From 9936a7bbe56df432838fef658aea6bcfdd994021 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 3 Aug 2012 04:46:59 +0000 Subject: igb: reduce Rx header size Reduce skb truesize by 256 bytes. Signed-off-by: Eric Dumazet Cc: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'drivers/net/ethernet/intel/igb/igb.h') diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 9e572dd29ab..0c9f62caa8f 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -131,9 +131,9 @@ struct vf_data_storage { #define MAXIMUM_ETHERNET_VLAN_SIZE 1522 /* Supported Rx Buffer Sizes */ -#define IGB_RXBUFFER_512 512 +#define IGB_RXBUFFER_256 256 #define IGB_RXBUFFER_16384 16384 -#define IGB_RX_HDR_LEN IGB_RXBUFFER_512 +#define IGB_RX_HDR_LEN IGB_RXBUFFER_256 /* How many Tx Descriptors do we need to call netif_wake_queue ? */ #define IGB_TX_QUEUE_WAKE 16 -- cgit v1.2.3-70-g09d2 From 3c89f6d0d4aa92ff252c17f8f6b5c8983ae2b77e Mon Sep 17 00:00:00 2001 From: Matthew Vick Date: Fri, 10 Aug 2012 05:40:43 +0000 Subject: igb: Tidy up wrapping for CONFIG_IGB_PTP. For users without CONFIG_IGB_PTP=y, we should not be compiling any PTP code into the driver. Tidy up the wrapping in igb to support this. Cc: Richard Cochran Signed-off-by: Matthew Vick Acked-by: Jacob Keller Tested-by: Jeff Pieper Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb.h | 8 ++++++-- drivers/net/ethernet/intel/igb/igb_ethtool.c | 4 ++-- drivers/net/ethernet/intel/igb/igb_main.c | 23 +++++++++++++++++------ 3 files changed, 25 insertions(+), 10 deletions(-) (limited to 'drivers/net/ethernet/intel/igb/igb.h') diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 0c9f62caa8f..a3b5b908448 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -34,9 +34,11 @@ #include "e1000_mac.h" #include "e1000_82575.h" +#ifdef CONFIG_IGB_PTP #include #include #include +#endif /* CONFIG_IGB_PTP */ #include #include @@ -376,12 +378,15 @@ struct igb_adapter { int node; u32 *shadow_vfta; +#ifdef CONFIG_IGB_PTP struct ptp_clock *ptp_clock; struct ptp_clock_info caps; struct delayed_work overflow_work; spinlock_t tmreg_lock; struct cyclecounter cc; struct timecounter tc; +#endif /* CONFIG_IGB_PTP */ + char fw_version[32]; }; @@ -436,12 +441,11 @@ extern void igb_set_fw_version(struct igb_adapter *); #ifdef CONFIG_IGB_PTP extern void igb_ptp_init(struct igb_adapter *adapter); extern void igb_ptp_remove(struct igb_adapter *adapter); - extern void igb_systim_to_hwtstamp(struct igb_adapter *adapter, struct skb_shared_hwtstamps *hwtstamps, u64 systim); +#endif /* CONFIG_IGB_PTP */ -#endif static inline s32 igb_reset_phy(struct e1000_hw *hw) { if (hw->phy.ops.reset) diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index a2944412a55..0c4e29aa24c 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -2338,8 +2338,8 @@ static int igb_ethtool_get_ts_info(struct net_device *dev, return 0; } +#endif /* CONFIG_IGB_PTP */ -#endif static const struct ethtool_ops igb_ethtool_ops = { .get_settings = igb_get_settings, .set_settings = igb_set_settings, @@ -2370,7 +2370,7 @@ static const struct ethtool_ops igb_ethtool_ops = { .complete = igb_ethtool_complete, #ifdef CONFIG_IGB_PTP .get_ts_info = igb_ethtool_get_ts_info, -#endif +#endif /* CONFIG_IGB_PTP */ }; void igb_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 73cc273ef98..03477d7451e 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2180,11 +2180,12 @@ static int __devinit igb_probe(struct pci_dev *pdev, } #endif + #ifdef CONFIG_IGB_PTP /* do hw tstamp init after resetting */ igb_ptp_init(adapter); +#endif /* CONFIG_IGB_PTP */ -#endif dev_info(&pdev->dev, "Intel(R) Gigabit Ethernet Network Connection\n"); /* print bus type/speed/width info */ dev_info(&pdev->dev, "%s: (PCIe:%s:%s) %pM\n", @@ -2260,8 +2261,8 @@ static void __devexit igb_remove(struct pci_dev *pdev) pm_runtime_get_noresume(&pdev->dev); #ifdef CONFIG_IGB_PTP igb_ptp_remove(adapter); +#endif /* CONFIG_IGB_PTP */ -#endif /* * The watchdog timer may be rescheduled, so explicitly * disable watchdog from being rescheduled. @@ -3184,8 +3185,10 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, srrctl |= (PAGE_SIZE / 2) >> E1000_SRRCTL_BSIZEPKT_SHIFT; #endif srrctl |= E1000_SRRCTL_DESCTYPE_HDR_SPLIT_ALWAYS; +#ifdef CONFIG_IGB_PTP if (hw->mac.type >= e1000_82580) srrctl |= E1000_SRRCTL_TIMESTAMP; +#endif /* CONFIG_IGB_PTP */ /* Only set Drop Enable if we are supporting multiple queues */ if (adapter->vfs_allocated_count || adapter->num_rx_queues > 1) srrctl |= E1000_SRRCTL_DROP_EN; @@ -4229,9 +4232,11 @@ static __le32 igb_tx_cmd_type(u32 tx_flags) if (tx_flags & IGB_TX_FLAGS_VLAN) cmd_type |= cpu_to_le32(E1000_ADVTXD_DCMD_VLE); +#ifdef CONFIG_IGB_PTP /* set timestamp bit if present */ if (tx_flags & IGB_TX_FLAGS_TSTAMP) cmd_type |= cpu_to_le32(E1000_ADVTXD_MAC_TSTAMP); +#endif /* CONFIG_IGB_PTP */ /* set segmentation bits for TSO */ if (tx_flags & IGB_TX_FLAGS_TSO) @@ -4462,10 +4467,12 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, first->bytecount = skb->len; first->gso_segs = 1; +#ifdef CONFIG_IGB_PTP if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; tx_flags |= IGB_TX_FLAGS_TSTAMP; } +#endif /* CONFIG_IGB_PTP */ if (vlan_tx_tag_present(skb)) { tx_flags |= IGB_TX_FLAGS_VLAN; @@ -5772,8 +5779,8 @@ static void igb_tx_hwtstamp(struct igb_q_vector *q_vector, igb_systim_to_hwtstamp(adapter, &shhwtstamps, regval); skb_tstamp_tx(buffer_info->skb, &shhwtstamps); } +#endif /* CONFIG_IGB_PTP */ -#endif /** * igb_clean_tx_irq - Reclaim resources after transmit completes * @q_vector: pointer to q_vector containing needed info @@ -5821,8 +5828,8 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) #ifdef CONFIG_IGB_PTP /* retrieve hardware timestamp */ igb_tx_hwtstamp(q_vector, tx_buffer); +#endif /* CONFIG_IGB_PTP */ -#endif /* free the skb */ dev_kfree_skb_any(tx_buffer->skb); tx_buffer->skb = NULL; @@ -6033,8 +6040,8 @@ static void igb_rx_hwtstamp(struct igb_q_vector *q_vector, igb_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), regval); } +#endif /* CONFIG_IGB_PTP */ -#endif static void igb_rx_vlan(struct igb_ring *ring, union e1000_adv_rx_desc *rx_desc, struct sk_buff *skb) @@ -6147,7 +6154,7 @@ static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, int budget) #ifdef CONFIG_IGB_PTP igb_rx_hwtstamp(q_vector, rx_desc, skb); -#endif +#endif /* CONFIG_IGB_PTP */ igb_rx_hash(rx_ring, rx_desc, skb); igb_rx_checksum(rx_ring, rx_desc, skb); igb_rx_vlan(rx_ring, rx_desc, skb); @@ -6340,6 +6347,7 @@ static int igb_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) return 0; } +#ifdef CONFIG_IGB_PTP /** * igb_hwtstamp_ioctl - control hardware time stamping * @netdev: @@ -6514,6 +6522,7 @@ static int igb_hwtstamp_ioctl(struct net_device *netdev, return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? -EFAULT : 0; } +#endif /* CONFIG_IGB_PTP */ /** * igb_ioctl - @@ -6528,8 +6537,10 @@ static int igb_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) case SIOCGMIIREG: case SIOCSMIIREG: return igb_mii_ioctl(netdev, ifr, cmd); +#ifdef CONFIG_IGB_PTP case SIOCSHWTSTAMP: return igb_hwtstamp_ioctl(netdev, ifr, cmd); +#endif /* CONFIG_IGB_PTP */ default: return -EOPNOTSUPP; } -- cgit v1.2.3-70-g09d2 From a79f4f88261d7fd492121daf85beafff663f1f01 Mon Sep 17 00:00:00 2001 From: Matthew Vick Date: Fri, 10 Aug 2012 05:40:44 +0000 Subject: igb: Update PTP function names/variables and locations. Where possible, move PTP-related functions into igb_ptp.c and update the names of functions and variables to match the established coding style in the files and specify that they are PTP-specific. Cc: Richard Cochran Signed-off-by: Matthew Vick Tested-by: Jeff Pieper Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb.h | 17 +- drivers/net/ethernet/intel/igb/igb_ethtool.c | 34 +- drivers/net/ethernet/intel/igb/igb_main.c | 257 +------------- drivers/net/ethernet/intel/igb/igb_ptp.c | 485 ++++++++++++++++++++------- 4 files changed, 398 insertions(+), 395 deletions(-) (limited to 'drivers/net/ethernet/intel/igb/igb.h') diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index a3b5b908448..797346998d5 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -344,7 +344,6 @@ struct igb_adapter { /* OS defined structs */ struct pci_dev *pdev; - struct hwtstamp_config hwtstamp_config; spinlock_t stats64_lock; struct rtnl_link_stats64 stats64; @@ -380,8 +379,8 @@ struct igb_adapter { #ifdef CONFIG_IGB_PTP struct ptp_clock *ptp_clock; - struct ptp_clock_info caps; - struct delayed_work overflow_work; + struct ptp_clock_info ptp_caps; + struct delayed_work ptp_overflow_work; spinlock_t tmreg_lock; struct cyclecounter cc; struct timecounter tc; @@ -440,10 +439,14 @@ extern void igb_power_up_link(struct igb_adapter *); extern void igb_set_fw_version(struct igb_adapter *); #ifdef CONFIG_IGB_PTP extern void igb_ptp_init(struct igb_adapter *adapter); -extern void igb_ptp_remove(struct igb_adapter *adapter); -extern void igb_systim_to_hwtstamp(struct igb_adapter *adapter, - struct skb_shared_hwtstamps *hwtstamps, - u64 systim); +extern void igb_ptp_stop(struct igb_adapter *adapter); +extern void igb_ptp_tx_hwtstamp(struct igb_q_vector *q_vector, + struct igb_tx_buffer *buffer_info); +extern void igb_ptp_rx_hwtstamp(struct igb_q_vector *q_vector, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb); +extern int igb_ptp_hwtstamp_ioctl(struct net_device *netdev, + struct ifreq *ifr, int cmd); #endif /* CONFIG_IGB_PTP */ static inline s32 igb_reset_phy(struct e1000_hw *hw) diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 0c4e29aa24c..ffed4d06859 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -2295,21 +2295,8 @@ static void igb_get_strings(struct net_device *netdev, u32 stringset, u8 *data) } } -static int igb_ethtool_begin(struct net_device *netdev) -{ - struct igb_adapter *adapter = netdev_priv(netdev); - pm_runtime_get_sync(&adapter->pdev->dev); - return 0; -} - -static void igb_ethtool_complete(struct net_device *netdev) -{ - struct igb_adapter *adapter = netdev_priv(netdev); - pm_runtime_put(&adapter->pdev->dev); -} - #ifdef CONFIG_IGB_PTP -static int igb_ethtool_get_ts_info(struct net_device *dev, +static int igb_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) { struct igb_adapter *adapter = netdev_priv(dev); @@ -2340,6 +2327,19 @@ static int igb_ethtool_get_ts_info(struct net_device *dev, } #endif /* CONFIG_IGB_PTP */ +static int igb_ethtool_begin(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + pm_runtime_get_sync(&adapter->pdev->dev); + return 0; +} + +static void igb_ethtool_complete(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + pm_runtime_put(&adapter->pdev->dev); +} + static const struct ethtool_ops igb_ethtool_ops = { .get_settings = igb_get_settings, .set_settings = igb_set_settings, @@ -2366,11 +2366,11 @@ static const struct ethtool_ops igb_ethtool_ops = { .get_ethtool_stats = igb_get_ethtool_stats, .get_coalesce = igb_get_coalesce, .set_coalesce = igb_set_coalesce, - .begin = igb_ethtool_begin, - .complete = igb_ethtool_complete, #ifdef CONFIG_IGB_PTP - .get_ts_info = igb_ethtool_get_ts_info, + .get_ts_info = igb_get_ts_info, #endif /* CONFIG_IGB_PTP */ + .begin = igb_ethtool_begin, + .complete = igb_ethtool_complete, }; void igb_set_ethtool_ops(struct net_device *netdev) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 03477d7451e..6e39f0ca9fc 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -2260,7 +2260,7 @@ static void __devexit igb_remove(struct pci_dev *pdev) pm_runtime_get_noresume(&pdev->dev); #ifdef CONFIG_IGB_PTP - igb_ptp_remove(adapter); + igb_ptp_stop(adapter); #endif /* CONFIG_IGB_PTP */ /* @@ -5750,37 +5750,6 @@ static int igb_poll(struct napi_struct *napi, int budget) return 0; } -#ifdef CONFIG_IGB_PTP -/** - * igb_tx_hwtstamp - utility function which checks for TX time stamp - * @q_vector: pointer to q_vector containing needed info - * @buffer: pointer to igb_tx_buffer structure - * - * If we were asked to do hardware stamping and such a time stamp is - * available, then it must have been for this skb here because we only - * allow only one such packet into the queue. - */ -static void igb_tx_hwtstamp(struct igb_q_vector *q_vector, - struct igb_tx_buffer *buffer_info) -{ - struct igb_adapter *adapter = q_vector->adapter; - struct e1000_hw *hw = &adapter->hw; - struct skb_shared_hwtstamps shhwtstamps; - u64 regval; - - /* if skb does not support hw timestamp or TX stamp not valid exit */ - if (likely(!(buffer_info->tx_flags & IGB_TX_FLAGS_TSTAMP)) || - !(rd32(E1000_TSYNCTXCTL) & E1000_TSYNCTXCTL_VALID)) - return; - - regval = rd32(E1000_TXSTMPL); - regval |= (u64)rd32(E1000_TXSTMPH) << 32; - - igb_systim_to_hwtstamp(adapter, &shhwtstamps, regval); - skb_tstamp_tx(buffer_info->skb, &shhwtstamps); -} -#endif /* CONFIG_IGB_PTP */ - /** * igb_clean_tx_irq - Reclaim resources after transmit completes * @q_vector: pointer to q_vector containing needed info @@ -5827,7 +5796,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) #ifdef CONFIG_IGB_PTP /* retrieve hardware timestamp */ - igb_tx_hwtstamp(q_vector, tx_buffer); + igb_ptp_tx_hwtstamp(q_vector, tx_buffer); #endif /* CONFIG_IGB_PTP */ /* free the skb */ @@ -6001,47 +5970,6 @@ static inline void igb_rx_hash(struct igb_ring *ring, skb->rxhash = le32_to_cpu(rx_desc->wb.lower.hi_dword.rss); } -#ifdef CONFIG_IGB_PTP -static void igb_rx_hwtstamp(struct igb_q_vector *q_vector, - union e1000_adv_rx_desc *rx_desc, - struct sk_buff *skb) -{ - struct igb_adapter *adapter = q_vector->adapter; - struct e1000_hw *hw = &adapter->hw; - u64 regval; - - if (!igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP | - E1000_RXDADV_STAT_TS)) - return; - - /* - * If this bit is set, then the RX registers contain the time stamp. No - * other packet will be time stamped until we read these registers, so - * read the registers to make them available again. Because only one - * packet can be time stamped at a time, we know that the register - * values must belong to this one here and therefore we don't need to - * compare any of the additional attributes stored for it. - * - * If nothing went wrong, then it should have a shared tx_flags that we - * can turn into a skb_shared_hwtstamps. - */ - if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { - u32 *stamp = (u32 *)skb->data; - regval = le32_to_cpu(*(stamp + 2)); - regval |= (u64)le32_to_cpu(*(stamp + 3)) << 32; - skb_pull(skb, IGB_TS_HDR_LEN); - } else { - if(!(rd32(E1000_TSYNCRXCTL) & E1000_TSYNCRXCTL_VALID)) - return; - - regval = rd32(E1000_RXSTMPL); - regval |= (u64)rd32(E1000_RXSTMPH) << 32; - } - - igb_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), regval); -} -#endif /* CONFIG_IGB_PTP */ - static void igb_rx_vlan(struct igb_ring *ring, union e1000_adv_rx_desc *rx_desc, struct sk_buff *skb) @@ -6153,7 +6081,7 @@ static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, int budget) } #ifdef CONFIG_IGB_PTP - igb_rx_hwtstamp(q_vector, rx_desc, skb); + igb_ptp_rx_hwtstamp(q_vector, rx_desc, skb); #endif /* CONFIG_IGB_PTP */ igb_rx_hash(rx_ring, rx_desc, skb); igb_rx_checksum(rx_ring, rx_desc, skb); @@ -6347,183 +6275,6 @@ static int igb_mii_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) return 0; } -#ifdef CONFIG_IGB_PTP -/** - * igb_hwtstamp_ioctl - control hardware time stamping - * @netdev: - * @ifreq: - * @cmd: - * - * Outgoing time stamping can be enabled and disabled. Play nice and - * disable it when requested, although it shouldn't case any overhead - * when no packet needs it. At most one packet in the queue may be - * marked for time stamping, otherwise it would be impossible to tell - * for sure to which packet the hardware time stamp belongs. - * - * Incoming time stamping has to be configured via the hardware - * filters. Not all combinations are supported, in particular event - * type has to be specified. Matching the kind of event packet is - * not supported, with the exception of "all V2 events regardless of - * level 2 or 4". - * - **/ -static int igb_hwtstamp_ioctl(struct net_device *netdev, - struct ifreq *ifr, int cmd) -{ - struct igb_adapter *adapter = netdev_priv(netdev); - struct e1000_hw *hw = &adapter->hw; - struct hwtstamp_config config; - u32 tsync_tx_ctl = E1000_TSYNCTXCTL_ENABLED; - u32 tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED; - u32 tsync_rx_cfg = 0; - bool is_l4 = false; - bool is_l2 = false; - u32 regval; - - if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) - return -EFAULT; - - /* reserved for future extensions */ - if (config.flags) - return -EINVAL; - - switch (config.tx_type) { - case HWTSTAMP_TX_OFF: - tsync_tx_ctl = 0; - case HWTSTAMP_TX_ON: - break; - default: - return -ERANGE; - } - - switch (config.rx_filter) { - case HWTSTAMP_FILTER_NONE: - tsync_rx_ctl = 0; - break; - case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: - case HWTSTAMP_FILTER_ALL: - /* - * register TSYNCRXCFG must be set, therefore it is not - * possible to time stamp both Sync and Delay_Req messages - * => fall back to time stamping all packets - */ - tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_ALL; - config.rx_filter = HWTSTAMP_FILTER_ALL; - break; - case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: - tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L4_V1; - tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V1_SYNC_MESSAGE; - is_l4 = true; - break; - case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: - tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L4_V1; - tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V1_DELAY_REQ_MESSAGE; - is_l4 = true; - break; - case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: - case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: - tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L2_L4_V2; - tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V2_SYNC_MESSAGE; - is_l2 = true; - is_l4 = true; - config.rx_filter = HWTSTAMP_FILTER_SOME; - break; - case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: - tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L2_L4_V2; - tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V2_DELAY_REQ_MESSAGE; - is_l2 = true; - is_l4 = true; - config.rx_filter = HWTSTAMP_FILTER_SOME; - break; - case HWTSTAMP_FILTER_PTP_V2_EVENT: - case HWTSTAMP_FILTER_PTP_V2_SYNC: - case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: - tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_EVENT_V2; - config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; - is_l2 = true; - is_l4 = true; - break; - default: - return -ERANGE; - } - - if (hw->mac.type == e1000_82575) { - if (tsync_rx_ctl | tsync_tx_ctl) - return -EINVAL; - return 0; - } - - /* - * Per-packet timestamping only works if all packets are - * timestamped, so enable timestamping in all packets as - * long as one rx filter was configured. - */ - if ((hw->mac.type >= e1000_82580) && tsync_rx_ctl) { - tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED; - tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_ALL; - } - - /* enable/disable TX */ - regval = rd32(E1000_TSYNCTXCTL); - regval &= ~E1000_TSYNCTXCTL_ENABLED; - regval |= tsync_tx_ctl; - wr32(E1000_TSYNCTXCTL, regval); - - /* enable/disable RX */ - regval = rd32(E1000_TSYNCRXCTL); - regval &= ~(E1000_TSYNCRXCTL_ENABLED | E1000_TSYNCRXCTL_TYPE_MASK); - regval |= tsync_rx_ctl; - wr32(E1000_TSYNCRXCTL, regval); - - /* define which PTP packets are time stamped */ - wr32(E1000_TSYNCRXCFG, tsync_rx_cfg); - - /* define ethertype filter for timestamped packets */ - if (is_l2) - wr32(E1000_ETQF(3), - (E1000_ETQF_FILTER_ENABLE | /* enable filter */ - E1000_ETQF_1588 | /* enable timestamping */ - ETH_P_1588)); /* 1588 eth protocol type */ - else - wr32(E1000_ETQF(3), 0); - -#define PTP_PORT 319 - /* L4 Queue Filter[3]: filter by destination port and protocol */ - if (is_l4) { - u32 ftqf = (IPPROTO_UDP /* UDP */ - | E1000_FTQF_VF_BP /* VF not compared */ - | E1000_FTQF_1588_TIME_STAMP /* Enable Timestamping */ - | E1000_FTQF_MASK); /* mask all inputs */ - ftqf &= ~E1000_FTQF_MASK_PROTO_BP; /* enable protocol check */ - - wr32(E1000_IMIR(3), htons(PTP_PORT)); - wr32(E1000_IMIREXT(3), - (E1000_IMIREXT_SIZE_BP | E1000_IMIREXT_CTRL_BP)); - if (hw->mac.type == e1000_82576) { - /* enable source port check */ - wr32(E1000_SPQF(3), htons(PTP_PORT)); - ftqf &= ~E1000_FTQF_MASK_SOURCE_PORT_BP; - } - wr32(E1000_FTQF(3), ftqf); - } else { - wr32(E1000_FTQF(3), E1000_FTQF_MASK); - } - wrfl(); - - adapter->hwtstamp_config = config; - - /* clear TX/RX time stamp registers, just to be sure */ - regval = rd32(E1000_TXSTMPH); - regval = rd32(E1000_RXSTMPH); - - return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? - -EFAULT : 0; -} -#endif /* CONFIG_IGB_PTP */ - /** * igb_ioctl - * @netdev: @@ -6539,7 +6290,7 @@ static int igb_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) return igb_mii_ioctl(netdev, ifr, cmd); #ifdef CONFIG_IGB_PTP case SIOCSHWTSTAMP: - return igb_hwtstamp_ioctl(netdev, ifr, cmd); + return igb_ptp_hwtstamp_ioctl(netdev, ifr, cmd); #endif /* CONFIG_IGB_PTP */ default: return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index c846ea9131a..34e0d698cbb 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -69,22 +69,22 @@ * 2^40 * 10^-9 / 60 = 18.3 minutes. */ -#define IGB_OVERFLOW_PERIOD (HZ * 60 * 9) -#define INCPERIOD_82576 (1 << E1000_TIMINCA_16NS_SHIFT) -#define INCVALUE_82576_MASK ((1 << E1000_TIMINCA_16NS_SHIFT) - 1) -#define INCVALUE_82576 (16 << IGB_82576_TSYNC_SHIFT) -#define IGB_NBITS_82580 40 +#define IGB_SYSTIM_OVERFLOW_PERIOD (HZ * 60 * 9) +#define INCPERIOD_82576 (1 << E1000_TIMINCA_16NS_SHIFT) +#define INCVALUE_82576_MASK ((1 << E1000_TIMINCA_16NS_SHIFT) - 1) +#define INCVALUE_82576 (16 << IGB_82576_TSYNC_SHIFT) +#define IGB_NBITS_82580 40 /* * SYSTIM read access for the 82576 */ -static cycle_t igb_82576_systim_read(const struct cyclecounter *cc) +static cycle_t igb_ptp_read_82576(const struct cyclecounter *cc) { - u64 val; - u32 lo, hi; struct igb_adapter *igb = container_of(cc, struct igb_adapter, cc); struct e1000_hw *hw = &igb->hw; + u64 val; + u32 lo, hi; lo = rd32(E1000_SYSTIML); hi = rd32(E1000_SYSTIMH); @@ -99,12 +99,12 @@ static cycle_t igb_82576_systim_read(const struct cyclecounter *cc) * SYSTIM read access for the 82580 */ -static cycle_t igb_82580_systim_read(const struct cyclecounter *cc) +static cycle_t igb_ptp_read_82580(const struct cyclecounter *cc) { - u64 val; - u32 lo, hi, jk; struct igb_adapter *igb = container_of(cc, struct igb_adapter, cc); struct e1000_hw *hw = &igb->hw; + u64 val; + u32 lo, hi, jk; /* * The timestamp latches on lowest register read. For the 82580 @@ -121,17 +121,63 @@ static cycle_t igb_82580_systim_read(const struct cyclecounter *cc) return val; } +/** + * igb_ptp_systim_to_hwtstamp - convert system time value to hw timestamp + * @adapter: board private structure + * @hwtstamps: timestamp structure to update + * @systim: unsigned 64bit system time value. + * + * We need to convert the system time value stored in the RX/TXSTMP registers + * into a hwtstamp which can be used by the upper level timestamping functions. + * + * The 'tmreg_lock' spinlock is used to protect the consistency of the + * system time value. This is needed because reading the 64 bit time + * value involves reading two (or three) 32 bit registers. The first + * read latches the value. Ditto for writing. + * + * In addition, here have extended the system time with an overflow + * counter in software. + **/ +static void igb_ptp_systim_to_hwtstamp(struct igb_adapter *adapter, + struct skb_shared_hwtstamps *hwtstamps, + u64 systim) +{ + unsigned long flags; + u64 ns; + + switch (adapter->hw.mac.type) { + case e1000_i210: + case e1000_i211: + case e1000_i350: + case e1000_82580: + case e1000_82576: + break; + default: + return; + } + + spin_lock_irqsave(&adapter->tmreg_lock, flags); + + ns = timecounter_cyc2time(&adapter->tc, systim); + + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + + memset(hwtstamps, 0, sizeof(*hwtstamps)); + hwtstamps->hwtstamp = ns_to_ktime(ns); +} + /* * PTP clock operations */ -static int ptp_82576_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int igb_ptp_adjfreq_82576(struct ptp_clock_info *ptp, s32 ppb) { + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); + struct e1000_hw *hw = &igb->hw; + int neg_adj = 0; u64 rate; u32 incvalue; - int neg_adj = 0; - struct igb_adapter *igb = container_of(ptp, struct igb_adapter, caps); - struct e1000_hw *hw = &igb->hw; if (ppb < 0) { neg_adj = 1; @@ -153,13 +199,14 @@ static int ptp_82576_adjfreq(struct ptp_clock_info *ptp, s32 ppb) return 0; } -static int ptp_82580_adjfreq(struct ptp_clock_info *ptp, s32 ppb) +static int igb_ptp_adjfreq_82580(struct ptp_clock_info *ptp, s32 ppb) { + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); + struct e1000_hw *hw = &igb->hw; + int neg_adj = 0; u64 rate; u32 inca; - int neg_adj = 0; - struct igb_adapter *igb = container_of(ptp, struct igb_adapter, caps); - struct e1000_hw *hw = &igb->hw; if (ppb < 0) { neg_adj = 1; @@ -178,11 +225,12 @@ static int ptp_82580_adjfreq(struct ptp_clock_info *ptp, s32 ppb) return 0; } -static int igb_adjtime(struct ptp_clock_info *ptp, s64 delta) +static int igb_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) { - s64 now; + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); unsigned long flags; - struct igb_adapter *igb = container_of(ptp, struct igb_adapter, caps); + s64 now; spin_lock_irqsave(&igb->tmreg_lock, flags); @@ -195,12 +243,13 @@ static int igb_adjtime(struct ptp_clock_info *ptp, s64 delta) return 0; } -static int igb_gettime(struct ptp_clock_info *ptp, struct timespec *ts) +static int igb_ptp_gettime(struct ptp_clock_info *ptp, struct timespec *ts) { + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); + unsigned long flags; u64 ns; u32 remainder; - unsigned long flags; - struct igb_adapter *igb = container_of(ptp, struct igb_adapter, caps); spin_lock_irqsave(&igb->tmreg_lock, flags); @@ -214,11 +263,13 @@ static int igb_gettime(struct ptp_clock_info *ptp, struct timespec *ts) return 0; } -static int igb_settime(struct ptp_clock_info *ptp, const struct timespec *ts) +static int igb_ptp_settime(struct ptp_clock_info *ptp, + const struct timespec *ts) { - u64 ns; + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); unsigned long flags; - struct igb_adapter *igb = container_of(ptp, struct igb_adapter, caps); + u64 ns; ns = ts->tv_sec * 1000000000ULL; ns += ts->tv_nsec; @@ -232,29 +283,265 @@ static int igb_settime(struct ptp_clock_info *ptp, const struct timespec *ts) return 0; } -static int ptp_82576_enable(struct ptp_clock_info *ptp, - struct ptp_clock_request *rq, int on) +static int igb_ptp_enable(struct ptp_clock_info *ptp, + struct ptp_clock_request *rq, int on) { return -EOPNOTSUPP; } -static int ptp_82580_enable(struct ptp_clock_info *ptp, - struct ptp_clock_request *rq, int on) +static void igb_ptp_overflow_check(struct work_struct *work) { - return -EOPNOTSUPP; + struct igb_adapter *igb = + container_of(work, struct igb_adapter, ptp_overflow_work.work); + struct timespec ts; + + igb_ptp_gettime(&igb->ptp_caps, &ts); + + pr_debug("igb overflow check at %ld.