_each_entry_safe(dev, tmp, &clockevent_devices, list) {
if (cpumask_test_cpu(cpu, dev->cpumask) &&
- cpumask_weight(dev->cpumask) == 1 &&
+ cpumask_weight_eq(dev->cpumask, 1) &&
!tick_is_broadcast_device(dev)) {
BUG_ON(!clockevent_state_detached(dev));
list_del(&dev->list);
Kernel code calls cpumask_weight() to compare the weight of cpumask with a given number. We can do it more efficiently with cpumask_weight_{eq, ...} because conditional cpumask_weight may stop traversing the cpumask earlier, as soon as condition is met. Signed-off-by: Yury Norov <yury.norov@gmail.com> --- arch/ia64/mm/tlb.c | 2 +- arch/mips/cavium-octeon/octeon-irq.c | 4 +- arch/mips/kernel/crash.c | 2 +- arch/powerpc/kernel/smp.c | 2 +- arch/powerpc/kernel/watchdog.c | 2 +- arch/powerpc/xmon/xmon.c | 4 +- arch/s390/kernel/perf_cpum_cf.c | 2 +- arch/x86/kernel/smpboot.c | 4 +- drivers/firmware/psci/psci_checker.c | 2 +- drivers/hv/channel_mgmt.c | 4 +- drivers/infiniband/hw/hfi1/affinity.c | 9 ++--- drivers/infiniband/hw/qib/qib_file_ops.c | 2 +- drivers/infiniband/hw/qib/qib_iba7322.c | 2 +- drivers/scsi/lpfc/lpfc_init.c | 2 +- drivers/soc/fsl/qbman/qman_test_stash.c | 2 +- include/linux/cpumask.h | 50 ++++++++++++++++++++++++ kernel/sched/core.c | 8 ++-- kernel/sched/topology.c | 2 +- kernel/time/clockevents.c | 2 +- 19 files changed, 78 insertions(+), 29 deletions(-)