From: Nelson Chang Date: Sat, 17 Sep 2016 15:50:55 +0000 (+0800) Subject: net: ethernet: mediatek: add HW LRO functions of PDMA RX rings X-Git-Url: https://git.stricted.de/?a=commitdiff_plain;h=ee40681037c0e5fa0058447d7603a4fb77308bce;p=GitHub%2FLineageOS%2Fandroid_kernel_motorola_exynos9610.git net: ethernet: mediatek: add HW LRO functions of PDMA RX rings The codes add the large receive offload (LRO) functions by hardware as below: 1) PDMA has total four RX rings that one is the normal ring, and others can be configured as LRO rings. 2) Only TCP/IP RX flows can be offloaded. The hardware can set four IP addresses at most, if the destination IP of the RX flow matches one of them, it has the chance to be offloaded. 3) There three RX flows can be offloaded at most, and one flow is mapped to one RX ring. 4) If there are more than three candidate RX flows, the hardware can choose three of them by throughput comparison results. Signed-off-by: Nelson Chang Signed-off-by: David S. Miller --- diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 522fe8dda6c3..18600cbbb907 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -820,11 +820,51 @@ drop: return NETDEV_TX_OK; } +static struct mtk_rx_ring *mtk_get_rx_ring(struct mtk_eth *eth) +{ + int i; + struct mtk_rx_ring *ring; + int idx; + + if (!eth->hwlro) + return ð->rx_ring[0]; + + for (i = 0; i < MTK_MAX_RX_RING_NUM; i++) { + ring = ð->rx_ring[i]; + idx = NEXT_RX_DESP_IDX(ring->calc_idx, ring->dma_size); + if (ring->dma[idx].rxd2 & RX_DMA_DONE) { + ring->calc_idx_update = true; + return ring; + } + } + + return NULL; +} + +static void mtk_update_rx_cpu_idx(struct mtk_eth *eth) +{ + struct mtk_rx_ring *ring; + int i; + + if (!eth->hwlro) { + ring = ð->rx_ring[0]; + mtk_w32(eth, ring->calc_idx, ring->crx_idx_reg); + } else { + for (i = 0; i < MTK_MAX_RX_RING_NUM; i++) { + ring = ð->rx_ring[i]; + if (ring->calc_idx_update) { + ring->calc_idx_update = false; + mtk_w32(eth, ring->calc_idx, ring->crx_idx_reg); + } + } + } +} + static int mtk_poll_rx(struct napi_struct *napi, int budget, struct mtk_eth *eth) { - struct mtk_rx_ring *ring = ð->rx_ring; - int idx = ring->calc_idx; + struct mtk_rx_ring *ring; + int idx; struct sk_buff *skb; u8 *data, *new_data; struct mtk_rx_dma *rxd, trxd; @@ -836,7 +876,11 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, dma_addr_t dma_addr; int mac = 0; - idx = NEXT_RX_DESP_IDX(idx); + ring = mtk_get_rx_ring(eth); + if (unlikely(!ring)) + goto rx_done; + + idx = NEXT_RX_DESP_IDX(ring->calc_idx, ring->dma_size); rxd = &ring->dma[idx]; data = ring->data[idx]; @@ -907,12 +951,13 @@ release_desc: done++; } +rx_done: if (done) { /* make sure that all changes to the dma ring are flushed before * we continue */ wmb(); - mtk_w32(eth, ring->calc_idx, MTK_PRX_CRX_IDX0); + mtk_update_rx_cpu_idx(eth); } return done; @@ -1135,32 +1180,41 @@ static void mtk_tx_clean(struct mtk_eth *eth) } } -static int mtk_rx_alloc(struct mtk_eth *eth) +static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag) { - struct mtk_rx_ring *ring = ð->rx_ring; + struct mtk_rx_ring *ring = ð->rx_ring[ring_no]; + int rx_data_len, rx_dma_size; int i; - ring->frag_size = mtk_max_frag_size(ETH_DATA_LEN); + if (rx_flag == MTK_RX_FLAGS_HWLRO) { + rx_data_len = MTK_MAX_LRO_RX_LENGTH; + rx_dma_size = MTK_HW_LRO_DMA_SIZE; + } else { + rx_data_len = ETH_DATA_LEN; + rx_dma_size = MTK_DMA_SIZE; + } + + ring->frag_size = mtk_max_frag_size(rx_data_len); ring->buf_size = mtk_max_buf_size(ring->frag_size); - ring->data = kcalloc(MTK_DMA_SIZE, sizeof(*ring->data), + ring->data = kcalloc(rx_dma_size, sizeof(*ring->data), GFP_KERNEL); if (!ring->data) return -ENOMEM; - for (i = 0; i < MTK_DMA_SIZE; i++) { + for (i = 0; i < rx_dma_size; i++) { ring->data[i] = netdev_alloc_frag(ring->frag_size); if (!ring->data[i]) return -ENOMEM; } ring->dma = dma_alloc_coherent(eth->dev, - MTK_DMA_SIZE * sizeof(*ring->dma), + rx_dma_size * sizeof(*ring->dma), &ring->phys, GFP_ATOMIC | __GFP_ZERO); if (!ring->dma) return -ENOMEM; - for (i = 0; i < MTK_DMA_SIZE; i++) { + for (i = 0; i < rx_dma_size; i++) { dma_addr_t dma_addr = dma_map_single(eth->dev, ring->data[i] + NET_SKB_PAD, ring->buf_size, @@ -1171,27 +1225,30 @@ static int mtk_rx_alloc(struct mtk_eth *eth) ring->dma[i].rxd2 = RX_DMA_PLEN0(ring->buf_size); } - ring->calc_idx = MTK_DMA_SIZE - 1; + ring->dma_size = rx_dma_size; + ring->calc_idx_update = false; + ring->calc_idx = rx_dma_size - 1; + ring->crx_idx_reg = MTK_PRX_CRX_IDX_CFG(ring_no); /* make sure that all changes to the dma ring are flushed before we * continue */ wmb(); - mtk_w32(eth, eth->rx_ring.phys, MTK_PRX_BASE_PTR0); - mtk_w32(eth, MTK_DMA_SIZE, MTK_PRX_MAX_CNT0); - mtk_w32(eth, eth->rx_ring.calc_idx, MTK_PRX_CRX_IDX0); - mtk_w32(eth, MTK_PST_DRX_IDX0, MTK_PDMA_RST_IDX); + mtk_w32(eth, ring->phys, MTK_PRX_BASE_PTR_CFG(ring_no)); + mtk_w32(eth, rx_dma_size, MTK_PRX_MAX_CNT_CFG(ring_no)); + mtk_w32(eth, ring->calc_idx, ring->crx_idx_reg); + mtk_w32(eth, MTK_PST_DRX_IDX_CFG(ring_no), MTK_PDMA_RST_IDX); return 0; } -static void mtk_rx_clean(struct mtk_eth *eth) +static void