diff options
author | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-08-07 13:18:06 +0000 |
---|---|---|
committer | Daniel Baumann <daniel.baumann@progress-linux.org> | 2024-08-07 13:18:06 +0000 |
commit | 638a9e433ecd61e64761352dbec1fa4f5874c941 (patch) | |
tree | fdbff74a238d7a5a7d1cef071b7230bc064b9f25 /drivers/net/ethernet/ti | |
parent | Releasing progress-linux version 6.9.12-1~progress7.99u1. (diff) | |
download | linux-638a9e433ecd61e64761352dbec1fa4f5874c941.tar.xz linux-638a9e433ecd61e64761352dbec1fa4f5874c941.zip |
Merging upstream version 6.10.3.
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to '')
20 files changed, 3600 insertions, 1362 deletions
diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig index 1530d13984..1729eb0e0b 100644 --- a/drivers/net/ethernet/ti/Kconfig +++ b/drivers/net/ethernet/ti/Kconfig @@ -167,7 +167,7 @@ config TI_KEYSTONE_NETCP_ETHSS config TLAN tristate "TI ThunderLAN support" - depends on (PCI || EISA) + depends on (PCI || EISA) && HAS_IOPORT help If you have a PCI Ethernet network card based on the ThunderLAN chip which is supported by this driver, say Y here. @@ -198,6 +198,21 @@ config TI_ICSSG_PRUETH to support the Ethernet operation. Currently, it supports Ethernet with 1G and 100M link speed. +config TI_ICSSG_PRUETH_SR1 + tristate "TI Gigabit PRU SR1.0 Ethernet driver" + select PHYLIB + select TI_ICSS_IEP + select TI_K3_CPPI_DESC_POOL + depends on PRU_REMOTEPROC + depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER + help + Support dual Gigabit Ethernet ports over the ICSSG PRU Subsystem. + This subsystem is available on the AM65 SR1.0 platform. + + This driver requires firmware binaries which will run on the PRUs + to support the Ethernet operation. Currently, it supports Ethernet + with 1G, 100M and 10M link speed. + config TI_ICSS_IEP tristate "TI PRU ICSS IEP driver" depends on PTP_1588_CLOCK_OPTIONAL diff --git a/drivers/net/ethernet/ti/Makefile b/drivers/net/ethernet/ti/Makefile index d8590304f3..6e086b4c03 100644 --- a/drivers/net/ethernet/ti/Makefile +++ b/drivers/net/ethernet/ti/Makefile @@ -33,10 +33,19 @@ obj-$(CONFIG_TI_K3_AM65_CPTS) += am65-cpts.o obj-$(CONFIG_TI_ICSSG_PRUETH) += icssg-prueth.o icssg-prueth-y := icssg/icssg_prueth.o \ + icssg/icssg_common.o \ icssg/icssg_classifier.o \ icssg/icssg_queues.o \ icssg/icssg_config.o \ icssg/icssg_mii_cfg.o \ icssg/icssg_stats.o \ icssg/icssg_ethtool.o +obj-$(CONFIG_TI_ICSSG_PRUETH_SR1) += icssg-prueth-sr1.o +icssg-prueth-sr1-y := icssg/icssg_prueth_sr1.o \ + icssg/icssg_common.o \ + icssg/icssg_classifier.o \ + icssg/icssg_config.o \ + icssg/icssg_mii_cfg.o \ + icssg/icssg_stats.o \ + icssg/icssg_ethtool.o obj-$(CONFIG_TI_ICSS_IEP) += icssg/icss_iep.o diff --git a/drivers/net/ethernet/ti/am65-cpsw-ethtool.c b/drivers/net/ethernet/ti/am65-cpsw-ethtool.c index d6ce2c9f0a..a1d0935d1e 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-ethtool.c +++ b/drivers/net/ethernet/ti/am65-cpsw-ethtool.c @@ -695,6 +695,17 @@ static int am65_cpsw_get_ethtool_ts_info(struct net_device *ndev, struct ethtool_ts_info *info) { struct am65_cpsw_common *common = am65_ndev_to_common(ndev); + unsigned int ptp_v2_filter; + + ptp_v2_filter = BIT(HWTSTAMP_FILTER_PTP_V2_L4_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_L4_SYNC) | + BIT(HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ) | + BIT(HWTSTAMP_FILTER_PTP_V2_L2_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_L2_SYNC) | + BIT(HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) | + BIT(HWTSTAMP_FILTER_PTP_V2_EVENT) | + BIT(HWTSTAMP_FILTER_PTP_V2_SYNC) | + BIT(HWTSTAMP_FILTER_PTP_V2_DELAY_REQ); if (!IS_ENABLED(CONFIG_TI_K3_AM65_CPTS)) return ethtool_op_get_ts_info(ndev, info); @@ -708,7 +719,7 @@ static int am65_cpsw_get_ethtool_ts_info(struct net_device *ndev, SOF_TIMESTAMPING_RAW_HARDWARE; info->phc_index = am65_cpts_phc_index(common->cpts); info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON); - info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL); + info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | ptp_v2_filter; return 0; } diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c index 1d00e21808..4e50b37928 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c @@ -5,6 +5,7 @@ * */ +#include <linux/bpf_trace.h> #include <linux/clk.h> #include <linux/etherdevice.h> #include <linux/if_vlan.h> @@ -30,6 +31,7 @@ #include <linux/sys_soc.h> #include <linux/dma/ti-cppi5.h> #include <linux/dma/k3-udma-glue.h> +#include <net/page_pool/helpers.h> #include <net/switchdev.h> #include "cpsw_ale.h" @@ -101,6 +103,12 @@ #define AM65_CPSW_PN_TS_CTL_TX_HOST_TS_EN BIT(11) #define AM65_CPSW_PN_TS_CTL_MSG_TYPE_EN_SHIFT 16 +#define AM65_CPSW_PN_TS_CTL_RX_ANX_F_EN BIT(0) +#define AM65_CPSW_PN_TS_CTL_RX_VLAN_LT1_EN BIT(1) +#define AM65_CPSW_PN_TS_CTL_RX_VLAN_LT2_EN BIT(2) +#define AM65_CPSW_PN_TS_CTL_RX_ANX_D_EN BIT(3) +#define AM65_CPSW_PN_TS_CTL_RX_ANX_E_EN BIT(9) + /* AM65_CPSW_PORTN_REG_TS_SEQ_LTYPE_REG register fields */ #define AM65_CPSW_PN_TS_SEQ_ID_OFFSET_SHIFT 16 @@ -124,6 +132,11 @@ AM65_CPSW_PN_TS_CTL_TX_ANX_E_EN | \ AM65_CPSW_PN_TS_CTL_TX_ANX_F_EN) +#define AM65_CPSW_TS_RX_ANX_ALL_EN \ + (AM65_CPSW_PN_TS_CTL_RX_ANX_D_EN | \ + AM65_CPSW_PN_TS_CTL_RX_ANX_E_EN | \ + AM65_CPSW_PN_TS_CTL_RX_ANX_F_EN) + #define AM65_CPSW_ALE_AGEOUT_DEFAULT 30 /* Number of TX/RX descriptors */ #define AM65_CPSW_MAX_TX_DESC 500 @@ -138,6 +151,18 @@ #define AM65_CPSW_DEFAULT_TX_CHNS 8 +/* CPPI streaming packet interface */ +#define AM65_CPSW_CPPI_TX_FLOW_ID 0x3FFF +#define AM65_CPSW_CPPI_TX_PKT_TYPE 0x7 + +/* XDP */ +#define AM65_CPSW_XDP_CONSUMED 2 +#define AM65_CPSW_XDP_REDIRECT 1 +#define AM65_CPSW_XDP_PASS 0 + +/* Include headroom compatible with both skb and xdpf */ +#define AM65_CPSW_HEADROOM (max(NET_SKB_PAD, XDP_PACKET_HEADROOM) + NET_IP_ALIGN) + static void am65_cpsw_port_set_sl_mac(struct am65_cpsw_port *slave, const u8 *dev_addr) { @@ -305,12 +330,11 @@ static void am65_cpsw_nuss_ndo_host_tx_timeout(struct net_device *ndev, } static int am65_cpsw_nuss_rx_push(struct am65_cpsw_common *common, - struct sk_buff *skb) + struct page *page) { struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns; struct cppi5_host_desc_t *desc_rx; struct device *dev = common->dev; - u32 pkt_len = skb_tailroom(skb); dma_addr_t desc_dma; dma_addr_t buf_dma; void *swdata; @@ -322,20 +346,22 @@ static int am65_cpsw_nuss_rx_push(struct am65_cpsw_common *common, } desc_dma = k3_cppi_desc_pool_virt2dma(rx_chn->desc_pool, desc_rx); - buf_dma = dma_map_single(rx_chn->dma_dev, skb->data, pkt_len, - DMA_FROM_DEVICE); + buf_dma = dma_map_single(rx_chn->dma_dev, + page_address(page) + AM65_CPSW_HEADROOM, + AM65_CPSW_MAX_PACKET_SIZE, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(rx_chn->dma_dev, buf_dma))) { k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); - dev_err(dev, "Failed to map rx skb buffer\n"); + dev_err(dev, "Failed to map rx buffer\n"); return -EINVAL; } cppi5_hdesc_init(desc_rx, CPPI5_INFO0_HDESC_EPIB_PRESENT, AM65_CPSW_NAV_PS_DATA_SIZE); k3_udma_glue_rx_dma_to_cppi5_addr(rx_chn->rx_chn, &buf_dma); - cppi5_hdesc_attach_buf(desc_rx, buf_dma, skb_tailroom(skb), buf_dma, skb_tailroom(skb)); + cppi5_hdesc_attach_buf(desc_rx, buf_dma, AM65_CPSW_MAX_PACKET_SIZE, + buf_dma, AM65_CPSW_MAX_PACKET_SIZE); swdata = cppi5_hdesc_get_swdata(desc_rx); - *((void **)swdata) = skb; + *((void **)swdata) = page_address(page); return k3_udma_glue_push_rx_chn(rx_chn->rx_chn, 0, desc_rx, desc_dma); } @@ -369,25 +395,137 @@ static void am65_cpsw_init_host_port_emac(struct am65_cpsw_common *common); static void am65_cpsw_init_port_switch_ale(struct am65_cpsw_port *port); static void am65_cpsw_init_port_emac_ale(struct am65_cpsw_port *port); +static void am65_cpsw_destroy_xdp_rxqs(struct am65_cpsw_common *common) +{ + struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns; + struct xdp_rxq_info *rxq; + int i; + + for (i = 0; i < common->port_num; i++) { + if (!common->ports[i].ndev) + continue; + + rxq = &common->ports[i].xdp_rxq; + + if (xdp_rxq_info_is_reg(rxq)) + xdp_rxq_info_unreg(rxq); + } + + if (rx_chn->page_pool) { + page_pool_destroy(rx_chn->page_pool); + rx_chn->page_pool = NULL; + } +} + +static int am65_cpsw_create_xdp_rxqs(struct am65_cpsw_common *common) +{ + struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns; + struct page_pool_params pp_params = { + .flags = PP_FLAG_DMA_MAP, + .order = 0, + .pool_size = AM65_CPSW_MAX_RX_DESC, + .nid = dev_to_node(common->dev), + .dev = common->dev, + .dma_dir = DMA_BIDIRECTIONAL, + .napi = &common->napi_rx, + }; + struct xdp_rxq_info *rxq; + struct page_pool *pool; + int i, ret; + + pool = page_pool_create(&pp_params); + if (IS_ERR(pool)) + return PTR_ERR(pool); + + rx_chn->page_pool = pool; + + for (i = 0; i < common->port_num; i++) { + if (!common->ports[i].ndev) + continue; + + rxq = &common->ports[i].xdp_rxq; + + ret = xdp_rxq_info_reg(rxq, common->ports[i].ndev, i, 0); + if (ret) + goto err; + + ret = xdp_rxq_info_reg_mem_model(rxq, MEM_TYPE_PAGE_POOL, pool); + if (ret) + goto err; + } + + return 0; + +err: + am65_cpsw_destroy_xdp_rxqs(common); + return ret; +} + +static int am65_cpsw_nuss_desc_idx(struct k3_cppi_desc_pool *desc_pool, + void *desc, + unsigned char dsize_log2) +{ + void *pool_addr = k3_cppi_desc_pool_cpuaddr(desc_pool); + + return (desc - pool_addr) >> dsize_log2; +} + +static void am65_cpsw_nuss_set_buf_type(struct am65_cpsw_tx_chn *tx_chn, + struct cppi5_host_desc_t *desc, + enum am65_cpsw_tx_buf_type buf_type) +{ + int desc_idx; + + desc_idx = am65_cpsw_nuss_desc_idx(tx_chn->desc_pool, desc, + tx_chn->dsize_log2); + k3_cppi_desc_pool_desc_info_set(tx_chn->desc_pool, desc_idx, + (void *)buf_type); +} + +static enum am65_cpsw_tx_buf_type am65_cpsw_nuss_buf_type(struct am65_cpsw_tx_chn *tx_chn, + dma_addr_t desc_dma) +{ + struct cppi5_host_desc_t *desc_tx; + int desc_idx; + + desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma); + desc_idx = am65_cpsw_nuss_desc_idx(tx_chn->desc_pool, desc_tx, + tx_chn->dsize_log2); + + return (enum am65_cpsw_tx_buf_type)k3_cppi_desc_pool_desc_info(tx_chn->desc_pool, + desc_idx); +} + +static inline void am65_cpsw_put_page(struct am65_cpsw_rx_chn *rx_chn, + struct page *page, + bool allow_direct, + int desc_idx) +{ + page_pool_put_full_page(rx_chn->page_pool, page, allow_direct); + rx_chn->pages[desc_idx] = NULL; +} + static void am65_cpsw_nuss_rx_cleanup(void *data, dma_addr_t desc_dma) { struct am65_cpsw_rx_chn *rx_chn = data; struct cppi5_host_desc_t *desc_rx; - struct sk_buff *skb; dma_addr_t buf_dma; u32 buf_dma_len; + void *page_addr; void **swdata; + int desc_idx; desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma); swdata = cppi5_hdesc_get_swdata(desc_rx); - skb = *swdata; + page_addr = *swdata; cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len); k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma); - dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE); k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); - dev_kfree_skb_any(skb); + desc_idx = am65_cpsw_nuss_desc_idx(rx_chn->desc_pool, desc_rx, + rx_chn->dsize_log2); + am65_cpsw_put_page(rx_chn, virt_to_page(page_addr), false, desc_idx); } static void am65_cpsw_nuss_xmit_free(struct am65_cpsw_tx_chn *tx_chn, @@ -440,12 +578,32 @@ static void am65_cpsw_nuss_tx_cleanup(void *data, dma_addr_t desc_dma) dev_kfree_skb_any(skb); } +static struct sk_buff *am65_cpsw_build_skb(void *page_addr, + struct net_device *ndev, + unsigned int len) +{ + struct sk_buff *skb; + + len += AM65_CPSW_HEADROOM; + + skb = build_skb(page_addr, len); + if (unlikely(!skb)) + return NULL; + + skb_reserve(skb, AM65_CPSW_HEADROOM); + skb->dev = ndev; + + return skb; +} + static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common) { struct am65_cpsw_host *host_p = am65_common_get_host(common); + struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns; + struct am65_cpsw_tx_chn *tx_chn = common->tx_chns; int port_idx, i, ret, tx; - struct sk_buff *skb; u32 val, port_mask; + struct page *page; if (common->usage_count) return 0; @@ -505,25 +663,29 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common) am65_cpsw_qos_tx_p0_rate_init(common); - for (i = 0; i < common->rx_chns.descs_num; i++) { - skb = __netdev_alloc_skb_ip_align(NULL, - AM65_CPSW_MAX_PACKET_SIZE, - GFP_KERNEL); - if (!skb) { + ret = am65_cpsw_create_xdp_rxqs(common); + if (ret) { + dev_err(common->dev, "Failed to create XDP rx queues\n"); + return ret; + } + + for (i = 0; i < rx_chn->descs_num; i++) { + page = page_pool_dev_alloc_pages(rx_chn->page_pool); + if (!page) { ret = -ENOMEM; - dev_err(common->dev, "cannot allocate skb\n"); if (i) goto fail_rx; return ret; } + rx_chn->pages[i] = page; - ret = am65_cpsw_nuss_rx_push(common, skb); + ret = am65_cpsw_nuss_rx_push(common, page); if (ret < 0) { dev_err(common->dev, - "cannot submit skb to channel rx, error %d\n", + "cannot submit page to channel rx: %d\n", ret); - kfree_skb(skb); + am65_cpsw_put_page(rx_chn, page, false, i); if (i) goto fail_rx; @@ -531,27 +693,27 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common) } } - ret = k3_udma_glue_enable_rx_chn(common->rx_chns.rx_chn); + ret = k3_udma_glue_enable_rx_chn(rx_chn->rx_chn); if (ret) { dev_err(common->dev, "couldn't enable rx chn: %d\n", ret); goto fail_rx; } for (tx = 0; tx < common->tx_ch_num; tx++) { - ret = k3_udma_glue_enable_tx_chn(common->tx_chns[tx].tx_chn); + ret = k3_udma_glue_enable_tx_chn(tx_chn[tx].tx_chn); if (ret) { dev_err(common->dev, "couldn't enable tx chn %d: %d\n", tx, ret); tx--; goto fail_tx; } - napi_enable(&common->tx_chns[tx].napi_tx); + napi_enable(&tx_chn[tx].napi_tx); } napi_enable(&common->napi_rx); if (common->rx_irq_disabled) { common->rx_irq_disabled = false; - enable_irq(common->rx_chns.irq); + enable_irq(rx_chn->irq); } dev_dbg(common->dev, "cpsw_nuss started\n"); @@ -559,22 +721,23 @@ static int am65_cpsw_nuss_common_open(struct am65_cpsw_common *common) fail_tx: while (tx >= 0) { - napi_disable(&common->tx_chns[tx].napi_tx); - k3_udma_glue_disable_tx_chn(common->tx_chns[tx].tx_chn); + napi_disable(&tx_chn[tx].napi_tx); + k3_udma_glue_disable_tx_chn(tx_chn[tx].tx_chn); tx--; } - k3_udma_glue_disable_rx_chn(common->rx_chns.rx_chn); + k3_udma_glue_disable_rx_chn(rx_chn->rx_chn); fail_rx: - k3_udma_glue_reset_rx_chn(common->rx_chns.rx_chn, 0, - &common->rx_chns, + k3_udma_glue_reset_rx_chn(rx_chn->rx_chn, 0, rx_chn, am65_cpsw_nuss_rx_cleanup, 0); return ret; } static int am65_cpsw_nuss_common_stop(struct am65_cpsw_common *common) { + struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns; + struct am65_cpsw_tx_chn *tx_chn = common->tx_chns; int i; if (common->usage_count != 1) @@ -590,26 +753,25 @@ static int am65_cpsw_nuss_common_stop(struct am65_cpsw_common *common) reinit_completion(&common->tdown_complete); for (i = 0; i < common->tx_ch_num; i++) - k3_udma_glue_tdown_tx_chn(common->tx_chns[i].tx_chn, false); + k3_udma_glue_tdown_tx_chn(tx_chn[i].tx_chn, false); i = wait_for_completion_timeout(&common->tdown_complete, msecs_to_jiffies(1000)); if (!i) dev_err(common->dev, "tx timeout\n"); for (i = 0; i < common->tx_ch_num; i++) { - napi_disable(&common->tx_chns[i].napi_tx); - hrtimer_cancel(&common->tx_chns[i].tx_hrtimer); + napi_disable(&tx_chn[i].napi_tx); + hrtimer_cancel(&tx_chn[i].tx_hrtimer); } for (i = 0; i < common->tx_ch_num; i++) { - k3_udma_glue_reset_tx_chn(common->tx_chns[i].tx_chn, - &common->tx_chns[i], + k3_udma_glue_reset_tx_chn(tx_chn[i].tx_chn, &tx_chn[i], am65_cpsw_nuss_tx_cleanup); - k3_udma_glue_disable_tx_chn(common->tx_chns[i].tx_chn); + k3_udma_glue_disable_tx_chn(tx_chn[i].tx_chn); } reinit_completion(&common->tdown_complete); - k3_udma_glue_tdown_rx_chn(common->rx_chns.rx_chn, true); + k3_udma_glue_tdown_rx_chn(rx_chn->rx_chn, true); if (common->pdata.quirks & AM64_CPSW_QUIRK_DMA_RX_TDOWN_IRQ) { i = wait_for_completion_timeout(&common->tdown_complete, msecs_to_jiffies(1000)); @@ -621,17 +783,22 @@ static int am65_cpsw_nuss_common_stop(struct am65_cpsw_common *common) hrtimer_cancel(&common->rx_hrtimer); for (i = 0; i < AM65_CPSW_MAX_RX_FLOWS; i++) - k3_udma_glue_reset_rx_chn(common->rx_chns.rx_chn, i, - &common->rx_chns, + k3_udma_glue_reset_rx_chn(rx_chn->rx_chn, i, rx_chn, am65_cpsw_nuss_rx_cleanup, !!i); - k3_udma_glue_disable_rx_chn(common->rx_chns.rx_chn); + k3_udma_glue_disable_rx_chn(rx_chn->rx_chn); cpsw_ale_stop(common->ale); writel(0, common->cpsw_base + AM65_CPSW_REG_CTL); writel(0, common->cpsw_base + AM65_CPSW_REG_STAT_PORT_EN); + for (i = 0; i < rx_chn->descs_num; i++) { + if (rx_chn->pages[i]) + am65_cpsw_put_page(rx_chn, rx_chn->pages[i], false, i); + } + am65_cpsw_destroy_xdp_rxqs(common); + dev_dbg(common->dev, "cpsw_nuss stopped\n"); return 0; } @@ -749,16 +916,149 @@ runtime_put: return ret; } -static void am65_cpsw_nuss_rx_ts(struct sk_buff *skb, u32 *psdata) +static int am65_cpsw_xdp_tx_frame(struct net_device *ndev, + struct am65_cpsw_tx_chn *tx_chn, + struct xdp_frame *xdpf, + enum am65_cpsw_tx_buf_type buf_type) { - struct skb_shared_hwtstamps *ssh; - u64 ns; + struct am65_cpsw_common *common = am65_ndev_to_common(ndev); + struct am65_cpsw_port *port = am65_ndev_to_port(ndev); + struct cppi5_host_desc_t *host_desc; + struct netdev_queue *netif_txq; + dma_addr_t dma_desc, dma_buf; + u32 pkt_len = xdpf->len; + void **swdata; + int ret; + + host_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool); + if (unlikely(!host_desc)) { + ndev->stats.tx_dropped++; + return -ENOMEM; + } + + am65_cpsw_nuss_set_buf_type(tx_chn, host_desc, buf_type); - ns = ((u64)psdata[1] << 32) | psdata[0]; + dma_buf = dma_map_single(tx_chn->dma_dev, xdpf->data, + pkt_len, DMA_TO_DEVICE); + if (unlikely(dma_mapping_error(tx_chn->dma_dev, dma_buf))) { + ndev->stats.tx_dropped++; + ret = -ENOMEM; + goto pool_free; + } + + cppi5_hdesc_init(host_desc, CPPI5_INFO0_HDESC_EPIB_PRESENT, + AM65_CPSW_NAV_PS_DATA_SIZE); + cppi5_hdesc_set_pkttype(host_desc, AM65_CPSW_CPPI_TX_PKT_TYPE); + cppi5_hdesc_set_pktlen(host_desc, pkt_len); + cppi5_desc_set_pktids(&host_desc->hdr, 0, AM65_CPSW_CPPI_TX_FLOW_ID); + cppi5_desc_set_tags_ids(&host_desc->hdr, 0, port->port_id); + + k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &dma_buf); + cppi5_hdesc_attach_buf(host_desc, dma_buf, pkt_len, dma_buf, pkt_len); + + swdata = cppi5_hdesc_get_swdata(host_desc); + *(swdata) = xdpf; + + /* Report BQL before sending the packet */ + netif_txq = netdev_get_tx_queue(ndev, tx_chn->id); + netdev_tx_sent_queue(netif_txq, pkt_len); + + dma_desc = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, host_desc); + if (AM65_CPSW_IS_CPSW2G(common)) { + ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, host_desc, + dma_desc); + } else { + spin_lock_bh(&tx_chn->lock); + ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, host_desc, + dma_desc); + spin_unlock_bh(&tx_chn->lock); + } + if (ret) { + /* Inform BQL */ + netdev_tx_completed_queue(netif_txq, 1, pkt_len); + ndev->stats.tx_errors++; + goto dma_unmap; + } + + return 0; - ssh = skb_hwtstamps(skb); - memset(ssh, 0, sizeof(*ssh)); - ssh->hwtstamp = ns_to_ktime(ns); +dma_unmap: + k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &dma_buf); + dma_unmap_single(tx_chn->dma_dev, dma_buf, pkt_len, DMA_TO_DEVICE); +pool_free: + k3_cppi_desc_pool_free(tx_chn->desc_pool, host_desc); + return ret; +} + +static int am65_cpsw_run_xdp(struct am65_cpsw_common *common, + struct am65_cpsw_port *port, + struct xdp_buff *xdp, + int desc_idx, int cpu, int *len) +{ + struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns; + struct net_device *ndev = port->ndev; + int ret = AM65_CPSW_XDP_CONSUMED; + struct am65_cpsw_tx_chn *tx_chn; + struct netdev_queue *netif_txq; + struct xdp_frame *xdpf; + struct bpf_prog *prog; + struct page *page; + u32 act; + + prog = READ_ONCE(port->xdp_prog); + if (!prog) + return AM65_CPSW_XDP_PASS; + + act = bpf_prog_run_xdp(prog, xdp); + /* XDP prog might have changed packet data and boundaries */ + *len = xdp->data_end - xdp->data; + + switch (act) { + case XDP_PASS: + ret = AM65_CPSW_XDP_PASS; + goto out; + case XDP_TX: + tx_chn = &common->tx_chns[cpu % AM65_CPSW_MAX_TX_QUEUES]; + netif_txq = netdev_get_tx_queue(ndev, tx_chn->id); + + xdpf = xdp_convert_buff_to_frame(xdp); + if (unlikely(!xdpf)) + break; + + __netif_tx_lock(netif_txq, cpu); + ret = am65_cpsw_xdp_tx_frame(ndev, tx_chn, xdpf, + AM65_CPSW_TX_BUF_TYPE_XDP_TX); + __netif_tx_unlock(netif_txq); + if (ret) + break; + + ndev->stats.rx_bytes += *len; + ndev->stats.rx_packets++; + ret = AM65_CPSW_XDP_CONSUMED; + goto out; + case XDP_REDIRECT: + if (unlikely(xdp_do_redirect(ndev, xdp, prog))) + break; + + ndev->stats.rx_bytes += *len; + ndev->stats.rx_packets++; + ret = AM65_CPSW_XDP_REDIRECT; + goto out; + default: + bpf_warn_invalid_xdp_action(ndev, prog, act); + fallthrough; + case XDP_ABORTED: + trace_xdp_exception(ndev, prog, act); + fallthrough; + case XDP_DROP: + ndev->stats.rx_dropped++; + } + + page = virt_to_head_page(xdp->data); + am65_cpsw_put_page(rx_chn, page, true, desc_idx); + +out: + return ret; } /* RX psdata[2] word format - checksum information */ @@ -795,7 +1095,7 @@ static void am65_cpsw_nuss_rx_csum(struct sk_buff *skb, u32 csum_info) } static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common, - u32 flow_idx) + u32 flow_idx, int cpu) { struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns; u32 