* [dpdk-users] Detect LSC capability of dpdk ports
@ 2016-06-27 9:55 John Sucaet
2016-06-27 16:23 ` Stephen Hemminger
0 siblings, 1 reply; 5+ messages in thread
From: John Sucaet @ 2016-06-27 9:55 UTC (permalink / raw)
To: users
Hi,
How can a dpdk application determine if a port has support for lsc,
before trying to configure it?
Thanks
John
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [dpdk-users] Detect LSC capability of dpdk ports
2016-06-27 9:55 [dpdk-users] Detect LSC capability of dpdk ports John Sucaet
@ 2016-06-27 16:23 ` Stephen Hemminger
2016-06-27 17:21 ` Thomas Monjalon
2016-06-28 8:20 ` John Sucaet
0 siblings, 2 replies; 5+ messages in thread
From: Stephen Hemminger @ 2016-06-27 16:23 UTC (permalink / raw)
To: John Sucaet; +Cc: users
On Mon, 27 Jun 2016 11:55:46 +0200
John Sucaet <john.sucaet@oneaccess-net.com> wrote:
> Hi,
>
> How can a dpdk application determine if a port has support for lsc,
> before trying to configure it?
>
> Thanks
>
> John
We ended up adding this patch, which never seemed to be accepted upstream.
From 79060ea428f070f309f577006af43eb4ab74586d Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <shemming@brocade.com>
Date: Tue, 3 Feb 2015 17:14:32 -0800
Subject: [PATCH 1/7] ether: add function to query for link state interrupt
Allow application to query whether link state will work.
This is also part of abstracting dependency on PCI.
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
---
lib/librte_ether/rte_ethdev.c | 14 ++++++++++++++
lib/librte_ether/rte_ethdev.h | 12 ++++++++++++
lib/librte_ether/rte_ether_version.map | 1 +
3 files changed, 27 insertions(+)
--- a/lib/librte_ether/rte_ethdev.c
+++ b/lib/librte_ether/rte_ethdev.c
@@ -1091,6 +1091,23 @@ rte_eth_dev_start(uint8_t port_id)
return 0;
}
+int
+rte_eth_has_link_state(uint8_t port_id)
+{
+ struct rte_eth_dev *dev;
+
+ if (!rte_eth_dev_is_valid_port(port_id)) {
+ RTE_PMD_DEBUG_TRACE("Invalid port_id=%d\n", port_id);
+ return 0;
+ }
+ dev = &rte_eth_devices[port_id];
+
+ if (!dev->driver || !dev->pci_dev)
+ return 0;
+
+ return (dev->pci_dev->driver->drv_flags & RTE_PCI_DRV_INTR_LSC) != 0;
+}
+
void
rte_eth_dev_stop(uint8_t port_id)
{
--- a/lib/librte_ether/rte_ethdev.h
+++ b/lib/librte_ether/rte_ethdev.h
@@ -2149,6 +2149,18 @@ extern void rte_eth_link_get_nowait(uint
struct rte_eth_link *link);
/**
+ * Test whether device supports link state interrupt mode.
+ *
+ * @param port_id
+ * The port identifier of the Ethernet device.
+ * @return
+ * - (1) if link state interrupt is supported
+ * - (0) if link state interrupt is not supported
+ */
+extern int
+rte_eth_has_link_state(uint8_t port_id);
+
+/**
* Retrieve the general I/O statistics of an Ethernet device.
*
* @param port_id
--- a/lib/librte_ether/rte_ether_version.map
+++ b/lib/librte_ether/rte_ether_version.map
@@ -83,6 +83,7 @@ DPDK_2.2 {
rte_eth_dev_wd_timeout_store;
rte_eth_dma_zone_reserve;
rte_eth_driver_register;
+ rte_eth_has_link_state;
rte_eth_led_off;
rte_eth_led_on;
rte_eth_link;
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [dpdk-users] Detect LSC capability of dpdk ports
2016-06-27 16:23 ` Stephen Hemminger
@ 2016-06-27 17:21 ` Thomas Monjalon
2016-06-27 17:35 ` Stephen Hemminger
2016-06-28 8:20 ` John Sucaet
1 sibling, 1 reply; 5+ messages in thread
From: Thomas Monjalon @ 2016-06-27 17:21 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: users, John Sucaet
2016-06-27 09:23, Stephen Hemminger:
> On Mon, 27 Jun 2016 11:55:46 +0200
> John Sucaet <john.sucaet@oneaccess-net.com> wrote:
> > How can a dpdk application determine if a port has support for lsc,
> > before trying to configure it?
>
> We ended up adding this patch, which never seemed to be accepted upstream.
No, this patch was part of a series for Hyper-V.
Why Hyper-V PMD is still not integrated? What is the status please?
> From 79060ea428f070f309f577006af43eb4ab74586d Mon Sep 17 00:00:00 2001
> From: Stephen Hemminger <shemming@brocade.com>
> Date: Tue, 3 Feb 2015 17:14:32 -0800
> Subject: [PATCH 1/7] ether: add function to query for link state interrupt
>
> Allow application to query whether link state will work.
> This is also part of abstracting dependency on PCI.
