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_release.c | 439 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 439 insertions(+) create mode 100644 drivers/gpu/drm/qxl/qxl_release.c (limited to 'drivers/gpu/drm/qxl/qxl_release.c') diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c new file mode 100644 index 000000000..368d26da0 --- /dev/null +++ b/drivers/gpu/drm/qxl/qxl_release.c @@ -0,0 +1,439 @@ +/* + * 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 "qxl_drv.h" +#include "qxl_object.h" + +/* + * drawable cmd cache - allocate a bunch of VRAM pages, suballocate + * into 256 byte chunks for now - gives 16 cmds per page. + * + * use an ida to index into the chunks? + */ +/* manage releaseables */ +/* stack them 16 high for now -drawable object is 191 */ +#define RELEASE_SIZE 256 +#define RELEASES_PER_BO (PAGE_SIZE / RELEASE_SIZE) +/* put an alloc/dealloc surface cmd into one bo and round up to 128 */ +#define SURFACE_RELEASE_SIZE 128 +#define SURFACE_RELEASES_PER_BO (PAGE_SIZE / SURFACE_RELEASE_SIZE) + +static const int release_size_per_bo[] = { RELEASE_SIZE, SURFACE_RELEASE_SIZE, RELEASE_SIZE }; +static const int releases_per_bo[] = { RELEASES_PER_BO, SURFACE_RELEASES_PER_BO, RELEASES_PER_BO }; + +static const char *qxl_get_driver_name(struct dma_fence *fence) +{ + return "qxl"; +} + +static const char *qxl_get_timeline_name(struct dma_fence *fence) +{ + return "release"; +} + +static long qxl_fence_wait(struct dma_fence *fence, bool intr, + signed long timeout) +{ + struct qxl_device *qdev; + unsigned long cur, end = jiffies + timeout; + + qdev = container_of(fence->lock, struct qxl_device, release_lock); + + if (!wait_event_timeout(qdev->release_event, + (dma_fence_is_signaled(fence) || + (qxl_io_notify_oom(qdev), 0)), + timeout)) + return 0; + + cur = jiffies; + if (time_after(cur, end)) + return 0; + return end - cur; +} + +static const struct dma_fence_ops qxl_fence_ops = { + .get_driver_name = qxl_get_driver_name, + .get_timeline_name = qxl_get_timeline_name, + .wait = qxl_fence_wait, +}; + +static int +qxl_release_alloc(struct qxl_device *qdev, int type, + struct qxl_release **ret) +{ + struct qxl_release *release; + int handle; + size_t size = sizeof(*release); + + release = kmalloc(size, GFP_KERNEL); + if (!release) { + DRM_ERROR("Out of memory\n"); + return -ENOMEM; + } + release->base.ops = NULL; + release->type = type; + release->release_offset = 0; + release->surface_release_id = 0; + INIT_LIST_HEAD(&release->bos); + + idr_preload(GFP_KERNEL); + spin_lock(&qdev->release_idr_lock); + handle = idr_alloc(&qdev->release_idr, release, 1, 0, GFP_NOWAIT); + release->base.seqno = ++qdev->release_seqno; + spin_unlock(&qdev->release_idr_lock); + idr_preload_end(); + if (handle < 0) { + kfree(release); + *ret = NULL; + return handle; + } + *ret = release; + DRM_DEBUG_DRIVER("allocated release %d\n", handle); + release->id = handle; + return handle; +} + +static void +qxl_release_free_list(struct qxl_release *release) +{ + while (!list_empty(&release->bos)) { + struct qxl_bo_list *entry; + struct qxl_bo *bo; + + entry = container_of(release->bos.next, + struct qxl_bo_list, tv.head); + bo = to_qxl_bo(entry->tv.bo); + qxl_bo_unref(&bo); + list_del(&entry->tv.head); + kfree(entry); + } + release->release_bo = NULL; +} + +void +qxl_release_free(struct qxl_device *qdev, + struct qxl_release *release) +{ + DRM_DEBUG_DRIVER("release %d, type %d\n", release->id, release->type); + + if (release->surface_release_id) + qxl_surface_id_dealloc(qdev, release->surface_release_id); + + spin_lock(&qdev->release_idr_lock); + idr_remove(&qdev->release_idr, release->id); + spin_unlock(&qdev->release_idr_lock); + + if (release->base.ops) { + WARN_ON(list_empty(&release->bos)); + qxl_release_free_list(release); + + dma_fence_signal(&release->base); + dma_fence_put(&release->base); + } else { + qxl_release_free_list(release); + kfree(release); + } + atomic_dec(&qdev->release_count); +} + +static int qxl_release_bo_alloc(struct qxl_device *qdev, + struct qxl_bo **bo, + u32 priority) +{ + /* pin releases bo's they are too messy to evict */ + return qxl_bo_create(qdev, PAGE_SIZE, false, true, + QXL_GEM_DOMAIN_VRAM, priority, NULL, bo); +} + +int qxl_release_list_add(struct qxl_release *release, struct qxl_bo *bo) +{ + struct qxl_bo_list *entry; + + list_for_each_entry(entry, &release->bos, tv.head) { + if (entry->tv.bo == &bo->tbo) + return 0; + } + + entry = kmalloc(sizeof(struct qxl_bo_list), GFP_KERNEL); + if (!entry) + return -ENOMEM; + + qxl_bo_ref(bo); + entry->tv.bo = &bo->tbo; + entry->tv.num_shared = 0; + list_add_tail(&entry->tv.head, &release->bos); + return 0; +} + +static int qxl_release_validate_bo(struct qxl_bo *bo) +{ + struct ttm_operation_ctx ctx = { true, false }; + int ret; + + if (!bo->tbo.pin_count) { + qxl_ttm_placement_from_domain(bo, bo->type); + ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx); + if (ret) + return ret; + } + + ret = dma_resv_reserve_fences(bo->tbo.base.resv, 1); + if (ret) + return ret; + + /* allocate a surface for reserved + validated buffers */ + ret = qxl_bo_check_id(to_qxl(bo->tbo.base.dev), bo); + if (ret) + return ret; + return 0; +} + +int qxl_release_reserve_list(struct qxl_release *release, bool no_intr) +{ + int ret; + struct qxl_bo_list *entry; + + /* if only one object on the release its the release itself + since these objects are pinned no need to reserve */ + if (list_is_singular(&release->bos)) + return 0; + + ret = ttm_eu_reserve_buffers(&release->ticket, &release->bos, + !no_intr, NULL); + if (ret) + return ret; + + list_for_each_entry(entry, &release->bos, tv.head) { + struct qxl_bo *bo = to_qxl_bo(entry->tv.bo); + + ret = qxl_release_validate_bo(bo); + if (ret) { + ttm_eu_backoff_reservation(&release->ticket, &release->bos); + return ret; + } + } + return 0; +} + +void qxl_release_backoff_reserve_list(struct qxl_release *release) +{ + /* if only one object on the release its the release itself + since these objects are pinned no need to reserve */ + if (list_is_singular(&release->bos)) + return; + + ttm_eu_backoff_reservation(&release->ticket, &release->bos); +} + +int qxl_alloc_surface_release_reserved(struct qxl_device *qdev, + enum qxl_surface_cmd_type surface_cmd_type, + struct qxl_release *create_rel, + struct qxl_release **release) +{ + if (surface_cmd_type == QXL_SURFACE_CMD_DESTROY && create_rel) { + int idr_ret; + struct qxl_bo *bo; + union qxl_release_info *info; + + /* stash the release after the create command */ + idr_ret = qxl_release_alloc(qdev, QXL_RELEASE_SURFACE_CMD, release); + if (idr_ret < 0) + return idr_ret; + bo = create_rel->release_bo; + + (*release)->release_bo = bo; + (*release)->release_offset = create_rel->release_offset + 64; + + qxl_release_list_add(*release, bo); + + info = qxl_release_map(qdev, *release); + info->id = idr_ret; + qxl_release_unmap(qdev, *release, info); + return 0; + } + + return qxl_alloc_release_reserved(qdev, sizeof(struct qxl_surface_cmd), + QXL_RELEASE_SURFACE_CMD, release, NULL); +} + +int qxl_alloc_release_reserved(struct qxl_device *qdev, unsigned long size, + int type, struct qxl_release **release, + struct qxl_bo **rbo) +{ + struct qxl_bo *bo, *free_bo = NULL; + int idr_ret; + int ret = 0; + union qxl_release_info *info; + int cur_idx; + u32 priority; + + if (type == QXL_RELEASE_DRAWABLE) { + cur_idx = 0; + priority = 0; + } else if (type == QXL_RELEASE_SURFACE_CMD) { + cur_idx = 