Re: [PATCH] eal: factorize lcore main loop

[David Marchand <david.marchand@redhat.com>]

On Thu, Mar 24, 2022 at 9:31 AM Tyler Retzlaff
<roretzla@linux.microsoft.com> wrote:
> > diff --git a/lib/eal/common/eal_common_thread.c b/lib/eal/common/eal_common_thread.c
> > index 684bea166c..256de91abc 100644
> > --- a/lib/eal/common/eal_common_thread.c
> > +++ b/lib/eal/common/eal_common_thread.c
> > @@ -9,6 +9,7 @@
> >  #include <assert.h>
> >  #include <string.h>
> >
> > +#include <rte_eal_trace.h>
> >  #include <rte_errno.h>
> >  #include <rte_lcore.h>
> >  #include <rte_log.h>
> > @@ -163,6 +164,77 @@ __rte_thread_uninit(void)
> >       RTE_PER_LCORE(_lcore_id) = LCORE_ID_ANY;
> >  }
> >
> > +/* main loop of threads */
> > +__rte_noreturn void *
> > +eal_thread_loop(__rte_unused void *arg)
> > +{
> > +     char cpuset[RTE_CPU_AFFINITY_STR_LEN];
> > +     pthread_t thread_id = pthread_self();
> > +     unsigned int lcore_id;
> > +     int ret;
> > +
> > +     /* retrieve our lcore_id from the configuration structure */
> > +     RTE_LCORE_FOREACH_WORKER(lcore_id) {
> > +             if (thread_id == lcore_config[lcore_id].thread_id)
>                                  ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
>
> i can see that in practice this isn't a problem since the linux
> implementation of pthread_create(3) stores to pthread_t *thread before
> executing start_routine.
>
> but strictly speaking i don't think the pthread_create api contractually
> guarantees that the thread id is stored before start_routine runs. so this
> is relying on an internal implementation detail.
>
> https://pubs.opengroup.org/onlinepubs/9699919799/functions/pthread_create.html
>
>   "Upon successful completion, pthread_create() shall store the ID of the
>    created thread in the location referenced by thread."
>
> https://man7.org/linux/man-pages/man3/pthread_create.3.html
>
>   "Before returning, a successful call to pthread_create() stores
>    the ID of the new thread in the buffer pointed to by thread; this
>    identifier is used to refer to the thread in subsequent calls to
>    other pthreads functions."
>
> it doesn't really say when it does this in relation to start_routine running.
> depends how hair splitty you want to be about it. but since you're revamping
> the code you might be interested in addressing it.

I had wondered about this part too in the past.

I don't see a reason to keep this loop (even considering baremetal,
since this code is within the linux implementation of EAL).
And this comment seems a good reason to cleanup the code (like simply
pass lcore_id via arg).

Something like:

Author: David Marchand <david.marchand@redhat.com>
Date:   Thu Mar 24 11:29:46 2022 +0100

    eal: cleanup lcore hand-over from main thread

    As noted by Tyler, there is nothing in the pthread API that strictly
    guarantees that the new thread won't start running eal_thread_loop
    before pthread_create writes to &lcore_config[xx].thread_id.

    Rather than rely on thread id, the main thread can directly pass the
    worker thread lcore.

    Signed-off-by: David Marchand <david.marchand@redhat.com>

diff --git a/lib/eal/common/eal_common_thread.c
b/lib/eal/common/eal_common_thread.c
index 256de91abc..962b7e9ac4 100644
--- a/lib/eal/common/eal_common_thread.c
+++ b/lib/eal/common/eal_common_thread.c
@@ -166,26 +166,17 @@ __rte_thread_uninit(void)

 /* main loop of threads */
 __rte_noreturn void *
-eal_thread_loop(__rte_unused void *arg)
+eal_thread_loop(void *arg)
 {
+    unsigned int lcore_id = (uintptr_t)arg;
     char cpuset[RTE_CPU_AFFINITY_STR_LEN];
-    pthread_t thread_id = pthread_self();
-    unsigned int lcore_id;
     int ret;

