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/drm_lock.c | 373 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 373 insertions(+) create mode 100644 drivers/gpu/drm/drm_lock.c (limited to 'drivers/gpu/drm/drm_lock.c') diff --git a/drivers/gpu/drm/drm_lock.c b/drivers/gpu/drm/drm_lock.c new file mode 100644 index 000000000..1efbd5389 --- /dev/null +++ b/drivers/gpu/drm/drm_lock.c @@ -0,0 +1,373 @@ +/* + * \file drm_lock.c + * IOCTLs for locking + * + * \author Rickard E. (Rik) Faith + * \author Gareth Hughes + */ + +/* + * Created: Tue Feb 2 08:37:54 1999 by faith@valinux.com + * + * Copyright 1999 Precision Insight, Inc., Cedar Park, Texas. + * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California. + * 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 + * VA LINUX SYSTEMS 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 +#include +#include +#include + +#include "drm_internal.h" +#include "drm_legacy.h" + +static int drm_lock_take(struct drm_lock_data *lock_data, unsigned int context); + +/* + * Take the heavyweight lock. + * + * \param lock lock pointer. + * \param context locking context. + * \return one if the lock is held, or zero otherwise. + * + * Attempt to mark the lock as held by the given context, via the \p cmpxchg instruction. + */ +static +int drm_lock_take(struct drm_lock_data *lock_data, + unsigned int context) +{ + unsigned int old, new, prev; + volatile unsigned int *lock = &lock_data->hw_lock->lock; + + spin_lock_bh(&lock_data->spinlock); + do { + old = *lock; + if (old & _DRM_LOCK_HELD) + new = old | _DRM_LOCK_CONT; + else { + new = context | _DRM_LOCK_HELD | + ((lock_data->user_waiters + lock_data->kernel_waiters > 1) ? + _DRM_LOCK_CONT : 0); + } + prev = cmpxchg(lock, old, new); + } while (prev != old); + spin_unlock_bh(&lock_data->spinlock); + + if (_DRM_LOCKING_CONTEXT(old) == context) { + if (old & _DRM_LOCK_HELD) { + if (context != DRM_KERNEL_CONTEXT) { + DRM_ERROR("%d holds heavyweight lock\n", + context); + } + return 0; + } + } + + if ((_DRM_LOCKING_CONTEXT(new)) == context && (new & _DRM_LOCK_HELD)) { + /* Have lock */ + return 1; + } + return 0; +} + +/* + * This takes a lock forcibly and hands it to context. Should ONLY be used + * inside *_unlock to give lock to kernel before calling *_dma_schedule. + * + * \param dev DRM device. + * \param lock lock pointer. + * \param context locking context. + * \return always one. + * + * Resets the lock file pointer. + * Marks the lock as held by the given context, via the \p cmpxchg instruction. + */ +static int drm_lock_transfer(struct drm_lock_data *lock_data, + unsigned int context) +{ + unsigned int old, new, prev; + volatile unsigned int *lock = &lock_data->hw_lock->lock; + + lock_data->file_priv = NULL; + do { + old = *lock; + new = context | _DRM_LOCK_HELD; + prev = cmpxchg(lock, old, new); + } while (prev != old); + return 1; +} + +static int drm_legacy_lock_free(struct drm_lock_data *lock_data, + unsigned int context) +{ + unsigned int old, new, prev; + volatile unsigned int *lock = &lock_data->hw_lock->lock; + + spin_lock_bh(&lock_data->spinlock); + if (lock_data->kernel_waiters != 0) { + drm_lock_transfer(lock_data, 0); + lock_data->idle_has_lock = 1; + spin_unlock_bh(&lock_data->spinlock); + return 1; + } + spin_unlock_bh(&lock_data->spinlock); + + do { + old = *lock; + new = _DRM_LOCKING_CONTEXT(old); + prev = cmpxchg(lock, old, new); + } while (prev != old); + + if (_DRM_LOCK_IS_HELD(old) && _DRM_LOCKING_CONTEXT(old) != context) { + DRM_ERROR("%d freed heavyweight lock held by %d\n", + context, _DRM_LOCKING_CONTEXT(old)); + return 1; + } + wake_up_interruptible(&lock_data->lock_queue); + return 0; +} + +/* + * Lock ioctl. + * + * \param inode device inode. + * \param file_priv DRM file private. + * \param cmd command. + * \param arg user argument, pointing to a drm_lock structure. + * \return zero on success or negative number on failure. + * + * Add the current task to the lock wait queue, and attempt to take to lock. + */ +int drm_legacy_lock(struct drm_device *dev, void *data, + struct drm_file *file_priv) +{ + DECLARE_WAITQUEUE(entry, current); + struct drm_lock *lock = data; + struct drm_master *master = file_priv->master; + int ret = 0; + + if (!drm_core_check_feature(dev, DRIVER_LEGACY)) + return -EOPNOTSUPP; + + ++file_priv->lock_count; + + if (lock->context == DRM_KERNEL_CONTEXT) { + DRM_ERROR("Process %d using kernel context %d\n", + task_pid_nr(current), lock->context); + return -EINVAL; + } + + DRM_DEBUG("%d (pid %d) requests lock (0x%08x), flags = 0x%08x\n", + lock->context, task_pid_nr(current), + master->lock.hw_lock ? master->lock.hw_lock->lock : -1, + lock->flags); + + add_wait_queue(&master->lock.lock_queue, &entry); + spin_lock_bh(&master->lock.spinlock); + master->lock.user_waiters++; + spin_unlock_bh(&master->lock.spinlock); + + for (;;) { + __set_current_state(TASK_INTERRUPTIBLE); + if (!master->lock.hw_lock) { + /* Device has been unregistered */ + send_sig(SIGTERM, current, 0); + ret = -EINTR; + break; + } + if (drm_lock_take(&master->lock, lock->context)) { + master->lock.file_priv = file_priv; + master->lock.lock_time = jiffies; + break; /* Got lock */ + } + + /* Contention */ + mutex_unlock(&drm_global_mutex); + schedule(); + mutex_lock(&drm_global_mutex); + if (signal_pending(current)) { + ret = -EINTR; + break; + } + } + spin_lock_bh(&master->lock.spinlock); + master->lock.user_waiters--; + spin_unlock_bh(&master->lock.spinlock); + __set_current_state(TASK_RUNNING); + remove_wait_queue(&master->lock.lock_queue, &entry); + + DRM_DEBUG("%d %s\n", lock->context, + ret ? "interrupted" : "has lock"); + if (ret) return ret; + + /* don't set the block all signals on the master process for now + * really probably not the correct answer but lets us debug xkb + * xserver for now */ + if (!drm_is_current_master(file_priv)) { + dev->sigdata.context = lock->context; + dev->sigdata.lock = master->lock.hw_lock; + } + + if (dev->driver->dma_quiescent && (lock->flags & _DRM_LOCK_QUIESCENT)) + { + if (dev->driver->dma_quiescent(dev)) { + DRM_DEBUG("%d waiting for DMA quiescent\n", + lock->context); + return -EBUSY; + } + } + + return 0; +} + +/* + * Unlock ioctl. + * + * \param inode device inode. + * \param file_priv DRM file private. + * \param cmd command. + * \param arg user argument, pointing to a drm_lock structure. + * \return zero on success or negative number on failure. + * + * Transfer and free the lock. + */ +int drm_legacy_unlock(struct drm_device *dev, void *data, struct drm_file *file_priv) +{ + struct drm_lock *lock = data; + struct drm_master *master = file_priv->master; + + if (!drm_core_check_feature(dev, DRIVER_LEGACY)) + return -EOPNOTSUPP; + + if (lock->context == DRM_KERNEL_CONTEXT) { + DRM_ERROR("Process %d using kernel context %d\n", + task_pid_nr(current), lock->context); + return -EINVAL; + } + + if (drm_legacy_lock_free(&master->lock, lock->context)) { + /* FIXME: Should really bail out here. */ + } + + return 0; +} + +/* + * This function returns immediately and takes the hw lock + * with the kernel context if it is free, otherwise it gets the highest priority when and if + * it is eventually released. + * + * This guarantees that the kernel will _eventually_ have the lock _unless_ it is held + * by a blocked process. (In the latter case an explicit wait for the hardware lock would cause + * a deadlock, which is why the "idlelock" was invented). + * + * This should be sufficient to wait for GPU idle without + * having to worry about starvation. + */ +void drm_legacy_idlelock_take(struct drm_lock_data *lock_data) +{ + int ret; + + spin_lock_bh(&lock_data->spinlock); + lock_data->kernel_waiters++; + if (!lock_data->idle_has_lock) { + + spin_unlock_bh(&lock_data->spinlock); + ret = drm_lock_take(lock_data, DRM_KERNEL_CONTEXT); + spin_lock_bh(&lock_data->spinlock); + + if (ret == 1) + lock_data->idle_has_lock = 1; + } + spin_unlock_bh(&lock_data->spinlock); +} +EXPORT_SYMBOL(drm_legacy_idlelock_take); + +void drm_legacy_idlelock_release(struct drm_lock_data *lock_data) +{ + unsigned int old, prev; + volatile unsigned int *lock = &lock_data->hw_lock->lock; + + spin_lock_bh(&lock_data->spinlock); + if (--lock_data->kernel_waiters == 0) { + if (lock_data->idle_has_lock) { + do { + old = *lock; + prev = cmpxchg(lock, old, DRM_KERNEL_CONTEXT); + } while (prev != old); + wake_up_interruptible(&lock_data->lock_queue); + lock_data->idle_has_lock = 0; + } + } + spin_unlock_bh(&lock_data->spinlock); +} +EXPORT_SYMBOL(drm_legacy_idlelock_release); + +static int drm_legacy_i_have_hw_lock(struct drm_device *dev, + struct drm_file *file_priv) +{ + struct drm_master *master = file_priv->master; + + return (file_priv->lock_count && master->lock.hw_lock && + _DRM_LOCK_IS_HELD(master->lock.hw_lock->lock) && + master->lock.file_priv == file_priv); +} + +void drm_legacy_lock_release(struct drm_device *dev, struct file *filp) +{ + struct drm_file *file_priv = filp->private_data; + + /* if the master has gone away we can't do anything with the lock */ + if (!dev->master) + return; + + if (drm_legacy_i_have_hw_lock(dev, file_priv)) { + DRM_DEBUG("File %p released, freeing lock for context %d\n", + filp, _DRM_LOCKING_CONTEXT(file_priv->master->lock.hw_lock->lock)); + drm_legacy_lock_free(&file_priv->master->lock, + _DRM_LOCKING_CONTEXT(file_priv->master->lock.hw_lock->lock)); + } +} + +void drm_legacy_lock_master_cleanup(struct drm_device *dev, struct drm_master *master) +{ + if (!drm_core_check_feature(dev, DRIVER_LEGACY)) + return; + + /* + * Since the master is disappearing, so is the + * possibility to lock. + */ + mutex_lock(&dev->struct_mutex); + if (master->lock.hw_lock) { + if (dev->sigdata.lock == master->lock.hw_lock) + dev->sigdata.lock = NULL; + master->lock.hw_lock = NULL; + master->lock.file_priv = NULL; + wake_up_interruptible_all(&master->lock.lock_queue); + } + mutex_unlock(&dev->struct_mutex); +} -- cgit v1.2.3