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_object.c | 249 ++++++++++++++++++++++++++++++++ 1 file changed, 249 insertions(+) create mode 100644 drivers/gpu/drm/virtio/virtgpu_object.c (limited to 'drivers/gpu/drm/virtio/virtgpu_object.c') diff --git a/drivers/gpu/drm/virtio/virtgpu_object.c b/drivers/gpu/drm/virtio/virtgpu_object.c new file mode 100644 index 000000000..c7e74cf13 --- /dev/null +++ b/drivers/gpu/drm/virtio/virtgpu_object.c @@ -0,0 +1,249 @@ +/* + * 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 "virtgpu_drv.h" + +static int virtio_gpu_virglrenderer_workaround = 1; +module_param_named(virglhack, virtio_gpu_virglrenderer_workaround, int, 0400); + +int virtio_gpu_resource_id_get(struct virtio_gpu_device *vgdev, uint32_t *resid) +{ + if (virtio_gpu_virglrenderer_workaround) { + /* + * Hack to avoid re-using resource IDs. + * + * virglrenderer versions up to (and including) 0.7.0 + * can't deal with that. virglrenderer commit + * "f91a9dd35715 Fix unlinking resources from hash + * table." (Feb 2019) fixes the bug. + */ + static atomic_t seqno = ATOMIC_INIT(0); + int handle = atomic_inc_return(&seqno); + *resid = handle + 1; + } else { + int handle = ida_alloc(&vgdev->resource_ida, GFP_KERNEL); + if (handle < 0) + return handle; + *resid = handle + 1; + } + return 0; +} + +static void virtio_gpu_resource_id_put(struct virtio_gpu_device *vgdev, uint32_t id) +{ + if (!virtio_gpu_virglrenderer_workaround) { + ida_free(&vgdev->resource_ida, id - 1); + } +} + +void virtio_gpu_cleanup_object(struct virtio_gpu_object *bo) +{ + struct virtio_gpu_device *vgdev = bo->base.base.dev->dev_private; + + virtio_gpu_resource_id_put(vgdev, bo->hw_res_handle); + if (virtio_gpu_is_shmem(bo)) { + drm_gem_shmem_free(&bo->base); + } else if (virtio_gpu_is_vram(bo)) { + struct virtio_gpu_object_vram *vram = to_virtio_gpu_vram(bo); + + spin_lock(&vgdev->host_visible_lock); + if (drm_mm_node_allocated(&vram->vram_node)) + drm_mm_remove_node(&vram->vram_node); + + spin_unlock(&vgdev->host_visible_lock); + + drm_gem_free_mmap_offset(&vram->base.base.base); + drm_gem_object_release(&vram->base.base.base); + kfree(vram); + } +} + +static void virtio_gpu_free_object(struct drm_gem_object *obj) +{ + struct virtio_gpu_object *bo = gem_to_virtio_gpu_obj(obj); + struct virtio_gpu_device *vgdev = bo->base.base.dev->dev_private; + + if (bo->created) { + virtio_gpu_cmd_unref_resource(vgdev, bo); + virtio_gpu_notify(vgdev); + /* completion handler calls virtio_gpu_cleanup_object() */ + return; + } + virtio_gpu_cleanup_object(bo); +} + +static const struct drm_gem_object_funcs virtio_gpu_shmem_funcs = { + .free = virtio_gpu_free_object, + .open = virtio_gpu_gem_object_open, + .close = virtio_gpu_gem_object_close, + .print_info = drm_gem_shmem_object_print_info, + .export = virtgpu_gem_prime_export, + .pin = drm_gem_shmem_object_pin, + .unpin = drm_gem_shmem_object_unpin, + .get_sg_table = drm_gem_shmem_object_get_sg_table, + .vmap = drm_gem_shmem_object_vmap, + .vunmap = drm_gem_shmem_object_vunmap, + .mmap = drm_gem_shmem_object_mmap, + .vm_ops = &drm_gem_shmem_vm_ops, +}; + +bool virtio_gpu_is_shmem(struct virtio_gpu_object *bo) +{ + return bo->base.base.funcs == &virtio_gpu_shmem_funcs; +} + +struct