-    /* retrieve our lcore_id from the configuration structure */
-    RTE_LCORE_FOREACH_WORKER(lcore_id) {
-        if (thread_id == lcore_config[lcore_id].thread_id)
-            break;
-    }
-    if (lcore_id == RTE_MAX_LCORE)
-        rte_panic("cannot retrieve lcore id\n");
-
     __rte_thread_init(lcore_id, &lcore_config[lcore_id].cpuset);

     ret = eal_thread_dump_current_affinity(cpuset, sizeof(cpuset));
     RTE_LOG(DEBUG, EAL, "lcore %u is ready (tid=%zx;cpuset=[%s%s])\n",
-        lcore_id, (uintptr_t)thread_id, cpuset,
+        lcore_id, (uintptr_t)pthread_self(), cpuset,
         ret == 0 ? "" : "...");

     rte_eal_trace_thread_lcore_ready(lcore_id, cpuset);
diff --git a/lib/eal/common/eal_thread.h b/lib/eal/common/eal_thread.h
index b08dcf34b5..0fde33e70c 100644
--- a/lib/eal/common/eal_thread.h
+++ b/lib/eal/common/eal_thread.h
@@ -11,7 +11,7 @@
  * basic loop of thread, called for each thread by eal_init().
  *
  * @param arg
- *   opaque pointer
+ *   The lcore_id (passed as an integer) of this worker thread.
  */
 __rte_noreturn void *eal_thread_loop(void *arg);

diff --git a/lib/eal/freebsd/eal.c b/lib/eal/freebsd/eal.c
index 80bc3d25e0..a6b20960f2 100644
--- a/lib/eal/freebsd/eal.c
+++ b/lib/eal/freebsd/eal.c
@@ -810,7 +810,7 @@ rte_eal_init(int argc, char **argv)

         /* create a thread for each lcore */
         ret = pthread_create(&lcore_config[i].thread_id, NULL,
-                     eal_thread_loop, NULL);
+                     eal_thread_loop, (void *)(uintptr_t)i);
         if (ret != 0)
             rte_panic("Cannot create thread\n");

diff --git a/lib/eal/linux/eal.c b/lib/eal/linux/eal.c
index 8a405d1d59..1ef263434a 100644
--- a/lib/eal/linux/eal.c
+++ b/lib/eal/linux/eal.c
@@ -1145,7 +1145,7 @@ rte_eal_init(int argc, char **argv)

         /* create a thread for each lcore */
         ret = pthread_create(&lcore_config[i].thread_id, NULL,
-                     eal_thread_loop, NULL);
+                     eal_thread_loop, (void *)(uintptr_t)i);
         if (ret != 0)
             rte_panic("Cannot create thread\n");

diff --git a/lib/eal/windows/eal.c b/lib/eal/windows/eal.c
index ca3c41aaa7..1874f9f6d7 100644
--- a/lib/eal/windows/eal.c
+++ b/lib/eal/windows/eal.c
@@ -420,7 +420,7 @@ rte_eal_init(int argc, char **argv)
         lcore_config[i].state = WAIT;

         /* create a thread for each lcore */
-        if (eal_thread_create(&lcore_config[i].thread_id) != 0)
+        if (eal_thread_create(&lcore_config[i].thread_id, i) != 0)
             rte_panic("Cannot create thread\n");
         ret = pthread_setaffinity_np(lcore_config[i].thread_id,
             sizeof(rte_cpuset_t), &lcore_config[i].cpuset);
diff --git a/lib/eal/windows/eal_thread.c b/lib/eal/windows/eal_thread.c
index de1c0078a5..704781a83c 100644
--- a/lib/eal/windows/eal_thread.c
+++ b/lib/eal/windows/eal_thread.c
@@ -71,13 +71,14 @@ eal_thread_ack_command(void)

 /* function to create threads */
 int
-eal_thread_create(pthread_t *thread)
+eal_thread_create(pthread_t *thread, unsigned int lcore_id)
 {
     HANDLE th;

     th = CreateThread(NULL, 0,
         (LPTHREAD_START_ROUTINE)(ULONG_PTR)eal_thread_loop,
-                        NULL, 0, (LPDWORD)thread);
+                        (LPVOID)(uintptr_t)lcore_id, 0,
+                        (LPDWORD)thread);
     if (!th)
         return -1;



But seeing how this code has been there from day 1, I would not
request a backport.


-- 
David Marchand