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/qxl/qxl_draw.c | 268 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 268 insertions(+) create mode 100644 drivers/gpu/drm/qxl/qxl_draw.c (limited to 'drivers/gpu/drm/qxl/qxl_draw.c') diff --git a/drivers/gpu/drm/qxl/qxl_draw.c b/drivers/gpu/drm/qxl/qxl_draw.c new file mode 100644 index 000000000..3a3e127ce --- /dev/null +++ b/drivers/gpu/drm/qxl/qxl_draw.c @@ -0,0 +1,268 @@ +/* + * Copyright 2011 Red Hat, Inc. + * + * 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 + * on the rights to use, copy, modify, merge, publish, distribute, sub + * license, 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 NON-INFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS 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 "qxl_drv.h" +#include "qxl_object.h" + +static int alloc_clips(struct qxl_device *qdev, + struct qxl_release *release, + unsigned int num_clips, + struct qxl_bo **clips_bo) +{ + int size = sizeof(struct qxl_clip_rects) + sizeof(struct qxl_rect) * num_clips; + + return qxl_alloc_bo_reserved(qdev, release, size, clips_bo); +} + +/* returns a pointer to the already allocated qxl_rect array inside + * the qxl_clip_rects. This is *not* the same as the memory allocated + * on the device, it is offset to qxl_clip_rects.chunk.data */ +static struct qxl_rect *drawable_set_clipping(struct qxl_device *qdev, + unsigned int num_clips, + struct qxl_bo *clips_bo) +{ + struct iosys_map map; + struct qxl_clip_rects *dev_clips; + int ret; + + ret = qxl_bo_vmap_locked(clips_bo, &map); + if (ret) + return NULL; + dev_clips = map.vaddr; /* TODO: Use mapping abstraction properly */ + + dev_clips->num_rects = num_clips; + dev_clips->chunk.next_chunk = 0; + dev_clips->chunk.prev_chunk = 0; + dev_clips->chunk.data_size = sizeof(struct qxl_rect) * num_clips; + return (struct qxl_rect *)dev_clips->chunk.data; +} + +static int +alloc_drawable(struct qxl_device *qdev, struct qxl_release **release) +{ + return qxl_alloc_release_reserved(qdev, sizeof(struct qxl_drawable), + QXL_RELEASE_DRAWABLE, release, NULL); +} + +static void +free_drawable(struct qxl_device *qdev, struct qxl_release *release) +{ + qxl_release_free(qdev, release); +} + +/* release needs to be reserved at this point */ +static int +make_drawable(struct qxl_device *qdev, int surface, uint8_t type, + const struct qxl_rect *rect, + struct qxl_release *release) +{ + struct qxl_drawable *drawable; + int i; + + drawable = (struct qxl_drawable *)qxl_release_map(qdev, release); + if (!drawable) + return -ENOMEM; + + drawable->type = type; + + drawable->surface_id = surface; /* Only primary for now */ + drawable->effect = QXL_EFFECT_OPAQUE; + drawable->self_bitmap = 0; + drawable->self_bitmap_area.top = 0; + drawable->self_bitmap_area.left = 0; + drawable->self_bitmap_area.bottom = 0; + drawable->self_bitmap_area.right = 0; + /* FIXME: add clipping */ + drawable->clip.type = SPICE_CLIP_TYPE_NONE; + + /* + * surfaces_dest[i] should apparently be filled out with the + * surfaces that we depend on, and surface_rects should be + * filled with the rectangles of those surfaces that we + * are going to use. + */ + for (i = 0; i < 3; ++i) + drawable->surfaces_dest[i] = -1; + + if (rect) + drawable->bbox = *rect; + + drawable->mm_time = qdev->rom->mm_clock; + qxl_release_unmap(qdev, release, &drawable->release_info); + return 0; +} + +/* push a draw command using the given clipping rectangles as + * the sources from the shadow framebuffer. + * + * Right now implementing with a single draw and a clip list. Clip + * lists are known to be a problem performance wise, this can be solved + * by treating them differently in the server. + */ +void qxl_draw_dirty_fb(struct qxl_device *qdev, + struct drm_framebuffer *fb, + struct qxl_bo *bo, + unsigned int flags, unsigned