%09lu\n", ts.tv_sec, ts.tv_nsec); + + schedule_delayed_work(&igb->ptp_overflow_work, + IGB_SYSTIM_OVERFLOW_PERIOD); } -static void igb_overflow_check(struct work_struct *work) +/** + * igb_ptp_tx_hwtstamp - utility function which checks for TX time stamp + * @q_vector: pointer to q_vector containing needed info + * @buffer: pointer to igb_tx_buffer structure + * + * If we were asked to do hardware stamping and such a time stamp is + * available, then it must have been for this skb here because we only + * allow only one such packet into the queue. + */ +void igb_ptp_tx_hwtstamp(struct igb_q_vector *q_vector, + struct igb_tx_buffer *buffer_info) { - struct timespec ts; - struct igb_adapter *igb = - container_of(work, struct igb_adapter, overflow_work.work); + struct igb_adapter *adapter = q_vector->adapter; + struct e1000_hw *hw = &adapter->hw; + struct skb_shared_hwtstamps shhwtstamps; + u64 regval; - igb_gettime(&igb->caps, &ts); + /* if skb does not support hw timestamp or TX stamp not valid exit */ + if (likely(!(buffer_info->tx_flags & IGB_TX_FLAGS_TSTAMP)) || + !(rd32(E1000_TSYNCTXCTL) & E1000_TSYNCTXCTL_VALID)) + return; - pr_debug("igb overflow check at %ld.%09lu\n", ts.tv_sec, ts.tv_nsec); + regval = rd32(E1000_TXSTMPL); + regval |= (u64)rd32(E1000_TXSTMPH) << 32; - schedule_delayed_work(&igb->overflow_work, IGB_OVERFLOW_PERIOD); + igb_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval); + skb_tstamp_tx(buffer_info->skb, &shhwtstamps); +} + +void igb_ptp_rx_hwtstamp(struct igb_q_vector *q_vector, + union e1000_adv_rx_desc *rx_desc, + struct sk_buff *skb) +{ + struct igb_adapter *adapter = q_vector->adapter; + struct e1000_hw *hw = &adapter->hw; + u64 regval; + + if (!igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP | + E1000_RXDADV_STAT_TS)) + return; + + /* + * If this bit is set, then the RX registers contain the time stamp. No + * other packet will be time stamped until we read these registers, so + * read the registers to make them available again. Because only one + * packet can be time stamped at a time, we know that the register + * values must belong to this one here and therefore we don't need to + * compare any of the additional attributes stored for it. + * + * If nothing went wrong, then it should have a shared tx_flags that we + * can turn into a skb_shared_hwtstamps. + */ + if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { + u32 *stamp = (u32 *)skb->data; + regval = le32_to_cpu(*(stamp + 2)); + regval |= (u64)le32_to_cpu(*(stamp + 3)) << 32; + skb_pull(skb, IGB_TS_HDR_LEN); + } else { + if (!(rd32(E1000_TSYNCRXCTL) & E1000_TSYNCRXCTL_VALID)) + return; + + regval = rd32(E1000_RXSTMPL); + regval |= (u64)rd32(E1000_RXSTMPH) << 32; + } + + igb_ptp_systim_to_hwtstamp(adapter, skb_hwtstamps(skb), regval); +} + +/** + * igb_ptp_hwtstamp_ioctl - control hardware time stamping + * @netdev: + * @ifreq: + * @cmd: + * + * Outgoing time stamping can be enabled and disabled. Play nice and + * disable it when requested, although it shouldn't case any overhead + * when no packet needs it. At most one packet in the queue may be + * marked for time stamping, otherwise it would be impossible to tell + * for sure to which packet the hardware time stamp belongs. + * + * Incoming time stamping has to be configured via the hardware + * filters. Not all combinations are supported, in particular event + * type has to be specified. Matching the kind of event packet is + * not supported, with the exception of "all V2 events regardless of + * level 2 or 4". + * + **/ +int igb_ptp_hwtstamp_ioctl(struct net_device *netdev, + struct ifreq *ifr, int cmd) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + struct hwtstamp_config config; + u32 tsync_tx_ctl = E1000_TSYNCTXCTL_ENABLED; + u32 tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED; + u32 tsync_rx_cfg = 0; + bool is_l4 = false; + bool is_l2 = false; + u32 regval; + + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) + return -EFAULT; + + /* reserved for future extensions */ + if (config.flags) + return -EINVAL; + + switch (config.tx_type) { + case HWTSTAMP_TX_OFF: + tsync_tx_ctl = 0; + case HWTSTAMP_TX_ON: + break; + default: + return -ERANGE; + } + + switch (config.rx_filter) { + case HWTSTAMP_FILTER_NONE: + tsync_rx_ctl = 0; + break; + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_ALL: + /* + * register TSYNCRXCFG must be set, therefore it is not + * possible to time stamp both Sync and Delay_Req messages + * => fall back to time stamping all packets + */ + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_ALL; + config.rx_filter = HWTSTAMP_FILTER_ALL; + break; + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L4_V1; + tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V1_SYNC_MESSAGE; + is_l4 = true; + break; + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L4_V1; + tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V1_DELAY_REQ_MESSAGE; + is_l4 = true; + break; + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L2_L4_V2; + tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V2_SYNC_MESSAGE; + is_l2 = true; + is_l4 = true; + config.rx_filter = HWTSTAMP_FILTER_SOME; + break; + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_L2_L4_V2; + tsync_rx_cfg = E1000_TSYNCRXCFG_PTP_V2_DELAY_REQ_MESSAGE; + is_l2 = true; + is_l4 = true; + config.rx_filter = HWTSTAMP_FILTER_SOME; + break; + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_EVENT_V2; + config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + is_l2 = true; + is_l4 = true; + break; + default: + return -ERANGE; + } + + if (hw->mac.type == e1000_82575) { + if (tsync_rx_ctl | tsync_tx_ctl) + return -EINVAL; + return 0; + } + + /* + * Per-packet timestamping only works if all packets are + * timestamped, so enable timestamping in all packets as + * long as one rx filter was configured. + */ + if ((hw->mac.type >= e1000_82580) && tsync_rx_ctl) { + tsync_rx_ctl = E1000_TSYNCRXCTL_ENABLED; + tsync_rx_ctl |= E1000_TSYNCRXCTL_TYPE_ALL; + } + + /* enable/disable TX */ + regval = rd32(E1000_TSYNCTXCTL); + regval &= ~E1000_TSYNCTXCTL_ENABLED; + regval |= tsync_tx_ctl; + wr32(E1000_TSYNCTXCTL, regval); + + /* enable/disable RX */ + regval = rd32(E1000_TSYNCRXCTL); + regval &= ~(E1000_TSYNCRXCTL_ENABLED | E1000_TSYNCRXCTL_TYPE_MASK); + regval |= tsync_rx_ctl; + wr32(E1000_TSYNCRXCTL, regval); + + /* define which PTP packets are time stamped */ + wr32(E1000_TSYNCRXCFG, tsync_rx_cfg); + + /* define ethertype filter for timestamped packets */ + if (is_l2) + wr32(E1000_ETQF(3), + (E1000_ETQF_FILTER_ENABLE | /* enable filter */ + E1000_ETQF_1588 | /* enable timestamping */ + ETH_P_1588)); /* 1588 eth protocol type */ + else + wr32(E1000_ETQF(3), 0); + +#define PTP_PORT 319 + /* L4 Queue Filter[3]: filter by destination port and protocol */ + if (is_l4) { + u32 ftqf = (IPPROTO_UDP /* UDP */ + | E1000_FTQF_VF_BP /* VF not compared */ + | E1000_FTQF_1588_TIME_STAMP /* Enable Timestamping */ + | E1000_FTQF_MASK); /* mask all inputs */ + ftqf &= ~E1000_FTQF_MASK_PROTO_BP; /* enable protocol check */ + + wr32(E1000_IMIR(3), htons(PTP_PORT)); + wr32(E1000_IMIREXT(3), + (E1000_IMIREXT_SIZE_BP | E1000_IMIREXT_CTRL_BP)); + if (hw->mac.type == e1000_82576) { + /* enable source port check */ + wr32(E1000_SPQF(3), htons(PTP_PORT)); + ftqf &= ~E1000_FTQF_MASK_SOURCE_PORT_BP; + } + wr32(E1000_FTQF(3), ftqf); + } else { + wr32(E1000_FTQF(3), E1000_FTQF_MASK); + } + wrfl(); + + /* clear TX/RX time stamp registers, just to be sure */ + regval = rd32(E1000_TXSTMPH); + regval = rd32(E1000_RXSTMPH); + + return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? + -EFAULT : 0; } void igb_ptp_init(struct igb_adapter *adapter) @@ -266,39 +553,39 @@ void igb_ptp_init(struct igb_adapter *adapter) case e1000_i211: case e1000_i350: case e1000_82580: - adapter->caps.owner = THIS_MODULE; - strcpy(adapter->caps.name, "igb-82580"); - adapter->caps.max_adj = 62499999; - adapter->caps.n_ext_ts = 0; - adapter->caps.pps = 0; - adapter->caps.adjfreq = ptp_82580_adjfreq; - adapter->caps.adjtime = igb_adjtime; - adapter->caps.gettime = igb_gettime; - adapter->caps.settime = igb_settime; - adapter->caps.enable = ptp_82580_enable; - adapter->cc.read = igb_82580_systim_read; - adapter->cc.mask = CLOCKSOURCE_MASK(IGB_NBITS_82580); - adapter->cc.mult = 1; - adapter->cc.shift = 0; + adapter->ptp_caps.owner = THIS_MODULE; + strcpy(adapter->ptp_caps.name, "igb-82580"); + adapter->ptp_caps.max_adj = 62499999; + adapter->ptp_caps.n_ext_ts = 0; + adapter->ptp_caps.pps = 0; + adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82580; + adapter->ptp_caps.adjtime = igb_ptp_adjtime; + adapter->ptp_caps.gettime = igb_ptp_gettime; + adapter->ptp_caps.settime = igb_ptp_settime; + adapter->ptp_caps.enable = igb_ptp_enable; + adapter->cc.read = igb_ptp_read_82580; + adapter->cc.mask = CLOCKSOURCE_MASK(IGB_NBITS_82580); + adapter->cc.mult = 1; + adapter->cc.shift = 0; /* Enable the timer functions by clearing bit 31. */ wr32(E1000_TSAUXC, 0x0); break; case e1000_82576: - adapter->caps.owner = THIS_MODULE; - strcpy(adapter->caps.name, "igb-82576"); - adapter->caps.max_adj = 1000000000; - adapter->caps.n_ext_ts = 0; - adapter->caps.pps = 0; - adapter->caps.adjfreq = ptp_82576_adjfreq; - adapter->caps.adjtime = igb_adjtime; - adapter->caps.gettime = igb_gettime; - adapter->caps.settime = igb_settime; - adapter->caps.enable = ptp_82576_enable; - adapter->cc.read = igb_82576_systim_read; - adapter->cc.mask = CLOCKSOURCE_MASK(64); - adapter->cc.mult = 1; - adapter->cc.shift = IGB_82576_TSYNC_SHIFT; + adapter->ptp_caps.owner = THIS_MODULE; + strcpy(adapter->ptp_caps.name, "igb-82576"); + adapter->ptp_caps.max_adj = 1000000000; + adapter->ptp_caps.n_ext_ts = 0; + adapter->ptp_caps.pps = 0; + adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82576; + adapter->ptp_caps.adjtime = igb_ptp_adjtime; + adapter->ptp_caps.gettime = igb_ptp_gettime; + adapter->ptp_caps.settime = igb_ptp_settime; + adapter->ptp_caps.enable = igb_ptp_enable; + adapter->cc.read = igb_ptp_read_82576; + adapter->cc.mask = CLOCKSOURCE_MASK(64); + adapter->cc.mult = 1; + adapter->cc.shift = IGB_82576_TSYNC_SHIFT; /* Dial the nominal frequency. */ wr32(E1000_TIMINCA, INCPERIOD_82576 | INCVALUE_82576); break; @@ -313,13 +600,14 @@ void igb_ptp_init(struct igb_adapter *adapter) timecounter_init(&adapter->tc, &adapter->cc, ktime_to_ns(ktime_get_real())); - INIT_DELAYED_WORK(&adapter->overflow_work, igb_overflow_check); + INIT_DELAYED_WORK(&adapter->ptp_overflow_work, igb_ptp_overflow_check); spin_lock_init(&adapter->tmreg_lock); - schedule_delayed_work(&adapter->overflow_work, IGB_OVERFLOW_PERIOD); + schedule_delayed_work(&adapter->ptp_overflow_work, + IGB_SYSTIM_OVERFLOW_PERIOD); - adapter->ptp_clock = ptp_clock_register(&adapter->caps); + adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps); if (IS_ERR(adapter->ptp_clock)) { adapter->ptp_clock = NULL; dev_err(&adapter->pdev->dev, "ptp_clock_register failed\n"); @@ -328,7 +616,13 @@ void igb_ptp_init(struct igb_adapter *adapter) adapter->netdev->name); } -void igb_ptp_remove(struct igb_adapter *adapter) +/** + * igb_ptp_stop - Disable PTP device and stop the overflow check. + * @adapter: Board private structure. + * + * This function stops the PTP support and cancels the delayed work. + **/ +void igb_ptp_stop(struct igb_adapter *adapter) { switch (adapter->hw.mac.type) { case e1000_i211: @@ -336,7 +630,7 @@ void igb_ptp_remove(struct igb_adapter *adapter) case e1000_i350: case e1000_82580: case e1000_82576: - cancel_delayed_work_sync(&adapter->overflow_work); + cancel_delayed_work_sync(&adapter->ptp_overflow_work); break; default: return; @@ -348,48 +642,3 @@ void igb_ptp_remove(struct igb_adapter *adapter) adapter->netdev->name); } } - -/** - * igb_systim_to_hwtstamp - convert system time value to hw timestamp - * @adapter: board private structure - * @hwtstamps: timestamp structure to update - * @systim: unsigned 64bit system time value. - * - * We need to convert the system time value stored in the RX/TXSTMP registers - * into a hwtstamp which can be used by the upper level timestamping functions. - * - * The 'tmreg_lock' spinlock is used to protect the consistency of the - * system time value. This is needed because reading the 64 bit time - * value involves reading two (or three) 32 bit registers. The first - * read latches the value. Ditto for writing. - * - * In addition, here have extended the system time with an overflow - * counter in software. - **/ -void igb_systim_to_hwtstamp(struct igb_adapter *adapter, - struct skb_shared_hwtstamps *hwtstamps, - u64 systim) -{ - u64 ns; - unsigned long flags; - - switch (adapter->hw.mac.type) { - case e1000_i210: - case e1000_i211: - case e1000_i350: - case e1000_82580: - case e1000_82576: - break; - default: - return; - } - - spin_lock_irqsave(&adapter->tmreg_lock, flags); - - ns = timecounter_cyc2time(&adapter->tc, systim); - - spin_unlock_irqrestore(&adapter->tmreg_lock, flags); - - memset(hwtstamps, 0, sizeof(*hwtstamps)); - hwtstamps->hwtstamp = ns_to_ktime(ns); -} -- cgit v1.2.3-70-g09d2 From 1f6e8178d6851951876ad8524f4de7a0e6b111be Mon Sep 17 00:00:00 2001 From: Matthew Vick Date: Sat, 18 Aug 2012 07:26:33 +0000 Subject: igb: Prevent dropped Tx timestamps via work items and interrupts. In rare circumstances, it's possible a descriptor writeback will occur before a timestamped Tx packet will go out on the wire, leading to the driver believing the hardware failed to timestamp the packet. Schedule a work item for 82576 and use the available time sync interrupt registers on 82580 and above to account for this. Cc: Richard Cochran Signed-off-by: Matthew Vick Tested-by: Jeff Pieper Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/e1000_defines.h | 5 ++ drivers/net/ethernet/intel/igb/e1000_regs.h | 2 + drivers/net/ethernet/intel/igb/igb.h | 8 +- drivers/net/ethernet/intel/igb/igb_main.c | 61 +++++++++++++-- drivers/net/ethernet/intel/igb/igb_ptp.c | 102 +++++++++++++++++++++---- 5 files changed, 153 insertions(+), 25 deletions(-) (limited to 'drivers/net/ethernet/intel/igb/igb.h') diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h index ec7e4fe3e3e..0b27e8fe06b 100644 --- a/drivers/net/ethernet/intel/igb/e1000_defines.h +++ b/drivers/net/ethernet/intel/igb/e1000_defines.h @@ -360,6 +360,7 @@ #define E1000_ICR_RXDMT0 0x00000010 /* rx desc min. threshold (0) */ #define E1000_ICR_RXT0 0x00000080 /* rx timer intr (ring 0) */ #define E1000_ICR_VMMB 0x00000100 /* VM MB event */ +#define E1000_ICR_TS 0x00080000 /* Time Sync Interrupt */ #define E1000_ICR_DRSTA 0x40000000 /* Device Reset Asserted */ /* If this bit asserted, the driver should claim the interrupt */ #define E1000_ICR_INT_ASSERTED 0x80000000 @@ -399,6 +400,7 @@ #define E1000_IMS_TXDW E1000_ICR_TXDW /* Transmit desc written back */ #define E1000_IMS_LSC E1000_ICR_LSC /* Link Status Change */ #define E1000_IMS_VMMB E1000_ICR_VMMB /* Mail box activity */ +#define E1000_IMS_TS E1000_ICR_TS /* Time Sync Interrupt */ #define E1000_IMS_RXSEQ E1000_ICR_RXSEQ /* rx sequence error */ #define E1000_IMS_RXDMT0 E1000_ICR_RXDMT0 /* rx desc min. threshold */ #define E1000_IMS_RXT0 E1000_ICR_RXT0 /* rx timer intr */ @@ -510,6 +512,9 @@ #define E1000_TIMINCA_16NS_SHIFT 24 +#define E1000_TSICR_TXTS 0x00000002 +#define E1000_TSIM_TXTS 0x00000002 + #define E1000_MDICNFG_EXT_MDIO 0x80000000 /* MDI ext/int destination */ #define E1000_MDICNFG_COM_MDIO 0x40000000 /* MDI shared w/ lan 0 */ #define E1000_MDICNFG_PHY_MASK 0x03E00000 diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h index 28394bea525..faec840a5a8 100644 --- a/drivers/net/ethernet/intel/igb/e1000_regs.h +++ b/drivers/net/ethernet/intel/igb/e1000_regs.h @@ -91,6 +91,8 @@ #define E1000_TIMINCA 0x0B608 /* Increment attributes register - RW */ #define E1000_TSAUXC 0x0B640 /* Timesync Auxiliary Control register */ #define E1000_SYSTIMR 0x0B6F8 /* System time register Residue */ +#define E1000_TSICR 0x0B66C /* Interrupt Cause Register */ +#define E1000_TSIM 0x0B674 /* Interrupt Mask Register */ /* Filtering Registers */ #define E1000_SAQF(_n) (0x5980 + 4 * (_n)) diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 797346998d5..43c8e291426 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -381,6 +381,8 @@ struct igb_adapter { struct ptp_clock *ptp_clock; struct ptp_clock_info ptp_caps; struct delayed_work ptp_overflow_work; + struct work_struct ptp_tx_work; + struct sk_buff *ptp_tx_skb; spinlock_t tmreg_lock; struct cyclecounter cc; struct timecounter tc; @@ -394,6 +396,7 @@ struct igb_adapter { #define IGB_FLAG_QUAD_PORT_A (1 << 2) #define IGB_FLAG_QUEUE_PAIRS (1 << 3) #define IGB_FLAG_DMAC (1 << 4) +#define IGB_FLAG_PTP (1 << 5) /* DMA Coalescing defines */ #define IGB_MIN_TXPBSIZE 20408 @@ -440,8 +443,9 @@ extern void igb_set_fw_version(struct igb_adapter *); #ifdef CONFIG_IGB_PTP extern void igb_ptp_init(struct igb_adapter *adapter); extern void igb_ptp_stop(struct igb_adapter *adapter); -extern void igb_ptp_tx_hwtstamp(struct igb_q_vector *q_vector, - struct igb_tx_buffer *buffer_info); +extern void igb_ptp_reset(struct igb_adapter *adapter); +extern void igb_ptp_tx_work(struct work_struct *work); +extern void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter); extern void igb_ptp_rx_hwtstamp(struct igb_q_vector *q_vector, union e1000_adv_rx_desc *rx_desc, struct sk_buff *skb); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 6e39f0ca9fc..19d7666dfcc 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -1751,6 +1751,11 @@ void igb_reset(struct igb_adapter *adapter) /* Enable h/w to recognize an 802.1Q VLAN Ethernet packet */ wr32(E1000_VET, ETHERNET_IEEE_VLAN_TYPE); +#ifdef CONFIG_IGB_PTP + /* Re-enable PTP, where applicable. */ + igb_ptp_reset(adapter); +#endif /* CONFIG_IGB_PTP */ + igb_get_phy_info(hw); } @@ -4234,7 +4239,7 @@ static __le32 igb_tx_cmd_type(u32 tx_flags) #ifdef CONFIG_IGB_PTP /* set timestamp bit if present */ - if (tx_flags & IGB_TX_FLAGS_TSTAMP) + if (unlikely(tx_flags & IGB_TX_FLAGS_TSTAMP)) cmd_type |= cpu_to_le32(E1000_ADVTXD_MAC_TSTAMP); #endif /* CONFIG_IGB_PTP */ @@ -4445,6 +4450,9 @@ static inline int igb_maybe_stop_tx(struct igb_ring *tx_ring, const u16 size) netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, struct igb_ring *tx_ring) { +#ifdef CONFIG_IGB_PTP + struct igb_adapter *adapter = netdev_priv(tx_ring->netdev); +#endif /* CONFIG_IGB_PTP */ struct igb_tx_buffer *first; int tso; u32 tx_flags = 0; @@ -4468,9 +4476,14 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, first->gso_segs = 1; #ifdef CONFIG_IGB_PTP - if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { + if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && + !(adapter->ptp_tx_skb))) { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; tx_flags |= IGB_TX_FLAGS_TSTAMP; + + adapter->ptp_tx_skb = skb_get(skb); + if (adapter->hw.mac.type == e1000_82576) + schedule_work(&adapter->ptp_tx_work); } #endif /* CONFIG_IGB_PTP */ @@ -4859,6 +4872,19 @@ static irqreturn_t igb_msix_other(int irq, void *data) mod_timer(&adapter->watchdog_timer, jiffies + 1); } +#ifdef CONFIG_IGB_PTP + if (icr & E1000_ICR_TS) { + u32 tsicr = rd32(E1000_TSICR); + + if (tsicr & E1000_TSICR_TXTS) { + /* acknowledge the interrupt */ + wr32(E1000_TSICR, E1000_TSICR_TXTS); + /* retrieve hardware timestamp */ + schedule_work(&adapter->ptp_tx_work); + } + } +#endif /* CONFIG_IGB_PTP */ + wr32(E1000_EIMS, adapter->eims_other); return IRQ_HANDLED; @@ -5650,6 +5676,19 @@ static irqreturn_t igb_intr_msi(int irq, void *data) mod_timer(&adapter->watchdog_timer, jiffies + 1); } +#ifdef CONFIG_IGB_PTP + if (icr & E1000_ICR_TS) { + u32 tsicr = rd32(E1000_TSICR); + + if (tsicr & E1000_TSICR_TXTS) { + /* acknowledge the interrupt */ + wr32(E1000_TSICR, E1000_TSICR_TXTS); + /* retrieve hardware timestamp */ + schedule_work(&adapter->ptp_tx_work); + } + } +#endif /* CONFIG_IGB_PTP */ + napi_schedule(&q_vector->napi); return IRQ_HANDLED; @@ -5691,6 +5730,19 @@ static irqreturn_t igb_intr(int irq, void *data) mod_timer(&adapter->watchdog_timer, jiffies + 1); } +#ifdef CONFIG_IGB_PTP + if (icr & E1000_ICR_TS) { + u32 tsicr = rd32(E1000_TSICR); + + if (tsicr & E1000_TSICR_TXTS) { + /* acknowledge the interrupt */ + wr32(E1000_TSICR, E1000_TSICR_TXTS); + /* retrieve hardware timestamp */ + schedule_work(&adapter->ptp_tx_work); + } + } +#endif /* CONFIG_IGB_PTP */ + napi_schedule(&q_vector->napi); return IRQ_HANDLED; @@ -5794,11 +5846,6 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) total_bytes += tx_buffer->bytecount; total_packets += tx_buffer->gso_segs; -#ifdef CONFIG_IGB_PTP - /* retrieve hardware timestamp */ - igb_ptp_tx_hwtstamp(q_vector, tx_buffer); -#endif /* CONFIG_IGB_PTP */ - /* free the skb */ dev_kfree_skb_any(tx_buffer->skb); tx_buffer->skb = NULL; diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index e69555f1f73..d57060c0813 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -289,6 +289,31 @@ static int igb_ptp_enable(struct ptp_clock_info *ptp, return -EOPNOTSUPP; } +/** + * igb_ptp_tx_work + * @work: pointer to work struct + * + * This work function polls the TSYNCTXCTL valid bit to determine when a + * timestamp has been taken for the current stored skb. + */ +void igb_ptp_tx_work(struct work_struct *work) +{ + struct igb_adapter *adapter = container_of(work, struct igb_adapter, + ptp_tx_work); + struct e1000_hw *hw = &adapter->hw; + u32 tsynctxctl; + + if (!adapter->ptp_tx_skb) + return; + + tsynctxctl = rd32(E1000_TSYNCTXCTL); + if (tsynctxctl & E1000_TSYNCTXCTL_VALID) + igb_ptp_tx_hwtstamp(adapter); + else + /* reschedule to check later */ + schedule_work(&adapter->ptp_tx_work); +} + static void igb_ptp_overflow_check(struct work_struct *work) { struct igb_adapter *igb = @@ -305,31 +330,25 @@ static void igb_ptp_overflow_check(struct work_struct *work) /** * igb_ptp_tx_hwtstamp - utility function which checks for TX time stamp - * @q_vector: pointer to q_vector containing needed info - * @buffer: pointer to igb_tx_buffer structure + * @adapter: Board private structure. * * If we were asked to do hardware stamping and such a time stamp is * available, then it must have been for this skb here because we only * allow only one such packet into the queue. */ -void igb_ptp_tx_hwtstamp(struct igb_q_vector *q_vector, - struct igb_tx_buffer *buffer_info) +void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter) { - struct igb_adapter *adapter = q_vector->adapter; struct e1000_hw *hw = &adapter->hw; struct skb_shared_hwtstamps shhwtstamps; u64 regval; - /* if skb does not support hw timestamp or TX stamp not valid exit */ - if (likely(!(buffer_info->tx_flags & IGB_TX_FLAGS_TSTAMP)) || - !(rd32(E1000_TSYNCTXCTL) & E1000_TSYNCTXCTL_VALID)) - return; - regval = rd32(E1000_TXSTMPL); regval |= (u64)rd32(E1000_TXSTMPH) << 32; igb_ptp_systim_to_hwtstamp(adapter, &shhwtstamps, regval); - skb_tstamp_tx(buffer_info->skb, &shhwtstamps); + skb_tstamp_tx(adapter->ptp_tx_skb, &shhwtstamps); + dev_kfree_skb_any(adapter->ptp_tx_skb); + adapter->ptp_tx_skb = NULL; } void igb_ptp_rx_hwtstamp(struct igb_q_vector *q_vector, @@ -603,16 +622,26 @@ void igb_ptp_init(struct igb_adapter *adapter) spin_lock_init(&adapter->tmreg_lock); + INIT_WORK(&adapter->ptp_tx_work, igb_ptp_tx_work); + schedule_delayed_work(&adapter->ptp_overflow_work, IGB_SYSTIM_OVERFLOW_PERIOD); + /* Initialize the time sync interrupts for devices that support it. */ + if (hw->mac.type >= e1000_82580) { + wr32(E1000_TSIM, E1000_TSIM_TXTS); + wr32(E1000_IMS, E1000_IMS_TS); + } + adapter->ptp_clock = ptp_clock_register(&adapter->ptp_caps); if (IS_ERR(adapter->ptp_clock)) { adapter->ptp_clock = NULL; dev_err(&adapter->pdev->dev, "ptp_clock_register failed\n"); - } else + } else { dev_info(&adapter->pdev->dev, "added PHC on %s\n", adapter->netdev->name); + adapter->flags |= IGB_FLAG_PTP; + } } /** @@ -624,20 +653,61 @@ void igb_ptp_init(struct igb_adapter *adapter) void igb_ptp_stop(struct igb_adapter *adapter) { switch (adapter->hw.mac.type) { - case e1000_i211: - case e1000_i210: - case e1000_i350: - case e1000_82580: case e1000_82576: + case e1000_82580: + case e1000_i350: cancel_delayed_work_sync(&adapter->ptp_overflow_work); break; + case e1000_i210: + case e1000_i211: + /* No delayed work to cancel. */ + break; default: return; } + cancel_work_sync(&adapter->ptp_tx_work); + if (adapter->ptp_clock) { ptp_clock_unregister(adapter->ptp_clock); dev_info(&adapter->pdev->dev, "removed PHC on %s\n", adapter->netdev->name); + adapter->flags &= ~IGB_FLAG_PTP; } } + +/** + * igb_ptp_reset - Re-enable the adapter for PTP following a reset. + * @adapter: Board private structure. + * + * This function handles the reset work required to re-enable the PTP device. + **/ +void igb_ptp_reset(struct igb_adapter *adapter) +{ + struct e1000_hw *hw = &adapter->hw; + + if (!(adapter->flags & IGB_FLAG_PTP)) + return; + + switch (adapter->hw.mac.type) { + case e1000_82576: + /* Dial the nominal frequency. */ + wr32(E1000_TIMINCA, INCPERIOD_82576 | INCVALUE_82576); + break; + case e1000_82580: + case e1000_i350: + case e1000_i210: + case e1000_i211: + /* Enable the timer functions and interrupts. */ + wr32(E1000_TSAUXC, 0x0); + wr32(E1000_TSIM, E1000_TSIM_TXTS); + wr32(E1000_IMS, E1000_IMS_TS); + break; + default: + /* No work to do. */ + return; + } + + timecounter_init(&adapter->tc, &adapter->cc, + ktime_to_ns(ktime_get_real())); +} -- cgit v1.2.3-70-g09d2 From f557147c4615f5e03abb673bd566901783565666 Mon Sep 17 00:00:00 2001 From: Stefan Assmann Date: Sat, 18 Aug 2012 04:06:11 +0000 Subject: igb: Change how we check for pre-existing and assigned VFs Adapt the pre-existing and assigned VFs code to the ixgbe way introduced in commit 9297127b9cdd8d30c829ef5fd28b7cc0323a7bcd. Instead of searching the enabled VFs we use pci_num_vf to determine enabled VFs. By comparing to which PF an assigned VF is owned it's possible to decide whether to leave it enabled or not. Signed-off-by: Stefan Assmann Acked-by: Greg Rose Tested-by: Robert Garrett Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb.h | 1 - drivers/net/ethernet/intel/igb/igb_main.c | 104 +++++++----------------------- 2 files changed, 22 insertions(+), 83 deletions(-) (limited to 'drivers/net/ethernet/intel/igb/igb.h') diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 43c8e291426..6f17f698faf 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -101,7 +101,6 @@ struct vf_data_storage { u16 pf_vlan; /* When set, guest VLAN config not allowed. */ u16 pf_qos; u16 tx_rate; - struct pci_dev *vfdev; }; #define IGB_VF_FLAG_CTS 0x00000001 /* VF is clear to send data */ diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 246646b61a1..073009671e7 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -172,8 +172,7 @@ static void igb_check_vf_rate_limit(struct igb_adapter *); #ifdef CONFIG_PCI_IOV static int igb_vf_configure(struct igb_adapter *adapter, int vf); -static int igb_find_enabled_vfs(struct igb_adapter *adapter); -static int igb_check_vf_assignment(struct igb_adapter *adapter); +static bool igb_vfs_are_assigned(struct igb_adapter *adapter); #endif #ifdef CONFIG_PM @@ -2300,11 +2299,11 @@ static void __devexit igb_remove(struct pci_dev *pdev) /* reclaim resources allocated to VFs */ if (adapter->vf_data) { /* disable iov and allow time for transactions to clear */ - if (!igb_check_vf_assignment(adapter)) { + if (igb_vfs_are_assigned(adapter)) { + dev_info(&pdev->dev, "Unloading driver while VFs are assigned - VFs will not be deallocated\n"); + } else { pci_disable_sriov(pdev); msleep(500); - } else { - dev_info(&pdev->dev, "VF(s) assigned to guests!