buf_dma_len, pkt_len, port_id = 0, csum_info; @@ -803,13 +1103,16 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common, struct am65_cpsw_ndev_stats *stats; struct cppi5_host_desc_t *desc_rx; struct device *dev = common->dev; - struct sk_buff *skb, *new_skb; + struct page *page, *new_page; dma_addr_t desc_dma, buf_dma; struct am65_cpsw_port *port; + int headroom, desc_idx, ret; struct net_device *ndev; + struct sk_buff *skb; + struct xdp_buff xdp; + void *page_addr; void **swdata; u32 *psdata; - int ret = 0; ret = k3_udma_glue_pop_rx_chn(rx_chn->rx_chn, flow_idx, &desc_dma); if (ret) { @@ -830,7 +1133,8 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common, __func__, flow_idx, &desc_dma); swdata = cppi5_hdesc_get_swdata(desc_rx); - skb = *swdata; + page_addr = *swdata; + page = virt_to_page(page_addr); cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len); k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma); pkt_len = cppi5_hdesc_get_pktlen(desc_rx); @@ -838,12 +1142,7 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common, dev_dbg(dev, "%s rx port_id:%d\n", __func__, port_id); port = am65_common_get_port(common, port_id); ndev = port->ndev; - skb->dev = ndev; - psdata = cppi5_hdesc_get_psdata(desc_rx); - /* add RX timestamp */ - if (port->rx_ts_enabled) - am65_cpsw_nuss_rx_ts(skb, psdata); csum_info = psdata[2]; dev_dbg(dev, "%s rx csum_info:%#x\n", __func__, csum_info); @@ -851,36 +1150,64 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common, k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); - new_skb = netdev_alloc_skb_ip_align(ndev, AM65_CPSW_MAX_PACKET_SIZE); - if (new_skb) { - ndev_priv = netdev_priv(ndev); - am65_cpsw_nuss_set_offload_fwd_mark(skb, ndev_priv->offload_fwd_mark); - skb_put(skb, pkt_len); - skb->protocol = eth_type_trans(skb, ndev); - am65_cpsw_nuss_rx_csum(skb, csum_info); - napi_gro_receive(&common->napi_rx, skb); - - stats = this_cpu_ptr(ndev_priv->stats); - - u64_stats_update_begin(&stats->syncp); - stats->rx_packets++; - stats->rx_bytes += pkt_len; - u64_stats_update_end(&stats->syncp); - kmemleak_not_leak(new_skb); - } else { - ndev->stats.rx_dropped++; - new_skb = skb; + desc_idx = am65_cpsw_nuss_desc_idx(rx_chn->desc_pool, desc_rx, + rx_chn->dsize_log2); + + skb = am65_cpsw_build_skb(page_addr, ndev, + AM65_CPSW_MAX_PACKET_SIZE); + if (unlikely(!skb)) { + new_page = page; + goto requeue; } + if (port->xdp_prog) { + xdp_init_buff(&xdp, AM65_CPSW_MAX_PACKET_SIZE, &port->xdp_rxq); + + xdp_prepare_buff(&xdp, page_addr, skb_headroom(skb), + pkt_len, false); + + ret = am65_cpsw_run_xdp(common, port, &xdp, desc_idx, + cpu, &pkt_len); + if (ret != AM65_CPSW_XDP_PASS) + return ret; + + /* Compute additional headroom to be reserved */ + headroom = (xdp.data - xdp.data_hard_start) - skb_headroom(skb); + skb_reserve(skb, headroom); + } + + ndev_priv = netdev_priv(ndev); + am65_cpsw_nuss_set_offload_fwd_mark(skb, ndev_priv->offload_fwd_mark); + skb_put(skb, pkt_len); + if (port->rx_ts_enabled) + am65_cpts_rx_timestamp(common->cpts, skb); + skb_mark_for_recycle(skb); + skb->protocol = eth_type_trans(skb, ndev); + am65_cpsw_nuss_rx_csum(skb, csum_info); + napi_gro_receive(&common->napi_rx, skb); + + stats = this_cpu_ptr(ndev_priv->stats); + + u64_stats_update_begin(&stats->syncp); + stats->rx_packets++; + stats->rx_bytes += pkt_len; + u64_stats_update_end(&stats->syncp); + + new_page = page_pool_dev_alloc_pages(rx_chn->page_pool); + if (unlikely(!new_page)) + return -ENOMEM; + rx_chn->pages[desc_idx] = new_page; + if (netif_dormant(ndev)) { - dev_kfree_skb_any(new_skb); + am65_cpsw_put_page(rx_chn, new_page, true, desc_idx); ndev->stats.rx_dropped++; return 0; } - ret = am65_cpsw_nuss_rx_push(common, new_skb); +requeue: + ret = am65_cpsw_nuss_rx_push(common, new_page); if (WARN_ON(ret < 0)) { - dev_kfree_skb_any(new_skb); + am65_cpsw_put_page(rx_chn, new_page, true, desc_idx); ndev->stats.rx_errors++; ndev->stats.rx_dropped++; } @@ -901,6 +1228,8 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget) { struct am65_cpsw_common *common = am65_cpsw_napi_to_common(napi_rx); int flow = AM65_CPSW_MAX_RX_FLOWS; + int cpu = smp_processor_id(); + bool xdp_redirect = false; int cur_budget, ret; int num_rx = 0; @@ -909,9 +1238,12 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget) cur_budget = budget - num_rx; while (cur_budget--) { - ret = am65_cpsw_nuss_rx_packets(common, flow); - if (ret) + ret = am65_cpsw_nuss_rx_packets(common, flow, cpu); + if (ret) { + if (ret == AM65_CPSW_XDP_REDIRECT) + xdp_redirect = true; break; + } num_rx++; } @@ -919,6 +1251,9 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget) break; } + if (xdp_redirect) + xdp_do_flush(); + dev_dbg(common->dev, "%s num_rx:%d %d\n", __func__, num_rx, budget); if (num_rx < budget && napi_complete_done(napi_rx, num_rx)) { @@ -938,8 +1273,8 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget) } static struct sk_buff * -am65_cpsw_nuss_tx_compl_packet(struct am65_cpsw_tx_chn *tx_chn, - dma_addr_t desc_dma) +am65_cpsw_nuss_tx_compl_packet_skb(struct am65_cpsw_tx_chn *tx_chn, + dma_addr_t desc_dma) { struct am65_cpsw_ndev_priv *ndev_priv; struct am65_cpsw_ndev_stats *stats; @@ -968,6 +1303,39 @@ am65_cpsw_nuss_tx_compl_packet(struct am65_cpsw_tx_chn *tx_chn, return skb; } +static struct xdp_frame * +am65_cpsw_nuss_tx_compl_packet_xdp(struct am65_cpsw_common *common, + struct am65_cpsw_tx_chn *tx_chn, + dma_addr_t desc_dma, + struct net_device **ndev) +{ + struct am65_cpsw_ndev_priv *ndev_priv; + struct am65_cpsw_ndev_stats *stats; + struct cppi5_host_desc_t *desc_tx; + struct am65_cpsw_port *port; + struct xdp_frame *xdpf; + u32 port_id = 0; + void **swdata; + + desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma); + cppi5_desc_get_tags_ids(&desc_tx->hdr, NULL, &port_id); + swdata = cppi5_hdesc_get_swdata(desc_tx); + xdpf = *(swdata); + am65_cpsw_nuss_xmit_free(tx_chn, desc_tx); + + port = am65_common_get_port(common, port_id); + *ndev = port->ndev; + + ndev_priv = netdev_priv(*ndev); + stats = this_cpu_ptr(ndev_priv->stats); + u64_stats_update_begin(&stats->syncp); + stats->tx_packets++; + stats->tx_bytes += xdpf->len; + u64_stats_update_end(&stats->syncp); + + return xdpf; +} + static void am65_cpsw_nuss_tx_wake(struct am65_cpsw_tx_chn *tx_chn, struct net_device *ndev, struct netdev_queue *netif_txq) { @@ -988,11 +1356,13 @@ static void am65_cpsw_nuss_tx_wake(struct am65_cpsw_tx_chn *tx_chn, struct net_d static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common, int chn, unsigned int budget, bool *tdown) { + enum am65_cpsw_tx_buf_type buf_type; struct device *dev = common->dev; struct am65_cpsw_tx_chn *tx_chn; struct netdev_queue *netif_txq; unsigned int total_bytes = 0; struct net_device *ndev; + struct xdp_frame *xdpf; struct sk_buff *skb; dma_addr_t desc_dma; int res, num_tx = 0; @@ -1013,10 +1383,21 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common, break; } - skb = am65_cpsw_nuss_tx_compl_packet(tx_chn, desc_dma); - total_bytes = skb->len; - ndev = skb->dev; - napi_consume_skb(skb, budget); + buf_type = am65_cpsw_nuss_buf_type(tx_chn, desc_dma); + if (buf_type == AM65_CPSW_TX_BUF_TYPE_SKB) { + skb = am65_cpsw_nuss_tx_compl_packet_skb(tx_chn, desc_dma); + ndev = skb->dev; + total_bytes = skb->len; + napi_consume_skb(skb, budget); + } else { + xdpf = am65_cpsw_nuss_tx_compl_packet_xdp(common, tx_chn, + desc_dma, &ndev); + total_bytes = xdpf->len; + if (buf_type == AM65_CPSW_TX_BUF_TYPE_XDP_TX) + xdp_return_frame_rx_napi(xdpf); + else + xdp_return_frame(xdpf); + } num_tx++; netif_txq = netdev_get_tx_queue(ndev, chn); @@ -1034,11 +1415,13 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common, static int am65_cpsw_nuss_tx_compl_packets_2g(struct am65_cpsw_common *common, int chn, unsigned int budget, bool *tdown) { + enum am65_cpsw_tx_buf_type buf_type; struct device *dev = common->dev; struct am65_cpsw_tx_chn *tx_chn; struct netdev_queue *netif_txq; unsigned int total_bytes = 0; struct net_device *ndev; + struct xdp_frame *xdpf; struct sk_buff *skb; dma_addr_t desc_dma; int res, num_tx = 0; @@ -1057,11 +1440,21 @@ static int am65_cpsw_nuss_tx_compl_packets_2g(struct am65_cpsw_common *common, break; } - skb = am65_cpsw_nuss_tx_compl_packet(tx_chn, desc_dma); - - ndev = skb->dev; - total_bytes += skb->len; - napi_consume_skb(skb, budget); + buf_type = am65_cpsw_nuss_buf_type(tx_chn, desc_dma); + if (buf_type == AM65_CPSW_TX_BUF_TYPE_SKB) { + skb = am65_cpsw_nuss_tx_compl_packet_skb(tx_chn, desc_dma); + ndev = skb->dev; + total_bytes += skb->len; + napi_consume_skb(skb, budget); + } else { + xdpf = am65_cpsw_nuss_tx_compl_packet_xdp(common, tx_chn, + desc_dma, &ndev); + total_bytes += xdpf->len; + if (buf_type == AM65_CPSW_TX_BUF_TYPE_XDP_TX) + xdp_return_frame_rx_napi(xdpf); + else + xdp_return_frame(xdpf); + } num_tx++; } @@ -1183,10 +1576,13 @@ static netdev_tx_t am65_cpsw_nuss_ndo_slave_xmit(struct sk_buff *skb, goto busy_stop_q; } + am65_cpsw_nuss_set_buf_type(tx_chn, first_desc, + AM65_CPSW_TX_BUF_TYPE_SKB); + cppi5_hdesc_init(first_desc, CPPI5_INFO0_HDESC_EPIB_PRESENT, AM65_CPSW_NAV_PS_DATA_SIZE); - cppi5_desc_set_pktids(&first_desc->hdr, 0, 0x3FFF); - cppi5_hdesc_set_pkttype(first_desc, 0x7); + cppi5_desc_set_pktids(&first_desc->hdr, 0, AM65_CPSW_CPPI_TX_FLOW_ID); + cppi5_hdesc_set_pkttype(first_desc, AM65_CPSW_CPPI_TX_PKT_TYPE); cppi5_desc_set_tags_ids(&first_desc->hdr, 0, port->port_id); k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma); @@ -1225,6 +1621,9 @@ static netdev_tx_t am65_cpsw_nuss_ndo_slave_xmit(struct sk_buff *skb, goto busy_free_descs; } + am65_cpsw_nuss_set_buf_type(tx_chn, next_desc, + AM65_CPSW_TX_BUF_TYPE_SKB); + buf_dma = skb_frag_dma_map(tx_chn->dma_dev, frag, 0, frag_size, DMA_TO_DEVICE); if (unlikely(dma_mapping_error(tx_chn->dma_dev, buf_dma))) { @@ -1334,7 +1733,6 @@ static int am65_cpsw_nuss_ndo_slave_set_mac_address(struct net_device *ndev, static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev, struct ifreq *ifr) { - struct am65_cpsw_common *common = am65_ndev_to_common(ndev); struct am65_cpsw_port *port = am65_ndev_to_port(ndev); u32 ts_ctrl, seq_id, ts_ctrl_ltype2, ts_vlan_ltype; struct hwtstamp_config cfg; @@ -1358,11 +1756,6 @@ static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev, case HWTSTAMP_FILTER_NONE: port->rx_ts_enabled = false; break; - case HWTSTAMP_FILTER_ALL: - case HWTSTAMP_FILTER_SOME: - case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: - case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: @@ -1372,10 +1765,13 @@ static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev, case HWTSTAMP_FILTER_PTP_V2_EVENT: case HWTSTAMP_FILTER_PTP_V2_SYNC: case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: - case HWTSTAMP_FILTER_NTP_ALL: port->rx_ts_enabled = true; - cfg.rx_filter = HWTSTAMP_FILTER_ALL; + cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; break; + case HWTSTAMP_FILTER_ALL: + case HWTSTAMP_FILTER_SOME: + case HWTSTAMP_FILTER_NTP_ALL: + return -EOPNOTSUPP; default: return -ERANGE; } @@ -1405,6 +1801,10 @@ static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev, ts_ctrl |= AM65_CPSW_TS_TX_ANX_ALL_EN | AM65_CPSW_PN_TS_CTL_TX_VLAN_LT1_EN; + if (port->rx_ts_enabled) + ts_ctrl |= AM65_CPSW_TS_RX_ANX_ALL_EN | + AM65_CPSW_PN_TS_CTL_RX_VLAN_LT1_EN; + writel(seq_id, port->port_base + AM65_CPSW_PORTN_REG_TS_SEQ_LTYPE_REG); writel(ts_vlan_ltype, port->port_base + AM65_CPSW_PORTN_REG_TS_VLAN_LTYPE_REG); @@ -1412,9 +1812,6 @@ static int am65_cpsw_nuss_hwtstamp_set(struct net_device *ndev, AM65_CPSW_PORTN_REG_TS_CTL_LTYPE2); writel(ts_ctrl, port->port_base + AM65_CPSW_PORTN_REG_TS_CTL); - /* en/dis RX timestamp */ - am65_cpts_rx_enable(common->cpts, port->rx_ts_enabled); - return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0; } @@ -1431,7 +1828,7 @@ static int am65_cpsw_nuss_hwtstamp_get(struct net_device *ndev, cfg.tx_type = port->tx_ts_enabled ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; cfg.rx_filter = port->rx_ts_enabled ? - HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE; + HWTSTAMP_FILTER_PTP_V2_EVENT : HWTSTAMP_FILTER_NONE; return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0; } @@ -1488,6 +1885,59 @@ static void am65_cpsw_nuss_ndo_get_stats(struct net_device *dev, stats->tx_dropped = dev->stats.tx_dropped; } +static int am65_cpsw_xdp_prog_setup(struct net_device *ndev, + struct bpf_prog *prog) +{ + struct am65_cpsw_port *port = am65_ndev_to_port(ndev); + bool running = netif_running(ndev); + struct bpf_prog *old_prog; + + if (running) + am65_cpsw_nuss_ndo_slave_stop(ndev); + + old_prog = xchg(&port->xdp_prog, prog); + if (old_prog) + bpf_prog_put(old_prog); + + if (running) + return am65_cpsw_nuss_ndo_slave_open(ndev); + + return 0; +} + +static int am65_cpsw_ndo_bpf(struct net_device *ndev, struct netdev_bpf *bpf) +{ + switch (bpf->command) { + case XDP_SETUP_PROG: + return am65_cpsw_xdp_prog_setup(ndev, bpf->prog); + default: + return -EINVAL; + } +} + +static int am65_cpsw_ndo_xdp_xmit(struct net_device *ndev, int n, + struct xdp_frame **frames, u32 flags) +{ + struct am65_cpsw_tx_chn *tx_chn; + struct netdev_queue *netif_txq; + int cpu = smp_processor_id(); + int i, nxmit = 0; + + tx_chn = &am65_ndev_to_common(ndev)->tx_chns[cpu % AM65_CPSW_MAX_TX_QUEUES]; + netif_txq = netdev_get_tx_queue(ndev, tx_chn->id); + + __netif_tx_lock(netif_txq, cpu); + for (i = 0; i < n; i++) { + if (am65_cpsw_xdp_tx_frame(ndev, tx_chn, frames[i], + AM65_CPSW_TX_BUF_TYPE_XDP_NDO)) + break; + nxmit++; + } + __netif_tx_unlock(netif_txq); + + return nxmit; +} + static const struct net_device_ops am65_cpsw_nuss_netdev_ops = { .ndo_open = am65_cpsw_nuss_ndo_slave_open, .ndo_stop = am65_cpsw_nuss_ndo_slave_stop, @@ -1502,6 +1952,8 @@ static const struct net_device_ops am65_cpsw_nuss_netdev_ops = { .ndo_eth_ioctl = am65_cpsw_nuss_ndo_slave_ioctl, .ndo_setup_tc = am65_cpsw_qos_ndo_setup_tc, .ndo_set_tx_maxrate = am65_cpsw_qos_ndo_tx_p0_set_maxrate, + .ndo_bpf = am65_cpsw_ndo_bpf, + .ndo_xdp_xmit = am65_cpsw_ndo_xdp_xmit, }; static void am65_cpsw_disable_phy(struct phy *phy) @@ -1772,7 +2224,7 @@ static int am65_cpsw_nuss_init_tx_chns(struct am65_cpsw_common *common) .mode = K3_RINGACC_RING_MODE_RING, .flags = 0 }; - u32 hdesc_size; + u32 hdesc_size, hdesc_size_out; int i, ret = 0; hdesc_size = cppi5_hdesc_calc_size(true, AM65_CPSW_NAV_PS_DATA_SIZE, @@ -1816,6 +2268,10 @@ static int am65_cpsw_nuss_init_tx_chns(struct am65_cpsw_common *common) goto err; } + hdesc_size_out = k3_cppi_desc_pool_desc_size(tx_chn->desc_pool); + tx_chn->dsize_log2 = __fls(hdesc_size_out); + WARN_ON(hdesc_size_out != (1 << tx_chn->dsize_log2)); + tx_chn->irq = k3_udma_glue_tx_get_irq(tx_chn->tx_chn); if (tx_chn->irq < 0) { dev_err(dev, "Failed to get tx dma irq %d\n", @@ -1862,8 +2318,8 @@ static void am65_cpsw_nuss_free_rx_chns(void *data) static void am65_cpsw_nuss_remove_rx_chns(void *data) { struct am65_cpsw_common *common = data; - struct am65_cpsw_rx_chn *rx_chn; struct device *dev = common->dev; + struct am65_cpsw_rx_chn *rx_chn; rx_chn = &common->rx_chns; devm_remove_action(dev, am65_cpsw_nuss_free_rx_chns, common); @@ -1873,11 +2329,7 @@ static void am65_cpsw_nuss_remove_rx_chns(void *data) netif_napi_del(&common->napi_rx); - if (!IS_ERR_OR_NULL(rx_chn->desc_pool)) - k3_cppi_desc_pool_destroy(rx_chn->desc_pool); - - if (!IS_ERR_OR_NULL(rx_chn->rx_chn)) - k3_udma_glue_release_rx_chn(rx_chn->rx_chn); + am65_cpsw_nuss_free_rx_chns(common); common->rx_flow_id_base = -1; } @@ -1888,7 +2340,7 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common) struct k3_udma_glue_rx_channel_cfg rx_cfg = { 0 }; u32 max_desc_num = AM65_CPSW_MAX_RX_DESC; struct device *dev = common->dev; - u32 hdesc_size; + u32 hdesc_size, hdesc_size_out; u32 fdqring_id; int i, ret = 0; @@ -1920,6 +2372,17 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common) goto err; } + hdesc_size_out = k3_cppi_desc_pool_desc_size(rx_chn->desc_pool); + rx_chn->dsize_log2 = __fls(hdesc_size_out); + WARN_ON(hdesc_size_out != (1 << rx_chn->dsize_log2)); + + rx_chn->page_pool = NULL; + + rx_chn->pages = devm_kcalloc(dev, rx_chn->descs_num, + sizeof(*rx_chn->pages), GFP_KERNEL); + if (!rx_chn->pages) + return -ENOMEM; + common->rx_flow_id_base = k3_udma_glue_rx_get_flow_id_base(rx_chn->rx_chn); dev_info(dev, "set new flow-id-base %u\n", common->rx_flow_id_base); @@ -2252,6 +2715,9 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx) NETIF_F_HW_TC; port->ndev->features = port->ndev->hw_features | NETIF_F_HW_VLAN_CTAG_FILTER; + port->ndev->xdp_features = NETDEV_XDP_ACT_BASIC | + NETDEV_XDP_ACT_REDIRECT | + NETDEV_XDP_ACT_NDO_XMIT; port->ndev->vlan_features |= NETIF_F_SG; port->ndev->netdev_ops = &am65_cpsw_nuss_netdev_ops; port->ndev->ethtool_ops = &am65_cpsw_ethtool_ops_slave; @@ -2315,6 +2781,8 @@ am65_cpsw_nuss_init_port_ndev(struct am65_cpsw_common *common, u32 port_idx) if (ret) dev_err(dev, "failed to add percpu stat free action %d\n", ret); + port->xdp_prog = NULL; + if (!common->dma_ndev) common->dma_ndev = port->ndev; @@ -2588,7 +3056,8 @@ static void am65_cpsw_init_port_switch_ale(struct am65_cpsw_port *port) } static int am65_cpsw_dl_switch_mode_set(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct am65_cpsw_devlink *dl_priv = devlink_priv(dl); struct am65_cpsw_common *cpsw = dl_priv->common; @@ -2922,7 +3391,8 @@ static const struct am65_cpsw_pdata j784s4_cpswxg_pdata = { .quirks = 0, .ale_dev_id = "am64-cpswxg", .fdqring_mode = K3_RINGACC_RING_MODE_MESSAGE, - .extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII) | BIT(PHY_INTERFACE_MODE_USXGMII), + .extra_modes = BIT(PHY_INTERFACE_MODE_QSGMII) | BIT(PHY_INTERFACE_MODE_SGMII) | + BIT(PHY_INTERFACE_MODE_USXGMII), }; static const struct of_device_id am65_cpsw_nuss_of_mtable[] = { @@ -2958,9 +3428,9 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev) struct device_node *node; struct resource *res; struct clk *clk; + int ale_entries; u64 id_temp; int ret, i; - int ale_entries; common = devm_kzalloc(dev, sizeof(struct am65_cpsw_common), GFP_KERNEL); if (!common) @@ -3172,10 +3642,10 @@ static int am65_cpsw_nuss_suspend(struct device *dev) static int am65_cpsw_nuss_resume(struct device *dev) { struct am65_cpsw_common *common = dev_get_drvdata(dev); + struct am65_cpsw_host *host_p = am65_common_get_host(common); struct am65_cpsw_port *port; struct net_device *ndev; int i, ret; - struct am65_cpsw_host *host_p = am65_common_get_host(common); ret = am65_cpsw_nuss_init_tx_chns(common); if (ret) diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h index 7da0492dc0..d8ce88dc9c 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h +++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h @@ -14,6 +14,7 @@ #include <linux/platform_device.h> #include <linux/soc/ti/k3-ringacc.h> #include <net/devlink.h> +#include <net/xdp.h> #include "am65-cpsw-qos.h" struct am65_cpts; @@ -56,10 +57,18 @@ struct am65_cpsw_port { bool rx_ts_enabled; struct am65_cpsw_qos qos; struct devlink_port devlink_port; + struct bpf_prog *xdp_prog; + struct xdp_rxq_info xdp_rxq; /* Only for suspend resume context */ u32 vid_context; }; +enum am65_cpsw_tx_buf_type { + AM65_CPSW_TX_BUF_TYPE_SKB, + AM65_CPSW_TX_BUF_TYPE_XDP_TX, + AM65_CPSW_TX_BUF_TYPE_XDP_NDO, +}; + struct am65_cpsw_host { struct am65_cpsw_common *common; void __iomem *port_base; @@ -80,6 +89,7 @@ struct am65_cpsw_tx_chn { int irq; u32 id; u32 descs_num; + unsigned char dsize_log2; char tx_chn_name[128]; u32 rate_mbps; }; @@ -89,7 +99,10 @@ struct am65_cpsw_rx_chn { struct device *dma_dev; struct k3_cppi_desc_pool *desc_pool; struct k3_udma_glue_rx_channel *rx_chn; + struct page_pool *page_pool; + struct page **pages; u32 descs_num; + unsigned char dsize_log2; int irq; }; diff --git a/drivers/net/ethernet/ti/am65-cpsw-qos.c b/drivers/net/ethernet/ti/am65-cpsw-qos.c index 816e73a3d6..fa96db7c1a 100644 --- a/drivers/net/ethernet/ti/am65-cpsw-qos.c +++ b/drivers/net/ethernet/ti/am65-cpsw-qos.c @@ -9,6 +9,7 @@ #include <linux/pm_runtime.h> #include <linux/math.h> +#include <linux/math64.h> #include <linux/time.h> #include <linux/units.h> #include <net/pkt_cls.h> @@ -837,6 +838,7 @@ static int am65_cpsw_taprio_replace(struct net_device *ndev, struct am65_cpsw_port *port = am65_ndev_to_port(ndev); struct am65_cpts *cpts = common->cpts; struct am65_cpsw_est *est_new; + u64 cur_time, n; int ret, tact; if (!netif_running(ndev)) { @@ -888,13 +890,21 @@ static int am65_cpsw_taprio_replace(struct net_device *ndev, if (tact == TACT_PROG) am65_cpsw_timer_stop(ndev); - if (!est_new->taprio.base_time) - est_new->taprio.base_time = am65_cpts_ns_gettime(cpts); - am65_cpsw_port_est_get_buf_num(ndev, est_new); am65_cpsw_est_set_sched_list(ndev, est_new); am65_cpsw_port_est_assign_buf_num(ndev, est_new->buf); + /* If the base-time is in the past, start schedule from the time: + * base_time + (N*cycle_time) + * where N is the smallest possible integer such that the above + * time is in the future. + */ + cur_time = am65_cpts_ns_gettime(cpts); + if (est_new->taprio.base_time < cur_time) { + n = div64_u64(cur_time - est_new->taprio.base_time, est_new->taprio.cycle_time); + est_new->taprio.base_time += (n + 1) * est_new->taprio.cycle_time; + } + am65_cpsw_est_set(ndev, 1); if (tact == TACT_PROG) { @@ -1008,6 +1018,9 @@ static int am65_cpsw_qos_clsflower_add_policer(struct am65_cpsw_port *port, return -EOPNOTSUPP; } + if (flow_rule_match_has_control_flags(rule, extack)) + return -EOPNOTSUPP; + if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { NL_SET_ERR_MSG_MOD(extack, "Not matching on eth address"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/ti/am65-cpts.c b/drivers/net/ethernet/ti/am65-cpts.c index f89716b1cf..59d6ab989c 100644 --- a/drivers/net/ethernet/ti/am65-cpts.c +++ b/drivers/net/ethernet/ti/am65-cpts.c @@ -275,15 +275,13 @@ static bool am65_cpts_fifo_pop_event(struct am65_cpts *cpts, return true; } -static int am65_cpts_fifo_read(struct am65_cpts *cpts) +static int __am65_cpts_fifo_read(struct am65_cpts *cpts) { struct ptp_clock_event pevent; struct am65_cpts_event *event; bool schedule = false; int i, type, ret = 0; - unsigned long flags; - spin_lock_irqsave(&cpts->lock, flags); for (i = 0; i < AM65_CPTS_FIFO_DEPTH; i++) { event = list_first_entry_or_null(&cpts->pool, struct am65_cpts_event, list); @@ -312,8 +310,7 @@ static int am65_cpts_fifo_read(struct am65_cpts *cpts) event->tmo = jiffies + msecs_to_jiffies(AM65_CPTS_EVENT_RX_TX_TIMEOUT); - list_del_init(&event->list); - list_add_tail(&event->list, &cpts->events); + list_move_tail(&event->list, &cpts->events); dev_dbg(cpts->dev, "AM65_CPTS_EV_TX e1:%08x e2:%08x t:%lld\n", @@ -356,14 +353,24 @@ static int am65_cpts_fifo_read(struct am65_cpts *cpts) } out: - spin_unlock_irqrestore(&cpts->lock, flags); - if (schedule) ptp_schedule_worker(cpts->ptp_clock, 0); return ret; } +static int am65_cpts_fifo_read(struct am65_cpts *cpts) +{ + unsigned long flags; + int ret = 0; + + spin_lock_irqsave(&cpts->lock, flags); + ret = __am65_cpts_fifo_read(cpts); + spin_unlock_irqrestore(&cpts->lock, flags); + + return ret; +} + static u64 am65_cpts_gettime(struct am65_cpts *cpts, struct ptp_system_timestamp *sts) { @@ -864,29 +871,6 @@ static long am65_cpts_ts_work(struct ptp_clock_info *ptp) return delay; } -/** - * am65_cpts_rx_enable - enable rx timestamping - * @cpts: cpts handle - * @en: enable - * - * This functions enables rx packets timestamping. The CPTS can timestamp all - * rx packets. - */ -void am65_cpts_rx_enable(struct am65_cpts *cpts, bool en) -{ - u32 val; - - mutex_lock(&cpts->ptp_clk_lock); - val = am65_cpts_read32(cpts, control); - if (en) - val |= AM65_CPTS_CONTROL_TSTAMP_EN; - else - val &= ~AM65_CPTS_CONTROL_TSTAMP_EN; - am65_cpts_write32(cpts, val, control); - mutex_unlock(&cpts->ptp_clk_lock); -} -EXPORT_SYMBOL_GPL(am65_cpts_rx_enable); - static int am65_skb_get_mtype_seqid(struct sk_buff *skb, u32 *mtype_seqid) { unsigned int ptp_class = ptp_classify_raw(skb); @@ -911,6 +895,69 @@ static int am65_skb_get_mtype_seqid(struct sk_buff *skb, u32 *mtype_seqid) return 1; } +static u64 am65_cpts_find_rx_ts(struct am65_cpts *cpts, u32 skb_mtype_seqid) +{ + struct list_head *this, *next; + struct am65_cpts_event *event; + unsigned long flags; + u32 mtype_seqid; + u64 ns = 0; + + spin_lock_irqsave(&cpts->lock, flags); + __am65_cpts_fifo_read(cpts); + list_for_each_safe(this, next, &cpts->events) { + event = list_entry(this, struct am65_cpts_event, list); + if (time_after(jiffies, event->tmo)) { + list_move(&event->list, &cpts->pool); + continue; + } + + mtype_seqid = event->event1 & + (AM65_CPTS_EVENT_1_MESSAGE_TYPE_MASK | + AM65_CPTS_EVENT_1_SEQUENCE_ID_MASK | + AM65_CPTS_EVENT_1_EVENT_TYPE_MASK); + + if (mtype_seqid == skb_mtype_seqid) { + ns = event->timestamp; + list_move(&event->list, &cpts->pool); + break; + } + } + spin_unlock_irqrestore(&cpts->lock, flags); + + return ns; +} + +void am65_cpts_rx_timestamp(struct am65_cpts *cpts, struct sk_buff *skb) +{ + struct am65_cpts_skb_cb_data *skb_cb = (struct am65_cpts_skb_cb_data *)skb->cb; + struct skb_shared_hwtstamps *ssh; + int ret; + u64 ns; + + /* am65_cpts_rx_timestamp() is called before eth_type_trans(), so + * skb MAC Hdr properties are not configured yet. Hence need to + * reset skb MAC header here + */ + skb_reset_mac_header(skb); + ret = am65_skb_get_mtype_seqid(skb, &skb_cb->skb_mtype_seqid); + if (!ret) + return; /* if not PTP class packet */ + + skb_cb->skb_mtype_seqid |= (AM65_CPTS_EV_RX << AM65_CPTS_EVENT_1_EVENT_TYPE_SHIFT); + + dev_dbg(cpts->dev, "%s mtype seqid %08x\n", __func__, skb_cb->skb_mtype_seqid); + + ns = am65_cpts_find_rx_ts(cpts, skb_cb->skb_mtype_seqid); + if (!ns) + return; + + ssh = skb_hwtstamps(skb); + memset(ssh, 0, sizeof(*ssh)); + ssh->hwtstamp = ns_to_ktime(ns); +} +EXPORT_SYMBOL_GPL(am65_cpts_rx_timestamp); + /** * am65_cpts_tx_timestamp - save tx packet for timestamping * @cpts: cpts handle diff --git a/drivers/net/ethernet/ti/am65-cpts.h b/drivers/net/ethernet/ti/am65-cpts.h index 6e14df0be1..6099d77279 100644 --- a/drivers/net/ethernet/ti/am65-cpts.h +++ b/drivers/net/ethernet/ti/am65-cpts.h @@ -22,9 +22,9 @@ void am65_cpts_release(struct am65_cpts *cpts); struct am65_cpts *am65_cpts_create(struct device *dev, void __iomem *regs, struct device_node *node); int am65_cpts_phc_index(struct am65_cpts *cpts); +void am65_cpts_rx_timestamp(struct am65_cpts *cpts, struct sk_buff *skb); void am65_cpts_tx_timestamp(struct am65_cpts *cpts, struct sk_buff *skb); void am65_cpts_prep_tx_timestamp(struct am65_cpts *cpts, struct sk_buff *skb); -void am65_cpts_rx_enable(struct am65_cpts *cpts, bool en); u64 am65_cpts_ns_gettime(struct am65_cpts *cpts); int am65_cpts_estf_enable(struct am65_cpts *cpts, int idx, struct am65_cpts_estf_cfg *cfg); @@ -48,17 +48,18 @@ static inline int am65_cpts_phc_index(struct am65_cpts *cpts) return -1; } -static inline void am65_cpts_tx_timestamp(struct am65_cpts *cpts, +static inline void am65_cpts_rx_timestamp(struct am65_cpts *cpts, struct sk_buff *skb) { } -static inline void am65_cpts_prep_tx_timestamp(struct am65_cpts *cpts, - struct sk_buff *skb) +static inline void am65_cpts_tx_timestamp(struct am65_cpts *cpts, + struct sk_buff *skb) { } -static inline void am65_cpts_rx_enable(struct am65_cpts *cpts, bool en) +static inline void am65_cpts_prep_tx_timestamp(struct am65_cpts *cpts, + struct sk_buff *skb) { } diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c index 087dcb6750..2baa198ebf 100644 --- a/drivers/net/ethernet/ti/cpsw_new.c +++ b/drivers/net/ethernet/ti/cpsw_new.c @@ -1625,7 +1625,8 @@ static int cpsw_dl_switch_mode_get(struct devlink *dl, u32 id, } static int cpsw_dl_switch_mode_set(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct cpsw_devlink *dl_priv = devlink_priv(dl); struct cpsw_common *cpsw = dl_priv->cpsw; @@ -1762,7 +1763,8 @@ static int cpsw_dl_ale_ctrl_get(struct devlink *dl, u32 id, } static int cpsw_dl_ale_ctrl_set(struct devlink *dl, u32 id, - struct devlink_param_gset_ctx *ctx) + struct devlink_param_gset_ctx *ctx, + struct netlink_ext_ack *extack) { struct cpsw_devlink *dl_priv = devlink_priv(dl); struct cpsw_common *cpsw = dl_priv->cpsw; diff --git a/drivers/net/ethernet/ti/cpsw_priv.c b/drivers/net/ethernet/ti/cpsw_priv.c index 764ed298b5..6fe4edabba 100644 --- a/drivers/net/ethernet/ti/cpsw_priv.c +++ b/drivers/net/ethernet/ti/cpsw_priv.c @@ -1404,6 +1404,9 @@ static int cpsw_qos_clsflower_add_policer(struct cpsw_priv *priv, return -EOPNOTSUPP; } + if (flow_rule_match_has_control_flags(rule, extack)) + return -EOPNOTSUPP; + if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { NL_SET_ERR_MSG_MOD(extack, "Not matching on eth address"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/ti/icssg/icssg_classifier.c b/drivers/net/ethernet/ti/icssg/icssg_classifier.c index 902a271778..f7d21da1a0 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_classifier.c +++ b/drivers/net/ethernet/ti/icssg/icssg_classifier.c @@ -274,6 +274,16 @@ static void rx_class_set_or(struct regmap *miig_rt, int slice, int n, regmap_write(miig_rt, offset, data); } +static u32 rx_class_get_or(struct regmap *miig_rt, int slice, int n) +{ + u32 offset, val; + + offset = RX_CLASS_N_REG(slice, n, RX_CLASS_OR_EN); + regmap_read(miig_rt, offset, &val); + + return val; +} + void icssg_class_set_host_mac_addr(struct regmap *miig_rt, const u8 *mac) { regmap_write(miig_rt, MAC_INTERFACE_0, (u32)(mac[0] | mac[1] << 8 | @@ -288,6 +298,26 @@ void icssg_class_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac) regmap_write(miig_rt, offs[slice].mac1, (u32)(mac[4] | mac[5] << 8)); } +static void icssg_class_ft1_add_mcast(struct regmap *miig_rt, int slice, + int slot, const u8 *addr, const u8 *mask) +{ + u32 val; + int i; + + WARN(slot >= FT1_NUM_SLOTS, "invalid slot: %d\n", slot); + + rx_class_ft1_set_da(miig_rt, slice, slot, addr); + rx_class_ft1_set_da_mask(miig_rt, slice, slot, mask); + rx_class_ft1_cfg_set_type(miig_rt, slice, slot, FT1_CFG_TYPE_EQ); + + /* Enable the FT1 slot in OR enable for all classifiers */ + for (i = 0; i < ICSSG_NUM_CLASSIFIERS_IN_USE; i++) { + val = rx_class_get_or(miig_rt, slice, i); + val |= RX_CLASS_FT_FT1_MATCH(slot); + rx_class_set_or(miig_rt, slice, i, val); + } +} + /* disable all RX traffic */ void icssg_class_disable(struct regmap *miig_rt, int slice) { @@ -331,30 +361,95 @@ void icssg_class_disable(struct regmap *miig_rt, int slice) regmap_write(miig_rt, offs[slice].rx_class_cfg2, 0); } -void icssg_class_default(struct regmap *miig_rt, int slice, bool allmulti) +void icssg_class_default(struct regmap *miig_rt, int slice, bool allmulti, + bool is_sr1) { + int num_classifiers = is_sr1 ? ICSSG_NUM_CLASSIFIERS_IN_USE : 1; u32 data; + int n; /* defaults */ icssg_class_disable(miig_rt, slice); /* Setup Classifier */ - /* match on Broadcast or MAC_PRU address */ - data = RX_CLASS_FT_BC | RX_CLASS_FT_DA_P; + for (n = 0; n < num_classifiers; n++) { + /* match on Broadcast or MAC_PRU address */ + data = RX_CLASS_FT_BC | RX_CLASS_FT_DA_P; - /* multicast */ - if (allmulti) - data |= RX_CLASS_FT_MC; + /* multicast */ + if (allmulti) + data |= RX_CLASS_FT_MC; - rx_class_set_or(miig_rt, slice, 0, data); + rx_class_set_or(miig_rt, slice, n, data); - /* set CFG1 for OR_OR_AND for classifier */ - rx_class_sel_set_type(miig_rt, slice, 0, RX_CLASS_SEL_TYPE_OR_OR_AND); + /* set CFG1 for OR_OR_AND for classifier */ + rx_class_sel_set_type(miig_rt, slice, n, + RX_CLASS_SEL_TYPE_OR_OR_AND); + } /* clear CFG2 */ regmap_write(miig_rt, offs[slice].rx_class_cfg2, 0); } +void icssg_class_promiscuous_sr1(struct regmap *miig_rt, int slice) +{ + u32 data, offset; + int n; + + /* defaults */ + icssg_class_disable(miig_rt, slice); + + /* Setup Classifier */ + for (n = 0; n < ICSSG_NUM_CLASSIFIERS_IN_USE; n++) { + /* set RAW_MASK to bypass filters */ + offset = RX_CLASS_GATES_N_REG(slice, n); + regmap_read(miig_rt, offset, &data); + data |= RX_CLASS_GATES_RAW_MASK; + regmap_write(miig_rt, offset, data); + } +} + +void icssg_class_add_mcast_sr1(struct regmap *miig_rt, int slice, + struct net_device *ndev) +{ + u8 mask_addr[6] = { 0, 0, 0, 0, 0, 0xff }; + struct netdev_hw_addr *ha; + int slot = 2; + + rx_class_ft1_set_start_len(miig_rt, slice, 0, 6); + /* reserve first 2 slots for + * 1) 01-80-C2-00-00-XX Known Service Ethernet Multicast addresses + * 2) 01-00-5e-00-00-XX Local Network Control Block + * (224.0.0.0 - 224.0.0.255 (224.0.0/24)) + */ + icssg_class_ft1_add_mcast(miig_rt, slice, 0, + eth_reserved_addr_base, mask_addr); + icssg_class_ft1_add_mcast(miig_rt, slice, 1, + eth_ipv4_mcast_addr_base, mask_addr); + mask_addr[5] = 0; + netdev_for_each_mc_addr(ha, ndev) { + /* skip addresses matching reserved slots */ + if (!memcmp(eth_reserved_addr_base, ha->addr, 5) || + !memcmp(eth_ipv4_mcast_addr_base, ha->addr, 5)) { + netdev_dbg(ndev, "mcast skip %pM\n", ha->addr); + continue; + } + + if (slot >= FT1_NUM_SLOTS) { + netdev_dbg(ndev, + "can't add more than %d MC addresses, enabling allmulti\n", + FT1_NUM_SLOTS); + icssg_class_default(miig_rt, slice, 1, true); + break; + } + + netdev_dbg(ndev, "mcast add %pM\n", ha->addr); + icssg_class_ft1_add_mcast(miig_rt, slice, slot, + ha->addr, mask_addr); + slot++; + } +} + /* required for SAV check */ void icssg_ft1_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac_addr) { diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c new file mode 100644 index 0000000000..088ab8076d --- /dev/null +++ b/drivers/net/ethernet/ti/icssg/icssg_common.c @@ -0,0 +1,1252 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* Texas Instruments ICSSG Ethernet Driver + * + * Copyright (C) 2018-2022 Texas Instruments Incorporated - https://www.ti.com/ + * Copyright (C) Siemens AG, 2024 + * + */ + +#include <linux/dma-mapping.h> +#include <linux/dma/ti-cppi5.h> +#include <linux/etherdevice.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/of.h> +#include <linux/of_mdio.h> +#include <linux/phy.h> +#include <linux/remoteproc/pruss.h> +#include <linux/regmap.h> +#include <linux/remoteproc.h> + +#include "icssg_prueth.h" +#include "../k3-cppi-desc-pool.h" + +/* Netif debug messages possible */ +#define PRUETH_EMAC_DEBUG (NETIF_MSG_DRV | \ + NETIF_MSG_PROBE | \ + NETIF_MSG_LINK | \ + NETIF_MSG_TIMER | \ + NETIF_MSG_IFDOWN | \ + NETIF_MSG_IFUP | \ + NETIF_MSG_RX_ERR | \ + NETIF_MSG_TX_ERR | \ + NETIF_MSG_TX_QUEUED | \ + NETIF_MSG_INTR | \ + NETIF_MSG_TX_DONE | \ + NETIF_MSG_RX_STATUS | \ + NETIF_MSG_PKTDATA | \ + NETIF_MSG_HW | \ + NETIF_MSG_WOL) + +#define prueth_napi_to_emac(napi) container_of(napi, struct prueth_emac, napi_rx) + +void prueth_cleanup_rx_chns(struct prueth_emac *emac, + struct prueth_rx_chn *rx_chn, + int max_rflows) +{ + if (rx_chn->desc_pool) + k3_cppi_desc_pool_destroy(rx_chn->desc_pool); + + if (rx_chn->rx_chn) + k3_udma_glue_release_rx_chn(rx_chn->rx_chn); +} + +void prueth_cleanup_tx_chns(struct prueth_emac *emac) +{ + int i; + + for (i = 0; i < emac->tx_ch_num; i++) { + struct prueth_tx_chn *tx_chn = &emac->tx_chns[i]; + + if (tx_chn->desc_pool) + k3_cppi_desc_pool_destroy(tx_chn->desc_pool); + + if (tx_chn->tx_chn) + k3_udma_glue_release_tx_chn(tx_chn->tx_chn); + + /* Assume prueth_cleanup_tx_chns() is called at the + * end after all channel resources are freed + */ + memset(tx_chn, 0, sizeof(*tx_chn)); + } +} + +void prueth_ndev_del_tx_napi(struct prueth_emac *emac, int num) +{ + int i; + + for (i = 0; i < num; i++) { + struct prueth_tx_chn *tx_chn = &emac->tx_chns[i]; + + if (tx_chn->irq) + free_irq(tx_chn->irq, tx_chn); + netif_napi_del(&tx_chn->napi_tx); + } +} + +void prueth_xmit_free(struct prueth_tx_chn *tx_chn, + struct cppi5_host_desc_t *desc) +{ + struct cppi5_host_desc_t *first_desc, *next_desc; + dma_addr_t buf_dma, next_desc_dma; + u32 buf_dma_len; + + first_desc = desc; + next_desc = first_desc; + + cppi5_hdesc_get_obuf(first_desc, &buf_dma, &buf_dma_len); + k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &buf_dma); + + dma_unmap_single(tx_chn->dma_dev, buf_dma, buf_dma_len, + DMA_TO_DEVICE); + + next_desc_dma = cppi5_hdesc_get_next_hbdesc(first_desc); + k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &next_desc_dma); + while (next_desc_dma) { + next_desc = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, + next_desc_dma); + cppi5_hdesc_get_obuf(next_desc, &buf_dma, &buf_dma_len); + k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &buf_dma); + + dma_unmap_page(tx_chn->dma_dev, buf_dma, buf_dma_len, + DMA_TO_DEVICE); + + next_desc_dma = cppi5_hdesc_get_next_hbdesc(next_desc); + k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &next_desc_dma); + + k3_cppi_desc_pool_free(tx_chn->desc_pool, next_desc); + } + + k3_cppi_desc_pool_free(tx_chn->desc_pool, first_desc); +} + +int emac_tx_complete_packets(struct prueth_emac *emac, int chn, + int budget, bool *tdown) +{ + struct net_device *ndev = emac->ndev; + struct cppi5_host_desc_t *desc_tx; + struct netdev_queue *netif_txq; + struct prueth_tx_chn *tx_chn; + unsigned int total_bytes = 0; + struct sk_buff *skb; + dma_addr_t desc_dma; + int res, num_tx = 0; + void **swdata; + + tx_chn = &emac->tx_chns[chn]; + + while (true) { + res = k3_udma_glue_pop_tx_chn(tx_chn->tx_chn, &desc_dma); + if (res == -ENODATA) + break; + + /* teardown completion */ + if (cppi5_desc_is_tdcm(desc_dma)) { + if (atomic_dec_and_test(&emac->tdown_cnt)) + complete(&emac->tdown_complete); + *tdown = true; + break; + } + + desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, + desc_dma); + swdata = cppi5_hdesc_get_swdata(desc_tx); + + /* was this command's TX complete? */ + if (emac->is_sr1 && *(swdata) == emac->cmd_data) { + prueth_xmit_free(tx_chn, desc_tx); + continue; + } + + skb = *(swdata); + prueth_xmit_free(tx_chn, desc_tx); + + ndev = skb->dev; + ndev->stats.tx_packets++; + ndev->stats.tx_bytes += skb->len; + total_bytes += skb->len; + napi_consume_skb(skb, budget); + num_tx++; + } + + if (!num_tx) + return 0; + + netif_txq = netdev_get_tx_queue(ndev, chn); + netdev_tx_completed_queue(netif_txq, num_tx, total_bytes); + + if (netif_tx_queue_stopped(netif_txq)) { + /* If the TX queue was stopped, wake it now + * if we have enough room. + */ + __netif_tx_lock(netif_txq, smp_processor_id()); + if (netif_running(ndev) && + (k3_cppi_desc_pool_avail(tx_chn->desc_pool) >= + MAX_SKB_FRAGS)) + netif_tx_wake_queue(netif_txq); + __netif_tx_unlock(netif_txq); + } + + return num_tx; +} + +static enum hrtimer_restart emac_tx_timer_callback(struct hrtimer *timer) +{ + struct prueth_tx_chn *tx_chns = + container_of(timer, struct prueth_tx_chn, tx_hrtimer); + + enable_irq(tx_chns->irq); + return HRTIMER_NORESTART; +} + +static int emac_napi_tx_poll(struct napi_struct *napi_tx, int budget) +{ + struct prueth_tx_chn *tx_chn = prueth_napi_to_tx_chn(napi_tx); + struct prueth_emac *emac = tx_chn->emac; + bool tdown = false; + int num_tx_packets; + + num_tx_packets = emac_tx_complete_packets(emac, tx_chn->id, budget, + &tdown); + + if (num_tx_packets >= budget) + return budget; + + if (napi_complete_done(napi_tx, num_tx_packets)) { + if (unlikely(tx_chn->tx_pace_timeout_ns && !tdown)) { + hrtimer_start(&tx_chn->tx_hrtimer, + ns_to_ktime(tx_chn->tx_pace_timeout_ns), + HRTIMER_MODE_REL_PINNED); + } else { + enable_irq(tx_chn->irq); + } + } + + return num_tx_packets; +} + +static irqreturn_t prueth_tx_irq(int irq, void *dev_id) +{ + struct prueth_tx_chn *tx_chn = dev_id; + + disable_irq_nosync(irq); + napi_schedule(&tx_chn->napi_tx); + + return IRQ_HANDLED; +} + +int prueth_ndev_add_tx_napi(struct prueth_emac *emac) +{ + struct prueth *prueth = emac->prueth; + int i, ret; + + for (i = 0; i < emac->tx_ch_num; i++) { + struct prueth_tx_chn *tx_chn = &emac->tx_chns[i]; + + netif_napi_add_tx(emac->ndev, &tx_chn->napi_tx, emac_napi_tx_poll); + hrtimer_init(&tx_chn->tx_hrtimer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_PINNED); + tx_chn->tx_hrtimer.function = &emac_tx_timer_callback; + ret = request_irq(tx_chn->irq, prueth_tx_irq, + IRQF_TRIGGER_HIGH, tx_chn->name, + tx_chn); + if (ret) { + netif_napi_del(&tx_chn->napi_tx); + dev_err(prueth->dev, "unable to request TX IRQ %d\n", + tx_chn->irq); + goto fail; + } + } + + return 0; +fail: + prueth_ndev_del_tx_napi(emac, i); + return ret; +} + +int prueth_init_tx_chns(struct prueth_emac *emac) +{ + static const struct k3_ring_cfg ring_cfg = { + .elm_size = K3_RINGACC_RING_ELSIZE_8, + .mode = K3_RINGACC_RING_MODE_RING, + .flags = 0, + .size = PRUETH_MAX_TX_DESC, + }; + struct k3_udma_glue_tx_channel_cfg tx_cfg; + struct device *dev = emac->prueth->dev; + struct net_device *ndev = emac->ndev; + int ret, slice, i; + u32 hdesc_size; + + slice = prueth_emac_slice(emac); + if (slice < 0) + return slice; + + init_completion(&emac->tdown_complete); + + hdesc_size = cppi5_hdesc_calc_size(true, PRUETH_NAV_PS_DATA_SIZE, + PRUETH_NAV_SW_DATA_SIZE); + memset(&tx_cfg, 0, sizeof(tx_cfg)); + tx_cfg.swdata_size = PRUETH_NAV_SW_DATA_SIZE; + tx_cfg.tx_cfg = ring_cfg; + tx_cfg.txcq_cfg = ring_cfg; + + for (i = 0; i < emac->tx_ch_num; i++) { + struct prueth_tx_chn *tx_chn = &emac->tx_chns[i]; + + /* To differentiate channels for SLICE0 vs SLICE1 */ + snprintf(tx_chn->name, sizeof(tx_chn->name), + "tx%d-%d", slice, i); + + tx_chn->emac = emac; + tx_chn->id = i; + tx_chn->descs_num = PRUETH_MAX_TX_DESC; + + tx_chn->tx_chn = + k3_udma_glue_request_tx_chn(dev, tx_chn->name, + &tx_cfg); + if (IS_ERR(tx_chn->tx_chn)) { + ret = PTR_ERR(tx_chn->tx_chn); + tx_chn->tx_chn = NULL; + netdev_err(ndev, + "Failed to request tx dma ch: %d\n", ret); + goto fail; + } + + tx_chn->dma_dev = k3_udma_glue_tx_get_dma_device(tx_chn->tx_chn); + tx_chn->desc_pool = + k3_cppi_desc_pool_create_name(tx_chn->dma_dev, + tx_chn->descs_num, + hdesc_size, + tx_chn->name); + if (IS_ERR(tx_chn->desc_pool)) { + ret = PTR_ERR(tx_chn->desc_pool); + tx_chn->desc_pool = NULL; + netdev_err(ndev, "Failed to create tx pool: %d\n", ret); + goto fail; + } + + ret = k3_udma_glue_tx_get_irq(tx_chn->tx_chn); + if (ret < 0) { + netdev_err(ndev, "failed to get tx irq\n"); + goto fail; + } + tx_chn->irq = ret; + + snprintf(tx_chn->name, sizeof(tx_chn->name), "%s-tx%d", + dev_name(dev), tx_chn->id); + } + + return 0; + +fail: + prueth_cleanup_tx_chns(emac); + return ret; +} + +int prueth_init_rx_chns(struct prueth_emac *emac, + struct prueth_rx_chn *rx_chn, + char *name, u32 max_rflows, + u32 max_desc_num) +{ + struct k3_udma_glue_rx_channel_cfg rx_cfg; + struct device *dev = emac->prueth->dev; + struct net_device *ndev = emac->ndev; + u32 fdqring_id, hdesc_size; + int i, ret = 0, slice; + int flow_id_base; + + slice = prueth_emac_slice(emac); + if (slice < 0) + return slice; + + /* To differentiate channels for SLICE0 vs SLICE1 */ + snprintf(rx_chn->name, sizeof(rx_chn->name), "%s%d", name, slice); + + hdesc_size = cppi5_hdesc_calc_size(true, PRUETH_NAV_PS_DATA_SIZE, + PRUETH_NAV_SW_DATA_SIZE); + memset(&rx_cfg, 0, sizeof(rx_cfg)); + rx_cfg.swdata_size = PRUETH_NAV_SW_DATA_SIZE; + rx_cfg.flow_id_num = max_rflows; + rx_cfg.flow_id_base = -1; /* udmax will auto select flow id base */ + + /* init all flows */ + rx_chn->dev = dev; + rx_chn->descs_num = max_desc_num; + + rx_chn->rx_chn = k3_udma_glue_request_rx_chn(dev, rx_chn->name, + &rx_cfg); + if (IS_ERR(rx_chn->rx_chn)) { + ret = PTR_ERR(rx_chn->rx_chn); + rx_chn->rx_chn = NULL; + netdev_err(ndev, "Failed to request rx dma ch: %d\n", ret); + goto fail; + } + + rx_chn->dma_dev = k3_udma_glue_rx_get_dma_device(rx_chn->rx_chn); + rx_chn->desc_pool = k3_cppi_desc_pool_create_name(rx_chn->dma_dev, + rx_chn->descs_num, + hdesc_size, + rx_chn->name); + if (IS_ERR(rx_chn->desc_pool)) { + ret = PTR_ERR(rx_chn->desc_pool); + rx_chn->desc_pool = NULL; + netdev_err(ndev, "Failed to create rx pool: %d\n", ret); + goto fail; + } + + flow_id_base = k3_udma_glue_rx_get_flow_id_base(rx_chn->rx_chn); + if (emac->is_sr1 && !strcmp(name, "rxmgm")) { + emac->rx_mgm_flow_id_base = flow_id_base; + netdev_dbg(ndev, "mgm flow id base = %d\n", flow_id_base); + } else { + emac->rx_flow_id_base = flow_id_base; + netdev_dbg(ndev, "flow id base = %d\n", flow_id_base); + } + + fdqring_id = K3_RINGACC_RING_ID_ANY; + for (i = 0; i < rx_cfg.flow_id_num; i++) { + struct k3_ring_cfg rxring_cfg = { + .elm_size = K3_RINGACC_RING_ELSIZE_8, + .mode = K3_RINGACC_RING_MODE_RING, + .flags = 0, + }; + struct k3_ring_cfg fdqring_cfg = { + .elm_size = K3_RINGACC_RING_ELSIZE_8, + .flags = K3_RINGACC_RING_SHARED, + }; + struct k3_udma_glue_rx_flow_cfg rx_flow_cfg = { + .rx_cfg = rxring_cfg, + .rxfdq_cfg = fdqring_cfg, + .ring_rxq_id = K3_RINGACC_RING_ID_ANY, + .src_tag_lo_sel = + K3_UDMA_GLUE_SRC_TAG_LO_USE_REMOTE_SRC_TAG, + }; + + rx_flow_cfg.ring_rxfdq0_id = fdqring_id; + rx_flow_cfg.rx_cfg.size = max_desc_num; + rx_flow_cfg.rxfdq_cfg.size = max_desc_num; + rx_flow_cfg.rxfdq_cfg.mode = emac->prueth->pdata.fdqring_mode; + + ret = k3_udma_glue_rx_flow_init(rx_chn->rx_chn, + i, &rx_flow_cfg); + if (ret) { + netdev_err(ndev, "Failed to init rx flow%d %d\n", + i, ret); + goto fail; + } + if (!i) + fdqring_id = k3_udma_glue_rx_flow_get_fdq_id(rx_chn->rx_chn, + i); + ret = k3_udma_glue_rx_get_irq(rx_chn->rx_chn, i); + if (ret <= 0) { + if (!ret) + ret = -ENXIO; + netdev_err(ndev, "Failed to get rx dma irq"); + goto fail; + } + rx_chn->irq[i] = ret; + } + + return 0; + +fail: + prueth_cleanup_rx_chns(emac, rx_chn, max_rflows); + return ret; +} + +int prueth_dma_rx_push(struct prueth_emac *emac, + struct sk_buff *skb, + struct prueth_rx_chn *rx_chn) +{ + struct net_device *ndev = emac->ndev; + struct cppi5_host_desc_t *desc_rx; + u32 pkt_len = skb_tailroom(skb); + dma_addr_t desc_dma; + dma_addr_t buf_dma; + void **swdata; + + desc_rx = k3_cppi_desc_pool_alloc(rx_chn->desc_pool); + if (!desc_rx) { + netdev_err(ndev, "rx push: failed to allocate descriptor\n"); + return -ENOMEM; + } + desc_dma = k3_cppi_desc_pool_virt2dma(rx_chn->desc_pool, desc_rx); + + buf_dma = dma_map_single(rx_chn->dma_dev, skb->data, pkt_len, DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(rx_chn->dma_dev, buf_dma))) { + k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); + netdev_err(ndev, "rx push: failed to map rx pkt buffer\n"); + return -EINVAL; + } + + cppi5_hdesc_init(desc_rx, CPPI5_INFO0_HDESC_EPIB_PRESENT, + PRUETH_NAV_PS_DATA_SIZE); + k3_udma_glue_rx_dma_to_cppi5_addr(rx_chn->rx_chn, &buf_dma); + cppi5_hdesc_attach_buf(desc_rx, buf_dma, skb_tailroom(skb), buf_dma, skb_tailroom(skb)); + + swdata = cppi5_hdesc_get_swdata(desc_rx); + *swdata = skb; + + return k3_udma_glue_push_rx_chn(rx_chn->rx_chn, 0, + desc_rx, desc_dma); +} + +u64 icssg_ts_to_ns(u32 hi_sw, u32 hi, u32 lo, u32 cycle_time_ns) +{ + u32 iepcount_lo, iepcount_hi, hi_rollover_count; + u64 ns; + + iepcount_lo = lo & GENMASK(19, 0); + iepcount_hi = (hi & GENMASK(11, 0)) << 12 | lo >> 20; + hi_rollover_count = hi >> 11; + + ns = ((u64)hi_rollover_count) << 23 | (iepcount_hi + hi_sw); + ns = ns * cycle_time_ns + iepcount_lo; + + return ns; +} + +void emac_rx_timestamp(struct prueth_emac *emac, + struct sk_buff *skb, u32 *psdata) +{ + struct skb_shared_hwtstamps *ssh; + u64 ns; + + if (emac->is_sr1) { + ns = (u64)psdata[1] << 32 | psdata[0]; + } else { + u32 hi_sw = readl(emac->prueth->shram.va + + TIMESYNC_FW_WC_COUNT_HI_SW_OFFSET_OFFSET); + ns = icssg_ts_to_ns(hi_sw, psdata[1], psdata[0], + IEP_DEFAULT_CYCLE_TIME_NS); + } + + ssh = skb_hwtstamps(skb); + memset(ssh, 0, sizeof(*ssh)); + ssh->hwtstamp = ns_to_ktime(ns); +} + +static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id) +{ + struct prueth_rx_chn *rx_chn = &emac->rx_chns; + u32 buf_dma_len, pkt_len, port_id = 0; + struct net_device *ndev = emac->ndev; + struct cppi5_host_desc_t *desc_rx; + struct sk_buff *skb, *new_skb; + dma_addr_t desc_dma, buf_dma; + void **swdata; + u32 *psdata; + int ret; + + ret = k3_udma_glue_pop_rx_chn(rx_chn->rx_chn, flow_id, &desc_dma); + if (ret) { + if (ret != -ENODATA) + netdev_err(ndev, "rx pop: failed: %d\n", ret); + return ret; + } + + if (cppi5_desc_is_tdcm(desc_dma)) /* Teardown ? */ + return 0; + + desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma); + + swdata = cppi5_hdesc_get_swdata(desc_rx); + skb = *swdata; + + psdata = cppi5_hdesc_get_psdata(desc_rx); + /* RX HW timestamp */ + if (emac->rx_ts_enabled) + emac_rx_timestamp(emac, skb, psdata); + + cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len); + k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma); + pkt_len = cppi5_hdesc_get_pktlen(desc_rx); + /* firmware adds 4 CRC bytes, strip them */ + pkt_len -= 4; + cppi5_desc_get_tags_ids(&desc_rx->hdr, &port_id, NULL); + + dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE); + k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); + + skb->dev = ndev; + new_skb = netdev_alloc_skb_ip_align(ndev, PRUETH_MAX_PKT_SIZE); + /* if allocation fails we drop the packet but push the + * descriptor back to the ring with old skb to prevent a stall + */ + if (!new_skb) { + ndev->stats.rx_dropped++; + new_skb = skb; + } else { + /* send the filled skb up the n/w stack */ + skb_put(skb, pkt_len); + skb->protocol = eth_type_trans(skb, ndev); + napi_gro_receive(&emac->napi_rx, skb); + ndev->stats.rx_bytes += pkt_len; + ndev->stats.rx_packets++; + } + + /* queue another RX DMA */ + ret = prueth_dma_rx_push(emac, new_skb, &emac->rx_chns); + if (WARN_ON(ret < 0)) { + dev_kfree_skb_any(new_skb); + ndev->stats.rx_errors++; + ndev->stats.rx_dropped++; + } + + return ret; +} + +static void prueth_rx_cleanup(void *data, dma_addr_t desc_dma) +{ + struct prueth_rx_chn *rx_chn = data; + struct cppi5_host_desc_t *desc_rx; + struct sk_buff *skb; + dma_addr_t buf_dma; + u32 buf_dma_len; + void **swdata; + + desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma); + swdata = cppi5_hdesc_get_swdata(desc_rx); + skb = *swdata; + cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len); + k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma); + + dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, + DMA_FROM_DEVICE); + k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); + + dev_kfree_skb_any(skb); +} + +static int prueth_tx_ts_cookie_get(struct prueth_emac *emac) +{ + int i; + + /* search and get the next free slot */ + for (i = 0; i < PRUETH_MAX_TX_TS_REQUESTS; i++) { + if (!emac->tx_ts_skb[i]) { + emac->tx_ts_skb[i] = ERR_PTR(-EBUSY); /* reserve slot */ + return i; + } + } + + return -EBUSY; +} + +/** + * emac_ndo_start_xmit - EMAC Transmit function + * @skb: SKB pointer + * @ndev: EMAC network adapter + * + * Called by the system to transmit a packet - we queue the packet in + * EMAC hardware transmit queue + * Doesn't wait for completion we'll check for TX completion in + * emac_tx_complete_packets(). + * + * Return: enum netdev_tx + */ +enum netdev_tx emac_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev) +{ + struct cppi5_host_desc_t *first_desc, *next_desc, *cur_desc; + struct prueth_emac *emac = netdev_priv(ndev); + struct netdev_queue *netif_txq; + struct prueth_tx_chn *tx_chn; + dma_addr_t desc_dma, buf_dma; + int i, ret = 0, q_idx; + bool in_tx_ts = 0; + int tx_ts_cookie; + void **swdata; + u32 pkt_len; + u32 *epib; + + pkt_len = skb_headlen(skb); + q_idx = skb_get_queue_mapping(skb); + + tx_chn = &emac->tx_chns[q_idx]; + netif_txq = netdev_get_tx_queue(ndev, q_idx); + + /* Map the linear buffer */ + buf_dma = dma_map_single(tx_chn->dma_dev, skb->data, pkt_len, DMA_TO_DEVICE); + if (dma_mapping_error(tx_chn->dma_dev, buf_dma)) { + netdev_err(ndev, "tx: failed to map skb buffer\n"); + ret = NETDEV_TX_OK; + goto drop_free_skb; + } + + first_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool); + if (!first_desc) { + netdev_dbg(ndev, "tx: failed to allocate descriptor\n"); + dma_unmap_single(tx_chn->dma_dev, buf_dma, pkt_len, DMA_TO_DEVICE); + goto drop_stop_q_busy; + } + + cppi5_hdesc_init(first_desc, CPPI5_INFO0_HDESC_EPIB_PRESENT, + PRUETH_NAV_PS_DATA_SIZE); + cppi5_hdesc_set_pkttype(first_desc, 0); + epib = first_desc->epib; + epib[0] = 0; + epib[1] = 0; + if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP && + emac->tx_ts_enabled) { + tx_ts_cookie = prueth_tx_ts_cookie_get(emac); + if (tx_ts_cookie >= 0) { + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + /* Request TX timestamp */ + epib[0] = (u32)tx_ts_cookie; + epib[1] = 0x80000000; /* TX TS request */ + emac->tx_ts_skb[tx_ts_cookie] = skb_get(skb); + in_tx_ts = 1; + } + } + + /* set dst tag to indicate internal qid at the firmware which is at + * bit8..bit15. bit0..bit7 indicates port num for directed + * packets in case of switch mode operation + */ + cppi5_desc_set_tags_ids(&first_desc->hdr, 0, (emac->port_id | (q_idx << 8))); + k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma); + cppi5_hdesc_attach_buf(first_desc, buf_dma, pkt_len, buf_dma, pkt_len); + swdata = cppi5_hdesc_get_swdata(first_desc); + *swdata = skb; + + /* Handle the case where skb is fragmented in pages */ + cur_desc = first_desc; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + u32 frag_size = skb_frag_size(frag); + + next_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool); + if (!next_desc) { + netdev_err(ndev, + "tx: failed to allocate frag. descriptor\n"); + goto free_desc_stop_q_busy_cleanup_tx_ts; + } + + buf_dma = skb_frag_dma_map(tx_chn->dma_dev, frag, 0, frag_size, + DMA_TO_DEVICE); + if (dma_mapping_error(tx_chn->dma_dev, buf_dma)) { + netdev_err(ndev, "tx: Failed to map skb page\n"); + k3_cppi_desc_pool_free(tx_chn->desc_pool, next_desc); + ret = NETDEV_TX_OK; + goto cleanup_tx_ts; + } + + cppi5_hdesc_reset_hbdesc(next_desc); + k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma); + cppi5_hdesc_attach_buf(next_desc, + buf_dma, frag_size, buf_dma, frag_size); + + desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, + next_desc); + k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &desc_dma); + cppi5_hdesc_link_hbdesc(cur_desc, desc_dma); + + pkt_len += frag_size; + cur_desc = next_desc; + } + WARN_ON_ONCE(pkt_len != skb->len); + + /* report bql before sending packet */ + netdev_tx_sent_queue(netif_txq, pkt_len); + + cppi5_hdesc_set_pktlen(first_desc, pkt_len); + desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, first_desc); + /* cppi5_desc_dump(first_desc, 64); */ + + skb_tx_timestamp(skb); /* SW timestamp if SKBTX_IN_PROGRESS not set */ + ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma); + if (ret) { + netdev_err(ndev, "tx: push failed: %d\n", ret); + goto drop_free_descs; + } + + if (in_tx_ts) + atomic_inc(&emac->tx_ts_pending); + + if (k3_cppi_desc_pool_avail(tx_chn->desc_pool) < MAX_SKB_FRAGS) { + netif_tx_stop_queue(netif_txq); + /* Barrier, so that stop_queue visible to other cpus */ + smp_mb__after_atomic(); + + if (k3_cppi_desc_pool_avail(tx_chn->desc_pool) >= + MAX_SKB_FRAGS) + netif_tx_wake_queue(netif_txq); + } + + return NETDEV_TX_OK; + +cleanup_tx_ts: + if (in_tx_ts) { + dev_kfree_skb_any(emac->tx_ts_skb[tx_ts_cookie]); + emac->tx_ts_skb[tx_ts_cookie] = NULL; + } + +drop_free_descs: + prueth_xmit_free(tx_chn, first_desc); + +drop_free_skb: + dev_kfree_skb_any(skb); + + /* error */ + ndev->stats.tx_dropped++; + netdev_err(ndev, "tx: error: %d\n", ret); + + return ret; + +free_desc_stop_q_busy_cleanup_tx_ts: + if (in_tx_ts) { + dev_kfree_skb_any(emac->tx_ts_skb[tx_ts_cookie]); + emac->tx_ts_skb[tx_ts_cookie] = NULL; + } + prueth_xmit_free(tx_chn, first_desc); + +drop_stop_q_busy: + netif_tx_stop_queue(netif_txq); + return NETDEV_TX_BUSY; +} + +static void prueth_tx_cleanup(void *data, dma_addr_t desc_dma) +{ + struct prueth_tx_chn *tx_chn = data; + struct cppi5_host_desc_t *desc_tx; + struct sk_buff *skb; + void **swdata; + + desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma); + swdata = cppi5_hdesc_get_swdata(desc_tx); + skb = *(swdata); + prueth_xmit_free(tx_chn, desc_tx); + + dev_kfree_skb_any(skb); +} + +irqreturn_t prueth_rx_irq(int irq, void *dev_id) +{ + struct prueth_emac *emac = dev_id; + + disable_irq_nosync(irq); + napi_schedule(&emac->napi_rx); + + return IRQ_HANDLED; +} + +void prueth_emac_stop(struct prueth_emac *emac) +{ + struct prueth *prueth = emac->prueth; + int slice; + + switch (emac->port_id) { + case PRUETH_PORT_MII0: + slice = ICSS_SLICE0; + break; + case PRUETH_PORT_MII1: + slice = ICSS_SLICE1; + break; + default: + netdev_err(emac->ndev, "invalid port\n"); + return; + } + + emac->fw_running = 0; + if (!emac->is_sr1) + rproc_shutdown(prueth->txpru[slice]); + rproc_shutdown(prueth->rtu[slice]); + rproc_shutdown(prueth->pru[slice]); +} + +void prueth_cleanup_tx_ts(struct prueth_emac *emac) +{ + int i; + + for (i = 0; i < PRUETH_MAX_TX_TS_REQUESTS; i++) { + if (emac->tx_ts_skb[i]) { + dev_kfree_skb_any(emac->tx_ts_skb[i]); + emac->tx_ts_skb[i] = NULL; + } + } +} + +int emac_napi_rx_poll(struct napi_struct *napi_rx, int budget) +{ + struct prueth_emac *emac = prueth_napi_to_emac(napi_rx); + int rx_flow = emac->is_sr1 ? + PRUETH_RX_FLOW_DATA_SR1 : PRUETH_RX_FLOW_DATA; + int flow = emac->is_sr1 ? + PRUETH_MAX_RX_FLOWS_SR1 : PRUETH_MAX_RX_FLOWS; + int num_rx = 0; + int cur_budget; + int ret; + + while (flow--) { + cur_budget = budget - num_rx; + + while (cur_budget--) { + ret = emac_rx_packet(emac, flow); + if (ret) + break; + num_rx++; + } + + if (num_rx >= budget) + break; + } + + if (num_rx < budget && napi_complete_done(napi_rx, num_rx)) { + if (unlikely(emac->rx_pace_timeout_ns)) { + hrtimer_start(&emac->rx_hrtimer, + ns_to_ktime(emac->rx_pace_timeout_ns), + HRTIMER_MODE_REL_PINNED); + } else { + enable_irq(emac->rx_chns.irq[rx_flow]); + } + } + + return num_rx; +} + +int prueth_prepare_rx_chan(struct prueth_emac *emac, + struct prueth_rx_chn *chn, + int buf_size) +{ + struct sk_buff *skb; + int i, ret; + + for (i = 0; i < chn->descs_num; i++) { + skb = __netdev_alloc_skb_ip_align(NULL, buf_size, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + ret = prueth_dma_rx_push(emac, skb, chn); + if (ret < 0) { + netdev_err(emac->ndev, + "cannot submit skb for rx chan %s ret %d\n", + chn->name, ret); + kfree_skb(skb); + return ret; + } + } + + return 0; +} + +void prueth_reset_tx_chan(struct prueth_emac *emac, int ch_num, + bool free_skb) +{ + int i; + + for (i = 0; i < ch_num; i++) { + if (free_skb) + k3_udma_glue_reset_tx_chn(emac->tx_chns[i].tx_chn, + &emac->tx_chns[i], + prueth_tx_cleanup); + k3_udma_glue_disable_tx_chn(emac->tx_chns[i].tx_chn); + } +} + +void prueth_reset_rx_chan(struct prueth_rx_chn *chn, + int num_flows, bool disable) +{ + int i; + + for (i = 0; i < num_flows; i++) + k3_udma_glue_reset_rx_chn(chn->rx_chn, i, chn, + prueth_rx_cleanup, !!i); + if (disable) + k3_udma_glue_disable_rx_chn(chn->rx_chn); +} + +void emac_ndo_tx_timeout(struct net_device *ndev, unsigned int txqueue) +{ + ndev->stats.tx_errors++; +} + +static int emac_set_ts_config(struct net_device *ndev, struct ifreq *ifr) +{ + struct prueth_emac *emac = netdev_priv(ndev); + struct hwtstamp_config config; + + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) + return -EFAULT; + + switch (config.tx_type) { + case HWTSTAMP_TX_OFF: + emac->tx_ts_enabled = 0; + break; + case HWTSTAMP_TX_ON: + emac->tx_ts_enabled = 1; + break; + default: + return -ERANGE; + } + + switch (config.rx_filter) { + case HWTSTAMP_FILTER_NONE: + emac->rx_ts_enabled = 0; + break; + case HWTSTAMP_FILTER_ALL: + case HWTSTAMP_FILTER_SOME: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + case HWTSTAMP_FILTER_NTP_ALL: + emac->rx_ts_enabled = 1; + config.rx_filter = HWTSTAMP_FILTER_ALL; + break; + default: + return -ERANGE; + } + + return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? + -EFAULT : 0; +} + +static int emac_get_ts_config(struct net_device *ndev, struct ifreq *ifr) +{ + struct prueth_emac *emac = netdev_priv(ndev); + struct hwtstamp_config config; + + config.flags = 0; + config.tx_type = emac->tx_ts_enabled ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; + config.rx_filter = emac->rx_ts_enabled ? HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE; + + return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? + -EFAULT : 0; +} + +int emac_ndo_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd) +{ + switch (cmd) { + case SIOCGHWTSTAMP: + return emac_get_ts_config(ndev, ifr); + case SIOCSHWTSTAMP: + return emac_set_ts_config(ndev, ifr); + default: + break; + } + + return phy_do_ioctl(ndev, ifr, cmd); +} + +void emac_ndo_get_stats64(struct net_device *ndev, + struct rtnl_link_stats64 *stats) +{ + struct prueth_emac *emac = netdev_priv(ndev); + + emac_update_hardware_stats(emac); + + stats->rx_packets = emac_get_stat_by_name(emac, "rx_packets"); + stats->rx_bytes = emac_get_stat_by_name(emac, "rx_bytes"); + stats->tx_packets = emac_get_stat_by_name(emac, "tx_packets"); + stats->tx_bytes = emac_get_stat_by_name(emac, "tx_bytes"); + stats->rx_crc_errors = emac_get_stat_by_name(emac, "rx_crc_errors"); + stats->rx_over_errors = emac_get_stat_by_name(emac, "rx_over_errors"); + stats->multicast = emac_get_stat_by_name(emac, "rx_multicast_frames"); + + stats->rx_errors = ndev->stats.rx_errors; + stats->rx_dropped = ndev->stats.rx_dropped; + stats->tx_errors = ndev->stats.tx_errors; + stats->tx_dropped = ndev->stats.tx_dropped; +} + +int emac_ndo_get_phys_port_name(struct net_device *ndev, char *name, + size_t len) +{ + struct prueth_emac *emac = netdev_priv(ndev); + int ret; + + ret = snprintf(name, len, "p%d", emac->port_id); + if (ret >= len) + return -EINVAL; + + return 0; +} + +/* get emac_port corresponding to eth_node name */ +int prueth_node_port(struct device_node *eth_node) +{ + u32 port_id; + int ret; + + ret = of_property_read_u32(eth_node, "reg", &port_id); + if (ret) + return ret; + + if (port_id == 0) + return PRUETH_PORT_MII0; + else if (port_id == 1) + return PRUETH_PORT_MII1; + else + return PRUETH_PORT_INVALID; +} + +/* get MAC instance corresponding to eth_node name */ +int prueth_node_mac(struct device_node *eth_node) +{ + u32 port_id; + int ret; + + ret = of_property_read_u32(eth_node, "reg", &port_id); + if (ret) + return ret; + + if (port_id == 0) + return PRUETH_MAC0; + else if (port_id == 1) + return PRUETH_MAC1; + else + return PRUETH_MAC_INVALID; +} + +void prueth_netdev_exit(struct prueth *prueth, + struct device_node *eth_node) +{ + struct prueth_emac *emac; + enum prueth_mac mac; + + mac = prueth_node_mac(eth_node); + if (mac == PRUETH_MAC_INVALID) + return; + + emac = prueth->emac[mac]; + if (!emac) + return; + + if (of_phy_is_fixed_link(emac->phy_node)) + of_phy_deregister_fixed_link(emac->phy_node); + + netif_napi_del(&emac->napi_rx); + + pruss_release_mem_region(prueth->pruss, &emac->dram); + destroy_workqueue(emac->cmd_wq); + free_netdev(emac->ndev); + prueth->emac[mac] = NULL; +} + +int prueth_get_cores(struct prueth *prueth, int slice, bool is_sr1) +{ + struct device *dev = prueth->dev; + enum pruss_pru_id pruss_id; + struct device_node *np; + int idx = -1, ret; + + np = dev->of_node; + + switch (slice) { + case ICSS_SLICE0: + idx = 0; + break; + case ICSS_SLICE1: + idx = is_sr1 ? 