From patchwork Fri Jan 5 09:00:27 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Justin Lai X-Patchwork-Id: 13511857 X-Patchwork-Delegate: kuba@kernel.org Received: from rtits2.realtek.com.tw (rtits2.realtek.com [211.75.126.72]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id D41FB225A1; Fri, 5 Jan 2024 09:01:08 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=realtek.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=realtek.com X-SpamFilter-By: ArmorX SpamTrap 5.78 with qID 40590ot162289439, This message is accepted by code: ctloc85258 Received: from mail.realtek.com (rtexh36506.realtek.com.tw[172.21.6.27]) by rtits2.realtek.com.tw (8.15.2/2.95/5.92) with ESMTPS id 40590ot162289439 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Fri, 5 Jan 2024 17:00:50 +0800 Received: from RTEXDAG02.realtek.com.tw (172.21.6.101) by RTEXH36506.realtek.com.tw (172.21.6.27) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2507.17; Fri, 5 Jan 2024 17:00:50 +0800 Received: from RTDOMAIN (172.21.210.160) by RTEXDAG02.realtek.com.tw (172.21.6.101) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2375.7; Fri, 5 Jan 2024 17:00:50 +0800 From: Justin Lai To: CC: , , , , , , , , Justin Lai Subject: [PATCH net-next v15 01/13] rtase: Add pci table supported in this module Date: Fri, 5 Jan 2024 17:00:27 +0800 Message-ID: <20240105090039.377561-2-justinlai0215@realtek.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240105090039.377561-1-justinlai0215@realtek.com> References: <20240105090039.377561-1-justinlai0215@realtek.com> Precedence: bulk X-Mailing-List: netdev@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-ClientProxiedBy: RTEXH36505.realtek.com.tw (172.21.6.25) To RTEXDAG02.realtek.com.tw (172.21.6.101) X-KSE-ServerInfo: RTEXDAG02.realtek.com.tw, 9 X-KSE-AntiSpam-Interceptor-Info: fallback X-KSE-Antivirus-Interceptor-Info: fallback X-KSE-AntiSpam-Interceptor-Info: fallback X-Patchwork-Delegate: kuba@kernel.org Add pci table supported in this module, and implement pci_driver function to initialize this driver, remove this driver, or shutdown this driver. Signed-off-by: Justin Lai --- drivers/net/ethernet/realtek/rtase/rtase.h | 336 ++++++++++ .../net/ethernet/realtek/rtase/rtase_main.c | 617 ++++++++++++++++++ 2 files changed, 953 insertions(+) create mode 100644 drivers/net/ethernet/realtek/rtase/rtase.h create mode 100644 drivers/net/ethernet/realtek/rtase/rtase_main.c diff --git a/drivers/net/ethernet/realtek/rtase/rtase.h b/drivers/net/ethernet/realtek/rtase/rtase.h new file mode 100644 index 000000000000..9874be9cd153 --- /dev/null +++ b/drivers/net/ethernet/realtek/rtase/rtase.h @@ -0,0 +1,336 @@ +/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */ +/* + * rtase is the Linux device driver released for Realtek Automotive Switch + * controllers with PCI-Express interface. + * + * Copyright(c) 2023 Realtek Semiconductor Corp. + */ + +#ifndef _RTASE_H_ +#define _RTASE_H_ + +/* the low 32 bit address of receive buffer must be 8-byte alignment. */ +#define RTK_RX_ALIGN 8 + +#define HW_VER_MASK 0x7C800000 + +#define RX_DMA_BURST_256 4 +#define TX_DMA_BURST_UNLIMITED 7 +#define RX_BUF_SIZE (PAGE_SIZE - \ + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))) +#define MAX_JUMBO_SIZE (RX_BUF_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN) + +/* 3 means InterFrameGap = the shortest one */ +#define INTERFRAMEGAP 0x03 + +#define RTASE_REGS_SIZE 256 +#define RTASE_PCI_REGS_SIZE 0x100 + +#define MULTICAST_FILTER_MASK GENMASK(30, 26) +#define MULTICAST_FILTER_LIMIT 32 + +#define RTASE_VLAN_FILTER_ENTRY_NUM 32 +#define RTASE_NUM_TX_QUEUE 8 +#define RTASE_NUM_RX_QUEUE 4 + +#define RTASE_TXQ_CTRL 1 +#define RTASE_FUNC_TXQ_NUM 1 +#define RTASE_FUNC_RXQ_NUM 1 +#define RTASE_INTERRUPT_NUM 1 + +#define MITI_TIME_COUNT_MASK GENMASK(3, 0) +#define MITI_TIME_UNIT_MASK GENMASK(7, 4) +#define MITI_DEFAULT_TIME 128 +#define MITI_MAX_TIME 491520 +#define MITI_PKT_NUM_COUNT_MASK GENMASK(11, 8) +#define MITI_PKT_NUM_UNIT_MASK GENMASK(13, 12) +#define MITI_DEFAULT_PKT_NUM 64 +#define MITI_MAX_PKT_NUM_IDX 3 +#define MITI_MAX_PKT_NUM_UNIT 16 +#define MITI_MAX_PKT_NUM 240 +#define MITI_COUNT_BIT_NUM 4 + +#define RTASE_NUM_MSIX 4 + +#define RTASE_DWORD_MOD 16 + +/*****************************************************************************/ +enum rtase_registers { + RTASE_MAC0 = 0x0000, + RTASE_MAC4 = 0x0004, + RTASE_MAR0 = 0x0008, + RTASE_MAR1 = 0x000C, + RTASE_DTCCR0 = 0x0010, + RTASE_DTCCR4 = 0x0014, +#define COUNTER_RESET BIT(0) +#define COUNTER_DUMP BIT(3) + + RTASE_FCR = 0x0018, +#define FCR_RXQ_MASK GENMASK(5, 4) +#define FCR_VLAN_FTR_EN BIT(1) + + RTASE_LBK_CTRL = 0x001A, +#define LBK_ATLD BIT(1) +#define LBK_CLR BIT(0) + + RTASE_TX_DESC_ADDR0 = 0x0020, + RTASE_TX_DESC_ADDR4 = 0x0024, + RTASE_TX_DESC_COMMAND = 0x0028, +#define TX_DESC_CMD_CS BIT(15) +#define TX_DESC_CMD_WE BIT(14) + + RTASE_BOOT_CTL = 0x6004, + RTASE_CLKSW_SET = 0x6018, + + RTASE_CHIP_CMD = 0x0037, +#define STOP_REQ BIT(7) +#define STOP_REQ_DONE BIT(6) +#define RE BIT(3) +#define TE BIT(2) + + RTASE_IMR0 = 0x0038, + RTASE_ISR0 = 0x003C, +#define TOK7 BIT(30) +#define TOK6 BIT(28) +#define TOK5 BIT(26) +#define TOK4 BIT(24) +#define FOVW BIT(6) +#define RDU BIT(4) +#define TOK BIT(2) +#define ROK BIT(0) + + RTASE_IMR1 = 0x0800, + RTASE_ISR1 = 0x0802, +#define Q_TOK BIT(4) +#define Q_RDU BIT(1) +#define Q_ROK BIT(0) + + RTASE_EPHY_ISR = 0x6014, + RTASE_EPHY_IMR = 0x6016, + + RTASE_TX_CONFIG_0 = 0x0040, +#define TX_INTER_FRAME_GAP_MASK GENMASK(25, 24) + /* DMA burst value (0-7) is shift this many bits */ +#define TX_DMA_MASK GENMASK(10, 8) + + RTASE_RX_CONFIG_0 = 0x0044, +#define RX_SINGLE_FETCH BIT(14) +#define RX_SINGLE_TAG BIT(13) +#define RX_MX_DMA_MASK GENMASK(10, 8) +#define ACPT_FLOW BIT(7) +#define ACCEPT_ERR BIT(5) +#define ACCEPT_RUNT BIT(4) +#define ACCEPT_BROADCAST BIT(3) +#define ACCEPT_MULTICAST BIT(2) +#define ACCEPT_MYPHYS BIT(1) +#define ACCEPT_ALLPHYS BIT(0) +#define ACCEPT_MASK (ACPT_FLOW | ACCEPT_ERR | ACCEPT_RUNT | \ + ACCEPT_BROADCAST | ACCEPT_MULTICAST | \ + ACCEPT_MYPHYS | ACCEPT_ALLPHYS) + + RTASE_RX_CONFIG_1 = 0x0046, +#define RX_MAX_FETCH_DESC_MASK GENMASK(15, 11) +#define RX_NEW_DESC_FORMAT_EN BIT(8) +#define OUTER_VLAN_DETAG_EN BIT(7) +#define INNER_VLAN_DETAG_EN BIT(6) +#define PCIE_NEW_FLOW BIT(2) +#define PCIE_RELOAD_En BIT(0) + + RTASE_EEM = 0x0050, +#define EEM_UNLOCK 0xC0 + + RTASE_TDFNR = 0x0057, + RTASE_TPPOLL = 0x0090, + RTASE_PDR = 0x00B0, + RTASE_FIFOR = 0x00D3, +#define TX_FIFO_EMPTY BIT(5) +#define RX_FIFO_EMPTY BIT(4) + + RTASE_PCPR = 0x00D8, +#define PCPR_VLAN_FTR_EN BIT(6) + + RTASE_RMS = 0x00DA, + RTASE_CPLUS_CMD = 0x00E0, +#define FORCE_RXFLOW_EN BIT(11) +#define FORCE_TXFLOW_EN BIT(10) +#define RX_CHKSUM BIT(5) + + RTASE_Q0_RX_DESC_ADDR0 = 0x00E4, + RTASE_Q0_RX_DESC_ADDR4 = 0x00E8, + RTASE_Q1_RX_DESC_ADDR0 = 0x4000, + RTASE_Q1_RX_DESC_ADDR4 = 0x4004, + RTASE_MTPS = 0x00EC, +#define TAG_NUM_SEL_MASK GENMASK(10, 8) + + RTASE_MISC = 0x00F2, +#define RX_DV_GATE_EN BIT(3) + + RTASE_TFUN_CTRL = 0x0400, +#define TX_NEW_DESC_FORMAT_EN BIT(0) + + RTASE_TX_CONFIG_1 = 0x203E, +#define TC_MODE_MASK GENMASK(11, 10) + + RTASE_TOKSEL = 0x2046, + RTASE_RFIFONFULL = 0x4406, + RTASE_INT_MITI_TX = 0x0A00, + RTASE_INT_MITI_RX = 0x0A80, + + RTASE_VLAN_ENTRY_MEM_0 = 0x7234, + RTASE_VLAN_ENTRY_0 = 0xAC80, +}; + +enum desc_status_bit { + DESC_OWN = BIT(31), /* Descriptor is owned by NIC */ + RING_END = BIT(30), /* End of descriptor ring */ +}; + +enum sw_flag_content { + SWF_MSI_ENABLED = BIT(1), + SWF_MSIX_ENABLED = BIT(2), +}; + +#define RSVD_MASK 0x3FFFC000 + +struct tx_desc { + __le32 opts1; + __le32 opts2; + __le64 addr; + __le32 opts3; + __le32 reserved1; + __le32 reserved2; + __le32 reserved3; +} __packed; + +/*------ offset 0 of tx descriptor ------*/ +#define TX_FIRST_FRAG BIT(29) /* Tx First segment of a packet */ +#define TX_LAST_FRAG BIT(28) /* Tx Final segment of a packet */ +#define GIANT_SEND_V4 BIT(26) /* TCP Giant Send Offload V4 (GSOv4) */ +#define GIANT_SEND_V6 BIT(25) /* TCP Giant Send Offload V6 (GSOv6) */ +#define TX_VLAN_TAG BIT(17) /* Add VLAN tag */ + +/*------ offset 4 of tx descriptor ------*/ +#define TX_UDPCS_C BIT(31) /* Calculate UDP/IP checksum */ +#define TX_TCPCS_C BIT(30) /* Calculate TCP/IP checksum */ +#define TX_IPCS_C BIT(29) /* Calculate IP checksum */ +#define TX_IPV6F_C BIT(28) /* Indicate it is an IPv6 packet */ + +union rx_desc { + struct { + __le64 header_buf_addr; + __le32 reserved1; + __le32 opts_header_len; + __le64 addr; + __le32 reserved2; + __le32 opts1; + } __packed desc_cmd; + + struct { + __le32 reserved1; + __le32 reserved2; + __le32 rss; + __le32 opts4; + __le32 reserved3; + __le32 opts3; + __le32 opts2; + __le32 opts1; + } __packed desc_status; +} __packed; + +/*------ offset 28 of rx descriptor ------*/ +#define RX_FIRST_FRAG BIT(25) /* Rx First segment of a packet */ +#define RX_LAST_FRAG BIT(24) /* Rx Final segment of a packet */ +#define RX_RES BIT(20) +#define RX_RUNT BIT(19) +#define RX_RWT BIT(18) +#define RX_CRC BIT(16) +#define RX_V6F BIT(31) +#define RX_V4F BIT(30) +#define RX_UDPT BIT(29) +#define RX_TCPT BIT(28) +#define RX_IPF BIT(26) /* IP checksum failed */ +#define RX_UDPF BIT(25) /* UDP/IP checksum failed */ +#define RX_TCPF BIT(24) /* TCP/IP checksum failed */ +#define RX_LBK_FIFO_FULL BIT(17) /* Loopback FIFO Full */ +#define RX_VLAN_TAG BIT(16) /* VLAN tag available */ + +#define NUM_DESC 1024 +#define RTASE_TX_BUDGET_DEFAULT 256 +#define RTASE_TX_RING_DESC_SIZE (NUM_DESC * sizeof(struct tx_desc)) +#define RTASE_RX_RING_DESC_SIZE (NUM_DESC * sizeof(union rx_desc)) +#define RTASE_TX_STOP_THRS (MAX_SKB_FRAGS + 1) +#define RTASE_TX_START_THRS (2 * RTASE_TX_STOP_THRS) +#define VLAN_ENTRY_CAREBIT 0xF0000000 +#define VLAN_TAG_MASK GENMASK(15, 0) +#define RX_PKT_SIZE_MASK GENMASK(13, 0) + +#define IVEC_NAME_SIZE (IFNAMSIZ + 10) + +struct rtase_int_vector { + struct rtase_private *tp; + unsigned int irq; + char name[IVEC_NAME_SIZE]; + u16 index; + u16 imr_addr; + u16 isr_addr; + u32 imr; + struct list_head ring_list; + struct napi_struct napi; + int (*poll)(struct napi_struct *napi, int budget); +}; + +struct rtase_ring { + struct rtase_int_vector *ivec; + void *desc; + dma_addr_t phy_addr; + u32 cur_idx; + u32 dirty_idx; + u16 index; + + struct sk_buff *skbuff[NUM_DESC]; + union { + u32 len[NUM_DESC]; + dma_addr_t data_phy_addr[NUM_DESC]; + } mis; + + struct list_head ring_entry; + int (*ring_handler)(struct rtase_ring *ring, int budget); +}; + +struct rtase_private { + void __iomem *mmio_addr; + u32 sw_flag; + + struct pci_dev *pdev; + struct net_device *dev; + u32 rx_buf_sz; + + struct page_pool *page_pool; + struct rtase_ring tx_ring[RTASE_NUM_TX_QUEUE]; + struct rtase_ring rx_ring[RTASE_NUM_RX_QUEUE]; + struct rtase_counters *tally_vaddr; + dma_addr_t tally_paddr; + + u32 vlan_filter_ctrl; + u16 vlan_filter_vid[RTASE_VLAN_FILTER_ENTRY_NUM]; + + struct msix_entry msix_entry[RTASE_NUM_MSIX]; + struct rtase_int_vector int_vector[RTASE_NUM_MSIX]; + + u16 tx_queue_ctrl; + u16 func_tx_queue_num; + u16 func_rx_queue_num; + u16 int_nums; + u16 tx_int_mit; + u16 rx_int_mit; +}; + +#define LSO_64K 64000 + +#define NIC_MAX_PHYS_BUF_COUNT_LSO2 (16 * 4) + +#define TCPHO_MASK GENMASK(24, 18) + +#define MSS_MASK GENMASK(28, 18) + +#endif /* _RTASE_H_ */ diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c new file mode 100644 index 000000000000..f6a817828d2e --- /dev/null +++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c @@ -0,0 +1,617 @@ +// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause +/* + * rtase is the Linux device driver released for Realtek Automotive Switch + * controllers with PCI-Express interface. + * + * Copyright(c) 2023 Realtek Semiconductor Corp. + * + * Below is a simplified block diagram of the chip and its relevant interfaces. + * + * ************************* + * * * + * * CPU network device * + * * * + * * +-------------+ * + * * | PCIE Host | * + * ***********++************ + * || + * PCIE + * || + * ********************++********************** + * * | PCIE Endpoint | * + * * +---------------+ * + * * | GMAC | * + * * +--++--+ Realtek * + * * || RTL90xx Series * + * * || * + * * +-------------++----------------+ * + * * | | MAC | | * + * * | +-----+ | * + * * | | * + * * | Ethernet Switch Core | * + * * | | * + * * | +-----+ +-----+ | * + * * | | MAC |...........| MAC | | * + * * +---+-----+-----------+-----+---+ * + * * | PHY |...........| PHY | * + * * +--++-+ +--++-+ * + * *************||****************||*********** + * + * The block of the Realtek RTL90xx series is our entire chip architecture, + * the GMAC is connected to the switch core, and there is no PHY in between. + * In addition, this driver is mainly used to control GMAC, but does not + * control the switch core, so it is not the same as DSA. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "rtase.h" + +#define RTK_OPTS1_DEBUG_VALUE 0x0BADBEEF +#define RTK_MAGIC_NUMBER 0x0BADBADBADBADBAD + +static const struct pci_device_id rtase_pci_tbl[] = { + {PCI_VDEVICE(REALTEK, 0x906A)}, + {} +}; + +MODULE_DEVICE_TABLE(pci, rtase_pci_tbl); + +MODULE_AUTHOR("Realtek ARD Software Team"); +MODULE_DESCRIPTION("Network Driver for the PCIe interface of Realtek Automotive Ethernet Switch"); +MODULE_LICENSE("Dual BSD/GPL"); + +struct rtase_counters { + __le64 tx_packets; + __le64 rx_packets; + __le64 tx_errors; + __le32 rx_errors; + __le16 rx_missed; + __le16 align_errors; + __le32 tx_one_collision; + __le32 tx_multi_collision; + __le64 rx_unicast; + __le64 rx_broadcast; + __le32 rx_multicast; + __le16 tx_aborted; + __le16 tx_underun; +} __packed; + +static void rtase_w8(const struct rtase_private *tp, u16 reg, u8 val8) +{ + writeb(val8, tp->mmio_addr + reg); +} + +static void rtase_w16(const struct rtase_private *tp, u16 reg, u16 val16) +{ + writew(val16, tp->mmio_addr + reg); +} + +static void rtase_w32(const struct rtase_private *tp, u16 reg, u32 val32) +{ + writel(val32, tp->mmio_addr + reg); +} + +static u8 rtase_r8(const struct rtase_private *tp, u16 reg) +{ + return readb(tp->mmio_addr + reg); +} + +static u16 rtase_r16(const struct rtase_private *tp, u16 reg) +{ + return readw(tp->mmio_addr + reg); +} + +static u32 rtase_r32(const struct rtase_private *tp, u16 reg) +{ + return readl(tp->mmio_addr + reg); +} + +static void rtase_tally_counter_clear(const struct rtase_private *tp) +{ + u32 cmd = lower_32_bits(tp->tally_paddr); + + rtase_w32(tp, RTASE_DTCCR4, upper_32_bits(tp->tally_paddr)); + rtase_w32(tp, RTASE_DTCCR0, cmd | COUNTER_RESET); +} + +static void rtase_enable_eem_write(const struct rtase_private *tp) +{ + u8 val; + + val = rtase_r8(tp, RTASE_EEM); + rtase_w8(tp, RTASE_EEM, val | EEM_UNLOCK); +} + +static void rtase_disable_eem_write(const struct rtase_private *tp) +{ + u8 val; + + val = rtase_r8(tp, RTASE_EEM); + rtase_w8(tp, RTASE_EEM, val & ~EEM_UNLOCK); +} + +static void rtase_rar_set(const struct rtase_private *tp, const u8 *addr) +{ + u32 rar_low, rar_high; + + rar_low = (u32)addr[0] | ((u32)addr[1] << 8) | + ((u32)addr[2] << 16) | ((u32)addr[3] << 24); + + rar_high = (u32)addr[4] | ((u32)addr[5] << 8); + + rtase_enable_eem_write(tp); + rtase_w32(tp, RTASE_MAC0, rar_low); + rtase_w32(tp, RTASE_MAC4, rar_high); + rtase_disable_eem_write(tp); + rtase_w16(tp, RTASE_LBK_CTRL, LBK_ATLD | LBK_CLR); +} + +static void rtase_get_mac_address(struct net_device *dev) +{ + struct rtase_private *tp = netdev_priv(dev); + u8 mac_addr[ETH_ALEN] __aligned(2) = {}; + u32 i; + + for (i = 0; i < ETH_ALEN; i++) + mac_addr[i] = rtase_r8(tp, RTASE_MAC0 + i); + + if (!is_valid_ether_addr(mac_addr)) { + eth_hw_addr_random(dev); + netdev_warn(dev, "Random ether addr %pM\n", dev->dev_addr); + } else { + eth_hw_addr_set(dev, mac_addr); + ether_addr_copy(dev->perm_addr, dev->dev_addr); + } + + rtase_rar_set(tp, dev->dev_addr); +} + +static void rtase_reset_interrupt(struct pci_dev *pdev, + const struct rtase_private *tp) +{ + if (tp->sw_flag & SWF_MSIX_ENABLED) + pci_disable_msix(pdev); + else + pci_disable_msi(pdev); +} + +static int rtase_alloc_msix(struct pci_dev *pdev, struct rtase_private *tp) +{ + int ret; + u16 i; + + memset(tp->msix_entry, 0x0, RTASE_NUM_MSIX * sizeof(struct msix_entry)); + + for (i = 0; i < RTASE_NUM_MSIX; i++) + tp->msix_entry[i].entry = i; + + ret = pci_enable_msix_exact(pdev, tp->msix_entry, tp->int_nums); + + if (!ret) { + for (i = 0; i < tp->int_nums; i++) + tp->int_vector[i].irq = pci_irq_vector(pdev, i); + } + + return ret; +} + +static int rtase_alloc_interrupt(struct pci_dev *pdev, + struct rtase_private *tp) +{ + int ret; + + ret = rtase_alloc_msix(pdev, tp); + if (ret) { + ret = pci_enable_msi(pdev); + if (ret) + dev_err(&pdev->dev, + "unable to alloc interrupt.(MSI)\n"); + else + tp->sw_flag |= SWF_MSI_ENABLED; + } else { + tp->sw_flag |= SWF_MSIX_ENABLED; + } + + return ret; +} + +static void rtase_init_hardware(const struct rtase_private *tp) +{ + u16 i; + + for (i = 0; i < RTASE_VLAN_FILTER_ENTRY_NUM; i++) + rtase_w32(tp, RTASE_VLAN_ENTRY_0 + i * 4, 0); +} + +static void rtase_init_int_vector(struct rtase_private *tp) +{ + u16 i; + + /* interrupt vector 0 */ + tp->int_vector[0].tp = tp; + tp->int_vector[0].index = 0; + tp->int_vector[0].imr_addr = RTASE_IMR0; + tp->int_vector[0].isr_addr = RTASE_ISR0; + tp->int_vector[0].imr = ROK | RDU | TOK | TOK4 | TOK5 | TOK6 | TOK7; + tp->int_vector[0].poll = rtase_poll; + + memset(tp->int_vector[0].name, 0x0, sizeof(tp->int_vector[0].name)); + INIT_LIST_HEAD(&tp->int_vector[0].ring_list); + + netif_napi_add(tp->dev, &tp->int_vector[0].napi, + tp->int_vector[0].poll); + + /* interrupt vector 1 ~ 3 */ + for (i = 1; i < tp->int_nums; i++) { + tp->int_vector[i].tp = tp; + tp->int_vector[i].index = i; + tp->int_vector[i].imr_addr = RTASE_IMR1 + (i - 1) * 4; + tp->int_vector[i].isr_addr = RTASE_ISR1 + (i - 1) * 4; + tp->int_vector[i].imr = Q_ROK | Q_RDU | Q_TOK; + tp->int_vector[i].poll = rtase_poll; + + memset(tp->int_vector[i].name, 0x0, sizeof(tp->int_vector[0].name)); + INIT_LIST_HEAD(&tp->int_vector[i].ring_list); + + netif_napi_add(tp->dev, &tp->int_vector[i].napi, + tp->int_vector[i].poll); + } +} + +static u16 rtase_calc_time_mitigation(u32 time_us) +{ + u8 msb, time_count, time_unit; + u16 int_miti; + + time_us = min_t(int, time_us, MITI_MAX_TIME); + + msb = fls(time_us); + if (msb >= MITI_COUNT_BIT_NUM) { + time_unit = msb - MITI_COUNT_BIT_NUM; + time_count = time_us >> (msb - MITI_COUNT_BIT_NUM); + } else { + time_unit = 0; + time_count = time_us; + } + + int_miti = u16_encode_bits(time_count, MITI_TIME_COUNT_MASK) | + u16_encode_bits(time_unit, MITI_TIME_UNIT_MASK); + + return int_miti; +} + +static u16 rtase_calc_packet_num_mitigation(u16 pkt_num) +{ + u8 msb, pkt_num_count, pkt_num_unit; + u16 int_miti; + + pkt_num = min_t(int, pkt_num, MITI_MAX_PKT_NUM); + + if (pkt_num > 60) { + pkt_num_unit = MITI_MAX_PKT_NUM_IDX; + pkt_num_count = pkt_num / MITI_MAX_PKT_NUM_UNIT; + } else { + msb = fls(pkt_num); + if (msb >= MITI_COUNT_BIT_NUM) { + pkt_num_unit = msb - MITI_COUNT_BIT_NUM; + pkt_num_count = pkt_num >> (msb - MITI_COUNT_BIT_NUM); + } else { + pkt_num_unit = 0; + pkt_num_count = pkt_num; + } + } + + int_miti = u16_encode_bits(pkt_num_count, MITI_PKT_NUM_COUNT_MASK) | + u16_encode_bits(pkt_num_unit, MITI_PKT_NUM_UNIT_MASK); + + return int_miti; +} + +static void rtase_init_software_variable(struct pci_dev *pdev, + struct rtase_private *tp) +{ + u16 int_miti; + + tp->tx_queue_ctrl = RTASE_TXQ_CTRL; + tp->func_tx_queue_num = RTASE_FUNC_TXQ_NUM; + tp->func_rx_queue_num = RTASE_FUNC_RXQ_NUM; + tp->int_nums = RTASE_INTERRUPT_NUM; + + int_miti = rtase_calc_time_mitigation(MITI_DEFAULT_TIME) | + rtase_calc_packet_num_mitigation(MITI_DEFAULT_PKT_NUM); + tp->tx_int_mit = int_miti; + tp->rx_int_mit = int_miti; + + tp->sw_flag = 0; + + rtase_init_int_vector(tp); + + /* MTU range: 60 - hw-specific max */ + tp->dev->min_mtu = ETH_ZLEN; + tp->dev->max_mtu = MAX_JUMBO_SIZE; +} + +static bool rtase_check_mac_version_valid(struct rtase_private *tp) +{ + u32 hw_ver = rtase_r32(tp, RTASE_TX_CONFIG_0) & HW_VER_MASK; + bool known_ver = false; + + switch (hw_ver) { + case 0x00800000: + case 0x04000000: + case 0x04800000: + known_ver = true; + break; + } + + return known_ver; +} + +static int rtase_init_board(struct pci_dev *pdev, struct net_device **dev_out, + void __iomem **ioaddr_out) +{ + struct net_device *dev; + void __iomem *ioaddr; + int ret = -ENOMEM; + + /* dev zeroed in alloc_etherdev */ + dev = alloc_etherdev_mq(sizeof(struct rtase_private), + RTASE_FUNC_TXQ_NUM); + if (!dev) + goto err_out; + + SET_NETDEV_DEV(dev, &pdev->dev); + + ret = pci_enable_device(pdev); + if (ret < 0) + goto err_out_free_dev; + + /* make sure PCI base addr 1 is MMIO */ + if (!(pci_resource_flags(pdev, 2) & IORESOURCE_MEM)) { + ret = -ENODEV; + goto err_out_disable; + } + + /* check for weird/broken PCI region reporting */ + if (pci_resource_len(pdev, 2) < RTASE_REGS_SIZE) { + ret = -ENODEV; + goto err_out_disable; + } + + ret = pci_request_regions(pdev, KBUILD_MODNAME); + if (ret < 0) + goto err_out_disable; + + if (dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64))) { + dev_err(&pdev->dev, "no usable dma addressing method\n"); + goto err_out_free_res; + } + + pci_set_master(pdev); + + /* ioremap MMIO region */ + ioaddr = ioremap(pci_resource_start(pdev, 2), + pci_resource_len(pdev, 2)); + if (!ioaddr) { + ret = -EIO; + goto err_out_free_res; + } + + *ioaddr_out = ioaddr; + *dev_out = dev; + + return ret; + +err_out_free_res: + pci_release_regions(pdev); + +err_out_disable: + pci_disable_device(pdev); + +err_out_free_dev: + free_netdev(dev); + +err_out: + *ioaddr_out = NULL; + *dev_out = NULL; + + return ret; +} + +static void rtase_release_board(struct pci_dev *pdev, struct net_device *dev, + void __iomem *ioaddr) +{ + const struct rtase_private *tp = netdev_priv(dev); + + rtase_rar_set(tp, tp->dev->perm_addr); + iounmap(ioaddr); + + if ((tp->sw_flag & SWF_MSIX_ENABLED)) + pci_disable_msix(pdev); + else + pci_disable_msi(pdev); + + pci_release_regions(pdev); + pci_disable_device(pdev); + free_netdev(dev); +} + +static int rtase_init_one(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + struct net_device *dev = NULL; + struct rtase_int_vector *ivec; + void __iomem *ioaddr = NULL; + struct rtase_private *tp; + int ret, i; + + if (!pdev->is_physfn && pdev->is_virtfn) { + dev_err(&pdev->dev, "This module does not support a virtual function."); + return -EINVAL; + } + + dev_dbg(&pdev->dev, "Automotive Switch Ethernet driver loaded\n"); + + ret = rtase_init_board(pdev, &dev, &ioaddr); + if (ret != 0) + return ret; + + tp = netdev_priv(dev); + tp->mmio_addr = ioaddr; + tp->dev = dev; + tp->pdev = pdev; + + /* identify chip attached to board */ + if (!rtase_check_mac_version_valid(tp)) { + return dev_err_probe(&pdev->dev, -ENODEV, + "unknown chip version, contact rtase maintainers (see MAINTAINERS file)\n"); + } + + rtase_init_software_variable(pdev, tp); + rtase_init_hardware(tp); + + ret = rtase_alloc_interrupt(pdev, tp); + if (ret < 0) { + dev_err(&pdev->dev, "unable to alloc MSIX/MSI\n"); + goto err_out_1; + } + + rtase_init_netdev_ops(dev); + + dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; + + dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; + + dev->features |= NETIF_F_IP_CSUM; + dev->features |= NETIF_F_HIGHDMA; + dev->features |= NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_TSO; + dev->features |= NETIF_F_IPV6_CSUM | NETIF_F_TSO6; + dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO | + NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX; + dev->hw_features |= NETIF_F_RXALL; + dev->hw_features |= NETIF_F_RXFCS; + dev->hw_features |= NETIF_F_IPV6_CSUM | NETIF_F_TSO6; + dev->vlan_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO | + NETIF_F_HIGHDMA; + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + netif_set_tso_max_size(dev, LSO_64K); + netif_set_tso_max_segs(dev, NIC_MAX_PHYS_BUF_COUNT_LSO2); + + rtase_get_mac_address(dev); + + tp->tally_vaddr = dma_alloc_coherent(&pdev->dev, + sizeof(*tp->tally_vaddr), + &tp->tally_paddr, + GFP_KERNEL); + if (!tp->tally_vaddr) { + ret = -ENOMEM; + goto err_out; + } + + rtase_tally_counter_clear(tp); + + pci_set_drvdata(pdev, dev); + + netif_carrier_off(dev); + + ret = register_netdev(dev); + if (ret != 0) + goto err_out; + + netdev_dbg(dev, "%pM, IRQ %d\n", dev->dev_addr, dev->irq); + + return 0; + +err_out: + if (tp->tally_vaddr) { + dma_free_coherent(&pdev->dev, + sizeof(*tp->tally_vaddr), + tp->tally_vaddr, + tp->tally_paddr); + + tp->tally_vaddr = NULL; + } + +err_out_1: + for (i = 0; i < tp->int_nums; i++) { + ivec = &tp->int_vector[i]; + netif_napi_del(&ivec->napi); + } + + rtase_release_board(pdev, dev, ioaddr); + + return ret; +} + +static void rtase_remove_one(struct pci_dev *pdev) +{ + struct net_device *dev = pci_get_drvdata(pdev); + struct rtase_private *tp = netdev_priv(dev); + struct rtase_int_vector *ivec; + u32 i; + + unregister_netdev(dev); + + for (i = 0; i < tp->int_nums; i++) { + ivec = &tp->int_vector[i]; + netif_napi_del(&ivec->napi); + } + + rtase_reset_interrupt(pdev, tp); + if (tp->tally_vaddr) { + dma_free_coherent(&pdev->dev, + sizeof(*tp->tally_vaddr), + tp->tally_vaddr, + tp->tally_paddr); + tp->tally_vaddr = NULL; + } + + rtase_release_board(pdev, dev, tp->mmio_addr); + pci_set_drvdata(pdev, NULL); +} + +static void rtase_shutdown(struct pci_dev *pdev) +{ + struct net_device *dev = pci_get_drvdata(pdev); + const struct rtase_private *tp = netdev_priv(dev); + + if (netif_running(dev)) + rtase_close(dev); + + rtase_reset_interrupt(pdev, tp); +} + +static struct pci_driver rtase_pci_driver = { + .name = KBUILD_MODNAME, + .id_table = rtase_pci_tbl, + .probe = rtase_init_one, + .remove = rtase_remove_one, + .shutdown = rtase_shutdown, +}; + +module_pci_driver(rtase_pci_driver); From patchwork Fri Jan 5 09:00:28 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Justin Lai X-Patchwork-Id: 13511859 X-Patchwork-Delegate: kuba@kernel.org Received: from rtits2.realtek.com.tw (rtits2.realtek.com [211.75.126.72]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id D6CDB22F03; Fri, 5 Jan 2024 09:01:13 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=realtek.