| Message ID | 1470374429-14848-1-git-send-email-wenzhuo.lu@intel.com (mailing list archive) |
|---|---|
| State | Superseded, archived |
| Delegated to: | Thomas Monjalon |
| Headers |
Return-Path: <dev-bounces@dpdk.org> X-Original-To: patchwork@dpdk.org Delivered-To: patchwork@dpdk.org Received: from [92.243.14.124] (localhost [IPv6:::1]) by dpdk.org (Postfix) with ESMTP id 8F8402B9B; Fri, 5 Aug 2016 07:20:39 +0200 (CEST) Received: from mga03.intel.com (mga03.intel.com [134.134.136.65]) by dpdk.org (Postfix) with ESMTP id 2899E2B98 for <dev@dpdk.org>; Fri, 5 Aug 2016 07:20:38 +0200 (CEST) Received: from fmsmga003.fm.intel.com ([10.253.24.29]) by orsmga103.jf.intel.com with ESMTP; 04 Aug 2016 22:20:37 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.28,472,1464678000"; d="scan'208";a="744479458" Received: from shvmail01.sh.intel.com ([10.239.29.42]) by FMSMGA003.fm.intel.com with ESMTP; 04 Aug 2016 22:20:36 -0700 Received: from shecgisg004.sh.intel.com (shecgisg004.sh.intel.com [10.239.29.89]) by shvmail01.sh.intel.com with ESMTP id u755KYvP030835; Fri, 5 Aug 2016 13:20:34 +0800 Received: from shecgisg004.sh.intel.com (localhost [127.0.0.1]) by shecgisg004.sh.intel.com (8.13.6/8.13.6/SuSE Linux 0.8) with ESMTP id u755KVBw014882; Fri, 5 Aug 2016 13:20:33 +0800 Received: (from wenzhuol@localhost) by shecgisg004.sh.intel.com (8.13.6/8.13.6/Submit) id u755KVpZ014878; Fri, 5 Aug 2016 13:20:31 +0800 From: Wenzhuo Lu <wenzhuo.lu@intel.com> To: dev@dpdk.org Cc: pablo.de.lara.guarch@intel.com, Wenzhuo Lu <wenzhuo.lu@intel.com> Date: Fri, 5 Aug 2016 13:20:29 +0800 Message-Id: <1470374429-14848-1-git-send-email-wenzhuo.lu@intel.com> X-Mailer: git-send-email 1.7.4.1 Subject: [dpdk-dev] [PATCH] app/testpmd: fix DCB config issue on ixgbe X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: patches and discussions about DPDK <dev.dpdk.org> List-Unsubscribe: <http://dpdk.org/ml/options/dev>, <mailto:dev-request@dpdk.org?subject=unsubscribe> List-Archive: <http://dpdk.org/ml/archives/dev/> List-Post: <mailto:dev@dpdk.org> List-Help: <mailto:dev-request@dpdk.org?subject=help> List-Subscribe: <http://dpdk.org/ml/listinfo/dev>, <mailto:dev-request@dpdk.org?subject=subscribe> Errors-To: dev-bounces@dpdk.org Sender: "dev" <dev-bounces@dpdk.org> |
Commit Message
Wenzhuo Lu
Aug. 5, 2016, 5:20 a.m. UTC
An issue is found that DCB cannot be configured on ixgbe
NICs. It's said the TX queue number is not right.
On ixgbe the max TX queue number is not fixed, it depends
on the multi-queue mode.
This patch adds the device configuration before getting
info in the DCB configuration process. So the right info
can be got depending on the configuration.
Fixes: 96c0450dff86 (ixgbe: fix dropping packets from unsupported Tx queues)
Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
---
app/test-pmd/testpmd.c | 39 +++++++++++++++++++++------------------
1 file changed, 21 insertions(+), 18 deletions(-)
Comments
Hi Wenzhuo, > -----Original Message----- > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Wenzhuo Lu > Sent: Friday, August 5, 2016 6:20 AM > To: dev@dpdk.org > Cc: De Lara Guarch, Pablo <pablo.de.lara.guarch@intel.com>; Lu, Wenzhuo > <wenzhuo.lu@intel.com> > Subject: [dpdk-dev] [PATCH] app/testpmd: fix DCB config issue on ixgbe > > An issue is found that DCB cannot be configured on ixgbe NICs. It's said the > TX queue number is not right. > On ixgbe the max TX queue number is not fixed, it depends on the multi- > queue mode. > > This patch adds the device configuration before getting info in the DCB > configuration process. So the right info can be got depending on the > configuration. > > Fixes: 96c0450dff86 (ixgbe: fix dropping packets from unsupported Tx > queues) > Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com> > --- > app/test-pmd/testpmd.c | 39 +++++++++++++++++++++------------------ > 1 file changed, 21 insertions(+), 18 deletions(-) > > diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c index > 1428974..ba41bea 100644 > --- a/app/test-pmd/testpmd.c > +++ b/app/test-pmd/testpmd.c > @@ -1962,17 +1962,30 @@ init_port_dcb_config(portid_t pid, > uint8_t pfc_en) > { > struct rte_eth_conf port_conf; > - struct rte_eth_dev_info dev_info; > struct rte_port *rte_port; > int retval; > uint16_t i; > > - rte_eth_dev_info_get(pid, &dev_info); > + rte_port = &ports[pid]; > + > + memset(&port_conf, 0, sizeof(struct rte_eth_conf)); > + /* Enter DCB configuration status */ > + dcb_config = 1; > + > + /*set configuration of DCB in vt mode and DCB in non-vt