Re: [RFC PATCH for 4.21 06/16] cpu_opv: Provide cpu_opv system call (v8)

[Mathieu Desnoyers]

----- On Oct 17, 2018, at 11:11 AM, Mathieu Desnoyers 
mathieu.desnoy...@efficios.com wrote:

> ----- On Oct 17, 2018, at 3:19 AM, Srikar Dronamraju sri...@linux.vnet.ibm.com
> wrote:
> 
>> Hi Mathieu,
>> 
>>> +static int do_cpu_opv(struct cpu_op *cpuop, int cpuopcnt,
>>> +                 struct cpu_opv_vaddr *vaddr_ptrs, int cpu)
>>> +{
>>> +   struct mm_struct *mm = current->mm;
>>> +   int ret;
>>> +
>>> +retry:
>>> +   if (cpu != raw_smp_processor_id()) {
>>> +           ret = push_task_to_cpu(current, cpu);
>>> +           if (ret)
>>> +                   goto check_online;
>>> +   }
>>> +   down_read(&mm->mmap_sem);
>>> +   ret = vaddr_ptrs_check(vaddr_ptrs);
>>> +   if (ret)
>>> +           goto end;
>>> +   preempt_disable();
>>> +   if (cpu != smp_processor_id()) {
>>> +           preempt_enable();
>>> +           up_read(&mm->mmap_sem);
>>> +           goto retry;
>>> +   }
>> 
>> If we have a higher priority task/s either pinned to the cpu, dont we end up
>> in busy-looping till the task exits/sleeps?
> 
> You're right!
> 
> How about we ditch the thread migration altogether, and simply perform
> the cpu_opv operations in a IPI handler ?
> 
> This is possible now that cpu_opv uses a temporary vmap() rather than
> try to touch the user-space page through the current thread's page table.
> 
> Thoughts ?

Here is the associated implementation on top of this patchset:

commit 759c5a8860d867091e168900329f0955e5101989
Author: Mathieu Desnoyers <mathieu.desnoy...@efficios.com>
Date:   Wed Oct 17 11:32:02 2018 -0400

    cpu opv: use ipi

diff --git a/kernel/cpu_opv.c b/kernel/cpu_opv.c
index db144b71d51a..30405e0cc049 100644
--- a/kernel/cpu_opv.c
+++ b/kernel/cpu_opv.c
@@ -31,6 +31,7 @@
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
 #include <linux/atomic.h>
+#include <linux/smp.h>
 #include <asm/ptrace.h>
 #include <asm/byteorder.h>
 #include <asm/cacheflush.h>
@@ -1039,41 +1040,48 @@ static int vaddr_ptrs_check(struct cpu_opv_vaddr 
*vaddr_ptrs)
        return 0;
 }

+struct opv_ipi_args {
+       struct cpu_op *cpuop;
+       int cpuopcnt;
+       int ret;
+};
+
+static void cpu_opv_ipi(void *info)
+{
+       struct opv_ipi_args *args = info;
+
+       rseq_preempt(current);
+       args->ret = __do_cpu_opv(args->cpuop, args->cpuopcnt);
+}
+
 static int do_cpu_opv(struct cpu_op *cpuop, int cpuopcnt,
                      struct cpu_opv_vaddr *vaddr_ptrs, int cpu)
 {
        struct mm_struct *mm = current->mm;
+       struct opv_ipi_args args = {
+               .cpuop = cpuop,
+               .cpuopcnt = cpuopcnt,
+       };
        int ret;

 retry:
-       if (cpu != raw_smp_processor_id()) {
-               ret = push_task_to_cpu(current, cpu);
-               if (ret)
-                       goto check_online;
-       }
+       if (!cpumask_test_cpu(cpu, &current->cpus_allowed))
+               return -EINVAL;
        down_read(&mm->mmap_sem);
        ret = vaddr_ptrs_check(vaddr_ptrs);
        if (ret)
                goto end;
-       preempt_disable();
-       if (cpu != smp_processor_id()) {
-               preempt_enable();
+       ret = smp_call_function_single(cpu, cpu_opv_ipi, &args, 1);
+       if (ret) {
                up_read(&mm->mmap_sem);
-               goto retry;
+               goto check_online;
        }
-       ret = __do_cpu_opv(cpuop, cpuopcnt);
-       preempt_enable();
+       ret = args.ret;
 end:
        up_read(&mm->mmap_sem);
        return ret;

 check_online:
-       /*
-        * push_task_to_cpu() returns -EINVAL if the requested cpu is not part
-        * of the current thread's cpus_allowed mask.
-        */
-       if (ret == -EINVAL)
-               return ret;
        get_online_cpus();
        if (cpu_online(cpu)) {
                put_online_cpus();




-- 
Mathieu Desnoyers
EfficiOS Inc.
http://www.efficios.com