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(). ... --- sound/soc/intel/avs/cldma.c | 316 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 316 insertions(+) create mode 100644 sound/soc/intel/avs/cldma.c (limited to 'sound/soc/intel/avs/cldma.c') diff --git a/sound/soc/intel/avs/cldma.c b/sound/soc/intel/avs/cldma.c new file mode 100644 index 000000000..d7a9390b5 --- /dev/null +++ b/sound/soc/intel/avs/cldma.c @@ -0,0 +1,316 @@ +// SPDX-License-Identifier: GPL-2.0-only +// +// Copyright(c) 2021-2022 Intel Corporation. All rights reserved. +// +// Author: Cezary Rojewski +// + +#include +#include +#include +#include "cldma.h" +#include "registers.h" + +/* Stream Registers */ +#define AZX_CL_SD_BASE 0x80 +#define AZX_SD_CTL_STRM_MASK GENMASK(23, 20) +#define AZX_SD_CTL_STRM(s) (((s)->stream_tag << 20) & AZX_SD_CTL_STRM_MASK) +#define AZX_SD_BDLPL_BDLPLBA_MASK GENMASK(31, 7) +#define AZX_SD_BDLPL_BDLPLBA(lb) ((lb) & AZX_SD_BDLPL_BDLPLBA_MASK) + +/* Software Position Based FIFO Capability Registers */ +#define AZX_CL_SPBFCS 0x20 +#define AZX_REG_CL_SPBFCTL (AZX_CL_SPBFCS + 0x4) +#define AZX_REG_CL_SD_SPIB (AZX_CL_SPBFCS + 0x8) + +#define AVS_CL_OP_INTERVAL_US 3 +#define AVS_CL_OP_TIMEOUT_US 300 +#define AVS_CL_IOC_TIMEOUT_MS 300 +#define AVS_CL_STREAM_INDEX 0 + +struct hda_cldma { + struct device *dev; + struct hdac_bus *bus; + void __iomem *dsp_ba; + + unsigned int buffer_size; + unsigned int num_periods; + unsigned int stream_tag; + void __iomem *sd_addr; + + struct snd_dma_buffer dmab_data; + struct snd_dma_buffer dmab_bdl; + struct delayed_work memcpy_work; + struct completion completion; + + /* runtime */ + void *position; + unsigned int remaining; + unsigned int sd_status; +}; + +static void cldma_memcpy_work(struct work_struct *work); + +struct hda_cldma code_loader = { + .stream_tag = AVS_CL_STREAM_INDEX + 1, + .memcpy_work = __DELAYED_WORK_INITIALIZER(code_loader.memcpy_work, cldma_memcpy_work, 0), + .completion = COMPLETION_INITIALIZER(code_loader.completion), +}; + +void hda_cldma_fill(struct hda_cldma *cl) +{ + unsigned int size, offset; + + if (cl->remaining > cl->buffer_size) + size = cl->buffer_size; + else + size = cl->remaining; + + offset = snd_hdac_stream_readl(cl, CL_SD_SPIB); + if (offset + size > cl->buffer_size) { + unsigned int ss; + + ss = cl->buffer_size - offset; + memcpy(cl->dmab_data.area + offset, cl->position, ss); + offset = 0; + size -= ss; + cl->position += ss; + cl->remaining -= ss; + } + + memcpy(cl->dmab_data.area + offset, cl->position, size); + cl->position += size; + cl->remaining -= size; + + snd_hdac_stream_writel(cl, CL_SD_SPIB, offset + size); +} + +static void cldma_memcpy_work(struct work_struct *work) +{ + struct hda_cldma *cl = container_of(work, struct hda_cldma, memcpy_work.work); + int ret; + + ret = hda_cldma_start(cl); + if (ret < 0) { + dev_err(cl->dev, "cldma set RUN failed: %d\n", ret); + return; + } + + while (true) { + ret = wait_for_completion_timeout(&cl->completion, + msecs_to_jiffies(AVS_CL_IOC_TIMEOUT_MS)); + if (!ret) { + dev_err(cl->dev, "cldma IOC timeout\n"); + break; + } + + if (!