From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ... --- .../net/ethernet/marvell/prestera/prestera_rxtx.c | 823 +++++++++++++++++++++ 1 file changed, 823 insertions(+) create mode 100644 drivers/net/ethernet/marvell/prestera/prestera_rxtx.c (limited to 'drivers/net/ethernet/marvell/prestera/prestera_rxtx.c') diff --git a/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c b/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c new file mode 100644 index 000000000..9277a8fd1 --- /dev/null +++ b/drivers/net/ethernet/marvell/prestera/prestera_rxtx.c @@ -0,0 +1,823 @@ +// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 +/* Copyright (c) 2019-2020 Marvell International Ltd. All rights reserved */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "prestera_dsa.h" +#include "prestera.h" +#include "prestera_hw.h" +#include "prestera_rxtx.h" +#include "prestera_devlink.h" + +#define PRESTERA_SDMA_WAIT_MUL 10 + +struct prestera_sdma_desc { + __le32 word1; + __le32 word2; + __le32 buff; + __le32 next; +} __packed __aligned(16); + +#define PRESTERA_SDMA_BUFF_SIZE_MAX 1544 + +#define PRESTERA_SDMA_RX_DESC_PKT_LEN(desc) \ + ((le32_to_cpu((desc)->word2) >> 16) & GENMASK(13, 0)) + +#define PRESTERA_SDMA_RX_DESC_OWNER(desc) \ + ((le32_to_cpu((desc)->word1) & BIT(31)) >> 31) + +#define PRESTERA_SDMA_RX_DESC_IS_RCVD(desc) \ + (PRESTERA_SDMA_RX_DESC_OWNER(desc) == PRESTERA_SDMA_RX_DESC_CPU_OWN) + +#define PRESTERA_SDMA_RX_DESC_CPU_OWN 0 +#define PRESTERA_SDMA_RX_DESC_DMA_OWN 1 + +#define PRESTERA_SDMA_RX_QUEUE_NUM 8 + +#define PRESTERA_SDMA_RX_DESC_PER_Q 1000 + +#define PRESTERA_SDMA_TX_DESC_PER_Q 1000 +#define PRESTERA_SDMA_TX_MAX_BURST 64 + +#define PRESTERA_SDMA_TX_DESC_OWNER(desc) \ + ((le32_to_cpu((desc)->word1) & BIT(31)) >> 31) + +#define PRESTERA_SDMA_TX_DESC_CPU_OWN 0 +#define PRESTERA_SDMA_TX_DESC_DMA_OWN 1U + +#define PRESTERA_SDMA_TX_DESC_IS_SENT(desc) \ + (PRESTERA_SDMA_TX_DESC_OWNER(desc) == PRESTERA_SDMA_TX_DESC_CPU_OWN) + +#define PRESTERA_SDMA_TX_DESC_LAST BIT(20) +#define PRESTERA_SDMA_TX_DESC_FIRST BIT(21) +#define PRESTERA_SDMA_TX_DESC_CALC_CRC BIT(12) + +#define PRESTERA_SDMA_TX_DESC_SINGLE \ + (PRESTERA_SDMA_TX_DESC_FIRST | PRESTERA_SDMA_TX_DESC_LAST) + +#define PRESTERA_SDMA_TX_DESC_INIT \ + (PRESTERA_SDMA_TX_DESC_SINGLE | PRESTERA_SDMA_TX_DESC_CALC_CRC) + +#define PRESTERA_SDMA_RX_INTR_MASK_REG 0x2814 +#define PRESTERA_SDMA_RX_QUEUE_STATUS_REG 0x2680 +#define PRESTERA_SDMA_RX_QUEUE_DESC_REG(n) (0x260C + (n) * 16) + +#define PRESTERA_SDMA_TX_QUEUE_DESC_REG 0x26C0 +#define PRESTERA_SDMA_TX_QUEUE_START_REG 0x2868 + +struct prestera_sdma_buf { + struct prestera_sdma_desc *desc; + dma_addr_t desc_dma; + struct sk_buff *skb; + dma_addr_t buf_dma; + bool is_used; +}; + +struct prestera_rx_ring { + struct prestera_sdma_buf *bufs; + int next_rx; +}; + +struct