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=realtek.com X-SpamFilter-By: ArmorX SpamTrap 5.78 with qID 40590vcH62289443, This message is accepted by code: ctloc85258 Received: from mail.realtek.com (rtexh36505.realtek.com.tw[172.21.6.25]) by rtits2.realtek.com.tw (8.15.2/2.95/5.92) with ESMTPS id 40590vcH62289443 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Fri, 5 Jan 2024 17:00:57 +0800 Received: from RTEXDAG02.realtek.com.tw (172.21.6.101) by RTEXH36505.realtek.com.tw (172.21.6.25) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2375.32; Fri, 5 Jan 2024 17:00:57 +0800 Received: from RTDOMAIN (172.21.210.160) by RTEXDAG02.realtek.com.tw (172.21.6.101) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2375.7; Fri, 5 Jan 2024 17:00:56 +0800 From: Justin Lai To: CC: , , , , , , , , Justin Lai Subject: [PATCH net-next v15 02/13] rtase: Implement the .ndo_open function Date: Fri, 5 Jan 2024 17:00:28 +0800 Message-ID: <20240105090039.377561-3-justinlai0215@realtek.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240105090039.377561-1-justinlai0215@realtek.com> References: <20240105090039.377561-1-justinlai0215@realtek.com> Precedence: bulk X-Mailing-List: netdev@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-ClientProxiedBy: RTEXH36505.realtek.com.tw (172.21.6.25) To RTEXDAG02.realtek.com.tw (172.21.6.101) X-KSE-ServerInfo: RTEXDAG02.realtek.com.tw, 9 X-KSE-AntiSpam-Interceptor-Info: fallback X-KSE-Antivirus-Interceptor-Info: fallback X-KSE-AntiSpam-Interceptor-Info: fallback X-KSE-ServerInfo: RTEXH36505.realtek.com.tw, 9 X-KSE-AntiSpam-Interceptor-Info: fallback X-KSE-Antivirus-Interceptor-Info: fallback X-KSE-AntiSpam-Interceptor-Info: fallback X-Patchwork-Delegate: kuba@kernel.org Implement the .ndo_open function to set default hardware settings and initialize the descriptor ring and interrupts. Among them, when requesting irq, because the first group of interrupts needs to process more events, the overall structure will be different from other groups of interrupts, so it needs to be processed separately. Signed-off-by: Justin Lai --- .../net/ethernet/realtek/rtase/rtase_main.c | 417 ++++++++++++++++++ 1 file changed, 417 insertions(+) diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c index f6a817828d2e..3c9905f81f6e 100644 --- a/drivers/net/ethernet/realtek/rtase/rtase_main.c +++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c @@ -130,6 +130,291 @@ static u32 rtase_r32(const struct rtase_private *tp, u16 reg) return readl(tp->mmio_addr + reg); } +static void rtase_set_rxbufsize(struct rtase_private *tp) +{ + tp->rx_buf_sz = RX_BUF_SIZE; +} + +static int rtase_alloc_desc(struct rtase_private *tp) +{ + struct pci_dev *pdev = tp->pdev; + u32 i; + + /* rx and tx descriptors needs 256 bytes alignment. + * dma_alloc_coherent provides more. + */ + for (i = 0; i < tp->func_tx_queue_num; i++) { + tp->tx_ring[i].desc = dma_alloc_coherent(&pdev->dev, + RTASE_TX_RING_DESC_SIZE, + &tp->tx_ring[i].phy_addr, + GFP_KERNEL); + if (!tp->tx_ring[i].desc) + return -ENOMEM; + } + + for (i = 0; i < tp->func_rx_queue_num; i++) { + tp->rx_ring[i].desc = + dma_alloc_coherent(&pdev->dev, RTASE_RX_RING_DESC_SIZE, + &tp->rx_ring[i].phy_addr, + GFP_KERNEL); + if (!tp->rx_ring[i].desc) + return -ENOMEM; + } + + return 0; +} + +static void rtase_free_desc(struct rtase_private *tp) +{ + struct pci_dev *pdev = tp->pdev; + u32 i; + + for (i = 0; i < tp->func_tx_queue_num; i++) { + if (!tp->tx_ring[i].desc) + continue; + + dma_free_coherent(&pdev->dev, RTASE_TX_RING_DESC_SIZE, + tp->tx_ring[i].desc, + tp->tx_ring[i].phy_addr); + tp->tx_ring[i].desc = NULL; + } + + for (i = 0; i < tp->func_rx_queue_num; i++) { + if (!tp->rx_ring[i].desc) + continue; + + dma_free_coherent(&pdev->dev, RTASE_RX_RING_DESC_SIZE, + tp->rx_ring[i].desc, + tp->rx_ring[i].phy_addr); + tp->rx_ring[i].desc = NULL; + } +} + +static void rtase_mark_to_asic(union rx_desc *desc, u32 rx_buf_sz) +{ + u32 eor = le32_to_cpu(desc->desc_cmd.opts1) & RING_END; + + desc->desc_status.opts2 = 0; + /* force memory writes to complete before releasing descriptor */ + dma_wmb(); + WRITE_ONCE(desc->desc_cmd.opts1, + cpu_to_le32(DESC_OWN | eor | rx_buf_sz)); +} + +static void rtase_tx_desc_init(struct rtase_private *tp, u16 idx) +{ + struct rtase_ring *ring = &tp->tx_ring[idx]; + struct tx_desc *desc; + u32 i; + + memset(ring->desc, 0x0, RTASE_TX_RING_DESC_SIZE); + memset(ring->skbuff, 0x0, sizeof(ring->skbuff)); + ring->cur_idx = 0; + ring->dirty_idx = 0; + ring->index = idx; + + for (i = 0; i < NUM_DESC; i++) { + ring->mis.len[i] = 0; + if ((NUM_DESC - 1) == i) { + desc = ring->desc + sizeof(struct tx_desc) * i; + desc->opts1 = cpu_to_le32(RING_END); + } + } + + ring->ring_handler = tx_handler; + if (idx < 4) { + ring->ivec = &tp->int_vector[idx]; + list_add_tail(&ring->ring_entry, + &tp->int_vector[idx].ring_list); + } else { + ring->ivec = &tp->int_vector[0]; + list_add_tail(&ring->ring_entry, &tp->int_vector[0].ring_list); + } +} + +static void rtase_map_to_asic(union rx_desc *desc, dma_addr_t mapping, + u32 rx_buf_sz) +{ + desc->desc_cmd.addr = cpu_to_le64(mapping); + /* make sure the physical address has been updated */ + wmb(); + rtase_mark_to_asic(desc, rx_buf_sz); +} + +static void rtase_make_unusable_by_asic(union rx_desc *desc) +{ + desc->desc_cmd.addr = cpu_to_le64(RTK_MAGIC_NUMBER); + desc->desc_cmd.opts1 &= ~cpu_to_le32(DESC_OWN | RSVD_MASK); +} + +static int rtase_alloc_rx_skb(const struct rtase_ring *ring, + struct sk_buff **p_sk_buff, union rx_desc *desc, + dma_addr_t *rx_phy_addr, u8 in_intr) +{ + struct rtase_int_vector *ivec = ring->ivec; + const struct rtase_private *tp = ivec->tp; + struct sk_buff *skb = NULL; + dma_addr_t mapping; + struct page *page; + void *buf_addr; + int ret = 