On 05/01/2014 07:24 PM, Ananyev, Konstantin wrote: > Hi Ivan, > So do I need to split that patch into 2 and resubmit, or can it be applied > like that? Yes, split the patch into 2 independent patches and resubmit them, please. Thanks.
Regards, Ivan > Thanks > Konstantin > > -----Original Message----- > From: Ivan Boule [mailto:ivan.boule at 6wind.com] > Sent: Wednesday, April 30, 2014 10:49 AM > To: Ananyev, Konstantin; dev at dpdk.org > Subject: Re: [dpdk-dev] [PATCH] ixgbevf jumbo frame issue with DPDK VF > > Hi Konstantin, > > The content's of your patch is OK. > However, the following fix in the function `eth_igbvf_rx_init`: > > - if (hw->mac.type == e1000_82576) { > + if (hw->mac.type == e1000_vfadapt) { > > should be sent in a different patch (without the spurious blank > character ) , > as this fix is not related to the jumbo frame issue that is addressed here. > > Regards, > Ivan > > On 04/24/2014 06:45 PM, Ananyev, Konstantin wrote: >> When latest Linux ixgbe PF is used, and DPDK VF is used in DPDK application, >> jumbo frames are not received. >> Also - if Linux ixgbe PF has MTU set to 1500 (default), >> then normal sized packets can be received by DPDK VF. >> However, if Linux PF has MTU > 1500, then DPDK VF receives no packets >> (normal or jumbo). >> With ixgbe_mbox_api_10 ixgbe simply didn't allow set VF MTU > 1514 for 82599. >> With ixgbe_mbox_ajpi_11 it does, though now, if PF uses jumbo frames, >> it simply disables RX for all VFs. >> So to work with PF ithat using jumbo frames, at startup each VF has to: >> 1. negotiate with PF mbox_api_11. >> 2. Send to PF SET_LPE message with desired MTU. >> Note, that if PF already uses MTU bigger then asked by the VF, >> then PF wouldn't take any action. >> >> Signed-off-by: Konstantin Ananyev <konstantin.ananyev at intel.com> >> --- >> lib/librte_pmd_e1000/igb_rxtx.c | 7 ++++- >> lib/librte_pmd_ixgbe/ixgbe_ethdev.c | 47 >> ++++++++++++++++++++++++---------- >> lib/librte_pmd_ixgbe/ixgbe_rxtx.c | 4 +++ >> 3 files changed, 43 insertions(+), 15 deletions(-) >> >> diff --git a/lib/librte_pmd_e1000/igb_rxtx.c >> b/lib/librte_pmd_e1000/igb_rxtx.c >> index 4608595..1ebe2f5 100644 >> --- a/lib/librte_pmd_e1000/igb_rxtx.c >> +++ b/lib/librte_pmd_e1000/igb_rxtx.c >> @@ -2077,6 +2077,11 @@ eth_igbvf_rx_init(struct rte_eth_dev *dev) >> >> hw = E1000_DEV_PRIVATE_TO_HW(dev->data->dev_private); >> >> + /* setup MTU */ >> + e1000_rlpml_set_vf(hw, >> + (uint16_t)(dev->data->dev_conf.rxmode.max_rx_pkt_len + >> + VLAN_TAG_SIZE)); >> + >> /* Configure and enable each RX queue. */ >> rctl_bsize = 0; >> dev->rx_pkt_burst = eth_igb_recv_pkts; >> @@ -2149,7 +2154,7 @@ eth_igbvf_rx_init(struct rte_eth_dev *dev) >> rxdctl &= 0xFFF00000; >> rxdctl |= (rxq->pthresh & 0x1F); >> rxdctl |= ((rxq->hthresh & 0x1F) << 8); >> - if (hw->mac.type == e1000_82576) { >> + if (hw->mac.type == e1000_vfadapt) { >> /* >> * Workaround of 82576 VF Erratum >> * force set WTHRESH to 1 >> diff --git a/lib/librte_pmd_ixgbe/ixgbe_ethdev.c >> b/lib/librte_pmd_ixgbe/ixgbe_ethdev.c >> index a5a7f9a..6dd52d7 100644 >> --- a/lib/librte_pmd_ixgbe/ixgbe_ethdev.c >> +++ b/lib/librte_pmd_ixgbe/ixgbe_ethdev.c >> @@ -808,19 +808,30 @@ eth_ixgbe_dev_init(__attribute__((unused)) struct >> eth_driver *eth_drv, >> return 0; >> } >> >> -static void ixgbevf_get_queue_num(struct ixgbe_hw *hw) >> + >> +/* >> + * Negotiate mailbox API version with the PF. >> + * After reset API version is always set to the basic one >> (ixgbe_mbox_api_10). >> + * Then we try to negotiate starting with the most recent one. >> + * If all negotiation attempts fail, then we will proceed with >> + * the default one (ixgbe_mbox_api_10). >> + */ >> +static void >> +ixgbevf_negotiate_api(struct ixgbe_hw *hw) >> { >> - /* Traffic classes are not supported by now */ >> - unsigned int tcs, tc; >> + int32_t i; >> >> - /* >> - * Must let PF know we are at mailbox API version 1.1. >> - * Otherwise PF won't answer properly. >> - * In case that PF fails to provide Rx/Tx queue number, >> - * max_tx_queues and max_rx_queues remain to be 1. >> - */ >> - if (!ixgbevf_negotiate_api_version(hw, ixgbe_mbox_api_11)) >> - ixgbevf_get_queues(hw, &tcs, &tc); >> + /* start with highest supported, proceed down */ >> + static const enum ixgbe_pfvf_api_rev sup_ver[] = { >> + ixgbe_mbox_api_11, >> + ixgbe_mbox_api_10, >> + }; >> + >> + for (i = 0; >> + i != RTE_DIM(sup_ver) && >> + ixgbevf_negotiate_api_version(hw, sup_ver[i]) != 0; >> + i++) >> + ; >> } >> >> /* >> @@ -830,9 +841,11 @@ static int >> eth_ixgbevf_dev_init(__attribute__((unused)) struct eth_driver *eth_drv, >> struct rte_eth_dev *eth_dev) >> { >> - struct rte_pci_device *pci_dev; >> - struct ixgbe_hw *hw = >> IXGBE_DEV_PRIVATE_TO_HW(eth_dev->data->dev_private); >> int diag; >> + uint32_t tc, tcs; >> + struct rte_pci_device *pci_dev; >> + struct ixgbe_hw *hw = >> + IXGBE_DEV_PRIVATE_TO_HW(eth_dev->data->dev_private); >> struct ixgbe_vfta * shadow_vfta = >> IXGBE_DEV_PRIVATE_TO_VFTA(eth_dev->data->dev_private); >> struct ixgbe_hwstrip *hwstrip = >> @@ -891,8 +904,11 @@ eth_ixgbevf_dev_init(__attribute__((unused)) struct >> eth_driver *eth_drv, >> return (diag); >> } >> >> + /* negotiate mailbox API version to use with the PF. */ >> + ixgbevf_negotiate_api(hw); >> + >> /* Get Rx/Tx queue count via mailbox, which is ready after reset_hw */ >> - ixgbevf_get_queue_num(hw); >> + ixgbevf_get_queues(hw, &tcs, &tc); >> >> /* Allocate memory for storing MAC addresses */ >> eth_dev->data->mac_addrs = rte_zmalloc("ixgbevf", ETHER_ADDR_LEN * >> @@ -2518,6 +2534,9 @@ ixgbevf_dev_start(struct rte_eth_dev *dev) >> >> hw->mac.ops.reset_hw(hw); >> >> + /* negotiate mailbox API version to use with the PF. */ >> + ixgbevf_negotiate_api(hw); >> + >> ixgbevf_dev_tx_init(dev); >> >> /* This can fail when allocating mbufs for descriptor rings */ >> diff --git a/lib/librte_pmd_ixgbe/ixgbe_rxtx.c >> b/lib/librte_pmd_ixgbe/ixgbe_rxtx.c >> index 55414b9..7930dbd 100644 >> --- a/lib/librte_pmd_ixgbe/ixgbe_rxtx.c >> +++ b/lib/librte_pmd_ixgbe/ixgbe_rxtx.c >> @@ -3594,6 +3594,10 @@ ixgbevf_dev_rx_init(struct rte_eth_dev *dev) >> PMD_INIT_FUNC_TRACE(); >> hw = IXGBE_DEV_PRIVATE_TO_HW(dev->data->dev_private); >> >> + /* setup MTU */ >> + ixgbevf_rlpml_set_vf(hw, >> + (uint16_t)dev->data->dev_conf.rxmode.max_rx_pkt_len); >> + >> /* Setup RX queues */ >> dev->rx_pkt_burst = ixgbe_recv_pkts; >> for (i = 0; i < dev->data->nb_rx_queues; i++) { > -- Ivan Boule 6WIND Development Engineer