drm_gem_object *virtio_gpu_create_object(struct drm_device *dev, + size_t size) +{ + struct virtio_gpu_object_shmem *shmem; + struct drm_gem_shmem_object *dshmem; + + shmem = kzalloc(sizeof(*shmem), GFP_KERNEL); + if (!shmem) + return ERR_PTR(-ENOMEM); + + dshmem = &shmem->base.base; + dshmem->base.funcs = &virtio_gpu_shmem_funcs; + return &dshmem->base; +} + +static int virtio_gpu_object_shmem_init(struct virtio_gpu_device *vgdev, + struct virtio_gpu_object *bo, + struct virtio_gpu_mem_entry **ents, + unsigned int *nents) +{ + bool use_dma_api = !virtio_has_dma_quirk(vgdev->vdev); + struct scatterlist *sg; + struct sg_table *pages; + int si; + + pages = drm_gem_shmem_get_pages_sgt(&bo->base); + if (IS_ERR(pages)) + return PTR_ERR(pages); + + if (use_dma_api) + *nents = pages->nents; + else + *nents = pages->orig_nents; + + *ents = kvmalloc_array(*nents, + sizeof(struct virtio_gpu_mem_entry), + GFP_KERNEL); + if (!(*ents)) { + DRM_ERROR("failed to allocate ent list\n"); + return -ENOMEM; + } + + if (use_dma_api) { + for_each_sgtable_dma_sg(pages, sg, si) { + (*ents)[si].addr = cpu_to_le64(sg_dma_address(sg)); + (*ents)[si].length = cpu_to_le32(sg_dma_len(sg)); + (*ents)[si].padding = 0; + } + } else { + for_each_sgtable_sg(pages, sg, si) { + (*ents)[si].addr = cpu_to_le64(sg_phys(sg)); + (*ents)[si].length = cpu_to_le32(sg->length); + (*ents)[si].padding = 0; + } + } + + return 0; +} + +int virtio_gpu_object_create(struct virtio_gpu_device *vgdev, + struct virtio_gpu_object_params *params, + struct virtio_gpu_object **bo_ptr, + struct virtio_gpu_fence *fence) +{ + struct virtio_gpu_object_array *objs = NULL; + struct drm_gem_shmem_object *shmem_obj; + struct virtio_gpu_object *bo; + struct virtio_gpu_mem_entry *ents = NULL; + unsigned int nents; + int ret; + + *bo_ptr = NULL; + + params->size = roundup(params->size, PAGE_SIZE); + shmem_obj = drm_gem_shmem_create(vgdev->ddev, params->size); + if (IS_ERR(shmem_obj)) + return PTR_ERR(shmem_obj); + bo = gem_to_virtio_gpu_obj(&shmem_obj->base); + + ret = virtio_gpu_resource_id_get(vgdev, &bo->hw_res_handle); + if (ret < 0) + goto err_free_gem; + + bo->dumb = params->dumb; + + ret = virtio_gpu_object_shmem_init(vgdev, bo, &ents, &nents); + if (ret != 0) + goto err_put_id; + + if (fence) { + ret = -ENOMEM; + objs = virtio_gpu_array_alloc(1); + if (!objs) + goto err_free_entry; + virtio_gpu_array_add_obj(objs, &bo->base.base); + + ret = virtio_gpu_array_lock_resv(objs); + if (ret != 0) + goto err_put_objs; + } + + if (params->blob) { + if (params->blob_mem == VIRTGPU_BLOB_MEM_GUEST) + bo->guest_blob = true; + + virtio_gpu_cmd_resource_create_blob(vgdev, bo, params, + ents, nents); + } else if (params->virgl) { + virtio_gpu_cmd_resource_create_3d(vgdev, bo, params, + objs, fence); + virtio_gpu_object_attach(vgdev, bo, ents, nents); + } else { + virtio_gpu_cmd_create_resource(vgdev, bo, params, + objs, fence); + virtio_gpu_object_attach(vgdev, bo, ents, nents); + } + + *bo_ptr = bo; + return 0; + +err_put_objs: + virtio_gpu_array_put_free(objs); +err_free_entry: + kvfree(ents); +err_put_id: + virtio_gpu_resource_id_put(vgdev, bo->hw_res_handle); +err_free_gem: + drm_gem_shmem_free(shmem_obj); + return ret; +} -- cgit v1.2.3