DPDK patches and discussions
 help / color / mirror / Atom feed
* [dpdk-dev] [PATCH v2 4/4] test: fix memory barrier test failure on power CPUs
@ 2019-05-06 19:24 David Christensen
  2019-05-06 19:24 ` David Christensen
  2019-05-07 10:40 ` Ananyev, Konstantin
  0 siblings, 2 replies; 4+ messages in thread
From: David Christensen @ 2019-05-06 19:24 UTC (permalink / raw)
  To: dev; +Cc: David Christensen

The memory barrier test fails on IBM Power 9 systems.  Add additional
barriers to accommodate the weakly ordered model used on Power CPUs.

Signed-off-by: David Christensen <drc@linux.vnet.ibm.com>
---
v2:
* Removed ifdef's for PPC since the rte_smp_*mb() macros are already
  customized for each CPU architecture

 app/test/test_barrier.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/app/test/test_barrier.c b/app/test/test_barrier.c
index a022708..0bf82cf 100644
--- a/app/test/test_barrier.c
+++ b/app/test/test_barrier.c
@@ -92,12 +92,14 @@ struct lcore_plock_test {
 	other = self ^ 1;
 
 	l->flag[self] = 1;
+	rte_smp_wmb();
 	l->victim = self;
 
 	store_load_barrier(l->utype);
 
 	while (l->flag[other] == 1 && l->victim == self)
 		rte_pause();
+	rte_smp_rmb();
 }
 
 static void
-- 
1.8.3.1

^ permalink raw reply	[flat|nested] 4+ messages in thread

* [dpdk-dev] [PATCH v2 4/4] test: fix memory barrier test failure on power CPUs
  2019-05-06 19:24 [dpdk-dev] [PATCH v2 4/4] test: fix memory barrier test failure on power CPUs David Christensen
@ 2019-05-06 19:24 ` David Christensen
  2019-05-07 10:40 ` Ananyev, Konstantin
  1 sibling, 0 replies; 4+ messages in thread
From: David Christensen @ 2019-05-06 19:24 UTC (permalink / raw)
  To: dev; +Cc: David Christensen

The memory barrier test fails on IBM Power 9 systems.  Add additional
barriers to accommodate the weakly ordered model used on Power CPUs.

Signed-off-by: David Christensen <drc@linux.vnet.ibm.com>
---
v2:
* Removed ifdef's for PPC since the rte_smp_*mb() macros are already
  customized for each CPU architecture

 app/test/test_barrier.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/app/test/test_barrier.c b/app/test/test_barrier.c
index a022708..0bf82cf 100644
--- a/app/test/test_barrier.c
+++ b/app/test/test_barrier.c
@@ -92,12 +92,14 @@ struct lcore_plock_test {
 	other = self ^ 1;
 
 	l->flag[self] = 1;
+	rte_smp_wmb();
 	l->victim = self;
 
 	store_load_barrier(l->utype);
 
 	while (l->flag[other] == 1 && l->victim == self)
 		rte_pause();
+	rte_smp_rmb();
 }
 
 static void
-- 
1.8.3.1


^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: [dpdk-dev] [PATCH v2 4/4] test: fix memory barrier test failure on power CPUs
  2019-05-06 19:24 [dpdk-dev] [PATCH v2 4/4] test: fix memory barrier test failure on power CPUs David Christensen
  2019-05-06 19:24 ` David Christensen
@ 2019-05-07 10:40 ` Ananyev, Konstantin
  2019-05-07 10:40   ` Ananyev, Konstantin
  1 sibling, 1 reply; 4+ messages in thread
From: Ananyev, Konstantin @ 2019-05-07 10:40 UTC (permalink / raw)
  To: David Christensen, dev



> 
> The memory barrier test fails on IBM Power 9 systems.  Add additional
> barriers to accommodate the weakly ordered model used on Power CPUs.
> 
> Signed-off-by: David Christensen <drc@linux.vnet.ibm.com>
> ---
> v2:
> * Removed ifdef's for PPC since the rte_smp_*mb() macros are already
>   customized for each CPU architecture
> 
>  app/test/test_barrier.c | 2 ++
>  1 file changed, 2 insertions(+)
> 
> diff --git a/app/test/test_barrier.c b/app/test/test_barrier.c
> index a022708..0bf82cf 100644
> --- a/app/test/test_barrier.c
> +++ b/app/test/test_barrier.c
> @@ -92,12 +92,14 @@ struct lcore_plock_test {
>  	other = self ^ 1;
> 
>  	l->flag[self] = 1;
> +	rte_smp_wmb();
>  	l->victim = self;
> 
>  	store_load_barrier(l->utype);
> 
>  	while (l->flag[other] == 1 && l->victim == self)
>  		rte_pause();
> +	rte_smp_rmb();
>  }
> 
>  static void
> --

Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>

> 1.8.3.1

^ permalink raw reply	[flat|nested] 4+ messages in thread

* Re: [dpdk-dev] [PATCH v2 4/4] test: fix memory barrier test failure on power CPUs
  2019-05-07 10:40 ` Ananyev, Konstantin
@ 2019-05-07 10:40   ` Ananyev, Konstantin
  0 siblings, 0 replies; 4+ messages in thread
From: Ananyev, Konstantin @ 2019-05-07 10:40 UTC (permalink / raw)
  To: David Christensen, dev



> 
> The memory barrier test fails on IBM Power 9 systems.  Add additional
> barriers to accommodate the weakly ordered model used on Power CPUs.
> 
> Signed-off-by: David Christensen <drc@linux.vnet.ibm.com>
> ---
> v2:
> * Removed ifdef's for PPC since the rte_smp_*mb() macros are already
>   customized for each CPU architecture
> 
>  app/test/test_barrier.c | 2 ++
>  1 file changed, 2 insertions(+)
> 
> diff --git a/app/test/test_barrier.c b/app/test/test_barrier.c
> index a022708..0bf82cf 100644
> --- a/app/test/test_barrier.c
> +++ b/app/test/test_barrier.c
> @@ -92,12 +92,14 @@ struct lcore_plock_test {
>  	other = self ^ 1;
> 
>  	l->flag[self] = 1;
> +	rte_smp_wmb();
>  	l->victim = self;
> 
>  	store_load_barrier(l->utype);
> 
>  	while (l->flag[other] == 1 && l->victim == self)
>  		rte_pause();
> +	rte_smp_rmb();
>  }
> 
>  static void
> --

Acked-by: Konstantin Ananyev <konstantin.ananyev@intel.com>

> 1.8.3.1


^ permalink raw reply	[flat|nested] 4+ messages in thread

end of thread, other threads:[~2019-05-07 10:40 UTC | newest]

Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2019-05-06 19:24 [dpdk-dev] [PATCH v2 4/4] test: fix memory barrier test failure on power CPUs David Christensen
2019-05-06 19:24 ` David Christensen
2019-05-07 10:40 ` Ananyev, Konstantin
2019-05-07 10:40   ` Ananyev, Konstantin

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).