2 : 3; + break; + default: + return -EINVAL; + } + + prueth->pru[slice] = pru_rproc_get(np, idx, &pruss_id); + if (IS_ERR(prueth->pru[slice])) { + ret = PTR_ERR(prueth->pru[slice]); + prueth->pru[slice] = NULL; + return dev_err_probe(dev, ret, "unable to get PRU%d\n", slice); + } + prueth->pru_id[slice] = pruss_id; + + idx++; + prueth->rtu[slice] = pru_rproc_get(np, idx, NULL); + if (IS_ERR(prueth->rtu[slice])) { + ret = PTR_ERR(prueth->rtu[slice]); + prueth->rtu[slice] = NULL; + return dev_err_probe(dev, ret, "unable to get RTU%d\n", slice); + } + + if (is_sr1) + return 0; + + idx++; + prueth->txpru[slice] = pru_rproc_get(np, idx, NULL); + if (IS_ERR(prueth->txpru[slice])) { + ret = PTR_ERR(prueth->txpru[slice]); + prueth->txpru[slice] = NULL; + return dev_err_probe(dev, ret, "unable to get TX_PRU%d\n", slice); + } + + return 0; +} + +void prueth_put_cores(struct prueth *prueth, int slice) +{ + if (prueth->txpru[slice]) + pru_rproc_put(prueth->txpru[slice]); + + if (prueth->rtu[slice]) + pru_rproc_put(prueth->rtu[slice]); + + if (prueth->pru[slice]) + pru_rproc_put(prueth->pru[slice]); +} + +#ifdef CONFIG_PM_SLEEP +static int prueth_suspend(struct device *dev) +{ + struct prueth *prueth = dev_get_drvdata(dev); + struct net_device *ndev; + int i, ret; + + for (i = 0; i < PRUETH_NUM_MACS; i++) { + ndev = prueth->registered_netdevs[i]; + + if (!ndev) + continue; + + if (netif_running(ndev)) { + netif_device_detach(ndev); + ret = ndev->netdev_ops->ndo_stop(ndev); + if (ret < 0) { + netdev_err(ndev, "failed to stop: %d", ret); + return ret; + } + } + } + + return 0; +} + +static int prueth_resume(struct device *dev) +{ + struct prueth *prueth = dev_get_drvdata(dev); + struct net_device *ndev; + int i, ret; + + for (i = 0; i < PRUETH_NUM_MACS; i++) { + ndev = prueth->registered_netdevs[i]; + + if (!ndev) + continue; + + if (netif_running(ndev)) { + ret = ndev->netdev_ops->ndo_open(ndev); + if (ret < 0) { + netdev_err(ndev, "failed to start: %d", ret); + return ret; + } + netif_device_attach(ndev); + } + } + + return 0; +} +#endif /* CONFIG_PM_SLEEP */ + +const struct dev_pm_ops prueth_dev_pm_ops = { + SET_SYSTEM_SLEEP_PM_OPS(prueth_suspend, prueth_resume) +}; diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c index 99de8a40ed..15f2235bf9 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_config.c +++ b/drivers/net/ethernet/ti/icssg/icssg_config.c @@ -20,6 +20,8 @@ /* IPG is in core_clk cycles */ #define MII_RT_TX_IPG_100M 0x17 #define MII_RT_TX_IPG_1G 0xb +#define MII_RT_TX_IPG_100M_SR1 0x166 +#define MII_RT_TX_IPG_1G_SR1 0x1a #define ICSSG_QUEUES_MAX 64 #define ICSSG_QUEUE_OFFSET 0xd00 @@ -202,23 +204,29 @@ void icssg_config_ipg(struct prueth_emac *emac) { struct prueth *prueth = emac->prueth; int slice = prueth_emac_slice(emac); + u32 ipg; switch (emac->speed) { case SPEED_1000: - icssg_mii_update_ipg(prueth->mii_rt, slice, MII_RT_TX_IPG_1G); + ipg = emac->is_sr1 ? MII_RT_TX_IPG_1G_SR1 : MII_RT_TX_IPG_1G; break; case SPEED_100: - icssg_mii_update_ipg(prueth->mii_rt, slice, MII_RT_TX_IPG_100M); + ipg = emac->is_sr1 ? MII_RT_TX_IPG_100M_SR1 : MII_RT_TX_IPG_100M; break; case SPEED_10: + /* Firmware hardcodes IPG for SR1.0 */ + if (emac->is_sr1) + return; /* IPG for 10M is same as 100M */ - icssg_mii_update_ipg(prueth->mii_rt, slice, MII_RT_TX_IPG_100M); + ipg = MII_RT_TX_IPG_100M; break; default: /* Other links speeds not supported */ netdev_err(emac->ndev, "Unsupported link speed\n"); return; } + + icssg_mii_update_ipg(prueth->mii_rt, slice, ipg); } static void emac_r30_cmd_init(struct prueth_emac *emac) diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.h b/drivers/net/ethernet/ti/icssg/icssg_config.h index 43eb092217..cf2ea4bd22 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_config.h +++ b/drivers/net/ethernet/ti/icssg/icssg_config.h @@ -109,6 +109,62 @@ enum icssg_port_state_cmd { #define ICSSG_FLAG_MASK 0xff00ffff +/* SR1.0-specific bits */ +#define PRUETH_MAX_RX_FLOWS_SR1 4 /* excluding default flow */ +#define PRUETH_RX_FLOW_DATA_SR1 3 /* highest priority flow */ +#define PRUETH_MAX_RX_MGM_DESC_SR1 8 +#define PRUETH_MAX_RX_MGM_FLOWS_SR1 2 /* excluding default flow */ +#define PRUETH_RX_MGM_FLOW_RESPONSE_SR1 0 +#define PRUETH_RX_MGM_FLOW_TIMESTAMP_SR1 1 + +#define PRUETH_NUM_BUF_POOLS_SR1 16 +#define PRUETH_EMAC_BUF_POOL_START_SR1 8 +#define PRUETH_EMAC_BUF_POOL_MIN_SIZE_SR1 128 +#define PRUETH_EMAC_BUF_SIZE_SR1 1536 +#define PRUETH_EMAC_NUM_BUF_SR1 4 +#define PRUETH_EMAC_BUF_POOL_SIZE_SR1 (PRUETH_EMAC_NUM_BUF_SR1 * \ + PRUETH_EMAC_BUF_SIZE_SR1) +#define MSMC_RAM_SIZE_SR1 (SZ_64K + SZ_32K + SZ_2K) /* 0x1880 x 8 x 2 */ + +struct icssg_sr1_config { + __le32 status; /* Firmware status */ + __le32 addr_lo; /* MSMC Buffer pool base address low. */ + __le32 addr_hi; /* MSMC Buffer pool base address high. Must be 0 */ + __le32 tx_buf_sz[16]; /* Array of buffer pool sizes */ + __le32 num_tx_threads; /* Number of active egress threads, 1 to 4 */ + __le32 tx_rate_lim_en; /* Bitmask: Egress rate limit en per thread */ + __le32 rx_flow_id; /* RX flow id for first rx ring */ + __le32 rx_mgr_flow_id; /* RX flow id for the first management ring */ + __le32 flags; /* TBD */ + __le32 n_burst; /* for debug */ + __le32 rtu_status; /* RTU status */ + __le32 info; /* reserved */ + __le32 reserve; + __le32 rand_seed; /* Used for the random number generation at fw */ +} __packed; + +/* SR1.0 shutdown command to stop processing at firmware. + * Command format: 0x8101ss00, where + * - ss: sequence number. Currently not used by driver. + */ +#define ICSSG_SHUTDOWN_CMD_SR1 0x81010000 + +/* SR1.0 pstate speed/duplex command to set speed and duplex settings + * in firmware. + * Command format: 0x8102ssPN, where + * - ss: sequence number. Currently not used by driver. + * - P: port number (for switch mode). + * - N: Speed/Duplex state: + * 0x0 - 10Mbps/Half duplex; + * 0x8 - 10Mbps/Full duplex; + * 0x2 - 100Mbps/Half duplex; + * 0xa - 100Mbps/Full duplex; + * 0xc - 1Gbps/Full duplex; + * NOTE: The above are the same value as bits [3..1](slice 0) + * or bits [7..5](slice 1) of RGMII CFG register. + */ +#define ICSSG_PSTATE_SPEED_DUPLEX_CMD_SR1 0x81020000 + struct icssg_setclock_desc { u8 request; u8 restore; diff --git a/drivers/net/ethernet/ti/icssg/icssg_ethtool.c b/drivers/net/ethernet/ti/icssg/icssg_ethtool.c index 9a7dd7efcf..c8d0f45cc5 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_ethtool.c +++ b/drivers/net/ethernet/ti/icssg/icssg_ethtool.c @@ -142,6 +142,9 @@ static int emac_set_channels(struct net_device *ndev, emac->tx_ch_num = ch->tx_count; + if (emac->is_sr1) + emac->tx_ch_num++; + return 0; } @@ -152,8 +155,17 @@ static void emac_get_channels(struct net_device *ndev, ch->max_rx = 1; ch->max_tx = PRUETH_MAX_TX_QUEUES; + + /* Disable multiple TX channels due to timeouts + * when using more than one queue */ + if (emac->is_sr1) + ch->max_tx = 1; + ch->rx_count = 1; ch->tx_count = emac->tx_ch_num; + + if (emac->is_sr1) + ch->tx_count--; } static const struct ethtool_rmon_hist_range emac_rmon_ranges[] = { @@ -189,6 +201,93 @@ static void emac_get_rmon_stats(struct net_device *ndev, rmon_stats->hist_tx[4] = emac_get_stat_by_name(emac, "tx_bucket5_frames"); } +static int emac_get_coalesce(struct net_device *ndev, + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) +{ + struct prueth_emac *emac = netdev_priv(ndev); + struct prueth_tx_chn *tx_chn; + + tx_chn = &emac->tx_chns[0]; + + coal->rx_coalesce_usecs = emac->rx_pace_timeout_ns / 1000; + coal->tx_coalesce_usecs = tx_chn->tx_pace_timeout_ns / 1000; + + return 0; +} + +static int emac_get_per_queue_coalesce(struct net_device *ndev, u32 queue, + struct ethtool_coalesce *coal) +{ + struct prueth_emac *emac = netdev_priv(ndev); + struct prueth_tx_chn *tx_chn; + + if (queue >= PRUETH_MAX_TX_QUEUES) + return -EINVAL; + + tx_chn = &emac->tx_chns[queue]; + + coal->tx_coalesce_usecs = tx_chn->tx_pace_timeout_ns / 1000; + + return 0; +} + +static int emac_set_coalesce(struct net_device *ndev, + struct ethtool_coalesce *coal, + struct kernel_ethtool_coalesce *kernel_coal, + struct netlink_ext_ack *extack) +{ + struct prueth_emac *emac = netdev_priv(ndev); + struct prueth *prueth = emac->prueth; + struct prueth_tx_chn *tx_chn; + + tx_chn = &emac->tx_chns[0]; + + if (coal->rx_coalesce_usecs && + coal->rx_coalesce_usecs < ICSSG_MIN_COALESCE_USECS) { + dev_info(prueth->dev, "defaulting to min value of %dus for rx-usecs\n", + ICSSG_MIN_COALESCE_USECS); + coal->rx_coalesce_usecs = ICSSG_MIN_COALESCE_USECS; + } + + if (coal->tx_coalesce_usecs && + coal->tx_coalesce_usecs < ICSSG_MIN_COALESCE_USECS) { + dev_info(prueth->dev, "defaulting to min value of %dus for tx-usecs\n", + ICSSG_MIN_COALESCE_USECS); + coal->tx_coalesce_usecs = ICSSG_MIN_COALESCE_USECS; + } + + emac->rx_pace_timeout_ns = coal->rx_coalesce_usecs * 1000; + tx_chn->tx_pace_timeout_ns = coal->tx_coalesce_usecs * 1000; + + return 0; +} + +static int emac_set_per_queue_coalesce(struct net_device *ndev, u32 queue, + struct ethtool_coalesce *coal) +{ + struct prueth_emac *emac = netdev_priv(ndev); + struct prueth *prueth = emac->prueth; + struct prueth_tx_chn *tx_chn; + + if (queue >= PRUETH_MAX_TX_QUEUES) + return -EINVAL; + + tx_chn = &emac->tx_chns[queue]; + + if (coal->tx_coalesce_usecs && + coal->tx_coalesce_usecs < ICSSG_MIN_COALESCE_USECS) { + dev_info(prueth->dev, "defaulting to min value of %dus for tx-usecs for tx-%u\n", + ICSSG_MIN_COALESCE_USECS, queue); + coal->tx_coalesce_usecs = ICSSG_MIN_COALESCE_USECS; + } + + tx_chn->tx_pace_timeout_ns = coal->tx_coalesce_usecs * 1000; + + return 0; +} + const struct ethtool_ops icssg_ethtool_ops = { .get_drvinfo = emac_get_drvinfo, .get_msglevel = emac_get_msglevel, @@ -197,6 +296,12 @@ const struct ethtool_ops icssg_ethtool_ops = { .get_ethtool_stats = emac_get_ethtool_stats, .get_strings = emac_get_strings, .get_ts_info = emac_get_ts_info, + .supported_coalesce_params = ETHTOOL_COALESCE_RX_USECS | + ETHTOOL_COALESCE_TX_USECS, + .get_coalesce = emac_get_coalesce, + .set_coalesce = emac_set_coalesce, + .get_per_queue_coalesce = emac_get_per_queue_coalesce, + .set_per_queue_coalesce = emac_set_per_queue_coalesce, .get_channels = emac_get_channels, .set_channels = emac_set_channels, .get_link_ksettings = emac_get_link_ksettings, diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c index 61ebac7ba6..1ea3fbd5e9 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c @@ -34,570 +34,9 @@ #define PRUETH_MODULE_DESCRIPTION "PRUSS ICSSG Ethernet driver" -/* Netif debug messages possible */ -#define PRUETH_EMAC_DEBUG (NETIF_MSG_DRV | \ - NETIF_MSG_PROBE | \ - NETIF_MSG_LINK | \ - NETIF_MSG_TIMER | \ - NETIF_MSG_IFDOWN | \ - NETIF_MSG_IFUP | \ - NETIF_MSG_RX_ERR | \ - NETIF_MSG_TX_ERR | \ - NETIF_MSG_TX_QUEUED | \ - NETIF_MSG_INTR | \ - NETIF_MSG_TX_DONE | \ - NETIF_MSG_RX_STATUS | \ - NETIF_MSG_PKTDATA | \ - NETIF_MSG_HW | \ - NETIF_MSG_WOL) - -#define prueth_napi_to_emac(napi) container_of(napi, struct prueth_emac, napi_rx) - /* CTRLMMR_ICSSG_RGMII_CTRL register bits */ #define ICSSG_CTRL_RGMII_ID_MODE BIT(24) -#define IEP_DEFAULT_CYCLE_TIME_NS 1000000 /* 1 ms */ - -static void prueth_cleanup_rx_chns(struct prueth_emac *emac, - struct prueth_rx_chn *rx_chn, - int max_rflows) -{ - if (rx_chn->desc_pool) - k3_cppi_desc_pool_destroy(rx_chn->desc_pool); - - if (rx_chn->rx_chn) - k3_udma_glue_release_rx_chn(rx_chn->rx_chn); -} - -static void prueth_cleanup_tx_chns(struct prueth_emac *emac) -{ - int i; - - for (i = 0; i < emac->tx_ch_num; i++) { - struct prueth_tx_chn *tx_chn = &emac->tx_chns[i]; - - if (tx_chn->desc_pool) - k3_cppi_desc_pool_destroy(tx_chn->desc_pool); - - if (tx_chn->tx_chn) - k3_udma_glue_release_tx_chn(tx_chn->tx_chn); - - /* Assume prueth_cleanup_tx_chns() is called at the - * end after all channel resources are freed - */ - memset(tx_chn, 0, sizeof(*tx_chn)); - } -} - -static void prueth_ndev_del_tx_napi(struct prueth_emac *emac, int num) -{ - int i; - - for (i = 0; i < num; i++) { - struct prueth_tx_chn *tx_chn = &emac->tx_chns[i]; - - if (tx_chn->irq) - free_irq(tx_chn->irq, tx_chn); - netif_napi_del(&tx_chn->napi_tx); - } -} - -static void prueth_xmit_free(struct prueth_tx_chn *tx_chn, - struct cppi5_host_desc_t *desc) -{ - struct cppi5_host_desc_t *first_desc, *next_desc; - dma_addr_t buf_dma, next_desc_dma; - u32 buf_dma_len; - - first_desc = desc; - next_desc = first_desc; - - cppi5_hdesc_get_obuf(first_desc, &buf_dma, &buf_dma_len); - k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &buf_dma); - - dma_unmap_single(tx_chn->dma_dev, buf_dma, buf_dma_len, - DMA_TO_DEVICE); - - next_desc_dma = cppi5_hdesc_get_next_hbdesc(first_desc); - k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &next_desc_dma); - while (next_desc_dma) { - next_desc = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, - next_desc_dma); - cppi5_hdesc_get_obuf(next_desc, &buf_dma, &buf_dma_len); - k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &buf_dma); - - dma_unmap_page(tx_chn->dma_dev, buf_dma, buf_dma_len, - DMA_TO_DEVICE); - - next_desc_dma = cppi5_hdesc_get_next_hbdesc(next_desc); - k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &next_desc_dma); - - k3_cppi_desc_pool_free(tx_chn->desc_pool, next_desc); - } - - k3_cppi_desc_pool_free(tx_chn->desc_pool, first_desc); -} - -static int emac_tx_complete_packets(struct prueth_emac *emac, int chn, - int budget) -{ - struct net_device *ndev = emac->ndev; - struct cppi5_host_desc_t *desc_tx; - struct netdev_queue *netif_txq; - struct prueth_tx_chn *tx_chn; - unsigned int total_bytes = 0; - struct sk_buff *skb; - dma_addr_t desc_dma; - int res, num_tx = 0; - void **swdata; - - tx_chn = &emac->tx_chns[chn]; - - while (true) { - res = k3_udma_glue_pop_tx_chn(tx_chn->tx_chn, &desc_dma); - if (res == -ENODATA) - break; - - /* teardown completion */ - if (cppi5_desc_is_tdcm(desc_dma)) { - if (atomic_dec_and_test(&emac->tdown_cnt)) - complete(&emac->tdown_complete); - break; - } - - desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, - desc_dma); - swdata = cppi5_hdesc_get_swdata(desc_tx); - - skb = *(swdata); - prueth_xmit_free(tx_chn, desc_tx); - - ndev = skb->dev; - ndev->stats.tx_packets++; - ndev->stats.tx_bytes += skb->len; - total_bytes += skb->len; - napi_consume_skb(skb, budget); - num_tx++; - } - - if (!num_tx) - return 0; - - netif_txq = netdev_get_tx_queue(ndev, chn); - netdev_tx_completed_queue(netif_txq, num_tx, total_bytes); - - if (netif_tx_queue_stopped(netif_txq)) { - /* If the TX queue was stopped, wake it now - * if we have enough room. - */ - __netif_tx_lock(netif_txq, smp_processor_id()); - if (netif_running(ndev) && - (k3_cppi_desc_pool_avail(tx_chn->desc_pool) >= - MAX_SKB_FRAGS)) - netif_tx_wake_queue(netif_txq); - __netif_tx_unlock(netif_txq); - } - - return num_tx; -} - -static int emac_napi_tx_poll(struct napi_struct *napi_tx, int budget) -{ - struct prueth_tx_chn *tx_chn = prueth_napi_to_tx_chn(napi_tx); - struct prueth_emac *emac = tx_chn->emac; - int num_tx_packets; - - num_tx_packets = emac_tx_complete_packets(emac, tx_chn->id, budget); - - if (num_tx_packets >= budget) - return budget; - - if (napi_complete_done(napi_tx, num_tx_packets)) - enable_irq(tx_chn->irq); - - return num_tx_packets; -} - -static irqreturn_t prueth_tx_irq(int irq, void *dev_id) -{ - struct prueth_tx_chn *tx_chn = dev_id; - - disable_irq_nosync(irq); - napi_schedule(&tx_chn->napi_tx); - - return IRQ_HANDLED; -} - -static int prueth_ndev_add_tx_napi(struct prueth_emac *emac) -{ - struct prueth *prueth = emac->prueth; - int i, ret; - - for (i = 0; i < emac->tx_ch_num; i++) { - struct prueth_tx_chn *tx_chn = &emac->tx_chns[i]; - - netif_napi_add_tx(emac->ndev, &tx_chn->napi_tx, emac_napi_tx_poll); - ret = request_irq(tx_chn->irq, prueth_tx_irq, - IRQF_TRIGGER_HIGH, tx_chn->name, - tx_chn); - if (ret) { - netif_napi_del(&tx_chn->napi_tx); - dev_err(prueth->dev, "unable to request TX IRQ %d\n", - tx_chn->irq); - goto fail; - } - } - - return 0; -fail: - prueth_ndev_del_tx_napi(emac, i); - return ret; -} - -static int prueth_init_tx_chns(struct prueth_emac *emac) -{ - static const struct k3_ring_cfg ring_cfg = { - .elm_size = K3_RINGACC_RING_ELSIZE_8, - .mode = K3_RINGACC_RING_MODE_RING, - .flags = 0, - .size = PRUETH_MAX_TX_DESC, - }; - struct k3_udma_glue_tx_channel_cfg tx_cfg; - struct device *dev = emac->prueth->dev; - struct net_device *ndev = emac->ndev; - int ret, slice, i; - u32 hdesc_size; - - slice = prueth_emac_slice(emac); - if (slice < 0) - return slice; - - init_completion(&emac->tdown_complete); - - hdesc_size = cppi5_hdesc_calc_size(true, PRUETH_NAV_PS_DATA_SIZE, - PRUETH_NAV_SW_DATA_SIZE); - memset(&tx_cfg, 0, sizeof(tx_cfg)); - tx_cfg.swdata_size = PRUETH_NAV_SW_DATA_SIZE; - tx_cfg.tx_cfg = ring_cfg; - tx_cfg.txcq_cfg = ring_cfg; - - for (i = 0; i < emac->tx_ch_num; i++) { - struct prueth_tx_chn *tx_chn = &emac->tx_chns[i]; - - /* To differentiate channels for SLICE0 vs SLICE1 */ - snprintf(tx_chn->name, sizeof(tx_chn->name), - "tx%d-%d", slice, i); - - tx_chn->emac = emac; - tx_chn->id = i; - tx_chn->descs_num = PRUETH_MAX_TX_DESC; - - tx_chn->tx_chn = - k3_udma_glue_request_tx_chn(dev, tx_chn->name, - &tx_cfg); - if (IS_ERR(tx_chn->tx_chn)) { - ret = PTR_ERR(tx_chn->tx_chn); - tx_chn->tx_chn = NULL; - netdev_err(ndev, - "Failed to request tx dma ch: %d\n", ret); - goto fail; - } - - tx_chn->dma_dev = k3_udma_glue_tx_get_dma_device(tx_chn->tx_chn); - tx_chn->desc_pool = - k3_cppi_desc_pool_create_name(tx_chn->dma_dev, - tx_chn->descs_num, - hdesc_size, - tx_chn->name); - if (IS_ERR(tx_chn->desc_pool)) { - ret = PTR_ERR(tx_chn->desc_pool); - tx_chn->desc_pool = NULL; - netdev_err(ndev, "Failed to create tx pool: %d\n", ret); - goto fail; - } - - ret = k3_udma_glue_tx_get_irq(tx_chn->tx_chn); - if (ret < 0) { - netdev_err(ndev, "failed to get tx irq\n"); - goto fail; - } - tx_chn->irq = ret; - - snprintf(tx_chn->name, sizeof(tx_chn->name), "%s-tx%d", - dev_name(dev), tx_chn->id); - } - - return 0; - -fail: - prueth_cleanup_tx_chns(emac); - return ret; -} - -static int prueth_init_rx_chns(struct prueth_emac *emac, - struct prueth_rx_chn *rx_chn, - char *name, u32 max_rflows, - u32 max_desc_num) -{ - struct k3_udma_glue_rx_channel_cfg rx_cfg; - struct device *dev = emac->prueth->dev; - struct net_device *ndev = emac->ndev; - u32 fdqring_id, hdesc_size; - int i, ret = 0, slice; - - slice = prueth_emac_slice(emac); - if (slice < 0) - return slice; - - /* To differentiate channels for SLICE0 vs SLICE1 */ - snprintf(rx_chn->name, sizeof(rx_chn->name), "%s%d", name, slice); - - hdesc_size = cppi5_hdesc_calc_size(true, PRUETH_NAV_PS_DATA_SIZE, - PRUETH_NAV_SW_DATA_SIZE); - memset(&rx_cfg, 0, sizeof(rx_cfg)); - rx_cfg.swdata_size = PRUETH_NAV_SW_DATA_SIZE; - rx_cfg.flow_id_num = max_rflows; - rx_cfg.flow_id_base = -1; /* udmax will auto select flow id base */ - - /* init all flows */ - rx_chn->dev = dev; - rx_chn->descs_num = max_desc_num; - - rx_chn->rx_chn = k3_udma_glue_request_rx_chn(dev, rx_chn->name, - &rx_cfg); - if (IS_ERR(rx_chn->rx_chn)) { - ret = PTR_ERR(rx_chn->rx_chn); - rx_chn->rx_chn = NULL; - netdev_err(ndev, "Failed to request rx dma ch: %d\n", ret); - goto fail; - } - - rx_chn->dma_dev = k3_udma_glue_rx_get_dma_device(rx_chn->rx_chn); - rx_chn->desc_pool = k3_cppi_desc_pool_create_name(rx_chn->dma_dev, - rx_chn->descs_num, - hdesc_size, - rx_chn->name); - if (IS_ERR(rx_chn->desc_pool)) { - ret = PTR_ERR(rx_chn->desc_pool); - rx_chn->desc_pool = NULL; - netdev_err(ndev, "Failed to create rx pool: %d\n", ret); - goto fail; - } - - emac->rx_flow_id_base = k3_udma_glue_rx_get_flow_id_base(rx_chn->rx_chn); - netdev_dbg(ndev, "flow id base = %d\n", emac->rx_flow_id_base); - - fdqring_id = K3_RINGACC_RING_ID_ANY; - for (i = 0; i < rx_cfg.flow_id_num; i++) { - struct k3_ring_cfg rxring_cfg = { - .elm_size = K3_RINGACC_RING_ELSIZE_8, - .mode = K3_RINGACC_RING_MODE_RING, - .flags = 0, - }; - struct k3_ring_cfg fdqring_cfg = { - .elm_size = K3_RINGACC_RING_ELSIZE_8, - .flags = K3_RINGACC_RING_SHARED, - }; - struct k3_udma_glue_rx_flow_cfg rx_flow_cfg = { - .rx_cfg = rxring_cfg, - .rxfdq_cfg = fdqring_cfg, - .ring_rxq_id = K3_RINGACC_RING_ID_ANY, - .src_tag_lo_sel = - K3_UDMA_GLUE_SRC_TAG_LO_USE_REMOTE_SRC_TAG, - }; - - rx_flow_cfg.ring_rxfdq0_id = fdqring_id; - rx_flow_cfg.rx_cfg.size = max_desc_num; - rx_flow_cfg.rxfdq_cfg.size = max_desc_num; - rx_flow_cfg.rxfdq_cfg.mode = emac->prueth->pdata.fdqring_mode; - - ret = k3_udma_glue_rx_flow_init(rx_chn->rx_chn, - i, &rx_flow_cfg); - if (ret) { - netdev_err(ndev, "Failed to init rx flow%d %d\n", - i, ret); - goto fail; - } - if (!i) - fdqring_id = k3_udma_glue_rx_flow_get_fdq_id(rx_chn->rx_chn, - i); - ret = k3_udma_glue_rx_get_irq(rx_chn->rx_chn, i); - if (ret <= 0) { - if (!ret) - ret = -ENXIO; - netdev_err(ndev, "Failed to get rx dma irq"); - goto fail; - } - rx_chn->irq[i] = ret; - } - - return 0; - -fail: - prueth_cleanup_rx_chns(emac, rx_chn, max_rflows); - return ret; -} - -static int prueth_dma_rx_push(struct prueth_emac *emac, - struct sk_buff *skb, - struct prueth_rx_chn *rx_chn) -{ - struct net_device *ndev = emac->ndev; - struct cppi5_host_desc_t *desc_rx; - u32 pkt_len = skb_tailroom(skb); - dma_addr_t desc_dma; - dma_addr_t buf_dma; - void **swdata; - - desc_rx = k3_cppi_desc_pool_alloc(rx_chn->desc_pool); - if (!desc_rx) { - netdev_err(ndev, "rx push: failed to allocate descriptor\n"); - return -ENOMEM; - } - desc_dma = k3_cppi_desc_pool_virt2dma(rx_chn->desc_pool, desc_rx); - - buf_dma = dma_map_single(rx_chn->dma_dev, skb->data, pkt_len, DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(rx_chn->dma_dev, buf_dma))) { - k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); - netdev_err(ndev, "rx push: failed to map rx pkt buffer\n"); - return -EINVAL; - } - - cppi5_hdesc_init(desc_rx, CPPI5_INFO0_HDESC_EPIB_PRESENT, - PRUETH_NAV_PS_DATA_SIZE); - k3_udma_glue_rx_dma_to_cppi5_addr(rx_chn->rx_chn, &buf_dma); - cppi5_hdesc_attach_buf(desc_rx, buf_dma, skb_tailroom(skb), buf_dma, skb_tailroom(skb)); - - swdata = cppi5_hdesc_get_swdata(desc_rx); - *swdata = skb; - - return k3_udma_glue_push_rx_chn(rx_chn->rx_chn, 0, - desc_rx, desc_dma); -} - -static u64 icssg_ts_to_ns(u32 hi_sw, u32 hi, u32 lo, u32 cycle_time_ns) -{ - u32 iepcount_lo, iepcount_hi, hi_rollover_count; - u64 ns; - - iepcount_lo = lo & GENMASK(19, 0); - iepcount_hi = (hi & GENMASK(11, 0)) << 12 | lo >> 20; - hi_rollover_count = hi >> 11; - - ns = ((u64)hi_rollover_count) << 23 | (iepcount_hi + hi_sw); - ns = ns * cycle_time_ns + iepcount_lo; - - return ns; -} - -static void emac_rx_timestamp(struct prueth_emac *emac, - struct sk_buff *skb, u32 *psdata) -{ - struct