mtk_rx_clean(struct mtk_eth *eth, int ring_no) { - struct mtk_rx_ring *ring = ð->rx_ring; + struct mtk_rx_ring *ring = ð->rx_ring[ring_no]; int i; if (ring->data && ring->dma) { - for (i = 0; i < MTK_DMA_SIZE; i++) { + for (i = 0; i < ring->dma_size; i++) { if (!ring->data[i]) continue; if (!ring->dma[i].rxd1) @@ -1208,13 +1265,98 @@ static void mtk_rx_clean(struct mtk_eth *eth) if (ring->dma) { dma_free_coherent(eth->dev, - MTK_DMA_SIZE * sizeof(*ring->dma), + ring->dma_size * sizeof(*ring->dma), ring->dma, ring->phys); ring->dma = NULL; } } +static int mtk_hwlro_rx_init(struct mtk_eth *eth) +{ + int i; + u32 ring_ctrl_dw1 = 0, ring_ctrl_dw2 = 0, ring_ctrl_dw3 = 0; + u32 lro_ctrl_dw0 = 0, lro_ctrl_dw3 = 0; + + /* set LRO rings to auto-learn modes */ + ring_ctrl_dw2 |= MTK_RING_AUTO_LERAN_MODE; + + /* validate LRO ring */ + ring_ctrl_dw2 |= MTK_RING_VLD; + + /* set AGE timer (unit: 20us) */ + ring_ctrl_dw2 |= MTK_RING_AGE_TIME_H; + ring_ctrl_dw1 |= MTK_RING_AGE_TIME_L; + + /* set max AGG timer (unit: 20us) */ + ring_ctrl_dw2 |= MTK_RING_MAX_AGG_TIME; + + /* set max LRO AGG count */ + ring_ctrl_dw2 |= MTK_RING_MAX_AGG_CNT_L; + ring_ctrl_dw3 |= MTK_RING_MAX_AGG_CNT_H; + + for (i = 1; i < MTK_MAX_RX_RING_NUM; i++) { + mtk_w32(eth, ring_ctrl_dw1, MTK_LRO_CTRL_DW1_CFG(i)); + mtk_w32(eth, ring_ctrl_dw2, MTK_LRO_CTRL_DW2_CFG(i)); + mtk_w32(eth, ring_ctrl_dw3, MTK_LRO_CTRL_DW3_CFG(i)); + } + + /* IPv4 checksum update enable */ + lro_ctrl_dw0 |= MTK_L3_CKS_UPD_EN; + + /* switch priority comparison to packet count mode */ + lro_ctrl_dw0 |= MTK_LRO_ALT_PKT_CNT_MODE; + + /* bandwidth threshold setting */ + mtk_w32(eth, MTK_HW_LRO_BW_THRE, MTK_PDMA_LRO_CTRL_DW2); + + /* auto-learn score delta setting */ + mtk_w32(eth, MTK_HW_LRO_REPLACE_DELTA, MTK_PDMA_LRO_ALT_SCORE_DELTA); + + /* set refresh timer for altering flows to 1 sec. (unit: 20us) */ + mtk_w32(eth, (MTK_HW_LRO_TIMER_UNIT << 16) | MTK_HW_LRO_REFRESH_TIME, + MTK_PDMA_LRO_ALT_REFRESH_TIMER); + + /* set HW LRO mode & the max aggregation count for rx packets */ + lro_ctrl_dw3 |= MTK_ADMA_MODE | (MTK_HW_LRO_MAX_AGG_CNT & 0xff); + + /* the minimal remaining room of SDL0 in RXD for lro aggregation */ + lro_ctrl_dw3 |= MTK_LRO_MIN_RXD_SDL; + + /* enable HW LRO */ + lro_ctrl_dw0 |= MTK_LRO_EN; + + mtk_w32(eth, lro_ctrl_dw3, MTK_PDMA_LRO_CTRL_DW3); + mtk_w32(eth, lro_ctrl_dw0, MTK_PDMA_LRO_CTRL_DW0); + + return 0; +} + +static void mtk_hwlro_rx_uninit(struct mtk_eth *eth) +{ + int i; + u32 val; + + /* relinquish lro rings, flush aggregated packets */ + mtk_w32(eth, MTK_LRO_RING_RELINQUISH_REQ, MTK_PDMA_LRO_CTRL_DW0); + + /* wait for relinquishments done */ + for (i = 0; i < 10; i++) { + val = mtk_r32(eth, MTK_PDMA_LRO_CTRL_DW0); + if (val & MTK_LRO_RING_RELINQUISH_DONE) { + msleep(20); + continue; + } + } + + /* invalidate lro rings */ + for (i = 1; i < MTK_MAX_RX_RING_NUM; i++) + mtk_w32(eth, 0, MTK_LRO_CTRL_DW2_CFG(i)); + + /* disable HW LRO */ + mtk_w32(eth, 0, MTK_PDMA_LRO_CTRL_DW0); +} + /* wait for DMA to finish whatever it is doing before we start using it again */ static int mtk_dma_busy_wait(struct mtk_eth *eth) { @@ -1235,6 +1377,7 @@ static int mtk_dma_busy_wait(struct mtk_eth *eth) static int mtk_dma_init(struct mtk_eth *eth) { int err; + u32 i; if (mtk_dma_busy_wait(eth)) return -EBUSY; @@ -1250,10 +1393,21 @@ static int mtk_dma_init(struct mtk_eth *eth) if (err) return err; - err = mtk_rx_alloc(eth); + err = mtk_rx_alloc(eth, 0, MTK_RX_FLAGS_NORMAL); if (err) return err; + if (eth->hwlro) { + for (i = 1; i < MTK_MAX_RX_RING_NUM; i++) { + err = mtk_rx_alloc(eth, i, MTK_RX_FLAGS_HWLRO); + if (err) + return err; + } + err = mtk_hwlro_rx_init(eth); + if (err) + return err; + } + /* Enable random early drop and set drop threshold automatically */ mtk_w32(eth, FC_THRES_DROP_MODE | FC_THRES_DROP_EN | FC_THRES_MIN, MTK_QDMA_FC_THRES); @@ -1278,7 +1432,14 @@ static void mtk_dma_free(struct mtk_eth *eth) eth->phy_scratch_ring = 0; } mtk_tx_clean(eth); - mtk_rx_clean(eth); + mtk_rx_clean(eth, 0); + + if (eth->hwlro) { + mtk_hwlro_rx_uninit(eth); + for (i = 1; i < MTK_MAX_RX_RING_NUM; i++) + mtk_rx_clean(eth, i); + } + kfree(eth->scratch_head); } @@ -1873,6 +2034,9 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) mac->hw = eth; mac->of_node = np; + memset(mac->hwlro_ip, 0, sizeof(mac->hwlro_ip)); + mac->hwlro_ip_cnt = 0; + mac->hw_stats = devm_kzalloc(eth->dev, sizeof(*mac->hw_stats), GFP_KERNEL); @@ -1889,6 +2053,11 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) eth->netdev[id]->watchdog_timeo = 5 * HZ; eth->netdev[id]->netdev_ops = &mtk_netdev_ops; eth->netdev[id]->base_addr = (unsigned long)eth->base; + + eth->netdev[id]->hw_features = MTK_HW_FEATURES; + if (eth->hwlro) + eth->netdev[id]->hw_features |= NETIF_F_LRO; + eth->netdev[id]->vlan_features = MTK_HW_FEATURES & ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX); eth->netdev[id]->features |= MTK_HW_FEATURES; @@ -1941,6 +2110,8 @@ static int mtk_probe(struct platform_device *pdev) return PTR_ERR(eth->pctl); } + eth->hwlro = of_property_read_bool(pdev->dev.of_node, "mediatek,hwlro"); + for (i = 0; i < 3; i++) { eth->irq[i] = platform_get_irq(pdev, i); if (eth->irq[i] < 0) { diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index 79954b419b53..7c5e534d2120 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -39,7 +39,21 @@ NETIF_F_SG | NETIF_F_TSO | \ NETIF_F_TSO6 | \ NETIF_F_IPV6_CSUM) -#define NEXT_RX_DESP_IDX(X) (((X) + 1) & (MTK_DMA_SIZE - 1)) +#define NEXT_RX_DESP_IDX(X, Y) (((X) + 1) & ((Y) - 1)) + +#define MTK_MAX_RX_RING_NUM 4 +#define MTK_HW_LRO_DMA_SIZE 8 + +#define MTK_MAX_LRO_RX_LENGTH (4096 * 3) +#define MTK_MAX_LRO_IP_CNT 2 +#define MTK_HW_LRO_TIMER_UNIT 1 /* 20 us */ +#define MTK_HW_LRO_REFRESH_TIME 50000 /* 1 sec. */ +#define MTK_HW_LRO_AGG_TIME 10 /* 200us */ +#define MTK_HW_LRO_AGE_TIME 50 /* 1ms */ +#define MTK_HW_LRO_MAX_AGG_CNT 64 +#define MTK_HW_LRO_BW_THRE 3000 +#define MTK_HW_LRO_REPLACE_DELTA 1000 +#define MTK_HW_LRO_SDL_REMAIN_ROOM 1522 /* Frame Engine Global Reset Register */ #define MTK_RST_GL 0x04 @@ -50,6 +64,9 @@ #define MTK_GDM1_AF BIT(28) #define MTK_GDM2_AF BIT(29) +/* PDMA HW LRO Alter Flow Timer Register */ +#define MTK_PDMA_LRO_ALT_REFRESH_TIMER 0x1c + /* Frame Engine Interrupt Grouping Register */ #define MTK_FE_INT_GRP 0x20 @@ -70,12 +87,29 @@ /* PDMA RX Base Pointer Register */ #define MTK_PRX_BASE_PTR0 0x900 +#define MTK_PRX_BASE_PTR_CFG(x) (MTK_PRX_BASE_PTR0 + (x * 0x10)) /* PDMA RX Maximum Count Register */ #define MTK_PRX_MAX_CNT0 0x904 +#define MTK_PRX_MAX_CNT_CFG(x) (MTK_PRX_MAX_CNT0 + (x * 0x10)) /* PDMA RX CPU Pointer Register */ #define MTK_PRX_CRX_IDX0 0x908 +#define MTK_PRX_CRX_IDX_CFG(x) (MTK_PRX_CRX_IDX0 + (x * 0x10)) + +/* PDMA HW LRO Control Registers */ +#define MTK_PDMA_LRO_CTRL_DW0 0x980 +#define MTK_LRO_EN BIT(0) +#define MTK_L3_CKS_UPD_EN BIT(7) +#define MTK_LRO_ALT_PKT_CNT_MODE BIT(21) +#define MTK_LRO_RING_RELINQUISH_REQ (0x3 << 26) +#define MTK_LRO_RING_RELINQUISH_DONE (0x3 << 29) + +#define MTK_PDMA_LRO_CTRL_DW1 0x984 +#define MTK_PDMA_LRO_CTRL_DW2 0x988 +#define MTK_PDMA_LRO_CTRL_DW3 0x98c +#define MTK_ADMA_MODE BIT(15) +#define MTK_LRO_MIN_RXD_SDL (MTK_HW_LRO_SDL_REMAIN_ROOM << 16) /* PDMA Global Configuration Register */ #define MTK_PDMA_GLO_CFG 0xa04 @@ -84,6 +118,7 @@ /* PDMA Reset Index Register */ #define MTK_PDMA_RST_IDX 0xa08 #define MTK_PST_DRX_IDX0 BIT(16) +#define MTK_PST_DRX_IDX_CFG(x) (MTK_PST_DRX_IDX0 << (x)) /* PDMA Delay Interrupt Register */ #define MTK_PDMA_DELAY_INT 0xa0c @@ -94,10 +129,33 @@ /* PDMA Interrupt Mask Register */ #define MTK_PDMA_INT_MASK 0xa28 +/* PDMA HW LRO Alter Flow Delta Register */ +#define MTK_PDMA_LRO_ALT_SCORE_DELTA 0xa4c + /* PDMA Interrupt grouping registers */ #define MTK_PDMA_INT_GRP1 0xa50 #define MTK_PDMA_INT_GRP2 0xa54 +/* PDMA HW LRO IP Setting Registers */ +#define MTK_LRO_RX_RING0_DIP_DW0 0xb04 +#define MTK_LRO_DIP_DW0_CFG(x) (MTK_LRO_RX_RING0_DIP_DW0 + (x * 0x40)) +#define MTK_RING_MYIP_VLD BIT(9) + +/* PDMA HW LRO Ring Control Registers */ +#define MTK_LRO_RX_RING0_CTRL_DW1 0xb28 +#define MTK_LRO_RX_RING0_CTRL_DW2 0xb2c +#define MTK_LRO_RX_RING0_CTRL_DW3 0xb30 +#define MTK_LRO_CTRL_DW1_CFG(x) (MTK_LRO_RX_RING0_CTRL_DW1 + (x * 0x40)) +#define MTK_LRO_CTRL_DW2_CFG(x) (MTK_LRO_RX_RING0_CTRL_DW2 + (x * 0x40)) +#define MTK_LRO_CTRL_DW3_CFG(x) (MTK_LRO_RX_RING0_CTRL_DW3 + (x * 0x40)) +#define MTK_RING_AGE_TIME_L ((MTK_HW_LRO_AGE_TIME & 0x3ff) << 22) +#define MTK_RING_AGE_TIME_H ((MTK_HW_LRO_AGE_TIME >> 10) & 0x3f) +#define MTK_RING_AUTO_LERAN_MODE (3 << 6) +#define MTK_RING_VLD BIT(8) +#define MTK_RING_MAX_AGG_TIME ((MTK_HW_LRO_AGG_TIME & 0xffff) << 10) +#define MTK_RING_MAX_AGG_CNT_L ((MTK_HW_LRO_MAX_AGG_CNT & 0x3f) << 26) +#define MTK_RING_MAX_AGG_CNT_H ((MTK_HW_LRO_MAX_AGG_CNT >> 6) & 0x3) + /* QDMA TX Queue Configuration Registers */ #define MTK_QTX_CFG(x) (0x1800 + (x * 0x10)) #define QDMA_RES_THRES 4 @@ -132,7 +190,6 @@ /* QDMA Reset Index Register */ #define MTK_QDMA_RST_IDX 0x1A08 -#define MTK_PST_DRX_IDX0 BIT(16) /* QDMA Delay Interrupt Register */ #define MTK_QDMA_DELAY_INT 0x1A0C @@ -377,6 +434,12 @@ struct mtk_tx_ring { atomic_t free_count; }; +/* PDMA rx ring mode */ +enum mtk_rx_flags { + MTK_RX_FLAGS_NORMAL = 0, + MTK_RX_FLAGS_HWLRO, +}; + /* struct mtk_rx_ring - This struct holds info describing a RX ring * @dma: The descriptor ring * @data: The memory pointed at by the ring @@ -391,7 +454,10 @@ struct mtk_rx_ring { dma_addr_t phys; u16 frag_size; u16 buf_size; + u16 dma_size; + bool calc_idx_update; u16 calc_idx; + u32 crx_idx_reg; }; /* currently no SoC has more than 2 macs */ @@ -439,9 +505,10 @@ struct mtk_eth { unsigned long sysclk; struct regmap *ethsys; struct regmap *pctl; + bool hwlro; atomic_t dma_refcnt; struct mtk_tx_ring tx_ring; - struct mtk_rx_ring rx_ring; + struct mtk_rx_ring rx_ring[MTK_MAX_RX_RING_NUM]; struct napi_struct tx_napi; struct napi_struct rx_napi; struct mtk_tx_dma *scratch_ring; @@ -470,6 +537,8 @@ struct mtk_mac { struct mtk_eth *hw; struct mtk_hw_stats *hw_stats; struct phy_device *phy_dev; + __be32 hwlro_ip[MTK_MAX_LRO_IP_CNT]; + int hwlro_ip_cnt; }; /* the struct describing the SoC. these are declared in the soc_xyz.c files */