prestera_tx_ring { + struct prestera_sdma_buf *bufs; + int next_tx; + int max_burst; + int burst; +}; + +struct prestera_sdma { + struct prestera_rx_ring rx_ring[PRESTERA_SDMA_RX_QUEUE_NUM]; + struct prestera_tx_ring tx_ring; + struct prestera_switch *sw; + struct dma_pool *desc_pool; + struct work_struct tx_work; + struct napi_struct rx_napi; + struct net_device napi_dev; + u32 map_addr; + u64 dma_mask; + /* protect SDMA with concurrent access from multiple CPUs */ + spinlock_t tx_lock; +}; + +struct prestera_rxtx { + struct prestera_sdma sdma; +}; + +static int prestera_sdma_buf_init(struct prestera_sdma *sdma, + struct prestera_sdma_buf *buf) +{ + struct prestera_sdma_desc *desc; + dma_addr_t dma; + + desc = dma_pool_alloc(sdma->desc_pool, GFP_DMA | GFP_KERNEL, &dma); + if (!desc) + return -ENOMEM; + + buf->buf_dma = DMA_MAPPING_ERROR; + buf->desc_dma = dma; + buf->desc = desc; + buf->skb = NULL; + + return 0; +} + +static u32 prestera_sdma_map(struct prestera_sdma *sdma, dma_addr_t pa) +{ + return sdma->map_addr + pa; +} + +static void prestera_sdma_rx_desc_init(struct prestera_sdma *sdma, + struct prestera_sdma_desc *desc, + dma_addr_t buf) +{ + u32 word = le32_to_cpu(desc->word2); + + u32p_replace_bits(&word, PRESTERA_SDMA_BUFF_SIZE_MAX, GENMASK(15, 0)); + desc->word2 = cpu_to_le32(word); + + desc->buff = cpu_to_le32(prestera_sdma_map(sdma, buf)); + + /* make sure buffer is set before reset the descriptor */ + wmb(); + + desc->word1 = cpu_to_le32(0xA0000000); +} + +static void prestera_sdma_rx_desc_set_next(struct prestera_sdma *sdma, + struct prestera_sdma_desc *desc, + dma_addr_t next) +{ + desc->next = cpu_to_le32(prestera_sdma_map(sdma, next)); +} + +static int prestera_sdma_rx_skb_alloc(struct prestera_sdma *sdma, + struct prestera_sdma_buf *buf) +{ + struct device *dev = sdma->sw->dev->dev; + struct sk_buff *skb; + dma_addr_t dma; + + skb = alloc_skb(PRESTERA_SDMA_BUFF_SIZE_MAX, GFP_DMA | GFP_ATOMIC); + if (!skb) + return -ENOMEM; + + dma = dma_map_single(dev, skb->data, skb->len, DMA_FROM_DEVICE); + if (dma_mapping_error(dev, dma)) + goto err_dma_map; + + if (buf->skb) + dma_unmap_single(dev, buf->buf_dma, buf->skb->len, + DMA_FROM_DEVICE); + + buf->buf_dma = dma; + buf->skb = skb; + + return 0; + +err_dma_map: + kfree_skb(skb); + + return -ENOMEM; +} + +static struct sk_buff *prestera_sdma_rx_skb_get(struct prestera_sdma *sdma, + struct prestera_sdma_buf *buf) +{ + dma_addr_t buf_dma = buf->buf_dma; + struct sk_buff *skb = buf->skb; + u32 len = skb->len; + int err; + + err = prestera_sdma_rx_skb_alloc(sdma, buf); + if (err) { + buf->buf_dma = buf_dma; + buf->skb = skb; + + skb = alloc_skb(skb->len, GFP_ATOMIC); + if (skb) { + skb_put(skb, len); + skb_copy_from_linear_data(buf->skb, skb->data, len); + } + } + + prestera_sdma_rx_desc_init(sdma, buf->desc, buf->buf_dma); + + return