skb_shared_hwtstamps *ssh; - u64 ns; - - u32 hi_sw = readl(emac->prueth->shram.va + - TIMESYNC_FW_WC_COUNT_HI_SW_OFFSET_OFFSET); - ns = icssg_ts_to_ns(hi_sw, psdata[1], psdata[0], - IEP_DEFAULT_CYCLE_TIME_NS); - - ssh = skb_hwtstamps(skb); - memset(ssh, 0, sizeof(*ssh)); - ssh->hwtstamp = ns_to_ktime(ns); -} - -static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id) -{ - struct prueth_rx_chn *rx_chn = &emac->rx_chns; - u32 buf_dma_len, pkt_len, port_id = 0; - struct net_device *ndev = emac->ndev; - struct cppi5_host_desc_t *desc_rx; - struct sk_buff *skb, *new_skb; - dma_addr_t desc_dma, buf_dma; - void **swdata; - u32 *psdata; - int ret; - - ret = k3_udma_glue_pop_rx_chn(rx_chn->rx_chn, flow_id, &desc_dma); - if (ret) { - if (ret != -ENODATA) - netdev_err(ndev, "rx pop: failed: %d\n", ret); - return ret; - } - - if (cppi5_desc_is_tdcm(desc_dma)) /* Teardown ? */ - return 0; - - desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma); - - swdata = cppi5_hdesc_get_swdata(desc_rx); - skb = *swdata; - - psdata = cppi5_hdesc_get_psdata(desc_rx); - /* RX HW timestamp */ - if (emac->rx_ts_enabled) - emac_rx_timestamp(emac, skb, psdata); - - cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len); - k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma); - pkt_len = cppi5_hdesc_get_pktlen(desc_rx); - /* firmware adds 4 CRC bytes, strip them */ - pkt_len -= 4; - cppi5_desc_get_tags_ids(&desc_rx->hdr, &port_id, NULL); - - dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE); - k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); - - skb->dev = ndev; - new_skb = netdev_alloc_skb_ip_align(ndev, PRUETH_MAX_PKT_SIZE); - /* if allocation fails we drop the packet but push the - * descriptor back to the ring with old skb to prevent a stall - */ - if (!new_skb) { - ndev->stats.rx_dropped++; - new_skb = skb; - } else { - /* send the filled skb up the n/w stack */ - skb_put(skb, pkt_len); - skb->protocol = eth_type_trans(skb, ndev); - napi_gro_receive(&emac->napi_rx, skb); - ndev->stats.rx_bytes += pkt_len; - ndev->stats.rx_packets++; - } - - /* queue another RX DMA */ - ret = prueth_dma_rx_push(emac, new_skb, &emac->rx_chns); - if (WARN_ON(ret < 0)) { - dev_kfree_skb_any(new_skb); - ndev->stats.rx_errors++; - ndev->stats.rx_dropped++; - } - - return ret; -} - -static void prueth_rx_cleanup(void *data, dma_addr_t desc_dma) -{ - struct prueth_rx_chn *rx_chn = data; - struct cppi5_host_desc_t *desc_rx; - struct sk_buff *skb; - dma_addr_t buf_dma; - u32 buf_dma_len; - void **swdata; - - desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma); - swdata = cppi5_hdesc_get_swdata(desc_rx); - skb = *swdata; - cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len); - k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma); - - dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, - DMA_FROM_DEVICE); - k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); - - dev_kfree_skb_any(skb); -} - static int emac_get_tx_ts(struct prueth_emac *emac, struct emac_tx_ts_response *rsp) { @@ -663,208 +102,6 @@ static void tx_ts_work(struct prueth_emac *emac) } } -static int prueth_tx_ts_cookie_get(struct prueth_emac *emac) -{ - int i; - - /* search and get the next free slot */ - for (i = 0; i < PRUETH_MAX_TX_TS_REQUESTS; i++) { - if (!emac->tx_ts_skb[i]) { - emac->tx_ts_skb[i] = ERR_PTR(-EBUSY); /* reserve slot */ - return i; - } - } - - return -EBUSY; -} - -/** - * emac_ndo_start_xmit - EMAC Transmit function - * @skb: SKB pointer - * @ndev: EMAC network adapter - * - * Called by the system to transmit a packet - we queue the packet in - * EMAC hardware transmit queue - * Doesn't wait for completion we'll check for TX completion in - * emac_tx_complete_packets(). - * - * Return: enum netdev_tx - */ -static enum netdev_tx emac_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev) -{ - struct cppi5_host_desc_t *first_desc, *next_desc, *cur_desc; - struct prueth_emac *emac = netdev_priv(ndev); - struct netdev_queue *netif_txq; - struct prueth_tx_chn *tx_chn; - dma_addr_t desc_dma, buf_dma; - int i, ret = 0, q_idx; - bool in_tx_ts = 0; - int tx_ts_cookie; - void **swdata; - u32 pkt_len; - u32 *epib; - - pkt_len = skb_headlen(skb); - q_idx = skb_get_queue_mapping(skb); - - tx_chn = &emac->tx_chns[q_idx]; - netif_txq = netdev_get_tx_queue(ndev, q_idx); - - /* Map the linear buffer */ - buf_dma = dma_map_single(tx_chn->dma_dev, skb->data, pkt_len, DMA_TO_DEVICE); - if (dma_mapping_error(tx_chn->dma_dev, buf_dma)) { - netdev_err(ndev, "tx: failed to map skb buffer\n"); - ret = NETDEV_TX_OK; - goto drop_free_skb; - } - - first_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool); - if (!first_desc) { - netdev_dbg(ndev, "tx: failed to allocate descriptor\n"); - dma_unmap_single(tx_chn->dma_dev, buf_dma, pkt_len, DMA_TO_DEVICE); - goto drop_stop_q_busy; - } - - cppi5_hdesc_init(first_desc, CPPI5_INFO0_HDESC_EPIB_PRESENT, - PRUETH_NAV_PS_DATA_SIZE); - cppi5_hdesc_set_pkttype(first_desc, 0); - epib = first_desc->epib; - epib[0] = 0; - epib[1] = 0; - if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP && - emac->tx_ts_enabled) { - tx_ts_cookie = prueth_tx_ts_cookie_get(emac); - if (tx_ts_cookie >= 0) { - skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; - /* Request TX timestamp */ - epib[0] = (u32)tx_ts_cookie; - epib[1] = 0x80000000; /* TX TS request */ - emac->tx_ts_skb[tx_ts_cookie] = skb_get(skb); - in_tx_ts = 1; - } - } - - /* set dst tag to indicate internal qid at the firmware which is at - * bit8..bit15. bit0..bit7 indicates port num for directed - * packets in case of switch mode operation - */ - cppi5_desc_set_tags_ids(&first_desc->hdr, 0, (emac->port_id | (q_idx << 8))); - k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma); - cppi5_hdesc_attach_buf(first_desc, buf_dma, pkt_len, buf_dma, pkt_len); - swdata = cppi5_hdesc_get_swdata(first_desc); - *swdata = skb; - - /* Handle the case where skb is fragmented in pages */ - cur_desc = first_desc; - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - u32 frag_size = skb_frag_size(frag); - - next_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool); - if (!next_desc) { - netdev_err(ndev, - "tx: failed to allocate frag. descriptor\n"); - goto free_desc_stop_q_busy_cleanup_tx_ts; - } - - buf_dma = skb_frag_dma_map(tx_chn->dma_dev, frag, 0, frag_size, - DMA_TO_DEVICE); - if (dma_mapping_error(tx_chn->dma_dev, buf_dma)) { - netdev_err(ndev, "tx: Failed to map skb page\n"); - k3_cppi_desc_pool_free(tx_chn->desc_pool, next_desc); - ret = NETDEV_TX_OK; - goto cleanup_tx_ts; - } - - cppi5_hdesc_reset_hbdesc(next_desc); - k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma); - cppi5_hdesc_attach_buf(next_desc, - buf_dma, frag_size, buf_dma, frag_size); - - desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, - next_desc); - k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &desc_dma); - cppi5_hdesc_link_hbdesc(cur_desc, desc_dma); - - pkt_len += frag_size; - cur_desc = next_desc; - } - WARN_ON_ONCE(pkt_len != skb->len); - - /* report bql before sending packet */ - netdev_tx_sent_queue(netif_txq, pkt_len); - - cppi5_hdesc_set_pktlen(first_desc, pkt_len); - desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, first_desc); - /* cppi5_desc_dump(first_desc, 64); */ - - skb_tx_timestamp(skb); /* SW timestamp if SKBTX_IN_PROGRESS not set */ - ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma); - if (ret) { - netdev_err(ndev, "tx: push failed: %d\n", ret); - goto drop_free_descs; - } - - if (in_tx_ts) - atomic_inc(&emac->tx_ts_pending); - - if (k3_cppi_desc_pool_avail(tx_chn->desc_pool) < MAX_SKB_FRAGS) { - netif_tx_stop_queue(netif_txq); - /* Barrier, so that stop_queue visible to other cpus */ - smp_mb__after_atomic(); - - if (k3_cppi_desc_pool_avail(tx_chn->desc_pool) >= - MAX_SKB_FRAGS) - netif_tx_wake_queue(netif_txq); - } - - return NETDEV_TX_OK; - -cleanup_tx_ts: - if (in_tx_ts) { - dev_kfree_skb_any(emac->tx_ts_skb[tx_ts_cookie]); - emac->tx_ts_skb[tx_ts_cookie] = NULL; - } - -drop_free_descs: - prueth_xmit_free(tx_chn, first_desc); - -drop_free_skb: - dev_kfree_skb_any(skb); - - /* error */ - ndev->stats.tx_dropped++; - netdev_err(ndev, "tx: error: %d\n", ret); - - return ret; - -free_desc_stop_q_busy_cleanup_tx_ts: - if (in_tx_ts) { - dev_kfree_skb_any(emac->tx_ts_skb[tx_ts_cookie]); - emac->tx_ts_skb[tx_ts_cookie] = NULL; - } - prueth_xmit_free(tx_chn, first_desc); - -drop_stop_q_busy: - netif_tx_stop_queue(netif_txq); - return NETDEV_TX_BUSY; -} - -static void prueth_tx_cleanup(void *data, dma_addr_t desc_dma) -{ - struct prueth_tx_chn *tx_chn = data; - struct cppi5_host_desc_t *desc_tx; - struct sk_buff *skb; - void **swdata; - - desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma); - swdata = cppi5_hdesc_get_swdata(desc_tx); - skb = *(swdata); - prueth_xmit_free(tx_chn, desc_tx); - - dev_kfree_skb_any(skb); -} - static irqreturn_t prueth_tx_ts_irq(int irq, void *dev_id) { struct prueth_emac *emac = dev_id; @@ -875,22 +112,6 @@ static irqreturn_t prueth_tx_ts_irq(int irq, void *dev_id) return IRQ_HANDLED; } -static irqreturn_t prueth_rx_irq(int irq, void *dev_id) -{ - struct prueth_emac *emac = dev_id; - - disable_irq_nosync(irq); - napi_schedule(&emac->napi_rx); - - return IRQ_HANDLED; -} - -struct icssg_firmwares { - char *pru; - char *rtu; - char *txpru; -}; - static struct icssg_firmwares icssg_emac_firmwares[] = { { .pru = "ti-pruss/am65x-sr2-pru0-prueth-fw.elf", @@ -955,41 +176,6 @@ halt_pru: return ret; } -static void prueth_emac_stop(struct prueth_emac *emac) -{ - struct prueth *prueth = emac->prueth; - int slice; - - switch (emac->port_id) { - case PRUETH_PORT_MII0: - slice = ICSS_SLICE0; - break; - case PRUETH_PORT_MII1: - slice = ICSS_SLICE1; - break; - default: - netdev_err(emac->ndev, "invalid port\n"); - return; - } - - emac->fw_running = 0; - rproc_shutdown(prueth->txpru[slice]); - rproc_shutdown(prueth->rtu[slice]); - rproc_shutdown(prueth->pru[slice]); -} - -static void prueth_cleanup_tx_ts(struct prueth_emac *emac) -{ - int i; - - for (i = 0; i < PRUETH_MAX_TX_TS_REQUESTS; i++) { - if (emac->tx_ts_skb[i]) { - dev_kfree_skb_any(emac->tx_ts_skb[i]); - emac->tx_ts_skb[i] = NULL; - } - } -} - /* called back by PHY layer if there is change in link state of hw port*/ static void emac_adjust_link(struct net_device *ndev) { @@ -1057,84 +243,14 @@ static void emac_adjust_link(struct net_device *ndev) } } -static int emac_napi_rx_poll(struct napi_struct *napi_rx, int budget) +static enum hrtimer_restart emac_rx_timer_callback(struct hrtimer *timer) { - struct prueth_emac *emac = prueth_napi_to_emac(napi_rx); + struct prueth_emac *emac = + container_of(timer, struct prueth_emac, rx_hrtimer); int rx_flow = PRUETH_RX_FLOW_DATA; - int flow = PRUETH_MAX_RX_FLOWS; - int num_rx = 0; - int cur_budget; - int ret; - - while (flow--) { - cur_budget = budget - num_rx; - - while (cur_budget--) { - ret = emac_rx_packet(emac, flow); - if (ret) - break; - num_rx++; - } - - if (num_rx >= budget) - break; - } - if (num_rx < budget && napi_complete_done(napi_rx, num_rx)) - enable_irq(emac->rx_chns.irq[rx_flow]); - - return num_rx; -} - -static int prueth_prepare_rx_chan(struct prueth_emac *emac, - struct prueth_rx_chn *chn, - int buf_size) -{ - struct sk_buff *skb; - int i, ret; - - for (i = 0; i < chn->descs_num; i++) { - skb = __netdev_alloc_skb_ip_align(NULL, buf_size, GFP_KERNEL); - if (!skb) - return -ENOMEM; - - ret = prueth_dma_rx_push(emac, skb, chn); - if (ret < 0) { - netdev_err(emac->ndev, - "cannot submit skb for rx chan %s ret %d\n", - chn->name, ret); - kfree_skb(skb); - return ret; - } - } - - return 0; -} - -static void prueth_reset_tx_chan(struct prueth_emac *emac, int ch_num, - bool free_skb) -{ - int i; - - for (i = 0; i < ch_num; i++) { - if (free_skb) - k3_udma_glue_reset_tx_chn(emac->tx_chns[i].tx_chn, - &emac->tx_chns[i], - prueth_tx_cleanup); - k3_udma_glue_disable_tx_chn(emac->tx_chns[i].tx_chn); - } -} - -static void prueth_reset_rx_chan(struct prueth_rx_chn *chn, - int num_flows, bool disable) -{ - int i; - - for (i = 0; i < num_flows; i++) - k3_udma_glue_reset_rx_chn(chn->rx_chn, i, chn, - prueth_rx_cleanup, !!i); - if (disable) - k3_udma_glue_disable_rx_chn(chn->rx_chn); + enable_irq(emac->rx_chns.irq[rx_flow]); + return HRTIMER_NORESTART; } static int emac_phy_connect(struct prueth_emac *emac) @@ -1331,7 +447,7 @@ static int emac_ndo_open(struct net_device *ndev) icssg_class_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr); icssg_ft1_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr); - icssg_class_default(prueth->miig_rt, slice, 0); + icssg_class_default(prueth->miig_rt, slice, 0, false); /* Notify the stack of the actual queue counts. */ ret = netif_set_real_num_tx_queues(ndev, num_data_chn); @@ -1476,8 +592,10 @@ static int emac_ndo_stop(struct net_device *ndev) netdev_err(ndev, "tx teardown timeout\n"); prueth_reset_tx_chan(emac, emac->tx_ch_num, true); - for (i = 0; i < emac->tx_ch_num; i++) + for (i = 0; i < emac->tx_ch_num; i++) { napi_disable(&emac->tx_chns[i].napi_tx); + hrtimer_cancel(&emac->tx_chns[i].tx_hrtimer); + } max_rx_flows = PRUETH_MAX_RX_FLOWS; k3_udma_glue_tdown_rx_chn(emac->rx_chns.rx_chn, true); @@ -1485,6 +603,7 @@ static int emac_ndo_stop(struct net_device *ndev) prueth_reset_rx_chan(&emac->rx_chns, max_rx_flows, true); napi_disable(&emac->napi_rx); + hrtimer_cancel(&emac->rx_hrtimer); cancel_work_sync(&emac->rx_mode_work); @@ -1510,11 +629,6 @@ static int emac_ndo_stop(struct net_device *ndev) return 0; } -static void emac_ndo_tx_timeout(struct net_device *ndev, unsigned int txqueue) -{ - ndev->stats.tx_errors++; -} - static void emac_ndo_set_rx_mode_work(struct work_struct *work) { struct prueth_emac *emac = container_of(work, struct prueth_emac, rx_mode_work); @@ -1560,116 +674,6 @@ static void emac_ndo_set_rx_mode(struct net_device *ndev) queue_work(emac->cmd_wq, &emac->rx_mode_work); } -static int emac_set_ts_config(struct net_device *ndev, struct ifreq *ifr) -{ - struct prueth_emac *emac = netdev_priv(ndev); - struct hwtstamp_config config; - - if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) - return -EFAULT; - - switch (config.tx_type) { - case HWTSTAMP_TX_OFF: - emac->tx_ts_enabled = 0; - break; - case HWTSTAMP_TX_ON: - emac->tx_ts_enabled = 1; - break; - default: - return -ERANGE; - } - - switch (config.rx_filter) { - case HWTSTAMP_FILTER_NONE: - emac->rx_ts_enabled = 0; - break; - case HWTSTAMP_FILTER_ALL: - case HWTSTAMP_FILTER_SOME: - case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: - case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: - case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: - case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_EVENT: - case HWTSTAMP_FILTER_PTP_V2_SYNC: - case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: - case HWTSTAMP_FILTER_NTP_ALL: - emac->rx_ts_enabled = 1; - config.rx_filter = HWTSTAMP_FILTER_ALL; - break; - default: - return -ERANGE; - } - - return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? - -EFAULT : 0; -} - -static int emac_get_ts_config(struct net_device *ndev, struct ifreq *ifr) -{ - struct prueth_emac *emac = netdev_priv(ndev); - struct hwtstamp_config config; - - config.flags = 0; - config.tx_type = emac->tx_ts_enabled ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; - config.rx_filter = emac->rx_ts_enabled ? HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE; - - return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? - -EFAULT : 0; -} - -static int emac_ndo_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd) -{ - switch (cmd) { - case SIOCGHWTSTAMP: - return emac_get_ts_config(ndev, ifr); - case SIOCSHWTSTAMP: - return emac_set_ts_config(ndev, ifr); - default: - break; - } - - return phy_do_ioctl(ndev, ifr, cmd); -} - -static void emac_ndo_get_stats64(struct net_device *ndev, - struct rtnl_link_stats64 *stats) -{ - struct prueth_emac *emac = netdev_priv(ndev); - - emac_update_hardware_stats(emac); - - stats->rx_packets = emac_get_stat_by_name(emac, "rx_packets"); - stats->rx_bytes = emac_get_stat_by_name(emac, "rx_bytes"); - stats->tx_packets = emac_get_stat_by_name(emac, "tx_packets"); - stats->tx_bytes = emac_get_stat_by_name(emac, "tx_bytes"); - stats->rx_crc_errors = emac_get_stat_by_name(emac, "rx_crc_errors"); - stats->rx_over_errors = emac_get_stat_by_name(emac, "rx_over_errors"); - stats->multicast = emac_get_stat_by_name(emac, "rx_multicast_frames"); - - stats->rx_errors = ndev->stats.rx_errors; - stats->rx_dropped = ndev->stats.rx_dropped; - stats->tx_errors = ndev->stats.tx_errors; - stats->tx_dropped = ndev->stats.tx_dropped; -} - -static int emac_ndo_get_phys_port_name(struct net_device *ndev, char *name, - size_t len) -{ - struct prueth_emac *emac = netdev_priv(ndev); - int ret; - - ret = snprintf(name, len, "p%d", emac->port_id); - if (ret >= len) - return -EINVAL; - - return 0; -} - static const struct net_device_ops emac_netdev_ops = { .ndo_open = emac_ndo_open, .ndo_stop = emac_ndo_stop, @@ -1683,42 +687,6 @@ static const struct net_device_ops emac_netdev_ops = { .ndo_get_phys_port_name = emac_ndo_get_phys_port_name, }; -/* get emac_port corresponding to eth_node name */ -static int prueth_node_port(struct device_node *eth_node) -{ - u32 port_id; - int ret; - - ret = of_property_read_u32(eth_node, "reg", &port_id); - if (ret) - return ret; - - if (port_id == 0) - return PRUETH_PORT_MII0; - else if (port_id == 1) - return PRUETH_PORT_MII1; - else - return PRUETH_PORT_INVALID; -} - -/* get MAC instance corresponding to eth_node name */ -static int prueth_node_mac(struct device_node *eth_node) -{ - u32 port_id; - int ret; - - ret = of_property_read_u32(eth_node, "reg", &port_id); - if (ret) - return ret; - - if (port_id == 0) - return PRUETH_MAC0; - else if (port_id == 1) - return PRUETH_MAC1; - else - return PRUETH_MAC_INVALID; -} - static int prueth_netdev_init(struct prueth *prueth, struct device_node *eth_node) { @@ -1846,6 +814,9 @@ static int prueth_netdev_init(struct prueth *prueth, ndev->features = ndev->hw_features; netif_napi_add(ndev, &emac->napi_rx, emac_napi_rx_poll); + hrtimer_init(&emac->rx_hrtimer, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_PINNED); + emac->rx_hrtimer.function = &emac_rx_timer_callback; prueth->emac[mac] = emac; return 0; @@ -1862,90 +833,6 @@ free_ndev: return ret; } -static void prueth_netdev_exit(struct prueth *prueth, - struct device_node *eth_node) -{ - struct prueth_emac *emac; - enum prueth_mac mac; - - mac = prueth_node_mac(eth_node); - if (mac == PRUETH_MAC_INVALID) - return; - - emac = prueth->emac[mac]; - if (!emac) - return; - - if (of_phy_is_fixed_link(emac->phy_node)) - of_phy_deregister_fixed_link(emac->phy_node); - - netif_napi_del(&emac->napi_rx); - - pruss_release_mem_region(prueth->pruss, &emac->dram); - destroy_workqueue(emac->cmd_wq); - free_netdev(emac->ndev); - prueth->emac[mac] = NULL; -} - -static int prueth_get_cores(struct prueth *prueth, int slice) -{ - struct device *dev = prueth->dev; - enum pruss_pru_id pruss_id; - struct device_node *np; - int idx = -1, ret; - - np = dev->of_node; - - switch (slice) { - case ICSS_SLICE0: - idx = 0; - break; - case ICSS_SLICE1: - idx = 3; - break; - default: - return -EINVAL; - } - - prueth->pru[slice] = pru_rproc_get(np, idx, &pruss_id); - if (IS_ERR(prueth->pru[slice])) { - ret = PTR_ERR(prueth->pru[slice]); - prueth->pru[slice] = NULL; - return dev_err_probe(dev, ret, "unable to get PRU%d\n", slice); - } - prueth->pru_id[slice] = pruss_id; - - idx++; - prueth->rtu[slice] = pru_rproc_get(np, idx, NULL); - if (IS_ERR(prueth->rtu[slice])) { - ret = PTR_ERR(prueth->rtu[slice]); - prueth->rtu[slice] = NULL; - return dev_err_probe(dev, ret, "unable to get RTU%d\n", slice); - } - - idx++; - prueth->txpru[slice] = pru_rproc_get(np, idx, NULL); - if (IS_ERR(prueth->txpru[slice])) { - ret = PTR_ERR(prueth->txpru[slice]); - prueth->txpru[slice] = NULL; - return dev_err_probe(dev, ret, "unable to get TX_PRU%d\n", slice); - } - - return 0; -} - -static void prueth_put_cores(struct prueth *prueth, int slice) -{ - if (prueth->txpru[slice]) - pru_rproc_put(prueth->txpru[slice]); - - if (prueth->rtu[slice]) - pru_rproc_put(prueth->rtu[slice]); - - if (prueth->pru[slice]) - pru_rproc_put(prueth->pru[slice]); -} - static int prueth_probe(struct platform_device *pdev) { struct device_node *eth_node, *eth_ports_node; @@ -2036,13 +923,13 @@ static int prueth_probe(struct platform_device *pdev) } if (eth0_node) { - ret = prueth_get_cores(prueth, ICSS_SLICE0); + ret = prueth_get_cores(prueth, ICSS_SLICE0, false); if (ret) goto put_cores; } if (eth1_node) { - ret = prueth_get_cores(prueth, ICSS_SLICE1); + ret = prueth_get_cores(prueth, ICSS_SLICE1, false); if (ret) goto put_cores; } @@ -2285,62 +1172,6 @@ static void prueth_remove(struct platform_device *pdev) prueth_put_cores(prueth, ICSS_SLICE0); } -#ifdef CONFIG_PM_SLEEP -static int prueth_suspend(struct device *dev) -{ - struct prueth *prueth = dev_get_drvdata(dev); - struct net_device *ndev; - int i, ret; - - for (i = 0; i < PRUETH_NUM_MACS; i++) { - ndev = prueth->registered_netdevs[i]; - - if (!ndev) - continue; - - if (netif_running(ndev)) { - netif_device_detach(ndev); - ret = emac_ndo_stop(ndev); - if (ret < 0) { - netdev_err(ndev, "failed to stop: %d", ret); - return ret; - } - } - } - - return 0; -} - -static int prueth_resume(struct device *dev) -{ - struct prueth *prueth = dev_get_drvdata(dev); - struct net_device *ndev; - int i, ret; - - for (i = 0; i < PRUETH_NUM_MACS; i++) { - ndev = prueth->registered_netdevs[i]; - - if (!ndev) - continue; - - if (netif_running(ndev)) { - ret = emac_ndo_open(ndev); - if (ret < 0) { - netdev_err(ndev, "failed to start: %d", ret); - return ret; - } - netif_device_attach(ndev); - } - } - - return 0; -} -#endif /* CONFIG_PM_SLEEP */ - -static const struct dev_pm_ops prueth_dev_pm_ops = { - SET_SYSTEM_SLEEP_PM_OPS(prueth_suspend, prueth_resume) -}; - static const struct prueth_pdata am654_icssg_pdata = { .fdqring_mode = K3_RINGACC_RING_MODE_MESSAGE, .quirk_10m_link_issue = 1, diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h index 8b6d6b4970..a78c5eb75f 100644 --- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h @@ -55,6 +55,8 @@ #define ICSSG_NUM_STANDARD_STATS 31 #define ICSSG_NUM_ETHTOOL_STATS (ICSSG_NUM_STATS - ICSSG_NUM_STANDARD_STATS) +#define IEP_DEFAULT_CYCLE_TIME_NS 1000000 /* 1 ms */ + /* Firmware status codes */ #define ICSS_HS_FW_READY 0x55555555 #define ICSS_HS_FW_DEAD 0xDEAD0000 /* lower 16 bits contain error code */ @@ -106,6 +108,8 @@ struct prueth_tx_chn { u32 descs_num; unsigned int irq; char name[32]; + struct hrtimer tx_hrtimer; + unsigned long tx_pace_timeout_ns; }; struct prueth_rx_chn { @@ -125,8 +129,12 @@ struct prueth_rx_chn { #define PRUETH_MAX_TX_TS_REQUESTS 50 /* Max simultaneous TX_TS requests */ +/* Minimum coalesce time in usecs for both Tx and Rx */ +#define ICSSG_MIN_COALESCE_USECS 20 + /* data for each emac port */ struct prueth_emac { + bool is_sr1; bool fw_running; struct prueth *prueth; struct net_device *ndev; @@ -155,6 +163,10 @@ struct prueth_emac { int rx_flow_id_base; int tx_ch_num; + /* SR1.0 Management channel */ + struct prueth_rx_chn rx_mgm_chn; + int rx_mgm_flow_id_base; + spinlock_t lock; /* serialize access */ /* TX HW Timestamping */ @@ -165,7 +177,7 @@ struct prueth_emac { u8 cmd_seq; /* shutdown related */ - u32 cmd_data[4]; + __le32 cmd_data[4]; struct completion cmd_complete; /* Mutex to serialize access to firmware command interface */ struct mutex cmd_lock; @@ -176,6 +188,10 @@ struct prueth_emac { struct delayed_work stats_work; u64 stats[ICSSG_NUM_STATS]; + + /* RX IRQ Coalescing Related */ + struct hrtimer rx_hrtimer; + unsigned long rx_pace_timeout_ns; }; /** @@ -188,6 +204,12 @@ struct prueth_pdata { u32 quirk_10m_link_issue:1; }; +struct icssg_firmwares { + char *pru; + char *rtu; + char *txpru; +}; + /** * struct prueth - PRUeth structure * @dev: device @@ -243,6 +265,13 @@ struct emac_tx_ts_response { u32 hi_ts; }; +struct emac_tx_ts_response_sr1 { + __le32 lo_ts; + __le32 hi_ts; + __le32 reserved; + __le32 cookie; +}; + /* get PRUSS SLICE number from prueth_emac */ static inline int prueth_emac_slice(struct prueth_emac *emac) { @@ -257,12 +286,17 @@ static inline int prueth_emac_slice(struct prueth_emac *emac) } extern const struct ethtool_ops icssg_ethtool_ops; +extern const struct dev_pm_ops prueth_dev_pm_ops; /* Classifier helpers */ void icssg_class_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac); void icssg_class_set_host_mac_addr(struct regmap *miig_rt, const u8 *mac); void icssg_class_disable(struct regmap *miig_rt, int slice); -void icssg_class_default(struct regmap *miig_rt, int slice, bool allmulti); +void icssg_class_default(struct regmap *miig_rt, int slice, bool allmulti, + bool is_sr1); +void icssg_class_promiscuous_sr1(struct regmap *miig_rt, int slice); +void icssg_class_add_mcast_sr1(struct regmap *miig_rt, int slice, + struct net_device *ndev); void icssg_ft1_set_mac_addr(struct regmap *miig_rt, int slice, u8 *mac_addr); /* config helpers */ @@ -285,4 +319,54 @@ u32 icssg_queue_level(struct prueth *prueth, int queue); void emac_stats_work_handler(struct work_struct *work); void emac_update_hardware_stats(struct prueth_emac *emac); int emac_get_stat_by_name(struct prueth_emac *emac, char *stat_name); + +/* Common functions */ +void prueth_cleanup_rx_chns(struct prueth_emac *emac, + struct prueth_rx_chn *rx_chn, + int max_rflows); +void prueth_cleanup_tx_chns(struct prueth_emac *emac); +void prueth_ndev_del_tx_napi(struct prueth_emac *emac, int num); +void prueth_xmit_free(struct prueth_tx_chn *tx_chn, + struct cppi5_host_desc_t *desc); +int emac_tx_complete_packets(struct prueth_emac *emac, int chn, + int budget, bool *tdown); +int prueth_ndev_add_tx_napi(struct prueth_emac *emac); +int prueth_init_tx_chns(struct prueth_emac *emac); +int prueth_init_rx_chns(struct prueth_emac *emac, + struct prueth_rx_chn *rx_chn, + char *name, u32 max_rflows, + u32 max_desc_num); +int prueth_dma_rx_push(struct prueth_emac *emac, + struct sk_buff *skb, + struct prueth_rx_chn *rx_chn); +void emac_rx_timestamp(struct prueth_emac *emac, + struct sk_buff *skb, u32 *psdata); +enum netdev_tx emac_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev); +irqreturn_t prueth_rx_irq(int irq, void *dev_id); +void prueth_emac_stop(struct prueth_emac *emac); +void prueth_cleanup_tx_ts(struct prueth_emac *emac); +int emac_napi_rx_poll(struct napi_struct *napi_rx, int budget); +int prueth_prepare_rx_chan(struct prueth_emac *emac, + struct prueth_rx_chn *chn, + int buf_size); +void prueth_reset_tx_chan(struct prueth_emac *emac, int ch_num, + bool free_skb); +void prueth_reset_rx_chan(struct prueth_rx_chn *chn, + int num_flows, bool disable); +void emac_ndo_tx_timeout(struct net_device *ndev, unsigned int txqueue); +int emac_ndo_ioctl(struct net_device *ndev, struct ifreq *ifr, int cmd); +void emac_ndo_get_stats64(struct net_device *ndev, + struct rtnl_link_stats64 *stats); +int emac_ndo_get_phys_port_name(struct net_device *ndev, char *name, + size_t len); +int prueth_node_port(struct device_node *eth_node); +int prueth_node_mac(struct device_node *eth_node); +void prueth_netdev_exit(struct prueth *prueth, + struct device_node *eth_node); +int prueth_get_cores(struct prueth *prueth, int slice, bool is_sr1); +void prueth_put_cores(struct prueth *prueth, int slice); + +/* Revision specific helper */ +u64 icssg_ts_to_ns(u32 hi_sw, u32 hi, u32 lo, u32 cycle_time_ns); + #endif /* __NET_TI_ICSSG_PRUETH_H */ diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c new file mode 100644 index 0000000000..7b3304bbd7 --- /dev/null +++ b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c @@ -0,0 +1,1181 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* Texas Instruments ICSSG SR1.0 Ethernet Driver + * + * Copyright (C) 2018-2022 Texas Instruments Incorporated - https://www.ti.com/ + * Copyright (c) Siemens AG, 2024 + * + */ + +#include <linux/etherdevice.h> +#include <linux/genalloc.h> +#include <linux/kernel.h> +#include <linux/mfd/syscon.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_mdio.h> +#include <linux/of_net.h> +#include <linux/platform_device.h> +#include <linux/property.h> +#include <linux/phy.h> +#include <linux/remoteproc/pruss.h> +#include <linux/pruss_driver.h> + +#include "icssg_prueth.h" +#include "icssg_mii_rt.h" +#include "../k3-cppi-desc-pool.h" + +#define PRUETH_MODULE_DESCRIPTION "PRUSS ICSSG SR1.0 Ethernet driver" + +/* SR1: Set buffer sizes for the pools. There are 8 internal queues + * implemented in firmware, but only 4 tx channels/threads in the Egress + * direction to firmware. Need a high priority queue for management + * messages since they shouldn't be blocked even during high traffic + * situation. So use Q0-Q2 as data queues and Q3 as management queue + * in the max case. However for ease of configuration, use the max + * data queue + 1 for management message if we are not using max + * case. + * + * Allocate 4 MTU buffers per data queue. Firmware requires + * pool sizes to be set for internal queues. Set the upper 5 queue + * pool size to min size of 128 bytes since there are only 3 tx + * data channels and management queue requires only minimum buffer. + * i.e lower queues are used by driver and highest priority queue + * from that is used for management message. + */ + +static int emac_egress_buf_pool_size[] = { + PRUETH_EMAC_BUF_POOL_SIZE_SR1, PRUETH_EMAC_BUF_POOL_SIZE_SR1, + PRUETH_EMAC_BUF_POOL_SIZE_SR1, PRUETH_EMAC_BUF_POOL_MIN_SIZE_SR1, + PRUETH_EMAC_BUF_POOL_MIN_SIZE_SR1, PRUETH_EMAC_BUF_POOL_MIN_SIZE_SR1, + PRUETH_EMAC_BUF_POOL_MIN_SIZE_SR1, PRUETH_EMAC_BUF_POOL_MIN_SIZE_SR1 +}; + +static void icssg_config_sr1(struct prueth *prueth, struct prueth_emac *emac, + int slice) +{ + struct icssg_sr1_config config; + void __iomem *va; + int i, index; + + memset(&config, 0, sizeof(config)); + config.addr_lo = cpu_to_le32(lower_32_bits(prueth->msmcram.pa)); + config.addr_hi = cpu_to_le32(upper_32_bits(prueth->msmcram.pa)); + config.rx_flow_id = cpu_to_le32(emac->rx_flow_id_base); /* flow id for host port */ + config.rx_mgr_flow_id = cpu_to_le32(emac->rx_mgm_flow_id_base); /* for mgm ch */ + config.rand_seed = cpu_to_le32(get_random_u32()); + + for (i = PRUETH_EMAC_BUF_POOL_START_SR1; i < PRUETH_NUM_BUF_POOLS_SR1; i++) { + index = i - PRUETH_EMAC_BUF_POOL_START_SR1; + config.tx_buf_sz[i] = cpu_to_le32(emac_egress_buf_pool_size[index]); + } + + va = prueth->shram.va + slice * ICSSG_CONFIG_OFFSET_SLICE1; + memcpy_toio(va, &config, sizeof(config)); + + emac->speed = SPEED_1000; + emac->duplex = DUPLEX_FULL; +} + +static int emac_send_command_sr1(struct prueth_emac *emac, u32 cmd) +{ + struct cppi5_host_desc_t *first_desc; + u32 pkt_len = sizeof(emac->cmd_data); + __le32 *data = emac->cmd_data; + dma_addr_t desc_dma, buf_dma; + struct prueth_tx_chn *tx_chn; + void **swdata; + int ret = 0; + u32 *epib; + + netdev_dbg(emac->ndev, "Sending cmd %x\n", cmd); + + /* only one command at a time allowed to firmware */ + mutex_lock(&emac->cmd_lock); + data[0] = cpu_to_le32(cmd); + + /* highest priority channel for management messages */ + tx_chn = &emac->tx_chns[emac->tx_ch_num - 1]; + + /* Map the linear buffer */ + buf_dma = dma_map_single(tx_chn->dma_dev, data, pkt_len, DMA_TO_DEVICE); + if (dma_mapping_error(tx_chn->dma_dev, buf_dma)) { + netdev_err(emac->ndev, "cmd %x: failed to map cmd buffer\n", cmd); + ret = -EINVAL; + goto err_unlock; + } + + first_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool); + if (!first_desc) { + netdev_err(emac->ndev, "cmd %x: failed to allocate descriptor\n", cmd); + dma_unmap_single(tx_chn->dma_dev, buf_dma, pkt_len, DMA_TO_DEVICE); + ret = -ENOMEM; + goto err_unlock; + } + + cppi5_hdesc_init(first_desc, CPPI5_INFO0_HDESC_EPIB_PRESENT, + PRUETH_NAV_PS_DATA_SIZE); + cppi5_hdesc_set_pkttype(first_desc, PRUETH_PKT_TYPE_CMD); + epib = first_desc->epib; + epib[0] = 0; + epib[1] = 0; + + cppi5_hdesc_attach_buf(first_desc, buf_dma, pkt_len, buf_dma, pkt_len); + swdata = cppi5_hdesc_get_swdata(first_desc); + *swdata = data; + + cppi5_hdesc_set_pktlen(first_desc, pkt_len); + desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, first_desc); + + /* send command */ + reinit_completion(&emac->cmd_complete); + ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma); + if (ret) { + netdev_err(emac->ndev, "cmd %x: push failed: %d\n", cmd, ret); + goto free_desc; + } + ret = wait_for_completion_timeout(&emac->cmd_complete, msecs_to_jiffies(100)); + if (!ret) + netdev_err(emac->ndev, "cmd %x: completion timeout\n", cmd); + + mutex_unlock(&emac->cmd_lock); + + return ret; +free_desc: + prueth_xmit_free(tx_chn, first_desc); +err_unlock: + mutex_unlock(&emac->cmd_lock); + + return ret; +} + +static void icssg_config_set_speed_sr1(struct prueth_emac *emac) +{ + u32 cmd = ICSSG_PSTATE_SPEED_DUPLEX_CMD_SR1, val; + struct prueth *prueth = emac->prueth; + int slice = prueth_emac_slice(emac); + + val = icssg_rgmii_get_speed(prueth->miig_rt, slice); + /* firmware expects speed settings in bit 2-1 */ + val <<= 1; + cmd |= val; + + val = icssg_rgmii_get_fullduplex(prueth->miig_rt, slice); + /* firmware expects full duplex settings in bit 3 */ + val <<= 3; + cmd |= val; + + emac_send_command_sr1(emac, cmd); +} + +/* called back by PHY layer if there is change in link state of hw port*/ +static void emac_adjust_link_sr1(struct net_device *ndev) +{ + struct prueth_emac *emac = netdev_priv(ndev); + struct phy_device *phydev = ndev->phydev; + struct prueth *prueth = emac->prueth; + bool new_state = false; + unsigned long flags; + + if (phydev->link) { + /* check the mode of operation - full/half duplex */ + if (phydev->duplex != emac->duplex) { + new_state = true; + emac->duplex = phydev->duplex; + } + if (phydev->speed != emac->speed) { + new_state = true; + emac->speed = phydev->speed; + } + if (!emac->link) { + new_state = true; + emac->link = 1; + } + } else if (emac->link) { + new_state = true; + emac->link = 0; + + /* f/w should support 100 & 1000 */ + emac->speed = SPEED_1000; + + /* half duplex may not be supported by f/w */ + emac->duplex = DUPLEX_FULL; + } + + if (new_state) { + phy_print_status(phydev); + + /* update RGMII and MII configuration based on PHY negotiated + * values + */ + if (emac->link) { + /* Set the RGMII cfg for gig en and full duplex */ + icssg_update_rgmii_cfg(prueth->miig_rt, emac); + + /* update the Tx IPG based on 100M/1G speed */ + spin_lock_irqsave(&emac->lock, flags); + icssg_config_ipg(emac); + spin_unlock_irqrestore(&emac->lock, flags); + icssg_config_set_speed_sr1(emac); + } + } + + if (emac->link) { + /* reactivate the transmit queue */ + netif_tx_wake_all_queues(ndev); + } else { + netif_tx_stop_all_queues(ndev); + prueth_cleanup_tx_ts(emac); + } +} + +static int emac_phy_connect(struct prueth_emac *emac) +{ + struct prueth *prueth = emac->prueth; + struct net_device *ndev = emac->ndev; + /* connect PHY */ + ndev->phydev = of_phy_connect(emac->ndev, emac->phy_node, + &emac_adjust_link_sr1, 0, + emac->phy_if); + if (!ndev->phydev) { + dev_err(prueth->dev, "couldn't connect to phy %s\n", + emac->phy_node->full_name); + return -ENODEV; + } + + if (!emac->half_duplex) { + dev_dbg(prueth->dev, "half duplex mode is not supported\n"); + phy_remove_link_mode(ndev->phydev, ETHTOOL_LINK_MODE_10baseT_Half_BIT); + } + + /* Remove 100Mbits half-duplex due to RGMII misreporting connection + * as full duplex */ + phy_remove_link_mode(ndev->phydev, ETHTOOL_LINK_MODE_100baseT_Half_BIT); + + /* remove unsupported modes */ + phy_remove_link_mode(ndev->phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT); + phy_remove_link_mode(ndev->phydev, ETHTOOL_LINK_MODE_Pause_BIT); + phy_remove_link_mode(ndev->phydev, ETHTOOL_LINK_MODE_Asym_Pause_BIT); + + if (emac->phy_if == PHY_INTERFACE_MODE_MII) + phy_set_max_speed(ndev->phydev, SPEED_100); + + return 0; +} + +/* get one packet from requested flow_id + * + * Returns skb pointer if packet found else NULL + * Caller must free the returned skb. + */ +static struct sk_buff *prueth_process_rx_mgm(struct prueth_emac *emac, + u32 flow_id) +{ + struct prueth_rx_chn *rx_chn = &emac->rx_mgm_chn; + struct net_device *ndev = emac->ndev; + struct cppi5_host_desc_t *desc_rx; + struct sk_buff *skb, *new_skb; + dma_addr_t desc_dma, buf_dma; + u32 buf_dma_len, pkt_len; + void **swdata; + int ret; + + ret = k3_udma_glue_pop_rx_chn(rx_chn->rx_chn, flow_id, &desc_dma); + if (ret) { + if (ret != -ENODATA) + netdev_err(ndev, "rx mgm pop: failed: %d\n", ret); + return NULL; + } + + if (cppi5_desc_is_tdcm(desc_dma)) /* Teardown */ + return NULL; + + desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma); + + /* Fix FW bug about incorrect PSDATA size */ + if (cppi5_hdesc_get_psdata_size(desc_rx) != PRUETH_NAV_PS_DATA_SIZE) { + cppi5_hdesc_update_psdata_size(desc_rx, + PRUETH_NAV_PS_DATA_SIZE); + } + + swdata = cppi5_hdesc_get_swdata(desc_rx); + skb = *swdata; + cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len); + pkt_len = cppi5_hdesc_get_pktlen(desc_rx); + + dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE); + k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx); + + new_skb = netdev_alloc_skb_ip_align(ndev, PRUETH_MAX_PKT_SIZE); + /* if allocation fails we drop the packet but push the + * descriptor back to the ring with old skb to prevent a stall + */ + if (!new_skb) { + netdev_err(ndev, + "skb alloc failed, dropped mgm pkt from flow %d\n", + flow_id); + new_skb = skb; + skb = NULL; /* return NULL */ + } else { + /* return the filled skb */ + skb_put(skb, pkt_len); + } + + /* queue another DMA */ + ret = prueth_dma_rx_push(emac, new_skb, &emac->rx_mgm_chn); + if (WARN_ON(ret < 0)) + dev_kfree_skb_any(new_skb); + + return skb; +} + +static void prueth_tx_ts_sr1(struct prueth_emac *emac, + struct emac_tx_ts_response_sr1 *tsr) +{ + struct skb_shared_hwtstamps ssh; + u32 hi_ts, lo_ts, cookie; + struct sk_buff *skb; + u64 ns; + + hi_ts = le32_to_cpu(tsr->hi_ts); + lo_ts = le32_to_cpu(tsr->lo_ts); + + ns = (u64)hi_ts << 32 | lo_ts; + + cookie = le32_to_cpu(tsr->cookie); + if (cookie >= PRUETH_MAX_TX_TS_REQUESTS) { + netdev_dbg(emac->ndev, "Invalid TX TS cookie 0x%x\n", + cookie); + return; + } + + skb = emac->tx_ts_skb[cookie]; + emac->tx_ts_skb[cookie] = NULL; /* free slot */ + + memset(&ssh, 0, sizeof(ssh)); + ssh.hwtstamp = ns_to_ktime(ns); + + skb_tstamp_tx(skb, &ssh); + dev_consume_skb_any(skb); +} + +static irqreturn_t prueth_rx_mgm_ts_thread_sr1(int irq, void *dev_id) +{ + struct prueth_emac *emac = dev_id; + struct sk_buff *skb; + + skb = prueth_process_rx_mgm(emac, PRUETH_RX_MGM_FLOW_TIMESTAMP_SR1); + if (!skb) + return IRQ_NONE; + + prueth_tx_ts_sr1(emac, (void *)skb->data); + dev_kfree_skb_any(skb); + + return IRQ_HANDLED; +} + +static irqreturn_t prueth_rx_mgm_rsp_thread(int irq, void *dev_id) +{ + struct prueth_emac *emac = dev_id; + struct sk_buff *skb; + u32 rsp; + + skb = prueth_process_rx_mgm(emac, PRUETH_RX_MGM_FLOW_RESPONSE_SR1); + if (!skb) + return IRQ_NONE; + + /* Process command response */ + rsp = le32_to_cpu(*(__le32 *)skb->data) & 0xffff0000; + if (rsp == ICSSG_SHUTDOWN_CMD_SR1) { + netdev_dbg(emac->ndev, "f/w Shutdown cmd resp %x\n", rsp); + complete(&emac->cmd_complete); + } else if (rsp == ICSSG_PSTATE_SPEED_DUPLEX_CMD_SR1) { + netdev_dbg(emac->ndev, "f/w Speed/Duplex cmd rsp %x\n", rsp); + complete(&emac->cmd_complete); + } + + dev_kfree_skb_any(skb); + + return IRQ_HANDLED; +} + +static struct icssg_firmwares icssg_sr1_emac_firmwares[] = { + { + .pru = "ti-pruss/am65x-pru0-prueth-fw.elf", + .rtu = "ti-pruss/am65x-rtu0-prueth-fw.elf", + }, + { + .pru = "ti-pruss/am65x-pru1-prueth-fw.elf", + .rtu = "ti-pruss/am65x-rtu1-prueth-fw.elf", + } +}; + +static int prueth_emac_start(struct prueth *prueth, struct prueth_emac *emac) +{ + struct icssg_firmwares *firmwares; + struct device *dev = prueth->dev; + int slice, ret; + + firmwares = icssg_sr1_emac_firmwares; + + slice = prueth_emac_slice(emac); + if (slice < 0) { + netdev_err(emac->ndev, "invalid port\n"); + return -EINVAL; + } + + icssg_config_sr1(prueth, emac, slice); + + ret = rproc_set_firmware(prueth->pru[slice], firmwares[slice].pru); + ret = rproc_boot(prueth->pru[slice]); + if (ret) { + dev_err(dev, "failed to boot PRU%d: %d\n", slice, ret); + return -EINVAL; + } + + ret = rproc_set_firmware(prueth->rtu[slice], firmwares[slice].rtu); + ret = rproc_boot(prueth->rtu[slice]); + if (ret) { + dev_err(dev, "failed to boot RTU%d: %d\n", slice, ret); + goto halt_pru; + } + + emac->fw_running = 1; + return 0; + +halt_pru: + rproc_shutdown(prueth->pru[slice]); + + return ret; +} + +/** + * emac_ndo_open - EMAC device open + * @ndev: network adapter device + * + * Called when system wants to start the interface. + * + * Return: 0 for a successful open, or appropriate error code + */ +static int emac_ndo_open(struct net_device *ndev) +{ + struct prueth_emac *emac = netdev_priv(ndev); + int num_data_chn = emac->tx_ch_num - 1; + struct prueth *prueth = emac->prueth; + int slice = prueth_emac_slice(emac); + struct device *dev = prueth->dev; + int max_rx_flows, rx_flow; + int ret, i; + + /* clear SMEM and MSMC settings for all slices */ + if (!prueth->emacs_initialized) { + memset_io(prueth->msmcram.va, 0, prueth->msmcram.size); + memset_io(prueth->shram.va, 0, ICSSG_CONFIG_OFFSET_SLICE1 * PRUETH_NUM_MACS); + } + + /* set h/w MAC as user might have re-configured */ + ether_addr_copy(emac->mac_addr, ndev->dev_addr); + + icssg_class_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr); + + icssg_class_default(prueth->miig_rt, slice, 0, true); + + /* Notify the stack of the actual queue counts. */ + ret = netif_set_real_num_tx_queues(ndev, num_data_chn); + if (ret) { + dev_err(dev, "cannot set real number of tx queues\n"); + return ret; + } + + init_completion(&emac->cmd_complete); + ret = prueth_init_tx_chns(emac); + if (ret) { + dev_err(dev, "failed to init tx channel: %d\n", ret); + return ret; + } + + max_rx_flows = PRUETH_MAX_RX_FLOWS_SR1; + ret = prueth_init_rx_chns(emac, &emac->rx_chns, "rx", + max_rx_flows, PRUETH_MAX_RX_DESC); + if (ret) { + dev_err(dev, "failed to init rx channel: %d\n", ret); + goto cleanup_tx; + } + + ret = prueth_init_rx_chns(emac, &emac->rx_mgm_chn, "rxmgm", + PRUETH_MAX_RX_MGM_FLOWS_SR1, + PRUETH_MAX_RX_MGM_DESC_SR1); + if (ret) { + dev_err(dev, "failed to init rx mgmt channel: %d\n", + ret); + goto cleanup_rx; + } + + ret = prueth_ndev_add_tx_napi(emac); + if (ret) + goto cleanup_rx_mgm; + + /* we use only the highest priority flow for now i.e. @irq[3] */ + rx_flow = PRUETH_RX_FLOW_DATA_SR1; + ret = request_irq(emac->rx_chns.irq[rx_flow], prueth_rx_irq, + IRQF_TRIGGER_HIGH, dev_name(dev), emac); + if (ret) { + dev_err(dev, "unable to