mode*/ > + retval = get_eth_dcb_conf(&port_conf, dcb_mode, num_tcs, > pfc_en); > + if (retval < 0) > + return retval; > + port_conf.rxmode.hw_vlan_filter = 1; > + > + (void)rte_eth_dev_configure(pid, 0, 0, &port_conf); The return value of rte_eth_dev_configure() should be checked. Calling rte_eth_dev_configure() with parameters nb_rx_q and nb_tx_q equal to 0 returns -EINVAL, and does nothing. Should the values of nb_rx_q and nb_tx_q be non zero? > + rte_eth_dev_info_get(pid, &rte_port->dev_info); > > /* If dev_info.vmdq_pool_base is greater than 0, > * the queue id of vmdq pools is started after pf queues. > */ > - if (dcb_mode == DCB_VT_ENABLED && dev_info.vmdq_pool_base > > 0) { > + if (dcb_mode == DCB_VT_ENABLED && > + rte_port->dev_info.vmdq_pool_base > 0) { > printf("VMDQ_DCB multi-queue mode is nonsensical" > " for port %d.", pid); > return -1; > @@ -1982,13 +1995,13 @@ init_port_dcb_config(portid_t pid, > * and has the same number of rxq and txq in dcb mode > */ > if (dcb_mode == DCB_VT_ENABLED) { > - nb_rxq = dev_info.max_rx_queues; > - nb_txq = dev_info.max_tx_queues; > + nb_rxq = rte_port->dev_info.max_rx_queues; > + nb_txq = rte_port->dev_info.max_tx_queues; > } else { > /*if vt is disabled, use all pf queues */ > - if (dev_info.vmdq_pool_base == 0) { > - nb_rxq = dev_info.max_rx_queues; > - nb_txq = dev_info.max_tx_queues; > + if (rte_port->dev_info.vmdq_pool_base == 0) { > + nb_rxq = rte_port->dev_info.max_rx_queues; > + nb_txq = rte_port->dev_info.max_tx_queues; > } else { > nb_rxq = (queueid_t)num_tcs; > nb_txq = (queueid_t)num_tcs; > @@ -1997,16 +2010,6 @@ init_port_dcb_config(portid_t pid, > } > rx_free_thresh = 64; > > - memset(&port_conf, 0, sizeof(struct rte_eth_conf)); > - /* Enter DCB configuration status */ > - dcb_config = 1; > - > - /*set configuration of DCB in vt mode and DCB in non-vt mode*/ > - retval = get_eth_dcb_conf(&port_conf, dcb_mode, num_tcs, > pfc_en); > - if (retval < 0) > - return retval; > - > - rte_port = &ports[pid]; > memcpy(&rte_port->dev_conf, &port_conf, sizeof(struct > rte_eth_conf)); > > rxtx_port_config(rte_port); > -- > 1.9.3 Regards, Bernard.
Hi Wenzhuo, <snip> > > Subject: [dpdk-dev] [PATCH] app/testpmd: fix DCB config issue on ixgbe > > > > An issue is found that DCB cannot be configured on ixgbe NICs. It's > > said the TX queue number is not right. > > On ixgbe the max TX queue number is not fixed, it depends on the > > multi- queue mode. > > > > This patch adds the device configuration before getting info in the > > DCB configuration process. So the right info can be got depending on > > the configuration. > > > > Fixes: 96c0450dff86 (ixgbe: fix dropping packets from unsupported Tx > > queues) As the fix in this patch is to testpmd, I don't think the fixes line is correct. > > Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com> > > --- > > app/test-pmd/testpmd.c | 39 +++++++++++++++++++++------------------ > > 1 file changed, 21 insertions(+), 18 deletions(-) > > > > diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c index > > 1428974..ba41bea 100644 > > --- a/app/test-pmd/testpmd.c > > +++ b/app/test-pmd/testpmd.c > > @@ -1962,17 +1962,30 @@ init_port_dcb_config(portid_t pid, > > uint8_t pfc_en) > > { > > struct rte_eth_conf port_conf; > > - struct rte_eth_dev_info dev_info; > > struct rte_port *rte_port; > > int retval; > > uint16_t i; > > > > - rte_eth_dev_info_get(pid, &dev_info); > > + rte_port = &ports[pid]; > > + > > + memset(&port_conf, 0, sizeof(struct rte_eth_conf)); > > + /* Enter DCB configuration status */ > > + dcb_config = 1; > > + > > + /*set configuration of DCB in vt mode and DCB in non-vt mode*/ > > + retval = get_eth_dcb_conf(&port_conf, dcb_mode, num_tcs, > > pfc_en); > > + if (retval < 0) > > + return retval; > > + port_conf.rxmode.hw_vlan_filter = 1; > > + > > + (void)rte_eth_dev_configure(pid, 0, 0, &port_conf); > > The return value of rte_eth_dev_configure() should be checked. > Calling rte_eth_dev_configure() with parameters nb_rx_q and nb_tx_q > equal to 0 returns -EINVAL, and does nothing. > Should the values of nb_rx_q and nb_tx_q be non zero? The call to rte_eth_dev_configure() may not be necessary, as it is also called when the port is started. > > + rte_eth_dev_info_get(pid, &rte_port->dev_info); > > > > /* If dev_info.vmdq_pool_base is greater than 0, > > * the queue id of vmdq pools is started after pf queues. > > */ > > - if (dcb_mode == DCB_VT_ENABLED && dev_info.vmdq_pool_base > > > 0) { > > + if (dcb_mode == DCB_VT_ENABLED && > > + rte_port->dev_info.vmdq_pool_base > 0) { > > printf("VMDQ_DCB multi-queue mode is nonsensical" > > " for port %d.", pid); > > return -1; > > @@ -1982,13 +1995,13 @@ init_port_dcb_config(portid_t pid, > > * and has the same number of rxq and txq in dcb mode > > */ > > if (dcb_mode == DCB_VT_ENABLED) { > > - nb_rxq = dev_info.max_rx_queues; > > - nb_txq = dev_info.max_tx_queues; > > + nb_rxq = rte_port->dev_info.max_rx_queues; > > + nb_txq = rte_port->dev_info.max_tx_queues; If nb_rxq and nb_txq are set to max_rx_queues and max_tx_queues respectively, there is a failure when the port is started in ixgbe_check_mq_mode() at line 1990 in ixgbe_ethdev.c. SRIOV is active, nb_rx_q=128 nb_tx_q=128 queue number must be less than or equal to 1. nb_rxq and nb_txq are equal to 1 at this point, if they are not changed, port start completes successfully. > > } else { > > /*if vt is disabled, use all pf queues */ > > - if (dev_info.vmdq_pool_base == 0) { > > - nb_rxq = dev_info.max_rx_queues; > > - nb_txq = dev_info.max_tx_queues; > > + if (rte_port->dev_info.vmdq_pool_base == 0) { > > + nb_rxq = rte_port->dev_info.max_rx_queues; > > + nb_txq = rte_port->dev_info.max_tx_queues; > > } else { > > nb_rxq = (queueid_t)num_tcs; > > nb_txq = (queueid_t)num_tcs; > > @@ -1997,16 +2010,6 @@ init_port_dcb_config(portid_t pid, > > } > > rx_free_thresh = 64; > > > > - memset(&port_conf, 0, sizeof(struct rte_eth_conf)); > > - /* Enter DCB configuration status */ > > - dcb_config = 1; > > - > > - /*set configuration of DCB in vt mode and DCB in non-vt mode*/ > > - retval = get_eth_dcb_conf(&port_conf, dcb_mode, num_tcs, > > pfc_en); > > - if (retval < 0) > > - return retval; > > - > > - rte_port = &ports[pid]; > > memcpy(&rte_port->dev_conf, &port_conf, sizeof(struct > > rte_eth_conf)); > > > > rxtx_port_config(rte_port); > > -- > > 1.9.3 Regards, Bernard
Hi Bernard, > -----Original Message----- > From: Iremonger, Bernard > Sent: Wednesday, August 24, 2016 11:22 PM > To: Iremonger, Bernard; Lu, Wenzhuo; dev@dpdk.org > Cc: De Lara Guarch, Pablo; Lu, Wenzhuo > Subject: RE: [dpdk-dev] [PATCH] app/testpmd: fix DCB config issue on ixgbe > > Hi Wenzhuo, > > <snip> > > > > Subject: [dpdk-dev] [PATCH] app/testpmd: fix DCB config issue on > > > ixgbe > > > > > > An issue is found that DCB cannot be configured on ixgbe NICs. It's > > > said the TX queue number is not right. > > > On ixgbe the max TX queue number is not fixed, it depends on the > > > multi- queue mode. > > > > > > This patch adds the device configuration before getting info in the > > > DCB configuration process. So the right info can be got depending on > > > the configuration. > > > > > > Fixes: 96c0450dff86 (ixgbe: fix dropping packets from unsupported Tx > > > queues) > > As the fix in this patch is to testpmd, I don't think the fixes line is correct. The bug is introduced by this patch. Before this patch, APP need not care about the multi-queue mode when it want to get the max queue number. > > > > Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com> > > > --- > > > app/test-pmd/testpmd.c | 39 +++++++++++++++++++++------------------ > > > 1 file changed, 21 insertions(+), 18 deletions(-) > > > > > > diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c index > > > 1428974..ba41bea 100644 > > > --- a/app/test-pmd/testpmd.c > > > +++ b/app/test-pmd/testpmd.c > > > @@ -1962,17 +1962,30 @@ init_port_dcb_config(portid_t pid, > > > uint8_t pfc_en) > > > { > > > struct rte_eth_conf port_conf; > > > - struct rte_eth_dev_info dev_info; > > > struct rte_port *rte_port; > > > int retval; > > > uint16_t i; > > > > > > - rte_eth_dev_info_get(pid, &dev_info); > > > + rte_port = &ports[pid]; > > > + > > > + memset(&port_conf, 0, sizeof(struct rte_eth_conf)); > > > + /* Enter DCB configuration status */ > > > + dcb_config = 1; > > > + > > > + /*set configuration of DCB in vt mode and DCB in non-vt mode*/ > > > + retval = get_eth_dcb_conf(&port_conf, dcb_mode, num_tcs, > > > pfc_en); > > > + if (retval < 0) > > > + return retval; > > > + port_conf.rxmode.hw_vlan_filter = 1; > > > + > > > + (void)rte_eth_dev_configure(pid, 0, 0, &port_conf); > > > > The return value of rte_eth_dev_configure() should be checked. > > Calling rte_eth_dev_configure() with parameters nb_rx_q and nb_tx_q > > equal to 0 returns -EINVAL, and does nothing. > > Should the values of nb_rx_q and nb_tx_q be non zero? The 0 is used on purpose. Because I don't want to configure the queues. The only purpose is to make all the configuration to write into the device. And that's