skb; +} + +static int prestera_rxtx_process_skb(struct prestera_sdma *sdma, + struct sk_buff *skb) +{ + struct prestera_port *port; + struct prestera_dsa dsa; + u32 hw_port, dev_id; + u8 cpu_code; + int err; + + skb_pull(skb, ETH_HLEN); + + /* ethertype field is part of the dsa header */ + err = prestera_dsa_parse(&dsa, skb->data - ETH_TLEN); + if (err) + return err; + + dev_id = dsa.hw_dev_num; + hw_port = dsa.port_num; + + port = prestera_port_find_by_hwid(sdma->sw, dev_id, hw_port); + if (unlikely(!port)) { + dev_warn_ratelimited(prestera_dev(sdma->sw), "received pkt for non-existent port(%u, %u)\n", + dev_id, hw_port); + return -ENOENT; + } + + if (unlikely(!pskb_may_pull(skb, PRESTERA_DSA_HLEN))) + return -EINVAL; + + /* remove DSA tag and update checksum */ + skb_pull_rcsum(skb, PRESTERA_DSA_HLEN); + + memmove(skb->data - ETH_HLEN, skb->data - ETH_HLEN - PRESTERA_DSA_HLEN, + ETH_ALEN * 2); + + skb_push(skb, ETH_HLEN); + + skb->protocol = eth_type_trans(skb, port->dev); + + if (dsa.vlan.is_tagged) { + u16 tci = dsa.vlan.vid & VLAN_VID_MASK; + + tci |= dsa.vlan.vpt << VLAN_PRIO_SHIFT; + if (dsa.vlan.cfi_bit) + tci |= VLAN_CFI_MASK; + + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), tci); + } + + cpu_code = dsa.cpu_code; + prestera_devlink_trap_report(port, skb, cpu_code); + + return 0; +} + +static int prestera_sdma_next_rx_buf_idx(int buf_idx) +{ + return (buf_idx + 1) % PRESTERA_SDMA_RX_DESC_PER_Q; +} + +static int prestera_sdma_rx_poll(struct napi_struct *napi, int budget) +{ + int qnum = PRESTERA_SDMA_RX_QUEUE_NUM; + unsigned int rxq_done_map = 0; + struct prestera_sdma *sdma; + struct list_head rx_list; + unsigned int qmask; + int pkts_done = 0; + int q; + + qnum = PRESTERA_SDMA_RX_QUEUE_NUM; + qmask = GENMASK(qnum - 1, 0); + + INIT_LIST_HEAD(&rx_list); + + sdma = container_of(napi, struct prestera_sdma, rx_napi); + + while (pkts_done < budget && rxq_done_map != qmask) { + for (q = 0; q < qnum && pkts_done < budget; q++) { + struct prestera_rx_ring *ring = &sdma->rx_ring[q]; + struct prestera_sdma_desc *desc; + struct prestera_sdma_buf *buf; + int buf_idx = ring->next_rx; + struct sk_buff *skb; + + buf = &ring->bufs[buf_idx]; + desc = buf->desc; + + if (PRESTERA_SDMA_RX_DESC_IS_RCVD(desc)) { + rxq_done_map &= ~BIT(q); + } else { + rxq_done_map |= BIT(q); + continue; + } + + pkts_done++; + + __skb_trim(buf->skb, PRESTERA_SDMA_RX_DESC_PKT_LEN(desc)); + + skb = prestera_sdma_rx_skb_get(sdma, buf); + if (!skb) + goto rx_next_buf; + + if (unlikely(prestera_rxtx_process_skb(sdma, skb))) + goto rx_next_buf; + + list_add_tail(&skb->list, &rx_list); +rx_next_buf: + ring->next_rx = prestera_sdma_next_rx_buf_idx(buf_idx); + } + } + + if (pkts_done < budget && napi_complete_done(napi, pkts_done)) + prestera_write(sdma->sw, PRESTERA_SDMA_RX_INTR_MASK_REG, + GENMASK(9, 