request RX IRQ\n"); + goto cleanup_napi; + } + + ret = request_threaded_irq(emac->rx_mgm_chn.irq[PRUETH_RX_MGM_FLOW_RESPONSE_SR1], + NULL, prueth_rx_mgm_rsp_thread, + IRQF_ONESHOT | IRQF_TRIGGER_HIGH, + dev_name(dev), emac); + if (ret) { + dev_err(dev, "unable to request RX Management RSP IRQ\n"); + goto free_rx_irq; + } + + ret = request_threaded_irq(emac->rx_mgm_chn.irq[PRUETH_RX_MGM_FLOW_TIMESTAMP_SR1], + NULL, prueth_rx_mgm_ts_thread_sr1, + IRQF_ONESHOT | IRQF_TRIGGER_HIGH, + dev_name(dev), emac); + if (ret) { + dev_err(dev, "unable to request RX Management TS IRQ\n"); + goto free_rx_mgm_rsp_irq; + } + + /* reset and start PRU firmware */ + ret = prueth_emac_start(prueth, emac); + if (ret) + goto free_rx_mgmt_ts_irq; + + icssg_mii_update_mtu(prueth->mii_rt, slice, ndev->max_mtu); + + /* Prepare RX */ + ret = prueth_prepare_rx_chan(emac, &emac->rx_chns, PRUETH_MAX_PKT_SIZE); + if (ret) + goto stop; + + ret = prueth_prepare_rx_chan(emac, &emac->rx_mgm_chn, 64); + if (ret) + goto reset_rx_chn; + + ret = k3_udma_glue_enable_rx_chn(emac->rx_mgm_chn.rx_chn); + if (ret) + goto reset_rx_chn; + + ret = k3_udma_glue_enable_rx_chn(emac->rx_chns.rx_chn); + if (ret) + goto reset_rx_mgm_chn; + + for (i = 0; i < emac->tx_ch_num; i++) { + ret = k3_udma_glue_enable_tx_chn(emac->tx_chns[i].tx_chn); + if (ret) + goto reset_tx_chan; + } + + /* Enable NAPI in Tx and Rx direction */ + for (i = 0; i < emac->tx_ch_num; i++) + napi_enable(&emac->tx_chns[i].napi_tx); + napi_enable(&emac->napi_rx); + + /* start PHY */ + phy_start(ndev->phydev); + + prueth->emacs_initialized++; + + queue_work(system_long_wq, &emac->stats_work.work); + + return 0; + +reset_tx_chan: + /* Since interface is not yet up, there is wouldn't be + * any SKB for completion. So set false to free_skb + */ + prueth_reset_tx_chan(emac, i, false); +reset_rx_mgm_chn: + prueth_reset_rx_chan(&emac->rx_mgm_chn, + PRUETH_MAX_RX_MGM_FLOWS_SR1, true); +reset_rx_chn: + prueth_reset_rx_chan(&emac->rx_chns, max_rx_flows, false); +stop: + prueth_emac_stop(emac); +free_rx_mgmt_ts_irq: + free_irq(emac->rx_mgm_chn.irq[PRUETH_RX_MGM_FLOW_TIMESTAMP_SR1], + emac); +free_rx_mgm_rsp_irq: + free_irq(emac->rx_mgm_chn.irq[PRUETH_RX_MGM_FLOW_RESPONSE_SR1], + emac); +free_rx_irq: + free_irq(emac->rx_chns.irq[rx_flow], emac); +cleanup_napi: + prueth_ndev_del_tx_napi(emac, emac->tx_ch_num); +cleanup_rx_mgm: + prueth_cleanup_rx_chns(emac, &emac->rx_mgm_chn, + PRUETH_MAX_RX_MGM_FLOWS_SR1); +cleanup_rx: + prueth_cleanup_rx_chns(emac, &emac->rx_chns, max_rx_flows); +cleanup_tx: + prueth_cleanup_tx_chns(emac); + + return ret; +} + +/** + * emac_ndo_stop - EMAC device stop + * @ndev: network adapter device + * + * Called when system wants to stop or down the interface. + * + * Return: Always 0 (Success) + */ +static int emac_ndo_stop(struct net_device *ndev) +{ + struct prueth_emac *emac = netdev_priv(ndev); + int rx_flow = PRUETH_RX_FLOW_DATA_SR1; + struct prueth *prueth = emac->prueth; + int max_rx_flows; + int ret, i; + + /* inform the upper layers. */ + netif_tx_stop_all_queues(ndev); + + /* block packets from wire */ + if (ndev->phydev) + phy_stop(ndev->phydev); + + icssg_class_disable(prueth->miig_rt, prueth_emac_slice(emac)); + + emac_send_command_sr1(emac, ICSSG_SHUTDOWN_CMD_SR1); + + atomic_set(&emac->tdown_cnt, emac->tx_ch_num); + /* ensure new tdown_cnt value is visible */ + smp_mb__after_atomic(); + /* tear down and disable UDMA channels */ + reinit_completion(&emac->tdown_complete); + for (i = 0; i < emac->tx_ch_num; i++) + k3_udma_glue_tdown_tx_chn(emac->tx_chns[i].tx_chn, false); + + ret = wait_for_completion_timeout(&emac->tdown_complete, + msecs_to_jiffies(1000)); + if (!ret) + netdev_err(ndev, "tx teardown timeout\n"); + + prueth_reset_tx_chan(emac, emac->tx_ch_num, true); + for (i = 0; i < emac->tx_ch_num; i++) + napi_disable(&emac->tx_chns[i].napi_tx); + + max_rx_flows = PRUETH_MAX_RX_FLOWS_SR1; + k3_udma_glue_tdown_rx_chn(emac->rx_chns.rx_chn, true); + + prueth_reset_rx_chan(&emac->rx_chns, max_rx_flows, true); + /* Teardown RX MGM channel */ + k3_udma_glue_tdown_rx_chn(emac->rx_mgm_chn.rx_chn, true); + prueth_reset_rx_chan(&emac->rx_mgm_chn, + PRUETH_MAX_RX_MGM_FLOWS_SR1, true); + + napi_disable(&emac->napi_rx); + + /* Destroying the queued work in ndo_stop() */ + cancel_delayed_work_sync(&emac->stats_work); + + /* stop PRUs */ + prueth_emac_stop(emac); + + free_irq(emac->rx_mgm_chn.irq[PRUETH_RX_MGM_FLOW_TIMESTAMP_SR1], emac); + free_irq(emac->rx_mgm_chn.irq[PRUETH_RX_MGM_FLOW_RESPONSE_SR1], emac); + free_irq(emac->rx_chns.irq[rx_flow], emac); + prueth_ndev_del_tx_napi(emac, emac->tx_ch_num); + prueth_cleanup_tx_chns(emac); + + prueth_cleanup_rx_chns(emac, &emac->rx_mgm_chn, PRUETH_MAX_RX_MGM_FLOWS_SR1); + prueth_cleanup_rx_chns(emac, &emac->rx_chns, max_rx_flows); + + prueth->emacs_initialized--; + + return 0; +} + +static void emac_ndo_set_rx_mode_sr1(struct net_device *ndev) +{ + struct prueth_emac *emac = netdev_priv(ndev); + bool allmulti = ndev->flags & IFF_ALLMULTI; + bool promisc = ndev->flags & IFF_PROMISC; + struct prueth *prueth = emac->prueth; + int slice = prueth_emac_slice(emac); + + if (promisc) { + icssg_class_promiscuous_sr1(prueth->miig_rt, slice); + return; + } + + if (allmulti) { + icssg_class_default(prueth->miig_rt, slice, 1, true); + return; + } + + icssg_class_default(prueth->miig_rt, slice, 0, true); + if (!netdev_mc_empty(ndev)) { + /* program multicast address list into Classifier */ + icssg_class_add_mcast_sr1(prueth->miig_rt, slice, ndev); + } +} + +static const struct net_device_ops emac_netdev_ops = { + .ndo_open = emac_ndo_open, + .ndo_stop = emac_ndo_stop, + .ndo_start_xmit = emac_ndo_start_xmit, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, + .ndo_tx_timeout = emac_ndo_tx_timeout, + .ndo_set_rx_mode = emac_ndo_set_rx_mode_sr1, + .ndo_eth_ioctl = emac_ndo_ioctl, + .ndo_get_stats64 = emac_ndo_get_stats64, + .ndo_get_phys_port_name = emac_ndo_get_phys_port_name, +}; + +static int prueth_netdev_init(struct prueth *prueth, + struct device_node *eth_node) +{ + struct prueth_emac *emac; + struct net_device *ndev; + enum prueth_port port; + enum prueth_mac mac; + /* Only enable one TX channel due to timeouts when + * using multiple channels */ + int num_tx_chn = 1; + int ret; + + port = prueth_node_port(eth_node); + if (port == PRUETH_PORT_INVALID) + return -EINVAL; + + mac = prueth_node_mac(eth_node); + if (mac == PRUETH_MAC_INVALID) + return -EINVAL; + + ndev = alloc_etherdev_mq(sizeof(*emac), num_tx_chn); + if (!ndev) + return -ENOMEM; + + emac = netdev_priv(ndev); + emac->is_sr1 = 1; + emac->prueth = prueth; + emac->ndev = ndev; + emac->port_id = port; + emac->cmd_wq = create_singlethread_workqueue("icssg_cmd_wq"); + if (!emac->cmd_wq) { + ret = -ENOMEM; + goto free_ndev; + } + + INIT_DELAYED_WORK(&emac->stats_work, emac_stats_work_handler); + + ret = pruss_request_mem_region(prueth->pruss, + port == PRUETH_PORT_MII0 ? + PRUSS_MEM_DRAM0 : PRUSS_MEM_DRAM1, + &emac->dram); + if (ret) { + dev_err(prueth->dev, "unable to get DRAM: %d\n", ret); + ret = -ENOMEM; + goto free_wq; + } + + /* SR1.0 uses a dedicated high priority channel + * to send commands to the firmware + */ + emac->tx_ch_num = 2; + + SET_NETDEV_DEV(ndev, prueth->dev); + spin_lock_init(&emac->lock); + mutex_init(&emac->cmd_lock); + + emac->phy_node = of_parse_phandle(eth_node, "phy-handle", 0); + if (!emac->phy_node && !of_phy_is_fixed_link(eth_node)) { + dev_err(prueth->dev, "couldn't find phy-handle\n"); + ret = -ENODEV; + goto free; + } else if (of_phy_is_fixed_link(eth_node)) { + ret = of_phy_register_fixed_link(eth_node); + if (ret) { + ret = dev_err_probe(prueth->dev, ret, + "failed to register fixed-link phy\n"); + goto free; + } + + emac->phy_node = eth_node; + } + + ret = of_get_phy_mode(eth_node, &emac->phy_if); + if (ret) { + dev_err(prueth->dev, "could not get phy-mode property\n"); + goto free; + } + + if (emac->phy_if != PHY_INTERFACE_MODE_MII && + !phy_interface_mode_is_rgmii(emac->phy_if)) { + dev_err(prueth->dev, "PHY mode unsupported %s\n", phy_modes(emac->phy_if)); + ret = -EINVAL; + goto free; + } + + /* AM65 SR2.0 has TX Internal delay always enabled by hardware + * and it is not possible to disable TX Internal delay. The below + * switch case block describes how we handle different phy modes + * based on hardware restriction. + */ + switch (emac->phy_if) { + case PHY_INTERFACE_MODE_RGMII_ID: + emac->phy_if = PHY_INTERFACE_MODE_RGMII_RXID; + break; + case PHY_INTERFACE_MODE_RGMII_TXID: + emac->phy_if = PHY_INTERFACE_MODE_RGMII; + break; + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_RXID: + dev_err(prueth->dev, "RGMII mode without TX delay is not supported"); + ret = -EINVAL; + goto free; + default: + break; + } + + /* get mac address from DT and set private and netdev addr */ + ret = of_get_ethdev_address(eth_node, ndev); + if (!is_valid_ether_addr(ndev->dev_addr)) { + eth_hw_addr_random(ndev); + dev_warn(prueth->dev, "port %d: using random MAC addr: %pM\n", + port, ndev->dev_addr); + } + ether_addr_copy(emac->mac_addr, ndev->dev_addr); + + ndev->min_mtu = PRUETH_MIN_PKT_SIZE; + ndev->max_mtu = PRUETH_MAX_MTU; + ndev->netdev_ops = &emac_netdev_ops; + ndev->ethtool_ops = &icssg_ethtool_ops; + ndev->hw_features = NETIF_F_SG; + ndev->features = ndev->hw_features; + + netif_napi_add(ndev, &emac->napi_rx, emac_napi_rx_poll); + prueth->emac[mac] = emac; + + return 0; + +free: + pruss_release_mem_region(prueth->pruss, &emac->dram); +free_wq: + destroy_workqueue(emac->cmd_wq); +free_ndev: + emac->ndev = NULL; + prueth->emac[mac] = NULL; + free_netdev(ndev); + + return ret; +} + +static int prueth_probe(struct platform_device *pdev) +{ + struct device_node *eth_node, *eth_ports_node; + struct device_node *eth0_node = NULL; + struct device_node *eth1_node = NULL; + struct device *dev = &pdev->dev; + struct device_node *np; + struct prueth *prueth; + struct pruss *pruss; + u32 msmc_ram_size; + int i, ret; + + np = dev->of_node; + + prueth = devm_kzalloc(dev, sizeof(*prueth), GFP_KERNEL); + if (!prueth) + return -ENOMEM; + + dev_set_drvdata(dev, prueth); + prueth->pdev = pdev; + prueth->pdata = *(const struct prueth_pdata *)device_get_match_data(dev); + + prueth->dev = dev; + eth_ports_node = of_get_child_by_name(np, "ethernet-ports"); + if (!eth_ports_node) + return -ENOENT; + + for_each_child_of_node(eth_ports_node, eth_node) { + u32 reg; + + if (strcmp(eth_node->name, "port")) + continue; + ret = of_property_read_u32(eth_node, "reg", ®); + if (ret < 0) { + dev_err(dev, "%pOF error reading port_id %d\n", + eth_node, ret); + } + + of_node_get(eth_node); + + if (reg == 0) { + eth0_node = eth_node; + if (!of_device_is_available(eth0_node)) { + of_node_put(eth0_node); + eth0_node = NULL; + } + } else if (reg == 1) { + eth1_node = eth_node; + if (!of_device_is_available(eth1_node)) { + of_node_put(eth1_node); + eth1_node = NULL; + } + } else { + dev_err(dev, "port reg should be 0 or 1\n"); + } + } + + of_node_put(eth_ports_node); + + /* At least one node must be present and available else we fail */ + if (!eth0_node && !eth1_node) { + dev_err(dev, "neither port0 nor port1 node available\n"); + return -ENODEV; + } + + if (eth0_node == eth1_node) { + dev_err(dev, "port0 and port1 can't have same reg\n"); + of_node_put(eth0_node); + return -ENODEV; + } + + prueth->eth_node[PRUETH_MAC0] = eth0_node; + prueth->eth_node[PRUETH_MAC1] = eth1_node; + + prueth->miig_rt = syscon_regmap_lookup_by_phandle(np, "ti,mii-g-rt"); + if (IS_ERR(prueth->miig_rt)) { + dev_err(dev, "couldn't get ti,mii-g-rt syscon regmap\n"); + return -ENODEV; + } + + prueth->mii_rt = syscon_regmap_lookup_by_phandle(np, "ti,mii-rt"); + if (IS_ERR(prueth->mii_rt)) { + dev_err(dev, "couldn't get ti,mii-rt syscon regmap\n"); + return -ENODEV; + } + + if (eth0_node) { + ret = prueth_get_cores(prueth, ICSS_SLICE0, true); + if (ret) + goto put_cores; + } + + if (eth1_node) { + ret = prueth_get_cores(prueth, ICSS_SLICE1, true); + if (ret) + goto put_cores; + } + + pruss = pruss_get(eth0_node ? + prueth->pru[ICSS_SLICE0] : prueth->pru[ICSS_SLICE1]); + if (IS_ERR(pruss)) { + ret = PTR_ERR(pruss); + dev_err(dev, "unable to get pruss handle\n"); + goto put_cores; + } + + prueth->pruss = pruss; + + ret = pruss_request_mem_region(pruss, PRUSS_MEM_SHRD_RAM2, + &prueth->shram); + if (ret) { + dev_err(dev, "unable to get PRUSS SHRD RAM2: %d\n", ret); + goto put_pruss; + } + + prueth->sram_pool = of_gen_pool_get(np, "sram", 0); + if (!prueth->sram_pool) { + dev_err(dev, "unable to get SRAM pool\n"); + ret = -ENODEV; + + goto put_mem; + } + + msmc_ram_size = MSMC_RAM_SIZE_SR1; + + prueth->msmcram.va = (void __iomem *)gen_pool_alloc(prueth->sram_pool, + msmc_ram_size); + + if (!prueth->msmcram.va) { + ret = -ENOMEM; + dev_err(dev, "unable to allocate MSMC resource\n"); + goto put_mem; + } + prueth->msmcram.pa = gen_pool_virt_to_phys(prueth->sram_pool, + (unsigned long)prueth->msmcram.va); + prueth->msmcram.size = msmc_ram_size; + memset_io(prueth->msmcram.va, 0, msmc_ram_size); + dev_dbg(dev, "sram: pa %llx va %p size %zx\n", prueth->msmcram.pa, + prueth->msmcram.va, prueth->msmcram.size); + + if (eth0_node) { + ret = prueth_netdev_init(prueth, eth0_node); + if (ret) { + dev_err_probe(dev, ret, "netdev init %s failed\n", + eth0_node->name); + goto free_pool; + } + + if (of_find_property(eth0_node, "ti,half-duplex-capable", NULL)) + prueth->emac[PRUETH_MAC0]->half_duplex = 1; + } + + if (eth1_node) { + ret = prueth_netdev_init(prueth, eth1_node); + if (ret) { + dev_err_probe(dev, ret, "netdev init %s failed\n", + eth1_node->name); + goto netdev_exit; + } + + if (of_find_property(eth1_node, "ti,half-duplex-capable", NULL)) + prueth->emac[PRUETH_MAC1]->half_duplex = 1; + } + + /* register the network devices */ + if (eth0_node) { + ret = register_netdev(prueth->emac[PRUETH_MAC0]->ndev); + if (ret) { + dev_err(dev, "can't register netdev for port MII0\n"); + goto netdev_exit; + } + + prueth->registered_netdevs[PRUETH_MAC0] = prueth->emac[PRUETH_MAC0]->ndev; + emac_phy_connect(prueth->emac[PRUETH_MAC0]); + phy_attached_info(prueth->emac[PRUETH_MAC0]->ndev->phydev); + } + + if (eth1_node) { + ret = register_netdev(prueth->emac[PRUETH_MAC1]->ndev); + if (ret) { + dev_err(dev, "can't register netdev for port MII1\n"); + goto netdev_unregister; + } + + prueth->registered_netdevs[PRUETH_MAC1] = prueth->emac[PRUETH_MAC1]->ndev; + emac_phy_connect(prueth->emac[PRUETH_MAC1]); + phy_attached_info(prueth->emac[PRUETH_MAC1]->ndev->phydev); + } + + dev_info(dev, "TI PRU SR1.0 ethernet driver initialized: %s EMAC mode\n", + (!eth0_node || !eth1_node) ? "single" : "dual"); + + if (eth1_node) + of_node_put(eth1_node); + if (eth0_node) + of_node_put(eth0_node); + + return 0; + +netdev_unregister: + for (i = 0; i < PRUETH_NUM_MACS; i++) { + if (!prueth->registered_netdevs[i]) + continue; + + if (prueth->emac[i]->ndev->phydev) { + phy_disconnect(prueth->emac[i]->ndev->phydev); + prueth->emac[i]->ndev->phydev = NULL; + } + unregister_netdev(prueth->registered_netdevs[i]); + } + +netdev_exit: + for (i = 0; i < PRUETH_NUM_MACS; i++) { + eth_node = prueth->eth_node[i]; + if (!eth_node) + continue; + + prueth_netdev_exit(prueth, eth_node); + } + +free_pool: + gen_pool_free(prueth->sram_pool, + (unsigned long)prueth->msmcram.va, msmc_ram_size); + +put_mem: + pruss_release_mem_region(prueth->pruss, &prueth->shram); + +put_pruss: + pruss_put(prueth->pruss); + +put_cores: + if (eth1_node) { + prueth_put_cores(prueth, ICSS_SLICE1); + of_node_put(eth1_node); + } + + if (eth0_node) { + prueth_put_cores(prueth, ICSS_SLICE0); + of_node_put(eth0_node); + } + + return ret; +} + +static void prueth_remove(struct platform_device *pdev) +{ + struct prueth *prueth = platform_get_drvdata(pdev); + struct device_node *eth_node; + int i; + + for (i = 0; i < PRUETH_NUM_MACS; i++) { + if (!prueth->registered_netdevs[i]) + continue; + phy_stop(prueth->emac[i]->ndev->phydev); + phy_disconnect(prueth->emac[i]->ndev->phydev); + prueth->emac[i]->ndev->phydev = NULL; + unregister_netdev(prueth->registered_netdevs[i]); + } + + for (i = 0; i < PRUETH_NUM_MACS; i++) { + eth_node = prueth->eth_node[i]; + if (!eth_node) + continue; + + prueth_netdev_exit(prueth, eth_node); + } + + gen_pool_free(prueth->sram_pool, + (unsigned long)prueth->msmcram.va, + MSMC_RAM_SIZE_SR1); + + pruss_release_mem_region(prueth->pruss, &prueth->shram); + + pruss_put(prueth->pruss); + + if (prueth->eth_node[PRUETH_MAC1]) + prueth_put_cores(prueth, ICSS_SLICE1); + + if (prueth->eth_node[PRUETH_MAC0]) + prueth_put_cores(prueth, ICSS_SLICE0); +} + +static const struct prueth_pdata am654_sr1_icssg_pdata = { + .fdqring_mode = K3_RINGACC_RING_MODE_MESSAGE, +}; + +static const struct of_device_id prueth_dt_match[] = { + { .compatible = "ti,am654-sr1-icssg-prueth", .data = &am654_sr1_icssg_pdata }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, prueth_dt_match); + +static struct platform_driver prueth_driver = { + .probe = prueth_probe, + .remove_new = prueth_remove, + .driver = { + .name = "icssg-prueth-sr1", + .of_match_table = prueth_dt_match, + .pm = &prueth_dev_pm_ops, + }, +}; +module_platform_driver(prueth_driver); + +MODULE_AUTHOR("Roger Quadros <rogerq@ti.com>"); +MODULE_AUTHOR("Md Danish Anwar <danishanwar@ti.com>"); +MODULE_AUTHOR("Diogo Ivo <diogo.ivo@siemens.com>"); +MODULE_DESCRIPTION(PRUETH_MODULE_DESCRIPTION); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/ethernet/ti/k3-cppi-desc-pool.c b/drivers/net/ethernet/ti/k3-cppi-desc-pool.c index 05cc7aab1e..739bae8e11 100644 --- a/drivers/net/ethernet/ti/k3-cppi-desc-pool.c +++ b/drivers/net/ethernet/ti/k3-cppi-desc-pool.c @@ -22,6 +22,7 @@ struct k3_cppi_desc_pool { size_t mem_size; size_t num_desc; struct gen_pool *gen_pool; + void **desc_infos; }; void k3_cppi_desc_pool_destroy(struct k3_cppi_desc_pool *pool) @@ -37,7 +38,11 @@ void k3_cppi_desc_pool_destroy(struct k3_cppi_desc_pool *pool) dma_free_coherent(pool->dev, pool->mem_size, pool->cpumem, pool->dma_addr); + kfree(pool->desc_infos); + gen_pool_destroy(pool->gen_pool); /* frees pool->name */ + + kfree(pool); } EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_destroy); @@ -50,7 +55,7 @@ k3_cppi_desc_pool_create_name(struct device *dev, size_t size, const char *pool_name = NULL; int ret = -ENOMEM; - pool = devm_kzalloc(dev, sizeof(*pool), GFP_KERNEL); + pool = kzalloc(sizeof(*pool), GFP_KERNEL); if (!pool) return ERR_PTR(ret); @@ -62,18 +67,21 @@ k3_cppi_desc_pool_create_name(struct device *dev, size_t size, pool_name = kstrdup_const(name ? name : dev_name(pool->dev), GFP_KERNEL); if (!pool_name) - return ERR_PTR(-ENOMEM); + goto gen_pool_create_fail; pool->gen_pool = gen_pool_create(ilog2(pool->desc_size), -1); if (!pool->gen_pool) { - ret = -ENOMEM; - dev_err(pool->dev, "pool create failed %d\n", ret); kfree_const(pool_name); goto gen_pool_create_fail; } pool->gen_pool->name = pool_name; + pool->desc_infos = kcalloc(pool->num_desc, + sizeof(*pool->desc_infos), GFP_KERNEL); + if (!pool->desc_infos) + goto gen_pool_desc_infos_alloc_fail; + pool->cpumem = dma_alloc_coherent(pool->dev, pool->mem_size, &pool->dma_addr, GFP_KERNEL); @@ -94,9 +102,11 @@ gen_pool_add_virt_fail: dma_free_coherent(pool->dev, pool->mem_size, pool->cpumem, pool->dma_addr); dma_alloc_fail: + kfree(pool->desc_infos); +gen_pool_desc_infos_alloc_fail: gen_pool_destroy(pool->gen_pool); /* frees pool->name */ gen_pool_create_fail: - devm_kfree(pool->dev, pool); + kfree(pool); return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_create_name); @@ -132,5 +142,31 @@ size_t k3_cppi_desc_pool_avail(struct k3_cppi_desc_pool *pool) } EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_avail); +size_t k3_cppi_desc_pool_desc_size(const struct k3_cppi_desc_pool *pool) +{ + return pool->desc_size; +} +EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_desc_size); + +void *k3_cppi_desc_pool_cpuaddr(const struct k3_cppi_desc_pool *pool) +{ + return pool->cpumem; +} +EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_cpuaddr); + +void k3_cppi_desc_pool_desc_info_set(struct k3_cppi_desc_pool *pool, + int desc_idx, void *info) +{ + pool->desc_infos[desc_idx] = info; +} +EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_desc_info_set); + +void *k3_cppi_desc_pool_desc_info(const struct k3_cppi_desc_pool *pool, + int desc_idx) +{ + return pool->desc_infos[desc_idx]; +} +EXPORT_SYMBOL_GPL(k3_cppi_desc_pool_desc_info); + MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("TI K3 CPPI5 descriptors pool API"); diff --git a/drivers/net/ethernet/ti/k3-cppi-desc-pool.h b/drivers/net/ethernet/ti/k3-cppi-desc-pool.h index a7e3fa5e7b..851d352b33 100644 --- a/drivers/net/ethernet/ti/k3-cppi-desc-pool.h +++ b/drivers/net/ethernet/ti/k3-cppi-desc-pool.h @@ -26,5 +26,11 @@ k3_cppi_desc_pool_dma2virt(struct k3_cppi_desc_pool *pool, dma_addr_t dma); void *k3_cppi_desc_pool_alloc(struct k3_cppi_desc_pool *pool); void k3_cppi_desc_pool_free(struct k3_cppi_desc_pool *pool, void *addr); size_t k3_cppi_desc_pool_avail(struct k3_cppi_desc_pool *pool); +size_t k3_cppi_desc_pool_desc_size(const struct k3_cppi_desc_pool *pool); +void *k3_cppi_desc_pool_cpuaddr(const struct k3_cppi_desc_pool *pool); +void k3_cppi_desc_pool_desc_info_set(struct k3_cppi_desc_pool *pool, + int desc_idx, void *info); +void *k3_cppi_desc_pool_desc_info(const struct k3_cppi_desc_pool *pool, + int desc_idx); #endif /* K3_CPPI_DESC_POOL_H_ */ |