diff options
| -rw-r--r-- | drivers/net/ethernet/intel/igb/igb.h | 58 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/igb/igb_ethtool.c | 65 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/igb/igb_main.c | 514 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/igb/igb_ptp.c | 3 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 2 |
5 files changed, 439 insertions, 203 deletions
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index acbc3abe2ddd..dc6e2980718f 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -142,12 +142,24 @@ struct vf_data_storage { /* Supported Rx Buffer Sizes */ #define IGB_RXBUFFER_256 256 #define IGB_RXBUFFER_2048 2048 +#define IGB_RXBUFFER_3072 3072 #define IGB_RX_HDR_LEN IGB_RXBUFFER_256 -#define IGB_RX_BUFSZ IGB_RXBUFFER_2048 +#define IGB_TS_HDR_LEN 16 + +#define IGB_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) +#if (PAGE_SIZE < 8192) +#define IGB_MAX_FRAME_BUILD_SKB \ + (SKB_WITH_OVERHEAD(IGB_RXBUFFER_2048) - IGB_SKB_PAD - IGB_TS_HDR_LEN) +#else +#define IGB_MAX_FRAME_BUILD_SKB (IGB_RXBUFFER_2048 - IGB_TS_HDR_LEN) +#endif /* How many Rx Buffers do we bundle into one write to the hardware ? */ #define IGB_RX_BUFFER_WRITE 16 /* Must be power of 2 */ +#define IGB_RX_DMA_ATTR \ + (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) + #define AUTO_ALL_MODES 0 #define IGB_EEPROM_APME 0x0400 @@ -301,12 +313,51 @@ struct igb_q_vector { }; enum e1000_ring_flags_t { + IGB_RING_FLAG_RX_3K_BUFFER, + IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, IGB_RING_FLAG_RX_SCTP_CSUM, IGB_RING_FLAG_RX_LB_VLAN_BSWAP, IGB_RING_FLAG_TX_CTX_IDX, IGB_RING_FLAG_TX_DETECT_HANG }; +#define ring_uses_large_buffer(ring) \ + test_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags) +#define set_ring_uses_large_buffer(ring) \ + set_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags) +#define clear_ring_uses_large_buffer(ring) \ + clear_bit(IGB_RING_FLAG_RX_3K_BUFFER, &(ring)->flags) + +#define ring_uses_build_skb(ring) \ + test_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) +#define set_ring_build_skb_enabled(ring) \ + set_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) +#define clear_ring_build_skb_enabled(ring) \ + clear_bit(IGB_RING_FLAG_RX_BUILD_SKB_ENABLED, &(ring)->flags) + +static inline unsigned int igb_rx_bufsz(struct igb_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring_uses_large_buffer(ring)) + return IGB_RXBUFFER_3072; + + if (ring_uses_build_skb(ring)) + return IGB_MAX_FRAME_BUILD_SKB + IGB_TS_HDR_LEN; +#endif + return IGB_RXBUFFER_2048; +} + +static inline unsigned int igb_rx_pg_order(struct igb_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring_uses_large_buffer(ring)) + return 1; +#endif + return 0; +} + +#define igb_rx_pg_size(_ring) (PAGE_SIZE << igb_rx_pg_order(_ring)) + #define IGB_TXD_DCMD (E1000_ADVTXD_DCMD_EOP | E1000_ADVTXD_DCMD_RS) #define IGB_RX_DESC(R, i) \ @@ -545,6 +596,7 @@ struct igb_adapter { #define IGB_FLAG_HAS_MSIX BIT(13) #define IGB_FLAG_EEE BIT(14) #define IGB_FLAG_VLAN_PROMISC BIT(15) +#define IGB_FLAG_RX_LEGACY BIT(16) /* Media Auto Sense */ #define IGB_MAS_ENABLE_0 0X0001 @@ -558,7 +610,6 @@ struct igb_adapter { #define IGB_DMCTLX_DCFLUSH_DIS 0x80000000 /* Disable DMA Coal Flush */ #define IGB_82576_TSYNC_SHIFT 19 -#define IGB_TS_HDR_LEN 16 enum e1000_state_t { __IGB_TESTING, __IGB_RESETTING, @@ -591,7 +642,6 @@ void igb_configure_rx_ring(struct igb_adapter *, struct igb_ring *); void igb_setup_tctl(struct igb_adapter *); void igb_setup_rctl(struct igb_adapter *); netdev_tx_t igb_xmit_frame_ring(struct sk_buff *, struct igb_ring *); -void igb_unmap_and_free_tx_resource(struct igb_ring *, struct igb_tx_buffer *); void igb_alloc_rx_buffers(struct igb_ring *, u16); void igb_update_stats(struct igb_adapter *, struct rtnl_link_stats64 *); bool igb_has_link(struct igb_adapter *adapter); @@ -604,7 +654,7 @@ void igb_ptp_reset(struct igb_adapter *adapter); void igb_ptp_suspend(struct igb_adapter *adapter); void igb_ptp_rx_hang(struct igb_adapter *adapter); void igb_ptp_rx_rgtstamp(struct igb_q_vector *q_vector, struct sk_buff *skb); -void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, unsigned char *va, +void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, struct sk_buff *skb); int igb_ptp_set_ts_config(struct net_device *netdev, struct ifreq *ifr); int igb_ptp_get_ts_config(struct net_device *netdev, struct ifreq *ifr); diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 737b664d004c..797b9daba224 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -144,6 +144,13 @@ static const char igb_gstrings_test[][ETH_GSTRING_LEN] = { }; #define IGB_TEST_LEN (sizeof(igb_gstrings_test) / ETH_GSTRING_LEN) +static const char igb_priv_flags_strings[][ETH_GSTRING_LEN] = { +#define IGB_PRIV_FLAGS_LEGACY_RX BIT(0) + "legacy-rx", +}; + +#define IGB_PRIV_FLAGS_STR_LEN ARRAY_SIZE(igb_priv_flags_strings) + static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd) { struct igb_adapter *adapter = netdev_priv(netdev); @@ -852,6 +859,8 @@ static void igb_get_drvinfo(struct net_device *netdev, sizeof(drvinfo->fw_version)); strlcpy(drvinfo->bus_info, pci_name(adapter->pdev), sizeof(drvinfo->bus_info)); + + drvinfo->n_priv_flags = IGB_PRIV_FLAGS_STR_LEN; } static void igb_get_ringparam(struct net_device *netdev, @@ -1811,14 +1820,14 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring, tx_ntc = tx_ring->next_to_clean; rx_desc = IGB_RX_DESC(rx_ring, rx_ntc); - while (igb_test_staterr(rx_desc, E1000_RXD_STAT_DD)) { + while (rx_desc->wb.upper.length) { /* check Rx buffer */ rx_buffer_info = &rx_ring->rx_buffer_info[rx_ntc]; /* sync Rx buffer for CPU read */ dma_sync_single_for_cpu(rx_ring->dev, rx_buffer_info->dma, - IGB_RX_BUFSZ, + size, DMA_FROM_DEVICE); /* verify contents of skb */ @@ -1828,12 +1837,21 @@ static int igb_clean_test_rings(struct igb_ring *rx_ring, /* sync Rx buffer for device write */ dma_sync_single_for_device(rx_ring->dev, rx_buffer_info->dma, - IGB_RX_BUFSZ, + size, DMA_FROM_DEVICE); /* unmap buffer on Tx side */ tx_buffer_info = &tx_ring->tx_buffer_info[tx_ntc]; - igb_unmap_and_free_tx_resource(tx_ring, tx_buffer_info); + + /* Free all the Tx ring sk_buffs */ + dev_kfree_skb_any(tx_buffer_info->skb); + + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer_info, dma), + dma_unmap_len(tx_buffer_info, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer_info, len, 0); /* increment Rx/Tx next to clean counters */ rx_ntc++; @@ -2271,6 +2289,8 @@ static int igb_get_sset_count(struct net_device *netdev, int sset) return IGB_STATS_LEN; case ETH_SS_TEST: return IGB_TEST_LEN; + case ETH_SS_PRIV_FLAGS: + return IGB_PRIV_FLAGS_STR_LEN; default: return -ENOTSUPP; } @@ -2376,6 +2396,10 @@ static void igb_get_strings(struct net_device *netdev, u32 stringset, u8 *data) } /* BUG_ON(p - data != IGB_STATS_LEN * ETH_GSTRING_LEN); */ break; + case ETH_SS_PRIV_FLAGS: + memcpy(data, igb_priv_flags_strings, + IGB_PRIV_FLAGS_STR_LEN * ETH_GSTRING_LEN); + break; } } @@ -3388,6 +3412,37 @@ static int igb_set_channels(struct net_device *netdev, return 0; } +static u32 igb_get_priv_flags(struct net_device *netdev) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + u32 priv_flags = 0; + + if (adapter->flags & IGB_FLAG_RX_LEGACY) + priv_flags |= IGB_PRIV_FLAGS_LEGACY_RX; + + return priv_flags; +} + +static int igb_set_priv_flags(struct net_device *netdev, u32 priv_flags) +{ + struct igb_adapter *adapter = netdev_priv(netdev); + unsigned int flags = adapter->flags; + + flags &= ~IGB_FLAG_RX_LEGACY; + if (priv_flags & IGB_PRIV_FLAGS_LEGACY_RX) + flags |= IGB_FLAG_RX_LEGACY; + + if (flags != adapter->flags) { + adapter->flags = flags; + + /* reset interface to repopulate queues */ + if (netif_running(netdev)) + igb_reinit_locked(adapter); + } + + return 0; +} + static const struct ethtool_ops igb_ethtool_ops = { .get_settings = igb_get_settings, .set_settings = igb_set_settings, @@ -3426,6 +3481,8 @@ static const struct ethtool_ops igb_ethtool_ops = { .set_rxfh = igb_set_rxfh, .get_channels = igb_get_channels, .set_channels = igb_set_channels, + .get_priv_flags = igb_get_priv_flags, + .set_priv_flags = igb_set_priv_flags, .begin = igb_ethtool_begin, .complete = igb_ethtool_complete, }; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index be456bae8169..26a821fcd220 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -554,7 +554,7 @@ rx_ring_summary: 16, 1, page_address(buffer_info->page) + buffer_info->page_offset, - IGB_RX_BUFSZ, true); + igb_rx_bufsz(rx_ring), true); } } } @@ -3293,7 +3293,7 @@ int igb_setup_tx_resources(struct igb_ring *tx_ring) size = sizeof(struct igb_tx_buffer) * tx_ring->count; - tx_ring->tx_buffer_info = vzalloc(size); + tx_ring->tx_buffer_info = vmalloc(size); if (!tx_ring->tx_buffer_info) goto err; @@ -3404,6 +3404,10 @@ void igb_configure_tx_ring(struct igb_adapter *adapter, txdctl |= IGB_TX_HTHRESH << 8; txdctl |= IGB_TX_WTHRESH << 16; + /* reinitialize tx_buffer_info */ + memset(ring->tx_buffer_info, 0, + sizeof(struct igb_tx_buffer) * ring->count); + txdctl |= E1000_TXDCTL_QUEUE_ENABLE; wr32(E1000_TXDCTL(reg_idx), txdctl); } @@ -3435,7 +3439,7 @@ int igb_setup_rx_resources(struct igb_ring *rx_ring) size = sizeof(struct igb_rx_buffer) * rx_ring->count; - rx_ring->rx_buffer_info = vzalloc(size); + rx_ring->rx_buffer_info = vmalloc(size); if (!rx_ring->rx_buffer_info) goto err; @@ -3720,6 +3724,7 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, struct igb_ring *ring) { struct e1000_hw *hw = &adapter->hw; + union e1000_adv_rx_desc *rx_desc; u64 rdba = ring->dma; int reg_idx = ring->reg_idx; u32 srrctl = 0, rxdctl = 0; @@ -3741,7 +3746,10 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, /* set descriptor configuration */ srrctl = IGB_RX_HDR_LEN << E1000_SRRCTL_BSIZEHDRSIZE_SHIFT; - srrctl |= IGB_RX_BUFSZ >> E1000_SRRCTL_BSIZEPKT_SHIFT; + if (ring_uses_large_buffer(ring)) + srrctl |= IGB_RXBUFFER_3072 >> E1000_SRRCTL_BSIZEPKT_SHIFT; + else + srrctl |= IGB_RXBUFFER_2048 >> E1000_SRRCTL_BSIZEPKT_SHIFT; srrctl |= E1000_SRRCTL_DESCTYPE_ADV_ONEBUF; if (hw->mac.type >= e1000_82580) srrctl |= E1000_SRRCTL_TIMESTAMP; @@ -3758,11 +3766,39 @@ void igb_configure_rx_ring(struct igb_adapter *adapter, rxdctl |= IGB_RX_HTHRESH << 8; rxdctl |= IGB_RX_WTHRESH << 16; + /* initialize rx_buffer_info */ + memset(ring->rx_buffer_info, 0, + sizeof(struct igb_rx_buffer) * ring->count); + + /* initialize Rx descriptor 0 */ + rx_desc = IGB_RX_DESC(ring, 0); + rx_desc->wb.upper.length = 0; + /* enable receive descriptor fetching */ rxdctl |= E1000_RXDCTL_QUEUE_ENABLE; wr32(E1000_RXDCTL(reg_idx), rxdctl); } +static void igb_set_rx_buffer_len(struct igb_adapter *adapter, + struct igb_ring *rx_ring) +{ + /* set build_skb and buffer size flags */ + clear_ring_build_skb_enabled(rx_ring); + clear_ring_uses_large_buffer(rx_ring); + + if (adapter->flags & IGB_FLAG_RX_LEGACY) + return; + + set_ring_build_skb_enabled(rx_ring); + +#if (PAGE_SIZE < 8192) + if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB) + return; + + set_ring_uses_large_buffer(rx_ring); +#endif +} + /** * igb_configure_rx - Configure receive Unit after Reset * @adapter: board private structure @@ -3780,8 +3816,12 @@ static void igb_configure_rx(struct igb_adapter *adapter) /* Setup the HW Rx Head and Tail Descriptor Pointers and * the Base and Length of the Rx Descriptor Ring */ - for (i = 0; i < adapter->num_rx_queues; i++) - igb_configure_rx_ring(adapter, adapter->rx_ring[i]); + for (i = 0; i < adapter->num_rx_queues; i++) { + struct igb_ring *rx_ring = adapter->rx_ring[i]; + + igb_set_rx_buffer_len(adapter, rx_ring); + igb_configure_rx_ring(adapter, rx_ring); + } } /** @@ -3822,55 +3862,63 @@ static void igb_free_all_tx_resources(struct igb_adapter *adapter) igb_free_tx_resources(adapter->tx_ring[i]); } -void igb_unmap_and_free_tx_resource(struct igb_ring *ring, - struct igb_tx_buffer *tx_buffer) -{ - if (tx_buffer->skb) { - dev_kfree_skb_any(tx_buffer->skb); - if (dma_unmap_len(tx_buffer, len)) - dma_unmap_single(ring->dev, - dma_unmap_addr(tx_buffer, dma), - dma_unmap_len(tx_buffer, len), - DMA_TO_DEVICE); - } else if (dma_unmap_len(tx_buffer, len)) { - dma_unmap_page(ring->dev, - 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; - dma_unmap_len_set(tx_buffer, len, 