why the return value is ignored by (void). > > The call to rte_eth_dev_configure() may not be necessary, as it is also called > when the port is started. In rte_ethdev.h, we can see it's said that rte_eth_dev_configure should be called before any other function of ethernet API. As the DCB configuration is changed here. We have to call rte_eth_dev_configure to make the configuration is right before we can use rte_eth_dev_info_get. > > > > + rte_eth_dev_info_get(pid, &rte_port->dev_info); > > > > > > /* If dev_info.vmdq_pool_base is greater than 0, > > > * the queue id of vmdq pools is started after pf queues. > > > */ > > > - if (dcb_mode == DCB_VT_ENABLED && dev_info.vmdq_pool_base > > > > 0) { > > > + if (dcb_mode == DCB_VT_ENABLED && > > > + rte_port->dev_info.vmdq_pool_base > 0) { > > > printf("VMDQ_DCB multi-queue mode is nonsensical" > > > " for port %d.", pid); > > > return -1; > > > @@ -1982,13 +1995,13 @@ init_port_dcb_config(portid_t pid, > > > * and has the same number of rxq and txq in dcb mode > > > */ > > > if (dcb_mode == DCB_VT_ENABLED) { > > > - nb_rxq = dev_info.max_rx_queues; > > > - nb_txq = dev_info.max_tx_queues; > > > + nb_rxq = rte_port->dev_info.max_rx_queues; > > > + nb_txq = rte_port->dev_info.max_tx_queues; > > If nb_rxq and nb_txq are set to max_rx_queues and max_tx_queues respectively, > there is a failure when the port is started in ixgbe_check_mq_mode() at line > 1990 in ixgbe_ethdev.c. > SRIOV is active, nb_rx_q=128 nb_tx_q=128 queue number must be less than or > equal to 1. I haven't hit this issue. Would you like to give more details about how to hit it? I'll check if I miss something. > > nb_rxq and nb_txq are equal to 1 at this point, if they are not changed, port start > completes successfully. > > > > > } else { > > > /*if vt is disabled, use all pf queues */ > > > - if (dev_info.vmdq_pool_base == 0) { > > > - nb_rxq = dev_info.max_rx_queues; > > > - nb_txq = dev_info.max_tx_queues; > > > + if (rte_port->dev_info.vmdq_pool_base == 0) { > > > + nb_rxq = rte_port->dev_info.max_rx_queues; > > > + nb_txq = rte_port->dev_info.max_tx_queues; > > > } else { > > > nb_rxq = (queueid_t)num_tcs; > > > nb_txq = (queueid_t)num_tcs; > > > @@ -1997,16 +2010,6 @@ init_port_dcb_config(portid_t pid, > > > } > > > rx_free_thresh = 64; > > > > > > - memset(&port_conf, 0, sizeof(struct rte_eth_conf)); > > > - /* Enter DCB configuration status */ > > > - dcb_config = 1; > > > - > > > - /*set configuration of DCB in vt mode and DCB in non-vt mode*/ > > > - retval = get_eth_dcb_conf(&port_conf, dcb_mode, num_tcs, > > > pfc_en); > > > - if (retval < 0) > > > - return retval; > > > - > > > - rte_port = &ports[pid]; > > > memcpy(&rte_port->dev_conf, &port_conf, sizeof(struct > > > rte_eth_conf)); > > > > > > rxtx_port_config(rte_port); > > > -- > > > 1.9.3 > Regards, > > Bernard
Hi Wenzhuo, <snip> > > > > Subject: [dpdk-dev] [PATCH] app/testpmd: fix DCB config issue on > > > > ixgbe > > > > > > > > An issue is found that DCB cannot be configured on ixgbe NICs. > > > > It's said the TX queue number is not right. > > > > On ixgbe the max TX queue number is not fixed, it depends on the > > > > multi- queue mode. > > > > > > > > This patch adds the device configuration before getting info in > > > > the DCB configuration process. So the right info can be got > > > > depending on the configuration. > > > > > > > > Fixes: 96c0450dff86 (ixgbe: fix dropping packets from unsupported > > > > Tx > > > > queues) > > > > As the fix in this patch is to testpmd, I don't think the fixes line is correct. > The bug is introduced by this patch. Before this patch, APP need not care > about the multi-queue mode when it want to get the max queue number. > > > > > > > Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com> > > > > --- > > > > app/test-pmd/testpmd.c | 39 > > > > +++++++++++++++++++++------------------ > > > > 1 file changed, 21 insertions(+), 18 deletions(-) > > > > > > > > diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c index > > > > 1428974..ba41bea 100644 > > > > --- a/app/test-pmd/testpmd.c > > > > +++ b/app/test-pmd/testpmd.c > > > > @@ -1962,17 +1962,30 @@ init_port_dcb_config(portid_t pid, > > > > uint8_t pfc_en) > > > > { > > > > struct rte_eth_conf port_conf; > > > > - struct rte_eth_dev_info dev_info; > > > > struct rte_port *rte_port; > > > > int retval; > > > > uint16_t i; > > > > > > > > - rte_eth_dev_info_get(pid, &dev_info); > > > > + rte_port = &ports[pid]; > > > > + > > > > + memset(&port_conf, 0, sizeof(struct