0; + + page = page_pool_dev_alloc_pages(tp->page_pool); + if (!page) { + netdev_err(tp->dev, "failed to alloc page\n"); + goto err_out; + } + + buf_addr = page_address(page); + mapping = page_pool_get_dma_addr(page); + + skb = build_skb(buf_addr, PAGE_SIZE); + if (!skb) { + page_pool_put_full_page(tp->page_pool, page, true); + netdev_err(tp->dev, "failed to build skb\n"); + goto err_out; + } + + *p_sk_buff = skb; + *rx_phy_addr = mapping; + rtase_map_to_asic(desc, mapping, tp->rx_buf_sz); + + return ret; + +err_out: + if (skb) + dev_kfree_skb(skb); + + ret = -ENOMEM; + rtase_make_unusable_by_asic(desc); + + return ret; +} + +static u32 rtase_rx_ring_fill(struct rtase_ring *ring, u32 ring_start, + u32 ring_end, u8 in_intr) +{ + union rx_desc *desc_base = ring->desc; + u32 cur; + + for (cur = ring_start; ring_end - cur > 0; cur++) { + u32 i = cur % NUM_DESC; + union rx_desc *desc = desc_base + i; + int ret; + + if (ring->skbuff[i]) + continue; + + ret = rtase_alloc_rx_skb(ring, &ring->skbuff[i], desc, + &ring->mis.data_phy_addr[i], + in_intr); + if (ret) + break; + } + + return cur - ring_start; +} + +static void rtase_mark_as_last_descriptor(union rx_desc *desc) +{ + desc->desc_cmd.opts1 |= cpu_to_le32(RING_END); +} + +static void rtase_rx_ring_clear(struct rtase_ring *ring) +{ + union rx_desc *desc; + u32 i; + + for (i = 0; i < NUM_DESC; i++) { + desc = ring->desc + sizeof(union rx_desc) * i; + + if (!ring->skbuff[i]) + continue; + + dev_kfree_skb(ring->skbuff[i]); + + ring->skbuff[i] = NULL; + + rtase_make_unusable_by_asic(desc); + } +} + +static void rtase_rx_desc_init(struct rtase_private *tp, u16 idx) +{ + struct rtase_ring *ring = &tp->rx_ring[idx]; + u16 i; + + memset(ring->desc, 0x0, RTASE_RX_RING_DESC_SIZE); + memset(ring->skbuff, 0x0, sizeof(ring->skbuff)); + ring->cur_idx = 0; + ring->dirty_idx = 0; + ring->index = idx; + + for (i = 0; i < NUM_DESC; i++) + ring->mis.data_phy_addr[i] = 0; + + ring->ring_handler = rx_handler; + ring->ivec = &tp->int_vector[idx]; + list_add_tail(&ring->ring_entry, &tp->int_vector[idx].ring_list); +} + +static void rtase_rx_clear(struct rtase_private *tp) +{ + u32 i; + + for (i = 0; i < tp->func_rx_queue_num; i++) + rtase_rx_ring_clear(&tp->rx_ring[i]); + + page_pool_destroy(tp->page_pool); + tp->page_pool = NULL; +} + +static int rtase_init_ring(const struct net_device *dev) +{ + struct rtase_private *tp = netdev_priv(dev); + struct page_pool_params pp_params = { + .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV, + .order = 0, + .pool_size = NUM_DESC * tp->func_rx_queue_num, + .nid = dev_to_node(&tp->pdev->dev), + .dev = &tp->pdev->dev, + .dma_dir = DMA_FROM_DEVICE, + .max_len = PAGE_SIZE, + .offset = 0, + }; + struct page_pool *page_pool; + u32 num; + u16 i; + + page_pool = page_pool_create(&pp_params); + if (IS_ERR(page_pool)) { + netdev_err(tp->dev, "failed to create page pool\n"); + return -ENOMEM; + } + + tp->page_pool = page_pool; + + for (i = 0; i < tp->func_tx_queue_num; i++) + rtase_tx_desc_init(tp, i); + + for (i = 0; i < tp->func_rx_queue_num; i++) { + rtase_rx_desc_init(tp, i); + num = rtase_rx_ring_fill(&tp->rx_ring[i], 0, NUM_DESC, 0); + if (num != NUM_DESC) + goto err_out; + + rtase_mark_as_last_descriptor(tp->rx_ring[i].desc + + sizeof(union rx_desc) * + (NUM_DESC - 1)); + } + + return 0; + +err_out: + rtase_rx_clear(tp); + return -ENOMEM; +} + static void rtase_tally_counter_clear(const struct rtase_private *tp) { u32 cmd = lower_32_bits(tp->tally_paddr); @@ -138,6 +423,128 @@ static void rtase_tally_counter_clear(const struct rtase_private *tp) rtase_w32(tp, RTASE_DTCCR0, cmd | COUNTER_RESET); } +static void rtase_nic_enable(const struct net_device *dev) +{ + const struct rtase_private *tp = netdev_priv(dev); + u16 rcr = rtase_r16(tp, RTASE_RX_CONFIG_1); + u8 val; + + rtase_w16(tp, RTASE_RX_CONFIG_1, rcr & ~PCIE_RELOAD_En); + rtase_w16(tp, RTASE_RX_CONFIG_1, rcr | PCIE_RELOAD_En); + + val = rtase_r8(tp, RTASE_CHIP_CMD); + rtase_w8(tp, RTASE_CHIP_CMD, val | TE | RE); + + val = rtase_r8(tp, RTASE_MISC); + rtase_w8(tp, RTASE_MISC, val & ~RX_DV_GATE_EN); +} + +static void rtase_enable_hw_interrupt(const struct rtase_private *tp) +{ + const struct rtase_int_vector *ivec = &tp->int_vector[0]; + u32 i; + + rtase_w32(tp, ivec->imr_addr, ivec->imr); + + for (i = 1; i < tp->int_nums; i++) { + ivec = &tp->int_vector[i]; + rtase_w16(tp, ivec->imr_addr, ivec->imr); + } +} + +static void rtase_hw_start(const struct net_device *dev) +{ + const struct rtase_private *tp = netdev_priv(dev); + + rtase_nic_enable(dev); + rtase_enable_hw_interrupt(tp); +} + +static int rtase_open(struct net_device *dev) +{ + struct rtase_private *tp = netdev_priv(dev); + struct rtase_int_vector *ivec = &tp->int_vector[0]; + const struct pci_dev *pdev = tp->pdev; + u16 i, j; + int ret; + + rtase_set_rxbufsize(tp); + + ret = rtase_alloc_desc(tp); + if (ret) + goto err_free_all_allocated_mem; + + ret = rtase_init_ring(dev); + if (ret) + goto err_free_all_allocated_mem; + + rtase_hw_config(dev); + + if (tp->sw_flag & SWF_MSIX_ENABLED) { + ret = request_irq(ivec->irq, rtase_interrupt, 0, + dev->name, ivec); + if (ret) + goto err_free_all_allocated_irq; + + /* request other interrupts to handle multiqueue */ + for (i = 1; i < tp->int_nums; i++) { + ivec = &tp->int_vector[i]; + snprintf(ivec->name, sizeof(ivec->name), "%s_int%i", tp->dev->name, i); + ret = request_irq(ivec->irq, rtase_q_interrupt, 0, + ivec->name, ivec); + if (ret) + goto err_free_all_allocated_irq; + } + } else { + ret = request_irq(pdev->irq, rtase_interrupt, 0, dev->name, + ivec); + if (ret) + goto err_free_all_allocated_mem; + } + + rtase_hw_start(dev); + + for (i = 0; i < tp->int_nums; i++) { + ivec = &tp->int_vector[i]; + napi_enable(&ivec->napi); + } + + netif_carrier_on(dev); + netif_wake_queue(dev); + + return 0; + +err_free_all_allocated_irq: + for (j = 0; j < i; j++) + free_irq(tp->int_vector[j].irq, &tp->int_vector[j]); + +err_free_all_allocated_mem: + rtase_free_desc(tp); + + return ret; +} + +static int rtase_close(struct net_device *dev) +{ + struct rtase_private *tp = netdev_priv(dev); + const struct pci_dev *pdev = tp->pdev; + u32 i; + + rtase_down(dev); + + if (tp->sw_flag & SWF_MSIX_ENABLED) { + for (i = 0; i < tp->int_nums; i++) + free_irq(tp->int_vector[i].irq, &tp->int_vector[i]); + + } else { + free_irq(pdev->irq, &tp->int_vector[0]); + } + + rtase_free_desc(tp); + + return 0; +} + static