\n"); } kfree(adapter->vf_data); @@ -2344,7 +2343,7 @@ static void __devinit igb_probe_vfs(struct igb_adapter * adapter) #ifdef CONFIG_PCI_IOV struct pci_dev *pdev = adapter->pdev; struct e1000_hw *hw = &adapter->hw; - int old_vfs = igb_find_enabled_vfs(adapter); + int old_vfs = pci_num_vf(adapter->pdev); int i; /* Virtualization features not supported on i210 family. */ @@ -5037,102 +5036,43 @@ static int igb_notify_dca(struct notifier_block *nb, unsigned long event, static int igb_vf_configure(struct igb_adapter *adapter, int vf) { unsigned char mac_addr[ETH_ALEN]; - struct pci_dev *pdev = adapter->pdev; - struct e1000_hw *hw = &adapter->hw; - struct pci_dev *pvfdev; - unsigned int device_id; - u16 thisvf_devfn; eth_random_addr(mac_addr); igb_set_vf_mac(adapter, vf, mac_addr); - switch (adapter->hw.mac.type) { - case e1000_82576: - device_id = IGB_82576_VF_DEV_ID; - /* VF Stride for 82576 is 2 */ - thisvf_devfn = (pdev->devfn + 0x80 + (vf << 1)) | - (pdev->devfn & 1); - break; - case e1000_i350: - device_id = IGB_I350_VF_DEV_ID; - /* VF Stride for I350 is 4 */ - thisvf_devfn = (pdev->devfn + 0x80 + (vf << 2)) | - (pdev->devfn & 3); - break; - default: - device_id = 0; - thisvf_devfn = 0; - break; - } - - pvfdev = pci_get_device(hw->vendor_id, device_id, NULL); - while (pvfdev) { - if (pvfdev->devfn == thisvf_devfn) - break; - pvfdev = pci_get_device(hw->vendor_id, - device_id, pvfdev); - } - - if (pvfdev) - adapter->vf_data[vf].vfdev = pvfdev; - else - dev_err(&pdev->dev, - "Couldn't find pci dev ptr for VF %4.4x\n", - thisvf_devfn); - return pvfdev != NULL; + return 0; } -static int igb_find_enabled_vfs(struct igb_adapter *adapter) +static bool igb_vfs_are_assigned(struct igb_adapter *adapter) { - struct e1000_hw *hw = &adapter->hw; struct pci_dev *pdev = adapter->pdev; - struct pci_dev *pvfdev; - u16 vf_devfn = 0; - u16 vf_stride; - unsigned int device_id; - int vfs_found = 0; + struct pci_dev *vfdev; + int dev_id; switch (adapter->hw.mac.type) { case e1000_82576: - device_id = IGB_82576_VF_DEV_ID; - /* VF Stride for 82576 is 2 */ - vf_stride = 2; + dev_id = IGB_82576_VF_DEV_ID; break; case e1000_i350: - device_id = IGB_I350_VF_DEV_ID; - /* VF Stride for I350 is 4 */ - vf_stride = 4; + dev_id = IGB_I350_VF_DEV_ID; break; default: - device_id = 0; - vf_stride = 0; - break; - } - - vf_devfn = pdev->devfn + 0x80; - pvfdev = pci_get_device(hw->vendor_id, device_id, NULL); - while (pvfdev) { - if (pvfdev->devfn == vf_devfn && - (pvfdev->bus->number >= pdev->bus->number)) - vfs_found++; - vf_devfn += vf_stride; - pvfdev = pci_get_device(hw->vendor_id, - device_id, pvfdev); + return false; } - return vfs_found; -} - -static int igb_check_vf_assignment(struct igb_adapter *adapter) -{ - int i; - for (i = 0; i < adapter->vfs_allocated_count; i++) { - if (adapter->vf_data[i].vfdev) { - if (adapter->vf_data[i].vfdev->dev_flags & - PCI_DEV_FLAGS_ASSIGNED) + /* loop through all the VFs to see if we own any that are assigned */ + vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, dev_id, NULL); + while (vfdev) { + /* if we don't own it we don't care */ + if (vfdev->is_virtfn && vfdev->physfn == pdev) { + /* if it is assigned we cannot release it */ + if (vfdev->dev_flags & PCI_DEV_FLAGS_ASSIGNED) return true; } + + vfdev = pci_get_device(PCI_VENDOR_ID_INTEL, dev_id, vfdev); } + return false; } -- cgit v1.2.3-70-g09d2 From f33005a637bffca72fe373d1e91f2dfbc8fae157 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 13 Sep 2012 06:27:55 +0000 Subject: igb: Remove logic that was doing NUMA pseudo-aware allocations This change removes the code that was doing the NUMA allocations for the q_vectors, rings, and ring resources. The problem is the logic used assumed that the NUMA nodes were always interleved and that is not always the case. At some point I hope to add this functionality back in a more controlled manner in the future. Signed-off-by: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb.h | 3 - drivers/net/ethernet/intel/igb/igb_main.c | 95 +++++-------------------------- 2 files changed, 13 insertions(+), 85 deletions(-) (limited to 'drivers/net/ethernet/intel/igb/igb.h') diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 6f17f698faf..9cad0589419 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -213,7 +213,6 @@ struct igb_q_vector { struct igb_ring_container rx, tx; struct napi_struct napi; - int numa_node; u16 itr_val; u8 set_itr; @@ -258,7 +257,6 @@ struct igb_ring { }; /* Items past this point are only used during ring alloc / free */ dma_addr_t dma; /* phys address of the ring */ - int numa_node; /* node to alloc ring memory on */ }; enum e1000_ring_flags_t { @@ -373,7 +371,6 @@ struct igb_adapter { int vf_rate_link_speed; u32 rss_queues; u32 wvbr; - int node; u32 *shadow_vfta; #ifdef CONFIG_IGB_PTP diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 60cf3ebf4bb..c9997d83de0 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -682,52 +682,29 @@ static int igb_alloc_queues(struct igb_adapter *adapter) { struct igb_ring *ring; int i; - int orig_node = adapter->node; for (i = 0; i < adapter->num_tx_queues; i++) { - if (orig_node == -1) { - int cur_node = next_online_node(adapter->node); - if (cur_node == MAX_NUMNODES) - cur_node = first_online_node; - adapter->node = cur_node; - } - ring = kzalloc_node(sizeof(struct igb_ring), GFP_KERNEL, - adapter->node); - if (!ring) - ring = kzalloc(sizeof(struct igb_ring), GFP_KERNEL); + ring = kzalloc(sizeof(struct igb_ring), GFP_KERNEL); if (!ring) goto err; ring->count = adapter->tx_ring_count; ring->queue_index = i; ring->dev = &adapter->pdev->dev; ring->netdev = adapter->netdev; - ring->numa_node = adapter->node; /* For 82575, context index must be unique per ring. */ if (adapter->hw.mac.type == e1000_82575) set_bit(IGB_RING_FLAG_TX_CTX_IDX, &ring->flags); adapter->tx_ring[i] = ring; } - /* Restore the adapter's original node */ - adapter->node = orig_node; for (i = 0; i < adapter->num_rx_queues; i++) { - if (orig_node == -1) { - int cur_node = next_online_node(adapter->node); - if (cur_node == MAX_NUMNODES) - cur_node = first_online_node; - adapter->node = cur_node; - } - ring = kzalloc_node(sizeof(struct igb_ring), GFP_KERNEL, - adapter->node); - if (!ring) - ring = kzalloc(sizeof(struct igb_ring), GFP_KERNEL); + ring = kzalloc(sizeof(struct igb_ring), GFP_KERNEL); if (!ring) goto err; ring->count = adapter->rx_ring_count; ring->queue_index = i; ring->dev = &adapter->pdev->dev; ring->netdev = adapter->netdev; - ring->numa_node = adapter->node; /* set flag indicating ring supports SCTP checksum offload */ if (adapter->hw.mac.type >= e1000_82576) set_bit(IGB_RING_FLAG_RX_SCTP_CSUM, &ring->flags); @@ -741,16 +718,12 @@ static int igb_alloc_queues(struct igb_adapter *adapter) adapter->rx_ring[i] = ring; } - /* Restore the adapter's original node */ - adapter->node = orig_node; igb_cache_ring_register(adapter); return 0; err: - /* Restore the adapter's original node */ - adapter->node = orig_node; igb_free_queues(adapter); return -ENOMEM; @@ -1116,24 +1089,10 @@ static int igb_alloc_q_vectors(struct igb_adapter *adapter) struct igb_q_vector *q_vector; struct e1000_hw *hw = &adapter->hw; int v_idx; - int orig_node = adapter->node; for (v_idx = 0; v_idx < adapter->num_q_vectors; v_idx++) { - if ((adapter->num_q_vectors == (adapter->num_rx_queues + - adapter->num_tx_queues)) && - (adapter->num_rx_queues == v_idx)) - adapter->node = orig_node; - if (orig_node == -1) { - int cur_node = next_online_node(adapter->node); - if (cur_node == MAX_NUMNODES) - cur_node = first_online_node; - adapter->node = cur_node; - } - q_vector = kzalloc_node(sizeof(struct igb_q_vector), GFP_KERNEL, - adapter->node); - if (!q_vector) - q_vector = kzalloc(sizeof(struct igb_q_vector), - GFP_KERNEL); + q_vector = kzalloc(sizeof(struct igb_q_vector), + GFP_KERNEL); if (!q_vector) goto err_out; q_vector->adapter = adapter; @@ -1142,14 +1101,10 @@ static int igb_alloc_q_vectors(struct igb_adapter *adapter) netif_napi_add(adapter->netdev, &q_vector->napi, igb_poll, 