0); - /* buffer_info must be completely set up in the transmit path */ -} - /** * igb_clean_tx_ring - Free Tx Buffers * @tx_ring: ring to be cleaned **/ static void igb_clean_tx_ring(struct igb_ring *tx_ring) { - struct igb_tx_buffer *buffer_info; - unsigned long size; - u16 i; + u16 i = tx_ring->next_to_clean; + struct igb_tx_buffer *tx_buffer = &tx_ring->tx_buffer_info[i]; - if (!tx_ring->tx_buffer_info) - return; - /* Free all the Tx ring sk_buffs */ + while (i != tx_ring->next_to_use) { + union e1000_adv_tx_desc *eop_desc, *tx_desc; - for (i = 0; i < tx_ring->count; i++) { - buffer_info = &tx_ring->tx_buffer_info[i]; - igb_unmap_and_free_tx_resource(tx_ring, buffer_info); - } + /* Free all the Tx ring sk_buffs */ + dev_kfree_skb_any(tx_buffer->skb); - netdev_tx_reset_queue(txring_txq(tx_ring)); + /* unmap skb header data */ + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); - size = sizeof(struct igb_tx_buffer) * tx_ring->count; - memset(tx_ring->tx_buffer_info, 0, size); + /* check for eop_desc to determine the end of the packet */ + eop_desc = tx_buffer->next_to_watch; + tx_desc = IGB_TX_DESC(tx_ring, i); + + /* unmap remaining buffers */ + while (tx_desc != eop_desc) { + tx_buffer++; + tx_desc++; + i++; + if (unlikely(i == tx_ring->count)) { + i = 0; + tx_buffer = tx_ring->tx_buffer_info; + tx_desc = IGB_TX_DESC(tx_ring, 0); + } + + /* unmap any remaining paged data */ + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + } - /* Zero out the descriptor ring */ - memset(tx_ring->desc, 0, tx_ring->size); + /* move us one more past the eop_desc for start of next pkt */ + tx_buffer++; + i++; + if (unlikely(i == tx_ring->count)) { + i = 0; + tx_buffer = tx_ring->tx_buffer_info; + } + } + /* reset BQL for queue */ + netdev_tx_reset_queue(txring_txq(tx_ring)); + + /* reset next_to_use and next_to_clean */ tx_ring->next_to_use = 0; tx_ring->next_to_clean = 0; } @@ -3932,50 +3980,39 @@ static void igb_free_all_rx_resources(struct igb_adapter *adapter) **/ static void igb_clean_rx_ring(struct igb_ring *rx_ring) { - unsigned long size; - u16 i; + u16 i = rx_ring->next_to_clean; if (rx_ring->skb) dev_kfree_skb(rx_ring->skb); rx_ring->skb = NULL; - if (!rx_ring->rx_buffer_info) - return; - /* Free all the Rx ring sk_buffs */ - for (i = 0; i < rx_ring->count; i++) { + while (i != rx_ring->next_to_alloc) { struct igb_rx_buffer *buffer_info = &rx_ring->rx_buffer_info[i]; - if (!buffer_info->page) - continue; - /* Invalidate cache lines that may have been written to by * device so that we avoid corrupting memory. */ dma_sync_single_range_for_cpu(rx_ring->dev, buffer_info->dma, buffer_info->page_offset, - IGB_RX_BUFSZ, + igb_rx_bufsz(rx_ring), DMA_FROM_DEVICE); /* free resources associated with mapping */ dma_unmap_page_attrs(rx_ring->dev, buffer_info->dma, - PAGE_SIZE, + igb_rx_pg_size(rx_ring), DMA_FROM_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); + IGB_RX_DMA_ATTR); __page_frag_cache_drain(buffer_info->page, buffer_info->pagecnt_bias); - buffer_info->page = NULL; + i++; + if (i == rx_ring->count) + i = 0; } - size = sizeof(struct igb_rx_buffer) * rx_ring->count; - memset(rx_ring->rx_buffer_info, 0, size); - - /* Zero out the descriptor ring */ - memset(rx_ring->desc, 0, rx_ring->size); - rx_ring->next_to_alloc = 0; rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0; @@ -4240,7 +4277,7 @@ static void igb_set_rx_mode(struct net_device *netdev) struct igb_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; unsigned int vfn = adapter->vfs_allocated_count; - u32 rctl = 0, vmolr = 0; + u32 rctl = 0, vmolr = 0, rlpml = MAX_JUMBO_FRAME_SIZE; int count; /* Check for Promiscuous and All Multicast modes */ @@ -4298,6 +4335,14 @@ static void igb_set_rx_mode(struct net_device *netdev) E1000_RCTL_VFE); wr32(E1000_RCTL, rctl); +#if (PAGE_SIZE < 8192) + if (!adapter->vfs_allocated_count) { + if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB) + rlpml = IGB_MAX_FRAME_BUILD_SKB; + } +#endif + wr32(E1000_RLPML, rlpml); + /* In order to support SR-IOV and eventually VMDq it is necessary to set * the VMOLR to enable the appropriate modes. Without this workaround * we will have issues with VLAN tag stripping not being done for frames @@ -4312,12 +4357,17 @@ static void igb_set_rx_mode(struct net_device *netdev) vmolr |= rd32(E1000_VMOLR(vfn)) & ~(E1000_VMOLR_ROPE | E1000_VMOLR_MPME | E1000_VMOLR_ROMPE); - /* enable Rx jumbo frames, no need for restriction */ + /* enable Rx jumbo frames, restrict as needed to support build_skb */ vmolr &= ~E1000_VMOLR_RLPML_MASK; - vmolr |= MAX_JUMBO_FRAME_SIZE | E1000_VMOLR_LPE; +#if (PAGE_SIZE < 8192) + if (adapter->max_frame_size <= IGB_MAX_FRAME_BUILD_SKB) + vmolr |= IGB_MAX_FRAME_BUILD_SKB; + else +#endif + vmolr |= MAX_JUMBO_FRAME_SIZE; + vmolr |= E1000_VMOLR_LPE; wr32(E1000_VMOLR(vfn), vmolr); - wr32(E1000_RLPML, MAX_JUMBO_FRAME_SIZE); igb_restore_vf_multicasts(adapter); } @@ -5256,18 +5306,32 @@ static void igb_tx_map(struct igb_ring *tx_ring, dma_error: dev_err(tx_ring->dev, "TX DMA map failed\n"); + tx_buffer = &tx_ring->tx_buffer_info[i]; /* clear dma mappings for failed tx_buffer_info map */ - for (;;) { + while (tx_buffer != first) { + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_page(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + + if (i--) + i += tx_ring->count; 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; - i--; } + if (dma_unmap_len(tx_buffer, len)) + dma_unmap_single(tx_ring->dev, + dma_unmap_addr(tx_buffer, dma), + dma_unmap_len(tx_buffer, len), + DMA_TO_DEVICE); + dma_unmap_len_set(tx_buffer, len, 0); + + dev_kfree_skb_any(tx_buffer->skb); + tx_buffer->skb = NULL; + tx_ring->next_to_use = i; } @@ -5339,7 +5403,8 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, return NETDEV_TX_OK; out_drop: - igb_unmap_and_free_tx_resource(tx_ring, first); + dev_kfree_skb_any(first->skb); + first->skb = NULL; return NETDEV_TX_OK; } @@ -6686,7 +6751,6 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget) 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 */ @@ -6822,8 +6886,14 @@ static void igb_reuse_rx_page(struct igb_ring *rx_ring, nta++; rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; - /* transfer page from old buffer to new buffer */ - *new_buff = *old_buff; + /* Transfer page from old buffer to new buffer. + * Move each member individually to avoid possible store + * forwarding stalls. + */ + new_buff->dma = old_buff->dma; + new_buff->page = old_buff->page; + new_buff->page_offset = old_buff->page_offset; + new_buff->pagecnt_bias = old_buff->pagecnt_bias; } static inline bool igb_page_is_reserved(struct page *page) @@ -6831,11 +6901,10 @@ static inline bool igb_page_is_reserved(struct page *page) return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page); } -static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, - struct page *page, - unsigned int truesize) +static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer) { - unsigned int pagecnt_bias = rx_buffer->pagecnt_bias--; + unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; + struct page *page = rx_buffer->page; /* avoid re-using remote pages */ if (unlikely(igb_page_is_reserved(page))) @@ -6843,16 +6912,13 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ - if (unlikely(page_ref_count(page) != pagecnt_bias)) + if (unlikely((page_ref_count(page) - pagecnt_bias) > 1)) return false; - - /* flip page offset to other buffer */ - rx_buffer->page_offset ^= IGB_RX_BUFSZ; #else - /* move offset up to the next cache line */ - rx_buffer->page_offset += truesize; +#define IGB_LAST_OFFSET \ + (SKB_WITH_OVERHEAD(PAGE_SIZE) - IGB_RXBUFFER_2048) - if (rx_buffer->page_offset > (PAGE_SIZE - IGB_RX_BUFSZ)) + if (rx_buffer->page_offset > IGB_LAST_OFFSET) return false; #endif @@ -6860,7 +6926,7 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, * the pagecnt_bias and page count so that we fully restock the * number of references the driver holds. */ - if (unlikely(pagecnt_bias == 1)) { + if (unlikely(!pagecnt_bias)) { page_ref_add(page, USHRT_MAX); rx_buffer->pagecnt_bias = USHRT_MAX; } @@ -6872,34 +6938,56 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, * igb_add_rx_frag - Add contents of Rx buffer to sk_buff * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: buffer containing page to add - * @rx_desc: descriptor containing length of buffer written by hardware * @skb: sk_buff to place the data into + * @size: size of buffer to be added * * This function will add the data contained in rx_buffer->page to the skb. - * This is done either through a direct copy if the data in the buffer is - * less than the skb header size, otherwise it will just attach the page as - * a frag to the skb. - * - * The function will then update the page offset if necessary and return - * true if the buffer can be reused by the adapter. **/ -static bool igb_add_rx_frag(struct igb_ring *rx_ring, +static void igb_add_rx_frag(struct igb_ring *rx_ring, struct igb_rx_buffer *rx_buffer, - unsigned int size, - union e1000_adv_rx_desc *rx_desc, - struct sk_buff *skb) + struct sk_buff *skb, + unsigned int size) { - struct page *page = rx_buffer->page; - unsigned char *va = page_address(page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) - unsigned int truesize = IGB_RX_BUFSZ; + unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = ring_uses_build_skb(rx_ring) ? + SKB_DATA_ALIGN(IGB_SKB_PAD + size) : + SKB_DATA_ALIGN(size); +#endif + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, + rx_buffer->page_offset, size, truesize); +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif +} + +static struct sk_buff *igb_construct_skb(struct igb_ring *rx_ring, + struct igb_rx_buffer *rx_buffer, + union e1000_adv_rx_desc *rx_desc, + unsigned int size) +{ + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; #else unsigned int truesize = SKB_DATA_ALIGN(size); #endif - unsigned int pull_len; + unsigned int headlen; + struct sk_buff *skb; - if (unlikely(skb_is_nonlinear(skb))) - goto add_tail_frag; + /* prefetch first cache line of first page */ + prefetch(va); +#if L1_CACHE_BYTES < 128 + prefetch(va + L1_CACHE_BYTES); +#endif + + /* allocate a skb to store the frags */ + skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGB_RX_HDR_LEN); + if (unlikely(!skb)) + return NULL; if (unlikely(igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP))) { igb_ptp_rx_pktstamp(rx_ring->q_vector, va, skb); @@ -6907,95 +6995,73 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring, size -= IGB_TS_HDR_LEN; } - if (likely(size <= IGB_RX_HDR_LEN)) { - memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); - - /* page is not reserved, we can reuse buffer as-is */ - if (likely(!igb_page_is_reserved(page))) - return true; - - /* this page cannot be reused so discard it */ - return false; - } - - /* we need the header to contain the greater of either ETH_HLEN or - * 60 bytes if the skb->len is less than 60 for skb_pad. - */ - pull_len = eth_get_headlen(va, IGB_RX_HDR_LEN); + /* Determine available headroom for copy */ + headlen = size; + if (headlen > IGB_RX_HDR_LEN) + headlen = eth_get_headlen(va, IGB_RX_HDR_LEN); /* align pull length to size of long to optimize memcpy performance */ - memcpy(__skb_put(skb, pull_len), va, ALIGN(pull_len, sizeof(long))); + memcpy(__skb_put(skb, headlen), va, ALIGN(headlen, sizeof(long))); /* update all of the pointers */ - va += pull_len; - size -= pull_len; - -add_tail_frag: - skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page, - (unsigned long)va & ~PAGE_MASK, size, truesize); + size -= headlen; + if (size) { + skb_add_rx_frag(skb, 0, rx_buffer->page, + (va + headlen) - page_address(rx_buffer->page), + size, truesize); +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif + } else { + rx_buffer->pagecnt_bias++; + } - return igb_can_reuse_rx_page(rx_buffer, page, truesize); + return skb; } -static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring, - union e1000_adv_rx_desc *rx_desc, - struct sk_buff *skb) +static struct sk_buff *igb_build_skb(struct igb_ring *rx_ring, + struct igb_rx_buffer *rx_buffer, + union e1000_adv_rx_desc *rx_desc, + unsigned int size) { - unsigned int size = le16_to_cpu(rx_desc->wb.upper.length); - struct igb_rx_buffer *rx_buffer; - struct page *page; - - rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; - page = rx_buffer->page; - prefetchw(page); - - /* we are reusing so sync this buffer for CPU use */ - dma_sync_single_range_for_cpu(rx_ring->dev, - rx_buffer->dma, - rx_buffer->page_offset, - size, - DMA_FROM_DEVICE); - - if (likely(!skb)) { - void *page_addr = page_address(page) + - rx_buffer->page_offset; + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = igb_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) + + SKB_DATA_ALIGN(IGB_SKB_PAD + size); +#endif + struct sk_buff *skb; - /* prefetch first cache line of first page */ - prefetch(page_addr); + /* prefetch first cache line of first page */ + prefetch(va); #if L1_CACHE_BYTES < 128 - prefetch(page_addr + L1_CACHE_BYTES); + prefetch(va + L1_CACHE_BYTES); #endif - /* allocate a skb to store the frags */ - skb = napi_alloc_skb(&rx_ring->q_vector->napi, IGB_RX_HDR_LEN); - if (unlikely(!skb)) { - rx_ring->rx_stats.alloc_failed++; - return NULL; - } + /* build an skb around the page buffer */ + skb = build_skb(va - IGB_SKB_PAD, truesize); + if (unlikely(!skb)) + return NULL; - /* we will be copying header into skb->data in - * pskb_may_pull so it is in our interest to prefetch - * it now to avoid a possible cache miss - */ - prefetchw(skb->data); - } + /* update pointers within the skb to store the data */ + skb_reserve(skb, IGB_SKB_PAD); + __skb_put(skb, size); - /* pull page into skb */ - if (igb_add_rx_frag(rx_ring, rx_buffer, size, rx_desc, skb)) { - /* hand second half of page back to the ring */ - igb_reuse_rx_page(rx_ring, rx_buffer); - } else { - /* We are not reusing the buffer so unmap it and free - * any references we are holding to it - */ - dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, - PAGE_SIZE, DMA_FROM_DEVICE, - DMA_ATTR_SKIP_CPU_SYNC); - __page_frag_cache_drain(page, rx_buffer->pagecnt_bias); + /* pull timestamp out of packet data */ + if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) { + igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb); + __skb_pull(skb, IGB_TS_HDR_LEN); } - /* clear contents of rx_buffer */ - rx_buffer->page = NULL; + /* update buffer offset */ +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif return skb; } @@ -7154,6 +7220,47 @@ static void igb_process_skb_fields(struct igb_ring *rx_ring, skb->protocol = eth_type_trans(skb, rx_ring->netdev); } +static struct igb_rx_buffer *igb_get_rx_buffer(struct igb_ring *rx_ring, + const unsigned int size) +{ + struct igb_rx_buffer *rx_buffer; + + rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean]; + prefetchw(rx_buffer->page); + + /* we are reusing so sync this buffer for CPU use */ + dma_sync_single_range_for_cpu(rx_ring->dev, + rx_buffer->dma, + rx_buffer->page_offset, + size, + DMA_FROM_DEVICE); + + rx_buffer->pagecnt_bias--; + + return rx_buffer; +} + +static void igb_put_rx_buffer(struct igb_ring *rx_ring, + struct igb_rx_buffer *rx_buffer) +{ + if (igb_can_reuse_rx_page(rx_buffer)) { + /* hand second half of page back to the ring */ + igb_reuse_rx_page(rx_ring, rx_buffer); + } else { + /* We are not reusing the buffer so unmap it and free + * any references we are holding to it + */ + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, + igb_rx_pg_size(rx_ring), DMA_FROM_DEVICE, + IGB_RX_DMA_ATTR); + __page_frag_cache_drain(rx_buffer->page, + rx_buffer->pagecnt_bias); + } + + /* clear contents of rx_buffer */ + rx_buffer->page = NULL; +} + static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) { struct igb_ring *rx_ring = q_vector->rx.ring; @@ -7163,6 +7270,8 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) while (likely(total_packets < budget)) { union e1000_adv_rx_desc *rx_desc; + struct igb_rx_buffer *rx_buffer; + unsigned int size; /* return some buffers to hardware, one at a time is too slow */ if (cleaned_count >= IGB_RX_BUFFER_WRITE) { @@ -7171,8 +7280,8 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) } rx_desc = IGB_RX_DESC(rx_ring, rx_ring->next_to_clean); - - if (!rx_desc->wb.upper.status_error) + size = le16_to_cpu(rx_desc->wb.upper.length); + if (!size) break; /* This memory barrier is needed to keep us from reading @@ -7181,13 +7290,25 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) */ dma_rmb(); + rx_buffer = igb_get_rx_buffer(rx_ring, size); + /* retrieve a buffer from the ring */ - skb = igb_fetch_rx_buffer(rx_ring, rx_desc, skb); + if (skb) + igb_add_rx_frag(rx_ring, rx_buffer, skb, size); + else if (ring_uses_build_skb(rx_ring)) + skb = igb_build_skb(rx_ring, rx_buffer, rx_desc, size); + else + skb = igb_construct_skb(rx_ring, rx_buffer, + rx_desc, size); /* exit if we failed to retrieve a buffer */ - if (!skb) + if (!skb) { + rx_ring->rx_stats.alloc_failed++; + rx_buffer->pagecnt_bias++; break; + } + igb_put_rx_buffer(rx_ring, rx_buffer); cleaned_count++; /* fetch next buffer in frame if non-eop */ @@ -7231,6 +7352,11 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget) return total_packets; } +static inline unsigned int igb_rx_offset(struct igb_ring *rx_ring) +{ + return ring_uses_build_skb(rx_ring) ? IGB_SKB_PAD : 0; +} + static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, struct igb_rx_buffer *bi) { @@ -7242,21 +7368,23 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, return true; /* alloc new page for storage */ - page = dev_alloc_page(); + page = dev_alloc_pages(igb_rx_pg_order(rx_ring)); if (unlikely(!page)) { rx_ring->rx_stats.alloc_failed++; return false; } /* map page for use */ - dma = dma_map_page_attrs(rx_ring->dev, page, 0, PAGE_SIZE, - DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC); + dma = dma_map_page_attrs(rx_ring->dev, page, 0, + igb_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IGB_RX_DMA_ATTR); /* if mapping failed free memory back to system since * there isn't much point in holding memory we can't use */ if (dma_mapping_error(rx_ring->dev, dma)) { - __free_page(page); + __free_pages(page, igb_rx_pg_order(rx_ring)); rx_ring->rx_stats.alloc_failed++; return false; @@ -7264,7 +7392,7 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring, bi->dma = dma; bi->page = page; - bi->page_offset = 0; + bi->page_offset = igb_rx_offset(rx_ring); bi->pagecnt_bias = 1; return true; @@ -7279,6 +7407,7 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) union e1000_adv_rx_desc *rx_desc; struct igb_rx_buffer *bi; u16 i = rx_ring->next_to_use; + u16 bufsz; /* nothing to do */ if (!cleaned_count) @@ -7288,14 +7417,15 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) bi = &rx_ring->rx_buffer_info[i]; i -= rx_ring->count; + bufsz = igb_rx_bufsz(rx_ring); + do { if (!igb_alloc_mapped_page(rx_ring, bi)) break; /* sync the buffer for use by the device */ dma_sync_single_range_for_device(rx_ring->dev, bi->dma, - bi->page_offset, - IGB_RX_BUFSZ, + bi->page_offset, bufsz, DMA_FROM_DEVICE); /* Refresh the desc even if buffer_addrs didn't change @@ -7312,8 +7442,8 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count) i -= rx_ring->count; } - /* clear the status bits for the next_to_use descriptor */ - rx_desc->wb.upper.status_error = 0; + /* clear the length for the next_to_use descriptor */ + rx_desc->wb.upper.length = 0; cleaned_count--; } while (cleaned_count); diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index c4477552ce9e..7a3fd4d74592 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -764,8 +764,7 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter) * incoming frame. The value is stored in little endian format starting on * byte 8. **/ -void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, - unsigned char *va, +void igb_ptp_rx_pktstamp(struct igb_q_vector *q_vector, void *va, struct sk_buff *skb) { __le64 *regval = (__le64 *)va; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index d45477db0227..852a2e7e25ed 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -2122,7 +2122,7 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, prefetch(va + L1_CACHE_BYTES); #endif - /* build an skb to around the page buffer */ + /* build an skb around the page buffer */ skb = build_skb(va - IXGBE_SKB_PAD, truesize); if (unlikely(!skb)) return NULL; |