void rtase_enable_eem_write(const struct rtase_private *tp) { u8 val; @@ -170,6 +577,11 @@ static void rtase_rar_set(const struct rtase_private *tp, const u8 *addr) rtase_w16(tp, RTASE_LBK_CTRL, LBK_ATLD | LBK_CLR); } +static const struct net_device_ops rtase_netdev_ops = { + .ndo_open = rtase_open, + .ndo_stop = rtase_close, +}; + static void rtase_get_mac_address(struct net_device *dev) { struct rtase_private *tp = netdev_priv(dev); @@ -190,6 +602,11 @@ static void rtase_get_mac_address(struct net_device *dev) rtase_rar_set(tp, dev->dev_addr); } +static void rtase_init_netdev_ops(struct net_device *dev) +{ + dev->netdev_ops = &rtase_netdev_ops; +} + static void rtase_reset_interrupt(struct pci_dev *pdev, const struct rtase_private *tp) { From patchwork Fri Jan 5 09:00:29 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Justin Lai X-Patchwork-Id: 13511860 X-Patchwork-Delegate: kuba@kernel.org Received: from rtits2.realtek.com.tw (rtits2.realtek.com [211.75.126.72]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 34B79225A1; Fri, 5 Jan 2024 09:01:20 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=realtek.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=realtek.com X-SpamFilter-By: ArmorX SpamTrap 5.78 with qID 4059132302289455, This message is accepted by code: ctloc85258 Received: from mail.realtek.com (rtexh36506.realtek.com.tw[172.21.6.27]) by rtits2.realtek.com.tw (8.15.2/2.95/5.92) with ESMTPS id 4059132302289455 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Fri, 5 Jan 2024 17:01:03 +0800 Received: from RTEXDAG02.realtek.com.tw (172.21.6.101) by RTEXH36506.realtek.com.tw (172.21.6.27) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2507.17; Fri, 5 Jan 2024 17:01:04 +0800 Received: from RTDOMAIN (172.21.210.160) by RTEXDAG02.realtek.com.tw (172.21.6.101) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2375.7; Fri, 5 Jan 2024 17:01:03 +0800 From: Justin Lai To: CC: , , , , , , , , Justin Lai Subject: [PATCH net-next v15 03/13] rtase: Implement the rtase_down function Date: Fri, 5 Jan 2024 17:00:29 +0800 Message-ID: <20240105090039.377561-4-justinlai0215@realtek.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240105090039.377561-1-justinlai0215@realtek.com> References: <20240105090039.377561-1-justinlai0215@realtek.com> Precedence: bulk X-Mailing-List: netdev@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-ClientProxiedBy: RTEXH36505.realtek.com.tw (172.21.6.25) To RTEXDAG02.realtek.com.tw (172.21.6.101) X-KSE-ServerInfo: RTEXDAG02.realtek.com.tw, 9 X-KSE-AntiSpam-Interceptor-Info: fallback X-KSE-Antivirus-Interceptor-Info: fallback X-KSE-AntiSpam-Interceptor-Info: fallback X-Patchwork-Delegate: kuba@kernel.org Implement the rtase_down function to disable hardware setting and interrupt and clear descriptor ring. Signed-off-by: Justin Lai --- .../net/ethernet/realtek/rtase/rtase_main.c | 148 ++++++++++++++++++ 1 file changed, 148 insertions(+) diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c index 3c9905f81f6e..9c7b27744d37 100644 --- a/drivers/net/ethernet/realtek/rtase/rtase_main.c +++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c @@ -190,6 +190,57 @@ static void rtase_free_desc(struct rtase_private *tp) } } +static void rtase_unmap_tx_skb(struct pci_dev *pdev, u32 len, + struct tx_desc *desc) +{ + dma_unmap_single(&pdev->dev, le64_to_cpu(desc->addr), len, + DMA_TO_DEVICE); + desc->opts1 = cpu_to_le32(RTK_OPTS1_DEBUG_VALUE); + desc->opts2 = 0x00; + desc->addr = cpu_to_le64(RTK_MAGIC_NUMBER); +} + +static void rtase_tx_clear_range(struct rtase_ring *ring, u32 start, u32 n) +{ + const struct rtase_private *tp = ring->ivec->tp; + struct tx_desc *desc_base = ring->desc; + struct net_device *dev = tp->dev; + u32 i; + + for (i = 0; i < n; i++) { + u32 entry = (start + i) % NUM_DESC; + struct tx_desc *desc = desc_base + entry; + u32 len = ring->mis.len[entry]; + struct sk_buff *skb; + + if (len == 0) + continue; + + rtase_unmap_tx_skb(tp->pdev, len, desc); + ring->mis.len[entry] = 0; + skb = ring->skbuff[entry]; + if (!skb) + continue; + + dev->stats.tx_dropped++; + dev_kfree_skb_any(skb); + ring->skbuff[entry] = NULL; + } +} + +static void rtase_tx_clear(struct rtase_private *tp) +{ + struct rtase_ring *ring; + u16 i; + + for (i = 0; i < tp->func_tx_queue_num; i++) { + ring = &tp->tx_ring[i]; + rtase_tx_clear_range(ring, ring->dirty_idx, NUM_DESC); + ring->cur_idx = 0; + ring->dirty_idx = 0; + } +} + static void rtase_mark_to_asic(union rx_desc *desc, u32 rx_buf_sz) { u32 eor = le32_to_cpu(desc->desc_cmd.opts1) & RING_END; @@ -423,6 +474,77 @@ static void rtase_tally_counter_clear(const struct rtase_private *tp) rtase_w32(tp, RTASE_DTCCR0, cmd | COUNTER_RESET); } +static void rtase_irq_dis_and_clear(const struct rtase_private *tp) +{ + const struct rtase_int_vector *ivec = &tp->int_vector[0]; + u32 val1; + u16 val2; + u8 i; + + rtase_w32(tp, ivec->imr_addr, 0); + val1 = rtase_r32(tp, ivec->isr_addr); + rtase_w32(tp, ivec->isr_addr, val1); + + for (i = 1; i < tp->int_nums; i++) { + ivec = &tp->int_vector[i]; + rtase_w16(tp, ivec->imr_addr, 0); + val2 = rtase_r16(tp, ivec->isr_addr); + rtase_w16(tp, ivec->isr_addr, val2); + } +} + +static void rtase_poll_timeout(const struct rtase_private *tp, u32 cond, + u32 sleep_us, u64 timeout_us, u16 reg) +{ + int err; + u8 val; + + err = read_poll_timeout(rtase_r8, val, val & cond, sleep_us, timeout_us, + false, tp, reg); + + if (err == -ETIMEDOUT) + netdev_err(tp->dev, "poll reg 0x00%x timeout\n", reg); +} + +static void rtase_nic_reset(const struct net_device *dev) +{ + const struct rtase_private *tp = netdev_priv(dev); + u16 rx_config; + u8 val; + + rx_config = rtase_r16(tp, RTASE_RX_CONFIG_0); + rtase_w16(tp, RTASE_RX_CONFIG_0, rx_config & ~ACCEPT_MASK); + + val = rtase_r8(tp, RTASE_MISC); + rtase_w8(tp, RTASE_MISC, val | RX_DV_GATE_EN); + + val = rtase_r8(tp, RTASE_CHIP_CMD); + rtase_w8(tp, RTASE_CHIP_CMD, val | STOP_REQ); + mdelay(2); + + rtase_poll_timeout(tp, STOP_REQ_DONE, 100, 150000, RTASE_CHIP_CMD); + + rtase_poll_timeout(tp, TX_FIFO_EMPTY, 100, 100000, RTASE_FIFOR); + + rtase_poll_timeout(tp, RX_FIFO_EMPTY, 100, 100000, RTASE_FIFOR); + + val = rtase_r8(tp, RTASE_CHIP_CMD); + rtase_w8(tp, RTASE_CHIP_CMD, val & ~(TE | RE)); + val = rtase_r8(tp, RTASE_CHIP_CMD); + rtase_w8(tp, RTASE_CHIP_CMD, val & ~STOP_REQ); + + rtase_w16(tp, RTASE_RX_CONFIG_0, rx_config); +} + +static void