>
> Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [dpdk-users] Detect LSC capability of dpdk ports
2016-06-27 17:21 ` Thomas Monjalon
@ 2016-06-27 17:35 ` Stephen Hemminger
0 siblings, 0 replies; 5+ messages in thread
From: Stephen Hemminger @ 2016-06-27 17:35 UTC (permalink / raw)
To: Thomas Monjalon; +Cc: users, John Sucaet
On Mon, 27 Jun 2016 19:21:12 +0200
Thomas Monjalon <thomas.monjalon@6wind.com> wrote:
> 2016-06-27 09:23, Stephen Hemminger:
> > On Mon, 27 Jun 2016 11:55:46 +0200
> > John Sucaet <john.sucaet@oneaccess-net.com> wrote:
> > > How can a dpdk application determine if a port has support for lsc,
> > > before trying to configure it?
> >
> > We ended up adding this patch, which never seemed to be accepted upstream.
>
> No, this patch was part of a series for Hyper-V.
> Why Hyper-V PMD is still not integrated? What is the status please?
The original driver was on older code base. There is some activity to port
a newer FreeBSD driver code base but it was not ready last I checked.
Ask Jan Blunck the DPDK maintainer now at Brocade.
^ permalink raw reply [flat|nested] 5+ messages in thread
* Re: [dpdk-users] Detect LSC capability of dpdk ports
2016-06-27 16:23 ` Stephen Hemminger
2016-06-27 17:21 ` Thomas Monjalon
@ 2016-06-28 8:20 ` John Sucaet
1 sibling, 0 replies; 5+ messages in thread
From: John Sucaet @ 2016-06-28 8:20 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: users
Thanks, Stephen.
This function rte_eth_has_link_state was exactly what I was looking for.
As it seems interesting to more people, could it be resubmitted outside
the patch serie for Hyper-V?
Regards
John
On 27-06-16 18:23, Stephen Hemminger wrote:
> On Mon, 27 Jun 2016 11:55:46 +0200
> John Sucaet <john.sucaet@oneaccess-net.com> wrote:
>
>> Hi,
>>
>> How can a dpdk application determine if a port has support for lsc,
>> before trying to configure it?
>>
>> Thanks
>>
>> John
> We ended up adding this patch, which never seemed to be accepted upstream.
> >From 79060ea428f070f309f577006af43eb4ab74586d Mon Sep 17 00:00:00 2001
> From: Stephen Hemminger <shemming@brocade.com>
> Date: Tue, 3 Feb 2015 17:14:32 -0800
> Subject: [PATCH 1/7] ether: add function to query for link state interrupt
>
> Allow application to query whether link state will work.
> This is also part of abstracting dependency on PCI.
>
> Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
> ---
> lib/librte_ether/rte_ethdev.c | 14 ++++++++++++++
> lib/librte_ether/rte_ethdev.h | 12 ++++++++++++
> lib/librte_ether/rte_ether_version.map | 1 +
> 3 files changed, 27 insertions(+)
>
> --- a/lib/librte_ether/rte_ethdev.c
> +++ b/lib/librte_ether/rte_ethdev.c
> @@ -1091,6 +1091,23 @@ rte_eth_dev_start(uint8_t port_id)
> return 0;
> }
>
> +int
> +rte_eth_has_link_state(uint8_t port_id)
> +{
> + struct rte_eth_dev *dev;
> +
> + if (!rte_eth_dev_is_valid_port(port_id)) {
> + RTE_PMD_DEBUG_TRACE("Invalid port_id=%d\n", port_id);
> + return 0;
> + }
> + dev = &rte_eth_devices[port_id];
> +
> + if (!dev->driver || !dev->pci_dev)
> + return 0;
> +
> + return (dev->pci_dev->driver->drv_flags & RTE_PCI_DRV_INTR_LSC) != 0;
> +}
> +
> void
> rte_eth_dev_stop(uint8_t port_id)
> {
> --- a/lib/librte_ether/rte_ethdev.h
> +++ b/lib/librte_ether/rte_ethdev.h
> @@ -2149,6 +2149,18 @@ extern void rte_eth_link_get_nowait(uint
> struct rte_eth_link *link);
>
> /**
> + * Test whether device supports link state interrupt mode.
> + *
> + * @param port_id
> + * The port identifier of the Ethernet device.
> + * @return
> + * - (1) if link state interrupt is supported
> + * - (0) if link state interrupt is not supported
> + */
> +extern int
> +rte_eth_has_link_state(uint8_t port_id);
> +
> +/**
> * Retrieve the general I/O statistics of an Ethernet device.
> *
> * @param port_id
> --- a/lib/librte_ether/rte_ether_version.map
> +++ b/lib/librte_ether/rte_ether_version.map
> @@ -83,6 +83,7 @@ DPDK_2.2 {
> rte_eth_dev_wd_timeout_store;
> rte_eth_dma_zone_reserve;
> rte_eth_driver_register;
> + rte_eth_has_link_state;
> rte_eth_led_off;
> rte_eth_led_on;
> rte_eth_link;
>
^ permalink raw reply [flat|nested] 5+ messages in thread
end of thread, other threads:[~2016-06-28 8:20 UTC | newest]
Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2016-06-27 9:55 [dpdk-users] Detect LSC capability of dpdk ports John Sucaet
2016-06-27 16:23 ` Stephen Hemminger
2016-06-27 17:21 ` Thomas Monjalon
2016-06-27 17:35 ` Stephen Hemminger
2016-06-28 8:20 ` John Sucaet
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).