diff options
Diffstat (limited to 'drivers/net/ethernet/intel/i40evf')
| -rw-r--r-- | drivers/net/ethernet/intel/i40evf/i40e_txrx.c | 89 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/i40evf/i40e_txrx.h | 82 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/i40evf/i40evf.h | 1 | ||||
| -rw-r--r-- | drivers/net/ethernet/intel/i40evf/i40evf_main.c | 14 |
4 files changed, 168 insertions, 18 deletions
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 95e383af41c4..460171edc412 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -509,14 +509,15 @@ void i40evf_clean_rx_ring(struct i40e_ring *rx_ring) dma_sync_single_range_for_cpu(rx_ring->dev, rx_bi->dma, rx_bi->page_offset, - I40E_RXBUFFER_2048, + rx_ring->rx_buf_len, DMA_FROM_DEVICE); /* free resources associated with mapping */ dma_unmap_page_attrs(rx_ring->dev, rx_bi->dma, - PAGE_SIZE, + i40e_rx_pg_size(rx_ring), DMA_FROM_DEVICE, I40E_RX_DMA_ATTR); + __page_frag_cache_drain(rx_bi->page, rx_bi->pagecnt_bias); rx_bi->page = NULL; @@ -618,6 +619,17 @@ static inline void i40e_release_rx_desc(struct i40e_ring *rx_ring, u32 val) } /** + * i40e_rx_offset - Return expected offset into page to access data + * @rx_ring: Ring we are requesting offset of + * + * Returns the offset value for ring into the data buffer. + */ +static inline unsigned int i40e_rx_offset(struct i40e_ring *rx_ring) +{ + return ring_uses_build_skb(rx_ring) ? I40E_SKB_PAD : 0; +} + +/** * i40e_alloc_mapped_page - recycle or make a new page * @rx_ring: ring to use * @bi: rx_buffer struct to modify @@ -638,7 +650,7 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, } /* alloc new page for storage */ - page = dev_alloc_page(); + page = dev_alloc_pages(i40e_rx_pg_order(rx_ring)); if (unlikely(!page)) { rx_ring->rx_stats.alloc_page_failed++; return false; @@ -646,7 +658,7 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, /* map page for use */ dma = dma_map_page_attrs(rx_ring->dev, page, 0, - PAGE_SIZE, + i40e_rx_pg_size(rx_ring), DMA_FROM_DEVICE, I40E_RX_DMA_ATTR); @@ -654,14 +666,14 @@ static bool i40e_alloc_mapped_page(struct i40e_ring *rx_ring, * there isn't much point in holding memory we can't use */ if (dma_mapping_error(rx_ring->dev, dma)) { - __free_pages(page, 0); + __free_pages(page, i40e_rx_pg_order(rx_ring)); rx_ring->rx_stats.alloc_page_failed++; return false; } bi->dma = dma; bi->page = page; - bi->page_offset = 0; + bi->page_offset = i40e_rx_offset(rx_ring); /* initialize pagecnt_bias to 1 representing we fully own page */ bi->pagecnt_bias = 1; @@ -714,7 +726,7 @@ bool i40evf_alloc_rx_buffers(struct i40e_ring *rx_ring, u16 cleaned_count) /* sync the buffer for use by the device */ dma_sync_single_range_for_device(rx_ring->dev, bi->dma, bi->page_offset, - I40E_RXBUFFER_2048, + rx_ring->rx_buf_len, DMA_FROM_DEVICE); /* Refresh the desc even if buffer_addrs didn't change @@ -1006,9 +1018,6 @@ static inline bool i40e_page_is_reusable(struct page *page) **/ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer) { -#if (PAGE_SIZE >= 8192) - unsigned int last_offset = PAGE_SIZE - I40E_RXBUFFER_2048; -#endif unsigned int pagecnt_bias = rx_buffer->pagecnt_bias; struct page *page = rx_buffer->page; @@ -1021,7 +1030,9 @@ static bool i40e_can_reuse_rx_page(struct i40e_rx_buffer *rx_buffer) if (unlikely((page_count(page) - pagecnt_bias) > 1)) return false; #else - if (rx_buffer->page_offset > last_offset) +#define I40E_LAST_OFFSET \ + (SKB_WITH_OVERHEAD(PAGE_SIZE) - I40E_RXBUFFER_2048) + if (rx_buffer->page_offset > I40E_LAST_OFFSET) return false; #endif @@ -1055,9 +1066,9 @@ static void i40e_add_rx_frag(struct i40e_ring *rx_ring, unsigned int size) { #if (PAGE_SIZE < 8192) - unsigned int truesize = I40E_RXBUFFER_2048; + unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; #else - unsigned int truesize = SKB_DATA_ALIGN(size); + unsigned int truesize = SKB_DATA_ALIGN(size + i40e_rx_offset(rx_ring)); #endif skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buffer->page, @@ -1116,7 +1127,7 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, { void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; #if (PAGE_SIZE < 8192) - unsigned int truesize = I40E_RXBUFFER_2048; + unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; #else unsigned int truesize = SKB_DATA_ALIGN(size); #endif @@ -1166,6 +1177,51 @@ static struct sk_buff *i40e_construct_skb(struct i40e_ring *rx_ring, } /** + * i40e_build_skb - Build skb around an existing buffer + * @rx_ring: Rx descriptor ring to transact packets on + * @rx_buffer: Rx buffer to pull data from + * @size: size of buffer to add to skb + * + * This function builds an skb around an existing Rx buffer, taking care + * to set up the skb correctly and avoid any memcpy overhead. + */ +static struct sk_buff *i40e_build_skb(struct i40e_ring *rx_ring, + struct i40e_rx_buffer *rx_buffer, + unsigned int size) +{ + void *va = page_address(rx_buffer->page) + rx_buffer->page_offset; +#if (PAGE_SIZE < 8192) + unsigned int truesize = i40e_rx_pg_size(rx_ring) / 2; +#else + unsigned int truesize = SKB_DATA_ALIGN(size); +#endif + struct sk_buff *skb; + + /* prefetch first cache line of first page */ + prefetch(va); +#if L1_CACHE_BYTES < 128 + prefetch(va + L1_CACHE_BYTES); +#endif + /* build an skb around the page buffer */ + skb = build_skb(va - I40E_SKB_PAD, truesize); + if (unlikely(!skb)) + return NULL; + + /* update pointers within the skb to store the data */ + skb_reserve(skb, I40E_SKB_PAD); + __skb_put(skb, size); + + /* buffer is used by skb, update page_offset */ +#if (PAGE_SIZE < 8192) + rx_buffer->page_offset ^= truesize; +#else + rx_buffer->page_offset += truesize; +#endif + + return skb; +} + +/** * i40e_put_rx_buffer - Clean up used buffer and either recycle or free * @rx_ring: rx descriptor ring to transact packets on * @rx_buffer: rx buffer to pull data from @@ -1182,7 +1238,8 @@ static void i40e_put_rx_buffer(struct i40e_ring *rx_ring, rx_ring->rx_stats.page_reuse_count++; } else { /* we are not reusing the buffer so unmap it */ - dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, PAGE_SIZE, + dma_unmap_page_attrs(rx_ring->dev, rx_buffer->dma, + i40e_rx_pg_size(rx_ring), DMA_FROM_DEVICE, I40E_RX_DMA_ATTR); __page_frag_cache_drain(rx_buffer->page, rx_buffer->pagecnt_bias); @@ -1283,6 +1340,8 @@ static int i40e_clean_rx_irq(struct i40e_ring *rx_ring, int budget) /* retrieve a buffer from the ring */ if (skb) i40e_add_rx_frag(rx_ring, rx_buffer, skb, size); + else if (ring_uses_build_skb(rx_ring)) + skb = i40e_build_skb(rx_ring, rx_buffer, size); else skb = i40e_construct_skb(rx_ring, rx_buffer, size); diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index 3bb4d732e467..901282c87cf6 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -106,6 +106,7 @@ enum i40e_dyn_idx_t { #define I40E_RXBUFFER_256 256 #define I40E_RXBUFFER_1536 1536 /* 128B aligned standard Ethernet frame */ #define I40E_RXBUFFER_2048 2048 +#define I40E_RXBUFFER_3072 3072 /* Used for large frames w/ padding */ #define I40E_MAX_RXBUFFER 9728 /* largest size for single descriptor */ /* NOTE: netdev_alloc_skb reserves up to 64 bytes, NET_IP_ALIGN means we @@ -121,6 +122,58 @@ enum i40e_dyn_idx_t { #define I40E_RX_DMA_ATTR \ (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING) +/* Attempt to maximize the headroom available for incoming frames. We + * use a 2K buffer for receives and need 1536/1534 to store the data for + * the frame. This leaves us with 512 bytes of room. From that we need + * to deduct the space needed for the shared info and the padding needed + * to IP align the frame. + * + * Note: For cache line sizes 256 or larger this value is going to end + * up negative. In these cases we should fall back to the legacy + * receive path. + */ +#if (PAGE_SIZE < 8192) +#define I40E_2K_TOO_SMALL_WITH_PADDING \ +((NET_SKB_PAD + I40E_RXBUFFER_1536) > SKB_WITH_OVERHEAD(I40E_RXBUFFER_2048)) + +static inline int i40e_compute_pad(int rx_buf_len) +{ + int page_size, pad_size; + + page_size = ALIGN(rx_buf_len, PAGE_SIZE / 2); + pad_size = SKB_WITH_OVERHEAD(page_size) - rx_buf_len; + + return pad_size; +} + +static inline int i40e_skb_pad(void) +{ + int rx_buf_len; + + /* If a 2K buffer cannot handle a standard Ethernet frame then + * optimize padding for a 3K buffer instead of a 1.5K buffer. + * + * For a 3K buffer we need to add enough padding to allow for + * tailroom due to NET_IP_ALIGN possibly shifting us out of + * cache-line alignment. + */ + if (I40E_2K_TOO_SMALL_WITH_PADDING) + rx_buf_len = I40E_RXBUFFER_3072 + SKB_DATA_ALIGN(NET_IP_ALIGN); + else + rx_buf_len = I40E_RXBUFFER_1536; + + /* if needed make room for NET_IP_ALIGN */ + rx_buf_len -= NET_IP_ALIGN; + + return i40e_compute_pad(rx_buf_len); +} + +#define I40E_SKB_PAD i40e_skb_pad() +#else +#define I40E_2K_TOO_SMALL_WITH_PADDING false +#define I40E_SKB_PAD (NET_SKB_PAD + NET_IP_ALIGN) +#endif + /** * i40e_test_staterr - tests bits in Rx descriptor status and error fields * @rx_desc: pointer to receive descriptor (in le64 format) @@ -327,7 +380,8 @@ struct i40e_ring { u8 packet_stride; u16 flags; -#define I40E_TXR_FLAGS_WB_ON_ITR BIT(0) +#define I40E_TXR_FLAGS_WB_ON_ITR BIT(0) +#define I40E_RXR_FLAGS_BUILD_SKB_ENABLED BIT(1) /* stats structs */ struct i40e_queue_stats stats; @@ -355,6 +409,21 @@ struct i40e_ring { */ } ____cacheline_internodealigned_in_smp; +static inline bool ring_uses_build_skb(struct i40e_ring *ring) +{ + return !!(ring->flags & I40E_RXR_FLAGS_BUILD_SKB_ENABLED); +} + +static inline void set_ring_build_skb_enabled(struct i40e_ring *ring) +{ + ring->flags |= I40E_RXR_FLAGS_BUILD_SKB_ENABLED; +} + +static inline void clear_ring_build_skb_enabled(struct i40e_ring *ring) +{ + ring->flags &= ~I40E_RXR_FLAGS_BUILD_SKB_ENABLED; +} + enum i40e_latency_range { I40E_LOWEST_LATENCY = 0, I40E_LOW_LATENCY = 1, @@ -376,6 +445,17 @@ struct i40e_ring_container { #define i40e_for_each_ring(pos, head) \ for (pos = (head).ring; pos != NULL; pos = pos->next) +static inline unsigned int i40e_rx_pg_order(struct i40e_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring->rx_buf_len > (PAGE_SIZE / 2)) + return 1; +#endif + return 0; +} + +#define i40e_rx_pg_size(_ring) (PAGE_SIZE << i40e_rx_pg_order(_ring)) + bool i40evf_alloc_rx_buffers(struct i40e_ring *rxr, u16 cleaned_count); netdev_tx_t i40evf_xmit_frame(struct sk_buff *skb, struct net_device *netdev); void i40evf_clean_tx_ring(struct i40e_ring *tx_ring); diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h index d61ecf655091..35ded19e9cc2 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf.h @@ -205,7 +205,6 @@ struct i40evf_adapter { #define I40EVF_FLAG_IN_NETPOLL BIT(4) #define I40EVF_FLAG_IMIR_ENABLED BIT(5) #define I40EVF_FLAG_MQ_CAPABLE BIT(6) -#define I40EVF_FLAG_NEED_LINK_UPDATE BIT(7) #define I40EVF_FLAG_PF_COMMS_FAILED BIT(8) #define I40EVF_FLAG_RESET_PENDING BIT(9) #define I40EVF_FLAG_RESET_NEEDED BIT(10) diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index c690aba8e8d1..12a930e879af 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -694,11 +694,18 @@ static void i40evf_configure_rx(struct i40evf_adapter *adapter) /* Legacy Rx will always default to a 2048 buffer size. */ #if (PAGE_SIZE < 8192) if (!(adapter->flags & I40EVF_FLAG_LEGACY_RX)) { + /* For jumbo frames on systems with 4K pages we have to use + * an order 1 page, so we might as well increase the size + * of our Rx buffer to make better use of the available space + */ + rx_buf_len = I40E_RXBUFFER_3072; + /* We use a 1536 buffer size for configurations with * standard Ethernet mtu. On x86 this gives us enough room * for shared info and 192 bytes of padding. */ - if (netdev->mtu <= ETH_DATA_LEN) + if (!I40E_2K_TOO_SMALL_WITH_PADDING && + (netdev->mtu <= ETH_DATA_LEN)) rx_buf_len = I40E_RXBUFFER_1536 - NET_IP_ALIGN; } #endif @@ -706,6 +713,11 @@ static void i40evf_configure_rx(struct i40evf_adapter *adapter) for (i = 0; i < adapter->num_active_queues; i++) { adapter->rx_rings[i].tail = hw->hw_addr + I40E_QRX_TAIL1(i); adapter->rx_rings[i].rx_buf_len = rx_buf_len; + + if (adapter->flags & I40EVF_FLAG_LEGACY_RX) + clear_ring_build_skb_enabled(&adapter->rx_rings[i]); + else + set_ring_build_skb_enabled(&adapter->rx_rings[i]); } } |