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/ttm/ttm_bo.c | 1207 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 1207 insertions(+) create mode 100644 drivers/gpu/drm/ttm/ttm_bo.c (limited to 'drivers/gpu/drm/ttm/ttm_bo.c') diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c new file mode 100644 index 000000000..c3f4b3313 --- /dev/null +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -0,0 +1,1207 @@ +/* SPDX-License-Identifier: GPL-2.0 OR MIT */ +/************************************************************************** + * + * Copyright (c) 2006-2009 VMware, Inc., Palo Alto, CA., USA + * 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, 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 COPYRIGHT HOLDERS, AUTHORS 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. + * + **************************************************************************/ +/* + * Authors: Thomas Hellstrom + */ + +#define pr_fmt(fmt) "[TTM] " fmt + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include "ttm_module.h" + +static void ttm_bo_mem_space_debug(struct ttm_buffer_object *bo, + struct ttm_placement *placement) +{ + struct drm_printer p = drm_debug_printer(TTM_PFX); + struct ttm_resource_manager *man; + int i, mem_type; + + for (i = 0; i < placement->num_placement; i++) { + mem_type = placement->placement[i].mem_type; + drm_printf(&p, " placement[%d]=0x%08X (%d)\n", + i, placement->placement[i].flags, mem_type); + man = ttm_manager_type(bo->bdev, mem_type); + ttm_resource_manager_debug(man, &p); + } +} + +/** + * ttm_bo_move_to_lru_tail + * + * @bo: The buffer object. + * + * Move this BO to the tail of all lru lists used to lookup and reserve an + * object. This function must be called with struct ttm_global::lru_lock + * held, and is used to make a BO less likely to be considered for eviction. + */ +void ttm_bo_move_to_lru_tail(struct ttm_buffer_object *bo) +{ + dma_resv_assert_held(bo->base.resv); + + if (bo->resource) + ttm_resource_move_to_lru_tail(bo->resource); +} +EXPORT_SYMBOL(ttm_bo_move_to_lru_tail); + +/** + * ttm_bo_set_bulk_move - update BOs bulk move object + * + * @bo: The buffer object. + * + * Update the BOs bulk move object, making sure that resources are added/removed + * as well. A bulk move allows to move many resource on the LRU at once, + * resulting in much less overhead of maintaining the LRU. + * The only requirement is that the resources stay together on the LRU and are + * never separated. This is enforces by setting the bulk_move structure on a BO. + * ttm_lru_bulk_move_tail() should be used to move all resources to the tail of + * their LRU list. + */ +void ttm_bo_set_bulk_move(struct ttm_buffer_object *bo, + struct ttm_lru_bulk_move *bulk) +{ + dma_resv_assert_held(bo->base.resv); + + if (bo->bulk_move == bulk) + return; + + spin_lock(&bo->bdev->lru_lock); + if (bo->resource) + ttm_resource_del_bulk_move(bo->resource, bo); + bo->bulk_move = bulk; + if (bo->resource) + ttm_resource_add_bulk_move(bo->resource, bo); + spin_unlock(&bo->bdev->lru_lock); +} +EXPORT_SYMBOL(ttm_bo_set_bulk_move); + +static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo, + struct ttm_resource *mem, bool evict, + struct ttm_operation_ctx *ctx, + struct ttm_place *hop) +{ + struct ttm_device *bdev = bo->bdev; + bool old_use_tt, new_use_tt; + int ret; + + old_use_tt = bo->resource && + ttm_manager_type(bdev, bo->resource->mem_type)->use_tt; + new_use_tt = ttm_manager_type(bdev, mem->mem_type)->use_tt; + + ttm_bo_unmap_virtual(bo); + + /* + * Create and bind a ttm if required. + */ + + if (new_use_tt) { + /* Zero init the new TTM structure if the old location should + * have used one as well. + */ + ret = ttm_tt_create(bo, old_use_tt); + if (ret) + goto out_err; + + if (mem->mem_type != TTM_PL_SYSTEM) { + ret = ttm_tt_populate(bo->bdev, bo->ttm, ctx); + if (ret) + goto