(cl->sd_status & SD_INT_COMPLETE)) { + dev_err(cl->dev, "cldma transfer error, SD status: 0x%08x\n", + cl->sd_status); + break; + } + + if (!cl->remaining) + break; + + reinit_completion(&cl->completion); + hda_cldma_fill(cl); + /* enable CLDMA interrupt */ + snd_hdac_adsp_updatel(cl, AVS_ADSP_REG_ADSPIC, AVS_ADSP_ADSPIC_CLDMA, + AVS_ADSP_ADSPIC_CLDMA); + } +} + +void hda_cldma_transfer(struct hda_cldma *cl, unsigned long start_delay) +{ + if (!cl->remaining) + return; + + reinit_completion(&cl->completion); + /* fill buffer with the first chunk before scheduling run */ + hda_cldma_fill(cl); + + schedule_delayed_work(&cl->memcpy_work, start_delay); +} + +int hda_cldma_start(struct hda_cldma *cl) +{ + unsigned int reg; + + /* enable interrupts */ + snd_hdac_adsp_updatel(cl, AVS_ADSP_REG_ADSPIC, AVS_ADSP_ADSPIC_CLDMA, + AVS_ADSP_ADSPIC_CLDMA); + snd_hdac_stream_updateb(cl, SD_CTL, SD_INT_MASK | SD_CTL_DMA_START, + SD_INT_MASK | SD_CTL_DMA_START); + + /* await DMA engine start */ + return snd_hdac_stream_readb_poll(cl, SD_CTL, reg, reg & SD_CTL_DMA_START, + AVS_CL_OP_INTERVAL_US, AVS_CL_OP_TIMEOUT_US); +} + +int hda_cldma_stop(struct hda_cldma *cl) +{ + unsigned int reg; + int ret; + + /* disable interrupts */ + snd_hdac_adsp_updatel(cl, AVS_ADSP_REG_ADSPIC, AVS_ADSP_ADSPIC_CLDMA, 0); + snd_hdac_stream_updateb(cl, SD_CTL, SD_INT_MASK | SD_CTL_DMA_START, 0); + + /* await DMA engine stop */ + ret = snd_hdac_stream_readb_poll(cl, SD_CTL, reg, !(reg & SD_CTL_DMA_START), + AVS_CL_OP_INTERVAL_US, AVS_CL_OP_TIMEOUT_US); + cancel_delayed_work_sync(&cl->memcpy_work); + + return ret; +} + +int hda_cldma_reset(struct hda_cldma *cl) +{ + unsigned int reg; + int ret; + + ret = hda_cldma_stop(cl); + if (ret < 0) { + dev_err(cl->dev, "cldma stop failed: %d\n", ret); + return ret; + } + + snd_hdac_stream_updateb(cl, SD_CTL, SD_CTL_STREAM_RESET, SD_CTL_STREAM_RESET); + ret = snd_hdac_stream_readb_poll(cl, SD_CTL, reg, (reg & SD_CTL_STREAM_RESET), + AVS_CL_OP_INTERVAL_US, AVS_CL_OP_TIMEOUT_US); + if (ret < 0) { + dev_err(cl->dev, "cldma set SRST failed: %d\n", ret); + return ret; + } + + snd_hdac_stream_updateb(cl, SD_CTL, SD_CTL_STREAM_RESET, 0); + ret = snd_hdac_stream_readb_poll(cl, SD_CTL, reg, !