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_vma_manager.c | 421 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 421 insertions(+) create mode 100644 drivers/gpu/drm/drm_vma_manager.c (limited to 'drivers/gpu/drm/drm_vma_manager.c') diff --git a/drivers/gpu/drm/drm_vma_manager.c b/drivers/gpu/drm/drm_vma_manager.c new file mode 100644 index 000000000..83229a031 --- /dev/null +++ b/drivers/gpu/drm/drm_vma_manager.c @@ -0,0 +1,421 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT +/* + * Copyright (c) 2006-2009 VMware, Inc., Palo Alto, CA., USA + * Copyright (c) 2012 David Airlie + * Copyright (c) 2013 David Herrmann + * + * 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 +#include + +#include +#include + +/** + * DOC: vma offset manager + * + * The vma-manager is responsible to map arbitrary driver-dependent memory + * regions into the linear user address-space. It provides offsets to the + * caller which can then be used on the address_space of the drm-device. It + * takes care to not overlap regions, size them appropriately and to not + * confuse mm-core by inconsistent fake vm_pgoff fields. + * Drivers shouldn't use this for object placement in VMEM. This manager should + * only be used to manage mappings into linear user-space VMs. + * + * We use drm_mm as backend to manage object allocations. But it is highly + * optimized for alloc/free calls, not lookups. Hence, we use an rb-tree to + * speed up offset lookups. + * + * You must not use multiple offset managers on a single address_space. + * Otherwise, mm-core will be unable to tear down memory mappings as the VM will + * no longer be linear. + * + * This offset manager works on page-based addresses. That is, every argument + * and return code (with the exception of drm_vma_node_offset_addr()) is given + * in number of pages, not number of bytes. That means, object sizes and offsets + * must always be page-aligned (as usual). + * If you want to get a valid byte-based user-space address for a given offset, + * please see drm_vma_node_offset_addr(). + * + * Additionally to offset management, the vma offset manager also handles access + * management. For every open-file context that is allowed to access a given + * node, you must call drm_vma_node_allow(). Otherwise, an mmap() call on this + * open-file with the offset of the node will fail with -EACCES. To revoke + * access again, use drm_vma_node_revoke(). However, the caller is responsible + * for destroying already existing mappings, if required. + */ + +/** + * drm_vma_offset_manager_init - Initialize new offset-manager + * @mgr: Manager object + * @page_offset: Offset of available memory area (page-based) + * @size: Size of available address space range (page-based) + * + * Initialize a new offset-manager. The offset and area size available for the + * manager are given as @page_offset and @size. Both are interpreted as + * page-numbers, not bytes. + * + * Adding/removing nodes from the manager is locked internally and protected + * against concurrent access. However, node allocation and destruction is left + * for the caller. While calling into the vma-manager, a given node must + * always be guaranteed to be referenced. + */ +void drm_vma_offset_manager_init(struct drm_vma_offset_manager *mgr, + unsigned long page_offset, unsigned long size) +{ + rwlock_init(&mgr->vm_lock); + drm_mm_init(&mgr->vm_addr_space_mm, page_offset, size); +} +EXPORT_SYMBOL(drm_vma_offset_manager_init); + +/** + * drm_vma_offset_manager_destroy() - Destroy offset manager + * @mgr: Manager object + * + * Destroy an object manager which was previously created via + * drm_vma_offset_manager_init(). The caller must remove all allocated nodes + * before destroying the manager. Otherwise, drm_mm will refuse to free the + * requested resources. + * + * The manager must not be accessed after this function is called. + */ +void drm_vma_offset_manager_destroy(struct drm_vma_offset_manager *mgr) +{ + drm_mm_takedown(&mgr->vm_addr_space_mm); +} +EXPORT_SYMBOL(drm_vma_offset_manager_destroy); + +/** + * drm_vma_offset_lookup_locked() - Find node in offset space + * @mgr: Manager object + * @start: Start address for object (page-based) + * @pages: Size of object (page-based) + * + * Find a node given a start address and object size. This returns the _best_ + * match for the given node. That is, @start