rte_eth_conf)); > > > > + /* Enter DCB configuration status */ > > > > + dcb_config = 1; > > > > + > > > > + /*set configuration of DCB in vt mode and DCB in non-vt mode*/ > > > > + retval = get_eth_dcb_conf(&port_conf, dcb_mode, num_tcs, > > > > pfc_en); > > > > + if (retval < 0) > > > > + return retval; > > > > + port_conf.rxmode.hw_vlan_filter = 1; > > > > + > > > > + (void)rte_eth_dev_configure(pid, 0, 0, &port_conf); > > > > > > The return value of rte_eth_dev_configure() should be checked. > > > Calling rte_eth_dev_configure() with parameters nb_rx_q and nb_tx_q > > > equal to 0 returns -EINVAL, and does nothing. > > > Should the values of nb_rx_q and nb_tx_q be non zero? > The 0 is used on purpose. Because I don't want to configure the queues. The > only purpose is to make all the configuration to write into the device. And > that's why the return value is ignored by (void). It might be useful to add a comment to explain why rte_eth_dev_configure() is being called in this way. > > The call to rte_eth_dev_configure() may not be necessary, as it is > > also called when the port is started. > In rte_ethdev.h, we can see it's said that rte_eth_dev_configure should be > called before any other function of ethernet API. As the DCB configuration is > changed here. We have to call rte_eth_dev_configure to make the > configuration is right before we can use rte_eth_dev_info_get. > > > > > > > + rte_eth_dev_info_get(pid, &rte_port->dev_info); > > > > > > > > /* If dev_info.vmdq_pool_base is greater than 0, > > > > * the queue id of vmdq pools is started after pf queues. > > > > */ > > > > - if (dcb_mode == DCB_VT_ENABLED && dev_info.vmdq_pool_base > > > > > 0) { > > > > + if (dcb_mode == DCB_VT_ENABLED && > > > > + rte_port->dev_info.vmdq_pool_base > 0) { > > > > printf("VMDQ_DCB multi-queue mode is nonsensical" > > > > " for port %d.", pid); > > > > return -1; > > > > @@ -1982,13 +1995,13 @@ init_port_dcb_config(portid_t pid, > > > > * and has the same number of rxq and txq in dcb mode > > > > */ > > > > if (dcb_mode == DCB_VT_ENABLED) { > > > > - nb_rxq = dev_info.max_rx_queues; > > > > - nb_txq = dev_info.max_tx_queues; > > > > + nb_rxq = rte_port->dev_info.max_rx_queues; > > > > + nb_txq = rte_port->dev_info.max_tx_queues; > > > > If nb_rxq and nb_txq are set to max_rx_queues and max_tx_queues > > respectively, there is a failure when the port is started in > > ixgbe_check_mq_mode() at line > > 1990 in ixgbe_ethdev.c. > > SRIOV is active, nb_rx_q=128 nb_tx_q=128 queue number must be less > > than or equal to 1. > I haven't hit this issue. Would you like to give more details about how to hit > it? I'll check if I miss something. There is a Niantic PF and VF bound to igb_uio. Port 0 is the PF and Port 1 is the VF. ./testpmd -c 3f -l 1-5 -n 4 -- -i testpmd> set corelist 2,3,4,5 testpmd> port stop 0 /* PF is 0 */ testpmd> port config 0 dcb vt on 4 pfc on testpmd> port start 0 /* PF is 0 */ line 1990 ixgbe_ethdev.c SRIOV is active, nb_rx_q=128 nb_tx_q=128 queue number must be less than or equal to 1. /* Works if nb_rx_q and nb_tx_q set to 1 */ testpmd> show port dcb_tc 0 ================ DCB infos for port 0 ================ TC NUMBER: 4 (showing 8 a lot of the time ??) /* port start should be called first */ TC : 0 1 2 3 Priority : 0 1 2 3 BW percent : 25% 25% 25% 25% RXQ base : 0 1 2 3 RXQ number : 1 1 1 1 TXQ base : 0 1 2 3 TXQ number : 1 1 1 1 testpmd> show port dcb_tc 1 Failed to get dcb infos on port 1 > > > > nb_rxq and nb_txq are equal to 1 at this point, if they are not > > changed, port start completes successfully. > > > > > > > > } else { > > > > /*if vt is disabled, use all pf queues */ > > > > - if (dev_info.vmdq_pool_base == 0) { > > > > - nb_rxq = dev_info.max_rx_queues; > > > > - nb_txq = dev_info.max_tx_queues; > > > > + if (rte_port->dev_info.vmdq_pool_base == 0) { > > > > + nb_rxq = rte_port->dev_info.max_rx_queues; > > > > + nb_txq = rte_port->dev_info.max_tx_queues; > > > > } else { > > > > nb_rxq = (queueid_t)num_tcs; > > > > nb_txq = (queueid_t)num_tcs; > > > > @@ -1997,16 +2010,6 @@ init_port_dcb_config(portid_t pid, > > > > } > > > > rx_free_thresh = 64; > > > > > > > > - memset(&port_conf, 0, sizeof(struct rte_eth_conf)); > > > > - /* Enter DCB configuration status */ > > > > - dcb_config = 1; > > > > - > > > > - /*set configuration of DCB in vt mode and DCB in non-vt mode*/ > > > > - retval = get_eth_dcb_conf(&port_conf, dcb_mode, num_tcs, > > > > pfc_en); > > > > - if (retval < 0) > > > > - return retval; > > > > - > > > > - rte_port = &ports[pid]; > > > > memcpy(&rte_port->dev_conf, &port_conf, sizeof(struct > > > > rte_eth_conf)); > > > > > > > > rxtx_port_config(rte_port); > > > > -- > > > > 1.9.3 Regards, Bernard