(reg & SD_CTL_STREAM_RESET), + AVS_CL_OP_INTERVAL_US, AVS_CL_OP_TIMEOUT_US); + if (ret < 0) { + dev_err(cl->dev, "cldma unset SRST failed: %d\n", ret); + return ret; + } + + return 0; +} + +void hda_cldma_set_data(struct hda_cldma *cl, void *data, unsigned int size) +{ + /* setup runtime */ + cl->position = data; + cl->remaining = size; +} + +static void cldma_setup_bdle(struct hda_cldma *cl, u32 bdle_size) +{ + struct snd_dma_buffer *dmab = &cl->dmab_data; + __le32 *bdl = (__le32 *)cl->dmab_bdl.area; + int remaining = cl->buffer_size; + int offset = 0; + + cl->num_periods = 0; + + while (remaining > 0) { + phys_addr_t addr; + int chunk; + + addr = snd_sgbuf_get_addr(dmab, offset); + bdl[0] = cpu_to_le32(lower_32_bits(addr)); + bdl[1] = cpu_to_le32(upper_32_bits(addr)); + chunk = snd_sgbuf_get_chunk_size(dmab, offset, bdle_size); + bdl[2] = cpu_to_le32(chunk); + + remaining -= chunk; + /* set IOC only for the last entry */ + bdl[3] = (remaining > 0) ? 0 : cpu_to_le32(0x01); + + bdl += 4; + offset += chunk; + cl->num_periods++; + } +} + +void hda_cldma_setup(struct hda_cldma *cl) +{ + dma_addr_t bdl_addr = cl->dmab_bdl.addr; + + cldma_setup_bdle(cl, cl->buffer_size / 2); + + snd_hdac_stream_writel(cl, SD_BDLPL, AZX_SD_BDLPL_BDLPLBA(lower_32_bits(bdl_addr))); + snd_hdac_stream_writel(cl, SD_BDLPU, upper_32_bits(bdl_addr)); + + snd_hdac_stream_writel(cl, SD_CBL, cl->buffer_size); + snd_hdac_stream_writeb(cl, SD_LVI, cl->num_periods - 1); + + snd_hdac_stream_updatel(cl, SD_CTL, AZX_SD_CTL_STRM_MASK, AZX_SD_CTL_STRM(cl)); + /* enable spib */ + snd_hdac_stream_writel(cl, CL_SPBFCTL, 1); +} + +static irqreturn_t cldma_irq_handler(int irq, void *dev_id) +{ + struct hda_cldma *cl = dev_id; + u32 adspis; + + adspis = snd_hdac_adsp_readl(cl, AVS_ADSP_REG_ADSPIS); + if (adspis == UINT_MAX) + return IRQ_NONE; + if (!(adspis & AVS_ADSP_ADSPIS_CLDMA)) + return IRQ_NONE; + + cl->sd_status = snd_hdac_stream_readb(cl, SD_STS); + dev_warn(cl->dev, "%s sd_status: 0x%08x\n", __func__, cl->sd_status); + + /* disable CLDMA interrupt */ + snd_hdac_adsp_updatel(cl, AVS_ADSP_REG_ADSPIC, AVS_ADSP_ADSPIC_CLDMA, 0); + + complete(&cl->completion); + + return IRQ_HANDLED; +} + +int hda_cldma_init(struct hda_cldma *cl, struct hdac_bus *bus, void __iomem *dsp_ba, + unsigned int buffer_size) +{ + struct pci_dev *pci = to_pci_dev(bus->dev); + int ret; + + ret = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV_SG, bus->dev, buffer_size, &cl->dmab_data); + if (ret < 0) + return ret; + + ret = snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, bus->dev, BDL_SIZE, &cl->dmab_bdl); + if (ret < 0) + goto alloc_err; + + cl->dev = bus->dev; + cl->bus = bus; + cl->dsp_ba = dsp_ba; + cl->buffer_size = buffer_size; + cl->sd_addr = dsp_ba + AZX_CL_SD_BASE; + + ret = pci_request_irq(pci, 0, cldma_irq_handler, NULL, cl, "CLDMA"); + if (ret < 0) { + dev_err(cl->dev, "Failed to request CLDMA IRQ handler: %d\n", ret); + goto req_err; + } + + return 0; + +req_err: + snd_dma_free_pages(&cl->dmab_bdl); +alloc_err: + snd_dma_free_pages(&cl->dmab_data); + + return ret; +} + +void hda_cldma_free(struct hda_cldma *cl) +{ + struct pci_dev *pci = to_pci_dev(cl->dev); + + pci_free_irq(pci, 0, cl); + snd_dma_free_pages(&cl->dmab_data); + snd_dma_free_pages(&cl->dmab_bdl); +} -- cgit v1.2.3