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/virtio/virtgpu_kms.c | 346 +++++++++++++++++++++++++++++++++++ 1 file changed, 346 insertions(+) create mode 100644 drivers/gpu/drm/virtio/virtgpu_kms.c (limited to 'drivers/gpu/drm/virtio/virtgpu_kms.c') diff --git a/drivers/gpu/drm/virtio/virtgpu_kms.c b/drivers/gpu/drm/virtio/virtgpu_kms.c new file mode 100644 index 000000000..27b7f14da --- /dev/null +++ b/drivers/gpu/drm/virtio/virtgpu_kms.c @@ -0,0 +1,346 @@ +/* + * Copyright (C) 2015 Red Hat, Inc. + * All Rights Reserved. + * + * Permission is hereby granted, free of charge, to any person obtaining + * a copy of this software and associated documentation files (the + * "Software"), to deal in the Software without restriction, including + * without limitation the rights to use, copy, modify, merge, publish, + * distribute, sublicense, and/or sell copies of the Software, and to + * permit persons to whom the Software is furnished to do so, subject to + * the following conditions: + * + * The above copyright notice and this permission notice (including the + * next paragraph) shall be included in all copies or substantial + * portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. + * IN NO EVENT SHALL THE COPYRIGHT OWNER(S) AND/OR ITS SUPPLIERS BE + * LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION + * OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION + * WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. + */ + +#include +#include +#include + +#include +#include + +#include "virtgpu_drv.h" + +static void virtio_gpu_config_changed_work_func(struct work_struct *work) +{ + struct virtio_gpu_device *vgdev = + container_of(work, struct virtio_gpu_device, + config_changed_work); + u32 events_read, events_clear = 0; + + /* read the config space */ + virtio_cread_le(vgdev->vdev, struct virtio_gpu_config, + events_read, &events_read); + if (events_read & VIRTIO_GPU_EVENT_DISPLAY) { + if (vgdev->has_edid) + virtio_gpu_cmd_get_edids(vgdev); + virtio_gpu_cmd_get_display_info(vgdev); + virtio_gpu_notify(vgdev); + drm_helper_hpd_irq_event(vgdev->ddev); + events_clear |= VIRTIO_GPU_EVENT_DISPLAY; + } + virtio_cwrite_le(vgdev->vdev, struct virtio_gpu_config, + events_clear, &events_clear); +} + +static void virtio_gpu_init_vq(struct virtio_gpu_queue *vgvq, + void (*work_func)(struct work_struct *work)) +{ + spin_lock_init(&vgvq->qlock); + init_waitqueue_head(&vgvq->ack_queue); + INIT_WORK(&vgvq->dequeue_work, work_func); +} + +static void virtio_gpu_get_capsets(struct virtio_gpu_device *vgdev, + int num_capsets) +{ + int i, ret; + bool invalid_capset_id = false; + struct drm_device *drm = vgdev->ddev; + + vgdev->capsets = drmm_kcalloc(drm, num_capsets, + sizeof(struct virtio_gpu_drv_capset), + GFP_KERNEL); + if (!vgdev->capsets) { + DRM_ERROR("failed to allocate cap sets\n"); + return; + } + for (i = 0; i < num_capsets; i++) { + virtio_gpu_cmd_get_capset_info(vgdev, i); + virtio_gpu_notify(vgdev); + ret = wait_event_timeout(vgdev->resp_wq, + vgdev->capsets[i].id > 0, 5 * HZ); + /* + * Capability ids are defined in the virtio-gpu spec and are + * between 1 to 63, inclusive. + */ + if (!vgdev->capsets[i].id || + vgdev->capsets[i].id > MAX_CAPSET_ID) + invalid_capset_id = true; + + if (ret == 0) + DRM_ERROR("timed out waiting for cap set %d\n", i); + else if (invalid_capset_id) + DRM_ERROR("invalid capset id %u", vgdev->capsets[i].id); + + if (ret == 0 || invalid_capset_id) { + spin_lock(&vgdev->display_info_lock); + drmm_kfree(drm, vgdev->capsets); + vgdev->capsets = NULL; + spin_unlock(&vgdev->display_info_lock); + return; + } + + vgdev->capset_id_mask |= 1 << vgdev->capsets[i].id; + DRM_INFO("cap set %d: id %d, max-version %d, max-size %d\n", + i, vgdev->capsets[i].id, + vgdev->capsets[i].max_version, + vgdev->capsets[i].max_size); + } + + vgdev->num_capsets = num_capsets; +} + +int virtio_gpu_init(struct virtio_device *vdev, struct drm_device *dev) +{ + static vq_callback_t *callbacks[] = { + virtio_gpu_ctrl_ack, virtio_gpu_cursor_ack + }; + static const char * const names[] = { "control", "cursor" }; + + struct virtio_gpu_device *vgdev; + /* this will expand later */ + struct virtqueue *vqs[2]; + u32 num_scanouts, num_capsets; + int ret = 0; + + if (!virtio_has_feature(vdev, VIRTIO_F_VERSION_1)) + return -ENODEV; + + vgdev = drmm_kzalloc(dev, sizeof(struct virtio_gpu_device), GFP_KERNEL); + if (!vgdev) + return -ENOMEM; + + vgdev->ddev = dev; + dev->dev_private = vgdev; + vgdev->vdev = vdev; + + spin_lock_init(&vgdev->display_info_lock); + spin_lock_init(&vgdev->resource_export_lock); + spin_lock_init(&vgdev->host_visible_lock); + ida_init(&vgdev->ctx_id_ida); + ida_init(&vgdev->resource_ida); + init_waitqueue_head(&vgdev->resp_wq); + virtio_gpu_init_vq(&vgdev->ctrlq, virtio_gpu_dequeue_ctrl_func); + virtio_gpu_init_vq(&vgdev->cursorq, virtio_gpu_dequeue_cursor_func); + + vgdev->fence_drv.context = dma_fence_context_alloc(1); + spin_lock_init(&vgdev->fence_drv.lock); + INIT_LIST_HEAD(&vgdev->fence_drv.fences); + INIT_LIST_HEAD(&vgdev->cap_cache); + INIT_WORK(&vgdev->config_changed_work, + virtio_gpu_config_changed_work_func); + + INIT_WORK(&vgdev->obj_free_work, + virtio_gpu_array_put_free_work); + INIT_LIST_HEAD(&vgdev->obj_free_list); + spin_lock_init(&vgdev->obj_free_lock); + +#ifdef __LITTLE_ENDIAN + if (virtio_has_feature(vgdev->vdev, VIRTIO_GPU_F_VIRGL)) + vgdev->has_virgl_3d = true; +#endif + if (virtio_has_feature(vgdev->vdev, VIRTIO_GPU_F_EDID)) { + vgdev->has_edid = true; + } + if (virtio_has_feature(vgdev->vdev, VIRTIO_RING_F_INDIRECT_DESC)) { + vgdev->has_indirect = true; + } + if (virtio_has_feature(vgdev->vdev, VIRTIO_GPU_F_RESOURCE_UUID)) { + vgdev->has_resource_assign_uuid = true; + } + if (virtio_has_feature(vgdev->vdev, VIRTIO_GPU_F_RESOURCE_BLOB)) { + vgdev->has_resource_blob = true; + } + if (virtio_get_shm_region(vgdev->vdev, &vgdev->host_visible_region, + VIRTIO_GPU_SHM_ID_HOST_VISIBLE)) { + if (!devm_request_mem_region(&vgdev->vdev->dev, + vgdev->host_visible_region.addr, + vgdev->host_visible_region.len, + dev_name(&vgdev->vdev->dev))) { + DRM_ERROR("Could not reserve host visible region\n"); + ret = -EBUSY; + goto err_vqs; + } + + DRM_INFO("Host memory window: 0x%lx +0x%lx\n", + (unsigned long)vgdev->host_visible_region.addr, + (unsigned long)vgdev->host_visible_region.len); + vgdev->has_host_visible = true; + drm_mm_init(&vgdev->host_visible_mm, + (unsigned long)vgdev->host_visible_region.addr, + (unsigned long)vgdev->host_visible_region.len); + } + if (virtio_has_feature(vgdev->vdev, VIRTIO_GPU_F_CONTEXT_INIT)) { + vgdev->has_context_init = true; + } + + DRM_INFO("features: %cvirgl %cedid %cresource_blob %chost_visible", + vgdev->has_virgl_3d ? '+' : '-', + vgdev->has_edid ? '+' : '-', + vgdev->has_resource_blob ? '+' : '-', + vgdev->has_host_visible ? '+' : '-'); + + DRM_INFO("features: %ccontext_init\n", + vgdev->has_context_init ? '+' : '-'); + + ret = virtio_find_vqs(vgdev->vdev, 