Hi Bernard, > > > > > > > > The return value of rte_eth_dev_configure() should be checked. > > > > Calling rte_eth_dev_configure() with parameters nb_rx_q and > > > > nb_tx_q equal to 0 returns -EINVAL, and does nothing. > > > > Should the values of nb_rx_q and nb_tx_q be non zero? > > The 0 is used on purpose. Because I don't want to configure the > > queues. The only purpose is to make all the configuration to write > > into the device. And that's why the return value is ignored by (void). > > It might be useful to add a comment to explain why rte_eth_dev_configure() is > being called in this way. Thanks for the suggestion. I'll add it:) > > > > > > If nb_rxq and nb_txq are set to max_rx_queues and max_tx_queues > > > respectively, there is a failure when the port is started in > > > ixgbe_check_mq_mode() at line > > > 1990 in ixgbe_ethdev.c. > > > SRIOV is active, nb_rx_q=128 nb_tx_q=128 queue number must be less > > > than or equal to 1. > > I haven't hit this issue. Would you like to give more details about > > how to hit it? I'll check if I miss something. > > There is a Niantic PF and VF bound to igb_uio. Port 0 is the PF and Port 1 is the > VF. > ./testpmd -c 3f -l 1-5 -n 4 -- -i > testpmd> set corelist 2,3,4,5 > testpmd> port stop 0 /* PF is 0 */ > testpmd> port config 0 dcb vt on 4 pfc on port start 0 /* PF is 0 */ > line 1990 ixgbe_ethdev.c > SRIOV is active, nb_rx_q=128 nb_tx_q=128 queue number must be less than or > equal to 1. > /* Works if nb_rx_q and nb_tx_q set to 1 */ To my opinion, it's a by-design limitation. After using the DCB configuration CLI, the queue number is set to a fix number which is the max number. But as you pointed, when SRIOV is active there's another requirement for the queue number. We need to investigate deeper and find a solution for it. But I think it's another story. We need another patch for it. > > testpmd> show port dcb_tc 0 > ================ DCB infos for port 0 ================ > TC NUMBER: 4 (showing 8 a lot of the time ??) /* port start should be called > first */ > TC : 0 1 2 3 > Priority : 0 1 2 3 > BW percent : 25% 25% 25% 25% > RXQ base : 0 1 2 3 > RXQ number : 1 1 1 1 > TXQ base : 0 1 2 3 > TXQ number : 1 1 1 1 > testpmd> show port dcb_tc 1 > Failed to get dcb infos on port 1 > > > > > > > nb_rxq and nb_txq are equal to 1 at this point, if they are not > > > changed, port start completes successfully. > > > > > > > > > > > } else { > > > > > /*if vt is disabled, use all pf queues */ > > > > > - if (dev_info.vmdq_pool_base == 0) { > > > > > - nb_rxq = dev_info.max_rx_queues; > > > > > - nb_txq = dev_info.max_tx_queues; > > > > > + if (rte_port->dev_info.vmdq_pool_base == 0) { > > > > > + nb_rxq = rte_port->dev_info.max_rx_queues; > > > > > + nb_txq = rte_port->dev_info.max_tx_queues; > > > > > } else { > > > > > nb_rxq = (queueid_t)num_tcs; > > > > > nb_txq = (queueid_t)num_tcs; @@ -1997,16 +2010,6 > @@ > > > > > init_port_dcb_config(portid_t pid, > > > > > } > > > > > rx_free_thresh = 64; > > > > > > > > > > - memset(&port_conf, 0, sizeof(struct rte_eth_conf)); > > > > > - /* Enter DCB configuration status */ > > > > > - dcb_config = 1; > > > > > - > > > > > - /*set configuration of DCB in vt mode and DCB in non-vt mode*/ > > > > > - retval = get_eth_dcb_conf(&port_conf, dcb_mode, num_tcs, > > > > > pfc_en); > > > > > - if (retval < 0) > > > > > - return retval; > > > > > - > > > > > - rte_port = &ports[pid]; > > > > > memcpy(&rte_port->dev_conf, &port_conf, sizeof(struct > > > > > rte_eth_conf)); > > > > > > > > > > rxtx_port_config(rte_port); > > > > > -- > > > > > 1.9.3 > Regards, > > Bernard
Hi Wenzhuo, <snip> > > > > If nb_rxq and nb_txq are set to max_rx_queues and max_tx_queues > > > > respectively, there is a failure when the port is started in > > > > ixgbe_check_mq_mode() at line > > > > 1990 in ixgbe_ethdev.c. > > > > SRIOV is active, nb_rx_q=128 nb_tx_q=128 queue number must be less > > > > than or equal to 1. > > > I haven't hit this issue. Would you like to give more details about > > > how to hit it? I'll check if I miss something. > > > > There is a Niantic PF and VF bound to igb_uio. Port 0 is the PF and > > Port 1 is the VF. > > ./testpmd -c 3f -l 1-5 -n 4 -- -i > > testpmd> set corelist 2,3,4,5 > > testpmd> port stop 0 /* PF is 0 */ > > testpmd> port config 0 dcb vt on 4 pfc on port