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/amd/amdgpu/amdgpu_job.c | 344 ++++++++++++++++++++++++++++++++ 1 file changed, 344 insertions(+) create mode 100644 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c (limited to 'drivers/gpu/drm/amd/amdgpu/amdgpu_job.c') diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c new file mode 100644 index 000000000..c3d9d7514 --- /dev/null +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c @@ -0,0 +1,344 @@ +/* + * Copyright 2015 Advanced Micro Devices, 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 + * 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 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 HOLDER(S) OR AUTHOR(S) 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 "amdgpu.h" +#include "amdgpu_trace.h" +#include "amdgpu_reset.h" + +static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job) +{ + struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched); + struct amdgpu_job *job = to_amdgpu_job(s_job); + struct amdgpu_task_info ti; + struct amdgpu_device *adev = ring->adev; + int idx; + int r; + + if (!drm_dev_enter(adev_to_drm(adev), &idx)) { + DRM_INFO("%s - device unplugged skipping recovery on scheduler:%s", + __func__, s_job->sched->name); + + /* Effectively the job is aborted as the device is gone */ + return DRM_GPU_SCHED_STAT_ENODEV; + } + + memset(&ti, 0, sizeof(struct amdgpu_task_info)); + adev->job_hang = true; + + if (amdgpu_gpu_recovery && + amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) { + DRM_ERROR("ring %s timeout, but soft recovered\n", + s_job->sched->name); + goto exit; + } + + amdgpu_vm_get_task_info(ring->adev, job->pasid, &ti); + DRM_ERROR("ring %s timeout, signaled seq=%u, emitted seq=%u\n", + job->base.sched->name, atomic_read(&ring->fence_drv.last_seq), + ring->fence_drv.sync_seq); + DRM_ERROR("Process information: process %s pid %d thread %s pid %d\n", + ti.process_name, ti.tgid, ti.task_name, ti.pid); + + if (amdgpu_device_should_recover_gpu(ring->adev)) { + struct amdgpu_reset_context reset_context; + memset(&reset_context, 0, sizeof(reset_context)); + + reset_context.method = AMD_RESET_METHOD_NONE; + reset_context.reset_req_dev = adev; + clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags); + + r = amdgpu_device_gpu_recover(ring->adev, job, &reset_context); + if (r) + DRM_ERROR("GPU Recovery Failed: %d\n", r); + } else { + drm_sched_suspend_timeout(&ring->sched); + if (amdgpu_sriov_vf(adev)) + adev->virt.tdr_debug = true; + } + +exit: + adev->job_hang = false; + drm_dev_exit(idx); + return DRM_GPU_SCHED_STAT_NOMINAL; +} + +int amdgpu_job_alloc(struct amdgpu_device *adev, struct amdgpu_vm *vm, + struct drm_sched_entity *entity, void *owner, + unsigned int num_ibs, struct amdgpu_job **job) +{ + if (num_ibs == 0) + return -EINVAL; + + *job = kzalloc(struct_size(*job, ibs, num_ibs), GFP_KERNEL); + if (!*job) + return -ENOMEM; + + /* + * Initialize the scheduler to at least some ring so that we always + * have a pointer to adev. + */ + (*job)->base.sched = &adev->rings[0]->sched; + (*job)->vm = vm; + + amdgpu_sync_create(&(*job)->explicit_sync); + (*job)->vram_lost_counter = atomic_read(&adev->vram_lost_counter); + (*job)->vm_pd_addr = AMDGPU_BO_INVALID_OFFSET; + + if (!entity) + return 0; + + return drm_sched_job_init(&(*job)->base, entity, owner); +} + +int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, + struct drm_sched_entity *entity, void *owner, + size_t size, enum amdgpu_ib_pool_type pool_type, + struct amdgpu_job **job) +{ + int r; + + r = amdgpu_job_alloc(adev, NULL, entity, owner, 1, job); + if (r) + return r; + + (*job)->num_ibs = 1; + r = amdgpu_ib_get(adev, NULL, size, pool_type, &(*job)->ibs[0]); + if (r) { + if (entity) + drm_sched_job_cleanup(&(*job)->base); + kfree(*job); + } + + return r; +} + +void amdgpu_job_set_resources(struct amdgpu_job *job, struct amdgpu_bo *gds, + struct amdgpu_bo *gws, struct amdgpu_bo *oa) +{ + if (gds) { + job->gds_base = amdgpu_bo_gpu_offset(gds) >> PAGE_SHIFT; + job->gds_size = amdgpu_bo_size(gds) >> PAGE_SHIFT; + } + if (gws) { + job->gws_base = amdgpu_bo_gpu_offset(gws) >> PAGE_SHIFT; + job->gws_size = amdgpu_bo_size(gws) >> PAGE_SHIFT; + } + if (oa) { + job->oa_base = amdgpu_bo_gpu_offset(oa) >> PAGE_SHIFT; + job->oa_size = amdgpu_bo_size(oa) >> PAGE_SHIFT; + } +} + +void amdgpu_job_free_resources(struct amdgpu_job *job) +{ + struct amdgpu_ring *ring = to_amdgpu_ring(job->base.sched); + struct dma_fence *f; + unsigned i; + + /* Check if any fences where initialized */ + if (job->base.s_fence && job->base.s_fence->finished.ops) + f = &job->base.s_fence->finished; + else if (job->hw_fence.ops) + f = &job->hw_fence; + else + f = NULL; + + for (i = 0; i < job->num_ibs; ++i) + amdgpu_ib_free(ring->adev, &job->ibs[i], f); +} + +static void amdgpu_job_free_cb(struct drm_sched_job *s_job) +{ + struct amdgpu_job *job = to_amdgpu_job(s_job); + + drm_sched_job_cleanup(s_job); + + amdgpu_sync_free(&job->explicit_sync); + + /* only put the hw fence if has embedded fence */ + if (!job->hw_fence.ops) + kfree(job); + else + dma_fence_put(&job->hw_fence); +} + +void amdgpu_job_set_gang_leader(struct amdgpu_job *job, + struct amdgpu_job *leader) +{ + struct dma_fence *fence = &leader->base.s_fence->scheduled; + + WARN_ON(job->gang_submit); + + /* + * Don't add a reference when we are the gang leader to avoid circle + * dependency. + */ + if (job != leader) + dma_fence_get(fence); + job->gang_submit = fence; +} + +void amdgpu_job_free(struct amdgpu_job *job) +{ + if (job->base.entity) + drm_sched_job_cleanup(&job->base); + + amdgpu_job_free_resources(job); + amdgpu_sync_free(&job->explicit_sync); + if (job->gang_submit != &job->base.s_fence->scheduled) + dma_fence_put(job->gang_submit); + + if (!job->hw_fence.ops) + kfree(job); + else + dma_fence_put(&job->hw_fence); +} + +struct dma_fence *amdgpu_job_submit(struct amdgpu_job *job) +{ + struct dma_fence *f; + + drm_sched_job_arm(&job->base); + f = dma_fence_get(&job->base.s_fence->finished); + amdgpu_job_free_resources(job); + drm_sched_entity_push_job(&job->base); + + return f; +} + +int amdgpu_job_submit_direct(struct amdgpu_job *job, struct amdgpu_ring *ring, + struct dma_fence **fence) +{ + int r; + + job->base.sched = &ring->sched; + r = amdgpu_ib_schedule(ring, job->num_ibs, job->ibs, job, fence); + + if (r) + return r; + + amdgpu_job_free(job); + return 0; +} + +static struct dma_fence * +amdgpu_job_prepare_job(struct drm_sched_job *sched_job, + struct drm_sched_entity *s_entity) +{ + struct amdgpu_ring *ring = to_amdgpu_ring(s_entity->rq->sched); + struct amdgpu_job *job = to_amdgpu_job(sched_job); + struct dma_fence *fence = NULL; + int r; + + if (!fence && job->gang_submit) + fence = amdgpu_device_switch_gang(ring->adev, job->gang_submit); + + while (!fence && job->vm && !job->vmid) { + r = amdgpu_vmid_grab(job->vm, ring, job, &fence); + if (r) + DRM_ERROR("Error getting VM ID (%d)\n", r); + } + + return fence; +} + +static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job) +{ + struct amdgpu_ring *ring = to_amdgpu_ring(sched_job->sched); + struct amdgpu_device *adev = ring->adev; + struct dma_fence *fence = NULL, *finished; + struct amdgpu_job *job; + int r = 0; + + job = to_amdgpu_job(sched_job); + finished = &job->base.s_fence->finished; + + trace_amdgpu_sched_run_job(job); + + /* Skip job if VRAM is lost and never resubmit gangs */ + if (job->vram_lost_counter != atomic_read(&adev->vram_lost_counter) || + (job->job_run_counter && job->gang_submit)) + dma_fence_set_error(finished, -ECANCELED); + + if (finished->error < 0) { + DRM_INFO("Skip scheduling IBs!\n"); + } else { + r = amdgpu_ib_schedule(ring, job->num_ibs, job->ibs, job, + &fence); + if (r) + DRM_ERROR("Error scheduling IBs (%d)\n", r); + } + + job->job_run_counter++; + amdgpu_job_free_resources(job); + + fence = r ? ERR_PTR(r) : fence; + return fence; +} + +#define to_drm_sched_job(sched_job) \ + container_of((sched_job), struct drm_sched_job, queue_node) + +void amdgpu_job_stop_all_jobs_on_sched(struct drm_gpu_scheduler *sched) +{ + struct drm_sched_job *s_job; + struct drm_sched_entity *s_entity = NULL; + int i; + + /* Signal all jobs not yet scheduled */ + for (i = DRM_SCHED_PRIORITY_COUNT - 1; i >= DRM_SCHED_PRIORITY_MIN; i--) { + struct drm_sched_rq *rq = &sched->sched_rq[i]; + spin_lock(&rq->lock); + list_for_each_entry(s_entity, &rq->entities, list) { + while ((s_job = to_drm_sched_job(spsc_queue_pop(&s_entity->job_queue)))) { + struct drm_sched_fence *s_fence = s_job->s_fence; + + dma_fence_signal(&s_fence->scheduled); + dma_fence_set_error(&s_fence->finished, -EHWPOISON); + dma_fence_signal(&s_fence->finished); + } + } + spin_unlock(&rq->lock); + } + + /* Signal all jobs already scheduled to HW */ + list_for_each_entry(s_job, &sched->pending_list, list) { + struct drm_sched_fence *s_fence = s_job->s_fence; + + dma_fence_set_error(&s_fence->finished, -EHWPOISON); + dma_fence_signal(&s_fence->finished); + } +} + +const struct drm_sched_backend_ops amdgpu_sched_ops = { + .prepare_job = amdgpu_job_prepare_job, + .run_job = amdgpu_job_run, + .timedout_job = amdgpu_job_timedout, + .free_job = amdgpu_job_free_cb +}; -- cgit v1.2.3