64); adapter->q_vector[v_idx] = q_vector; } - /* Restore the adapter's original node */ - adapter->node = orig_node; return 0; err_out: - /* Restore the adapter's original node */ - adapter->node = orig_node; igb_free_q_vectors(adapter); return -ENOMEM; } @@ -2423,8 +2378,6 @@ static int __devinit igb_sw_init(struct igb_adapter *adapter) VLAN_HLEN; adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN; - adapter->node = -1; - spin_lock_init(&adapter->stats64_lock); #ifdef CONFIG_PCI_IOV switch (hw->mac.type) { @@ -2671,13 +2624,11 @@ static int igb_close(struct net_device *netdev) int igb_setup_tx_resources(struct igb_ring *tx_ring) { struct device *dev = tx_ring->dev; - int orig_node = dev_to_node(dev); int size; size = sizeof(struct igb_tx_buffer) * tx_ring->count; - tx_ring->tx_buffer_info = vzalloc_node(size, tx_ring->numa_node); - if (!tx_ring->tx_buffer_info) - tx_ring->tx_buffer_info = vzalloc(size); + + tx_ring->tx_buffer_info = vzalloc(size); if (!tx_ring->tx_buffer_info) goto err; @@ -2685,18 +2636,10 @@ int igb_setup_tx_resources(struct igb_ring *tx_ring) tx_ring->size = tx_ring->count * sizeof(union e1000_adv_tx_desc); tx_ring->size = ALIGN(tx_ring->size, 4096); - set_dev_node(dev, tx_ring->numa_node); tx_ring->desc = dma_alloc_coherent(dev, tx_ring->size, &tx_ring->dma, GFP_KERNEL); - set_dev_node(dev, orig_node); - if (!tx_ring->desc) - tx_ring->desc = dma_alloc_coherent(dev, - tx_ring->size, - &tx_ring->dma, - GFP_KERNEL); - if (!tx_ring->desc) goto err; @@ -2707,8 +2650,8 @@ int igb_setup_tx_resources(struct igb_ring *tx_ring) err: vfree(tx_ring->tx_buffer_info); - dev_err(dev, - "Unable to allocate memory for the transmit descriptor ring\n"); + tx_ring->tx_buffer_info = NULL; + dev_err(dev, "Unable to allocate memory for the Tx descriptor ring\n"); return -ENOMEM; } @@ -2825,34 +2768,23 @@ static void igb_configure_tx(struct igb_adapter *adapter) int igb_setup_rx_resources(struct igb_ring *rx_ring) { struct device *dev = rx_ring->dev; - int orig_node = dev_to_node(dev); - int size, desc_len; + int size; size = sizeof(struct igb_rx_buffer) * rx_ring->count; - rx_ring->rx_buffer_info = vzalloc_node(size, rx_ring->numa_node); - if (!rx_ring->rx_buffer_info) - rx_ring->rx_buffer_info = vzalloc(size); + + rx_ring->rx_buffer_info = vzalloc(size); if (!rx_ring->rx_buffer_info) goto err; - desc_len = sizeof(union e1000_adv_rx_desc); /* Round up to nearest 4K */ - rx_ring->size = rx_ring->count * desc_len; + rx_ring->size = rx_ring->count * sizeof(union e1000_adv_rx_desc); rx_ring->size = ALIGN(rx_ring->size, 4096); - set_dev_node(dev, rx_ring->numa_node); rx_ring->desc = dma_alloc_coherent(dev, rx_ring->size, &rx_ring->dma, GFP_KERNEL); - set_dev_node(dev, orig_node); - if (!rx_ring->desc) - rx_ring->desc = dma_alloc_coherent(dev, - rx_ring->size, - &rx_ring->dma, - GFP_KERNEL); - if (!rx_ring->desc) goto err; @@ -2864,8 +2796,7 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring) err: vfree(rx_ring->rx_buffer_info); rx_ring->rx_buffer_info = NULL; - dev_err(dev, "Unable to allocate memory for the receive descriptor" - " ring\n"); + dev_err(dev, "Unable to allocate memory for the Rx descriptor ring\n"); return -ENOMEM; } -- cgit v1.2.3-70-g09d2 From c9f14bf3a49f86e6402a6e3476a180f2bdc8a71b Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Tue, 18 Sep 2012 01:56:27 +0000 Subject: igb: Use dma_unmap_addr and dma_unmap_len defines This change is meant to improve performance on systems that do not require the DMA unmap calls. On those systems we do not need to make use of the unmap address for Tx or the unmap length so we can drop both thereby reducing the size of the Tx buffer info structure. In addition I have changed the logic to check for unmap length instead of unmap address when checking to see if a buffer needs to be unmapped from DMA use. The reasons for this change is that on some platforms it is possible to receive a valid DMA address of 0 from an IOMMU. Signed-off-by: Alexander Duyck Tested-by: Aaron Brown Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/igb/igb.h | 4 +- drivers/net/ethernet/intel/igb/igb_main.c | 64 +++++++++++++++---------------- 2 files changed, 34 insertions(+), 34 deletions(-) (limited to 'drivers/net/ethernet/intel/igb/igb.h') diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 9cad0589419..8aad230c059 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -168,8 +168,8 @@ struct igb_tx_buffer { unsigned int bytecount; u16 gso_segs; __be16 protocol; - dma_addr_t dma; - u32 length; + DEFINE_DMA_UNMAP_ADDR(dma); + DEFINE_DMA_UNMAP_LEN(len); u32 tx_flags; }; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index db6e456688a..60bf4653483 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -403,8 +403,8 @@ static void igb_dump(struct igb_adapter *adapter) buffer_info = &tx_ring->tx_buffer_info[tx_ring->next_to_clean]; pr_info(" %5d %5X %5X %016llX %04X %p %016llX\n", n, tx_ring->next_to_use, tx_ring->next_to_clean, - (u64)buffer_info->dma, - buffer_info->length, + (u64)dma_unmap_addr(buffer_info, dma), + dma_unmap_len(buffer_info, len), buffer_info->next_to_watch, (u64)buffer_info->time_stamp); } @@ -455,8 +455,8 @@ static void igb_dump(struct igb_adapter *adapter) " %04X %p %016llX %p%s\n", i, le64_to_cpu(u0->a), le64_to_cpu(u0->b), - (u64)buffer_info->dma, - buffer_info->length, + (u64)dma_unmap_addr(buffer_info, dma), + dma_unmap_len(buffer_info, len), buffer_info->next_to_watch, (u64)buffer_info->time_stamp, buffer_info->skb, next_desc); @@ -465,7 +465,8 @@ static void igb_dump(struct igb_adapter *adapter) print_hex_dump(KERN_INFO, "", DUMP_PREFIX_ADDRESS, 16, 1, buffer_info->skb->data, - buffer_info->length, true); + dma_unmap_len(buffer_info, len), + true); } } @@ -3198,20 +3199,20 @@ void igb_unmap_and_free_tx_resource(struct igb_ring *ring, { if (tx_buffer->skb) { dev_kfree_skb_any(tx_buffer->skb); - if (tx_buffer->dma) + if (dma_unmap_len(tx_buffer, len)) dma_unmap_single(ring->dev, - tx_buffer->dma, - tx_buffer->length, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), DMA_TO_DEVICE); - } else if (tx_buffer->dma) { + } else if (dma_unmap_len(tx_buffer, len)) { dma_unmap_page(ring->dev, - tx_buffer->dma, - tx_buffer->length, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), DMA_TO_DEVICE); } tx_buffer->next_to_watch = NULL; tx_buffer->skb = NULL; - tx_buffer->dma = 0; + dma_unmap_len_set(tx_buffer, len, 0); /* buffer_info must be completely set up in the transmit path */ } @@ -4206,7 +4207,7 @@ static void igb_tx_map(struct igb_ring *tx_ring, const u8 hdr_len) { struct sk_buff *skb = first->skb; - struct igb_tx_buffer *tx_buffer_info; + struct igb_tx_buffer *tx_buffer; union e1000_adv_tx_desc *tx_desc; dma_addr_t dma; struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; @@ -4227,8 +4228,8 @@ static void igb_tx_map(struct igb_ring *tx_ring, goto dma_error; /* record length, and DMA address */ - first->length = size; - first->dma = dma; + dma_unmap_len_set(first, len, size); + dma_unmap_addr_set(first, dma, dma); tx_desc->read.buffer_addr = cpu_to_le64(dma); for (;;) { @@ -4270,9 +4271,9 @@ static void igb_tx_map(struct igb_ring *tx_ring, if (dma_mapping_error(tx_ring->dev, dma)) goto dma_error; - tx_buffer_info = &tx_ring->tx_buffer_info[i]; - tx_buffer_info->length = size; - tx_buffer_info->dma = dma; + tx_buffer = &tx_ring->tx_buffer_info[i]; + dma_unmap_len_set(tx_buffer, len, size); + dma_unmap_addr_set(tx_buffer, dma, dma); tx_desc->read.olinfo_status = 0; tx_desc->read.buffer_addr = cpu_to_le64(dma); @@ -4323,9 +4324,9 @@ dma_error: /* clear dma mappings for failed tx_buffer_info map */ for (;;) { - tx_buffer_info = &tx_ring->tx_buffer_info[i]; - igb_unmap_and_free_tx_resource(tx_ring, tx_buffer_info); - if (tx_buffer_info == first) + tx_buffer = &tx_ring->tx_buffer_info[i]; + igb_unmap_and_free_tx_resource(tx_ring, tx_buffer); + if (tx_buffer == first) break; if (i == 0) i = tx_ring->count; @@ -5716,18 +5717,19 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) /* free the skb */ dev_kfree_skb_any(tx_buffer->skb); - tx_buffer->skb = NULL; /* unmap skb header data */ dma_unmap_single(tx_ring->dev, - tx_buffer->dma, - tx_buffer->length, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), DMA_TO_DEVICE); + /* clear tx_buffer data */ + tx_buffer->skb = NULL; + dma_unmap_len_set(tx_buffer, len, 0); + /* clear last DMA location and unmap remaining buffers */ while (tx_desc != eop_desc) { - tx_buffer->dma = 0; - tx_buffer++; tx_desc++; i++; @@ -5738,17 +5740,15 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector) } /* unmap any remaining paged data */ - if (tx_buffer->dma) { + if (dma_unmap_len(tx_buffer, len)) { dma_unmap_page(tx_ring->dev, - tx_buffer->dma, - tx_buffer->length, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); } } - /* clear last DMA location */ - tx_buffer->dma = 0; - /* move us one more past the eop_desc for start of next pkt */ tx_buffer++; tx_desc++; -- cgit v1.2.3-70-g09d2