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(). ... --- drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c | 264 ++++++++++++++++++++++++++++ 1 file changed, 264 insertions(+) create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c (limited to 'drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c') diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c new file mode 100644 index 000000000..16c56e240 --- /dev/null +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c @@ -0,0 +1,264 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved. + */ + +#include "dpu_hwio.h" +#include "dpu_hw_catalog.h" +#include "dpu_hw_vbif.h" + +#define VBIF_VERSION 0x0000 +#define VBIF_CLK_FORCE_CTRL0 0x0008 +#define VBIF_CLK_FORCE_CTRL1 0x000C +#define VBIF_QOS_REMAP_00 0x0020 +#define VBIF_QOS_REMAP_01 0x0024 +#define VBIF_QOS_REMAP_10 0x0028 +#define VBIF_QOS_REMAP_11 0x002C +#define VBIF_WRITE_GATHER_EN 0x00AC +#define VBIF_IN_RD_LIM_CONF0 0x00B0 +#define VBIF_IN_RD_LIM_CONF1 0x00B4 +#define VBIF_IN_RD_LIM_CONF2 0x00B8 +#define VBIF_IN_WR_LIM_CONF0 0x00C0 +#define VBIF_IN_WR_LIM_CONF1 0x00C4 +#define VBIF_IN_WR_LIM_CONF2 0x00C8 +#define VBIF_OUT_RD_LIM_CONF0 0x00D0 +#define VBIF_OUT_WR_LIM_CONF0 0x00D4 +#define VBIF_OUT_AXI_AMEMTYPE_CONF0 0x0160 +#define VBIF_OUT_AXI_AMEMTYPE_CONF1 0x0164 +#define VBIF_XIN_PND_ERR 0x0190 +#define VBIF_XIN_SRC_ERR 0x0194 +#define VBIF_XIN_CLR_ERR 0x019C +#define VBIF_XIN_HALT_CTRL0 0x0200 +#define VBIF_XIN_HALT_CTRL1 0x0204 +#define VBIF_XINL_QOS_RP_REMAP_000 0x0550 +#define VBIF_XINL_QOS_LVL_REMAP_000(vbif) (VBIF_XINL_QOS_RP_REMAP_000 + (vbif)->cap->qos_rp_remap_size) + +static void dpu_hw_clear_errors(struct dpu_hw_vbif *vbif, + u32 *pnd_errors, u32 *src_errors) +{ + struct dpu_hw_blk_reg_map *c; + u32 pnd, src; + + if (!vbif) + return; + c = &vbif->hw; + pnd = DPU_REG_READ(c, VBIF_XIN_PND_ERR); + src = DPU_REG_READ(c, VBIF_XIN_SRC_ERR); + + if (pnd_errors) + *pnd_errors = pnd; + if (src_errors) + *src_errors = src; + + DPU_REG_WRITE(c, VBIF_XIN_CLR_ERR, pnd | src); +} + +static void dpu_hw_set_mem_type(struct dpu_hw_vbif *vbif, + u32 xin_id, u32 value) +{ + struct dpu_hw_blk_reg_map *c; + u32 reg_off; + u32 bit_off; + u32 reg_val; + + /* + * Assume 4 bits per bit field, 8 fields per 32-bit register so + * 16 bit fields maximum across two registers + */ + if (!vbif || xin_id >= MAX_XIN_COUNT || xin_id >= 16) + return; + + c = &vbif->hw; + + if (xin_id >= 8) { + xin_id -= 8; + reg_off = VBIF_OUT_AXI_AMEMTYPE_CONF1; + } else { + reg_off = VBIF_OUT_AXI_AMEMTYPE_CONF0; + } + bit_off = (xin_id & 0x7) * 4; + reg_val = DPU_REG_READ(c, reg_off); + reg_val &= ~(0x7 << bit_off); + reg_val |= (value & 0x7) << bit_off; + DPU_REG_WRITE(c, reg_off, reg_val); +} + +static void dpu_hw_set_limit_conf(struct dpu_hw_vbif *vbif, + u32 xin_id, bool rd, u32 limit) +{ + struct dpu_hw_blk_reg_map *c = &vbif->hw; + u32 reg_val; + u32 reg_off; + u32 bit_off; + + if (rd) + reg_off = VBIF_IN_RD_LIM_CONF0; + else + reg_off = VBIF_IN_WR_LIM_CONF0; + + reg_off += (xin_id / 4) * 4; + bit_off = (xin_id % 4) * 8; + reg_val = DPU_REG_READ(c, reg_off); + reg_val &= ~(0xFF << bit_off); + reg_val |= (limit) << bit_off; + DPU_REG_WRITE(c, reg_off, reg_val); +} + +static u32 dpu_hw_get_limit_conf(struct dpu_hw_vbif *vbif, + u32 xin_id, bool rd) +{ + struct dpu_hw_blk_reg_map *c = &vbif->hw; + u32 reg_val; + u32 reg_off; + u32 bit_off; + u32 limit; + + if (rd) + reg_off = VBIF_IN_RD_LIM_CONF0; + else + reg_off = VBIF_IN_WR_LIM_CONF0; + + reg_off += (xin_id / 4) * 4; + bit_off = (xin_id % 4) * 8; + reg_val = DPU_REG_READ(c, reg_off); + limit = (reg_val >> bit_off) & 0xFF; + + return limit; +} + +static void dpu_hw_set_halt_ctrl(struct dpu_hw_vbif *vbif, + u32 xin_id, bool enable) +{ + struct dpu_hw_blk_reg_map *c = &vbif->hw; + u32 reg_val; + + reg_val = DPU_REG_READ(c, VBIF_XIN_HALT_CTRL0); + + if (enable) + reg_val |= BIT(xin_id); + else + reg_val &= ~BIT(xin_id); + + DPU_REG_WRITE(c, VBIF_XIN_HALT_CTRL0, reg_val); +} + +static bool dpu_hw_get_halt_ctrl(struct dpu_hw_vbif *vbif, + u32 xin_id) +{ + struct dpu_hw_blk_reg_map *c = &vbif->hw; + u32 reg_val; + + reg_val = DPU_REG_READ(c, VBIF_XIN_HALT_CTRL1); + + return (reg_val & BIT(xin_id)) ? true : false; +} + +static void dpu_hw_set_qos_remap(struct dpu_hw_vbif *vbif, + u32 xin_id, u32 level, u32 remap_level) +{ + struct dpu_hw_blk_reg_map *c; + u32 reg_lvl, reg_val, reg_val_lvl, mask, reg_high, reg_shift; + + if (!vbif) + return; + + c = &vbif->hw; + + reg_lvl = VBIF_XINL_QOS_LVL_REMAP_000(vbif); + reg_high = ((xin_id & 0x8) >> 3) * 4 + (level * 8); + reg_shift = (xin_id & 0x7) * 4; + + reg_val = DPU_REG_READ(c, VBIF_XINL_QOS_RP_REMAP_000 + reg_high); + reg_val_lvl = DPU_REG_READ(c, reg_lvl + reg_high); + + mask = 0x7 << reg_shift; + + reg_val &= ~mask; + reg_val |= (remap_level << reg_shift) & mask; + + reg_val_lvl &= ~mask; + reg_val_lvl |= (remap_level << reg_shift) & mask; + + DPU_REG_WRITE(c, VBIF_XINL_QOS_RP_REMAP_000 + reg_high, reg_val); + DPU_REG_WRITE(c, reg_lvl + reg_high, reg_val_lvl); +} + +static void dpu_hw_set_write_gather_en(struct dpu_hw_vbif *vbif, u32 xin_id) +{ + struct dpu_hw_blk_reg_map *c; + u32 reg_val; + + if (!vbif || xin_id >= MAX_XIN_COUNT) + return; + + c = &vbif->hw; + + reg_val = DPU_REG_READ(c, VBIF_WRITE_GATHER_EN); + reg_val |= BIT(xin_id); + DPU_REG_WRITE(c, VBIF_WRITE_GATHER_EN, reg_val); +} + +static void _setup_vbif_ops(struct dpu_hw_vbif_ops *ops, + unsigned long cap) +{ + ops->set_limit_conf = dpu_hw_set_limit_conf; + ops->get_limit_conf = dpu_hw_get_limit_conf; + ops->set_halt_ctrl = dpu_hw_set_halt_ctrl; + ops->get_halt_ctrl = dpu_hw_get_halt_ctrl; + if (test_bit(DPU_VBIF_QOS_REMAP, &cap)) + ops->set_qos_remap = dpu_hw_set_qos_remap; + ops->set_mem_type = dpu_hw_set_mem_type; + ops->clear_errors = dpu_hw_clear_errors; + ops->set_write_gather_en = dpu_hw_set_write_gather_en; +} + +static const struct dpu_vbif_cfg *_top_offset(enum dpu_vbif vbif, + const struct dpu_mdss_cfg *m, + void __iomem *addr, + struct dpu_hw_blk_reg_map *b) +{ + int i; + + for (i = 0; i < m->vbif_count; i++) { + if (vbif == m->vbif[i].id) { + b->blk_addr = addr + m->vbif[i].base; + b->log_mask = DPU_DBG_MASK_VBIF; + return &m->vbif[i]; + } + } + + return ERR_PTR(-EINVAL); +} + +struct dpu_hw_vbif *dpu_hw_vbif_init(enum dpu_vbif idx, + void __iomem *addr, + const struct dpu_mdss_cfg *m) +{ + struct dpu_hw_vbif *c; + const struct dpu_vbif_cfg *cfg; + + c = kzalloc(sizeof(*c), GFP_KERNEL); + if (!c) + return ERR_PTR(-ENOMEM); + + cfg = _top_offset(idx, m, addr, &c->hw); + if (IS_ERR_OR_NULL(cfg)) { + kfree(c); + return ERR_PTR(-EINVAL); + } + + /* + * Assign ops + */ + c->idx = idx; + c->cap = cfg; + _setup_vbif_ops(&c->ops, c->cap->features); + + /* no need to register sub-range in dpu dbg, dump entire vbif io base */ + + return c; +} + +void dpu_hw_vbif_destroy(struct dpu_hw_vbif *vbif) +{ + kfree(vbif); +} -- cgit v1.2.3