Detection of task affinities at API opt-in time is not the best
approach, the approach is to kill the task if it runs on a
SMT enable core. This is better than not flushing the L1D cache
when the task switches from a non-SMT core to an SMT enabled core.

Signed-off-by: Balbir Singh <sbl...@amazon.com>
---
 arch/x86/include/asm/processor.h |  2 ++
 arch/x86/kernel/smpboot.c        | 11 ++++++++++-
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 82a08b585818..60dbcdcb833f 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -136,6 +136,8 @@ struct cpuinfo_x86 {
        u16                     logical_die_id;
        /* Index into per_cpu list: */
        u16                     cpu_index;
+       /*  Is SMT active on this core? */
+       bool                    smt_active;
        u32                     microcode;
        /* Address space bits used by the cache internally */
        u8                      x86_cache_bits;
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index de776b2e6046..9a94934fae5f 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -635,6 +635,9 @@ void set_cpu_sibling_map(int cpu)
        threads = cpumask_weight(topology_sibling_cpumask(cpu));
        if (threads > __max_smt_threads)
                __max_smt_threads = threads;
+
+       for_each_cpu(i, topology_sibling_cpumask(cpu))
+               cpu_data(i).smt_active = threads > 1;
 }
 
 /* maps the cpu to the sched domain representing multi-core */
@@ -1548,10 +1551,16 @@ static void remove_siblinginfo(int cpu)
 
        for_each_cpu(sibling, topology_die_cpumask(cpu))
                cpumask_clear_cpu(cpu, topology_die_cpumask(sibling));
-       for_each_cpu(sibling, topology_sibling_cpumask(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)
+                       cpu_data(sibling).smt_active = false;
+       }
+
        for_each_cpu(sibling, cpu_llc_shared_mask(cpu))
                cpumask_clear_cpu(cpu, cpu_llc_shared_mask(sibling));
+
        cpumask_clear(cpu_llc_shared_mask(cpu));
        cpumask_clear(topology_sibling_cpumask(cpu));
        cpumask_clear(topology_core_cpumask(cpu));
-- 
2.17.1

Reply via email to