out_err; + } + } + + ret = dma_resv_reserve_fences(bo->base.resv, 1); + if (ret) + goto out_err; + + ret = bdev->funcs->move(bo, evict, ctx, mem, hop); + if (ret) { + if (ret == -EMULTIHOP) + return ret; + goto out_err; + } + + ctx->bytes_moved += bo->base.size; + return 0; + +out_err: + if (!old_use_tt) + ttm_bo_tt_destroy(bo); + + return ret; +} + +/* + * Call bo::reserved. + * Will release GPU memory type usage on destruction. + * This is the place to put in driver specific hooks to release + * driver private resources. + * Will release the bo::reserved lock. + */ + +static void ttm_bo_cleanup_memtype_use(struct ttm_buffer_object *bo) +{ + if (bo->bdev->funcs->delete_mem_notify) + bo->bdev->funcs->delete_mem_notify(bo); + + ttm_bo_tt_destroy(bo); + ttm_resource_free(bo, &bo->resource); +} + +static int ttm_bo_individualize_resv(struct ttm_buffer_object *bo) +{ + int r; + + if (bo->base.resv == &bo->base._resv) + return 0; + + BUG_ON(!dma_resv_trylock(&bo->base._resv)); + + r = dma_resv_copy_fences(&bo->base._resv, bo->base.resv); + dma_resv_unlock(&bo->base._resv); + if (r) + return r; + + if (bo->type != ttm_bo_type_sg) { + /* This works because the BO is about to be destroyed and nobody + * reference it any more. The only tricky case is the trylock on + * the resv object while holding the lru_lock. + */ + spin_lock(&bo->bdev->lru_lock); + bo->base.resv = &bo->base._resv; + spin_unlock(&bo->bdev->lru_lock); + } + + return r; +} + +static void ttm_bo_flush_all_fences(struct ttm_buffer_object *bo) +{ + struct dma_resv *resv = &bo->base._resv; + struct dma_resv_iter cursor; + struct dma_fence *fence; + + dma_resv_iter_begin(&cursor, resv, DMA_RESV_USAGE_BOOKKEEP); + dma_resv_for_each_fence_unlocked(&cursor, fence) { + if (!fence->ops->signaled) + dma_fence_enable_sw_signaling(fence); + } + dma_resv_iter_end(&cursor); +} + +/** + * ttm_bo_cleanup_refs + * If bo idle, remove from lru lists, and unref. + * If not idle, block if possible. + * + * Must be called with lru_lock and reservation held, this function + * will drop the lru lock and optionally the reservation lock before returning. + * + * @bo: The buffer object to clean-up + * @interruptible: Any sleeps should occur interruptibly. + * @no_wait_gpu: Never wait for gpu. Return -EBUSY instead. + * @unlock_resv: Unlock the reservation lock as well. + */ + +static int ttm_bo_cleanup_refs(struct ttm_buffer_object *bo, + bool interruptible, bool no_wait_gpu, + bool unlock_resv) +{ + struct dma_resv *resv = &bo->base._resv; + int ret; + + if (dma_resv_test_signaled(resv, DMA_RESV_USAGE_BOOKKEEP)) + ret = 0; + else + ret = -EBUSY; + + if (ret && !no_wait_gpu) { + long lret; + + if (unlock_resv) + dma_resv_unlock(bo->base.resv); + spin_unlock(&bo->bdev->lru_lock); + + lret = dma_resv_wait_timeout(resv, DMA_RESV_USAGE_BOOKKEEP, + interruptible, + 30 * HZ); + + if (lret < 0) + return lret; + else if (lret == 0) + return -EBUSY; + + spin_lock(&bo->bdev->lru_lock); + if (unlock_resv && !dma_resv_trylock(bo->base.resv)) { + /* + * We raced, and lost, someone else holds the reservation now, + * and is probably busy in ttm_bo_cleanup_memtype_use. + * + * Even if it's not the case, because we finished waiting any + * delayed destruction would succeed, so just return success + * here. + */ + spin_unlock(&bo->bdev->lru_lock); + return 0; + } + ret = 0; + } + + if (ret || unlikely(list_empty(&bo->ddestroy))) { + if (unlock_resv) + dma_resv_unlock(bo->base.resv); + spin_unlock(&bo->bdev->lru_lock); + return ret; + } + + list_del_init(&bo->ddestroy); + spin_unlock(&bo->bdev->lru_lock); + ttm_bo_cleanup_memtype_use(bo); + + if (unlock_resv) + dma_resv_unlock(bo->base.resv); + + ttm_bo_put(bo); + + return 0; +} + +/* + * Traverse the delayed list, and call ttm_bo_cleanup_refs on all + * encountered buffers. + */ +bool ttm_bo_delayed_delete(struct ttm_device *bdev, bool remove_all) +{ + struct list_head removed; + bool empty; + + INIT_LIST_HEAD(&removed); + + spin_lock(&bdev->lru_lock); + while (!list_empty(&bdev->ddestroy)) { + struct ttm_buffer_object *bo; + + bo = list_first_entry(&bdev->ddestroy, struct ttm_buffer_object, + ddestroy); + list_move_tail(&bo->ddestroy, &removed); + if (!ttm_bo_get_unless_zero(bo)) + continue; + + if (remove_all || bo->base.resv != &bo->base._resv) { + spin_unlock(&bdev->lru_lock); + dma_resv_lock(bo->base.resv, NULL); + + spin_lock(&bdev->lru_lock); + ttm_bo_cleanup_refs(bo, false, !remove_all, true); + + } else if (dma_resv_trylock(bo->base.resv)) { + ttm_bo_cleanup_refs(bo, false, !remove_all, true); + } else { + spin_unlock(&bdev->lru_lock); + } + + ttm_bo_put(bo); + spin_lock(&bdev->lru_lock); + } + list_splice_tail(&removed, &bdev->ddestroy); + empty = list_empty(&bdev->ddestroy); + spin_unlock(&bdev->lru_lock); + + return empty; +} + +static void ttm_bo_release(struct kref *kref) +{ + struct ttm_buffer_object *bo = + container_of(kref, struct ttm_buffer_object, kref); + struct ttm_device *bdev = bo->bdev; + int ret; + + WARN_ON_ONCE(bo->pin_count); + WARN_ON_ONCE(bo->bulk_move); + + if (!bo->deleted) { + ret = ttm_bo_individualize_resv(bo); + if (ret) { + /* Last resort, if we fail to allocate memory for the + * fences block for the BO to become idle + */ + dma_resv_wait_timeout(bo->base.resv, + DMA_RESV_USAGE_BOOKKEEP, false, + 30 * HZ); + } + + if (bo->bdev->funcs->release_notify) + bo->bdev->funcs->release_notify(bo); + + drm_vma_offset_remove(bdev->vma_manager, &bo->base.vma_node); + ttm_mem_io_free(bdev, bo->resource); + } + + if (!dma_resv_test_signaled(bo->base.resv, DMA_RESV_USAGE_BOOKKEEP) || + !dma_resv_trylock(bo->base.resv)) { + /* The BO is not idle, resurrect it for delayed destroy */ + ttm_bo_flush_all_fences(bo); + bo->deleted = true; + + spin_lock(&bo->bdev->lru_lock); + + /* + * Make pinned bos immediately available to + * shrinkers, now that they are queued for + * destruction. + * + * FIXME: QXL is triggering this. Can be removed when the + * driver is fixed. + */ + if (bo->pin_count) { + bo->pin_count = 0; + ttm_resource_move_to_lru_tail(bo->resource); + } + + kref_init(&bo->kref); + list_add_tail(&bo->ddestroy, &bdev->ddestroy); + spin_unlock(&bo->bdev->lru_lock); + + schedule_delayed_work(&bdev->wq, + ((HZ / 100) < 1) ? 1 : HZ / 100); + return; + } + + spin_lock(&bo->bdev->lru_lock); + list_del(&bo->ddestroy); + spin_unlock(&bo->bdev->lru_lock); + + ttm_bo_cleanup_memtype_use(bo); + dma_resv_unlock(bo->base.resv); + + atomic_dec(&ttm_glob.bo_count); + bo->destroy(bo); +} + +void ttm_bo_put(struct ttm_buffer_object *bo) +{ + kref_put(&bo->kref, ttm_bo_release); +} +EXPORT_SYMBOL(ttm_bo_put); + +int ttm_bo_lock_delayed_workqueue(struct ttm_device *bdev) +{ + return cancel_delayed_work_sync(&bdev->wq); +} +EXPORT_SYMBOL(ttm_bo_lock_delayed_workqueue); + +void ttm_bo_unlock_delayed_workqueue(struct ttm_device *bdev, int resched) +{ + if (resched) + schedule_delayed_work(&bdev->wq, + ((HZ / 100) < 1) ? 1 : HZ / 100); +} +EXPORT_SYMBOL(ttm_bo_unlock_delayed_workqueue); + +static int ttm_bo_bounce_temp_buffer(struct ttm_buffer_object *bo, + struct ttm_resource **mem, + struct ttm_operation_ctx *ctx, + struct ttm_place *hop) +{ + struct ttm_placement hop_placement; + struct ttm_resource *hop_mem; + int ret; + + hop_placement.num_placement = hop_placement.num_busy_placement = 1; + hop_placement.placement = hop_placement.busy_placement = hop; + + /* find space in the bounce domain */ + ret = ttm_bo_mem_space(bo, &hop_placement, &hop_mem, ctx); + if (ret) + return ret; + /* move to the bounce domain */ + ret = ttm_bo_handle_move_mem(bo, hop_mem, false, ctx, NULL); + if (ret) { + ttm_resource_free(bo, &hop_mem); + return ret; + } + return 0; +} + +static int ttm_bo_evict(struct ttm_buffer_object *bo, + struct ttm_operation_ctx *ctx) +{ + struct ttm_device *bdev = bo->bdev; + struct ttm_resource *evict_mem; + struct ttm_placement placement; + struct ttm_place hop; + int ret = 0; + + memset(&hop, 0, sizeof(hop)); + + dma_resv_assert_held(bo->base.resv); + + placement.num_placement = 0; + placement.num_busy_placement = 0; + bdev->funcs->evict_flags(bo, &placement); + + if (!placement.num_placement && !placement.num_busy_placement) { + ret = ttm_bo_wait(bo, true, false); + if (ret) + return ret; + + /* + * Since we've already synced, this frees backing store + * immediately. + */ + return ttm_bo_pipeline_gutting(bo); + } + + ret = ttm_bo_mem_space(bo, &placement, &evict_mem, ctx); + if (ret) { + if (ret != -ERESTARTSYS) { + pr_err("Failed to find memory space for buffer 0x%p eviction\n", + bo); + ttm_bo_mem_space_debug(bo, &placement); + } + goto out; + } + +bounce: + ret = ttm_bo_handle_move_mem(bo, evict_mem, true, ctx, &hop); + if (ret == -EMULTIHOP) { + ret = ttm_bo_bounce_temp_buffer(bo, &evict_mem, ctx, &hop); + if (ret) { + pr_err("Buffer eviction failed\n"); + ttm_resource_free(bo, &evict_mem); + goto out; + } + /* try and move to final place now. */ + goto bounce; + } +out: + return ret; +} + +bool ttm_bo_eviction_valuable(struct ttm_buffer_object *bo, + const struct ttm_place *place) +{ + struct ttm_resource *res = bo->resource; + struct ttm_device *bdev = bo->bdev; + + dma_resv_assert_held(bo->base.resv); + if (bo->resource->mem_type == TTM_PL_SYSTEM) + return true; + + /* Don't evict this BO if it's outside of the + * requested placement range + */ + return ttm_resource_intersects(bdev, res, place, bo->base.size); +} +EXPORT_SYMBOL(ttm_bo_eviction_valuable); + +/* + * Check the target bo is allowable to be evicted or swapout, including cases: + * + * a. if share same reservation object with ctx->resv, have assumption + * reservation objects should already be locked, so not lock again and + * return true directly when either the opreation allow_reserved_eviction + * or the target bo already is in delayed free list; + * + * b. Otherwise, trylock it. + */ +static bool ttm_bo_evict_swapout_allowable(struct ttm_buffer_object *bo, + struct ttm_operation_ctx *ctx, + const struct ttm_place *place, + bool *locked, bool *busy) +{ + bool ret = false; + + if (bo->base.resv == ctx->resv) { + dma_resv_assert_held(bo->base.resv); + if (ctx->allow_res_evict) + ret = true; + *locked = false; + if (busy) + *busy = false; + } else { + ret = dma_resv_trylock(bo->base.resv); + *locked = ret; + if (busy) + *busy = !ret; + } + + if (ret && place && (bo->resource->mem_type != place->mem_type || + !bo->bdev->funcs->eviction_valuable(bo, place))) { + ret = false; + if (*locked) { + dma_resv_unlock(bo->base.resv); + *locked = false; + } + } + + return ret; +} + +/** + * ttm_mem_evict_wait_busy - wait for a busy BO to become available + * + * @busy_bo: BO which couldn't be locked with trylock + * @ctx: operation context + * @ticket: acquire ticket + * + * Try to lock a busy buffer object to avoid failing eviction. + */ +static int ttm_mem_evict_wait_busy(struct ttm_buffer_object *busy_bo, + struct ttm_operation_ctx *ctx, + struct ww_acquire_ctx *ticket) +{ + int r; + + if (!busy_bo || !ticket) + return -EBUSY; + + if (ctx->interruptible) + r = dma_resv_lock_interruptible(busy_bo->base.resv, + ticket); + else + r = dma_resv_lock(busy_bo->base.resv, ticket); + + /* + * TODO: It would be better to keep the BO locked until allocation is at + * least tried one more time, but that would mean a much larger rework + * of TTM. + */ + if (!r) + dma_resv_unlock(busy_bo->base.resv); + + return r == -EDEADLK ? -EBUSY : r; +} + +int ttm_mem_evict_first(struct ttm_device *bdev, + struct ttm_resource_manager *man, + const struct ttm_place *place, + struct ttm_operation_ctx *ctx, + struct ww_acquire_ctx *ticket) +{ + struct ttm_buffer_object *bo = NULL, *busy_bo = NULL; + struct ttm_resource_cursor cursor; + struct ttm_resource *res; + bool locked = false; + int ret; + + spin_lock(&bdev->lru_lock); + ttm_resource_manager_for_each_res(man, &cursor, res) { + bool busy; + + if (!ttm_bo_evict_swapout_allowable(res->bo, ctx, place, + &locked, &busy)) { + if (busy && !busy_bo && ticket != + dma_resv_locking_ctx(res->bo->base.resv)) + busy_bo = res->bo; + continue; + } + + if (ttm_bo_get_unless_zero(res->bo)) { + bo = res->bo; + break; + } + if (locked) + dma_resv_unlock(res->bo->base.resv); + } + + if (!bo) { + if (busy_bo && !ttm_bo_get_unless_zero(busy_bo)) + busy_bo = NULL; + spin_unlock(&bdev->lru_lock); + ret = ttm_mem_evict_wait_busy(busy_bo, ctx, ticket); + if (busy_bo) + ttm_bo_put(busy_bo); + return ret; + } + + if (bo->deleted) { + ret = ttm_bo_cleanup_refs(bo, ctx->interruptible, + ctx->no_wait_gpu, locked); + ttm_bo_put(bo); + return ret; + } + + spin_unlock(&bdev->lru_lock); + + ret = ttm_bo_evict(bo, ctx); + if (locked) + ttm_bo_unreserve(bo); + else + ttm_bo_move_to_lru_tail_unlocked(bo); + + ttm_bo_put(bo); + return ret; +} + +/** + * ttm_bo_pin - Pin the buffer object. + * @bo: The buffer object to pin + * + * Make sure the buffer is not evicted any more during memory pressure. + * @bo must be unpinned again by calling ttm_bo_unpin(). + */ +void ttm_bo_pin(struct ttm_buffer_object *bo) +{ + dma_resv_assert_held(bo->base.resv); + WARN_ON_ONCE(!kref_read(&bo->kref)); + spin_lock(&bo->bdev->lru_lock); + if (bo->resource) + ttm_resource_del_bulk_move(bo->resource, bo); + ++bo->pin_count; + spin_unlock(&bo->bdev->lru_lock); +} +EXPORT_SYMBOL(ttm_bo_pin); + +/** + * ttm_bo_unpin - Unpin the buffer object. + * @bo: The buffer object to unpin + * + * Allows the buffer object to be evicted again during memory pressure. + */ +void ttm_bo_unpin(struct ttm_buffer_object *bo) +{ + dma_resv_assert_held(bo->base.resv); + WARN_ON_ONCE(!kref_read(&bo->kref)); + if (WARN_ON_ONCE(!bo->pin_count)) + return; + + spin_lock(&bo->bdev->lru_lock); + --bo->pin_count; + if (bo->resource) + ttm_resource_add_bulk_move(bo->resource, bo); + spin_unlock(&bo->bdev->lru_lock); +} +EXPORT_SYMBOL(ttm_bo_unpin); + +/* + * Add the last move fence to the BO as kernel dependency and reserve a new + * fence slot. + */ +static int ttm_bo_add_move_fence(struct ttm_buffer_object *bo, + struct ttm_resource_manager *man, + struct ttm_resource *mem, + bool no_wait_gpu) +{ + struct dma_fence *fence; + int ret; + + spin_lock(&man->move_lock); + fence = dma_fence_get(man->move); + spin_unlock(&man->move_lock); + + if (!fence) + return 0; + + if (no_wait_gpu) { + ret = dma_fence_is_signaled(fence) ? 0 : -EBUSY; + dma_fence_put(fence); + return ret; + } + + dma_resv_add_fence(bo->base.resv, fence, DMA_RESV_USAGE_KERNEL); + + ret = dma_resv_reserve_fences(bo->base.resv, 1); + dma_fence_put(fence); + return ret; +} + +/* + * Repeatedly evict memory from the LRU for @mem_type until we create enough + * space, or we've evicted everything and there isn't enough space. + */ +static int ttm_bo_mem_force_space(struct ttm_buffer_object *bo, + const struct ttm_place *place, + struct ttm_resource **mem, + struct ttm_operation_ctx *ctx) +{ + struct ttm_device *bdev = bo->bdev; + struct ttm_resource_manager *man; + struct ww_acquire_ctx *ticket; + int ret; + + man = ttm_manager_type(bdev, place->mem_type); + ticket = dma_resv_locking_ctx(bo->base.resv); + do { + ret = ttm_resource_alloc(bo, place, mem); + if (likely(!ret)) + break; + if (unlikely(ret != -ENOSPC)) + return ret; + ret = ttm_mem_evict_first(bdev, man, place, ctx, + ticket); + if (unlikely(ret != 0)) + return ret; + } while (1); + + return ttm_bo_add_move_fence(bo, man, *mem, ctx->no_wait_gpu); +} + +/* + * Creates space for memory region @mem according to its type. + * + * This function first searches for free space in compatible memory types in + * the