start 0 /* PF is 0 */ > > line 1990 ixgbe_ethdev.c > > SRIOV is active, nb_rx_q=128 nb_tx_q=128 queue number must be less > > than or equal to 1. > > /* Works if nb_rx_q and nb_tx_q set to 1 */ > To my opinion, it's a by-design limitation. After using the DCB configuration > CLI, the queue number is set to a fix number which is the max number. But > as you pointed, when SRIOV is active there's another requirement for the > queue number. > We need to investigate deeper and find a solution for it. But I think it's > another story. We need another patch for it. Line 1997 in testpmd.c 1997 if (dcb_mode == DCB_VT_ENABLED) { nb_rxq = rte_port->dev_info.max_rx_queues; nb_txq = rte_port->dev_info.max_tx_queues; } else { 2001 /*if vt is disabled, use all pf queues */ if (rte_port->dev_info.vmdq_pool_base == 0) { nb_rxq = rte_port->dev_info.max_rx_queues; nb_txq = rte_port->dev_info.max_tx_queues; } else { nb_rxq = (queueid_t)num_tcs; nb_txq = (queueid_t)num_tcs; } } The comment at line 2001 implies that when dcb_mode is DCB_VT_ENABLED all pf queues should not be used. When dcb_mode is DCB_VT_ENABLED, setting nb_rxq and nb_txq equal to 1 works when the PF (port 0) is started. When dcb_mode is DCB_VT_ENABLED, setting nb_rxq to max_rx_queues and nb_txq to max_tx_queues results in the following failure in ixgbe when the PF (port 0) is started. SRIOV is active, nb_rx_q=128 nb_tx_q=128 queue number must be less than or equal to 1. <snip> Regards, Bernard
Hi Bernard, > -----Original Message----- > From: Iremonger, Bernard > Sent: Friday, August 26, 2016 6:04 PM > To: Lu, Wenzhuo; dev@dpdk.org > Cc: De Lara Guarch, Pablo; Wu, Jingjing > Subject: RE: [dpdk-dev] [PATCH] app/testpmd: fix DCB config issue on ixgbe > > Hi Wenzhuo, > > <snip> > > > > > > If nb_rxq and nb_txq are set to max_rx_queues and max_tx_queues > > > > > respectively, there is a failure when the port is started in > > > > > ixgbe_check_mq_mode() at line > > > > > 1990 in ixgbe_ethdev.c. > > > > > SRIOV is active, nb_rx_q=128 nb_tx_q=128 queue number must be > > > > > less than or equal to 1. > > > > I haven't hit this issue. Would you like to give more details > > > > about how to hit it? I'll check if I miss something. > > > > > > There is a Niantic PF and VF bound to igb_uio. Port 0 is the PF and > > > Port 1 is the VF. > > > ./testpmd -c 3f -l 1-5 -n 4 -- -i > > > testpmd> set corelist 2,3,4,5 > > > testpmd> port stop 0 /* PF is 0 */ > > > testpmd> port config 0 dcb vt on 4 pfc on port start 0 /* PF is 0 */ > > > line 1990 ixgbe_ethdev.c > > > SRIOV is active, nb_rx_q=128 nb_tx_q=128 queue number must be less > > > than or equal to 1. > > > /* Works if nb_rx_q and nb_tx_q set to 1 */ > > To my opinion, it's a by-design limitation. After using the DCB > > configuration CLI, the queue number is set to a fix number which is > > the max number. But as you pointed, when SRIOV is active there's > > another requirement for the queue number. > > We need to investigate deeper and find a solution for it. But I think > > it's another story. We need another patch for it. > > Line 1997 in testpmd.c > 1997 if (dcb_mode == DCB_VT_ENABLED) { > nb_rxq = rte_port->dev_info.max_rx_queues; > nb_txq = rte_port->dev_info.max_tx_queues; > } else { > 2001 /*if vt is disabled, use all pf queues */ > if (rte_port->dev_info.vmdq_pool_base == 0) { > nb_rxq = rte_port->dev_info.max_rx_queues; > nb_txq = rte_port->dev_info.max_tx_queues; > } else { > nb_rxq = (queueid_t)num_tcs; > nb_txq = (queueid_t)num_tcs; > } > } > > The comment at line 2001 implies that when dcb_mode is DCB_VT_ENABLED all > pf queues should not be used. > When dcb_mode is DCB_VT_ENABLED, setting nb_rxq and nb_txq equal to 1 > works when the PF (port 0) is started. > When dcb_mode is DCB_VT_ENABLED, setting nb_rxq to max_rx_queues and > nb_txq to max_tx_queues results in the following failure in ixgbe when the PF > (port 0) is started. > SRIOV is active, nb_rx_q=128 nb_tx_q=128 queue number must be less than or > equal to 1. PF and its VF port cannot be used in the same APP. As VF depends on its PF. We must wait until PF is completed, then run VF. Normally, like use DPDK PF on host, then use DPDK VF on guest. If you use PF and VF on parallel, the behavior is unpredicted. I think that's why you see this prompt " SRIOV is active, nb_rx_q=128 nb_tx_q=128 queue number must be less than or equal to 1.". I've tried PF only testpmd. The result is like " PMD: ixgbe_check_mq_mode(): SRIOV active, unsupported mq_mode rx 6.". It means DCB is not supported by DPDK PF.