int color, + struct drm_clip_rect *clips, + unsigned int num_clips, int inc, + uint32_t dumb_shadow_offset) +{ + /* + * TODO: if flags & DRM_MODE_FB_DIRTY_ANNOTATE_FILL then we should + * send a fill command instead, much cheaper. + * + * See include/drm/drm_mode.h + */ + struct drm_clip_rect *clips_ptr; + int i; + int left, right, top, bottom; + int width, height; + struct qxl_drawable *drawable; + struct qxl_rect drawable_rect; + struct qxl_rect *rects; + int stride = fb->pitches[0]; + /* depth is not actually interesting, we don't mask with it */ + int depth = fb->format->cpp[0] * 8; + struct iosys_map surface_map; + uint8_t *surface_base; + struct qxl_release *release; + struct qxl_bo *clips_bo; + struct qxl_drm_image *dimage; + int ret; + + ret = alloc_drawable(qdev, &release); + if (ret) + return; + + clips->x1 += dumb_shadow_offset; + clips->x2 += dumb_shadow_offset; + + left = clips->x1; + right = clips->x2; + top = clips->y1; + bottom = clips->y2; + + /* skip the first clip rect */ + for (i = 1, clips_ptr = clips + inc; + i < num_clips; i++, clips_ptr += inc) { + left = min_t(int, left, (int)clips_ptr->x1); + right = max_t(int, right, (int)clips_ptr->x2); + top = min_t(int, top, (int)clips_ptr->y1); + bottom = max_t(int, bottom, (int)clips_ptr->y2); + } + + width = right - left; + height = bottom - top; + + ret = alloc_clips(qdev, release, num_clips, &clips_bo); + if (ret) + goto out_free_drawable; + + ret = qxl_image_alloc_objects(qdev, release, + &dimage, + height, stride); + if (ret) + goto out_free_clips; + + /* do a reservation run over all the objects we just allocated */ + ret = qxl_release_reserve_list(release, true); + if (ret) + goto out_free_image; + + drawable_rect.left = left; + drawable_rect.right = right; + drawable_rect.top = top; + drawable_rect.bottom = bottom; + + ret = make_drawable(qdev, 0, QXL_DRAW_COPY, &drawable_rect, + release); + if (ret) + goto out_release_backoff; + + ret = qxl_bo_vmap_locked(bo, &surface_map); + if (ret) + goto out_release_backoff; + surface_base = surface_map.vaddr; /* TODO: Use mapping abstraction properly */ + + ret = qxl_image_init(qdev, release, dimage, surface_base, + left - dumb_shadow_offset, + top, width, height, depth, stride); + qxl_bo_vunmap_locked(bo); + if (ret) + goto out_release_backoff; + + rects = drawable_set_clipping(qdev, num_clips, clips_bo); + if (!rects) { + ret = -EINVAL; + goto out_release_backoff; + } + drawable = (struct qxl_drawable *)qxl_release_map(qdev, release); + + drawable->clip.type = SPICE_CLIP_TYPE_RECTS; + drawable->clip.data = qxl_bo_physical_address(qdev, + clips_bo, 0); + + drawable->u.copy.src_area.top = 0; + drawable->u.copy.src_area.bottom = height; + drawable->u.copy.src_area.left = 0; + drawable->u.copy.src_area.right = width; + + drawable->u.copy.rop_descriptor = SPICE_ROPD_OP_PUT; + drawable->u.copy.scale_mode = 0; + drawable->u.copy.mask.flags = 0; + drawable->u.copy.mask.pos.x = 0; + drawable->u.copy.mask.pos.y = 0; + drawable->u.copy.mask.bitmap = 0; + + drawable->u.copy.src_bitmap = qxl_bo_physical_address(qdev, dimage->bo, 0); + qxl_release_unmap(qdev, release, &drawable->release_info); + + clips_ptr = clips; + for (i = 0; i < num_clips; i++, clips_ptr += inc) { + rects[i].left = clips_ptr->x1; + rects[i].right = clips_ptr->x2; + rects[i].top = clips_ptr->y1; + rects[i].bottom = clips_ptr->y2; + } + qxl_bo_vunmap_locked(clips_bo); + + qxl_release_fence_buffer_objects(release); + qxl_push_command_ring_release(qdev, release, QXL_CMD_DRAW, false); + +out_release_backoff: + if (ret) + qxl_release_backoff_reserve_list(release); +out_free_image: + qxl_image_free_objects(qdev, dimage); +out_free_clips: + qxl_bo_unref(&clips_bo); +out_free_drawable: + /* only free drawable on error */ + if (ret) + free_drawable(qdev, release); + +} -- cgit v1.2.3