priority order defined by the driver. If free space isn't found, then + * ttm_bo_mem_force_space is attempted in priority order to evict and find + * space. + */ +int ttm_bo_mem_space(struct ttm_buffer_object *bo, + struct ttm_placement *placement, + struct ttm_resource **mem, + struct ttm_operation_ctx *ctx) +{ + struct ttm_device *bdev = bo->bdev; + bool type_found = false; + int i, ret; + + ret = dma_resv_reserve_fences(bo->base.resv, 1); + if (unlikely(ret)) + return ret; + + for (i = 0; i < placement->num_placement; ++i) { + const struct ttm_place *place = &placement->placement[i]; + struct ttm_resource_manager *man; + + man = ttm_manager_type(bdev, place->mem_type); + if (!man || !ttm_resource_manager_used(man)) + continue; + + type_found = true; + ret = ttm_resource_alloc(bo, place, mem); + if (ret == -ENOSPC) + continue; + if (unlikely(ret)) + goto error; + + ret = ttm_bo_add_move_fence(bo, man, *mem, ctx->no_wait_gpu); + if (unlikely(ret)) { + ttm_resource_free(bo, mem); + if (ret == -EBUSY) + continue; + + goto error; + } + return 0; + } + + for (i = 0; i < placement->num_busy_placement; ++i) { + const struct ttm_place *place = &placement->busy_placement[i]; + struct ttm_resource_manager *man; + + man = ttm_manager_type(bdev, place->mem_type); + if (!man || !ttm_resource_manager_used(man)) + continue; + + type_found = true; + ret = ttm_bo_mem_force_space(bo, place, mem, ctx); + if (likely(!ret)) + return 0; + + if (ret && ret != -EBUSY) + goto error; + } + + ret = -ENOMEM; + if (!type_found) { + pr_err(TTM_PFX "No compatible memory type found\n"); + ret = -EINVAL; + } + +error: + return ret; +} +EXPORT_SYMBOL(ttm_bo_mem_space); + +static int ttm_bo_move_buffer(struct ttm_buffer_object *bo, + struct ttm_placement *placement, + struct ttm_operation_ctx *ctx) +{ + struct ttm_resource *mem; + struct ttm_place hop; + int ret; + + dma_resv_assert_held(bo->base.resv); + + /* + * Determine where to move the buffer. + * + * If driver determines move is going to need + * an extra step then it will return -EMULTIHOP + * and the buffer will be moved to the temporary + * stop and the driver will be called to make + * the second hop. + */ + ret = ttm_bo_mem_space(bo, placement, &mem, ctx); + if (ret) + return ret; +bounce: + ret = ttm_bo_handle_move_mem(bo, mem, false, ctx, &hop); + if (ret == -EMULTIHOP) { + ret = ttm_bo_bounce_temp_buffer(bo, &mem, ctx, &hop); + if (ret) + goto out; + /* try and move to final place now. */ + goto bounce; + } +out: + if (ret) + ttm_resource_free(bo, &mem); + return ret; +} + +int ttm_bo_validate(struct ttm_buffer_object *bo, + struct ttm_placement *placement, + struct ttm_operation_ctx *ctx) +{ + int ret; + + dma_resv_assert_held(bo->base.resv); + + /* + * Remove the backing store if no placement is given. + */ + if (!placement->num_placement && !placement->num_busy_placement) + return ttm_bo_pipeline_gutting(bo); + + /* + * Check whether we need to move buffer. + */ + if (!bo->resource || !ttm_resource_compat(bo->resource, placement)) { + ret = ttm_bo_move_buffer(bo, placement, ctx); + if (ret) + return ret; + } + /* + * We might need to add a TTM. + */ + if (!bo->resource || bo->resource->mem_type == TTM_PL_SYSTEM) { + ret = ttm_tt_create(bo, true); + if (ret) + return ret; + } + return 0; +} +EXPORT_SYMBOL(ttm_bo_validate); + +/** + * ttm_bo_init_reserved + * + * @bdev: Pointer to a ttm_device struct. + * @bo: Pointer to a ttm_buffer_object to be initialized. + * @type: Requested type of buffer object. + * @placement: Initial placement for buffer object. + * @alignment: Data alignment in pages. + * @ctx: TTM operation context for memory allocation. + * @sg: Scatter-gather table. + * @resv: Pointer to a dma_resv, or NULL to let ttm allocate one. + * @destroy: Destroy function. Use NULL for kfree(). + * + * This function initializes a pre-allocated struct ttm_buffer_object. + * As