1; + priority = 1; + } else if (type == QXL_RELEASE_CURSOR_CMD) { + cur_idx = 2; + priority = 1; + } + else { + DRM_ERROR("got illegal type: %d\n", type); + return -EINVAL; + } + + idr_ret = qxl_release_alloc(qdev, type, release); + if (idr_ret < 0) { + if (rbo) + *rbo = NULL; + return idr_ret; + } + atomic_inc(&qdev->release_count); + + mutex_lock(&qdev->release_mutex); + if (qdev->current_release_bo_offset[cur_idx] + 1 >= releases_per_bo[cur_idx]) { + free_bo = qdev->current_release_bo[cur_idx]; + qdev->current_release_bo_offset[cur_idx] = 0; + qdev->current_release_bo[cur_idx] = NULL; + } + if (!qdev->current_release_bo[cur_idx]) { + ret = qxl_release_bo_alloc(qdev, &qdev->current_release_bo[cur_idx], priority); + if (ret) { + mutex_unlock(&qdev->release_mutex); + if (free_bo) { + qxl_bo_unpin(free_bo); + qxl_bo_unref(&free_bo); + } + qxl_release_free(qdev, *release); + return ret; + } + } + + bo = qxl_bo_ref(qdev->current_release_bo[cur_idx]); + + (*release)->release_bo = bo; + (*release)->release_offset = qdev->current_release_bo_offset[cur_idx] * release_size_per_bo[cur_idx]; + qdev->current_release_bo_offset[cur_idx]++; + + if (rbo) + *rbo = bo; + + mutex_unlock(&qdev->release_mutex); + if (free_bo) { + qxl_bo_unpin(free_bo); + qxl_bo_unref(&free_bo); + } + + ret = qxl_release_list_add(*release, bo); + qxl_bo_unref(&bo); + if (ret) { + qxl_release_free(qdev, *release); + return ret; + } + + info = qxl_release_map(qdev, *release); + info->id = idr_ret; + qxl_release_unmap(qdev, *release, info); + + return ret; +} + +struct qxl_release *qxl_release_from_id_locked(struct qxl_device *qdev, + uint64_t id) +{ + struct qxl_release *release; + + spin_lock(&qdev->release_idr_lock); + release = idr_find(&qdev->release_idr, id); + spin_unlock(&qdev->release_idr_lock); + if (!release) { + DRM_ERROR("failed to find id in release_idr\n"); + return NULL; + } + + return release; +} + +union qxl_release_info *qxl_release_map(struct qxl_device *qdev, + struct qxl_release *release) +{ + void *ptr; + union qxl_release_info *info; + struct qxl_bo *bo = release->release_bo; + + ptr = qxl_bo_kmap_atomic_page(qdev, bo, release->release_offset & PAGE_MASK); + if (!ptr) + return NULL; + info = ptr + (release->release_offset & ~PAGE_MASK); + return info; +} + +void qxl_release_unmap(struct qxl_device *qdev, + struct qxl_release *release, + union qxl_release_info *info) +{ + struct qxl_bo *bo = release->release_bo; + void *ptr; + + ptr = ((void *)info) - (release->release_offset & ~PAGE_MASK); + qxl_bo_kunmap_atomic_page(qdev, bo, ptr); +} + +void qxl_release_fence_buffer_objects(struct qxl_release *release) +{ + struct ttm_buffer_object *bo; + struct ttm_device *bdev; + struct ttm_validate_buffer *entry; + struct qxl_device *qdev; + + /* if only one object on the release its the release itself + since these objects are pinned no need to reserve */ + if (list_is_singular(&release->bos) || list_empty(&release->bos)) + return; + + bo = list_first_entry(&release->bos, struct ttm_validate_buffer, head)->bo; + bdev = bo->bdev; + qdev = container_of(bdev, struct qxl_device, mman.bdev); + + /* + * Since we never really allocated a context and we don't want to conflict, + * set the highest bits. This will break if we really allow exporting of dma-bufs. + */ + dma_fence_init(&release->base, &qxl_fence_ops, &qdev->release_lock, + release->id | 0xf0000000, release->base.seqno); + trace_dma_fence_emit(&release->base); + + list_for_each_entry(entry, &release->bos, head) { + bo = entry->bo; + + dma_resv_add_fence(bo->base.resv, &release->base, + DMA_RESV_USAGE_READ); + ttm_bo_move_to_lru_tail_unlocked(bo); + dma_resv_unlock(bo->base.resv); + } + ww_acquire_fini(&release->ticket); +} + -- cgit v1.2.3