2, vqs, callbacks, names, NULL); + if (ret) { + DRM_ERROR("failed to find virt queues\n"); + goto err_vqs; + } + vgdev->ctrlq.vq = vqs[0]; + vgdev->cursorq.vq = vqs[1]; + ret = virtio_gpu_alloc_vbufs(vgdev); + if (ret) { + DRM_ERROR("failed to alloc vbufs\n"); + goto err_vbufs; + } + + /* get display info */ + virtio_cread_le(vgdev->vdev, struct virtio_gpu_config, + num_scanouts, &num_scanouts); + vgdev->num_scanouts = min_t(uint32_t, num_scanouts, + VIRTIO_GPU_MAX_SCANOUTS); + if (!vgdev->num_scanouts) { + DRM_ERROR("num_scanouts is zero\n"); + ret = -EINVAL; + goto err_scanouts; + } + DRM_INFO("number of scanouts: %d\n", num_scanouts); + + virtio_cread_le(vgdev->vdev, struct virtio_gpu_config, + num_capsets, &num_capsets); + DRM_INFO("number of cap sets: %d\n", num_capsets); + + ret = virtio_gpu_modeset_init(vgdev); + if (ret) { + DRM_ERROR("modeset init failed\n"); + goto err_scanouts; + } + + virtio_device_ready(vgdev->vdev); + + if (num_capsets) + virtio_gpu_get_capsets(vgdev, num_capsets); + if (vgdev->has_edid) + virtio_gpu_cmd_get_edids(vgdev); + virtio_gpu_cmd_get_display_info(vgdev); + virtio_gpu_notify(vgdev); + wait_event_timeout(vgdev->resp_wq, !vgdev->display_info_pending, + 5 * HZ); + return 0; + +err_scanouts: + virtio_gpu_free_vbufs(vgdev); +err_vbufs: + vgdev->vdev->config->del_vqs(vgdev->vdev); +err_vqs: + dev->dev_private = NULL; + return ret; +} + +static void virtio_gpu_cleanup_cap_cache(struct virtio_gpu_device *vgdev) +{ + struct virtio_gpu_drv_cap_cache *cache_ent, *tmp; + + list_for_each_entry_safe(cache_ent, tmp, &vgdev->cap_cache, head) { + kfree(cache_ent->caps_cache); + kfree(cache_ent); + } +} + +void virtio_gpu_deinit(struct drm_device *dev) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; + + flush_work(&vgdev->obj_free_work); + flush_work(&vgdev->ctrlq.dequeue_work); + flush_work(&vgdev->cursorq.dequeue_work); + flush_work(&vgdev->config_changed_work); + virtio_reset_device(vgdev->vdev); + vgdev->vdev->config->del_vqs(vgdev->vdev); +} + +void virtio_gpu_release(struct drm_device *dev) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; + + if (!vgdev) + return; + + virtio_gpu_modeset_fini(vgdev); + virtio_gpu_free_vbufs(vgdev); + virtio_gpu_cleanup_cap_cache(vgdev); + + if (vgdev->has_host_visible) + drm_mm_takedown(&vgdev->host_visible_mm); +} + +int virtio_gpu_driver_open(struct drm_device *dev, struct drm_file *file) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; + struct virtio_gpu_fpriv *vfpriv; + int handle; + + /* can't create contexts without 3d renderer */ + if (!vgdev->has_virgl_3d) + return 0; + + /* allocate a virt GPU context for this opener */ + vfpriv = kzalloc(sizeof(*vfpriv), GFP_KERNEL); + if (!vfpriv) + return -ENOMEM; + + mutex_init(&vfpriv->context_lock); + + handle = ida_alloc(&vgdev->ctx_id_ida, GFP_KERNEL); + if (handle < 0) { + kfree(vfpriv); + return handle; + } + + vfpriv->ctx_id = handle + 1; + file->driver_priv = vfpriv; + return 0; +} + +void virtio_gpu_driver_postclose(struct drm_device *dev, struct drm_file *file) +{ + struct virtio_gpu_device *vgdev = dev->dev_private; + struct virtio_gpu_fpriv *vfpriv = file->driver_priv; + + if (!vgdev->has_virgl_3d) + return; + + if (vfpriv->context_created) { + virtio_gpu_cmd_context_destroy(vgdev, vfpriv->ctx_id); + virtio_gpu_notify(vgdev); + } + + ida_free(&vgdev->ctx_id_ida, vfpriv->ctx_id - 1); + mutex_destroy(&vfpriv->context_lock); + kfree(vfpriv); + file->driver_priv = NULL; +} -- cgit v1.2.3