may point somewhere into a valid + * region and the given node will be returned, as long as the node spans the + * whole requested area (given the size in number of pages as @pages). + * + * Note that before lookup the vma offset manager lookup lock must be acquired + * with drm_vma_offset_lock_lookup(). See there for an example. This can then be + * used to implement weakly referenced lookups using kref_get_unless_zero(). + * + * Example: + * + * :: + * + * drm_vma_offset_lock_lookup(mgr); + * node = drm_vma_offset_lookup_locked(mgr); + * if (node) + * kref_get_unless_zero(container_of(node, sth, entr)); + * drm_vma_offset_unlock_lookup(mgr); + * + * RETURNS: + * Returns NULL if no suitable node can be found. Otherwise, the best match + * is returned. It's the caller's responsibility to make sure the node doesn't + * get destroyed before the caller can access it. + */ +struct drm_vma_offset_node *drm_vma_offset_lookup_locked(struct drm_vma_offset_manager *mgr, + unsigned long start, + unsigned long pages) +{ + struct drm_mm_node *node, *best; + struct rb_node *iter; + unsigned long offset; + + iter = mgr->vm_addr_space_mm.interval_tree.rb_root.rb_node; + best = NULL; + + while (likely(iter)) { + node = rb_entry(iter, struct drm_mm_node, rb); + offset = node->start; + if (start >= offset) { + iter = iter->rb_right; + best = node; + if (start == offset) + break; + } else { + iter = iter->rb_left; + } + } + + /* verify that the node spans the requested area */ + if (best) { + offset = best->start + best->size; + if (offset < start + pages) + best = NULL; + } + + if (!best) + return NULL; + + return container_of(best, struct drm_vma_offset_node, vm_node); +} +EXPORT_SYMBOL(drm_vma_offset_lookup_locked); + +/** + * drm_vma_offset_add() - Add offset node to manager + * @mgr: Manager object + * @node: Node to be added + * @pages: Allocation size visible to user-space (in number of pages) + * + * Add a node to the offset-manager. If the node was already added, this does + * nothing and return 0. @pages is the size of the object given in number of + * pages. + * After this call succeeds, you can access the offset of the node until it + * is removed again. + * + * If this call fails, it is safe to retry the operation or call + * drm_vma_offset_remove(), anyway. However, no cleanup is required in that + * case. + * + * @pages is not required to be the same size as the underlying memory object + * that you want to map. It only limits the size that user-space can map into + * their address space. + * + * RETURNS: + * 0 on success, negative error code on failure. + */ +int drm_vma_offset_add(struct drm_vma_offset_manager *mgr, + struct drm_vma_offset_node *node, unsigned long pages) +{ + int ret = 0; + + write_lock(&mgr->vm_lock); + + if (!drm_mm_node_allocated(&node->vm_node)) + ret = drm_mm_insert_node(&mgr->vm_addr_space_mm, + &node->vm_node, pages); + + write_unlock(&mgr->vm_lock); + + return ret; +} +EXPORT_SYMBOL(drm_vma_offset_add); + +/** + * drm_vma_offset_remove() - Remove offset node from manager + * @mgr: Manager object + * @node: Node to be removed + * + * Remove a node from the offset manager. If the node wasn't added before, this + * does nothing. After this call returns, the offset and size will be 0 until a + * new offset is allocated via drm_vma_offset_add() again. Helper functions like + * drm_vma_node_start() and drm_vma_node_offset_addr() will return 0 if no + * offset is allocated. + */ +void drm_vma_offset_remove(struct drm_vma_offset_manager *mgr, + struct drm_vma_offset_node *node) +{ + write_lock(&mgr->vm_lock); + + if (drm_mm_node_allocated(&node->vm_node)) { + drm_mm_remove_node(&node->vm_node); + memset(&node->vm_node, 0, sizeof(node->vm_node)); + } + + write_unlock(&mgr->vm_lock); +} +EXPORT_SYMBOL(drm_vma_offset_remove); + +static int vma_node_allow(struct drm_vma_offset_node *node, + struct drm_file *tag, bool ref_counted) +{ + struct rb_node **iter; + struct rb_node *parent = NULL; + struct drm_vma_offset_file *new, *entry; + int ret = 0; + + /* Preallocate entry to avoid atomic allocations below. It is quite + * unlikely that an open-file is added twice to a single node so we + * don't optimize for this case. OOM is checked below only if the entry + * is actually used. */ + new = kmalloc(sizeof(*entry), GFP_KERNEL); + + write_lock(&node->vm_lock); + + iter = &node->vm_files.rb_node; + + while (likely(*iter)) { + parent = *iter; + entry = rb_entry(*iter, struct drm_vma_offset_file, vm_rb); + + if (tag == entry->vm_tag) { + if (ref_counted) + entry->vm_count++; + goto unlock; + } else if (tag > entry->vm_tag) { + iter = &(*iter)->rb_right; + } else { + iter = &(*iter)->rb_left; + } + } + + if (!new) { + ret = -ENOMEM; + goto unlock; + } + + new->vm_tag = tag; + new->vm_count = 1; + rb_link_node(&new->vm_rb, parent, iter); + rb_insert_color(&new->vm_rb, &node->vm_files); + new = NULL; + +unlock: + write_unlock(&node->vm_lock); + kfree(new); + return ret; +} + +/** + * drm_vma_node_allow - Add open-file to list of allowed users + * @node: Node to modify + * @tag: Tag of file to remove + * + * Add @tag to the list of allowed open-files for this node. If @tag is + * already on this list, the ref-count is incremented. + * + * The list of allowed-users is preserved across drm_vma_offset_add() and + * drm_vma_offset_remove() calls. You may even call it if the node is currently + * not added to any offset-manager. + * + * You must remove all open-files the same number of times as you added them + * before destroying the node. Otherwise, you will leak memory. + * + * This is locked against concurrent access internally. + * + * RETURNS: + * 0 on success, negative error code on internal failure (out-of-mem) + */ +int drm_vma_node_allow(struct drm_vma_offset_node *node, struct drm_file *tag) +{ + return vma_node_allow(node, tag, true); +} +EXPORT_SYMBOL(drm_vma_node_allow); + +/** + * drm_vma_node_allow_once - Add open-file to list of allowed users + * @node: Node to modify + * @tag: Tag of file to remove + * + * Add @tag to the list of allowed open-files for this node. + * + * The list of allowed-users is preserved across drm_vma_offset_add() and + * drm_vma_offset_remove() calls. You may even call it if the node is currently + * not added to any offset-manager. + * + * This is not ref-counted unlike drm_vma_node_allow() hence drm_vma_node_revoke() + * should only be called once after this. + * + * This is locked against concurrent access internally. + * + * RETURNS: + * 0 on success, negative error code on internal failure (out-of-mem) + */ +int drm_vma_node_allow_once(struct drm_vma_offset_node *node, struct drm_file *tag) +{ + return vma_node_allow(node, tag, false); +} +EXPORT_SYMBOL(drm_vma_node_allow_once); + +/** + * drm_vma_node_revoke - Remove open-file from list of allowed users + * @node: Node to modify + * @tag: Tag of file to remove + * + * Decrement the ref-count of @tag in the list of allowed open-files on @node. + * If the ref-count drops to zero, remove @tag from the list. You must call + * this once for every drm_vma_node_allow() on @tag. + * + * This is locked against concurrent access internally. + * + * If @tag is not on the list, nothing is done. + */ +void drm_vma_node_revoke(struct drm_vma_offset_node *node, + struct drm_file *tag) +{ + struct drm_vma_offset_file *entry; + struct rb_node *iter; + + write_lock(&node->vm_lock); + + iter = node->vm_files.rb_node; + while (likely(iter)) { + entry = rb_entry(iter, struct drm_vma_offset_file, vm_rb); + if (tag == entry->vm_tag) { + if (!--entry->vm_count) { + rb_erase(&entry->vm_rb, &node->vm_files); + kfree(entry); + } + break; + } else if (tag > entry->vm_tag) { + iter = iter->rb_right; + } else { + iter = iter->rb_left; + } + } + + write_unlock(&node->vm_lock); +} +EXPORT_SYMBOL(drm_vma_node_revoke); + +/** + * drm_vma_node_is_allowed - Check whether an open-file is granted access + * @node: Node to check + * @tag: Tag of file to remove + * + * Search the list in @node whether @tag is currently on the list of allowed + * open-files (see drm_vma_node_allow()). + * + * This is locked against concurrent access internally. + * + * RETURNS: + * true if @filp is on the list + */ +bool drm_vma_node_is_allowed(struct drm_vma_offset_node *node, + struct drm_file *tag) +{ + struct drm_vma_offset_file *entry; + struct rb_node *iter; + + read_lock(&node->vm_lock); + + iter = node->vm_files.rb_node; + while (likely(iter)) { + entry = rb_entry(iter, struct drm_vma_offset_file, vm_rb); + if (tag == entry->vm_tag) + break; + else if (tag > entry->vm_tag) + iter = iter->rb_right; + else + iter = iter->rb_left; + } + + read_unlock(&node->vm_lock); + + return iter; +} +EXPORT_SYMBOL(drm_vma_node_is_allowed); -- cgit v1.2.3