this object may be part of a larger structure, this function, + * together with the @destroy function, enables driver-specific objects + * derived from a ttm_buffer_object. + * + * On successful return, the caller owns an object kref to @bo. The kref and + * list_kref are usually set to 1, but note that in some situations, other + * tasks may already be holding references to @bo as well. + * Furthermore, if resv == NULL, the buffer's reservation lock will be held, + * and it is the caller's responsibility to call ttm_bo_unreserve. + * + * If a failure occurs, the function will call the @destroy function. Thus, + * after a failure, dereferencing @bo is illegal and will likely cause memory + * corruption. + * + * Returns + * -ENOMEM: Out of memory. + * -EINVAL: Invalid placement flags. + * -ERESTARTSYS: Interrupted by signal while sleeping waiting for resources. + */ +int ttm_bo_init_reserved(struct ttm_device *bdev, struct ttm_buffer_object *bo, + enum ttm_bo_type type, struct ttm_placement *placement, + uint32_t alignment, struct ttm_operation_ctx *ctx, + struct sg_table *sg, struct dma_resv *resv, + void (*destroy) (struct ttm_buffer_object *)) +{ + static const struct ttm_place sys_mem = { .mem_type = TTM_PL_SYSTEM }; + int ret; + + kref_init(&bo->kref); + INIT_LIST_HEAD(&bo->ddestroy); + bo->bdev = bdev; + bo->type = type; + bo->page_alignment = alignment; + bo->destroy = destroy; + bo->pin_count = 0; + bo->sg = sg; + bo->bulk_move = NULL; + if (resv) + bo->base.resv = resv; + else + bo->base.resv = &bo->base._resv; + atomic_inc(&ttm_glob.bo_count); + + ret = ttm_resource_alloc(bo, &sys_mem, &bo->resource); + if (unlikely(ret)) { + ttm_bo_put(bo); + return ret; + } + + /* + * For ttm_bo_type_device buffers, allocate + * address space from the device. + */ + if (bo->type == ttm_bo_type_device || bo->type == ttm_bo_type_sg) { + ret = drm_vma_offset_add(bdev->vma_manager, &bo->base.vma_node, + PFN_UP(bo->base.size)); + if (ret) + goto err_put; + } + + /* passed reservation objects should already be locked, + * since otherwise lockdep will be angered in radeon. + */ + if (!resv) + WARN_ON(!dma_resv_trylock(bo->base.resv)); + else + dma_resv_assert_held(resv); + + ret = ttm_bo_validate(bo, placement, ctx); + if (unlikely(ret)) + goto err_unlock; + + return 0; + +err_unlock: + if (!resv) + dma_resv_unlock(bo->base.resv); + +err_put: + ttm_bo_put(bo); + return ret; +} +EXPORT_SYMBOL(ttm_bo_init_reserved); + +/** + * ttm_bo_init_validate + * + * @bdev: Pointer to a ttm_device struct. + * @bo: Pointer to a ttm_buffer_object to be initialized. + * @type: Requested type of buffer object. + * @placement: Initial placement for buffer object. + * @alignment: Data alignment in pages. + * @interruptible: If needing to sleep to wait for GPU resources, + * sleep interruptible. + * pinned in physical memory. If this behaviour is not desired, this member + * holds a pointer to a persistent shmem object. Typically, this would + * point to the shmem object backing a GEM object if TTM is used to back a + * GEM user interface. + * @sg: Scatter-gather table. + * @resv: Pointer to a dma_resv, or NULL to let ttm allocate one. + * @destroy: Destroy function. Use NULL for kfree(). + * + * This function initializes a pre-allocated struct ttm_buffer_object. + * As this object may be part of a larger structure, this function, + * together with the @destroy function, + * enables driver-specific objects derived from a ttm_buffer_object. + * + * On successful return, the caller owns an object kref to @bo. The kref and + * list_kref are usually set to 1, but note that in some situations, other + * tasks may already be holding references to @bo as well. + * + * If a failure occurs, the function will call the @destroy function, Thus, + * after a failure, dereferencing @bo is illegal and will likely cause memory + * corruption. + * + * Returns + * -ENOMEM: Out of memory. + * -EINVAL: Invalid placement flags. + * -ERESTARTSYS: Interrupted by signal while sleeping waiting for resources. + */ +int ttm_bo_init_validate(struct ttm_device *bdev, struct ttm_buffer_object *bo, + enum ttm_bo_type type, struct ttm_placement *placement, + uint32_t alignment, bool interruptible, + struct sg_table *sg, struct dma_resv *resv, + void (*destroy) (struct ttm_buffer_object *)) +{ + struct ttm_operation_ctx ctx = { interruptible, false }; + int ret; + + ret = ttm_bo_init_reserved(bdev, bo, type, placement, alignment, &ctx, + sg, resv, destroy); + if (ret) + return ret; + + if (!resv) + ttm_bo_unreserve(bo); + + return 0; +} +EXPORT_SYMBOL(ttm_bo_init_validate); + +/* + * buffer object vm functions. + */ + +void ttm_bo_unmap_virtual(struct ttm_buffer_object *bo) +{ + struct ttm_device *bdev = bo->bdev; + + drm_vma_node_unmap(&bo->base.vma_node, bdev->dev_mapping); + ttm_mem_io_free(bdev, bo->resource); +} +EXPORT_SYMBOL(ttm_bo_unmap_virtual); + +int ttm_bo_wait(struct ttm_buffer_object *bo, + bool interruptible, bool no_wait) +{ + long timeout = 15 * HZ; + + if (no_wait) { + if (dma_resv_test_signaled(bo->base.resv, DMA_RESV_USAGE_BOOKKEEP)) + return 0; + else + return -EBUSY; + } + + timeout = dma_resv_wait_timeout(bo->base.resv, DMA_RESV_USAGE_BOOKKEEP, + interruptible, timeout); + if (timeout < 0) + return timeout; + + if (timeout == 0) + return -EBUSY; + + return 0; +} +EXPORT_SYMBOL(ttm_bo_wait); + +int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, + gfp_t gfp_flags) +{ + struct ttm_place place; + bool locked; + int ret; + + /* + * While the bo may already reside in SYSTEM placement, set + * SYSTEM as new placement to cover also the move further below. + * The driver may use the fact that we're moving from SYSTEM + * as an indication that we're about to swap out. + */ + memset(&place, 0, sizeof(place)); + place.mem_type = bo->resource->mem_type; + if (!ttm_bo_evict_swapout_allowable(bo, ctx, &place, &locked, NULL)) + return -EBUSY; + + if (!bo->ttm || !ttm_tt_is_populated(bo->ttm) || + bo->ttm->page_flags & TTM_TT_FLAG_EXTERNAL || + bo->ttm->page_flags & TTM_TT_FLAG_SWAPPED || + !ttm_bo_get_unless_zero(bo)) { + if (locked) + dma_resv_unlock(bo->base.resv); + return -EBUSY; + } + + if (bo->deleted) { + ret = ttm_bo_cleanup_refs(bo, false, false, locked); + ttm_bo_put(bo); + return ret == -EBUSY ? -ENOSPC : ret; + } + + /* TODO: Cleanup the locking */ + spin_unlock(&bo->bdev->lru_lock); + + /* + * Move to system cached + */ + if (bo->resource->mem_type != TTM_PL_SYSTEM) { + struct ttm_operation_ctx ctx = { false, false }; + struct ttm_resource *evict_mem; + struct ttm_place hop; + + memset(&hop, 0, sizeof(hop)); + place.mem_type = TTM_PL_SYSTEM; + ret = ttm_resource_alloc(bo, &place, &evict_mem); + if (unlikely(ret)) + goto out; + + ret = ttm_bo_handle_move_mem(bo, evict_mem, true, &ctx, &hop); + if (unlikely(ret != 0)) { + WARN(ret == -EMULTIHOP, "Unexpected multihop in swaput - likely driver bug.\n"); + goto out; + } + } + + /* + * Make sure BO is idle. + */ + ret = ttm_bo_wait(bo, false, false); + if (unlikely(ret != 0)) + goto out; + + ttm_bo_unmap_virtual(bo); + + /* + * Swap out. Buffer will be swapped in again as soon as + * anyone tries to access a ttm page. + */ + if (bo->bdev->funcs->swap_notify) + bo->bdev->funcs->swap_notify(bo); + + if (ttm_tt_is_populated(bo->ttm)) + ret = ttm_tt_swapout(bo->bdev, bo->ttm, gfp_flags); +out: + + /* + * Unreserve without putting on LRU to avoid swapping out an + * already swapped buffer. + */ + if (locked) + dma_resv_unlock(bo->base.resv); + ttm_bo_put(bo); + return ret == -EBUSY ? -ENOSPC : ret; +} + +void ttm_bo_tt_destroy(struct ttm_buffer_object *bo) +{ + if (bo->ttm == NULL) + return; + + ttm_tt_unpopulate(bo->bdev, bo->ttm); + ttm_tt_destroy(bo->bdev, bo->ttm); + bo->ttm = NULL; +} -- cgit v1.2.3