2)); + + netif_receive_skb_list(&rx_list); + + return pkts_done; +} + +static void prestera_sdma_rx_fini(struct prestera_sdma *sdma) +{ + int qnum = PRESTERA_SDMA_RX_QUEUE_NUM; + int q, b; + + /* disable all rx queues */ + prestera_write(sdma->sw, PRESTERA_SDMA_RX_QUEUE_STATUS_REG, + GENMASK(15, 8)); + + for (q = 0; q < qnum; q++) { + struct prestera_rx_ring *ring = &sdma->rx_ring[q]; + + if (!ring->bufs) + break; + + for (b = 0; b < PRESTERA_SDMA_RX_DESC_PER_Q; b++) { + struct prestera_sdma_buf *buf = &ring->bufs[b]; + + if (buf->desc_dma) + dma_pool_free(sdma->desc_pool, buf->desc, + buf->desc_dma); + + if (!buf->skb) + continue; + + if (buf->buf_dma != DMA_MAPPING_ERROR) + dma_unmap_single(sdma->sw->dev->dev, + buf->buf_dma, buf->skb->len, + DMA_FROM_DEVICE); + kfree_skb(buf->skb); + } + } +} + +static int prestera_sdma_rx_init(struct prestera_sdma *sdma) +{ + int bnum = PRESTERA_SDMA_RX_DESC_PER_Q; + int qnum = PRESTERA_SDMA_RX_QUEUE_NUM; + int err; + int q; + + /* disable all rx queues */ + prestera_write(sdma->sw, PRESTERA_SDMA_RX_QUEUE_STATUS_REG, + GENMASK(15, 8)); + + for (q = 0; q < qnum; q++) { + struct prestera_sdma_buf *head, *tail, *next, *prev; + struct prestera_rx_ring *ring = &sdma->rx_ring[q]; + + ring->bufs = kmalloc_array(bnum, sizeof(*head), GFP_KERNEL); + if (!ring->bufs) + return -ENOMEM; + + ring->next_rx = 0; + + tail = &ring->bufs[bnum - 1]; + head = &ring->bufs[0]; + next = head; + prev = next; + + do { + err = prestera_sdma_buf_init(sdma, next); + if (err) + return err; + + err = prestera_sdma_rx_skb_alloc(sdma, next); + if (err) + return err; + + prestera_sdma_rx_desc_init(sdma, next->desc, + next->buf_dma); + + prestera_sdma_rx_desc_set_next(sdma, prev->desc, + next->desc_dma); + + prev = next; + next++; + } while (prev != tail); + + /* join tail with head to make a circular list */ + prestera_sdma_rx_desc_set_next(sdma, tail->desc, head->desc_dma); + + prestera_write(sdma->sw, PRESTERA_SDMA_RX_QUEUE_DESC_REG(q), + prestera_sdma_map(sdma, head->desc_dma)); + } + + /* make sure all rx descs are filled before enabling all rx queues */ + wmb(); + + prestera_write(sdma->sw, PRESTERA_SDMA_RX_QUEUE_STATUS_REG, + GENMASK(7, 0)); + + return 0; +} + +static void prestera_sdma_tx_desc_init(struct prestera_sdma *sdma, + struct prestera_sdma_desc *desc) +{ + desc->word1 = cpu_to_le32(PRESTERA_SDMA_TX_DESC_INIT); + desc->word2 = 0; +} + +static void prestera_sdma_tx_desc_set_next(struct prestera_sdma *sdma, + struct prestera_sdma_desc *desc, + dma_addr_t next) +{ + desc->next = cpu_to_le32(prestera_sdma_map(sdma, next)); +} + +static void prestera_sdma_tx_desc_set_buf(struct prestera_sdma *sdma, + struct prestera_sdma_desc *desc, + dma_addr_t buf, size_t len) +{ + u32 word = le32_to_cpu(desc->word2); + + u32p_replace_bits(&word, len + ETH_FCS_LEN, GENMASK(30, 16)); + + desc->buff = cpu_to_le32(prestera_sdma_map(sdma, buf)); + desc->word2 = cpu_to_le32(word); +} + +static void prestera_sdma_tx_desc_xmit(struct prestera_sdma_desc *desc) +{ + u32 word = le32_to_cpu(desc->word1); + + word |= PRESTERA_SDMA_TX_DESC_DMA_OWN << 31; + + /* make sure everything is written before enable xmit */ + wmb(); + + desc->word1 = cpu_to_le32(word); +} + +static int prestera_sdma_tx_buf_map(struct prestera_sdma *sdma, + struct prestera_sdma_buf *buf, + struct sk_buff *skb) +{ + struct device *dma_dev = sdma->sw->dev->dev; + dma_addr_t dma; + + dma = dma_map_single(dma_dev, skb->data, skb->len, DMA_TO_DEVICE); + if (dma_mapping_error(dma_dev, dma)) + return -ENOMEM; + + buf->buf_dma = dma; + buf->skb = skb; + + return 0; +} + +static void prestera_sdma_tx_buf_unmap(struct prestera_sdma *sdma, + struct prestera_sdma_buf *buf) +{ + struct device *dma_dev = sdma->sw->dev->dev; + + dma_unmap_single(dma_dev, buf->buf_dma, buf->skb->len, DMA_TO_DEVICE); +} + +static void prestera_sdma_tx_recycle_work_fn(struct work_struct *work) +{ + int bnum = PRESTERA_SDMA_TX_DESC_PER_Q; + struct prestera_tx_ring *tx_ring; + struct prestera_sdma *sdma; + int b; + + sdma = container_of(work, struct prestera_sdma, tx_work); + + tx_ring = &sdma->tx_ring; + + for (b = 0; b < bnum; b++) { + struct prestera_sdma_buf *buf = &tx_ring->bufs[b]; + + if (!buf->is_used) + continue; + + if (!PRESTERA_SDMA_TX_DESC_IS_SENT(buf->desc)) + continue; + + prestera_sdma_tx_buf_unmap(sdma, buf); + dev_consume_skb_any(buf->skb); + buf->skb = NULL; + + /* make sure everything is cleaned up */ + wmb(); + + buf->is_used = false; + } +} + +static int prestera_sdma_tx_init(struct prestera_sdma *sdma) +{ + struct prestera_sdma_buf *head, *tail, *next, *prev; + struct prestera_tx_ring *tx_ring = &sdma->tx_ring; + int bnum = PRESTERA_SDMA_TX_DESC_PER_Q; + int err; + + INIT_WORK(&sdma->tx_work, prestera_sdma_tx_recycle_work_fn); + spin_lock_init(&sdma->tx_lock); + + tx_ring->bufs = kmalloc_array(bnum, sizeof(*head), GFP_KERNEL); + if (!tx_ring->bufs) + return -ENOMEM; + + tail = &tx_ring->bufs[bnum - 1]; + head = &tx_ring->bufs[0]; + next = head; + prev = next; + + tx_ring->max_burst = PRESTERA_SDMA_TX_MAX_BURST; + tx_ring->burst = tx_ring->max_burst; + tx_ring->next_tx = 0; + + do { + err = prestera_sdma_buf_init(sdma, next); + if (err) + return err; + + next->is_used = false; + + prestera_sdma_tx_desc_init(sdma, next->desc); + + prestera_sdma_tx_desc_set_next(sdma, prev->desc, + next->desc_dma); + + prev = next; + next++; + } while (prev != tail); + + /* join tail with head to make a circular list */ + prestera_sdma_tx_desc_set_next(sdma, tail->desc, head->desc_dma); + + /* make sure descriptors are written */ + wmb(); + + prestera_write(sdma->sw, PRESTERA_SDMA_TX_QUEUE_DESC_REG, + prestera_sdma_map(sdma, head->desc_dma)); + + return 0; +} + +static void prestera_sdma_tx_fini(struct prestera_sdma *sdma) +{ + struct prestera_tx_ring *ring = &sdma->tx_ring; + int bnum = PRESTERA_SDMA_TX_DESC_PER_Q; + int b; + + cancel_work_sync(&sdma->tx_work); + + if (!ring->bufs) + return; + + for (b = 0; b < bnum; b++) { + struct prestera_sdma_buf *buf = &ring->bufs[b]; + + if (buf->desc) + dma_pool_free(sdma->desc_pool, buf->desc, + buf->desc_dma); + + if (!buf->skb) + continue; + + dma_unmap_single(sdma->sw->dev->dev, buf->buf_dma, + buf->skb->len, DMA_TO_DEVICE); + + dev_consume_skb_any(buf->skb); + } +} + +static void prestera_rxtx_handle_event(struct prestera_switch *sw, + struct prestera_event *evt, + void *arg) +{ + struct prestera_sdma *sdma = arg; + + if (evt->id != PRESTERA_RXTX_EVENT_RCV_PKT) + return; + + prestera_write(sdma->sw, PRESTERA_SDMA_RX_INTR_MASK_REG, 0); + napi_schedule(&sdma->rx_napi); +} + +static int prestera_sdma_switch_init(struct prestera_switch *sw) +{ + struct prestera_sdma *sdma = &sw->rxtx->sdma; + struct device *dev = sw->dev->dev; + struct prestera_rxtx_params p; + int err; + + p.use_sdma = true; + + err = prestera_hw_rxtx_init(sw, &p); + if (err) { + dev_err(dev, "failed to init rxtx by hw\n"); + return err; + } + + sdma->dma_mask = dma_get_mask(dev); + sdma->map_addr = p.map_addr; + sdma->sw = sw; + + sdma->desc_pool = dma_pool_create("desc_pool", dev, + sizeof(struct prestera_sdma_desc), + 16, 0); + if (!sdma->desc_pool) + return -ENOMEM; + + err = prestera_sdma_rx_init(sdma); + if (err) { + dev_err(dev, "failed to init rx ring\n"); + goto err_rx_init; + } + + err = prestera_sdma_tx_init(sdma); + if (err) { + dev_err(dev, "failed to init tx ring\n"); + goto err_tx_init; + } + + err = prestera_hw_event_handler_register(sw, PRESTERA_EVENT_TYPE_RXTX, + prestera_rxtx_handle_event, + sdma); + if (err) + goto err_evt_register; + + init_dummy_netdev(&sdma->napi_dev); + + netif_napi_add(&sdma->napi_dev, &sdma->rx_napi, prestera_sdma_rx_poll); + napi_enable(&sdma->rx_napi); + + return 0; + +err_evt_register: +err_tx_init: + prestera_sdma_tx_fini(sdma); +err_rx_init: + prestera_sdma_rx_fini(sdma); + + dma_pool_destroy(sdma->desc_pool); + return err; +} + +static void prestera_sdma_switch_fini(struct prestera_switch *sw) +{ + struct prestera_sdma *sdma = &sw->rxtx->sdma; + + napi_disable(&sdma->rx_napi); + netif_napi_del(&sdma->rx_napi); + prestera_hw_event_handler_unregister(sw, PRESTERA_EVENT_TYPE_RXTX, + prestera_rxtx_handle_event); + prestera_sdma_tx_fini(sdma); + prestera_sdma_rx_fini(sdma); + dma_pool_destroy(sdma->desc_pool); +} + +static bool prestera_sdma_is_ready(struct prestera_sdma *sdma) +{ + return !