rtase_hw_reset(const struct net_device *dev) +{ + const struct rtase_private *tp = netdev_priv(dev); + + rtase_irq_dis_and_clear(tp); + + rtase_nic_reset(dev); +} + static void rtase_nic_enable(const struct net_device *dev) { const struct rtase_private *tp = netdev_priv(dev); @@ -524,6 +646,32 @@ static int rtase_open(struct net_device *dev) return ret; } +static void rtase_down(struct net_device *dev) +{ + struct rtase_private *tp = netdev_priv(dev); + struct rtase_int_vector *ivec; + struct rtase_ring *ring, *tmp; + u32 i; + + for (i = 0; i < tp->int_nums; i++) { + ivec = &tp->int_vector[i]; + napi_disable(&ivec->napi); + list_for_each_entry_safe(ring, tmp, &ivec->ring_list, ring_entry) { + list_del(&ring->ring_entry); + } + } + + netif_tx_disable(dev); + + netif_carrier_off(dev); + + rtase_hw_reset(dev); + + rtase_tx_clear(tp); + + rtase_rx_clear(tp); +} + static int rtase_close(struct net_device *dev) { struct rtase_private *tp = netdev_priv(dev); From patchwork Fri Jan 5 09:00:30 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Justin Lai X-Patchwork-Id: 13511861 X-Patchwork-Delegate: kuba@kernel.org Received: from rtits2.realtek.com.tw (rtits2.realtek.com [211.75.126.72]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 5E173225A1; Fri, 5 Jan 2024 09:01:28 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=none (p=none dis=none) header.from=realtek.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=realtek.com X-SpamFilter-By: ArmorX SpamTrap 5.78 with qID 40591CsY42289474, This message is accepted by code: ctloc85258 Received: from mail.realtek.com (rtexh36506.realtek.com.tw[172.21.6.27]) by rtits2.realtek.com.tw (8.15.2/2.95/5.92) with ESMTPS id 40591CsY42289474 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Fri, 5 Jan 2024 17:01:12 +0800 Received: from RTEXDAG02.realtek.com.tw (172.21.6.101) by RTEXH36506.realtek.com.tw (172.21.6.27) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2507.17; Fri, 5 Jan 2024 17:01:12 +0800 Received: from RTDOMAIN (172.21.210.160) by RTEXDAG02.realtek.com.tw (172.21.6.101) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2375.7; Fri, 5 Jan 2024 17:01:09 +0800 From: Justin Lai To: CC: , , , , , , , , Justin Lai Subject: [PATCH net-next v15 04/13] rtase: Implement the interrupt routine and rtase_poll Date: Fri, 5 Jan 2024 17:00:30 +0800 Message-ID: <20240105090039.377561-5-justinlai0215@realtek.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20240105090039.377561-1-justinlai0215@realtek.com> References: <20240105090039.377561-1-justinlai0215@realtek.com> Precedence: bulk X-Mailing-List: netdev@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-ClientProxiedBy: RTEXH36505.realtek.com.tw (172.21.6.25) To RTEXDAG02.realtek.com.tw (172.21.6.101) X-KSE-ServerInfo: RTEXDAG02.realtek.com.tw, 9 X-KSE-AntiSpam-Interceptor-Info: fallback X-KSE-Antivirus-Interceptor-Info: fallback X-KSE-AntiSpam-Interceptor-Info: fallback X-Patchwork-Delegate: kuba@kernel.org 1. Implement rtase_interrupt to handle txQ0/rxQ0, txQ4~txQ7 interrupts, and implement rtase_q_interrupt to handle txQ1/rxQ1, txQ2/rxQ2 and txQ3/rxQ3 interrupts. 2. Implement rtase_poll to call ring_handler to process the tx or rx packet of each ring. If the returned value is budget,it means that there is still work of a certain ring that has not yet been completed. Signed-off-by: Justin Lai --- .../net/ethernet/realtek/rtase/rtase_main.c | 89 +++++++++++++++++++ 1 file changed, 89 insertions(+) diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c index 9c7b27744d37..1bd4634a8bdb 100644 --- a/drivers/net/ethernet/realtek/rtase/rtase_main.c +++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c @@ -582,6 +582,76 @@ static void rtase_hw_start(const struct net_device *dev) rtase_enable_hw_interrupt(tp); } +/* the interrupt handler does RXQ0 and TXQ0, TXQ4~7 interrutp status + */ +static irqreturn_t rtase_interrupt(int irq, void *dev_instance) +{ + const struct rtase_private *tp; + struct rtase_int_vector *ivec; + u32 status; + + ivec = dev_instance; + tp = ivec->tp; + status = rtase_r32(tp, ivec->isr_addr); + + rtase_w32(tp, ivec->imr_addr, 0x0); + rtase_w32(tp, ivec->isr_addr, status & ~FOVW); + + if (napi_schedule_prep(&ivec->napi)) + __napi_schedule(&ivec->napi); + + return IRQ_HANDLED; +} + +/* the interrupt handler does RXQ1&TXQ1 or RXQ2&TXQ2 or RXQ3&TXQ3 interrupt + * status according to interrupt vector + */ +static irqreturn_t rtase_q_interrupt(int irq, void *dev_instance) +{ + const struct rtase_private *tp; + struct rtase_int_vector *ivec; + u16 status; + + ivec = dev_instance; + tp = ivec->tp; + status = rtase_r16(tp, ivec->isr_addr); + + rtase_w16(tp, ivec->imr_addr, 0x0); + rtase_w16(tp, ivec->isr_addr, status); + + if (napi_schedule_prep(&ivec->napi)) + __napi_schedule(&ivec->napi); + + return IRQ_HANDLED; +} + +static int rtase_poll(struct napi_struct *napi, int budget) +{ + const struct rtase_int_vector *ivec; + const struct rtase_private *tp; + struct rtase_ring *ring; + int total_workdone = 0; + + ivec = container_of(napi, struct rtase_int_vector, napi); + tp = ivec->tp; + + list_for_each_entry(ring, &ivec->ring_list, ring_entry) { + total_workdone += ring->ring_handler(ring, budget); + } + + if (total_workdone >= budget) + return budget; + + if (napi_complete_done(napi, total_workdone)) { + if (!ivec->index) + rtase_w32(tp, ivec->imr_addr, ivec->imr); + else + rtase_w16(tp, ivec->imr_addr, ivec->imr); + } + + return total_workdone; +} + static int rtase_open(struct net_device *dev) { struct rtase_private *tp = netdev_priv(dev); @@ -725,9 +795,28 @@ static void rtase_rar_set(const struct rtase_private *tp, const u8 *addr) rtase_w16(tp, RTASE_LBK_CTRL, LBK_ATLD | LBK_CLR); } +#ifdef CONFIG_NET_POLL_CONTROLLER +/* Polling 'interrupt' - used by things like netconsole to send skbs + * without having to re-enable interrupts. It's not called while + * the interrupt routine is executing. + */ +static void rtase_netpoll(struct net_device *dev) +{ + const struct rtase_private *tp = netdev_priv(dev); + const struct pci_dev *pdev = tp->pdev; + + disable_irq(pdev->irq); + rtase_interrupt(pdev->irq, dev); + enable_irq(pdev->irq); +} +#endif + static const struct net_device_ops rtase_netdev_ops = { .ndo_open = rtase_open, .ndo_stop = rtase_close, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = rtase_netpoll, +#endif }; static void rtase_get_mac_address(struct net_device *dev)