diff --git a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c index 8ad162c16f618c6a87142643301b6dc10e6334cf..92d2208d13c7edd78265e6f4b1a42a5e90bec5fc 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_fcoe.c +++ b/drivers/net/ethernet/intel/i40e/i40e_fcoe.c @@ -1371,7 +1371,7 @@ static netdev_tx_t i40e_fcoe_xmit_frame(struct sk_buff *skb, if (i40e_chk_linearize(skb, count)) { if (__skb_linearize(skb)) goto out_drop; - count = TXD_USE_COUNT(skb->len); + count = i40e_txd_use_count(skb->len); tx_ring->tx_stats.tx_linearize++; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 084d0ab316b796b5d5af2ab87b7a5bee193b5a84..9af1411bd4237785e510d8d95e7971c107e1719a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2717,6 +2717,8 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, tx_bi = first; for (frag = &skb_shinfo(skb)->frags[0];; frag++) { + unsigned int max_data = I40E_MAX_DATA_PER_TXD_ALIGNED; + if (dma_mapping_error(tx_ring->dev, dma)) goto dma_error; @@ -2724,12 +2726,14 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, dma_unmap_len_set(tx_bi, len, size); dma_unmap_addr_set(tx_bi, dma, dma); + /* align size to end of page */ + max_data += -dma & (I40E_MAX_READ_REQ_SIZE - 1); tx_desc->buffer_addr = cpu_to_le64(dma); while (unlikely(size > I40E_MAX_DATA_PER_TXD)) { tx_desc->cmd_type_offset_bsz = build_ctob(td_cmd, td_offset, - I40E_MAX_DATA_PER_TXD, td_tag); + max_data, td_tag); tx_desc++; i++; @@ -2740,9 +2744,10 @@ static inline void i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, i = 0; } - dma += I40E_MAX_DATA_PER_TXD; - size -= I40E_MAX_DATA_PER_TXD; + dma += max_data; + size -= max_data; + max_data = I40E_MAX_DATA_PER_TXD_ALIGNED; tx_desc->buffer_addr = cpu_to_le64(dma); } @@ -2892,7 +2897,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, if (i40e_chk_linearize(skb, count)) { if (__skb_linearize(skb)) goto out_drop; - count = TXD_USE_COUNT(skb->len); + count = i40e_txd_use_count(skb->len); tx_ring->tx_stats.tx_linearize++; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index cdd5dc00aec519972dd3af6166666a0d3c65766f..9e654e611642a77e46077408bfc243e959477084 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -146,10 +146,39 @@ enum i40e_dyn_idx_t { #define I40E_MAX_BUFFER_TXD 8 #define I40E_MIN_TX_LEN 17 -#define I40E_MAX_DATA_PER_TXD 8192 + +/* The size limit for a transmit buffer in a descriptor is (16K - 1). + * In order to align with the read requests we will align the value to + * the nearest 4K which represents our maximum read request size. + */ +#define I40E_MAX_READ_REQ_SIZE 4096 +#define I40E_MAX_DATA_PER_TXD (16 * 1024 - 1) +#define I40E_MAX_DATA_PER_TXD_ALIGNED \ + (I40E_MAX_DATA_PER_TXD & ~(I40E_MAX_READ_REQ_SIZE - 1)) + +/* This ugly bit of math is equivalent to DIV_ROUNDUP(size, X) where X is + * the value I40E_MAX_DATA_PER_TXD_ALIGNED. It is needed due to the fact + * that 12K is not a power of 2 and division is expensive. It is used to + * approximate the number of descriptors used per linear buffer. Note + * that this will overestimate in some cases as it doesn't account for the + * fact that we will add up to 4K - 1 in aligning the 12K buffer, however + * the error should not impact things much as large buffers usually mean + * we will use fewer descriptors then there are frags in an skb. + */ +static inline unsigned int i40e_txd_use_count(unsigned int size) +{ + const unsigned int max = I40E_MAX_DATA_PER_TXD_ALIGNED; + const unsigned int reciprocal = ((1ull << 32) - 1 + (max / 2)) / max; + unsigned int adjust = ~(u32)0; + + /* if we rounded up on the reciprocal pull down the adjustment */ + if ((max * reciprocal) > adjust) + adjust = ~(u32)(reciprocal - 1); + + return (u32)((((u64)size * reciprocal) + adjust) >> 32); +} /* Tx Descriptors needed, worst case */ -#define TXD_USE_COUNT(S) DIV_ROUND_UP((S), I40E_MAX_DATA_PER_TXD) #define DESC_NEEDED (MAX_SKB_FRAGS + 4) #define