(prestera_read(sdma->sw, PRESTERA_SDMA_TX_QUEUE_START_REG) & 1); +} + +static int prestera_sdma_tx_wait(struct prestera_sdma *sdma, + struct prestera_tx_ring *tx_ring) +{ + int tx_wait_num = PRESTERA_SDMA_WAIT_MUL * tx_ring->max_burst; + + do { + if (prestera_sdma_is_ready(sdma)) + return 0; + + udelay(1); + } while (--tx_wait_num); + + return -EBUSY; +} + +static void prestera_sdma_tx_start(struct prestera_sdma *sdma) +{ + prestera_write(sdma->sw, PRESTERA_SDMA_TX_QUEUE_START_REG, 1); + schedule_work(&sdma->tx_work); +} + +static netdev_tx_t prestera_sdma_xmit(struct prestera_sdma *sdma, + struct sk_buff *skb) +{ + struct device *dma_dev = sdma->sw->dev->dev; + struct net_device *dev = skb->dev; + struct prestera_tx_ring *tx_ring; + struct prestera_sdma_buf *buf; + int err; + + spin_lock(&sdma->tx_lock); + + tx_ring = &sdma->tx_ring; + + buf = &tx_ring->bufs[tx_ring->next_tx]; + if (buf->is_used) { + schedule_work(&sdma->tx_work); + goto drop_skb; + } + + if (unlikely(eth_skb_pad(skb))) + goto drop_skb_nofree; + + err = prestera_sdma_tx_buf_map(sdma, buf, skb); + if (err) + goto drop_skb; + + prestera_sdma_tx_desc_set_buf(sdma, buf->desc, buf->buf_dma, skb->len); + + dma_sync_single_for_device(dma_dev, buf->buf_dma, skb->len, + DMA_TO_DEVICE); + + if (tx_ring->burst) { + tx_ring->burst--; + } else { + tx_ring->burst = tx_ring->max_burst; + + err = prestera_sdma_tx_wait(sdma, tx_ring); + if (err) + goto drop_skb_unmap; + } + + tx_ring->next_tx = (tx_ring->next_tx + 1) % PRESTERA_SDMA_TX_DESC_PER_Q; + prestera_sdma_tx_desc_xmit(buf->desc); + buf->is_used = true; + + prestera_sdma_tx_start(sdma); + + goto tx_done; + +drop_skb_unmap: + prestera_sdma_tx_buf_unmap(sdma, buf); +drop_skb: + dev_consume_skb_any(skb); +drop_skb_nofree: + dev->stats.tx_dropped++; +tx_done: + spin_unlock(&sdma->tx_lock); + return NETDEV_TX_OK; +} + +int prestera_rxtx_switch_init(struct prestera_switch *sw) +{ + struct prestera_rxtx *rxtx; + int err; + + rxtx = kzalloc(sizeof(*rxtx), GFP_KERNEL); + if (!rxtx) + return -ENOMEM; + + sw->rxtx = rxtx; + + err = prestera_sdma_switch_init(sw); + if (err) + kfree(rxtx); + + return err; +} + +void prestera_rxtx_switch_fini(struct prestera_switch *sw) +{ + prestera_sdma_switch_fini(sw); + kfree(sw->rxtx); +} + +int prestera_rxtx_port_init(struct prestera_port *port) +{ + port->dev->needed_headroom = PRESTERA_DSA_HLEN; + return 0; +} + +netdev_tx_t prestera_rxtx_xmit(struct prestera_port *port, struct sk_buff *skb) +{ + struct prestera_dsa dsa; + + dsa.hw_dev_num = port->dev_id; + dsa.port_num = port->hw_id; + + if (skb_cow_head(skb, PRESTERA_DSA_HLEN) < 0) + return NET_XMIT_DROP; + + skb_push(skb, PRESTERA_DSA_HLEN); + memmove(skb->data, skb->data + PRESTERA_DSA_HLEN, 2 * ETH_ALEN); + + if (prestera_dsa_build(&dsa, skb->data + 2 * ETH_ALEN) != 0) + return NET_XMIT_DROP; + + return prestera_sdma_xmit(&port->sw->rxtx->sdma, skb); +} -- cgit v1.2.3