What is the status of this patch? 2016-08-05 13:20, Wenzhuo Lu: > An issue is found that DCB cannot be configured on ixgbe > NICs. It's said the TX queue number is not right. > On ixgbe the max TX queue number is not fixed, it depends > on the multi-queue mode. > > This patch adds the device configuration before getting > info in the DCB configuration process. So the right info > can be got depending on the configuration. > > Fixes: 96c0450dff86 (ixgbe: fix dropping packets from unsupported Tx queues) > Signed-off-by: Wenzhuo Lu <wenzhuo.lu@intel.com>
Hi Thomas, > -----Original Message----- > From: Thomas Monjalon [mailto:thomas.monjalon@6wind.com] > Sent: Saturday, September 24, 2016 2:25 AM > To: Lu, Wenzhuo; De Lara Guarch, Pablo > Cc: dev@dpdk.org > Subject: Re: [dpdk-dev] [PATCH] app/testpmd: fix DCB config issue on ixgbe > > What is the status of this patch? I need to send a V2 to add more explanation in the code. I'll send it soon.
diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c index 1428974..ba41bea 100644 --- a/app/test-pmd/testpmd.c +++ b/app/test-pmd/testpmd.c @@ -1962,17 +1962,30 @@ init_port_dcb_config(portid_t pid, uint8_t pfc_en) { struct rte_eth_conf port_conf; - struct rte_eth_dev_info dev_info; struct rte_port *rte_port; int retval; uint16_t i; - rte_eth_dev_info_get(pid, &dev_info); + rte_port = &ports[pid]; + + memset(&port_conf, 0, sizeof(struct rte_eth_conf)); + /* Enter DCB configuration status */ + dcb_config = 1; + + /*set configuration of DCB in vt mode and DCB in non-vt mode*/ + retval = get_eth_dcb_conf(&port_conf, dcb_mode, num_tcs, pfc_en); + if (retval < 0) + return retval; + port_conf.rxmode.hw_vlan_filter = 1; + + (void)rte_eth_dev_configure(pid, 0, 0, &port_conf); + rte_eth_dev_info_get(pid, &rte_port->dev_info); /* If dev_info.vmdq_pool_base is greater than 0, * the queue id of vmdq pools is started after pf queues. */ - if (dcb_mode == DCB_VT_ENABLED && dev_info.vmdq_pool_base > 0) { + if (dcb_mode == DCB_VT_ENABLED && + rte_port->dev_info.vmdq_pool_base > 0) { printf("VMDQ_DCB multi-queue mode is nonsensical" " for port %d.", pid); return -1; @@ -1982,13 +1995,13 @@ init_port_dcb_config(portid_t pid, * and has the same number of rxq and txq in dcb mode */ if (dcb_mode == DCB_VT_ENABLED) { - nb_rxq = dev_info.max_rx_queues; - nb_txq = dev_info.max_tx_queues; + nb_rxq = rte_port->dev_info.max_rx_queues; + nb_txq = rte_port->dev_info.max_tx_queues; } else { /*if vt is disabled, use all pf queues */ - if (dev_info.vmdq_pool_base == 0) { - nb_rxq = dev_info.max_rx_queues; - nb_txq = dev_info.max_tx_queues; + if (rte_port->dev_info.vmdq_pool_base == 0) { + nb_rxq = rte_port->dev_info.max_rx_queues; + nb_txq = rte_port->dev_info.max_tx_queues; } else { nb_rxq = (queueid_t)num_tcs; nb_txq = (queueid_t)num_tcs; @@ -1997,16 +2010,6 @@ init_port_dcb_config(portid_t pid, } rx_free_thresh = 64; - memset(&port_conf, 0, sizeof(struct rte_eth_conf)); - /* Enter DCB configuration status */ - dcb_config = 1; - - /*set configuration of DCB in vt mode and DCB in non-vt mode*/ - retval = get_eth_dcb_conf(&port_conf, dcb_mode, num_tcs, pfc_en); - if (retval < 0) - return retval; - - rte_port = &ports[pid]; memcpy(&rte_port->dev_conf, &port_conf, sizeof(struct rte_eth_conf)); rxtx_port_config(rte_port);