diff options
| author | Chen Yu <yu.c.chen@intel.com> | 2017-04-16 23:43:30 +0800 |
|---|---|---|
| committer | Thomas Gleixner <tglx@linutronix.de> | 2017-04-20 15:25:09 +0200 |
| commit | c0edbd4a1693600d6eb9e2faad452638c35391f7 (patch) | |
| tree | 0de0f80d627d7b88f24c6646a1f3bd532895f3f1 /arch/x86/kernel/irq.c | |
| parent | f61143c45077df4fa78e2f1ba455a00bbe1d5b8c (diff) | |
| download | linux-c0edbd4a1693600d6eb9e2faad452638c35391f7.tar.gz linux-c0edbd4a1693600d6eb9e2faad452638c35391f7.tar.bz2 linux-c0edbd4a1693600d6eb9e2faad452638c35391f7.zip | |
x86/irq: Optimize free vector check in the CPU offline path
Before offlining a CPU its required to check whether there are enough free
irq vectors available so interrupts can be migrated away from the CPU.
This check is executed whether its required or not and neither stops
searching when the number of required free vectors are reached.
Bypass the free vector check if the current CPU has no irq to migrate and
leave the for_each_online_cpu() loop when the free vector count reaches the
number of required vectors.
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Len Brown <lenb@kernel.orq>
Cc: "Rafael J. Wysocki" <rjw@rjwysocki.net>
Link: http://lkml.kernel.org/r/1492357410-510-1-git-send-email-yu.c.chen@intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Diffstat (limited to 'arch/x86/kernel/irq.c')
| -rw-r--r-- | arch/x86/kernel/irq.c | 9 |
1 files changed, 7 insertions, 2 deletions
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 4d8183b5f113..f34fe7444836 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -394,6 +394,9 @@ int check_irq_vectors_for_cpu_disable(void) !cpumask_subset(&affinity_new, &online_new)) this_count++; } + /* No need to check any further. */ + if (!this_count) + return 0; count = 0; for_each_online_cpu(cpu) { @@ -411,8 +414,10 @@ int check_irq_vectors_for_cpu_disable(void) for (vector = FIRST_EXTERNAL_VECTOR; vector < first_system_vector; vector++) { if (!test_bit(vector, used_vectors) && - IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector])) - count++; + IS_ERR_OR_NULL(per_cpu(vector_irq, cpu)[vector])) { + if (++count == this_count) + return 0; + } } } |