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/vc4/vc4_irq.c | 360 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 360 insertions(+) create mode 100644 drivers/gpu/drm/vc4/vc4_irq.c (limited to 'drivers/gpu/drm/vc4/vc4_irq.c') diff --git a/drivers/gpu/drm/vc4/vc4_irq.c b/drivers/gpu/drm/vc4/vc4_irq.c new file mode 100644 index 000000000..1e6db0121 --- /dev/null +++ b/drivers/gpu/drm/vc4/vc4_irq.c @@ -0,0 +1,360 @@ +/* + * Copyright © 2014 Broadcom + * + * 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 AUTHORS OR COPYRIGHT HOLDERS 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. + */ + +/** + * DOC: Interrupt management for the V3D engine + * + * We have an interrupt status register (V3D_INTCTL) which reports + * interrupts, and where writing 1 bits clears those interrupts. + * There are also a pair of interrupt registers + * (V3D_INTENA/V3D_INTDIS) where writing a 1 to their bits enables or + * disables that specific interrupt, and 0s written are ignored + * (reading either one returns the set of enabled interrupts). + * + * When we take a binning flush done interrupt, we need to submit the + * next frame for binning and move the finished frame to the render + * thread. + * + * When we take a render frame interrupt, we need to wake the + * processes waiting for some frame to be done, and get the next frame + * submitted ASAP (so the hardware doesn't sit idle when there's work + * to do). + * + * When we take the binner out of memory interrupt, we need to + * allocate some new memory and pass it to the binner so that the + * current job can make progress. + */ + +#include + +#include + +#include "vc4_drv.h" +#include "vc4_regs.h" +#include "vc4_trace.h" + +#define V3D_DRIVER_IRQS (V3D_INT_OUTOMEM | \ + V3D_INT_FLDONE | \ + V3D_INT_FRDONE) + +DECLARE_WAIT_QUEUE_HEAD(render_wait); + +static void +vc4_overflow_mem_work(struct work_struct *work) +{ + struct vc4_dev *vc4 = + container_of(work, struct vc4_dev, overflow_mem_work); + struct vc4_bo *bo; + int bin_bo_slot; + struct vc4_exec_info *exec; + unsigned long irqflags; + + mutex_lock(&vc4->bin_bo_lock); + + if (!vc4->bin_bo) + goto complete; + + bo = vc4->bin_bo; + + bin_bo_slot = vc4_v3d_get_bin_slot(vc4); + if (bin_bo_slot < 0) { + DRM_ERROR("Couldn't allocate binner overflow mem\n"); + goto complete; + } + + spin_lock_irqsave(&vc4->job_lock, irqflags); + + if (vc4->bin_alloc_overflow) { + /* If we had overflow memory allocated previously, + * then that chunk will free when the current bin job + * is done. If we don't have a bin job running, then + * the chunk will be done whenever the list of render + * jobs has drained. + */ + exec = vc4_first_bin_job(vc4); + if (!exec) + exec = vc4_last_render_job(vc4); + if (exec) { + exec->bin_slots |= vc4->bin_alloc_overflow; + } else { + /* There's nothing queued in the hardware, so + * the old slot is free immediately. + */ + vc4->bin_alloc_used &= ~vc4->bin_alloc_overflow; + } + } + vc4->bin_alloc_overflow = BIT(bin_bo_slot); + + V3D_WRITE(V3D_BPOA, bo->base.dma_addr + bin_bo_slot * vc4->bin_alloc_size); + V3D_WRITE(V3D_BPOS, bo->base.base.size); + V3D_WRITE(V3D_INTCTL, V3D_INT_OUTOMEM); + V3D_WRITE(V3D_INTENA, V3D_INT_OUTOMEM); + spin_unlock_irqrestore(&vc4->job_lock, irqflags); + +complete: + mutex_unlock(&vc4->bin_bo_lock); +} + +static void +vc4_irq_finish_bin_job(struct drm_device *dev) +{ + struct vc4_dev *vc4 = to_vc4_dev(dev); + struct vc4_exec_info *next, *exec = vc4_first_bin_job(vc4); + + if (!exec) + return; + + trace_vc4_bcl_end_irq(dev, exec->seqno); + + vc4_move_job_to_render(dev, exec); + next = vc4_first_bin_job(vc4); + + /* Only submit the next job in the bin list if it matches the perfmon + * attached to the one that just finished (or if both jobs don't have + * perfmon attached to them). + */ + if (next && next->perfmon == exec->perfmon) + vc4_submit_next_bin_job(dev); +} + +static void +vc4_cancel_bin_job(struct drm_device *dev) +{ + struct vc4_dev *vc4 = to_vc4_dev(dev); + struct vc4_exec_info *exec = vc4_first_bin_job(vc4); + + if (!exec) + return; + + /* Stop the perfmon so that the next bin job can be started. */ + if (exec->perfmon) + vc4_perfmon_stop(vc4, exec->perfmon, false); + + list_move_tail(&exec->head, &vc4->bin_job_list); + vc4_submit_next_bin_job(dev); +} + +static void +vc4_irq_finish_render_job(struct drm_device *dev) +{ + struct vc4_dev *vc4 = to_vc4_dev(dev); + struct vc4_exec_info *exec = vc4_first_render_job(vc4); + struct vc4_exec_info *nextbin, *nextrender; + + if (!exec) + return; + + trace_vc4_rcl_end_irq(dev, exec->seqno); + + vc4->finished_seqno++; + list_move_tail(&exec->head, &vc4->job_done_list); + + nextbin = vc4_first_bin_job(vc4); + nextrender = vc4_first_render_job(vc4); + + /* Only stop the perfmon if following jobs in the queue don't expect it + * to be enabled. + */ + if (exec->perfmon && !nextrender && + (!nextbin || nextbin->perfmon != exec->perfmon)) + vc4_perfmon_stop(vc4, exec->perfmon, true); + + /* If there's a render job waiting, start it. If this is not the case + * we may have to unblock the binner if it's been stalled because of + * perfmon (this can be checked by comparing the perfmon attached to + * the finished renderjob to the one attached to the next bin job: if + * they don't match, this means the binner is stalled and should be + * restarted). + */ + if (nextrender) + vc4_submit_next_render_job(dev); + else if (nextbin && nextbin->perfmon != exec->perfmon) + vc4_submit_next_bin_job(dev); + + if (exec->fence) { + dma_fence_signal_locked(exec->fence); + dma_fence_put(exec->fence); + exec->fence = NULL; + } + + wake_up_all(&vc4->job_wait_queue); + schedule_work(&vc4->job_done_work); +} + +static irqreturn_t +vc4_irq(int irq, void *arg) +{ + struct drm_device *dev = arg; + struct vc4_dev *vc4 = to_vc4_dev(dev); + uint32_t intctl; + irqreturn_t status = IRQ_NONE; + + barrier(); + intctl = V3D_READ(V3D_INTCTL); + + /* Acknowledge the interrupts we're handling here. The binner + * last flush / render frame done interrupt will be cleared, + * while OUTOMEM will stay high until the underlying cause is + * cleared. + */ + V3D_WRITE(V3D_INTCTL, intctl); + + if (intctl & V3D_INT_OUTOMEM) { + /* Disable OUTOMEM until the work is done. */ + V3D_WRITE(V3D_INTDIS, V3D_INT_OUTOMEM); + schedule_work(&vc4->overflow_mem_work); + status = IRQ_HANDLED; + } + + if (intctl & V3D_INT_FLDONE) { + spin_lock(&vc4->job_lock); + vc4_irq_finish_bin_job(dev); + spin_unlock(&vc4->job_lock); + status = IRQ_HANDLED; + } + + if (intctl & V3D_INT_FRDONE) { + spin_lock(&vc4->job_lock); + vc4_irq_finish_render_job(dev); + spin_unlock(&vc4->job_lock); + status = IRQ_HANDLED; + } + + return status; +} + +static void +vc4_irq_prepare(struct drm_device *dev) +{ + struct vc4_dev *vc4 = to_vc4_dev(dev); + + if (!vc4->v3d) + return; + + init_waitqueue_head(&vc4->job_wait_queue); + INIT_WORK(&vc4->overflow_mem_work, vc4_overflow_mem_work); + + /* Clear any pending interrupts someone might have left around + * for us. + */ + V3D_WRITE(V3D_INTCTL, V3D_DRIVER_IRQS); +} + +void +vc4_irq_enable(struct drm_device *dev) +{ + struct vc4_dev *vc4 = to_vc4_dev(dev); + + if (WARN_ON_ONCE(vc4->is_vc5)) + return; + + if (!vc4->v3d) + return; + + /* Enable the render done interrupts. The out-of-memory interrupt is + * enabled as soon as we have a binner BO allocated. + */ + V3D_WRITE(V3D_INTENA, V3D_INT_FLDONE | V3D_INT_FRDONE); +} + +void +vc4_irq_disable(struct drm_device *dev) +{ + struct vc4_dev *vc4 = to_vc4_dev(dev); + + if (WARN_ON_ONCE(vc4->is_vc5)) + return; + + if (!vc4->v3d) + return; + + /* Disable sending interrupts for our driver's IRQs. */ + V3D_WRITE(V3D_INTDIS, V3D_DRIVER_IRQS); + + /* Clear any pending interrupts we might have left. */ + V3D_WRITE(V3D_INTCTL, V3D_DRIVER_IRQS); + + /* Finish any interrupt handler still in flight. */ + synchronize_irq(vc4->irq); + + cancel_work_sync(&vc4->overflow_mem_work); +} + +int vc4_irq_install(struct drm_device *dev, int irq) +{ + struct vc4_dev *vc4 = to_vc4_dev(dev); + int ret; + + if (WARN_ON_ONCE(vc4->is_vc5)) + return -ENODEV; + + if (irq == IRQ_NOTCONNECTED) + return -ENOTCONN; + + vc4_irq_prepare(dev); + + ret = request_irq(irq, vc4_irq, 0, dev->driver->name, dev); + if (ret) + return ret; + + vc4_irq_enable(dev); + + return 0; +} + +void vc4_irq_uninstall(struct drm_device *dev) +{ + struct vc4_dev *vc4 = to_vc4_dev(dev); + + if (WARN_ON_ONCE(vc4->is_vc5)) + return; + + vc4_irq_disable(dev); + free_irq(vc4->irq, dev); +} + +/** Reinitializes interrupt registers when a GPU reset is performed. */ +void vc4_irq_reset(struct drm_device *dev) +{ + struct vc4_dev *vc4 = to_vc4_dev(dev); + unsigned long irqflags; + + if (WARN_ON_ONCE(vc4->is_vc5)) + return; + + /* Acknowledge any stale IRQs. */ + V3D_WRITE(V3D_INTCTL, V3D_DRIVER_IRQS); + + /* + * Turn all our interrupts on. Binner out of memory is the + * only one we expect to trigger at this point, since we've + * just come from poweron and haven't supplied any overflow + * memory yet. + */ + V3D_WRITE(V3D_INTENA, V3D_DRIVER_IRQS); + + spin_lock_irqsave(&vc4->job_lock, irqflags); + vc4_cancel_bin_job(dev); + vc4_irq_finish_render_job(dev); + spin_unlock_irqrestore(&vc4->job_lock, irqflags); +} -- cgit v1.2.3