I40E_MIN_DESC_PENDING 4 @@ -377,7 +406,7 @@ static inline int i40e_xmit_descriptor_count(struct sk_buff *skb) int count = 0, size = skb_headlen(skb); for (;;) { - count += TXD_USE_COUNT(size); + count += i40e_txd_use_count(size); if (!nr_frags--) break; diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index ebcc25c05796d7d42372395ba9f8d3bf838d547a..5f9c1bbab1fa44efd8265dbd6b5cd50efa5c7942 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -1936,6 +1936,8 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, tx_bi = first; for (frag = &skb_shinfo(skb)->frags[0];; frag++) { + unsigned int max_data = I40E_MAX_DATA_PER_TXD_ALIGNED; + if (dma_mapping_error(tx_ring->dev, dma)) goto dma_error; @@ -1943,12 +1945,14 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, dma_unmap_len_set(tx_bi, len, size); dma_unmap_addr_set(tx_bi, dma, dma); + /* align size to end of page */ + max_data += -dma & (I40E_MAX_READ_REQ_SIZE - 1); tx_desc->buffer_addr = cpu_to_le64(dma); while (unlikely(size > I40E_MAX_DATA_PER_TXD)) { tx_desc->cmd_type_offset_bsz = build_ctob(td_cmd, td_offset, - I40E_MAX_DATA_PER_TXD, td_tag); + max_data, td_tag); tx_desc++; i++; @@ -1959,9 +1963,10 @@ static inline void i40evf_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, i = 0; } - dma += I40E_MAX_DATA_PER_TXD; - size -= I40E_MAX_DATA_PER_TXD; + dma += max_data; + size -= max_data; + max_data = I40E_MAX_DATA_PER_TXD_ALIGNED; tx_desc->buffer_addr = cpu_to_le64(dma); } @@ -2110,7 +2115,7 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, if (i40e_chk_linearize(skb, count)) { if (__skb_linearize(skb)) goto out_drop; - count = TXD_USE_COUNT(skb->len); + count = i40e_txd_use_count(skb->len); tx_ring->tx_stats.tx_linearize++; } diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index c1dd8c5c966697bc79ae47babbab8a598d20ef18..3ec0ea5ea3db904b2a6438a49faa08564499e3f2 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -146,10 +146,39 @@ enum i40e_dyn_idx_t { #define I40E_MAX_BUFFER_TXD 8 #define I40E_MIN_TX_LEN 17 -#define I40E_MAX_DATA_PER_TXD 8192 + +/* The size limit for a transmit buffer in a descriptor is (16K - 1). + * In order to align with the read requests we will align the value to + * the nearest 4K which represents our maximum read request size. + */ +#define I40E_MAX_READ_REQ_SIZE 4096 +#define I40E_MAX_DATA_PER_TXD (16 * 1024 - 1) +#define I40E_MAX_DATA_PER_TXD_ALIGNED \ + (I40E_MAX_DATA_PER_TXD & ~(I40E_MAX_READ_REQ_SIZE - 1)) + +/* This ugly bit of math is equivalent to DIV_ROUNDUP(size, X) where X is + * the value I40E_MAX_DATA_PER_TXD_ALIGNED. It is needed due to the fact + * that 12K is not a power of 2 and division is expensive. It is used to + * approximate the number of descriptors used per linear buffer. Note + * that this will overestimate in some cases as it doesn't account for the + * fact that we will add up to 4K - 1 in aligning the 12K buffer, however + * the error should not impact things much as large buffers usually mean + * we will use fewer descriptors then there are frags in an skb. + */ +static inline unsigned int i40e_txd_use_count(unsigned int size) +{ + const unsigned int max = I40E_MAX_DATA_PER_TXD_ALIGNED; + const unsigned int reciprocal = ((1ull << 32) - 1 + (max / 2)) / max; + unsigned int adjust = ~(u32)0; + + /* if we rounded up on the reciprocal pull down the adjustment */ + if ((max * reciprocal) > adjust) + adjust = ~(u32)(reciprocal - 1); + + return (u32)((((u64)size * reciprocal) + adjust) >> 32); +} /* Tx Descriptors needed, worst case */ -#define TXD_USE_COUNT(S) DIV_ROUND_UP((S), I40E_MAX_DATA_PER_TXD) #define DESC_NEEDED (MAX_SKB_FRAGS + 4) #define I40E_MIN_DESC_PENDING 4 @@ -359,7 +388,7 @@ static inline int i40e_xmit_descriptor_count(struct sk_buff *skb) int count = 0, size = skb_headlen(skb); for (;;) { - count += TXD_USE_COUNT(size); + count += i40e_txd_use_count(size); if (!nr_frags--) break;